From 2e5aa86609ec1cf37bcc204fd7ba6c24c2f49fec Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Tue, 23 Jul 2013 17:38:38 -0400
Subject: lsm: split the xfrm_state_alloc_security() hook implementation

The xfrm_state_alloc_security() LSM hook implementation is really a
multiplexed hook with two different behaviors depending on the
arguments passed to it by the caller.  This patch splits the LSM hook
implementation into two new hook implementations, which match the
LSM hooks in the rest of the kernel:

 * xfrm_state_alloc
 * xfrm_state_alloc_acquire

Also included in this patch are the necessary changes to the SELinux
code; no other LSMs are affected.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/security.h | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 4686491852a7..e5a5e8a41e55 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1039,17 +1039,25 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  * @xfrm_policy_delete_security:
  *	@ctx contains the xfrm_sec_ctx.
  *	Authorize deletion of xp->security.
- * @xfrm_state_alloc_security:
+ * @xfrm_state_alloc:
  *	@x contains the xfrm_state being added to the Security Association
  *	Database by the XFRM system.
  *	@sec_ctx contains the security context information being provided by
  *	the user-level SA generation program (e.g., setkey or racoon).
- *	@secid contains the secid from which to take the mls portion of the context.
  *	Allocate a security structure to the x->security field; the security
  *	field is initialized to NULL when the xfrm_state is allocated. Set the
- *	context to correspond to either sec_ctx or polsec, with the mls portion
- *	taken from secid in the latter case.
- *	Return 0 if operation was successful (memory to allocate, legal context).
+ *	context to correspond to sec_ctx. Return 0 if operation was successful
+ *	(memory to allocate, legal context).
+ * @xfrm_state_alloc_acquire:
+ *	@x contains the xfrm_state being added to the Security Association
+ *	Database by the XFRM system.
+ *	@polsec contains the policy's security context.
+ *	@secid contains the secid from which to take the mls portion of the
+ *	context.
+ *	Allocate a security structure to the x->security field; the security
+ *	field is initialized to NULL when the xfrm_state is allocated. Set the
+ *	context to correspond to secid. Return 0 if operation was successful
+ *	(memory to allocate, legal context).
  * @xfrm_state_free_security:
  *	@x contains the xfrm_state.
  *	Deallocate x->security.
@@ -1651,9 +1659,11 @@ struct security_operations {
 	int (*xfrm_policy_clone_security) (struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctx);
 	void (*xfrm_policy_free_security) (struct xfrm_sec_ctx *ctx);
 	int (*xfrm_policy_delete_security) (struct xfrm_sec_ctx *ctx);
-	int (*xfrm_state_alloc_security) (struct xfrm_state *x,
-		struct xfrm_user_sec_ctx *sec_ctx,
-		u32 secid);
+	int (*xfrm_state_alloc) (struct xfrm_state *x,
+				 struct xfrm_user_sec_ctx *sec_ctx);
+	int (*xfrm_state_alloc_acquire) (struct xfrm_state *x,
+					 struct xfrm_sec_ctx *polsec,
+					 u32 secid);
 	void (*xfrm_state_free_security) (struct xfrm_state *x);
 	int (*xfrm_state_delete_security) (struct xfrm_state *x);
 	int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir);
-- 
cgit 


From 1a6b69b6548cd0dd82549393f30dd982ceeb79d2 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Thu, 12 Apr 2012 01:40:31 -0400
Subject: ARM: gic: add CPU migration support

This is required by the big.LITTLE switcher code.

The gic_migrate_target() changes the CPU interface mapping for the
current CPU to redirect SGIs to the specified interface, and it also
updates the target CPU for each interrupts to that CPU interface
if they were targeting the current interface.  Finally, pending
SGIs for the current CPU are forwarded to the new interface.

Because Linux does not use it, the SGI source information for the
forwarded SGIs is not preserved.  Neither is the source information
for the SGIs sent by the current CPU to other CPUs adjusted to match
the new CPU interface mapping.  The required registers are banked so
only the target CPU could do it.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 drivers/irqchip/irq-gic.c       | 87 +++++++++++++++++++++++++++++++++++++++--
 include/linux/irqchip/arm-gic.h |  4 ++
 2 files changed, 88 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index ee7c50312066..268874ac75e6 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -253,10 +253,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
+	raw_spin_lock(&irq_controller_lock);
 	mask = 0xff << shift;
 	bit = gic_cpu_map[cpu] << shift;
-
-	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	raw_spin_unlock(&irq_controller_lock);
@@ -646,7 +645,9 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
-	unsigned long map = 0;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 
 	/* Convert our logical CPU mask into a physical one. */
 	for_each_cpu(cpu, mask)
@@ -660,6 +661,86 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
+#endif
+
+#ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_migrate_target - migrate IRQs to another CPU interface
+ *
+ * @new_cpu_id: the CPU target ID to migrate IRQs to
+ *
+ * Migrate all peripheral interrupts with a target matching the current CPU
+ * to the interface corresponding to @new_cpu_id.  The CPU interface mapping
+ * is also updated.  Targets to other CPU interfaces are unchanged.
+ * This must be called with IRQs locally disabled.
+ */
+void gic_migrate_target(unsigned int new_cpu_id)
+{
+	unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
+	void __iomem *dist_base;
+	int i, ror_val, cpu = smp_processor_id();
+	u32 val, cur_target_mask, active_mask;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	if (!dist_base)
+		return;
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+
+	cur_cpu_id = __ffs(gic_cpu_map[cpu]);
+	cur_target_mask = 0x01010101 << cur_cpu_id;
+	ror_val = (cur_cpu_id - new_cpu_id) & 31;
+
+	raw_spin_lock(&irq_controller_lock);
+
+	/* Update the target interface for this logical CPU */
+	gic_cpu_map[cpu] = 1 << new_cpu_id;
+
+	/*
+	 * Find all the peripheral interrupts targetting the current
+	 * CPU interface and migrate them to the new CPU interface.
+	 * We skip DIST_TARGET 0 to 7 as they are read-only.
+	 */
+	for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
+		val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+		active_mask = val & cur_target_mask;
+		if (active_mask) {
+			val &= ~active_mask;
+			val |= ror32(active_mask, ror_val);
+			writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
+		}
+	}
+
+	raw_spin_unlock(&irq_controller_lock);
+
+	/*
+	 * Now let's migrate and clear any potential SGIs that might be
+	 * pending for us (cur_cpu_id).  Since GIC_DIST_SGI_PENDING_SET
+	 * is a banked register, we can only forward the SGI using
+	 * GIC_DIST_SOFTINT.  The original SGI source is lost but Linux
+	 * doesn't use that information anyway.
+	 *
+	 * For the same reason we do not adjust SGI source information
+	 * for previously sent SGIs by us to other CPUs either.
+	 */
+	for (i = 0; i < 16; i += 4) {
+		int j;
+		val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
+		if (!val)
+			continue;
+		writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
+		for (j = i; j < i + 4; j++) {
+			if (val & 0xff)
+				writel_relaxed((1 << (new_cpu_id + 16)) | j,
+						dist_base + GIC_DIST_SOFTINT);
+			val >>= 8;
+		}
+	}
 }
 #endif
 
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 3e203eb23cc7..40bfcac95940 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -31,6 +31,8 @@
 #define GIC_DIST_TARGET			0x800
 #define GIC_DIST_CONFIG			0xc00
 #define GIC_DIST_SOFTINT		0xf00
+#define GIC_DIST_SGI_PENDING_CLEAR	0xf10
+#define GIC_DIST_SGI_PENDING_SET	0xf20
 
 #define GICH_HCR			0x0
 #define GICH_VTR			0x4
@@ -73,6 +75,8 @@ static inline void gic_init(unsigned int nr, int start,
 	gic_init_bases(nr, start, dist, cpu, 0, NULL);
 }
 
+void gic_migrate_target(unsigned int new_cpu_id);
+
 #endif /* __ASSEMBLY */
 
 #endif
-- 
cgit 


From ed96762e3241f57aa812977cf1920d3ee0363f4d Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Thu, 5 Jul 2012 21:33:26 -0400
Subject: ARM: bL_switcher: do not hardcode GIC IDs in the code

Currently, GIC IDs are hardcoded making the code dependent on the 4+4 b.L
configuration.  Let's allow for GIC IDs to be discovered upon switcher
initialization to support other b.L configurations such as the 1+1 one,
or 2+3 as on the VExpress TC2.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 arch/arm/common/bL_switcher.c   | 14 +++++++++++++-
 drivers/irqchip/irq-gic.c       | 21 +++++++++++++++++++++
 include/linux/irqchip/arm-gic.h |  1 +
 3 files changed, 35 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 50e95d894e35..1c2e5bcfb1f7 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -110,6 +110,8 @@ static int bL_switchpoint(unsigned long _arg)
  * Generic switcher interface
  */
 
+static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS];
+
 /*
  * bL_switch_to - Switch to a specific cluster for the current CPU
  * @new_cluster_id: the ID of the cluster to switch to.
@@ -159,7 +161,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 	this_cpu = smp_processor_id();
 
 	/* redirect GIC's SGIs to our counterpart */
-	gic_migrate_target(cpuid + ib_cluster*4);
+	gic_migrate_target(bL_gic_id[cpuid][ib_cluster]);
 
 	/*
 	 * Raise a SGI on the inbound CPU to make sure it doesn't stall
@@ -332,6 +334,16 @@ static int __init bL_switcher_halve_cpus(void)
 		cluster = (cpu_logical_map(i) >> 8) & 0xff;
 
 		if (cpumask_test_cpu(cpu, &common_mask)) {
+			/* Let's take note of the GIC ID for this CPU */
+			int gic_id = gic_get_cpu_id(i);
+			if (gic_id < 0) {
+				pr_err("%s: bad GIC ID for CPU %d\n", __func__, i);
+				return -EINVAL;
+			}
+			bL_gic_id[cpu][cluster] = gic_id;
+			pr_info("GIC ID for CPU %u cluster %u is %u\n",
+				cpu, cluster, gic_id);
+
 			/*
 			 * We keep only those logical CPUs which number
 			 * is equal to their physical CPU number. This is
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 268874ac75e6..3862cb54c714 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -667,6 +667,27 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 #endif
 
 #ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_get_cpu_id - get the CPU interface ID for the specified CPU
+ *
+ * @cpu: the logical CPU number to get the GIC ID for.
+ *
+ * Return the CPU interface ID for the given logical CPU number,
+ * or -1 if the CPU number is too large or the interface ID is
+ * unknown (more than one bit set).
+ */
+int gic_get_cpu_id(unsigned int cpu)
+{
+	unsigned int cpu_bit;
+
+	if (cpu >= NR_GIC_CPU_IF)
+		return -1;
+	cpu_bit = gic_cpu_map[cpu];
+	if (cpu_bit & (cpu_bit - 1))
+		return -1;
+	return __ffs(cpu_bit);
+}
+
 /*
  * gic_migrate_target - migrate IRQs to another CPU interface
  *
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 40bfcac95940..2d7d47e8dfaf 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -75,6 +75,7 @@ static inline void gic_init(unsigned int nr, int start,
 	gic_init_bases(nr, start, dist, cpu, 0, NULL);
 }
 
+int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
 
 #endif /* __ASSEMBLY */
-- 
cgit 


From 87d8b9eb7eb6669aad6435a51e9862362141ba76 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Thu, 18 Jul 2013 16:21:14 -0700
Subject: clocksource: Extract max nsec calculation into separate function

We need to calculate the same number in the clocksource code and
the sched_clock code, so extract this code into its own function.
We also drop the min_t and just use min() because the two types
are the same.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/clocksource.h |  2 ++
 kernel/time/clocksource.c   | 45 ++++++++++++++++++++++++++++++---------------
 2 files changed, 32 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index dbbf8aa7731b..67301a405712 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -292,6 +292,8 @@ extern void clocksource_resume(void);
 extern struct clocksource * __init __weak clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
 
+extern u64
+clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask);
 extern void
 clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec);
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 50a8736757f3..637a14af6c21 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -537,40 +537,55 @@ static u32 clocksource_max_adjustment(struct clocksource *cs)
 }
 
 /**
- * clocksource_max_deferment - Returns max time the clocksource can be deferred
- * @cs:         Pointer to clocksource
- *
+ * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted
+ * @mult:	cycle to nanosecond multiplier
+ * @shift:	cycle to nanosecond divisor (power of two)
+ * @maxadj:	maximum adjustment value to mult (~11%)
+ * @mask:	bitmask for two's complement subtraction of non 64 bit counters
  */
-static u64 clocksource_max_deferment(struct clocksource *cs)
+u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask)
 {
 	u64 max_nsecs, max_cycles;
 
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * maximum number of cycles is equal to ULLONG_MAX/(mult+maxadj)
 	 * which is equivalent to the below.
-	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
-	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
-	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
-	 * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < (2^63)/(mult + maxadj)
+	 * max_cycles < 2^(log2((2^63)/(mult + maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(mult + maxadj))
+	 * max_cycles < 2^(63 - log2(mult + maxadj))
+	 * max_cycles < 1 << (63 - log2(mult + maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(mult + maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
-	 * determined by the minimum of max_cycles and cs->mask.
+	 * determined by the minimum of max_cycles and mask.
 	 * Note: Here we subtract the maxadj to make sure we don't sleep for
 	 * too long if there's a large negative adjustment.
 	 */
-	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
-					cs->shift);
+	max_cycles = min(max_cycles, mask);
+	max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift);
+
+	return max_nsecs;
+}
+
+/**
+ * clocksource_max_deferment - Returns max time the clocksource can be deferred
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u64 clocksource_max_deferment(struct clocksource *cs)
+{
+	u64 max_nsecs;
 
+	max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj,
+					  cs->mask);
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
 	 * limit the time the clocksource can be deferred by 12.5%. Please
-- 
cgit 


From e7e3ff1bfe9c42ee31172e9afdc0383a9e595e29 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Thu, 18 Jul 2013 16:21:17 -0700
Subject: sched_clock: Add support for >32 bit sched_clock

The ARM architected system counter has at least 56 usable bits.
Add support for counters with more than 32 bits to the generic
sched_clock implementation so we can increase the time between
wakeups due to dealing with wrap-around on these devices while
benefiting from the irqtime accounting and suspend/resume
handling that the generic sched_clock code already has. On my
system using 56 bits over 32 bits changes the wraparound time
from a few minutes to an hour. For faster running counters (GHz
range) this is even more important because we may not be able to
execute the timer in time to deal with the wraparound if only 32
bits are used.

We choose a maxsec value of 3600 seconds because we assume no
system will go idle for more than an hour. In the future we may
need to increase this value.

Note: All users should switch over to the 64-bit read function so
we can remove setup_sched_clock() in favor of sched_clock_register().

Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/sched_clock.h |  2 ++
 kernel/time/sched_clock.c   | 46 +++++++++++++++++++++++++++++++--------------
 2 files changed, 34 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index fa7922c80a41..eca7abeb86fc 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -15,6 +15,8 @@ static inline void sched_clock_postinit(void) { }
 #endif
 
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+extern void sched_clock_register(u64 (*read)(void), int bits,
+				 unsigned long rate);
 
 extern unsigned long long (*sched_clock_func)(void);
 
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index c018ffc59937..f388baeaf2b6 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -16,11 +16,12 @@
 #include <linux/hrtimer.h>
 #include <linux/sched_clock.h>
 #include <linux/seqlock.h>
+#include <linux/bitops.h>
 
 struct clock_data {
 	ktime_t wrap_kt;
 	u64 epoch_ns;
-	u32 epoch_cyc;
+	u64 epoch_cyc;
 	seqcount_t seq;
 	unsigned long rate;
 	u32 mult;
@@ -37,14 +38,25 @@ static struct clock_data cd = {
 	.mult	= NSEC_PER_SEC / HZ,
 };
 
-static u32 __read_mostly sched_clock_mask = 0xffffffff;
+static u64 __read_mostly sched_clock_mask;
 
-static u32 notrace jiffy_sched_clock_read(void)
+static u64 notrace jiffy_sched_clock_read(void)
 {
-	return (u32)(jiffies - INITIAL_JIFFIES);
+	/*
+	 * We don't need to use get_jiffies_64 on 32-bit arches here
+	 * because we register with BITS_PER_LONG
+	 */
+	return (u64)(jiffies - INITIAL_JIFFIES);
+}
+
+static u32 __read_mostly (*read_sched_clock_32)(void);
+
+static u64 notrace read_sched_clock_32_wrapper(void)
+{
+	return read_sched_clock_32();
 }
 
-static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
+static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
 static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
@@ -54,8 +66,8 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 static unsigned long long notrace sched_clock_32(void)
 {
 	u64 epoch_ns;
-	u32 epoch_cyc;
-	u32 cyc;
+	u64 epoch_cyc;
+	u64 cyc;
 	unsigned long seq;
 
 	if (cd.suspended)
@@ -78,7 +90,7 @@ static unsigned long long notrace sched_clock_32(void)
 static void notrace update_sched_clock(void)
 {
 	unsigned long flags;
-	u32 cyc;
+	u64 cyc;
 	u64 ns;
 
 	cyc = read_sched_clock();
@@ -101,7 +113,8 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
 	return HRTIMER_RESTART;
 }
 
-void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
+void __init sched_clock_register(u64 (*read)(void), int bits,
+				 unsigned long rate)
 {
 	unsigned long r;
 	u64 res, wrap;
@@ -110,14 +123,13 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	if (cd.rate > rate)
 		return;
 
-	BUG_ON(bits > 32);
 	WARN_ON(!irqs_disabled());
 	read_sched_clock = read;
-	sched_clock_mask = (1 << bits) - 1;
+	sched_clock_mask = CLOCKSOURCE_MASK(bits);
 	cd.rate = rate;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
-	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0);
+	clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
 
 	r = rate;
 	if (r >= 4000000) {
@@ -130,7 +142,7 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 		r_unit = ' ';
 
 	/* calculate how many ns until we wrap */
-	wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift);
+	wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
 	cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
 
 	/* calculate the ns resolution of this counter */
@@ -152,6 +164,12 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
+void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
+{
+	read_sched_clock_32 = read;
+	sched_clock_register(read_sched_clock_32_wrapper, bits, rate);
+}
+
 unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
 
 unsigned long long notrace sched_clock(void)
@@ -166,7 +184,7 @@ void __init sched_clock_postinit(void)
 	 * make it the final one one.
 	 */
 	if (read_sched_clock == jiffy_sched_clock_read)
-		setup_sched_clock(jiffy_sched_clock_read, 32, HZ);
+		sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
 
 	update_sched_clock();
 
-- 
cgit 


From aba8269588301f7778bea811d6f7ec74c2e37279 Mon Sep 17 00:00:00 2001
From: Fan Du <fan.du@windriver.com>
Date: Wed, 28 Aug 2013 15:09:40 +0800
Subject: {ipv4,xfrm}: Introduce xfrm_tunnel_notifier for xfrm tunnel mode
 callback

Some thoughts on IPv4 VTI implementation:

The connection between VTI receiving part and xfrm tunnel mode input process
is hardly a "xfrm_tunnel", xfrm_tunnel is used in places where, e.g ipip/sit
and xfrm4_tunnel, acts like a true "tunnel" device.

In addition, IMHO, VTI doesn't need vti_err to do something meaningful, as all
VTI needs is just a notifier to be called whenever xfrm_input ingress a packet
to update statistics.

A IPsec protected packet is first handled by protocol handlers, e.g AH/ESP,
to check packet authentication or encryption rightness. PMTU update is taken
care of in this stage by protocol error handler.

Then the packet is rearranged properly depending on whether it's transport
mode or tunnel mode packed by mode "input" handler. The VTI handler code
takes effects in this stage in tunnel mode only. So it neither need propagate
PMTU, as it has already been done if necessary, nor the VTI handler is
qualified as a xfrm_tunnel.

So this patch introduces xfrm_tunnel_notifier and meanwhile wipe out vti_err
code.

Signed-off-by: Fan Du <fan.du@windriver.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: Saurabh Mohan <saurabh.mohan@vyatta.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h           | 10 +++++--
 net/ipv4/ip_vti.c            | 67 +-------------------------------------------
 net/ipv4/xfrm4_mode_tunnel.c | 16 +++++------
 3 files changed, 17 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 89d3d8ae204e..c7afa6e476c8 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1352,6 +1352,12 @@ struct xfrm_tunnel {
 	int priority;
 };
 
+struct xfrm_tunnel_notifier {
+	int (*handler)(struct sk_buff *skb);
+	struct xfrm_tunnel_notifier __rcu *next;
+	int priority;
+};
+
 struct xfrm6_tunnel {
 	int (*handler)(struct sk_buff *skb);
 	int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
@@ -1495,8 +1501,8 @@ extern int xfrm4_output(struct sk_buff *skb);
 extern int xfrm4_output_finish(struct sk_buff *skb);
 extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
 extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
-extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler);
-extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler);
+extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
+extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
 extern int xfrm6_extract_header(struct sk_buff *skb);
 extern int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
 extern int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e805e7b3030e..91f69bc883fe 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -49,70 +49,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly;
 static int vti_net_id __read_mostly;
 static int vti_tunnel_init(struct net_device *dev);
 
-static int vti_err(struct sk_buff *skb, u32 info)
-{
-
-	/* All the routers (except for Linux) return only
-	 * 8 bytes of packet payload. It means, that precise relaying of
-	 * ICMP in the real Internet is absolutely infeasible.
-	 */
-	struct net *net = dev_net(skb->dev);
-	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
-	struct iphdr *iph = (struct iphdr *)skb->data;
-	const int type = icmp_hdr(skb)->type;
-	const int code = icmp_hdr(skb)->code;
-	struct ip_tunnel *t;
-	int err;
-
-	switch (type) {
-	default:
-	case ICMP_PARAMETERPROB:
-		return 0;
-
-	case ICMP_DEST_UNREACH:
-		switch (code) {
-		case ICMP_SR_FAILED:
-		case ICMP_PORT_UNREACH:
-			/* Impossible event. */
-			return 0;
-		default:
-			/* All others are translated to HOST_UNREACH. */
-			break;
-		}
-		break;
-	case ICMP_TIME_EXCEEDED:
-		if (code != ICMP_EXC_TTL)
-			return 0;
-		break;
-	}
-
-	err = -ENOENT;
-
-	t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
-			     iph->daddr, iph->saddr, 0);
-	if (t == NULL)
-		goto out;
-
-	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
-		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPIP, 0);
-		err = 0;
-		goto out;
-	}
-
-	err = 0;
-	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
-		goto out;
-
-	if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
-		t->err_count++;
-	else
-		t->err_count = 1;
-	t->err_time = jiffies;
-out:
-	return err;
-}
-
 /* We dont digest the packet therefore let the packet pass */
 static int vti_rcv(struct sk_buff *skb)
 {
@@ -296,9 +232,8 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev)
 	iph->ihl		= 5;
 }
 
-static struct xfrm_tunnel vti_handler __read_mostly = {
+static struct xfrm_tunnel_notifier vti_handler __read_mostly = {
 	.handler	=	vti_rcv,
-	.err_handler	=	vti_err,
 	.priority	=	1,
 };
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index eb1dd4d643f2..b82cde1ea1b6 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -16,13 +16,13 @@
 #include <net/xfrm.h>
 
 /* Informational hook. The decap is still done here. */
-static struct xfrm_tunnel __rcu *rcv_notify_handlers __read_mostly;
+static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
 static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex);
 
-int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
 {
-	struct xfrm_tunnel __rcu **pprev;
-	struct xfrm_tunnel *t;
+	struct xfrm_tunnel_notifier __rcu **pprev;
+	struct xfrm_tunnel_notifier *t;
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
@@ -50,10 +50,10 @@ err:
 }
 EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register);
 
-int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler)
+int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
 {
-	struct xfrm_tunnel __rcu **pprev;
-	struct xfrm_tunnel *t;
+	struct xfrm_tunnel_notifier __rcu **pprev;
+	struct xfrm_tunnel_notifier *t;
 	int ret = -ENOENT;
 
 	mutex_lock(&xfrm4_mode_tunnel_input_mutex);
@@ -134,7 +134,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct xfrm_tunnel *handler;
+	struct xfrm_tunnel_notifier *handler;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
-- 
cgit 


From 6898eb89655a8ac7d098b2fada95c1c91870365c Mon Sep 17 00:00:00 2001
From: Peter Meerwald <pmeerw@pmeerw.net>
Date: Wed, 21 Aug 2013 00:15:00 +0100
Subject: iio: Remove trailing ; from function definitions

Signed-off-by: Peter Meerwald <pmeerw@pmeerw.net>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/iio.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 2103cc32a5fb..8e7a8132b109 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -457,7 +457,7 @@ static inline void iio_device_put(struct iio_dev *indio_dev)
 {
 	if (indio_dev)
 		put_device(&indio_dev->dev);
-};
+}
 
 /**
  * dev_to_iio_dev() - Get IIO device struct from a device struct
@@ -593,7 +593,7 @@ static inline bool iio_buffer_enabled(struct iio_dev *indio_dev)
 {
 	return indio_dev->currentmode
 		& (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE);
-};
+}
 
 /**
  * iio_get_debugfs_dentry() - helper function to get the debugfs_dentry
@@ -603,12 +603,12 @@ static inline bool iio_buffer_enabled(struct iio_dev *indio_dev)
 static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
 {
 	return indio_dev->debugfs_dentry;
-};
+}
 #else
 static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
 {
 	return NULL;
-};
+}
 #endif
 
 int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer,
-- 
cgit 


From b89232732f642bfa24f9e252dd241ddfb40d3817 Mon Sep 17 00:00:00 2001
From: Shobhit Kumar <shobhit.kumar@intel.com>
Date: Tue, 27 Aug 2013 15:12:13 +0300
Subject: drm: add MIPI DSI encoder and connector types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shobhit Kumar <shobhit.kumar@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c  | 2 ++
 include/uapi/drm/drm_mode.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index bff2fa941f60..e79577cb4665 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -202,6 +202,7 @@ static struct drm_conn_prop_enum_list drm_connector_enum_list[] =
 	{ DRM_MODE_CONNECTOR_TV, "TV" },
 	{ DRM_MODE_CONNECTOR_eDP, "eDP" },
 	{ DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" },
+	{ DRM_MODE_CONNECTOR_DSI, "DSI" },
 };
 
 static const struct drm_prop_enum_list drm_encoder_enum_list[] =
@@ -211,6 +212,7 @@ static const struct drm_prop_enum_list drm_encoder_enum_list[] =
 	{ DRM_MODE_ENCODER_LVDS, "LVDS" },
 	{ DRM_MODE_ENCODER_TVDAC, "TV" },
 	{ DRM_MODE_ENCODER_VIRTUAL, "Virtual" },
+	{ DRM_MODE_ENCODER_DSI, "DSI" },
 };
 
 void drm_connector_ida_init(void)
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 550811712f78..113d32457fa4 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -165,6 +165,7 @@ struct drm_mode_get_plane_res {
 #define DRM_MODE_ENCODER_LVDS	3
 #define DRM_MODE_ENCODER_TVDAC	4
 #define DRM_MODE_ENCODER_VIRTUAL 5
+#define DRM_MODE_ENCODER_DSI	6
 
 struct drm_mode_get_encoder {
 	__u32 encoder_id;
@@ -203,6 +204,7 @@ struct drm_mode_get_encoder {
 #define DRM_MODE_CONNECTOR_TV		13
 #define DRM_MODE_CONNECTOR_eDP		14
 #define DRM_MODE_CONNECTOR_VIRTUAL      15
+#define DRM_MODE_CONNECTOR_DSI		16
 
 struct drm_mode_get_connector {
 
-- 
cgit 


From c1d454246c1339388ed0788f34f88ee12ad58ef3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 14 Aug 2013 15:31:52 +0000
Subject: libfc: Source code comment spelling fixes

Change 'initiaive' into 'initiative', 'remainig' into 'remaining'
and change 'exected' into 'expected'.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Robert Love <robert.w.love@intel.com>
---
 drivers/scsi/libfc/fc_exch.c  | 5 +----
 drivers/scsi/libfc/fc_lport.c | 2 +-
 drivers/scsi/libfc/fc_rport.c | 6 +++---
 include/scsi/fc/fc_fc2.h      | 2 +-
 4 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 587992952b3c..b233a2dea122 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -303,10 +303,7 @@ static void fc_exch_setup_hdr(struct fc_exch *ep, struct fc_frame *fp,
 		fr_eof(fp) = FC_EOF_N;
 	}
 
-	/*
-	 * Initialize remainig fh fields
-	 * from fc_fill_fc_hdr
-	 */
+	/* Initialize remaining fh fields from fc_fill_fc_hdr */
 	fh->fh_ox_id = htons(ep->oxid);
 	fh->fh_rx_id = htons(ep->rxid);
 	fh->fh_seq_id = ep->seq.id;
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index f04d15c67df3..a32f3141f3f9 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -516,7 +516,7 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
  * @lport: The local port receiving the LOGO
  * @fp:	   The LOGO request frame
  *
- * Locking Note: The lport lock is exected to be held before calling
+ * Locking Note: The lport lock is expected to be held before calling
  * this function.
  */
 static void fc_lport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index c710d908fda6..589ff9aedd31 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1705,7 +1705,7 @@ reject:
  * @rdata: The remote port that sent the PRLI request
  * @rx_fp: The PRLI request frame
  *
- * Locking Note: The rport lock is exected to be held before calling
+ * Locking Note: The rport lock is expected to be held before calling
  * this function.
  */
 static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
@@ -1824,7 +1824,7 @@ drop:
  * @rdata: The remote port that sent the PRLO request
  * @rx_fp: The PRLO request frame
  *
- * Locking Note: The rport lock is exected to be held before calling
+ * Locking Note: The rport lock is expected to be held before calling
  * this function.
  */
 static void fc_rport_recv_prlo_req(struct fc_rport_priv *rdata,
@@ -1895,7 +1895,7 @@ drop:
  * @lport: The local port that received the LOGO request
  * @fp:	   The LOGO request frame
  *
- * Locking Note: The rport lock is exected to be held before calling
+ * Locking Note: The rport lock is expected to be held before calling
  * this function.
  */
 static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
diff --git a/include/scsi/fc/fc_fc2.h b/include/scsi/fc/fc_fc2.h
index f87777d0d5bd..0b2671431305 100644
--- a/include/scsi/fc/fc_fc2.h
+++ b/include/scsi/fc/fc_fc2.h
@@ -104,7 +104,7 @@ struct fc_esb {
  * esb_e_stat - flags from FC-FS-2 T11/1619-D Rev 0.90.
  */
 #define ESB_ST_RESP         (1 << 31)   /* responder to exchange */
-#define ESB_ST_SEQ_INIT     (1 << 30)   /* port holds sequence initiaive */
+#define ESB_ST_SEQ_INIT     (1 << 30)   /* port holds sequence initiative */
 #define ESB_ST_COMPLETE     (1 << 29)   /* exchange is complete */
 #define ESB_ST_ABNORMAL     (1 << 28)   /* abnormal ending condition */
 #define ESB_ST_REC_QUAL     (1 << 26)   /* recovery qualifier active */
-- 
cgit 


From 7030fd626129ec4d616784516a462d317c251d39 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 17 Aug 2013 20:34:43 +0000
Subject: libfc: Do not invoke the response handler after fc_exch_done()

While the FCoE initiator driver invokes fc_exch_done() from inside
the libfc response handler, FCoE target drivers typically invoke
fc_exch_done() from outside the libfc response handler. The object
fc_exch.arg points at may disappear as soon as fc_exch_done() has
finished. So it's important not to invoke the response handler
function after fc_exch_done() has finished. Modify libfc such that
this guarantee is provided if fc_exch_done() is invoked from
outside a response handler. This patch fixes a sporadic crash in
FCoE target implementations after a command has been aborted.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
---
 drivers/scsi/libfc/fc_exch.c | 131 ++++++++++++++++++++++++++++++-------------
 include/scsi/libfc.h         |   9 +++
 2 files changed, 101 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 47ebc7b1e143..1b3a09473452 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -381,6 +381,8 @@ static void fc_exch_timer_set(struct fc_exch *ep, unsigned int timer_msec)
 /**
  * fc_exch_done_locked() - Complete an exchange with the exchange lock held
  * @ep: The exchange that is complete
+ *
+ * Note: May sleep if invoked from outside a response handler.
  */
 static int fc_exch_done_locked(struct fc_exch *ep)
 {
@@ -392,7 +394,6 @@ static int fc_exch_done_locked(struct fc_exch *ep)
 	 * ep, and in that case we only clear the resp and set it as
 	 * complete, so it can be reused by the timer to send the rrq.
 	 */
-	ep->resp = NULL;
 	if (ep->state & FC_EX_DONE)
 		return rc;
 	ep->esb_stat |= ESB_ST_COMPLETE;
@@ -589,6 +590,8 @@ static struct fc_seq *fc_seq_start_next(struct fc_seq *sp)
 
 /*
  * Set the response handler for the exchange associated with a sequence.
+ *
+ * Note: May sleep if invoked from outside a response handler.
  */
 static void fc_seq_set_resp(struct fc_seq *sp,
 			    void (*resp)(struct fc_seq *, struct fc_frame *,
@@ -596,8 +599,18 @@ static void fc_seq_set_resp(struct fc_seq *sp,
 			    void *arg)
 {
 	struct fc_exch *ep = fc_seq_exch(sp);
+	DEFINE_WAIT(wait);
 
 	spin_lock_bh(&ep->ex_lock);
+	while (ep->resp_active && ep->resp_task != current) {
+		prepare_to_wait(&ep->resp_wq, &wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock_bh(&ep->ex_lock);
+
+		schedule();
+
+		spin_lock_bh(&ep->ex_lock);
+	}
+	finish_wait(&ep->resp_wq, &wait);
 	ep->resp = resp;
 	ep->arg = arg;
 	spin_unlock_bh(&ep->ex_lock);
@@ -680,6 +693,61 @@ static int fc_seq_exch_abort(const struct fc_seq *req_sp,
 	return error;
 }
 
+/**
+ * fc_invoke_resp() - invoke ep->resp()
+ *
+ * Notes:
+ * It is assumed that after initialization finished (this means the
+ * first unlock of ex_lock after fc_exch_alloc()) ep->resp and ep->arg are
+ * modified only via fc_seq_set_resp(). This guarantees that none of these
+ * two variables changes if ep->resp_active > 0.
+ *
+ * If an fc_seq_set_resp() call is busy modifying ep->resp and ep->arg when
+ * this function is invoked, the first spin_lock_bh() call in this function
+ * will wait until fc_seq_set_resp() has finished modifying these variables.
+ *
+ * Since fc_exch_done() invokes fc_seq_set_resp() it is guaranteed that that
+ * ep->resp() won't be invoked after fc_exch_done() has returned.
+ *
+ * The response handler itself may invoke fc_exch_done(), which will clear the
+ * ep->resp pointer.
+ *
+ * Return value:
+ * Returns true if and only if ep->resp has been invoked.
+ */
+static bool fc_invoke_resp(struct fc_exch *ep, struct fc_seq *sp,
+			   struct fc_frame *fp)
+{
+	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
+	void *arg;
+	bool res = false;
+
+	spin_lock_bh(&ep->ex_lock);
+	ep->resp_active++;
+	if (ep->resp_task != current)
+		ep->resp_task = !ep->resp_task ? current : NULL;
+	resp = ep->resp;
+	arg = ep->arg;
+	spin_unlock_bh(&ep->ex_lock);
+
+	if (resp) {
+		resp(sp, fp, arg);
+		res = true;
+	} else if (!IS_ERR(fp)) {
+		fc_frame_free(fp);
+	}
+
+	spin_lock_bh(&ep->ex_lock);
+	if (--ep->resp_active == 0)
+		ep->resp_task = NULL;
+	spin_unlock_bh(&ep->ex_lock);
+
+	if (ep->resp_active == 0)
+		wake_up(&ep->resp_wq);
+
+	return res;
+}
+
 /**
  * fc_exch_timeout() - Handle exchange timer expiration
  * @work: The work_struct identifying the exchange that timed out
@@ -689,8 +757,6 @@ static void fc_exch_timeout(struct work_struct *work)
 	struct fc_exch *ep = container_of(work, struct fc_exch,
 					  timeout_work.work);
 	struct fc_seq *sp = &ep->seq;
-	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
-	void *arg;
 	u32 e_stat;
 	int rc = 1;
 
@@ -708,16 +774,13 @@ static void fc_exch_timeout(struct work_struct *work)
 			fc_exch_rrq(ep);
 		goto done;
 	} else {
-		resp = ep->resp;
-		arg = ep->arg;
-		ep->resp = NULL;
 		if (e_stat & ESB_ST_ABNORMAL)
 			rc = fc_exch_done_locked(ep);
 		spin_unlock_bh(&ep->ex_lock);
 		if (!rc)
 			fc_exch_delete(ep);
-		if (resp)
-			resp(sp, ERR_PTR(-FC_EX_TIMEOUT), arg);
+		fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_TIMEOUT));
+		fc_seq_set_resp(sp, NULL, ep->arg);
 		fc_seq_exch_abort(sp, 2 * ep->r_a_tov);
 		goto done;
 	}
@@ -804,6 +867,8 @@ hit:
 	ep->f_ctl = FC_FC_FIRST_SEQ;	/* next seq is first seq */
 	ep->rxid = FC_XID_UNKNOWN;
 	ep->class = mp->class;
+	ep->resp_active = 0;
+	init_waitqueue_head(&ep->resp_wq);
 	INIT_DELAYED_WORK(&ep->timeout_work, fc_exch_timeout);
 out:
 	return ep;
@@ -864,6 +929,8 @@ static struct fc_exch *fc_exch_find(struct fc_exch_mgr *mp, u16 xid)
  * fc_exch_done() - Indicate that an exchange/sequence tuple is complete and
  *		    the memory allocated for the related objects may be freed.
  * @sp: The sequence that has completed
+ *
+ * Note: May sleep if invoked from outside a response handler.
  */
 static void fc_exch_done(struct fc_seq *sp)
 {
@@ -873,6 +940,8 @@ static void fc_exch_done(struct fc_seq *sp)
 	spin_lock_bh(&ep->ex_lock);
 	rc = fc_exch_done_locked(ep);
 	spin_unlock_bh(&ep->ex_lock);
+
+	fc_seq_set_resp(sp, NULL, ep->arg);
 	if (!rc)
 		fc_exch_delete(ep);
 }
@@ -1436,9 +1505,7 @@ static void fc_exch_recv_req(struct fc_lport *lport, struct fc_exch_mgr *mp,
 		 * If new exch resp handler is valid then call that
 		 * first.
 		 */
-		if (ep->resp)
-			ep->resp(sp, fp, ep->arg);
-		else
+		if (!fc_invoke_resp(ep, sp, fp))
 			lport->tt.lport_recv(lport, fp);
 		fc_exch_release(ep);	/* release from lookup */
 	} else {
@@ -1462,8 +1529,6 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
 	struct fc_exch *ep;
 	enum fc_sof sof;
 	u32 f_ctl;
-	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
-	void *ex_resp_arg;
 	int rc;
 
 	ep = fc_exch_find(mp, ntohs(fh->fh_ox_id));
@@ -1506,14 +1571,11 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
 
 	if (fc_sof_needs_ack(sof))
 		fc_seq_send_ack(sp, fp);
-	resp = ep->resp;
-	ex_resp_arg = ep->arg;
 
 	if (fh->fh_type != FC_TYPE_FCP && fr_eof(fp) == FC_EOF_T &&
 	    (f_ctl & (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) ==
 	    (FC_FC_LAST_SEQ | FC_FC_END_SEQ)) {
 		spin_lock_bh(&ep->ex_lock);
-		resp = ep->resp;
 		rc = fc_exch_done_locked(ep);
 		WARN_ON(fc_seq_exch(sp) != ep);
 		spin_unlock_bh(&ep->ex_lock);
@@ -1534,10 +1596,8 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
 	 * If new exch resp handler is valid then call that
 	 * first.
 	 */
-	if (resp)
-		resp(sp, fp, ex_resp_arg);
-	else
-		fc_frame_free(fp);
+	fc_invoke_resp(ep, sp, fp);
+
 	fc_exch_release(ep);
 	return;
 rel:
@@ -1576,8 +1636,6 @@ static void fc_exch_recv_resp(struct fc_exch_mgr *mp, struct fc_frame *fp)
  */
 static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp)
 {
-	void (*resp)(struct fc_seq *, struct fc_frame *fp, void *arg);
-	void *ex_resp_arg;
 	struct fc_frame_header *fh;
 	struct fc_ba_acc *ap;
 	struct fc_seq *sp;
@@ -1622,9 +1680,6 @@ static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp)
 		break;
 	}
 
-	resp = ep->resp;
-	ex_resp_arg = ep->arg;
-
 	/* do we need to do some other checks here. Can we reuse more of
 	 * fc_exch_recv_seq_resp
 	 */
@@ -1636,17 +1691,14 @@ static void fc_exch_abts_resp(struct fc_exch *ep, struct fc_frame *fp)
 	    ntoh24(fh->fh_f_ctl) & FC_FC_LAST_SEQ)
 		rc = fc_exch_done_locked(ep);
 	spin_unlock_bh(&ep->ex_lock);
+
+	fc_exch_hold(ep);
 	if (!rc)
 		fc_exch_delete(ep);
-
-	if (resp)
-		resp(sp, fp, ex_resp_arg);
-	else
-		fc_frame_free(fp);
-
+	fc_invoke_resp(ep, sp, fp);
 	if (has_rec)
 		fc_exch_timer_set(ep, ep->r_a_tov);
-
+	fc_exch_release(ep);
 }
 
 /**
@@ -1768,32 +1820,33 @@ static void fc_seq_ls_rjt(struct fc_frame *rx_fp, enum fc_els_rjt_reason reason,
 /**
  * fc_exch_reset() - Reset an exchange
  * @ep: The exchange to be reset
+ *
+ * Note: May sleep if invoked from outside a response handler.
  */
 static void fc_exch_reset(struct fc_exch *ep)
 {
 	struct fc_seq *sp;
-	void (*resp)(struct fc_seq *, struct fc_frame *, void *);
-	void *arg;
 	int rc = 1;
 
 	spin_lock_bh(&ep->ex_lock);
 	fc_exch_abort_locked(ep, 0);
 	ep->state |= FC_EX_RST_CLEANUP;
 	fc_exch_timer_cancel(ep);
-	resp = ep->resp;
-	ep->resp = NULL;
 	if (ep->esb_stat & ESB_ST_REC_QUAL)
 		atomic_dec(&ep->ex_refcnt);	/* drop hold for rec_qual */
 	ep->esb_stat &= ~ESB_ST_REC_QUAL;
-	arg = ep->arg;
 	sp = &ep->seq;
 	rc = fc_exch_done_locked(ep);
 	spin_unlock_bh(&ep->ex_lock);
+
+	fc_exch_hold(ep);
+
 	if (!rc)
 		fc_exch_delete(ep);
 
-	if (resp)
-		resp(sp, ERR_PTR(-FC_EX_CLOSED), arg);
+	fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_CLOSED));
+	fc_seq_set_resp(sp, NULL, ep->arg);
+	fc_exch_release(ep);
 }
 
 /**
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index e1379b4e8faf..52beadf9a29b 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -410,6 +410,12 @@ struct fc_seq {
  * @fh_type:      The frame type
  * @class:        The class of service
  * @seq:          The sequence in use on this exchange
+ * @resp_active:  Number of tasks that are concurrently executing @resp().
+ * @resp_task:    If @resp_active > 0, either the task executing @resp(), the
+ *                task that has been interrupted to execute the soft-IRQ
+ *                executing @resp() or NULL if more than one task is executing
+ *                @resp concurrently.
+ * @resp_wq:      Waitqueue for the tasks waiting on @resp_active.
  * @resp:         Callback for responses on this exchange
  * @destructor:   Called when destroying the exchange
  * @arg:          Passed as a void pointer to the resp() callback
@@ -441,6 +447,9 @@ struct fc_exch {
 	u32		    r_a_tov;
 	u32		    f_ctl;
 	struct fc_seq       seq;
+	int		    resp_active;
+	struct task_struct  *resp_task;
+	wait_queue_head_t   resp_wq;
 	void		    (*resp)(struct fc_seq *, struct fc_frame *, void *);
 	void		    *arg;
 	void		    (*destructor)(struct fc_seq *, void *);
-- 
cgit 


From 272686bf46a34f86d270cf192f68769667792026 Mon Sep 17 00:00:00 2001
From: Leif Lindholm <leif.lindholm@linaro.org>
Date: Thu, 5 Sep 2013 11:34:54 +0100
Subject: efi: x86: ia64: provide a generic efi_config_init()

Common to (U)EFI support on all platforms is the global "efi" data
structure, and the code that parses the System Table to locate
addresses to populate that structure with.

This patch adds both of these to the global EFI driver code and
removes the local definition of the global "efi" data structure from
the x86 and ia64 code.

Squashed into one big patch to avoid breaking bisection.

Signed-off-by: Leif Lindholm <leif.lindholm@linaro.org>
Acked-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 arch/ia64/kernel/efi.c      |  54 +++++-----------------
 arch/x86/platform/efi/efi.c |  96 ++++-----------------------------------
 drivers/firmware/efi/efi.c  | 108 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/efi.h         |   7 +++
 4 files changed, 134 insertions(+), 131 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index 51bce594eb83..da5b462e6de6 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -44,10 +44,15 @@
 
 #define EFI_DEBUG	0
 
+static __initdata unsigned long palo_phys;
+
+static __initdata efi_config_table_type_t arch_tables[] = {
+	{PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys},
+	{NULL_GUID, NULL, 0},
+};
+
 extern efi_status_t efi_call_phys (void *, ...);
 
-struct efi efi;
-EXPORT_SYMBOL(efi);
 static efi_runtime_services_t *runtime;
 static u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL;
 
@@ -423,9 +428,9 @@ static u8 __init palo_checksum(u8 *buffer, u32 length)
  * Parse and handle PALO table which is published at:
  * http://www.dig64.org/home/DIG64_PALO_R1_0.pdf
  */
-static void __init handle_palo(unsigned long palo_phys)
+static void __init handle_palo(unsigned long phys_addr)
 {
-	struct palo_table *palo = __va(palo_phys);
+	struct palo_table *palo = __va(phys_addr);
 	u8  checksum;
 
 	if (strncmp(palo->signature, PALO_SIG, sizeof(PALO_SIG) - 1)) {
@@ -467,12 +472,10 @@ void __init
 efi_init (void)
 {
 	void *efi_map_start, *efi_map_end;
-	efi_config_table_t *config_tables;
 	efi_char16_t *c16;
 	u64 efi_desc_size;
 	char *cp, vendor[100] = "unknown";
 	int i;
-	unsigned long palo_phys;
 
 	/*
 	 * It's too early to be able to use the standard kernel command line
@@ -514,8 +517,6 @@ efi_init (void)
 		       efi.systab->hdr.revision >> 16,
 		       efi.systab->hdr.revision & 0xffff);
 
-	config_tables = __va(efi.systab->tables);
-
 	/* Show what we know for posterity */
 	c16 = __va(efi.systab->fw_vendor);
 	if (c16) {
@@ -528,43 +529,10 @@ efi_init (void)
 	       efi.systab->hdr.revision >> 16,
 	       efi.systab->hdr.revision & 0xffff, vendor);
 
-	efi.mps        = EFI_INVALID_TABLE_ADDR;
-	efi.acpi       = EFI_INVALID_TABLE_ADDR;
-	efi.acpi20     = EFI_INVALID_TABLE_ADDR;
-	efi.smbios     = EFI_INVALID_TABLE_ADDR;
-	efi.sal_systab = EFI_INVALID_TABLE_ADDR;
-	efi.boot_info  = EFI_INVALID_TABLE_ADDR;
-	efi.hcdp       = EFI_INVALID_TABLE_ADDR;
-	efi.uga        = EFI_INVALID_TABLE_ADDR;
-
 	palo_phys      = EFI_INVALID_TABLE_ADDR;
 
-	for (i = 0; i < (int) efi.systab->nr_tables; i++) {
-		if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
-			efi.mps = config_tables[i].table;
-			printk(" MPS=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) {
-			efi.acpi20 = config_tables[i].table;
-			printk(" ACPI 2.0=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) {
-			efi.acpi = config_tables[i].table;
-			printk(" ACPI=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) {
-			efi.smbios = config_tables[i].table;
-			printk(" SMBIOS=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) {
-			efi.sal_systab = config_tables[i].table;
-			printk(" SALsystab=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
-			efi.hcdp = config_tables[i].table;
-			printk(" HCDP=0x%lx", config_tables[i].table);
-		} else if (efi_guidcmp(config_tables[i].guid,
-			 PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID) == 0) {
-			palo_phys = config_tables[i].table;
-			printk(" PALO=0x%lx", config_tables[i].table);
-		}
-	}
-	printk("\n");
+	if (efi_config_init(arch_tables) != 0)
+		return;
 
 	if (palo_phys != EFI_INVALID_TABLE_ADDR)
 		handle_palo(palo_phys);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed127096..ed2be58ea3f1 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -60,19 +60,6 @@
 
 static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
 
-struct efi __read_mostly efi = {
-	.mps        = EFI_INVALID_TABLE_ADDR,
-	.acpi       = EFI_INVALID_TABLE_ADDR,
-	.acpi20     = EFI_INVALID_TABLE_ADDR,
-	.smbios     = EFI_INVALID_TABLE_ADDR,
-	.sal_systab = EFI_INVALID_TABLE_ADDR,
-	.boot_info  = EFI_INVALID_TABLE_ADDR,
-	.hcdp       = EFI_INVALID_TABLE_ADDR,
-	.uga        = EFI_INVALID_TABLE_ADDR,
-	.uv_systab  = EFI_INVALID_TABLE_ADDR,
-};
-EXPORT_SYMBOL(efi);
-
 struct efi_memory_map memmap;
 
 static struct efi efi_phys __initdata;
@@ -80,6 +67,13 @@ static efi_system_table_t efi_systab __initdata;
 
 unsigned long x86_efi_facility;
 
+static __initdata efi_config_table_type_t arch_tables[] = {
+#ifdef CONFIG_X86_UV
+	{UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+	{NULL_GUID, NULL, 0},
+};
+
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
  */
@@ -578,80 +572,6 @@ static int __init efi_systab_init(void *phys)
 	return 0;
 }
 
-static int __init efi_config_init(u64 tables, int nr_tables)
-{
-	void *config_tables, *tablep;
-	int i, sz;
-
-	if (efi_enabled(EFI_64BIT))
-		sz = sizeof(efi_config_table_64_t);
-	else
-		sz = sizeof(efi_config_table_32_t);
-
-	/*
-	 * Let's see what config tables the firmware passed to us.
-	 */
-	config_tables = early_ioremap(tables, nr_tables * sz);
-	if (config_tables == NULL) {
-		pr_err("Could not map Configuration table!\n");
-		return -ENOMEM;
-	}
-
-	tablep = config_tables;
-	pr_info("");
-	for (i = 0; i < efi.systab->nr_tables; i++) {
-		efi_guid_t guid;
-		unsigned long table;
-
-		if (efi_enabled(EFI_64BIT)) {
-			u64 table64;
-			guid = ((efi_config_table_64_t *)tablep)->guid;
-			table64 = ((efi_config_table_64_t *)tablep)->table;
-			table = table64;
-#ifdef CONFIG_X86_32
-			if (table64 >> 32) {
-				pr_cont("\n");
-				pr_err("Table located above 4GB, disabling EFI.\n");
-				early_iounmap(config_tables,
-					      efi.systab->nr_tables * sz);
-				return -EINVAL;
-			}
-#endif
-		} else {
-			guid = ((efi_config_table_32_t *)tablep)->guid;
-			table = ((efi_config_table_32_t *)tablep)->table;
-		}
-		if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
-			efi.mps = table;
-			pr_cont(" MPS=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
-			efi.acpi20 = table;
-			pr_cont(" ACPI 2.0=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
-			efi.acpi = table;
-			pr_cont(" ACPI=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
-			efi.smbios = table;
-			pr_cont(" SMBIOS=0x%lx ", table);
-#ifdef CONFIG_X86_UV
-		} else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
-			efi.uv_systab = table;
-			pr_cont(" UVsystab=0x%lx ", table);
-#endif
-		} else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
-			efi.hcdp = table;
-			pr_cont(" HCDP=0x%lx ", table);
-		} else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
-			efi.uga = table;
-			pr_cont(" UGA=0x%lx ", table);
-		}
-		tablep += sz;
-	}
-	pr_cont("\n");
-	early_iounmap(config_tables, efi.systab->nr_tables * sz);
-	return 0;
-}
-
 static int __init efi_runtime_init(void)
 {
 	efi_runtime_services_t *runtime;
@@ -745,7 +665,7 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
+	if (efi_config_init(arch_tables))
 		return;
 
 	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5145fa344ad5..e1010d450b65 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -13,11 +13,27 @@
  * This file is released under the GPLv2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kobject.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/efi.h>
+#include <linux/io.h>
+
+struct efi __read_mostly efi = {
+	.mps        = EFI_INVALID_TABLE_ADDR,
+	.acpi       = EFI_INVALID_TABLE_ADDR,
+	.acpi20     = EFI_INVALID_TABLE_ADDR,
+	.smbios     = EFI_INVALID_TABLE_ADDR,
+	.sal_systab = EFI_INVALID_TABLE_ADDR,
+	.boot_info  = EFI_INVALID_TABLE_ADDR,
+	.hcdp       = EFI_INVALID_TABLE_ADDR,
+	.uga        = EFI_INVALID_TABLE_ADDR,
+	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+};
+EXPORT_SYMBOL(efi);
 
 static struct kobject *efi_kobj;
 static struct kobject *efivars_kobj;
@@ -132,3 +148,95 @@ err_put:
 }
 
 subsys_initcall(efisubsys_init);
+
+
+static __initdata efi_config_table_type_t common_tables[] = {
+	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
+	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
+	{HCDP_TABLE_GUID, "HCDP", &efi.hcdp},
+	{MPS_TABLE_GUID, "MPS", &efi.mps},
+	{SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab},
+	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
+	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+	{NULL_GUID, NULL, 0},
+};
+
+static __init int match_config_table(efi_guid_t *guid,
+				     unsigned long table,
+				     efi_config_table_type_t *table_types)
+{
+	u8 str[EFI_VARIABLE_GUID_LEN + 1];
+	int i;
+
+	if (table_types) {
+		efi_guid_unparse(guid, str);
+
+		for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
+			efi_guid_unparse(&table_types[i].guid, str);
+
+			if (!efi_guidcmp(*guid, table_types[i].guid)) {
+				*(table_types[i].ptr) = table;
+				pr_cont(" %s=0x%lx ",
+					table_types[i].name, table);
+				return 1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+int __init efi_config_init(efi_config_table_type_t *arch_tables)
+{
+	void *config_tables, *tablep;
+	int i, sz;
+
+	if (efi_enabled(EFI_64BIT))
+		sz = sizeof(efi_config_table_64_t);
+	else
+		sz = sizeof(efi_config_table_32_t);
+
+	/*
+	 * Let's see what config tables the firmware passed to us.
+	 */
+	config_tables = early_memremap(efi.systab->tables,
+				       efi.systab->nr_tables * sz);
+	if (config_tables == NULL) {
+		pr_err("Could not map Configuration table!\n");
+		return -ENOMEM;
+	}
+
+	tablep = config_tables;
+	pr_info("");
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+		unsigned long table;
+
+		if (efi_enabled(EFI_64BIT)) {
+			u64 table64;
+			guid = ((efi_config_table_64_t *)tablep)->guid;
+			table64 = ((efi_config_table_64_t *)tablep)->table;
+			table = table64;
+#ifndef CONFIG_64BIT
+			if (table64 >> 32) {
+				pr_cont("\n");
+				pr_err("Table located above 4GB, disabling EFI.\n");
+				early_iounmap(config_tables,
+					       efi.systab->nr_tables * sz);
+				return -EINVAL;
+			}
+#endif
+		} else {
+			guid = ((efi_config_table_32_t *)tablep)->guid;
+			table = ((efi_config_table_32_t *)tablep)->table;
+		}
+
+		if (!match_config_table(&guid, table, common_tables))
+			match_config_table(&guid, table, arch_tables);
+
+		tablep += sz;
+	}
+	pr_cont("\n");
+	early_iounmap(config_tables, efi.systab->nr_tables * sz);
+	return 0;
+}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 5f8f176154f7..09d9e4212799 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -404,6 +404,12 @@ typedef struct {
 	unsigned long table;
 } efi_config_table_t;
 
+typedef struct {
+	efi_guid_t guid;
+	const char *name;
+	unsigned long *ptr;
+} efi_config_table_type_t;
+
 #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL)
 
 #define EFI_2_30_SYSTEM_TABLE_REVISION  ((2 << 16) | (30))
@@ -587,6 +593,7 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon
 }
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
+extern int efi_config_init(efi_config_table_type_t *arch_tables);
 extern u64 efi_get_iobase (void);
 extern u32 efi_mem_type (unsigned long phys_addr);
 extern u64 efi_mem_attributes (unsigned long phys_addr);
-- 
cgit 


From 258f6fd738221766b512cd8c7120563b78d62829 Mon Sep 17 00:00:00 2001
From: Leif Lindholm <leif.lindholm@linaro.org>
Date: Thu, 5 Sep 2013 11:34:55 +0100
Subject: efi: x86: make efi_lookup_mapped_addr() a common function

efi_lookup_mapped_addr() is a handy utility for other platforms than
x86. Move it from arch/x86 to drivers/firmware. Add memmap pointer
to global efi structure, and initialise it on x86.

Signed-off-by: Leif Lindholm <leif.lindholm@linaro.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 arch/x86/platform/efi/efi.c | 30 ++----------------------------
 drivers/firmware/efi/efi.c  | 32 ++++++++++++++++++++++++++++++++
 include/linux/efi.h         |  1 +
 3 files changed, 35 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ed2be58ea3f1..fbc1d70188f8 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -393,6 +393,8 @@ int __init efi_memblock_x86_reserve_range(void)
 
 	memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
 
+	efi.memmap = &memmap;
+
 	return 0;
 }
 
@@ -736,34 +738,6 @@ static void __init runtime_code_page_mkexec(void)
 	}
 }
 
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
-	void *p;
-	if (WARN_ON(!memmap.map))
-		return NULL;
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-		u64 end = md->phys_addr + size;
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		if (!md->virt_addr)
-			continue;
-		if (phys_addr >= md->phys_addr && phys_addr < end) {
-			phys_addr += md->virt_addr - md->phys_addr;
-			return (__force void __iomem *)(unsigned long)phys_addr;
-		}
-	}
-	return NULL;
-}
-
 void efi_memory_uc(u64 addr, unsigned long size)
 {
 	unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e1010d450b65..2e2fbdec0845 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -150,6 +150,38 @@ err_put:
 subsys_initcall(efisubsys_init);
 
 
+/*
+ * We can't ioremap data in EFI boot services RAM, because we've already mapped
+ * it as RAM.  So, look it up in the existing EFI memory map instead.  Only
+ * callable after efi_enter_virtual_mode and before efi_free_boot_services.
+ */
+void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
+{
+	struct efi_memory_map *map;
+	void *p;
+	map = efi.memmap;
+	if (!map)
+		return NULL;
+	if (WARN_ON(!map->map))
+		return NULL;
+	for (p = map->map; p < map->map_end; p += map->desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 end = md->phys_addr + size;
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		if (!md->virt_addr)
+			continue;
+		if (phys_addr >= md->phys_addr && phys_addr < end) {
+			phys_addr += md->virt_addr - md->phys_addr;
+			return (__force void __iomem *)(unsigned long)phys_addr;
+		}
+	}
+	return NULL;
+}
+
 static __initdata efi_config_table_type_t common_tables[] = {
 	{ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
 	{ACPI_TABLE_GUID, "ACPI", &efi.acpi},
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 09d9e4212799..c084b6d942c3 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -558,6 +558,7 @@ extern struct efi {
 	efi_get_next_high_mono_count_t *get_next_high_mono_count;
 	efi_reset_system_t *reset_system;
 	efi_set_virtual_address_map_t *set_virtual_address_map;
+	struct efi_memory_map *memmap;
 } efi;
 
 static inline int
-- 
cgit 


From 5a523605afa7d3b54b2e7041f8c9e6bc39872a7e Mon Sep 17 00:00:00 2001
From: Laxman Dewangan <ldewangan@nvidia.com>
Date: Tue, 10 Sep 2013 15:45:05 +0530
Subject: regulator: core: provide fixed voltage in desc for single voltage
 rail

If given rail has the single voltage (n_voltages = 1) then provide the
rail voltage through regulator descriptor so that core can use this
value for finding voltage.

This will avoid the implementation of the callback for get_voltage() or
list_voltage() callback on regulator driver.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c         | 5 ++++-
 include/linux/regulator/driver.h | 2 ++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a01b8b3b70ca..abc899ed1ebf 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2489,6 +2489,8 @@ static int _regulator_get_voltage(struct regulator_dev *rdev)
 		ret = rdev->desc->ops->get_voltage(rdev);
 	} else if (rdev->desc->ops->list_voltage) {
 		ret = rdev->desc->ops->list_voltage(rdev, 0);
+	} else if (rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1)) {
+		ret = rdev->desc->fixed_uV;
 	} else {
 		return -EINVAL;
 	}
@@ -3170,7 +3172,8 @@ static int add_regulator_attributes(struct regulator_dev *rdev)
 	/* some attributes need specific methods to be displayed */
 	if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) ||
 	    (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) ||
-	    (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0)) {
+	    (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) ||
+		(rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1))) {
 		status = device_create_file(dev, &dev_attr_microvolts);
 		if (status < 0)
 			return status;
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 67e13aa5a478..9e8241a9f28f 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -207,6 +207,7 @@ enum regulator_type {
  * @min_uV: Voltage given by the lowest selector (if linear mapping)
  * @uV_step: Voltage increase with each selector (if linear mapping)
  * @linear_min_sel: Minimal selector for starting linear mapping
+ * @fixed_uV: Fixed voltage of rails.
  * @ramp_delay: Time to settle down after voltage change (unit: uV/us)
  * @volt_table: Voltage mapping table (if table based mapping)
  *
@@ -239,6 +240,7 @@ struct regulator_desc {
 	unsigned int min_uV;
 	unsigned int uV_step;
 	unsigned int linear_min_sel;
+	int fixed_uV;
 	unsigned int ramp_delay;
 
 	const struct regulator_linear_range *linear_ranges;
-- 
cgit 


From 899d90bdf4d4ef4c3ac0b33cd337c9b3e999ec2d Mon Sep 17 00:00:00 2001
From: Peter Meerwald <pmeerw@pmeerw.net>
Date: Sun, 8 Sep 2013 16:20:00 +0100
Subject: iio: Add INT_TIME (integration time) channel info attribute

Integration time is in seconds; it controls the measurement
time and influences the gain of a sensor.

There are two typical ways that scaling is implemented in a device:
1) input amplifier,
2) reference to the ADC is changed.
These both result in the accuracy of the ADC varying (by applying its
sampling over a more relevant range).

Integration time is a way of dealing with noise inherent in the analog
sensor itself.  In the case of a light sensor, a mixture of photon noise
and device specific noise.  Photon noise is dealt with by either improving
the efficiency of the sensor, (more photons actually captured) which is not
easily varied dynamically, or by integrating the measurement over a longer
time period.  Note that this can also be thought of as an averaging of a
number of individual samples and is infact sometimes implemented this way.
Altering integration time implies that the duration of a measurement changes,
a fact the device's user may be interested in.

Hence it makes sense to distinguish between integration time and simple
scale. In some devices both types of control are present and whilst they
will have similar effects on the amplitude of the reading, their effect
on the noise of the measurements will differ considerably.

Used by adjd_s311, tsl4531, tcs3472
The following drivers have similar controls (and could be adapted):
* tsl2563 (integration time is controlled via CALIBSCALE among other things)
* tsl2583 (has integration_time device_attr, but driver doesn't use channels yet)
* tsl2x7x (has integration_time attr)

Signed-off-by: Peter Meerwald <pmeerw@pmeerw.net>
Cc: Jon Brenner <jon.brenner@ams.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 Documentation/ABI/testing/sysfs-bus-iio | 11 +++++++++++
 drivers/iio/industrialio-core.c         |  1 +
 include/linux/iio/iio.h                 |  1 +
 include/linux/iio/sysfs.h               | 15 +++++++++++++++
 4 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 39c8de0e53d0..ab1047c20495 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -811,3 +811,14 @@ Description:
 		Writing '1' stores the current device configuration into
 		on-chip EEPROM. After power-up or chip reset the device will
 		automatically load the saved configuration.
+
+What:		/sys/.../iio:deviceX/in_intensity_red_integration_time
+What:		/sys/.../iio:deviceX/in_intensity_green_integration_time
+What:		/sys/.../iio:deviceX/in_intensity_blue_integration_time
+What:		/sys/.../iio:deviceX/in_intensity_clear_integration_time
+What:		/sys/.../iio:deviceX/in_illuminance_integration_time
+KernelVersion:	3.12
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This attribute is used to get/set the integration time in
+		seconds.
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 97f0297b120f..2cb4841d5357 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -101,6 +101,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_PHASE] = "phase",
 	[IIO_CHAN_INFO_HARDWAREGAIN] = "hardwaregain",
 	[IIO_CHAN_INFO_HYSTERESIS] = "hysteresis",
+	[IIO_CHAN_INFO_INT_TIME] = "integration_time",
 };
 
 const struct iio_chan_spec
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 8e7a8132b109..01edd6795550 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -36,6 +36,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_PHASE,
 	IIO_CHAN_INFO_HARDWAREGAIN,
 	IIO_CHAN_INFO_HYSTERESIS,
+	IIO_CHAN_INFO_INT_TIME,
 };
 
 enum iio_endian {
diff --git a/include/linux/iio/sysfs.h b/include/linux/iio/sysfs.h
index 2958c960003a..8a1d18640ab9 100644
--- a/include/linux/iio/sysfs.h
+++ b/include/linux/iio/sysfs.h
@@ -100,6 +100,21 @@ struct iio_const_attr {
 #define IIO_CONST_ATTR_SAMP_FREQ_AVAIL(_string)			\
 	IIO_CONST_ATTR(sampling_frequency_available, _string)
 
+/**
+ * IIO_DEV_ATTR_INT_TIME_AVAIL - list available integration times
+ * @_show: output method for the attribute
+ **/
+#define IIO_DEV_ATTR_INT_TIME_AVAIL(_show)		\
+	IIO_DEVICE_ATTR(integration_time_available, S_IRUGO, _show, NULL, 0)
+/**
+ * IIO_CONST_ATTR_INT_TIME_AVAIL - list available integration times
+ * @_string: frequency string for the attribute
+ *
+ * Constant version
+ **/
+#define IIO_CONST_ATTR_INT_TIME_AVAIL(_string)		\
+	IIO_CONST_ATTR(integration_time_available, _string)
+
 #define IIO_DEV_ATTR_TEMP_RAW(_show)			\
 	IIO_DEVICE_ATTR(in_temp_raw, S_IRUGO, _show, NULL, 0)
 
-- 
cgit 


From ea01f2c18a22a2a8385909d64662afc92da6b13f Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Tue, 10 Sep 2013 13:49:00 +0100
Subject: iio: pressure-core: st: Allow for number of channels to vary

At the moment the number of channels specified is dictated by the first
sensor supported by the driver. As we add support for more sensors this
is likely to vary. Instead of using the ARRAY_SIZE() of the LPS331AP's
channel specifier we'll use a new adaptable 'struct st_sensors' element
instead.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Denis Ciocca <denis.ciocca@st.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/pressure/st_pressure_core.c | 3 ++-
 include/linux/iio/common/st_sensors.h   | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 506b02d27b0a..93bff9ba05d6 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -107,6 +107,7 @@ static const struct st_sensors st_press_sensors[] = {
 			[0] = LPS331AP_PRESS_DEV_NAME,
 		},
 		.ch = (struct iio_chan_spec *)st_press_lps331ap_channels,
+		.num_ch = ARRAY_SIZE(st_press_lps331ap_channels),
 		.odr = {
 			.addr = ST_PRESS_LPS331AP_ODR_ADDR,
 			.mask = ST_PRESS_LPS331AP_ODR_MASK,
@@ -245,7 +246,7 @@ int st_press_common_probe(struct iio_dev *indio_dev,
 	pdata->num_data_channels = ST_PRESS_NUMBER_DATA_CHANNELS;
 	pdata->multiread_bit = pdata->sensor->multi_read_bit;
 	indio_dev->channels = pdata->sensor->ch;
-	indio_dev->num_channels = ARRAY_SIZE(st_press_lps331ap_channels);
+	indio_dev->num_channels = pdata->sensor->num_ch;
 
 	if (pdata->sensor->fs.addr != 0)
 		pdata->current_fullscale = (struct st_sensor_fullscale_avl *)
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index e51f65480ea5..e732fda6c8e6 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -184,6 +184,7 @@ struct st_sensors {
 	u8 wai;
 	char sensors_supported[ST_SENSORS_MAX_4WAI][ST_SENSORS_MAX_NAME];
 	struct iio_chan_spec *ch;
+	int num_ch;
 	struct st_sensor_odr odr;
 	struct st_sensor_power pw;
 	struct st_sensor_axis enable_axis;
-- 
cgit 


From 9761696f2be276b169b77bcf359bc50a251c9280 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <jic23@kernel.org>
Date: Sun, 8 Sep 2013 14:57:00 +0100
Subject: iio: drop info_mask from struct iio_dev

Somehow this got missed when dropping all the code that used it
prior to the split.  Remove it now, there are no users.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
---
 include/linux/iio/iio.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 01edd6795550..bc408e2def40 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -147,12 +147,10 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev,
  *			shift:		Shift right by this before masking out
  *					realbits.
  *			endianness:	little or big endian
- * @info_mask:		What information is to be exported about this channel.
- *			This includes calibbias, scale etc.
  * @info_mask_separate: What information is to be exported that is specific to
  *			this channel.
  * @info_mask_shared_by_type: What information is to be exported that is shared
-*			by all channels of the same type.
+ *			by all channels of the same type.
  * @event_mask:		What events can this channel produce.
  * @ext_info:		Array of extended info attributes for this channel.
  *			The array is NULL terminated, the last element should
@@ -187,7 +185,6 @@ struct iio_chan_spec {
 		u8	shift;
 		enum iio_endian endianness;
 	} scan_type;
-	long			info_mask;
 	long			info_mask_separate;
 	long			info_mask_shared_by_type;
 	long			event_mask;
-- 
cgit 


From 3704432fb1fd8ab2df114bad6df752381246b609 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <jic23@kernel.org>
Date: Sun, 8 Sep 2013 14:57:00 +0100
Subject: iio: refactor info mask and ext_info attribute creation.

Introduce an enum to specify whether the attribute is separate or
shared.

Factor out the bitmap handling for loop into a separate function.

Tidy up error handling and add a NULL assignment to squish a false
positive warning from GCC.

Change ext_info shared type from boolean to enum and update in all
drivers.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
---
 drivers/iio/dac/ad5064.c          |   3 +-
 drivers/iio/dac/ad5380.c          |   4 +-
 drivers/iio/dac/ad5446.c          |   3 +-
 drivers/iio/dac/ad5504.c          |   4 +-
 drivers/iio/dac/ad5624r_spi.c     |   4 +-
 drivers/iio/dac/ad5686.c          |   3 +-
 drivers/iio/dac/ad5755.c          |   1 +
 drivers/iio/dac/ad5791.c          |   5 +-
 drivers/iio/dac/ad7303.c          |   1 +
 drivers/iio/dac/mcp4725.c         |   3 +-
 drivers/iio/frequency/adf4350.c   |   1 +
 drivers/iio/iio_core.h            |   2 +-
 drivers/iio/industrialio-buffer.c |   2 +-
 drivers/iio/industrialio-core.c   | 149 ++++++++++++++++++++------------------
 include/linux/iio/iio.h           |   9 ++-
 15 files changed, 112 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/dac/ad5064.c b/drivers/iio/dac/ad5064.c
index a3a52be4852c..b18e8c4347c2 100644
--- a/drivers/iio/dac/ad5064.c
+++ b/drivers/iio/dac/ad5064.c
@@ -285,8 +285,9 @@ static const struct iio_chan_spec_ext_info ad5064_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5064_read_dac_powerdown,
 		.write = ad5064_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", false, &ad5064_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5064_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5064_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5380.c b/drivers/iio/dac/ad5380.c
index 1c44ae3920e2..4c791e66e0d7 100644
--- a/drivers/iio/dac/ad5380.c
+++ b/drivers/iio/dac/ad5380.c
@@ -247,8 +247,10 @@ static struct iio_chan_spec_ext_info ad5380_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5380_read_dac_powerdown,
 		.write = ad5380_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", true, &ad5380_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE,
+		 &ad5380_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5380_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c
index 96e9ed4c2d01..6dcb6d93f0e4 100644
--- a/drivers/iio/dac/ad5446.c
+++ b/drivers/iio/dac/ad5446.c
@@ -132,8 +132,9 @@ static const struct iio_chan_spec_ext_info ad5446_ext_info_powerdown[] = {
 		.name = "powerdown",
 		.read = ad5446_read_dac_powerdown,
 		.write = ad5446_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", false, &ad5446_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5446_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5446_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5504.c b/drivers/iio/dac/ad5504.c
index caffb16bc05c..31f4ff29f914 100644
--- a/drivers/iio/dac/ad5504.c
+++ b/drivers/iio/dac/ad5504.c
@@ -248,8 +248,10 @@ static const struct iio_chan_spec_ext_info ad5504_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5504_read_dac_powerdown,
 		.write = ad5504_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", true, &ad5504_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE,
+		 &ad5504_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5504_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c
index 714af757cd56..dbb1289cc7a6 100644
--- a/drivers/iio/dac/ad5624r_spi.c
+++ b/drivers/iio/dac/ad5624r_spi.c
@@ -163,8 +163,10 @@ static const struct iio_chan_spec_ext_info ad5624r_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5624r_read_dac_powerdown,
 		.write = ad5624r_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", true, &ad5624r_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE,
+		 &ad5624r_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5624r_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 3e1080feedbf..f472b48445f6 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -264,8 +264,9 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5686_read_dac_powerdown,
 		.write = ad5686_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", false, &ad5686_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5686_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5686_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad5755.c b/drivers/iio/dac/ad5755.c
index 36a4361aece1..f305a0c83418 100644
--- a/drivers/iio/dac/ad5755.c
+++ b/drivers/iio/dac/ad5755.c
@@ -386,6 +386,7 @@ static const struct iio_chan_spec_ext_info ad5755_ext_info[] = {
 		.name = "powerdown",
 		.read = ad5755_read_powerdown,
 		.write = ad5755_write_powerdown,
+		.shared = IIO_SEPARATE,
 	},
 	{ },
 };
diff --git a/drivers/iio/dac/ad5791.c b/drivers/iio/dac/ad5791.c
index ce7458963309..3cee89be68c3 100644
--- a/drivers/iio/dac/ad5791.c
+++ b/drivers/iio/dac/ad5791.c
@@ -287,11 +287,12 @@ static int ad5791_read_raw(struct iio_dev *indio_dev,
 static const struct iio_chan_spec_ext_info ad5791_ext_info[] = {
 	{
 		.name = "powerdown",
-		.shared = true,
+		.shared = IIO_SHARED_BY_TYPE,
 		.read = ad5791_read_dac_powerdown,
 		.write = ad5791_write_dac_powerdown,
 	},
-	IIO_ENUM("powerdown_mode", true, &ad5791_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE,
+		 &ad5791_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &ad5791_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/dac/ad7303.c b/drivers/iio/dac/ad7303.c
index ed2d276477bd..d0505fd22ef4 100644
--- a/drivers/iio/dac/ad7303.c
+++ b/drivers/iio/dac/ad7303.c
@@ -169,6 +169,7 @@ static const struct iio_chan_spec_ext_info ad7303_ext_info[] = {
 		.name = "powerdown",
 		.read = ad7303_read_dac_powerdown,
 		.write = ad7303_write_dac_powerdown,
+		.shared = IIO_SEPARATE,
 	},
 	{ },
 };
diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c
index 1f4a48e6a82c..6711a33b16ba 100644
--- a/drivers/iio/dac/mcp4725.c
+++ b/drivers/iio/dac/mcp4725.c
@@ -195,8 +195,9 @@ static const struct iio_chan_spec_ext_info mcp4725_ext_info[] = {
 		.name = "powerdown",
 		.read = mcp4725_read_powerdown,
 		.write = mcp4725_write_powerdown,
+		.shared = IIO_SEPARATE,
 	},
-	IIO_ENUM("powerdown_mode", false, &mcp4725_powerdown_mode_enum),
+	IIO_ENUM("powerdown_mode", IIO_SEPARATE, &mcp4725_powerdown_mode_enum),
 	IIO_ENUM_AVAILABLE("powerdown_mode", &mcp4725_powerdown_mode_enum),
 	{ },
 };
diff --git a/drivers/iio/frequency/adf4350.c b/drivers/iio/frequency/adf4350.c
index a7b30be86ae0..85152547aa8b 100644
--- a/drivers/iio/frequency/adf4350.c
+++ b/drivers/iio/frequency/adf4350.c
@@ -351,6 +351,7 @@ static ssize_t adf4350_read(struct iio_dev *indio_dev,
 	.read = adf4350_read, \
 	.write = adf4350_write, \
 	.private = _ident, \
+	.shared = IIO_SEPARATE, \
 }
 
 static const struct iio_chan_spec_ext_info adf4350_ext_info[] = {
diff --git a/drivers/iio/iio_core.h b/drivers/iio/iio_core.h
index 05c1b74502a3..6be5ab864b1a 100644
--- a/drivers/iio/iio_core.h
+++ b/drivers/iio/iio_core.h
@@ -30,7 +30,7 @@ int __iio_add_chan_devattr(const char *postfix,
 						const char *buf,
 						size_t len),
 			   u64 mask,
-			   bool generic,
+			   enum iio_shared_by shared_by,
 			   struct device *dev,
 			   struct list_head *attr_list);
 
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 96e97ad2538c..7ea2edbf7614 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -208,7 +208,7 @@ static int iio_buffer_add_channel_sysfs(struct iio_dev *indio_dev,
 				     &iio_show_scan_index,
 				     NULL,
 				     0,
-				     0,
+				     IIO_SEPARATE,
 				     &indio_dev->dev,
 				     &buffer->scan_el_dev_attr_list);
 	if (ret)
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 2cb4841d5357..d380c7278a26 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -517,14 +517,15 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
 						struct device_attribute *attr,
 						const char *buf,
 						size_t len),
-			   bool generic)
+			   enum iio_shared_by shared_by)
 {
-	int ret;
-	char *name_format, *full_postfix;
+	int ret = 0;
+	char *name_format = NULL;
+	char *full_postfix;
 	sysfs_attr_init(&dev_attr->attr);
 
 	/* Build up postfix of <extend_name>_<modifier>_postfix */
-	if (chan->modified && !generic) {
+	if (chan->modified && (shared_by == IIO_SEPARATE)) {
 		if (chan->extend_name)
 			full_postfix = kasprintf(GFP_KERNEL, "%s_%s_%s",
 						 iio_modifier_names[chan
@@ -545,53 +546,62 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
 						 chan->extend_name,
 						 postfix);
 	}
-	if (full_postfix == NULL) {
-		ret = -ENOMEM;
-		goto error_ret;
-	}
+	if (full_postfix == NULL)
+		return -ENOMEM;
 
 	if (chan->differential) { /* Differential can not have modifier */
-		if (generic)
+		switch (shared_by) {
+		case IIO_SHARED_BY_TYPE:
 			name_format
 				= kasprintf(GFP_KERNEL, "%s_%s-%s_%s",
 					    iio_direction[chan->output],
 					    iio_chan_type_name_spec[chan->type],
 					    iio_chan_type_name_spec[chan->type],
 					    full_postfix);
-		else if (chan->indexed)
+			break;
+		case IIO_SEPARATE:
+			if (!chan->indexed) {
+				WARN_ON("Differential channels must be indexed\n");
+				ret = -EINVAL;
+				goto error_free_full_postfix;
+			}
 			name_format
-				= kasprintf(GFP_KERNEL, "%s_%s%d-%s%d_%s",
+				= kasprintf(GFP_KERNEL,
+					    "%s_%s%d-%s%d_%s",
 					    iio_direction[chan->output],
 					    iio_chan_type_name_spec[chan->type],
 					    chan->channel,
 					    iio_chan_type_name_spec[chan->type],
 					    chan->channel2,
 					    full_postfix);
-		else {
-			WARN_ON("Differential channels must be indexed\n");
-			ret = -EINVAL;
-			goto error_free_full_postfix;
+			break;
 		}
 	} else { /* Single ended */
-		if (generic)
-			name_format
-				= kasprintf(GFP_KERNEL, "%s_%s_%s",
-					    iio_direction[chan->output],
-					    iio_chan_type_name_spec[chan->type],
-					    full_postfix);
-		else if (chan->indexed)
-			name_format
-				= kasprintf(GFP_KERNEL, "%s_%s%d_%s",
-					    iio_direction[chan->output],
-					    iio_chan_type_name_spec[chan->type],
-					    chan->channel,
-					    full_postfix);
-		else
+		switch (shared_by) {
+		case IIO_SHARED_BY_TYPE:
 			name_format
 				= kasprintf(GFP_KERNEL, "%s_%s_%s",
 					    iio_direction[chan->output],
 					    iio_chan_type_name_spec[chan->type],
 					    full_postfix);
+			break;
+
+		case IIO_SEPARATE:
+			if (chan->indexed)
+				name_format
+					= kasprintf(GFP_KERNEL, "%s_%s%d_%s",
+						    iio_direction[chan->output],
+						    iio_chan_type_name_spec[chan->type],
+						    chan->channel,
+						    full_postfix);
+			else
+				name_format
+					= kasprintf(GFP_KERNEL, "%s_%s_%s",
+						    iio_direction[chan->output],
+						    iio_chan_type_name_spec[chan->type],
+						    full_postfix);
+			break;
+		}
 	}
 	if (name_format == NULL) {
 		ret = -ENOMEM;
@@ -615,16 +625,11 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
 		dev_attr->attr.mode |= S_IWUSR;
 		dev_attr->store = writefunc;
 	}
-	kfree(name_format);
-	kfree(full_postfix);
-
-	return 0;
-
 error_free_name_format:
 	kfree(name_format);
 error_free_full_postfix:
 	kfree(full_postfix);
-error_ret:
+
 	return ret;
 }
 
@@ -643,7 +648,7 @@ int __iio_add_chan_devattr(const char *postfix,
 						const char *buf,
 						size_t len),
 			   u64 mask,
-			   bool generic,
+			   enum iio_shared_by shared_by,
 			   struct device *dev,
 			   struct list_head *attr_list)
 {
@@ -657,7 +662,7 @@ int __iio_add_chan_devattr(const char *postfix,
 	}
 	ret = __iio_device_attr_init(&iio_attr->dev_attr,
 				     postfix, chan,
-				     readfunc, writefunc, generic);
+				     readfunc, writefunc, shared_by);
 	if (ret)
 		goto error_iio_dev_attr_free;
 	iio_attr->c = chan;
@@ -665,7 +670,7 @@ int __iio_add_chan_devattr(const char *postfix,
 	list_for_each_entry(t, attr_list, l)
 		if (strcmp(t->dev_attr.attr.name,
 			   iio_attr->dev_attr.attr.name) == 0) {
-			if (!generic)
+			if (shared_by == IIO_SEPARATE)
 				dev_err(dev, "tried to double register : %s\n",
 					t->dev_attr.attr.name);
 			ret = -EBUSY;
@@ -683,46 +688,54 @@ error_ret:
 	return ret;
 }
 
-static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
-					struct iio_chan_spec const *chan)
+static int iio_device_add_info_mask_type(struct iio_dev *indio_dev,
+					 struct iio_chan_spec const *chan,
+					 enum iio_shared_by shared_by,
+					 const long *infomask)
 {
-	int ret, attrcount = 0;
-	int i;
-	const struct iio_chan_spec_ext_info *ext_info;
+	int i, ret, attrcount = 0;
 
-	if (chan->channel < 0)
-		return 0;
-	for_each_set_bit(i, &chan->info_mask_separate, sizeof(long)*8) {
+	for_each_set_bit(i, infomask, sizeof(infomask)*8) {
 		ret = __iio_add_chan_devattr(iio_chan_info_postfix[i],
 					     chan,
 					     &iio_read_channel_info,
 					     &iio_write_channel_info,
 					     i,
-					     0,
+					     shared_by,
 					     &indio_dev->dev,
 					     &indio_dev->channel_attr_list);
-		if (ret < 0)
-			goto error_ret;
-		attrcount++;
-	}
-	for_each_set_bit(i, &chan->info_mask_shared_by_type, sizeof(long)*8) {
-		ret = __iio_add_chan_devattr(iio_chan_info_postfix[i],
-					     chan,
-					     &iio_read_channel_info,
-					     &iio_write_channel_info,
-					     i,
-					     1,
-					     &indio_dev->dev,
-					     &indio_dev->channel_attr_list);
-		if (ret == -EBUSY) {
-			ret = 0;
+		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
 			continue;
-		} else if (ret < 0) {
-			goto error_ret;
-		}
+		else if (ret < 0)
+			return ret;
 		attrcount++;
 	}
 
+	return attrcount;
+}
+
+static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
+					struct iio_chan_spec const *chan)
+{
+	int ret, attrcount = 0;
+	const struct iio_chan_spec_ext_info *ext_info;
+
+	if (chan->channel < 0)
+		return 0;
+	ret = iio_device_add_info_mask_type(indio_dev, chan,
+					    IIO_SEPARATE,
+					    &chan->info_mask_separate);
+	if (ret < 0)
+		return ret;
+	attrcount += ret;
+
+	ret = iio_device_add_info_mask_type(indio_dev, chan,
+					    IIO_SHARED_BY_TYPE,
+					    &chan->info_mask_shared_by_type);
+	if (ret < 0)
+		return ret;
+	attrcount += ret;
+
 	if (chan->ext_info) {
 		unsigned int i = 0;
 		for (ext_info = chan->ext_info; ext_info->name; ext_info++) {
@@ -741,15 +754,13 @@ static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
 				continue;
 
 			if (ret)
-				goto error_ret;
+				return ret;
 
 			attrcount++;
 		}
 	}
 
-	ret = attrcount;
-error_ret:
-	return ret;
+	return attrcount;
 }
 
 static void iio_device_remove_and_free_read_attr(struct iio_dev *indio_dev,
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index bc408e2def40..21de272f1eb6 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -39,6 +39,11 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_INT_TIME,
 };
 
+enum iio_shared_by {
+	IIO_SEPARATE,
+	IIO_SHARED_BY_TYPE
+};
+
 enum iio_endian {
 	IIO_CPU,
 	IIO_BE,
@@ -58,7 +63,7 @@ struct iio_dev;
  */
 struct iio_chan_spec_ext_info {
 	const char *name;
-	bool shared;
+	enum iio_shared_by shared;
 	ssize_t (*read)(struct iio_dev *, uintptr_t private,
 			struct iio_chan_spec const *, char *buf);
 	ssize_t (*write)(struct iio_dev *, uintptr_t private,
@@ -126,7 +131,7 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev,
 #define IIO_ENUM_AVAILABLE(_name, _e) \
 { \
 	.name = (_name "_available"), \
-	.shared = true, \
+	.shared = IIO_SHARED_BY_TYPE, \
 	.read = iio_enum_available_read, \
 	.private = (uintptr_t)(_e), \
 }
-- 
cgit 


From c006ec838414d910bdd63ba8d919e602425e194e Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <jic23@kernel.org>
Date: Sun, 8 Sep 2013 14:57:00 +0100
Subject: iio: add info_mask_[shared_by_dir/shared_by_all]

These two additional info_mask bitmaps should allow all 'standard'
numeric attributes to be handled using the read_raw and write_raw
callbacks.  Whilst this should reduce code, the more important element
is that this makes these values easily accessible to in kernel users
of IIO devices.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
---
 drivers/iio/industrialio-core.c | 30 ++++++++++++++++++++++++++++++
 include/linux/iio/iio.h         | 14 ++++++++++++--
 2 files changed, 42 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index d380c7278a26..24db1855dbab 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -551,6 +551,14 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
 
 	if (chan->differential) { /* Differential can not have modifier */
 		switch (shared_by) {
+		case IIO_SHARED_BY_ALL:
+			name_format = kasprintf(GFP_KERNEL, "%s", full_postfix);
+			break;
+		case IIO_SHARED_BY_DIR:
+			name_format = kasprintf(GFP_KERNEL, "%s_%s",
+						iio_direction[chan->output],
+						full_postfix);
+			break;
 		case IIO_SHARED_BY_TYPE:
 			name_format
 				= kasprintf(GFP_KERNEL, "%s_%s-%s_%s",
@@ -578,6 +586,14 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
 		}
 	} else { /* Single ended */
 		switch (shared_by) {
+		case IIO_SHARED_BY_ALL:
+			name_format = kasprintf(GFP_KERNEL, "%s", full_postfix);
+			break;
+		case IIO_SHARED_BY_DIR:
+			name_format = kasprintf(GFP_KERNEL, "%s_%s",
+						iio_direction[chan->output],
+						full_postfix);
+			break;
 		case IIO_SHARED_BY_TYPE:
 			name_format
 				= kasprintf(GFP_KERNEL, "%s_%s_%s",
@@ -736,6 +752,20 @@ static int iio_device_add_channel_sysfs(struct iio_dev *indio_dev,
 		return ret;
 	attrcount += ret;
 
+	ret = iio_device_add_info_mask_type(indio_dev, chan,
+					    IIO_SHARED_BY_DIR,
+					    &chan->info_mask_shared_by_dir);
+	if (ret < 0)
+		return ret;
+	attrcount += ret;
+
+	ret = iio_device_add_info_mask_type(indio_dev, chan,
+					    IIO_SHARED_BY_ALL,
+					    &chan->info_mask_shared_by_all);
+	if (ret < 0)
+		return ret;
+	attrcount += ret;
+
 	if (chan->ext_info) {
 		unsigned int i = 0;
 		for (ext_info = chan->ext_info; ext_info->name; ext_info++) {
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 21de272f1eb6..ac1cb8f1858c 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -41,7 +41,9 @@ enum iio_chan_info_enum {
 
 enum iio_shared_by {
 	IIO_SEPARATE,
-	IIO_SHARED_BY_TYPE
+	IIO_SHARED_BY_TYPE,
+	IIO_SHARED_BY_DIR,
+	IIO_SHARED_BY_ALL
 };
 
 enum iio_endian {
@@ -156,6 +158,10 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev,
  *			this channel.
  * @info_mask_shared_by_type: What information is to be exported that is shared
  *			by all channels of the same type.
+ * @info_mask_shared_by_dir: What information is to be exported that is shared
+ *			by all channels of the same direction.
+ * @info_mask_shared_by_all: What information is to be exported that is shared
+ *			by all channels.
  * @event_mask:		What events can this channel produce.
  * @ext_info:		Array of extended info attributes for this channel.
  *			The array is NULL terminated, the last element should
@@ -192,6 +198,8 @@ struct iio_chan_spec {
 	} scan_type;
 	long			info_mask_separate;
 	long			info_mask_shared_by_type;
+	long			info_mask_shared_by_dir;
+	long			info_mask_shared_by_all;
 	long			event_mask;
 	const struct iio_chan_spec_ext_info *ext_info;
 	const char		*extend_name;
@@ -215,7 +223,9 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan,
 	enum iio_chan_info_enum type)
 {
 	return (chan->info_mask_separate & BIT(type)) |
-	       (chan->info_mask_shared_by_type & BIT(type));
+		(chan->info_mask_shared_by_type & BIT(type)) |
+		(chan->info_mask_shared_by_dir & BIT(type)) |
+		(chan->info_mask_shared_by_all & BIT(type));
 }
 
 #define IIO_ST(si, rb, sb, sh)						\
-- 
cgit 


From 5d65d92045cb7d3b2c45020c0e62d6d1c1d34f37 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 15 Sep 2013 17:50:00 +0100
Subject: iio: iio_push_to_buffers(): Change type of 'data' to const void *

Change the type of the 'data' parameter for iio_push_to_buffers() from 'u8 *' to
'const void *'. Drivers typically use the correct type (e.g. __be16 *) for their
data buffer. When passing the buffer to iio_push_to_buffers() it needs to be
cast to 'u8 *' for the compiler to not complain (and also having to add __force
if we want to keep sparse happy as well). Since the buffer implementation should
not care about the data layout (except the size of one sample) using a void
pointer is the correct thing to do. Also make it const as the buffer
implementations are not supposed to modify it.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/buffer_cb.c           |  6 +++---
 drivers/iio/industrialio-buffer.c | 10 +++++-----
 drivers/iio/kfifo_buf.c           |  2 +-
 include/linux/iio/buffer.h        |  6 +++---
 include/linux/iio/consumer.h      |  2 +-
 5 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/buffer_cb.c b/drivers/iio/buffer_cb.c
index f406889248c8..578f7199ed51 100644
--- a/drivers/iio/buffer_cb.c
+++ b/drivers/iio/buffer_cb.c
@@ -7,12 +7,12 @@
 
 struct iio_cb_buffer {
 	struct iio_buffer buffer;
-	int (*cb)(u8 *data, void *private);
+	int (*cb)(const void *data, void *private);
 	void *private;
 	struct iio_channel *channels;
 };
 
-static int iio_buffer_cb_store_to(struct iio_buffer *buffer, u8 *data)
+static int iio_buffer_cb_store_to(struct iio_buffer *buffer, const void *data)
 {
 	struct iio_cb_buffer *cb_buff = container_of(buffer,
 						     struct iio_cb_buffer,
@@ -26,7 +26,7 @@ static const struct iio_buffer_access_funcs iio_cb_access = {
 };
 
 struct iio_cb_buffer *iio_channel_get_all_cb(struct device *dev,
-					     int (*cb)(u8 *data,
+					     int (*cb)(const void *data,
 						       void *private),
 					     void *private)
 {
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 7ea2edbf7614..a7ac4b5af03e 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -769,8 +769,8 @@ struct iio_demux_table {
 	struct list_head l;
 };
 
-static unsigned char *iio_demux(struct iio_buffer *buffer,
-				 unsigned char *datain)
+static const void *iio_demux(struct iio_buffer *buffer,
+				 const void *datain)
 {
 	struct iio_demux_table *t;
 
@@ -783,9 +783,9 @@ static unsigned char *iio_demux(struct iio_buffer *buffer,
 	return buffer->demux_bounce;
 }
 
-static int iio_push_to_buffer(struct iio_buffer *buffer, unsigned char *data)
+static int iio_push_to_buffer(struct iio_buffer *buffer, const void *data)
 {
-	unsigned char *dataout = iio_demux(buffer, data);
+	const void *dataout = iio_demux(buffer, data);
 
 	return buffer->access->store_to(buffer, dataout);
 }
@@ -800,7 +800,7 @@ static void iio_buffer_demux_free(struct iio_buffer *buffer)
 }
 
 
-int iio_push_to_buffers(struct iio_dev *indio_dev, unsigned char *data)
+int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data)
 {
 	int ret;
 	struct iio_buffer *buf;
diff --git a/drivers/iio/kfifo_buf.c b/drivers/iio/kfifo_buf.c
index 1bea41bcbdc6..538d4616e48f 100644
--- a/drivers/iio/kfifo_buf.c
+++ b/drivers/iio/kfifo_buf.c
@@ -95,7 +95,7 @@ static int iio_set_length_kfifo(struct iio_buffer *r, int length)
 }
 
 static int iio_store_to_kfifo(struct iio_buffer *r,
-			      u8 *data)
+			      const void *data)
 {
 	int ret;
 	struct iio_kfifo *kf = iio_to_kfifo(r);
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index 2bac0eb8948d..e5507e999ed1 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -36,7 +36,7 @@ struct iio_buffer;
  * any of them not existing.
  **/
 struct iio_buffer_access_funcs {
-	int (*store_to)(struct iio_buffer *buffer, u8 *data);
+	int (*store_to)(struct iio_buffer *buffer, const void *data);
 	int (*read_first_n)(struct iio_buffer *buffer,
 			    size_t n,
 			    char __user *buf);
@@ -81,7 +81,7 @@ struct iio_buffer {
 	bool					stufftoread;
 	const struct attribute_group *attrs;
 	struct list_head			demux_list;
-	unsigned char				*demux_bounce;
+	void					*demux_bounce;
 	struct list_head			buffer_list;
 };
 
@@ -120,7 +120,7 @@ int iio_scan_mask_set(struct iio_dev *indio_dev,
  * @indio_dev:		iio_dev structure for device.
  * @data:		Full scan.
  */
-int iio_push_to_buffers(struct iio_dev *indio_dev, unsigned char *data);
+int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data);
 
 int iio_update_demux(struct iio_dev *indio_dev);
 
diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index 833926c91aa8..2752b1fd12be 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -77,7 +77,7 @@ struct iio_cb_buffer;
  * fail.
  */
 struct iio_cb_buffer *iio_channel_get_all_cb(struct device *dev,
-					     int (*cb)(u8 *data,
+					     int (*cb)(const void *data,
 						       void *private),
 					     void *private);
 /**
-- 
cgit 


From 0736cfa8e5bb7ee1d7b7d28aabe634fd3f85cb92 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 26 Aug 2013 21:40:51 -0700
Subject: Bluetooth: Introduce user channel flag for HCI devices

This patch introduces a new user channel flag that allows to give full
control of a HCI device to a user application. The kernel will stay away
from the device and does not allow any further modifications of the
device states.

The existing raw flag is not used since it has a bit of unclear meaning
due to its legacy. Using a new flag makes the code clearer.

A device with the user channel flag set can still be enumerate using the
legacy API, but it does not longer enumerate using the new management
interface used by BlueZ 5 and beyond. This is intentional to not confuse
users of modern systems.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/hci_core.c    | 39 ++++++++++++++++++++++++++++++++++++---
 net/bluetooth/hci_sock.c    | 15 +++++++++------
 net/bluetooth/mgmt.c        |  9 +++++++++
 4 files changed, 55 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index aaeaf0938ec0..128157db0680 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -109,6 +109,7 @@ enum {
 	HCI_SERVICE_CACHE,
 	HCI_DEBUG_KEYS,
 	HCI_UNREGISTER,
+	HCI_USER_CHANNEL,
 
 	HCI_LE_SCAN,
 	HCI_SSP_ENABLED,
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 0976eabdafb0..0ee0f01d33df 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -984,6 +984,11 @@ int hci_inquiry(void __user *arg)
 	if (!hdev)
 		return -ENODEV;
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		err = -EBUSY;
+		goto done;
+	}
+
 	hci_dev_lock(hdev);
 	if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX ||
 	    inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) {
@@ -1177,7 +1182,8 @@ int hci_dev_open(__u16 dev)
 		if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
 			set_bit(HCI_RAW, &hdev->flags);
 
-		if (!test_bit(HCI_RAW, &hdev->flags))
+		if (!test_bit(HCI_RAW, &hdev->flags) &&
+		    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
 			ret = __hci_init(hdev);
 	}
 
@@ -1188,6 +1194,7 @@ int hci_dev_open(__u16 dev)
 		set_bit(HCI_UP, &hdev->flags);
 		hci_notify(hdev, HCI_DEV_UP);
 		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
+		    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
 		    mgmt_valid_hdev(hdev)) {
 			hci_dev_lock(hdev);
 			mgmt_powered(hdev, 1);
@@ -1324,11 +1331,17 @@ int hci_dev_close(__u16 dev)
 	if (!hdev)
 		return -ENODEV;
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		err = -EBUSY;
+		goto done;
+	}
+
 	if (test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags))
 		cancel_delayed_work(&hdev->power_off);
 
 	err = hci_dev_do_close(hdev);
 
+done:
 	hci_dev_put(hdev);
 	return err;
 }
@@ -1349,6 +1362,11 @@ int hci_dev_reset(__u16 dev)
 		goto done;
 	}
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		ret = -EBUSY;
+		goto done;
+	}
+
 	/* Drop queues */
 	skb_queue_purge(&hdev->rx_q);
 	skb_queue_purge(&hdev->cmd_q);
@@ -1382,10 +1400,15 @@ int hci_dev_reset_stat(__u16 dev)
 	if (!hdev)
 		return -ENODEV;
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		ret = -EBUSY;
+		goto done;
+	}
+
 	memset(&hdev->stat, 0, sizeof(struct hci_dev_stats));
 
+done:
 	hci_dev_put(hdev);
-
 	return ret;
 }
 
@@ -1402,6 +1425,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 	if (!hdev)
 		return -ENODEV;
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+		err = -EBUSY;
+		goto done;
+	}
+
 	switch (cmd) {
 	case HCISETAUTH:
 		err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt,
@@ -1460,6 +1488,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 		break;
 	}
 
+done:
 	hci_dev_put(hdev);
 	return err;
 }
@@ -1568,6 +1597,9 @@ static int hci_rfkill_set_block(void *data, bool blocked)
 
 	BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked);
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+		return -EBUSY;
+
 	if (!blocked)
 		return 0;
 
@@ -3459,7 +3491,8 @@ static void hci_rx_work(struct work_struct *work)
 			hci_send_to_sock(hdev, skb);
 		}
 
-		if (test_bit(HCI_RAW, &hdev->flags)) {
+		if (test_bit(HCI_RAW, &hdev->flags) ||
+		    test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
 			kfree_skb(skb);
 			continue;
 		}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index ab570387f505..59e68f199178 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -500,6 +500,9 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 	if (!hdev)
 		return -EBADFD;
 
+	if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags))
+		return -EBUSY;
+
 	switch (cmd) {
 	case HCISETRAW:
 		if (!capable(CAP_NET_ADMIN))
@@ -530,19 +533,19 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 		return hci_sock_blacklist_del(hdev, (void __user *) arg);
-
-	default:
-		if (hdev->ioctl)
-			return hdev->ioctl(hdev, cmd, arg);
-		return -EINVAL;
 	}
+
+	if (hdev->ioctl)
+		return hdev->ioctl(hdev, cmd, arg);
+
+	return -EINVAL;
 }
 
 static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,
 			  unsigned long arg)
 {
-	struct sock *sk = sock->sk;
 	void __user *argp = (void __user *) arg;
+	struct sock *sk = sock->sk;
 	int err;
 
 	BT_DBG("cmd %x arg %lx", cmd, arg);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index fedc5399d465..3070e772db6b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -339,6 +339,9 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 		if (test_bit(HCI_SETUP, &d->dev_flags))
 			continue;
 
+		if (test_bit(HCI_USER_CHANNEL, &d->dev_flags))
+			continue;
+
 		if (!mgmt_valid_hdev(d))
 			continue;
 
@@ -3320,6 +3323,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen)
 					 MGMT_STATUS_INVALID_INDEX);
 			goto done;
 		}
+
+		if (test_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+			err = cmd_status(sk, index, opcode,
+					 MGMT_STATUS_INVALID_INDEX);
+			goto done;
+		}
 	}
 
 	if (opcode >= ARRAY_SIZE(mgmt_handlers) ||
-- 
cgit 


From 23500189d7e03a071f0746f43f2cce875a62c91c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 26 Aug 2013 21:40:52 -0700
Subject: Bluetooth: Introduce new HCI socket channel for user operation

This patch introcuces a new HCI socket channel that allows user
applications to take control over a specific HCI device. The application
gains exclusive access to this device and forces the kernel to stay away
and not manage it. In case of the management interface it will actually
hide the device.

Such operation is useful for security testing tools that need to operate
underneath the Bluetooth stack and need full control over a device. The
advantage here is that the kernel still provides the service of hardware
abstraction and HCI level access. The use of Bluetooth drivers for
hardware access also means that sniffing tools like btmon or hcidump
are still working and the whole set of transaction can be traced with
existing tools.

With the new channel it is possible to send HCI commands, ACL and SCO
data packets and receive HCI events, ACL and SCO packets from the
device. The format follows the well established H:4 protocol.

The new HCI user channel can only be established when a device has been
through its setup routine and is currently powered down. This is
enforced to not cause any problems with current operations. In addition
only one user channel per HCI device is allowed. It is exclusive access
for one user application. Access to this channel is limited to process
with CAP_NET_RAW capability.

Using this new facility does not require any external library or special
ioctl or socket filters. Just create the socket and bind it. After that
the file descriptor is ready to speak H:4 protocol.

        struct sockaddr_hci addr;
        int fd;

        fd = socket(AF_BLUETOOTH, SOCK_RAW, BTPROTO_HCI);

        memset(&addr, 0, sizeof(addr));
        addr.hci_family = AF_BLUETOOTH;
        addr.hci_dev = 0;
        addr.hci_channel = HCI_CHANNEL_USER;

        bind(fd, (struct sockaddr *) &addr, sizeof(addr));

The example shows on how to create a user channel for hci0 device. Error
handling has been left out of the example. However with the limitations
mentioned above it is advised to handle errors. Binding of the user
cahnnel socket can fail for various reasons. Specifically if the device
is currently activated by BlueZ or if the access permissions are not
present.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/hci_sock.c    | 86 ++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 82 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 128157db0680..30c88b585c1b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1571,6 +1571,7 @@ struct sockaddr_hci {
 #define HCI_DEV_NONE	0xffff
 
 #define HCI_CHANNEL_RAW		0
+#define HCI_CHANNEL_USER	1
 #define HCI_CHANNEL_MONITOR	2
 #define HCI_CHANNEL_CONTROL	3
 
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 59e68f199178..c09e97638065 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -126,11 +126,20 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 		if (skb->sk == sk)
 			continue;
 
-		if (hci_pi(sk)->channel != HCI_CHANNEL_RAW)
-			continue;
-
-		if (is_filtered_packet(sk, skb))
+		if (hci_pi(sk)->channel == HCI_CHANNEL_RAW) {
+			if (is_filtered_packet(sk, skb))
+				continue;
+		} else if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+			if (!bt_cb(skb)->incoming)
+				continue;
+			if (bt_cb(skb)->pkt_type != HCI_EVENT_PKT &&
+			    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+			    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT)
+				continue;
+		} else {
+			/* Don't send frame to other channel types */
 			continue;
+		}
 
 		if (!skb_copy) {
 			/* Create a private copy with headroom */
@@ -444,6 +453,12 @@ static int hci_sock_release(struct socket *sock)
 	bt_sock_unlink(&hci_sk_list, sk);
 
 	if (hdev) {
+		if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+			mgmt_index_added(hdev);
+			clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+			hci_dev_close(hdev->id);
+		}
+
 		atomic_dec(&hdev->promisc);
 		hci_dev_put(hdev);
 	}
@@ -661,6 +676,56 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
 		hci_pi(sk)->hdev = hdev;
 		break;
 
+	case HCI_CHANNEL_USER:
+		if (hci_pi(sk)->hdev) {
+			err = -EALREADY;
+			goto done;
+		}
+
+		if (haddr.hci_dev == HCI_DEV_NONE) {
+			err = -EINVAL;
+			goto done;
+		}
+
+		if (!capable(CAP_NET_RAW)) {
+			err = -EPERM;
+			goto done;
+		}
+
+		hdev = hci_dev_get(haddr.hci_dev);
+		if (!hdev) {
+			err = -ENODEV;
+			goto done;
+		}
+
+		if (test_bit(HCI_UP, &hdev->flags) ||
+		    test_bit(HCI_INIT, &hdev->flags) ||
+		    test_bit(HCI_SETUP, &hdev->dev_flags)) {
+			err = -EBUSY;
+			hci_dev_put(hdev);
+			goto done;
+		}
+
+		if (test_and_set_bit(HCI_USER_CHANNEL, &hdev->dev_flags)) {
+			err = -EUSERS;
+			hci_dev_put(hdev);
+			goto done;
+		}
+
+		mgmt_index_removed(hdev);
+
+		err = hci_dev_open(hdev->id);
+		if (err) {
+			clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags);
+			hci_dev_put(hdev);
+			goto done;
+		}
+
+		atomic_inc(&hdev->promisc);
+
+		hci_pi(sk)->hdev = hdev;
+		break;
+
 	case HCI_CHANNEL_CONTROL:
 		if (haddr.hci_dev != HCI_DEV_NONE) {
 			err = -EINVAL;
@@ -807,6 +872,7 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	case HCI_CHANNEL_RAW:
 		hci_sock_cmsg(sk, msg, skb);
 		break;
+	case HCI_CHANNEL_USER:
 	case HCI_CHANNEL_CONTROL:
 	case HCI_CHANNEL_MONITOR:
 		sock_recv_timestamp(msg, sk, skb);
@@ -841,6 +907,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	switch (hci_pi(sk)->channel) {
 	case HCI_CHANNEL_RAW:
+	case HCI_CHANNEL_USER:
 		break;
 	case HCI_CHANNEL_CONTROL:
 		err = mgmt_control(sk, msg, len);
@@ -877,7 +944,8 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	skb_pull(skb, 1);
 	skb->dev = (void *) hdev;
 
-	if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
+	if (hci_pi(sk)->channel == HCI_CHANNEL_RAW &&
+	    bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
 		u16 opcode = get_unaligned_le16(skb->data);
 		u16 ogf = hci_opcode_ogf(opcode);
 		u16 ocf = hci_opcode_ocf(opcode);
@@ -908,6 +976,14 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 			goto drop;
 		}
 
+		if (hci_pi(sk)->channel == HCI_CHANNEL_USER &&
+		    bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+			err = -EINVAL;
+			goto drop;
+		}
+
 		skb_queue_tail(&hdev->raw_q, skb);
 		queue_work(hdev->workqueue, &hdev->tx_work);
 	}
-- 
cgit 


From 5ce0ba88650f2606244a761d92e2b725f4ab3583 Mon Sep 17 00:00:00 2001
From: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Date: Tue, 3 Sep 2013 13:10:26 +0900
Subject: spi: rcar: add Renesas QSPI support on RSPI

The R8A7790 has QSPI module which is very similar to RSPI.
This patch adds into RSPI module together to supports QSPI module.

Signed-off-by: Hiep Cao Minh <cm-hiep@jinso.co.jp>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/Kconfig      |   2 +-
 drivers/spi/spi-rspi.c   | 183 ++++++++++++++++++++++++++++++++++++-----------
 include/linux/spi/rspi.h |   2 +
 3 files changed, 145 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index b9c53cc40e1f..738facf90597 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -369,7 +369,7 @@ config SPI_PXA2XX_PCI
 
 config SPI_RSPI
 	tristate "Renesas RSPI controller"
-	depends on SUPERH && SH_DMAE_BASE
+	depends on (SUPERH || ARCH_SHMOBILE) && SH_DMAE_BASE
 	help
 	  SPI driver for Renesas RSPI blocks.
 
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 8719206a03a0..4c8dbac11b42 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -59,6 +59,14 @@
 #define RSPI_SPCMD6		0x1c
 #define RSPI_SPCMD7		0x1e
 
+/*qspi only */
+#define QSPI_SPBFCR		0x18
+#define QSPI_SPBDCR		0x1a
+#define QSPI_SPBMUL0		0x1c
+#define QSPI_SPBMUL1		0x20
+#define QSPI_SPBMUL2		0x24
+#define QSPI_SPBMUL3		0x28
+
 /* SPCR */
 #define SPCR_SPRIE		0x80
 #define SPCR_SPE		0x40
@@ -126,6 +134,8 @@
 #define SPCMD_LSBF		0x1000
 #define SPCMD_SPB_MASK		0x0f00
 #define SPCMD_SPB_8_TO_16(bit)	(((bit - 1) << 8) & SPCMD_SPB_MASK)
+#define SPCMD_SPB_8BIT		0x0000	/* qspi only */
+#define SPCMD_SPB_16BIT		0x0100
 #define SPCMD_SPB_20BIT		0x0000
 #define SPCMD_SPB_24BIT		0x0100
 #define SPCMD_SPB_32BIT		0x0200
@@ -135,6 +145,10 @@
 #define SPCMD_CPOL		0x0002
 #define SPCMD_CPHA		0x0001
 
+/* SPBFCR */
+#define SPBFCR_TXRST		0x80	/* qspi only */
+#define SPBFCR_RXRST		0x40	/* qspi only */
+
 struct rspi_data {
 	void __iomem *addr;
 	u32 max_speed_hz;
@@ -145,6 +159,7 @@ struct rspi_data {
 	spinlock_t lock;
 	struct clk *clk;
 	unsigned char spsr;
+	const struct spi_ops *ops;
 
 	/* for dmaengine */
 	struct dma_chan *chan_tx;
@@ -165,6 +180,11 @@ static void rspi_write16(struct rspi_data *rspi, u16 data, u16 offset)
 	iowrite16(data, rspi->addr + offset);
 }
 
+static void rspi_write32(struct rspi_data *rspi, u32 data, u16 offset)
+{
+	iowrite32(data, rspi->addr + offset);
+}
+
 static u8 rspi_read8(struct rspi_data *rspi, u16 offset)
 {
 	return ioread8(rspi->addr + offset);
@@ -175,17 +195,98 @@ static u16 rspi_read16(struct rspi_data *rspi, u16 offset)
 	return ioread16(rspi->addr + offset);
 }
 
-static unsigned char rspi_calc_spbr(struct rspi_data *rspi)
+/* optional functions */
+struct spi_ops {
+	int (*set_config_register)(struct rspi_data *rspi, int access_size);
+};
+
+/*
+ * functions for RSPI
+ */
+static int rspi_set_config_register(struct rspi_data *rspi, int access_size)
 {
-	int tmp;
-	unsigned char spbr;
+	int spbr;
+
+	/* Sets output mode(CMOS) and MOSI signal(from previous transfer) */
+	rspi_write8(rspi, 0x00, RSPI_SPPCR);
 
-	tmp = clk_get_rate(rspi->clk) / (2 * rspi->max_speed_hz) - 1;
-	spbr = clamp(tmp, 0, 255);
+	/* Sets transfer bit rate */
+	spbr = clk_get_rate(rspi->clk) / (2 * rspi->max_speed_hz) - 1;
+	rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR);
+
+	/* Sets number of frames to be used: 1 frame */
+	rspi_write8(rspi, 0x00, RSPI_SPDCR);
 
-	return spbr;
+	/* Sets RSPCK, SSL, next-access delay value */
+	rspi_write8(rspi, 0x00, RSPI_SPCKD);
+	rspi_write8(rspi, 0x00, RSPI_SSLND);
+	rspi_write8(rspi, 0x00, RSPI_SPND);
+
+	/* Sets parity, interrupt mask */
+	rspi_write8(rspi, 0x00, RSPI_SPCR2);
+
+	/* Sets SPCMD */
+	rspi_write16(rspi, SPCMD_SPB_8_TO_16(access_size) | SPCMD_SSLKP,
+		     RSPI_SPCMD0);
+
+	/* Sets RSPI mode */
+	rspi_write8(rspi, SPCR_MSTR, RSPI_SPCR);
+
+	return 0;
 }
 
+/*
+ * functions for QSPI
+ */
+static int qspi_set_config_register(struct rspi_data *rspi, int access_size)
+{
+	u16 spcmd;
+	int spbr;
+
+	/* Sets output mode(CMOS) and MOSI signal(from previous transfer) */
+	rspi_write8(rspi, 0x00, RSPI_SPPCR);
+
+	/* Sets transfer bit rate */
+	spbr = clk_get_rate(rspi->clk) / (2 * rspi->max_speed_hz);
+	rspi_write8(rspi, clamp(spbr, 0, 255), RSPI_SPBR);
+
+	/* Sets number of frames to be used: 1 frame */
+	rspi_write8(rspi, 0x00, RSPI_SPDCR);
+
+	/* Sets RSPCK, SSL, next-access delay value */
+	rspi_write8(rspi, 0x00, RSPI_SPCKD);
+	rspi_write8(rspi, 0x00, RSPI_SSLND);
+	rspi_write8(rspi, 0x00, RSPI_SPND);
+
+	/* Data Length Setting */
+	if (access_size == 8)
+		spcmd = SPCMD_SPB_8BIT;
+	else if (access_size == 16)
+		spcmd = SPCMD_SPB_16BIT;
+	else if (access_size == 32)
+		spcmd = SPCMD_SPB_32BIT;
+
+	spcmd |= SPCMD_SCKDEN | SPCMD_SLNDEN | SPCMD_SSLKP | SPCMD_SPNDEN;
+
+	/* Resets transfer data length */
+	rspi_write32(rspi, 0, QSPI_SPBMUL0);
+
+	/* Resets transmit and receive buffer */
+	rspi_write8(rspi, SPBFCR_TXRST | SPBFCR_RXRST, QSPI_SPBFCR);
+	/* Sets buffer to allow normal operation */
+	rspi_write8(rspi, 0x00, QSPI_SPBFCR);
+
+	/* Sets SPCMD */
+	rspi_write16(rspi, spcmd, RSPI_SPCMD0);
+
+	/* Enables SPI function in a master mode */
+	rspi_write8(rspi, SPCR_SPE | SPCR_MSTR, RSPI_SPCR);
+
+	return 0;
+}
+
+#define set_config_register(spi, n) spi->ops->set_config_register(spi, n)
+
 static void rspi_enable_irq(struct rspi_data *rspi, u8 enable)
 {
 	rspi_write8(rspi, rspi_read8(rspi, RSPI_SPCR) | enable, RSPI_SPCR);
@@ -220,35 +321,6 @@ static void rspi_negate_ssl(struct rspi_data *rspi)
 	rspi_write8(rspi, rspi_read8(rspi, RSPI_SPCR) & ~SPCR_SPE, RSPI_SPCR);
 }
 
-static int rspi_set_config_register(struct rspi_data *rspi, int access_size)
-{
-	/* Sets output mode(CMOS) and MOSI signal(from previous transfer) */
-	rspi_write8(rspi, 0x00, RSPI_SPPCR);
-
-	/* Sets transfer bit rate */
-	rspi_write8(rspi, rspi_calc_spbr(rspi), RSPI_SPBR);
-
-	/* Sets number of frames to be used: 1 frame */
-	rspi_write8(rspi, 0x00, RSPI_SPDCR);
-
-	/* Sets RSPCK, SSL, next-access delay value */
-	rspi_write8(rspi, 0x00, RSPI_SPCKD);
-	rspi_write8(rspi, 0x00, RSPI_SSLND);
-	rspi_write8(rspi, 0x00, RSPI_SPND);
-
-	/* Sets parity, interrupt mask */
-	rspi_write8(rspi, 0x00, RSPI_SPCR2);
-
-	/* Sets SPCMD */
-	rspi_write16(rspi, SPCMD_SPB_8_TO_16(access_size) | SPCMD_SSLKP,
-		     RSPI_SPCMD0);
-
-	/* Sets RSPI mode */
-	rspi_write8(rspi, SPCR_MSTR, RSPI_SPCR);
-
-	return 0;
-}
-
 static int rspi_send_pio(struct rspi_data *rspi, struct spi_message *mesg,
 			 struct spi_transfer *t)
 {
@@ -616,7 +688,7 @@ static int rspi_setup(struct spi_device *spi)
 		spi->bits_per_word = 8;
 	rspi->max_speed_hz = spi->max_speed_hz;
 
-	rspi_set_config_register(rspi, 8);
+	set_config_register(rspi, 8);
 
 	return 0;
 }
@@ -745,7 +817,16 @@ static int rspi_probe(struct platform_device *pdev)
 	struct rspi_data *rspi;
 	int ret, irq;
 	char clk_name[16];
-
+	struct rspi_plat_data *rspi_pd = pdev->dev.platform_data;
+	const struct spi_ops *ops;
+	const struct platform_device_id *id_entry = pdev->id_entry;
+
+	ops = (struct spi_ops *)id_entry->driver_data;
+	/* ops parameter check */
+	if (!ops->set_config_register) {
+		dev_err(&pdev->dev, "there is no set_config_register\n");
+		return -ENODEV;
+	}
 	/* get base addr */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (unlikely(res == NULL)) {
@@ -767,7 +848,7 @@ static int rspi_probe(struct platform_device *pdev)
 
 	rspi = spi_master_get_devdata(master);
 	platform_set_drvdata(pdev, rspi);
-
+	rspi->ops = ops;
 	rspi->master = master;
 	rspi->addr = ioremap(res->start, resource_size(res));
 	if (rspi->addr == NULL) {
@@ -776,7 +857,7 @@ static int rspi_probe(struct platform_device *pdev)
 		goto error1;
 	}
 
-	snprintf(clk_name, sizeof(clk_name), "rspi%d", pdev->id);
+	snprintf(clk_name, sizeof(clk_name), "%s%d", id_entry->name, pdev->id);
 	rspi->clk = clk_get(&pdev->dev, clk_name);
 	if (IS_ERR(rspi->clk)) {
 		dev_err(&pdev->dev, "cannot get clock\n");
@@ -790,7 +871,10 @@ static int rspi_probe(struct platform_device *pdev)
 	INIT_WORK(&rspi->ws, rspi_work);
 	init_waitqueue_head(&rspi->wait);
 
-	master->num_chipselect = 2;
+	master->num_chipselect = rspi_pd->num_chipselect;
+	if (!master->num_chipselect)
+		master->num_chipselect = 2; /* default */
+
 	master->bus_num = pdev->id;
 	master->setup = rspi_setup;
 	master->transfer = rspi_transfer;
@@ -832,11 +916,28 @@ error1:
 	return ret;
 }
 
+static struct spi_ops rspi_ops = {
+	.set_config_register =		rspi_set_config_register,
+};
+
+static struct spi_ops qspi_ops = {
+	.set_config_register =		qspi_set_config_register,
+};
+
+static struct platform_device_id spi_driver_ids[] = {
+	{ "rspi",	(kernel_ulong_t)&rspi_ops },
+	{ "qspi",	(kernel_ulong_t)&qspi_ops },
+	{},
+};
+
+MODULE_DEVICE_TABLE(platform, spi_driver_ids);
+
 static struct platform_driver rspi_driver = {
 	.probe =	rspi_probe,
 	.remove =	rspi_remove,
+	.id_table =	spi_driver_ids,
 	.driver		= {
-		.name = "rspi",
+		.name = "renesas_spi",
 		.owner	= THIS_MODULE,
 	},
 };
diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h
index 900f0e328235..a25bd6f65e7f 100644
--- a/include/linux/spi/rspi.h
+++ b/include/linux/spi/rspi.h
@@ -26,6 +26,8 @@ struct rspi_plat_data {
 	unsigned int dma_rx_id;
 
 	unsigned dma_width_16bit:1;	/* DMAC read/write width = 16-bit */
+
+	u16 num_chipselect;
 };
 
 #endif
-- 
cgit 


From b33e46bcdc4e598d738ed12a5a7906be4e11d786 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Sat, 31 Aug 2013 11:58:26 +0100
Subject: regulator: core: Provide managed regulator registration

Many regulator drivers have a remove function that consists solely of
calling regulator_unregister() so provide a devm_regulator_register()
in order to allow this repeated code to be removed and help eliminate
error handling code.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 Documentation/driver-model/devres.txt |  1 +
 drivers/regulator/core.c              | 66 +++++++++++++++++++++++++++++++++++
 include/linux/regulator/driver.h      |  5 +++
 3 files changed, 72 insertions(+)

(limited to 'include')

diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index fcb34a5697ea..3d9c2a766230 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -283,6 +283,7 @@ REGULATOR
   devm_regulator_get()
   devm_regulator_put()
   devm_regulator_bulk_get()
+  devm_regulator_register()
 
 CLOCK
   devm_clk_get()
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a01b8b3b70ca..5f995d281672 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -3492,6 +3492,44 @@ clean:
 }
 EXPORT_SYMBOL_GPL(regulator_register);
 
+static void devm_rdev_release(struct device *dev, void *res)
+{
+	regulator_unregister(*(struct regulator_dev **)res);
+}
+
+/**
+ * devm_regulator_register - Resource managed regulator_register()
+ * @regulator_desc: regulator to register
+ * @config: runtime configuration for regulator
+ *
+ * Called by regulator drivers to register a regulator.  Returns a
+ * valid pointer to struct regulator_dev on success or an ERR_PTR() on
+ * error.  The regulator will automaticall be released when the device
+ * is unbound.
+ */
+struct regulator_dev *devm_regulator_register(struct device *dev,
+				  const struct regulator_desc *regulator_desc,
+				  const struct regulator_config *config)
+{
+	struct regulator_dev **ptr, *rdev;
+
+	ptr = devres_alloc(devm_rdev_release, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	rdev = regulator_register(regulator_desc, config);
+	if (!IS_ERR(rdev)) {
+		*ptr = rdev;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return rdev;
+}
+EXPORT_SYMBOL_GPL(devm_regulator_register);
+
 /**
  * regulator_unregister - unregister regulator
  * @rdev: regulator to unregister
@@ -3521,6 +3559,34 @@ void regulator_unregister(struct regulator_dev *rdev)
 }
 EXPORT_SYMBOL_GPL(regulator_unregister);
 
+static int devm_rdev_match(struct device *dev, void *res, void *data)
+{
+	struct regulator_dev **r = res;
+	if (!r || !*r) {
+		WARN_ON(!r || !*r);
+		return 0;
+	}
+	return *r == data;
+}
+
+/**
+ * devm_regulator_unregister - Resource managed regulator_unregister()
+ * @regulator: regulator to free
+ *
+ * Unregister a regulator registered with devm_regulator_register().
+ * Normally this function will not need to be called and the resource
+ * management code will ensure that the resource is freed.
+ */
+void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev)
+{
+	int rc;
+
+	rc = devres_release(dev, devm_rdev_release, devm_rdev_match, rdev);
+	if (rc != 0)
+		WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_regulator_unregister);
+
 /**
  * regulator_suspend_prepare - prepare regulators for system wide suspend
  * @state: system suspend state
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 67e13aa5a478..8474c7f88745 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -334,7 +334,12 @@ struct regulator_dev {
 struct regulator_dev *
 regulator_register(const struct regulator_desc *regulator_desc,
 		   const struct regulator_config *config);
+struct regulator_dev *
+devm_regulator_register(struct device *dev,
+			const struct regulator_desc *regulator_desc,
+			const struct regulator_config *config);
 void regulator_unregister(struct regulator_dev *rdev);
+void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev);
 
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data);
-- 
cgit 


From 4f0ac6dabf867095b31f851ba0d0ceaca2f87e2e Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Fri, 13 Sep 2013 19:51:47 +0100
Subject: regulator: core: Remove unused regulator_use_dummy_regulator()

No boards have used this functionality and the new default of providing
dummy regulators by default provides a better solution to the problem it
was trying to solve.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c          | 17 -----------------
 include/linux/regulator/machine.h |  5 -----
 2 files changed, 22 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 8fd170788c3e..ac3a864d3635 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -53,7 +53,6 @@ static LIST_HEAD(regulator_list);
 static LIST_HEAD(regulator_map_list);
 static LIST_HEAD(regulator_ena_gpio_list);
 static bool has_full_constraints;
-static bool board_wants_dummy_regulator;
 
 static struct dentry *debugfs_root;
 
@@ -3615,22 +3614,6 @@ void regulator_has_full_constraints(void)
 }
 EXPORT_SYMBOL_GPL(regulator_has_full_constraints);
 
-/**
- * regulator_use_dummy_regulator - Provide a dummy regulator when none is found
- *
- * Calling this function will cause the regulator API to provide a
- * dummy regulator to consumers if no physical regulator is found,
- * allowing most consumers to proceed as though a regulator were
- * configured.  This allows systems such as those with software
- * controllable regulators for the CPU core only to be brought up more
- * readily.
- */
-void regulator_use_dummy_regulator(void)
-{
-	board_wants_dummy_regulator = true;
-}
-EXPORT_SYMBOL_GPL(regulator_use_dummy_regulator);
-
 /**
  * rdev_get_drvdata - get rdev regulator driver data
  * @rdev: regulator
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 999b20ce06cf..a9f7c55a4d4d 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -193,15 +193,10 @@ int regulator_suspend_finish(void);
 
 #ifdef CONFIG_REGULATOR
 void regulator_has_full_constraints(void);
-void regulator_use_dummy_regulator(void);
 #else
 static inline void regulator_has_full_constraints(void)
 {
 }
-
-static inline void regulator_use_dummy_regulator(void)
-{
-}
 #endif
 
 #endif
-- 
cgit 


From 666d5b4c742ba666eb68b467d777b7862f362ae5 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Sat, 31 Aug 2013 18:50:52 +0100
Subject: spi: core: Add devm_spi_register_master()

Help simplify the cleanup code for SPI master drivers by providing a
managed master registration function, ensuring that the master is
automatically unregistered whenever the device is unbound.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 Documentation/driver-model/devres.txt |  3 +++
 drivers/spi/spi.c                     | 35 +++++++++++++++++++++++++++++++++++
 include/linux/spi/spi.h               |  2 ++
 3 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index fcb34a5697ea..84ea8216cc7d 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -302,3 +302,6 @@ PHY
 
 SLAVE DMA ENGINE
   devm_acpi_dma_controller_register()
+
+SPI
+  devm_spi_register_master()
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 9e039c60c068..a586ceb111fc 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1245,6 +1245,41 @@ done:
 }
 EXPORT_SYMBOL_GPL(spi_register_master);
 
+static void devm_spi_unregister(struct device *dev, void *res)
+{
+	spi_unregister_master(*(struct spi_master **)res);
+}
+
+/**
+ * dev_spi_register_master - register managed SPI master controller
+ * @dev:    device managing SPI master
+ * @master: initialized master, originally from spi_alloc_master()
+ * Context: can sleep
+ *
+ * Register a SPI device as with spi_register_master() which will
+ * automatically be unregister
+ */
+int devm_spi_register_master(struct device *dev, struct spi_master *master)
+{
+	struct spi_master **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_spi_unregister, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = spi_register_master(master);
+	if (ret != 0) {
+		*ptr = master;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_spi_register_master);
+
 static int __unregister(struct device *dev, void *null)
 {
 	spi_unregister_device(to_spi_device(dev));
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 887116dbce2c..4d634d66ba0b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -434,6 +434,8 @@ extern struct spi_master *
 spi_alloc_master(struct device *host, unsigned size);
 
 extern int spi_register_master(struct spi_master *master);
+extern int devm_spi_register_master(struct device *dev,
+				    struct spi_master *master);
 extern void spi_unregister_master(struct spi_master *master);
 
 extern struct spi_master *spi_busnum_to_master(u16 busnum);
-- 
cgit 


From 4b08478422040ae8cb11acc15d51f1cdb0ac39c8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 30 Aug 2013 06:01:49 -0700
Subject: Drop support for Renesas H8/300 (h8300) architecture

H8/300 has been dead for several years, and the kernel for it
has not compiled for ages. Drop support for it.

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/scheduler/sched-arch.txt           |   5 -
 arch/h8300/Kconfig                               | 108 ------
 arch/h8300/Kconfig.cpu                           | 171 ---------
 arch/h8300/Kconfig.debug                         |  68 ----
 arch/h8300/Kconfig.ide                           |  44 ---
 arch/h8300/Makefile                              |  71 ----
 arch/h8300/README                                |  38 --
 arch/h8300/boot/Makefile                         |  22 --
 arch/h8300/boot/compressed/Makefile              |  37 --
 arch/h8300/boot/compressed/head.S                |  47 ---
 arch/h8300/boot/compressed/misc.c                | 180 ---------
 arch/h8300/boot/compressed/vmlinux.lds           |  32 --
 arch/h8300/boot/compressed/vmlinux.scr           |   9 -
 arch/h8300/defconfig                             |  42 ---
 arch/h8300/include/asm/Kbuild                    |   8 -
 arch/h8300/include/asm/asm-offsets.h             |   1 -
 arch/h8300/include/asm/atomic.h                  | 146 --------
 arch/h8300/include/asm/barrier.h                 |  29 --
 arch/h8300/include/asm/bitops.h                  | 211 -----------
 arch/h8300/include/asm/bootinfo.h                |   2 -
 arch/h8300/include/asm/bug.h                     |  12 -
 arch/h8300/include/asm/bugs.h                    |  16 -
 arch/h8300/include/asm/cache.h                   |  13 -
 arch/h8300/include/asm/cachectl.h                |  14 -
 arch/h8300/include/asm/cacheflush.h              |  40 --
 arch/h8300/include/asm/checksum.h                | 102 ------
 arch/h8300/include/asm/cmpxchg.h                 |  60 ---
 arch/h8300/include/asm/cputime.h                 |   6 -
 arch/h8300/include/asm/current.h                 |  25 --
 arch/h8300/include/asm/dbg.h                     |   2 -
 arch/h8300/include/asm/delay.h                   |  38 --
 arch/h8300/include/asm/device.h                  |   7 -
 arch/h8300/include/asm/div64.h                   |   1 -
 arch/h8300/include/asm/dma.h                     |  15 -
 arch/h8300/include/asm/elf.h                     | 101 ------
 arch/h8300/include/asm/emergency-restart.h       |   6 -
 arch/h8300/include/asm/fb.h                      |  12 -
 arch/h8300/include/asm/flat.h                    |  26 --
 arch/h8300/include/asm/fpu.h                     |   1 -
 arch/h8300/include/asm/ftrace.h                  |   1 -
 arch/h8300/include/asm/futex.h                   |   6 -
 arch/h8300/include/asm/gpio-internal.h           |  52 ---
 arch/h8300/include/asm/hardirq.h                 |  19 -
 arch/h8300/include/asm/hw_irq.h                  |   1 -
 arch/h8300/include/asm/io.h                      | 358 ------------------
 arch/h8300/include/asm/irq.h                     |  49 ---
 arch/h8300/include/asm/irq_regs.h                |   1 -
 arch/h8300/include/asm/irqflags.h                |  43 ---
 arch/h8300/include/asm/kdebug.h                  |   1 -
 arch/h8300/include/asm/kmap_types.h              |   6 -
 arch/h8300/include/asm/local.h                   |   6 -
 arch/h8300/include/asm/local64.h                 |   1 -
 arch/h8300/include/asm/mc146818rtc.h             |   9 -
 arch/h8300/include/asm/mmu_context.h             |  32 --
 arch/h8300/include/asm/mutex.h                   |   9 -
 arch/h8300/include/asm/page.h                    |  78 ----
 arch/h8300/include/asm/page_offset.h             |   3 -
 arch/h8300/include/asm/param.h                   |   9 -
 arch/h8300/include/asm/pci.h                     |  19 -
 arch/h8300/include/asm/percpu.h                  |   6 -
 arch/h8300/include/asm/pgalloc.h                 |   8 -
 arch/h8300/include/asm/pgtable.h                 |  73 ----
 arch/h8300/include/asm/processor.h               | 139 -------
 arch/h8300/include/asm/ptrace.h                  |  33 --
 arch/h8300/include/asm/regs267x.h                | 336 -----------------
 arch/h8300/include/asm/regs306x.h                | 212 -----------
 arch/h8300/include/asm/scatterlist.h             |   6 -
 arch/h8300/include/asm/sections.h                |   6 -
 arch/h8300/include/asm/segment.h                 |  49 ---
 arch/h8300/include/asm/sh_bios.h                 |  29 --
 arch/h8300/include/asm/shm.h                     |  31 --
 arch/h8300/include/asm/shmparam.h                |   6 -
 arch/h8300/include/asm/signal.h                  |  24 --
 arch/h8300/include/asm/smp.h                     |   1 -
 arch/h8300/include/asm/spinlock.h                |   6 -
 arch/h8300/include/asm/string.h                  |  44 ---
 arch/h8300/include/asm/switch_to.h               |  50 ---
 arch/h8300/include/asm/target_time.h             |   4 -
 arch/h8300/include/asm/termios.h                 |  50 ---
 arch/h8300/include/asm/thread_info.h             | 103 ------
 arch/h8300/include/asm/timer.h                   |  25 --
 arch/h8300/include/asm/timex.h                   |  19 -
 arch/h8300/include/asm/tlb.h                     |   8 -
 arch/h8300/include/asm/tlbflush.h                |  55 ---
 arch/h8300/include/asm/topology.h                |   6 -
 arch/h8300/include/asm/traps.h                   |  37 --
 arch/h8300/include/asm/types.h                   |   9 -
 arch/h8300/include/asm/uaccess.h                 | 163 ---------
 arch/h8300/include/asm/ucontext.h                |  12 -
 arch/h8300/include/asm/unaligned.h               |  11 -
 arch/h8300/include/asm/unistd.h                  |  36 --
 arch/h8300/include/asm/user.h                    |  75 ----
 arch/h8300/include/asm/virtconvert.h             |  20 -
 arch/h8300/include/uapi/asm/Kbuild               |  34 --
 arch/h8300/include/uapi/asm/auxvec.h             |   4 -
 arch/h8300/include/uapi/asm/bitsperlong.h        |   1 -
 arch/h8300/include/uapi/asm/byteorder.h          |   6 -
 arch/h8300/include/uapi/asm/errno.h              |   6 -
 arch/h8300/include/uapi/asm/fcntl.h              |  11 -
 arch/h8300/include/uapi/asm/ioctl.h              |   1 -
 arch/h8300/include/uapi/asm/ioctls.h             |   8 -
 arch/h8300/include/uapi/asm/ipcbuf.h             |   1 -
 arch/h8300/include/uapi/asm/kvm_para.h           |   1 -
 arch/h8300/include/uapi/asm/mman.h               |   1 -
 arch/h8300/include/uapi/asm/msgbuf.h             |  31 --
 arch/h8300/include/uapi/asm/param.h              |  16 -
 arch/h8300/include/uapi/asm/poll.h               |  11 -
 arch/h8300/include/uapi/asm/posix_types.h        |  26 --
 arch/h8300/include/uapi/asm/ptrace.h             |  44 ---
 arch/h8300/include/uapi/asm/resource.h           |   6 -
 arch/h8300/include/uapi/asm/sembuf.h             |  25 --
 arch/h8300/include/uapi/asm/setup.h              |   6 -
 arch/h8300/include/uapi/asm/shmbuf.h             |  42 ---
 arch/h8300/include/uapi/asm/sigcontext.h         |  18 -
 arch/h8300/include/uapi/asm/siginfo.h            |   6 -
 arch/h8300/include/uapi/asm/signal.h             | 115 ------
 arch/h8300/include/uapi/asm/socket.h             |  79 ----
 arch/h8300/include/uapi/asm/sockios.h            |  13 -
 arch/h8300/include/uapi/asm/stat.h               |  78 ----
 arch/h8300/include/uapi/asm/statfs.h             |   6 -
 arch/h8300/include/uapi/asm/swab.h               |  10 -
 arch/h8300/include/uapi/asm/termbits.h           | 201 ----------
 arch/h8300/include/uapi/asm/termios.h            |  44 ---
 arch/h8300/include/uapi/asm/types.h              |   1 -
 arch/h8300/include/uapi/asm/unistd.h             | 330 -----------------
 arch/h8300/kernel/Makefile                       |  12 -
 arch/h8300/kernel/asm-offsets.c                  |  60 ---
 arch/h8300/kernel/entry.S                        | 402 --------------------
 arch/h8300/kernel/gpio.c                         | 178 ---------
 arch/h8300/kernel/h8300_ksyms.c                  | 100 -----
 arch/h8300/kernel/irq.c                          | 165 ---------
 arch/h8300/kernel/module.c                       |  75 ----
 arch/h8300/kernel/process.c                      | 154 --------
 arch/h8300/kernel/ptrace.c                       | 168 ---------
 arch/h8300/kernel/setup.c                        | 242 ------------
 arch/h8300/kernel/signal.c                       | 444 -----------------------
 arch/h8300/kernel/sys_h8300.c                    |  48 ---
 arch/h8300/kernel/syscalls.S                     | 338 -----------------
 arch/h8300/kernel/time.c                         |  66 ----
 arch/h8300/kernel/timer/Makefile                 |   6 -
 arch/h8300/kernel/timer/itu.c                    |  82 -----
 arch/h8300/kernel/timer/timer16.c                |  77 ----
 arch/h8300/kernel/timer/timer8.c                 | 102 ------
 arch/h8300/kernel/timer/tpu.c                    | 100 -----
 arch/h8300/kernel/traps.c                        | 166 ---------
 arch/h8300/kernel/vmlinux.lds.S                  | 157 --------
 arch/h8300/lib/Makefile                          |   5 -
 arch/h8300/lib/abs.S                             |  21 --
 arch/h8300/lib/ashrdi3.c                         |  63 ----
 arch/h8300/lib/checksum.c                        | 164 ---------
 arch/h8300/lib/memcpy.S                          |  84 -----
 arch/h8300/lib/memset.S                          |  61 ----
 arch/h8300/lib/romfs.S                           |  57 ---
 arch/h8300/mm/Makefile                           |   5 -
 arch/h8300/mm/fault.c                            |  56 ---
 arch/h8300/mm/init.c                             | 155 --------
 arch/h8300/mm/kmap.c                             |  58 ---
 arch/h8300/mm/memory.c                           |  54 ---
 arch/h8300/platform/h8300h/Makefile              |   7 -
 arch/h8300/platform/h8300h/aki3068net/Makefile   |   5 -
 arch/h8300/platform/h8300h/aki3068net/crt0_ram.S | 110 ------
 arch/h8300/platform/h8300h/generic/Makefile      |   5 -
 arch/h8300/platform/h8300h/generic/crt0_ram.S    | 107 ------
 arch/h8300/platform/h8300h/generic/crt0_rom.S    | 122 -------
 arch/h8300/platform/h8300h/h8max/Makefile        |   5 -
 arch/h8300/platform/h8300h/h8max/crt0_ram.S      | 110 ------
 arch/h8300/platform/h8300h/irq.c                 |  82 -----
 arch/h8300/platform/h8300h/ptrace_h8300h.c       | 284 ---------------
 arch/h8300/platform/h8s/Makefile                 |   7 -
 arch/h8300/platform/h8s/edosk2674/Makefile       |   5 -
 arch/h8300/platform/h8s/edosk2674/crt0_ram.S     | 130 -------
 arch/h8300/platform/h8s/edosk2674/crt0_rom.S     | 186 ----------
 arch/h8300/platform/h8s/generic/Makefile         |   5 -
 arch/h8300/platform/h8s/generic/crt0_ram.S       | 127 -------
 arch/h8300/platform/h8s/generic/crt0_rom.S       | 128 -------
 arch/h8300/platform/h8s/irq.c                    | 104 ------
 arch/h8300/platform/h8s/ptrace_h8s.c             |  84 -----
 include/linux/serial_sci.h                       |   2 +-
 tools/testing/ktest/examples/crosstests.conf     |   6 -
 179 files changed, 1 insertion(+), 10890 deletions(-)
 delete mode 100644 arch/h8300/Kconfig
 delete mode 100644 arch/h8300/Kconfig.cpu
 delete mode 100644 arch/h8300/Kconfig.debug
 delete mode 100644 arch/h8300/Kconfig.ide
 delete mode 100644 arch/h8300/Makefile
 delete mode 100644 arch/h8300/README
 delete mode 100644 arch/h8300/boot/Makefile
 delete mode 100644 arch/h8300/boot/compressed/Makefile
 delete mode 100644 arch/h8300/boot/compressed/head.S
 delete mode 100644 arch/h8300/boot/compressed/misc.c
 delete mode 100644 arch/h8300/boot/compressed/vmlinux.lds
 delete mode 100644 arch/h8300/boot/compressed/vmlinux.scr
 delete mode 100644 arch/h8300/defconfig
 delete mode 100644 arch/h8300/include/asm/Kbuild
 delete mode 100644 arch/h8300/include/asm/asm-offsets.h
 delete mode 100644 arch/h8300/include/asm/atomic.h
 delete mode 100644 arch/h8300/include/asm/barrier.h
 delete mode 100644 arch/h8300/include/asm/bitops.h
 delete mode 100644 arch/h8300/include/asm/bootinfo.h
 delete mode 100644 arch/h8300/include/asm/bug.h
 delete mode 100644 arch/h8300/include/asm/bugs.h
 delete mode 100644 arch/h8300/include/asm/cache.h
 delete mode 100644 arch/h8300/include/asm/cachectl.h
 delete mode 100644 arch/h8300/include/asm/cacheflush.h
 delete mode 100644 arch/h8300/include/asm/checksum.h
 delete mode 100644 arch/h8300/include/asm/cmpxchg.h
 delete mode 100644 arch/h8300/include/asm/cputime.h
 delete mode 100644 arch/h8300/include/asm/current.h
 delete mode 100644 arch/h8300/include/asm/dbg.h
 delete mode 100644 arch/h8300/include/asm/delay.h
 delete mode 100644 arch/h8300/include/asm/device.h
 delete mode 100644 arch/h8300/include/asm/div64.h
 delete mode 100644 arch/h8300/include/asm/dma.h
 delete mode 100644 arch/h8300/include/asm/elf.h
 delete mode 100644 arch/h8300/include/asm/emergency-restart.h
 delete mode 100644 arch/h8300/include/asm/fb.h
 delete mode 100644 arch/h8300/include/asm/flat.h
 delete mode 100644 arch/h8300/include/asm/fpu.h
 delete mode 100644 arch/h8300/include/asm/ftrace.h
 delete mode 100644 arch/h8300/include/asm/futex.h
 delete mode 100644 arch/h8300/include/asm/gpio-internal.h
 delete mode 100644 arch/h8300/include/asm/hardirq.h
 delete mode 100644 arch/h8300/include/asm/hw_irq.h
 delete mode 100644 arch/h8300/include/asm/io.h
 delete mode 100644 arch/h8300/include/asm/irq.h
 delete mode 100644 arch/h8300/include/asm/irq_regs.h
 delete mode 100644 arch/h8300/include/asm/irqflags.h
 delete mode 100644 arch/h8300/include/asm/kdebug.h
 delete mode 100644 arch/h8300/include/asm/kmap_types.h
 delete mode 100644 arch/h8300/include/asm/local.h
 delete mode 100644 arch/h8300/include/asm/local64.h
 delete mode 100644 arch/h8300/include/asm/mc146818rtc.h
 delete mode 100644 arch/h8300/include/asm/mmu_context.h
 delete mode 100644 arch/h8300/include/asm/mutex.h
 delete mode 100644 arch/h8300/include/asm/page.h
 delete mode 100644 arch/h8300/include/asm/page_offset.h
 delete mode 100644 arch/h8300/include/asm/param.h
 delete mode 100644 arch/h8300/include/asm/pci.h
 delete mode 100644 arch/h8300/include/asm/percpu.h
 delete mode 100644 arch/h8300/include/asm/pgalloc.h
 delete mode 100644 arch/h8300/include/asm/pgtable.h
 delete mode 100644 arch/h8300/include/asm/processor.h
 delete mode 100644 arch/h8300/include/asm/ptrace.h
 delete mode 100644 arch/h8300/include/asm/regs267x.h
 delete mode 100644 arch/h8300/include/asm/regs306x.h
 delete mode 100644 arch/h8300/include/asm/scatterlist.h
 delete mode 100644 arch/h8300/include/asm/sections.h
 delete mode 100644 arch/h8300/include/asm/segment.h
 delete mode 100644 arch/h8300/include/asm/sh_bios.h
 delete mode 100644 arch/h8300/include/asm/shm.h
 delete mode 100644 arch/h8300/include/asm/shmparam.h
 delete mode 100644 arch/h8300/include/asm/signal.h
 delete mode 100644 arch/h8300/include/asm/smp.h
 delete mode 100644 arch/h8300/include/asm/spinlock.h
 delete mode 100644 arch/h8300/include/asm/string.h
 delete mode 100644 arch/h8300/include/asm/switch_to.h
 delete mode 100644 arch/h8300/include/asm/target_time.h
 delete mode 100644 arch/h8300/include/asm/termios.h
 delete mode 100644 arch/h8300/include/asm/thread_info.h
 delete mode 100644 arch/h8300/include/asm/timer.h
 delete mode 100644 arch/h8300/include/asm/timex.h
 delete mode 100644 arch/h8300/include/asm/tlb.h
 delete mode 100644 arch/h8300/include/asm/tlbflush.h
 delete mode 100644 arch/h8300/include/asm/topology.h
 delete mode 100644 arch/h8300/include/asm/traps.h
 delete mode 100644 arch/h8300/include/asm/types.h
 delete mode 100644 arch/h8300/include/asm/uaccess.h
 delete mode 100644 arch/h8300/include/asm/ucontext.h
 delete mode 100644 arch/h8300/include/asm/unaligned.h
 delete mode 100644 arch/h8300/include/asm/unistd.h
 delete mode 100644 arch/h8300/include/asm/user.h
 delete mode 100644 arch/h8300/include/asm/virtconvert.h
 delete mode 100644 arch/h8300/include/uapi/asm/Kbuild
 delete mode 100644 arch/h8300/include/uapi/asm/auxvec.h
 delete mode 100644 arch/h8300/include/uapi/asm/bitsperlong.h
 delete mode 100644 arch/h8300/include/uapi/asm/byteorder.h
 delete mode 100644 arch/h8300/include/uapi/asm/errno.h
 delete mode 100644 arch/h8300/include/uapi/asm/fcntl.h
 delete mode 100644 arch/h8300/include/uapi/asm/ioctl.h
 delete mode 100644 arch/h8300/include/uapi/asm/ioctls.h
 delete mode 100644 arch/h8300/include/uapi/asm/ipcbuf.h
 delete mode 100644 arch/h8300/include/uapi/asm/kvm_para.h
 delete mode 100644 arch/h8300/include/uapi/asm/mman.h
 delete mode 100644 arch/h8300/include/uapi/asm/msgbuf.h
 delete mode 100644 arch/h8300/include/uapi/asm/param.h
 delete mode 100644 arch/h8300/include/uapi/asm/poll.h
 delete mode 100644 arch/h8300/include/uapi/asm/posix_types.h
 delete mode 100644 arch/h8300/include/uapi/asm/ptrace.h
 delete mode 100644 arch/h8300/include/uapi/asm/resource.h
 delete mode 100644 arch/h8300/include/uapi/asm/sembuf.h
 delete mode 100644 arch/h8300/include/uapi/asm/setup.h
 delete mode 100644 arch/h8300/include/uapi/asm/shmbuf.h
 delete mode 100644 arch/h8300/include/uapi/asm/sigcontext.h
 delete mode 100644 arch/h8300/include/uapi/asm/siginfo.h
 delete mode 100644 arch/h8300/include/uapi/asm/signal.h
 delete mode 100644 arch/h8300/include/uapi/asm/socket.h
 delete mode 100644 arch/h8300/include/uapi/asm/sockios.h
 delete mode 100644 arch/h8300/include/uapi/asm/stat.h
 delete mode 100644 arch/h8300/include/uapi/asm/statfs.h
 delete mode 100644 arch/h8300/include/uapi/asm/swab.h
 delete mode 100644 arch/h8300/include/uapi/asm/termbits.h
 delete mode 100644 arch/h8300/include/uapi/asm/termios.h
 delete mode 100644 arch/h8300/include/uapi/asm/types.h
 delete mode 100644 arch/h8300/include/uapi/asm/unistd.h
 delete mode 100644 arch/h8300/kernel/Makefile
 delete mode 100644 arch/h8300/kernel/asm-offsets.c
 delete mode 100644 arch/h8300/kernel/entry.S
 delete mode 100644 arch/h8300/kernel/gpio.c
 delete mode 100644 arch/h8300/kernel/h8300_ksyms.c
 delete mode 100644 arch/h8300/kernel/irq.c
 delete mode 100644 arch/h8300/kernel/module.c
 delete mode 100644 arch/h8300/kernel/process.c
 delete mode 100644 arch/h8300/kernel/ptrace.c
 delete mode 100644 arch/h8300/kernel/setup.c
 delete mode 100644 arch/h8300/kernel/signal.c
 delete mode 100644 arch/h8300/kernel/sys_h8300.c
 delete mode 100644 arch/h8300/kernel/syscalls.S
 delete mode 100644 arch/h8300/kernel/time.c
 delete mode 100644 arch/h8300/kernel/timer/Makefile
 delete mode 100644 arch/h8300/kernel/timer/itu.c
 delete mode 100644 arch/h8300/kernel/timer/timer16.c
 delete mode 100644 arch/h8300/kernel/timer/timer8.c
 delete mode 100644 arch/h8300/kernel/timer/tpu.c
 delete mode 100644 arch/h8300/kernel/traps.c
 delete mode 100644 arch/h8300/kernel/vmlinux.lds.S
 delete mode 100644 arch/h8300/lib/Makefile
 delete mode 100644 arch/h8300/lib/abs.S
 delete mode 100644 arch/h8300/lib/ashrdi3.c
 delete mode 100644 arch/h8300/lib/checksum.c
 delete mode 100644 arch/h8300/lib/memcpy.S
 delete mode 100644 arch/h8300/lib/memset.S
 delete mode 100644 arch/h8300/lib/romfs.S
 delete mode 100644 arch/h8300/mm/Makefile
 delete mode 100644 arch/h8300/mm/fault.c
 delete mode 100644 arch/h8300/mm/init.c
 delete mode 100644 arch/h8300/mm/kmap.c
 delete mode 100644 arch/h8300/mm/memory.c
 delete mode 100644 arch/h8300/platform/h8300h/Makefile
 delete mode 100644 arch/h8300/platform/h8300h/aki3068net/Makefile
 delete mode 100644 arch/h8300/platform/h8300h/aki3068net/crt0_ram.S
 delete mode 100644 arch/h8300/platform/h8300h/generic/Makefile
 delete mode 100644 arch/h8300/platform/h8300h/generic/crt0_ram.S
 delete mode 100644 arch/h8300/platform/h8300h/generic/crt0_rom.S
 delete mode 100644 arch/h8300/platform/h8300h/h8max/Makefile
 delete mode 100644 arch/h8300/platform/h8300h/h8max/crt0_ram.S
 delete mode 100644 arch/h8300/platform/h8300h/irq.c
 delete mode 100644 arch/h8300/platform/h8300h/ptrace_h8300h.c
 delete mode 100644 arch/h8300/platform/h8s/Makefile
 delete mode 100644 arch/h8300/platform/h8s/edosk2674/Makefile
 delete mode 100644 arch/h8300/platform/h8s/edosk2674/crt0_ram.S
 delete mode 100644 arch/h8300/platform/h8s/edosk2674/crt0_rom.S
 delete mode 100644 arch/h8300/platform/h8s/generic/Makefile
 delete mode 100644 arch/h8300/platform/h8s/generic/crt0_ram.S
 delete mode 100644 arch/h8300/platform/h8s/generic/crt0_rom.S
 delete mode 100644 arch/h8300/platform/h8s/irq.c
 delete mode 100644 arch/h8300/platform/h8s/ptrace_h8s.c

(limited to 'include')

diff --git a/Documentation/scheduler/sched-arch.txt b/Documentation/scheduler/sched-arch.txt
index b1b8587b86f0..9290de703450 100644
--- a/Documentation/scheduler/sched-arch.txt
+++ b/Documentation/scheduler/sched-arch.txt
@@ -65,11 +65,6 @@ Possible arch/ problems
 
 Possible arch problems I found (and either tried to fix or didn't):
 
-h8300 - Is such sleeping racy vs interrupts? (See #4a).
-        The H8/300 manual I found indicates yes, however disabling IRQs
-        over the sleep mean only NMIs can wake it up, so can't fix easily
-        without doing spin waiting.
-
 ia64 - is safe_halt call racy vs interrupts? (does it sleep?) (See #4a)
 
 sh64 - Is sleeping racy vs interrupts? (See #4a)
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
deleted file mode 100644
index 24b1dc2564f1..000000000000
--- a/arch/h8300/Kconfig
+++ /dev/null
@@ -1,108 +0,0 @@
-config H8300
-	bool
-	default y
-	select HAVE_IDE
-	select GENERIC_ATOMIC64
-	select HAVE_UID16
-	select VIRT_TO_BUS
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select GENERIC_IRQ_SHOW
-	select GENERIC_CPU_DEVICES
-	select MODULES_USE_ELF_RELA
-	select OLD_SIGSUSPEND3
-	select OLD_SIGACTION
-	select HAVE_UNDERSCORE_SYMBOL_PREFIX
-
-config MMU
-	bool
-	default n
-
-config SWAP
-	bool
-	default n
-
-config ZONE_DMA
-	bool
-	default y
-
-config FPU
-	bool
-	default n
-
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default n
-
-config ARCH_HAS_ILOG2_U32
-	bool
-	default n
-
-config ARCH_HAS_ILOG2_U64
-	bool
-	default n
-
-config GENERIC_HWEIGHT
-	bool
-	default y
-
-config GENERIC_CALIBRATE_DELAY
-	bool
-	default y
-
-config GENERIC_BUG
-        bool
-        depends on BUG
-
-config TIME_LOW_RES
-	bool
-	default y
-
-config NO_IOPORT
-	def_bool y
-
-config NO_DMA
-	def_bool y
-
-config ISA
-	bool
-	default y
-
-config PCI
-	bool
-	default n
-
-config HZ
-	int
-	default 100
-
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
-source "arch/h8300/Kconfig.cpu"
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "arch/h8300/Kconfig.ide"
-
-source "fs/Kconfig"
-
-source "arch/h8300/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu
deleted file mode 100644
index cdee771460ed..000000000000
--- a/arch/h8300/Kconfig.cpu
+++ /dev/null
@@ -1,171 +0,0 @@
-menu "Processor type and features"
-
-choice
-	prompt "H8/300 platform"
-	default H8300H_GENERIC
-
-config H8300H_GENERIC
-	bool "H8/300H Generic"
-	help
-	  H8/300H CPU Generic Hardware Support
-
-config H8300H_AKI3068NET
-	bool "AE-3068/69"
-	select H83068
-	help
-	  AKI-H8/3068F / AKI-H8/3069F Flashmicom LAN Board Support
-	  More Information. (Japanese Only)
-	  <http://akizukidenshi.com/catalog/default.aspx>
-	  AE-3068/69 Evaluation Board Support
-	  More Information.
-	  <http://www.microtronique.com/ae3069lan.htm>
-
-config H8300H_H8MAX
-	bool "H8MAX"
-	select H83068
-	help
-	  H8MAX Evaluation Board Support
-	  More Information. (Japanese Only)
-	  <http://strawberry-linux.com/h8/index.html>
-
-config H8300H_SIM
-	bool "H8/300H Simulator"
-	select H83007
-	help
-	  GDB Simulator Support
-	  More Information.
-	  <http://sourceware.org/sid/>
-
-config H8S_GENERIC
-	bool "H8S Generic"
-	help
-	  H8S CPU Generic Hardware Support
-
-config H8S_EDOSK2674
-	bool "EDOSK-2674"
-	select H8S2678
-	help
-	  Renesas EDOSK-2674 Evaluation Board Support
-	  More Information.
-	  <http://www.azpower.com/H8-uClinux/index.html>
- 	  <http://www.renesas.eu/products/tools/introductory_evaluation_tools/evaluation_development_os_kits/edosk2674r/edosk2674r_software_tools_root.jsp>
-
-config H8S_SIM
-	bool "H8S Simulator"
-	help
-	  GDB Simulator Support
-	  More Information.
-	  <http://sourceware.org/sid/>
-
-endchoice
-
-choice
-	prompt "CPU Selection"
-
-config H83002
-	bool "H8/3001,3002,3003"
-	depends on BROKEN
-	select CPU_H8300H
-
-config H83007
-	bool "H8/3006,3007"
-	select CPU_H8300H
-
-config H83048
-	bool "H8/3044,3045,3046,3047,3048,3052"
-	depends on BROKEN
-	select CPU_H8300H
-
-config H83068
-	bool "H8/3065,3066,3067,3068,3069"
-	select CPU_H8300H
-
-config H8S2678
-	bool "H8S/2670,2673,2674R,2675,2676"
-	select CPU_H8S
-
-endchoice
-
-config CPU_CLOCK
-	int "CPU Clock Frequency (/1KHz)"
-	default "20000"
-	help
-	  CPU Clock Frequency divide to 1000
-
-choice
-	prompt "Kernel executes from"
-	---help---
-	  Choose the memory type that the kernel will be running in.
-
-config RAMKERNEL
-	bool "RAM"
-	help
-	  The kernel will be resident in RAM when running.
-
-config ROMKERNEL
-	bool "ROM"
-	help
-	  The kernel will be resident in FLASH/ROM when running.
-endchoice
-
-
-config CPU_H8300H
-	bool
-	depends on (H83002 || H83007 || H83048 || H83068)
-	default y
-
-config CPU_H8S
-	bool
-	depends on H8S2678
-	default y
-
-choice
-	prompt "Timer"
-config H8300_TIMER8
-	bool "8bit timer (2ch cascade)"
-	depends on (H83007 || H83068 || H8S2678)
-
-config H8300_TIMER16
-	bool "16bit timer"
-	depends on (H83007 || H83068)
-
-config H8300_ITU
-	bool "ITU"
-	depends on (H83002 || H83048)
-
-config H8300_TPU
-	bool "TPU"
-	depends on H8S2678
-endchoice
-
-if H8300_TIMER8
-choice
-	prompt "Timer Channel"
-config H8300_TIMER8_CH0
-	bool "Channel 0"
-config H8300_TIMER8_CH2
-	bool "Channel 2"
-	depends on CPU_H8300H
-endchoice
-endif
-
-config H8300_TIMER16_CH
-	int "16bit timer channel (0 - 2)"
-	depends on H8300_TIMER16
-	range 0 2
-
-config H8300_ITU_CH
-	int "ITU channel"
-	depends on H8300_ITU
-	range 0 4
-
-config H8300_TPU_CH
-	int "TPU channel"
-	depends on H8300_TPU
-	range 0 4
-
-source "kernel/Kconfig.preempt"
-
-source "mm/Kconfig"
-
-endmenu
diff --git a/arch/h8300/Kconfig.debug b/arch/h8300/Kconfig.debug
deleted file mode 100644
index e8d1b236ad8c..000000000000
--- a/arch/h8300/Kconfig.debug
+++ /dev/null
@@ -1,68 +0,0 @@
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
-
-config FULLDEBUG
-	bool "Full Symbolic/Source Debugging support"
-	help
-	  Enable debugging symbols on kernel build.
-
-config HIGHPROFILE
-	bool "Use fast second timer for profiling"
-	help
-	  Use a fast secondary clock to produce profiling information.
-
-config NO_KERNEL_MSG
-	bool "Suppress Kernel BUG Messages"
-	help
-	  Do not output any debug BUG messages within the kernel.
-
-config GDB_MAGICPRINT
-	bool "Message Output for GDB MagicPrint service"
-	depends on (H8300H_SIM || H8S_SIM)
-	help
-	  kernel messages output using MagicPrint service from GDB
-
-config SYSCALL_PRINT
-	bool "SystemCall trace print"
-	help
-	  output history of systemcall
-
-config GDB_DEBUG
-   	bool "Use gdb stub"
-	depends on (!H8300H_SIM && !H8S_SIM)
-	help
-	  gdb stub exception support
-
-config SH_STANDARD_BIOS
-	bool "Use gdb protocol serial console"
-	depends on (!H8300H_SIM && !H8S_SIM)
-	help
-	  serial console output using GDB protocol.
-	  Require eCos/RedBoot
-
-config DEFAULT_CMDLINE
-	bool "Use builtin commandline"
-	default n
-	help
-	  builtin kernel commandline enabled.
-
-config KERNEL_COMMAND
-	string "Buildin command string"
-	depends on DEFAULT_CMDLINE
-	help
-	  builtin kernel commandline strings.
-
-config BLKDEV_RESERVE
-	bool "BLKDEV Reserved Memory"
-	default n
-	help
-	  Reserved BLKDEV area.
-
-config BLKDEV_RESERVE_ADDRESS
-	hex 'start address'
-	depends on BLKDEV_RESERVE
-	help
-	  BLKDEV start address.
-
-endmenu
diff --git a/arch/h8300/Kconfig.ide b/arch/h8300/Kconfig.ide
deleted file mode 100644
index a38a63054ac2..000000000000
--- a/arch/h8300/Kconfig.ide
+++ /dev/null
@@ -1,44 +0,0 @@
-# uClinux H8/300 Target Board Selection Menu (IDE)
-
-if (H8300H_AKI3068NET)
-menu "IDE Extra configuration"
-
-config H8300_IDE_BASE
-	hex "IDE register base address"
-	depends on IDE
-	default 0
-	help
-	  IDE registers base address
-
-config H8300_IDE_ALT
-	hex "IDE register alternate address"
-	depends on IDE
-	default 0
-	help
-	  IDE alternate registers address
-
-config H8300_IDE_IRQ
-	int "IDE IRQ no"
-	depends on IDE
-	default 0
-	help
-	  IDE use IRQ no
-endmenu
-endif
-
-if (H8300H_H8MAX)
-config H8300_IDE_BASE
-	hex
-	depends on IDE
-	default 0x200000
-
-config H8300_IDE_ALT
-	hex
-	depends on IDE
-	default 0x60000c
-
-config H8300_IDE_IRQ
-	int
-	depends on IDE
-	default 5
-endif
diff --git a/arch/h8300/Makefile b/arch/h8300/Makefile
deleted file mode 100644
index a556447877b4..000000000000
--- a/arch/h8300/Makefile
+++ /dev/null
@@ -1,71 +0,0 @@
-#
-# arch/h8300/Makefile
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License.  See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# (C) Copyright 2002,2003 Yoshinori Sato <ysato@users.sourceforge.jp>
-#
-
-platform-$(CONFIG_CPU_H8300H)	:= h8300h
-platform-$(CONFIG_CPU_H8S)	:= h8s
-PLATFORM := $(platform-y)
-
-board-$(CONFIG_H8300H_GENERIC)		:= generic
-board-$(CONFIG_H8300H_AKI3068NET)	:= aki3068net
-board-$(CONFIG_H8300H_H8MAX)		:= h8max
-board-$(CONFIG_H8300H_SIM)		:= generic
-board-$(CONFIG_H8S_GENERIC)		:= generic
-board-$(CONFIG_H8S_EDOSK2674)		:= edosk2674
-board-$(CONFIG_H8S_SIM)			:= generic
-BOARD := $(board-y)
-
-model-$(CONFIG_RAMKERNEL)	:= ram
-model-$(CONFIG_ROMKERNEL)	:= rom
-MODEL := $(model-y)
-
-cflags-$(CONFIG_CPU_H8300H)	:= -mh
-ldflags-$(CONFIG_CPU_H8300H)	:= -mh8300helf
-cflags-$(CONFIG_CPU_H8S)	:= -ms
-ldflags-$(CONFIG_CPU_H8S)	:= -mh8300self
-
-KBUILD_CFLAGS += $(cflags-y)
-KBUILD_CFLAGS += -mint32 -fno-builtin
-KBUILD_CFLAGS += -g
-KBUILD_CFLAGS += -D__linux__
-KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\"
-KBUILD_AFLAGS += -DPLATFORM=$(PLATFORM) -DMODEL=$(MODEL) $(cflags-y)
-LDFLAGS += $(ldflags-y)
-
-CROSS_COMPILE = h8300-elf-
-LIBGCC := $(shell $(CROSS-COMPILE)$(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
-
-head-y := arch/$(ARCH)/platform/$(PLATFORM)/$(BOARD)/crt0_$(MODEL).o
-
-core-y	+= arch/$(ARCH)/kernel/ \
-	   arch/$(ARCH)/mm/
-ifdef PLATFORM
-core-y	+= arch/$(ARCH)/platform/$(PLATFORM)/ \
-	   arch/$(ARCH)/platform/$(PLATFORM)/$(BOARD)/
-endif
-
-libs-y	+= arch/$(ARCH)/lib/ $(LIBGCC)
-
-boot := arch/h8300/boot
-
-export MODEL PLATFORM BOARD
-
-archmrproper:
-
-archclean:
-	$(Q)$(MAKE) $(clean)=$(boot)
-
-vmlinux.srec vmlinux.bin zImage: vmlinux
-	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-
-define archhelp
-  @echo  'vmlinux.bin  - Create raw binary'
-  @echo  'vmlinux.srec - Create srec binary'
-  @echo  'zImage       - Compressed kernel image'
-endef
diff --git a/arch/h8300/README b/arch/h8300/README
deleted file mode 100644
index efa805fda19b..000000000000
--- a/arch/h8300/README
+++ /dev/null
@@ -1,38 +0,0 @@
-linux-2.6 for H8/300 README
-Yoshinori Sato <ysato@users.sourceforge.jp>
-
-* Supported CPU
-H8/300H and H8S
-
-* Supported Target
-1.simulator of GDB
-  require patches.
-
-2.AE 3068/AE 3069
-  more information 
-  MICROTRONIQUE <http://www.microtronique.com/>
-  Akizuki Denshi Tsusho Ltd. <http://akizukidenshi.com/> (Japanese Only)
-
-3.H8MAX 
-  see http://ip-sol.jp/h8max/ (Japanese Only)
-
-4.EDOSK2674
-  see http://www.eu.renesas.com/products/mpumcu/tool/edk/support/edosk2674.html
-      http://www.uclinux.org/pub/uClinux/ports/h8/HITACHI-EDOSK2674-HOWTO
-      http://www.azpower.com/H8-uClinux/
-
-* Toolchain Version
-gcc-3.1 or higher and patch
-see arch/h8300/tools_patch/README
-binutils-2.12 or higher
-gdb-5.2 or higher
-The environment that can compile a h8300-elf binary is necessary.
-
-* Userland Develop environment
-used h8300-elf toolchains.
-see http://www.uclinux.org/pub/uClinux/ports/h8/
-
-* A few words of thanks
-Porting to H8/300 serieses is support of Information-technology Promotion Agency, Japan.
-I thank support.
-and All developer/user.
diff --git a/arch/h8300/boot/Makefile b/arch/h8300/boot/Makefile
deleted file mode 100644
index 0bb62e064eea..000000000000
--- a/arch/h8300/boot/Makefile
+++ /dev/null
@@ -1,22 +0,0 @@
-# arch/h8300/boot/Makefile
-
-targets := vmlinux.srec vmlinux.bin zImage
-subdir- := compressed
-
-OBJCOPYFLAGS_vmlinux.srec := -Osrec
-OBJCOPYFLAGS_vmlinux.bin  := -Obinary
-OBJCOPYFLAGS_zImage := -O binary -R .note -R .comment -R .stab -R .stabstr -S
-
-$(obj)/vmlinux.srec $(obj)/vmlinux.bin:  vmlinux FORCE
-	$(call if_changed,objcopy)
-	@echo '  Kernel: $@ is ready'
-
-$(obj)/zImage: $(obj)/compressed/vmlinux FORCE
-	$(call if_changed,objcopy)
-	@echo 'Kernel: $@ is ready'
-
-$(obj)/compressed/vmlinux: FORCE
-	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
-
-CLEAN_FILES += arch/$(ARCH)/vmlinux.bin arch/$(ARCH)/vmlinux.srec
-
diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile
deleted file mode 100644
index a6c98fe3bbc3..000000000000
--- a/arch/h8300/boot/compressed/Makefile
+++ /dev/null
@@ -1,37 +0,0 @@
-#
-# linux/arch/sh/boot/compressed/Makefile
-#
-# create a compressed vmlinux image from the original vmlinux
-#
-
-targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o
-asflags-y	:= -traditional
-
-OBJECTS = $(obj)/head.o $(obj)/misc.o
-
-#
-# IMAGE_OFFSET is the load offset of the compression loader
-# Assign dummy values if these 2 variables are not defined,
-# in order to suppress error message.
-#
-CONFIG_MEMORY_START     ?= 0x00400000
-CONFIG_BOOT_LINK_OFFSET ?= 0x00140000
-IMAGE_OFFSET := $(shell printf "0x%08x" $$(($(CONFIG_MEMORY_START)+$(CONFIG_BOOT_LINK_OFFSET))))
-
-LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup $(obj)/vmlinux.lds
-
-$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o FORCE
-	$(call if_changed,ld)
-	@:
-
-$(obj)/vmlinux.bin: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-h8300 -T
-OBJCOPYFLAGS := -O binary
-
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,ld)
diff --git a/arch/h8300/boot/compressed/head.S b/arch/h8300/boot/compressed/head.S
deleted file mode 100644
index 10e9a2d1cc6c..000000000000
--- a/arch/h8300/boot/compressed/head.S
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- *  linux/arch/h8300/boot/compressed/head.S
- *
- *  Copyright (C) 2006 Yoshinori Sato
- */
-
-	.h8300h
-#include <linux/linkage.h>
-
-#define SRAM_START 0xff4000
-
-	.section	.text..startup
-	.global	startup
-startup:
-	mov.l	#SRAM_START+0x8000, sp
-	mov.l	#__sbss, er0
-	mov.l	#__ebss, er1
-	sub.l	er0, er1
-	shlr	er1
-	shlr	er1
-	sub.l	er2, er2
-1:
-	mov.l	er2, @er0
-	adds	#4, er0
-	dec.l	#1, er1
-	bne	1b
-	jsr	@_decompress_kernel
-	jmp	@0x400000
-
-	.align	9
-fake_headers_as_bzImage:
-	.word	0
-	.ascii	"HdrS"		; header signature
-	.word	0x0202		; header version number (>= 0x0105)
-				; or else old loadlin-1.5 will fail)
-	.word	0		; default_switch
-	.word	0		; SETUPSEG
-	.word	0x1000
-	.word	0		; pointing to kernel version string
-	.byte	0		; = 0, old one (LILO, Loadlin,
-				; 0xTV: T=0 for LILO
-				;       V = version
-	.byte	1		; Load flags bzImage=1
-	.word	0x8000		; size to move, when setup is not
-	.long	0x100000	; 0x100000 = default for big kernel
-	.long	0		; address of loaded ramdisk image
-	.long	0		; its size in bytes
diff --git a/arch/h8300/boot/compressed/misc.c b/arch/h8300/boot/compressed/misc.c
deleted file mode 100644
index 4a1e3dd43948..000000000000
--- a/arch/h8300/boot/compressed/misc.c
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * arch/h8300/boot/compressed/misc.c
- *
- * This is a collection of several routines from gzip-1.0.3
- * adapted for Linux.
- *
- * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
- *
- * Adapted for h8300 by Yoshinori Sato 2006
- */
-
-#include <asm/uaccess.h>
-
-/*
- * gzip declarations
- */
-
-#define OF(args)  args
-#define STATIC static
-
-#undef memset
-#undef memcpy
-#define memzero(s, n)     memset ((s), 0, (n))
-
-typedef unsigned char  uch;
-typedef unsigned short ush;
-typedef unsigned long  ulg;
-
-#define WSIZE 0x8000		/* Window size must be at least 32k, */
-				/* and a power of two */
-
-static uch *inbuf;	     /* input buffer */
-static uch window[WSIZE];    /* Sliding window buffer */
-
-static unsigned insize = 0;  /* valid bytes in inbuf */
-static unsigned inptr = 0;   /* index of next byte to be processed in inbuf */
-static unsigned outcnt = 0;  /* bytes in output buffer */
-
-/* gzip flag byte */
-#define ASCII_FLAG   0x01 /* bit 0 set: file probably ASCII text */
-#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
-#define EXTRA_FIELD  0x04 /* bit 2 set: extra field present */
-#define ORIG_NAME    0x08 /* bit 3 set: original file name present */
-#define COMMENT      0x10 /* bit 4 set: file comment present */
-#define ENCRYPTED    0x20 /* bit 5 set: file is encrypted */
-#define RESERVED     0xC0 /* bit 6,7:   reserved */
-
-#define get_byte()  (inptr < insize ? inbuf[inptr++] : fill_inbuf())
-
-/* Diagnostic functions */
-#ifdef DEBUG
-#  define Assert(cond,msg) {if(!(cond)) error(msg);}
-#  define Trace(x) fprintf x
-#  define Tracev(x) {if (verbose) fprintf x ;}
-#  define Tracevv(x) {if (verbose>1) fprintf x ;}
-#  define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
-#  define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
-#else
-#  define Assert(cond,msg)
-#  define Trace(x)
-#  define Tracev(x)
-#  define Tracevv(x)
-#  define Tracec(c,x)
-#  define Tracecv(c,x)
-#endif
-
-static int  fill_inbuf(void);
-static void flush_window(void);
-static void error(char *m);
-
-extern char input_data[];
-extern int input_len;
-
-static long bytes_out = 0;
-static uch *output_data;
-static unsigned long output_ptr = 0;
-
-static void error(char *m);
-
-int puts(const char *);
-
-extern int _end;
-static unsigned long free_mem_ptr;
-static unsigned long free_mem_end_ptr;
-
-#define HEAP_SIZE             0x10000
-
-#include "../../../../lib/inflate.c"
-
-#define SCR *((volatile unsigned char *)0xffff8a)
-#define TDR *((volatile unsigned char *)0xffff8b)
-#define SSR *((volatile unsigned char *)0xffff8c)
-
-int puts(const char *s)
-{
-	return 0;
-}
-
-void* memset(void* s, int c, size_t n)
-{
-	int i;
-	char *ss = (char*)s;
-
-	for (i=0;i<n;i++) ss[i] = c;
-	return s;
-}
-
-void* memcpy(void* __dest, __const void* __src,
-			    size_t __n)
-{
-	int i;
-	char *d = (char *)__dest, *s = (char *)__src;
-
-	for (i=0;i<__n;i++) d[i] = s[i];
-	return __dest;
-}
-
-/* ===========================================================================
- * Fill the input buffer. This is called only when the buffer is empty
- * and at least one byte is really needed.
- */
-static int fill_inbuf(void)
-{
-	if (insize != 0) {
-		error("ran out of input data");
-	}
-
-	inbuf = input_data;
-	insize = input_len;
-	inptr = 1;
-	return inbuf[0];
-}
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-static void flush_window(void)
-{
-    ulg c = crc;         /* temporary variable */
-    unsigned n;
-    uch *in, *out, ch;
-
-    in = window;
-    out = &output_data[output_ptr];
-    for (n = 0; n < outcnt; n++) {
-	    ch = *out++ = *in++;
-	    c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
-    }
-    crc = c;
-    bytes_out += (ulg)outcnt;
-    output_ptr += (ulg)outcnt;
-    outcnt = 0;
-}
-
-static void error(char *x)
-{
-	puts("\n\n");
-	puts(x);
-	puts("\n\n -- System halted");
-
-	while(1);	/* Halt */
-}
-
-#define STACK_SIZE (4096)
-long user_stack [STACK_SIZE];
-long* stack_start = &user_stack[STACK_SIZE];
-
-void decompress_kernel(void)
-{
-	output_data = 0;
-	output_ptr = (unsigned long)0x400000;
-	free_mem_ptr = (unsigned long)&_end;
-	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
-
-	makecrc();
-	puts("Uncompressing Linux... ");
-	gunzip();
-	puts("Ok, booting the kernel.\n");
-}
diff --git a/arch/h8300/boot/compressed/vmlinux.lds b/arch/h8300/boot/compressed/vmlinux.lds
deleted file mode 100644
index a0a3a0ed54ef..000000000000
--- a/arch/h8300/boot/compressed/vmlinux.lds
+++ /dev/null
@@ -1,32 +0,0 @@
-SECTIONS
-{
-        .text :
-        {
-        __stext = . ;
-	__text = .;
-	       *(.text..startup)
-	       *(.text)
-        __etext = . ;
-        }
-
-	.rodata :
-	{
-		*(.rodata)
-	}
-        .data :
-
-        {
-        __sdata = . ;
-        ___data_start = . ;
-                *(.data.*)
-	}
-        .bss :
-        {
-        . = ALIGN(0x4) ;
-        __sbss = . ;
-                *(.bss*)
-        . = ALIGN(0x4) ;
-        __ebss = . ;
-        __end = . ;
-        }
-}
diff --git a/arch/h8300/boot/compressed/vmlinux.scr b/arch/h8300/boot/compressed/vmlinux.scr
deleted file mode 100644
index a0f6962736e9..000000000000
--- a/arch/h8300/boot/compressed/vmlinux.scr
+++ /dev/null
@@ -1,9 +0,0 @@
-SECTIONS
-{
-  .data : {
-	_input_len = .;
-	LONG(_input_data_end - _input_data) _input_data = .;
-	*(.data)
-	_input_data_end = .;
-	}
-}
diff --git a/arch/h8300/defconfig b/arch/h8300/defconfig
deleted file mode 100644
index 042425a02645..000000000000
--- a/arch/h8300/defconfig
+++ /dev/null
@@ -1,42 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_EXPERT=y
-# CONFIG_UID16 is not set
-# CONFIG_SYSCTL_SYSCALL is not set
-# CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
-# CONFIG_BASE_FULL is not set
-# CONFIG_FUTEX is not set
-# CONFIG_EPOLL is not set
-# CONFIG_SIGNALFD is not set
-# CONFIG_TIMERFD is not set
-# CONFIG_EVENTFD is not set
-# CONFIG_VM_EVENT_COUNTERS is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_SLOB=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-CONFIG_H83007=y
-CONFIG_BINFMT_FLAT=y
-CONFIG_BINFMT_ZFLAT=y
-CONFIG_BINFMT_MISC=y
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_REDBOOT_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_RAM=y
-CONFIG_MTD_ROM=y
-CONFIG_MTD_UCLINUX=y
-# CONFIG_BLK_DEV is not set
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_HWMON is not set
-# CONFIG_USB_SUPPORT is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_ROMFS_FS=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_CRC32 is not set
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
deleted file mode 100644
index 8ada3cf0c98d..000000000000
--- a/arch/h8300/include/asm/Kbuild
+++ /dev/null
@@ -1,8 +0,0 @@
-
-generic-y += clkdev.h
-generic-y += exec.h
-generic-y += linkage.h
-generic-y += mmu.h
-generic-y += module.h
-generic-y += trace_clock.h
-generic-y += xor.h
diff --git a/arch/h8300/include/asm/asm-offsets.h b/arch/h8300/include/asm/asm-offsets.h
deleted file mode 100644
index d370ee36a182..000000000000
--- a/arch/h8300/include/asm/asm-offsets.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <generated/asm-offsets.h>
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
deleted file mode 100644
index 40901e353c21..000000000000
--- a/arch/h8300/include/asm/atomic.h
+++ /dev/null
@@ -1,146 +0,0 @@
-#ifndef __ARCH_H8300_ATOMIC__
-#define __ARCH_H8300_ATOMIC__
-
-#include <linux/types.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- */
-
-#define ATOMIC_INIT(i)	{ (i) }
-
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic_set(v, i)	(((v)->counter) = i)
-
-#include <linux/kernel.h>
-
-static __inline__ int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int ret;
-	local_irq_save(flags);
-	ret = v->counter += i;
-	local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_add(i, v) atomic_add_return(i, v)
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-static __inline__ int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int ret;
-	local_irq_save(flags);
-	ret = v->counter -= i;
-	local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_sub(i, v) atomic_sub_return(i, v)
-#define atomic_sub_and_test(i,v) (atomic_sub_return(i, v) == 0)
-
-static __inline__ int atomic_inc_return(atomic_t *v)
-{
-	unsigned long flags;
-	int ret;
-	local_irq_save(flags);
-	v->counter++;
-	ret = v->counter;
-	local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_inc(v) atomic_inc_return(v)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-static __inline__ int atomic_dec_return(atomic_t *v)
-{
-	unsigned long flags;
-	int ret;
-	local_irq_save(flags);
-	--v->counter;
-	ret = v->counter;
-	local_irq_restore(flags);
-	return ret;
-}
-
-#define atomic_dec(v) atomic_dec_return(v)
-
-static __inline__ int atomic_dec_and_test(atomic_t *v)
-{
-	unsigned long flags;
-	int ret;
-	local_irq_save(flags);
-	--v->counter;
-	ret = v->counter;
-	local_irq_restore(flags);
-	return ret == 0;
-}
-
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
-{
-	int ret;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	ret = v->counter;
-	if (likely(ret == old))
-		v->counter = new;
-	local_irq_restore(flags);
-	return ret;
-}
-
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int ret;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	ret = v->counter;
-	if (ret != u)
-		v->counter += a;
-	local_irq_restore(flags);
-	return ret;
-}
-
-static __inline__ void atomic_clear_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("stc ccr,r1l\n\t"
-	                     "orc #0x80,ccr\n\t"
-	                     "mov.l %0,er0\n\t"
-	                     "and.l %1,er0\n\t"
-	                     "mov.l er0,%0\n\t"
-	                     "ldc r1l,ccr" 
-                             : "=m" (*v) : "g" (~(mask)) :"er0","er1");
-}
-
-static __inline__ void atomic_set_mask(unsigned long mask, unsigned long *v)
-{
-	__asm__ __volatile__("stc ccr,r1l\n\t"
-	                     "orc #0x80,ccr\n\t"
-	                     "mov.l %0,er0\n\t"
-	                     "or.l %1,er0\n\t"
-	                     "mov.l er0,%0\n\t"
-	                     "ldc r1l,ccr" 
-                             : "=m" (*v) : "g" (mask) :"er0","er1");
-}
-
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()    barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc()    barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
-#endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/h8300/include/asm/barrier.h b/arch/h8300/include/asm/barrier.h
deleted file mode 100644
index 9e0aa9fc195d..000000000000
--- a/arch/h8300/include/asm/barrier.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _H8300_BARRIER_H
-#define _H8300_BARRIER_H
-
-#define nop()  asm volatile ("nop"::)
-
-/*
- * Force strict CPU ordering.
- * Not really required on H8...
- */
-#define mb()   asm volatile (""   : : :"memory")
-#define rmb()  asm volatile (""   : : :"memory")
-#define wmb()  asm volatile (""   : : :"memory")
-#define set_mb(var, value) do { xchg(&var, value); } while (0)
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
-#endif
-
-#endif /* _H8300_BARRIER_H */
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
deleted file mode 100644
index eb34e0cd33d5..000000000000
--- a/arch/h8300/include/asm/bitops.h
+++ /dev/null
@@ -1,211 +0,0 @@
-#ifndef _H8300_BITOPS_H
-#define _H8300_BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- * Copyright 2002, Yoshinori Sato
- */
-
-#include <linux/compiler.h>
-
-#ifdef __KERNEL__
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-/*
- * Function prototypes to keep gcc -Wall happy
- */
-
-/*
- * ffz = Find First Zero in word. Undefined if no zero exists,
- * so code should check against ~0UL first..
- */
-static __inline__ unsigned long ffz(unsigned long word)
-{
-	unsigned long result;
-
-	result = -1;
-	__asm__("1:\n\t"
-		"shlr.l %2\n\t"
-		"adds #1,%0\n\t"
-		"bcs 1b"
-		: "=r" (result)
-		: "0"  (result),"r" (word));
-	return result;
-}
-
-#define H8300_GEN_BITOP_CONST(OP,BIT)			    \
-	case BIT:					    \
-	__asm__(OP " #" #BIT ",@%0"::"r"(b_addr):"memory"); \
-	break;
-
-#define H8300_GEN_BITOP(FNAME,OP)				      \
-static __inline__ void FNAME(int nr, volatile unsigned long* addr)    \
-{								      \
-	volatile unsigned char *b_addr;				      \
-	b_addr = (volatile unsigned char *)addr + ((nr >> 3) ^ 3);    \
-	if (__builtin_constant_p(nr)) {				      \
-		switch(nr & 7) {				      \
-			H8300_GEN_BITOP_CONST(OP,0)		      \
-			H8300_GEN_BITOP_CONST(OP,1)		      \
-			H8300_GEN_BITOP_CONST(OP,2)		      \
-			H8300_GEN_BITOP_CONST(OP,3)		      \
-			H8300_GEN_BITOP_CONST(OP,4)		      \
-			H8300_GEN_BITOP_CONST(OP,5)		      \
-			H8300_GEN_BITOP_CONST(OP,6)		      \
-			H8300_GEN_BITOP_CONST(OP,7)		      \
-		}						      \
-	} else {						      \
-		__asm__(OP " %w0,@%1"::"r"(nr),"r"(b_addr):"memory"); \
-	}							      \
-}
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-H8300_GEN_BITOP(set_bit	  ,"bset")
-H8300_GEN_BITOP(clear_bit ,"bclr")
-H8300_GEN_BITOP(change_bit,"bnot")
-#define __set_bit(nr,addr)    set_bit((nr),(addr))
-#define __clear_bit(nr,addr)  clear_bit((nr),(addr))
-#define __change_bit(nr,addr) change_bit((nr),(addr))
-
-#undef H8300_GEN_BITOP
-#undef H8300_GEN_BITOP_CONST
-
-static __inline__ int test_bit(int nr, const unsigned long* addr)
-{
-	return (*((volatile unsigned char *)addr + 
-               ((nr >> 3) ^ 3)) & (1UL << (nr & 7))) != 0;
-}
-
-#define __test_bit(nr, addr) test_bit(nr, addr)
-
-#define H8300_GEN_TEST_BITOP_CONST_INT(OP,BIT)			     \
-	case BIT:						     \
-	__asm__("stc ccr,%w1\n\t"				     \
-		"orc #0x80,ccr\n\t"				     \
-		"bld #" #BIT ",@%4\n\t"				     \
-		OP " #" #BIT ",@%4\n\t"				     \
-		"rotxl.l %0\n\t"				     \
-		"ldc %w1,ccr"					     \
-		: "=r"(retval),"=&r"(ccrsave),"=m"(*b_addr)	     \
-		: "0" (retval),"r" (b_addr)			     \
-		: "memory");                                         \
-        break;
-
-#define H8300_GEN_TEST_BITOP_CONST(OP,BIT)			     \
-	case BIT:						     \
-	__asm__("bld #" #BIT ",@%3\n\t"				     \
-		OP " #" #BIT ",@%3\n\t"				     \
-		"rotxl.l %0\n\t"				     \
-		: "=r"(retval),"=m"(*b_addr)			     \
-		: "0" (retval),"r" (b_addr)			     \
-		: "memory");                                         \
-        break;
-
-#define H8300_GEN_TEST_BITOP(FNNAME,OP)				     \
-static __inline__ int FNNAME(int nr, volatile void * addr)	     \
-{								     \
-	int retval = 0;						     \
-	char ccrsave;						     \
-	volatile unsigned char *b_addr;				     \
-	b_addr = (volatile unsigned char *)addr + ((nr >> 3) ^ 3);   \
-	if (__builtin_constant_p(nr)) {				     \
-		switch(nr & 7) {				     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,0)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,1)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,2)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,3)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,4)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,5)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,6)	     \
-			H8300_GEN_TEST_BITOP_CONST_INT(OP,7)	     \
-		}						     \
-	} else {						     \
-		__asm__("stc ccr,%w1\n\t"			     \
-			"orc #0x80,ccr\n\t"			     \
-			"btst %w5,@%4\n\t"			     \
-			OP " %w5,@%4\n\t"			     \
-			"beq 1f\n\t"				     \
-			"inc.l #1,%0\n"				     \
-			"1:\n\t"				     \
-			"ldc %w1,ccr"				     \
-			: "=r"(retval),"=&r"(ccrsave),"=m"(*b_addr)  \
-			: "0" (retval),"r" (b_addr),"r"(nr)	     \
-			: "memory");				     \
-	}							     \
-	return retval;						     \
-}								     \
-								     \
-static __inline__ int __ ## FNNAME(int nr, volatile void * addr)     \
-{								     \
-	int retval = 0;						     \
-	volatile unsigned char *b_addr;				     \
-	b_addr = (volatile unsigned char *)addr + ((nr >> 3) ^ 3);   \
-	if (__builtin_constant_p(nr)) {				     \
-		switch(nr & 7) {				     \
-			H8300_GEN_TEST_BITOP_CONST(OP,0) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,1) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,2) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,3) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,4) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,5) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,6) 	     \
-			H8300_GEN_TEST_BITOP_CONST(OP,7) 	     \
-		}						     \
-	} else {						     \
-		__asm__("btst %w4,@%3\n\t"			     \
-			OP " %w4,@%3\n\t"			     \
-			"beq 1f\n\t"				     \
-			"inc.l #1,%0\n"				     \
-			"1:"					     \
-			: "=r"(retval),"=m"(*b_addr)		     \
-			: "0" (retval),"r" (b_addr),"r"(nr)	     \
-			: "memory");				     \
-	}							     \
-	return retval;						     \
-}
-
-H8300_GEN_TEST_BITOP(test_and_set_bit,	 "bset")
-H8300_GEN_TEST_BITOP(test_and_clear_bit, "bclr")
-H8300_GEN_TEST_BITOP(test_and_change_bit,"bnot")
-#undef H8300_GEN_TEST_BITOP_CONST
-#undef H8300_GEN_TEST_BITOP_CONST_INT
-#undef H8300_GEN_TEST_BITOP
-
-#include <asm-generic/bitops/ffs.h>
-
-static __inline__ unsigned long __ffs(unsigned long word)
-{
-	unsigned long result;
-
-	result = -1;
-	__asm__("1:\n\t"
-		"shlr.l %2\n\t"
-		"adds #1,%0\n\t"
-		"bcc 1b"
-		: "=r" (result)
-		: "0"(result),"r"(word));
-	return result;
-}
-
-#include <asm-generic/bitops/find.h>
-#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-#include <asm-generic/bitops/le.h>
-#include <asm-generic/bitops/ext2-atomic.h>
-
-#endif /* __KERNEL__ */
-
-#include <asm-generic/bitops/fls.h>
-#include <asm-generic/bitops/__fls.h>
-#include <asm-generic/bitops/fls64.h>
-
-#endif /* _H8300_BITOPS_H */
diff --git a/arch/h8300/include/asm/bootinfo.h b/arch/h8300/include/asm/bootinfo.h
deleted file mode 100644
index 5bed7e7aac0a..000000000000
--- a/arch/h8300/include/asm/bootinfo.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-/* Nothing for h8300 */
diff --git a/arch/h8300/include/asm/bug.h b/arch/h8300/include/asm/bug.h
deleted file mode 100644
index 1e1be8119935..000000000000
--- a/arch/h8300/include/asm/bug.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _H8300_BUG_H
-#define _H8300_BUG_H
-
-/* always true */
-#define is_valid_bugaddr(addr) (1)
-
-#include <asm-generic/bug.h>
-
-struct pt_regs;
-extern void die(const char *str, struct pt_regs *fp, unsigned long err);
-
-#endif
diff --git a/arch/h8300/include/asm/bugs.h b/arch/h8300/include/asm/bugs.h
deleted file mode 100644
index 1cb4afba6eb1..000000000000
--- a/arch/h8300/include/asm/bugs.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- *  include/asm-h8300/bugs.h
- *
- *  Copyright (C) 1994  Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *	void check_bugs(void);
- */
-
-static void check_bugs(void)
-{
-}
diff --git a/arch/h8300/include/asm/cache.h b/arch/h8300/include/asm/cache.h
deleted file mode 100644
index 05887a1d80e5..000000000000
--- a/arch/h8300/include/asm/cache.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ARCH_H8300_CACHE_H
-#define __ARCH_H8300_CACHE_H
-
-/* bytes per L1 cache line */
-#define        L1_CACHE_SHIFT  2
-#define        L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
-
-/* m68k-elf-gcc  2.95.2 doesn't like these */
-
-#define __cacheline_aligned
-#define ____cacheline_aligned
-
-#endif
diff --git a/arch/h8300/include/asm/cachectl.h b/arch/h8300/include/asm/cachectl.h
deleted file mode 100644
index c464022d8e26..000000000000
--- a/arch/h8300/include/asm/cachectl.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _H8300_CACHECTL_H
-#define _H8300_CACHECTL_H
-
-/* Definitions for the cacheflush system call.  */
-
-#define FLUSH_SCOPE_LINE    0	/* Flush a cache line */
-#define FLUSH_SCOPE_PAGE    0	/* Flush a page */
-#define FLUSH_SCOPE_ALL     0	/* Flush the whole cache -- superuser only */
-
-#define FLUSH_CACHE_DATA    0	/* Writeback and flush data cache */
-#define FLUSH_CACHE_INSN    0	/* Flush instruction cache */
-#define FLUSH_CACHE_BOTH    0	/* Flush both caches */
-
-#endif /* _H8300_CACHECTL_H */
diff --git a/arch/h8300/include/asm/cacheflush.h b/arch/h8300/include/asm/cacheflush.h
deleted file mode 100644
index 4cf2df20c1ce..000000000000
--- a/arch/h8300/include/asm/cacheflush.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * (C) Copyright 2002, Yoshinori Sato <ysato@users.sourceforge.jp>
- */
-
-#ifndef _ASM_H8300_CACHEFLUSH_H
-#define _ASM_H8300_CACHEFLUSH_H
-
-/*
- * Cache handling functions
- * No Cache memory all dummy functions
- */
-
-#define flush_cache_all()
-#define	flush_cache_mm(mm)
-#define	flush_cache_dup_mm(mm)		do { } while (0)
-#define	flush_cache_range(vma,a,b)
-#define	flush_cache_page(vma,p,pfn)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define	flush_dcache_page(page)
-#define	flush_dcache_mmap_lock(mapping)
-#define	flush_dcache_mmap_unlock(mapping)
-#define	flush_icache()
-#define	flush_icache_page(vma,page)
-#define	flush_icache_range(start,len)
-#define flush_cache_vmap(start, end)
-#define flush_cache_vunmap(start, end)
-#define	cache_push_v(vaddr,len)
-#define	cache_push(paddr,len)
-#define	cache_clear(paddr,len)
-
-#define	flush_dcache_range(a,b)
-
-#define	flush_icache_user_range(vma,page,addr,len)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-
-#endif /* _ASM_H8300_CACHEFLUSH_H */
diff --git a/arch/h8300/include/asm/checksum.h b/arch/h8300/include/asm/checksum.h
deleted file mode 100644
index 98724e12508c..000000000000
--- a/arch/h8300/include/asm/checksum.h
+++ /dev/null
@@ -1,102 +0,0 @@
-#ifndef _H8300_CHECKSUM_H
-#define _H8300_CHECKSUM_H
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-__wsum csum_partial(const void *buff, int len, __wsum sum);
-
-/*
- * the same as csum_partial, but copies from src while it
- * checksums
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
-
-
-/*
- * the same as csum_partial_copy, but copies from user space.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-
-extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
-						int len, __wsum sum, int *csum_err);
-
-__sum16 ip_fast_csum(const void *iph, unsigned int ihl);
-
-
-/*
- *	Fold a partial checksum
- */
-
-static inline __sum16 csum_fold(__wsum sum)
-{
-	__asm__("mov.l %0,er0\n\t"
-		"add.w e0,r0\n\t"
-		"xor.w e0,e0\n\t"
-		"rotxl.w e0\n\t"
-		"add.w e0,r0\n\t"
-		"sub.w e0,e0\n\t"
-		"mov.l er0,%0"
-		: "=r"(sum)
-		: "0"(sum)
-		: "er0");
-	return (__force __sum16)~sum;
-}
-
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-
-static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
-{
-	__asm__ ("sub.l er0,er0\n\t"
-		 "add.l %2,%0\n\t"
-		 "addx	#0,r0l\n\t"
-		 "add.l	%3,%0\n\t"
-		 "addx	#0,r0l\n\t"
-		 "add.l %4,%0\n\t"
-		 "addx	#0,r0l\n\t"
-		 "add.l	er0,%0\n\t"
-		 "bcc	1f\n\t"
-		 "inc.l	#1,%0\n"
-		 "1:"
-		 : "=&r" (sum)
-		 : "0" (sum), "r" (daddr), "r" (saddr), "r" (len + proto)
-		 :"er0");
-	return sum;
-}
-
-static inline __sum16
-csum_tcpudp_magic(__be32 saddr, __be32 daddr, unsigned short len,
-		  unsigned short proto, __wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-
-extern __sum16 ip_compute_csum(const void *buff, int len);
-
-#endif /* _H8300_CHECKSUM_H */
diff --git a/arch/h8300/include/asm/cmpxchg.h b/arch/h8300/include/asm/cmpxchg.h
deleted file mode 100644
index cdb203ef681f..000000000000
--- a/arch/h8300/include/asm/cmpxchg.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef __ARCH_H8300_CMPXCHG__
-#define __ARCH_H8300_CMPXCHG__
-
-#include <linux/irqflags.h>
-
-#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-struct __xchg_dummy { unsigned long a[100]; };
-#define __xg(x) ((volatile struct __xchg_dummy *)(x))
-
-static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
-{
-  unsigned long tmp, flags;
-
-  local_irq_save(flags);
-
-  switch (size) {
-  case 1:
-    __asm__ __volatile__
-    ("mov.b %2,%0\n\t"
-     "mov.b %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 2:
-    __asm__ __volatile__
-    ("mov.w %2,%0\n\t"
-     "mov.w %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  case 4:
-    __asm__ __volatile__
-    ("mov.l %2,%0\n\t"
-     "mov.l %1,%2"
-    : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)) : "memory");
-    break;
-  default:
-    tmp = 0;	  
-  }
-  local_irq_restore(flags);
-  return tmp;
-}
-
-#include <asm-generic/cmpxchg-local.h>
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#ifndef CONFIG_SMP
-#include <asm-generic/cmpxchg.h>
-#endif
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
-#endif /* __ARCH_H8300_CMPXCHG__ */
diff --git a/arch/h8300/include/asm/cputime.h b/arch/h8300/include/asm/cputime.h
deleted file mode 100644
index 092e187c7b08..000000000000
--- a/arch/h8300/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __H8300_CPUTIME_H
-#define __H8300_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __H8300_CPUTIME_H */
diff --git a/arch/h8300/include/asm/current.h b/arch/h8300/include/asm/current.h
deleted file mode 100644
index 57d74ee55a14..000000000000
--- a/arch/h8300/include/asm/current.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _H8300_CURRENT_H
-#define _H8300_CURRENT_H
-/*
- *	current.h
- *	(C) Copyright 2000, Lineo, David McCullough <davidm@lineo.com>
- *	(C) Copyright 2002, Greg Ungerer (gerg@snapgear.com)
- *
- *	rather than dedicate a register (as the m68k source does), we
- *	just keep a global,  we should probably just change it all to be
- *	current and lose _current_task.
- */
-
-#include <linux/thread_info.h>
-#include <asm/thread_info.h>
-
-struct task_struct;
-
-static inline struct task_struct *get_current(void)
-{
-	return(current_thread_info()->task);
-}
-
-#define	current	get_current()
-
-#endif /* _H8300_CURRENT_H */
diff --git a/arch/h8300/include/asm/dbg.h b/arch/h8300/include/asm/dbg.h
deleted file mode 100644
index 2c6d1cbcf736..000000000000
--- a/arch/h8300/include/asm/dbg.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#define DEBUG 1
-#define	BREAK asm volatile ("trap #3")
diff --git a/arch/h8300/include/asm/delay.h b/arch/h8300/include/asm/delay.h
deleted file mode 100644
index 743beba70f82..000000000000
--- a/arch/h8300/include/asm/delay.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef _H8300_DELAY_H
-#define _H8300_DELAY_H
-
-#include <asm/param.h>
-
-/*
- * Copyright (C) 2002 Yoshinori Sato <ysato@sourceforge.jp>
- *
- * Delay routines, using a pre-computed "loops_per_second" value.
- */
-
-static inline void __delay(unsigned long loops)
-{
-	__asm__ __volatile__ ("1:\n\t"
-			      "dec.l #1,%0\n\t"
-			      "bne 1b"
-			      :"=r" (loops):"0"(loops));
-}
-
-/*
- * Use only for very small delays ( < 1 msec).  Should probably use a
- * lookup table, really, as the multiplications take much too long with
- * short delays.  This is a "reasonable" implementation, though (and the
- * first constant multiplications gets optimized away if the delay is
- * a constant)  
- */
-
-extern unsigned long loops_per_jiffy;
-
-static inline void udelay(unsigned long usecs)
-{
-	usecs *= 4295;		/* 2**32 / 1000000 */
-	usecs /= (loops_per_jiffy*HZ);
-	if (usecs)
-		__delay(usecs);
-}
-
-#endif /* _H8300_DELAY_H */
diff --git a/arch/h8300/include/asm/device.h b/arch/h8300/include/asm/device.h
deleted file mode 100644
index d8f9872b0e2d..000000000000
--- a/arch/h8300/include/asm/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/arch/h8300/include/asm/div64.h b/arch/h8300/include/asm/div64.h
deleted file mode 100644
index 6cd978cefb28..000000000000
--- a/arch/h8300/include/asm/div64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/arch/h8300/include/asm/dma.h b/arch/h8300/include/asm/dma.h
deleted file mode 100644
index 3edbaaaedf5b..000000000000
--- a/arch/h8300/include/asm/dma.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _H8300_DMA_H
-#define _H8300_DMA_H 
- 
-
-/*
- * Set number of channels of DMA on ColdFire for different implementations.
- */
-#define MAX_DMA_CHANNELS 0
-#define MAX_DMA_ADDRESS PAGE_OFFSET
-
-/* These are in kernel/dma.c: */
-extern int request_dma(unsigned int dmanr, const char *device_id);	/* reserve a DMA channel */
-extern void free_dma(unsigned int dmanr);	/* release it again */
- 
-#endif /* _H8300_DMA_H */
diff --git a/arch/h8300/include/asm/elf.h b/arch/h8300/include/asm/elf.h
deleted file mode 100644
index 6db71248a82f..000000000000
--- a/arch/h8300/include/asm/elf.h
+++ /dev/null
@@ -1,101 +0,0 @@
-#ifndef __ASMH8300_ELF_H
-#define __ASMH8300_ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-typedef unsigned long elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ((x)->e_machine == EM_H8_300)
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA	ELFDATA2MSB
-#define ELF_ARCH	EM_H8_300
-#if defined(__H8300H__)
-#define ELF_CORE_EFLAGS 0x810000
-#endif
-#if defined(__H8300S__)
-#define ELF_CORE_EFLAGS 0x820000
-#endif
-
-#define ELF_PLAT_INIT(_r)	_r->er1 = 0
-
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE         0xD0000000UL
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-#define ELF_HWCAP	(0)
-
-/* This yields a string that ld.so will use to load implementation
-   specific libraries for optimization.  This is more specific in
-   intent than poking at uname or /proc/cpuinfo.  */
-
-#define ELF_PLATFORM  (NULL)
-
-#define R_H8_NONE       0
-#define R_H8_DIR32      1
-#define R_H8_DIR32_28   2
-#define R_H8_DIR32_24   3
-#define R_H8_DIR32_16   4
-#define R_H8_DIR32U     6
-#define R_H8_DIR32U_28  7
-#define R_H8_DIR32U_24  8
-#define R_H8_DIR32U_20  9
-#define R_H8_DIR32U_16 10
-#define R_H8_DIR24     11
-#define R_H8_DIR24_20  12
-#define R_H8_DIR24_16  13
-#define R_H8_DIR24U    14
-#define R_H8_DIR24U_20 15
-#define R_H8_DIR24U_16 16
-#define R_H8_DIR16     17
-#define R_H8_DIR16U    18
-#define R_H8_DIR16S_32 19
-#define R_H8_DIR16S_28 20
-#define R_H8_DIR16S_24 21
-#define R_H8_DIR16S_20 22
-#define R_H8_DIR16S    23
-#define R_H8_DIR8      24
-#define R_H8_DIR8U     25
-#define R_H8_DIR8Z_32  26
-#define R_H8_DIR8Z_28  27
-#define R_H8_DIR8Z_24  28
-#define R_H8_DIR8Z_20  29
-#define R_H8_DIR8Z_16  30
-#define R_H8_PCREL16   31
-#define R_H8_PCREL8    32
-#define R_H8_BPOS      33
-#define R_H8_PCREL32   34
-#define R_H8_GOT32O    35
-#define R_H8_GOT16O    36
-#define R_H8_DIR16A8   59
-#define R_H8_DIR16R8   60
-#define R_H8_DIR24A8   61
-#define R_H8_DIR24R8   62
-#define R_H8_DIR32A16  63
-#define R_H8_ABS32     65
-#define R_H8_ABS32A16 127
-
-#endif
diff --git a/arch/h8300/include/asm/emergency-restart.h b/arch/h8300/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/arch/h8300/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/h8300/include/asm/fb.h b/arch/h8300/include/asm/fb.h
deleted file mode 100644
index c7df38030992..000000000000
--- a/arch/h8300/include/asm/fb.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-#include <linux/fb.h>
-
-#define fb_pgprotect(...) do {} while (0)
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h
deleted file mode 100644
index bd12b31b90e6..000000000000
--- a/arch/h8300/include/asm/flat.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * include/asm-h8300/flat.h -- uClinux flat-format executables
- */
-
-#ifndef __H8300_FLAT_H__
-#define __H8300_FLAT_H__
-
-#define	flat_argvp_envp_on_stack()		1
-#define	flat_old_ram_flag(flags)		1
-#define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_set_persistent(relval, p)		0
-
-/*
- * on the H8 a couple of the relocations have an instruction in the
- * top byte.  As there can only be 24bits of address space,  we just
- * always preserve that 8bits at the top,  when it isn't an instruction
- * is is 0 (davidm@snapgear.com)
- */
-
-#define	flat_get_relocate_addr(rel)		(rel)
-#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
-        (get_unaligned(rp) & ((flags & FLAT_FLAG_GOTPIC) ? 0xffffffff: 0x00ffffff))
-#define flat_put_addr_at_rp(rp, addr, rel) \
-	put_unaligned (((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), rp)
-
-#endif /* __H8300_FLAT_H__ */
diff --git a/arch/h8300/include/asm/fpu.h b/arch/h8300/include/asm/fpu.h
deleted file mode 100644
index 4fc416e80bef..000000000000
--- a/arch/h8300/include/asm/fpu.h
+++ /dev/null
@@ -1 +0,0 @@
-/* Nothing do */
diff --git a/arch/h8300/include/asm/ftrace.h b/arch/h8300/include/asm/ftrace.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/h8300/include/asm/ftrace.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/h8300/include/asm/futex.h b/arch/h8300/include/asm/futex.h
deleted file mode 100644
index 6a332a9f099c..000000000000
--- a/arch/h8300/include/asm/futex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_FUTEX_H
-#define _ASM_FUTEX_H
-
-#include <asm-generic/futex.h>
-
-#endif
diff --git a/arch/h8300/include/asm/gpio-internal.h b/arch/h8300/include/asm/gpio-internal.h
deleted file mode 100644
index a714f0c0efbc..000000000000
--- a/arch/h8300/include/asm/gpio-internal.h
+++ /dev/null
@@ -1,52 +0,0 @@
-#ifndef _H8300_GPIO_H
-#define _H8300_GPIO_H
-
-#define H8300_GPIO_P1 0
-#define H8300_GPIO_P2 1
-#define H8300_GPIO_P3 2
-#define H8300_GPIO_P4 3
-#define H8300_GPIO_P5 4
-#define H8300_GPIO_P6 5
-#define H8300_GPIO_P7 6
-#define H8300_GPIO_P8 7
-#define H8300_GPIO_P9 8
-#define H8300_GPIO_PA 9
-#define H8300_GPIO_PB 10
-#define H8300_GPIO_PC 11
-#define H8300_GPIO_PD 12
-#define H8300_GPIO_PE 13
-#define H8300_GPIO_PF 14
-#define H8300_GPIO_PG 15
-#define H8300_GPIO_PH 16
-
-#define H8300_GPIO_B7 0x80
-#define H8300_GPIO_B6 0x40
-#define H8300_GPIO_B5 0x20
-#define H8300_GPIO_B4 0x10
-#define H8300_GPIO_B3 0x08
-#define H8300_GPIO_B2 0x04
-#define H8300_GPIO_B1 0x02
-#define H8300_GPIO_B0 0x01
-
-#define H8300_GPIO_INPUT 0
-#define H8300_GPIO_OUTPUT 1
-
-#define H8300_GPIO_RESERVE(port, bits) \
-        h8300_reserved_gpio(port, bits)
-
-#define H8300_GPIO_FREE(port, bits) \
-        h8300_free_gpio(port, bits)
-
-#define H8300_GPIO_DDR(port, bit, dir) \
-        h8300_set_gpio_dir(((port) << 8) | (bit), dir)
-
-#define H8300_GPIO_GETDIR(port, bit) \
-        h8300_get_gpio_dir(((port) << 8) | (bit))
-
-extern int h8300_reserved_gpio(int port, int bits);
-extern int h8300_free_gpio(int port, int bits);
-extern int h8300_set_gpio_dir(int port_bit, int dir);
-extern int h8300_get_gpio_dir(int port_bit);
-extern int h8300_init_gpio(void);
-
-#endif
diff --git a/arch/h8300/include/asm/hardirq.h b/arch/h8300/include/asm/hardirq.h
deleted file mode 100644
index c2e1aa0f0d14..000000000000
--- a/arch/h8300/include/asm/hardirq.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef __H8300_HARDIRQ_H
-#define __H8300_HARDIRQ_H
-
-#include <asm/irq.h>
-
-#define HARDIRQ_BITS	8
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
-#include <asm-generic/hardirq.h>
-
-#endif
diff --git a/arch/h8300/include/asm/hw_irq.h b/arch/h8300/include/asm/hw_irq.h
deleted file mode 100644
index d75a5a1119e8..000000000000
--- a/arch/h8300/include/asm/hw_irq.h
+++ /dev/null
@@ -1 +0,0 @@
-/* Do Nothing */
diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h
deleted file mode 100644
index c1a8df22080f..000000000000
--- a/arch/h8300/include/asm/io.h
+++ /dev/null
@@ -1,358 +0,0 @@
-#ifndef _H8300_IO_H
-#define _H8300_IO_H
-
-#ifdef __KERNEL__
-
-#include <asm/virtconvert.h>
-
-#if defined(CONFIG_H83007) || defined(CONFIG_H83068)
-#include <asm/regs306x.h>
-#elif defined(CONFIG_H8S2678)
-#include <asm/regs267x.h>
-#else
-#error UNKNOWN CPU TYPE
-#endif
-
-
-/*
- * These are for ISA/PCI shared memory _only_ and should never be used
- * on any other type of memory, including Zorro memory. They are meant to
- * access the bus in the bus byte order which is little-endian!.
- *
- * readX/writeX() are used to access memory mapped devices. On some
- * architectures the memory mapped IO stuff needs to be accessed
- * differently. On the m68k architecture, we just read/write the
- * memory location directly.
- */
-/* ++roman: The assignments to temp. vars avoid that gcc sometimes generates
- * two accesses to memory, which may be undesirable for some devices.
- */
-
-/*
- * swap functions are sometimes needed to interface little-endian hardware
- */
-
-static inline unsigned short _swapw(volatile unsigned short v)
-{
-#ifndef H8300_IO_NOSWAP
-	unsigned short r;
-	__asm__("xor.b %w0,%x0\n\t"
-		"xor.b %x0,%w0\n\t"
-		"xor.b %w0,%x0"
-		:"=r"(r)
-		:"0"(v));
-	return r;
-#else
-	return v;
-#endif
-}
-
-static inline unsigned long _swapl(volatile unsigned long v)
-{
-#ifndef H8300_IO_NOSWAP
-	unsigned long r;
-	__asm__("xor.b %w0,%x0\n\t"
-		"xor.b %x0,%w0\n\t"
-		"xor.b %w0,%x0\n\t"
-		"xor.w %e0,%f0\n\t"
-		"xor.w %f0,%e0\n\t"
-		"xor.w %e0,%f0\n\t"
-		"xor.b %w0,%x0\n\t"
-		"xor.b %x0,%w0\n\t"
-		"xor.b %w0,%x0"
-		:"=r"(r)
-		:"0"(v));
-	return r;
-#else
-	return v;
-#endif
-}
-
-#define readb(addr) \
-    ({ unsigned char __v = \
-     *(volatile unsigned char *)((unsigned long)(addr) & 0x00ffffff); \
-     __v; })
-#define readw(addr) \
-    ({ unsigned short __v = \
-     *(volatile unsigned short *)((unsigned long)(addr) & 0x00ffffff); \
-     __v; })
-#define readl(addr) \
-    ({ unsigned long __v = \
-     *(volatile unsigned long *)((unsigned long)(addr) & 0x00ffffff); \
-     __v; })
-
-#define writeb(b,addr) (void)((*(volatile unsigned char *) \
-                             ((unsigned long)(addr) & 0x00ffffff)) = (b))
-#define writew(b,addr) (void)((*(volatile unsigned short *) \
-                             ((unsigned long)(addr) & 0x00ffffff)) = (b))
-#define writel(b,addr) (void)((*(volatile unsigned long *) \
-                             ((unsigned long)(addr) & 0x00ffffff)) = (b))
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-
-#define __raw_readb readb
-#define __raw_readw readw
-#define __raw_readl readl
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-
-static inline int h8300_buswidth(unsigned int addr)
-{
-	return (*(volatile unsigned char *)ABWCR & (1 << ((addr >> 21) & 7))) == 0;
-}
-
-static inline void io_outsb(unsigned int addr, const void *buf, int len)
-{
-	volatile unsigned char  *ap_b = (volatile unsigned char *) addr;
-	volatile unsigned short *ap_w = (volatile unsigned short *) addr;
-	unsigned char *bp = (unsigned char *) buf;
-
-	if(h8300_buswidth(addr) && (addr & 1)) {
-		while (len--)
-			*ap_w = *bp++;
-	} else {
-		while (len--)
-			*ap_b = *bp++;
-	}
-}
-
-static inline void io_outsw(unsigned int addr, const void *buf, int len)
-{
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*ap = _swapw(*bp++);
-}
-
-static inline void io_outsl(unsigned int addr, const void *buf, int len)
-{
-	volatile unsigned long *ap = (volatile unsigned long *) addr;
-	unsigned long *bp = (unsigned long *) buf;
-	while (len--)
-		*ap = _swapl(*bp++);
-}
-
-static inline void io_outsw_noswap(unsigned int addr, const void *buf, int len)
-{
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*ap = *bp++;
-}
-
-static inline void io_outsl_noswap(unsigned int addr, const void *buf, int len)
-{
-	volatile unsigned long *ap = (volatile unsigned long *) addr;
-	unsigned long *bp = (unsigned long *) buf;
-	while (len--)
-		*ap = *bp++;
-}
-
-static inline void io_insb(unsigned int addr, void *buf, int len)
-{
-	volatile unsigned char  *ap_b;
-	volatile unsigned short *ap_w;
-	unsigned char *bp = (unsigned char *) buf;
-
-	if(h8300_buswidth(addr)) {
-		ap_w = (volatile unsigned short *)(addr & ~1);
-		while (len--)
-			*bp++ = *ap_w & 0xff;
-	} else {
-		ap_b = (volatile unsigned char *)addr;
-		while (len--)
-			*bp++ = *ap_b;
-	}
-}
-
-static inline void io_insw(unsigned int addr, void *buf, int len)
-{
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*bp++ = _swapw(*ap);
-}
-
-static inline void io_insl(unsigned int addr, void *buf, int len)
-{
-	volatile unsigned long *ap = (volatile unsigned long *) addr;
-	unsigned long *bp = (unsigned long *) buf;
-	while (len--)
-		*bp++ = _swapl(*ap);
-}
-
-static inline void io_insw_noswap(unsigned int addr, void *buf, int len)
-{
-	volatile unsigned short *ap = (volatile unsigned short *) addr;
-	unsigned short *bp = (unsigned short *) buf;
-	while (len--)
-		*bp++ = *ap;
-}
-
-static inline void io_insl_noswap(unsigned int addr, void *buf, int len)
-{
-	volatile unsigned long *ap = (volatile unsigned long *) addr;
-	unsigned long *bp = (unsigned long *) buf;
-	while (len--)
-		*bp++ = *ap;
-}
-
-/*
- *	make the short names macros so specific devices
- *	can override them as required
- */
-
-#define memset_io(a,b,c)	memset((void *)(a),(b),(c))
-#define memcpy_fromio(a,b,c)	memcpy((a),(void *)(b),(c))
-#define memcpy_toio(a,b,c)	memcpy((void *)(a),(b),(c))
-
-#define mmiowb()
-
-#define inb(addr)    ((h8300_buswidth(addr))?readw((addr) & ~1) & 0xff:readb(addr))
-#define inw(addr)    _swapw(readw(addr))
-#define inl(addr)    _swapl(readl(addr))
-#define outb(x,addr) ((void)((h8300_buswidth(addr) && \
-                      ((addr) & 1))?writew(x,(addr) & ~1):writeb(x,addr)))
-#define outw(x,addr) ((void) writew(_swapw(x),addr))
-#define outl(x,addr) ((void) writel(_swapl(x),addr))
-
-#define inb_p(addr)    inb(addr)
-#define inw_p(addr)    inw(addr)
-#define inl_p(addr)    inl(addr)
-#define outb_p(x,addr) outb(x,addr)
-#define outw_p(x,addr) outw(x,addr)
-#define outl_p(x,addr) outl(x,addr)
-
-#define outsb(a,b,l) io_outsb(a,b,l)
-#define outsw(a,b,l) io_outsw(a,b,l)
-#define outsl(a,b,l) io_outsl(a,b,l)
-
-#define insb(a,b,l) io_insb(a,b,l)
-#define insw(a,b,l) io_insw(a,b,l)
-#define insl(a,b,l) io_insl(a,b,l)
-
-#define IO_SPACE_LIMIT 0xffffff
-
-
-/* Values for nocacheflag and cmode */
-#define IOMAP_FULL_CACHING		0
-#define IOMAP_NOCACHE_SER		1
-#define IOMAP_NOCACHE_NONSER		2
-#define IOMAP_WRITETHROUGH		3
-
-extern void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag);
-extern void __iounmap(void *addr, unsigned long size);
-
-static inline void *ioremap(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
-}
-static inline void *ioremap_writethrough(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
-}
-static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size)
-{
-	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
-}
-
-extern void iounmap(void *addr);
-
-/* H8/300 internal I/O functions */
-static __inline__ unsigned char ctrl_inb(unsigned long addr)
-{
-	return *(volatile unsigned char*)addr;
-}
-
-static __inline__ unsigned short ctrl_inw(unsigned long addr)
-{
-	return *(volatile unsigned short*)addr;
-}
-
-static __inline__ unsigned long ctrl_inl(unsigned long addr)
-{
-	return *(volatile unsigned long*)addr;
-}
-
-static __inline__ void ctrl_outb(unsigned char b, unsigned long addr)
-{
-	*(volatile unsigned char*)addr = b;
-}
-
-static __inline__ void ctrl_outw(unsigned short b, unsigned long addr)
-{
-	*(volatile unsigned short*)addr = b;
-}
-
-static __inline__ void ctrl_outl(unsigned long b, unsigned long addr)
-{
-        *(volatile unsigned long*)addr = b;
-}
-
-static __inline__ void ctrl_bclr(int b, unsigned long addr)
-{
-	if (__builtin_constant_p(b))
-		switch (b) {
-		case 0: __asm__("bclr #0,@%0"::"r"(addr)); break;
-		case 1: __asm__("bclr #1,@%0"::"r"(addr)); break;
-		case 2: __asm__("bclr #2,@%0"::"r"(addr)); break;
-		case 3: __asm__("bclr #3,@%0"::"r"(addr)); break;
-		case 4: __asm__("bclr #4,@%0"::"r"(addr)); break;
-		case 5: __asm__("bclr #5,@%0"::"r"(addr)); break;
-		case 6: __asm__("bclr #6,@%0"::"r"(addr)); break;
-		case 7: __asm__("bclr #7,@%0"::"r"(addr)); break;
-		}
-	else
-		__asm__("bclr %w0,@%1"::"r"(b), "r"(addr));
-}
-
-static __inline__ void ctrl_bset(int b, unsigned long addr)
-{
-	if (__builtin_constant_p(b))
-		switch (b) {
-		case 0: __asm__("bset #0,@%0"::"r"(addr)); break;
-		case 1: __asm__("bset #1,@%0"::"r"(addr)); break;
-		case 2: __asm__("bset #2,@%0"::"r"(addr)); break;
-		case 3: __asm__("bset #3,@%0"::"r"(addr)); break;
-		case 4: __asm__("bset #4,@%0"::"r"(addr)); break;
-		case 5: __asm__("bset #5,@%0"::"r"(addr)); break;
-		case 6: __asm__("bset #6,@%0"::"r"(addr)); break;
-		case 7: __asm__("bset #7,@%0"::"r"(addr)); break;
-		}
-	else
-		__asm__("bset %w0,@%1"::"r"(b), "r"(addr));
-}
-
-/* Pages to physical address... */
-#define page_to_phys(page)      ((page - mem_map) << PAGE_SHIFT)
-#define page_to_bus(page)       ((page - mem_map) << PAGE_SHIFT)
-
-/*
- * Macros used for converting between virtual and physical mappings.
- */
-#define phys_to_virt(vaddr)	((void *) (vaddr))
-#define virt_to_phys(vaddr)	((unsigned long) (vaddr))
-
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-#endif /* __KERNEL__ */
-
-#endif /* _H8300_IO_H */
diff --git a/arch/h8300/include/asm/irq.h b/arch/h8300/include/asm/irq.h
deleted file mode 100644
index 13d7c601cd0a..000000000000
--- a/arch/h8300/include/asm/irq.h
+++ /dev/null
@@ -1,49 +0,0 @@
-#ifndef _H8300_IRQ_H_
-#define _H8300_IRQ_H_
-
-#include <asm/ptrace.h>
-
-#if defined(CONFIG_CPU_H8300H)
-#define NR_IRQS 64
-#define EXT_IRQ0 12
-#define EXT_IRQ1 13
-#define EXT_IRQ2 14
-#define EXT_IRQ3 15
-#define EXT_IRQ4 16
-#define EXT_IRQ5 17
-#define EXT_IRQ6 18
-#define EXT_IRQ7 19
-#define EXT_IRQS 5
-#define IER_REGS *(volatile unsigned char *)IER
-#endif
-#if defined(CONFIG_CPU_H8S)
-#define NR_IRQS 128
-#define EXT_IRQ0 16
-#define EXT_IRQ1 17
-#define EXT_IRQ2 18
-#define EXT_IRQ3 19
-#define EXT_IRQ4 20
-#define EXT_IRQ5 21
-#define EXT_IRQ6 22
-#define EXT_IRQ7 23
-#define EXT_IRQ8 24
-#define EXT_IRQ9 25
-#define EXT_IRQ10 26
-#define EXT_IRQ11 27
-#define EXT_IRQ12 28
-#define EXT_IRQ13 29
-#define EXT_IRQ14 30
-#define EXT_IRQ15 31
-#define EXT_IRQS 15
-
-#define IER_REGS *(volatile unsigned short *)IER
-#endif
-
-static __inline__ int irq_canonicalize(int irq)
-{
-	return irq;
-}
-
-typedef void (*h8300_vector)(void);
-
-#endif /* _H8300_IRQ_H_ */
diff --git a/arch/h8300/include/asm/irq_regs.h b/arch/h8300/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/arch/h8300/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/h8300/include/asm/irqflags.h b/arch/h8300/include/asm/irqflags.h
deleted file mode 100644
index 9617cd57aebd..000000000000
--- a/arch/h8300/include/asm/irqflags.h
+++ /dev/null
@@ -1,43 +0,0 @@
-#ifndef _H8300_IRQFLAGS_H
-#define _H8300_IRQFLAGS_H
-
-static inline unsigned long arch_local_save_flags(void)
-{
-	unsigned long flags;
-	asm volatile ("stc ccr,%w0" : "=r" (flags));
-	return flags;
-}
-
-static inline void arch_local_irq_disable(void)
-{
-	asm volatile ("orc  #0x80,ccr" : : : "memory");
-}
-
-static inline void arch_local_irq_enable(void)
-{
-	asm volatile ("andc #0x7f,ccr" : : : "memory");
-}
-
-static inline unsigned long arch_local_irq_save(void)
-{
-	unsigned long flags = arch_local_save_flags();
-	arch_local_irq_disable();
-	return flags;
-}
-
-static inline void arch_local_irq_restore(unsigned long flags)
-{
-	asm volatile ("ldc %w0,ccr" : : "r" (flags) : "memory");
-}
-
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
-{
-	return (flags & 0x80) == 0x80;
-}
-
-static inline bool arch_irqs_disabled(void)
-{
-	return arch_irqs_disabled_flags(arch_local_save_flags());
-}
-
-#endif /* _H8300_IRQFLAGS_H */
diff --git a/arch/h8300/include/asm/kdebug.h b/arch/h8300/include/asm/kdebug.h
deleted file mode 100644
index 6ece1b037665..000000000000
--- a/arch/h8300/include/asm/kdebug.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kdebug.h>
diff --git a/arch/h8300/include/asm/kmap_types.h b/arch/h8300/include/asm/kmap_types.h
deleted file mode 100644
index be12a7160116..000000000000
--- a/arch/h8300/include/asm/kmap_types.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_H8300_KMAP_TYPES_H
-#define _ASM_H8300_KMAP_TYPES_H
-
-#include <asm-generic/kmap_types.h>
-
-#endif
diff --git a/arch/h8300/include/asm/local.h b/arch/h8300/include/asm/local.h
deleted file mode 100644
index fdd4efe437cd..000000000000
--- a/arch/h8300/include/asm/local.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_LOCAL_H_
-#define _H8300_LOCAL_H_
-
-#include <asm-generic/local.h>
-
-#endif
diff --git a/arch/h8300/include/asm/local64.h b/arch/h8300/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/h8300/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/h8300/include/asm/mc146818rtc.h b/arch/h8300/include/asm/mc146818rtc.h
deleted file mode 100644
index ab9d9646d241..000000000000
--- a/arch/h8300/include/asm/mc146818rtc.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef _H8300_MC146818RTC_H
-#define _H8300_MC146818RTC_H
-
-/* empty include file to satisfy the include in genrtc.c/ide-geometry.c */
-
-#endif /* _H8300_MC146818RTC_H */
diff --git a/arch/h8300/include/asm/mmu_context.h b/arch/h8300/include/asm/mmu_context.h
deleted file mode 100644
index f44b730da54d..000000000000
--- a/arch/h8300/include/asm/mmu_context.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef __H8300_MMU_CONTEXT_H
-#define __H8300_MMU_CONTEXT_H
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm-generic/mm_hooks.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-static inline int
-init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
-	// mm->context = virt_to_phys(mm->pgd);
-	return(0);
-}
-
-#define destroy_context(mm)		do { } while(0)
-#define deactivate_mm(tsk,mm)           do { } while(0)
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
-{
-}
-
-static inline void activate_mm(struct mm_struct *prev_mm,
-			       struct mm_struct *next_mm)
-{
-}
-
-#endif
diff --git a/arch/h8300/include/asm/mutex.h b/arch/h8300/include/asm/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/arch/h8300/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/h8300/include/asm/page.h b/arch/h8300/include/asm/page.h
deleted file mode 100644
index 837381a2df46..000000000000
--- a/arch/h8300/include/asm/page.h
+++ /dev/null
@@ -1,78 +0,0 @@
-#ifndef _H8300_PAGE_H
-#define _H8300_PAGE_H
-
-/* PAGE_SHIFT determines the page size */
-
-#define PAGE_SHIFT	(12)
-#define PAGE_SIZE	(1UL << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
-
-#include <asm/setup.h>
-
-#ifndef __ASSEMBLY__
- 
-#define get_user_page(vaddr)		__get_free_page(GFP_KERNEL)
-#define free_user_page(page, addr)	free_page(addr)
-
-#define clear_page(page)	memset((page), 0, PAGE_SIZE)
-#define copy_page(to,from)	memcpy((to), (from), PAGE_SIZE)
-
-#define clear_user_page(page, vaddr, pg)	clear_page(page)
-#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
-
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned long pmd[16]; } pmd_t;
-typedef struct { unsigned long pgd; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-typedef struct page *pgtable_t;
-
-#define pte_val(x)	((x).pte)
-#define pmd_val(x)	((&x)->pmd[0])
-#define pgd_val(x)	((x).pgd)
-#define pgprot_val(x)	((x).pgprot)
-
-#define __pte(x)	((pte_t) { (x) } )
-#define __pmd(x)	((pmd_t) { (x) } )
-#define __pgd(x)	((pgd_t) { (x) } )
-#define __pgprot(x)	((pgprot_t) { (x) } )
-
-extern unsigned long memory_start;
-extern unsigned long memory_end;
-
-#endif /* !__ASSEMBLY__ */
-
-#include <asm/page_offset.h>
-
-#define PAGE_OFFSET		(PAGE_OFFSET_RAW)
-
-#ifndef __ASSEMBLY__
-
-#define __pa(vaddr)		virt_to_phys(vaddr)
-#define __va(paddr)		phys_to_virt((unsigned long)paddr)
-
-#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
-#define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
-
-#define MAP_NR(addr)		(((unsigned long)(addr)-PAGE_OFFSET) >> PAGE_SHIFT)
-#define virt_to_page(addr)	(mem_map + (((unsigned long)(addr)-PAGE_OFFSET) >> PAGE_SHIFT))
-#define page_to_virt(page)	((((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET)
-#define pfn_valid(page)	        (page < max_mapnr)
-
-#define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
-
-#define	virt_addr_valid(kaddr)	(((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
-				((void *)(kaddr) < (void *)memory_end))
-
-#endif /* __ASSEMBLY__ */
-
-#include <asm-generic/memory_model.h>
-#include <asm-generic/getorder.h>
-
-#endif /* _H8300_PAGE_H */
diff --git a/arch/h8300/include/asm/page_offset.h b/arch/h8300/include/asm/page_offset.h
deleted file mode 100644
index f8706463008c..000000000000
--- a/arch/h8300/include/asm/page_offset.h
+++ /dev/null
@@ -1,3 +0,0 @@
-
-#define PAGE_OFFSET_RAW		0x00000000
-
diff --git a/arch/h8300/include/asm/param.h b/arch/h8300/include/asm/param.h
deleted file mode 100644
index c3909e7ff178..000000000000
--- a/arch/h8300/include/asm/param.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _H8300_PARAM_H
-#define _H8300_PARAM_H
-
-#include <uapi/asm/param.h>
-
-#define HZ		CONFIG_HZ
-#define	USER_HZ		HZ
-#define	CLOCKS_PER_SEC	(USER_HZ)
-#endif /* _H8300_PARAM_H */
diff --git a/arch/h8300/include/asm/pci.h b/arch/h8300/include/asm/pci.h
deleted file mode 100644
index 0b2acaa3dd84..000000000000
--- a/arch/h8300/include/asm/pci.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef _ASM_H8300_PCI_H
-#define _ASM_H8300_PCI_H
-
-/*
- * asm-h8300/pci.h - H8/300 specific PCI declarations.
- *
- * Yoshinori Sato <ysato@users.sourceforge.jp>
- */
-
-#define pcibios_assign_all_busses()	0
-
-static inline void pcibios_penalize_isa_irq(int irq, int active)
-{
-	/* We don't do dynamic PCI IRQ allocation */
-}
-
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-#endif /* _ASM_H8300_PCI_H */
diff --git a/arch/h8300/include/asm/percpu.h b/arch/h8300/include/asm/percpu.h
deleted file mode 100644
index 72c03e3666d8..000000000000
--- a/arch/h8300/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ARCH_H8300_PERCPU__
-#define __ARCH_H8300_PERCPU__
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_H8300_PERCPU__ */
diff --git a/arch/h8300/include/asm/pgalloc.h b/arch/h8300/include/asm/pgalloc.h
deleted file mode 100644
index c2e89a286d23..000000000000
--- a/arch/h8300/include/asm/pgalloc.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _H8300_PGALLOC_H
-#define _H8300_PGALLOC_H
-
-#include <asm/setup.h>
-
-#define check_pgt_cache()	do { } while (0)
-
-#endif /* _H8300_PGALLOC_H */
diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h
deleted file mode 100644
index 7ca20f894dd7..000000000000
--- a/arch/h8300/include/asm/pgtable.h
+++ /dev/null
@@ -1,73 +0,0 @@
-#ifndef _H8300_PGTABLE_H
-#define _H8300_PGTABLE_H
-
-#include <asm-generic/4level-fixup.h>
-
-#include <linux/slab.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/io.h>
-
-#define pgd_present(pgd)     (1)       /* pages are always present on NO_MM */
-#define pgd_none(pgd)		(0)
-#define pgd_bad(pgd)		(0)
-#define pgd_clear(pgdp)
-#define kern_addr_valid(addr)	(1)
-#define	pmd_offset(a, b)	((void *)0)
-#define pmd_none(pmd)           (1)
-#define pgd_offset_k(adrdress)  ((pgd_t *)0)
-#define pte_offset_kernel(dir, address) ((pte_t *)0)
-
-#define PAGE_NONE		__pgprot(0)    /* these mean nothing to NO_MM */
-#define PAGE_SHARED		__pgprot(0)    /* these mean nothing to NO_MM */
-#define PAGE_COPY		__pgprot(0)    /* these mean nothing to NO_MM */
-#define PAGE_READONLY	__pgprot(0)    /* these mean nothing to NO_MM */
-#define PAGE_KERNEL		__pgprot(0)    /* these mean nothing to NO_MM */
-
-extern void paging_init(void);
-#define swapper_pg_dir ((pgd_t *) 0)
-
-#define __swp_type(x)		(0)
-#define __swp_offset(x)		(0)
-#define __swp_entry(typ,off)	((swp_entry_t) { ((typ) | ((off) << 7)) })
-#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
-
-static inline int pte_file(pte_t pte) { return 0; }
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-#define ZERO_PAGE(vaddr)	(virt_to_page(0))
-
-/*
- * These would be in other places but having them here reduces the diffs.
- */
-extern unsigned int kobjsize(const void *objp);
-extern int is_in_rom(unsigned long);
-
-/*
- * No page table caches to initialise
- */
-#define pgtable_cache_init()   do { } while (0)
-
-/*
- * All 32bit addresses are effectively valid for vmalloc...
- * Sort of meaningless for non-VM targets.
- */
-#define	VMALLOC_START	0
-#define	VMALLOC_END	0xffffffff
-
-/*
- * All 32bit addresses are effectively valid for vmalloc...
- * Sort of meaningless for non-VM targets.
- */
-#define	VMALLOC_START	0
-#define	VMALLOC_END	0xffffffff
-
-#define arch_enter_lazy_cpu_mode()    do {} while (0)
-
-#include <asm-generic/pgtable.h>
-
-#endif /* _H8300_PGTABLE_H */
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
deleted file mode 100644
index 4b0ca49bb463..000000000000
--- a/arch/h8300/include/asm/processor.h
+++ /dev/null
@@ -1,139 +0,0 @@
-/*
- * include/asm-h8300/processor.h
- *
- * Copyright (C) 2002 Yoshinori Sato
- *
- * Based on: linux/asm-m68nommu/processor.h
- *
- * Copyright (C) 1995 Hamish Macdonald
- */
-
-#ifndef __ASM_H8300_PROCESSOR_H
-#define __ASM_H8300_PROCESSOR_H
-
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-#define current_text_addr() ({ __label__ _l; _l: &&_l;})
-
-#include <linux/compiler.h>
-#include <asm/segment.h>
-#include <asm/fpu.h>
-#include <asm/ptrace.h>
-#include <asm/current.h>
-
-static inline unsigned long rdusp(void) {
-	extern unsigned int	sw_usp;
-	return(sw_usp);
-}
-
-static inline void wrusp(unsigned long usp) {
-	extern unsigned int	sw_usp;
-	sw_usp = usp;
-}
-
-/*
- * User space process size: 3.75GB. This is hardcoded into a few places,
- * so don't change it unless you know what you are doing.
- */
-#define TASK_SIZE	(0xFFFFFFFFUL)
-
-#ifdef __KERNEL__
-#define STACK_TOP	TASK_SIZE
-#define STACK_TOP_MAX	STACK_TOP
-#endif
-
-/*
- * This decides where the kernel will search for a free chunk of vm
- * space during mmap's. We won't be using it
- */
-#define TASK_UNMAPPED_BASE	0
-
-struct thread_struct {
-	unsigned long  ksp;		/* kernel stack pointer */
-	unsigned long  usp;		/* user stack pointer */
-	unsigned long  ccr;		/* saved status register */
-	unsigned long  esp0;            /* points to SR of stack frame */
-	struct {
-		unsigned short *addr;
-		unsigned short inst;
-	} breakinfo;
-};
-
-#define INIT_THREAD  {						\
-	.ksp  = sizeof(init_stack) + (unsigned long)init_stack, \
-	.usp  = 0,						\
-	.ccr  = PS_S,						\
-	.esp0 = 0,						\
-	.breakinfo = {						\
-		.addr = (unsigned short *)-1,			\
-		.inst = 0					\
-	}							\
-}
-
-/*
- * Do necessary setup to start up a newly executed thread.
- *
- * pass the data segment into user programs if it exists,
- * it can't hurt anything as far as I can tell
- */
-#if defined(__H8300H__)
-#define start_thread(_regs, _pc, _usp)			        \
-do {							        \
-  	(_regs)->pc = (_pc);				        \
-	(_regs)->ccr = 0x00;	   /* clear all flags */        \
-	(_regs)->er5 = current->mm->start_data;	/* GOT base */  \
-	wrusp((unsigned long)(_usp) - sizeof(unsigned long)*3);	\
-} while(0)
-#endif
-#if defined(__H8300S__)
-#define start_thread(_regs, _pc, _usp)			        \
-do {							        \
-	(_regs)->pc = (_pc);				        \
-	(_regs)->ccr = 0x00;	   /* clear kernel flag */      \
-	(_regs)->exr = 0x78;       /* enable all interrupts */  \
-	(_regs)->er5 = current->mm->start_data;	/* GOT base */  \
-	/* 14 = space for retaddr(4), vector(4), er0(4) and ext(2) on stack */ \
-	wrusp(((unsigned long)(_usp)) - 14);                    \
-} while(0)
-#endif
-
-/* Forward declaration, a strange C thing */
-struct task_struct;
-
-/* Free all resources held by a thread. */
-static inline void release_thread(struct task_struct *dead_task)
-{
-}
-
-/*
- * Free current thread data structures etc..
- */
-static inline void exit_thread(void)
-{
-}
-
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk);
-unsigned long get_wchan(struct task_struct *p);
-
-#define	KSTK_EIP(tsk)	\
-    ({			\
-	unsigned long eip = 0;	 \
-	if ((tsk)->thread.esp0 > PAGE_SIZE && \
-	    MAP_NR((tsk)->thread.esp0) < max_mapnr) \
-	      eip = ((struct pt_regs *) (tsk)->thread.esp0)->pc; \
-	eip; })
-#define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
-
-#define cpu_relax()    barrier()
-
-#define HARD_RESET_NOW() ({		\
-        local_irq_disable();		\
-        asm("jmp @@0");			\
-})
-
-#endif
diff --git a/arch/h8300/include/asm/ptrace.h b/arch/h8300/include/asm/ptrace.h
deleted file mode 100644
index c1826b95c5ca..000000000000
--- a/arch/h8300/include/asm/ptrace.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef _H8300_PTRACE_H
-#define _H8300_PTRACE_H
-
-#include <uapi/asm/ptrace.h>
-
-#ifndef __ASSEMBLY__
-#if defined(CONFIG_CPU_H8S)
-#endif
-#ifndef PS_S
-#define PS_S  (0x10)
-#endif
-
-#if defined(__H8300H__)
-#define H8300_REGS_NO 11
-#endif
-#if defined(__H8300S__)
-#define H8300_REGS_NO 12
-#endif
-
-/* Find the stack offset for a register, relative to thread.esp0. */
-#define PT_REG(reg)	((long)&((struct pt_regs *)0)->reg)
-
-#define arch_has_single_step()	(1)
-
-#define user_mode(regs) (!((regs)->ccr & PS_S))
-#define instruction_pointer(regs) ((regs)->pc)
-#define profile_pc(regs) instruction_pointer(regs)
-#define current_pt_regs() ((struct pt_regs *) \
-	(THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
-#define signal_pt_regs() ((struct pt_regs *)current->thread.esp0)
-#define current_user_stack_pointer() rdusp()
-#endif /* __ASSEMBLY__ */
-#endif /* _H8300_PTRACE_H */
diff --git a/arch/h8300/include/asm/regs267x.h b/arch/h8300/include/asm/regs267x.h
deleted file mode 100644
index 1bff731a9f77..000000000000
--- a/arch/h8300/include/asm/regs267x.h
+++ /dev/null
@@ -1,336 +0,0 @@
-/* internal Peripherals Register address define */
-/* CPU: H8/306x                                 */
-
-#if !defined(__REGS_H8S267x__)
-#define __REGS_H8S267x__ 
-
-#if defined(__KERNEL__)
-
-#define DASTCR 0xFEE01A
-#define DADR0  0xFFFFA4
-#define DADR1  0xFFFFA5
-#define DACR01 0xFFFFA6
-#define DADR2  0xFFFFA8
-#define DADR3  0xFFFFA9
-#define DACR23 0xFFFFAA
-
-#define ADDRA  0xFFFF90
-#define ADDRAH 0xFFFF90
-#define ADDRAL 0xFFFF91
-#define ADDRB  0xFFFF92
-#define ADDRBH 0xFFFF92
-#define ADDRBL 0xFFFF93
-#define ADDRC  0xFFFF94
-#define ADDRCH 0xFFFF94
-#define ADDRCL 0xFFFF95
-#define ADDRD  0xFFFF96
-#define ADDRDH 0xFFFF96
-#define ADDRDL 0xFFFF97
-#define ADDRE  0xFFFF98
-#define ADDREH 0xFFFF98
-#define ADDREL 0xFFFF99
-#define ADDRF  0xFFFF9A
-#define ADDRFH 0xFFFF9A
-#define ADDRFL 0xFFFF9B
-#define ADDRG  0xFFFF9C
-#define ADDRGH 0xFFFF9C
-#define ADDRGL 0xFFFF9D
-#define ADDRH  0xFFFF9E
-#define ADDRHH 0xFFFF9E
-#define ADDRHL 0xFFFF9F
-
-#define ADCSR  0xFFFFA0
-#define ADCR   0xFFFFA1
-
-#define ABWCR  0xFFFEC0
-#define ASTCR  0xFFFEC1
-#define WTCRAH 0xFFFEC2
-#define WTCRAL 0xFFFEC3
-#define WTCRBH 0xFFFEC4
-#define WTCRBL 0xFFFEC5
-#define RDNCR  0xFFFEC6
-#define CSACRH 0xFFFEC8
-#define CSACRL 0xFFFEC9
-#define BROMCRH 0xFFFECA
-#define BROMCRL 0xFFFECB
-#define BCR    0xFFFECC
-#define DRAMCR 0xFFFED0
-#define DRACCR 0xFFFED2
-#define REFCR  0xFFFED4
-#define RTCNT  0xFFFED6
-#define RTCOR  0xFFFED7
-
-#define MAR0AH  0xFFFEE0
-#define MAR0AL  0xFFFEE2
-#define IOAR0A  0xFFFEE4
-#define ETCR0A  0xFFFEE6
-#define MAR0BH  0xFFFEE8
-#define MAR0BL  0xFFFEEA
-#define IOAR0B  0xFFFEEC
-#define ETCR0B  0xFFFEEE
-#define MAR1AH  0xFFFEF0
-#define MAR1AL  0xFFFEF2
-#define IOAR1A  0xFFFEF4
-#define ETCR1A  0xFFFEF6
-#define MAR1BH  0xFFFEF8
-#define MAR1BL  0xFFFEFA
-#define IOAR1B  0xFFFEFC
-#define ETCR1B  0xFFFEFE
-#define DMAWER  0xFFFF20
-#define DMATCR  0xFFFF21
-#define DMACR0A 0xFFFF22
-#define DMACR0B 0xFFFF23
-#define DMACR1A 0xFFFF24
-#define DMACR1B 0xFFFF25
-#define DMABCRH 0xFFFF26
-#define DMABCRL 0xFFFF27
-
-#define EDSAR0  0xFFFDC0
-#define EDDAR0  0xFFFDC4
-#define EDTCR0  0xFFFDC8
-#define EDMDR0  0xFFFDCC
-#define EDMDR0H 0xFFFDCC
-#define EDMDR0L 0xFFFDCD
-#define EDACR0  0xFFFDCE
-#define EDSAR1  0xFFFDD0
-#define EDDAR1  0xFFFDD4
-#define EDTCR1  0xFFFDD8
-#define EDMDR1  0xFFFDDC
-#define EDMDR1H 0xFFFDDC
-#define EDMDR1L 0xFFFDDD
-#define EDACR1  0xFFFDDE
-#define EDSAR2  0xFFFDE0
-#define EDDAR2  0xFFFDE4
-#define EDTCR2  0xFFFDE8
-#define EDMDR2  0xFFFDEC
-#define EDMDR2H 0xFFFDEC
-#define EDMDR2L 0xFFFDED
-#define EDACR2  0xFFFDEE
-#define EDSAR3  0xFFFDF0
-#define EDDAR3  0xFFFDF4
-#define EDTCR3  0xFFFDF8
-#define EDMDR3  0xFFFDFC
-#define EDMDR3H 0xFFFDFC
-#define EDMDR3L 0xFFFDFD
-#define EDACR3  0xFFFDFE
-
-#define IPRA  0xFFFE00
-#define IPRB  0xFFFE02
-#define IPRC  0xFFFE04
-#define IPRD  0xFFFE06
-#define IPRE  0xFFFE08
-#define IPRF  0xFFFE0A
-#define IPRG  0xFFFE0C
-#define IPRH  0xFFFE0E
-#define IPRI  0xFFFE10
-#define IPRJ  0xFFFE12
-#define IPRK  0xFFFE14
-#define ITSR  0xFFFE16
-#define SSIER 0xFFFE18
-#define ISCRH 0xFFFE1A
-#define ISCRL 0xFFFE1C
-
-#define INTCR 0xFFFF31
-#define IER   0xFFFF32
-#define IERH  0xFFFF32
-#define IERL  0xFFFF33
-#define ISR   0xFFFF34
-#define ISRH  0xFFFF34
-#define ISRL  0xFFFF35
-
-#define P1DDR 0xFFFE20
-#define P2DDR 0xFFFE21
-#define P3DDR 0xFFFE22
-#define P4DDR 0xFFFE23
-#define P5DDR 0xFFFE24
-#define P6DDR 0xFFFE25
-#define P7DDR 0xFFFE26
-#define P8DDR 0xFFFE27
-#define P9DDR 0xFFFE28
-#define PADDR 0xFFFE29
-#define PBDDR 0xFFFE2A
-#define PCDDR 0xFFFE2B
-#define PDDDR 0xFFFE2C
-#define PEDDR 0xFFFE2D
-#define PFDDR 0xFFFE2E
-#define PGDDR 0xFFFE2F
-#define PHDDR 0xFFFF74
-
-#define PFCR0 0xFFFE32
-#define PFCR1 0xFFFE33
-#define PFCR2 0xFFFE34
-
-#define PAPCR 0xFFFE36
-#define PBPCR 0xFFFE37
-#define PCPCR 0xFFFE38
-#define PDPCR 0xFFFE39
-#define PEPCR 0xFFFE3A
-
-#define P3ODR 0xFFFE3C
-#define PAODR 0xFFFE3D
-
-#define P1DR  0xFFFF60
-#define P2DR  0xFFFF61
-#define P3DR  0xFFFF62
-#define P4DR  0xFFFF63
-#define P5DR  0xFFFF64
-#define P6DR  0xFFFF65
-#define P7DR  0xFFFF66
-#define P8DR  0xFFFF67
-#define P9DR  0xFFFF68
-#define PADR  0xFFFF69
-#define PBDR  0xFFFF6A
-#define PCDR  0xFFFF6B
-#define PDDR  0xFFFF6C
-#define PEDR  0xFFFF6D
-#define PFDR  0xFFFF6E
-#define PGDR  0xFFFF6F
-#define PHDR  0xFFFF72
-
-#define PORT1 0xFFFF50
-#define PORT2 0xFFFF51
-#define PORT3 0xFFFF52
-#define PORT4 0xFFFF53
-#define PORT5 0xFFFF54
-#define PORT6 0xFFFF55
-#define PORT7 0xFFFF56
-#define PORT8 0xFFFF57
-#define PORT9 0xFFFF58
-#define PORTA 0xFFFF59
-#define PORTB 0xFFFF5A
-#define PORTC 0xFFFF5B
-#define PORTD 0xFFFF5C
-#define PORTE 0xFFFF5D
-#define PORTF 0xFFFF5E
-#define PORTG 0xFFFF5F
-#define PORTH 0xFFFF70
-
-#define PCR   0xFFFF46
-#define PMR   0xFFFF47
-#define NDERH 0xFFFF48
-#define NDERL 0xFFFF49
-#define PODRH 0xFFFF4A
-#define PODRL 0xFFFF4B
-#define NDRH1 0xFFFF4C
-#define NDRL1 0xFFFF4D
-#define NDRH2 0xFFFF4E
-#define NDRL2 0xFFFF4F
-
-#define SMR0  0xFFFF78
-#define BRR0  0xFFFF79
-#define SCR0  0xFFFF7A
-#define TDR0  0xFFFF7B
-#define SSR0  0xFFFF7C
-#define RDR0  0xFFFF7D
-#define SCMR0 0xFFFF7E
-#define SMR1  0xFFFF80
-#define BRR1  0xFFFF81
-#define SCR1  0xFFFF82
-#define TDR1  0xFFFF83
-#define SSR1  0xFFFF84
-#define RDR1  0xFFFF85
-#define SCMR1 0xFFFF86
-#define SMR2  0xFFFF88
-#define BRR2  0xFFFF89
-#define SCR2  0xFFFF8A
-#define TDR2  0xFFFF8B
-#define SSR2  0xFFFF8C
-#define RDR2  0xFFFF8D
-#define SCMR2 0xFFFF8E
-
-#define IRCR0 0xFFFE1E
-#define SEMR  0xFFFDA8
-
-#define MDCR    0xFFFF3E
-#define SYSCR   0xFFFF3D
-#define MSTPCRH 0xFFFF40
-#define MSTPCRL 0xFFFF41
-#define FLMCR1  0xFFFFC8
-#define FLMCR2  0xFFFFC9
-#define EBR1    0xFFFFCA
-#define EBR2    0xFFFFCB
-#define CTGARC_RAMCR   0xFFFECE
-#define SBYCR   0xFFFF3A
-#define SCKCR   0xFFFF3B
-#define PLLCR   0xFFFF45
-
-#define TSTR   0xFFFFC0
-#define TSNC   0XFFFFC1
-
-#define TCR0   0xFFFFD0
-#define TMDR0  0xFFFFD1
-#define TIORH0 0xFFFFD2
-#define TIORL0 0xFFFFD3
-#define TIER0  0xFFFFD4
-#define TSR0   0xFFFFD5
-#define TCNT0  0xFFFFD6
-#define GRA0   0xFFFFD8
-#define GRB0   0xFFFFDA
-#define GRC0   0xFFFFDC
-#define GRD0   0xFFFFDE
-#define TCR1   0xFFFFE0
-#define TMDR1  0xFFFFE1
-#define TIORH1 0xFFFFE2
-#define TIORL1 0xFFFFE3
-#define TIER1  0xFFFFE4
-#define TSR1   0xFFFFE5
-#define TCNT1  0xFFFFE6
-#define GRA1   0xFFFFE8
-#define GRB1   0xFFFFEA
-#define TCR2   0xFFFFF0
-#define TMDR2  0xFFFFF1
-#define TIORH2 0xFFFFF2
-#define TIORL2 0xFFFFF3
-#define TIER2  0xFFFFF4
-#define TSR2   0xFFFFF5
-#define TCNT2  0xFFFFF6
-#define GRA2   0xFFFFF8
-#define GRB2   0xFFFFFA
-#define TCR3   0xFFFE80
-#define TMDR3  0xFFFE81
-#define TIORH3 0xFFFE82
-#define TIORL3 0xFFFE83
-#define TIER3  0xFFFE84
-#define TSR3   0xFFFE85
-#define TCNT3  0xFFFE86
-#define GRA3   0xFFFE88
-#define GRB3   0xFFFE8A
-#define GRC3   0xFFFE8C
-#define GRD3   0xFFFE8E
-#define TCR4   0xFFFE90
-#define TMDR4  0xFFFE91
-#define TIORH4 0xFFFE92
-#define TIORL4 0xFFFE93
-#define TIER4  0xFFFE94
-#define TSR4   0xFFFE95
-#define TCNT4  0xFFFE96
-#define GRA4   0xFFFE98
-#define GRB4   0xFFFE9A
-#define TCR5   0xFFFEA0
-#define TMDR5  0xFFFEA1
-#define TIORH5 0xFFFEA2
-#define TIORL5 0xFFFEA3
-#define TIER5  0xFFFEA4
-#define TSR5   0xFFFEA5
-#define TCNT5  0xFFFEA6
-#define GRA5   0xFFFEA8
-#define GRB5   0xFFFEAA
-
-#define _8TCR0   0xFFFFB0
-#define _8TCR1   0xFFFFB1
-#define _8TCSR0  0xFFFFB2
-#define _8TCSR1  0xFFFFB3
-#define _8TCORA0 0xFFFFB4
-#define _8TCORA1 0xFFFFB5
-#define _8TCORB0 0xFFFFB6
-#define _8TCORB1 0xFFFFB7
-#define _8TCNT0  0xFFFFB8
-#define _8TCNT1  0xFFFFB9
-
-#define TCSR    0xFFFFBC
-#define TCNT    0xFFFFBD
-#define RSTCSRW 0xFFFFBE
-#define RSTCSRR 0xFFFFBF
-
-#endif /* __KERNEL__ */
-#endif /* __REGS_H8S267x__ */
diff --git a/arch/h8300/include/asm/regs306x.h b/arch/h8300/include/asm/regs306x.h
deleted file mode 100644
index 027dd633fa25..000000000000
--- a/arch/h8300/include/asm/regs306x.h
+++ /dev/null
@@ -1,212 +0,0 @@
-/* internal Peripherals Register address define */
-/* CPU: H8/306x                                 */
-
-#if !defined(__REGS_H8306x__)
-#define __REGS_H8306x__ 
-
-#if defined(__KERNEL__)
-
-#define DASTCR 0xFEE01A
-#define DADR0  0xFEE09C
-#define DADR1  0xFEE09D
-#define DACR   0xFEE09E
-
-#define ADDRAH 0xFFFFE0
-#define ADDRAL 0xFFFFE1
-#define ADDRBH 0xFFFFE2
-#define ADDRBL 0xFFFFE3
-#define ADDRCH 0xFFFFE4
-#define ADDRCL 0xFFFFE5
-#define ADDRDH 0xFFFFE6
-#define ADDRDL 0xFFFFE7
-#define ADCSR  0xFFFFE8
-#define ADCR   0xFFFFE9
-
-#define BRCR   0xFEE013
-#define ADRCR  0xFEE01E
-#define CSCR   0xFEE01F
-#define ABWCR  0xFEE020
-#define ASTCR  0xFEE021
-#define WCRH   0xFEE022
-#define WCRL   0xFEE023
-#define BCR    0xFEE024
-#define DRCRA  0xFEE026
-#define DRCRB  0xFEE027
-#define RTMCSR 0xFEE028
-#define RTCNT  0xFEE029
-#define RTCOR  0xFEE02A
-
-#define MAR0AR  0xFFFF20
-#define MAR0AE  0xFFFF21
-#define MAR0AH  0xFFFF22
-#define MAR0AL  0xFFFF23
-#define ETCR0AL 0xFFFF24
-#define ETCR0AH 0xFFFF25
-#define IOAR0A  0xFFFF26
-#define DTCR0A  0xFFFF27
-#define MAR0BR  0xFFFF28
-#define MAR0BE  0xFFFF29
-#define MAR0BH  0xFFFF2A
-#define MAR0BL  0xFFFF2B
-#define ETCR0BL 0xFFFF2C
-#define ETCR0BH 0xFFFF2D
-#define IOAR0B  0xFFFF2E
-#define DTCR0B  0xFFFF2F
-#define MAR1AR  0xFFFF30
-#define MAR1AE  0xFFFF31
-#define MAR1AH  0xFFFF32
-#define MAR1AL  0xFFFF33
-#define ETCR1AL 0xFFFF34
-#define ETCR1AH 0xFFFF35
-#define IOAR1A  0xFFFF36
-#define DTCR1A  0xFFFF37
-#define MAR1BR  0xFFFF38
-#define MAR1BE  0xFFFF39
-#define MAR1BH  0xFFFF3A
-#define MAR1BL  0xFFFF3B
-#define ETCR1BL 0xFFFF3C
-#define ETCR1BH 0xFFFF3D
-#define IOAR1B  0xFFFF3E
-#define DTCR1B  0xFFFF3F
-
-#define ISCR 0xFEE014
-#define IER  0xFEE015
-#define ISR  0xFEE016
-#define IPRA 0xFEE018
-#define IPRB 0xFEE019
-
-#define P1DDR 0xFEE000
-#define P2DDR 0xFEE001
-#define P3DDR 0xFEE002
-#define P4DDR 0xFEE003
-#define P5DDR 0xFEE004
-#define P6DDR 0xFEE005
-/*#define P7DDR 0xFEE006*/
-#define P8DDR 0xFEE007
-#define P9DDR 0xFEE008
-#define PADDR 0xFEE009
-#define PBDDR 0xFEE00A
-
-#define P1DR  0xFFFFD0
-#define P2DR  0xFFFFD1
-#define P3DR  0xFFFFD2
-#define P4DR  0xFFFFD3
-#define P5DR  0xFFFFD4
-#define P6DR  0xFFFFD5
-/*#define P7DR  0xFFFFD6*/
-#define P8DR  0xFFFFD7
-#define P9DR  0xFFFFD8
-#define PADR  0xFFFFD9
-#define PBDR  0xFFFFDA
-
-#define P2CR  0xFEE03C
-#define P4CR  0xFEE03E
-#define P5CR  0xFEE03F
-
-#define SMR0  0xFFFFB0
-#define BRR0  0xFFFFB1
-#define SCR0  0xFFFFB2
-#define TDR0  0xFFFFB3
-#define SSR0  0xFFFFB4
-#define RDR0  0xFFFFB5
-#define SCMR0 0xFFFFB6
-#define SMR1  0xFFFFB8
-#define BRR1  0xFFFFB9
-#define SCR1  0xFFFFBA
-#define TDR1  0xFFFFBB
-#define SSR1  0xFFFFBC
-#define RDR1  0xFFFFBD
-#define SCMR1 0xFFFFBE
-#define SMR2  0xFFFFC0
-#define BRR2  0xFFFFC1
-#define SCR2  0xFFFFC2
-#define TDR2  0xFFFFC3
-#define SSR2  0xFFFFC4
-#define RDR2  0xFFFFC5
-#define SCMR2 0xFFFFC6
-
-#define MDCR   0xFEE011
-#define SYSCR  0xFEE012
-#define DIVCR  0xFEE01B
-#define MSTCRH 0xFEE01C
-#define MSTCRL 0xFEE01D
-#define FLMCR1 0xFEE030
-#define FLMCR2 0xFEE031
-#define EBR1   0xFEE032
-#define EBR2   0xFEE033
-#define RAMCR  0xFEE077
-
-#define TSTR   0xFFFF60
-#define TSNC   0XFFFF61
-#define TMDR   0xFFFF62
-#define TOLR   0xFFFF63
-#define TISRA  0xFFFF64
-#define TISRB  0xFFFF65
-#define TISRC  0xFFFF66
-#define TCR0   0xFFFF68
-#define TIOR0  0xFFFF69
-#define TCNT0H 0xFFFF6A
-#define TCNT0L 0xFFFF6B
-#define GRA0H  0xFFFF6C
-#define GRA0L  0xFFFF6D
-#define GRB0H  0xFFFF6E
-#define GRB0L  0xFFFF6F
-#define TCR1   0xFFFF70
-#define TIOR1  0xFFFF71
-#define TCNT1H 0xFFFF72
-#define TCNT1L 0xFFFF73
-#define GRA1H  0xFFFF74
-#define GRA1L  0xFFFF75
-#define GRB1H  0xFFFF76
-#define GRB1L  0xFFFF77
-#define TCR3   0xFFFF78
-#define TIOR3  0xFFFF79
-#define TCNT3H 0xFFFF7A
-#define TCNT3L 0xFFFF7B
-#define GRA3H  0xFFFF7C
-#define GRA3L  0xFFFF7D
-#define GRB3H  0xFFFF7E
-#define GRB3L  0xFFFF7F
-
-#define _8TCR0  0xFFFF80
-#define _8TCR1  0xFFFF81
-#define _8TCSR0 0xFFFF82
-#define _8TCSR1 0xFFFF83
-#define TCORA0 0xFFFF84
-#define TCORA1 0xFFFF85
-#define TCORB0 0xFFFF86
-#define TCORB1 0xFFFF87
-#define _8TCNT0 0xFFFF88
-#define _8TCNT1 0xFFFF89
-
-#define _8TCR2  0xFFFF90
-#define _8TCR3  0xFFFF91
-#define _8TCSR2 0xFFFF92
-#define _8TCSR3 0xFFFF93
-#define TCORA2 0xFFFF94
-#define TCORA3 0xFFFF95
-#define TCORB2 0xFFFF96
-#define TCORB3 0xFFFF97
-#define _8TCNT2 0xFFFF98
-#define _8TCNT3 0xFFFF99
-
-#define TCSR   0xFFFF8C
-#define TCNT   0xFFFF8D
-#define RSTCSR 0xFFFF8F
-
-#define TPMR  0xFFFFA0
-#define TPCR  0xFFFFA1
-#define NDERB 0xFFFFA2
-#define NDERA 0xFFFFA3
-#define NDRB1 0xFFFFA4
-#define NDRA1 0xFFFFA5
-#define NDRB2 0xFFFFA6
-#define NDRA2 0xFFFFA7
-
-#define TCSR    0xFFFF8C
-#define TCNT    0xFFFF8D
-#define RSTCSRW 0xFFFF8E
-#define RSTCSRR 0xFFFF8F
-
-#endif /* __KERNEL__ */
-#endif /* __REGS_H8306x__ */
diff --git a/arch/h8300/include/asm/scatterlist.h b/arch/h8300/include/asm/scatterlist.h
deleted file mode 100644
index 82130eda0e5f..000000000000
--- a/arch/h8300/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_SCATTERLIST_H
-#define _H8300_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* !(_H8300_SCATTERLIST_H) */
diff --git a/arch/h8300/include/asm/sections.h b/arch/h8300/include/asm/sections.h
deleted file mode 100644
index a81743e8b743..000000000000
--- a/arch/h8300/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_SECTIONS_H_
-#define _H8300_SECTIONS_H_
-
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h
deleted file mode 100644
index b79a82d0f99d..000000000000
--- a/arch/h8300/include/asm/segment.h
+++ /dev/null
@@ -1,49 +0,0 @@
-#ifndef _H8300_SEGMENT_H
-#define _H8300_SEGMENT_H
-
-/* define constants */
-#define USER_DATA     (1)
-#ifndef __USER_DS
-#define __USER_DS     (USER_DATA)
-#endif
-#define USER_PROGRAM  (2)
-#define SUPER_DATA    (3)
-#ifndef __KERNEL_DS
-#define __KERNEL_DS   (SUPER_DATA)
-#endif
-#define SUPER_PROGRAM (4)
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-#define USER_DS		MAKE_MM_SEG(__USER_DS)
-#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
-
-/*
- * Get/set the SFC/DFC registers for MOVES instructions
- */
-
-static inline mm_segment_t get_fs(void)
-{
-    return USER_DS;
-}
-
-static inline mm_segment_t get_ds(void)
-{
-    /* return the supervisor data space code */
-    return KERNEL_DS;
-}
-
-static inline void set_fs(mm_segment_t val)
-{
-}
-
-#define segment_eq(a,b)	((a).seg == (b).seg)
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _H8300_SEGMENT_H */
diff --git a/arch/h8300/include/asm/sh_bios.h b/arch/h8300/include/asm/sh_bios.h
deleted file mode 100644
index b6bb6e58295c..000000000000
--- a/arch/h8300/include/asm/sh_bios.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* eCos HAL interface header */
-
-#ifndef SH_BIOS_H
-#define SH_BIOS_H
-
-#define HAL_IF_VECTOR_TABLE 0xfffe20
-#define CALL_IF_SET_CONSOLE_COMM  13
-#define QUERY_CURRENT -1
-#define MANGLER       -3
-
-/* Checking for GDB stub active */
-/* suggestion Jonathan Larmour */
-static int sh_bios_in_gdb_mode(void)
-{
-	static int gdb_active = -1;
-	if (gdb_active == -1) {
-		int (*set_console_comm)(int);
-		set_console_comm = ((void **)HAL_IF_VECTOR_TABLE)[CALL_IF_SET_CONSOLE_COMM];
-		gdb_active = (set_console_comm(QUERY_CURRENT) == MANGLER);
-	}
-	return gdb_active;
-}
-
-static void sh_bios_gdb_detach(void)
-{
-
-}
-
-#endif
diff --git a/arch/h8300/include/asm/shm.h b/arch/h8300/include/asm/shm.h
deleted file mode 100644
index ed6623c0545d..000000000000
--- a/arch/h8300/include/asm/shm.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _H8300_SHM_H
-#define _H8300_SHM_H
-
-
-/* format of page table entries that correspond to shared memory pages
-   currently out in swap space (see also mm/swap.c):
-   bits 0-1 (PAGE_PRESENT) is  = 0
-   bits 8..2 (SWP_TYPE) are = SHM_SWP_TYPE
-   bits 31..9 are used like this:
-   bits 15..9 (SHM_ID) the id of the shared memory segment
-   bits 30..16 (SHM_IDX) the index of the page within the shared memory segment
-                    (actually only bits 25..16 get used since SHMMAX is so low)
-   bit 31 (SHM_READ_ONLY) flag whether the page belongs to a read-only attach
-*/
-/* on the m68k both bits 0 and 1 must be zero */
-/* format on the sun3 is similar, but bits 30, 31 are set to zero and all
-   others are reduced by 2. --m */
-
-#ifndef CONFIG_SUN3
-#define SHM_ID_SHIFT	9
-#else
-#define SHM_ID_SHIFT	7
-#endif
-#define _SHM_ID_BITS	7
-#define SHM_ID_MASK	((1<<_SHM_ID_BITS)-1)
-
-#define SHM_IDX_SHIFT	(SHM_ID_SHIFT+_SHM_ID_BITS)
-#define _SHM_IDX_BITS	15
-#define SHM_IDX_MASK	((1<<_SHM_IDX_BITS)-1)
-
-#endif /* _H8300_SHM_H */
diff --git a/arch/h8300/include/asm/shmparam.h b/arch/h8300/include/asm/shmparam.h
deleted file mode 100644
index d1863953ec64..000000000000
--- a/arch/h8300/include/asm/shmparam.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_SHMPARAM_H
-#define _H8300_SHMPARAM_H
-
-#define	SHMLBA PAGE_SIZE		 /* attach addr a multiple of this */
-
-#endif /* _H8300_SHMPARAM_H */
diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h
deleted file mode 100644
index 6341e36386f8..000000000000
--- a/arch/h8300/include/asm/signal.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _H8300_SIGNAL_H
-#define _H8300_SIGNAL_H
-
-#include <uapi/asm/signal.h>
-
-/* Most things should be clean enough to redefine this at will, if care
-   is taken to make libc match.  */
-
-#define _NSIG		64
-#define _NSIG_BPW	32
-#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
-
-typedef unsigned long old_sigset_t;		/* at least 32 bits */
-
-typedef struct {
-	unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-#define __ARCH_HAS_SA_RESTORER
-
-#include <asm/sigcontext.h>
-#undef __HAVE_ARCH_SIG_BITOPS
-
-#endif /* _H8300_SIGNAL_H */
diff --git a/arch/h8300/include/asm/smp.h b/arch/h8300/include/asm/smp.h
deleted file mode 100644
index 9e9bd7e58922..000000000000
--- a/arch/h8300/include/asm/smp.h
+++ /dev/null
@@ -1 +0,0 @@
-/* nothing required here yet */
diff --git a/arch/h8300/include/asm/spinlock.h b/arch/h8300/include/asm/spinlock.h
deleted file mode 100644
index d5407fa173e4..000000000000
--- a/arch/h8300/include/asm/spinlock.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __H8300_SPINLOCK_H
-#define __H8300_SPINLOCK_H
-
-#error "H8/300 doesn't do SMP yet"
-
-#endif
diff --git a/arch/h8300/include/asm/string.h b/arch/h8300/include/asm/string.h
deleted file mode 100644
index ca5034897d87..000000000000
--- a/arch/h8300/include/asm/string.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _H8300_STRING_H_
-#define _H8300_STRING_H_
-
-#ifdef __KERNEL__ /* only set these up for kernel code */
-
-#include <asm/setup.h>
-#include <asm/page.h>
-
-#define __HAVE_ARCH_MEMSET
-extern void * memset(void * s, int c, size_t count);
-
-#define __HAVE_ARCH_MEMCPY
-extern void * memcpy(void *d, const void *s, size_t count);
-
-#else /* KERNEL */
-
-/*
- *	let user libraries deal with these,
- *	IMHO the kernel has no place defining these functions for user apps
- */
-
-#define __HAVE_ARCH_STRCPY 1
-#define __HAVE_ARCH_STRNCPY 1
-#define __HAVE_ARCH_STRCAT 1
-#define __HAVE_ARCH_STRNCAT 1
-#define __HAVE_ARCH_STRCMP 1
-#define __HAVE_ARCH_STRNCMP 1
-#define __HAVE_ARCH_STRNICMP 1
-#define __HAVE_ARCH_STRCHR 1
-#define __HAVE_ARCH_STRRCHR 1
-#define __HAVE_ARCH_STRSTR 1
-#define __HAVE_ARCH_STRLEN 1
-#define __HAVE_ARCH_STRNLEN 1
-#define __HAVE_ARCH_MEMSET 1
-#define __HAVE_ARCH_MEMCPY 1
-#define __HAVE_ARCH_MEMMOVE 1
-#define __HAVE_ARCH_MEMSCAN 1
-#define __HAVE_ARCH_MEMCMP 1
-#define __HAVE_ARCH_MEMCHR 1
-#define __HAVE_ARCH_STRTOK 1
-
-#endif /* KERNEL */
-
-#endif /* _M68K_STRING_H_ */
diff --git a/arch/h8300/include/asm/switch_to.h b/arch/h8300/include/asm/switch_to.h
deleted file mode 100644
index cdd8731ce487..000000000000
--- a/arch/h8300/include/asm/switch_to.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#ifndef _H8300_SWITCH_TO_H
-#define _H8300_SWITCH_TO_H
-
-/*
- * switch_to(n) should switch tasks to task ptr, first checking that
- * ptr isn't the current task, in which case it does nothing.  This
- * also clears the TS-flag if the task we switched to has used the
- * math co-processor latest.
- */
-/*
- * switch_to() saves the extra registers, that are not saved
- * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
- * a0-a1. Some of these are used by schedule() and its predecessors
- * and so we might get see unexpected behaviors when a task returns
- * with unexpected register values.
- *
- * syscall stores these registers itself and none of them are used
- * by syscall after the function in the syscall has been called.
- *
- * Beware that resume now expects *next to be in d1 and the offset of
- * tss to be in a1. This saves a few instructions as we no longer have
- * to push them onto the stack and read them back right after.
- *
- * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
- *
- * Changed 96/09/19 by Andreas Schwab
- * pass prev in a0, next in a1, offset of tss in d1, and whether
- * the mm structures are shared in d2 (to avoid atc flushing).
- *
- * H8/300 Porting 2002/09/04 Yoshinori Sato
- */
-
-asmlinkage void resume(void);
-#define switch_to(prev,next,last) {                         \
-  void *_last;						    \
-  __asm__ __volatile__(					    \
-  			"mov.l	%1, er0\n\t"		    \
-			"mov.l	%2, er1\n\t"		    \
-                        "mov.l  %3, er2\n\t"                \
-			"jsr @_resume\n\t"                  \
-                        "mov.l  er2,%0\n\t"                 \
-		       : "=r" (_last)			    \
-		       : "r" (&(prev->thread)),		    \
-			 "r" (&(next->thread)),		    \
-                         "g" (prev)                         \
-		       : "cc", "er0", "er1", "er2", "er3"); \
-  (last) = _last; 					    \
-}
-
-#endif /* _H8300_SWITCH_TO_H */
diff --git a/arch/h8300/include/asm/target_time.h b/arch/h8300/include/asm/target_time.h
deleted file mode 100644
index 9f2a9aa1fe6f..000000000000
--- a/arch/h8300/include/asm/target_time.h
+++ /dev/null
@@ -1,4 +0,0 @@
-extern int platform_timer_setup(void (*timer_int)(int, void *, struct pt_regs *));
-extern void platform_timer_eoi(void);
-extern void platform_gettod(unsigned int *year, unsigned int *mon, unsigned int *day, 
-                            unsigned int *hour, unsigned int *min, unsigned int *sec);
diff --git a/arch/h8300/include/asm/termios.h b/arch/h8300/include/asm/termios.h
deleted file mode 100644
index 93a63df56247..000000000000
--- a/arch/h8300/include/asm/termios.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#ifndef _H8300_TERMIOS_H
-#define _H8300_TERMIOS_H
-
-#include <uapi/asm/termios.h>
-
-/*	intr=^C		quit=^|		erase=del	kill=^U
-	eof=^D		vtime=\0	vmin=\1		sxtc=\0
-	start=^Q	stop=^S		susp=^Z		eol=\0
-	reprint=^R	discard=^U	werase=^W	lnext=^V
-	eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
-	unsigned short tmp; \
-	get_user(tmp, &(termio)->c_iflag); \
-	(termios)->c_iflag = (0xffff0000 & ((termios)->c_iflag)) | tmp; \
-	get_user(tmp, &(termio)->c_oflag); \
-	(termios)->c_oflag = (0xffff0000 & ((termios)->c_oflag)) | tmp; \
-	get_user(tmp, &(termio)->c_cflag); \
-	(termios)->c_cflag = (0xffff0000 & ((termios)->c_cflag)) | tmp; \
-	get_user(tmp, &(termio)->c_lflag); \
-	(termios)->c_lflag = (0xffff0000 & ((termios)->c_lflag)) | tmp; \
-	get_user((termios)->c_line, &(termio)->c_line); \
-	copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
-	put_user((termios)->c_iflag, &(termio)->c_iflag); \
-	put_user((termios)->c_oflag, &(termio)->c_oflag); \
-	put_user((termios)->c_cflag, &(termio)->c_cflag); \
-	put_user((termios)->c_lflag, &(termio)->c_lflag); \
-	put_user((termios)->c_line,  &(termio)->c_line); \
-	copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
-#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
-
-#endif /* _H8300_TERMIOS_H */
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
deleted file mode 100644
index ec2f7777c65a..000000000000
--- a/arch/h8300/include/asm/thread_info.h
+++ /dev/null
@@ -1,103 +0,0 @@
-/* thread_info.h: h8300 low-level thread information
- * adapted from the i386 and PPC versions by Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef _ASM_THREAD_INFO_H
-#define _ASM_THREAD_INFO_H
-
-#include <asm/page.h>
-
-#ifdef __KERNEL__
-
-#ifndef __ASSEMBLY__
-
-/*
- * low level task data.
- * If you change this, change the TI_* offsets below to match.
- */
-struct thread_info {
-	struct task_struct *task;		/* main task structure */
-	struct exec_domain *exec_domain;	/* execution domain */
-	unsigned long	   flags;		/* low level flags */
-	int		   cpu;			/* cpu we're on */
-	int		   preempt_count;	/* 0 => preemptable, <0 => BUG */
-	struct restart_block restart_block;
-};
-
-/*
- * macros/functions for gaining access to the thread information structure
- */
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task =		&tsk,			\
-	.exec_domain =	&default_exec_domain,	\
-	.flags =	0,			\
-	.cpu =		0,			\
-	.preempt_count = INIT_PREEMPT_COUNT,	\
-	.restart_block	= {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-
-/*
- * Size of kernel stack for each process. This must be a power of 2...
- */
-#define THREAD_SIZE_ORDER	1
-#define THREAD_SIZE		8192	/* 2 pages */
-
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	struct thread_info *ti;
-	__asm__(
-		"mov.l	sp, %0 \n\t"
-		"and.l	%1, %0"
-		: "=&r"(ti)
-		: "i" (~(THREAD_SIZE-1))
-		);
-	return ti;
-}
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * Offsets in thread_info structure, used in assembly code
- */
-#define TI_TASK		0
-#define TI_EXECDOMAIN	4
-#define TI_FLAGS	8
-#define TI_CPU		12
-#define TI_PRE_COUNT	16
-
-#define	PREEMPT_ACTIVE	0x4000000
-
-/*
- * thread information flag bit numbers
- */
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_MEMDIE		4	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
-#define TIF_NOTIFY_RESUME	6	/* callback before returning to user */
-
-/* as above, but as bit values */
-#define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
-#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-
-#define _TIF_WORK_MASK		(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
-				 _TIF_NOTIFY_RESUME)
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/h8300/include/asm/timer.h b/arch/h8300/include/asm/timer.h
deleted file mode 100644
index def80464d38f..000000000000
--- a/arch/h8300/include/asm/timer.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __H8300_TIMER_H
-#define __H8300_TIMER_H
-
-void h8300_timer_tick(void);
-void h8300_timer_setup(void);
-void h8300_gettod(unsigned int *year, unsigned int *mon, unsigned int *day,
-		   unsigned int *hour, unsigned int *min, unsigned int *sec);
-
-#define TIMER_FREQ (CONFIG_CPU_CLOCK*10000) /* Timer input freq. */
-
-#define calc_param(cnt, div, rate, limit)			\
-do {								\
-	cnt = TIMER_FREQ / HZ;					\
-	for (div = 0; div < ARRAY_SIZE(divide_rate); div++) {	\
-		if (rate[div] == 0)				\
-			continue;				\
-		if ((cnt / rate[div]) > limit)			\
-			break;					\
-	}							\
-	if (div == ARRAY_SIZE(divide_rate))			\
-		panic("Timer counter overflow");		\
-	cnt /= divide_rate[div];				\
-} while(0)
-
-#endif
diff --git a/arch/h8300/include/asm/timex.h b/arch/h8300/include/asm/timex.h
deleted file mode 100644
index 23e67013439f..000000000000
--- a/arch/h8300/include/asm/timex.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * linux/include/asm-h8300/timex.h
- *
- * H8/300 architecture timex specifications
- */
-#ifndef _ASM_H8300_TIMEX_H
-#define _ASM_H8300_TIMEX_H
-
-#define CLOCK_TICK_RATE (CONFIG_CPU_CLOCK*1000/8192) /* Timer input freq. */
-
-typedef unsigned long cycles_t;
-extern short h8300_timer_count;
-
-static inline cycles_t get_cycles(void)
-{
-	return 0;
-}
-
-#endif
diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h
deleted file mode 100644
index 7f0743051ad5..000000000000
--- a/arch/h8300/include/asm/tlb.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __H8300_TLB_H__
-#define __H8300_TLB_H__
-
-#define tlb_flush(tlb)	do { } while(0)
-
-#include <asm-generic/tlb.h>
-
-#endif
diff --git a/arch/h8300/include/asm/tlbflush.h b/arch/h8300/include/asm/tlbflush.h
deleted file mode 100644
index 41c148a9208e..000000000000
--- a/arch/h8300/include/asm/tlbflush.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _H8300_TLBFLUSH_H
-#define _H8300_TLBFLUSH_H
-
-/*
- * Copyright (C) 2000 Lineo, David McCullough <davidm@uclinux.org>
- * Copyright (C) 2000-2002, Greg Ungerer <gerg@snapgear.com>
- */
-
-#include <asm/setup.h>
-
-/*
- * flush all user-space atc entries.
- */
-static inline void __flush_tlb(void)
-{
-	BUG();
-}
-
-static inline void __flush_tlb_one(unsigned long addr)
-{
-	BUG();
-}
-
-#define flush_tlb() __flush_tlb()
-
-/*
- * flush all atc entries (both kernel and user-space entries).
- */
-static inline void flush_tlb_all(void)
-{
-	BUG();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	BUG();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
-{
-	BUG();
-}
-
-static inline void flush_tlb_range(struct mm_struct *mm,
-				   unsigned long start, unsigned long end)
-{
-	BUG();
-}
-
-static inline void flush_tlb_kernel_page(unsigned long addr)
-{
-	BUG();
-}
-
-#endif /* _H8300_TLBFLUSH_H */
diff --git a/arch/h8300/include/asm/topology.h b/arch/h8300/include/asm/topology.h
deleted file mode 100644
index fdc121924d4c..000000000000
--- a/arch/h8300/include/asm/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_H8300_TOPOLOGY_H
-#define _ASM_H8300_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif /* _ASM_H8300_TOPOLOGY_H */
diff --git a/arch/h8300/include/asm/traps.h b/arch/h8300/include/asm/traps.h
deleted file mode 100644
index 41cf6be02f68..000000000000
--- a/arch/h8300/include/asm/traps.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- *  linux/include/asm-h8300/traps.h
- *
- *  Copyright (C) 2003 Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#ifndef _H8300_TRAPS_H
-#define _H8300_TRAPS_H
-
-extern void system_call(void);
-extern void interrupt_entry(void);
-extern void trace_break(void);
-
-#define JMP_OP 0x5a000000
-#define JSR_OP 0x5e000000
-#define VECTOR(address) ((JMP_OP)|((unsigned long)address))
-#define REDIRECT(address) ((JSR_OP)|((unsigned long)address))
-
-#define TRACE_VEC 5
-
-#define TRAP0_VEC 8
-#define TRAP1_VEC 9
-#define TRAP2_VEC 10
-#define TRAP3_VEC 11
-
-#if defined(__H8300H__)
-#define NR_TRAPS 12
-#endif
-#if defined(__H8300S__)
-#define NR_TRAPS 16
-#endif
-
-#endif /* _H8300_TRAPS_H */
diff --git a/arch/h8300/include/asm/types.h b/arch/h8300/include/asm/types.h
deleted file mode 100644
index c012707f6037..000000000000
--- a/arch/h8300/include/asm/types.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _H8300_TYPES_H
-#define _H8300_TYPES_H
-
-#include <uapi/asm/types.h>
-
-
-#define BITS_PER_LONG 32
-
-#endif /* _H8300_TYPES_H */
diff --git a/arch/h8300/include/asm/uaccess.h b/arch/h8300/include/asm/uaccess.h
deleted file mode 100644
index 8725d1ad4272..000000000000
--- a/arch/h8300/include/asm/uaccess.h
+++ /dev/null
@@ -1,163 +0,0 @@
-#ifndef __H8300_UACCESS_H
-#define __H8300_UACCESS_H
-
-/*
- * User space memory access functions
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-
-#include <asm/segment.h>
-
-#define VERIFY_READ	0
-#define VERIFY_WRITE	1
-
-/* We let the MMU do all checking */
-#define access_ok(type, addr, size) __access_ok((unsigned long)addr,size)
-static inline int __access_ok(unsigned long addr, unsigned long size)
-{
-#define	RANGE_CHECK_OK(addr, size, lower, upper) \
-	(((addr) >= (lower)) && (((addr) + (size)) < (upper)))
-
-	extern unsigned long _ramend;
-	return(RANGE_CHECK_OK(addr, size, 0L, (unsigned long)&_ramend));
-}
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
-	unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise.  */
-extern unsigned long search_exception_table(unsigned long);
-
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- */
-
-#define put_user(x, ptr)				\
-({							\
-    int __pu_err = 0;					\
-    typeof(*(ptr)) __pu_val = (x);			\
-    switch (sizeof (*(ptr))) {				\
-    case 1:						\
-    case 2:						\
-    case 4:						\
-	*(ptr) = (__pu_val);   	        		\
-	break;						\
-    case 8:						\
-	memcpy(ptr, &__pu_val, sizeof (*(ptr)));        \
-	break;						\
-    default:						\
-	__pu_err = __put_user_bad();			\
-	break;						\
-    }							\
-    __pu_err;						\
-})
-#define __put_user(x, ptr) put_user(x, ptr)
-
-extern int __put_user_bad(void);
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-
-#define __ptr(x) ((unsigned long *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-
-#define get_user(x, ptr)					\
-({								\
-    int __gu_err = 0;						\
-    typeof(*(ptr)) __gu_val = *ptr;				\
-    switch (sizeof(*(ptr))) {					\
-    case 1:							\
-    case 2:							\
-    case 4:							\
-    case 8: 							\
-	break;							\
-    default:							\
-	__gu_err = __get_user_bad();				\
-	break;							\
-    }								\
-    (x) = __gu_val;						\
-    __gu_err;							\
-})
-#define __get_user(x, ptr) get_user(x, ptr)
-
-extern int __get_user_bad(void);
-
-#define copy_from_user(to, from, n)		(memcpy(to, from, n), 0)
-#define copy_to_user(to, from, n)		(memcpy(to, from, n), 0)
-
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-#define copy_to_user_ret(to,from,n,retval) ({ if (copy_to_user(to,from,n)) return retval; })
-
-#define copy_from_user_ret(to,from,n,retval) ({ if (copy_from_user(to,from,n)) return retval; })
-
-/*
- * Copy a null terminated string from userspace.
- */
-
-static inline long
-strncpy_from_user(char *dst, const char *src, long count)
-{
-	char *tmp;
-	strncpy(dst, src, count);
-	for (tmp = dst; *tmp && count > 0; tmp++, count--)
-		;
-	return(tmp - dst); /* DAVIDM should we count a NUL ?  check getname */
-}
-
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-static inline long strnlen_user(const char *src, long n)
-{
-	return(strlen(src) + 1); /* DAVIDM make safer */
-}
-
-#define strlen_user(str) strnlen_user(str, 32767)
-
-/*
- * Zero Userspace
- */
-
-static inline unsigned long
-clear_user(void *to, unsigned long n)
-{
-	memset(to, 0, n);
-	return 0;
-}
-
-#define __clear_user	clear_user
-
-#endif /* _H8300_UACCESS_H */
diff --git a/arch/h8300/include/asm/ucontext.h b/arch/h8300/include/asm/ucontext.h
deleted file mode 100644
index 0bcf8f85fab9..000000000000
--- a/arch/h8300/include/asm/ucontext.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _H8300_UCONTEXT_H
-#define _H8300_UCONTEXT_H
-
-struct ucontext {
-	unsigned long	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct sigcontext uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif
diff --git a/arch/h8300/include/asm/unaligned.h b/arch/h8300/include/asm/unaligned.h
deleted file mode 100644
index b8d06c70c2da..000000000000
--- a/arch/h8300/include/asm/unaligned.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _ASM_H8300_UNALIGNED_H
-#define _ASM_H8300_UNALIGNED_H
-
-#include <linux/unaligned/be_memmove.h>
-#include <linux/unaligned/le_byteshift.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#endif /* _ASM_H8300_UNALIGNED_H */
diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h
deleted file mode 100644
index ab671ecf5196..000000000000
--- a/arch/h8300/include/asm/unistd.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef _ASM_H8300_UNISTD_H_
-#define _ASM_H8300_UNISTD_H_
-
-#include <uapi/asm/unistd.h>
-
-
-#define NR_syscalls 321
-
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_IPC
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLD_MMAP
-#define __ARCH_WANT_SYS_OLD_SELECT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_FORK
-#define __ARCH_WANT_SYS_VFORK
-#define __ARCH_WANT_SYS_CLONE
-
-#endif /* _ASM_H8300_UNISTD_H_ */
diff --git a/arch/h8300/include/asm/user.h b/arch/h8300/include/asm/user.h
deleted file mode 100644
index 14a9e18950f1..000000000000
--- a/arch/h8300/include/asm/user.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef _H8300_USER_H
-#define _H8300_USER_H
-
-#include <asm/page.h>
-
-/* Core file format: The core file is written in such a way that gdb
-   can understand it and provide useful information to the user (under
-   linux we use the 'trad-core' bfd).  There are quite a number of
-   obstacles to being able to view the contents of the floating point
-   registers, and until these are solved you will not be able to view the
-   contents of them.  Actually, you can read in the core file and look at
-   the contents of the user struct to find out what the floating point
-   registers contain.
-   The actual file contents are as follows:
-   UPAGE: 1 page consisting of a user struct that tells gdb what is present
-   in the file.  Directly after this is a copy of the task_struct, which
-   is currently not used by gdb, but it may come in useful at some point.
-   All of the registers are stored as part of the upage.  The upage should
-   always be only one page.
-   DATA: The data area is stored.  We use current->end_text to
-   current->brk to pick up all of the user variables, plus any memory
-   that may have been malloced.  No attempt is made to determine if a page
-   is demand-zero or if a page is totally unused, we just cover the entire
-   range.  All of the addresses are rounded in such a way that an integral
-   number of pages is written.
-   STACK: We need the stack information in order to get a meaningful
-   backtrace.  We need to write the data from (esp) to
-   current->start_stack, so we round each of these off in order to be able
-   to write an integer number of pages.
-   The minimum core file size is 3 pages, or 12288 bytes.
-*/
-
-/* This is the old layout of "struct pt_regs" as of Linux 1.x, and
-   is still the layout used by user (the new pt_regs doesn't have
-   all registers). */
-struct user_regs_struct {
-	long er1,er2,er3,er4,er5,er6;
-	long er0;
-	long usp;
-	long orig_er0;
-	short ccr;
-	long pc;
-};
-
-	
-/* When the kernel dumps core, it starts by dumping the user struct -
-   this will be used by gdb to figure out where the data and stack segments
-   are within the file, and what virtual addresses to use. */
-struct user{
-/* We start with the registers, to mimic the way that "memory" is returned
-   from the ptrace(3,...) function.  */
-  struct user_regs_struct regs;	/* Where the registers are actually stored */
-/* ptrace does not yet supply these.  Someday.... */
-/* The rest of this junk is to help gdb figure out what goes where */
-  unsigned long int u_tsize;	/* Text segment size (pages). */
-  unsigned long int u_dsize;	/* Data segment size (pages). */
-  unsigned long int u_ssize;	/* Stack segment size (pages). */
-  unsigned long start_code;     /* Starting virtual address of text. */
-  unsigned long start_stack;	/* Starting virtual address of stack area.
-				   This is actually the bottom of the stack,
-				   the top of the stack is always found in the
-				   esp register.  */
-  long int signal;     		/* Signal that caused the core dump. */
-  int reserved;			/* No longer used */
-  unsigned long u_ar0;		/* Used by gdb to help find the values for */
-				/* the registers. */
-  unsigned long magic;		/* To uniquely identify a core file */
-  char u_comm[32];		/* User command that was responsible */
-};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
-#endif
diff --git a/arch/h8300/include/asm/virtconvert.h b/arch/h8300/include/asm/virtconvert.h
deleted file mode 100644
index 19cfd62b11c3..000000000000
--- a/arch/h8300/include/asm/virtconvert.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef __H8300_VIRT_CONVERT__
-#define __H8300_VIRT_CONVERT__
-
-/*
- * Macros used for converting between virtual and physical mappings.
- */
-
-#ifdef __KERNEL__
-
-#include <asm/setup.h>
-#include <asm/page.h>
-
-#define phys_to_virt(vaddr)	((void *) (vaddr))
-#define virt_to_phys(vaddr)	((unsigned long) (vaddr))
-
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-#endif
-#endif
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
deleted file mode 100644
index 040178cdb3eb..000000000000
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ /dev/null
@@ -1,34 +0,0 @@
-# UAPI Header export list
-include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
diff --git a/arch/h8300/include/uapi/asm/auxvec.h b/arch/h8300/include/uapi/asm/auxvec.h
deleted file mode 100644
index 1d36fe38b088..000000000000
--- a/arch/h8300/include/uapi/asm/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __ASMH8300_AUXVEC_H
-#define __ASMH8300_AUXVEC_H
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/bitsperlong.h b/arch/h8300/include/uapi/asm/bitsperlong.h
deleted file mode 100644
index 6dc0bb0c13b2..000000000000
--- a/arch/h8300/include/uapi/asm/bitsperlong.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/bitsperlong.h>
diff --git a/arch/h8300/include/uapi/asm/byteorder.h b/arch/h8300/include/uapi/asm/byteorder.h
deleted file mode 100644
index 13539da99efd..000000000000
--- a/arch/h8300/include/uapi/asm/byteorder.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_BYTEORDER_H
-#define _H8300_BYTEORDER_H
-
-#include <linux/byteorder/big_endian.h>
-
-#endif /* _H8300_BYTEORDER_H */
diff --git a/arch/h8300/include/uapi/asm/errno.h b/arch/h8300/include/uapi/asm/errno.h
deleted file mode 100644
index 0c2f5641fdcc..000000000000
--- a/arch/h8300/include/uapi/asm/errno.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_ERRNO_H
-#define _H8300_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif /* _H8300_ERRNO_H */
diff --git a/arch/h8300/include/uapi/asm/fcntl.h b/arch/h8300/include/uapi/asm/fcntl.h
deleted file mode 100644
index 1952cb2e3b06..000000000000
--- a/arch/h8300/include/uapi/asm/fcntl.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _H8300_FCNTL_H
-#define _H8300_FCNTL_H
-
-#define O_DIRECTORY	040000	/* must be a directory */
-#define O_NOFOLLOW	0100000	/* don't follow links */
-#define O_DIRECT	0200000	/* direct disk access hint - currently ignored */
-#define O_LARGEFILE	0400000
-
-#include <asm-generic/fcntl.h>
-
-#endif /* _H8300_FCNTL_H */
diff --git a/arch/h8300/include/uapi/asm/ioctl.h b/arch/h8300/include/uapi/asm/ioctl.h
deleted file mode 100644
index b279fe06dfe5..000000000000
--- a/arch/h8300/include/uapi/asm/ioctl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ioctl.h>
diff --git a/arch/h8300/include/uapi/asm/ioctls.h b/arch/h8300/include/uapi/asm/ioctls.h
deleted file mode 100644
index 30eaed2facdb..000000000000
--- a/arch/h8300/include/uapi/asm/ioctls.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __ARCH_H8300_IOCTLS_H__
-#define __ARCH_H8300_IOCTLS_H__
-
-#define FIOQSIZE	0x545E
-
-#include <asm-generic/ioctls.h>
-
-#endif /* __ARCH_H8300_IOCTLS_H__ */
diff --git a/arch/h8300/include/uapi/asm/ipcbuf.h b/arch/h8300/include/uapi/asm/ipcbuf.h
deleted file mode 100644
index 84c7e51cb6d0..000000000000
--- a/arch/h8300/include/uapi/asm/ipcbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/h8300/include/uapi/asm/kvm_para.h b/arch/h8300/include/uapi/asm/kvm_para.h
deleted file mode 100644
index 14fab8f0b957..000000000000
--- a/arch/h8300/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kvm_para.h>
diff --git a/arch/h8300/include/uapi/asm/mman.h b/arch/h8300/include/uapi/asm/mman.h
deleted file mode 100644
index 8eebf89f5ab1..000000000000
--- a/arch/h8300/include/uapi/asm/mman.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mman.h>
diff --git a/arch/h8300/include/uapi/asm/msgbuf.h b/arch/h8300/include/uapi/asm/msgbuf.h
deleted file mode 100644
index 6b148cd09aa5..000000000000
--- a/arch/h8300/include/uapi/asm/msgbuf.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _H8300_MSGBUF_H
-#define _H8300_MSGBUF_H
-
-/* 
- * The msqid64_ds structure for H8/300 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-	unsigned long	__unused1;
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-	unsigned long	__unused2;
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned long	__unused3;
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-#endif /* _H8300_MSGBUF_H */
diff --git a/arch/h8300/include/uapi/asm/param.h b/arch/h8300/include/uapi/asm/param.h
deleted file mode 100644
index 3dd18ae15f03..000000000000
--- a/arch/h8300/include/uapi/asm/param.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _UAPI_H8300_PARAM_H
-#define _UAPI_H8300_PARAM_H
-
-#ifndef __KERNEL__
-#define HZ		100
-#endif
-
-#define EXEC_PAGESIZE	4096
-
-#ifndef NOGROUP
-#define NOGROUP		(-1)
-#endif
-
-#define MAXHOSTNAMELEN	64	/* max length of hostname */
-
-#endif /* _UAPI_H8300_PARAM_H */
diff --git a/arch/h8300/include/uapi/asm/poll.h b/arch/h8300/include/uapi/asm/poll.h
deleted file mode 100644
index f61540c22d94..000000000000
--- a/arch/h8300/include/uapi/asm/poll.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __H8300_POLL_H
-#define __H8300_POLL_H
-
-#define POLLWRNORM	POLLOUT
-#define POLLWRBAND	256
-
-#include <asm-generic/poll.h>
-
-#undef POLLREMOVE
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/posix_types.h b/arch/h8300/include/uapi/asm/posix_types.h
deleted file mode 100644
index 91e62ba4c7b0..000000000000
--- a/arch/h8300/include/uapi/asm/posix_types.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __ARCH_H8300_POSIX_TYPES_H
-#define __ARCH_H8300_POSIX_TYPES_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned short	__kernel_mode_t;
-#define __kernel_mode_t __kernel_mode_t
-
-typedef unsigned short	__kernel_ipc_pid_t;
-#define __kernel_ipc_pid_t __kernel_ipc_pid_t
-
-typedef unsigned short	__kernel_uid_t;
-typedef unsigned short	__kernel_gid_t;
-#define __kernel_uid_t __kernel_uid_t
-
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-#define __kernel_old_uid_t __kernel_old_uid_t
-
-#include <asm-generic/posix_types.h>
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/ptrace.h b/arch/h8300/include/uapi/asm/ptrace.h
deleted file mode 100644
index ef39ec5977b6..000000000000
--- a/arch/h8300/include/uapi/asm/ptrace.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _UAPI_H8300_PTRACE_H
-#define _UAPI_H8300_PTRACE_H
-
-#ifndef __ASSEMBLY__
-
-#define PT_ER1	   0
-#define PT_ER2	   1
-#define PT_ER3	   2
-#define PT_ER4	   3
-#define PT_ER5	   4
-#define PT_ER6	   5
-#define PT_ER0	   6
-#define PT_ORIG_ER0	   7
-#define PT_CCR	   8
-#define PT_PC	   9
-#define PT_USP	   10
-#define PT_EXR     12
-
-/* this struct defines the way the registers are stored on the
-   stack during a system call. */
-
-struct pt_regs {
-	long     retpc;
-	long     er4;
-	long     er5;
-	long     er6;
-	long     er3;
-	long     er2;
-	long     er1;
-	long     orig_er0;
-	unsigned short ccr;
-	long     er0;
-	long     vector;
-#if defined(CONFIG_CPU_H8S)
-	unsigned short exr;
-#endif
-	unsigned long  pc;
-} __attribute__((aligned(2),packed));
-
-#define PTRACE_GETREGS            12
-#define PTRACE_SETREGS            13
-
-#endif /* __ASSEMBLY__ */
-#endif /* _UAPI_H8300_PTRACE_H */
diff --git a/arch/h8300/include/uapi/asm/resource.h b/arch/h8300/include/uapi/asm/resource.h
deleted file mode 100644
index 46c5f4391607..000000000000
--- a/arch/h8300/include/uapi/asm/resource.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_RESOURCE_H
-#define _H8300_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif /* _H8300_RESOURCE_H */
diff --git a/arch/h8300/include/uapi/asm/sembuf.h b/arch/h8300/include/uapi/asm/sembuf.h
deleted file mode 100644
index e04a3ec0cb92..000000000000
--- a/arch/h8300/include/uapi/asm/sembuf.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _H8300_SEMBUF_H
-#define _H8300_SEMBUF_H
-
-/* 
- * The semid64_ds structure for m68k architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-	__kernel_time_t	sem_otime;		/* last semop time */
-	unsigned long	__unused1;
-	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned long	__unused2;
-	unsigned long	sem_nsems;		/* no. of semaphores in array */
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _H8300_SEMBUF_H */
diff --git a/arch/h8300/include/uapi/asm/setup.h b/arch/h8300/include/uapi/asm/setup.h
deleted file mode 100644
index e2c600e96733..000000000000
--- a/arch/h8300/include/uapi/asm/setup.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __H8300_SETUP_H
-#define __H8300_SETUP_H
-
-#define COMMAND_LINE_SIZE	512
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/shmbuf.h b/arch/h8300/include/uapi/asm/shmbuf.h
deleted file mode 100644
index 64e77993a7a9..000000000000
--- a/arch/h8300/include/uapi/asm/shmbuf.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef _H8300_SHMBUF_H
-#define _H8300_SHMBUF_H
-
-/* 
- * The shmid64_ds structure for m68k architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-	unsigned long		__unused1;
-	__kernel_time_t		shm_dtime;	/* last detach time */
-	unsigned long		__unused2;
-	__kernel_time_t		shm_ctime;	/* last change time */
-	unsigned long		__unused3;
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused4;
-	unsigned long		__unused5;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* _H8300_SHMBUF_H */
diff --git a/arch/h8300/include/uapi/asm/sigcontext.h b/arch/h8300/include/uapi/asm/sigcontext.h
deleted file mode 100644
index e4b81505f8f8..000000000000
--- a/arch/h8300/include/uapi/asm/sigcontext.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef _ASM_H8300_SIGCONTEXT_H
-#define _ASM_H8300_SIGCONTEXT_H
-
-struct sigcontext {
-	unsigned long  sc_mask; 	/* old sigmask */
-	unsigned long  sc_usp;		/* old user stack pointer */
-	unsigned long  sc_er0;
-	unsigned long  sc_er1;
-	unsigned long  sc_er2;
-	unsigned long  sc_er3;
-	unsigned long  sc_er4;
-	unsigned long  sc_er5;
-	unsigned long  sc_er6;
-	unsigned short sc_ccr;
-	unsigned long  sc_pc;
-};
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/siginfo.h b/arch/h8300/include/uapi/asm/siginfo.h
deleted file mode 100644
index bc8fbea931a5..000000000000
--- a/arch/h8300/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_SIGINFO_H
-#define _H8300_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-#endif
diff --git a/arch/h8300/include/uapi/asm/signal.h b/arch/h8300/include/uapi/asm/signal.h
deleted file mode 100644
index af3a6c37fee6..000000000000
--- a/arch/h8300/include/uapi/asm/signal.h
+++ /dev/null
@@ -1,115 +0,0 @@
-#ifndef _UAPI_H8300_SIGNAL_H
-#define _UAPI_H8300_SIGNAL_H
-
-#include <linux/types.h>
-
-/* Avoid too many header ordering problems.  */
-struct siginfo;
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-#define NSIG		32
-typedef unsigned long sigset_t;
-
-#endif /* __KERNEL__ */
-
-#define SIGHUP		 1
-#define SIGINT		 2
-#define SIGQUIT		 3
-#define SIGILL		 4
-#define SIGTRAP		 5
-#define SIGABRT		 6
-#define SIGIOT		 6
-#define SIGBUS		 7
-#define SIGFPE		 8
-#define SIGKILL		 9
-#define SIGUSR1		10
-#define SIGSEGV		11
-#define SIGUSR2		12
-#define SIGPIPE		13
-#define SIGALRM		14
-#define SIGTERM		15
-#define SIGSTKFLT	16
-#define SIGCHLD		17
-#define SIGCONT		18
-#define SIGSTOP		19
-#define SIGTSTP		20
-#define SIGTTIN		21
-#define SIGTTOU		22
-#define SIGURG		23
-#define SIGXCPU		24
-#define SIGXFSZ		25
-#define SIGVTALRM	26
-#define SIGPROF		27
-#define SIGWINCH	28
-#define SIGIO		29
-#define SIGPOLL		SIGIO
-/*
-#define SIGLOST		29
-*/
-#define SIGPWR		30
-#define SIGSYS		31
-#define	SIGUNUSED	31
-
-/* These should not be considered constants from userland.  */
-#define SIGRTMIN	32
-#define SIGRTMAX	_NSIG
-
-/*
- * SA_FLAGS values:
- *
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_RESETHAND clears the handler when the signal is delivered.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_NODEFER prevents the current signal from being masked in the handler.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP	0x00000001
-#define SA_NOCLDWAIT	0x00000002 /* not supported yet */
-#define SA_SIGINFO	0x00000004
-#define SA_ONSTACK	0x08000000
-#define SA_RESTART	0x10000000
-#define SA_NODEFER	0x40000000
-#define SA_RESETHAND	0x80000000
-
-#define SA_NOMASK	SA_NODEFER
-#define SA_ONESHOT	SA_RESETHAND
-
-#define SA_RESTORER	0x04000000
-
-#define MINSIGSTKSZ	2048
-#define SIGSTKSZ	8192
-
-#include <asm-generic/signal-defs.h>
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-struct sigaction {
-	union {
-	  __sighandler_t _sa_handler;
-	  void (*_sa_sigaction)(int, struct siginfo *, void *);
-	} _u;
-	sigset_t sa_mask;
-	unsigned long sa_flags;
-	void (*sa_restorer)(void);
-};
-
-#define sa_handler	_u._sa_handler
-#define sa_sigaction	_u._sa_sigaction
-
-#endif /* __KERNEL__ */
-
-typedef struct sigaltstack {
-	void *ss_sp;
-	int ss_flags;
-	size_t ss_size;
-} stack_t;
-
-
-#endif /* _UAPI_H8300_SIGNAL_H */
diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h
deleted file mode 100644
index 9490758c5e2b..000000000000
--- a/arch/h8300/include/uapi/asm/socket.h
+++ /dev/null
@@ -1,79 +0,0 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockoptions(2) */
-#define SOL_SOCKET	1
-
-#define SO_DEBUG	1
-#define SO_REUSEADDR	2
-#define SO_TYPE		3
-#define SO_ERROR	4
-#define SO_DONTROUTE	5
-#define SO_BROADCAST	6
-#define SO_SNDBUF	7
-#define SO_RCVBUF	8
-#define SO_SNDBUFFORCE	32
-#define SO_RCVBUFFORCE	33
-#define SO_KEEPALIVE	9
-#define SO_OOBINLINE	10
-#define SO_NO_CHECK	11
-#define SO_PRIORITY	12
-#define SO_LINGER	13
-#define SO_BSDCOMPAT	14
-#define SO_REUSEPORT	15
-#define SO_PASSCRED	16
-#define SO_PEERCRED	17
-#define SO_RCVLOWAT	18
-#define SO_SNDLOWAT	19
-#define SO_RCVTIMEO	20
-#define SO_SNDTIMEO	21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION		22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
-#define SO_SECURITY_ENCRYPTION_NETWORK		24
-
-#define SO_BINDTODEVICE	25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER        26
-#define SO_DETACH_FILTER        27
-#define SO_GET_FILTER		SO_ATTACH_FILTER
-
-#define SO_PEERNAME             28
-#define SO_TIMESTAMP		29
-#define SCM_TIMESTAMP		SO_TIMESTAMP
-
-#define SO_ACCEPTCONN		30
-
-#define SO_PEERSEC		31
-#define SO_PASSSEC		34
-#define SO_TIMESTAMPNS		35
-#define SCM_TIMESTAMPNS		SO_TIMESTAMPNS
-
-#define SO_MARK			36
-
-#define SO_TIMESTAMPING		37
-#define SCM_TIMESTAMPING	SO_TIMESTAMPING
-
-#define SO_PROTOCOL		38
-#define SO_DOMAIN		39
-
-#define SO_RXQ_OVFL             40
-
-#define SO_WIFI_STATUS		41
-#define SCM_WIFI_STATUS		SO_WIFI_STATUS
-#define SO_PEEK_OFF		42
-
-/* Instruct lower device to use last 4-bytes of skb data as FCS */
-#define SO_NOFCS		43
-
-#define SO_LOCK_FILTER		44
-
-#define SO_SELECT_ERR_QUEUE	45
-
-#define SO_BUSY_POLL		46
-
-#endif /* _ASM_SOCKET_H */
diff --git a/arch/h8300/include/uapi/asm/sockios.h b/arch/h8300/include/uapi/asm/sockios.h
deleted file mode 100644
index e9c7ec810c23..000000000000
--- a/arch/h8300/include/uapi/asm/sockios.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ARCH_H8300_SOCKIOS__
-#define __ARCH_H8300_SOCKIOS__
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 	0x8901
-#define SIOCSPGRP	0x8902
-#define FIOGETOWN	0x8903
-#define SIOCGPGRP	0x8904
-#define SIOCATMARK	0x8905
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
-
-#endif /* __ARCH_H8300_SOCKIOS__ */
diff --git a/arch/h8300/include/uapi/asm/stat.h b/arch/h8300/include/uapi/asm/stat.h
deleted file mode 100644
index 62c3cc24dfe6..000000000000
--- a/arch/h8300/include/uapi/asm/stat.h
+++ /dev/null
@@ -1,78 +0,0 @@
-#ifndef _H8300_STAT_H
-#define _H8300_STAT_H
-
-struct __old_kernel_stat {
-	unsigned short st_dev;
-	unsigned short st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-	unsigned short st_rdev;
-	unsigned long  st_size;
-	unsigned long  st_atime;
-	unsigned long  st_mtime;
-	unsigned long  st_ctime;
-};
-
-struct stat {
-	unsigned short st_dev;
-	unsigned short __pad1;
-	unsigned long st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-	unsigned short st_rdev;
-	unsigned short __pad2;
-	unsigned long  st_size;
-	unsigned long  st_blksize;
-	unsigned long  st_blocks;
-	unsigned long  st_atime;
-	unsigned long  __unused1;
-	unsigned long  st_mtime;
-	unsigned long  __unused2;
-	unsigned long  st_ctime;
-	unsigned long  __unused3;
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-/* This matches struct stat64 in glibc2.1, hence the absolutely
- * insane amounts of padding around dev_t's.
- */
-struct stat64 {
-	unsigned long long	st_dev;
-	unsigned char	__pad1[2];
-
-#define STAT64_HAS_BROKEN_ST_INO	1
-	unsigned long	__st_ino;
-
-	unsigned int	st_mode;
-	unsigned int	st_nlink;
-
-	unsigned long	st_uid;
-	unsigned long	st_gid;
-
-	unsigned long long	st_rdev;
-	unsigned char	__pad3[2];
-
-	long long	st_size;
-	unsigned long	st_blksize;
-
-	unsigned long	__pad4;		/* future possible st_blocks high bits */
-	unsigned long	st_blocks;	/* Number 512-byte blocks allocated. */
-
-	unsigned long	st_atime;
-	unsigned long	st_atime_nsec;
-
-	unsigned long	st_mtime;
-	unsigned long	st_mtime_nsec;
-
-	unsigned long	st_ctime;
-	unsigned long	st_ctime_nsec;
-
-	unsigned long long	st_ino;
-};
-
-#endif /* _H8300_STAT_H */
diff --git a/arch/h8300/include/uapi/asm/statfs.h b/arch/h8300/include/uapi/asm/statfs.h
deleted file mode 100644
index b96efa712aac..000000000000
--- a/arch/h8300/include/uapi/asm/statfs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _H8300_STATFS_H
-#define _H8300_STATFS_H
-
-#include <asm-generic/statfs.h>
-
-#endif /* _H8300_STATFS_H */
diff --git a/arch/h8300/include/uapi/asm/swab.h b/arch/h8300/include/uapi/asm/swab.h
deleted file mode 100644
index 39abbf52807d..000000000000
--- a/arch/h8300/include/uapi/asm/swab.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _H8300_SWAB_H
-#define _H8300_SWAB_H
-
-#include <linux/types.h>
-
-#if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-#  define __SWAB_64_THRU_32__
-#endif
-
-#endif /* _H8300_SWAB_H */
diff --git a/arch/h8300/include/uapi/asm/termbits.h b/arch/h8300/include/uapi/asm/termbits.h
deleted file mode 100644
index 3287a6244d74..000000000000
--- a/arch/h8300/include/uapi/asm/termbits.h
+++ /dev/null
@@ -1,201 +0,0 @@
-#ifndef __ARCH_H8300_TERMBITS_H__
-#define __ARCH_H8300_TERMBITS_H__
-
-#include <linux/posix_types.h>
-
-typedef unsigned char	cc_t;
-typedef unsigned int	speed_t;
-typedef unsigned int	tcflag_t;
-
-#define NCCS 19
-struct termios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-};
-
-struct termios2 {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-struct ktermios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-
-/* c_iflag bits */
-#define IGNBRK	0000001
-#define BRKINT	0000002
-#define IGNPAR	0000004
-#define PARMRK	0000010
-#define INPCK	0000020
-#define ISTRIP	0000040
-#define INLCR	0000100
-#define IGNCR	0000200
-#define ICRNL	0000400
-#define IUCLC	0001000
-#define IXON	0002000
-#define IXANY	0004000
-#define IXOFF	0010000
-#define IMAXBEL	0020000
-#define IUTF8	0040000
-
-/* c_oflag bits */
-#define OPOST	0000001
-#define OLCUC	0000002
-#define ONLCR	0000004
-#define OCRNL	0000010
-#define ONOCR	0000020
-#define ONLRET	0000040
-#define OFILL	0000100
-#define OFDEL	0000200
-#define NLDLY	0000400
-#define   NL0	0000000
-#define   NL1	0000400
-#define CRDLY	0003000
-#define   CR0	0000000
-#define   CR1	0001000
-#define   CR2	0002000
-#define   CR3	0003000
-#define TABDLY	0014000
-#define   TAB0	0000000
-#define   TAB1	0004000
-#define   TAB2	0010000
-#define   TAB3	0014000
-#define   XTABS	0014000
-#define BSDLY	0020000
-#define   BS0	0000000
-#define   BS1	0020000
-#define VTDLY	0040000
-#define   VT0	0000000
-#define   VT1	0040000
-#define FFDLY	0100000
-#define   FF0	0000000
-#define   FF1	0100000
-
-/* c_cflag bit meaning */
-#define CBAUD	0010017
-#define  B0	0000000		/* hang up */
-#define  B50	0000001
-#define  B75	0000002
-#define  B110	0000003
-#define  B134	0000004
-#define  B150	0000005
-#define  B200	0000006
-#define  B300	0000007
-#define  B600	0000010
-#define  B1200	0000011
-#define  B1800	0000012
-#define  B2400	0000013
-#define  B4800	0000014
-#define  B9600	0000015
-#define  B19200	0000016
-#define  B38400	0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE	0000060
-#define   CS5	0000000
-#define   CS6	0000020
-#define   CS7	0000040
-#define   CS8	0000060
-#define CSTOPB	0000100
-#define CREAD	0000200
-#define PARENB	0000400
-#define PARODD	0001000
-#define HUPCL	0002000
-#define CLOCAL	0004000
-#define CBAUDEX 0010000
-#define    BOTHER 0010000
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD	  002003600000		/* input baud rate */
-#define CMSPAR	  010000000000		/* mark or space (stick) parity */
-#define CRTSCTS	  020000000000		/* flow control */
-
-#define IBSHIFT	  16			/* shift from CBAUD to CIBAUD */
-
-/* c_lflag bits */
-#define ISIG	0000001
-#define ICANON	0000002
-#define XCASE	0000004
-#define ECHO	0000010
-#define ECHOE	0000020
-#define ECHOK	0000040
-#define ECHONL	0000100
-#define NOFLSH	0000200
-#define TOSTOP	0000400
-#define ECHOCTL	0001000
-#define ECHOPRT	0002000
-#define ECHOKE	0004000
-#define FLUSHO	0010000
-#define PENDIN	0040000
-#define IEXTEN	0100000
-#define EXTPROC	0200000
-
-
-/* tcflow() and TCXONC use these */
-#define	TCOOFF		0
-#define	TCOON		1
-#define	TCIOFF		2
-#define	TCION		3
-
-/* tcflush() and TCFLSH use these */
-#define	TCIFLUSH	0
-#define	TCOFLUSH	1
-#define	TCIOFLUSH	2
-
-/* tcsetattr uses these */
-#define	TCSANOW		0
-#define	TCSADRAIN	1
-#define	TCSAFLUSH	2
-
-#endif /* __ARCH_H8300_TERMBITS_H__ */
diff --git a/arch/h8300/include/uapi/asm/termios.h b/arch/h8300/include/uapi/asm/termios.h
deleted file mode 100644
index 5a67d7e38843..000000000000
--- a/arch/h8300/include/uapi/asm/termios.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef _UAPI_H8300_TERMIOS_H
-#define _UAPI_H8300_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
- 
-struct winsize {
-	unsigned short ws_row;
-	unsigned short ws_col;
-	unsigned short ws_xpixel;
-	unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-	unsigned short c_iflag;		/* input mode flags */
-	unsigned short c_oflag;		/* output mode flags */
-	unsigned short c_cflag;		/* control mode flags */
-	unsigned short c_lflag;		/* local mode flags */
-	unsigned char c_line;		/* line discipline */
-	unsigned char c_cc[NCC];	/* control characters */
-};
-
-
-/* modem lines */
-#define TIOCM_LE	0x001
-#define TIOCM_DTR	0x002
-#define TIOCM_RTS	0x004
-#define TIOCM_ST	0x008
-#define TIOCM_SR	0x010
-#define TIOCM_CTS	0x020
-#define TIOCM_CAR	0x040
-#define TIOCM_RNG	0x080
-#define TIOCM_DSR	0x100
-#define TIOCM_CD	TIOCM_CAR
-#define TIOCM_RI	TIOCM_RNG
-#define TIOCM_OUT1	0x2000
-#define TIOCM_OUT2	0x4000
-#define TIOCM_LOOP	0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-
-#endif /* _UAPI_H8300_TERMIOS_H */
diff --git a/arch/h8300/include/uapi/asm/types.h b/arch/h8300/include/uapi/asm/types.h
deleted file mode 100644
index 9ec9d4c5ac4d..000000000000
--- a/arch/h8300/include/uapi/asm/types.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/int-ll64.h>
diff --git a/arch/h8300/include/uapi/asm/unistd.h b/arch/h8300/include/uapi/asm/unistd.h
deleted file mode 100644
index 8cb5d429f840..000000000000
--- a/arch/h8300/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,330 +0,0 @@
-#ifndef _UAPI_ASM_H8300_UNISTD_H_
-#define _UAPI_ASM_H8300_UNISTD_H_
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_restart_syscall      0
-#define __NR_exit		  1
-#define __NR_fork		  2
-#define __NR_read		  3
-#define __NR_write		  4
-#define __NR_open		  5
-#define __NR_close		  6
-#define __NR_waitpid		  7
-#define __NR_creat		  8
-#define __NR_link		  9
-#define __NR_unlink		 10
-#define __NR_execve		 11
-#define __NR_chdir		 12
-#define __NR_time		 13
-#define __NR_mknod		 14
-#define __NR_chmod		 15
-#define __NR_lchown		 16
-#define __NR_break		 17
-#define __NR_oldstat		 18
-#define __NR_lseek		 19
-#define __NR_getpid		 20
-#define __NR_mount		 21
-#define __NR_umount		 22
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_ptrace		 26
-#define __NR_alarm		 27
-#define __NR_oldfstat		 28
-#define __NR_pause		 29
-#define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
-#define __NR_access		 33
-#define __NR_nice		 34
-#define __NR_ftime		 35
-#define __NR_sync		 36
-#define __NR_kill		 37
-#define __NR_rename		 38
-#define __NR_mkdir		 39
-#define __NR_rmdir		 40
-#define __NR_dup		 41
-#define __NR_pipe		 42
-#define __NR_times		 43
-#define __NR_prof		 44
-#define __NR_brk		 45
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_signal		 48
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_acct		 51
-#define __NR_umount2		 52
-#define __NR_lock		 53
-#define __NR_ioctl		 54
-#define __NR_fcntl		 55
-#define __NR_mpx		 56
-#define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
-#define __NR_umask		 60
-#define __NR_chroot		 61
-#define __NR_ustat		 62
-#define __NR_dup2		 63
-#define __NR_getppid		 64
-#define __NR_getpgrp		 65
-#define __NR_setsid		 66
-#define __NR_sigaction		 67
-#define __NR_sgetmask		 68
-#define __NR_ssetmask		 69
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_sigsuspend		 72
-#define __NR_sigpending		 73
-#define __NR_sethostname	 74
-#define __NR_setrlimit		 75
-#define __NR_getrlimit		 76
-#define __NR_getrusage		 77
-#define __NR_gettimeofday	 78
-#define __NR_settimeofday	 79
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_select		 82
-#define __NR_symlink		 83
-#define __NR_oldlstat		 84
-#define __NR_readlink		 85
-#define __NR_uselib		 86
-#define __NR_swapon		 87
-#define __NR_reboot		 88
-#define __NR_readdir		 89
-#define __NR_mmap		 90
-#define __NR_munmap		 91
-#define __NR_truncate		 92
-#define __NR_ftruncate		 93
-#define __NR_fchmod		 94
-#define __NR_fchown		 95
-#define __NR_getpriority	 96
-#define __NR_setpriority	 97
-#define __NR_profil		 98
-#define __NR_statfs		 99
-#define __NR_fstatfs		100
-#define __NR_ioperm		101
-#define __NR_socketcall		102
-#define __NR_syslog		103
-#define __NR_setitimer		104
-#define __NR_getitimer		105
-#define __NR_stat		106
-#define __NR_lstat		107
-#define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		110
-#define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86old		113
-#define __NR_wait4		114
-#define __NR_swapoff		115
-#define __NR_sysinfo		116
-#define __NR_ipc		117
-#define __NR_fsync		118
-#define __NR_sigreturn		119
-#define __NR_clone		120
-#define __NR_setdomainname	121
-#define __NR_uname		122
-#define __NR_modify_ldt		123
-#define __NR_adjtimex		124
-#define __NR_mprotect		125
-#define __NR_sigprocmask	126
-#define __NR_create_module	127
-#define __NR_init_module	128
-#define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
-#define __NR_quotactl		131
-#define __NR_getpgid		132
-#define __NR_fchdir		133
-#define __NR_bdflush		134
-#define __NR_sysfs		135
-#define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR_getdents		141
-#define __NR__newselect		142
-#define __NR_flock		143
-#define __NR_msync		144
-#define __NR_readv		145
-#define __NR_writev		146
-#define __NR_getsid		147
-#define __NR_fdatasync		148
-#define __NR__sysctl		149
-#define __NR_mlock		150
-#define __NR_munlock		151
-#define __NR_mlockall		152
-#define __NR_munlockall		153
-#define __NR_sched_setparam		154
-#define __NR_sched_getparam		155
-#define __NR_sched_setscheduler		156
-#define __NR_sched_getscheduler		157
-#define __NR_sched_yield		158
-#define __NR_sched_get_priority_max	159
-#define __NR_sched_get_priority_min	160
-#define __NR_sched_rr_get_interval	161
-#define __NR_nanosleep		162
-#define __NR_mremap		163
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_vm86		166
-#define __NR_query_module	167
-#define __NR_poll		168
-#define __NR_nfsservctl		169
-#define __NR_setresgid		170
-#define __NR_getresgid		171
-#define __NR_prctl		172
-#define __NR_rt_sigreturn	173
-#define __NR_rt_sigaction	174
-#define __NR_rt_sigprocmask	175
-#define __NR_rt_sigpending	176
-#define __NR_rt_sigtimedwait	177
-#define __NR_rt_sigqueueinfo	178
-#define __NR_rt_sigsuspend	179
-#define __NR_pread64		180
-#define __NR_pwrite64		181
-#define __NR_chown		182
-#define __NR_getcwd		183
-#define __NR_capget		184
-#define __NR_capset		185
-#define __NR_sigaltstack	186
-#define __NR_sendfile		187
-#define __NR_getpmsg		188	/* some people actually want streams */
-#define __NR_putpmsg		189	/* some people actually want streams */
-#define __NR_vfork		190
-#define __NR_ugetrlimit		191
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#define __NR_lchown32		198
-#define __NR_getuid32		199
-#define __NR_getgid32		200
-#define __NR_geteuid32		201
-#define __NR_getegid32		202
-#define __NR_setreuid32		203
-#define __NR_setregid32		204
-#define __NR_getgroups32	205
-#define __NR_setgroups32	206
-#define __NR_fchown32		207
-#define __NR_setresuid32	208
-#define __NR_getresuid32	209
-#define __NR_setresgid32	210
-#define __NR_getresgid32	211
-#define __NR_chown32		212
-#define __NR_setuid32		213
-#define __NR_setgid32		214
-#define __NR_setfsuid32		215
-#define __NR_setfsgid32		216
-#define __NR_pivot_root		217
-#define __NR_mincore		218
-#define __NR_madvise		219
-#define __NR_madvise1		219
-#define __NR_getdents64		220
-#define __NR_fcntl64		221
-/* 223 is unused */
-#define __NR_gettid		224
-#define __NR_readahead		225
-#define __NR_setxattr		226
-#define __NR_lsetxattr		227
-#define __NR_fsetxattr		228
-#define __NR_getxattr		229
-#define __NR_lgetxattr		230
-#define __NR_fgetxattr		231
-#define __NR_listxattr		232
-#define __NR_llistxattr		233
-#define __NR_flistxattr		234
-#define __NR_removexattr	235
-#define __NR_lremovexattr	236
-#define __NR_fremovexattr	237
-#define __NR_tkill		238
-#define __NR_sendfile64		239
-#define __NR_futex		240
-#define __NR_sched_setaffinity	241
-#define __NR_sched_getaffinity	242
-#define __NR_set_thread_area	243
-#define __NR_get_thread_area	244
-#define __NR_io_setup		245
-#define __NR_io_destroy		246
-#define __NR_io_getevents	247
-#define __NR_io_submit		248
-#define __NR_io_cancel		249
-#define __NR_fadvise64		250
-/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
-#define __NR_exit_group		252
-#define __NR_lookup_dcookie	253
-#define __NR_epoll_create	254
-#define __NR_epoll_ctl		255
-#define __NR_epoll_wait		256
-#define __NR_remap_file_pages	257
-#define __NR_set_tid_address	258
-#define __NR_timer_create	259
-#define __NR_timer_settime	(__NR_timer_create+1)
-#define __NR_timer_gettime	(__NR_timer_create+2)
-#define __NR_timer_getoverrun	(__NR_timer_create+3)
-#define __NR_timer_delete	(__NR_timer_create+4)
-#define __NR_clock_settime	(__NR_timer_create+5)
-#define __NR_clock_gettime	(__NR_timer_create+6)
-#define __NR_clock_getres	(__NR_timer_create+7)
-#define __NR_clock_nanosleep	(__NR_timer_create+8)
-#define __NR_statfs64		268
-#define __NR_fstatfs64		269
-#define __NR_tgkill		270
-#define __NR_utimes		271
-#define __NR_fadvise64_64	272
-#define __NR_vserver		273
-#define __NR_mbind		274
-#define __NR_get_mempolicy	275
-#define __NR_set_mempolicy	276
-#define __NR_mq_open 		277
-#define __NR_mq_unlink		(__NR_mq_open+1)
-#define __NR_mq_timedsend	(__NR_mq_open+2)
-#define __NR_mq_timedreceive	(__NR_mq_open+3)
-#define __NR_mq_notify		(__NR_mq_open+4)
-#define __NR_mq_getsetattr	(__NR_mq_open+5)
-#define __NR_kexec_load		283
-#define __NR_waitid		284
-/* #define __NR_sys_setaltroot	285 */
-#define __NR_add_key		286
-#define __NR_request_key	287
-#define __NR_keyctl		288
-#define __NR_ioprio_set		289
-#define __NR_ioprio_get		290
-#define __NR_inotify_init	291
-#define __NR_inotify_add_watch	292
-#define __NR_inotify_rm_watch	293
-#define __NR_migrate_pages	294
-#define __NR_openat		295
-#define __NR_mkdirat		296
-#define __NR_mknodat		297
-#define __NR_fchownat		298
-#define __NR_futimesat		299
-#define __NR_fstatat64		300
-#define __NR_unlinkat		301
-#define __NR_renameat		302
-#define __NR_linkat		303
-#define __NR_symlinkat		304
-#define __NR_readlinkat		305
-#define __NR_fchmodat		306
-#define __NR_faccessat		307
-#define __NR_pselect6		308
-#define __NR_ppoll		309
-#define __NR_unshare		310
-#define __NR_set_robust_list	311
-#define __NR_get_robust_list	312
-#define __NR_splice		313
-#define __NR_sync_file_range	314
-#define __NR_tee		315
-#define __NR_vmsplice		316
-#define __NR_move_pages		317
-#define __NR_getcpu		318
-#define __NR_epoll_pwait	319
-#define __NR_setns		320
-
-#endif /* _UAPI_ASM_H8300_UNISTD_H_ */
diff --git a/arch/h8300/kernel/Makefile b/arch/h8300/kernel/Makefile
deleted file mode 100644
index 1cc57f872d34..000000000000
--- a/arch/h8300/kernel/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y := vmlinux.lds
-
-obj-y := process.o traps.o ptrace.o irq.o \
-	 sys_h8300.o time.o signal.o \
-         setup.o gpio.o syscalls.o \
-	 entry.o timer/
-
-obj-$(CONFIG_MODULES) += module.o h8300_ksyms.o 
diff --git a/arch/h8300/kernel/asm-offsets.c b/arch/h8300/kernel/asm-offsets.c
deleted file mode 100644
index fd961e0bd741..000000000000
--- a/arch/h8300/kernel/asm-offsets.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * This program is used to generate definitions needed by
- * assembly language modules.
- *
- * We use the technique used in the OSF Mach kernel code:
- * generate asm statements containing #defines,
- * compile this file to assembler, and then extract the
- * #defines from the assembly-language output.
- */
-
-#include <linux/stddef.h>
-#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/ptrace.h>
-#include <linux/hardirq.h>
-#include <linux/kbuild.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/ptrace.h>
-
-int main(void)
-{
-	/* offsets into the task struct */
-	DEFINE(TASK_STATE, offsetof(struct task_struct, state));
-	DEFINE(TASK_FLAGS, offsetof(struct task_struct, flags));
-	DEFINE(TASK_PTRACE, offsetof(struct task_struct, ptrace));
-	DEFINE(TASK_BLOCKED, offsetof(struct task_struct, blocked));
-	DEFINE(TASK_THREAD, offsetof(struct task_struct, thread));
-	DEFINE(TASK_THREAD_INFO, offsetof(struct task_struct, stack));
-	DEFINE(TASK_MM, offsetof(struct task_struct, mm));
-	DEFINE(TASK_ACTIVE_MM, offsetof(struct task_struct, active_mm));
-
-	/* offsets into the irq_cpustat_t struct */
-	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
-
-	/* offsets into the thread struct */
-	DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp));
-	DEFINE(THREAD_USP, offsetof(struct thread_struct, usp));
-	DEFINE(THREAD_CCR, offsetof(struct thread_struct, ccr));
-
-	/* offsets into the pt_regs struct */
-	DEFINE(LER0,  offsetof(struct pt_regs, er0)      - sizeof(long));
-	DEFINE(LER1,  offsetof(struct pt_regs, er1)      - sizeof(long));
-	DEFINE(LER2,  offsetof(struct pt_regs, er2)      - sizeof(long));
-	DEFINE(LER3,  offsetof(struct pt_regs, er3)      - sizeof(long));
-	DEFINE(LER4,  offsetof(struct pt_regs, er4)      - sizeof(long));
-	DEFINE(LER5,  offsetof(struct pt_regs, er5)      - sizeof(long));
-	DEFINE(LER6,  offsetof(struct pt_regs, er6)      - sizeof(long));
-	DEFINE(LORIG, offsetof(struct pt_regs, orig_er0) - sizeof(long));
-	DEFINE(LCCR,  offsetof(struct pt_regs, ccr)      - sizeof(long));
-	DEFINE(LVEC,  offsetof(struct pt_regs, vector)   - sizeof(long));
-#if defined(__H8300S__)
-	DEFINE(LEXR,  offsetof(struct pt_regs, exr)      - sizeof(long));
-#endif
-	DEFINE(LRET,  offsetof(struct pt_regs, pc)       - sizeof(long));
-
-	DEFINE(PT_PTRACED, PT_PTRACED);
-
-	return 0;
-}
diff --git a/arch/h8300/kernel/entry.S b/arch/h8300/kernel/entry.S
deleted file mode 100644
index 94bd30f11df6..000000000000
--- a/arch/h8300/kernel/entry.S
+++ /dev/null
@@ -1,402 +0,0 @@
-/* -*- mode: asm -*-
- *
- *  linux/arch/h8300/platform/h8300h/entry.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *  David McCullough <davidm@snapgear.com>
- *
- */
-
-/*
- *  entry.S
- *  include exception/interrupt gateway
- *          system call entry
- */
-
-#include <linux/sys.h>
-#include <asm/unistd.h>
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/errno.h>
-
-#if defined(CONFIG_CPU_H8300H)
-#define USERRET 8
-INTERRUPTS = 64
-	.h8300h
-	.macro	SHLL2 reg
-	shll.l	\reg
-	shll.l	\reg
-	.endm
-	.macro	SHLR2 reg
-	shlr.l	\reg
-	shlr.l	\reg
-	.endm
-	.macro	SAVEREGS
-	mov.l	er0,@-sp
-	mov.l	er1,@-sp
-	mov.l	er2,@-sp
-	mov.l	er3,@-sp
-	.endm
-	.macro	RESTOREREGS
-	mov.l	@sp+,er3
-	mov.l	@sp+,er2
-	.endm
-	.macro	SAVEEXR
-	.endm
-	.macro	RESTOREEXR
-	.endm
-#endif
-#if defined(CONFIG_CPU_H8S)
-#define USERRET 10
-#define USEREXR 8
-INTERRUPTS = 128
-	.h8300s
-	.macro	SHLL2 reg
-	shll.l	#2,\reg
-	.endm
-	.macro	SHLR2 reg
-	shlr.l	#2,\reg
-	.endm
-	.macro	SAVEREGS
-	stm.l	er0-er3,@-sp
-	.endm
-	.macro	RESTOREREGS
-	ldm.l	@sp+,er2-er3
-	.endm
-	.macro	SAVEEXR
-	mov.w	@(USEREXR:16,er0),r1
-	mov.w	r1,@(LEXR-LER3:16,sp)		/* copy EXR */
-	.endm
-	.macro	RESTOREEXR
-	mov.w	@(LEXR-LER1:16,sp),r1		/* restore EXR */
-	mov.b	r1l,r1h
-	mov.w	r1,@(USEREXR:16,er0)
-	.endm
-#endif
-
-
-/* CPU context save/restore macros. */
-
-	.macro	SAVE_ALL
-	mov.l	er0,@-sp
-	stc	ccr,r0l				/* check kernel mode */
-	btst	#4,r0l
-	bne	5f
-
-	/* user mode */
-	mov.l	sp,@_sw_usp
-	mov.l	@sp,er0				/* restore saved er0 */
-	orc	#0x10,ccr			/* switch kernel stack */
-	mov.l	@_sw_ksp,sp
-	sub.l	#(LRET-LORIG),sp		/* allocate LORIG - LRET */
-	SAVEREGS
-	mov.l   @_sw_usp,er0
-	mov.l   @(USERRET:16,er0),er1           /* copy the RET addr */
-	mov.l   er1,@(LRET-LER3:16,sp)
-	SAVEEXR
-
-	mov.l	@(LORIG-LER3:16,sp),er0
-	mov.l	er0,@(LER0-LER3:16,sp)		/* copy ER0 */
-	mov.w	e1,r1				/* e1 highbyte = ccr */
-	and	#0xef,r1h			/* mask mode? flag */
-	bra	6f
-5:
-	/* kernel mode */
-	mov.l	@sp,er0				/* restore saved er0 */
-	subs	#2,sp				/* set dummy ccr */
-	SAVEREGS
-	mov.w	@(LRET-LER3:16,sp),r1		/* copy old ccr */
-6:
-	mov.b	r1h,r1l
-	mov.b	#0,r1h
-	mov.w	r1,@(LCCR-LER3:16,sp)		/* set ccr */
-	mov.l	er6,@-sp			/* syscall arg #6 */
-	mov.l	er5,@-sp			/* syscall arg #5 */
-	mov.l	er4,@-sp			/* syscall arg #4 */
-	.endm					/* r1 = ccr */
-
-	.macro	RESTORE_ALL
-	mov.l	@sp+,er4
-	mov.l	@sp+,er5
-	mov.l	@sp+,er6
-	RESTOREREGS
-	mov.w	@(LCCR-LER1:16,sp),r0		/* check kernel mode */
-	btst	#4,r0l
-	bne	7f
-
-	orc	#0x80,ccr
-	mov.l	@_sw_usp,er0
-	mov.l	@(LER0-LER1:16,sp),er1		/* restore ER0 */
-	mov.l	er1,@er0
-	RESTOREEXR
-	mov.w	@(LCCR-LER1:16,sp),r1		/* restore the RET addr */
-	mov.b	r1l,r1h
-	mov.b	@(LRET+1-LER1:16,sp),r1l
-	mov.w	r1,e1
-	mov.w	@(LRET+2-LER1:16,sp),r1
-	mov.l	er1,@(USERRET:16,er0)
-
-	mov.l	@sp+,er1
-	add.l	#(LRET-LER1),sp			/* remove LORIG - LRET */
-	mov.l	sp,@_sw_ksp
-	andc	#0xef,ccr			/* switch to user mode */
-	mov.l	er0,sp
-	bra	8f
-7:
-	mov.l	@sp+,er1
-	adds	#4,sp
-	adds	#2,sp
-8:
-	mov.l	@sp+,er0
-	adds	#4,sp				/* remove the sw created LVEC */
-	rte
-	.endm
-
-.globl _system_call
-.globl _ret_from_exception
-.globl _ret_from_fork
-.globl _ret_from_kernel_thread
-.globl _ret_from_interrupt
-.globl _interrupt_redirect_table
-.globl _sw_ksp,_sw_usp
-.globl _resume
-.globl _interrupt_entry
-.globl _trace_break
-
-#if defined(CONFIG_ROMKERNEL)
-	.section .int_redirect,"ax"
-_interrupt_redirect_table:
-#if defined(CONFIG_CPU_H8300H)
-	.rept	7
-	.long	0
-	.endr
-#endif
-#if defined(CONFIG_CPU_H8S)
-	.rept	5
-	.long	0
-	.endr
-	jmp	@_trace_break
-	.long	0
-#endif
-
-	jsr	@_interrupt_entry		/* NMI */
-	jmp	@_system_call			/* TRAPA #0 (System call) */
-	.long	0
-	.long	0
-	jmp	@_trace_break			/* TRAPA #3 (breakpoint) */
-	.rept	INTERRUPTS-12
-	jsr	@_interrupt_entry
-	.endr
-#endif
-#if defined(CONFIG_RAMKERNEL)
-.globl _interrupt_redirect_table
-	.section .bss
-_interrupt_redirect_table:
-	.space	4
-#endif
-
-	.section .text
-	.align	2
-_interrupt_entry:
-	SAVE_ALL
-	mov.l	sp,er0
-	add.l	#LVEC,er0
-	btst	#4,r1l
-	bne	1f
-	/* user LVEC */
-	mov.l	@_sw_usp,er0
-	adds	#4,er0
-1:
-	mov.l	@er0,er0			/* LVEC address */
-#if defined(CONFIG_ROMKERNEL)
-	sub.l	#_interrupt_redirect_table,er0
-#endif
-#if defined(CONFIG_RAMKERNEL)
-	mov.l	@_interrupt_redirect_table,er1
-	sub.l	er1,er0
-#endif
-	SHLR2	er0
-	dec.l	#1,er0
-	mov.l	sp,er1
-	subs	#4,er1				/* adjust ret_pc */
-	jsr	@_do_IRQ
-	jmp	@_ret_from_interrupt
-
-_system_call:
-	subs	#4,sp				/* dummy LVEC */
-	SAVE_ALL
-	andc	#0x7f,ccr
-	mov.l	er0,er4
-
-	/* save top of frame */
-	mov.l	sp,er0
-	jsr	@_set_esp0
-	mov.l	sp,er2
-	and.w	#0xe000,r2
-	mov.b	@((TI_FLAGS+3-(TIF_SYSCALL_TRACE >> 3)):16,er2),r2l
-	btst	#(TIF_SYSCALL_TRACE & 7),r2l
-	beq	1f
-	jsr	@_do_syscall_trace
-1:
-	cmp.l	#NR_syscalls,er4
-	bcc	badsys
-	SHLL2	er4
-	mov.l	#_sys_call_table,er0
-	add.l	er4,er0
-	mov.l	@er0,er4
-	beq	_ret_from_exception:16
-	mov.l	@(LER1:16,sp),er0
-	mov.l	@(LER2:16,sp),er1
-	mov.l	@(LER3:16,sp),er2
-	jsr	@er4
-	mov.l	er0,@(LER0:16,sp)		/* save the return value */
-	mov.l	sp,er2
-	and.w	#0xe000,r2
-	mov.b	@((TI_FLAGS+3-(TIF_SYSCALL_TRACE >> 3)):16,er2),r2l
-	btst	#(TIF_SYSCALL_TRACE & 7),r2l
-	beq	2f
-	jsr	@_do_syscall_trace
-2:
-#if defined(CONFIG_SYSCALL_PRINT)
-	jsr	@_syscall_print
-#endif
-	orc	#0x80,ccr
-	bra	resume_userspace
-
-badsys:
-	mov.l	#-ENOSYS,er0
-	mov.l	er0,@(LER0:16,sp)
-	bra	resume_userspace
-
-#if !defined(CONFIG_PREEMPT)
-#define resume_kernel restore_all
-#endif
-
-_ret_from_exception:
-#if defined(CONFIG_PREEMPT)
-	orc	#0x80,ccr
-#endif
-_ret_from_interrupt:
-	mov.b	@(LCCR+1:16,sp),r0l
-	btst	#4,r0l
-	bne	resume_kernel:8		/* return from kernel */
-resume_userspace:
-	andc	#0x7f,ccr
-	mov.l	sp,er4
-	and.w	#0xe000,r4		/* er4 <- current thread info */
-	mov.l	@(TI_FLAGS:16,er4),er1
-	and.l	#_TIF_WORK_MASK,er1
-	beq	restore_all:8
-work_pending:
-	btst	#TIF_NEED_RESCHED,r1l
-	bne	work_resched:8
-	/* work notifysig */
-	mov.l	sp,er0
-	subs	#4,er0			/* er0: pt_regs */
-	jsr	@_do_notify_resume
-	bra	restore_all:8
-work_resched:
-	mov.l	sp,er0
-	jsr	@_set_esp0
-	jsr	@_schedule
-	bra	resume_userspace:8
-restore_all:
-	RESTORE_ALL			/* Does RTE */
-
-#if defined(CONFIG_PREEMPT)
-resume_kernel:
-	mov.l	@(TI_PRE_COUNT:16,er4),er0
-	bne	restore_all:8
-need_resched:
-	mov.l	@(TI_FLAGS:16,er4),er0
-	btst	#TIF_NEED_RESCHED,r0l
-	beq	restore_all:8
-	mov.b	@(LCCR+1:16,sp),r0l	/* Interrupt Enabled? */
-	bmi	restore_all:8
-	mov.l	#PREEMPT_ACTIVE,er0
-	mov.l	er0,@(TI_PRE_COUNT:16,er4)
-	andc	#0x7f,ccr
-	mov.l	sp,er0
-	jsr	@_set_esp0
-	jsr	@_schedule
-	orc	#0x80,ccr
-	bra	need_resched:8
-#endif
-
-_ret_from_fork:
-	mov.l	er2,er0
-	jsr	@_schedule_tail
-	jmp	@_ret_from_exception
-
-_ret_from_kernel_thread:
-	mov.l	er2,er0
-	jsr	@_schedule_tail
-	mov.l	@(LER4:16,sp),er0
-	mov.l	@(LER5:16,sp),er1
-	jsr	@er1
-	jmp	@_ret_from_exception
-
-_resume:
-	/*
-	 * Beware - when entering resume, offset of tss is in d1,
-	 * prev (the current task) is in a0, next (the new task)
-	 * is in a1 and d2.b is non-zero if the mm structure is
-	 * shared between the tasks, so don't change these
-	 * registers until their contents are no longer needed.
-	 */
-
-	/* save sr */
-	sub.w	r3,r3
-	stc	ccr,r3l
-	mov.w	r3,@(THREAD_CCR+2:16,er0)
-
-	/* disable interrupts */
-	orc	#0x80,ccr
-	mov.l	@_sw_usp,er3
-	mov.l	er3,@(THREAD_USP:16,er0)
-	mov.l	sp,@(THREAD_KSP:16,er0)
-
-	/* Skip address space switching if they are the same. */
-	/* FIXME: what did we hack out of here, this does nothing! */
-
-	mov.l	@(THREAD_USP:16,er1),er0
-	mov.l	er0,@_sw_usp
-	mov.l	@(THREAD_KSP:16,er1),sp
-
-	/* restore status register */
-	mov.w	@(THREAD_CCR+2:16,er1),r3
-
-	ldc	r3l,ccr
-	rts
-
-_trace_break:
-	subs	#4,sp
-	SAVE_ALL
-	sub.l	er1,er1
-	dec.l	#1,er1
-	mov.l	er1,@(LORIG,sp)
-	mov.l	sp,er0
-	jsr	@_set_esp0
-	mov.l	@_sw_usp,er0
-	mov.l	@er0,er1
-	mov.w	@(-2:16,er1),r2
-	cmp.w	#0x5730,r2
-	beq	1f
-	subs	#2,er1
-	mov.l	er1,@er0
-1:
-	and.w	#0xff,e1
-	mov.l	er1,er0
-	jsr	@_trace_trap
-	jmp	@_ret_from_exception
-
-	.section	.bss
-_sw_ksp:
-	.space	4
-_sw_usp:
-	.space	4
-
-	.end
diff --git a/arch/h8300/kernel/gpio.c b/arch/h8300/kernel/gpio.c
deleted file mode 100644
index 084bfd0c107e..000000000000
--- a/arch/h8300/kernel/gpio.c
+++ /dev/null
@@ -1,178 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/gpio.c
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- */
-
-/*
- * Internal I/O Port Management
- */
-
-#include <linux/stddef.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-
-#define _(addr) (volatile unsigned char *)(addr)
-#if defined(CONFIG_H83007) || defined(CONFIG_H83068)
-#include <asm/regs306x.h>
-static volatile unsigned char *ddrs[] = {
-	_(P1DDR),_(P2DDR),_(P3DDR),_(P4DDR),_(P5DDR),_(P6DDR),
-	NULL,    _(P8DDR),_(P9DDR),_(PADDR),_(PBDDR),
-};
-#define MAX_PORT 11
-#endif
-
- #if defined(CONFIG_H83002) || defined(CONFIG_H8048)
-/* Fix me!! */
-#include <asm/regs306x.h>
-static volatile unsigned char *ddrs[] = {
-	_(P1DDR),_(P2DDR),_(P3DDR),_(P4DDR),_(P5DDR),_(P6DDR),
-	NULL,    _(P8DDR),_(P9DDR),_(PADDR),_(PBDDR),
-};
-#define MAX_PORT 11
-#endif
-
-#if defined(CONFIG_H8S2678)
-#include <asm/regs267x.h>
-static volatile unsigned char *ddrs[] = {
-	_(P1DDR),_(P2DDR),_(P3DDR),NULL    ,_(P5DDR),_(P6DDR),
-	_(P7DDR),_(P8DDR),NULL,    _(PADDR),_(PBDDR),_(PCDDR),
-	_(PDDDR),_(PEDDR),_(PFDDR),_(PGDDR),_(PHDDR),
-	_(PADDR),_(PBDDR),_(PCDDR),_(PDDDR),_(PEDDR),_(PFDDR),
-	_(PGDDR),_(PHDDR)
-};
-#define MAX_PORT 17
-#endif
-#undef _
- 
-#if !defined(P1DDR)
-#error Unsuppoted CPU Selection
-#endif
-
-static struct {
-	unsigned char used;
-	unsigned char ddr;
-} gpio_regs[MAX_PORT];
-
-extern char *_platform_gpio_table(int length);
-
-int h8300_reserved_gpio(int port, unsigned int bits)
-{
-	unsigned char *used;
-
-	if (port < 0 || port >= MAX_PORT)
-		return -1;
-	used = &(gpio_regs[port].used);
-	if ((*used & bits) != 0)
-		return 0;
-	*used |= bits;
-	return 1;
-}
-
-int h8300_free_gpio(int port, unsigned int bits)
-{
-	unsigned char *used;
-
-	if (port < 0 || port >= MAX_PORT)
-		return -1;
-	used = &(gpio_regs[port].used);
-	if ((*used & bits) != bits)
-		return 0;
-	*used &= (~bits);
-	return 1;
-}
-
-int h8300_set_gpio_dir(int port_bit,int dir)
-{
-	int port = (port_bit >> 8) & 0xff;
-	int bit  = port_bit & 0xff;
-
-	if (ddrs[port] == NULL)
-		return 0;
-	if (gpio_regs[port].used & bit) {
-		if (dir)
-			gpio_regs[port].ddr |= bit;
-		else
-			gpio_regs[port].ddr &= ~bit;
-		*ddrs[port] = gpio_regs[port].ddr;
-		return 1;
-	} else
-		return 0;
-}
-
-int h8300_get_gpio_dir(int port_bit)
-{
-	int port = (port_bit >> 8) & 0xff;
-	int bit  = port_bit & 0xff;
-
-	if (ddrs[port] == NULL)
-		return 0;
-	if (gpio_regs[port].used & bit) {
-		return (gpio_regs[port].ddr & bit) != 0;
-	} else
-		return -1;
-}
-
-#if defined(CONFIG_PROC_FS)
-static char *port_status(int portno)
-{
-	static char result[10];
-	static const char io[2]={'I','O'};
-	char *rp;
-	int c;
-	unsigned char used,ddr;
-	
-	used = gpio_regs[portno].used;
-	ddr  = gpio_regs[portno].ddr;
-	result[8]='\0';
-	rp = result + 7;
-	for (c = 8; c > 0; c--,rp--,used >>= 1, ddr >>= 1)
-		if (used & 0x01)
-			*rp = io[ ddr & 0x01];
-		else	
-			*rp = '-';
-	return result;
-}
-
-static int gpio_proc_show(struct seq_file *m, void *v)
-{
-	static const char port_name[]="123456789ABCDEFGH";
-	int c;
-
-	for (c = 0; c < MAX_PORT; c++) {
-		if (ddrs[c] == NULL)
-			continue;
-		seq_printf(m, "P%c: %s\n", port_name[c], port_status(c));
-	}
-	return 0;
-}
-
-static int gpio_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, gpio_proc_show, PDE_DATA(inode));
-}
-
-static const struct file_operations gpio_proc_fops = {
-	.open		= gpio_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static __init int register_proc(void)
-{
-	return proc_create("gpio", S_IRUGO, NULL, &gpio_proc_fops) != NULL;
-}
-
-__initcall(register_proc);
-#endif
-
-void __init h8300_gpio_init(void)
-{
-	memcpy(gpio_regs,_platform_gpio_table(sizeof(gpio_regs)),sizeof(gpio_regs));
-}
diff --git a/arch/h8300/kernel/h8300_ksyms.c b/arch/h8300/kernel/h8300_ksyms.c
deleted file mode 100644
index 53d7c0e4bd83..000000000000
--- a/arch/h8300/kernel/h8300_ksyms.c
+++ /dev/null
@@ -1,100 +0,0 @@
-#include <linux/module.h>
-#include <linux/linkage.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/in6.h>
-#include <linux/interrupt.h>
-
-#include <asm/setup.h>
-#include <asm/pgalloc.h>
-#include <asm/irq.h>
-#include <asm/io.h>
-#include <asm/checksum.h>
-#include <asm/current.h>
-#include <asm/gpio.h>
-
-//asmlinkage long long __ashrdi3 (long long, int);
-//asmlinkage long long __lshrdi3 (long long, int);
-extern char h8300_debug_device[];
-
-/* platform dependent support */
-
-EXPORT_SYMBOL(strnlen);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(strstr);
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
-
-EXPORT_SYMBOL(ip_fast_csum);
-
-EXPORT_SYMBOL(enable_irq);
-EXPORT_SYMBOL(disable_irq);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-
-/* The following are special because they're not called
-   explicitly (the C compiler generates them).  Fortunately,
-   their interface isn't gonna change any time soon now, so
-   it's OK to leave it out of version control.  */
-//EXPORT_SYMBOL(__ashrdi3);
-//EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memscan);
-EXPORT_SYMBOL(memmove);
-
-/*
- * libgcc functions - functions that are used internally by the
- * compiler...  (prototypes are not correct though, but that
- * doesn't really matter since they're not versioned).
- */
-extern void __gcc_bcmp(void);
-extern void __ashldi3(void);
-extern void __ashrdi3(void);
-extern void __cmpdi2(void);
-extern void __divdi3(void);
-extern void __divsi3(void);
-extern void __lshrdi3(void);
-extern void __moddi3(void);
-extern void __modsi3(void);
-extern void __muldi3(void);
-extern void __mulsi3(void);
-extern void __negdi2(void);
-extern void __ucmpdi2(void);
-extern void __udivdi3(void);
-extern void __udivmoddi4(void);
-extern void __udivsi3(void);
-extern void __umoddi3(void);
-extern void __umodsi3(void);
-
-        /* gcc lib functions */
-EXPORT_SYMBOL(__gcc_bcmp);
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__cmpdi2);
-EXPORT_SYMBOL(__divdi3);
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__moddi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__muldi3);
-EXPORT_SYMBOL(__mulsi3);
-EXPORT_SYMBOL(__negdi2);
-EXPORT_SYMBOL(__ucmpdi2);
-EXPORT_SYMBOL(__udivdi3);
-EXPORT_SYMBOL(__udivmoddi4);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__umoddi3);
-EXPORT_SYMBOL(__umodsi3);
-
-EXPORT_SYMBOL(h8300_reserved_gpio);
-EXPORT_SYMBOL(h8300_free_gpio);
-EXPORT_SYMBOL(h8300_set_gpio_dir);
diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c
deleted file mode 100644
index 2fa8ac7b79b5..000000000000
--- a/arch/h8300/kernel/irq.c
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * linux/arch/h8300/kernel/irq.c
- *
- * Copyright 2007 Yoshinori Sato <ysato@users.sourceforge.jp>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/seq_file.h>
-#include <linux/init.h>
-#include <linux/random.h>
-#include <linux/bootmem.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-
-#include <asm/traps.h>
-#include <asm/io.h>
-#include <asm/setup.h>
-#include <asm/errno.h>
-
-/*#define DEBUG*/
-
-extern unsigned long *interrupt_redirect_table;
-extern const int h8300_saved_vectors[];
-extern const h8300_vector h8300_trap_table[];
-int h8300_enable_irq_pin(unsigned int irq);
-void h8300_disable_irq_pin(unsigned int irq);
-
-#define CPU_VECTOR ((unsigned long *)0x000000)
-#define ADDR_MASK (0xffffff)
-
-static inline int is_ext_irq(unsigned int irq)
-{
-	return (irq >= EXT_IRQ0 && irq <= (EXT_IRQ0 + EXT_IRQS));
-}
-
-static void h8300_enable_irq(struct irq_data *data)
-{
-	if (is_ext_irq(data->irq))
-		IER_REGS |= 1 << (data->irq - EXT_IRQ0);
-}
-
-static void h8300_disable_irq(struct irq_data *data)
-{
-	if (is_ext_irq(data->irq))
-		IER_REGS &= ~(1 << (data->irq - EXT_IRQ0));
-}
-
-static unsigned int h8300_startup_irq(struct irq_data *data)
-{
-	if (is_ext_irq(data->irq))
-		return h8300_enable_irq_pin(data->irq);
-	else
-		return 0;
-}
-
-static void h8300_shutdown_irq(struct irq_data *data)
-{
-	if (is_ext_irq(data->irq))
-		h8300_disable_irq_pin(data->irq);
-}
-
-/*
- * h8300 interrupt controller implementation
- */
-struct irq_chip h8300irq_chip = {
-	.name		= "H8300-INTC",
-	.irq_startup	= h8300_startup_irq,
-	.irq_shutdown	= h8300_shutdown_irq,
-	.irq_enable	= h8300_enable_irq,
-	.irq_disable	= h8300_disable_irq,
-};
-
-#if defined(CONFIG_RAMKERNEL)
-static unsigned long __init *get_vector_address(void)
-{
-	unsigned long *rom_vector = CPU_VECTOR;
-	unsigned long base,tmp;
-	int vec_no;
-
-	base = rom_vector[EXT_IRQ0] & ADDR_MASK;
-
-	/* check romvector format */
-	for (vec_no = EXT_IRQ1; vec_no <= EXT_IRQ0+EXT_IRQS; vec_no++) {
-		if ((base+(vec_no - EXT_IRQ0)*4) != (rom_vector[vec_no] & ADDR_MASK))
-			return NULL;
-	}
-
-	/* ramvector base address */
-	base -= EXT_IRQ0*4;
-
-	/* writerble check */
-	tmp = ~(*(volatile unsigned long *)base);
-	(*(volatile unsigned long *)base) = tmp;
-	if ((*(volatile unsigned long *)base) != tmp)
-		return NULL;
-	return (unsigned long *)base;
-}
-
-static void __init setup_vector(void)
-{
-	int i;
-	unsigned long *ramvec,*ramvec_p;
-	const h8300_vector *trap_entry;
-	const int *saved_vector;
-
-	ramvec = get_vector_address();
-	if (ramvec == NULL)
-		panic("interrupt vector serup failed.");
-	else
-		printk(KERN_INFO "virtual vector at 0x%08lx\n",(unsigned long)ramvec);
-
-	/* create redirect table */
-	ramvec_p = ramvec;
-	trap_entry = h8300_trap_table;
-	saved_vector = h8300_saved_vectors;
-	for ( i = 0; i < NR_IRQS; i++) {
-		if (i == *saved_vector) {
-			ramvec_p++;
-			saved_vector++;
-		} else {
-			if ( i < NR_TRAPS ) {
-				if (*trap_entry)
-					*ramvec_p = VECTOR(*trap_entry);
-				ramvec_p++;
-				trap_entry++;
-			} else
-				*ramvec_p++ = REDIRECT(interrupt_entry);
-		}
-	}
-	interrupt_redirect_table = ramvec;
-#ifdef DEBUG
-	ramvec_p = ramvec;
-	for (i = 0; i < NR_IRQS; i++) {
-		if ((i % 8) == 0)
-			printk(KERN_DEBUG "\n%p: ",ramvec_p);
-		printk(KERN_DEBUG "%p ",*ramvec_p);
-		ramvec_p++;
-	}
-	printk(KERN_DEBUG "\n");
-#endif
-}
-#else
-#define setup_vector() do { } while(0)
-#endif
-
-void __init init_IRQ(void)
-{
-	int c;
-
-	setup_vector();
-
-	for (c = 0; c < NR_IRQS; c++)
-		irq_set_chip_and_handler(c, &h8300irq_chip, handle_simple_irq);
-}
-
-asmlinkage void do_IRQ(int irq)
-{
-	irq_enter();
-	generic_handle_irq(irq);
-	irq_exit();
-}
diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c
deleted file mode 100644
index 1d526e05db19..000000000000
--- a/arch/h8300/kernel/module.c
+++ /dev/null
@@ -1,75 +0,0 @@
-#include <linux/moduleloader.h>
-#include <linux/elf.h>
-#include <linux/vmalloc.h>
-#include <linux/fs.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt...)
-#endif
-
-int apply_relocate_add(Elf32_Shdr *sechdrs,
-		       const char *strtab,
-		       unsigned int symindex,
-		       unsigned int relsec,
-		       struct module *me)
-{
-	unsigned int i;
-	Elf32_Rela *rela = (void *)sechdrs[relsec].sh_addr;
-
-	DEBUGP("Applying relocate section %u to %u\n", relsec,
-	       sechdrs[relsec].sh_info);
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
-		/* This is where to make the change */
-		uint32_t *loc = (uint32_t *)(sechdrs[sechdrs[relsec].sh_info].sh_addr
-					     + rela[i].r_offset);
-		/* This is the symbol it is referring to.  Note that all
-		   undefined symbols have been resolved.  */
-		Elf32_Sym *sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
-			+ ELF32_R_SYM(rela[i].r_info);
-		uint32_t v = sym->st_value + rela[i].r_addend;
-
-		switch (ELF32_R_TYPE(rela[i].r_info)) {
-		case R_H8_DIR24R8:
-			loc = (uint32_t *)((uint32_t)loc - 1);
-			*loc = (*loc & 0xff000000) | ((*loc & 0xffffff) + v);
-			break;
-		case R_H8_DIR24A8:
-			if (ELF32_R_SYM(rela[i].r_info))
-				*loc += v;
-			break;
-		case R_H8_DIR32:
-		case R_H8_DIR32A16:
-			*loc += v;
-			break;
-		case R_H8_PCREL16:
-			v -= (unsigned long)loc + 2;
-			if ((Elf32_Sword)v > 0x7fff || 
-			    (Elf32_Sword)v < -(Elf32_Sword)0x8000)
-				goto overflow;
-			else 
-				*(unsigned short *)loc = v;
-			break;
-		case R_H8_PCREL8:
-			v -= (unsigned long)loc + 1;
-			if ((Elf32_Sword)v > 0x7f || 
-			    (Elf32_Sword)v < -(Elf32_Sword)0x80)
-				goto overflow;
-			else 
-				*(unsigned char *)loc = v;
-			break;
-		default:
-			printk(KERN_ERR "module %s: Unknown relocation: %u\n",
-			       me->name, ELF32_R_TYPE(rela[i].r_info));
-			return -ENOEXEC;
-		}
-	}
-	return 0;
- overflow:
-	printk(KERN_ERR "module %s: relocation offset overflow: %08x\n",
-	       me->name, rela[i].r_offset);
-	return -ENOEXEC;
-}
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
deleted file mode 100644
index 1a744ab7e7e5..000000000000
--- a/arch/h8300/kernel/process.c
+++ /dev/null
@@ -1,154 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/process.c
- *
- * Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Based on:
- *
- *  linux/arch/m68knommu/kernel/process.c
- *
- *  Copyright (C) 1998  D. Jeff Dionne <jeff@ryeham.ee.ryerson.ca>,
- *                      Kenneth Albanowski <kjahds@kjahds.com>,
- *                      The Silver Hammer Group, Ltd.
- *
- *  linux/arch/m68k/kernel/process.c
- *
- *  Copyright (C) 1995  Hamish Macdonald
- *
- *  68060 fixes by Jesper Skov
- */
-
-/*
- * This file handles the architecture-dependent parts of process handling..
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/interrupt.h>
-#include <linux/reboot.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/rcupdate.h>
-
-#include <asm/uaccess.h>
-#include <asm/traps.h>
-#include <asm/setup.h>
-#include <asm/pgtable.h>
-
-void (*pm_power_off)(void) = NULL;
-EXPORT_SYMBOL(pm_power_off);
-
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
-
-/*
- * The idle loop on an H8/300..
- */
-#if !defined(CONFIG_H8300H_SIM) && !defined(CONFIG_H8S_SIM)
-void arch_cpu_idle(void)
-{
-	local_irq_enable();
-	/* XXX: race here! What if need_resched() gets set now? */
-	__asm__("sleep");
-}
-#endif
-
-void machine_restart(char * __unused)
-{
-	local_irq_disable();
-	__asm__("jmp @@0"); 
-}
-
-void machine_halt(void)
-{
-	local_irq_disable();
-	__asm__("sleep");
-	for (;;);
-}
-
-void machine_power_off(void)
-{
-	local_irq_disable();
-	__asm__("sleep");
-	for (;;);
-}
-
-void show_regs(struct pt_regs * regs)
-{
-	show_regs_print_info(KERN_DEFAULT);
-
-	printk("\nPC: %08lx  Status: %02x",
-	       regs->pc, regs->ccr);
-	printk("\nORIG_ER0: %08lx ER0: %08lx ER1: %08lx",
-	       regs->orig_er0, regs->er0, regs->er1);
-	printk("\nER2: %08lx ER3: %08lx ER4: %08lx ER5: %08lx",
-	       regs->er2, regs->er3, regs->er4, regs->er5);
-	printk("\nER6' %08lx ",regs->er6);
-	if (user_mode(regs))
-		printk("USP: %08lx\n", rdusp());
-	else
-		printk("\n");
-}
-
-void flush_thread(void)
-{
-}
-
-int copy_thread(unsigned long clone_flags,
-                unsigned long usp, unsigned long topstk,
-		 struct task_struct * p)
-{
-	struct pt_regs * childregs;
-
-	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
-
-	if (unlikely(p->flags & PF_KTHREAD)) {
-		memset(childregs, 0, sizeof(struct pt_regs));
-		childregs->retpc = (unsigned long) ret_from_kernel_thread;
-		childregs->er4 = topstk; /* arg */
-		childregs->er5 = usp; /* fn */
-		p->thread.ksp = (unsigned long)childregs;
-	}
-	*childregs = *current_pt_regs();
-	childregs->retpc = (unsigned long) ret_from_fork;
-	childregs->er0 = 0;
-	p->thread.usp = usp ?: rdusp();
-	p->thread.ksp = (unsigned long)childregs;
-
-	return 0;
-}
-
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return ((struct pt_regs *)tsk->thread.esp0)->pc;
-}
-
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long fp, pc;
-	unsigned long stack_page;
-	int count = 0;
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-
-	stack_page = (unsigned long)p;
-	fp = ((struct pt_regs *)p->thread.ksp)->er6;
-	do {
-		if (fp < stack_page+sizeof(struct thread_info) ||
-		    fp >= 8184+stack_page)
-			return 0;
-		pc = ((unsigned long *)fp)[1];
-		if (!in_sched_functions(pc))
-			return pc;
-		fp = *(unsigned long *) fp;
-	} while (count++ < 16);
-	return 0;
-}
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
deleted file mode 100644
index 748cf6585aa4..000000000000
--- a/arch/h8300/kernel/ptrace.c
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/ptrace.c
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Based on:
- *  linux/arch/m68k/kernel/ptrace.c
- *
- *  Copyright (C) 1994 by Hamish Macdonald
- *  Taken from linux/kernel/ptrace.c and modified for M680x0.
- *  linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of
- * this archive for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/signal.h>
-
-#include <asm/uaccess.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/signal.h>
-
-/* cpu depend functions */
-extern long h8300_get_reg(struct task_struct *task, int regno);
-extern int  h8300_put_reg(struct task_struct *task, int regno, unsigned long data);
-
-
-void user_disable_single_step(struct task_struct *child)
-{
-}
-
-/*
- * does not yet catch signals sent when the child dies.
- * in exit.c or in signal.c.
- */
-
-void ptrace_disable(struct task_struct *child)
-{
-	user_disable_single_step(child);
-}
-
-long arch_ptrace(struct task_struct *child, long request,
-		 unsigned long addr, unsigned long data)
-{
-	int ret;
-	int regno = addr >> 2;
-	unsigned long __user *datap = (unsigned long __user *) data;
-
-	switch (request) {
-	/* read the word at location addr in the USER area. */
-		case PTRACE_PEEKUSR: {
-			unsigned long tmp = 0;
-			
-			if ((addr & 3) || addr >= sizeof(struct user)) {
-				ret = -EIO;
-				break ;
-			}
-			
-		        ret = 0;  /* Default return condition */
-
-			if (regno < H8300_REGS_NO)
-				tmp = h8300_get_reg(child, regno);
-			else {
-				switch (regno) {
-				case 49:
-					tmp = child->mm->start_code;
-					break ;
-				case 50:
-					tmp = child->mm->start_data;
-					break ;
-				case 51:
-					tmp = child->mm->end_code;
-					break ;
-				case 52:
-					tmp = child->mm->end_data;
-					break ;
-				default:
-					ret = -EIO;
-				}
-			}
-			if (!ret)
-				ret = put_user(tmp, datap);
-			break ;
-		}
-
-      /* when I and D space are separate, this will have to be fixed. */
-		case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
-			if ((addr & 3) || addr >= sizeof(struct user)) {
-				ret = -EIO;
-				break ;
-			}
-			    
-			if (regno == PT_ORIG_ER0) {
-				ret = -EIO;
-				break ;
-			}
-			if (regno < H8300_REGS_NO) {
-				ret = h8300_put_reg(child, regno, data);
-				break ;
-			}
-			ret = -EIO;
-			break ;
-
-		case PTRACE_GETREGS: { /* Get all gp regs from the child. */
-		  	int i;
-			unsigned long tmp;
-			for (i = 0; i < H8300_REGS_NO; i++) {
-			    tmp = h8300_get_reg(child, i);
-			    if (put_user(tmp, datap)) {
-				ret = -EFAULT;
-				break;
-			    }
-			    datap++;
-			}
-			ret = 0;
-			break;
-		}
-
-		case PTRACE_SETREGS: { /* Set all gp regs in the child. */
-			int i;
-			unsigned long tmp;
-			for (i = 0; i < H8300_REGS_NO; i++) {
-			    if (get_user(tmp, datap)) {
-				ret = -EFAULT;
-				break;
-			    }
-			    h8300_put_reg(child, i, tmp);
-			    datap++;
-			}
-			ret = 0;
-			break;
-		}
-
-		default:
-			ret = ptrace_request(child, request, addr, data);
-			break;
-	}
-	return ret;
-}
-
-asmlinkage void do_syscall_trace(void)
-{
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return;
-	if (!(current->ptrace & PT_PTRACED))
-		return;
-	ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
-				 ? 0x80 : 0));
-	/*
-	 * this isn't the same as continuing with a signal, but it will do
-	 * for normal use.  strace only continues with a signal if the
-	 * stopping signal is not SIGTRAP.  -brl
-	 */
-	if (current->exit_code) {
-		send_sig(current->exit_code, current, 1);
-		current->exit_code = 0;
-	}
-}
diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c
deleted file mode 100644
index d0b1607f2711..000000000000
--- a/arch/h8300/kernel/setup.c
+++ /dev/null
@@ -1,242 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/setup.c
- *
- *  Copyleft  ()) 2000       James D. Schettine {james@telos-systems.com}
- *  Copyright (C) 1999,2000  Greg Ungerer (gerg@snapgear.com)
- *  Copyright (C) 1998,1999  D. Jeff Dionne <jeff@lineo.ca>
- *  Copyright (C) 1998       Kenneth Albanowski <kjahds@kjahds.com>
- *  Copyright (C) 1995       Hamish Macdonald
- *  Copyright (C) 2000       Lineo Inc. (www.lineo.com) 
- *  Copyright (C) 2001 	     Lineo, Inc. <www.lineo.com>
- *
- *  H8/300 porting Yoshinori Sato <ysato@users.sourceforge.jp>
- */
-
-/*
- * This file handles the architecture-dependent parts of system setup
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/fb.h>
-#include <linux/console.h>
-#include <linux/genhd.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/major.h>
-#include <linux/bootmem.h>
-#include <linux/seq_file.h>
-#include <linux/init.h>
-
-#include <asm/setup.h>
-#include <asm/irq.h>
-#include <asm/pgtable.h>
-#include <asm/sections.h>
-
-#if defined(__H8300H__)
-#define CPU "H8/300H"
-#include <asm/regs306x.h>
-#endif
-
-#if defined(__H8300S__)
-#define CPU "H8S"
-#include <asm/regs267x.h>
-#endif
-
-#define STUBSIZE 0xc000
-
-unsigned long rom_length;
-unsigned long memory_start;
-unsigned long memory_end;
-
-char __initdata command_line[COMMAND_LINE_SIZE];
-
-extern int _ramstart, _ramend;
-extern char _target_name[];
-extern void h8300_gpio_init(void);
-
-#if (defined(CONFIG_H8300H_SIM) || defined(CONFIG_H8S_SIM)) \
-    && defined(CONFIG_GDB_MAGICPRINT)
-/* printk with gdb service */
-static void gdb_console_output(struct console *c, const char *msg, unsigned len)
-{
-	for (; len > 0; len--) {
-		asm("mov.w %0,r2\n\t"
-                    "jsr @0xc4"::"r"(*msg++):"er2");
-	}
-}
-
-/*
- *	Setup initial baud/bits/parity. We do two things here:
- *	- construct a cflag setting for the first rs_open()
- *	- initialize the serial port
- *	Return non-zero if we didn't find a serial port.
- */
-static int __init gdb_console_setup(struct console *co, char *options)
-{
-	return 0;
-}
-
-static const struct console gdb_console = {
-	.name		= "gdb_con",
-	.write		= gdb_console_output,
-	.device		= NULL,
-	.setup		= gdb_console_setup,
-	.flags		= CON_PRINTBUFFER,
-	.index		= -1,
-};
-#endif
-
-void __init setup_arch(char **cmdline_p)
-{
-	int bootmap_size;
-
-	memory_start = (unsigned long) &_ramstart;
-
-	/* allow for ROMFS on the end of the kernel */
-	if (memcmp((void *)memory_start, "-rom1fs-", 8) == 0) {
-#if defined(CONFIG_BLK_DEV_INITRD)
-		initrd_start = memory_start;
-		initrd_end = memory_start += be32_to_cpu(((unsigned long *) (memory_start))[2]);
-#else
-		memory_start += be32_to_cpu(((unsigned long *) memory_start)[2]);
-#endif
-	}
-	memory_start = PAGE_ALIGN(memory_start);
-#if !defined(CONFIG_BLKDEV_RESERVE)
-	memory_end = (unsigned long) &_ramend; /* by now the stack is part of the init task */
-#if defined(CONFIG_GDB_DEBUG)
-	memory_end -= STUBSIZE;
-#endif
-#else
-	if ((memory_end < CONFIG_BLKDEV_RESERVE_ADDRESS) && 
-	    (memory_end > CONFIG_BLKDEV_RESERVE_ADDRESS))
-	    /* overlap userarea */
-	    memory_end = CONFIG_BLKDEV_RESERVE_ADDRESS; 
-#endif
-
-	init_mm.start_code = (unsigned long) _stext;
-	init_mm.end_code = (unsigned long) _etext;
-	init_mm.end_data = (unsigned long) _edata;
-	init_mm.brk = (unsigned long) 0; 
-
-#if (defined(CONFIG_H8300H_SIM) || defined(CONFIG_H8S_SIM)) && defined(CONFIG_GDB_MAGICPRINT)
-	register_console((struct console *)&gdb_console);
-#endif
-
-	printk(KERN_INFO "\r\n\nuClinux " CPU "\n");
-	printk(KERN_INFO "Target Hardware: %s\n",_target_name);
-	printk(KERN_INFO "Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n");
-	printk(KERN_INFO "H8/300 series support by Yoshinori Sato <ysato@users.sourceforge.jp>\n");
-
-#ifdef DEBUG
-	printk(KERN_DEBUG "KERNEL -> TEXT=0x%p-0x%p DATA=0x%p-0x%p "
-		"BSS=0x%p-0x%p\n", _stext, _etext, _sdata, _edata, __bss_start,
-		__bss_stop);
-	printk(KERN_DEBUG "KERNEL -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx "
-		"STACK=0x%06lx-0x%p\n", __bss_stop, memory_start, memory_start,
-		memory_end, memory_end, &_ramend);
-#endif
-
-#ifdef CONFIG_DEFAULT_CMDLINE
-	/* set from default command line */
-	if (*command_line == '\0')
-		strcpy(command_line,CONFIG_KERNEL_COMMAND);
-#endif
-	/* Keep a copy of command line */
-	*cmdline_p = &command_line[0];
-	memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
-	boot_command_line[COMMAND_LINE_SIZE-1] = 0;
-
-#ifdef DEBUG
-	if (strlen(*cmdline_p)) 
-		printk(KERN_DEBUG "Command line: '%s'\n", *cmdline_p);
-#endif
-
-	/*
-	 * give all the memory to the bootmap allocator,  tell it to put the
-	 * boot mem_map at the start of memory
-	 */
-	bootmap_size = init_bootmem_node(
-			NODE_DATA(0),
-			memory_start >> PAGE_SHIFT, /* map goes here */
-			PAGE_OFFSET >> PAGE_SHIFT,	/* 0 on coldfire */
-			memory_end >> PAGE_SHIFT);
-	/*
-	 * free the usable memory,  we have to make sure we do not free
-	 * the bootmem bitmap so we then reserve it after freeing it :-)
-	 */
-	free_bootmem(memory_start, memory_end - memory_start);
-	reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-	/*
-	 * get kmalloc into gear
-	 */
-	paging_init();
-	h8300_gpio_init();
-#if defined(CONFIG_H8300_AKI3068NET) && defined(CONFIG_IDE)
-	{
-#define AREABIT(addr) (1 << (((addr) >> 21) & 7))
-		/* setup BSC */
-		volatile unsigned char *abwcr = (volatile unsigned char *)ABWCR;
-		volatile unsigned char *cscr = (volatile unsigned char *)CSCR;
-		*abwcr &= ~(AREABIT(CONFIG_H8300_IDE_BASE) | AREABIT(CONFIG_H8300_IDE_ALT));
-		*cscr  |= (AREABIT(CONFIG_H8300_IDE_BASE) | AREABIT(CONFIG_H8300_IDE_ALT)) | 0x0f;
-	}
-#endif
-#ifdef DEBUG
-	printk(KERN_DEBUG "Done setup_arch\n");
-#endif
-}
-
-/*
- *	Get CPU information for use by the procfs.
- */
-
-static int show_cpuinfo(struct seq_file *m, void *v)
-{
-    char *cpu;
-    int mode;
-    u_long clockfreq;
-
-    cpu = CPU;
-    mode = *(volatile unsigned char *)MDCR & 0x07;
-
-    clockfreq = CONFIG_CPU_CLOCK;
-
-    seq_printf(m,  "CPU:\t\t%s (mode:%d)\n"
-		   "Clock:\t\t%lu.%1luMHz\n"
-		   "BogoMips:\t%lu.%02lu\n"
-		   "Calibration:\t%lu loops\n",
-	           cpu,mode,
-		   clockfreq/1000,clockfreq%1000,
-		   (loops_per_jiffy*HZ)/500000,((loops_per_jiffy*HZ)/5000)%100,
-		   (loops_per_jiffy*HZ));
-
-    return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
-	return *pos < NR_CPUS ? ((void *) 0x12345678) : NULL;
-}
-
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	++*pos;
-	return c_start(m, pos);
-}
-
-static void c_stop(struct seq_file *m, void *v)
-{
-}
-
-const struct seq_operations cpuinfo_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
-	.show	= show_cpuinfo,
-};
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
deleted file mode 100644
index a65ff3b76326..000000000000
--- a/arch/h8300/kernel/signal.c
+++ /dev/null
@@ -1,444 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/signal.c
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-/*
- * uClinux H8/300 support by Yoshinori Sato <ysato@users.sourceforge.jp>
- *                and David McCullough <davidm@snapgear.com>
- *
- * Based on
- * Linux/m68k by Hamish Macdonald
- */
-
-/*
- * ++roman (07/09/96): implemented signal stacks (specially for tosemu on
- * Atari :-) Current limitation: Only one sigstack can be active at one time.
- * If a second signal with SA_ONSTACK set arrives while working on a sigstack,
- * SA_ONSTACK is ignored. This behaviour avoids lots of trouble with nested
- * signal handlers!
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/syscalls.h>
-#include <linux/errno.h>
-#include <linux/wait.h>
-#include <linux/ptrace.h>
-#include <linux/unistd.h>
-#include <linux/stddef.h>
-#include <linux/highuid.h>
-#include <linux/personality.h>
-#include <linux/tty.h>
-#include <linux/binfmts.h>
-#include <linux/tracehook.h>
-
-#include <asm/setup.h>
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/traps.h>
-#include <asm/ucontext.h>
-
-/*
- * Do a signal return; undo the signal stack.
- *
- * Keep the return code on the stack quadword aligned!
- * That makes the cache flush below easier.
- */
-
-struct sigframe
-{
-	long dummy_er0;
-	long dummy_vector;
-#if defined(CONFIG_CPU_H8S)
-	short dummy_exr;
-#endif
-	long dummy_pc;
-	char *pretcode;
-	unsigned char retcode[8];
-	unsigned long extramask[_NSIG_WORDS-1];
-	struct sigcontext sc;
-	int sig;
-} __attribute__((aligned(2),packed));
-
-struct rt_sigframe
-{
-	long dummy_er0;
-	long dummy_vector;
-#if defined(CONFIG_CPU_H8S)
-	short dummy_exr;
-#endif
-	long dummy_pc;
-	char *pretcode;
-	struct siginfo *pinfo;
-	void *puc;
-	unsigned char retcode[8];
-	struct siginfo info;
-	struct ucontext uc;
-	int sig;
-} __attribute__((aligned(2),packed));
-
-static inline int
-restore_sigcontext(struct sigcontext *usc, int *pd0)
-{
-	struct pt_regs *regs = current_pt_regs();
-	int err = 0;
-	unsigned int ccr;
-	unsigned int usp;
-	unsigned int er0;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
-#define COPY(r) err |= __get_user(regs->r, &usc->sc_##r)    /* restore passed registers */
-	COPY(er1);
-	COPY(er2);
-	COPY(er3);
-	COPY(er5);
-	COPY(pc);
-	ccr = regs->ccr & 0x10;
-	COPY(ccr);
-#undef COPY
-	regs->ccr &= 0xef;
-	regs->ccr |= ccr;
-	regs->orig_er0 = -1;		/* disable syscall checks */
-	err |= __get_user(usp, &usc->sc_usp);
-	wrusp(usp);
-
-	err |= __get_user(er0, &usc->sc_er0);
-	*pd0 = er0;
-	return err;
-}
-
-asmlinkage int sys_sigreturn(void)
-{
-	unsigned long usp = rdusp();
-	struct sigframe *frame = (struct sigframe *)(usp - 4);
-	sigset_t set;
-	int er0;
-
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__get_user(set.sig[0], &frame->sc.sc_mask) ||
-	    (_NSIG_WORDS > 1 &&
-	     __copy_from_user(&set.sig[1], &frame->extramask,
-			      sizeof(frame->extramask))))
-		goto badframe;
-
-	set_current_blocked(&set);
-	
-	if (restore_sigcontext(&frame->sc, &er0))
-		goto badframe;
-	return er0;
-
-badframe:
-	force_sig(SIGSEGV, current);
-	return 0;
-}
-
-asmlinkage int sys_rt_sigreturn(void)
-{
-	unsigned long usp = rdusp();
-	struct rt_sigframe *frame = (struct rt_sigframe *)(usp - 4);
-	sigset_t set;
-	int er0;
-
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-		goto badframe;
-
-	set_current_blocked(&set);
-	
-	if (restore_sigcontext(&frame->uc.uc_mcontext, &er0))
-		goto badframe;
-
-	if (restore_altstack(&frame->uc.uc_stack))
-		goto badframe;
-
-	return er0;
-
-badframe:
-	force_sig(SIGSEGV, current);
-	return 0;
-}
-
-static int setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
-			     unsigned long mask)
-{
-	int err = 0;
-
-	err |= __put_user(regs->er0, &sc->sc_er0);
-	err |= __put_user(regs->er1, &sc->sc_er1);
-	err |= __put_user(regs->er2, &sc->sc_er2);
-	err |= __put_user(regs->er3, &sc->sc_er3);
-	err |= __put_user(regs->er4, &sc->sc_er4);
-	err |= __put_user(regs->er5, &sc->sc_er5);
-	err |= __put_user(regs->er6, &sc->sc_er6);
-	err |= __put_user(rdusp(),   &sc->sc_usp);
-	err |= __put_user(regs->pc,  &sc->sc_pc);
-	err |= __put_user(regs->ccr, &sc->sc_ccr);
-	err |= __put_user(mask,      &sc->sc_mask);
-
-	return err;
-}
-
-static inline void *
-get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size)
-{
-	unsigned long usp;
-
-	/* Default to using normal stack.  */
-	usp = rdusp();
-
-	/* This is the X/Open sanctioned signal stack switching.  */
-	if (ka->sa.sa_flags & SA_ONSTACK) {
-		if (!sas_ss_flags(usp))
-			usp = current->sas_ss_sp + current->sas_ss_size;
-	}
-	return (void *)((usp - frame_size) & -8UL);
-}
-
-static int setup_frame (int sig, struct k_sigaction *ka,
-			 sigset_t *set, struct pt_regs *regs)
-{
-	struct sigframe *frame;
-	int err = 0;
-	int usig;
-	unsigned char *ret;
-
-	frame = get_sigframe(ka, regs, sizeof(*frame));
-
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		goto give_sigsegv;
-
-	usig = current_thread_info()->exec_domain
-		&& current_thread_info()->exec_domain->signal_invmap
-		&& sig < 32
-		? current_thread_info()->exec_domain->signal_invmap[sig]
-		: sig;
-
-	err |= __put_user(usig, &frame->sig);
-	if (err)
-		goto give_sigsegv;
-
-	err |= setup_sigcontext(&frame->sc, regs, set->sig[0]);
-	if (err)
-		goto give_sigsegv;
-
-	if (_NSIG_WORDS > 1) {
-		err |= copy_to_user(frame->extramask, &set->sig[1],
-				    sizeof(frame->extramask));
-		if (err)
-			goto give_sigsegv;
-	}
-
-	ret = frame->retcode;
-	if (ka->sa.sa_flags & SA_RESTORER)
-		ret = (unsigned char *)(ka->sa.sa_restorer);
-	else {
-		/* sub.l er0,er0; mov.b #__NR_sigreturn,r0l; trapa #0 */
-		err |= __put_user(0x1a80f800 + (__NR_sigreturn & 0xff),
-				  (unsigned long *)(frame->retcode + 0));
-		err |= __put_user(0x5700, (unsigned short *)(frame->retcode + 4));
-	}
-
-	/* Set up to return from userspace.  */
-	err |= __put_user(ret, &frame->pretcode);
-
-	if (err)
-		goto give_sigsegv;
-
-	/* Set up registers for signal handler */
-	wrusp ((unsigned long) frame);
-	regs->pc = (unsigned long) ka->sa.sa_handler;
-	regs->er0 = (current_thread_info()->exec_domain
-			   && current_thread_info()->exec_domain->signal_invmap
-			   && sig < 32
-			   ? current_thread_info()->exec_domain->signal_invmap[sig]
-		          : sig);
-	regs->er1 = (unsigned long)&(frame->sc);
-	regs->er5 = current->mm->start_data;	/* GOT base */
-
-	return 0;
-
-give_sigsegv:
-	force_sigsegv(sig, current);
-	return -EFAULT;
-}
-
-static int setup_rt_frame (int sig, struct k_sigaction *ka, siginfo_t *info,
-			    sigset_t *set, struct pt_regs *regs)
-{
-	struct rt_sigframe *frame;
-	int err = 0;
-	int usig;
-	unsigned char *ret;
-
-	frame = get_sigframe(ka, regs, sizeof(*frame));
-
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		goto give_sigsegv;
-
-	usig = current_thread_info()->exec_domain
-		&& current_thread_info()->exec_domain->signal_invmap
-		&& sig < 32
-		? current_thread_info()->exec_domain->signal_invmap[sig]
-		: sig;
-
-	err |= __put_user(usig, &frame->sig);
-	if (err)
-		goto give_sigsegv;
-
-	err |= __put_user(&frame->info, &frame->pinfo);
-	err |= __put_user(&frame->uc, &frame->puc);
-	err |= copy_siginfo_to_user(&frame->info, info);
-	if (err)
-		goto give_sigsegv;
-
-	/* Create the ucontext.  */
-	err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __save_altstack(&frame->uc.uc_stack, rdusp());
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0]);
-	err |= copy_to_user (&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
-		goto give_sigsegv;
-
-	/* Set up to return from userspace.  */
-	ret = frame->retcode;
-	if (ka->sa.sa_flags & SA_RESTORER)
-		ret = (unsigned char *)(ka->sa.sa_restorer);
-	else {
-		/* sub.l er0,er0; mov.b #__NR_sigreturn,r0l; trapa #0 */
-		err |= __put_user(0x1a80f800 + (__NR_sigreturn & 0xff),
-				  (unsigned long *)(frame->retcode + 0));
-		err |= __put_user(0x5700, (unsigned short *)(frame->retcode + 4));
-	}
-	err |= __put_user(ret, &frame->pretcode);
-
-	if (err)
-		goto give_sigsegv;
-
-	/* Set up registers for signal handler */
-	wrusp ((unsigned long) frame);
-	regs->pc  = (unsigned long) ka->sa.sa_handler;
-	regs->er0 = (current_thread_info()->exec_domain
-		     && current_thread_info()->exec_domain->signal_invmap
-		     && sig < 32
-		     ? current_thread_info()->exec_domain->signal_invmap[sig]
-		     : sig);
-	regs->er1 = (unsigned long)&(frame->info);
-	regs->er2 = (unsigned long)&frame->uc;
-	regs->er5 = current->mm->start_data;	/* GOT base */
-
-	return 0;
-
-give_sigsegv:
-	force_sigsegv(sig, current);
-	return -EFAULT;
-}
-
-/*
- * OK, we're invoking a handler
- */
-static void
-handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
-	      struct pt_regs * regs)
-{
-	sigset_t *oldset = sigmask_to_save();
-	int ret;
-	/* are we from a system call? */
-	if (regs->orig_er0 >= 0) {
-		switch (regs->er0) {
-		        case -ERESTART_RESTARTBLOCK:
-			case -ERESTARTNOHAND:
-				regs->er0 = -EINTR;
-				break;
-
-			case -ERESTARTSYS:
-				if (!(ka->sa.sa_flags & SA_RESTART)) {
-					regs->er0 = -EINTR;
-					break;
-				}
-			/* fallthrough */
-			case -ERESTARTNOINTR:
-				regs->er0 = regs->orig_er0;
-				regs->pc -= 2;
-		}
-	}
-
-	/* set up the stack frame */
-	if (ka->sa.sa_flags & SA_SIGINFO)
-		ret = setup_rt_frame(sig, ka, info, oldset, regs);
-	else
-		ret = setup_frame(sig, ka, oldset, regs);
-
-	if (!ret)
-		signal_delivered(sig, info, ka, regs, 0);
-}
-
-/*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- */
-static void do_signal(struct pt_regs *regs)
-{
-	siginfo_t info;
-	int signr;
-	struct k_sigaction ka;
-
-	/*
-	 * We want the common case to go fast, which
-	 * is why we may in certain cases get here from
-	 * kernel mode. Just return without doing anything
-	 * if so.
-	 */
-	if ((regs->ccr & 0x10))
-		return;
-
-	current->thread.esp0 = (unsigned long) regs;
-
-	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-	if (signr > 0) {
-		/* Whee!  Actually deliver the signal.  */
-		handle_signal(signr, &info, &ka, regs);
-		return;
-	}
-	/* Did we come from a system call? */
-	if (regs->orig_er0 >= 0) {
-		/* Restart the system call - no handlers present */
-		if (regs->er0 == -ERESTARTNOHAND ||
-		    regs->er0 == -ERESTARTSYS ||
-		    regs->er0 == -ERESTARTNOINTR) {
-			regs->er0 = regs->orig_er0;
-			regs->pc -= 2;
-		}
-		if (regs->er0 == -ERESTART_RESTARTBLOCK){
-			regs->er0 = __NR_restart_syscall;
-			regs->pc -= 2;
-		}
-	}
-
-	/* If there's no signal to deliver, we just restore the saved mask.  */
-	restore_saved_sigmask();
-}
-
-asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
-{
-	if (thread_info_flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-}
diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c
deleted file mode 100644
index bf350cb7f597..000000000000
--- a/arch/h8300/kernel/sys_h8300.c
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * linux/arch/h8300/kernel/sys_h8300.c
- *
- * This file contains various random system calls that
- * have a non-standard calling sequence on the H8/300
- * platform.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/ipc.h>
-
-#include <asm/setup.h>
-#include <asm/uaccess.h>
-#include <asm/cachectl.h>
-#include <asm/traps.h>
-#include <asm/unistd.h>
-
-/* sys_cacheflush -- no support.  */
-asmlinkage int
-sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
-{
-	return -EINVAL;
-}
-
-asmlinkage int sys_getpagesize(void)
-{
-	return PAGE_SIZE;
-}
-
-#if defined(CONFIG_SYSCALL_PRINT)
-asmlinkage void syscall_print(void *dummy,...)
-{
-	struct pt_regs *regs = (struct pt_regs *) ((unsigned char *)&dummy-4);
-	printk("call %06lx:%ld 1:%08lx,2:%08lx,3:%08lx,ret:%08lx\n",
-               ((regs->pc)&0xffffff)-2,regs->orig_er0,regs->er1,regs->er2,regs->er3,regs->er0);
-}
-#endif
diff --git a/arch/h8300/kernel/syscalls.S b/arch/h8300/kernel/syscalls.S
deleted file mode 100644
index c55e0ed270d5..000000000000
--- a/arch/h8300/kernel/syscalls.S
+++ /dev/null
@@ -1,338 +0,0 @@
-/* Systemcall Entry Table */
-#include <linux/sys.h>
-#include <asm/linkage.h>
-#include <asm/unistd.h>
-
-#define CALL(x)	.long _ ## x
-
-.globl _sys_call_table
-
-#if defined(CONFIG_CPU_H8300H)
-	.h8300h
-#endif
-#if defined(CONFIG_CPU_H8S)
-	.h8300s
-#endif
-	.section .text
-	.align	2
-_sys_call_table:
-	CALL(sys_ni_syscall)		/* 0  -  old "setup()" system call*/
-	CALL(sys_exit)
-	CALL(sys_fork)
-	CALL(sys_read)
-	CALL(sys_write)
-	CALL(sys_open)			/* 5 */
-	CALL(sys_close)
-	CALL(sys_waitpid)
-	CALL(sys_creat)
-	CALL(sys_link)
-	CALL(sys_unlink)		/* 10 */
-	CALL(sys_execve)
-	CALL(sys_chdir)
-	CALL(sys_time)
-	CALL(sys_mknod)
-	CALL(sys_chmod)			/* 15 */
-	CALL(sys_chown16)
-	CALL(sys_ni_syscall)		/* old break syscall holder */
-	CALL(sys_stat)
-	CALL(sys_lseek)
-	CALL(sys_getpid)		/* 20 */
-	CALL(sys_mount)
-	CALL(sys_oldumount)
-	CALL(sys_setuid16)
-	CALL(sys_getuid16)
-	CALL(sys_stime)			/* 25 */
-	CALL(sys_ptrace)
-	CALL(sys_alarm)
-	CALL(sys_fstat)
-	CALL(sys_pause)
-	CALL(sys_utime)			/* 30 */
-	CALL(sys_ni_syscall)		/* old stty syscall holder */
-	CALL(sys_ni_syscall)		/* old gtty syscall holder */
-	CALL(sys_access)
-	CALL(sys_nice)
-	CALL(sys_ni_syscall)		/* 35 old ftime syscall holder */
-	CALL(sys_sync)
-	CALL(sys_kill)
-	CALL(sys_rename)
-	CALL(sys_mkdir)
-	CALL(sys_rmdir)			/* 40 */
-	CALL(sys_dup)
-	CALL(sys_pipe)
-	CALL(sys_times)
-	CALL(sys_ni_syscall)		/* old prof syscall holder */
-	CALL(sys_brk)			/* 45 */
-	CALL(sys_setgid16)
-	CALL(sys_getgid16)
-	CALL(sys_signal)
-	CALL(sys_geteuid16)
-	CALL(sys_getegid16)		/* 50 */
-	CALL(sys_acct)
-	CALL(sys_umount)		/* recycled never used phys() */
-	CALL(sys_ni_syscall)		/* old lock syscall holder */
-	CALL(sys_ioctl)
-	CALL(sys_fcntl)			/* 55 */
-	CALL(sys_ni_syscall)		/* old mpx syscall holder */
-	CALL(sys_setpgid)
-	CALL(sys_ni_syscall)		/* old ulimit syscall holder */
-	CALL(sys_ni_syscall)
-	CALL(sys_umask)			/* 60 */
-	CALL(sys_chroot)
-	CALL(sys_ustat)
-	CALL(sys_dup2)
-	CALL(sys_getppid)
-	CALL(sys_getpgrp)		/* 65 */
-	CALL(sys_setsid)
-	CALL(sys_sigaction)
-	CALL(sys_sgetmask)
-	CALL(sys_ssetmask)
-	CALL(sys_setreuid16)		/* 70 */
-	CALL(sys_setregid16)
-	CALL(sys_sigsuspend)
-	CALL(sys_sigpending)
-	CALL(sys_sethostname)
-	CALL(sys_setrlimit)		/* 75 */
-	CALL(sys_old_getrlimit)
-	CALL(sys_getrusage)
-	CALL(sys_gettimeofday)
-	CALL(sys_settimeofday)
-	CALL(sys_getgroups16)		/* 80 */
-	CALL(sys_setgroups16)
-	CALL(sys_old_select)
-	CALL(sys_symlink)
-	CALL(sys_lstat)
-	CALL(sys_readlink)		/* 85 */
-	CALL(sys_uselib)
-	CALL(sys_swapon)
-	CALL(sys_reboot)
-	CALL(sys_old_readdir)
-	CALL(sys_old_mmap)		/* 90 */
-	CALL(sys_munmap)
-	CALL(sys_truncate)
-	CALL(sys_ftruncate)
-	CALL(sys_fchmod)
-	CALL(sys_fchown16)		/* 95 */
-	CALL(sys_getpriority)
-	CALL(sys_setpriority)
-	CALL(sys_ni_syscall)		/* old profil syscall holder */
-	CALL(sys_statfs)
-	CALL(sys_fstatfs)		/* 100 */
-	CALL(sys_ni_syscall)		/* ioperm for i386 */
-	CALL(sys_socketcall)
-	CALL(sys_syslog)
-	CALL(sys_setitimer)
-	CALL(sys_getitimer)		/* 105 */
-	CALL(sys_newstat)
-	CALL(sys_newlstat)
-	CALL(sys_newfstat)
-	CALL(sys_ni_syscall)
-	CALL(sys_ni_syscall)		/* iopl for i386 */ /* 110 */
-	CALL(sys_vhangup)
-	CALL(sys_ni_syscall)		/* obsolete idle() syscall */
-	CALL(sys_ni_syscall)		/* vm86old for i386 */
-	CALL(sys_wait4)
-	CALL(sys_swapoff)		/* 115 */
-	CALL(sys_sysinfo)
-	CALL(sys_ipc)
-	CALL(sys_fsync)
-	CALL(sys_sigreturn)
-	CALL(sys_clone)			/* 120 */
-	CALL(sys_setdomainname)
-	CALL(sys_newuname)
-	CALL(sys_cacheflush)		/* modify_ldt for i386 */
-	CALL(sys_adjtimex)
-	CALL(sys_ni_syscall)		/* 125 sys_mprotect */
-	CALL(sys_sigprocmask)
-	CALL(sys_ni_syscall)		/* sys_create_module */
-	CALL(sys_init_module)
-	CALL(sys_delete_module)
-	CALL(sys_ni_syscall)		/* 130 sys_get_kernel_syms */
-	CALL(sys_quotactl)
-	CALL(sys_getpgid)
-	CALL(sys_fchdir)
-	CALL(sys_bdflush)
-	CALL(sys_sysfs)			/* 135 */
-	CALL(sys_personality)
-	CALL(sys_ni_syscall)		/* for afs_syscall */
-	CALL(sys_setfsuid16)
-	CALL(sys_setfsgid16)
-	CALL(sys_llseek)		/* 140 */
-	CALL(sys_getdents)
-	CALL(sys_select)
-	CALL(sys_flock)
-	CALL(sys_ni_syscall)		/* sys_msync */
-	CALL(sys_readv)			/* 145 */
-	CALL(sys_writev)
-	CALL(sys_getsid)
-	CALL(sys_fdatasync)
-	CALL(sys_sysctl)
-	CALL(sys_ni_syscall)		/* 150 sys_mlock */
-	CALL(sys_ni_syscall)		/* sys_munlock */
-	CALL(sys_ni_syscall)		/* sys_mlockall */
-	CALL(sys_ni_syscall)		/* sys_munlockall */
-	CALL(sys_sched_setparam)
-	CALL(sys_sched_getparam)	/* 155 */
-	CALL(sys_sched_setscheduler)
-	CALL(sys_sched_getscheduler)
-	CALL(sys_sched_yield)
-	CALL(sys_sched_get_priority_max)
-	CALL(sys_sched_get_priority_min)  /* 160 */
-	CALL(sys_sched_rr_get_interval)
-	CALL(sys_nanosleep)
-	CALL(sys_ni_syscall)		/* sys_mremap */
-	CALL(sys_setresuid16)
-	CALL(sys_getresuid16)		/* 165 */
-	CALL(sys_ni_syscall)		/* for vm86 */
-	CALL(sys_ni_syscall)		/* sys_query_module */
-	CALL(sys_poll)
-	CALL(sys_ni_syscall)		/* old nfsservctl */
-	CALL(sys_setresgid16)		/* 170 */
-	CALL(sys_getresgid16)
-	CALL(sys_prctl)
-	CALL(sys_rt_sigreturn)
-	CALL(sys_rt_sigaction)
-	CALL(sys_rt_sigprocmask)	/* 175 */
-	CALL(sys_rt_sigpending)
-	CALL(sys_rt_sigtimedwait)
-	CALL(sys_rt_sigqueueinfo)
-	CALL(sys_rt_sigsuspend)
-	CALL(sys_pread64)		/* 180 */
-	CALL(sys_pwrite64)
-	CALL(sys_lchown16);
-	CALL(sys_getcwd)
-	CALL(sys_capget)
-	CALL(sys_capset)		/* 185 */
-	CALL(sys_sigaltstack)
-	CALL(sys_sendfile)
-	CALL(sys_ni_syscall)		/* streams1 */
-	CALL(sys_ni_syscall)		/* streams2 */
-	CALL(sys_vfork)			/* 190 */
-	CALL(sys_getrlimit)
-	CALL(sys_mmap_pgoff)
-	CALL(sys_truncate64)
-	CALL(sys_ftruncate64)
-	CALL(sys_stat64)		/* 195 */
-	CALL(sys_lstat64)
-	CALL(sys_fstat64)
-	CALL(sys_chown)
-	CALL(sys_getuid)
-	CALL(sys_getgid)		/* 200 */
-	CALL(sys_geteuid)
-	CALL(sys_getegid)
-	CALL(sys_setreuid)
-	CALL(sys_setregid)
-	CALL(sys_getgroups)		/* 205 */
-	CALL(sys_setgroups)
-	CALL(sys_fchown)
-	CALL(sys_setresuid)
-	CALL(sys_getresuid)
-	CALL(sys_setresgid)		/* 210 */
-	CALL(sys_getresgid)
-	CALL(sys_lchown)
-	CALL(sys_setuid)
-	CALL(sys_setgid)
-	CALL(sys_setfsuid)		/* 215 */
-	CALL(sys_setfsgid)
-	CALL(sys_pivot_root)
-	CALL(sys_ni_syscall)
-	CALL(sys_ni_syscall)
-	CALL(sys_getdents64)		/* 220 */
-	CALL(sys_fcntl64)
-	CALL(sys_ni_syscall)		/* reserved TUX */
-	CALL(sys_ni_syscall)		/* reserved Security */
-	CALL(sys_gettid)
-	CALL(sys_readahead)		/* 225 */
-	CALL(sys_setxattr)
-	CALL(sys_lsetxattr)
-	CALL(sys_fsetxattr)
-	CALL(sys_getxattr)
-	CALL(sys_lgetxattr)		/* 230 */
-	CALL(sys_fgetxattr)
-	CALL(sys_listxattr)
-	CALL(sys_llistxattr)
-	CALL(sys_flistxattr)
-	CALL(sys_removexattr)		/* 235 */
-	CALL(sys_lremovexattr)
-	CALL(sys_fremovexattr)
-	CALL(sys_tkill)
-	CALL(sys_sendfile64)
-	CALL(sys_futex)			/* 240 */
-	CALL(sys_sched_setaffinity)
-	CALL(sys_sched_getaffinity)
-	CALL(sys_ni_syscall)
-	CALL(sys_ni_syscall)
-	CALL(sys_io_setup)		/* 245 */
-	CALL(sys_io_destroy)
-	CALL(sys_io_getevents)
-	CALL(sys_io_submit)
-	CALL(sys_io_cancel)
-	CALL(sys_fadvise64)		/* 250 */
-	CALL(sys_ni_syscall)
-	CALL(sys_exit_group)
-	CALL(sys_lookup_dcookie)
-	CALL(sys_epoll_create)
-	CALL(sys_epoll_ctl)		/* 255 */
-	CALL(sys_epoll_wait)
-	CALL(sys_ni_syscall)		/* sys_remap_file_pages */
-	CALL(sys_set_tid_address)
-	CALL(sys_timer_create)
-	CALL(sys_timer_settime)		/* 260 */
-	CALL(sys_timer_gettime)
-	CALL(sys_timer_getoverrun)
-	CALL(sys_timer_delete)
-	CALL(sys_clock_settime)
-	CALL(sys_clock_gettime)		/* 265 */
-	CALL(sys_clock_getres)
-	CALL(sys_clock_nanosleep)
-	CALL(sys_statfs64)
-	CALL(sys_fstatfs64)
-	CALL(sys_tgkill)		/* 270 */
-	CALL(sys_utimes)
-	CALL(sys_fadvise64_64)
-	CALL(sys_ni_syscall)		/* sys_vserver */
-	CALL(sys_ni_syscall)
-	CALL(sys_get_mempolicy)		/* 275 */
-	CALL(sys_set_mempolicy)
-	CALL(sys_mq_open)
-	CALL(sys_mq_unlink)
-	CALL(sys_mq_timedsend)
-	CALL(sys_mq_timedreceive)	/* 280 */
-	CALL(sys_mq_notify)
-	CALL(sys_mq_getsetattr)
-	CALL(sys_waitid)
-	CALL(sys_ni_syscall)		/* sys_kexec_load */
-	CALL(sys_add_key) 		/* 285 */
-	CALL(sys_request_key)
-	CALL(sys_keyctl)
-	CALL(sys_ioprio_set)
-	CALL(sys_ioprio_get)		/* 290 */
-	CALL(sys_inotify_init)
-	CALL(sys_inotify_add_watch)
-	CALL(sys_inotify_rm_watch)
-	CALL(sys_migrate_pages)
-	CALL(sys_openat)		/* 295 */
-	CALL(sys_mkdirat)
-	CALL(sys_mknodat)
-	CALL(sys_fchownat)
-	CALL(sys_futimesat)
-	CALL(sys_fstatat64)		/* 300 */
-	CALL(sys_unlinkat)
-	CALL(sys_renameat)
-	CALL(sys_linkat)
-	CALL(sys_symlinkat)
-	CALL(sys_readlinkat)		/* 305 */
-	CALL(sys_fchmodat)
-	CALL(sys_faccessat)
-	CALL(sys_ni_syscall)		/* sys_pselect6 */
-	CALL(sys_ni_syscall)		/* sys_ppoll */
-	CALL(sys_unshare)		/* 310 */
-	CALL(sys_set_robust_list)
-	CALL(sys_get_robust_list)
-	CALL(sys_splice)
-	CALL(sys_sync_file_range)
-	CALL(sys_tee)			/* 315 */
-	CALL(sys_vmsplice)
-	CALL(sys_ni_syscall)		/* sys_move_pages */
-	CALL(sys_getcpu)
-	CALL(sys_ni_syscall)		/* sys_epoll_pwait */
-	CALL(sys_setns)			/* 320 */
diff --git a/arch/h8300/kernel/time.c b/arch/h8300/kernel/time.c
deleted file mode 100644
index e0f74191d553..000000000000
--- a/arch/h8300/kernel/time.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/time.c
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Copied/hacked from:
- *
- *  linux/arch/m68k/kernel/time.c
- *
- *  Copyright (C) 1991, 1992, 1995  Linus Torvalds
- *
- * This file contains the m68k-specific time handling details.
- * Most of the stuff is located in the machine specific files.
- *
- * 1997-09-10	Updated NTP code according to technical memorandum Jan '96
- *		"A Kernel Model for Precision Timekeeping" by Dave Mills
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/timex.h>
-#include <linux/profile.h>
-
-#include <asm/io.h>
-#include <asm/irq_regs.h>
-#include <asm/timer.h>
-
-#define	TICK_SIZE (tick_nsec / 1000)
-
-void h8300_timer_tick(void)
-{
-	if (current->pid)
-		profile_tick(CPU_PROFILING);
-	xtime_update(1);
-	update_process_times(user_mode(get_irq_regs()));
-}
-
-void read_persistent_clock(struct timespec *ts)
-{
-	unsigned int year, mon, day, hour, min, sec;
-
-	/* FIX by dqg : Set to zero for platforms that don't have tod */
-	/* without this time is undefined and can overflow time_t, causing  */
-	/* very strange errors */
-	year = 1980;
-	mon = day = 1;
-	hour = min = sec = 0;
-#ifdef CONFIG_H8300_GETTOD
-	h8300_gettod (&year, &mon, &day, &hour, &min, &sec);
-#endif
-	if ((year += 1900) < 1970)
-		year += 100;
-	ts->tv_sec = mktime(year, mon, day, hour, min, sec);
-	ts->tv_nsec = 0;
-}
-
-void __init time_init(void)
-{
-
-	h8300_timer_setup();
-}
diff --git a/arch/h8300/kernel/timer/Makefile b/arch/h8300/kernel/timer/Makefile
deleted file mode 100644
index bef0510ea6ad..000000000000
--- a/arch/h8300/kernel/timer/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# h8300 internal timer handler
-
-obj-$(CONFIG_H8300_TIMER8)  := timer8.o
-obj-$(CONFIG_H8300_TIMER16) := timer16.o
-obj-$(CONFIG_H8300_ITU)     := itu.o
-obj-$(CONFIG_H8300_TPU)     := tpu.o
diff --git a/arch/h8300/kernel/timer/itu.c b/arch/h8300/kernel/timer/itu.c
deleted file mode 100644
index 0a8b5cd5bf38..000000000000
--- a/arch/h8300/kernel/timer/itu.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/timer/itu.c
- *
- *  Yoshinori Sato <ysato@users.sourcefoge.jp>
- *
- *  ITU Timer Handler
- *
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/timex.h>
-
-#include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/regs306x.h>
-
-#if CONFIG_H8300_ITU_CH == 0
-#define ITUBASE	0xffff64
-#define ITUIRQ	24
-#elif CONFIG_H8300_ITU_CH == 1
-#define ITUBASE	0xffff6e
-#define ITUIRQ	28
-#elif CONFIG_H8300_ITU_CH == 2
-#define ITUBASE	0xffff78
-#define ITUIRQ	32
-#elif CONFIG_H8300_ITU_CH == 3
-#define ITUBASE	0xffff82
-#define ITUIRQ	36
-#elif CONFIG_H8300_ITU_CH == 4
-#define ITUBASE	0xffff92
-#define ITUIRQ	40
-#else
-#error Unknown timer channel.
-#endif
-
-#define TCR	0
-#define TIOR	1
-#define TIER	2
-#define TSR	3
-#define TCNT	4
-#define GRA	6
-#define GRB	8
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	h8300_timer_tick();
-	ctrl_bclr(IMFA, ITUBASE + TSR);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction itu_irq = {
-	.name		= "itu",
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
-};
-
-static const int __initconst divide_rate[] = {1, 2, 4, 8};
-
-void __init h8300_timer_setup(void)
-{
-	unsigned int div;
-	unsigned int cnt;
-
-	calc_param(cnt, div, divide_rate, 0x10000);
-
-	setup_irq(ITUIRQ, &itu_irq);
-
-	/* initialize timer */
-	ctrl_outb(0, TSTR);
-	ctrl_outb(CCLR0 | div, ITUBASE + TCR);
-	ctrl_outb(0x01, ITUBASE + TIER);
-	ctrl_outw(cnt, ITUBASE + GRA);
-	ctrl_bset(CONFIG_H8300_ITU_CH, TSTR);
-}
diff --git a/arch/h8300/kernel/timer/timer16.c b/arch/h8300/kernel/timer/timer16.c
deleted file mode 100644
index 462d9f581719..000000000000
--- a/arch/h8300/kernel/timer/timer16.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/timer/timer16.c
- *
- *  Yoshinori Sato <ysato@users.sourcefoge.jp>
- *
- *  16bit Timer Handler
- *
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/timex.h>
-
-#include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/regs306x.h>
-
-/* 16bit timer */
-#if CONFIG_H8300_TIMER16_CH == 0
-#define _16BASE	0xffff78
-#define _16IRQ	24
-#elif CONFIG_H8300_TIMER16_CH == 1
-#define _16BASE	0xffff80
-#define _16IRQ	28
-#elif CONFIG_H8300_TIMER16_CH == 2
-#define _16BASE	0xffff88
-#define _16IRQ	32
-#else
-#error Unknown timer channel.
-#endif
-
-#define TCR	0
-#define TIOR	1
-#define TCNT	2
-#define GRA	4
-#define GRB	6
-
-#define H8300_TIMER_FREQ CONFIG_CPU_CLOCK*10000 /* Timer input freq. */
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	h8300_timer_tick();
-	ctrl_bclr(CONFIG_H8300_TIMER16_CH, TISRA);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction timer16_irq = {
-	.name		= "timer-16",
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
-};
-
-static const int __initconst divide_rate[] = {1, 2, 4, 8};
-
-void __init h8300_timer_setup(void)
-{
-	unsigned int div;
-	unsigned int cnt;
-
-	calc_param(cnt, div, divide_rate, 0x10000);
-
-	setup_irq(_16IRQ, &timer16_irq);
-
-	/* initialize timer */
-	ctrl_outb(0, TSTR);
-	ctrl_outb(CCLR0 | div, _16BASE + TCR);
-	ctrl_outw(cnt, _16BASE + GRA);
-	ctrl_bset(4 + CONFIG_H8300_TIMER16_CH, TISRA);
-	ctrl_bset(CONFIG_H8300_TIMER16_CH, TSTR);
-}
diff --git a/arch/h8300/kernel/timer/timer8.c b/arch/h8300/kernel/timer/timer8.c
deleted file mode 100644
index 505f3415b40f..000000000000
--- a/arch/h8300/kernel/timer/timer8.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/cpu/timer/timer8.c
- *
- *  Yoshinori Sato <ysato@users.sourcefoge.jp>
- *
- *  8bit Timer Handler
- *
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/profile.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/timer.h>
-#if defined(CONFIG_CPU_H8300H)
-#include <asm/regs306x.h>
-#endif
-#if defined(CONFIG_CPU_H8S)
-#include <asm/regs267x.h>
-#endif
-
-/* 8bit timer x2 */
-#define CMFA	6
-
-#if defined(CONFIG_H8300_TIMER8_CH0)
-#define _8BASE	_8TCR0
-#ifdef CONFIG_CPU_H8300H
-#define _8IRQ	36
-#endif
-#ifdef CONFIG_CPU_H8S
-#define _8IRQ	72
-#endif
-#elif defined(CONFIG_H8300_TIMER8_CH2)
-#ifdef CONFIG_CPU_H8300H
-#define _8BASE	_8TCR2
-#define _8IRQ	40
-#endif
-#endif
-
-#ifndef _8BASE
-#error Unknown timer channel.
-#endif
-
-#define _8TCR	0
-#define _8TCSR	2
-#define TCORA	4
-#define TCORB	6
-#define _8TCNT	8
-
-#define CMIEA	0x40
-#define CCLR_CMA 0x08
-#define CKS2	0x04
-
-/*
- * timer_interrupt() needs to keep up the real-time clock,
- * as well as call the "xtime_update()" routine every clocktick
- */
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	h8300_timer_tick();
-	ctrl_bclr(CMFA, _8BASE + _8TCSR);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction timer8_irq = {
-	.name		= "timer-8",
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
-};
-
-static const int __initconst divide_rate[] = {8, 64, 8192};
-
-void __init h8300_timer_setup(void)
-{
-	unsigned int div;
-	unsigned int cnt;
-
-	calc_param(cnt, div, divide_rate, 0x10000);
-	div++;
-
-	setup_irq(_8IRQ, &timer8_irq);
-
-#if defined(CONFIG_CPU_H8S)
-	/* Timer module enable */
-	ctrl_bclr(0, MSTPCRL)
-#endif
-
-	/* initialize timer */
-	ctrl_outw(cnt, _8BASE + TCORA);
-	ctrl_outw(0x0000, _8BASE + _8TCSR);
-	ctrl_outw((CMIEA|CCLR_CMA|CKS2) << 8 | div,
-		  _8BASE + _8TCR);
-}
diff --git a/arch/h8300/kernel/timer/tpu.c b/arch/h8300/kernel/timer/tpu.c
deleted file mode 100644
index 0350f6204ecf..000000000000
--- a/arch/h8300/kernel/timer/tpu.c
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- *  linux/arch/h8300/kernel/timer/tpu.c
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  TPU Timer Handler
- *
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/timex.h>
-
-#include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/regs267x.h>
-
-/* TPU */
-#if CONFIG_H8300_TPU_CH == 0
-#define TPUBASE	0xffffd0
-#define TPUIRQ	40
-#elif CONFIG_H8300_TPU_CH == 1
-#define TPUBASE	0xffffe0
-#define TPUIRQ	48
-#elif CONFIG_H8300_TPU_CH == 2
-#define TPUBASE	0xfffff0
-#define TPUIRQ	52
-#elif CONFIG_H8300_TPU_CH == 3
-#define TPUBASE	0xfffe80
-#define TPUIRQ	56
-#elif CONFIG_H8300_TPU_CH == 4
-#define TPUBASE	0xfffe90
-#define TPUIRQ	64
-#else
-#error Unknown timer channel.
-#endif
-
-#define _TCR	0
-#define _TMDR	1
-#define _TIOR	2
-#define _TIER	4
-#define _TSR	5
-#define _TCNT	6
-#define _GRA	8
-#define _GRB	10
-
-#define CCLR0	0x20
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
-	h8300_timer_tick();
-	ctrl_bclr(0, TPUBASE + _TSR);
-	return IRQ_HANDLED;
-}
-
-static struct irqaction tpu_irq = {
-	.name		= "tpu",
-	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
-};
-
-static const int __initconst divide_rate[] = {
-#if CONFIG_H8300_TPU_CH == 0
-	1,4,16,64,0,0,0,0,
-#elif (CONFIG_H8300_TPU_CH == 1) || (CONFIG_H8300_TPU_CH == 5)
-	1,4,16,64,0,0,256,0,
-#elif (CONFIG_H8300_TPU_CH == 2) || (CONFIG_H8300_TPU_CH == 4)
-	1,4,16,64,0,0,0,1024,
-#elif CONFIG_H8300_TPU_CH == 3
-	1,4,16,64,0,1024,256,4096,
-#endif
-};
-
-void __init h8300_timer_setup(void)
-{
-	unsigned int cnt;
-	unsigned int div;
-
-	calc_param(cnt, div, divide_rate, 0x10000);
-
-	setup_irq(TPUIRQ, &tpu_irq);
-
-	/* TPU module enabled */
-	ctrl_bclr(3, MSTPCRH);
-
-	ctrl_outb(0, TSTR);
-	ctrl_outb(CCLR0 | div, TPUBASE + _TCR);
-	ctrl_outb(0, TPUBASE + _TMDR);
-	ctrl_outw(0, TPUBASE + _TIOR);
-	ctrl_outb(0x01, TPUBASE + _TIER);
-	ctrl_outw(cnt, TPUBASE + _GRA);
-	ctrl_bset(CONFIG_H8300_TPU_CH, TSTR);
-}
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
deleted file mode 100644
index cfe494dbe3da..000000000000
--- a/arch/h8300/kernel/traps.c
+++ /dev/null
@@ -1,166 +0,0 @@
-/*
- * linux/arch/h8300/boot/traps.c -- general exception handling code
- * H8/300 support Yoshinori Sato <ysato@users.sourceforge.jp>
- * 
- * Cloned from Linux/m68k.
- *
- * No original Copyright holder listed,
- * Probable original (C) Roman Zippel (assigned DJD, 1999)
- *
- * Copyright 1999-2000 D. Jeff Dionne, <jeff@rt-control.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/bug.h>
-
-#include <asm/irq.h>
-#include <asm/traps.h>
-#include <asm/page.h>
-
-static DEFINE_SPINLOCK(die_lock);
-
-/*
- * this must be called very early as the kernel might
- * use some instruction that are emulated on the 060
- */
-
-void __init base_trap_init(void)
-{
-}
-
-void __init trap_init (void)
-{
-}
-
-asmlinkage void set_esp0 (unsigned long ssp)
-{
-	current->thread.esp0 = ssp;
-}
-
-/*
- *	Generic dumping code. Used for panic and debug.
- */
-
-static void dump(struct pt_regs *fp)
-{
-	unsigned long	*sp;
-	unsigned char	*tp;
-	int		i;
-
-	printk("\nCURRENT PROCESS:\n\n");
-	printk("COMM=%s PID=%d\n", current->comm, current->pid);
-	if (current->mm) {
-		printk("TEXT=%08x-%08x DATA=%08x-%08x BSS=%08x-%08x\n",
-			(int) current->mm->start_code,
-			(int) current->mm->end_code,
-			(int) current->mm->start_data,
-			(int) current->mm->end_data,
-			(int) current->mm->end_data,
-			(int) current->mm->brk);
-		printk("USER-STACK=%08x  KERNEL-STACK=%08lx\n\n",
-			(int) current->mm->start_stack,
-			(int) PAGE_SIZE+(unsigned long)current);
-	}
-
-	show_regs(fp);
-	printk("\nCODE:");
-	tp = ((unsigned char *) fp->pc) - 0x20;
-	for (sp = (unsigned long *) tp, i = 0; (i < 0x40);  i += 4) {
-		if ((i % 0x10) == 0)
-			printk("\n%08x: ", (int) (tp + i));
-		printk("%08x ", (int) *sp++);
-	}
-	printk("\n");
-
-	printk("\nKERNEL STACK:");
-	tp = ((unsigned char *) fp) - 0x40;
-	for (sp = (unsigned long *) tp, i = 0; (i < 0xc0); i += 4) {
-		if ((i % 0x10) == 0)
-			printk("\n%08x: ", (int) (tp + i));
-		printk("%08x ", (int) *sp++);
-	}
-	printk("\n");
-	if (STACK_MAGIC != *(unsigned long *)((unsigned long)current+PAGE_SIZE))
-                printk("(Possibly corrupted stack page??)\n");
-
-	printk("\n\n");
-}
-
-void die(const char *str, struct pt_regs *fp, unsigned long err)
-{
-	static int diecount;
-
-	oops_enter();
-
-	console_verbose();
-	spin_lock_irq(&die_lock);
-	report_bug(fp->pc, fp);
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++diecount);
-	dump(fp);
-
-	spin_unlock_irq(&die_lock);
-	do_exit(SIGSEGV);
-}
-
-extern char _start, _etext;
-#define check_kernel_text(addr) \
-        ((addr >= (unsigned long)(&_start)) && \
-         (addr <  (unsigned long)(&_etext))) 
-
-static int kstack_depth_to_print = 24;
-
-void show_stack(struct task_struct *task, unsigned long *esp)
-{
-	unsigned long *stack,  addr;
-	int i;
-
-	if (esp == NULL)
-		esp = (unsigned long *) &esp;
-
-	stack = esp;
-
-	printk("Stack from %08lx:", (unsigned long)stack);
-	for (i = 0; i < kstack_depth_to_print; i++) {
-		if (((unsigned long)stack & (THREAD_SIZE - 1)) == 0)
-			break;
-		if (i % 8 == 0)
-			printk("\n       ");
-		printk(" %08lx", *stack++);
-	}
-
-	printk("\nCall Trace:");
-	i = 0;
-	stack = esp;
-	while (((unsigned long)stack & (THREAD_SIZE - 1)) != 0) {
-		addr = *stack++;
-		/*
-		 * If the address is either in the text segment of the
-		 * kernel, or in the region which contains vmalloc'ed
-		 * memory, it *may* be the address of a calling
-		 * routine; if so, print it so that someone tracing
-		 * down the cause of the crash will be able to figure
-		 * out the call path that was taken.
-		 */
-		if (check_kernel_text(addr)) {
-			if (i % 4 == 0)
-				printk("\n       ");
-			printk(" [<%08lx>]", addr);
-			i++;
-		}
-	}
-	printk("\n");
-}
-
-void show_trace_task(struct task_struct *tsk)
-{
-	show_stack(tsk,(unsigned long *)tsk->thread.esp0);
-}
diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S
deleted file mode 100644
index 3253fed42ac1..000000000000
--- a/arch/h8300/kernel/vmlinux.lds.S
+++ /dev/null
@@ -1,157 +0,0 @@
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/page.h>
-
-/* target memory map */
-#ifdef CONFIG_H8300H_GENERIC
-#define ROMTOP  0x000000
-#define ROMSIZE 0x400000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x400000
-#endif
-
-#ifdef CONFIG_H8300H_AKI3068NET
-#define ROMTOP  0x000000
-#define ROMSIZE 0x080000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x200000
-#endif
-
-#ifdef CONFIG_H8300H_H8MAX
-#define ROMTOP  0x000000
-#define ROMSIZE 0x080000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x200000
-#endif
-
-#ifdef CONFIG_H8300H_SIM
-#define ROMTOP  0x000000
-#define ROMSIZE 0x400000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x400000
-#endif
-
-#ifdef CONFIG_H8S_SIM
-#define ROMTOP  0x000000
-#define ROMSIZE 0x400000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x800000
-#endif
-
-#ifdef CONFIG_H8S_EDOSK2674
-#define ROMTOP  0x000000
-#define ROMSIZE 0x400000
-#define RAMTOP  0x400000
-#define RAMSIZE 0x800000
-#endif
-
-#if defined(CONFIG_H8300H_SIM) || defined(CONFIG_H8S_SIM)
-INPUT(romfs.o)
-#endif
-
-_jiffies = _jiffies_64 + 4;
-
-ENTRY(__start)
-
-SECTIONS
-{
-#if defined(CONFIG_ROMKERNEL)
-	. = ROMTOP; 
-	.vectors :
-	{
-	__vector = . ;
-		*(.vectors*)
-	}
-#else
-	. = RAMTOP; 
-	.bootvec :	
-	{
-		*(.bootvec)
-	}
-#endif
-        .text :
-	{
-	_text = .;
-#if defined(CONFIG_ROMKERNEL)
-	*(.int_redirect)
-#endif
-	__stext = . ;
-	TEXT_TEXT
-	SCHED_TEXT
-	LOCK_TEXT
-	__etext = . ;
-	}
-	EXCEPTION_TABLE(16)
-
-	RODATA
-#if defined(CONFIG_ROMKERNEL)
-	SECURITY_INIT
-#endif
-	ROEND = .; 
-#if defined(CONFIG_ROMKERNEL)
-	. = RAMTOP;
-	.data :	AT(ROEND)
-#else
-	.data :	
-#endif
-	{
-	__sdata = . ;
-	___data_start = . ;
-
-	INIT_TASK_DATA(0x2000)
-	. = ALIGN(0x4) ;
-		DATA_DATA
-	. = ALIGN(0x4) ;
-		*(.data.*)	
-
-	. = ALIGN(0x4) ;
-	___init_begin = .;
-	__sinittext = .; 
-		INIT_TEXT
-	__einittext = .; 
-		INIT_DATA
-	. = ALIGN(0x4) ;
-	INIT_SETUP(0x4)
-	___setup_start = .;
-		*(.init.setup)
-	. = ALIGN(0x4) ;
-	___setup_end = .;
-	INIT_CALLS
-	CON_INITCALL
-		EXIT_TEXT
-		EXIT_DATA
-	INIT_RAM_FS
-	. = ALIGN(0x4) ;
-	___init_end = .;
-	__edata = . ;
-	}
-#if defined(CONFIG_RAMKERNEL)
-	SECURITY_INIT
-#endif
-	__begin_data = LOADADDR(.data);
-        .bss : 
-        {
-	. = ALIGN(0x4) ;
-	__sbss = . ;
-	___bss_start = . ;
-		*(.bss*)
-	. = ALIGN(0x4) ;
-		*(COMMON)
-	. = ALIGN(0x4) ;
-	___bss_stop = . ;
-	__ebss = . ;
-	__end = . ;
-	__ramstart = .;
-	}
-        .romfs :	
-	{
-		*(.romfs*)
-	}
-	. = RAMTOP+RAMSIZE;
-        .dummy :
-        {
-	COMMAND_START = . - 0x200 ;
-	__ramend = . ;
-	}
-
-	DISCARDS
-}
diff --git a/arch/h8300/lib/Makefile b/arch/h8300/lib/Makefile
deleted file mode 100644
index 1577f5075b10..000000000000
--- a/arch/h8300/lib/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for H8/300-specific library files..
-#
-
-lib-y  = ashrdi3.o checksum.o memcpy.o memset.o abs.o romfs.o
diff --git a/arch/h8300/lib/abs.S b/arch/h8300/lib/abs.S
deleted file mode 100644
index ddd1fb3d01ad..000000000000
--- a/arch/h8300/lib/abs.S
+++ /dev/null
@@ -1,21 +0,0 @@
-;;; abs.S
-
-#include <asm/linkage.h>
-
-#if defined(__H8300H__) 
-	.h8300h
-#endif
-#if defined(__H8300S__) 
-	.h8300s
-#endif
-	.text
-.global _abs
-
-;;; int abs(int n)
-_abs:
-	mov.l	er0,er0
-	bpl	1f
-	neg.l	er0
-1:
-	rts
-	
diff --git a/arch/h8300/lib/ashrdi3.c b/arch/h8300/lib/ashrdi3.c
deleted file mode 100644
index 78efb65e315a..000000000000
--- a/arch/h8300/lib/ashrdi3.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/* ashrdi3.c extracted from gcc-2.7.2/libgcc2.c which is: */
-/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc.
-
-This file is part of GNU CC.
-
-GNU CC is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2, or (at your option)
-any later version.
-
-GNU CC is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with GNU CC; see the file COPYING.  If not, write to
-the Free Software Foundation, 59 Temple Place - Suite 330,
-Boston, MA 02111-1307, USA.  */
-
-#define BITS_PER_UNIT 8
-
-typedef 	 int SItype	__attribute__ ((mode (SI)));
-typedef unsigned int USItype	__attribute__ ((mode (SI)));
-typedef		 int DItype	__attribute__ ((mode (DI)));
-typedef int word_type __attribute__ ((mode (__word__)));
-
-struct DIstruct {SItype high, low;};
-
-typedef union
-{
-  struct DIstruct s;
-  DItype ll;
-} DIunion;
-
-DItype
-__ashrdi3 (DItype u, word_type b)
-{
-  DIunion w;
-  word_type bm;
-  DIunion uu;
-
-  if (b == 0)
-    return u;
-
-  uu.ll = u;
-
-  bm = (sizeof (SItype) * BITS_PER_UNIT) - b;
-  if (bm <= 0)
-    {
-      /* w.s.high = 1..1 or 0..0 */
-      w.s.high = uu.s.high >> (sizeof (SItype) * BITS_PER_UNIT - 1);
-      w.s.low = uu.s.high >> -bm;
-    }
-  else
-    {
-      USItype carries = (USItype)uu.s.high << bm;
-      w.s.high = uu.s.high >> b;
-      w.s.low = ((USItype)uu.s.low >> b) | carries;
-    }
-
-  return w.ll;
-}
diff --git a/arch/h8300/lib/checksum.c b/arch/h8300/lib/checksum.c
deleted file mode 100644
index bdc5b032acd6..000000000000
--- a/arch/h8300/lib/checksum.c
+++ /dev/null
@@ -1,164 +0,0 @@
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		IP/TCP/UDP checksumming routines
- *
- * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
- *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
- *		Tom May, <ftom@netcom.com>
- *		Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
- *		Lots of code moved from tcp.c and ip.c; see those files
- *		for more names.
- *
- * 03/02/96	Jes Sorensen, Andreas Schwab, Roman Hodek:
- *		Fixed some nasty bugs, causing some horrible crashes.
- *		A: At some points, the sum (%0) was used as
- *		length-counter instead of the length counter
- *		(%1). Thanks to Roman Hodek for pointing this out.
- *		B: GCC seems to mess up if one uses too many
- *		data-registers to hold input values and one tries to
- *		specify d0 and d1 as scratch registers. Letting gcc choose these
- *      registers itself solves the problem.
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- */
- 
-/* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access kills, so most
-   of the assembly has to go. */
-
-#include <net/checksum.h>
-#include <linux/module.h>
-
-static inline unsigned short from32to16(unsigned long x)
-{
-	/* add up 16-bit and 16-bit for 16+c bit */
-	x = (x & 0xffff) + (x >> 16);
-	/* add up carry.. */
-	x = (x & 0xffff) + (x >> 16);
-	return x;
-}
-
-static unsigned long do_csum(const unsigned char * buff, int len)
-{
-	int odd, count;
-	unsigned long result = 0;
-
-	if (len <= 0)
-		goto out;
-	odd = 1 & (unsigned long) buff;
-	if (odd) {
-		result = *buff;
-		len--;
-		buff++;
-	}
-	count = len >> 1;		/* nr of 16-bit words.. */
-	if (count) {
-		if (2 & (unsigned long) buff) {
-			result += *(unsigned short *) buff;
-			count--;
-			len -= 2;
-			buff += 2;
-		}
-		count >>= 1;		/* nr of 32-bit words.. */
-		if (count) {
-		        unsigned long carry = 0;
-			do {
-				unsigned long w = *(unsigned long *) buff;
-				count--;
-				buff += 4;
-				result += carry;
-				result += w;
-				carry = (w > result);
-			} while (count);
-			result += carry;
-			result = (result & 0xffff) + (result >> 16);
-		}
-		if (len & 2) {
-			result += *(unsigned short *) buff;
-			buff += 2;
-		}
-	}
-	if (len & 1)
-		result += (*buff << 8);
-	result = from32to16(result);
-	if (odd)
-		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
-out:
-	return result;
-}
-
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- */
-__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	return (__force __sum16)~do_csum(iph,ihl*4);
-}
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-/*
- * Egads...  That thing apparently assumes that *all* checksums it ever sees will
- * be folded.  Very likely a bug.
- */
-__wsum csum_partial(const void *buff, int len, __wsum sum)
-{
-	unsigned int result = do_csum(buff, len);
-
-	/* add in old sum, and carry.. */
-	result += (__force u32)sum;
-	/* 16+c bits -> 16 bits */
-	result = (result & 0xffff) + (result >> 16);
-	return (__force __wsum)result;
-}
-
-EXPORT_SYMBOL(csum_partial);
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-__sum16 ip_compute_csum(const void *buff, int len)
-{
-	return (__force __sum16)~do_csum(buff,len);
-}
-
-/*
- * copy from fs while checksumming, otherwise like csum_partial
- */
-
-__wsum
-csum_partial_copy_from_user(const void __user *src, void *dst, int len,
-			    __wsum sum, int *csum_err)
-{
-	if (csum_err) *csum_err = 0;
-	memcpy(dst, (__force const void *)src, len);
-	return csum_partial(dst, len, sum);
-}
-
-/*
- * copy from ds while checksumming, otherwise like csum_partial
- */
-
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
diff --git a/arch/h8300/lib/memcpy.S b/arch/h8300/lib/memcpy.S
deleted file mode 100644
index cad325e2c0e8..000000000000
--- a/arch/h8300/lib/memcpy.S
+++ /dev/null
@@ -1,84 +0,0 @@
-;;; memcpy.S
-
-#include <asm/linkage.h>
-
-#if defined(__H8300H__) 
-	.h8300h
-#endif
-#if defined(__H8300S__) 
-	.h8300s
-#endif
-
-	.text
-.global _memcpy
-
-;;; void *memcpy(void *to, void *from, size_t n)
-_memcpy:
-	mov.l	er2,er2
-	bne	1f
-	rts	
-1:	
-	;; address check
-	bld	#0,r0l
-	bxor	#0,r1l
-	bcs	4f
-	mov.l	er4,@-sp
-	mov.l	er0,@-sp
-	btst	#0,r0l
-	beq	1f
-	;; (aligned even) odd address
-	mov.b	@er1,r3l
-	mov.b	r3l,@er0
-	adds	#1,er1
-	adds	#1,er0
-	dec.l	#1,er2
-	beq	3f
-1:	
-	;; n < sizeof(unsigned long) check
-	sub.l	er4,er4
-	adds	#4,er4		; loop count check value
-	cmp.l	er4,er2
-	blo	2f
-	;; unsigned long copy
-1:	
-	mov.l	@er1,er3
-	mov.l	er3,@er0
-	adds	#4,er0
-	adds	#4,er1
-	subs	#4,er2
-	cmp.l	er4,er2
-	bcc	1b	
-	;; rest
-2:	
-	mov.l	er2,er2
-	beq	3f
-1:	
-	mov.b	@er1,r3l
-	mov.b	r3l,@er0
-	adds	#1,er1
-	adds	#1,er0
-	dec.l	#1,er2
-	bne	1b
-3:
-	mov.l	@sp+,er0
-	mov.l	@sp+,er4
-	rts
-
-	;; odd <- even / even <- odd
-4:	
-	mov.l	er4,er3
-	mov.l	er2,er4
-	mov.l	er5,er2
-	mov.l	er1,er5
-	mov.l	er6,er1
-	mov.l	er0,er6
-1:
-	eepmov.w
-	mov.w	r4,r4
-	bne	1b
-	dec.w	#1,e4
-	bpl	1b
-	mov.l	er1,er6
-	mov.l	er2,er5
-	mov.l	er3,er4
-	rts
diff --git a/arch/h8300/lib/memset.S b/arch/h8300/lib/memset.S
deleted file mode 100644
index 4549a64c5b79..000000000000
--- a/arch/h8300/lib/memset.S
+++ /dev/null
@@ -1,61 +0,0 @@
-/* memset.S */
-
-#include <asm/linkage.h>
-
-#if defined(__H8300H__) 
-	.h8300h
-#endif
-#if defined(__H8300S__) 
-	.h8300s
-#endif
-	.text
-
-.global	_memset
-
-;;void *memset(*ptr, int c, size_t count)
-;; ptr = er0
-;; c   = er1(r1l)
-;; count = er2
-_memset:
-	btst	#0,r0l
-	beq	2f
-
-	;; odd address
-1:
-	mov.b	r1l,@er0
-	adds	#1,er0
-	dec.l	#1,er2
-	beq	6f
-
-	;; even address
-2:
-	mov.l	er2,er3
-	cmp.l	#4,er2
-	blo	4f
-	;; count>=4 -> count/4
-#if defined(__H8300H__)
-	shlr.l	er2
-	shlr.l	er2
-#endif
-#if defined(__H8300S__)
-	shlr.l	#2,er2
-#endif
-	;; byte -> long
-	mov.b	r1l,r1h
-	mov.w	r1,e1
-3:
-	mov.l	er1,@er0
-	adds	#4,er0
-	dec.l	#1,er2
-	bne	3b
-4:
-	;; count % 4
-	and.b	#3,r3l
-	beq	6f
-5:
-	mov.b	r1l,@er0
-	adds	#1,er0
-	dec.b	r3l
-	bne	5b
-6:
-	rts
diff --git a/arch/h8300/lib/romfs.S b/arch/h8300/lib/romfs.S
deleted file mode 100644
index 68910d8e1ff4..000000000000
--- a/arch/h8300/lib/romfs.S
+++ /dev/null
@@ -1,57 +0,0 @@
-/* romfs move to __ebss */
-
-#include <asm/linkage.h>
-
-#if defined(__H8300H__) 
-	.h8300h
-#endif
-#if defined(__H8300S__) 
-	.h8300s
-#endif
-
-#define BLKOFFSET 512
-
-	.text
-.globl	__move_romfs
-_romfs_sig_len = 8
-
-__move_romfs:	
-	mov.l	#__sbss,er0
-	mov.l	#_romfs_sig,er1
-	mov.b	#_romfs_sig_len,r3l
-1:					/* check romfs image */
-	mov.b	@er0+,r2l
-	mov.b	@er1+,r2h
-	cmp.b	r2l,r2h
-	bne	2f
-	dec.b	r3l
-	bne	1b
-
-	/* find romfs image */
-	mov.l	@__sbss+8,er0		/* romfs length(be) */
-	mov.l	#__sbss,er1
-	add.l	er0,er1			/* romfs image end */
-	mov.l	#__ebss,er2
-	add.l	er0,er2			/* distination address */
-#if defined(CONFIG_INTELFLASH)
-	add.l	#BLKOFFSET,er2
-#endif
-	adds	#2,er0
-	adds	#1,er0
-	shlr	er0
-	shlr	er0			/* transfer length */
-1:
-	mov.l	@er1,er3		/* copy image */
-	mov.l	er3,@er2
-	subs	#4,er1
-	subs	#4,er2
-	dec.l	#1,er0
-	bpl	1b
-2:
-	rts
-
-	.section	.rodata
-_romfs_sig:	
-	.ascii	"-rom1fs-"
-
-	.end
diff --git a/arch/h8300/mm/Makefile b/arch/h8300/mm/Makefile
deleted file mode 100644
index 5f4bc42b6453..000000000000
--- a/arch/h8300/mm/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux m68k-specific parts of the memory manager.
-#
-
-obj-y	 := init.o fault.o memory.o kmap.o
diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c
deleted file mode 100644
index 472535977006..000000000000
--- a/arch/h8300/mm/fault.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  linux/arch/h8300/mm/fault.c
- *
- *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
- *  Copyright (C) 2000  Lineo, Inc.  (www.lineo.com) 
- *
- *  Based on:
- *
- *  linux/arch/m68knommu/mm/fault.c
- *  linux/arch/m68k/mm/fault.c
- *
- *  Copyright (C) 1995  Hamish Macdonald
- */
-
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-
-#include <asm/pgtable.h>
-
-/*
- * This routine handles page faults.  It determines the problem, and
- * then passes it off to one of the appropriate routines.
- *
- * error_code:
- *	bit 0 == 0 means no page found, 1 means protection fault
- *	bit 1 == 0 means read, 1 means write
- *
- * If this routine detects a bad access, it returns 1, otherwise it
- * returns 0.
- */
-asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
-			      unsigned long error_code)
-{
-#ifdef DEBUG
-	printk ("regs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld\n",
-		regs->sr, regs->pc, address, error_code);
-#endif
-
-/*
- * Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
- */
-	if ((unsigned long) address < PAGE_SIZE) {
-		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
-	} else
-		printk(KERN_ALERT "Unable to handle kernel access");
-	printk(" at virtual address %08lx\n",address);
-	if (!user_mode(regs))
-		die("Oops", regs, error_code);
-	do_exit(SIGKILL);
-
-	return 1;
-}
-
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
deleted file mode 100644
index 6c1251e491af..000000000000
--- a/arch/h8300/mm/init.c
+++ /dev/null
@@ -1,155 +0,0 @@
-/*
- *  linux/arch/h8300/mm/init.c
- *
- *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
- *                      Kenneth Albanowski <kjahds@kjahds.com>,
- *  Copyright (C) 2000  Lineo, Inc.  (www.lineo.com) 
- *
- *  Based on:
- *
- *  linux/arch/m68knommu/mm/init.c
- *  linux/arch/m68k/mm/init.c
- *
- *  Copyright (C) 1995  Hamish Macdonald
- *
- *  JAN/1999 -- hacked to support ColdFire (gerg@snapgear.com)
- *  DEC/2000 -- linux 2.4 support <davidm@snapgear.com>
- */
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/init.h>
-#include <linux/highmem.h>
-#include <linux/pagemap.h>
-#include <linux/bootmem.h>
-#include <linux/gfp.h>
-
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/sections.h>
-
-#undef DEBUG
-
-/*
- * BAD_PAGE is the page that is used for page faults when linux
- * is out-of-memory. Older versions of linux just did a
- * do_exit(), but using this instead means there is less risk
- * for a process dying in kernel mode, possibly leaving a inode
- * unused etc..
- *
- * BAD_PAGETABLE is the accompanying page-table: it is initialized
- * to point to BAD_PAGE entries.
- *
- * ZERO_PAGE is a special page that is used for zero-initialized
- * data and COW.
- */
-static unsigned long empty_bad_page_table;
-
-static unsigned long empty_bad_page;
-
-unsigned long empty_zero_page;
-
-extern unsigned long rom_length;
-
-extern unsigned long memory_start;
-extern unsigned long memory_end;
-
-/*
- * paging_init() continues the virtual memory environment setup which
- * was begun by the code in arch/head.S.
- * The parameters are pointers to where to stick the starting and ending
- * addresses of available kernel virtual memory.
- */
-void __init paging_init(void)
-{
-	/*
-	 * Make sure start_mem is page aligned,  otherwise bootmem and
-	 * page_alloc get different views og the world.
-	 */
-#ifdef DEBUG
-	unsigned long start_mem = PAGE_ALIGN(memory_start);
-#endif
-	unsigned long end_mem   = memory_end & PAGE_MASK;
-
-#ifdef DEBUG
-	printk ("start_mem is %#lx\nvirtual_end is %#lx\n",
-		start_mem, end_mem);
-#endif
-
-	/*
-	 * Initialize the bad page table and bad page to point
-	 * to a couple of allocated pages.
-	 */
-	empty_bad_page_table = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
-	empty_bad_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
-	empty_zero_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
-	memset((void *)empty_zero_page, 0, PAGE_SIZE);
-
-	/*
-	 * Set up SFC/DFC registers (user data space).
-	 */
-	set_fs (USER_DS);
-
-#ifdef DEBUG
-	printk ("before free_area_init\n");
-
-	printk ("free_area_init -> start_mem is %#lx\nvirtual_end is %#lx\n",
-		start_mem, end_mem);
-#endif
-
-	{
-		unsigned long zones_size[MAX_NR_ZONES] = {0, };
-
-		zones_size[ZONE_DMA]     = 0 >> PAGE_SHIFT;
-		zones_size[ZONE_NORMAL]  = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
-#ifdef CONFIG_HIGHMEM
-		zones_size[ZONE_HIGHMEM] = 0;
-#endif
-		free_area_init(zones_size);
-	}
-}
-
-void __init mem_init(void)
-{
-	unsigned long codesize = _etext - _stext;
-
-	pr_devel("Mem_init: start=%lx, end=%lx\n", memory_start, memory_end);
-
-	high_memory = (void *) (memory_end & PAGE_MASK);
-	max_mapnr = MAP_NR(high_memory);
-
-	/* this will put all low memory onto the freelists */
-	free_all_bootmem();
-
-	mem_init_print_info(NULL);
-	if (rom_length > 0 && rom_length > codesize)
-		pr_info("Memory available: %luK/%luK ROM\n",
-			(rom_length - codesize) >> 10, rom_length >> 10);
-}
-
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
-void
-free_initmem(void)
-{
-#ifdef CONFIG_RAMKERNEL
-	free_initmem_default(-1);
-#endif
-}
-
diff --git a/arch/h8300/mm/kmap.c b/arch/h8300/mm/kmap.c
deleted file mode 100644
index f79edcdadf39..000000000000
--- a/arch/h8300/mm/kmap.c
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- *  linux/arch/h8300/mm/kmap.c
- *  
- *  Based on
- *  linux/arch/m68knommu/mm/kmap.c
- *
- *  Copyright (C) 2000 Lineo, <davidm@snapgear.com>
- *  Copyright (C) 2000-2002 David McCullough <davidm@snapgear.com>
- */
-
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm/io.h>
-
-#undef DEBUG
-
-#define VIRT_OFFSET (0x01000000)
-
-/*
- * Map some physical address range into the kernel address space.
- */
-void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag)
-{
-	return (void *)(physaddr + VIRT_OFFSET);
-}
-
-/*
- * Unmap a ioremap()ed region again.
- */
-void iounmap(void *addr)
-{
-}
-
-/*
- * __iounmap unmaps nearly everything, so be careful
- * it doesn't free currently pointer/page tables anymore but it
- * wans't used anyway and might be added later.
- */
-void __iounmap(void *addr, unsigned long size)
-{
-}
-
-/*
- * Set new cache mode for some kernel address space.
- * The caller must push data for that range itself, if such data may already
- * be in the cache.
- */
-void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
-{
-}
diff --git a/arch/h8300/mm/memory.c b/arch/h8300/mm/memory.c
deleted file mode 100644
index 06e364641392..000000000000
--- a/arch/h8300/mm/memory.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- *  linux/arch/h8300/mm/memory.c
- *
- *  Copyright (C) 2002  Yoshinori Sato <ysato@users.sourceforge.jp>,
- *
- *  Based on:
- *
- *  linux/arch/m68knommu/mm/memory.c
- *
- *  Copyright (C) 1998  Kenneth Albanowski <kjahds@kjahds.com>,
- *  Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
- *
- *  Based on:
- *
- *  linux/arch/m68k/mm/memory.c
- *
- *  Copyright (C) 1995  Hamish Macdonald
- */
-
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/setup.h>
-#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/traps.h>
-#include <asm/io.h>
-
-void cache_clear (unsigned long paddr, int len)
-{
-}
-
-
-void cache_push (unsigned long paddr, int len)
-{
-}
-
-void cache_push_v (unsigned long vaddr, int len)
-{
-}
-
-/*
- * Map some physical address range into the kernel address space.
- */
-
-unsigned long kernel_map(unsigned long paddr, unsigned long size,
-			 int nocacheflag, unsigned long *memavailp )
-{
-	return paddr;
-}
-
diff --git a/arch/h8300/platform/h8300h/Makefile b/arch/h8300/platform/h8300h/Makefile
deleted file mode 100644
index 420f73b0d962..000000000000
--- a/arch/h8300/platform/h8300h/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-# Reuse any files we can from the H8/300H
-#
-
-obj-y := irq.o ptrace_h8300h.o
diff --git a/arch/h8300/platform/h8300h/aki3068net/Makefile b/arch/h8300/platform/h8300h/aki3068net/Makefile
deleted file mode 100644
index b7ff78050b7f..000000000000
--- a/arch/h8300/platform/h8300h/aki3068net/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y := crt0_ram.o
diff --git a/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S b/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S
deleted file mode 100644
index b2ad0f2d0417..000000000000
--- a/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8300h/aki3068net/crt0_ram.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	AE-3068 (aka. aki3068net)
- *  Memory Layout     :	RAM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-	
-#if !defined(CONFIG_BLKDEV_RESERVE)
-#if defined(CONFIG_GDB_DEBUG)
-#define RAMEND (__ramend - 0xc000)
-#else
-#define RAMEND __ramend
-#endif
-#else
-#define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS
-#endif
-	
-	.global __start
-	.global _command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300h
-
-	.section .text
-	.file	"crt0_ram.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#RAMEND,sp
-	ldc	#0x80,ccr
-
-	/* Peripheral Setup */
-	
-#if defined(CONFIG_MTD_UCLINUX)
-	/* move romfs image */
-	jsr	@__move_romfs	
-#endif
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	er4
-	shlr	er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#_command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* uClinux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	.byte	0xff,0xff
-	;; P2DDR
-	.byte	0xff,0xff
-	;; P3DDR
-	.byte	0xff,0x00
-	;; P4DDR
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x01,0x01
-	;; P6DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x0c,0x0c
-	;; P9DDR
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x30,0x30
-
-__target_name:	
-	.asciz	"AE-3068"
-	
-	.section .bootvec,"ax"
-	jmp	@__start
diff --git a/arch/h8300/platform/h8300h/generic/Makefile b/arch/h8300/platform/h8300h/generic/Makefile
deleted file mode 100644
index 2b12a170209e..000000000000
--- a/arch/h8300/platform/h8300h/generic/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y :=  crt0_$(MODEL).o
diff --git a/arch/h8300/platform/h8300h/generic/crt0_ram.S b/arch/h8300/platform/h8300h/generic/crt0_ram.S
deleted file mode 100644
index 5ab7d9c12910..000000000000
--- a/arch/h8300/platform/h8300h/generic/crt0_ram.S
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8300h/generic/crt0_ram.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	AE-3068 (aka. aki3068net)
- *  Memory Layout     :	RAM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-	
-#if !defined(CONFIG_BLKDEV_RESERVE)
-#if defined(CONFIG_GDB_DEBUG)
-#define RAMEND (__ramend - 0xc000)
-#else
-#define RAMEND __ramend
-#endif
-#else
-#define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS
-#endif
-	
-	.global __start
-	.global _command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300h
-
-	.section .text
-	.file	"crt0_ram.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#RAMEND,sp
-	ldc	#0x80,ccr
-
-	/* Peripheral Setup */
-	
-#if defined(CONFIG_BLK_DEV_BLKMEM)
-	/* move romfs image */
-	jsr	@__move_romfs	
-#endif
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	er4
-	shlr	er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#_command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* uClinux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x00,0x00
-	;; P4DDR
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; P9DDR
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x00,0x00
-
-__target_name:	
-	.asciz	"generic"
diff --git a/arch/h8300/platform/h8300h/generic/crt0_rom.S b/arch/h8300/platform/h8300h/generic/crt0_rom.S
deleted file mode 100644
index dda1dfa15a5e..000000000000
--- a/arch/h8300/platform/h8300h/generic/crt0_rom.S
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8300h/generic/crt0_rom.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	generic
- *  Memory Layout     :	ROM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-	
-	.global __start
-	.global __command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300h
-	.section .text
-	.file	"crt0_rom.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#__ramend,sp
-	ldc	#0x80,ccr
-
-	/* Peripheral Setup */
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	er4
-	shlr	er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy .data */
-#if !defined(CONFIG_H8300H_SIM)
-	/* copy .data */
-	mov.l	#__begin_data,er5
-	mov.l	#__sdata,er6
-	mov.l	#__edata,er4
-	sub.l	er6,er4
-	shlr.l	er4
-	shlr.l	er4
-1:	
-	mov.l	@er5+,er0
-	mov.l	er0,@er6
-	adds	#4,er6
-	dec.l	#1,er4
-	bne	1b	
-#endif
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#__command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* linux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x00,0x00
-	;; P4DDR
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; P9DDR
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x00,0x00
-
-	.section .rodata
-__target_name:	
-	.asciz	"generic"
-	
-	.section .bss
-__command_line:	
-	.space	512
-
-	/* interrupt vector */
-	.section .vectors,"ax"
-	.long	__start
-vector	=	1
-	.rept	64-1
-	.long	_interrupt_redirect_table+vector*4
-vector	=	vector + 1
-	.endr
diff --git a/arch/h8300/platform/h8300h/h8max/Makefile b/arch/h8300/platform/h8300h/h8max/Makefile
deleted file mode 100644
index b7ff78050b7f..000000000000
--- a/arch/h8300/platform/h8300h/h8max/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y := crt0_ram.o
diff --git a/arch/h8300/platform/h8300h/h8max/crt0_ram.S b/arch/h8300/platform/h8300h/h8max/crt0_ram.S
deleted file mode 100644
index 6a0d4e2d9ec6..000000000000
--- a/arch/h8300/platform/h8300h/h8max/crt0_ram.S
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8300h/h8max/crt0_ram.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	H8MAX
- *  Memory Layout     :	RAM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-	
-#if !defined(CONFIG_BLKDEV_RESERVE)
-#if defined(CONFIG_GDB_DEBUG)
-#define RAMEND (__ramend - 0xc000)
-#else
-#define RAMEND __ramend
-#endif
-#else
-#define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS
-#endif
-	
-	.global __start
-	.global _command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300h
-
-	.section .text
-	.file	"crt0_ram.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#RAMEND,sp
-	ldc	#0x80,ccr
-
-	/* Peripheral Setup */
-	
-#if defined(CONFIG_MTD_UCLINUX)
-	/* move romfs image */
-	jsr	@__move_romfs	
-#endif
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	er4
-	shlr	er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#_command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* uClinux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	.byte	0xff,0xff
-	;; P2DDR
-	.byte	0xff,0xff
-	;; P3DDR
-	.byte	0x00,0x00
-	;; P4DDR
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x01,0x01
-	;; P6DDR
-	.byte	0xf6,0xf6
-	;; dummy
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0xee,0xee
-	;; P9DDR
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x30,0x30
-
-__target_name:	
-	.asciz	"H8MAX"
-	
-	.section .bootvec,"ax"
-	jmp	@__start
diff --git a/arch/h8300/platform/h8300h/irq.c b/arch/h8300/platform/h8300h/irq.c
deleted file mode 100644
index 0a50353e09d5..000000000000
--- a/arch/h8300/platform/h8300h/irq.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * Interrupt handling H8/300H depend.
- * Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- */
-
-#include <linux/init.h>
-#include <linux/errno.h>
-
-#include <asm/ptrace.h>
-#include <asm/traps.h>
-#include <asm/irq.h>
-#include <asm/io.h>
-#include <asm/gpio-internal.h>
-#include <asm/regs306x.h>
-
-const int __initconst h8300_saved_vectors[] = {
-#if defined(CONFIG_GDB_DEBUG)
-	TRAP3_VEC,	/* TRAPA #3 is GDB breakpoint */
-#endif
-	-1,
-};
-
-const h8300_vector __initconst h8300_trap_table[] = {
-	0, 0, 0, 0, 0, 0, 0, 0,
-	system_call,
-	0,
-	0,
-	trace_break,
-};
-
-int h8300_enable_irq_pin(unsigned int irq)
-{
-	int bitmask;
-	if (irq < EXT_IRQ0 || irq > EXT_IRQ5)
-		return 0;
-
-	/* initialize IRQ pin */
-	bitmask = 1 << (irq - EXT_IRQ0);
-	switch(irq) {
-	case EXT_IRQ0:
-	case EXT_IRQ1:
-	case EXT_IRQ2:
-	case EXT_IRQ3:
-		if (H8300_GPIO_RESERVE(H8300_GPIO_P8, bitmask) == 0)
-			return -EBUSY;
-		H8300_GPIO_DDR(H8300_GPIO_P8, bitmask, H8300_GPIO_INPUT);
-		break;
-	case EXT_IRQ4:
-	case EXT_IRQ5:
-		if (H8300_GPIO_RESERVE(H8300_GPIO_P9, bitmask) == 0)
-			return -EBUSY;
-		H8300_GPIO_DDR(H8300_GPIO_P9, bitmask, H8300_GPIO_INPUT);
-		break;
-	}
-
-	return 0;
-}
-
-void h8300_disable_irq_pin(unsigned int irq)
-{
-	int bitmask;
-	if (irq < EXT_IRQ0 || irq > EXT_IRQ5)
-		return;
-
-	/* disable interrupt & release IRQ pin */
-	bitmask = 1 << (irq - EXT_IRQ0);
-	switch(irq) {
-	case EXT_IRQ0:
-	case EXT_IRQ1:
-	case EXT_IRQ2:
-	case EXT_IRQ3:
-		*(volatile unsigned char *)IER &= ~bitmask;
-		H8300_GPIO_FREE(H8300_GPIO_P8, bitmask);
-		break ;
-	case EXT_IRQ4:
-	case EXT_IRQ5:
-		*(volatile unsigned char *)IER &= ~bitmask;
-		H8300_GPIO_FREE(H8300_GPIO_P9, bitmask);
-		break;
-	}
-}
diff --git a/arch/h8300/platform/h8300h/ptrace_h8300h.c b/arch/h8300/platform/h8300h/ptrace_h8300h.c
deleted file mode 100644
index 4f1ed0279633..000000000000
--- a/arch/h8300/platform/h8300h/ptrace_h8300h.c
+++ /dev/null
@@ -1,284 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8300h/ptrace_h8300h.c
- *    ptrace cpu depend helper functions
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of
- * this archive for more details.
- */
-
-#include <linux/linkage.h>
-#include <linux/sched.h>
-#include <asm/ptrace.h>
-
-#define CCR_MASK 0x6f    /* mode/imask not set */
-#define BREAKINST 0x5730 /* trapa #3 */
-
-/* Mapping from PT_xxx to the stack offset at which the register is
-   saved.  Notice that usp has no stack-slot and needs to be treated
-   specially (see get_reg/put_reg below). */
-static const int h8300_register_offset[] = {
-	PT_REG(er1), PT_REG(er2), PT_REG(er3), PT_REG(er4),
-	PT_REG(er5), PT_REG(er6), PT_REG(er0), PT_REG(orig_er0),
-	PT_REG(ccr), PT_REG(pc)
-};
-
-/* read register */
-long h8300_get_reg(struct task_struct *task, int regno)
-{
-	switch (regno) {
-	case PT_USP:
-		return task->thread.usp + sizeof(long)*2;
-	case PT_CCR:
-	    return *(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]);
-	default:
-	    return *(unsigned long *)(task->thread.esp0 + h8300_register_offset[regno]);
-	}
-}
-
-/* write register */
-int h8300_put_reg(struct task_struct *task, int regno, unsigned long data)
-{
-	unsigned short oldccr;
-	switch (regno) {
-	case PT_USP:
-		task->thread.usp = data - sizeof(long)*2;
-	case PT_CCR:
-		oldccr = *(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]);
-		oldccr &= ~CCR_MASK;
-		data &= CCR_MASK;
-		data |= oldccr;
-		*(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]) = data;
-		break;
-	default:
-		*(unsigned long *)(task->thread.esp0 + h8300_register_offset[regno]) = data;
-		break;
-	}
-	return 0;
-}
-
-/* disable singlestep */
-void user_disable_single_step(struct task_struct *child)
-{
-	if((long)child->thread.breakinfo.addr != -1L) {
-		*child->thread.breakinfo.addr = child->thread.breakinfo.inst;
-		child->thread.breakinfo.addr = (unsigned short *)-1L;
-	}
-}
-
-/* calculate next pc */
-enum jump_type {none,    /* normal instruction */
-		jabs,    /* absolute address jump */
-		ind,     /* indirect address jump */
-		ret,     /* return to subrutine */
-		reg,     /* register indexed jump */
-		relb,    /* pc relative jump (byte offset) */
-		relw,    /* pc relative jump (word offset) */
-               };
-
-/* opcode decode table define
-   ptn: opcode pattern
-   msk: opcode bitmask
-   len: instruction length (<0 next table index)
-   jmp: jump operation mode */
-struct optable {
-	unsigned char bitpattern;
-	unsigned char bitmask;
-	signed char length;
-	signed char type;
-} __attribute__((aligned(1),packed));
-
-#define OPTABLE(ptn,msk,len,jmp)   \
-        {                          \
-		.bitpattern = ptn, \
-		.bitmask    = msk, \
-		.length	    = len, \
-		.type       = jmp, \
-	}
-
-static const struct optable optable_0[] = {
-	OPTABLE(0x00,0xff, 1,none), /* 0x00 */
-	OPTABLE(0x01,0xff,-1,none), /* 0x01 */
-	OPTABLE(0x02,0xfe, 1,none), /* 0x02-0x03 */
-	OPTABLE(0x04,0xee, 1,none), /* 0x04-0x05/0x14-0x15 */
-	OPTABLE(0x06,0xfe, 1,none), /* 0x06-0x07 */
-	OPTABLE(0x08,0xea, 1,none), /* 0x08-0x09/0x0c-0x0d/0x18-0x19/0x1c-0x1d */
-	OPTABLE(0x0a,0xee, 1,none), /* 0x0a-0x0b/0x1a-0x1b */
-	OPTABLE(0x0e,0xee, 1,none), /* 0x0e-0x0f/0x1e-0x1f */
-	OPTABLE(0x10,0xfc, 1,none), /* 0x10-0x13 */
-	OPTABLE(0x16,0xfe, 1,none), /* 0x16-0x17 */
-	OPTABLE(0x20,0xe0, 1,none), /* 0x20-0x3f */
-	OPTABLE(0x40,0xf0, 1,relb), /* 0x40-0x4f */
-	OPTABLE(0x50,0xfc, 1,none), /* 0x50-0x53 */
-	OPTABLE(0x54,0xfd, 1,ret ), /* 0x54/0x56 */
-	OPTABLE(0x55,0xff, 1,relb), /* 0x55 */
-	OPTABLE(0x57,0xff, 1,none), /* 0x57 */
-	OPTABLE(0x58,0xfb, 2,relw), /* 0x58/0x5c */
-	OPTABLE(0x59,0xfb, 1,reg ), /* 0x59/0x5b */
-	OPTABLE(0x5a,0xfb, 2,jabs), /* 0x5a/0x5e */
-	OPTABLE(0x5b,0xfb, 2,ind ), /* 0x5b/0x5f */
-	OPTABLE(0x60,0xe8, 1,none), /* 0x60-0x67/0x70-0x77 */
-	OPTABLE(0x68,0xfa, 1,none), /* 0x68-0x69/0x6c-0x6d */
-	OPTABLE(0x6a,0xfe,-2,none), /* 0x6a-0x6b */
-	OPTABLE(0x6e,0xfe, 2,none), /* 0x6e-0x6f */
-	OPTABLE(0x78,0xff, 4,none), /* 0x78 */
-	OPTABLE(0x79,0xff, 2,none), /* 0x79 */
-	OPTABLE(0x7a,0xff, 3,none), /* 0x7a */
-	OPTABLE(0x7b,0xff, 2,none), /* 0x7b */
-	OPTABLE(0x7c,0xfc, 2,none), /* 0x7c-0x7f */
-	OPTABLE(0x80,0x80, 1,none), /* 0x80-0xff */
-};
-
-static const struct optable optable_1[] = {
-	OPTABLE(0x00,0xff,-3,none), /* 0x0100 */
-	OPTABLE(0x40,0xf0,-3,none), /* 0x0140-0x14f */
-	OPTABLE(0x80,0xf0, 1,none), /* 0x0180-0x018f */
-	OPTABLE(0xc0,0xc0, 2,none), /* 0x01c0-0x01ff */
-};
-
-static const struct optable optable_2[] = {
-	OPTABLE(0x00,0x20, 2,none), /* 0x6a0?/0x6a8?/0x6b0?/0x6b8? */
-	OPTABLE(0x20,0x20, 3,none), /* 0x6a2?/0x6aa?/0x6b2?/0x6ba? */
-};
-
-static const struct optable optable_3[] = {
-	OPTABLE(0x69,0xfb, 2,none), /* 0x010069/0x01006d/014069/0x01406d */
-	OPTABLE(0x6b,0xff,-4,none), /* 0x01006b/0x01406b */
-	OPTABLE(0x6f,0xff, 3,none), /* 0x01006f/0x01406f */
-	OPTABLE(0x78,0xff, 5,none), /* 0x010078/0x014078 */
-};
-
-static const struct optable optable_4[] = {
-	OPTABLE(0x00,0x78, 3,none), /* 0x0100690?/0x01006d0?/0140690/0x01406d0?/0x0100698?/0x01006d8?/0140698?/0x01406d8? */
-	OPTABLE(0x20,0x78, 4,none), /* 0x0100692?/0x01006d2?/0140692/0x01406d2?/0x010069a?/0x01006da?/014069a?/0x01406da? */
-};
-
-static const struct optables_list {
-	const struct optable *ptr;
-	int size;
-} optables[] = {
-#define OPTABLES(no)                                                   \
-        {                                                              \
-		.ptr  = optable_##no,                                  \
-		.size = sizeof(optable_##no) / sizeof(struct optable), \
-	}
-	OPTABLES(0),
-	OPTABLES(1),
-	OPTABLES(2),
-	OPTABLES(3),
-	OPTABLES(4),
-
-};
-
-const unsigned char condmask[] = {
-	0x00,0x40,0x01,0x04,0x02,0x08,0x10,0x20
-};
-
-static int isbranch(struct task_struct *task,int reson)
-{
-	unsigned char cond = h8300_get_reg(task, PT_CCR);
-	/* encode complex conditions */
-	/* B4: N^V
-	   B5: Z|(N^V)
-	   B6: C|Z */
-	__asm__("bld #3,%w0\n\t"
-		"bxor #1,%w0\n\t"
-		"bst #4,%w0\n\t"
-		"bor #2,%w0\n\t"
-		"bst #5,%w0\n\t"
-		"bld #2,%w0\n\t"
-		"bor #0,%w0\n\t"
-		"bst #6,%w0\n\t"
-		:"=&r"(cond)::"cc");
-	cond &= condmask[reson >> 1];
-	if (!(reson & 1))
-		return cond == 0;
-	else
-		return cond != 0;
-}
-
-static unsigned short *getnextpc(struct task_struct *child, unsigned short *pc)
-{
-	const struct optable *op;
-	unsigned char *fetch_p;
-	unsigned char inst;
-	unsigned long addr;
-	unsigned long *sp;
-	int op_len,regno;
-	op = optables[0].ptr;
-	op_len = optables[0].size;
-	fetch_p = (unsigned char *)pc;
-	inst = *fetch_p++;
-	do {
-		if ((inst & op->bitmask) == op->bitpattern) {
-			if (op->length < 0) {
-				op = optables[-op->length].ptr;
-				op_len = optables[-op->length].size + 1;
-				inst = *fetch_p++;
-			} else {
-				switch (op->type) {
-				case none:
-					return pc + op->length;
-				case jabs:
-					addr = *(unsigned long *)pc;
-					return (unsigned short *)(addr & 0x00ffffff);
-				case ind:
-					addr = *pc & 0xff;
-					return (unsigned short *)(*(unsigned long *)addr);
-				case ret:
-					sp = (unsigned long *)h8300_get_reg(child, PT_USP);
-					/* user stack frames
-					   |   er0  | temporary saved
-					   +--------+
-					   |   exp  | exception stack frames
-					   +--------+
-					   | ret pc | userspace return address
-					*/
-					return (unsigned short *)(*(sp+2) & 0x00ffffff);
-				case reg:
-					regno = (*pc >> 4) & 0x07;
-					if (regno == 0)
-						addr = h8300_get_reg(child, PT_ER0);
-					else
-						addr = h8300_get_reg(child, regno-1+PT_ER1);
-					return (unsigned short *)addr;
-				case relb:
-					if (inst == 0x55 || isbranch(child,inst & 0x0f))
-						pc = (unsigned short *)((unsigned long)pc +
-								       ((signed char)(*fetch_p)));
-					return pc+1; /* skip myself */
-				case relw:
-					if (inst == 0x5c || isbranch(child,(*fetch_p & 0xf0) >> 4))
-						pc = (unsigned short *)((unsigned long)pc +
-								       ((signed short)(*(pc+1))));
-					return pc+2; /* skip myself */
-				}
-			}
-		} else
-			op++;
-	} while(--op_len > 0);
-	return NULL;
-}
-
-/* Set breakpoint(s) to simulate a single step from the current PC.  */
-
-void user_enable_single_step(struct task_struct *child)
-{
-	unsigned short *nextpc;
-	nextpc = getnextpc(child,(unsigned short *)h8300_get_reg(child, PT_PC));
-	child->thread.breakinfo.addr = nextpc;
-	child->thread.breakinfo.inst = *nextpc;
-	*nextpc = BREAKINST;
-}
-
-asmlinkage void trace_trap(unsigned long bp)
-{
-	if ((unsigned long)current->thread.breakinfo.addr == bp) {
-		user_disable_single_step(current);
-		force_sig(SIGTRAP,current);
-	} else
-	        force_sig(SIGILL,current);
-}
-
diff --git a/arch/h8300/platform/h8s/Makefile b/arch/h8300/platform/h8s/Makefile
deleted file mode 100644
index bf1241883766..000000000000
--- a/arch/h8300/platform/h8s/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-# Reuse any files we can from the H8S
-#
-
-obj-y := ints_h8s.o ptrace_h8s.o
diff --git a/arch/h8300/platform/h8s/edosk2674/Makefile b/arch/h8300/platform/h8s/edosk2674/Makefile
deleted file mode 100644
index 8e349723bb4f..000000000000
--- a/arch/h8300/platform/h8s/edosk2674/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y := crt0_$(MODEL).o
diff --git a/arch/h8300/platform/h8s/edosk2674/crt0_ram.S b/arch/h8300/platform/h8s/edosk2674/crt0_ram.S
deleted file mode 100644
index 5ed191b37cde..000000000000
--- a/arch/h8300/platform/h8s/edosk2674/crt0_ram.S
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8s/edosk2674/crt0_ram.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	EDOSK-2674
- *  Memory Layout     :	RAM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-#include <asm/regs267x.h>
-			
-#if !defined(CONFIG_BLKDEV_RESERVE)
-#if defined(CONFIG_GDB_DEBUG)
-#define RAMEND (__ramend - 0xc000)
-#else
-#define RAMEND __ramend
-#endif
-#else
-#define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS
-#endif
-	
-	.global __start
-	.global __command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300s
-
-	.section .text
-	.file	"crt0_ram.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#RAMEND,sp
-	ldc	#0x80,ccr
-	ldc	#0x00,exr
-
-	/* Peripheral Setup */
-	bclr	#4,@INTCR:8	/* interrupt mode 2 */
-	bset	#5,@INTCR:8
-	bclr	#0,@IER+1:16
-	bset	#1,@ISCRL+1:16	/* IRQ0 Positive Edge */
-	bclr	#0,@ISCRL+1:16
-
-#if defined(CONFIG_MTD_UCLINUX)
-	/* move romfs image */
-	jsr	@__move_romfs	
-#endif
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	er5,er6
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	#2,er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#_command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* uClinux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	;;      used,ddr
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x3f,0x3a
-	;; dummy
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; P7DDR
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0xff,0xff
-	;; PBDDR
-	.byte	0xff,0x00
-	;; PCDDR
-	.byte	0xff,0x00
-	;; PDDDR
-	.byte	0xff,0x00
-	;; PEDDR
-	.byte	0xff,0x00
-	;; PFDDR
-	.byte	0xff,0xff
-	;; PGDDR
-	.byte	0x0f,0x0f
-	;; PHDDR
-	.byte	0x0f,0x0f
-
-__target_name:	
-	.asciz	"EDOSK-2674"
-	
-	.section .bootvec,"ax"
-	jmp	@__start
diff --git a/arch/h8300/platform/h8s/edosk2674/crt0_rom.S b/arch/h8300/platform/h8s/edosk2674/crt0_rom.S
deleted file mode 100644
index 06d1d7f324ca..000000000000
--- a/arch/h8300/platform/h8s/edosk2674/crt0_rom.S
+++ /dev/null
@@ -1,186 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8s/edosk2674/crt0_rom.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	EDOSK-2674
- *  Memory Layout     :	ROM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-#include <asm/regs267x.h>
-		
-	.global __start
-	.global __command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300s
-	.section .text
-	.file	"crt0_rom.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#__ramend,sp
-	ldc	#0x80,ccr
-	ldc	#0,exr
-	
-	/* Peripheral Setup */
-;BSC/GPIO setup
-	mov.l	#init_regs,er0
-	mov.w	#0xffff,e2
-1:
-	mov.w	@er0+,r2
-	beq	2f
-	mov.w	@er0+,r1
-	mov.b	r1l,@er2
-	bra	1b
-
-2:
-;SDRAM setup
-#define SDRAM_SMR 0x400040
-
-	mov.b	#0,r0l
-	mov.b	r0l,@DRACCR:16
-	mov.w	#0x188,r0
-	mov.w	r0,@REFCR:16
-	mov.w	#0x85b4,r0
-	mov.w	r0,@DRAMCR:16
-	mov.b	#0,r1l
-	mov.b	r1l,@SDRAM_SMR
-	mov.w	#0x84b4,r0
-	mov.w	r0,@DRAMCR:16
-;special thanks to Arizona Cooperative Power
-	
-	/* copy .data */
-	mov.l	#__begin_data,er5
-	mov.l	#__sdata,er6
-	mov.l	#__edata,er4
-	sub.l	er6,er4
-	shlr.l	#2,er4
-1:	
-	mov.l	@er5+,er0
-	mov.l	er0,@er6
-	adds	#4,er6
-	dec.l	#1,er4
-	bne	1b	
-
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr.l	#2,er4		
-	sub.l	er0,er0
-1:
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#__command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* linux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-#define INIT_REGS_DATA(REGS,DATA) \
-	.word	((REGS) & 0xffff),DATA
-
-init_regs:
-INIT_REGS_DATA(ASTCR,0xff)
-INIT_REGS_DATA(RDNCR,0x00)
-INIT_REGS_DATA(ABWCR,0x80)
-INIT_REGS_DATA(WTCRAH,0x27)
-INIT_REGS_DATA(WTCRAL,0x77)
-INIT_REGS_DATA(WTCRBH,0x71)
-INIT_REGS_DATA(WTCRBL,0x22)
-INIT_REGS_DATA(CSACRH,0x80)
-INIT_REGS_DATA(CSACRL,0x80)
-INIT_REGS_DATA(BROMCRH,0xa0)
-INIT_REGS_DATA(BROMCRL,0xa0)
-INIT_REGS_DATA(P3DDR,0x3a)
-INIT_REGS_DATA(P3ODR,0x06)
-INIT_REGS_DATA(PADDR,0xff)
-INIT_REGS_DATA(PFDDR,0xfe)
-INIT_REGS_DATA(PGDDR,0x0f)
-INIT_REGS_DATA(PHDDR,0x0f)
-INIT_REGS_DATA(PFCR0,0xff)
-INIT_REGS_DATA(PFCR2,0x0d)
-INIT_REGS_DATA(ITSR, 0x00)
-INIT_REGS_DATA(ITSR+1,0x3f)
-INIT_REGS_DATA(INTCR,0x20)
-		
-	.word	0
-
-gpio_table:
-	;; P1DDR
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; P7DDR
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x00,0x00
-	;; PCDDR
-	.byte	0x00,0x00
-	;; PDDDR
-	.byte	0x00,0x00
-	;; PEDDR
-	.byte	0x00,0x00
-	;; PFDDR
-	.byte	0x00,0x00
-	;; PGDDR
-	.byte	0x00,0x00
-	;; PHDDR
-	.byte	0x00,0x00
-
-	.section .rodata
-__target_name:	
-	.asciz	"EDOSK-2674"
-	
-	.section .bss
-__command_line:	
-	.space	512
-
-	/* interrupt vector */
-	.section .vectors,"ax"
-	.long	__start
-	.long	__start
-vector	=	2
-	.rept	126
-	.long	_interrupt_redirect_table+vector*4
-vector	=	vector + 1
-	.endr
diff --git a/arch/h8300/platform/h8s/generic/Makefile b/arch/h8300/platform/h8s/generic/Makefile
deleted file mode 100644
index 44b4685c664c..000000000000
--- a/arch/h8300/platform/h8s/generic/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-extra-y =  crt0_$(MODEL).o
diff --git a/arch/h8300/platform/h8s/generic/crt0_ram.S b/arch/h8300/platform/h8s/generic/crt0_ram.S
deleted file mode 100644
index 7018915de74f..000000000000
--- a/arch/h8300/platform/h8s/generic/crt0_ram.S
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8s/edosk2674/crt0_ram.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup
- *  Target Archtecture:	generic
- *  Memory Layout     :	RAM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-#include <asm/regs267x.h>
-			
-#if !defined(CONFIG_BLKDEV_RESERVE)
-#if defined(CONFIG_GDB_DEBUG)
-#define RAMEND (__ramend - 0xc000)
-#else
-#define RAMEND __ramend
-#endif
-#else
-#define RAMEND CONFIG_BLKDEV_RESERVE_ADDRESS
-#endif
-	
-	.global __start
-	.global __command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300s
-
-	.section .text
-	.file	"crt0_ram.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#RAMEND,sp
-	ldc	#0x80,ccr
-	ldc	#0x00,exr
-
-	/* Peripheral Setup */
-	bclr	#4,@INTCR:8	/* interrupt mode 2 */
-	bset	#5,@INTCR:8
-
-#if defined(CONFIG_MTD_UCLINUX)
-	/* move romfs image */
-	jsr	@__move_romfs	
-#endif
-	
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	er5,er6
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr	#2,er4
-	sub.l	er0,er0
-1:	
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* copy kernel commandline */
-	mov.l	#COMMAND_START,er5
-	mov.l	#_command_line,er6
-	mov.w	#512,r4
-	eepmov.w
-
-	/* uClinux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	;;      used,ddr
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; P7DDR
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x00,0x00
-	;; PCDDR
-	.byte	0x00,0x00
-	;; PDDDR
-	.byte	0x00,0x00
-	;; PEDDR
-	.byte	0x00,0x00
-	;; PFDDR
-	.byte	0x00,0x00
-	;; PGDDR
-	.byte	0x00,0x00
-	;; PHDDR
-	.byte	0x00,0x00
-
-__target_name:	
-	.asciz	"generic"
-	
-	.section .bootvec,"ax"
-	jmp	@__start
diff --git a/arch/h8300/platform/h8s/generic/crt0_rom.S b/arch/h8300/platform/h8s/generic/crt0_rom.S
deleted file mode 100644
index 623ba7828193..000000000000
--- a/arch/h8300/platform/h8s/generic/crt0_rom.S
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8s/generic/crt0_rom.S
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- *  Platform depend startup 
- *  Target Archtecture:	generic
- *  Memory Layout     :	ROM
- */
-
-#define ASSEMBLY
-
-#include <asm/linkage.h>
-#include <asm/regs267x.h>
-	
-	.global __start
-	.global __command_line
-	.global __platform_gpio_table
-	.global __target_name
-	
-	.h8300s
-	.section .text
-	.file	"crt0_rom.S"
-
-	/* CPU Reset entry */
-__start:
-	mov.l	#__ramend,sp
-	ldc	#0x80,ccr
-	ldc	#0,exr
-	bclr	#4,@INTCR:8
-	bset	#5,@INTCR:8	/* Interrupt mode 2 */
-	
-	/* Peripheral Setup */
-	
-	/* copy .data */
-#if !defined(CONFIG_H8S_SIM)
-	mov.l	#__begin_data,er5
-	mov.l	#__sdata,er6
-	mov.l	#__edata,er4
-	sub.l	er6,er4
-	shlr.l	#2,er4
-1:	
-	mov.l	@er5+,er0
-	mov.l	er0,@er6
-	adds	#4,er6
-	dec.l	#1,er4
-	bne	1b	
-#endif
-
-	/* .bss clear */
-	mov.l	#__sbss,er5
-	mov.l	#__ebss,er4
-	sub.l	er5,er4
-	shlr.l	#2,er4		
-	sub.l	er0,er0
-1:
-	mov.l	er0,@er5
-	adds	#4,er5
-	dec.l	#1,er4
-	bne	1b
-
-	/* linux kernel start */
-	ldc	#0x90,ccr	/* running kernel */
-	mov.l	#_init_thread_union,sp
-	add.l	#0x2000,sp
-	jsr	@_start_kernel
-_exit:
-
-	jmp	_exit
-
-	rts
-
-	/* I/O port assign information */
-__platform_gpio_table:	
-	mov.l	#gpio_table,er0
-	rts
-
-gpio_table:
-	;; P1DDR
-	.byte	0x00,0x00
-	;; P2DDR
-	.byte	0x00,0x00
-	;; P3DDR
-	.byte	0x00,0x00
-	;; P4DDR
-	.byte	0x00,0x00
-	;; P5DDR
-	.byte	0x00,0x00
-	;; P6DDR
-	.byte	0x00,0x00
-	;; dummy
-	.byte	0x00,0x00
-	;; P8DDR
-	.byte	0x00,0x00
-	;; PADDR
-	.byte	0x00,0x00
-	;; PBDDR
-	.byte	0x00,0x00
-	;; PCDDR
-	.byte	0x00,0x00
-	;; PDDDR
-	.byte	0x00,0x00
-	;; PEDDR
-	.byte	0x00,0x00
-	;; PFDDR
-	.byte	0x00,0x00
-	;; PGDDR
-	.byte	0x00,0x00
-	;; PHDDR
-	.byte	0x00,0x00
-
-	.section .rodata
-__target_name:	
-	.asciz	"generic"
-	
-	.section .bss
-__command_line:	
-	.space	512
-
-	/* interrupt vector */
-	.section .vectors,"ax"
-	.long	__start
-	.long	__start
-vector	=	2
-	.rept	126-1
-	.long	_interrupt_redirect_table+vector*4
-vector	=	vector + 1
-	.endr
diff --git a/arch/h8300/platform/h8s/irq.c b/arch/h8300/platform/h8s/irq.c
deleted file mode 100644
index f3a5511c16b1..000000000000
--- a/arch/h8300/platform/h8s/irq.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * linux/arch/h8300/platform/h8s/ints_h8s.c
- * Interrupt handling CPU variants
- *
- * Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- */
-
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-
-#include <asm/ptrace.h>
-#include <asm/traps.h>
-#include <asm/irq.h>
-#include <asm/io.h>
-#include <asm/gpio-internal.h>
-#include <asm/regs267x.h>
-
-/* saved vector list */
-const int __initconst h8300_saved_vectors[] = {
-#if defined(CONFIG_GDB_DEBUG)
-	TRACE_VEC,
-	TRAP3_VEC,
-#endif
-	-1
-};
-
-/* trap entry table */
-const H8300_VECTOR __initconst h8300_trap_table[] = {
-	0,0,0,0,0,
-	trace_break,  /* TRACE */
-	0,0,
-	system_call,  /* TRAPA #0 */
-	0,0,0,0,0,0,0
-};
-
-/* IRQ pin assignment */
-struct irq_pins {
-	unsigned char port_no;
-	unsigned char bit_no;
-} __attribute__((aligned(1),packed));
-/* ISTR = 0 */
-static const struct irq_pins irq_assign_table0[16]={
-        {H8300_GPIO_P5,H8300_GPIO_B0},{H8300_GPIO_P5,H8300_GPIO_B1},
-	{H8300_GPIO_P5,H8300_GPIO_B2},{H8300_GPIO_P5,H8300_GPIO_B3},
-	{H8300_GPIO_P5,H8300_GPIO_B4},{H8300_GPIO_P5,H8300_GPIO_B5},
-	{H8300_GPIO_P5,H8300_GPIO_B6},{H8300_GPIO_P5,H8300_GPIO_B7},
-	{H8300_GPIO_P6,H8300_GPIO_B0},{H8300_GPIO_P6,H8300_GPIO_B1},
-	{H8300_GPIO_P6,H8300_GPIO_B2},{H8300_GPIO_P6,H8300_GPIO_B3},
-	{H8300_GPIO_P6,H8300_GPIO_B4},{H8300_GPIO_P6,H8300_GPIO_B5},
-	{H8300_GPIO_PF,H8300_GPIO_B1},{H8300_GPIO_PF,H8300_GPIO_B2},
-};
-/* ISTR = 1 */
-static const struct irq_pins irq_assign_table1[16]={
-	{H8300_GPIO_P8,H8300_GPIO_B0},{H8300_GPIO_P8,H8300_GPIO_B1},
-	{H8300_GPIO_P8,H8300_GPIO_B2},{H8300_GPIO_P8,H8300_GPIO_B3},
-	{H8300_GPIO_P8,H8300_GPIO_B4},{H8300_GPIO_P8,H8300_GPIO_B5},
-	{H8300_GPIO_PH,H8300_GPIO_B2},{H8300_GPIO_PH,H8300_GPIO_B3},
-	{H8300_GPIO_P2,H8300_GPIO_B0},{H8300_GPIO_P2,H8300_GPIO_B1},
-	{H8300_GPIO_P2,H8300_GPIO_B2},{H8300_GPIO_P2,H8300_GPIO_B3},
-	{H8300_GPIO_P2,H8300_GPIO_B4},{H8300_GPIO_P2,H8300_GPIO_B5},
-	{H8300_GPIO_P2,H8300_GPIO_B6},{H8300_GPIO_P2,H8300_GPIO_B7},
-};
-
-/* IRQ to GPIO pin translation */
-#define IRQ_GPIO_MAP(irqbit,irq,port,bit)			  \
-do {								  \
-	if (*(volatile unsigned short *)ITSR & irqbit) {	  \
-		port = irq_assign_table1[irq - EXT_IRQ0].port_no; \
-		bit  = irq_assign_table1[irq - EXT_IRQ0].bit_no;  \
-	} else {						  \
-		port = irq_assign_table0[irq - EXT_IRQ0].port_no; \
-		bit  = irq_assign_table0[irq - EXT_IRQ0].bit_no;  \
-	}							  \
-} while(0)
-
-int h8300_enable_irq_pin(unsigned int irq)
-{
-	if (irq >= EXT_IRQ0 && irq <= EXT_IRQ15) {
-		unsigned short ptn = 1 << (irq - EXT_IRQ0);
-		unsigned int port_no,bit_no;
-		IRQ_GPIO_MAP(ptn, irq, port_no, bit_no);
-		if (H8300_GPIO_RESERVE(port_no, bit_no) == 0)
-			return -EBUSY;                   /* pin already use */
-		H8300_GPIO_DDR(port_no, bit_no, H8300_GPIO_INPUT);
-		*(volatile unsigned short *)ISR &= ~ptn; /* ISR clear */
-	}
-
-	return 0;
-}
-
-void h8300_disable_irq_pin(unsigned int irq)
-{
-	if (irq >= EXT_IRQ0 && irq <= EXT_IRQ15) {
-		/* disable interrupt & release IRQ pin */
-		unsigned short ptn = 1 << (irq - EXT_IRQ0);
-		unsigned short port_no,bit_no;
-		*(volatile unsigned short *)ISR &= ~ptn;
-		*(volatile unsigned short *)IER &= ~ptn;
-		IRQ_GPIO_MAP(ptn, irq, port_no, bit_no);
-		H8300_GPIO_FREE(port_no, bit_no);
-	}
-}
diff --git a/arch/h8300/platform/h8s/ptrace_h8s.c b/arch/h8300/platform/h8s/ptrace_h8s.c
deleted file mode 100644
index c058ab1a8495..000000000000
--- a/arch/h8300/platform/h8s/ptrace_h8s.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- *  linux/arch/h8300/platform/h8s/ptrace_h8s.c
- *    ptrace cpu depend helper functions
- *
- *  Yoshinori Sato <ysato@users.sourceforge.jp>
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of
- * this archive for more details.
- */
-
-#include <linux/linkage.h>
-#include <linux/sched.h>
-#include <linux/errno.h>
-#include <asm/ptrace.h>
-
-#define CCR_MASK  0x6f
-#define EXR_TRACE 0x80
-
-/* Mapping from PT_xxx to the stack offset at which the register is
-   saved.  Notice that usp has no stack-slot and needs to be treated
-   specially (see get_reg/put_reg below). */
-static const int h8300_register_offset[] = {
-	PT_REG(er1), PT_REG(er2), PT_REG(er3), PT_REG(er4),
-	PT_REG(er5), PT_REG(er6), PT_REG(er0), PT_REG(orig_er0),
-	PT_REG(ccr), PT_REG(pc),  0,           PT_REG(exr)
-};
-
-/* read register */
-long h8300_get_reg(struct task_struct *task, int regno)
-{
-	switch (regno) {
-	case PT_USP:
-		return task->thread.usp + sizeof(long)*2 + 2;
-	case PT_CCR:
-	case PT_EXR:
-	    return *(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]);
-	default:
-	    return *(unsigned long *)(task->thread.esp0 + h8300_register_offset[regno]);
-	}
-}
-
-/* write register */
-int h8300_put_reg(struct task_struct *task, int regno, unsigned long data)
-{
-	unsigned short oldccr;
-	switch (regno) {
-	case PT_USP:
-		task->thread.usp = data - sizeof(long)*2 - 2;
-	case PT_CCR:
-		oldccr = *(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]);
-		oldccr &= ~CCR_MASK;
-		data &= CCR_MASK;
-		data |= oldccr;
-		*(unsigned short *)(task->thread.esp0 + h8300_register_offset[regno]) = data;
-		break;
-	case PT_EXR:
-		/* exr modify not support */
-		return -EIO;
-	default:
-		*(unsigned long *)(task->thread.esp0 + h8300_register_offset[regno]) = data;
-		break;
-	}
-	return 0;
-}
-
-/* disable singlestep */
-void user_disable_single_step(struct task_struct *child)
-{
-	*(unsigned short *)(child->thread.esp0 + h8300_register_offset[PT_EXR]) &= ~EXR_TRACE;
-}
-
-/* enable singlestep */
-void user_enable_single_step(struct task_struct *child)
-{
-	*(unsigned short *)(child->thread.esp0 + h8300_register_offset[PT_EXR]) |= EXR_TRACE;
-}
-
-asmlinkage void trace_trap(unsigned long bp)
-{
-	(void)bp;
-	force_sig(SIGTRAP,current);
-}
-
diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h
index d34049712a4d..50fe651da965 100644
--- a/include/linux/serial_sci.h
+++ b/include/linux/serial_sci.h
@@ -5,7 +5,7 @@
 #include <linux/sh_dma.h>
 
 /*
- * Generic header for SuperH (H)SCI(F) (used by sh/sh64/h8300 and related parts)
+ * Generic header for SuperH (H)SCI(F) (used by sh/sh64 and related parts)
  */
 
 #define SCIx_NOT_SUPPORTED	(-1)
diff --git a/tools/testing/ktest/examples/crosstests.conf b/tools/testing/ktest/examples/crosstests.conf
index 46736604c26c..a1203148dfa1 100644
--- a/tools/testing/ktest/examples/crosstests.conf
+++ b/tools/testing/ktest/examples/crosstests.conf
@@ -133,12 +133,6 @@ CROSS = frv-linux
 ARCH = frv
 GCC_VER = 4.5.1
 
-# h8300 - failed make defconfig??
-TEST_START IF ${RUN} == h8300 || ${DO_FAILED}
-CROSS = h8300-elf
-ARCH = h8300
-GCC_VER = 4.5.1
-
 # m68k fails with error?
 TEST_START IF ${RUN} == m68k || ${DO_DEFAULT}
 CROSS = m68k-linux
-- 
cgit 


From 6f6f467eaaa0ac4fb77714d0172d65c781dabb8c Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 30 Aug 2013 06:12:40 -0700
Subject: Drop remaining references to H8/300 architecture

With the architecture gone, any references to it are no longer needed.

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 include/uapi/linux/audit.h  | 1 -
 include/uapi/linux/elf-em.h | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 75cef3fd97ad..db0b825b4810 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -329,7 +329,6 @@ enum {
 #define AUDIT_ARCH_ARMEB	(EM_ARM)
 #define AUDIT_ARCH_CRIS		(EM_CRIS|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_FRV		(EM_FRV)
-#define AUDIT_ARCH_H8300	(EM_H8_300)
 #define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_IA64		(EM_IA_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_M32R		(EM_M32R)
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 59c17a2d38ad..01529bd96438 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -31,7 +31,6 @@
 #define EM_CRIS		76	/* Axis Communications 32-bit embedded processor */
 #define EM_V850		87	/* NEC v850 */
 #define EM_M32R		88	/* Renesas M32R */
-#define EM_H8_300	46	/* Renesas H8/300,300H,H8S */
 #define EM_MN10300	89	/* Panasonic/MEI MN10300, AM33 */
 #define EM_BLACKFIN     106     /* ADI Blackfin Processor */
 #define EM_TI_C6000	140	/* TI C6X DSPs */
-- 
cgit 


From 4aa806b771d16b810771d86ce23c4c3160888db3 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 26 Jun 2013 13:49:44 +0100
Subject: DMA-API: provide a helper to set both DMA and coherent DMA masks

Provide a helper to set both the DMA and coherent DMA masks to the
same value - this avoids duplicated code in a number of drivers,
sometimes with buggy error handling, and also allows us identify
which drivers do things differently.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 Documentation/DMA-API-HOWTO.txt | 37 ++++++++++++++++++++++---------------
 Documentation/DMA-API.txt       |  8 ++++++++
 include/linux/dma-mapping.h     | 14 ++++++++++++++
 3 files changed, 44 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 14129f149a75..5e983031cc11 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -101,14 +101,23 @@ style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to dma_set_mask():
+The query is performed via a call to dma_set_mask_and_coherent():
 
-	int dma_set_mask(struct device *dev, u64 mask);
+	int dma_set_mask_and_coherent(struct device *dev, u64 mask);
 
-The query for consistent allocations is performed via a call to
-dma_set_coherent_mask():
+which will query the mask for both streaming and coherent APIs together.
+If you have some special requirements, then the following two separate
+queries can be used instead:
 
-	int dma_set_coherent_mask(struct device *dev, u64 mask);
+	The query for streaming mappings is performed via a call to
+	dma_set_mask():
+
+		int dma_set_mask(struct device *dev, u64 mask);
+
+	The query for consistent allocations is performed via a call
+	to dma_set_coherent_mask():
+
+		int dma_set_coherent_mask(struct device *dev, u64 mask);
 
 Here, dev is a pointer to the device struct of your device, and mask
 is a bit mask describing which bits of an address your device
@@ -137,7 +146,7 @@ exactly why.
 
 The standard 32-bit addressing device would do something like this:
 
-	if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
@@ -171,22 +180,20 @@ the case would look like this:
 
 	int using_dac, consistent_using_dac;
 
-	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
-	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	} else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}
 
-dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as dma_set_mask(). However for the rare case that a
+The coherent coherent mask will always be able to set the same or a
+smaller mask as the streaming mask. However for the rare case that a
 device driver only uses consistent allocations, one would have to
 check the return value from dma_set_coherent_mask().
 
@@ -199,9 +206,9 @@ address you might do something like:
 		goto ignore_this_device;
 	}
 
-When dma_set_mask() is successful, and returns zero, the kernel saves
-away this mask you have provided.  The kernel will use this
-information later when you make DMA mappings.
+When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
+returns zero, the kernel saves away this mask you have provided.  The
+kernel will use this information later when you make DMA mappings.
 
 There is a case which we are aware of at this time, which is worth
 mentioning in this documentation.  If your device supports multiple
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 78a6c569d204..e865279cec58 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -141,6 +141,14 @@ won't change the current mask settings.  It is more intended as an
 internal API for use by the platform than an external API for use by
 driver writers.
 
+int
+dma_set_mask_and_coherent(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+streaming and coherent DMA mask parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
 dma_set_mask(struct device *dev, u64 mask)
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 3a8d0a2af607..ec951f98e3d9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -97,6 +97,20 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 #endif
 
+/*
+ * Set both the DMA mask and the coherent DMA mask to the same thing.
+ * Note that we don't check the return value from dma_set_coherent_mask()
+ * as the DMA API guarantees that the coherent DMA mask can be set to
+ * the same or smaller than the streaming DMA mask.
+ */
+static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask)
+{
+	int rc = dma_set_mask(dev, mask);
+	if (rc == 0)
+		dma_set_coherent_mask(dev, mask);
+	return rc;
+}
+
 extern u64 dma_get_required_mask(struct device *dev);
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
-- 
cgit 


From c7ccde6eac6d3c4bc6110cc3fd76ef3823bc0831 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 3 Sep 2013 13:58:43 -0400
Subject: USB: see if URB comes from a completion handler

Now that URBs can be completed inside tasklets, we need a way of
determining whether a completion handler for a given endpoint is
currently running.  Otherwise it's not possible to maintain the API
guarantee about keeping isochronous streams synchronous when an
underrun occurs.

This patch adds a field and a routine to check whether a completion
handler for a periodic endpoint is running.  At the moment no
analogous routine appears to be necessary for async endpoints, but one
can always be added.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
CC: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c  | 2 ++
 include/linux/usb/hcd.h | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d6a8d23f047b..3a2e82a9c115 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1703,7 +1703,9 @@ static void usb_giveback_urb_bh(unsigned long param)
 
 		urb = list_entry(local_list.next, struct urb, urb_list);
 		list_del_init(&urb->urb_list);
+		bh->completing_ep = urb->ep;
 		__usb_hcd_giveback_urb(urb);
+		bh->completing_ep = NULL;
 	}
 
 	/* check if there are new URBs to giveback */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 75efc45eaa2f..8c865134c881 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -73,6 +73,7 @@ struct giveback_urb_bh {
 	spinlock_t lock;
 	struct list_head  head;
 	struct tasklet_struct bh;
+	struct usb_host_endpoint *completing_ep;
 };
 
 struct usb_hcd {
@@ -378,6 +379,12 @@ static inline int hcd_giveback_urb_in_bh(struct usb_hcd *hcd)
 	return hcd->driver->flags & HCD_BH;
 }
 
+static inline bool hcd_periodic_completion_in_progress(struct usb_hcd *hcd,
+		struct usb_host_endpoint *ep)
+{
+	return hcd->high_prio_bh.completing_ep == ep;
+}
+
 extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb);
 extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb,
 		int status);
-- 
cgit 


From 6c74dada4f5a37037dee1da6a8a7aeb56c558bca Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 30 Aug 2013 14:03:59 +0200
Subject: usb-core: Make usb_free_streams return an error

The hcd-driver free_streams method can return an error, so lets properly
propagate that.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 11 +++++++----
 include/linux/usb.h    |  2 +-
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 3a2e82a9c115..ab54999da2bf 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2075,8 +2075,11 @@ EXPORT_SYMBOL_GPL(usb_alloc_streams);
  *
  * Reverts a group of bulk endpoints back to not using stream IDs.
  * Can fail if we are given bad arguments, or HCD is broken.
+ *
+ * Return: On success, the number of allocated streams. On failure, a negative
+ * error code.
  */
-void usb_free_streams(struct usb_interface *interface,
+int usb_free_streams(struct usb_interface *interface,
 		struct usb_host_endpoint **eps, unsigned int num_eps,
 		gfp_t mem_flags)
 {
@@ -2087,14 +2090,14 @@ void usb_free_streams(struct usb_interface *interface,
 	dev = interface_to_usbdev(interface);
 	hcd = bus_to_hcd(dev->bus);
 	if (dev->speed != USB_SPEED_SUPER)
-		return;
+		return -EINVAL;
 
 	/* Streams only apply to bulk endpoints. */
 	for (i = 0; i < num_eps; i++)
 		if (!eps[i] || !usb_endpoint_xfer_bulk(&eps[i]->desc))
-			return;
+			return -EINVAL;
 
-	hcd->driver->free_streams(hcd, dev, eps, num_eps, mem_flags);
+	return hcd->driver->free_streams(hcd, dev, eps, num_eps, mem_flags);
 }
 EXPORT_SYMBOL_GPL(usb_free_streams);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 001629cd1a97..f726c39097e0 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -702,7 +702,7 @@ extern int usb_alloc_streams(struct usb_interface *interface,
 		unsigned int num_streams, gfp_t mem_flags);
 
 /* Reverts a group of bulk endpoints back to not using stream IDs. */
-extern void usb_free_streams(struct usb_interface *interface,
+extern int usb_free_streams(struct usb_interface *interface,
 		struct usb_host_endpoint **eps, unsigned int num_eps,
 		gfp_t mem_flags);
 
-- 
cgit 


From 00c877c69ba315d6c565a4df51c71b11e82cdeb8 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan <ldewangan@nvidia.com>
Date: Wed, 18 Sep 2013 18:18:02 +0530
Subject: regulator: core: add support for configuring turn-on time through
 constraints

The turn-on time of the regulator depends on the regulator device's
electrical characteristics. Sometimes regulator turn-on time also
depends on the capacitive load on the given platform and it can be
more than the datasheet value.

The driver provides the enable-time as per datasheet.

Add support for configure the enable ramp time through regulator
constraints so that regulator core can take this value for enable
time for that regulator.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 Documentation/devicetree/bindings/regulator/regulator.txt | 5 +++++
 drivers/regulator/core.c                                  | 2 ++
 drivers/regulator/of_regulator.c                          | 6 ++++++
 include/linux/regulator/machine.h                         | 2 ++
 4 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index 2bd8f0978765..e2c7f1e7251a 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -14,6 +14,11 @@ Optional properties:
 - regulator-ramp-delay: ramp delay for regulator(in uV/uS)
   For hardwares which support disabling ramp rate, it should be explicitly
   intialised to zero (regulator-ramp-delay = <0>) for disabling ramp delay.
+- regulator-enable-ramp-delay: The time taken, in microseconds, for the supply
+  rail to reach the target voltage, plus/minus whatever tolerance the board
+  design requires. This property describes the total system ramp time
+  required due to the combination of internal ramping of the regulator itself,
+  and board design issues such as trace capacitance and load on the supply.
 
 Deprecated properties:
 - regulator-compatible: If a regulator chip contains multiple
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a01b8b3b70ca..5217c1964c32 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1186,6 +1186,8 @@ overflow_err:
 
 static int _regulator_get_enable_time(struct regulator_dev *rdev)
 {
+	if (rdev->constraints && rdev->constraints->enable_time)
+		return rdev->constraints->enable_time;
 	if (!rdev->desc->ops->enable_time)
 		return rdev->desc->enable_time;
 	return rdev->desc->ops->enable_time(rdev);
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 7827384680d6..ea4f36f2cbe2 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -23,6 +23,8 @@ static void of_get_regulation_constraints(struct device_node *np,
 	const __be32 *min_uA, *max_uA, *ramp_delay;
 	struct property *prop;
 	struct regulation_constraints *constraints = &(*init_data)->constraints;
+	int ret;
+	u32 pval;
 
 	constraints->name = of_get_property(np, "regulator-name", NULL);
 
@@ -73,6 +75,10 @@ static void of_get_regulation_constraints(struct device_node *np,
 		else
 			constraints->ramp_disable = true;
 	}
+
+	ret = of_property_read_u32(np, "regulator-enable-ramp-delay", &pval);
+	if (!ret)
+		constraints->enable_time = pval;
 }
 
 /**
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 999b20ce06cf..8108751acb86 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -95,6 +95,7 @@ struct regulator_state {
  * @initial_state: Suspend state to set by default.
  * @initial_mode: Mode to set at startup.
  * @ramp_delay: Time to settle down after voltage change (unit: uV/us)
+ * @enable_time: Turn-on time of the rails (unit: microseconds)
  */
 struct regulation_constraints {
 
@@ -129,6 +130,7 @@ struct regulation_constraints {
 	unsigned int initial_mode;
 
 	unsigned int ramp_delay;
+	unsigned int enable_time;
 
 	/* constraint flags */
 	unsigned always_on:1;	/* regulator never off when system is on */
-- 
cgit 


From 0af784dcbc44e3cf21a1bda3ce14df5fcc2bfe93 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 16 Sep 2013 13:05:12 +0300
Subject: Bluetooth: Remove unused event mask struct

The struct for HCI_Set_Event_Mask is never used. Instead a local 8-byte
array is used for sending this command. Therefore, remove the
unnecessary struct definition.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 30c88b585c1b..52bd2488ff4a 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -694,9 +694,6 @@ struct hci_cp_sniff_subrate {
 } __packed;
 
 #define HCI_OP_SET_EVENT_MASK		0x0c01
-struct hci_cp_set_event_mask {
-	__u8     mask[8];
-} __packed;
 
 #define HCI_OP_RESET			0x0c03
 
-- 
cgit 


From e793dcf082c847bd2b742c781252c20cbec37986 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 16 Sep 2013 13:05:19 +0300
Subject: Bluetooth: Fix waiting for clearing of BT_SK_SUSPEND flag

In the case of blocking sockets we should not proceed with sendmsg() if
the socket has the BT_SK_SUSPEND flag set. So far the code was only
ensuring that POLLOUT doesn't get set for non-blocking sockets using
poll() but there was no code in place to ensure that blocking sockets do
the right thing when writing to them.

This patch adds a new bt_sock_wait_ready helper function to sleep in the
sendmsg call if the BT_SK_SUSPEND flag is set, and wake up as soon as it
is unset. It also updates the L2CAP and RFCOMM sendmsg callbacks to take
advantage of this new helper function.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/bluetooth.h |  1 +
 net/bluetooth/af_bluetooth.c      | 40 +++++++++++++++++++++++++++++++++++++++
 net/bluetooth/l2cap_sock.c        |  6 ++++++
 net/bluetooth/rfcomm/sock.c       |  7 ++++++-
 4 files changed, 53 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 10d43d8c7037..afbc711ba37a 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -249,6 +249,7 @@ int  bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 uint bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
 int  bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 int  bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
+int  bt_sock_wait_ready(struct sock *sk, unsigned long flags);
 
 void bt_accept_enqueue(struct sock *parent, struct sock *sk);
 void bt_accept_unlink(struct sock *sk);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9096137c889c..c600631cd19e 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -525,6 +525,46 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
 }
 EXPORT_SYMBOL(bt_sock_wait_state);
 
+/* This function expects the sk lock to be held when called */
+int bt_sock_wait_ready(struct sock *sk, unsigned long flags)
+{
+	DECLARE_WAITQUEUE(wait, current);
+	unsigned long timeo;
+	int err = 0;
+
+	BT_DBG("sk %p", sk);
+
+	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags)) {
+		if (!timeo) {
+			err = -EAGAIN;
+			break;
+		}
+
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeo);
+			break;
+		}
+
+		release_sock(sk);
+		timeo = schedule_timeout(timeo);
+		lock_sock(sk);
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		err = sock_error(sk);
+		if (err)
+			break;
+	}
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return err;
+}
+EXPORT_SYMBOL(bt_sock_wait_ready);
+
 #ifdef CONFIG_PROC_FS
 struct bt_seq_state {
 	struct bt_sock_list *l;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 0098af80b213..ad95b426b09c 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -777,6 +777,12 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	if (sk->sk_state != BT_CONNECTED)
 		return -ENOTCONN;
 
+	lock_sock(sk);
+	err = bt_sock_wait_ready(sk, msg->msg_flags);
+	release_sock(sk);
+	if (err)
+		return err;
+
 	l2cap_chan_lock(chan);
 	err = l2cap_chan_send(chan, msg, len, sk->sk_priority);
 	l2cap_chan_unlock(chan);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 30b3721dc6d7..072938dc527d 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -544,7 +544,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct rfcomm_dlc *d = rfcomm_pi(sk)->dlc;
 	struct sk_buff *skb;
-	int sent = 0;
+	int sent;
 
 	if (test_bit(RFCOMM_DEFER_SETUP, &d->flags))
 		return -ENOTCONN;
@@ -559,6 +559,10 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	lock_sock(sk);
 
+	sent = bt_sock_wait_ready(sk, msg->msg_flags);
+	if (sent)
+		goto done;
+
 	while (len) {
 		size_t size = min_t(size_t, len, d->mtu);
 		int err;
@@ -594,6 +598,7 @@ static int rfcomm_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 		len  -= size;
 	}
 
+done:
 	release_sock(sk);
 
 	return sent;
-- 
cgit 


From e9a03add0c6ed5341fc59ff9c76843c2888a33fa Mon Sep 17 00:00:00 2001
From: Sonic Zhang <sonic.zhang@analog.com>
Date: Tue, 3 Sep 2013 16:28:59 +0800
Subject: pinctrl: ADI PIN control driver for the GPIO controller on bf54x and
 bf60x.

The new ADI GPIO2 controller was introduced since the BF548 and BF60x
processors. It differs a lot from the old one on BF5xx processors. So,
create a pinctrl driver under the pinctrl framework.

- Define gpio ports and pin interrupt controllers as individual platform
  devices.
- Register a pinctrl driver for the whole GPIO ports and pin interrupt
  devices.
- Probe pint devices before port devices. Put device instances into
  the global gpio and pint lists.
- Define peripheral, irq and gpio reservation bit masks for each gpio
  port as runtime resources.
- Save and restore gpio port and pint status MMRs in syscore PM functions.
- Create the plug-in subdrivers to hold the pinctrl soc data for bf54x
  and bf60x. Add soc data into struct adi_pinctrl. Initialize the soc data
  in pin controller probe function. Get the pin groups and functions via
  the soc data reference.
- Call gpiochip_add_pin_range() in gpio device probe function to register
  range cross reference between gpio device and pin control device.
- Get range by pinctrl_find_gpio_range_from_pin(), find gpio_port object
  by container_of() and find adi_pinctrl by pin control device name.
- Handle peripheral and gpio requests in pinctrl operation functions.
- Demux gpio IRQs via the irq_domain created by each GPIO port.

v2-changes:
- Remove unlinke() directive.

v3-changes:
- Rename struct adi_pmx to adi_pinctrl.
- Fix the comments of struct gpio_pint.
- Remove unused pin_base in struct gpio_port.
- Change pint_assign into bool type.
- Add comments about the relationship between pint device and port device
to the driver header.
- Use BIT macro to shift bit.
- Remove all bitmap reservation help functions. Inline reservation functions
into the actual code.
- Remove gpio and offset mutual reference help functions.
- Remove all help functions to find gpio_port and adi_pinctrl structs. Get
range by pinctrl_find_gpio_range_from_pin(), find gpio_port object by
container_of() and find adi_pinctrl by pin control device name.
- Pass bool type usage variable to port_setup help function.
- Separate long bit operations into several lines and add comments.
- Use debugfs to output all GPIO request information.
- Avoid to set drvdata to NULL
- Add explanation to function adi_gpio_init_int()
- Call gpiochip_add_pin_range() in gpio device probe function to register
range cross reference between gpio device and pin control device.
- Remove the reference to pin control device from the gpio_port struct.
Remove the reference list to gpio device from the adi_pinctrl struct.
Replace the global adi_pinctrl list with adi_gpio_port_list. Walk through
the gpio list to do power suspend and resume operations.
- Remove the global GPIO base from struct adi_pinctrl, define pin base in
the platform data for each GPIO port device.
- Initialize adi_pinctrl_setup in arch_initcall().
- print the status of triggers, whether it is in GPIO mode, if it is
flagged to be used as IRQ, etc in adi_pin_dbg_show().
- Create the plug-in subdrivers to hold the pinctrl soc data for bf54x
and bf60x. Add soc data into struct adi_pinctrl. Initialize the soc data
in pin controller probe function. Get the pin groups and functions via
the soc data reference.

v4-changes:
- remove useless system_state checking.
- replace dev_err with dev_warn in both irq and gpio pin cases.
- comment on relationship between irq type and invert operation.
- It is not necessary to check the reservation mode of the requested
pin in IRQ chip operation. Remove the reservation map.
- Use existing gpio/pinctrl subsystem debugfs files. Remove pinctrl-adi2
driver specific debugfs output.
- Add linkport group and function information for bf60x.
- Separate uart and ctsrts pins into 2 groups.
- Separate APAPI and alternative ATAPI pins into 2 groups.

Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig                    |   17 +
 drivers/pinctrl/Makefile                   |    3 +
 drivers/pinctrl/pinctrl-adi2-bf54x.c       |  592 ++++++++++++++
 drivers/pinctrl/pinctrl-adi2-bf60x.c       |  522 ++++++++++++
 drivers/pinctrl/pinctrl-adi2.c             | 1183 ++++++++++++++++++++++++++++
 drivers/pinctrl/pinctrl-adi2.h             |   75 ++
 include/linux/platform_data/pinctrl-adi2.h |   40 +
 7 files changed, 2432 insertions(+)
 create mode 100644 drivers/pinctrl/pinctrl-adi2-bf54x.c
 create mode 100644 drivers/pinctrl/pinctrl-adi2-bf60x.c
 create mode 100644 drivers/pinctrl/pinctrl-adi2.c
 create mode 100644 drivers/pinctrl/pinctrl-adi2.h
 create mode 100644 include/linux/platform_data/pinctrl-adi2.h

(limited to 'include')

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index b6e864e8c9e8..f45a21c57e0e 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -49,6 +49,23 @@ config PINCTRL_AB8505
 	bool "AB8505 pin controller driver"
 	depends on PINCTRL_ABX500 && ARCH_U8500
 
+config PINCTRL_ADI2
+	bool "ADI pin controller driver"
+	select PINMUX
+	select IRQ_DOMAIN
+	help
+	  This is the pin controller and gpio driver for ADI BF54x, BF60x and
+	  future processors. This option is selected automatically when specific
+	  machine and arch are selected to build.
+
+config PINCTRL_BF54x
+	def_bool y if BF54x
+	select PINCTRL_ADI2
+
+config PINCTRL_BF60x
+	def_bool y if BF60x
+	select PINCTRL_ADI2
+
 config PINCTRL_AT91
 	bool "AT91 pinctrl driver"
 	depends on OF
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 496d9bf9e1b9..bbeb98086495 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -14,6 +14,9 @@ obj-$(CONFIG_PINCTRL_AB8500)	+= pinctrl-ab8500.o
 obj-$(CONFIG_PINCTRL_AB8540)	+= pinctrl-ab8540.o
 obj-$(CONFIG_PINCTRL_AB9540)	+= pinctrl-ab9540.o
 obj-$(CONFIG_PINCTRL_AB8505)	+= pinctrl-ab8505.o
+obj-$(CONFIG_PINCTRL_ADI2)	+= pinctrl-adi2.o
+obj-$(CONFIG_PINCTRL_BF54x)	+= pinctrl-adi2-bf54x.o
+obj-$(CONFIG_PINCTRL_BF60x)	+= pinctrl-adi2-bf60x.o
 obj-$(CONFIG_PINCTRL_AT91)	+= pinctrl-at91.o
 obj-$(CONFIG_PINCTRL_BCM2835)	+= pinctrl-bcm2835.o
 obj-$(CONFIG_PINCTRL_BAYTRAIL)	+= pinctrl-baytrail.o
diff --git a/drivers/pinctrl/pinctrl-adi2-bf54x.c b/drivers/pinctrl/pinctrl-adi2-bf54x.c
new file mode 100644
index 000000000000..ea9d9ab9cda1
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-adi2-bf54x.c
@@ -0,0 +1,592 @@
+/*
+ * Pinctrl Driver for ADI GPIO2 controller
+ *
+ * Copyright 2007-2013 Analog Devices Inc.
+ *
+ * Licensed under the GPLv2 or later
+ */
+
+#include <asm/portmux.h>
+#include "pinctrl-adi2.h"
+
+static const struct pinctrl_pin_desc adi_pads[] = {
+	PINCTRL_PIN(0, "PA0"),
+	PINCTRL_PIN(1, "PA1"),
+	PINCTRL_PIN(2, "PA2"),
+	PINCTRL_PIN(3, "PG3"),
+	PINCTRL_PIN(4, "PA4"),
+	PINCTRL_PIN(5, "PA5"),
+	PINCTRL_PIN(6, "PA6"),
+	PINCTRL_PIN(7, "PA7"),
+	PINCTRL_PIN(8, "PA8"),
+	PINCTRL_PIN(9, "PA9"),
+	PINCTRL_PIN(10, "PA10"),
+	PINCTRL_PIN(11, "PA11"),
+	PINCTRL_PIN(12, "PA12"),
+	PINCTRL_PIN(13, "PA13"),
+	PINCTRL_PIN(14, "PA14"),
+	PINCTRL_PIN(15, "PA15"),
+	PINCTRL_PIN(16, "PB0"),
+	PINCTRL_PIN(17, "PB1"),
+	PINCTRL_PIN(18, "PB2"),
+	PINCTRL_PIN(19, "PB3"),
+	PINCTRL_PIN(20, "PB4"),
+	PINCTRL_PIN(21, "PB5"),
+	PINCTRL_PIN(22, "PB6"),
+	PINCTRL_PIN(23, "PB7"),
+	PINCTRL_PIN(24, "PB8"),
+	PINCTRL_PIN(25, "PB9"),
+	PINCTRL_PIN(26, "PB10"),
+	PINCTRL_PIN(27, "PB11"),
+	PINCTRL_PIN(28, "PB12"),
+	PINCTRL_PIN(29, "PB13"),
+	PINCTRL_PIN(30, "PB14"),
+	PINCTRL_PIN(32, "PC0"),
+	PINCTRL_PIN(33, "PC1"),
+	PINCTRL_PIN(34, "PC2"),
+	PINCTRL_PIN(35, "PC3"),
+	PINCTRL_PIN(36, "PC4"),
+	PINCTRL_PIN(37, "PC5"),
+	PINCTRL_PIN(38, "PC6"),
+	PINCTRL_PIN(39, "PC7"),
+	PINCTRL_PIN(40, "PC8"),
+	PINCTRL_PIN(41, "PC9"),
+	PINCTRL_PIN(42, "PC10"),
+	PINCTRL_PIN(43, "PC11"),
+	PINCTRL_PIN(44, "PC12"),
+	PINCTRL_PIN(45, "PC13"),
+	PINCTRL_PIN(48, "PD0"),
+	PINCTRL_PIN(49, "PD1"),
+	PINCTRL_PIN(50, "PD2"),
+	PINCTRL_PIN(51, "PD3"),
+	PINCTRL_PIN(52, "PD4"),
+	PINCTRL_PIN(53, "PD5"),
+	PINCTRL_PIN(54, "PD6"),
+	PINCTRL_PIN(55, "PD7"),
+	PINCTRL_PIN(56, "PD8"),
+	PINCTRL_PIN(57, "PD9"),
+	PINCTRL_PIN(58, "PD10"),
+	PINCTRL_PIN(59, "PD11"),
+	PINCTRL_PIN(60, "PD12"),
+	PINCTRL_PIN(61, "PD13"),
+	PINCTRL_PIN(62, "PD14"),
+	PINCTRL_PIN(63, "PD15"),
+	PINCTRL_PIN(64, "PE0"),
+	PINCTRL_PIN(65, "PE1"),
+	PINCTRL_PIN(66, "PE2"),
+	PINCTRL_PIN(67, "PE3"),
+	PINCTRL_PIN(68, "PE4"),
+	PINCTRL_PIN(69, "PE5"),
+	PINCTRL_PIN(70, "PE6"),
+	PINCTRL_PIN(71, "PE7"),
+	PINCTRL_PIN(72, "PE8"),
+	PINCTRL_PIN(73, "PE9"),
+	PINCTRL_PIN(74, "PE10"),
+	PINCTRL_PIN(75, "PE11"),
+	PINCTRL_PIN(76, "PE12"),
+	PINCTRL_PIN(77, "PE13"),
+	PINCTRL_PIN(78, "PE14"),
+	PINCTRL_PIN(79, "PE15"),
+	PINCTRL_PIN(80, "PF0"),
+	PINCTRL_PIN(81, "PF1"),
+	PINCTRL_PIN(82, "PF2"),
+	PINCTRL_PIN(83, "PF3"),
+	PINCTRL_PIN(84, "PF4"),
+	PINCTRL_PIN(85, "PF5"),
+	PINCTRL_PIN(86, "PF6"),
+	PINCTRL_PIN(87, "PF7"),
+	PINCTRL_PIN(88, "PF8"),
+	PINCTRL_PIN(89, "PF9"),
+	PINCTRL_PIN(90, "PF10"),
+	PINCTRL_PIN(91, "PF11"),
+	PINCTRL_PIN(92, "PF12"),
+	PINCTRL_PIN(93, "PF13"),
+	PINCTRL_PIN(94, "PF14"),
+	PINCTRL_PIN(95, "PF15"),
+	PINCTRL_PIN(96, "PG0"),
+	PINCTRL_PIN(97, "PG1"),
+	PINCTRL_PIN(98, "PG2"),
+	PINCTRL_PIN(99, "PG3"),
+	PINCTRL_PIN(100, "PG4"),
+	PINCTRL_PIN(101, "PG5"),
+	PINCTRL_PIN(102, "PG6"),
+	PINCTRL_PIN(103, "PG7"),
+	PINCTRL_PIN(104, "PG8"),
+	PINCTRL_PIN(105, "PG9"),
+	PINCTRL_PIN(106, "PG10"),
+	PINCTRL_PIN(107, "PG11"),
+	PINCTRL_PIN(108, "PG12"),
+	PINCTRL_PIN(109, "PG13"),
+	PINCTRL_PIN(110, "PG14"),
+	PINCTRL_PIN(111, "PG15"),
+	PINCTRL_PIN(112, "PH0"),
+	PINCTRL_PIN(113, "PH1"),
+	PINCTRL_PIN(114, "PH2"),
+	PINCTRL_PIN(115, "PH3"),
+	PINCTRL_PIN(116, "PH4"),
+	PINCTRL_PIN(117, "PH5"),
+	PINCTRL_PIN(118, "PH6"),
+	PINCTRL_PIN(119, "PH7"),
+	PINCTRL_PIN(120, "PH8"),
+	PINCTRL_PIN(121, "PH9"),
+	PINCTRL_PIN(122, "PH10"),
+	PINCTRL_PIN(123, "PH11"),
+	PINCTRL_PIN(124, "PH12"),
+	PINCTRL_PIN(125, "PH13"),
+	PINCTRL_PIN(128, "PI0"),
+	PINCTRL_PIN(129, "PI1"),
+	PINCTRL_PIN(130, "PI2"),
+	PINCTRL_PIN(131, "PI3"),
+	PINCTRL_PIN(132, "PI4"),
+	PINCTRL_PIN(133, "PI5"),
+	PINCTRL_PIN(134, "PI6"),
+	PINCTRL_PIN(135, "PI7"),
+	PINCTRL_PIN(136, "PI8"),
+	PINCTRL_PIN(137, "PI9"),
+	PINCTRL_PIN(138, "PI10"),
+	PINCTRL_PIN(139, "PI11"),
+	PINCTRL_PIN(140, "PI12"),
+	PINCTRL_PIN(141, "PI13"),
+	PINCTRL_PIN(142, "PI14"),
+	PINCTRL_PIN(143, "PI15"),
+	PINCTRL_PIN(144, "PJ0"),
+	PINCTRL_PIN(145, "PJ1"),
+	PINCTRL_PIN(146, "PJ2"),
+	PINCTRL_PIN(147, "PJ3"),
+	PINCTRL_PIN(148, "PJ4"),
+	PINCTRL_PIN(149, "PJ5"),
+	PINCTRL_PIN(150, "PJ6"),
+	PINCTRL_PIN(151, "PJ7"),
+	PINCTRL_PIN(152, "PJ8"),
+	PINCTRL_PIN(153, "PJ9"),
+	PINCTRL_PIN(154, "PJ10"),
+	PINCTRL_PIN(155, "PJ11"),
+	PINCTRL_PIN(156, "PJ12"),
+	PINCTRL_PIN(157, "PJ13"),
+};
+
+static const unsigned uart0_pins[] = {
+	GPIO_PE7, GPIO_PE8,
+};
+
+static const unsigned uart1_pins[] = {
+	GPIO_PH0, GPIO_PH1,
+};
+
+static const unsigned uart1_ctsrts_pins[] = {
+	GPIO_PE9, GPIO_PE10,
+};
+
+static const unsigned uart2_pins[] = {
+	GPIO_PB4, GPIO_PB5,
+};
+
+static const unsigned uart3_pins[] = {
+	GPIO_PB6, GPIO_PB7,
+};
+
+static const unsigned uart3_ctsrts_pins[] = {
+	GPIO_PB2, GPIO_PB3,
+};
+
+static const unsigned rsi0_pins[] = {
+	GPIO_PC8, GPIO_PC9, GPIO_PC10, GPIO_PC11, GPIO_PC12, GPIO_PC13,
+};
+
+static const unsigned spi0_pins[] = {
+	GPIO_PE0, GPIO_PE1, GPIO_PE2,
+};
+
+static const unsigned spi1_pins[] = {
+	GPIO_PG8, GPIO_PG9, GPIO_PG10,
+};
+
+static const unsigned twi0_pins[] = {
+	GPIO_PE14, GPIO_PE15,
+};
+
+static const unsigned twi1_pins[] = {
+	GPIO_PB0, GPIO_PB1,
+};
+
+static const unsigned rotary_pins[] = {
+	GPIO_PH4, GPIO_PH3, GPIO_PH5,
+};
+
+static const unsigned can0_pins[] = {
+	GPIO_PG13, GPIO_PG12,
+};
+
+static const unsigned can1_pins[] = {
+	GPIO_PG14, GPIO_PG15,
+};
+
+static const unsigned smc0_pins[] = {
+	GPIO_PH8, GPIO_PH9, GPIO_PH10, GPIO_PH11, GPIO_PH12, GPIO_PH13,
+	GPIO_PI0, GPIO_PI1, GPIO_PI2, GPIO_PI3, GPIO_PI4, GPIO_PI5, GPIO_PI6,
+	GPIO_PI7, GPIO_PI8, GPIO_PI9, GPIO_PI10, GPIO_PI11,
+	GPIO_PI12, GPIO_PI13, GPIO_PI14, GPIO_PI15,
+};
+
+static const unsigned sport0_pins[] = {
+	GPIO_PC0, GPIO_PC2, GPIO_PC3, GPIO_PC4, GPIO_PC6, GPIO_PC7,
+};
+
+static const unsigned sport1_pins[] = {
+	GPIO_PD0, GPIO_PD2, GPIO_PD3, GPIO_PD4, GPIO_PD6, GPIO_PD7,
+};
+
+static const unsigned sport2_pins[] = {
+	GPIO_PA0, GPIO_PA2, GPIO_PA3, GPIO_PA4, GPIO_PA6, GPIO_PA7,
+};
+
+static const unsigned sport3_pins[] = {
+	GPIO_PA8, GPIO_PA10, GPIO_PA11, GPIO_PA12, GPIO_PA14, GPIO_PA15,
+};
+
+static const unsigned ppi0_8b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF13, GPIO_PG0, GPIO_PG1, GPIO_PG2,
+};
+
+static const unsigned ppi0_16b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF9, GPIO_PF10, GPIO_PF11, GPIO_PF12,
+	GPIO_PF13, GPIO_PF14, GPIO_PF15,
+	GPIO_PG0, GPIO_PG1, GPIO_PG2,
+};
+
+static const unsigned ppi0_24b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF8, GPIO_PF9, GPIO_PF10, GPIO_PF11, GPIO_PF12,
+	GPIO_PF13, GPIO_PF14, GPIO_PF15, GPIO_PD0, GPIO_PD1, GPIO_PD2,
+	GPIO_PD3, GPIO_PD4, GPIO_PD5, GPIO_PG3, GPIO_PG4,
+	GPIO_PG0, GPIO_PG1, GPIO_PG2,
+};
+
+static const unsigned ppi1_8b_pins[] = {
+	GPIO_PD0, GPIO_PD1, GPIO_PD2, GPIO_PD3, GPIO_PD4, GPIO_PD5, GPIO_PD6,
+	GPIO_PD7, GPIO_PE11, GPIO_PE12, GPIO_PE13,
+};
+
+static const unsigned ppi1_16b_pins[] = {
+	GPIO_PD0, GPIO_PD1, GPIO_PD2, GPIO_PD3, GPIO_PD4, GPIO_PD5, GPIO_PD6,
+	GPIO_PD7, GPIO_PD8, GPIO_PD9, GPIO_PD10, GPIO_PD11, GPIO_PD12,
+	GPIO_PD13, GPIO_PD14, GPIO_PD15,
+	GPIO_PE11, GPIO_PE12, GPIO_PE13,
+};
+
+static const unsigned ppi2_8b_pins[] = {
+	GPIO_PD8, GPIO_PD9, GPIO_PD10, GPIO_PD11, GPIO_PD12,
+	GPIO_PD13, GPIO_PD14, GPIO_PD15,
+	GPIO_PA7, GPIO_PB0, GPIO_PB1, GPIO_PB2, GPIO_PB3,
+};
+
+static const unsigned atapi_pins[] = {
+	GPIO_PH2, GPIO_PJ3, GPIO_PJ4, GPIO_PJ5, GPIO_PJ6,
+	GPIO_PJ7, GPIO_PJ8, GPIO_PJ9, GPIO_PJ10,
+};
+
+static const unsigned atapi_alter_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF8, GPIO_PF9, GPIO_PF10, GPIO_PF11, GPIO_PF12,
+	GPIO_PF13, GPIO_PF14, GPIO_PF15, GPIO_PG2, GPIO_PG3, GPIO_PG4,
+};
+
+static const unsigned nfc0_pins[] = {
+	GPIO_PJ1, GPIO_PJ2,
+};
+
+static const unsigned keys_4x4_pins[] = {
+	GPIO_PD8, GPIO_PD9, GPIO_PD10, GPIO_PD11,
+	GPIO_PD12, GPIO_PD13, GPIO_PD14, GPIO_PD15,
+};
+
+static const unsigned keys_8x8_pins[] = {
+	GPIO_PD8, GPIO_PD9, GPIO_PD10, GPIO_PD11,
+	GPIO_PD12, GPIO_PD13, GPIO_PD14, GPIO_PD15,
+	GPIO_PE0, GPIO_PE1, GPIO_PE2, GPIO_PE3,
+	GPIO_PE4, GPIO_PE5, GPIO_PE6, GPIO_PE7,
+};
+
+static const struct adi_pin_group adi_pin_groups[] = {
+	ADI_PIN_GROUP("uart0grp", uart0_pins),
+	ADI_PIN_GROUP("uart1grp", uart1_pins),
+	ADI_PIN_GROUP("uart1ctsrtsgrp", uart1_ctsrts_pins),
+	ADI_PIN_GROUP("uart2grp", uart2_pins),
+	ADI_PIN_GROUP("uart3grp", uart3_pins),
+	ADI_PIN_GROUP("uart3ctsrtsgrp", uart3_ctsrts_pins),
+	ADI_PIN_GROUP("rsi0grp", rsi0_pins),
+	ADI_PIN_GROUP("spi0grp", spi0_pins),
+	ADI_PIN_GROUP("spi1grp", spi1_pins),
+	ADI_PIN_GROUP("twi0grp", twi0_pins),
+	ADI_PIN_GROUP("twi1grp", twi1_pins),
+	ADI_PIN_GROUP("rotarygrp", rotary_pins),
+	ADI_PIN_GROUP("can0grp", can0_pins),
+	ADI_PIN_GROUP("can1grp", can1_pins),
+	ADI_PIN_GROUP("smc0grp", smc0_pins),
+	ADI_PIN_GROUP("sport0grp", sport0_pins),
+	ADI_PIN_GROUP("sport1grp", sport1_pins),
+	ADI_PIN_GROUP("sport2grp", sport2_pins),
+	ADI_PIN_GROUP("sport3grp", sport3_pins),
+	ADI_PIN_GROUP("ppi0_8bgrp", ppi0_8b_pins),
+	ADI_PIN_GROUP("ppi0_16bgrp", ppi0_16b_pins),
+	ADI_PIN_GROUP("ppi0_24bgrp", ppi0_24b_pins),
+	ADI_PIN_GROUP("ppi1_8bgrp", ppi1_8b_pins),
+	ADI_PIN_GROUP("ppi1_16bgrp", ppi1_16b_pins),
+	ADI_PIN_GROUP("ppi2_8bgrp", ppi2_8b_pins),
+	ADI_PIN_GROUP("atapigrp", atapi_pins),
+	ADI_PIN_GROUP("atapialtergrp", atapi_alter_pins),
+	ADI_PIN_GROUP("nfc0grp", nfc0_pins),
+	ADI_PIN_GROUP("keys_4x4grp", keys_4x4_pins),
+	ADI_PIN_GROUP("keys_8x8grp", keys_8x8_pins),
+};
+
+static const unsigned short uart0_mux[] = {
+	P_UART0_TX, P_UART0_RX,
+	0
+};
+
+static const unsigned short uart1_mux[] = {
+	P_UART1_TX, P_UART1_RX,
+	0
+};
+
+static const unsigned short uart1_ctsrts_mux[] = {
+	P_UART1_RTS, P_UART1_CTS,
+	0
+};
+
+static const unsigned short uart2_mux[] = {
+	P_UART2_TX, P_UART2_RX,
+	0
+};
+
+static const unsigned short uart3_mux[] = {
+	P_UART3_TX, P_UART3_RX,
+	0
+};
+
+static const unsigned short uart3_ctsrts_mux[] = {
+	P_UART3_RTS, P_UART3_CTS,
+	0
+};
+
+static const unsigned short rsi0_mux[] = {
+	P_SD_D0, P_SD_D1, P_SD_D2, P_SD_D3, P_SD_CLK, P_SD_CMD,
+	0
+};
+
+static const unsigned short spi0_mux[] = {
+	P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0
+};
+
+static const unsigned short spi1_mux[] = {
+	P_SPI1_SCK, P_SPI1_MISO, P_SPI1_MOSI, 0
+};
+
+static const unsigned short twi0_mux[] = {
+	P_TWI0_SCL, P_TWI0_SDA, 0
+};
+
+static const unsigned short twi1_mux[] = {
+	P_TWI1_SCL, P_TWI1_SDA, 0
+};
+
+static const unsigned short rotary_mux[] = {
+	P_CNT_CUD, P_CNT_CDG, P_CNT_CZM, 0
+};
+
+static const unsigned short sport0_mux[] = {
+	P_SPORT0_TFS, P_SPORT0_DTPRI, P_SPORT0_TSCLK, P_SPORT0_RFS,
+	P_SPORT0_DRPRI, P_SPORT0_RSCLK, 0
+};
+
+static const unsigned short sport1_mux[] = {
+	P_SPORT1_TFS, P_SPORT1_DTPRI, P_SPORT1_TSCLK, P_SPORT1_RFS,
+	P_SPORT1_DRPRI, P_SPORT1_RSCLK, 0
+};
+
+static const unsigned short sport2_mux[] = {
+	P_SPORT2_TFS, P_SPORT2_DTPRI, P_SPORT2_TSCLK, P_SPORT2_RFS,
+	P_SPORT2_DRPRI, P_SPORT2_RSCLK, 0
+};
+
+static const unsigned short sport3_mux[] = {
+	P_SPORT3_TFS, P_SPORT3_DTPRI, P_SPORT3_TSCLK, P_SPORT3_RFS,
+	P_SPORT3_DRPRI, P_SPORT3_RSCLK, 0
+};
+
+static const unsigned short can0_mux[] = {
+	P_CAN0_RX, P_CAN0_TX, 0
+};
+
+static const unsigned short can1_mux[] = {
+	P_CAN1_RX, P_CAN1_TX, 0
+};
+
+static const unsigned short smc0_mux[] = {
+	P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12,
+	P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21,
+	P_A22, P_A23, P_A24, P_A25, P_NOR_CLK, 0,
+};
+
+static const unsigned short ppi0_8b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi0_16b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11,
+	P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi0_24b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11,
+	P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15,
+	P_PPI0_D16, P_PPI0_D17, P_PPI0_D18, P_PPI0_D19,
+	P_PPI0_D20, P_PPI0_D21, P_PPI0_D22, P_PPI0_D23,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi1_8b_mux[] = {
+	P_PPI1_D0, P_PPI1_D1, P_PPI1_D2, P_PPI1_D3,
+	P_PPI1_D4, P_PPI1_D5, P_PPI1_D6, P_PPI1_D7,
+	P_PPI1_CLK, P_PPI1_FS1, P_PPI1_FS2,
+	0,
+};
+
+static const unsigned short ppi1_16b_mux[] = {
+	P_PPI1_D0, P_PPI1_D1, P_PPI1_D2, P_PPI1_D3,
+	P_PPI1_D4, P_PPI1_D5, P_PPI1_D6, P_PPI1_D7,
+	P_PPI1_D8, P_PPI1_D9, P_PPI1_D10, P_PPI1_D11,
+	P_PPI1_D12, P_PPI1_D13, P_PPI1_D14, P_PPI1_D15,
+	P_PPI1_CLK, P_PPI1_FS1, P_PPI1_FS2,
+	0,
+};
+
+static const unsigned short ppi2_8b_mux[] = {
+	P_PPI2_D0, P_PPI2_D1, P_PPI2_D2, P_PPI2_D3,
+	P_PPI2_D4, P_PPI2_D5, P_PPI2_D6, P_PPI2_D7,
+	P_PPI2_CLK, P_PPI2_FS1, P_PPI2_FS2,
+	0,
+};
+
+static const unsigned short atapi_mux[] = {
+	P_ATAPI_RESET, P_ATAPI_DIOR, P_ATAPI_DIOW, P_ATAPI_CS0, P_ATAPI_CS1,
+	P_ATAPI_DMACK, P_ATAPI_DMARQ, P_ATAPI_INTRQ, P_ATAPI_IORDY,
+};
+
+static const unsigned short atapi_alter_mux[] = {
+	P_ATAPI_D0A, P_ATAPI_D1A, P_ATAPI_D2A, P_ATAPI_D3A, P_ATAPI_D4A,
+	P_ATAPI_D5A, P_ATAPI_D6A, P_ATAPI_D7A, P_ATAPI_D8A, P_ATAPI_D9A,
+	P_ATAPI_D10A, P_ATAPI_D11A, P_ATAPI_D12A, P_ATAPI_D13A, P_ATAPI_D14A,
+	P_ATAPI_D15A, P_ATAPI_A0A, P_ATAPI_A1A, P_ATAPI_A2A,
+	0
+};
+
+static const unsigned short nfc0_mux[] = {
+	P_NAND_CE, P_NAND_RB,
+	0
+};
+
+static const unsigned short keys_4x4_mux[] = {
+	P_KEY_ROW3, P_KEY_ROW2, P_KEY_ROW1, P_KEY_ROW0,
+	P_KEY_COL3, P_KEY_COL2, P_KEY_COL1, P_KEY_COL0,
+	0
+};
+
+static const unsigned short keys_8x8_mux[] = {
+	P_KEY_ROW7, P_KEY_ROW6, P_KEY_ROW5, P_KEY_ROW4,
+	P_KEY_ROW3, P_KEY_ROW2, P_KEY_ROW1, P_KEY_ROW0,
+	P_KEY_COL7, P_KEY_COL6, P_KEY_COL5, P_KEY_COL4,
+	P_KEY_COL3, P_KEY_COL2, P_KEY_COL1, P_KEY_COL0,
+	0
+};
+
+static const char * const uart0grp[] = { "uart0grp" };
+static const char * const uart1grp[] = { "uart1grp" };
+static const char * const uart1ctsrtsgrp[] = { "uart1ctsrtsgrp" };
+static const char * const uart2grp[] = { "uart2grp" };
+static const char * const uart3grp[] = { "uart3grp" };
+static const char * const uart3ctsrtsgrp[] = { "uart3ctsrtsgrp" };
+static const char * const rsi0grp[] = { "rsi0grp" };
+static const char * const spi0grp[] = { "spi0grp" };
+static const char * const spi1grp[] = { "spi1grp" };
+static const char * const twi0grp[] = { "twi0grp" };
+static const char * const twi1grp[] = { "twi1grp" };
+static const char * const rotarygrp[] = { "rotarygrp" };
+static const char * const can0grp[] = { "can0grp" };
+static const char * const can1grp[] = { "can1grp" };
+static const char * const smc0grp[] = { "smc0grp" };
+static const char * const sport0grp[] = { "sport0grp" };
+static const char * const sport1grp[] = { "sport1grp" };
+static const char * const sport2grp[] = { "sport2grp" };
+static const char * const sport3grp[] = { "sport3grp" };
+static const char * const ppi0_8bgrp[] = { "ppi0_8bgrp" };
+static const char * const ppi0_16bgrp[] = { "ppi0_16bgrp" };
+static const char * const ppi0_24bgrp[] = { "ppi0_24bgrp" };
+static const char * const ppi1_8bgrp[] = { "ppi1_8bgrp" };
+static const char * const ppi1_16bgrp[] = { "ppi1_16bgrp" };
+static const char * const ppi2_8bgrp[] = { "ppi2_8bgrp" };
+static const char * const atapigrp[] = { "atapigrp" };
+static const char * const atapialtergrp[] = { "atapialtergrp" };
+static const char * const nfc0grp[] = { "nfc0grp" };
+static const char * const keys_4x4grp[] = { "keys_4x4grp" };
+static const char * const keys_8x8grp[] = { "keys_8x8grp" };
+
+static const struct adi_pmx_func adi_pmx_functions[] = {
+	ADI_PMX_FUNCTION("uart0", uart0grp, uart0_mux),
+	ADI_PMX_FUNCTION("uart1", uart1grp, uart1_mux),
+	ADI_PMX_FUNCTION("uart1_ctsrts", uart1ctsrtsgrp, uart1_ctsrts_mux),
+	ADI_PMX_FUNCTION("uart2", uart2grp, uart2_mux),
+	ADI_PMX_FUNCTION("uart3", uart3grp, uart3_mux),
+	ADI_PMX_FUNCTION("uart3_ctsrts", uart3ctsrtsgrp, uart3_ctsrts_mux),
+	ADI_PMX_FUNCTION("rsi0", rsi0grp, rsi0_mux),
+	ADI_PMX_FUNCTION("spi0", spi0grp, spi0_mux),
+	ADI_PMX_FUNCTION("spi1", spi1grp, spi1_mux),
+	ADI_PMX_FUNCTION("twi0", twi0grp, twi0_mux),
+	ADI_PMX_FUNCTION("twi1", twi1grp, twi1_mux),
+	ADI_PMX_FUNCTION("rotary", rotarygrp, rotary_mux),
+	ADI_PMX_FUNCTION("can0", can0grp, can0_mux),
+	ADI_PMX_FUNCTION("can1", can1grp, can1_mux),
+	ADI_PMX_FUNCTION("smc0", smc0grp, smc0_mux),
+	ADI_PMX_FUNCTION("sport0", sport0grp, sport0_mux),
+	ADI_PMX_FUNCTION("sport1", sport1grp, sport1_mux),
+	ADI_PMX_FUNCTION("sport2", sport2grp, sport2_mux),
+	ADI_PMX_FUNCTION("sport3", sport3grp, sport3_mux),
+	ADI_PMX_FUNCTION("ppi0_8b", ppi0_8bgrp, ppi0_8b_mux),
+	ADI_PMX_FUNCTION("ppi0_16b", ppi0_16bgrp, ppi0_16b_mux),
+	ADI_PMX_FUNCTION("ppi0_24b", ppi0_24bgrp, ppi0_24b_mux),
+	ADI_PMX_FUNCTION("ppi1_8b", ppi1_8bgrp, ppi1_8b_mux),
+	ADI_PMX_FUNCTION("ppi1_16b", ppi1_16bgrp, ppi1_16b_mux),
+	ADI_PMX_FUNCTION("ppi2_8b", ppi2_8bgrp, ppi2_8b_mux),
+	ADI_PMX_FUNCTION("atapi", atapigrp, atapi_mux),
+	ADI_PMX_FUNCTION("atapi_alter", atapialtergrp, atapi_alter_mux),
+	ADI_PMX_FUNCTION("nfc0", nfc0grp, nfc0_mux),
+	ADI_PMX_FUNCTION("keys_4x4", keys_4x4grp, keys_4x4_mux),
+	ADI_PMX_FUNCTION("keys_8x8", keys_8x8grp, keys_8x8_mux),
+};
+
+static const struct adi_pinctrl_soc_data adi_bf54x_soc = {
+	.functions = adi_pmx_functions,
+	.nfunctions = ARRAY_SIZE(adi_pmx_functions),
+	.groups = adi_pin_groups,
+	.ngroups = ARRAY_SIZE(adi_pin_groups),
+	.pins = adi_pads,
+	.npins = ARRAY_SIZE(adi_pads),
+};
+
+void adi_pinctrl_soc_init(const struct adi_pinctrl_soc_data **soc)
+{
+	*soc = &adi_bf54x_soc;
+}
diff --git a/drivers/pinctrl/pinctrl-adi2-bf60x.c b/drivers/pinctrl/pinctrl-adi2-bf60x.c
new file mode 100644
index 000000000000..e90cb80c8d0b
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-adi2-bf60x.c
@@ -0,0 +1,522 @@
+/*
+ * Pinctrl Driver for ADI GPIO2 controller
+ *
+ * Copyright 2007-2013 Analog Devices Inc.
+ *
+ * Licensed under the GPLv2 or later
+ */
+
+#include <asm/portmux.h>
+#include "pinctrl-adi2.h"
+
+static const struct pinctrl_pin_desc adi_pads[] = {
+	PINCTRL_PIN(0, "PA0"),
+	PINCTRL_PIN(1, "PA1"),
+	PINCTRL_PIN(2, "PA2"),
+	PINCTRL_PIN(3, "PG3"),
+	PINCTRL_PIN(4, "PA4"),
+	PINCTRL_PIN(5, "PA5"),
+	PINCTRL_PIN(6, "PA6"),
+	PINCTRL_PIN(7, "PA7"),
+	PINCTRL_PIN(8, "PA8"),
+	PINCTRL_PIN(9, "PA9"),
+	PINCTRL_PIN(10, "PA10"),
+	PINCTRL_PIN(11, "PA11"),
+	PINCTRL_PIN(12, "PA12"),
+	PINCTRL_PIN(13, "PA13"),
+	PINCTRL_PIN(14, "PA14"),
+	PINCTRL_PIN(15, "PA15"),
+	PINCTRL_PIN(16, "PB0"),
+	PINCTRL_PIN(17, "PB1"),
+	PINCTRL_PIN(18, "PB2"),
+	PINCTRL_PIN(19, "PB3"),
+	PINCTRL_PIN(20, "PB4"),
+	PINCTRL_PIN(21, "PB5"),
+	PINCTRL_PIN(22, "PB6"),
+	PINCTRL_PIN(23, "PB7"),
+	PINCTRL_PIN(24, "PB8"),
+	PINCTRL_PIN(25, "PB9"),
+	PINCTRL_PIN(26, "PB10"),
+	PINCTRL_PIN(27, "PB11"),
+	PINCTRL_PIN(28, "PB12"),
+	PINCTRL_PIN(29, "PB13"),
+	PINCTRL_PIN(30, "PB14"),
+	PINCTRL_PIN(31, "PB15"),
+	PINCTRL_PIN(32, "PC0"),
+	PINCTRL_PIN(33, "PC1"),
+	PINCTRL_PIN(34, "PC2"),
+	PINCTRL_PIN(35, "PC3"),
+	PINCTRL_PIN(36, "PC4"),
+	PINCTRL_PIN(37, "PC5"),
+	PINCTRL_PIN(38, "PC6"),
+	PINCTRL_PIN(39, "PC7"),
+	PINCTRL_PIN(40, "PC8"),
+	PINCTRL_PIN(41, "PC9"),
+	PINCTRL_PIN(42, "PC10"),
+	PINCTRL_PIN(43, "PC11"),
+	PINCTRL_PIN(44, "PC12"),
+	PINCTRL_PIN(45, "PC13"),
+	PINCTRL_PIN(46, "PC14"),
+	PINCTRL_PIN(47, "PC15"),
+	PINCTRL_PIN(48, "PD0"),
+	PINCTRL_PIN(49, "PD1"),
+	PINCTRL_PIN(50, "PD2"),
+	PINCTRL_PIN(51, "PD3"),
+	PINCTRL_PIN(52, "PD4"),
+	PINCTRL_PIN(53, "PD5"),
+	PINCTRL_PIN(54, "PD6"),
+	PINCTRL_PIN(55, "PD7"),
+	PINCTRL_PIN(56, "PD8"),
+	PINCTRL_PIN(57, "PD9"),
+	PINCTRL_PIN(58, "PD10"),
+	PINCTRL_PIN(59, "PD11"),
+	PINCTRL_PIN(60, "PD12"),
+	PINCTRL_PIN(61, "PD13"),
+	PINCTRL_PIN(62, "PD14"),
+	PINCTRL_PIN(63, "PD15"),
+	PINCTRL_PIN(64, "PE0"),
+	PINCTRL_PIN(65, "PE1"),
+	PINCTRL_PIN(66, "PE2"),
+	PINCTRL_PIN(67, "PE3"),
+	PINCTRL_PIN(68, "PE4"),
+	PINCTRL_PIN(69, "PE5"),
+	PINCTRL_PIN(70, "PE6"),
+	PINCTRL_PIN(71, "PE7"),
+	PINCTRL_PIN(72, "PE8"),
+	PINCTRL_PIN(73, "PE9"),
+	PINCTRL_PIN(74, "PE10"),
+	PINCTRL_PIN(75, "PE11"),
+	PINCTRL_PIN(76, "PE12"),
+	PINCTRL_PIN(77, "PE13"),
+	PINCTRL_PIN(78, "PE14"),
+	PINCTRL_PIN(79, "PE15"),
+	PINCTRL_PIN(80, "PF0"),
+	PINCTRL_PIN(81, "PF1"),
+	PINCTRL_PIN(82, "PF2"),
+	PINCTRL_PIN(83, "PF3"),
+	PINCTRL_PIN(84, "PF4"),
+	PINCTRL_PIN(85, "PF5"),
+	PINCTRL_PIN(86, "PF6"),
+	PINCTRL_PIN(87, "PF7"),
+	PINCTRL_PIN(88, "PF8"),
+	PINCTRL_PIN(89, "PF9"),
+	PINCTRL_PIN(90, "PF10"),
+	PINCTRL_PIN(91, "PF11"),
+	PINCTRL_PIN(92, "PF12"),
+	PINCTRL_PIN(93, "PF13"),
+	PINCTRL_PIN(94, "PF14"),
+	PINCTRL_PIN(95, "PF15"),
+	PINCTRL_PIN(96, "PG0"),
+	PINCTRL_PIN(97, "PG1"),
+	PINCTRL_PIN(98, "PG2"),
+	PINCTRL_PIN(99, "PG3"),
+	PINCTRL_PIN(100, "PG4"),
+	PINCTRL_PIN(101, "PG5"),
+	PINCTRL_PIN(102, "PG6"),
+	PINCTRL_PIN(103, "PG7"),
+	PINCTRL_PIN(104, "PG8"),
+	PINCTRL_PIN(105, "PG9"),
+	PINCTRL_PIN(106, "PG10"),
+	PINCTRL_PIN(107, "PG11"),
+	PINCTRL_PIN(108, "PG12"),
+	PINCTRL_PIN(109, "PG13"),
+	PINCTRL_PIN(110, "PG14"),
+	PINCTRL_PIN(111, "PG15"),
+};
+
+static const unsigned uart0_pins[] = {
+	GPIO_PD7, GPIO_PD8,
+};
+
+static const unsigned uart0_ctsrts_pins[] = {
+	GPIO_PD9, GPIO_PD10,
+};
+
+static const unsigned uart1_pins[] = {
+	GPIO_PG15, GPIO_PG14,
+};
+
+static const unsigned uart1_ctsrts_pins[] = {
+	GPIO_PG10, GPIO_PG13,
+};
+
+static const unsigned rsi0_pins[] = {
+	GPIO_PG3, GPIO_PG2, GPIO_PG0, GPIO_PE15, GPIO_PG5, GPIO_PG6,
+};
+
+static const unsigned eth0_pins[] = {
+	GPIO_PC6, GPIO_PC7, GPIO_PC2, GPIO_PC0, GPIO_PC3, GPIO_PC1,
+	GPIO_PB13, GPIO_PD6, GPIO_PC5, GPIO_PC4, GPIO_PB14, GPIO_PB15,
+};
+
+static const unsigned eth1_pins[] = {
+	GPIO_PE10, GPIO_PE11, GPIO_PG3, GPIO_PG0, GPIO_PG2, GPIO_PE15,
+	GPIO_PG5, GPIO_PE12, GPIO_PE13, GPIO_PE14, GPIO_PG6, GPIO_PC9,
+};
+
+static const unsigned spi0_pins[] = {
+	GPIO_PD4, GPIO_PD2, GPIO_PD3,
+};
+
+static const unsigned spi1_pins[] = {
+	GPIO_PD5, GPIO_PD14, GPIO_PD13,
+};
+
+static const unsigned twi0_pins[] = {
+};
+
+static const unsigned twi1_pins[] = {
+};
+
+static const unsigned rotary_pins[] = {
+	GPIO_PG7, GPIO_PG11, GPIO_PG12,
+};
+
+static const unsigned can0_pins[] = {
+	GPIO_PG1, GPIO_PG4,
+};
+
+static const unsigned smc0_pins[] = {
+	GPIO_PA0, GPIO_PA1, GPIO_PA2, GPIO_PA3, GPIO_PA4, GPIO_PA5, GPIO_PA6,
+	GPIO_PA7, GPIO_PA8, GPIO_PA9, GPIO_PB2, GPIO_PA10, GPIO_PA11,
+	GPIO_PB3, GPIO_PA12, GPIO_PA13, GPIO_PA14, GPIO_PA15, GPIO_PB6,
+	GPIO_PB7, GPIO_PB8, GPIO_PB10, GPIO_PB11, GPIO_PB0,
+};
+
+static const unsigned sport0_pins[] = {
+	GPIO_PB5, GPIO_PB4, GPIO_PB9, GPIO_PB8, GPIO_PB7, GPIO_PB11,
+};
+
+static const unsigned sport1_pins[] = {
+	GPIO_PE2, GPIO_PE5, GPIO_PD15, GPIO_PE4, GPIO_PE3, GPIO_PE1,
+};
+
+static const unsigned sport2_pins[] = {
+	GPIO_PG4, GPIO_PG1, GPIO_PG9, GPIO_PG10, GPIO_PG7, GPIO_PB12,
+};
+
+static const unsigned ppi0_8b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF13, GPIO_PF14, GPIO_PF15,
+	GPIO_PE6, GPIO_PE7, GPIO_PE8, GPIO_PE9,
+};
+
+static const unsigned ppi0_16b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF9, GPIO_PF10, GPIO_PF11, GPIO_PF12,
+	GPIO_PF13, GPIO_PF14, GPIO_PF15,
+	GPIO_PE6, GPIO_PE7, GPIO_PE8, GPIO_PE9,
+};
+
+static const unsigned ppi0_24b_pins[] = {
+	GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3, GPIO_PF4, GPIO_PF5, GPIO_PF6,
+	GPIO_PF7, GPIO_PF8, GPIO_PF9, GPIO_PF10, GPIO_PF11, GPIO_PF12,
+	GPIO_PF13, GPIO_PF14, GPIO_PF15, GPIO_PE0, GPIO_PE1, GPIO_PE2,
+	GPIO_PE3, GPIO_PE4, GPIO_PE5, GPIO_PE6, GPIO_PE7, GPIO_PE8,
+	GPIO_PE9, GPIO_PD12, GPIO_PD15,
+};
+
+static const unsigned ppi1_8b_pins[] = {
+	GPIO_PC0, GPIO_PC1, GPIO_PC2, GPIO_PC3, GPIO_PC4, GPIO_PC5, GPIO_PC6,
+	GPIO_PC7, GPIO_PC8, GPIO_PB13, GPIO_PB14, GPIO_PB15, GPIO_PD6,
+};
+
+static const unsigned ppi1_16b_pins[] = {
+	GPIO_PC0, GPIO_PC1, GPIO_PC2, GPIO_PC3, GPIO_PC4, GPIO_PC5, GPIO_PC6,
+	GPIO_PC7, GPIO_PC9, GPIO_PC10, GPIO_PC11, GPIO_PC12,
+	GPIO_PC13, GPIO_PC14, GPIO_PC15,
+	GPIO_PB13, GPIO_PB14, GPIO_PB15, GPIO_PD6,
+};
+
+static const unsigned ppi2_8b_pins[] = {
+	GPIO_PA0, GPIO_PA1, GPIO_PA2, GPIO_PA3, GPIO_PA4, GPIO_PA5, GPIO_PA6,
+	GPIO_PA7, GPIO_PB0, GPIO_PB1, GPIO_PB2, GPIO_PB3,
+};
+
+static const unsigned ppi2_16b_pins[] = {
+	GPIO_PA0, GPIO_PA1, GPIO_PA2, GPIO_PA3, GPIO_PA4, GPIO_PA5, GPIO_PA6,
+	GPIO_PA7, GPIO_PA8, GPIO_PA9, GPIO_PA10, GPIO_PA11, GPIO_PA12,
+	GPIO_PA13, GPIO_PA14, GPIO_PA15,
+	GPIO_PA7, GPIO_PB0, GPIO_PB1, GPIO_PB2, GPIO_PB3,
+};
+
+static const unsigned lp0_pins[] = {
+	GPIO_PB0, GPIO_PB1, GPIO_PA0, GPIO_PA1, GPIO_PA2, GPIO_PA3,
+	GPIO_PA4, GPIO_PA5, GPIO_PA6, GPIO_PA7,
+};
+
+static const unsigned lp1_pins[] = {
+	GPIO_PB3, GPIO_PB2, GPIO_PA8, GPIO_PA9, GPIO_PA10, GPIO_PA11,
+	GPIO_PA12, GPIO_PA13, GPIO_PA14, GPIO_PA15,
+};
+
+static const unsigned lp2_pins[] = {
+	GPIO_PE6, GPIO_PE7, GPIO_PF0, GPIO_PF1, GPIO_PF2, GPIO_PF3,
+	GPIO_PF4, GPIO_PF5, GPIO_PF6, GPIO_PF7,
+};
+
+static const unsigned lp3_pins[] = {
+	GPIO_PE9, GPIO_PE8, GPIO_PF8, GPIO_PF9, GPIO_PF10, GPIO_PF11,
+	GPIO_PF12, GPIO_PF13, GPIO_PF14, GPIO_PF15,
+};
+
+static const struct adi_pin_group adi_pin_groups[] = {
+	ADI_PIN_GROUP("uart0grp", uart0_pins),
+	ADI_PIN_GROUP("uart0ctsrtsgrp", uart0_ctsrts_pins),
+	ADI_PIN_GROUP("uart1grp", uart1_pins),
+	ADI_PIN_GROUP("uart1ctsrtsgrp", uart1_ctsrts_pins),
+	ADI_PIN_GROUP("rsi0grp", rsi0_pins),
+	ADI_PIN_GROUP("eth0grp", eth0_pins),
+	ADI_PIN_GROUP("eth1grp", eth1_pins),
+	ADI_PIN_GROUP("spi0grp", spi0_pins),
+	ADI_PIN_GROUP("spi1grp", spi1_pins),
+	ADI_PIN_GROUP("twi0grp", twi0_pins),
+	ADI_PIN_GROUP("twi1grp", twi1_pins),
+	ADI_PIN_GROUP("rotarygrp", rotary_pins),
+	ADI_PIN_GROUP("can0grp", can0_pins),
+	ADI_PIN_GROUP("smc0grp", smc0_pins),
+	ADI_PIN_GROUP("sport0grp", sport0_pins),
+	ADI_PIN_GROUP("sport1grp", sport1_pins),
+	ADI_PIN_GROUP("sport2grp", sport2_pins),
+	ADI_PIN_GROUP("ppi0_8bgrp", ppi0_8b_pins),
+	ADI_PIN_GROUP("ppi0_16bgrp", ppi0_16b_pins),
+	ADI_PIN_GROUP("ppi0_24bgrp", ppi0_24b_pins),
+	ADI_PIN_GROUP("ppi1_8bgrp", ppi1_8b_pins),
+	ADI_PIN_GROUP("ppi1_16bgrp", ppi1_16b_pins),
+	ADI_PIN_GROUP("ppi2_8bgrp", ppi2_8b_pins),
+	ADI_PIN_GROUP("ppi2_16bgrp", ppi2_16b_pins),
+	ADI_PIN_GROUP("lp0grp", lp0_pins),
+	ADI_PIN_GROUP("lp1grp", lp1_pins),
+	ADI_PIN_GROUP("lp2grp", lp2_pins),
+	ADI_PIN_GROUP("lp3grp", lp3_pins),
+};
+
+static const unsigned short uart0_mux[] = {
+	P_UART0_TX, P_UART0_RX,
+	0
+};
+
+static const unsigned short uart0_ctsrts_mux[] = {
+	P_UART0_RTS, P_UART0_CTS,
+	0
+};
+
+static const unsigned short uart1_mux[] = {
+	P_UART1_TX, P_UART1_RX,
+	0
+};
+
+static const unsigned short uart1_ctsrts_mux[] = {
+	P_UART1_RTS, P_UART1_CTS,
+	0
+};
+
+static const unsigned short rsi0_mux[] = {
+	P_RSI_DATA0, P_RSI_DATA1, P_RSI_DATA2, P_RSI_DATA3,
+	P_RSI_CMD, P_RSI_CLK, 0
+};
+
+static const unsigned short eth0_mux[] = P_RMII0;
+static const unsigned short eth1_mux[] = P_RMII1;
+
+static const unsigned short spi0_mux[] = {
+	P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0
+};
+
+static const unsigned short spi1_mux[] = {
+	P_SPI1_SCK, P_SPI1_MISO, P_SPI1_MOSI, 0
+};
+
+static const unsigned short twi0_mux[] = {
+	P_TWI0_SCL, P_TWI0_SDA, 0
+};
+
+static const unsigned short twi1_mux[] = {
+	P_TWI1_SCL, P_TWI1_SDA, 0
+};
+
+static const unsigned short rotary_mux[] = {
+	P_CNT_CUD, P_CNT_CDG, P_CNT_CZM, 0
+};
+
+static const unsigned short sport0_mux[] = {
+	P_SPORT0_ACLK, P_SPORT0_AFS, P_SPORT0_AD0, P_SPORT0_BCLK,
+	P_SPORT0_BFS, P_SPORT0_BD0, 0,
+};
+
+static const unsigned short sport1_mux[] = {
+	P_SPORT1_ACLK, P_SPORT1_AFS, P_SPORT1_AD0, P_SPORT1_BCLK,
+	P_SPORT1_BFS, P_SPORT1_BD0, 0,
+};
+
+static const unsigned short sport2_mux[] = {
+	P_SPORT2_ACLK, P_SPORT2_AFS, P_SPORT2_AD0, P_SPORT2_BCLK,
+	P_SPORT2_BFS, P_SPORT2_BD0, 0,
+};
+
+static const unsigned short can0_mux[] = {
+	P_CAN0_RX, P_CAN0_TX, 0
+};
+
+static const unsigned short smc0_mux[] = {
+	P_A3, P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12,
+	P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21,
+	P_A22, P_A23, P_A24, P_A25, P_NORCK, 0,
+};
+
+static const unsigned short ppi0_8b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi0_16b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11,
+	P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi0_24b_mux[] = {
+	P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3,
+	P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7,
+	P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11,
+	P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15,
+	P_PPI0_D16, P_PPI0_D17, P_PPI0_D18, P_PPI0_D19,
+	P_PPI0_D20, P_PPI0_D21, P_PPI0_D22, P_PPI0_D23,
+	P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2,
+	0,
+};
+
+static const unsigned short ppi1_8b_mux[] = {
+	P_PPI1_D0, P_PPI1_D1, P_PPI1_D2, P_PPI1_D3,
+	P_PPI1_D4, P_PPI1_D5, P_PPI1_D6, P_PPI1_D7,
+	P_PPI1_CLK, P_PPI1_FS1, P_PPI1_FS2,
+	0,
+};
+
+static const unsigned short ppi1_16b_mux[] = {
+	P_PPI1_D0, P_PPI1_D1, P_PPI1_D2, P_PPI1_D3,
+	P_PPI1_D4, P_PPI1_D5, P_PPI1_D6, P_PPI1_D7,
+	P_PPI1_D8, P_PPI1_D9, P_PPI1_D10, P_PPI1_D11,
+	P_PPI1_D12, P_PPI1_D13, P_PPI1_D14, P_PPI1_D15,
+	P_PPI1_CLK, P_PPI1_FS1, P_PPI1_FS2,
+	0,
+};
+
+static const unsigned short ppi2_8b_mux[] = {
+	P_PPI2_D0, P_PPI2_D1, P_PPI2_D2, P_PPI2_D3,
+	P_PPI2_D4, P_PPI2_D5, P_PPI2_D6, P_PPI2_D7,
+	P_PPI2_CLK, P_PPI2_FS1, P_PPI2_FS2,
+	0,
+};
+
+static const unsigned short ppi2_16b_mux[] = {
+	P_PPI2_D0, P_PPI2_D1, P_PPI2_D2, P_PPI2_D3,
+	P_PPI2_D4, P_PPI2_D5, P_PPI2_D6, P_PPI2_D7,
+	P_PPI2_D8, P_PPI2_D9, P_PPI2_D10, P_PPI2_D11,
+	P_PPI2_D12, P_PPI2_D13, P_PPI2_D14, P_PPI2_D15,
+	P_PPI2_CLK, P_PPI2_FS1, P_PPI2_FS2,
+	0,
+};
+
+static const unsigned short lp0_mux[] = {
+	P_LP0_CLK, P_LP0_ACK, P_LP0_D0, P_LP0_D1, P_LP0_D2,
+	P_LP0_D3, P_LP0_D4, P_LP0_D5, P_LP0_D6, P_LP0_D7,
+        0
+};
+
+static const unsigned short lp1_mux[] = {
+	P_LP1_CLK, P_LP1_ACK, P_LP1_D0, P_LP1_D1, P_LP1_D2,
+	P_LP1_D3, P_LP1_D4, P_LP1_D5, P_LP1_D6, P_LP1_D7,
+        0
+};
+
+static const unsigned short lp2_mux[] = {
+	P_LP2_CLK, P_LP2_ACK, P_LP2_D0, P_LP2_D1, P_LP2_D2,
+	P_LP2_D3, P_LP2_D4, P_LP2_D5, P_LP2_D6, P_LP2_D7,
+        0
+};
+
+static const unsigned short lp3_mux[] = {
+	P_LP3_CLK, P_LP3_ACK, P_LP3_D0, P_LP3_D1, P_LP3_D2,
+	P_LP3_D3, P_LP3_D4, P_LP3_D5, P_LP3_D6, P_LP3_D7,
+        0
+};
+
+static const char * const uart0grp[] = { "uart0grp" };
+static const char * const uart0ctsrtsgrp[] = { "uart0ctsrtsgrp" };
+static const char * const uart1grp[] = { "uart1grp" };
+static const char * const uart1ctsrtsgrp[] = { "uart1ctsrtsgrp" };
+static const char * const rsi0grp[] = { "rsi0grp" };
+static const char * const eth0grp[] = { "eth0grp" };
+static const char * const eth1grp[] = { "eth1grp" };
+static const char * const spi0grp[] = { "spi0grp" };
+static const char * const spi1grp[] = { "spi1grp" };
+static const char * const twi0grp[] = { "twi0grp" };
+static const char * const twi1grp[] = { "twi1grp" };
+static const char * const rotarygrp[] = { "rotarygrp" };
+static const char * const can0grp[] = { "can0grp" };
+static const char * const smc0grp[] = { "smc0grp" };
+static const char * const sport0grp[] = { "sport0grp" };
+static const char * const sport1grp[] = { "sport1grp" };
+static const char * const sport2grp[] = { "sport2grp" };
+static const char * const ppi0_8bgrp[] = { "ppi0_8bgrp" };
+static const char * const ppi0_16bgrp[] = { "ppi0_16bgrp" };
+static const char * const ppi0_24bgrp[] = { "ppi0_24bgrp" };
+static const char * const ppi1_8bgrp[] = { "ppi1_8bgrp" };
+static const char * const ppi1_16bgrp[] = { "ppi1_16bgrp" };
+static const char * const ppi2_8bgrp[] = { "ppi2_8bgrp" };
+static const char * const ppi2_16bgrp[] = { "ppi2_16bgrp" };
+static const char * const lp0grp[] = { "lp0grp" };
+static const char * const lp1grp[] = { "lp1grp" };
+static const char * const lp2grp[] = { "lp2grp" };
+static const char * const lp3grp[] = { "lp3grp" };
+
+static const struct adi_pmx_func adi_pmx_functions[] = {
+	ADI_PMX_FUNCTION("uart0", uart0grp, uart0_mux),
+	ADI_PMX_FUNCTION("uart0_ctsrts", uart0ctsrtsgrp, uart0_ctsrts_mux),
+	ADI_PMX_FUNCTION("uart1", uart1grp, uart1_mux),
+	ADI_PMX_FUNCTION("uart1_ctsrts", uart1ctsrtsgrp, uart1_ctsrts_mux),
+	ADI_PMX_FUNCTION("rsi0", rsi0grp, rsi0_mux),
+	ADI_PMX_FUNCTION("eth0", eth0grp, eth0_mux),
+	ADI_PMX_FUNCTION("eth1", eth1grp, eth1_mux),
+	ADI_PMX_FUNCTION("spi0", spi0grp, spi0_mux),
+	ADI_PMX_FUNCTION("spi1", spi1grp, spi1_mux),
+	ADI_PMX_FUNCTION("twi0", twi0grp, twi0_mux),
+	ADI_PMX_FUNCTION("twi1", twi1grp, twi1_mux),
+	ADI_PMX_FUNCTION("rotary", rotarygrp, rotary_mux),
+	ADI_PMX_FUNCTION("can0", can0grp, can0_mux),
+	ADI_PMX_FUNCTION("smc0", smc0grp, smc0_mux),
+	ADI_PMX_FUNCTION("sport0", sport0grp, sport0_mux),
+	ADI_PMX_FUNCTION("sport1", sport1grp, sport1_mux),
+	ADI_PMX_FUNCTION("sport2", sport2grp, sport2_mux),
+	ADI_PMX_FUNCTION("ppi0_8b", ppi0_8bgrp, ppi0_8b_mux),
+	ADI_PMX_FUNCTION("ppi0_16b", ppi0_16bgrp, ppi0_16b_mux),
+	ADI_PMX_FUNCTION("ppi0_24b", ppi0_24bgrp, ppi0_24b_mux),
+	ADI_PMX_FUNCTION("ppi1_8b", ppi1_8bgrp, ppi1_8b_mux),
+	ADI_PMX_FUNCTION("ppi1_16b", ppi1_16bgrp, ppi1_16b_mux),
+	ADI_PMX_FUNCTION("ppi2_8b", ppi2_8bgrp, ppi2_8b_mux),
+	ADI_PMX_FUNCTION("ppi2_16b", ppi2_16bgrp, ppi2_16b_mux),
+	ADI_PMX_FUNCTION("lp0", lp0grp, lp0_mux),
+	ADI_PMX_FUNCTION("lp1", lp1grp, lp1_mux),
+	ADI_PMX_FUNCTION("lp2", lp2grp, lp2_mux),
+	ADI_PMX_FUNCTION("lp3", lp3grp, lp3_mux),
+};
+
+static const struct adi_pinctrl_soc_data adi_bf60x_soc = {
+	.functions = adi_pmx_functions,
+	.nfunctions = ARRAY_SIZE(adi_pmx_functions),
+	.groups = adi_pin_groups,
+	.ngroups = ARRAY_SIZE(adi_pin_groups),
+	.pins = adi_pads,
+	.npins = ARRAY_SIZE(adi_pads),
+};
+
+void adi_pinctrl_soc_init(const struct adi_pinctrl_soc_data **soc)
+{
+	*soc = &adi_bf60x_soc;
+}
diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c
new file mode 100644
index 000000000000..7a24e59b4138
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-adi2.c
@@ -0,0 +1,1183 @@
+/*
+ * Pinctrl Driver for ADI GPIO2 controller
+ *
+ * Copyright 2007-2013 Analog Devices Inc.
+ *
+ * Licensed under the GPLv2 or later
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/irq.h>
+#include <linux/platform_data/pinctrl-adi2.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/pinctrl/machine.h>
+#include <linux/syscore_ops.h>
+#include <linux/gpio.h>
+#include <asm/portmux.h>
+#include "pinctrl-adi2.h"
+#include "core.h"
+
+/*
+According to the BF54x HRM, pint means "pin interrupt".
+http://www.analog.com/static/imported-files/processor_manuals/ADSP-BF54x_hwr_rev1.2.pdf
+
+ADSP-BF54x processor Blackfin processors have four SIC interrupt chan-
+nels dedicated to pin interrupt purposes. These channels are managed by
+four hardware blocks, called PINT0, PINT1, PINT2, and PINT3. Every PINTx
+block can sense to up to 32 pins. While PINT0 and PINT1 can sense the
+pins of port A and port B, PINT2 and PINT3 manage all the pins from port
+C to port J as shown in Figure 9-2.
+
+n BF54x HRM:
+The ten GPIO ports are subdivided into 8-bit half ports, resulting in lower and
+upper half 8-bit units. The PINTx_ASSIGN registers control the 8-bit multi-
+plexers shown in Figure 9-3. Lower half units of eight pins can be
+forwarded to either byte 0 or byte 2 of either associated PINTx block.
+Upper half units can be forwarded to either byte 1 or byte 3 of the pin
+interrupt blocks, without further restrictions.
+
+All MMR registers in the pin interrupt module are 32 bits wide. To simply the
+mapping logic, this driver only maps a 16-bit gpio port to the upper or lower
+16 bits of a PINTx block. You can find the Figure 9-3 on page 583.
+
+Each IRQ domain is binding to a GPIO bank device. 2 GPIO bank devices can map
+to one PINT device. Two in "struct gpio_pint" are used to ease the PINT
+interrupt handler.
+
+The GPIO bank mapping to the lower 16 bits of the PINT device set its IRQ
+domain pointer in domain[0]. The IRQ domain pointer of the other bank is set
+to domain[1]. PINT interrupt handler adi_gpio_handle_pint_irq() finds out
+the current domain pointer according to whether the interrupt request mask
+is in lower 16 bits (domain[0]) or upper 16bits (domain[1]).
+
+A PINT device is not part of a GPIO port device in Blackfin. Multiple GPIO
+port devices can be mapped to the same PINT device.
+
+*/
+
+static LIST_HEAD(adi_pint_list);
+static LIST_HEAD(adi_gpio_port_list);
+
+#define DRIVER_NAME "pinctrl-adi2"
+
+#define PINT_HI_OFFSET		16
+
+/**
+ * struct gpio_port_saved - GPIO port registers that should be saved between
+ * power suspend and resume operations.
+ *
+ * @fer: PORTx_FER register
+ * @data: PORTx_DATA register
+ * @dir: PORTx_DIR register
+ * @inen: PORTx_INEN register
+ * @mux: PORTx_MUX register
+ */
+struct gpio_port_saved {
+	u16 fer;
+	u16 data;
+	u16 dir;
+	u16 inen;
+	u32 mux;
+};
+
+/**
+ * struct gpio_pint - Pin interrupt controller device. Multiple ADI GPIO
+ * banks can be mapped into one Pin interrupt controller.
+ *
+ * @node: All gpio_pint instances are added to a global list.
+ * @base: PINT device register base address
+ * @irq: IRQ of the PINT device, it is the parent IRQ of all
+ *       GPIO IRQs mapping to this device.
+ * @domain: [0] irq domain of the gpio port, whose hardware interrupts are
+ *		mapping to the low 16-bit of the pint registers.
+ *          [1] irq domain of the gpio port, whose hardware interrupts are
+ *		mapping to the high 16-bit of the pint registers.
+ * @regs: address pointer to the PINT device
+ * @map_count: No more than 2 GPIO banks can be mapped to this PINT device.
+ * @lock: This lock make sure the irq_chip operations to one PINT device
+ *        for different GPIO interrrupts are atomic.
+ * @pint_map_port: Set up the mapping between one PINT device and
+ *                 multiple GPIO banks.
+ */
+struct gpio_pint {
+	struct list_head node;
+	void __iomem *base;
+	int irq;
+	struct irq_domain *domain[2];
+	struct gpio_pint_regs *regs;
+	struct adi_pm_pint_save saved_data;
+	int map_count;
+	spinlock_t lock;
+
+	int (*pint_map_port)(struct gpio_pint *pint, bool assign,
+				u8 map, struct irq_domain *domain);
+};
+
+/**
+ * ADI pin controller
+ *
+ * @dev: a pointer back to containing device
+ * @pctl: the pinctrl device
+ * @soc: SoC data for this specific chip
+ */
+struct adi_pinctrl {
+	struct device *dev;
+	struct pinctrl_dev *pctl;
+	const struct adi_pinctrl_soc_data *soc;
+};
+
+/**
+ * struct gpio_port - GPIO bank device. Multiple ADI GPIO banks can be mapped
+ * into one pin interrupt controller.
+ *
+ * @node: All gpio_port instances are added to a list.
+ * @base: GPIO bank device register base address
+ * @irq_base: base IRQ of the GPIO bank device
+ * @width: PIN number of the GPIO bank device
+ * @regs: address pointer to the GPIO bank device
+ * @saved_data: registers that should be saved between PM operations.
+ * @dev: device structure of this GPIO bank
+ * @pint: GPIO PINT device that this GPIO bank mapped to
+ * @pint_map: GIOP bank mapping code in PINT device
+ * @pint_assign: The 32-bit PINT registers can be divided into 2 parts. A
+ *               GPIO bank can be mapped into either low 16 bits[0] or high 16
+ *               bits[1] of each PINT register.
+ * @lock: This lock make sure the irq_chip operations to one PINT device
+ *        for different GPIO interrrupts are atomic.
+ * @chip: abstract a GPIO controller
+ * @domain: The irq domain owned by the GPIO port.
+ * @rsvmap: Reservation map array for each pin in the GPIO bank
+ */
+struct gpio_port {
+	struct list_head node;
+	void __iomem *base;
+	unsigned int irq_base;
+	unsigned int width;
+	struct gpio_port_t *regs;
+	struct gpio_port_saved saved_data;
+	struct device *dev;
+
+	struct gpio_pint *pint;
+	u8 pint_map;
+	bool pint_assign;
+
+	spinlock_t lock;
+	struct gpio_chip chip;
+	struct irq_domain *domain;
+};
+
+static inline u8 pin_to_offset(struct pinctrl_gpio_range *range, unsigned pin)
+{
+	return pin - range->pin_base;
+}
+
+static inline u32 hwirq_to_pintbit(struct gpio_port *port, int hwirq)
+{
+	return port->pint_assign ? BIT(hwirq) << PINT_HI_OFFSET : BIT(hwirq);
+}
+
+static struct gpio_pint *find_gpio_pint(unsigned id)
+{
+	struct gpio_pint *pint;
+	int i = 0;
+
+	list_for_each_entry(pint, &adi_pint_list, node) {
+		if (id == i)
+			return pint;
+		i++;
+	}
+
+	return NULL;
+}
+
+static inline void port_setup(struct gpio_port *port, unsigned offset,
+	bool use_for_gpio)
+{
+	struct gpio_port_t *regs = port->regs;
+
+	if (use_for_gpio)
+		writew(readw(&regs->port_fer) & ~BIT(offset),
+			&regs->port_fer);
+	else
+		writew(readw(&regs->port_fer) | BIT(offset), &regs->port_fer);
+}
+
+static inline void portmux_setup(struct gpio_port *port, unsigned offset,
+	unsigned short function)
+{
+	struct gpio_port_t *regs = port->regs;
+	u32 pmux;
+
+	pmux = readl(&regs->port_mux);
+
+	/* The function field of each pin has 2 consecutive bits in
+	 * the mux register.
+	 */
+	pmux &= ~(0x3 << (2 * offset));
+	pmux |= (function & 0x3) << (2 * offset);
+
+	writel(pmux, &regs->port_mux);
+}
+
+static inline u16 get_portmux(struct gpio_port *port, unsigned offset)
+{
+	struct gpio_port_t *regs = port->regs;
+	u32 pmux = readl(&regs->port_mux);
+
+	/* The function field of each pin has 2 consecutive bits in
+	 * the mux register.
+	 */
+	return pmux >> (2 * offset) & 0x3;
+}
+
+static void adi_gpio_ack_irq(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+	unsigned pintbit = hwirq_to_pintbit(port, d->hwirq);
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	if (irqd_get_trigger_type(d) == IRQ_TYPE_EDGE_BOTH) {
+		if (readl(&regs->invert_set) & pintbit)
+			writel(pintbit, &regs->invert_clear);
+		else
+			writel(pintbit, &regs->invert_set);
+	}
+
+	writel(pintbit, &regs->request);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static void adi_gpio_mask_ack_irq(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+	unsigned pintbit = hwirq_to_pintbit(port, d->hwirq);
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	if (irqd_get_trigger_type(d) == IRQ_TYPE_EDGE_BOTH) {
+		if (readl(&regs->invert_set) & pintbit)
+			writel(pintbit, &regs->invert_clear);
+		else
+			writel(pintbit, &regs->invert_set);
+	}
+
+	writel(pintbit, &regs->request);
+	writel(pintbit, &regs->mask_clear);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static void adi_gpio_mask_irq(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	writel(hwirq_to_pintbit(port, d->hwirq), &regs->mask_clear);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static void adi_gpio_unmask_irq(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	writel(hwirq_to_pintbit(port, d->hwirq), &regs->mask_set);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static unsigned int adi_gpio_irq_startup(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+
+	if (!port) {
+		dev_err(port->dev, "GPIO IRQ %d :Not exist\n", d->irq);
+		return -ENODEV;
+	}
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	port_setup(port, d->hwirq, true);
+	writew(BIT(d->hwirq), &port->regs->dir_clear);
+	writew(readw(&port->regs->inen) | BIT(d->hwirq), &port->regs->inen);
+
+	writel(hwirq_to_pintbit(port, d->hwirq), &regs->mask_set);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 0;
+}
+
+static void adi_gpio_irq_shutdown(struct irq_data *d)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *regs = port->pint->regs;
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	writel(hwirq_to_pintbit(port, d->hwirq), &regs->mask_clear);
+
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static int adi_gpio_irq_type(struct irq_data *d, unsigned int type)
+{
+	unsigned long flags;
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+	struct gpio_pint_regs *pint_regs = port->pint->regs;
+	unsigned pintmask;
+	unsigned int irq = d->irq;
+	int ret = 0;
+	char buf[16];
+
+	if (!port) {
+		dev_err(port->dev, "GPIO IRQ %d :Not exist\n", irq);
+		return -ENODEV;
+	}
+
+	pintmask = hwirq_to_pintbit(port, d->hwirq);
+
+	spin_lock_irqsave(&port->lock, flags);
+	spin_lock_irqsave(&port->pint->lock, flags);
+
+	/* In case of interrupt autodetect, set irq type to edge sensitive. */
+	if (type == IRQ_TYPE_PROBE)
+		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
+
+	if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING |
+		    IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW)) {
+		snprintf(buf, 16, "gpio-irq%d", irq);
+		port_setup(port, d->hwirq, true);
+	} else
+		goto out;
+
+	/* The GPIO interrupt is triggered only when its input value
+	 * transfer from 0 to 1. So, invert the input value if the
+	 * irq type is low or falling
+	 */
+	if ((type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_LEVEL_LOW)))
+		writel(pintmask, &pint_regs->invert_set);
+	else
+		writel(pintmask, &pint_regs->invert_clear);
+
+	/* In edge sensitive case, if the input value of the requested irq
+	 * is already 1, invert it.
+	 */
+	if ((type & IRQ_TYPE_EDGE_BOTH) == IRQ_TYPE_EDGE_BOTH) {
+		if (gpio_get_value(port->chip.base + d->hwirq))
+			writel(pintmask, &pint_regs->invert_set);
+		else
+			writel(pintmask, &pint_regs->invert_clear);
+	}
+
+	if (type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING)) {
+		writel(pintmask, &pint_regs->edge_set);
+		__irq_set_handler_locked(irq, handle_edge_irq);
+	} else {
+		writel(pintmask, &pint_regs->edge_clear);
+		__irq_set_handler_locked(irq, handle_level_irq);
+	}
+
+out:
+	spin_unlock_irqrestore(&port->pint->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM
+static int adi_gpio_set_wake(struct irq_data *d, unsigned int state)
+{
+	struct gpio_port *port = irq_data_get_irq_chip_data(d);
+
+	if (!port || !port->pint || port->pint->irq != d->irq)
+		return -EINVAL;
+
+#ifndef SEC_GCTL
+	adi_internal_set_wake(port->pint->irq, state);
+#endif
+
+	return 0;
+}
+
+static int adi_pint_suspend(void)
+{
+	struct gpio_pint *pint;
+
+	list_for_each_entry(pint, &adi_pint_list, node) {
+		writel(0xffffffff, &pint->regs->mask_clear);
+		pint->saved_data.assign = readl(&pint->regs->assign);
+		pint->saved_data.edge_set = readl(&pint->regs->edge_set);
+		pint->saved_data.invert_set = readl(&pint->regs->invert_set);
+	}
+
+	return 0;
+}
+
+static void adi_pint_resume(void)
+{
+	struct gpio_pint *pint;
+
+	list_for_each_entry(pint, &adi_pint_list, node) {
+		writel(pint->saved_data.assign, &pint->regs->assign);
+		writel(pint->saved_data.edge_set, &pint->regs->edge_set);
+		writel(pint->saved_data.invert_set, &pint->regs->invert_set);
+	}
+}
+
+static int adi_gpio_suspend(void)
+{
+	struct gpio_port *port;
+
+	list_for_each_entry(port, &adi_gpio_port_list, node) {
+		port->saved_data.fer = readw(&port->regs->port_fer);
+		port->saved_data.mux = readl(&port->regs->port_mux);
+		port->saved_data.data = readw(&port->regs->data);
+		port->saved_data.inen = readw(&port->regs->inen);
+		port->saved_data.dir = readw(&port->regs->dir_set);
+	}
+
+	return adi_pint_suspend();
+}
+
+static void adi_gpio_resume(void)
+{
+	struct gpio_port *port;
+
+	adi_pint_resume();
+
+	list_for_each_entry(port, &adi_gpio_port_list, node) {
+		writel(port->saved_data.mux, &port->regs->port_mux);
+		writew(port->saved_data.fer, &port->regs->port_fer);
+		writew(port->saved_data.inen, &port->regs->inen);
+		writew(port->saved_data.data & port->saved_data.dir,
+					&port->regs->data_set);
+		writew(port->saved_data.dir, &port->regs->dir_set);
+	}
+
+}
+
+static struct syscore_ops gpio_pm_syscore_ops = {
+	.suspend = adi_gpio_suspend,
+	.resume = adi_gpio_resume,
+};
+#else /* CONFIG_PM */
+#define adi_gpio_set_wake NULL
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void preflow_handler(struct irq_desc *desc)
+{
+	if (desc->preflow_handler)
+		desc->preflow_handler(&desc->irq_data);
+}
+#else
+static inline void preflow_handler(struct irq_desc *desc) { }
+#endif
+
+static void adi_gpio_handle_pint_irq(unsigned int inta_irq,
+			struct irq_desc *desc)
+{
+	u32 request;
+	u32 level_mask, hwirq;
+	bool umask = false;
+	struct gpio_pint *pint = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct gpio_pint_regs *regs = pint->regs;
+	struct irq_domain *domain;
+
+	preflow_handler(desc);
+	chained_irq_enter(chip, desc);
+
+	request = readl(&regs->request);
+	level_mask = readl(&regs->edge_set) & request;
+
+	hwirq = 0;
+	domain = pint->domain[0];
+	while (request) {
+		/* domain pointer need to be changed only once at IRQ 16 when
+		 * we go through IRQ requests from bit 0 to bit 31.
+		 */
+		if (hwirq == PINT_HI_OFFSET)
+			domain = pint->domain[1];
+
+		if (request & 1) {
+			if (level_mask & BIT(hwirq)) {
+				umask = true;
+				chained_irq_exit(chip, desc);
+			}
+			generic_handle_irq(irq_find_mapping(domain,
+					hwirq % PINT_HI_OFFSET));
+		}
+
+		hwirq++;
+		request >>= 1;
+	}
+
+	if (!umask)
+		chained_irq_exit(chip, desc);
+}
+
+static struct irq_chip adi_gpio_irqchip = {
+	.name = "GPIO",
+	.irq_ack = adi_gpio_ack_irq,
+	.irq_mask = adi_gpio_mask_irq,
+	.irq_mask_ack = adi_gpio_mask_ack_irq,
+	.irq_unmask = adi_gpio_unmask_irq,
+	.irq_disable = adi_gpio_mask_irq,
+	.irq_enable = adi_gpio_unmask_irq,
+	.irq_set_type = adi_gpio_irq_type,
+	.irq_startup = adi_gpio_irq_startup,
+	.irq_shutdown = adi_gpio_irq_shutdown,
+	.irq_set_wake = adi_gpio_set_wake,
+};
+
+static int adi_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->soc->ngroups;
+}
+
+static const char *adi_get_group_name(struct pinctrl_dev *pctldev,
+				       unsigned selector)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->soc->groups[selector].name;
+}
+
+static int adi_get_group_pins(struct pinctrl_dev *pctldev, unsigned selector,
+			       const unsigned **pins,
+			       unsigned *num_pins)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = pinctrl->soc->groups[selector].pins;
+	*num_pins = pinctrl->soc->groups[selector].num;
+	return 0;
+}
+
+static struct pinctrl_ops adi_pctrl_ops = {
+	.get_groups_count = adi_get_groups_count,
+	.get_group_name = adi_get_group_name,
+	.get_group_pins = adi_get_group_pins,
+};
+
+static int adi_pinmux_enable(struct pinctrl_dev *pctldev, unsigned selector,
+	unsigned group)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	struct gpio_port *port;
+	struct pinctrl_gpio_range *range;
+	unsigned long flags;
+	unsigned short *mux, pin;
+
+	mux = (unsigned short *)pinctrl->soc->functions[selector].mux;
+
+	while (*mux) {
+		pin = P_IDENT(*mux);
+
+		range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+		if (range == NULL) /* should not happen */
+			return -ENODEV;
+
+		port = container_of(range->gc, struct gpio_port, chip);
+
+		spin_lock_irqsave(&port->lock, flags);
+
+		portmux_setup(port, pin_to_offset(range, pin),
+				 P_FUNCT2MUX(*mux));
+		port_setup(port, pin_to_offset(range, pin), false);
+		mux++;
+
+		spin_unlock_irqrestore(&port->lock, flags);
+	}
+
+	return 0;
+}
+
+static void adi_pinmux_disable(struct pinctrl_dev *pctldev, unsigned selector,
+	unsigned group)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+	struct gpio_port *port;
+	struct pinctrl_gpio_range *range;
+	unsigned long flags;
+	unsigned short *mux, pin;
+
+	mux = (unsigned short *)pinctrl->soc->functions[selector].mux;
+
+	while (*mux) {
+		pin = P_IDENT(*mux);
+
+		range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+		if (range == NULL) /* should not happen */
+			return;
+
+		port = container_of(range->gc, struct gpio_port, chip);
+
+		spin_lock_irqsave(&port->lock, flags);
+
+		port_setup(port, pin_to_offset(range, pin), true);
+		mux++;
+
+		spin_unlock_irqrestore(&port->lock, flags);
+	}
+}
+
+static int adi_pinmux_get_funcs_count(struct pinctrl_dev *pctldev)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->soc->nfunctions;
+}
+
+static const char *adi_pinmux_get_func_name(struct pinctrl_dev *pctldev,
+					  unsigned selector)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pinctrl->soc->functions[selector].name;
+}
+
+static int adi_pinmux_get_groups(struct pinctrl_dev *pctldev, unsigned selector,
+			       const char * const **groups,
+			       unsigned * const num_groups)
+{
+	struct adi_pinctrl *pinctrl = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pinctrl->soc->functions[selector].groups;
+	*num_groups = pinctrl->soc->functions[selector].num_groups;
+	return 0;
+}
+
+static int adi_pinmux_request_gpio(struct pinctrl_dev *pctldev,
+	struct pinctrl_gpio_range *range, unsigned pin)
+{
+	struct gpio_port *port;
+	unsigned long flags;
+	u8 offset;
+
+	port = container_of(range->gc, struct gpio_port, chip);
+	offset = pin_to_offset(range, pin);
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	port_setup(port, offset, true);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 0;
+}
+
+static struct pinmux_ops adi_pinmux_ops = {
+	.enable = adi_pinmux_enable,
+	.disable = adi_pinmux_disable,
+	.get_functions_count = adi_pinmux_get_funcs_count,
+	.get_function_name = adi_pinmux_get_func_name,
+	.get_function_groups = adi_pinmux_get_groups,
+	.gpio_request_enable = adi_pinmux_request_gpio,
+};
+
+
+static struct pinctrl_desc adi_pinmux_desc = {
+	.name = DRIVER_NAME,
+	.pctlops = &adi_pctrl_ops,
+	.pmxops = &adi_pinmux_ops,
+	.owner = THIS_MODULE,
+};
+
+static int adi_gpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_request_gpio(chip->base + offset);
+}
+
+static void adi_gpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	pinctrl_free_gpio(chip->base + offset);
+}
+
+static int adi_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	struct gpio_port *port;
+	unsigned long flags;
+
+	port = container_of(chip, struct gpio_port, chip);
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	writew(BIT(offset), &port->regs->dir_clear);
+	writew(readw(&port->regs->inen) | BIT(offset), &port->regs->inen);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 0;
+}
+
+static void adi_gpio_set_value(struct gpio_chip *chip, unsigned offset,
+	int value)
+{
+	struct gpio_port *port = container_of(chip, struct gpio_port, chip);
+	struct gpio_port_t *regs = port->regs;
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	if (value)
+		writew(1 << offset, &regs->data_set);
+	else
+		writew(1 << offset, &regs->data_clear);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+}
+
+static int adi_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
+	int value)
+{
+	struct gpio_port *port = container_of(chip, struct gpio_port, chip);
+	struct gpio_port_t *regs = port->regs;
+	unsigned long flags;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	writew(readw(&regs->inen) & ~(1 << offset), &regs->inen);
+	adi_gpio_set_value(chip, offset, value);
+	writew(1 << offset, &regs->dir_set);
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return 0;
+}
+
+static int adi_gpio_get_value(struct gpio_chip *chip, unsigned offset)
+{
+	struct gpio_port *port = container_of(chip, struct gpio_port, chip);
+	struct gpio_port_t *regs = port->regs;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&port->lock, flags);
+
+	ret = !!(readw(&regs->data) & BIT(offset));
+
+	spin_unlock_irqrestore(&port->lock, flags);
+
+	return ret;
+}
+
+static int adi_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	struct gpio_port *port = container_of(chip, struct gpio_port, chip);
+
+	if (port->irq_base >= 0)
+		return irq_find_mapping(port->domain, offset);
+	else
+		return irq_create_mapping(port->domain, offset);
+}
+
+static int adi_pint_map_port(struct gpio_pint *pint, bool assign, u8 map,
+	struct irq_domain *domain)
+{
+	struct gpio_pint_regs *regs = pint->regs;
+	u32 map_mask;
+
+	if (pint->map_count > 1)
+		return -EINVAL;
+
+	pint->map_count++;
+
+	/* The map_mask of each gpio port is a 16-bit duplicate
+	 * of the 8-bit map. It can be set to either high 16 bits or low
+	 * 16 bits of the pint assignment register.
+	 */
+	map_mask = (map << 8) | map;
+	if (assign) {
+		map_mask <<= PINT_HI_OFFSET;
+		writel((readl(&regs->assign) & 0xFFFF) | map_mask,
+			&regs->assign);
+	} else
+		writel((readl(&regs->assign) & 0xFFFF0000) | map_mask,
+			&regs->assign);
+
+	pint->domain[assign] = domain;
+
+	return 0;
+}
+
+static int adi_gpio_pint_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct gpio_pint *pint;
+
+	pint = devm_kzalloc(dev, sizeof(struct gpio_pint), GFP_KERNEL);
+	if (!pint) {
+		dev_err(dev, "Memory alloc failed\n");
+		return -ENOMEM;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Invalid mem resource\n");
+		return -ENODEV;
+	}
+
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				     pdev->name)) {
+		dev_err(dev, "Region already claimed\n");
+		return -EBUSY;
+	}
+
+	pint->base = devm_ioremap(dev, res->start, resource_size(res));
+	if (!pint->base) {
+		dev_err(dev, "Could not ioremap\n");
+		return -ENOMEM;
+	}
+
+	pint->regs = (struct gpio_pint_regs *)pint->base;
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(dev, "Invalid IRQ resource\n");
+		return -ENODEV;
+	}
+
+	spin_lock_init(&pint->lock);
+
+	pint->irq = res->start;
+	pint->pint_map_port = adi_pint_map_port;
+	platform_set_drvdata(pdev, pint);
+
+	irq_set_chained_handler(pint->irq, adi_gpio_handle_pint_irq);
+	irq_set_handler_data(pint->irq, pint);
+
+	list_add_tail(&pint->node, &adi_pint_list);
+
+	return 0;
+}
+
+static int adi_gpio_pint_remove(struct platform_device *pdev)
+{
+	struct gpio_pint *pint = platform_get_drvdata(pdev);
+
+	list_del(&pint->node);
+	irq_set_handler(pint->irq, handle_simple_irq);
+
+	return 0;
+}
+
+static int adi_gpio_irq_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hwirq)
+{
+	struct gpio_port *port = d->host_data;
+
+	if (!port)
+		return -EINVAL;
+
+	irq_set_chip_data(irq, port);
+	irq_set_chip_and_handler(irq, &adi_gpio_irqchip,
+				handle_level_irq);
+
+	return 0;
+}
+
+const struct irq_domain_ops adi_gpio_irq_domain_ops = {
+	.map = adi_gpio_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int adi_gpio_init_int(struct gpio_port *port)
+{
+	struct device_node *node = port->dev->of_node;
+	struct gpio_pint *pint = port->pint;
+	int ret;
+
+	port->domain = irq_domain_add_linear(node, port->width,
+				&adi_gpio_irq_domain_ops, port);
+	if (!port->domain) {
+		dev_err(port->dev, "Failed to create irqdomain\n");
+		return -ENOSYS;
+	}
+
+	/* According to BF54x and BF60x HRM, pin interrupt devices are not
+	 * part of the GPIO port device. in GPIO interrupt mode, the GPIO
+	 * pins of multiple port devices can be routed into one pin interrupt
+	 * device. The mapping can be configured by setting pint assignment
+	 * register with the mapping value of different GPIO port. This is
+	 * done via function pint_map_port().
+	 */
+	ret = pint->pint_map_port(port->pint, port->pint_assign,
+			port->pint_map,	port->domain);
+	if (ret)
+		return ret;
+
+	if (port->irq_base >= 0) {
+		ret = irq_create_strict_mappings(port->domain, port->irq_base,
+					0, port->width);
+		if (ret) {
+			dev_err(port->dev, "Couldn't associate to domain\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+#define DEVNAME_SIZE 16
+
+static int adi_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct adi_pinctrl_gpio_platform_data *pdata;
+	struct resource *res;
+	struct gpio_port *port;
+	char pinctrl_devname[DEVNAME_SIZE];
+	static int gpio;
+	int ret = 0, ret1;
+
+	pdata = dev->platform_data;
+	if (!pdata)
+		return -EINVAL;
+
+	port = devm_kzalloc(dev, sizeof(struct gpio_port), GFP_KERNEL);
+	if (!port) {
+		dev_err(dev, "Memory alloc failed\n");
+		return -ENOMEM;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Invalid mem resource\n");
+		return -ENODEV;
+	}
+
+	if (!devm_request_mem_region(dev, res->start, resource_size(res),
+				     pdev->name)) {
+		dev_err(dev, "Region already claimed\n");
+		return -EBUSY;
+	}
+
+	port->base = devm_ioremap(dev, res->start, resource_size(res));
+	if (!port->base) {
+		dev_err(dev, "Could not ioremap\n");
+		return -ENOMEM;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res)
+		port->irq_base = -1;
+	else
+		port->irq_base = res->start;
+
+	port->width = pdata->port_width;
+	port->dev = dev;
+	port->regs = (struct gpio_port_t *)port->base;
+	port->pint_assign = pdata->pint_assign;
+	port->pint_map = pdata->pint_map;
+
+	port->pint = find_gpio_pint(pdata->pint_id);
+	if (port->pint) {
+		ret = adi_gpio_init_int(port);
+		if (ret)
+			return ret;
+	}
+
+	spin_lock_init(&port->lock);
+
+	platform_set_drvdata(pdev, port);
+
+	port->chip.label		= "adi-gpio";
+	port->chip.direction_input	= adi_gpio_direction_input;
+	port->chip.get			= adi_gpio_get_value;
+	port->chip.direction_output	= adi_gpio_direction_output;
+	port->chip.set			= adi_gpio_set_value;
+	port->chip.request		= adi_gpio_request;
+	port->chip.free			= adi_gpio_free;
+	port->chip.to_irq		= adi_gpio_to_irq;
+	if (pdata->port_gpio_base > 0)
+		port->chip.base		= pdata->port_gpio_base;
+	else
+		port->chip.base		= gpio;
+	port->chip.ngpio		= port->width;
+	gpio = port->chip.base + port->width;
+
+	ret = gpiochip_add(&port->chip);
+	if (ret) {
+		dev_err(&pdev->dev, "Fail to add GPIO chip.\n");
+		goto out_remove_domain;
+	}
+
+	/* Add gpio pin range */
+	snprintf(pinctrl_devname, DEVNAME_SIZE, "pinctrl-adi2.%d",
+		pdata->pinctrl_id);
+	pinctrl_devname[DEVNAME_SIZE - 1] = 0;
+	ret = gpiochip_add_pin_range(&port->chip, pinctrl_devname,
+		0, pdata->port_pin_base, port->width);
+	if (ret) {
+		dev_err(&pdev->dev, "Fail to add pin range to %s.\n",
+				pinctrl_devname);
+		goto out_remove_gpiochip;
+	}
+
+	list_add_tail(&port->node, &adi_gpio_port_list);
+
+	return 0;
+
+out_remove_gpiochip:
+	ret1 = gpiochip_remove(&port->chip);
+out_remove_domain:
+	if (port->pint)
+		irq_domain_remove(port->domain);
+
+	return ret;
+}
+
+static int adi_gpio_remove(struct platform_device *pdev)
+{
+	struct gpio_port *port = platform_get_drvdata(pdev);
+	int ret;
+	u8 offset;
+
+	list_del(&port->node);
+	gpiochip_remove_pin_ranges(&port->chip);
+	ret = gpiochip_remove(&port->chip);
+	if (port->pint) {
+		for (offset = 0; offset < port->width; offset++)
+			irq_dispose_mapping(irq_find_mapping(port->domain,
+				offset));
+		irq_domain_remove(port->domain);
+	}
+
+	return ret;
+}
+
+static int adi_pinctrl_probe(struct platform_device *pdev)
+{
+	struct adi_pinctrl *pinctrl;
+
+	pinctrl = devm_kzalloc(&pdev->dev, sizeof(*pinctrl), GFP_KERNEL);
+	if (!pinctrl)
+		return -ENOMEM;
+
+	pinctrl->dev = &pdev->dev;
+
+	adi_pinctrl_soc_init(&pinctrl->soc);
+
+	adi_pinmux_desc.pins = pinctrl->soc->pins;
+	adi_pinmux_desc.npins = pinctrl->soc->npins;
+
+	/* Now register the pin controller and all pins it handles */
+	pinctrl->pctl = pinctrl_register(&adi_pinmux_desc, &pdev->dev, pinctrl);
+	if (!pinctrl->pctl) {
+		dev_err(&pdev->dev, "could not register pinctrl ADI2 driver\n");
+		return -EINVAL;
+	}
+
+	platform_set_drvdata(pdev, pinctrl);
+
+	return 0;
+}
+
+static int adi_pinctrl_remove(struct platform_device *pdev)
+{
+	struct adi_pinctrl *pinctrl = platform_get_drvdata(pdev);
+
+	pinctrl_unregister(pinctrl->pctl);
+
+	return 0;
+}
+
+static struct platform_driver adi_pinctrl_driver = {
+	.probe		= adi_pinctrl_probe,
+	.remove		= adi_pinctrl_remove,
+	.driver		= {
+		.name	= DRIVER_NAME,
+	},
+};
+
+static struct platform_driver adi_gpio_pint_driver = {
+	.probe		= adi_gpio_pint_probe,
+	.remove		= adi_gpio_pint_remove,
+	.driver		= {
+		.name	= "adi-gpio-pint",
+	},
+};
+
+static struct platform_driver adi_gpio_driver = {
+	.probe		= adi_gpio_probe,
+	.remove		= adi_gpio_remove,
+	.driver		= {
+		.name	= "adi-gpio",
+	},
+};
+
+static int __init adi_pinctrl_setup(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&adi_pinctrl_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&adi_gpio_pint_driver);
+	if (ret)
+		goto pint_error;
+
+	ret = platform_driver_register(&adi_gpio_driver);
+	if (ret)
+		goto gpio_error;
+
+#ifdef CONFIG_PM
+	register_syscore_ops(&gpio_pm_syscore_ops);
+#endif
+	return ret;
+gpio_error:
+	platform_driver_unregister(&adi_gpio_pint_driver);
+pint_error:
+	platform_driver_unregister(&adi_pinctrl_driver);
+
+	return ret;
+}
+arch_initcall(adi_pinctrl_setup);
+
+MODULE_AUTHOR("Sonic Zhang <sonic.zhang@analog.com>");
+MODULE_DESCRIPTION("ADI gpio2 pin control driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pinctrl/pinctrl-adi2.h b/drivers/pinctrl/pinctrl-adi2.h
new file mode 100644
index 000000000000..1f06f8df1fa3
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-adi2.h
@@ -0,0 +1,75 @@
+/*
+ * Pinctrl Driver for ADI GPIO2 controller
+ *
+ * Copyright 2007-2013 Analog Devices Inc.
+ *
+ * Licensed under the GPLv2 or later
+ */
+
+#ifndef PINCTRL_PINCTRL_ADI2_H
+#define PINCTRL_PINCTRL_ADI2_H
+
+#include <linux/pinctrl/pinctrl.h>
+
+ /**
+ * struct adi_pin_group - describes a pin group
+ * @name: the name of this pin group
+ * @pins: an array of pins
+ * @num: the number of pins in this array
+ */
+struct adi_pin_group {
+	const char *name;
+	const unsigned *pins;
+	const unsigned num;
+};
+
+#define ADI_PIN_GROUP(n, p)  \
+	{			\
+		.name = n,	\
+		.pins = p,	\
+		.num = ARRAY_SIZE(p),	\
+	}
+
+ /**
+ * struct adi_pmx_func - describes function mux setting of pin groups
+ * @name: the name of this function mux setting
+ * @groups: an array of pin groups
+ * @num_groups: the number of pin groups in this array
+ * @mux: the function mux setting array, end by zero
+ */
+struct adi_pmx_func {
+	const char *name;
+	const char * const *groups;
+	const unsigned num_groups;
+	const unsigned short *mux;
+};
+
+#define ADI_PMX_FUNCTION(n, g, m)		\
+	{					\
+		.name = n,			\
+		.groups = g,			\
+		.num_groups = ARRAY_SIZE(g),	\
+		.mux = m,			\
+	}
+
+/**
+ * struct adi_pinctrl_soc_data - ADI pin controller per-SoC configuration
+ * @functions:  The functions supported on this SoC.
+ * @nfunction:  The number of entries in @functions.
+ * @groups:     An array describing all pin groups the pin SoC supports.
+ * @ngroups:    The number of entries in @groups.
+ * @pins:       An array describing all pins the pin controller affects.
+ * @npins:      The number of entries in @pins.
+ */
+struct adi_pinctrl_soc_data {
+	const struct adi_pmx_func *functions;
+	int nfunctions;
+	const struct adi_pin_group *groups;
+	int ngroups;
+	const struct pinctrl_pin_desc *pins;
+	int npins;
+};
+
+void adi_pinctrl_soc_init(const struct adi_pinctrl_soc_data **soc);
+
+#endif /* PINCTRL_PINCTRL_ADI2_H */
diff --git a/include/linux/platform_data/pinctrl-adi2.h b/include/linux/platform_data/pinctrl-adi2.h
new file mode 100644
index 000000000000..8f91300617ec
--- /dev/null
+++ b/include/linux/platform_data/pinctrl-adi2.h
@@ -0,0 +1,40 @@
+/*
+ * Pinctrl Driver for ADI GPIO2 controller
+ *
+ * Copyright 2007-2013 Analog Devices Inc.
+ *
+ * Licensed under the GPLv2 or later
+ */
+
+
+#ifndef PINCTRL_ADI2_H
+#define PINCTRL_ADI2_H
+
+#include <linux/io.h>
+#include <linux/platform_device.h>
+
+/**
+ * struct adi_pinctrl_gpio_platform_data - Pinctrl gpio platform data
+ * for ADI GPIO2 device.
+ *
+ * @port_gpio_base: Optional global GPIO index of the GPIO bank.
+ *                 0 means driver decides.
+ * @port_pin_base: Pin index of the pin controller device.
+ * @port_width: PIN number of the GPIO bank device
+ * @pint_id: GPIO PINT device id that this GPIO bank should map to.
+ * @pint_assign: The 32-bit GPIO PINT registers can be divided into 2 parts. A
+ *               GPIO bank can be mapped into either low 16 bits[0] or high 16
+ *               bits[1] of each PINT register.
+ * @pint_map: GIOP bank mapping code in PINT device
+ */
+struct adi_pinctrl_gpio_platform_data {
+	unsigned int port_gpio_base;
+	unsigned int port_pin_base;
+	unsigned int port_width;
+	u8 pinctrl_id;
+	u8 pint_id;
+	bool pint_assign;
+	u8 pint_map;
+};
+
+#endif
-- 
cgit 


From 5d4e7e8db0544ec53025383bac49a3328affdad3 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 13 Sep 2013 11:40:01 +0300
Subject: Bluetooth: Add synchronization train parameters reading support

This patch adds support for reading the synchronization train parameters
for controllers that support the feature. Since the feature is
detectable through the local features page 2, which is retreived only in
stage 3 of the HCI init sequence, there is no other option than to add a
fourth stage to the init sequence.

For now the patch doesn't yet add storing of the parameters, but it is
nevertheless convenient to have around to see what kind of parameters
various controllers use by default (analyzable e.g. with the btmon user
space tool).

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  2 ++
 net/bluetooth/hci_core.c    | 15 ++++++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 52bd2488ff4a..f7197a0ac759 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -835,6 +835,8 @@ struct hci_cp_write_le_host_supported {
 	__u8	simul;
 } __packed;
 
+#define HCI_OP_READ_SYNC_TRAIN_PARAMS	0x0c77
+
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
 struct hci_rp_read_local_version {
 	__u8     status;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b24d2fa02c2f..ea542e07b2e9 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -648,6 +648,15 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 	}
 }
 
+static void hci_init4_req(struct hci_request *req, unsigned long opt)
+{
+	struct hci_dev *hdev = req->hdev;
+
+	/* Check for Synchronization Train support */
+	if (hdev->features[2][0] & 0x04)
+		hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL);
+}
+
 static int __hci_init(struct hci_dev *hdev)
 {
 	int err;
@@ -667,7 +676,11 @@ static int __hci_init(struct hci_dev *hdev)
 	if (err < 0)
 		return err;
 
-	return __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT);
+	err = __hci_req_sync(hdev, hci_init3_req, 0, HCI_INIT_TIMEOUT);
+	if (err < 0)
+		return err;
+
+	return __hci_req_sync(hdev, hci_init4_req, 0, HCI_INIT_TIMEOUT);
 }
 
 static void hci_scan_req(struct hci_request *req, unsigned long opt)
-- 
cgit 


From d62e6d67a776fe6a0a725e2835e4f9e16e8db512 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 13 Sep 2013 11:40:02 +0300
Subject: Bluetooth: Add event mask page 2 setting support

For those controller that support the HCI_Set_Event_Mask_Page_2 command
we should include it in the init sequence. This patch implements sending
of the command and enables the events in it based on supported features
(currently only CSB is checked).

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h |  2 ++
 net/bluetooth/hci_core.c    | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index f7197a0ac759..22d6e664612a 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -823,6 +823,8 @@ struct hci_rp_read_inq_rsp_tx_power {
 	__s8     tx_power;
 } __packed;
 
+#define HCI_OP_SET_EVENT_MASK_PAGE_2	0x0c63
+
 #define HCI_OP_READ_FLOW_CONTROL_MODE	0x0c66
 struct hci_rp_read_flow_control_mode {
 	__u8     status;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ea542e07b2e9..3d9f02b2f010 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -607,6 +607,34 @@ static void hci_set_le_support(struct hci_request *req)
 			    &cp);
 }
 
+static void hci_set_event_mask_page_2(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	u8 events[8] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
+
+	/* If Connectionless Slave Broadcast master role is supported
+	 * enable all necessary events for it.
+	 */
+	if (hdev->features[2][0] & 0x01) {
+		events[1] |= 0x40;	/* Triggered Clock Capture */
+		events[1] |= 0x80;	/* Synchronization Train Complete */
+		events[2] |= 0x10;	/* Slave Page Response Timeout */
+		events[2] |= 0x20;	/* CSB Channel Map Change */
+	}
+
+	/* If Connectionless Slave Broadcast slave role is supported
+	 * enable all necessary events for it.
+	 */
+	if (hdev->features[2][0] & 0x02) {
+		events[2] |= 0x01;	/* Synchronization Train Received */
+		events[2] |= 0x02;	/* CSB Receive */
+		events[2] |= 0x04;	/* CSB Timeout */
+		events[2] |= 0x08;	/* Truncated Page Complete */
+	}
+
+	hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events);
+}
+
 static void hci_init3_req(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
@@ -652,6 +680,10 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
 
+	/* Set event mask page 2 if the HCI command for it is supported */
+	if (hdev->commands[22] & 0x04)
+		hci_set_event_mask_page_2(req);
+
 	/* Check for Synchronization Train support */
 	if (hdev->features[2][0] & 0x04)
 		hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL);
-- 
cgit 


From 35a85ac60618521d41cfdb14f3fbfc8ad7329e9e Mon Sep 17 00:00:00 2001
From: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Thu, 19 Sep 2013 11:13:41 -0700
Subject: drm/i915: Add second slice l3 remapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Certain HSW SKUs have a second bank of L3. This L3 remapping has a
separate register set, and interrupt from the first "slice". A slice is
simply a term to define some subset of the GPU's l3 cache. This patch
implements both the interrupt handler, and ability to communicate with
userspace about this second slice.

v2:  Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE
Handle the case where we get 2 slice interrupts concurrently, and switch
the tracking of interrupts to be non-destructive (all Ville)
Don't enable/mask the second slice parity interrupt for ivb/vlv (even
though all docs I can find claim it's rsvd) (Ville + Bryan)
Keep BYT excluded from L3 parity

v3: Fix the slice = ffs to be decremented by one (found by Ville). When
I initially did my testing on the series, I was using 1-based slice
counting, so this code was correct. Not sure why my simpler tests that
I've been running since then didn't pick it up sooner.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h         |  7 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 26 +++++-----
 drivers/gpu/drm/i915/i915_irq.c         | 89 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_reg.h         |  7 +++
 drivers/gpu/drm/i915/i915_sysfs.c       | 34 ++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 ++-
 include/uapi/drm/i915_drm.h             |  8 +--
 7 files changed, 117 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8b16d47280f9..c6e8df737566 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -917,9 +917,11 @@ struct i915_ums_state {
 	int mm_suspended;
 };
 
+#define MAX_L3_SLICES 2
 struct intel_l3_parity {
-	u32 *remap_info;
+	u32 *remap_info[MAX_L3_SLICES];
 	struct work_struct error_work;
+	int which_slice;
 };
 
 struct i915_gem_mm {
@@ -1686,6 +1688,7 @@ struct drm_i915_file_private {
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
 #define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
@@ -1946,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev);
+void i915_gem_l3_remap(struct drm_device *dev, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d00d24f7a976..21a3d69679ee 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4222,16 +4222,15 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev)
+void i915_gem_l3_remap(struct drm_device *dev, int slice)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	u32 misccpctl;
 	int i;
 
-	if (!HAS_L3_GPU_CACHE(dev))
-		return;
-
-	if (!dev_priv->l3_parity.remap_info)
+	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
 		return;
 
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
@@ -4239,17 +4238,17 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
-		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+		u32 remap = I915_READ(reg_base + i);
+		if (remap && remap != remap_info[i/4])
 			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  GEN7_L3LOG_BASE + i, remap);
-		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+				  reg_base + i, remap);
+		if (remap && !remap_info[i/4])
 			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+		I915_WRITE(reg_base + i, remap_info[i/4]);
 	}
 
 	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(GEN7_L3LOG_BASE);
+	POSTING_READ(reg_base);
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
@@ -4343,7 +4342,7 @@ int
 i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4362,7 +4361,8 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	i915_gem_l3_remap(dev);
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(dev, i);
 
 	i915_gem_init_swizzling(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a610f5abcc41..60a7bac4fc3b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -888,9 +888,10 @@ static void ivybridge_parity_work(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    l3_parity.error_work);
 	u32 error_status, row, bank, subbank;
-	char *parity_event[5];
+	char *parity_event[6];
 	uint32_t misccpctl;
 	unsigned long flags;
+	uint8_t slice = 0;
 
 	/* We must turn off DOP level clock gating to access the L3 registers.
 	 * In order to prevent a get/put style interface, acquire struct mutex
@@ -898,45 +899,64 @@ static void ivybridge_parity_work(struct work_struct *work)
 	 */
 	mutex_lock(&dev_priv->dev->struct_mutex);
 
+	/* If we've screwed up tracking, just let the interrupt fire again */
+	if (WARN_ON(!dev_priv->l3_parity.which_slice))
+		goto out;
+
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 	POSTING_READ(GEN7_MISCCPCTL);
 
-	error_status = I915_READ(GEN7_L3CDERRST1);
-	row = GEN7_PARITY_ERROR_ROW(error_status);
-	bank = GEN7_PARITY_ERROR_BANK(error_status);
-	subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+	while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) {
+		u32 reg;
 
-	I915_WRITE(GEN7_L3CDERRST1, GEN7_PARITY_ERROR_VALID |
-				    GEN7_L3CDERRST1_ENABLE);
-	POSTING_READ(GEN7_L3CDERRST1);
+		slice--;
+		if (WARN_ON_ONCE(slice >= NUM_L3_SLICES(dev_priv->dev)))
+			break;
 
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+		dev_priv->l3_parity.which_slice &= ~(1<<slice);
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	ilk_enable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+		reg = GEN7_L3CDERRST1 + (slice * 0x200);
 
-	mutex_unlock(&dev_priv->dev->struct_mutex);
+		error_status = I915_READ(reg);
+		row = GEN7_PARITY_ERROR_ROW(error_status);
+		bank = GEN7_PARITY_ERROR_BANK(error_status);
+		subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+
+		I915_WRITE(reg, GEN7_PARITY_ERROR_VALID | GEN7_L3CDERRST1_ENABLE);
+		POSTING_READ(reg);
+
+		parity_event[0] = I915_L3_PARITY_UEVENT "=1";
+		parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
+		parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
+		parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
+		parity_event[4] = kasprintf(GFP_KERNEL, "SLICE=%d", slice);
+		parity_event[5] = NULL;
+
+		kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
+				   KOBJ_CHANGE, parity_event);
 
-	parity_event[0] = I915_L3_PARITY_UEVENT "=1";
-	parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
-	parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
-	parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
-	parity_event[4] = NULL;
+		DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n",
+			  slice, row, bank, subbank);
 
-	kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
-			   KOBJ_CHANGE, parity_event);
+		kfree(parity_event[4]);
+		kfree(parity_event[3]);
+		kfree(parity_event[2]);
+		kfree(parity_event[1]);
+	}
 
-	DRM_DEBUG("Parity error: Row = %d, Bank = %d, Sub bank = %d.\n",
-		  row, bank, subbank);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
-	kfree(parity_event[3]);
-	kfree(parity_event[2]);
-	kfree(parity_event[1]);
+out:
+	WARN_ON(dev_priv->l3_parity.which_slice);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	ilk_enable_gt_irq(dev_priv, GT_PARITY_ERROR(dev_priv->dev));
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	mutex_unlock(&dev_priv->dev->struct_mutex);
 }
 
-static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
+static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
@@ -944,9 +964,16 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	ilk_disable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+	ilk_disable_gt_irq(dev_priv, GT_PARITY_ERROR(dev));
 	spin_unlock(&dev_priv->irq_lock);
 
+	iir &= GT_PARITY_ERROR(dev);
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1)
+		dev_priv->l3_parity.which_slice |= 1 << 1;
+
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
+		dev_priv->l3_parity.which_slice |= 1 << 0;
+
 	queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work);
 }
 
@@ -981,8 +1008,8 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		i915_handle_error(dev, false);
 	}
 
-	if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
-		ivybridge_parity_error_irq_handler(dev);
+	if (gt_iir & GT_PARITY_ERROR(dev))
+		ivybridge_parity_error_irq_handler(dev, gt_iir);
 }
 
 #define HPD_STORM_DETECT_PERIOD 1000
@@ -2221,8 +2248,8 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	dev_priv->gt_irq_mask = ~0;
 	if (HAS_L3_GPU_CACHE(dev)) {
 		/* L3 parity interrupt is always unmasked. */
-		dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-		gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
+		gt_irqs |= GT_PARITY_ERROR(dev);
 	}
 
 	gt_irqs |= GT_RENDER_USER_INTERRUPT;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index af6f93ca7296..c4f9bef6d073 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -927,6 +927,7 @@
 #define GT_BLT_USER_INTERRUPT			(1 << 22)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -937,6 +938,10 @@
 #define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
 #define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
 
+#define GT_PARITY_ERROR(dev) \
+	(GT_RENDER_L3_PARITY_ERROR_INTERRUPT | \
+	 IS_HASWELL(dev) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0)
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
@@ -4747,6 +4752,7 @@
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1			0xB008 /* L3CD Error Status 1 */
+#define HSW_L3CDERRST11			0xB208 /* L3CD Error Status register 1 slice 1 */
 #define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
 #define   GEN7_PARITY_ERROR_VALID	(1<<13)
 #define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
@@ -4760,6 +4766,7 @@
 #define   GEN7_L3CDERRST1_ENABLE	(1<<7)
 
 #define GEN7_L3LOG_BASE			0xB070
+#define HSW_L3LOG_BASE_SLICE1		0xB270
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	0xe100 /* IVB GT1 + VLV */
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 71f6de24444e..3a8bf0c9b5ce 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -119,6 +119,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	uint32_t misccpctl;
+	int slice = (int)(uintptr_t)attr->private;
 	int i, ret;
 
 	count = round_down(count, 4);
@@ -134,9 +135,9 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 		return ret;
 
 	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info)
+		if (dev_priv->l3_parity.remap_info[slice])
 			memcpy(buf,
-			       dev_priv->l3_parity.remap_info + (offset/4),
+			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
 			       count);
 		else
 			memset(buf, 0, count);
@@ -168,6 +169,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
+	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
 	ret = l3_access_valid(drm_dev, offset);
@@ -178,7 +180,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (!dev_priv->l3_parity.remap_info) {
+	if (!dev_priv->l3_parity.remap_info[slice]) {
 		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!temp) {
 			mutex_unlock(&drm_dev->struct_mutex);
@@ -198,11 +200,11 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	 * at this point it is left as a TODO.
 	*/
 	if (temp)
-		dev_priv->l3_parity.remap_info = temp;
+		dev_priv->l3_parity.remap_info[slice] = temp;
 
-	memcpy(dev_priv->l3_parity.remap_info + (offset/4), buf, count);
+	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev);
+	i915_gem_l3_remap(drm_dev, slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
@@ -214,7 +216,17 @@ static struct bin_attribute dpf_attrs = {
 	.size = GEN7_L3LOG_SIZE,
 	.read = i915_l3_read,
 	.write = i915_l3_write,
-	.mmap = NULL
+	.mmap = NULL,
+	.private = (void *)0
+};
+
+static struct bin_attribute dpf_attrs_1 = {
+	.attr = {.name = "l3_parity_slice_1", .mode = (S_IRUSR | S_IWUSR)},
+	.size = GEN7_L3LOG_SIZE,
+	.read = i915_l3_read,
+	.write = i915_l3_write,
+	.mmap = NULL,
+	.private = (void *)1
 };
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
@@ -525,6 +537,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
+
+		if (NUM_L3_SLICES(dev) > 1) {
+			ret = device_create_bin_file(&dev->primary->kdev,
+						     &dpf_attrs_1);
+			if (ret)
+				DRM_ERROR("l3 parity slice 1 setup failed\n");
+		}
 	}
 
 	ret = 0;
@@ -548,6 +567,7 @@ void i915_teardown_sysfs(struct drm_device *dev)
 		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
 	else
 		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 686e5b23481d..958b7d8fea8b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -570,7 +570,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
 }
@@ -1000,7 +1000,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
+					 GT_PARITY_ERROR(dev)));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
@@ -1020,8 +1020,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 55bb5729bd78..3a4e97bd8607 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -38,10 +38,10 @@
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
  *	event from the gpu l3 cache. Additional information supplied is ROW,
- *	BANK, SUBBANK of the affected cacheline. Userspace should keep track of
- *	these events and if a specific cache-line seems to have a persistent
- *	error remap it with the l3 remapping tool supplied in intel-gpu-tools.
- *	The value supplied with the event is always 1.
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events and if a specific cache-line seems to have a
+ *	persistent error remap it with the l3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
  *	hangcheck. The error detection event is a good indicator of when things
-- 
cgit 


From 9a27d5916b1d0338f76a4a8cb6fabc5320664453 Mon Sep 17 00:00:00 2001
From: Guoqing Li <ligq@marvell.com>
Date: Fri, 13 Sep 2013 14:59:45 +0800
Subject: video: mmp: rb swap setting update for mmp display

We could set rb swap in two modules: DMA controler input part and
dsi interface output part.
DMA input part is based on pix_fmt to set rbswap, dsi output interface
part will set rbswap based on platform dsi_rbswap configuration.

This patch include below change and enhancement:

1) The input format which support rbswap is based on RGB format,
eg. RGB565 indicates the source data in memory is that Red is [15~11],
Green is [10~5], Blue is [4:0], Red is MSB, Blue is LSB, but for the
display dma input default setting(rbswap = 0), it only support Blue
is [15~11], Green is [10~5], Red is [4:0], Red is LSB, Blue is MSB,
so for this format(RGB565), display controller need to set rbswap
 = 1 and it can support the MSB/LSB correctly.
BGR/YUV format will not set it in mmp display driver.

2) The dsi output part of rbswap is depend on dsi_rbswap which is
defined in specific platfrom. For output dsi interface, it has this
feature to do rbswap again if it needs specifc byte sequence of RGB
byte for DSI panel.
eg. If display content is set RGB565 in memory and DMA input part set
rbswap in driver to support Red as MSB , Blue LSB, but dsi panel only
support Red as LSB, Blue as MSB, then it can use this feature.
If there is no this requirement of panel, this dsi output part is not
needed.

Signed-off-by: Guoqing Li <ligq@marvell.com>
Signed-off-by: Jett.Zhou <jtzhou@marvell.com>
Signed-off-by: Zhou Zhu <zzhu3@marvell.com>
Reviewed-by: Daniel Drake <dsd@laptop.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/mmp/hw/mmp_ctrl.c | 19 +++++++++++--------
 drivers/video/mmp/hw/mmp_ctrl.h |  5 +++++
 include/video/mmp_disp.h        |  1 +
 3 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/video/mmp/hw/mmp_ctrl.c b/drivers/video/mmp/hw/mmp_ctrl.c
index 75dca19bf214..a40d95a54eec 100644
--- a/drivers/video/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/mmp/hw/mmp_ctrl.c
@@ -60,8 +60,7 @@ static irqreturn_t ctrl_handle_irq(int irq, void *dev_id)
 
 static u32 fmt_to_reg(struct mmp_overlay *overlay, int pix_fmt)
 {
-	u32 link_config = path_to_path_plat(overlay->path)->link_config;
-	u32 rbswap, uvswap = 0, yuvswap = 0,
+	u32 rbswap = 0, uvswap = 0, yuvswap = 0,
 		csc_en = 0, val = 0,
 		vid = overlay_is_vid(overlay);
 
@@ -71,27 +70,23 @@ static u32 fmt_to_reg(struct mmp_overlay *overlay, int pix_fmt)
 	case PIXFMT_RGB888PACK:
 	case PIXFMT_RGB888UNPACK:
 	case PIXFMT_RGBA888:
-		rbswap = !(link_config & 0x1);
+		rbswap = 1;
 		break;
 	case PIXFMT_VYUY:
 	case PIXFMT_YVU422P:
 	case PIXFMT_YVU420P:
-		rbswap = link_config & 0x1;
 		uvswap = 1;
 		break;
 	case PIXFMT_YUYV:
-		rbswap = link_config & 0x1;
 		yuvswap = 1;
 		break;
 	default:
-		rbswap = link_config & 0x1;
 		break;
 	}
 
 	switch (pix_fmt) {
 	case PIXFMT_RGB565:
 	case PIXFMT_BGR565:
-		val = 0;
 		break;
 	case PIXFMT_RGB1555:
 	case PIXFMT_BGR1555:
@@ -248,7 +243,8 @@ static void path_set_mode(struct mmp_path *path, struct mmp_mode *mode)
 {
 	struct lcd_regs *regs = path_regs(path);
 	u32 total_x, total_y, vsync_ctrl, tmp, sclk_src, sclk_div,
-		link_config = path_to_path_plat(path)->link_config;
+		link_config = path_to_path_plat(path)->link_config,
+		dsi_rbswap = path_to_path_plat(path)->link_config;
 
 	/* FIXME: assert videomode supported */
 	memcpy(&path->mode, mode, sizeof(struct mmp_mode));
@@ -263,6 +259,12 @@ static void path_set_mode(struct mmp_path *path, struct mmp_mode *mode)
 	tmp |= CFG_DUMB_ENA(1);
 	writel_relaxed(tmp, ctrl_regs(path) + intf_ctrl(path->id));
 
+	/* interface rb_swap setting */
+	tmp = readl_relaxed(ctrl_regs(path) + intf_rbswap_ctrl(path->id)) &
+		(~(CFG_INTFRBSWAP_MASK));
+	tmp |= dsi_rbswap & CFG_INTFRBSWAP_MASK;
+	writel_relaxed(tmp, ctrl_regs(path) + intf_rbswap_ctrl(path->id));
+
 	writel_relaxed((mode->yres << 16) | mode->xres, &regs->screen_active);
 	writel_relaxed((mode->left_margin << 16) | mode->right_margin,
 		&regs->screen_h_porch);
@@ -419,6 +421,7 @@ static int path_init(struct mmphw_path_plat *path_plat,
 	path_plat->path = path;
 	path_plat->path_config = config->path_config;
 	path_plat->link_config = config->link_config;
+	path_plat->dsi_rbswap = config->dsi_rbswap;
 	path_set_default(path);
 
 	kfree(path_info);
diff --git a/drivers/video/mmp/hw/mmp_ctrl.h b/drivers/video/mmp/hw/mmp_ctrl.h
index edd2002b0e99..53301cfdb1ae 100644
--- a/drivers/video/mmp/hw/mmp_ctrl.h
+++ b/drivers/video/mmp/hw/mmp_ctrl.h
@@ -163,6 +163,8 @@ struct lcd_regs {
 
 #define LCD_SCLK(path) ((PATH_PN == path->id) ? LCD_CFG_SCLK_DIV :\
 	((PATH_TV == path->id) ? LCD_TCLK_DIV : LCD_PN2_SCLK_DIV))
+#define intf_rbswap_ctrl(id)	((id) ? (((id) & 1) ? LCD_TVIF_CTRL : \
+				PN2_IOPAD_CONTROL) : LCD_TOP_CTRL)
 
 /* dither configure */
 #ifdef CONFIG_CPU_PXA988
@@ -615,6 +617,8 @@ struct lcd_regs {
 #define LCD_SPU_DUMB_CTRL			0x01B8
 #define	 CFG_DUMBMODE(mode)			((mode)<<28)
 #define	 CFG_DUMBMODE_MASK			0xF0000000
+#define	 CFG_INTFRBSWAP(mode)			((mode)<<24)
+#define	 CFG_INTFRBSWAP_MASK			0x0F000000
 #define	 CFG_LCDGPIO_O(data)			((data)<<20)
 #define	 CFG_LCDGPIO_O_MASK			0x0FF00000
 #define	 CFG_LCDGPIO_ENA(gpio)			((gpio)<<12)
@@ -1427,6 +1431,7 @@ struct mmphw_path_plat {
 	struct mmp_path *path;
 	u32 path_config;
 	u32 link_config;
+	u32 dsi_rbswap;
 };
 
 /* mmp ctrl describes mmp controller related info */
diff --git a/include/video/mmp_disp.h b/include/video/mmp_disp.h
index b9dd1fbb0082..32094c052deb 100644
--- a/include/video/mmp_disp.h
+++ b/include/video/mmp_disp.h
@@ -334,6 +334,7 @@ struct mmp_mach_path_config {
 	int output_type;
 	u32 path_config;
 	u32 link_config;
+	u32 dsi_rbswap;
 };
 
 struct mmp_mach_plat_info {
-- 
cgit 


From 24586d8342ab27bc75e4560d71e98f3e5dc67d8e Mon Sep 17 00:00:00 2001
From: Jing Xiang <jxiang@marvell.com>
Date: Fri, 13 Sep 2013 14:59:49 +0800
Subject: video: mmp: add pitch info in mmp_win structure

Add pitch length info of graphics/video layer, pitch is used
to represent line length in byte, the usage depends on pix_fmt.
If the fmt is YUV, the pitch[0] will be Y length,pitch[1]
will be U length, pitch[2] will be V lenth.
If the fmt is RGB, the picth[0] will be line lenth, and
pitch[1]/pitch[2] will be 0 and not be used.

Signed-off-by: Jing Xiang <jxiang@marvell.com>
Signed-off-by: Jett.Zhou <jtzhou@marvell.com>
Signed-off-by: Zhou Zhu <zzhu3@marvell.com>
Reviewed-by: Daniel Drake <dsd@laptop.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/mmp/fb/mmpfb.c    |  6 ++++++
 drivers/video/mmp/hw/mmp_ctrl.c | 30 +++++++++++++++++++++++-------
 include/video/mmp_disp.h        |  5 +++++
 3 files changed, 34 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/video/mmp/fb/mmpfb.c b/drivers/video/mmp/fb/mmpfb.c
index 19fd913f462d..7ab31eb76a8c 100644
--- a/drivers/video/mmp/fb/mmpfb.c
+++ b/drivers/video/mmp/fb/mmpfb.c
@@ -395,12 +395,18 @@ static int var_update(struct fb_info *info)
 static void mmpfb_set_win(struct fb_info *info)
 {
 	struct mmpfb_info *fbi = info->par;
+	struct fb_var_screeninfo *var = &info->var;
 	struct mmp_win win;
+	u32 stride;
 
 	memset(&win, 0, sizeof(win));
 	win.xsrc = win.xdst = fbi->mode.xres;
 	win.ysrc = win.ydst = fbi->mode.yres;
 	win.pix_fmt = fbi->pix_fmt;
+	stride = pixfmt_to_stride(win.pix_fmt);
+	win.pitch[0] = var->xres_virtual * stride;
+	win.pitch[1] = win.pitch[2] =
+		(stride == 1) ? (var->xres_virtual >> 1) : 0;
 	mmp_overlay_set_win(fbi->overlay, &win);
 }
 
diff --git a/drivers/video/mmp/hw/mmp_ctrl.c b/drivers/video/mmp/hw/mmp_ctrl.c
index c0eb8bccfb87..ae724aaaad47 100644
--- a/drivers/video/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/mmp/hw/mmp_ctrl.c
@@ -142,17 +142,27 @@ static void dmafetch_set_fmt(struct mmp_overlay *overlay)
 static void overlay_set_win(struct mmp_overlay *overlay, struct mmp_win *win)
 {
 	struct lcd_regs *regs = path_regs(overlay->path);
-	u32 pitch;
 
 	/* assert win supported */
 	memcpy(&overlay->win, win, sizeof(struct mmp_win));
 
 	mutex_lock(&overlay->access_ok);
-	pitch = win->xsrc * pixfmt_to_stride(win->pix_fmt);
-	writel_relaxed(pitch, &regs->g_pitch);
-	writel_relaxed((win->ysrc << 16) | win->xsrc, &regs->g_size);
-	writel_relaxed((win->ydst << 16) | win->xdst, &regs->g_size_z);
-	writel_relaxed(0, &regs->g_start);
+
+	if (overlay_is_vid(overlay)) {
+		writel_relaxed(win->pitch[0], &regs->v_pitch_yc);
+		writel_relaxed(win->pitch[2] << 16 |
+				win->pitch[1], &regs->v_pitch_uv);
+
+		writel_relaxed((win->ysrc << 16) | win->xsrc, &regs->v_size);
+		writel_relaxed((win->ydst << 16) | win->xdst, &regs->v_size_z);
+		writel_relaxed(win->ypos << 16 | win->xpos, &regs->v_start);
+	} else {
+		writel_relaxed(win->pitch[0], &regs->g_pitch);
+
+		writel_relaxed((win->ysrc << 16) | win->xsrc, &regs->g_size);
+		writel_relaxed((win->ydst << 16) | win->xdst, &regs->g_size_z);
+		writel_relaxed(win->ypos << 16 | win->xpos, &regs->g_start);
+	}
 
 	dmafetch_set_fmt(overlay);
 	mutex_unlock(&overlay->access_ok);
@@ -234,7 +244,13 @@ static int overlay_set_addr(struct mmp_overlay *overlay, struct mmp_addr *addr)
 
 	/* FIXME: assert addr supported */
 	memcpy(&overlay->addr, addr, sizeof(struct mmp_addr));
-	writel(addr->phys[0], &regs->g_0);
+
+	if (overlay_is_vid(overlay)) {
+		writel_relaxed(addr->phys[0], &regs->v_y0);
+		writel_relaxed(addr->phys[1], &regs->v_u0);
+		writel_relaxed(addr->phys[2], &regs->v_v0);
+	} else
+		writel_relaxed(addr->phys[0], &regs->g_0);
 
 	return overlay->addr.phys[0];
 }
diff --git a/include/video/mmp_disp.h b/include/video/mmp_disp.h
index 32094c052deb..9fd9398368d5 100644
--- a/include/video/mmp_disp.h
+++ b/include/video/mmp_disp.h
@@ -91,6 +91,11 @@ struct mmp_win {
 	u16	up_crop;
 	u16	bottom_crop;
 	int	pix_fmt;
+	/*
+	 * pitch[0]: graphics/video layer line length or y pitch
+	 * pitch[1]/pitch[2]: video u/v pitch if non-zero
+	 */
+	u32	pitch[3];
 };
 
 struct mmp_addr {
-- 
cgit 


From 9bd721c55c8a886b938a45198aab0ccb52f1f7fa Mon Sep 17 00:00:00 2001
From: Jason Low <jason.low2@hp.com>
Date: Fri, 13 Sep 2013 11:26:52 -0700
Subject: sched/balancing: Consider max cost of idle balance per sched domain

In this patch, we keep track of the max cost we spend doing idle load balancing
for each sched domain. If the avg time the CPU remains idle is less then the
time we have already spent on idle balancing + the max cost of idle balancing
in the sched domain, then we don't continue to attempt the balance. We also
keep a per rq variable, max_idle_balance_cost, which keeps track of the max
time spent on newidle load balances throughout all its domains so that we can
determine the avg_idle's max value.

By using the max, we avoid overrunning the average. This further reduces the
chance we attempt balancing when the CPU is not idle for longer than the cost
to balance.

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379096813-3032-3-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/metag/include/asm/topology.h |  1 +
 include/linux/sched.h             |  1 +
 include/linux/topology.h          |  3 +++
 kernel/sched/core.c               |  3 ++-
 kernel/sched/fair.c               | 16 ++++++++++++++++
 kernel/sched/sched.h              |  3 +++
 6 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h
index 23f5118f58db..db192924f4b0 100644
--- a/arch/metag/include/asm/topology.h
+++ b/arch/metag/include/asm/topology.h
@@ -26,6 +26,7 @@
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
+	.max_newidle_lb_cost	= 0,			\
 }
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6682da36b293..be078ff9157f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -810,6 +810,7 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	u64 last_update;
+	u64 max_newidle_lb_cost;
 
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
diff --git a/include/linux/topology.h b/include/linux/topology.h
index d3cf0d6e7712..e2a2c3da2929 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -106,6 +106,7 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.smt_gain		= 1178,	/* 15% */			\
+	.max_newidle_lb_cost	= 0,					\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
@@ -135,6 +136,7 @@ int arch_update_cpu_topology(void);
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
+	.max_newidle_lb_cost	= 0,					\
 }
 #endif
 #endif /* CONFIG_SCHED_MC */
@@ -166,6 +168,7 @@ int arch_update_cpu_topology(void);
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
+	.max_newidle_lb_cost	= 0,					\
 }
 #endif
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 048f39e45761..c2283c54aed0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1330,7 +1330,7 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 
 	if (rq->idle_stamp) {
 		u64 delta = rq_clock(rq) - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
+		u64 max = 2*rq->max_idle_balance_cost;
 
 		update_avg(&rq->avg_idle, delta);
 
@@ -6506,6 +6506,7 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
+		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
 		INIT_LIST_HEAD(&rq->cfs_tasks);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0784ab6fcc59..ffc99d8f0a95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5396,6 +5396,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
+	u64 curr_cost = 0;
 
 	this_rq->idle_stamp = rq_clock(this_rq);
 
@@ -5412,15 +5413,27 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 		int continue_balancing = 1;
+		u64 t0, domain_cost;
 
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
+			break;
+
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			t0 = sched_clock_cpu(this_cpu);
+
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance(this_cpu, this_rq,
 						   sd, CPU_NEWLY_IDLE,
 						   &continue_balancing);
+
+			domain_cost = sched_clock_cpu(this_cpu) - t0;
+			if (domain_cost > sd->max_newidle_lb_cost)
+				sd->max_newidle_lb_cost = domain_cost;
+
+			curr_cost += domain_cost;
 		}
 
 		interval = msecs_to_jiffies(sd->balance_interval);
@@ -5442,6 +5455,9 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
+
+	if (curr_cost > this_rq->max_idle_balance_cost)
+		this_rq->max_idle_balance_cost = curr_cost;
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0d7544c3dba7..e82484db7699 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -476,6 +476,9 @@ struct rq {
 	u64 age_stamp;
 	u64 idle_stamp;
 	u64 avg_idle;
+
+	/* This is used to determine avg_idle's max value */
+	u64 max_idle_balance_cost;
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
-- 
cgit 


From f48627e686a69f5215cb0761e731edb3d9859dd9 Mon Sep 17 00:00:00 2001
From: Jason Low <jason.low2@hp.com>
Date: Fri, 13 Sep 2013 11:26:53 -0700
Subject: sched/balancing: Periodically decay max cost of idle balance

This patch builds on patch 2 and periodically decays that max value to
do idle balancing per sched domain by approximately 1% per second. Also
decay the rq's max_idle_balance_cost value.

Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379096813-3032-4-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/metag/include/asm/topology.h |  1 +
 include/linux/sched.h             |  3 +++
 include/linux/topology.h          |  3 +++
 kernel/sched/fair.c               | 38 +++++++++++++++++++++++++++++++-------
 4 files changed, 38 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h
index db192924f4b0..8e9c0b3b9691 100644
--- a/arch/metag/include/asm/topology.h
+++ b/arch/metag/include/asm/topology.h
@@ -27,6 +27,7 @@
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
 	.max_newidle_lb_cost	= 0,			\
+	.next_decay_max_lb_cost	= jiffies,		\
 }
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index be078ff9157f..b5344de1658b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -810,7 +810,10 @@ struct sched_domain {
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
 	u64 last_update;
+
+	/* idle_balance() stats */
 	u64 max_newidle_lb_cost;
+	unsigned long next_decay_max_lb_cost;
 
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
diff --git a/include/linux/topology.h b/include/linux/topology.h
index e2a2c3da2929..12ae6ce997d6 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -107,6 +107,7 @@ int arch_update_cpu_topology(void);
 	.balance_interval	= 1,					\
 	.smt_gain		= 1178,	/* 15% */			\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_SMT */
@@ -137,6 +138,7 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 #endif /* CONFIG_SCHED_MC */
@@ -169,6 +171,7 @@ int arch_update_cpu_topology(void);
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
 	.max_newidle_lb_cost	= 0,					\
+	.next_decay_max_lb_cost	= jiffies,				\
 }
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ffc99d8f0a95..2b89cd244b0d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5681,15 +5681,39 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
-	int need_serialize;
+	int need_serialize, need_decay = 0;
+	u64 max_cost = 0;
 
 	update_blocked_averages(cpu);
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
+		/*
+		 * Decay the newidle max times here because this is a regular
+		 * visit to all the domains. Decay ~1% per second.
+		 */
+		if (time_after(jiffies, sd->next_decay_max_lb_cost)) {
+			sd->max_newidle_lb_cost =
+				(sd->max_newidle_lb_cost * 253) / 256;
+			sd->next_decay_max_lb_cost = jiffies + HZ;
+			need_decay = 1;
+		}
+		max_cost += sd->max_newidle_lb_cost;
+
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!continue_balancing) {
+			if (need_decay)
+				continue;
+			break;
+		}
+
 		interval = sd->balance_interval;
 		if (idle != CPU_IDLE)
 			interval *= sd->busy_factor;
@@ -5723,14 +5747,14 @@ out:
 			next_balance = sd->last_balance + interval;
 			update_next_balance = 1;
 		}
-
+	}
+	if (need_decay) {
 		/*
-		 * Stop the load balance at this level. There is another
-		 * CPU in our sched group which is doing load balancing more
-		 * actively.
+		 * Ensure the rq-wide value also decays but keep it at a
+		 * reasonable floor to avoid funnies with rq->avg_idle.
 		 */
-		if (!continue_balancing)
-			break;
+		rq->max_idle_balance_cost =
+			max((u64)sysctl_sched_migration_cost, max_cost);
 	}
 	rcu_read_unlock();
 
-- 
cgit 


From 6112fe60ac1bd1e68da8cc4248289d6e48015f9b Mon Sep 17 00:00:00 2001
From: Laxman Dewangan <ldewangan@nvidia.com>
Date: Fri, 20 Sep 2013 18:00:10 +0530
Subject: regmap: add helper macro to set min/max range of register

Add helper macro to set the min and max value of the register range.

This is useful when initialising the register ranges of the device like

static const struct regmap_range readable_ranges[] = {
	regmap_reg_range(DEVICE_REG0, DEVICE_REG10),
};

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/regmap.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index a10380bfbeac..7d3ae2be6869 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -70,6 +70,8 @@ struct regmap_range {
 	unsigned int range_max;
 };
 
+#define regmap_reg_range(low, high) { .range_min = low, .range_max = high, }
+
 /*
  * A table of ranges including some yes ranges and some no ranges.
  * If a register belongs to a no_range, the corresponding check function
-- 
cgit 


From 3e1e3aae1f5d4e8e5edb7e332f6e265597cc5b0a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Sep 2013 09:10:03 -0700
Subject: net_sched: add u64 rate to psched_ratecfg_precompute()

Add an extra u64 rate parameter to psched_ratecfg_precompute()
so that some qdisc can opt-in for 64bit rates in the future,
to overcome the ~34 Gbits limit.

psched_ratecfg_getrate() reports a legacy structure to
tc utility, so if actual rate is above the 32bit rate field,
cap it to the 34Gbit limit.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 11 +++++++++--
 net/sched/act_police.c    |  4 ++--
 net/sched/sch_generic.c   |  5 +++--
 net/sched/sch_htb.c       |  4 ++--
 net/sched/sch_tbf.c       |  4 ++--
 5 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f4eb365f7dcd..d0a6321c302e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -702,13 +702,20 @@ static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
 }
 
 void psched_ratecfg_precompute(struct psched_ratecfg *r,
-			       const struct tc_ratespec *conf);
+			       const struct tc_ratespec *conf,
+			       u64 rate64);
 
 static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
 					  const struct psched_ratecfg *r)
 {
 	memset(res, 0, sizeof(*res));
-	res->rate = r->rate_bytes_ps;
+
+	/* legacy struct tc_ratespec has a 32bit @rate field
+	 * Qdisc using 64bit rate should add new attributes
+	 * in order to maintain compatibility.
+	 */
+	res->rate = min_t(u64, r->rate_bytes_ps, ~0U);
+
 	res->overhead = r->overhead;
 	res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
 }
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 189e3c5b3d09..272d8e924cf6 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,14 +231,14 @@ override:
 	}
 	if (R_tab) {
 		police->rate_present = true;
-		psched_ratecfg_precompute(&police->rate, &R_tab->rate);
+		psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0);
 		qdisc_put_rtab(R_tab);
 	} else {
 		police->rate_present = false;
 	}
 	if (P_tab) {
 		police->peak_present = true;
-		psched_ratecfg_precompute(&police->peak, &P_tab->rate);
+		psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0);
 		qdisc_put_rtab(P_tab);
 	} else {
 		police->peak_present = false;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a74e278654aa..e7121d29c4bd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -910,11 +910,12 @@ void dev_shutdown(struct net_device *dev)
 }
 
 void psched_ratecfg_precompute(struct psched_ratecfg *r,
-			       const struct tc_ratespec *conf)
+			       const struct tc_ratespec *conf,
+			       u64 rate64)
 {
 	memset(r, 0, sizeof(*r));
 	r->overhead = conf->overhead;
-	r->rate_bytes_ps = conf->rate;
+	r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
 	r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
 	r->mult = 1;
 	/*
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 863846cc5513..6b126f6c9957 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1491,8 +1491,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			cl->prio = TC_HTB_NUMPRIO - 1;
 	}
 
-	psched_ratecfg_precompute(&cl->rate, &hopt->rate);
-	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
+	psched_ratecfg_precompute(&cl->rate, &hopt->rate, 0);
+	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, 0);
 
 	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
 	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1aaf1b6e51a2..b0571224f3c9 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -341,9 +341,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	psched_ratecfg_precompute(&q->rate, &rtab->rate);
+	psched_ratecfg_precompute(&q->rate, &rtab->rate, 0);
 	if (ptab) {
-		psched_ratecfg_precompute(&q->peak, &ptab->rate);
+		psched_ratecfg_precompute(&q->peak, &ptab->rate, 0);
 		q->peak_present = true;
 	} else {
 		q->peak_present = false;
-- 
cgit 


From df62cdf348c91baac61b4cb19d19ea1ef87b271e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Sep 2013 09:10:20 -0700
Subject: net_sched: htb: support of 64bit rates

HTB already can deal with 64bit rates, we only have to add two new
attributes so that tc can use them to break the current 32bit ABI
barrier.

TCA_HTB_RATE64 : class rate  (in bytes per second)
TCA_HTB_CEIL64 : class ceil  (in bytes per second)

This allows us to setup HTB on 40Gbps links, as 32bit limit is
actually ~34Gbps

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  2 ++
 net/sched/sch_htb.c            | 17 +++++++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 9b829134d422..f2624b549e61 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -357,6 +357,8 @@ enum {
 	TCA_HTB_CTAB,
 	TCA_HTB_RTAB,
 	TCA_HTB_DIRECT_QLEN,
+	TCA_HTB_RATE64,
+	TCA_HTB_CEIL64,
 	__TCA_HTB_MAX,
 };
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 6b126f6c9957..0e1e38b40025 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -997,6 +997,8 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
 	[TCA_HTB_CTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_HTB_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 },
+	[TCA_HTB_RATE64] = { .type = NLA_U64 },
+	[TCA_HTB_CEIL64] = { .type = NLA_U64 },
 };
 
 static void htb_work_func(struct work_struct *work)
@@ -1114,6 +1116,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 	opt.level = cl->level;
 	if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
+	if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) &&
+	    nla_put_u64(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps))
+		goto nla_put_failure;
+	if ((cl->ceil.rate_bytes_ps >= (1ULL << 32)) &&
+	    nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
+		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 	spin_unlock_bh(root_lock);
@@ -1332,6 +1340,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
 	struct nlattr *tb[TCA_HTB_MAX + 1];
 	struct tc_htb_opt *hopt;
+	u64 rate64, ceil64;
 
 	/* extract all subattrs from opt attr */
 	if (!opt)
@@ -1491,8 +1500,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			cl->prio = TC_HTB_NUMPRIO - 1;
 	}
 
-	psched_ratecfg_precompute(&cl->rate, &hopt->rate, 0);
-	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, 0);
+	rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
+
+	ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
+
+	psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
+	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
 
 	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
 	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
-- 
cgit 


From e8d895a4bb26167292c8c14ecdf61d02502e9c03 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:18 -0700
Subject: compat.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/compat.h | 48 +++++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/compat.h b/include/net/compat.h
index 6e9565324989..3b603b199c01 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -29,8 +29,8 @@ struct compat_cmsghdr {
 	compat_int_t	cmsg_type;
 };
 
-extern int compat_sock_get_timestamp(struct sock *, struct timeval __user *);
-extern int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
+int compat_sock_get_timestamp(struct sock *, struct timeval __user *);
+int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
 
 #else /* defined(CONFIG_COMPAT) */
 /*
@@ -40,24 +40,30 @@ extern int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
 #define compat_mmsghdr	mmsghdr
 #endif /* defined(CONFIG_COMPAT) */
 
-extern int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *);
-extern int verify_compat_iovec(struct msghdr *, struct iovec *, struct sockaddr_storage *, int);
-extern asmlinkage long compat_sys_sendmsg(int,struct compat_msghdr __user *,unsigned int);
-extern asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
-					   unsigned int, unsigned int);
-extern asmlinkage long compat_sys_recvmsg(int,struct compat_msghdr __user *,unsigned int);
-extern asmlinkage long compat_sys_recvmmsg(int, struct compat_mmsghdr __user *,
-					   unsigned int, unsigned int,
-					   struct compat_timespec __user *);
-extern asmlinkage long compat_sys_getsockopt(int, int, int, char __user *, int __user *);
-extern int put_cmsg_compat(struct msghdr*, int, int, int, void *);
-
-extern int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *, unsigned char *, int);
-
-extern int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int,
-	int (*)(struct sock *, int, int, char __user *, unsigned int));
-extern int compat_mc_getsockopt(struct sock *, int, int, char __user *,
-	int __user *, int (*)(struct sock *, int, int, char __user *,
-				int __user *));
+int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *);
+int verify_compat_iovec(struct msghdr *, struct iovec *,
+			struct sockaddr_storage *, int);
+asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
+				   unsigned int);
+asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
+				    unsigned int, unsigned int);
+asmlinkage long compat_sys_recvmsg(int, struct compat_msghdr __user *,
+				   unsigned int);
+asmlinkage long compat_sys_recvmmsg(int, struct compat_mmsghdr __user *,
+				    unsigned int, unsigned int,
+				    struct compat_timespec __user *);
+asmlinkage long compat_sys_getsockopt(int, int, int, char __user *,
+				      int __user *);
+int put_cmsg_compat(struct msghdr*, int, int, int, void *);
+
+int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *,
+				     unsigned char *, int);
+
+int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int,
+			 int (*)(struct sock *, int, int, char __user *,
+				 unsigned int));
+int compat_mc_getsockopt(struct sock *, int, int, char __user *, int __user *,
+			 int (*)(struct sock *, int, int, char __user *,
+				 int __user *));
 
 #endif /* NET_COMPAT_H */
-- 
cgit 


From 126c623b3980e7c2dd68777171f5b6b6ab352912 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:19 -0700
Subject: dcbevent.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dcbevent.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/dcbevent.h b/include/net/dcbevent.h
index 443626ed4cbc..d2f3041c0dfa 100644
--- a/include/net/dcbevent.h
+++ b/include/net/dcbevent.h
@@ -25,9 +25,9 @@ enum dcbevent_notif_type {
 };
 
 #ifdef CONFIG_DCB
-extern int register_dcbevent_notifier(struct notifier_block *nb);
-extern int unregister_dcbevent_notifier(struct notifier_block *nb);
-extern int call_dcbevent_notifiers(unsigned long val, void *v);
+int register_dcbevent_notifier(struct notifier_block *nb);
+int unregister_dcbevent_notifier(struct notifier_block *nb);
+int call_dcbevent_notifiers(unsigned long val, void *v);
 #else
 static inline int
 register_dcbevent_notifier(struct notifier_block *nb)
-- 
cgit 


From 59ddd965c2388720681eb4dc386bfb074e80788e Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:20 -0700
Subject: decnet (dn*.h): Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dn.h       | 20 +++++++++++---------
 include/net/dn_dev.h   | 30 +++++++++++++++---------------
 include/net/dn_fib.h   | 47 ++++++++++++++++++++++-------------------------
 include/net/dn_neigh.h | 12 ++++++------
 include/net/dn_nsp.h   | 49 ++++++++++++++++++++++++++-----------------------
 include/net/dn_route.h | 13 +++++++------
 6 files changed, 87 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/include/net/dn.h b/include/net/dn.h
index c88bf4ebd330..ccc15588d108 100644
--- a/include/net/dn.h
+++ b/include/net/dn.h
@@ -199,24 +199,26 @@ static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp)
 	fld->fld_dport = scp->addrrem;
 }
 
-extern unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu);
+unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu);
 
 #define DN_MENUVER_ACC 0x01
 #define DN_MENUVER_USR 0x02
 #define DN_MENUVER_PRX 0x04
 #define DN_MENUVER_UIC 0x08
 
-extern struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr);
-extern struct sock *dn_find_by_skb(struct sk_buff *skb);
+struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr);
+struct sock *dn_find_by_skb(struct sk_buff *skb);
 #define DN_ASCBUF_LEN 9
-extern char *dn_addr2asc(__u16, char *);
-extern int dn_destroy_timer(struct sock *sk);
+char *dn_addr2asc(__u16, char *);
+int dn_destroy_timer(struct sock *sk);
 
-extern int dn_sockaddr2username(struct sockaddr_dn *addr, unsigned char *buf, unsigned char type);
-extern int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *addr, unsigned char *type);
+int dn_sockaddr2username(struct sockaddr_dn *addr, unsigned char *buf,
+			 unsigned char type);
+int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *addr,
+			 unsigned char *type);
 
-extern void dn_start_slow_timer(struct sock *sk);
-extern void dn_stop_slow_timer(struct sock *sk);
+void dn_start_slow_timer(struct sock *sk);
+void dn_stop_slow_timer(struct sock *sk);
 
 extern __le16 decnet_address;
 extern int decnet_debug_level;
diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h
index b9e32db03f20..20b5ab06032d 100644
--- a/include/net/dn_dev.h
+++ b/include/net/dn_dev.h
@@ -148,27 +148,27 @@ struct rtnode_hello_message {
 } __packed;
 
 
-extern void dn_dev_init(void);
-extern void dn_dev_cleanup(void);
+void dn_dev_init(void);
+void dn_dev_cleanup(void);
 
-extern int dn_dev_ioctl(unsigned int cmd, void __user *arg);
+int dn_dev_ioctl(unsigned int cmd, void __user *arg);
 
-extern void dn_dev_devices_off(void);
-extern void dn_dev_devices_on(void);
+void dn_dev_devices_off(void);
+void dn_dev_devices_on(void);
 
-extern void dn_dev_init_pkt(struct sk_buff *skb);
-extern void dn_dev_veri_pkt(struct sk_buff *skb);
-extern void dn_dev_hello(struct sk_buff *skb);
+void dn_dev_init_pkt(struct sk_buff *skb);
+void dn_dev_veri_pkt(struct sk_buff *skb);
+void dn_dev_hello(struct sk_buff *skb);
 
-extern void dn_dev_up(struct net_device *);
-extern void dn_dev_down(struct net_device *);
+void dn_dev_up(struct net_device *);
+void dn_dev_down(struct net_device *);
 
-extern int dn_dev_set_default(struct net_device *dev, int force);
-extern struct net_device *dn_dev_get_default(void);
-extern int dn_dev_bind_default(__le16 *addr);
+int dn_dev_set_default(struct net_device *dev, int force);
+struct net_device *dn_dev_get_default(void);
+int dn_dev_bind_default(__le16 *addr);
 
-extern int register_dnaddr_notifier(struct notifier_block *nb);
-extern int unregister_dnaddr_notifier(struct notifier_block *nb);
+int register_dnaddr_notifier(struct notifier_block *nb);
+int unregister_dnaddr_notifier(struct notifier_block *nb);
 
 static inline int dn_dev_islocal(struct net_device *dev, __le16 addr)
 {
diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h
index 74004af31c48..f2ca135ddcc9 100644
--- a/include/net/dn_fib.h
+++ b/include/net/dn_fib.h
@@ -95,41 +95,38 @@ struct dn_fib_table {
 /*
  * dn_fib.c
  */
-extern void dn_fib_init(void);
-extern void dn_fib_cleanup(void);
-
-extern int dn_fib_ioctl(struct socket *sock, unsigned int cmd, 
-			unsigned long arg);
-extern struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, 
-				struct nlattr *attrs[],
-				const struct nlmsghdr *nlh, int *errp);
-extern int dn_fib_semantic_match(int type, struct dn_fib_info *fi, 
-			const struct flowidn *fld,
-			struct dn_fib_res *res);
-extern void dn_fib_release_info(struct dn_fib_info *fi);
-extern void dn_fib_flush(void);
-extern void dn_fib_select_multipath(const struct flowidn *fld,
-					struct dn_fib_res *res);
+void dn_fib_init(void);
+void dn_fib_cleanup(void);
+
+int dn_fib_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r,
+				       struct nlattr *attrs[],
+				       const struct nlmsghdr *nlh, int *errp);
+int dn_fib_semantic_match(int type, struct dn_fib_info *fi,
+			  const struct flowidn *fld, struct dn_fib_res *res);
+void dn_fib_release_info(struct dn_fib_info *fi);
+void dn_fib_flush(void);
+void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res);
 
 /*
  * dn_tables.c
  */
-extern struct dn_fib_table *dn_fib_get_table(u32 n, int creat);
-extern struct dn_fib_table *dn_fib_empty_table(void);
-extern void dn_fib_table_init(void);
-extern void dn_fib_table_cleanup(void);
+struct dn_fib_table *dn_fib_get_table(u32 n, int creat);
+struct dn_fib_table *dn_fib_empty_table(void);
+void dn_fib_table_init(void);
+void dn_fib_table_cleanup(void);
 
 /*
  * dn_rules.c
  */
-extern void dn_fib_rules_init(void);
-extern void dn_fib_rules_cleanup(void);
-extern unsigned int dnet_addr_type(__le16 addr);
-extern int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res);
+void dn_fib_rules_init(void);
+void dn_fib_rules_cleanup(void);
+unsigned int dnet_addr_type(__le16 addr);
+int dn_fib_lookup(struct flowidn *fld, struct dn_fib_res *res);
 
-extern int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb);
+int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb);
 
-extern void dn_fib_free_info(struct dn_fib_info *fi);
+void dn_fib_free_info(struct dn_fib_info *fi);
 
 static inline void dn_fib_info_put(struct dn_fib_info *fi)
 {
diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h
index 4cb4ae7fb81f..fac4e3f4a6d3 100644
--- a/include/net/dn_neigh.h
+++ b/include/net/dn_neigh.h
@@ -16,12 +16,12 @@ struct dn_neigh {
 	__u8 priority;
 };
 
-extern void dn_neigh_init(void);
-extern void dn_neigh_cleanup(void);
-extern int dn_neigh_router_hello(struct sk_buff *skb);
-extern int dn_neigh_endnode_hello(struct sk_buff *skb);
-extern void dn_neigh_pointopoint_hello(struct sk_buff *skb);
-extern int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n);
+void dn_neigh_init(void);
+void dn_neigh_cleanup(void);
+int dn_neigh_router_hello(struct sk_buff *skb);
+int dn_neigh_endnode_hello(struct sk_buff *skb);
+void dn_neigh_pointopoint_hello(struct sk_buff *skb);
+int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n);
 
 extern struct neigh_table dn_neigh_table;
 
diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h
index e43a2893f132..3a3e33d18456 100644
--- a/include/net/dn_nsp.h
+++ b/include/net/dn_nsp.h
@@ -15,29 +15,32 @@
 *******************************************************************************/
 /* dn_nsp.c functions prototyping */
 
-extern void dn_nsp_send_data_ack(struct sock *sk);
-extern void dn_nsp_send_oth_ack(struct sock *sk);
-extern void dn_nsp_delayed_ack(struct sock *sk);
-extern void dn_send_conn_ack(struct sock *sk);
-extern void dn_send_conn_conf(struct sock *sk, gfp_t gfp);
-extern void dn_nsp_send_disc(struct sock *sk, unsigned char type, 
-			unsigned short reason, gfp_t gfp);
-extern void dn_nsp_return_disc(struct sk_buff *skb, unsigned char type,
-				unsigned short reason);
-extern void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval);
-extern void dn_nsp_send_conninit(struct sock *sk, unsigned char flags);
-
-extern void dn_nsp_output(struct sock *sk);
-extern int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff_head *q, unsigned short acknum);
-extern void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, gfp_t gfp, int oob);
-extern unsigned long dn_nsp_persist(struct sock *sk);
-extern int dn_nsp_xmit_timeout(struct sock *sk);
-
-extern int dn_nsp_rx(struct sk_buff *);
-extern int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
-
-extern struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri);
-extern struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int noblock, long timeo, int *err);
+void dn_nsp_send_data_ack(struct sock *sk);
+void dn_nsp_send_oth_ack(struct sock *sk);
+void dn_nsp_delayed_ack(struct sock *sk);
+void dn_send_conn_ack(struct sock *sk);
+void dn_send_conn_conf(struct sock *sk, gfp_t gfp);
+void dn_nsp_send_disc(struct sock *sk, unsigned char type,
+		      unsigned short reason, gfp_t gfp);
+void dn_nsp_return_disc(struct sk_buff *skb, unsigned char type,
+			unsigned short reason);
+void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval);
+void dn_nsp_send_conninit(struct sock *sk, unsigned char flags);
+
+void dn_nsp_output(struct sock *sk);
+int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb,
+			    struct sk_buff_head *q, unsigned short acknum);
+void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, gfp_t gfp,
+		       int oob);
+unsigned long dn_nsp_persist(struct sock *sk);
+int dn_nsp_xmit_timeout(struct sock *sk);
+
+int dn_nsp_rx(struct sk_buff *);
+int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
+struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri);
+struct sk_buff *dn_alloc_send_skb(struct sock *sk, size_t *size, int noblock,
+				  long timeo, int *err);
 
 #define NSP_REASON_OK 0		/* No error */
 #define NSP_REASON_NR 1		/* No resources */
diff --git a/include/net/dn_route.h b/include/net/dn_route.h
index 2e9d317c82dc..b409ad6b8d7a 100644
--- a/include/net/dn_route.h
+++ b/include/net/dn_route.h
@@ -15,10 +15,11 @@
     GNU General Public License for more details.
 *******************************************************************************/
 
-extern struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri);
-extern int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *, struct sock *sk, int flags);
-extern int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb);
-extern void dn_rt_cache_flush(int delay);
+struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri);
+int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *,
+			 struct sock *sk, int flags);
+int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb);
+void dn_rt_cache_flush(int delay);
 
 /* Masks for flags field */
 #define DN_RT_F_PID 0x07 /* Mask for packet type                      */
@@ -92,8 +93,8 @@ static inline bool dn_is_output_route(struct dn_route *rt)
 	return rt->fld.flowidn_iif == 0;
 }
 
-extern void dn_route_init(void);
-extern void dn_route_cleanup(void);
+void dn_route_init(void);
+void dn_route_cleanup(void);
 
 #include <net/sock.h>
 #include <linux/if_arp.h>
-- 
cgit 


From a4023dd01a37f3a648ea028269f946cb55896337 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:21 -0700
Subject: dst.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 3bc4865f8267..211dcf1e758e 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -106,7 +106,7 @@ struct dst_entry {
 	};
 };
 
-extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
+u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
 extern const u32 dst_default_metrics[];
 
 #define DST_METRICS_READ_ONLY	0x1UL
@@ -119,7 +119,7 @@ static inline bool dst_metrics_read_only(const struct dst_entry *dst)
 	return dst->_metrics & DST_METRICS_READ_ONLY;
 }
 
-extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
+void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
 
 static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
 {
@@ -262,7 +262,7 @@ static inline struct dst_entry *dst_clone(struct dst_entry *dst)
 	return dst;
 }
 
-extern void dst_release(struct dst_entry *dst);
+void dst_release(struct dst_entry *dst);
 
 static inline void refdst_drop(unsigned long refdst)
 {
@@ -362,12 +362,11 @@ static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 	return child;
 }
 
-extern int dst_discard(struct sk_buff *skb);
-extern void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
-		       int initial_ref, int initial_obsolete,
-		       unsigned short flags);
-extern void __dst_free(struct dst_entry *dst);
-extern struct dst_entry *dst_destroy(struct dst_entry *dst);
+int dst_discard(struct sk_buff *skb);
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
+		int initial_obsolete, unsigned short flags);
+void __dst_free(struct dst_entry *dst);
+struct dst_entry *dst_destroy(struct dst_entry *dst);
 
 static inline void dst_free(struct dst_entry *dst)
 {
@@ -463,7 +462,7 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
-extern void		dst_init(void);
+void dst_init(void);
 
 /* Flags for xfrm_lookup flags argument. */
 enum {
@@ -480,9 +479,9 @@ static inline struct dst_entry *xfrm_lookup(struct net *net,
 	return dst_orig;
 } 
 #else
-extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
-				     const struct flowi *fl, struct sock *sk,
-				     int flags);
+struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+			      const struct flowi *fl, struct sock *sk,
+			      int flags);
 #endif
 
 #endif /* _NET_DST_H */
-- 
cgit 


From 7b3852a2fdd86238709038654f010befca5b47c3 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:22 -0700
Subject: esp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/esp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/esp.h b/include/net/esp.h
index d58451331dbd..1356dda00d22 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -13,7 +13,7 @@ struct esp_data {
 	struct crypto_aead *aead;
 };
 
-extern void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
+void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
 
 struct ip_esp_hdr;
 
-- 
cgit 


From 8de6879fa949b3817f19f145a491e93df8925bc0 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:23 -0700
Subject: fib_rules.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_rules.h | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 4b2b557fb0e8..e584de16e4c3 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -115,14 +115,13 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 	return frh->table;
 }
 
-extern struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *, struct net *);
-extern void fib_rules_unregister(struct fib_rules_ops *);
+struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *,
+					 struct net *);
+void fib_rules_unregister(struct fib_rules_ops *);
 
-extern int			fib_rules_lookup(struct fib_rules_ops *,
-						 struct flowi *, int flags,
-						 struct fib_lookup_arg *);
-extern int			fib_default_rule_add(struct fib_rules_ops *,
-						     u32 pref, u32 table,
-						     u32 flags);
-extern u32			fib_default_rule_pref(struct fib_rules_ops *ops);
+int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
+		     struct fib_lookup_arg *);
+int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
+			 u32 flags);
+u32 fib_default_rule_pref(struct fib_rules_ops *ops);
 #endif
-- 
cgit 


From 4787342c390a8e7570a81a62c9b361d7a4380893 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:24 -0700
Subject: flow.h/flow_keys.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow.h      | 11 ++++++-----
 include/net/flow_keys.h |  2 +-
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/flow.h b/include/net/flow.h
index 628e11b98c58..65ce471d2ab5 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -215,12 +215,13 @@ typedef struct flow_cache_object *(*flow_resolve_t)(
 		struct net *net, const struct flowi *key, u16 family,
 		u8 dir, struct flow_cache_object *oldobj, void *ctx);
 
-extern struct flow_cache_object *flow_cache_lookup(
-		struct net *net, const struct flowi *key, u16 family,
-		u8 dir, flow_resolve_t resolver, void *ctx);
+struct flow_cache_object *flow_cache_lookup(struct net *net,
+					    const struct flowi *key, u16 family,
+					    u8 dir, flow_resolve_t resolver,
+					    void *ctx);
 
-extern void flow_cache_flush(void);
-extern void flow_cache_flush_deferred(void);
+void flow_cache_flush(void);
+void flow_cache_flush_deferred(void);
 extern atomic_t flow_cache_genid;
 
 #endif
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index bb8271d487b7..ac2439d02f54 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -13,5 +13,5 @@ struct flow_keys {
 	u8 ip_proto;
 };
 
-extern bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
+bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
 #endif
-- 
cgit 


From 2008f21cbdc48761270cec119c8385584691cf34 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:25 -0700
Subject: garp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/garp.h | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/garp.h b/include/net/garp.h
index 834d8add9e5f..abf33bbd2e6a 100644
--- a/include/net/garp.h
+++ b/include/net/garp.h
@@ -112,19 +112,18 @@ struct garp_port {
 	struct rcu_head			rcu;
 };
 
-extern int	garp_register_application(struct garp_application *app);
-extern void	garp_unregister_application(struct garp_application *app);
-
-extern int	garp_init_applicant(struct net_device *dev,
-				    struct garp_application *app);
-extern void	garp_uninit_applicant(struct net_device *dev,
-				      struct garp_application *app);
-
-extern int	garp_request_join(const struct net_device *dev,
-				  const struct garp_application *app,
-				  const void *data, u8 len, u8 type);
-extern void	garp_request_leave(const struct net_device *dev,
-				   const struct garp_application *app,
-				   const void *data, u8 len, u8 type);
+int garp_register_application(struct garp_application *app);
+void garp_unregister_application(struct garp_application *app);
+
+int garp_init_applicant(struct net_device *dev, struct garp_application *app);
+void garp_uninit_applicant(struct net_device *dev,
+			   struct garp_application *app);
+
+int garp_request_join(const struct net_device *dev,
+		      const struct garp_application *app, const void *data,
+		      u8 len, u8 type);
+void garp_request_leave(const struct net_device *dev,
+			const struct garp_application *app,
+			const void *data, u8 len, u8 type);
 
 #endif /* _NET_GARP_H */
-- 
cgit 


From 8aae218f58f44471c6715e695da5ed9f54dd4491 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:26 -0700
Subject: gen_stats.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h | 51 ++++++++++++++++++++++++-------------------------
 1 file changed, 25 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index cf8439ba4d11..ea4271dceff0 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -19,32 +19,31 @@ struct gnet_dump {
 	struct tc_stats   tc_stats;
 };
 
-extern int gnet_stats_start_copy(struct sk_buff *skb, int type,
+int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
+			  struct gnet_dump *d);
+
+int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
+				 int tc_stats_type, int xstats_type,
 				 spinlock_t *lock, struct gnet_dump *d);
 
-extern int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
-					int tc_stats_type,int xstats_type,
-					spinlock_t *lock, struct gnet_dump *d);
-
-extern int gnet_stats_copy_basic(struct gnet_dump *d,
-				 struct gnet_stats_basic_packed *b);
-extern int gnet_stats_copy_rate_est(struct gnet_dump *d,
-				    const struct gnet_stats_basic_packed *b,
-				    struct gnet_stats_rate_est64 *r);
-extern int gnet_stats_copy_queue(struct gnet_dump *d,
-				 struct gnet_stats_queue *q);
-extern int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
-
-extern int gnet_stats_finish_copy(struct gnet_dump *d);
-
-extern int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
-			     struct gnet_stats_rate_est64 *rate_est,
-			     spinlock_t *stats_lock, struct nlattr *opt);
-extern void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
-			       struct gnet_stats_rate_est64 *rate_est);
-extern int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
-				 struct gnet_stats_rate_est64 *rate_est,
-				 spinlock_t *stats_lock, struct nlattr *opt);
-extern bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
-				 const struct gnet_stats_rate_est64 *rate_est);
+int gnet_stats_copy_basic(struct gnet_dump *d,
+			  struct gnet_stats_basic_packed *b);
+int gnet_stats_copy_rate_est(struct gnet_dump *d,
+			     const struct gnet_stats_basic_packed *b,
+			     struct gnet_stats_rate_est64 *r);
+int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q);
+int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
+
+int gnet_stats_finish_copy(struct gnet_dump *d);
+
+int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+		      struct gnet_stats_rate_est64 *rate_est,
+		      spinlock_t *stats_lock, struct nlattr *opt);
+void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_rate_est64 *rate_est);
+int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_rate_est64 *rate_est,
+			  spinlock_t *stats_lock, struct nlattr *opt);
+bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
+			  const struct gnet_stats_rate_est64 *rate_est);
 #endif
-- 
cgit 


From ff2b94d2c3d075d0f2fde330e3b5a73053c426c7 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:27 -0700
Subject: genetlink.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 8e0b6c856a13..9b787b62cf16 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -122,7 +122,7 @@ struct genl_ops {
 	struct list_head	ops_list;
 };
 
-extern int __genl_register_family(struct genl_family *family);
+int __genl_register_family(struct genl_family *family);
 
 static inline int genl_register_family(struct genl_family *family)
 {
@@ -130,8 +130,8 @@ static inline int genl_register_family(struct genl_family *family)
 	return __genl_register_family(family);
 }
 
-extern int __genl_register_family_with_ops(struct genl_family *family,
-	struct genl_ops *ops, size_t n_ops);
+int __genl_register_family_with_ops(struct genl_family *family,
+				    struct genl_ops *ops, size_t n_ops);
 
 static inline int genl_register_family_with_ops(struct genl_family *family,
 	struct genl_ops *ops, size_t n_ops)
@@ -140,18 +140,18 @@ static inline int genl_register_family_with_ops(struct genl_family *family,
 	return __genl_register_family_with_ops(family, ops, n_ops);
 }
 
-extern int genl_unregister_family(struct genl_family *family);
-extern int genl_register_ops(struct genl_family *, struct genl_ops *ops);
-extern int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
-extern int genl_register_mc_group(struct genl_family *family,
-				  struct genl_multicast_group *grp);
-extern void genl_unregister_mc_group(struct genl_family *family,
-				     struct genl_multicast_group *grp);
-extern void genl_notify(struct sk_buff *skb, struct net *net, u32 portid,
-			u32 group, struct nlmsghdr *nlh, gfp_t flags);
+int genl_unregister_family(struct genl_family *family);
+int genl_register_ops(struct genl_family *, struct genl_ops *ops);
+int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
+int genl_register_mc_group(struct genl_family *family,
+			   struct genl_multicast_group *grp);
+void genl_unregister_mc_group(struct genl_family *family,
+			      struct genl_multicast_group *grp);
+void genl_notify(struct sk_buff *skb, struct net *net, u32 portid,
+		 u32 group, struct nlmsghdr *nlh, gfp_t flags);
 
 void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
-				struct genl_family *family, int flags, u8 cmd);
+		  struct genl_family *family, int flags, u8 cmd);
 
 /**
  * genlmsg_nlhdr - Obtain netlink header from user specified header
-- 
cgit 


From e60ab84dd59cc0ddb46a7696a56f9de8b8b22f39 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 20 Sep 2013 11:23:28 -0700
Subject: icmp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/icmp.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/icmp.h b/include/net/icmp.h
index 081439fd070e..970028e13382 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -39,10 +39,10 @@ struct net_proto_family;
 struct sk_buff;
 struct net;
 
-extern void	icmp_send(struct sk_buff *skb_in,  int type, int code, __be32 info);
-extern int	icmp_rcv(struct sk_buff *skb);
-extern void	icmp_err(struct sk_buff *, u32 info);
-extern int	icmp_init(void);
-extern void	icmp_out_count(struct net *net, unsigned char type);
+void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info);
+int icmp_rcv(struct sk_buff *skb);
+void icmp_err(struct sk_buff *skb, u32 info);
+int icmp_init(void);
+void icmp_out_count(struct net *net, unsigned char type);
 
 #endif	/* _ICMP_H */
-- 
cgit 


From 2485602f1af209aaef3f394ac8336a67cb8742aa Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Sun, 18 Aug 2013 22:41:37 +0200
Subject: can: add explicit copyrights to can headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These files are copied to the source code of user space applications (in
this case can-utils) and so it makes sense to mention explicitly their
copyright. I added the terms of C code that was introduced in the same
commit as these headers.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Urs Thuermann <urs.thuermann@volkswagen.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can/bcm.h   | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/can/error.h | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/can/gw.h    | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/can/raw.h   | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 128 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h
index 3ebe387fea4d..382251a1d214 100644
--- a/include/uapi/linux/can/bcm.h
+++ b/include/uapi/linux/can/bcm.h
@@ -7,6 +7,38 @@
  * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
  * All rights reserved.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
  */
 
 #ifndef CAN_BCM_H
diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h
index 7b7148bded71..b63204545320 100644
--- a/include/uapi/linux/can/error.h
+++ b/include/uapi/linux/can/error.h
@@ -7,6 +7,38 @@
  * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
  * All rights reserved.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
  */
 
 #ifndef CAN_ERROR_H
diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h
index 4e27c82b564a..844c8964bdfe 100644
--- a/include/uapi/linux/can/gw.h
+++ b/include/uapi/linux/can/gw.h
@@ -7,6 +7,38 @@
  * Copyright (c) 2011 Volkswagen Group Electronic Research
  * All rights reserved.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
  */
 
 #ifndef CAN_GW_H
diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h
index a814062b0719..c7d8c334e0ce 100644
--- a/include/uapi/linux/can/raw.h
+++ b/include/uapi/linux/can/raw.h
@@ -8,6 +8,38 @@
  * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
  * All rights reserved.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
  */
 
 #ifndef CAN_RAW_H
-- 
cgit 


From 1c2da13c21a14e9db99c701412ac9069d5b91cf5 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Sat, 7 Sep 2013 21:34:38 +0200
Subject: can: add explicit copyrights to can's netlink header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This file is copied to the source code of user space applications (in
this case can-utils) and so it makes sense to mention explicitly their
copyright.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Wolfgang Grandegger <wg@grandegger.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can/netlink.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index 14966ddb7df1..df944ed206a8 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -5,6 +5,14 @@
  *
  * Copyright (c) 2009 Wolfgang Grandegger <wg@grandegger.com>
  *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
  */
 
 #ifndef CAN_NETLINK_H
-- 
cgit 


From 1fd51155387264e3ca72094abadcaadb3f5969f6 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:41 -0700
Subject: inet*.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_connection_sock.h | 32 +++++++--------
 include/net/inet6_hashtables.h      | 38 +++++++++---------
 include/net/inet_common.h           | 48 +++++++++++-----------
 include/net/inet_connection_sock.h  | 79 ++++++++++++++++++-------------------
 include/net/inet_hashtables.h       | 72 ++++++++++++++++-----------------
 include/net/inet_sock.h             |  4 +-
 include/net/inet_timewait_sock.h    | 37 +++++++++--------
 include/net/inetpeer.h              | 12 +++---
 8 files changed, 157 insertions(+), 165 deletions(-)

(limited to 'include')

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index 04642c920431..f981ba7adeed 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -22,27 +22,25 @@ struct sk_buff;
 struct sock;
 struct sockaddr;
 
-extern int inet6_csk_bind_conflict(const struct sock *sk,
-				   const struct inet_bind_bucket *tb, bool relax);
+int inet6_csk_bind_conflict(const struct sock *sk,
+			    const struct inet_bind_bucket *tb, bool relax);
 
-extern struct dst_entry* inet6_csk_route_req(struct sock *sk,
-					     struct flowi6 *fl6,
-					     const struct request_sock *req);
+struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6,
+				      const struct request_sock *req);
 
-extern struct request_sock *inet6_csk_search_req(const struct sock *sk,
-						 struct request_sock ***prevp,
-						 const __be16 rport,
-						 const struct in6_addr *raddr,
-						 const struct in6_addr *laddr,
-						 const int iif);
+struct request_sock *inet6_csk_search_req(const struct sock *sk,
+					  struct request_sock ***prevp,
+					  const __be16 rport,
+					  const struct in6_addr *raddr,
+					  const struct in6_addr *laddr,
+					  const int iif);
 
-extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
-					   struct request_sock *req,
-					   const unsigned long timeout);
+void inet6_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+				    const unsigned long timeout);
 
-extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
+void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
-extern int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl);
+int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl);
 
-extern struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu);
+struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET6_CONNECTION_SOCK_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fd4ee016ba5c..f52fa88feb64 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -53,7 +53,7 @@ static inline int inet6_sk_ehashfn(const struct sock *sk)
 	return inet6_ehashfn(net, laddr, lport, faddr, fport);
 }
 
-extern int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp);
+int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp);
 
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
@@ -61,21 +61,19 @@ extern int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp);
  *
  * The sockhash lock must be held as a reader here.
  */
-extern struct sock *__inet6_lookup_established(struct net *net,
-					   struct inet_hashinfo *hashinfo,
-					   const struct in6_addr *saddr,
-					   const __be16 sport,
-					   const struct in6_addr *daddr,
-					   const u16 hnum,
-					   const int dif);
-
-extern struct sock *inet6_lookup_listener(struct net *net,
-					  struct inet_hashinfo *hashinfo,
-					  const struct in6_addr *saddr,
-					  const __be16 sport,
-					  const struct in6_addr *daddr,
-					  const unsigned short hnum,
-					  const int dif);
+struct sock *__inet6_lookup_established(struct net *net,
+					struct inet_hashinfo *hashinfo,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif);
+
+struct sock *inet6_lookup_listener(struct net *net,
+				   struct inet_hashinfo *hashinfo,
+				   const struct in6_addr *saddr,
+				   const __be16 sport,
+				   const struct in6_addr *daddr,
+				   const unsigned short hnum, const int dif);
 
 static inline struct sock *__inet6_lookup(struct net *net,
 					  struct inet_hashinfo *hashinfo,
@@ -110,9 +108,9 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 			      inet6_iif(skb));
 }
 
-extern struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
-				 const struct in6_addr *saddr, const __be16 sport,
-				 const struct in6_addr *daddr, const __be16 dport,
-				 const int dif);
+struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+			  const struct in6_addr *saddr, const __be16 sport,
+			  const struct in6_addr *daddr, const __be16 dport,
+			  const int dif);
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 #endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 234008782c8c..fe7994c48b75 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -13,30 +13,30 @@ struct sock;
 struct sockaddr;
 struct socket;
 
-extern int inet_release(struct socket *sock);
-extern int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
-			       int addr_len, int flags);
-extern int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
-				 int addr_len, int flags);
-extern int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
-			      int addr_len, int flags);
-extern int inet_accept(struct socket *sock, struct socket *newsock, int flags);
-extern int inet_sendmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t size);
-extern ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
-			     size_t size, int flags);
-extern int inet_recvmsg(struct kiocb *iocb, struct socket *sock,
-			struct msghdr *msg, size_t size, int flags);
-extern int inet_shutdown(struct socket *sock, int how);
-extern int inet_listen(struct socket *sock, int backlog);
-extern void inet_sock_destruct(struct sock *sk);
-extern int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
-extern int inet_getname(struct socket *sock, struct sockaddr *uaddr,
-			int *uaddr_len, int peer);
-extern int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
-extern int inet_ctl_sock_create(struct sock **sk, unsigned short family,
-				unsigned short type, unsigned char protocol,
-				struct net *net);
+int inet_release(struct socket *sock);
+int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+			int addr_len, int flags);
+int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+			  int addr_len, int flags);
+int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
+		       int addr_len, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock, int flags);
+int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+		 size_t size);
+ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
+		      size_t size, int flags);
+int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+		 size_t size, int flags);
+int inet_shutdown(struct socket *sock, int how);
+int inet_listen(struct socket *sock, int backlog);
+void inet_sock_destruct(struct sock *sk);
+int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int inet_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len,
+		 int peer);
+int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+int inet_ctl_sock_create(struct sock **sk, unsigned short family,
+			 unsigned short type, unsigned char protocol,
+			 struct net *net);
 
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index de2c78529afa..c55aeed41ace 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -146,9 +146,9 @@ static inline void *inet_csk_ca(const struct sock *sk)
 	return (void *)inet_csk(sk)->icsk_ca_priv;
 }
 
-extern struct sock *inet_csk_clone_lock(const struct sock *sk,
-					const struct request_sock *req,
-					const gfp_t priority);
+struct sock *inet_csk_clone_lock(const struct sock *sk,
+				 const struct request_sock *req,
+				 const gfp_t priority);
 
 enum inet_csk_ack_state_t {
 	ICSK_ACK_SCHED	= 1,
@@ -157,11 +157,11 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_PUSHED2 = 8
 };
 
-extern void inet_csk_init_xmit_timers(struct sock *sk,
-				      void (*retransmit_handler)(unsigned long),
-				      void (*delack_handler)(unsigned long),
-				      void (*keepalive_handler)(unsigned long));
-extern void inet_csk_clear_xmit_timers(struct sock *sk);
+void inet_csk_init_xmit_timers(struct sock *sk,
+			       void (*retransmit_handler)(unsigned long),
+			       void (*delack_handler)(unsigned long),
+			       void (*keepalive_handler)(unsigned long));
+void inet_csk_clear_xmit_timers(struct sock *sk);
 
 static inline void inet_csk_schedule_ack(struct sock *sk)
 {
@@ -178,8 +178,8 @@ static inline void inet_csk_delack_init(struct sock *sk)
 	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
 }
 
-extern void inet_csk_delete_keepalive_timer(struct sock *sk);
-extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
+void inet_csk_delete_keepalive_timer(struct sock *sk);
+void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
 
 #ifdef INET_CSK_DEBUG
 extern const char inet_csk_timer_bug_msg[];
@@ -241,23 +241,21 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 #endif
 }
 
-extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
 
-extern struct request_sock *inet_csk_search_req(const struct sock *sk,
-						struct request_sock ***prevp,
-						const __be16 rport,
-						const __be32 raddr,
-						const __be32 laddr);
-extern int inet_csk_bind_conflict(const struct sock *sk,
-				  const struct inet_bind_bucket *tb, bool relax);
-extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
+struct request_sock *inet_csk_search_req(const struct sock *sk,
+					 struct request_sock ***prevp,
+					 const __be16 rport,
+					 const __be32 raddr,
+					 const __be32 laddr);
+int inet_csk_bind_conflict(const struct sock *sk,
+			   const struct inet_bind_bucket *tb, bool relax);
+int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
-extern struct dst_entry* inet_csk_route_req(struct sock *sk,
-					    struct flowi4 *fl4,
+struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4,
+				     const struct request_sock *req);
+struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk,
 					    const struct request_sock *req);
-extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk,
-						   struct sock *newsk,
-						   const struct request_sock *req);
 
 static inline void inet_csk_reqsk_queue_add(struct sock *sk,
 					    struct request_sock *req,
@@ -266,9 +264,8 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk,
 	reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
 }
 
-extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
-					  struct request_sock *req,
-					  unsigned long timeout);
+void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+				   unsigned long timeout);
 
 static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
 						struct request_sock *req)
@@ -315,13 +312,13 @@ static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
 	reqsk_free(req);
 }
 
-extern void inet_csk_reqsk_queue_prune(struct sock *parent,
-				       const unsigned long interval,
-				       const unsigned long timeout,
-				       const unsigned long max_rto);
+void inet_csk_reqsk_queue_prune(struct sock *parent,
+				const unsigned long interval,
+				const unsigned long timeout,
+				const unsigned long max_rto);
 
-extern void inet_csk_destroy_sock(struct sock *sk);
-extern void inet_csk_prepare_forced_close(struct sock *sk);
+void inet_csk_destroy_sock(struct sock *sk);
+void inet_csk_prepare_forced_close(struct sock *sk);
 
 /*
  * LISTEN is a special case for poll..
@@ -332,15 +329,15 @@ static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
 			(POLLIN | POLLRDNORM) : 0;
 }
 
-extern int  inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
-extern void inet_csk_listen_stop(struct sock *sk);
+int inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
+void inet_csk_listen_stop(struct sock *sk);
 
-extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
+void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
 
-extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
-				      char __user *optval, int __user *optlen);
-extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
-				      char __user *optval, unsigned int optlen);
+int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
+			       char __user *optval, int __user *optlen);
+int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
+			       char __user *optval, unsigned int optlen);
 
-extern struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
+struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
 #endif /* _INET_CONNECTION_SOCK_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ef83d9e844b5..594dfeead70f 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -218,22 +218,21 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 	}
 }
 
-extern struct inet_bind_bucket *
-		    inet_bind_bucket_create(struct kmem_cache *cachep,
-					    struct net *net,
-					    struct inet_bind_hashbucket *head,
-					    const unsigned short snum);
-extern void inet_bind_bucket_destroy(struct kmem_cache *cachep,
-				     struct inet_bind_bucket *tb);
-
-static inline int inet_bhashfn(struct net *net,
-		const __u16 lport, const int bhash_size)
+struct inet_bind_bucket *
+inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
+			struct inet_bind_hashbucket *head,
+			const unsigned short snum);
+void inet_bind_bucket_destroy(struct kmem_cache *cachep,
+			      struct inet_bind_bucket *tb);
+
+static inline int inet_bhashfn(struct net *net, const __u16 lport,
+			       const int bhash_size)
 {
 	return (lport + net_hash_mix(net)) & (bhash_size - 1);
 }
 
-extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
-			   const unsigned short snum);
+void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
+		    const unsigned short snum);
 
 /* These can have wildcards, don't try too hard. */
 static inline int inet_lhashfn(struct net *net, const unsigned short num)
@@ -247,23 +246,22 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk)
 }
 
 /* Caller must disable local BH processing. */
-extern int __inet_inherit_port(struct sock *sk, struct sock *child);
+int __inet_inherit_port(struct sock *sk, struct sock *child);
 
-extern void inet_put_port(struct sock *sk);
+void inet_put_port(struct sock *sk);
 
 void inet_hashinfo_init(struct inet_hashinfo *h);
 
-extern int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw);
-extern void inet_hash(struct sock *sk);
-extern void inet_unhash(struct sock *sk);
+int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw);
+void inet_hash(struct sock *sk);
+void inet_unhash(struct sock *sk);
 
-extern struct sock *__inet_lookup_listener(struct net *net,
-					   struct inet_hashinfo *hashinfo,
-					   const __be32 saddr,
-					   const __be16 sport,
-					   const __be32 daddr,
-					   const unsigned short hnum,
-					   const int dif);
+struct sock *__inet_lookup_listener(struct net *net,
+				    struct inet_hashinfo *hashinfo,
+				    const __be32 saddr, const __be16 sport,
+				    const __be32 daddr,
+				    const unsigned short hnum,
+				    const int dif);
 
 static inline struct sock *inet_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
@@ -339,10 +337,11 @@ static inline struct sock *inet_lookup_listener(struct net *net,
  *
  * Local BH must be disabled here.
  */
-extern struct sock * __inet_lookup_established(struct net *net,
-		struct inet_hashinfo *hashinfo,
-		const __be32 saddr, const __be16 sport,
-		const __be32 daddr, const u16 hnum, const int dif);
+struct sock *__inet_lookup_established(struct net *net,
+				       struct inet_hashinfo *hashinfo,
+				       const __be32 saddr, const __be16 sport,
+				       const __be32 daddr, const u16 hnum,
+				       const int dif);
 
 static inline struct sock *
 	inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
@@ -399,13 +398,14 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 				     iph->daddr, dport, inet_iif(skb));
 }
 
-extern int __inet_hash_connect(struct inet_timewait_death_row *death_row,
-		struct sock *sk,
-		u32 port_offset,
-		int (*check_established)(struct inet_timewait_death_row *,
-			struct sock *, __u16, struct inet_timewait_sock **),
-		int (*hash)(struct sock *sk, struct inet_timewait_sock *twp));
+int __inet_hash_connect(struct inet_timewait_death_row *death_row,
+			struct sock *sk, u32 port_offset,
+			int (*check_established)(struct inet_timewait_death_row *,
+						 struct sock *, __u16,
+						 struct inet_timewait_sock **),
+			int (*hash)(struct sock *sk,
+				    struct inet_timewait_sock *twp));
 
-extern int inet_hash_connect(struct inet_timewait_death_row *death_row,
-			     struct sock *sk);
+int inet_hash_connect(struct inet_timewait_death_row *death_row,
+		      struct sock *sk);
 #endif /* _INET_HASHTABLES_H */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index b21a7f06d6a4..636d203727a2 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -199,11 +199,11 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 }
 #endif
 
-extern int inet_sk_rebuild_header(struct sock *sk);
+int inet_sk_rebuild_header(struct sock *sk);
 
 extern u32 inet_ehash_secret;
 extern u32 ipv6_hash_secret;
-extern void build_ehash_secret(void);
+void build_ehash_secret(void);
 
 static inline unsigned int inet_ehashfn(struct net *net,
 					const __be32 laddr, const __u16 lport,
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index f908dfc06505..828200ab1125 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -83,9 +83,9 @@ struct inet_timewait_death_row {
 	int			sysctl_max_tw_buckets;
 };
 
-extern void inet_twdr_hangman(unsigned long data);
-extern void inet_twdr_twkill_work(struct work_struct *work);
-extern void inet_twdr_twcal_tick(unsigned long data);
+void inet_twdr_hangman(unsigned long data);
+void inet_twdr_twkill_work(struct work_struct *work);
+void inet_twdr_twcal_tick(unsigned long data);
 
 struct inet_bind_bucket;
 
@@ -195,28 +195,27 @@ static inline __be32 sk_rcv_saddr(const struct sock *sk)
 	return sk->__sk_common.skc_rcv_saddr;
 }
 
-extern void inet_twsk_put(struct inet_timewait_sock *tw);
+void inet_twsk_put(struct inet_timewait_sock *tw);
 
-extern int inet_twsk_unhash(struct inet_timewait_sock *tw);
+int inet_twsk_unhash(struct inet_timewait_sock *tw);
 
-extern int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
-				 struct inet_hashinfo *hashinfo);
+int inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
+			  struct inet_hashinfo *hashinfo);
 
-extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
-						  const int state);
+struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
+					   const int state);
 
-extern void __inet_twsk_hashdance(struct inet_timewait_sock *tw,
-				  struct sock *sk,
-				  struct inet_hashinfo *hashinfo);
+void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+			   struct inet_hashinfo *hashinfo);
 
-extern void inet_twsk_schedule(struct inet_timewait_sock *tw,
-			       struct inet_timewait_death_row *twdr,
-			       const int timeo, const int timewait_len);
-extern void inet_twsk_deschedule(struct inet_timewait_sock *tw,
-				 struct inet_timewait_death_row *twdr);
+void inet_twsk_schedule(struct inet_timewait_sock *tw,
+			struct inet_timewait_death_row *twdr,
+			const int timeo, const int timewait_len);
+void inet_twsk_deschedule(struct inet_timewait_sock *tw,
+			  struct inet_timewait_death_row *twdr);
 
-extern void inet_twsk_purge(struct inet_hashinfo *hashinfo,
-			    struct inet_timewait_death_row *twdr, int family);
+void inet_twsk_purge(struct inet_hashinfo *hashinfo,
+		     struct inet_timewait_death_row *twdr, int family);
 
 static inline
 struct net *twsk_net(const struct inet_timewait_sock *twsk)
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 53f464d7cddc..f4e127af4e17 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -120,9 +120,9 @@ static inline void inetpeer_transfer_peer(unsigned long *to, unsigned long *from
 	}
 }
 
-extern void inet_peer_base_init(struct inet_peer_base *);
+void inet_peer_base_init(struct inet_peer_base *);
 
-void			inet_initpeers(void) __init;
+void inet_initpeers(void) __init;
 
 #define INETPEER_METRICS_NEW	(~(u32) 0)
 
@@ -159,11 +159,11 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base,
 }
 
 /* can be called from BH context or outside */
-extern void inet_putpeer(struct inet_peer *p);
-extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
+void inet_putpeer(struct inet_peer *p);
+bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 
-extern void inetpeer_invalidate_tree(struct inet_peer_base *);
-extern void inetpeer_invalidate_family(int family);
+void inetpeer_invalidate_tree(struct inet_peer_base *);
+void inetpeer_invalidate_family(int family);
 
 /*
  * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
-- 
cgit 


From 5c3a0fd7d0fc2985fcd540aa9d7656dcc2d57b41 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:42 -0700
Subject: ip*.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h        | 169 +++++++++++++++---------------
 include/net/ip6_fib.h   |  53 +++++-----
 include/net/ip6_route.h |  98 ++++++++----------
 include/net/ip_fib.h    |  61 ++++++-----
 include/net/ip_vs.h     | 245 +++++++++++++++++++++----------------------
 include/net/ipv6.h      | 268 +++++++++++++++++++++---------------------------
 6 files changed, 416 insertions(+), 478 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 5e5268807a1c..c1f192b8cd0e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -86,53 +86,51 @@ struct packet_type;
 struct rtable;
 struct sockaddr;
 
-extern int		igmp_mc_proc_init(void);
+int igmp_mc_proc_init(void);
 
 /*
  *	Functions provided by ip.c
  */
 
-extern int		ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
-					      __be32 saddr, __be32 daddr,
-					      struct ip_options_rcu *opt);
-extern int		ip_rcv(struct sk_buff *skb, struct net_device *dev,
-			       struct packet_type *pt, struct net_device *orig_dev);
-extern int		ip_local_deliver(struct sk_buff *skb);
-extern int		ip_mr_input(struct sk_buff *skb);
-extern int		ip_output(struct sk_buff *skb);
-extern int		ip_mc_output(struct sk_buff *skb);
-extern int		ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
-extern int		ip_do_nat(struct sk_buff *skb);
-extern void		ip_send_check(struct iphdr *ip);
-extern int		__ip_local_out(struct sk_buff *skb);
-extern int		ip_local_out(struct sk_buff *skb);
-extern int		ip_queue_xmit(struct sk_buff *skb, struct flowi *fl);
-extern void		ip_init(void);
-extern int		ip_append_data(struct sock *sk, struct flowi4 *fl4,
-				       int getfrag(void *from, char *to, int offset, int len,
-						   int odd, struct sk_buff *skb),
-				void *from, int len, int protolen,
-				struct ipcm_cookie *ipc,
-				struct rtable **rt,
-				unsigned int flags);
-extern int		ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb);
-extern ssize_t		ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
-				int offset, size_t size, int flags);
-extern struct sk_buff  *__ip_make_skb(struct sock *sk,
-				      struct flowi4 *fl4,
-				      struct sk_buff_head *queue,
-				      struct inet_cork *cork);
-extern int		ip_send_skb(struct net *net, struct sk_buff *skb);
-extern int		ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);
-extern void		ip_flush_pending_frames(struct sock *sk);
-extern struct sk_buff  *ip_make_skb(struct sock *sk,
-				    struct flowi4 *fl4,
-				    int getfrag(void *from, char *to, int offset, int len,
-						int odd, struct sk_buff *skb),
-				    void *from, int length, int transhdrlen,
-				    struct ipcm_cookie *ipc,
-				    struct rtable **rtp,
-				    unsigned int flags);
+int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
+			  __be32 saddr, __be32 daddr,
+			  struct ip_options_rcu *opt);
+int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+	   struct net_device *orig_dev);
+int ip_local_deliver(struct sk_buff *skb);
+int ip_mr_input(struct sk_buff *skb);
+int ip_output(struct sk_buff *skb);
+int ip_mc_output(struct sk_buff *skb);
+int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
+int ip_do_nat(struct sk_buff *skb);
+void ip_send_check(struct iphdr *ip);
+int __ip_local_out(struct sk_buff *skb);
+int ip_local_out(struct sk_buff *skb);
+int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl);
+void ip_init(void);
+int ip_append_data(struct sock *sk, struct flowi4 *fl4,
+		   int getfrag(void *from, char *to, int offset, int len,
+			       int odd, struct sk_buff *skb),
+		   void *from, int len, int protolen,
+		   struct ipcm_cookie *ipc,
+		   struct rtable **rt,
+		   unsigned int flags);
+int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd,
+		       struct sk_buff *skb);
+ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
+		       int offset, size_t size, int flags);
+struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4,
+			      struct sk_buff_head *queue,
+			      struct inet_cork *cork);
+int ip_send_skb(struct net *net, struct sk_buff *skb);
+int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);
+void ip_flush_pending_frames(struct sock *sk);
+struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
+			    int getfrag(void *from, char *to, int offset,
+					int len, int odd, struct sk_buff *skb),
+			    void *from, int length, int transhdrlen,
+			    struct ipcm_cookie *ipc, struct rtable **rtp,
+			    unsigned int flags);
 
 static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 {
@@ -140,10 +138,9 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 }
 
 /* datagram.c */
-extern int		ip4_datagram_connect(struct sock *sk, 
-					     struct sockaddr *uaddr, int addr_len);
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
-extern void ip4_datagram_release_cb(struct sock *sk);
+void ip4_datagram_release_cb(struct sock *sk);
 
 struct ip_reply_arg {
 	struct kvec iov[1];   
@@ -184,16 +181,16 @@ extern struct ipv4_config ipv4_config;
 #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd)
 #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)
 
-extern unsigned long snmp_fold_field(void __percpu *mib[], int offt);
+unsigned long snmp_fold_field(void __percpu *mib[], int offt);
 #if BITS_PER_LONG==32
-extern u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off);
+u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off);
 #else
 static inline u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_off)
 {
 	return snmp_fold_field(mib, offt);
 }
 #endif
-extern int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align);
+int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align);
 
 static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ])
 {
@@ -210,7 +207,7 @@ extern struct local_ports {
 	seqlock_t	lock;
 	int		range[2];
 } sysctl_local_ports;
-extern void inet_get_local_port_range(int *low, int *high);
+void inet_get_local_port_range(int *low, int *high);
 
 extern unsigned long *sysctl_local_reserved_ports;
 static inline int inet_is_reserved_local_port(int port)
@@ -231,9 +228,9 @@ extern int sysctl_ip_early_demux;
 /* From ip_output.c */
 extern int sysctl_ip_dynaddr;
 
-extern void ipfrag_init(void);
+void ipfrag_init(void);
 
-extern void ip_static_sysctl_init(void);
+void ip_static_sysctl_init(void);
 
 static inline bool ip_is_fragment(const struct iphdr *iph)
 {
@@ -262,7 +259,7 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
 		 !(dst_metric_locked(dst, RTAX_MTU)));
 }
 
-extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
 
 static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
 {
@@ -390,7 +387,7 @@ static inline int sk_mc_loop(struct sock *sk)
 	return 1;
 }
 
-extern bool ip_call_ra_chain(struct sk_buff *skb);
+bool ip_call_ra_chain(struct sk_buff *skb);
 
 /*
  *	Functions provided by ip_fragment.c
@@ -428,50 +425,52 @@ int ip_frag_nqueues(struct net *net);
  *	Functions provided by ip_forward.c
  */
  
-extern int ip_forward(struct sk_buff *skb);
+int ip_forward(struct sk_buff *skb);
  
 /*
  *	Functions provided by ip_options.c
  */
  
-extern void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
-			     __be32 daddr, struct rtable *rt, int is_frag);
-extern int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
-extern void ip_options_fragment(struct sk_buff *skb);
-extern int ip_options_compile(struct net *net,
-			      struct ip_options *opt, struct sk_buff *skb);
-extern int ip_options_get(struct net *net, struct ip_options_rcu **optp,
-			  unsigned char *data, int optlen);
-extern int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
-				    unsigned char __user *data, int optlen);
-extern void ip_options_undo(struct ip_options * opt);
-extern void ip_forward_options(struct sk_buff *skb);
-extern int ip_options_rcv_srr(struct sk_buff *skb);
+void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
+		      __be32 daddr, struct rtable *rt, int is_frag);
+int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);
+void ip_options_fragment(struct sk_buff *skb);
+int ip_options_compile(struct net *net, struct ip_options *opt,
+		       struct sk_buff *skb);
+int ip_options_get(struct net *net, struct ip_options_rcu **optp,
+		   unsigned char *data, int optlen);
+int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
+			     unsigned char __user *data, int optlen);
+void ip_options_undo(struct ip_options *opt);
+void ip_forward_options(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb);
 
 /*
  *	Functions provided by ip_sockglue.c
  */
 
-extern void	ipv4_pktinfo_prepare(struct sk_buff *skb);
-extern void	ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
-extern int	ip_cmsg_send(struct net *net,
-			     struct msghdr *msg, struct ipcm_cookie *ipc);
-extern int	ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen);
-extern int	ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen);
-extern int	compat_ip_setsockopt(struct sock *sk, int level,
-			int optname, char __user *optval, unsigned int optlen);
-extern int	compat_ip_getsockopt(struct sock *sk, int level,
-			int optname, char __user *optval, int __user *optlen);
-extern int	ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *));
-
-extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
-extern void	ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
-			      __be16 port, u32 info, u8 *payload);
-extern void	ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
-			       u32 info);
+void ipv4_pktinfo_prepare(struct sk_buff *skb);
+void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
+int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc);
+int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
+		  unsigned int optlen);
+int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
+		  int __user *optlen);
+int compat_ip_setsockopt(struct sock *sk, int level, int optname,
+			 char __user *optval, unsigned int optlen);
+int compat_ip_getsockopt(struct sock *sk, int level, int optname,
+			 char __user *optval, int __user *optlen);
+int ip_ra_control(struct sock *sk, unsigned char on,
+		  void (*destructor)(struct sock *));
+
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
+void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
+		   u32 info, u8 *payload);
+void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
+		    u32 info);
 
 #ifdef CONFIG_PROC_FS
-extern int ip_misc_proc_init(void);
+int ip_misc_proc_init(void);
 #endif
 
 #endif	/* _IP_H */
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 48ec25a7fcb6..eab88f0e2088 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -267,48 +267,41 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *,
  *	exported functions
  */
 
-extern struct fib6_table        *fib6_get_table(struct net *net, u32 id);
-extern struct fib6_table        *fib6_new_table(struct net *net, u32 id);
-extern struct dst_entry         *fib6_rule_lookup(struct net *net,
-						  struct flowi6 *fl6, int flags,
-						  pol_lookup_t lookup);
+struct fib6_table *fib6_get_table(struct net *net, u32 id);
+struct fib6_table *fib6_new_table(struct net *net, u32 id);
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   int flags, pol_lookup_t lookup);
 
-extern struct fib6_node		*fib6_lookup(struct fib6_node *root,
-					     const struct in6_addr *daddr,
-					     const struct in6_addr *saddr);
+struct fib6_node *fib6_lookup(struct fib6_node *root,
+			      const struct in6_addr *daddr,
+			      const struct in6_addr *saddr);
 
-struct fib6_node		*fib6_locate(struct fib6_node *root,
-					     const struct in6_addr *daddr, int dst_len,
-					     const struct in6_addr *saddr, int src_len);
+struct fib6_node *fib6_locate(struct fib6_node *root,
+			      const struct in6_addr *daddr, int dst_len,
+			      const struct in6_addr *saddr, int src_len);
 
-extern void			fib6_clean_all_ro(struct net *net,
-					       int (*func)(struct rt6_info *, void *arg),
-					       int prune, void *arg);
+void fib6_clean_all_ro(struct net *net,
+		       int (*func)(struct rt6_info *, void *arg),
+		       int prune, void *arg);
 
-extern void			fib6_clean_all(struct net *net,
-					       int (*func)(struct rt6_info *, void *arg),
-					       int prune, void *arg);
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
+		    int prune, void *arg);
 
-extern int			fib6_add(struct fib6_node *root,
-					 struct rt6_info *rt,
-					 struct nl_info *info);
+int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info);
 
-extern int			fib6_del(struct rt6_info *rt,
-					 struct nl_info *info);
+int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
-extern void			inet6_rt_notify(int event, struct rt6_info *rt,
-						struct nl_info *info);
+void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
 
-extern void			fib6_run_gc(unsigned long expires,
-					    struct net *net, bool force);
+void fib6_run_gc(unsigned long expires, struct net *net, bool force);
 
-extern void			fib6_gc_cleanup(void);
+void fib6_gc_cleanup(void);
 
-extern int			fib6_init(void);
+int fib6_init(void);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-extern int			fib6_rules_init(void);
-extern void			fib6_rules_cleanup(void);
+int fib6_rules_init(void);
+void fib6_rules_cleanup(void);
 #else
 static inline int               fib6_rules_init(void)
 {
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f525e7038cca..02e220dc4cf5 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -51,7 +51,7 @@ static inline unsigned int rt6_flags2srcprefs(int flags)
 	return (flags >> 3) & 7;
 }
 
-extern void rt6_bind_peer(struct rt6_info *rt, int create);
+void rt6_bind_peer(struct rt6_info *rt, int create);
 
 static inline struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
 {
@@ -72,70 +72,58 @@ static inline struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
 	return __rt6_get_peer(rt, 1);
 }
 
-extern void			ip6_route_input(struct sk_buff *skb);
+void ip6_route_input(struct sk_buff *skb);
 
-extern struct dst_entry *	ip6_route_output(struct net *net,
-						 const struct sock *sk,
-						 struct flowi6 *fl6);
-extern struct dst_entry *	ip6_route_lookup(struct net *net,
-						 struct flowi6 *fl6, int flags);
+struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
+				   struct flowi6 *fl6);
+struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
+				   int flags);
 
-extern int			ip6_route_init(void);
-extern void			ip6_route_cleanup(void);
+int ip6_route_init(void);
+void ip6_route_cleanup(void);
 
-extern int			ipv6_route_ioctl(struct net *net,
-						 unsigned int cmd,
-						 void __user *arg);
+int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
 
-extern int			ip6_route_add(struct fib6_config *cfg);
-extern int			ip6_ins_rt(struct rt6_info *);
-extern int			ip6_del_rt(struct rt6_info *);
+int ip6_route_add(struct fib6_config *cfg);
+int ip6_ins_rt(struct rt6_info *);
+int ip6_del_rt(struct rt6_info *);
 
-extern int			ip6_route_get_saddr(struct net *net,
-						    struct rt6_info *rt,
-						    const struct in6_addr *daddr,
-						    unsigned int prefs,
-						    struct in6_addr *saddr);
+int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
+			const struct in6_addr *daddr, unsigned int prefs,
+			struct in6_addr *saddr);
 
-extern struct rt6_info		*rt6_lookup(struct net *net,
-					    const struct in6_addr *daddr,
-					    const struct in6_addr *saddr,
-					    int oif, int flags);
+struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
+			    const struct in6_addr *saddr, int oif, int flags);
 
-extern struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
-					 struct flowi6 *fl6);
-extern int icmp6_dst_gc(void);
+struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
+int icmp6_dst_gc(void);
 
-extern void fib6_force_start_gc(struct net *net);
+void fib6_force_start_gc(struct net *net);
 
-extern struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
-					   const struct in6_addr *addr,
-					   bool anycast);
+struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
+				    const struct in6_addr *addr, bool anycast);
 
 /*
  *	support functions for ND
  *
  */
-extern struct rt6_info *	rt6_get_dflt_router(const struct in6_addr *addr,
-						    struct net_device *dev);
-extern struct rt6_info *	rt6_add_dflt_router(const struct in6_addr *gwaddr,
-						    struct net_device *dev,
-						    unsigned int pref);
-
-extern void			rt6_purge_dflt_routers(struct net *net);
-
-extern int			rt6_route_rcv(struct net_device *dev,
-					      u8 *opt, int len,
-					      const struct in6_addr *gwaddr);
-
-extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
-			    int oif, u32 mark);
-extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk,
-			       __be32 mtu);
-extern void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
-extern void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
-				   u32 mark);
-extern void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk);
+struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr,
+				     struct net_device *dev);
+struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
+				     struct net_device *dev, unsigned int pref);
+
+void rt6_purge_dflt_routers(struct net *net);
+
+int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
+		  const struct in6_addr *gwaddr);
+
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
+		     u32 mark);
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
+void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
+			    u32 mark);
+void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk);
 
 struct netlink_callback;
 
@@ -145,10 +133,10 @@ struct rt6_rtnl_dump_arg {
 	struct net *net;
 };
 
-extern int rt6_dump_route(struct rt6_info *rt, void *p_arg);
-extern void rt6_ifdown(struct net *net, struct net_device *dev);
-extern void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
-extern void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
+int rt6_dump_route(struct rt6_info *rt, void *p_arg);
+void rt6_ifdown(struct net *net, struct net_device *dev);
+void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
+void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
 
 
 /*
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index cbf2be37c91a..9922093f575e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -165,7 +165,7 @@ struct fib_result_nl {
 #define FIB_TABLE_HASHSZ 2
 #endif
 
-extern __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
+__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 
 #define FIB_RES_SADDR(net, res)				\
 	((FIB_RES_NH(res).nh_saddr_genid ==		\
@@ -187,14 +187,14 @@ struct fib_table {
 	unsigned long		tb_data[0];
 };
 
-extern int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
-			    struct fib_result *res, int fib_flags);
-extern int fib_table_insert(struct fib_table *, struct fib_config *);
-extern int fib_table_delete(struct fib_table *, struct fib_config *);
-extern int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
-			  struct netlink_callback *cb);
-extern int fib_table_flush(struct fib_table *table);
-extern void fib_free_table(struct fib_table *tb);
+int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
+		     struct fib_result *res, int fib_flags);
+int fib_table_insert(struct fib_table *, struct fib_config *);
+int fib_table_delete(struct fib_table *, struct fib_config *);
+int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
+		   struct netlink_callback *cb);
+int fib_table_flush(struct fib_table *table);
+void fib_free_table(struct fib_table *tb);
 
 
 
@@ -234,14 +234,13 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 }
 
 #else /* CONFIG_IP_MULTIPLE_TABLES */
-extern int __net_init fib4_rules_init(struct net *net);
-extern void __net_exit fib4_rules_exit(struct net *net);
+int __net_init fib4_rules_init(struct net *net);
+void __net_exit fib4_rules_exit(struct net *net);
 
-extern struct fib_table *fib_new_table(struct net *net, u32 id);
-extern struct fib_table *fib_get_table(struct net *net, u32 id);
+struct fib_table *fib_new_table(struct net *net, u32 id);
+struct fib_table *fib_get_table(struct net *net, u32 id);
 
-extern int __fib_lookup(struct net *net, struct flowi4 *flp,
-			struct fib_result *res);
+int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res);
 
 static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 			     struct fib_result *res)
@@ -269,12 +268,12 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 
 /* Exported by fib_frontend.c */
 extern const struct nla_policy rtm_ipv4_policy[];
-extern void		ip_fib_init(void);
-extern __be32 fib_compute_spec_dst(struct sk_buff *skb);
-extern int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
-			       u8 tos, int oif, struct net_device *dev,
-			       struct in_device *idev, u32 *itag);
-extern void fib_select_default(struct fib_result *res);
+void ip_fib_init(void);
+__be32 fib_compute_spec_dst(struct sk_buff *skb);
+int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
+			u8 tos, int oif, struct net_device *dev,
+			struct in_device *idev, u32 *itag);
+void fib_select_default(struct fib_result *res);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
@@ -288,15 +287,15 @@ static inline int fib_num_tclassid_users(struct net *net)
 #endif
 
 /* Exported by fib_semantics.c */
-extern int ip_fib_check_default(__be32 gw, struct net_device *dev);
-extern int fib_sync_down_dev(struct net_device *dev, int force);
-extern int fib_sync_down_addr(struct net *net, __be32 local);
-extern int fib_sync_up(struct net_device *dev);
-extern void fib_select_multipath(struct fib_result *res);
+int ip_fib_check_default(__be32 gw, struct net_device *dev);
+int fib_sync_down_dev(struct net_device *dev, int force);
+int fib_sync_down_addr(struct net *net, __be32 local);
+int fib_sync_up(struct net_device *dev);
+void fib_select_multipath(struct fib_result *res);
 
 /* Exported by fib_trie.c */
-extern void fib_trie_init(void);
-extern struct fib_table *fib_trie_table(u32 id);
+void fib_trie_init(void);
+struct fib_table *fib_trie_table(u32 id);
 
 static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 {
@@ -314,7 +313,7 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 #endif
 }
 
-extern void free_fib_info(struct fib_info *fi);
+void free_fib_info(struct fib_info *fi);
 
 static inline void fib_info_put(struct fib_info *fi)
 {
@@ -323,8 +322,8 @@ static inline void fib_info_put(struct fib_info *fi)
 }
 
 #ifdef CONFIG_PROC_FS
-extern int __net_init  fib_proc_init(struct net *net);
-extern void __net_exit fib_proc_exit(struct net *net);
+int __net_init fib_proc_init(struct net *net);
+void __net_exit fib_proc_exit(struct net *net);
 #else
 static inline int fib_proc_init(struct net *net)
 {
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index f0d70f066f3d..b6fd378c09c8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -236,7 +236,7 @@ static inline int ip_vs_addr_equal(int af, const union nf_inet_addr *a,
 #ifdef CONFIG_IP_VS_DEBUG
 #include <linux/net.h>
 
-extern int ip_vs_get_debug_level(void);
+int ip_vs_get_debug_level(void);
 
 static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
 					 const union nf_inet_addr *addr,
@@ -532,9 +532,9 @@ struct ip_vs_proto_data {
 	struct tcp_states_t	*tcp_state_table;
 };
 
-extern struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
-extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
-						     unsigned short proto);
+struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
+struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net,
+					      unsigned short proto);
 
 struct ip_vs_conn_param {
 	struct net			*net;
@@ -1176,8 +1176,8 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
  *      IPVS core functions
  *      (from ip_vs_core.c)
  */
-extern const char *ip_vs_proto_name(unsigned int proto);
-extern void ip_vs_init_hash_table(struct list_head *table, int rows);
+const char *ip_vs_proto_name(unsigned int proto);
+void ip_vs_init_hash_table(struct list_head *table, int rows);
 #define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))
 
 #define IP_VS_APP_TYPE_FTP	1
@@ -1240,22 +1240,22 @@ static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 	smp_mb__before_atomic_dec();
 	atomic_dec(&cp->refcnt);
 }
-extern void ip_vs_conn_put(struct ip_vs_conn *cp);
-extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
+void ip_vs_conn_put(struct ip_vs_conn *cp);
+void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);
 
 struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p,
 				  const union nf_inet_addr *daddr,
 				  __be16 dport, unsigned int flags,
 				  struct ip_vs_dest *dest, __u32 fwmark);
-extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
+void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
-extern const char * ip_vs_state_name(__u16 proto, int state);
+const char *ip_vs_state_name(__u16 proto, int state);
 
-extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
-extern int ip_vs_check_template(struct ip_vs_conn *ct);
-extern void ip_vs_random_dropentry(struct net *net);
-extern int ip_vs_conn_init(void);
-extern void ip_vs_conn_cleanup(void);
+void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp);
+int ip_vs_check_template(struct ip_vs_conn *ct);
+void ip_vs_random_dropentry(struct net *net);
+int ip_vs_conn_init(void);
+void ip_vs_conn_cleanup(void);
 
 static inline void ip_vs_control_del(struct ip_vs_conn *cp)
 {
@@ -1320,37 +1320,36 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
 /*
  * IPVS netns init & cleanup functions
  */
-extern int ip_vs_estimator_net_init(struct net *net);
-extern int ip_vs_control_net_init(struct net *net);
-extern int ip_vs_protocol_net_init(struct net *net);
-extern int ip_vs_app_net_init(struct net *net);
-extern int ip_vs_conn_net_init(struct net *net);
-extern int ip_vs_sync_net_init(struct net *net);
-extern void ip_vs_conn_net_cleanup(struct net *net);
-extern void ip_vs_app_net_cleanup(struct net *net);
-extern void ip_vs_protocol_net_cleanup(struct net *net);
-extern void ip_vs_control_net_cleanup(struct net *net);
-extern void ip_vs_estimator_net_cleanup(struct net *net);
-extern void ip_vs_sync_net_cleanup(struct net *net);
-extern void ip_vs_service_net_cleanup(struct net *net);
+int ip_vs_estimator_net_init(struct net *net);
+int ip_vs_control_net_init(struct net *net);
+int ip_vs_protocol_net_init(struct net *net);
+int ip_vs_app_net_init(struct net *net);
+int ip_vs_conn_net_init(struct net *net);
+int ip_vs_sync_net_init(struct net *net);
+void ip_vs_conn_net_cleanup(struct net *net);
+void ip_vs_app_net_cleanup(struct net *net);
+void ip_vs_protocol_net_cleanup(struct net *net);
+void ip_vs_control_net_cleanup(struct net *net);
+void ip_vs_estimator_net_cleanup(struct net *net);
+void ip_vs_sync_net_cleanup(struct net *net);
+void ip_vs_service_net_cleanup(struct net *net);
 
 /*
  *      IPVS application functions
  *      (from ip_vs_app.c)
  */
 #define IP_VS_APP_MAX_PORTS  8
-extern struct ip_vs_app *register_ip_vs_app(struct net *net,
-					    struct ip_vs_app *app);
-extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
-extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
-extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
-extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app,
-				  __u16 proto, __u16 port);
-extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
-extern void ip_vs_app_inc_put(struct ip_vs_app *inc);
-
-extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
-extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
+struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app);
+void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app);
+int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
+void ip_vs_unbind_app(struct ip_vs_conn *cp);
+int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
+			   __u16 port);
+int ip_vs_app_inc_get(struct ip_vs_app *inc);
+void ip_vs_app_inc_put(struct ip_vs_app *inc);
+
+int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
+int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
 
 int register_ip_vs_pe(struct ip_vs_pe *pe);
 int unregister_ip_vs_pe(struct ip_vs_pe *pe);
@@ -1371,17 +1370,15 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);
 /*
  *	IPVS protocol functions (from ip_vs_proto.c)
  */
-extern int ip_vs_protocol_init(void);
-extern void ip_vs_protocol_cleanup(void);
-extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
-extern int *ip_vs_create_timeout_table(int *table, int size);
-extern int
-ip_vs_set_state_timeout(int *table, int num, const char *const *names,
-			const char *name, int to);
-extern void
-ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
-			  const struct sk_buff *skb,
-			  int offset, const char *msg);
+int ip_vs_protocol_init(void);
+void ip_vs_protocol_cleanup(void);
+void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
+int *ip_vs_create_timeout_table(int *table, int size);
+int ip_vs_set_state_timeout(int *table, int num, const char *const *names,
+			    const char *name, int to);
+void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
+			       const struct sk_buff *skb, int offset,
+			       const char *msg);
 
 extern struct ip_vs_protocol ip_vs_protocol_tcp;
 extern struct ip_vs_protocol ip_vs_protocol_udp;
@@ -1394,22 +1391,22 @@ extern struct ip_vs_protocol ip_vs_protocol_sctp;
  *      Registering/unregistering scheduler functions
  *      (from ip_vs_sched.c)
  */
-extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
-extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
-extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
-				struct ip_vs_scheduler *scheduler);
-extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
-				   struct ip_vs_scheduler *sched);
-extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
-extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
-extern struct ip_vs_conn *
+int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
+int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
+int ip_vs_bind_scheduler(struct ip_vs_service *svc,
+			 struct ip_vs_scheduler *scheduler);
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
+			    struct ip_vs_scheduler *sched);
+struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
+void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
+struct ip_vs_conn *
 ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	       struct ip_vs_proto_data *pd, int *ignored,
 	       struct ip_vs_iphdr *iph);
-extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
-			struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph);
+int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
+		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph);
 
-extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
+void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 
 
 /*
@@ -1418,25 +1415,24 @@ extern void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);
 extern struct ip_vs_stats ip_vs_stats;
 extern int sysctl_ip_vs_sync_ver;
 
-extern struct ip_vs_service *
+struct ip_vs_service *
 ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
 		  const union nf_inet_addr *vaddr, __be16 vport);
 
-extern bool
-ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
-		       const union nf_inet_addr *daddr, __be16 dport);
-
-extern int ip_vs_use_count_inc(void);
-extern void ip_vs_use_count_dec(void);
-extern int ip_vs_register_nl_ioctl(void);
-extern void ip_vs_unregister_nl_ioctl(void);
-extern int ip_vs_control_init(void);
-extern void ip_vs_control_cleanup(void);
-extern struct ip_vs_dest *
+bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
+			    const union nf_inet_addr *daddr, __be16 dport);
+
+int ip_vs_use_count_inc(void);
+void ip_vs_use_count_dec(void);
+int ip_vs_register_nl_ioctl(void);
+void ip_vs_unregister_nl_ioctl(void);
+int ip_vs_control_init(void);
+void ip_vs_control_cleanup(void);
+struct ip_vs_dest *
 ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
 		__be16 dport, const union nf_inet_addr *vaddr, __be16 vport,
 		__u16 protocol, __u32 fwmark, __u32 flags);
-extern void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
+void ip_vs_try_bind_dest(struct ip_vs_conn *cp);
 
 static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
 {
@@ -1453,56 +1449,49 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)
  */
-extern int start_sync_thread(struct net *net, int state, char *mcast_ifn,
-			     __u8 syncid);
-extern int stop_sync_thread(struct net *net, int state);
-extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
-
+int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid);
+int stop_sync_thread(struct net *net, int state);
+void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts);
 
 /*
  *      IPVS rate estimator prototypes (from ip_vs_est.c)
  */
-extern void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
-extern void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
-extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
-extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
-				 struct ip_vs_stats *stats);
+void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
+void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
+void ip_vs_zero_estimator(struct ip_vs_stats *stats);
+void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+			  struct ip_vs_stats *stats);
 
 /*
  *	Various IPVS packet transmitters (from ip_vs_xmit.c)
  */
-extern int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
-extern int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			     struct ip_vs_protocol *pp,
-			     struct ip_vs_iphdr *iph);
-extern int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
-extern int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			     struct ip_vs_protocol *pp,
-			     struct ip_vs_iphdr *iph);
-extern int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
-extern int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-			   struct ip_vs_protocol *pp, int offset,
-			   unsigned int hooknum, struct ip_vs_iphdr *iph);
-extern void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
+int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
+		    struct ip_vs_protocol *pp, int offset,
+		    unsigned int hooknum, struct ip_vs_iphdr *iph);
+void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
 
 #ifdef CONFIG_IP_VS_IPV6
-extern int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-				struct ip_vs_protocol *pp,
-				struct ip_vs_iphdr *iph);
-extern int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-			     struct ip_vs_protocol *pp,
-			     struct ip_vs_iphdr *iph);
-extern int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-				struct ip_vs_protocol *pp,
-				struct ip_vs_iphdr *iph);
-extern int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-			    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
-extern int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-			      struct ip_vs_protocol *pp, int offset,
-			      unsigned int hooknum, struct ip_vs_iphdr *iph);
+int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
+int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
+		       struct ip_vs_protocol *pp, int offset,
+		       unsigned int hooknum, struct ip_vs_iphdr *iph);
 #endif
 
 #ifdef CONFIG_SYSCTL
@@ -1551,15 +1540,15 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
 	return fwd;
 }
 
-extern void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-			   struct ip_vs_conn *cp, int dir);
+void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		    struct ip_vs_conn *cp, int dir);
 
 #ifdef CONFIG_IP_VS_IPV6
-extern void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
-			      struct ip_vs_conn *cp, int dir);
+void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
+		       struct ip_vs_conn *cp, int dir);
 #endif
 
-extern __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
+__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
 
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
 {
@@ -1618,13 +1607,13 @@ static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
 #endif
 }
 
-extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
-				   int outin);
-extern int ip_vs_confirm_conntrack(struct sk_buff *skb);
-extern void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
-				      struct ip_vs_conn *cp, u_int8_t proto,
-				      const __be16 port, int from_rs);
-extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);
+void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
+			    int outin);
+int ip_vs_confirm_conntrack(struct sk_buff *skb);
+void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
+			       struct ip_vs_conn *cp, u_int8_t proto,
+			       const __be16 port, int from_rs);
+void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);
 
 #else
 
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index bbf1c8fb8511..fe1c7f6c9217 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -244,14 +244,14 @@ struct ipv6_fl_socklist {
 	struct rcu_head			rcu;
 };
 
-extern struct ip6_flowlabel	*fl6_sock_lookup(struct sock *sk, __be32 label);
-extern struct ipv6_txoptions	*fl6_merge_options(struct ipv6_txoptions * opt_space,
-						   struct ip6_flowlabel * fl,
-						   struct ipv6_txoptions * fopt);
-extern void			fl6_free_socklist(struct sock *sk);
-extern int			ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
-extern int			ip6_flowlabel_init(void);
-extern void			ip6_flowlabel_cleanup(void);
+struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
+struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
+					 struct ip6_flowlabel *fl,
+					 struct ipv6_txoptions *fopt);
+void fl6_free_socklist(struct sock *sk);
+int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
+int ip6_flowlabel_init(void);
+void ip6_flowlabel_cleanup(void);
 
 static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 {
@@ -259,7 +259,7 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl)
 		atomic_dec(&fl->users);
 }
 
-extern void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
+void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info);
 
 int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 			       struct icmp6hdr *thdr, int len);
@@ -267,19 +267,21 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
 struct dst_entry *icmpv6_route_lookup(struct net *net, struct sk_buff *skb,
 				      struct sock *sk, struct flowi6 *fl6);
 
-extern int 			ip6_ra_control(struct sock *sk, int sel);
+int ip6_ra_control(struct sock *sk, int sel);
 
-extern int			ipv6_parse_hopopts(struct sk_buff *skb);
+int ipv6_parse_hopopts(struct sk_buff *skb);
 
-extern struct ipv6_txoptions *  ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt);
-extern struct ipv6_txoptions *	ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
-						   int newtype,
-						   struct ipv6_opt_hdr __user *newopt,
-						   int newoptlen);
+struct ipv6_txoptions *ipv6_dup_options(struct sock *sk,
+					struct ipv6_txoptions *opt);
+struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
+					  struct ipv6_txoptions *opt,
+					  int newtype,
+					  struct ipv6_opt_hdr __user *newopt,
+					  int newoptlen);
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
-extern bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
+bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
 
 static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 {
@@ -306,7 +308,7 @@ static inline int ip6_frag_mem(struct net *net)
 #define IPV6_FRAG_LOW_THRESH	(3 * 1024*1024)	/* 3145728 */
 #define IPV6_FRAG_TIMEOUT	(60 * HZ)	/* 60 seconds */
 
-extern int __ipv6_addr_type(const struct in6_addr *addr);
+int __ipv6_addr_type(const struct in6_addr *addr);
 static inline int ipv6_addr_type(const struct in6_addr *addr)
 {
 	return __ipv6_addr_type(addr) & 0xffff;
@@ -656,9 +658,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-extern void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 
-extern int ip6_dst_hoplimit(struct dst_entry *dst);
+int ip6_dst_hoplimit(struct dst_entry *dst);
 
 /*
  *	Header manipulation
@@ -682,83 +684,65 @@ static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr)
  *	rcv function (called from netdevice level)
  */
 
-extern int			ipv6_rcv(struct sk_buff *skb, 
-					 struct net_device *dev, 
-					 struct packet_type *pt,
-					 struct net_device *orig_dev);
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
+	     struct packet_type *pt, struct net_device *orig_dev);
 
-extern int			ip6_rcv_finish(struct sk_buff *skb);
+int ip6_rcv_finish(struct sk_buff *skb);
 
 /*
  *	upper-layer output functions
  */
-extern int			ip6_xmit(struct sock *sk,
-					 struct sk_buff *skb,
-					 struct flowi6 *fl6,
-					 struct ipv6_txoptions *opt,
-					 int tclass);
-
-extern int			ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
-
-extern int			ip6_append_data(struct sock *sk,
-						int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb),
-		    				void *from,
-						int length,
-						int transhdrlen,
-		      				int hlimit,
-		      				int tclass,
-						struct ipv6_txoptions *opt,
-						struct flowi6 *fl6,
-						struct rt6_info *rt,
-						unsigned int flags,
-						int dontfrag);
-
-extern int			ip6_push_pending_frames(struct sock *sk);
-
-extern void			ip6_flush_pending_frames(struct sock *sk);
-
-extern int			ip6_dst_lookup(struct sock *sk,
-					       struct dst_entry **dst,
-					       struct flowi6 *fl6);
-extern struct dst_entry *	ip6_dst_lookup_flow(struct sock *sk,
-						    struct flowi6 *fl6,
-						    const struct in6_addr *final_dst,
-						    bool can_sleep);
-extern struct dst_entry *	ip6_sk_dst_lookup_flow(struct sock *sk,
-						       struct flowi6 *fl6,
-						       const struct in6_addr *final_dst,
-						       bool can_sleep);
-extern struct dst_entry *	ip6_blackhole_route(struct net *net,
-						    struct dst_entry *orig_dst);
+int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+	     struct ipv6_txoptions *opt, int tclass);
+
+int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
+
+int ip6_append_data(struct sock *sk,
+		    int getfrag(void *from, char *to, int offset, int len,
+				int odd, struct sk_buff *skb),
+		    void *from, int length, int transhdrlen, int hlimit,
+		    int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
+		    struct rt6_info *rt, unsigned int flags, int dontfrag);
+
+int ip6_push_pending_frames(struct sock *sk);
+
+void ip6_flush_pending_frames(struct sock *sk);
+
+int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6);
+struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+				      const struct in6_addr *final_dst,
+				      bool can_sleep);
+struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+					 const struct in6_addr *final_dst,
+					 bool can_sleep);
+struct dst_entry *ip6_blackhole_route(struct net *net,
+				      struct dst_entry *orig_dst);
 
 /*
  *	skb processing functions
  */
 
-extern int			ip6_output(struct sk_buff *skb);
-extern int			ip6_forward(struct sk_buff *skb);
-extern int			ip6_input(struct sk_buff *skb);
-extern int			ip6_mc_input(struct sk_buff *skb);
+int ip6_output(struct sk_buff *skb);
+int ip6_forward(struct sk_buff *skb);
+int ip6_input(struct sk_buff *skb);
+int ip6_mc_input(struct sk_buff *skb);
 
-extern int			__ip6_local_out(struct sk_buff *skb);
-extern int			ip6_local_out(struct sk_buff *skb);
+int __ip6_local_out(struct sk_buff *skb);
+int ip6_local_out(struct sk_buff *skb);
 
 /*
  *	Extension header (options) processing
  */
 
-extern void 			ipv6_push_nfrag_opts(struct sk_buff *skb,
-						     struct ipv6_txoptions *opt,
-						     u8 *proto,
-						     struct in6_addr **daddr_p);
-extern void			ipv6_push_frag_opts(struct sk_buff *skb,
-						    struct ipv6_txoptions *opt,
-						    u8 *proto);
+void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
+			  u8 *proto, struct in6_addr **daddr_p);
+void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
+			 u8 *proto);
 
-extern int			ipv6_skip_exthdr(const struct sk_buff *, int start,
-					         u8 *nexthdrp, __be16 *frag_offp);
+int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp,
+		     __be16 *frag_offp);
 
-extern bool			ipv6_ext_hdr(u8 nexthdr);
+bool ipv6_ext_hdr(u8 nexthdr);
 
 enum {
 	IP6_FH_F_FRAG		= (1 << 0),
@@ -767,57 +751,44 @@ enum {
 };
 
 /* find specified header and get offset to it */
-extern int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
-			 int target, unsigned short *fragoff, int *fragflg);
+int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target,
+		  unsigned short *fragoff, int *fragflg);
 
-extern int ipv6_find_tlv(struct sk_buff *skb, int offset, int type);
+int ipv6_find_tlv(struct sk_buff *skb, int offset, int type);
 
-extern struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
-				       const struct ipv6_txoptions *opt,
-				       struct in6_addr *orig);
+struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
+				const struct ipv6_txoptions *opt,
+				struct in6_addr *orig);
 
 /*
  *	socket options (ipv6_sockglue.c)
  */
 
-extern int			ipv6_setsockopt(struct sock *sk, int level, 
-						int optname,
-						char __user *optval, 
-						unsigned int optlen);
-extern int			ipv6_getsockopt(struct sock *sk, int level, 
-						int optname,
-						char __user *optval, 
-						int __user *optlen);
-extern int			compat_ipv6_setsockopt(struct sock *sk,
-						int level,
-						int optname,
-						char __user *optval,
-						unsigned int optlen);
-extern int			compat_ipv6_getsockopt(struct sock *sk,
-						int level,
-						int optname,
-						char __user *optval,
-						int __user *optlen);
-
-extern int			ip6_datagram_connect(struct sock *sk, 
-						     struct sockaddr *addr, int addr_len);
-
-extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
-extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
-extern void			ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
-						u32 info, u8 *payload);
-extern void			ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
-extern void			ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
-
-extern int inet6_release(struct socket *sock);
-extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr, 
-		      int addr_len);
-extern int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
-			 int *uaddr_len, int peer);
-extern int inet6_ioctl(struct socket *sock, unsigned int cmd, 
-		       unsigned long arg);
-
-extern int inet6_hash_connect(struct inet_timewait_death_row *death_row,
+int ipv6_setsockopt(struct sock *sk, int level, int optname,
+		    char __user *optval, unsigned int optlen);
+int ipv6_getsockopt(struct sock *sk, int level, int optname,
+		    char __user *optval, int __user *optlen);
+int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
+			   char __user *optval, unsigned int optlen);
+int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
+			   char __user *optval, int __user *optlen);
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len);
+
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
+void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
+		     u32 info, u8 *payload);
+void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu);
+
+int inet6_release(struct socket *sock);
+int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
+int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len,
+		  int peer);
+int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+
+int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 			      struct sock *sk);
 
 /*
@@ -829,30 +800,29 @@ extern const struct proto_ops inet6_dgram_ops;
 struct group_source_req;
 struct group_filter;
 
-extern int ip6_mc_source(int add, int omode, struct sock *sk,
-			 struct group_source_req *pgsr);
-extern int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
-extern int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-			 struct group_filter __user *optval,
-			 int __user *optlen);
-extern unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-				    const struct in6_addr *daddr, u32 rnd);
+int ip6_mc_source(int add, int omode, struct sock *sk,
+		  struct group_source_req *pgsr);
+int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
+int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
+		  struct group_filter __user *optval, int __user *optlen);
+unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
+			     const struct in6_addr *daddr, u32 rnd);
 
 #ifdef CONFIG_PROC_FS
-extern int  ac6_proc_init(struct net *net);
-extern void ac6_proc_exit(struct net *net);
-extern int  raw6_proc_init(void);
-extern void raw6_proc_exit(void);
-extern int  tcp6_proc_init(struct net *net);
-extern void tcp6_proc_exit(struct net *net);
-extern int  udp6_proc_init(struct net *net);
-extern void udp6_proc_exit(struct net *net);
-extern int  udplite6_proc_init(void);
-extern void udplite6_proc_exit(void);
-extern int  ipv6_misc_proc_init(void);
-extern void ipv6_misc_proc_exit(void);
-extern int snmp6_register_dev(struct inet6_dev *idev);
-extern int snmp6_unregister_dev(struct inet6_dev *idev);
+int ac6_proc_init(struct net *net);
+void ac6_proc_exit(struct net *net);
+int raw6_proc_init(void);
+void raw6_proc_exit(void);
+int tcp6_proc_init(struct net *net);
+void tcp6_proc_exit(struct net *net);
+int udp6_proc_init(struct net *net);
+void udp6_proc_exit(struct net *net);
+int udplite6_proc_init(void);
+void udplite6_proc_exit(void);
+int ipv6_misc_proc_init(void);
+void ipv6_misc_proc_exit(void);
+int snmp6_register_dev(struct inet6_dev *idev);
+int snmp6_unregister_dev(struct inet6_dev *idev);
 
 #else
 static inline int ac6_proc_init(struct net *net) { return 0; }
@@ -865,10 +835,10 @@ static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; }
 extern struct ctl_table ipv6_route_table_template[];
 extern struct ctl_table ipv6_icmp_table_template[];
 
-extern struct ctl_table *ipv6_icmp_sysctl_init(struct net *net);
-extern struct ctl_table *ipv6_route_sysctl_init(struct net *net);
-extern int ipv6_sysctl_register(void);
-extern void ipv6_sysctl_unregister(void);
+struct ctl_table *ipv6_icmp_sysctl_init(struct net *net);
+struct ctl_table *ipv6_route_sysctl_init(struct net *net);
+int ipv6_sysctl_register(void);
+void ipv6_sysctl_unregister(void);
 #endif
 
 #endif /* _NET_IPV6_H */
-- 
cgit 


From 9d03626a28fd8c14511c96826cb4ca2112fb7709 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:43 -0700
Subject: ipx.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipx.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/ipx.h b/include/net/ipx.h
index c1fec6b464cc..9e9e35465baf 100644
--- a/include/net/ipx.h
+++ b/include/net/ipx.h
@@ -123,23 +123,23 @@ extern struct list_head ipx_routes;
 extern rwlock_t ipx_routes_lock;
 
 extern struct list_head ipx_interfaces;
-extern struct ipx_interface *ipx_interfaces_head(void);
+struct ipx_interface *ipx_interfaces_head(void);
 extern spinlock_t ipx_interfaces_lock;
 
 extern struct ipx_interface *ipx_primary_net;
 
-extern int ipx_proc_init(void);
-extern void ipx_proc_exit(void);
+int ipx_proc_init(void);
+void ipx_proc_exit(void);
 
-extern const char *ipx_frame_name(__be16);
-extern const char *ipx_device_name(struct ipx_interface *intrfc);
+const char *ipx_frame_name(__be16);
+const char *ipx_device_name(struct ipx_interface *intrfc);
 
 static __inline__ void ipxitf_hold(struct ipx_interface *intrfc)
 {
 	atomic_inc(&intrfc->refcnt);
 }
 
-extern void ipxitf_down(struct ipx_interface *intrfc);
+void ipxitf_down(struct ipx_interface *intrfc);
 
 static __inline__ void ipxitf_put(struct ipx_interface *intrfc)
 {
-- 
cgit 


From cb7d3d71e986067d19d991d75bff07ca304c9084 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:44 -0700
Subject: lapb.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lapb.h | 52 ++++++++++++++++++++++++++--------------------------
 1 file changed, 26 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/lapb.h b/include/net/lapb.h
index df892a94f2c6..9510f8725f03 100644
--- a/include/net/lapb.h
+++ b/include/net/lapb.h
@@ -105,40 +105,40 @@ struct lapb_cb {
 };
 
 /* lapb_iface.c */
-extern void lapb_connect_confirmation(struct lapb_cb *lapb, int);
-extern void lapb_connect_indication(struct lapb_cb *lapb, int);
-extern void lapb_disconnect_confirmation(struct lapb_cb *lapb, int);
-extern void lapb_disconnect_indication(struct lapb_cb *lapb, int);
-extern int  lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *);
-extern int  lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *);
+void lapb_connect_confirmation(struct lapb_cb *lapb, int);
+void lapb_connect_indication(struct lapb_cb *lapb, int);
+void lapb_disconnect_confirmation(struct lapb_cb *lapb, int);
+void lapb_disconnect_indication(struct lapb_cb *lapb, int);
+int lapb_data_indication(struct lapb_cb *lapb, struct sk_buff *);
+int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *);
 
 /* lapb_in.c */
-extern void lapb_data_input(struct lapb_cb *lapb, struct sk_buff *);
+void lapb_data_input(struct lapb_cb *lapb, struct sk_buff *);
 
 /* lapb_out.c */
-extern void lapb_kick(struct lapb_cb *lapb);
-extern void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *, int);
-extern void lapb_establish_data_link(struct lapb_cb *lapb);
-extern void lapb_enquiry_response(struct lapb_cb *lapb);
-extern void lapb_timeout_response(struct lapb_cb *lapb);
-extern void lapb_check_iframes_acked(struct lapb_cb *lapb, unsigned short);
-extern void lapb_check_need_response(struct lapb_cb *lapb, int, int);
+void lapb_kick(struct lapb_cb *lapb);
+void lapb_transmit_buffer(struct lapb_cb *lapb, struct sk_buff *, int);
+void lapb_establish_data_link(struct lapb_cb *lapb);
+void lapb_enquiry_response(struct lapb_cb *lapb);
+void lapb_timeout_response(struct lapb_cb *lapb);
+void lapb_check_iframes_acked(struct lapb_cb *lapb, unsigned short);
+void lapb_check_need_response(struct lapb_cb *lapb, int, int);
 
 /* lapb_subr.c */
-extern void lapb_clear_queues(struct lapb_cb *lapb);
-extern void lapb_frames_acked(struct lapb_cb *lapb, unsigned short);
-extern void lapb_requeue_frames(struct lapb_cb *lapb);
-extern int  lapb_validate_nr(struct lapb_cb *lapb, unsigned short);
-extern int lapb_decode(struct lapb_cb *lapb, struct sk_buff *, struct lapb_frame *);
-extern void lapb_send_control(struct lapb_cb *lapb, int, int, int);
-extern void lapb_transmit_frmr(struct lapb_cb *lapb);
+void lapb_clear_queues(struct lapb_cb *lapb);
+void lapb_frames_acked(struct lapb_cb *lapb, unsigned short);
+void lapb_requeue_frames(struct lapb_cb *lapb);
+int lapb_validate_nr(struct lapb_cb *lapb, unsigned short);
+int lapb_decode(struct lapb_cb *lapb, struct sk_buff *, struct lapb_frame *);
+void lapb_send_control(struct lapb_cb *lapb, int, int, int);
+void lapb_transmit_frmr(struct lapb_cb *lapb);
 
 /* lapb_timer.c */
-extern void lapb_start_t1timer(struct lapb_cb *lapb);
-extern void lapb_start_t2timer(struct lapb_cb *lapb);
-extern void lapb_stop_t1timer(struct lapb_cb *lapb);
-extern void lapb_stop_t2timer(struct lapb_cb *lapb);
-extern int  lapb_t1timer_running(struct lapb_cb *lapb);
+void lapb_start_t1timer(struct lapb_cb *lapb);
+void lapb_start_t2timer(struct lapb_cb *lapb);
+void lapb_stop_t1timer(struct lapb_cb *lapb);
+void lapb_stop_t2timer(struct lapb_cb *lapb);
+int lapb_t1timer_running(struct lapb_cb *lapb);
 
 /*
  * Debug levels.
-- 
cgit 


From bf3c710f71a6144bd4d3bb9efb91099863debfb8 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:45 -0700
Subject: llc*.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/llc.h      |  50 ++++++------
 include/net/llc_c_ac.h | 190 ++++++++++++++++++++-------------------------
 include/net/llc_c_ev.h | 207 +++++++++++++++++++------------------------------
 include/net/llc_conn.h |  36 ++++-----
 include/net/llc_if.h   |   7 +-
 include/net/llc_pdu.h  |  33 ++++----
 include/net/llc_s_ac.h |  20 +++--
 include/net/llc_s_ev.h |  21 +++--
 include/net/llc_sap.h  |  22 +++---
 9 files changed, 253 insertions(+), 333 deletions(-)

(limited to 'include')

diff --git a/include/net/llc.h b/include/net/llc.h
index 9e7d7f08ef77..68490cbc8a65 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -95,29 +95,29 @@ struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap,
 extern struct list_head llc_sap_list;
 extern spinlock_t llc_sap_list_lock;
 
-extern int llc_rcv(struct sk_buff *skb, struct net_device *dev,
-		   struct packet_type *pt, struct net_device *orig_dev);
+int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+	    struct net_device *orig_dev);
 
-extern int llc_mac_hdr_init(struct sk_buff *skb,
-			    const unsigned char *sa, const unsigned char *da);
+int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa,
+		     const unsigned char *da);
 
-extern void llc_add_pack(int type, void (*handler)(struct llc_sap *sap,
-						   struct sk_buff *skb));
-extern void llc_remove_pack(int type);
+void llc_add_pack(int type,
+		  void (*handler)(struct llc_sap *sap, struct sk_buff *skb));
+void llc_remove_pack(int type);
 
-extern void llc_set_station_handler(void (*handler)(struct sk_buff *skb));
+void llc_set_station_handler(void (*handler)(struct sk_buff *skb));
 
-extern struct llc_sap *llc_sap_open(unsigned char lsap,
-				    int (*rcv)(struct sk_buff *skb,
-					       struct net_device *dev,
-					       struct packet_type *pt,
-					       struct net_device *orig_dev));
+struct llc_sap *llc_sap_open(unsigned char lsap,
+			     int (*rcv)(struct sk_buff *skb,
+					struct net_device *dev,
+					struct packet_type *pt,
+					struct net_device *orig_dev));
 static inline void llc_sap_hold(struct llc_sap *sap)
 {
 	atomic_inc(&sap->refcnt);
 }
 
-extern void llc_sap_close(struct llc_sap *sap);
+void llc_sap_close(struct llc_sap *sap);
 
 static inline void llc_sap_put(struct llc_sap *sap)
 {
@@ -125,27 +125,27 @@ static inline void llc_sap_put(struct llc_sap *sap)
 		llc_sap_close(sap);
 }
 
-extern struct llc_sap *llc_sap_find(unsigned char sap_value);
+struct llc_sap *llc_sap_find(unsigned char sap_value);
 
-extern int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb,
-				     unsigned char *dmac, unsigned char dsap);
+int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb,
+			      unsigned char *dmac, unsigned char dsap);
 
-extern void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb);
-extern void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb);
+void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb);
+void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb);
 
-extern void llc_station_init(void);
-extern void llc_station_exit(void);
+void llc_station_init(void);
+void llc_station_exit(void);
 
 #ifdef CONFIG_PROC_FS
-extern int llc_proc_init(void);
-extern void llc_proc_exit(void);
+int llc_proc_init(void);
+void llc_proc_exit(void);
 #else
 #define llc_proc_init()	(0)
 #define llc_proc_exit()	do { } while(0)
 #endif /* CONFIG_PROC_FS */
 #ifdef CONFIG_SYSCTL
-extern int llc_sysctl_init(void);
-extern void llc_sysctl_exit(void);
+int llc_sysctl_init(void);
+void llc_sysctl_exit(void);
 
 extern int sysctl_llc2_ack_timeout;
 extern int sysctl_llc2_busy_timeout;
diff --git a/include/net/llc_c_ac.h b/include/net/llc_c_ac.h
index df83f69d2de4..f3be818e73c1 100644
--- a/include/net/llc_c_ac.h
+++ b/include/net/llc_c_ac.h
@@ -89,114 +89,92 @@
 
 typedef int (*llc_conn_action_t)(struct sock *sk, struct sk_buff *skb);
 
-extern int llc_conn_ac_clear_remote_busy(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ac_conn_ind(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ac_conn_confirm(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_data_ind(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_disc_ind(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_rst_ind(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_rst_confirm(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_clear_remote_busy_if_f_eq_1(struct sock* sk,
-						   struct sk_buff *skb);
-extern int llc_conn_ac_stop_rej_tmr_if_data_flag_eq_2(struct sock* sk,
-						      struct sk_buff *skb);
-extern int llc_conn_ac_send_disc_cmd_p_set_x(struct sock* sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ac_send_dm_rsp_f_set_p(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_send_dm_rsp_f_set_1(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_send_frmr_rsp_f_set_x(struct sock* sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ac_resend_frmr_rsp_f_set_0(struct sock* sk,
-					       struct sk_buff *skb);
-extern int llc_conn_ac_resend_frmr_rsp_f_set_p(struct sock* sk,
-					       struct sk_buff *skb);
-extern int llc_conn_ac_send_i_cmd_p_set_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_send_i_xxx_x_set_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_resend_i_xxx_x_set_0(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_resend_i_xxx_x_set_0_or_send_rr(struct sock* sk,
-						       struct sk_buff *skb);
-extern int llc_conn_ac_resend_i_rsp_f_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rej_cmd_p_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rej_rsp_f_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rej_xxx_x_set_0(struct sock* sk,
+int llc_conn_ac_clear_remote_busy(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_conn_ind(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_conn_confirm(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_data_ind(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_disc_ind(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_rst_ind(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_rst_confirm(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_clear_remote_busy_if_f_eq_1(struct sock *sk,
 					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rnr_cmd_p_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rnr_rsp_f_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rnr_xxx_x_set_0(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_set_remote_busy(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_opt_send_rnr_xxx_x_set_0(struct sock* sk,
+int llc_conn_ac_stop_rej_tmr_if_data_flag_eq_2(struct sock *sk,
+					       struct sk_buff *skb);
+int llc_conn_ac_send_disc_cmd_p_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_dm_rsp_f_set_p(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_dm_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_frmr_rsp_f_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_resend_frmr_rsp_f_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_resend_frmr_rsp_f_set_p(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_resend_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_resend_i_xxx_x_set_0_or_send_rr(struct sock *sk,
 						struct sk_buff *skb);
-extern int llc_conn_ac_send_rr_cmd_p_set_1(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_send_rr_rsp_f_set_1(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_send_ack_rsp_f_set_1(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_rr_xxx_x_set_0(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_send_ack_xxx_x_set_0(struct sock* sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ac_send_sabme_cmd_p_set_x(struct sock* sk,
-					      struct sk_buff *skb);
-extern int llc_conn_ac_send_ua_rsp_f_set_p(struct sock* sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ac_set_s_flag_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_s_flag_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_start_p_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_start_ack_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_start_rej_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_start_ack_tmr_if_not_running(struct sock* sk,
-						    struct sk_buff *skb);
-extern int llc_conn_ac_stop_ack_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_stop_p_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_stop_rej_timer(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_stop_all_timers(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_stop_other_timers(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_upd_nr_received(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_inc_tx_win_size(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_dec_tx_win_size(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_upd_p_flag(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_data_flag_2(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_data_flag_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_data_flag_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_data_flag_1_if_data_flag_eq_0(struct sock* sk,
-							 struct sk_buff *skb);
-extern int llc_conn_ac_set_p_flag_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_remote_busy_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_retry_cnt_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_cause_flag_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_cause_flag_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_inc_retry_cnt_by_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_vr_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_inc_vr_by_1(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_vs_0(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_set_vs_nr(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_rst_vs(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_upd_vs(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_disc(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_reset(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_disc_confirm(struct sock* sk, struct sk_buff *skb);
-extern u8 llc_circular_between(u8 a, u8 b, u8 c);
-extern int llc_conn_ac_send_ack_if_needed(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_adjust_npta_by_rr(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_adjust_npta_by_rnr(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_rst_sendack_flag(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_send_i_rsp_as_ack(struct sock* sk, struct sk_buff *skb);
-extern int llc_conn_ac_send_i_as_ack(struct sock* sk, struct sk_buff *skb);
+int llc_conn_ac_resend_i_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rej_cmd_p_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rej_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rej_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rnr_cmd_p_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rnr_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rnr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_remote_busy(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_opt_send_rnr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rr_cmd_p_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rr_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_ack_rsp_f_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_rr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_ack_xxx_x_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_sabme_cmd_p_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_ua_rsp_f_set_p(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_s_flag_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_s_flag_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_start_p_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_start_ack_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_start_rej_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_start_ack_tmr_if_not_running(struct sock *sk,
+					     struct sk_buff *skb);
+int llc_conn_ac_stop_ack_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_stop_p_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_stop_rej_timer(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_stop_other_timers(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_upd_nr_received(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_dec_tx_win_size(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_upd_p_flag(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_data_flag_2(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_data_flag_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_data_flag_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_data_flag_1_if_data_flag_eq_0(struct sock *sk,
+						  struct sk_buff *skb);
+int llc_conn_ac_set_p_flag_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_remote_busy_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_retry_cnt_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_cause_flag_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_cause_flag_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_inc_retry_cnt_by_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_vr_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_inc_vr_by_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_vs_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_set_vs_nr(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_rst_vs(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_upd_vs(struct sock *sk, struct sk_buff *skb);
+int llc_conn_disc(struct sock *sk, struct sk_buff *skb);
+int llc_conn_reset(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_disc_confirm(struct sock *sk, struct sk_buff *skb);
+u8 llc_circular_between(u8 a, u8 b, u8 c);
+int llc_conn_ac_send_ack_if_needed(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_adjust_npta_by_rr(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_adjust_npta_by_rnr(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_i_rsp_as_ack(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb);
 
-extern void llc_conn_busy_tmr_cb(unsigned long timeout_data);
-extern void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data);
-extern void llc_conn_ack_tmr_cb(unsigned long timeout_data);
-extern void llc_conn_rej_tmr_cb(unsigned long timeout_data);
+void llc_conn_busy_tmr_cb(unsigned long timeout_data);
+void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data);
+void llc_conn_ack_tmr_cb(unsigned long timeout_data);
+void llc_conn_rej_tmr_cb(unsigned long timeout_data);
 
-extern void llc_conn_set_p_flag(struct sock *sk, u8 value);
+void llc_conn_set_p_flag(struct sock *sk, u8 value);
 #endif /* LLC_C_AC_H */
diff --git a/include/net/llc_c_ev.h b/include/net/llc_c_ev.h
index 6ca3113df39e..3948cf111dd0 100644
--- a/include/net/llc_c_ev.h
+++ b/include/net/llc_c_ev.h
@@ -128,138 +128,93 @@ static __inline__ struct llc_conn_state_ev *llc_conn_ev(struct sk_buff *skb)
 typedef int (*llc_conn_ev_t)(struct sock *sk, struct sk_buff *skb);
 typedef int (*llc_conn_ev_qfyr_t)(struct sock *sk, struct sk_buff *skb);
 
-extern int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_local_busy_detected(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk,
+int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk,
+					     struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk,
 					      struct sk_buff *skb);
-extern int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk,
-					      struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk,
-						    struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk,
+int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk,
+					     struct sk_buff *skb);
+int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk,
 					       struct sk_buff *skb);
-extern int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk,
-						      struct sk_buff *skb);
-extern int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk,
-						      struct sk_buff *skb);
-extern int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_sendack_tmr_exp(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk,
+					       struct sk_buff *skb);
+int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_sendack_tmr_exp(struct sock *sk, struct sk_buff *skb);
 /* NOT_USED functions and their variations */
-extern int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk,
+					      struct sk_buff *skb);
+int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk,
+					      struct sk_buff *skb);
+int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk,
+					      struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk,
+					      struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb);
 
 /* Available connection action qualifiers */
-extern int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk,
-					   struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk,
-					     struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk,
+int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk,
 					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_conn(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_disc(struct sock *sk,
-					    struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_failed(struct sock *sk,
-					      struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk,
-						  struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk,
-					      struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk,
-						struct sk_buff *skb);
-extern int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk,
-						struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb);
+int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb);
 
 static __inline__ int llc_conn_space(struct sock *sk, struct sk_buff *skb)
 {
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index 2f97d8ddce92..0134681acc4c 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -95,28 +95,24 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb)
 	return skb->cb[sizeof(skb->cb) - 1];
 }
 
-extern struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
-				 struct proto *prot);
-extern void llc_sk_free(struct sock *sk);
+struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority,
+			  struct proto *prot);
+void llc_sk_free(struct sock *sk);
 
-extern void llc_sk_reset(struct sock *sk);
+void llc_sk_reset(struct sock *sk);
 
 /* Access to a connection */
-extern int llc_conn_state_process(struct sock *sk, struct sk_buff *skb);
-extern void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb);
-extern void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb);
-extern void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr,
-					 u8 first_p_bit);
-extern void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr,
-					 u8 first_f_bit);
-extern int llc_conn_remove_acked_pdus(struct sock *conn, u8 nr,
-				      u16 *how_many_unacked);
-extern struct sock *llc_lookup_established(struct llc_sap *sap,
-					   struct llc_addr *daddr,
-					   struct llc_addr *laddr);
-extern void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk);
-extern void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk);
+int llc_conn_state_process(struct sock *sk, struct sk_buff *skb);
+void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb);
+void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb);
+void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit);
+void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit);
+int llc_conn_remove_acked_pdus(struct sock *conn, u8 nr, u16 *how_many_unacked);
+struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr,
+				    struct llc_addr *laddr);
+void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk);
+void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk);
 
-extern u8 llc_data_accept_state(u8 state);
-extern void llc_build_offset_table(void);
+u8 llc_data_accept_state(u8 state);
+void llc_build_offset_table(void);
 #endif /* LLC_CONN_H */
diff --git a/include/net/llc_if.h b/include/net/llc_if.h
index f0cb909b60eb..8d5c543cd620 100644
--- a/include/net/llc_if.h
+++ b/include/net/llc_if.h
@@ -62,8 +62,7 @@
 #define LLC_STATUS_CONFLICT	7 /* disconnect conn */
 #define LLC_STATUS_RESET_DONE	8 /*  */
 
-extern int llc_establish_connection(struct sock *sk, u8 *lmac,
-				    u8 *dmac, u8 dsap);
-extern int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb);
-extern int llc_send_disc(struct sock *sk);
+int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap);
+int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb);
+int llc_send_disc(struct sock *sk);
 #endif /* LLC_IF_H */
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 5a93d13ac95c..31e2de7d57c5 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -410,21 +410,20 @@ struct llc_frmr_info {
 	u8  ind_bits;		/* indicator bits set with macro */
 } __packed;
 
-extern void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 type);
-extern void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value);
-extern void llc_pdu_decode_pf_bit(struct sk_buff *skb, u8 *pf_bit);
-extern void llc_pdu_init_as_disc_cmd(struct sk_buff *skb, u8 p_bit);
-extern void llc_pdu_init_as_i_cmd(struct sk_buff *skb, u8 p_bit, u8 ns, u8 nr);
-extern void llc_pdu_init_as_rej_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
-extern void llc_pdu_init_as_rnr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
-extern void llc_pdu_init_as_rr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
-extern void llc_pdu_init_as_sabme_cmd(struct sk_buff *skb, u8 p_bit);
-extern void llc_pdu_init_as_dm_rsp(struct sk_buff *skb, u8 f_bit);
-extern void llc_pdu_init_as_frmr_rsp(struct sk_buff *skb,
-				     struct llc_pdu_sn *prev_pdu,
-				     u8 f_bit, u8 vs, u8 vr, u8 vzyxw);
-extern void llc_pdu_init_as_rr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
-extern void llc_pdu_init_as_rej_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
-extern void llc_pdu_init_as_rnr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
-extern void llc_pdu_init_as_ua_rsp(struct sk_buff *skb, u8 f_bit);
+void llc_pdu_set_cmd_rsp(struct sk_buff *skb, u8 type);
+void llc_pdu_set_pf_bit(struct sk_buff *skb, u8 bit_value);
+void llc_pdu_decode_pf_bit(struct sk_buff *skb, u8 *pf_bit);
+void llc_pdu_init_as_disc_cmd(struct sk_buff *skb, u8 p_bit);
+void llc_pdu_init_as_i_cmd(struct sk_buff *skb, u8 p_bit, u8 ns, u8 nr);
+void llc_pdu_init_as_rej_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
+void llc_pdu_init_as_rnr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
+void llc_pdu_init_as_rr_cmd(struct sk_buff *skb, u8 p_bit, u8 nr);
+void llc_pdu_init_as_sabme_cmd(struct sk_buff *skb, u8 p_bit);
+void llc_pdu_init_as_dm_rsp(struct sk_buff *skb, u8 f_bit);
+void llc_pdu_init_as_frmr_rsp(struct sk_buff *skb, struct llc_pdu_sn *prev_pdu,
+			      u8 f_bit, u8 vs, u8 vr, u8 vzyxw);
+void llc_pdu_init_as_rr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
+void llc_pdu_init_as_rej_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
+void llc_pdu_init_as_rnr_rsp(struct sk_buff *skb, u8 f_bit, u8 nr);
+void llc_pdu_init_as_ua_rsp(struct sk_buff *skb, u8 f_bit);
 #endif /* LLC_PDU_H */
diff --git a/include/net/llc_s_ac.h b/include/net/llc_s_ac.h
index 37a3bbd02394..a61b98c108ee 100644
--- a/include/net/llc_s_ac.h
+++ b/include/net/llc_s_ac.h
@@ -25,15 +25,13 @@
 /* All action functions must look like this */
 typedef int (*llc_sap_action_t)(struct llc_sap *sap, struct sk_buff *skb);
 
-extern int llc_sap_action_unitdata_ind(struct llc_sap *sap,
-				       struct sk_buff *skb);
-extern int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_send_xid_r(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_report_status(struct llc_sap *sap,
-					struct sk_buff *skb);
-extern int llc_sap_action_xid_ind(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_action_test_ind(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_send_xid_r(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_report_status(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_xid_ind(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_action_test_ind(struct llc_sap *sap, struct sk_buff *skb);
 #endif /* LLC_S_AC_H */
diff --git a/include/net/llc_s_ev.h b/include/net/llc_s_ev.h
index e3acb9329e4a..84db3a59ed28 100644
--- a/include/net/llc_s_ev.h
+++ b/include/net/llc_s_ev.h
@@ -53,15 +53,14 @@ struct llc_sap;
 
 typedef int (*llc_sap_ev_t)(struct llc_sap *sap, struct sk_buff *skb);
 
-extern int llc_sap_ev_activation_req(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_rx_ui(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_unitdata_req(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_xid_req(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_rx_xid_c(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_rx_xid_r(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_test_req(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_rx_test_c(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_rx_test_r(struct llc_sap *sap, struct sk_buff *skb);
-extern int llc_sap_ev_deactivation_req(struct llc_sap *sap,
-				       struct sk_buff *skb);
+int llc_sap_ev_activation_req(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_rx_ui(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_unitdata_req(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_xid_req(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_rx_xid_c(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_rx_xid_r(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_test_req(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_rx_test_c(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_rx_test_r(struct llc_sap *sap, struct sk_buff *skb);
+int llc_sap_ev_deactivation_req(struct llc_sap *sap, struct sk_buff *skb);
 #endif /* LLC_S_EV_H */
diff --git a/include/net/llc_sap.h b/include/net/llc_sap.h
index ed25bec2f648..1e4df9fd9fb2 100644
--- a/include/net/llc_sap.h
+++ b/include/net/llc_sap.h
@@ -19,18 +19,14 @@ struct net_device;
 struct sk_buff;
 struct sock;
 
-extern void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb);
-extern void llc_save_primitive(struct sock *sk, struct sk_buff* skb,
-			       unsigned char prim);
-extern struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev,
-				       u8 type, u32 data_size);
+void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb);
+void llc_save_primitive(struct sock *sk, struct sk_buff *skb,
+			unsigned char prim);
+struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev,
+				u8 type, u32 data_size);
 
-extern void llc_build_and_send_test_pkt(struct llc_sap *sap,
-				        struct sk_buff *skb,
-					unsigned char *dmac,
-					unsigned char dsap);
-extern void llc_build_and_send_xid_pkt(struct llc_sap *sap,
-				       struct sk_buff *skb,
-				       unsigned char *dmac,
-				       unsigned char dsap);
+void llc_build_and_send_test_pkt(struct llc_sap *sap, struct sk_buff *skb,
+				 unsigned char *dmac, unsigned char dsap);
+void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb,
+				unsigned char *dmac, unsigned char dsap);
 #endif /* LLC_SAP_H */
-- 
cgit 


From a5be1eb6488f4755a8dc237d5ba689667ddeeab5 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:46 -0700
Subject: mrp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/mrp.h | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/mrp.h b/include/net/mrp.h
index 4fbf02aa2ec1..687c8feecd09 100644
--- a/include/net/mrp.h
+++ b/include/net/mrp.h
@@ -125,19 +125,17 @@ struct mrp_port {
 	struct rcu_head			rcu;
 };
 
-extern int	mrp_register_application(struct mrp_application *app);
-extern void	mrp_unregister_application(struct mrp_application *app);
-
-extern int	mrp_init_applicant(struct net_device *dev,
-				    struct mrp_application *app);
-extern void	mrp_uninit_applicant(struct net_device *dev,
-				      struct mrp_application *app);
-
-extern int	mrp_request_join(const struct net_device *dev,
-				  const struct mrp_application *app,
-				  const void *value, u8 len, u8 type);
-extern void	mrp_request_leave(const struct net_device *dev,
-				   const struct mrp_application *app,
-				   const void *value, u8 len, u8 type);
+int mrp_register_application(struct mrp_application *app);
+void mrp_unregister_application(struct mrp_application *app);
+
+int mrp_init_applicant(struct net_device *dev, struct mrp_application *app);
+void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *app);
+
+int mrp_request_join(const struct net_device *dev,
+		     const struct mrp_application *app,
+		     const void *value, u8 len, u8 type);
+void mrp_request_leave(const struct net_device *dev,
+		       const struct mrp_application *app,
+		       const void *value, u8 len, u8 type);
 
 #endif /* _NET_MRP_H */
-- 
cgit 


From 3cc818a27d17fc57aa37ee89d09feb2bc2dd789f Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:47 -0700
Subject: ndisc.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h | 61 +++++++++++++++++++++++------------------------------
 1 file changed, 26 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index ea0cc26ab70e..6bbda34d5e59 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -110,8 +110,8 @@ struct ndisc_options {
 
 #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7)
 
-extern struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
-						 struct ndisc_options *ndopts);
+struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+					  struct ndisc_options *ndopts);
 
 /*
  * Return the padding between the option length and the start of the
@@ -189,60 +189,51 @@ static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, cons
 	return n;
 }
 
-extern int			ndisc_init(void);
-extern int			ndisc_late_init(void);
+int ndisc_init(void);
+int ndisc_late_init(void);
 
-extern void			ndisc_late_cleanup(void);
-extern void			ndisc_cleanup(void);
+void ndisc_late_cleanup(void);
+void ndisc_cleanup(void);
 
-extern int			ndisc_rcv(struct sk_buff *skb);
+int ndisc_rcv(struct sk_buff *skb);
 
-extern void			ndisc_send_ns(struct net_device *dev,
-					      struct neighbour *neigh,
-					      const struct in6_addr *solicit,
-					      const struct in6_addr *daddr,
-					      const struct in6_addr *saddr);
+void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
+		   const struct in6_addr *solicit,
+		   const struct in6_addr *daddr, const struct in6_addr *saddr);
 
-extern void			ndisc_send_rs(struct net_device *dev,
-					      const struct in6_addr *saddr,
-					      const struct in6_addr *daddr);
-extern void			ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
-					      const struct in6_addr *daddr,
-					      const struct in6_addr *solicited_addr,
-					      bool router, bool solicited, bool override,
-					      bool inc_opt);
+void ndisc_send_rs(struct net_device *dev,
+		   const struct in6_addr *saddr, const struct in6_addr *daddr);
+void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
+		   const struct in6_addr *daddr,
+		   const struct in6_addr *solicited_addr,
+		   bool router, bool solicited, bool override, bool inc_opt);
 
-extern void			ndisc_send_redirect(struct sk_buff *skb,
-						    const struct in6_addr *target);
+void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target);
 
-extern int			ndisc_mc_map(const struct in6_addr *addr, char *buf,
-					     struct net_device *dev, int dir);
+int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
+		 int dir);
 
 
 /*
  *	IGMP
  */
-extern int			igmp6_init(void);
+int igmp6_init(void);
 
-extern void			igmp6_cleanup(void);
+void igmp6_cleanup(void);
 
-extern int			igmp6_event_query(struct sk_buff *skb);
+int igmp6_event_query(struct sk_buff *skb);
 
-extern int			igmp6_event_report(struct sk_buff *skb);
+int igmp6_event_report(struct sk_buff *skb);
 
 
 #ifdef CONFIG_SYSCTL
-extern int 			ndisc_ifinfo_sysctl_change(struct ctl_table *ctl,
-							   int write,
-							   void __user *buffer,
-							   size_t *lenp,
-							   loff_t *ppos);
+int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write,
+			       void __user *buffer, size_t *lenp, loff_t *ppos);
 int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl,
 				 void __user *oldval, size_t __user *oldlenp,
 				 void __user *newval, size_t newlen);
 #endif
 
-extern void 			inet6_ifinfo_notify(int event,
-						    struct inet6_dev *idev);
+void inet6_ifinfo_notify(int event, struct inet6_dev *idev);
 
 #endif
-- 
cgit 


From e67e16ea9b5ad1dd76adf32233aed75c1f619433 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:48 -0700
Subject: net_namespace.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 1313456a0994..38c2afb585de 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -136,8 +136,8 @@ struct net {
 extern struct net init_net;
 
 #ifdef CONFIG_NET_NS
-extern struct net *copy_net_ns(unsigned long flags,
-	struct user_namespace *user_ns, struct net *old_net);
+struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns,
+			struct net *old_net);
 
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
@@ -154,11 +154,11 @@ static inline struct net *copy_net_ns(unsigned long flags,
 
 extern struct list_head net_namespace_list;
 
-extern struct net *get_net_ns_by_pid(pid_t pid);
-extern struct net *get_net_ns_by_fd(int pid);
+struct net *get_net_ns_by_pid(pid_t pid);
+struct net *get_net_ns_by_fd(int pid);
 
 #ifdef CONFIG_NET_NS
-extern void __put_net(struct net *net);
+void __put_net(struct net *net);
 
 static inline struct net *get_net(struct net *net)
 {
@@ -190,7 +190,7 @@ int net_eq(const struct net *net1, const struct net *net2)
 	return net1 == net2;
 }
 
-extern void net_drop_ns(void *);
+void net_drop_ns(void *);
 
 #else
 
@@ -307,19 +307,19 @@ struct pernet_operations {
  * device which caused kernel oops, and panics during network
  * namespace cleanup.   So please don't get this wrong.
  */
-extern int register_pernet_subsys(struct pernet_operations *);
-extern void unregister_pernet_subsys(struct pernet_operations *);
-extern int register_pernet_device(struct pernet_operations *);
-extern void unregister_pernet_device(struct pernet_operations *);
+int register_pernet_subsys(struct pernet_operations *);
+void unregister_pernet_subsys(struct pernet_operations *);
+int register_pernet_device(struct pernet_operations *);
+void unregister_pernet_device(struct pernet_operations *);
 
 struct ctl_table;
 struct ctl_table_header;
 
 #ifdef CONFIG_SYSCTL
-extern int net_sysctl_init(void);
-extern struct ctl_table_header *register_net_sysctl(struct net *net,
-	const char *path, struct ctl_table *table);
-extern void unregister_net_sysctl_table(struct ctl_table_header *header);
+int net_sysctl_init(void);
+struct ctl_table_header *register_net_sysctl(struct net *net, const char *path,
+					     struct ctl_table *table);
+void unregister_net_sysctl_table(struct ctl_table_header *header);
 #else
 static inline int net_sysctl_init(void) { return 0; }
 static inline struct ctl_table_header *register_net_sysctl(struct net *net,
-- 
cgit 


From 70a3926f49896be866e5f2bd9c47cf4b33e3f2e3 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:49 -0700
Subject: iw_handler.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/iw_handler.h | 38 +++++++++++++-------------------------
 1 file changed, 13 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index 5d5a6a4732ef..a830b01baba4 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -432,44 +432,32 @@ struct iw_public_data {
 /* First : function strictly used inside the kernel */
 
 /* Handle /proc/net/wireless, called in net/code/dev.c */
-extern int dev_get_wireless_info(char * buffer, char **start, off_t offset,
-				 int length);
+int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length);
 
 /* Second : functions that may be called by driver modules */
 
 /* Send a single event to user space */
-extern void wireless_send_event(struct net_device *	dev,
-				unsigned int		cmd,
-				union iwreq_data *	wrqu,
-				const char *		extra);
+void wireless_send_event(struct net_device *dev, unsigned int cmd,
+			 union iwreq_data *wrqu, const char *extra);
 
 /* We may need a function to send a stream of events to user space.
  * More on that later... */
 
 /* Standard handler for SIOCSIWSPY */
-extern int iw_handler_set_spy(struct net_device *	dev,
-			      struct iw_request_info *	info,
-			      union iwreq_data *	wrqu,
-			      char *			extra);
+int iw_handler_set_spy(struct net_device *dev, struct iw_request_info *info,
+		       union iwreq_data *wrqu, char *extra);
 /* Standard handler for SIOCGIWSPY */
-extern int iw_handler_get_spy(struct net_device *	dev,
-			      struct iw_request_info *	info,
-			      union iwreq_data *	wrqu,
-			      char *			extra);
+int iw_handler_get_spy(struct net_device *dev, struct iw_request_info *info,
+		       union iwreq_data *wrqu, char *extra);
 /* Standard handler for SIOCSIWTHRSPY */
-extern int iw_handler_set_thrspy(struct net_device *	dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *	wrqu,
-				 char *			extra);
+int iw_handler_set_thrspy(struct net_device *dev, struct iw_request_info *info,
+			  union iwreq_data *wrqu, char *extra);
 /* Standard handler for SIOCGIWTHRSPY */
-extern int iw_handler_get_thrspy(struct net_device *	dev,
-				 struct iw_request_info *info,
-				 union iwreq_data *	wrqu,
-				 char *			extra);
+int iw_handler_get_thrspy(struct net_device *dev, struct iw_request_info *info,
+			  union iwreq_data *wrqu, char *extra);
 /* Driver call to update spy records */
-extern void wireless_spy_update(struct net_device *	dev,
-				unsigned char *		address,
-				struct iw_quality *	wstats);
+void wireless_spy_update(struct net_device *dev, unsigned char *address,
+			 struct iw_quality *wstats);
 
 /************************* INLINE FUNTIONS *************************/
 /*
-- 
cgit 


From 4f69053b72c542faec2096ab454bba729a423efe Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:50 -0700
Subject: netevent/netlink.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netevent.h |  6 ++---
 include/net/netlink.h  | 63 ++++++++++++++++++++------------------------------
 2 files changed, 28 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/net/netevent.h b/include/net/netevent.h
index fe630dde35c3..d8bbb38584b6 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -26,8 +26,8 @@ enum netevent_notif_type {
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 };
 
-extern int register_netevent_notifier(struct notifier_block *nb);
-extern int unregister_netevent_notifier(struct notifier_block *nb);
-extern int call_netevent_notifiers(unsigned long val, void *v);
+int register_netevent_notifier(struct notifier_block *nb);
+int unregister_netevent_notifier(struct notifier_block *nb);
+int call_netevent_notifiers(unsigned long val, void *v);
 
 #endif
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 9690b0f6698a..2b47eaadba8f 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -225,44 +225,31 @@ struct nl_info {
 	u32			portid;
 };
 
-extern int		netlink_rcv_skb(struct sk_buff *skb,
-					int (*cb)(struct sk_buff *,
-						  struct nlmsghdr *));
-extern int		nlmsg_notify(struct sock *sk, struct sk_buff *skb,
-				     u32 portid, unsigned int group, int report,
-				     gfp_t flags);
-
-extern int		nla_validate(const struct nlattr *head,
-				     int len, int maxtype,
-				     const struct nla_policy *policy);
-extern int		nla_parse(struct nlattr **tb, int maxtype,
-				  const struct nlattr *head, int len,
-				  const struct nla_policy *policy);
-extern int		nla_policy_len(const struct nla_policy *, int);
-extern struct nlattr *	nla_find(const struct nlattr *head,
-				 int len, int attrtype);
-extern size_t		nla_strlcpy(char *dst, const struct nlattr *nla,
-				    size_t dstsize);
-extern int		nla_memcpy(void *dest, const struct nlattr *src, int count);
-extern int		nla_memcmp(const struct nlattr *nla, const void *data,
-				   size_t size);
-extern int		nla_strcmp(const struct nlattr *nla, const char *str);
-extern struct nlattr *	__nla_reserve(struct sk_buff *skb, int attrtype,
-				      int attrlen);
-extern void *		__nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
-extern struct nlattr *	nla_reserve(struct sk_buff *skb, int attrtype,
-				    int attrlen);
-extern void *		nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
-extern void		__nla_put(struct sk_buff *skb, int attrtype,
-				  int attrlen, const void *data);
-extern void		__nla_put_nohdr(struct sk_buff *skb, int attrlen,
-					const void *data);
-extern int		nla_put(struct sk_buff *skb, int attrtype,
-				int attrlen, const void *data);
-extern int		nla_put_nohdr(struct sk_buff *skb, int attrlen,
-				      const void *data);
-extern int		nla_append(struct sk_buff *skb, int attrlen,
-				   const void *data);
+int netlink_rcv_skb(struct sk_buff *skb,
+		    int (*cb)(struct sk_buff *, struct nlmsghdr *));
+int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
+		 unsigned int group, int report, gfp_t flags);
+
+int nla_validate(const struct nlattr *head, int len, int maxtype,
+		 const struct nla_policy *policy);
+int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
+	      int len, const struct nla_policy *policy);
+int nla_policy_len(const struct nla_policy *, int);
+struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
+size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
+int nla_memcpy(void *dest, const struct nlattr *src, int count);
+int nla_memcmp(const struct nlattr *nla, const void *data, size_t size);
+int nla_strcmp(const struct nlattr *nla, const char *str);
+struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen);
+void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
+struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen);
+void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen);
+void __nla_put(struct sk_buff *skb, int attrtype, int attrlen,
+	       const void *data);
+void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data);
+int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data);
+int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data);
+int nla_append(struct sk_buff *skb, int attrlen, const void *data);
 
 /**************************************************************************
  * Netlink Messages
-- 
cgit 


From 96496127fe2f37c3670facfdbcc5cc51460c439c Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:51 -0700
Subject: netrom.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netrom.h | 89 ++++++++++++++++++++++++++--------------------------
 1 file changed, 44 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/net/netrom.h b/include/net/netrom.h
index 121dcf854db5..110350aca3df 100644
--- a/include/net/netrom.h
+++ b/include/net/netrom.h
@@ -183,51 +183,50 @@ extern int  sysctl_netrom_routing_control;
 extern int  sysctl_netrom_link_fails_count;
 extern int  sysctl_netrom_reset_circuit;
 
-extern int  nr_rx_frame(struct sk_buff *, struct net_device *);
-extern void nr_destroy_socket(struct sock *);
+int nr_rx_frame(struct sk_buff *, struct net_device *);
+void nr_destroy_socket(struct sock *);
 
 /* nr_dev.c */
-extern int  nr_rx_ip(struct sk_buff *, struct net_device *);
-extern void nr_setup(struct net_device *);
+int nr_rx_ip(struct sk_buff *, struct net_device *);
+void nr_setup(struct net_device *);
 
 /* nr_in.c */
-extern int  nr_process_rx_frame(struct sock *, struct sk_buff *);
+int nr_process_rx_frame(struct sock *, struct sk_buff *);
 
 /* nr_loopback.c */
-extern void nr_loopback_init(void);
-extern void nr_loopback_clear(void);
-extern int  nr_loopback_queue(struct sk_buff *);
+void nr_loopback_init(void);
+void nr_loopback_clear(void);
+int nr_loopback_queue(struct sk_buff *);
 
 /* nr_out.c */
-extern void nr_output(struct sock *, struct sk_buff *);
-extern void nr_send_nak_frame(struct sock *);
-extern void nr_kick(struct sock *);
-extern void nr_transmit_buffer(struct sock *, struct sk_buff *);
-extern void nr_establish_data_link(struct sock *);
-extern void nr_enquiry_response(struct sock *);
-extern void nr_check_iframes_acked(struct sock *, unsigned short);
+void nr_output(struct sock *, struct sk_buff *);
+void nr_send_nak_frame(struct sock *);
+void nr_kick(struct sock *);
+void nr_transmit_buffer(struct sock *, struct sk_buff *);
+void nr_establish_data_link(struct sock *);
+void nr_enquiry_response(struct sock *);
+void nr_check_iframes_acked(struct sock *, unsigned short);
 
 /* nr_route.c */
-extern void nr_rt_device_down(struct net_device *);
-extern struct net_device *nr_dev_first(void);
-extern struct net_device *nr_dev_get(ax25_address *);
-extern int  nr_rt_ioctl(unsigned int, void __user *);
-extern void nr_link_failed(ax25_cb *, int);
-extern int  nr_route_frame(struct sk_buff *, ax25_cb *);
+void nr_rt_device_down(struct net_device *);
+struct net_device *nr_dev_first(void);
+struct net_device *nr_dev_get(ax25_address *);
+int nr_rt_ioctl(unsigned int, void __user *);
+void nr_link_failed(ax25_cb *, int);
+int nr_route_frame(struct sk_buff *, ax25_cb *);
 extern const struct file_operations nr_nodes_fops;
 extern const struct file_operations nr_neigh_fops;
-extern void nr_rt_free(void);
+void nr_rt_free(void);
 
 /* nr_subr.c */
-extern void nr_clear_queues(struct sock *);
-extern void nr_frames_acked(struct sock *, unsigned short);
-extern void nr_requeue_frames(struct sock *);
-extern int  nr_validate_nr(struct sock *, unsigned short);
-extern int  nr_in_rx_window(struct sock *, unsigned short);
-extern void nr_write_internal(struct sock *, int);
+void nr_clear_queues(struct sock *);
+void nr_frames_acked(struct sock *, unsigned short);
+void nr_requeue_frames(struct sock *);
+int nr_validate_nr(struct sock *, unsigned short);
+int nr_in_rx_window(struct sock *, unsigned short);
+void nr_write_internal(struct sock *, int);
 
-extern void __nr_transmit_reply(struct sk_buff *skb, int mine,
-	unsigned char cmdflags);
+void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags);
 
 /*
  * This routine is called when a Connect Acknowledge with the Choke Flag
@@ -247,24 +246,24 @@ do {									\
 	__nr_transmit_reply((skb), (mine), NR_RESET);			\
 } while (0)
 
-extern void nr_disconnect(struct sock *, int);
+void nr_disconnect(struct sock *, int);
 
 /* nr_timer.c */
-extern void nr_init_timers(struct sock *sk);
-extern void nr_start_heartbeat(struct sock *);
-extern void nr_start_t1timer(struct sock *);
-extern void nr_start_t2timer(struct sock *);
-extern void nr_start_t4timer(struct sock *);
-extern void nr_start_idletimer(struct sock *);
-extern void nr_stop_heartbeat(struct sock *);
-extern void nr_stop_t1timer(struct sock *);
-extern void nr_stop_t2timer(struct sock *);
-extern void nr_stop_t4timer(struct sock *);
-extern void nr_stop_idletimer(struct sock *);
-extern int  nr_t1timer_running(struct sock *);
+void nr_init_timers(struct sock *sk);
+void nr_start_heartbeat(struct sock *);
+void nr_start_t1timer(struct sock *);
+void nr_start_t2timer(struct sock *);
+void nr_start_t4timer(struct sock *);
+void nr_start_idletimer(struct sock *);
+void nr_stop_heartbeat(struct sock *);
+void nr_stop_t1timer(struct sock *);
+void nr_stop_t2timer(struct sock *);
+void nr_stop_t4timer(struct sock *);
+void nr_stop_idletimer(struct sock *);
+int nr_t1timer_running(struct sock *);
 
 /* sysctl_net_netrom.c */
-extern void nr_register_sysctl(void);
-extern void nr_unregister_sysctl(void);
+void nr_register_sysctl(void);
+void nr_unregister_sysctl(void);
 
 #endif
-- 
cgit 


From 8dda204164131ff56fffc5443c475d8ed57d5ebd Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 21 Sep 2013 10:22:52 -0700
Subject: p8022.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/p8022.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/p8022.h b/include/net/p8022.h
index 42e9fac51b31..05e41383856b 100644
--- a/include/net/p8022.h
+++ b/include/net/p8022.h
@@ -1,13 +1,13 @@
 #ifndef _NET_P8022_H
 #define _NET_P8022_H
-extern struct datalink_proto *
-	register_8022_client(unsigned char type,
-			     int (*func)(struct sk_buff *skb,
-					 struct net_device *dev,
-					 struct packet_type *pt,
-					 struct net_device *orig_dev));
-extern void unregister_8022_client(struct datalink_proto *proto);
+struct datalink_proto *
+register_8022_client(unsigned char type,
+		     int (*func)(struct sk_buff *skb,
+				 struct net_device *dev,
+				 struct packet_type *pt,
+				 struct net_device *orig_dev));
+void unregister_8022_client(struct datalink_proto *proto);
 
-extern struct datalink_proto *make_8023_client(void);
-extern void destroy_8023_client(struct datalink_proto *dl);
+struct datalink_proto *make_8023_client(void);
+void destroy_8023_client(struct datalink_proto *dl);
 #endif
-- 
cgit 


From ca9a563805f7ae821e3303b1bdbc65d3a3c783ff Mon Sep 17 00:00:00 2001
From: Zubair Lutfullah <zubair.lutfullah@gmail.com>
Date: Thu, 19 Sep 2013 07:24:00 +0100
Subject: iio: ti_am335x_adc: Add continuous sampling support

Previously the driver had only one-shot reading functionality.
This patch adds continuous sampling support to the driver.

Continuous sampling starts when buffer is enabled.
HW IRQ wakes worker thread that pushes samples to userspace.
Sampling stops when buffer is disabled by userspace.

Patil Rachna (TI) laid the ground work for ADC HW register access.
Russ Dill (TI) fixed bugs in the driver relevant to FIFOs and IRQs.

I fixed channel scanning so multiple ADC channels can be read
simultaneously and pushed to userspace.
Restructured the driver to fit IIO ABI.
And added INDIO_BUFFER_HARDWARE mode.

Signed-off-by: Zubair Lutfullah <zubair.lutfullah@gmail.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Russ Dill <Russ.Dill@ti.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/adc/Kconfig              |   1 +
 drivers/iio/adc/ti_am335x_adc.c      | 213 ++++++++++++++++++++++++++++++++++-
 include/linux/mfd/ti_am335x_tscadc.h |   9 ++
 3 files changed, 218 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 0cf5c611b4c6..8b885188b839 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -177,6 +177,7 @@ config TI_ADC081C
 config TI_AM335X_ADC
 	tristate "TI's AM335X ADC driver"
 	depends on MFD_TI_AM335X_TSCADC
+	select IIO_KFIFO_BUF
 	help
 	  Say yes here to build support for Texas Instruments ADC
 	  driver which is also a MFD client.
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index ebe93eba3ec8..5287bffd8a75 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -28,12 +28,20 @@
 #include <linux/iio/driver.h>
 
 #include <linux/mfd/ti_am335x_tscadc.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/kfifo_buf.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
 
 struct tiadc_device {
 	struct ti_tscadc_dev *mfd_tscadc;
 	int channels;
 	u8 channel_line[8];
 	u8 channel_step[8];
+	int buffer_en_ch_steps;
+	struct iio_trigger *trig;
+	u16 data[8];
 };
 
 static unsigned int tiadc_readl(struct tiadc_device *adc, unsigned int reg)
@@ -56,8 +64,14 @@ static u32 get_adc_step_mask(struct tiadc_device *adc_dev)
 	return step_en;
 }
 
-static void tiadc_step_config(struct tiadc_device *adc_dev)
+static u32 get_adc_step_bit(struct tiadc_device *adc_dev, int chan)
 {
+	return 1 << adc_dev->channel_step[chan];
+}
+
+static void tiadc_step_config(struct iio_dev *indio_dev)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
 	unsigned int stepconfig;
 	int i, steps;
 
@@ -72,7 +86,11 @@ static void tiadc_step_config(struct tiadc_device *adc_dev)
 	 */
 
 	steps = TOTAL_STEPS - adc_dev->channels;
-	stepconfig = STEPCONFIG_AVG_16 | STEPCONFIG_FIFO1;
+	if (iio_buffer_enabled(indio_dev))
+		stepconfig = STEPCONFIG_AVG_16 | STEPCONFIG_FIFO1
+					| STEPCONFIG_MODE_SWCNT;
+	else
+		stepconfig = STEPCONFIG_AVG_16 | STEPCONFIG_FIFO1;
 
 	for (i = 0; i < adc_dev->channels; i++) {
 		int chan;
@@ -85,9 +103,175 @@ static void tiadc_step_config(struct tiadc_device *adc_dev)
 		adc_dev->channel_step[i] = steps;
 		steps++;
 	}
+}
+
+static irqreturn_t tiadc_irq_h(int irq, void *private)
+{
+	struct iio_dev *indio_dev = private;
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	unsigned int status, config;
+	status = tiadc_readl(adc_dev, REG_IRQSTATUS);
+
+	/*
+	 * ADC and touchscreen share the IRQ line.
+	 * FIFO0 interrupts are used by TSC. Handle FIFO1 IRQs here only
+	 */
+	if (status & IRQENB_FIFO1OVRRUN) {
+		/* FIFO Overrun. Clear flag. Disable/Enable ADC to recover */
+		config = tiadc_readl(adc_dev, REG_CTRL);
+		config &= ~(CNTRLREG_TSCSSENB);
+		tiadc_writel(adc_dev, REG_CTRL, config);
+		tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN
+				| IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES);
+		tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB));
+		return IRQ_HANDLED;
+	} else if (status & IRQENB_FIFO1THRES) {
+		/* Disable irq and wake worker thread */
+		tiadc_writel(adc_dev, REG_IRQCLR, IRQENB_FIFO1THRES);
+		return IRQ_WAKE_THREAD;
+	}
+
+	return IRQ_NONE;
+}
+
+static irqreturn_t tiadc_worker_h(int irq, void *private)
+{
+	struct iio_dev *indio_dev = private;
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	int i, k, fifo1count, read;
+	u16 *data = adc_dev->data;
+
+	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
+	for (k = 0; k < fifo1count; k = k + i) {
+		for (i = 0; i < (indio_dev->scan_bytes)/2; i++) {
+			read = tiadc_readl(adc_dev, REG_FIFO1);
+			data[i] = read & FIFOREAD_DATA_MASK;
+		}
+		iio_push_to_buffers(indio_dev, (u8 *) data);
+	}
+
+	tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1THRES);
+	tiadc_writel(adc_dev, REG_IRQENABLE, IRQENB_FIFO1THRES);
+
+	return IRQ_HANDLED;
+}
+
+static int tiadc_buffer_preenable(struct iio_dev *indio_dev)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	int i, fifo1count, read;
+
+	tiadc_writel(adc_dev, REG_IRQCLR, (IRQENB_FIFO1THRES |
+				IRQENB_FIFO1OVRRUN |
+				IRQENB_FIFO1UNDRFLW));
+
+	/* Flush FIFO. Needed in corner cases in simultaneous tsc/adc use */
+	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
+	for (i = 0; i < fifo1count; i++)
+		read = tiadc_readl(adc_dev, REG_FIFO1);
+
+	return iio_sw_buffer_preenable(indio_dev);
+}
+
+static int tiadc_buffer_postenable(struct iio_dev *indio_dev)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	struct iio_buffer *buffer = indio_dev->buffer;
+	unsigned int enb = 0;
+	u8 bit;
+
+	tiadc_step_config(indio_dev);
+	for_each_set_bit(bit, buffer->scan_mask, adc_dev->channels)
+		enb |= (get_adc_step_bit(adc_dev, bit) << 1);
+	adc_dev->buffer_en_ch_steps = enb;
+
+	am335x_tsc_se_set(adc_dev->mfd_tscadc, enb);
+
+	tiadc_writel(adc_dev,  REG_IRQSTATUS, IRQENB_FIFO1THRES
+				| IRQENB_FIFO1OVRRUN | IRQENB_FIFO1UNDRFLW);
+	tiadc_writel(adc_dev,  REG_IRQENABLE, IRQENB_FIFO1THRES
+				| IRQENB_FIFO1OVRRUN);
+
+	return 0;
+}
+
+static int tiadc_buffer_predisable(struct iio_dev *indio_dev)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+	int fifo1count, i, read;
+
+	tiadc_writel(adc_dev, REG_IRQCLR, (IRQENB_FIFO1THRES |
+				IRQENB_FIFO1OVRRUN | IRQENB_FIFO1UNDRFLW));
+	am335x_tsc_se_clr(adc_dev->mfd_tscadc, adc_dev->buffer_en_ch_steps);
 
+	/* Flush FIFO of leftover data in the time it takes to disable adc */
+	fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
+	for (i = 0; i < fifo1count; i++)
+		read = tiadc_readl(adc_dev, REG_FIFO1);
+
+	return 0;
 }
 
+static int tiadc_buffer_postdisable(struct iio_dev *indio_dev)
+{
+	tiadc_step_config(indio_dev);
+
+	return 0;
+}
+
+static const struct iio_buffer_setup_ops tiadc_buffer_setup_ops = {
+	.preenable = &tiadc_buffer_preenable,
+	.postenable = &tiadc_buffer_postenable,
+	.predisable = &tiadc_buffer_predisable,
+	.postdisable = &tiadc_buffer_postdisable,
+};
+
+int tiadc_iio_buffered_hardware_setup(struct iio_dev *indio_dev,
+	irqreturn_t (*pollfunc_bh)(int irq, void *p),
+	irqreturn_t (*pollfunc_th)(int irq, void *p),
+	int irq,
+	unsigned long flags,
+	const struct iio_buffer_setup_ops *setup_ops)
+{
+	int ret;
+
+	indio_dev->buffer = iio_kfifo_allocate(indio_dev);
+	if (!indio_dev->buffer)
+		return -ENOMEM;
+
+	ret = request_threaded_irq(irq,	pollfunc_th, pollfunc_bh,
+				flags, indio_dev->name, indio_dev);
+	if (ret)
+		goto error_kfifo_free;
+
+	indio_dev->setup_ops = setup_ops;
+	indio_dev->modes |= INDIO_BUFFER_HARDWARE;
+
+	ret = iio_buffer_register(indio_dev,
+				  indio_dev->channels,
+				  indio_dev->num_channels);
+	if (ret)
+		goto error_free_irq;
+
+	return 0;
+
+error_free_irq:
+	free_irq(irq, indio_dev);
+error_kfifo_free:
+	iio_kfifo_free(indio_dev->buffer);
+	return ret;
+}
+
+static void tiadc_iio_buffered_hardware_remove(struct iio_dev *indio_dev)
+{
+	struct tiadc_device *adc_dev = iio_priv(indio_dev);
+
+	free_irq(adc_dev->mfd_tscadc->irq, indio_dev);
+	iio_kfifo_free(indio_dev->buffer);
+	iio_buffer_unregister(indio_dev);
+}
+
+
 static const char * const chan_name_ain[] = {
 	"AIN0",
 	"AIN1",
@@ -120,6 +304,7 @@ static int tiadc_channel_init(struct iio_dev *indio_dev, int channels)
 		chan->channel = adc_dev->channel_line[i];
 		chan->info_mask_separate = BIT(IIO_CHAN_INFO_RAW);
 		chan->datasheet_name = chan_name_ain[chan->channel];
+		chan->scan_index = i;
 		chan->scan_type.sign = 'u';
 		chan->scan_type.realbits = 12;
 		chan->scan_type.storagebits = 16;
@@ -147,6 +332,10 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 	u32 step_en;
 	unsigned long timeout = jiffies + usecs_to_jiffies
 				(IDLE_TIMEOUT * adc_dev->channels);
+
+	if (iio_buffer_enabled(indio_dev))
+		return -EBUSY;
+
 	step_en = get_adc_step_mask(adc_dev);
 	am335x_tsc_se_set(adc_dev->mfd_tscadc, step_en);
 
@@ -237,20 +426,33 @@ static int tiadc_probe(struct platform_device *pdev)
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &tiadc_info;
 
-	tiadc_step_config(adc_dev);
+	tiadc_step_config(indio_dev);
+	tiadc_writel(adc_dev, REG_FIFO1THR, FIFO1_THRESHOLD);
 
 	err = tiadc_channel_init(indio_dev, adc_dev->channels);
 	if (err < 0)
 		return err;
 
-	err = iio_device_register(indio_dev);
+	err = tiadc_iio_buffered_hardware_setup(indio_dev,
+		&tiadc_worker_h,
+		&tiadc_irq_h,
+		adc_dev->mfd_tscadc->irq,
+		IRQF_SHARED,
+		&tiadc_buffer_setup_ops);
+
 	if (err)
 		goto err_free_channels;
 
+	err = iio_device_register(indio_dev);
+	if (err)
+		goto err_buffer_unregister;
+
 	platform_set_drvdata(pdev, indio_dev);
 
 	return 0;
 
+err_buffer_unregister:
+	tiadc_iio_buffered_hardware_remove(indio_dev);
 err_free_channels:
 	tiadc_channels_remove(indio_dev);
 	return err;
@@ -263,6 +465,7 @@ static int tiadc_remove(struct platform_device *pdev)
 	u32 step_en;
 
 	iio_device_unregister(indio_dev);
+	tiadc_iio_buffered_hardware_remove(indio_dev);
 	tiadc_channels_remove(indio_dev);
 
 	step_en = get_adc_step_mask(adc_dev);
@@ -301,7 +504,7 @@ static int tiadc_resume(struct device *dev)
 	restore &= ~(CNTRLREG_POWERDOWN);
 	tiadc_writel(adc_dev, REG_CTRL, restore);
 
-	tiadc_step_config(adc_dev);
+	tiadc_step_config(indio_dev);
 
 	return 0;
 }
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index db1791bb997a..7d98562b3b51 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -46,16 +46,24 @@
 /* Step Enable */
 #define STEPENB_MASK		(0x1FFFF << 0)
 #define STEPENB(val)		((val) << 0)
+#define ENB(val)			(1 << (val))
+#define STPENB_STEPENB		STEPENB(0x1FFFF)
+#define STPENB_STEPENB_TC	STEPENB(0x1FFF)
 
 /* IRQ enable */
 #define IRQENB_HW_PEN		BIT(0)
 #define IRQENB_FIFO0THRES	BIT(2)
+#define IRQENB_FIFO0OVRRUN	BIT(3)
+#define IRQENB_FIFO0UNDRFLW	BIT(4)
 #define IRQENB_FIFO1THRES	BIT(5)
+#define IRQENB_FIFO1OVRRUN	BIT(6)
+#define IRQENB_FIFO1UNDRFLW	BIT(7)
 #define IRQENB_PENUP		BIT(9)
 
 /* Step Configuration */
 #define STEPCONFIG_MODE_MASK	(3 << 0)
 #define STEPCONFIG_MODE(val)	((val) << 0)
+#define STEPCONFIG_MODE_SWCNT	STEPCONFIG_MODE(1)
 #define STEPCONFIG_MODE_HWSYNC	STEPCONFIG_MODE(2)
 #define STEPCONFIG_AVG_MASK	(7 << 2)
 #define STEPCONFIG_AVG(val)	((val) << 2)
@@ -124,6 +132,7 @@
 #define	MAX_CLK_DIV		7
 #define TOTAL_STEPS		16
 #define TOTAL_CHANNELS		8
+#define FIFO1_THRESHOLD		19
 
 /*
 * ADC runs at 3MHz, and it takes
-- 
cgit 


From d2c3d072c4aded65f0632223cc0d3a8a2e577b3a Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Thu, 19 Sep 2013 13:59:00 +0100
Subject: iio: Add iio_push_buffers_with_timestamp() helper

Drivers using software buffers often store the timestamp in their data buffer
before calling iio_push_to_buffers() with that data buffer. Storing the
timestamp in the buffer usually involves some ugly pointer arithmetic. This
patch adds a new helper function called iio_push_buffers_with_timestamp() which
is similar to iio_push_to_buffers but takes an additional timestamp parameter.
The function will help to hide to uglyness in one central place instead of
exposing it in every driver. If timestamps are enabled for the IIO device
iio_push_buffers_with_timestamp() will store the timestamp as the last element
in buffer, before passing the buffer on to iio_push_buffers(). The buffer needs
large enough to hold the timestamp in this case. If timestamps are disabled
iio_push_buffers_with_timestamp() will behave just like iio_push_buffers().

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Cc: Oleksandr Kravchenko <o.v.kravchenko@globallogic.com>
Cc: Josh Wu <josh.wu@atmel.com>
Cc: Denis Ciocca <denis.ciocca@gmail.com>
Cc: Manuel Stahl <manuel.stahl@iis.fraunhofer.de>
Cc: Ge Gao <ggao@invensense.com>
Cc: Peter Meerwald <pmeerw@pmeerw.net>
Cc: Jacek Anaszewski <j.anaszewski@samsung.com>
Cc: Fabio Estevam <fabio.estevam@freescale.com>
Cc: Marek Vasut <marex@denx.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/buffer.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index e5507e999ed1..a1124bdc4cac 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -122,6 +122,31 @@ int iio_scan_mask_set(struct iio_dev *indio_dev,
  */
 int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data);
 
+/*
+ * iio_push_to_buffers_with_timestamp() - push data and timestamp to buffers
+ * @indio_dev:		iio_dev structure for device.
+ * @data:		sample data
+ * @timestamp:		timestamp for the sample data
+ *
+ * Pushes data to the IIO device's buffers. If timestamps are enabled for the
+ * device the function will store the supplied timestamp as the last element in
+ * the sample data buffer before pushing it to the device buffers. The sample
+ * data buffer needs to be large enough to hold the additional timestamp
+ * (usually the buffer should be indio->scan_bytes bytes large).
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ */
+static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev,
+	void *data, int64_t timestamp)
+{
+	if (indio_dev->scan_timestamp) {
+		size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1;
+		((int64_t *)data)[ts_offset] = timestamp;
+	}
+
+	return iio_push_to_buffers(indio_dev, data);
+}
+
 int iio_update_demux(struct iio_dev *indio_dev);
 
 /**
-- 
cgit 


From 6d3b334d677cd0c18cf99ababe1441b62dd08020 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:16 -0700
Subject: ping.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ping.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ping.h b/include/net/ping.h
index 5db0224b73ac..3f67704f3747 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -103,8 +103,8 @@ void ping_seq_stop(struct seq_file *seq, void *v);
 int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo);
 void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo);
 
-extern int __init ping_proc_init(void);
-extern void ping_proc_exit(void);
+int __init ping_proc_init(void);
+void ping_proc_exit(void);
 #endif
 
 void __init ping_init(void);
-- 
cgit 


From f307c6365648e919d7ac733f0b3a7e9ee3e31eb2 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:17 -0700
Subject: protocol.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/protocol.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 047c0476c0a0..fbf7676c9a02 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -96,20 +96,20 @@ extern const struct net_offload __rcu *inet6_offloads[MAX_INET_PROTOS];
 extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
 #endif
 
-extern int	inet_add_protocol(const struct net_protocol *prot, unsigned char num);
-extern int	inet_del_protocol(const struct net_protocol *prot, unsigned char num);
-extern int	inet_add_offload(const struct net_offload *prot, unsigned char num);
-extern int	inet_del_offload(const struct net_offload *prot, unsigned char num);
-extern void	inet_register_protosw(struct inet_protosw *p);
-extern void	inet_unregister_protosw(struct inet_protosw *p);
+int inet_add_protocol(const struct net_protocol *prot, unsigned char num);
+int inet_del_protocol(const struct net_protocol *prot, unsigned char num);
+int inet_add_offload(const struct net_offload *prot, unsigned char num);
+int inet_del_offload(const struct net_offload *prot, unsigned char num);
+void inet_register_protosw(struct inet_protosw *p);
+void inet_unregister_protosw(struct inet_protosw *p);
 
 #if IS_ENABLED(CONFIG_IPV6)
-extern int	inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
-extern int	inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
-extern int	inet6_register_protosw(struct inet_protosw *p);
-extern void	inet6_unregister_protosw(struct inet_protosw *p);
+int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
+int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
+int inet6_register_protosw(struct inet_protosw *p);
+void inet6_unregister_protosw(struct inet_protosw *p);
 #endif
-extern int	inet6_add_offload(const struct net_offload *prot, unsigned char num);
-extern int	inet6_del_offload(const struct net_offload *prot, unsigned char num);
+int inet6_add_offload(const struct net_offload *prot, unsigned char num);
+int inet6_del_offload(const struct net_offload *prot, unsigned char num);
 
 #endif	/* _PROTOCOL_H */
-- 
cgit 


From c64b5c4b916f47ba854a560d6c56d87790e344ca Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:18 -0700
Subject: psnap.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/psnap.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/psnap.h b/include/net/psnap.h
index fe456c295b04..78db4cc1306a 100644
--- a/include/net/psnap.h
+++ b/include/net/psnap.h
@@ -1,11 +1,11 @@
 #ifndef _NET_PSNAP_H
 #define _NET_PSNAP_H
 
-extern struct datalink_proto *
+struct datalink_proto *
 register_snap_client(const unsigned char *desc,
 		     int (*rcvfunc)(struct sk_buff *, struct net_device *,
 				    struct packet_type *,
 				    struct net_device *orig_dev));
-extern void unregister_snap_client(struct datalink_proto *proto);
+void unregister_snap_client(struct datalink_proto *proto);
 
 #endif
-- 
cgit 


From 0ad6ad946167a706e22eb7bad9e77735bc577074 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:19 -0700
Subject: raw/rawv6.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/raw.h   | 6 +++---
 include/net/rawv6.h | 3 +--
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/raw.h b/include/net/raw.h
index 42ce6fe7a2d5..6a40c6562dd2 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -26,7 +26,7 @@ extern struct proto raw_prot;
 void raw_icmp_error(struct sk_buff *, int, u32);
 int raw_local_deliver(struct sk_buff *, int);
 
-extern int 	raw_rcv(struct sock *, struct sk_buff *);
+int raw_rcv(struct sock *, struct sk_buff *);
 
 #define RAW_HTABLE_SIZE	MAX_INET_PROTOS
 
@@ -36,8 +36,8 @@ struct raw_hashinfo {
 };
 
 #ifdef CONFIG_PROC_FS
-extern int  raw_proc_init(void);
-extern void raw_proc_exit(void);
+int raw_proc_init(void);
+void raw_proc_exit(void);
 
 struct raw_iter_state {
 	struct seq_net_private p;
diff --git a/include/net/rawv6.h b/include/net/rawv6.h
index e7ea660e4db6..87783dea0791 100644
--- a/include/net/rawv6.h
+++ b/include/net/rawv6.h
@@ -7,8 +7,7 @@ void raw6_icmp_error(struct sk_buff *, int nexthdr,
 		u8 type, u8 code, int inner_offset, __be32);
 bool raw6_local_deliver(struct sk_buff *, int);
 
-extern int			rawv6_rcv(struct sock *sk,
-					  struct sk_buff *skb);
+int rawv6_rcv(struct sock *sk, struct sk_buff *skb);
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 int rawv6_mh_filter_register(int (*filter)(struct sock *sock,
-- 
cgit 


From c0f4502a8700832bb3a917fdcfe080f5ccf1c617 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:20 -0700
Subject: request_sock.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/request_sock.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 59795e42c8b6..65c3e5164a5c 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -43,7 +43,7 @@ struct request_sock_ops {
 					   struct request_sock *req);
 };
 
-extern int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
+int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
 
 /* struct request_sock - mini sock to represent a connection request
  */
@@ -162,13 +162,13 @@ struct request_sock_queue {
 					     */
 };
 
-extern int reqsk_queue_alloc(struct request_sock_queue *queue,
-			     unsigned int nr_table_entries);
+int reqsk_queue_alloc(struct request_sock_queue *queue,
+		      unsigned int nr_table_entries);
 
-extern void __reqsk_queue_destroy(struct request_sock_queue *queue);
-extern void reqsk_queue_destroy(struct request_sock_queue *queue);
-extern void reqsk_fastopen_remove(struct sock *sk,
-				  struct request_sock *req, bool reset);
+void __reqsk_queue_destroy(struct request_sock_queue *queue);
+void reqsk_queue_destroy(struct request_sock_queue *queue);
+void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
+			   bool reset);
 
 static inline struct request_sock *
 	reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
-- 
cgit 


From 54df3b961db19e3eb6ccbac0ca469c56b1b58689 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:21 -0700
Subject: rose.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rose.h | 114 ++++++++++++++++++++++++++++-------------------------
 1 file changed, 60 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/include/net/rose.h b/include/net/rose.h
index 555dd198aab7..50811fe2c585 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -160,38 +160,42 @@ extern int  sysctl_rose_routing_control;
 extern int  sysctl_rose_link_fail_timeout;
 extern int  sysctl_rose_maximum_vcs;
 extern int  sysctl_rose_window_size;
-extern int  rosecmp(rose_address *, rose_address *);
-extern int  rosecmpm(rose_address *, rose_address *, unsigned short);
-extern char *rose2asc(char *buf, const rose_address *);
-extern struct sock *rose_find_socket(unsigned int, struct rose_neigh *);
-extern void rose_kill_by_neigh(struct rose_neigh *);
-extern unsigned int rose_new_lci(struct rose_neigh *);
-extern int  rose_rx_call_request(struct sk_buff *, struct net_device *, struct rose_neigh *, unsigned int);
-extern void rose_destroy_socket(struct sock *);
+
+int rosecmp(rose_address *, rose_address *);
+int rosecmpm(rose_address *, rose_address *, unsigned short);
+char *rose2asc(char *buf, const rose_address *);
+struct sock *rose_find_socket(unsigned int, struct rose_neigh *);
+void rose_kill_by_neigh(struct rose_neigh *);
+unsigned int rose_new_lci(struct rose_neigh *);
+int rose_rx_call_request(struct sk_buff *, struct net_device *,
+			 struct rose_neigh *, unsigned int);
+void rose_destroy_socket(struct sock *);
 
 /* rose_dev.c */
-extern void  rose_setup(struct net_device *);
+void rose_setup(struct net_device *);
 
 /* rose_in.c */
-extern int  rose_process_rx_frame(struct sock *, struct sk_buff *);
+int rose_process_rx_frame(struct sock *, struct sk_buff *);
 
 /* rose_link.c */
-extern void rose_start_ftimer(struct rose_neigh *);
-extern void rose_stop_ftimer(struct rose_neigh *);
-extern void rose_stop_t0timer(struct rose_neigh *);
-extern int  rose_ftimer_running(struct rose_neigh *);
-extern void rose_link_rx_restart(struct sk_buff *, struct rose_neigh *, unsigned short);
-extern void rose_transmit_clear_request(struct rose_neigh *, unsigned int, unsigned char, unsigned char);
-extern void rose_transmit_link(struct sk_buff *, struct rose_neigh *);
+void rose_start_ftimer(struct rose_neigh *);
+void rose_stop_ftimer(struct rose_neigh *);
+void rose_stop_t0timer(struct rose_neigh *);
+int rose_ftimer_running(struct rose_neigh *);
+void rose_link_rx_restart(struct sk_buff *, struct rose_neigh *,
+			  unsigned short);
+void rose_transmit_clear_request(struct rose_neigh *, unsigned int,
+				 unsigned char, unsigned char);
+void rose_transmit_link(struct sk_buff *, struct rose_neigh *);
 
 /* rose_loopback.c */
-extern void rose_loopback_init(void);
-extern void rose_loopback_clear(void);
-extern int  rose_loopback_queue(struct sk_buff *, struct rose_neigh *);
+void rose_loopback_init(void);
+void rose_loopback_clear(void);
+int rose_loopback_queue(struct sk_buff *, struct rose_neigh *);
 
 /* rose_out.c */
-extern void rose_kick(struct sock *);
-extern void rose_enquiry_response(struct sock *);
+void rose_kick(struct sock *);
+void rose_enquiry_response(struct sock *);
 
 /* rose_route.c */
 extern struct rose_neigh *rose_loopback_neigh;
@@ -199,43 +203,45 @@ extern const struct file_operations rose_neigh_fops;
 extern const struct file_operations rose_nodes_fops;
 extern const struct file_operations rose_routes_fops;
 
-extern void rose_add_loopback_neigh(void);
-extern int __must_check rose_add_loopback_node(rose_address *);
-extern void rose_del_loopback_node(rose_address *);
-extern void rose_rt_device_down(struct net_device *);
-extern void rose_link_device_down(struct net_device *);
-extern struct net_device *rose_dev_first(void);
-extern struct net_device *rose_dev_get(rose_address *);
-extern struct rose_route *rose_route_free_lci(unsigned int, struct rose_neigh *);
-extern struct rose_neigh *rose_get_neigh(rose_address *, unsigned char *, unsigned char *, int);
-extern int  rose_rt_ioctl(unsigned int, void __user *);
-extern void rose_link_failed(ax25_cb *, int);
-extern int  rose_route_frame(struct sk_buff *, ax25_cb *);
-extern void rose_rt_free(void);
+void rose_add_loopback_neigh(void);
+int __must_check rose_add_loopback_node(rose_address *);
+void rose_del_loopback_node(rose_address *);
+void rose_rt_device_down(struct net_device *);
+void rose_link_device_down(struct net_device *);
+struct net_device *rose_dev_first(void);
+struct net_device *rose_dev_get(rose_address *);
+struct rose_route *rose_route_free_lci(unsigned int, struct rose_neigh *);
+struct rose_neigh *rose_get_neigh(rose_address *, unsigned char *,
+				  unsigned char *, int);
+int rose_rt_ioctl(unsigned int, void __user *);
+void rose_link_failed(ax25_cb *, int);
+int rose_route_frame(struct sk_buff *, ax25_cb *);
+void rose_rt_free(void);
 
 /* rose_subr.c */
-extern void rose_clear_queues(struct sock *);
-extern void rose_frames_acked(struct sock *, unsigned short);
-extern void rose_requeue_frames(struct sock *);
-extern int  rose_validate_nr(struct sock *, unsigned short);
-extern void rose_write_internal(struct sock *, int);
-extern int  rose_decode(struct sk_buff *, int *, int *, int *, int *, int *);
-extern int  rose_parse_facilities(unsigned char *, unsigned int, struct rose_facilities_struct *);
-extern void rose_disconnect(struct sock *, int, int, int);
+void rose_clear_queues(struct sock *);
+void rose_frames_acked(struct sock *, unsigned short);
+void rose_requeue_frames(struct sock *);
+int rose_validate_nr(struct sock *, unsigned short);
+void rose_write_internal(struct sock *, int);
+int rose_decode(struct sk_buff *, int *, int *, int *, int *, int *);
+int rose_parse_facilities(unsigned char *, unsigned int,
+			  struct rose_facilities_struct *);
+void rose_disconnect(struct sock *, int, int, int);
 
 /* rose_timer.c */
-extern void rose_start_heartbeat(struct sock *);
-extern void rose_start_t1timer(struct sock *);
-extern void rose_start_t2timer(struct sock *);
-extern void rose_start_t3timer(struct sock *);
-extern void rose_start_hbtimer(struct sock *);
-extern void rose_start_idletimer(struct sock *);
-extern void rose_stop_heartbeat(struct sock *);
-extern void rose_stop_timer(struct sock *);
-extern void rose_stop_idletimer(struct sock *);
+void rose_start_heartbeat(struct sock *);
+void rose_start_t1timer(struct sock *);
+void rose_start_t2timer(struct sock *);
+void rose_start_t3timer(struct sock *);
+void rose_start_hbtimer(struct sock *);
+void rose_start_idletimer(struct sock *);
+void rose_stop_heartbeat(struct sock *);
+void rose_stop_timer(struct sock *);
+void rose_stop_idletimer(struct sock *);
 
 /* sysctl_net_rose.c */
-extern void rose_register_sysctl(void);
-extern void rose_unregister_sysctl(void);
+void rose_register_sysctl(void);
+void rose_unregister_sysctl(void);
 
 #endif
-- 
cgit 


From 2702c4bb89b2a9bfe49f3db77a1bac88d5c6404c Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:22 -0700
Subject: route.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 53 ++++++++++++++++++++++++++++-------------------------
 1 file changed, 28 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index afdeeb5bec25..6f572ca66d25 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -108,13 +108,15 @@ struct rt_cache_stat {
 extern struct ip_rt_acct __percpu *ip_rt_acct;
 
 struct in_device;
-extern int		ip_rt_init(void);
-extern void		rt_cache_flush(struct net *net);
-extern void		rt_flush_dev(struct net_device *dev);
-extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
-extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
-					   struct sock *sk);
-extern struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig);
+
+int ip_rt_init(void);
+void rt_cache_flush(struct net *net);
+void rt_flush_dev(struct net_device *dev);
+struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
+struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
+				    struct sock *sk);
+struct dst_entry *ipv4_blackhole_route(struct net *net,
+				       struct dst_entry *dst_orig);
 
 static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp)
 {
@@ -162,8 +164,8 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 	return ip_route_output_key(net, fl4);
 }
 
-extern int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-				u8 tos, struct net_device *devin);
+int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
+			 u8 tos, struct net_device *devin);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin)
@@ -179,24 +181,25 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 	return err;
 }
 
-extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
-			     int oif, u32 mark, u8 protocol, int flow_flags);
-extern void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
-extern void ipv4_redirect(struct sk_buff *skb, struct net *net,
-			  int oif, u32 mark, u8 protocol, int flow_flags);
-extern void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
-extern void ip_rt_send_redirect(struct sk_buff *skb);
-
-extern unsigned int		inet_addr_type(struct net *net, __be32 addr);
-extern unsigned int		inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr);
-extern void		ip_rt_multicast_event(struct in_device *);
-extern int		ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
-extern void		ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
-extern int		ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
+void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif,
+		      u32 mark, u8 protocol, int flow_flags);
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
+void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+		   u8 protocol, int flow_flags);
+void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk);
+void ip_rt_send_redirect(struct sk_buff *skb);
+
+unsigned int inet_addr_type(struct net *net, __be32 addr);
+unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
+				__be32 addr);
+void ip_rt_multicast_event(struct in_device *);
+int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
+void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
+int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb);
 
 struct in_ifaddr;
-extern void fib_add_ifaddr(struct in_ifaddr *);
-extern void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
+void fib_add_ifaddr(struct in_ifaddr *);
+void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
 
 static inline void ip_rt_put(struct rtable *rt)
 {
-- 
cgit 


From efb48ccfcda4dbb9fce39c5c8df19644a08121c0 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:23 -0700
Subject: rtnetlink.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h | 40 +++++++++++++++++++---------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 702664833a53..bb13a182fba6 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -8,14 +8,12 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *);
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *);
 
-extern int	__rtnl_register(int protocol, int msgtype,
-				rtnl_doit_func, rtnl_dumpit_func,
-				rtnl_calcit_func);
-extern void	rtnl_register(int protocol, int msgtype,
-			      rtnl_doit_func, rtnl_dumpit_func,
-			      rtnl_calcit_func);
-extern int	rtnl_unregister(int protocol, int msgtype);
-extern void	rtnl_unregister_all(int protocol);
+int __rtnl_register(int protocol, int msgtype,
+		    rtnl_doit_func, rtnl_dumpit_func, rtnl_calcit_func);
+void rtnl_register(int protocol, int msgtype,
+		   rtnl_doit_func, rtnl_dumpit_func, rtnl_calcit_func);
+int rtnl_unregister(int protocol, int msgtype);
+void rtnl_unregister_all(int protocol);
 
 static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
 {
@@ -83,11 +81,11 @@ struct rtnl_link_ops {
 	unsigned int		(*get_num_rx_queues)(void);
 };
 
-extern int	__rtnl_link_register(struct rtnl_link_ops *ops);
-extern void	__rtnl_link_unregister(struct rtnl_link_ops *ops);
+int __rtnl_link_register(struct rtnl_link_ops *ops);
+void __rtnl_link_unregister(struct rtnl_link_ops *ops);
 
-extern int	rtnl_link_register(struct rtnl_link_ops *ops);
-extern void	rtnl_link_unregister(struct rtnl_link_ops *ops);
+int rtnl_link_register(struct rtnl_link_ops *ops);
+void rtnl_link_unregister(struct rtnl_link_ops *ops);
 
 /**
  * 	struct rtnl_af_ops - rtnetlink address family operations
@@ -117,18 +115,18 @@ struct rtnl_af_ops {
 					       const struct nlattr *attr);
 };
 
-extern int	__rtnl_af_register(struct rtnl_af_ops *ops);
-extern void	__rtnl_af_unregister(struct rtnl_af_ops *ops);
+int __rtnl_af_register(struct rtnl_af_ops *ops);
+void __rtnl_af_unregister(struct rtnl_af_ops *ops);
 
-extern int	rtnl_af_register(struct rtnl_af_ops *ops);
-extern void	rtnl_af_unregister(struct rtnl_af_ops *ops);
+int rtnl_af_register(struct rtnl_af_ops *ops);
+void rtnl_af_unregister(struct rtnl_af_ops *ops);
 
+struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]);
+struct net_device *rtnl_create_link(struct net *net, char *ifname,
+				    const struct rtnl_link_ops *ops,
+				    struct nlattr *tb[]);
+int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm);
 
-extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]);
-extern struct net_device *rtnl_create_link(struct net *net,
-	char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]);
-extern int rtnl_configure_link(struct net_device *dev,
-			       const struct ifinfomsg *ifm);
 extern const struct nla_policy ifla_policy[IFLA_MAX+1];
 
 #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind)
-- 
cgit 


From 8153ff5c5f3183dec007469d7e039b4d01ea6d82 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:24 -0700
Subject: scm.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/scm.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/scm.h b/include/net/scm.h
index 8de2d37d2077..262532d111f5 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -33,11 +33,11 @@ struct scm_cookie {
 #endif
 };
 
-extern void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm);
-extern void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm);
-extern int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm);
-extern void __scm_destroy(struct scm_cookie *scm);
-extern struct scm_fp_list * scm_fp_dup(struct scm_fp_list *fpl);
+void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm);
+void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm);
+int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm);
+void __scm_destroy(struct scm_cookie *scm);
+struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl);
 
 #ifdef CONFIG_SECURITY_NETWORK
 static __inline__ void unix_get_peersec_dgram(struct socket *sock, struct scm_cookie *scm)
-- 
cgit 


From a4ea1fef97e31fbdac77e5d1e183ea345fbb2cd6 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:25 -0700
Subject: secure_seq.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/secure_seq.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 6ca975bebd37..52c1a906f288 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,19 +3,19 @@
 
 #include <linux/types.h>
 
-extern void net_secret_init(void);
-extern __u32 secure_ip_id(__be32 daddr);
-extern __u32 secure_ipv6_id(const __be32 daddr[4]);
-extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
-extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
-				      __be16 dport);
-extern __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
-					__be16 sport, __be16 dport);
-extern __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
-					  __be16 sport, __be16 dport);
-extern u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
-				       __be16 sport, __be16 dport);
-extern u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
-					 __be16 sport, __be16 dport);
+void net_secret_init(void);
+__u32 secure_ip_id(__be32 daddr);
+__u32 secure_ipv6_id(const __be32 daddr[4]);
+u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
+u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+			       __be16 dport);
+__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+				 __be16 sport, __be16 dport);
+__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
+				   __be16 sport, __be16 dport);
+u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
+				__be16 sport, __be16 dport);
+u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
+				  __be16 sport, __be16 dport);
 
 #endif /* _NET_SECURE_SEQ */
-- 
cgit 


From 69336bd2d3ddce315dc57be894e4b57a91036a14 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:26 -0700
Subject: sock.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 223 ++++++++++++++++++++++++-----------------------------
 1 file changed, 99 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 6ba2e7b0e2b1..4625d2eff461 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -746,7 +746,7 @@ static inline int sk_stream_wspace(const struct sock *sk)
 	return sk->sk_sndbuf - sk->sk_wmem_queued;
 }
 
-extern void sk_stream_write_space(struct sock *sk);
+void sk_stream_write_space(struct sock *sk);
 
 /* OOB backlog add */
 static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
@@ -788,7 +788,7 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	return 0;
 }
 
-extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
@@ -853,15 +853,15 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
 		__rc;							\
 	})
 
-extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
-extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
-extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
-extern int sk_stream_error(struct sock *sk, int flags, int err);
-extern void sk_stream_kill_queues(struct sock *sk);
-extern void sk_set_memalloc(struct sock *sk);
-extern void sk_clear_memalloc(struct sock *sk);
+int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
+int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
+void sk_stream_wait_close(struct sock *sk, long timeo_p);
+int sk_stream_error(struct sock *sk, int flags, int err);
+void sk_stream_kill_queues(struct sock *sk);
+void sk_set_memalloc(struct sock *sk);
+void sk_clear_memalloc(struct sock *sk);
 
-extern int sk_wait_data(struct sock *sk, long *timeo);
+int sk_wait_data(struct sock *sk, long *timeo);
 
 struct request_sock_ops;
 struct timewait_sock_ops;
@@ -1031,8 +1031,8 @@ struct cg_proto {
 	struct mem_cgroup	*memcg;
 };
 
-extern int proto_register(struct proto *prot, int alloc_slab);
-extern void proto_unregister(struct proto *prot);
+int proto_register(struct proto *prot, int alloc_slab);
+void proto_unregister(struct proto *prot);
 
 static inline bool memcg_proto_active(struct cg_proto *cg_proto)
 {
@@ -1287,8 +1287,8 @@ proto_memory_pressure(struct proto *prot)
 
 #ifdef CONFIG_PROC_FS
 /* Called with local bh disabled */
-extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
-extern int sock_prot_inuse_get(struct net *net, struct proto *proto);
+void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
+int sock_prot_inuse_get(struct net *net, struct proto *proto);
 #else
 static inline void sock_prot_inuse_add(struct net *net, struct proto *prot,
 		int inc)
@@ -1364,8 +1364,8 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
 /*
  * Functions for memory accounting
  */
-extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
-extern void __sk_mem_reclaim(struct sock *sk);
+int __sk_mem_schedule(struct sock *sk, int size, int kind);
+void __sk_mem_reclaim(struct sock *sk);
 
 #define SK_MEM_QUANTUM ((int)PAGE_SIZE)
 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
@@ -1473,14 +1473,14 @@ do {									\
 	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
 } while (0)
 
-extern void lock_sock_nested(struct sock *sk, int subclass);
+void lock_sock_nested(struct sock *sk, int subclass);
 
 static inline void lock_sock(struct sock *sk)
 {
 	lock_sock_nested(sk, 0);
 }
 
-extern void release_sock(struct sock *sk);
+void release_sock(struct sock *sk);
 
 /* BH context may only use the following locking interface. */
 #define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
@@ -1489,7 +1489,7 @@ extern void release_sock(struct sock *sk);
 				SINGLE_DEPTH_NESTING)
 #define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))
 
-extern bool lock_sock_fast(struct sock *sk);
+bool lock_sock_fast(struct sock *sk);
 /**
  * unlock_sock_fast - complement of lock_sock_fast
  * @sk: socket
@@ -1507,108 +1507,84 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
 }
 
 
-extern struct sock		*sk_alloc(struct net *net, int family,
-					  gfp_t priority,
-					  struct proto *prot);
-extern void			sk_free(struct sock *sk);
-extern void			sk_release_kernel(struct sock *sk);
-extern struct sock		*sk_clone_lock(const struct sock *sk,
-					       const gfp_t priority);
-
-extern struct sk_buff		*sock_wmalloc(struct sock *sk,
-					      unsigned long size, int force,
-					      gfp_t priority);
-extern struct sk_buff		*sock_rmalloc(struct sock *sk,
-					      unsigned long size, int force,
-					      gfp_t priority);
-extern void			sock_wfree(struct sk_buff *skb);
-extern void			skb_orphan_partial(struct sk_buff *skb);
-extern void			sock_rfree(struct sk_buff *skb);
-extern void			sock_edemux(struct sk_buff *skb);
-
-extern int			sock_setsockopt(struct socket *sock, int level,
-						int op, char __user *optval,
-						unsigned int optlen);
-
-extern int			sock_getsockopt(struct socket *sock, int level,
-						int op, char __user *optval,
-						int __user *optlen);
-extern struct sk_buff		*sock_alloc_send_skb(struct sock *sk,
-						     unsigned long size,
-						     int noblock,
-						     int *errcode);
-extern struct sk_buff		*sock_alloc_send_pskb(struct sock *sk,
-						      unsigned long header_len,
-						      unsigned long data_len,
-						      int noblock,
-						      int *errcode,
-						      int max_page_order);
-extern void *sock_kmalloc(struct sock *sk, int size,
-			  gfp_t priority);
-extern void sock_kfree_s(struct sock *sk, void *mem, int size);
-extern void sk_send_sigurg(struct sock *sk);
+struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
+		      struct proto *prot);
+void sk_free(struct sock *sk);
+void sk_release_kernel(struct sock *sk);
+struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
+
+struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
+			     gfp_t priority);
+struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
+			     gfp_t priority);
+void sock_wfree(struct sk_buff *skb);
+void skb_orphan_partial(struct sk_buff *skb);
+void sock_rfree(struct sk_buff *skb);
+void sock_edemux(struct sk_buff *skb);
+
+int sock_setsockopt(struct socket *sock, int level, int op,
+		    char __user *optval, unsigned int optlen);
+
+int sock_getsockopt(struct socket *sock, int level, int op,
+		    char __user *optval, int __user *optlen);
+struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
+				    int noblock, int *errcode);
+struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
+				     unsigned long data_len, int noblock,
+				     int *errcode, int max_page_order);
+void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
+void sock_kfree_s(struct sock *sk, void *mem, int size);
+void sk_send_sigurg(struct sock *sk);
 
 /*
  * Functions to fill in entries in struct proto_ops when a protocol
  * does not implement a particular function.
  */
-extern int                      sock_no_bind(struct socket *,
-					     struct sockaddr *, int);
-extern int                      sock_no_connect(struct socket *,
-						struct sockaddr *, int, int);
-extern int                      sock_no_socketpair(struct socket *,
-						   struct socket *);
-extern int                      sock_no_accept(struct socket *,
-					       struct socket *, int);
-extern int                      sock_no_getname(struct socket *,
-						struct sockaddr *, int *, int);
-extern unsigned int             sock_no_poll(struct file *, struct socket *,
-					     struct poll_table_struct *);
-extern int                      sock_no_ioctl(struct socket *, unsigned int,
-					      unsigned long);
-extern int			sock_no_listen(struct socket *, int);
-extern int                      sock_no_shutdown(struct socket *, int);
-extern int			sock_no_getsockopt(struct socket *, int , int,
-						   char __user *, int __user *);
-extern int			sock_no_setsockopt(struct socket *, int, int,
-						   char __user *, unsigned int);
-extern int                      sock_no_sendmsg(struct kiocb *, struct socket *,
-						struct msghdr *, size_t);
-extern int                      sock_no_recvmsg(struct kiocb *, struct socket *,
-						struct msghdr *, size_t, int);
-extern int			sock_no_mmap(struct file *file,
-					     struct socket *sock,
-					     struct vm_area_struct *vma);
-extern ssize_t			sock_no_sendpage(struct socket *sock,
-						struct page *page,
-						int offset, size_t size,
-						int flags);
+int sock_no_bind(struct socket *, struct sockaddr *, int);
+int sock_no_connect(struct socket *, struct sockaddr *, int, int);
+int sock_no_socketpair(struct socket *, struct socket *);
+int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
+unsigned int sock_no_poll(struct file *, struct socket *,
+			  struct poll_table_struct *);
+int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
+int sock_no_listen(struct socket *, int);
+int sock_no_shutdown(struct socket *, int);
+int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *);
+int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int);
+int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t);
+int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t,
+		    int);
+int sock_no_mmap(struct file *file, struct socket *sock,
+		 struct vm_area_struct *vma);
+ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset,
+			 size_t size, int flags);
 
 /*
  * Functions to fill in entries in struct proto_ops when a protocol
  * uses the inet style.
  */
-extern int sock_common_getsockopt(struct socket *sock, int level, int optname,
+int sock_common_getsockopt(struct socket *sock, int level, int optname,
 				  char __user *optval, int __user *optlen);
-extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
+int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
 			       struct msghdr *msg, size_t size, int flags);
-extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
+int sock_common_setsockopt(struct socket *sock, int level, int optname,
 				  char __user *optval, unsigned int optlen);
-extern int compat_sock_common_getsockopt(struct socket *sock, int level,
+int compat_sock_common_getsockopt(struct socket *sock, int level,
 		int optname, char __user *optval, int __user *optlen);
-extern int compat_sock_common_setsockopt(struct socket *sock, int level,
+int compat_sock_common_setsockopt(struct socket *sock, int level,
 		int optname, char __user *optval, unsigned int optlen);
 
-extern void sk_common_release(struct sock *sk);
+void sk_common_release(struct sock *sk);
 
 /*
  *	Default socket callbacks and setup code
  */
 
 /* Initialise core socket variables */
-extern void sock_init_data(struct socket *sock, struct sock *sk);
+void sock_init_data(struct socket *sock, struct sock *sk);
 
-extern void sk_filter_release_rcu(struct rcu_head *rcu);
+void sk_filter_release_rcu(struct rcu_head *rcu);
 
 /**
  *	sk_filter_release - release a socket filter
@@ -1669,8 +1645,7 @@ static inline void sock_put(struct sock *sk)
 		sk_free(sk);
 }
 
-extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
-			  const int nested);
+int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
 {
@@ -1724,8 +1699,8 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
-extern kuid_t sock_i_uid(struct sock *sk);
-extern unsigned long sock_i_ino(struct sock *sk);
+kuid_t sock_i_uid(struct sock *sk);
+unsigned long sock_i_ino(struct sock *sk);
 
 static inline struct dst_entry *
 __sk_dst_get(struct sock *sk)
@@ -1747,7 +1722,7 @@ sk_dst_get(struct sock *sk)
 	return dst;
 }
 
-extern void sk_reset_txq(struct sock *sk);
+void sk_reset_txq(struct sock *sk);
 
 static inline void dst_negative_advice(struct sock *sk)
 {
@@ -1800,16 +1775,16 @@ sk_dst_reset(struct sock *sk)
 	spin_unlock(&sk->sk_dst_lock);
 }
 
-extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
+struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
 
-extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
+struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
 
 static inline bool sk_can_gso(const struct sock *sk)
 {
 	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
 }
 
-extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
+void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
 
 static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 {
@@ -2022,14 +1997,14 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-extern void sk_reset_timer(struct sock *sk, struct timer_list *timer,
-			   unsigned long expires);
+void sk_reset_timer(struct sock *sk, struct timer_list *timer,
+		    unsigned long expires);
 
-extern void sk_stop_timer(struct sock *sk, struct timer_list *timer);
+void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
-extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
-extern int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
+int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
 
 /*
  *	Recover an error report and clear atomically
@@ -2097,7 +2072,7 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
 	return &sk->sk_frag;
 }
 
-extern bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
+bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
 
 /*
  *	Default write policy as shown to user space via poll/select/SIGIO
@@ -2135,10 +2110,10 @@ static inline int sock_intr_errno(long timeo)
 	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
 }
 
-extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
-	struct sk_buff *skb);
-extern void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
-	struct sk_buff *skb);
+void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
+			   struct sk_buff *skb);
+void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
+			     struct sk_buff *skb);
 
 static inline void
 sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
@@ -2171,8 +2146,8 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 		__sock_recv_wifi_status(msg, sk, skb);
 }
 
-extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
-				     struct sk_buff *skb);
+void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
+			      struct sk_buff *skb);
 
 static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 					  struct sk_buff *skb)
@@ -2197,7 +2172,7 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
  *
  * Currently only depends on SOCK_TIMESTAMPING* flags.
  */
-extern void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
+void sock_tx_timestamp(struct sock *sk, __u8 *tx_flags);
 
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
@@ -2261,11 +2236,11 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb)
 	return NULL;
 }
 
-extern void sock_enable_timestamp(struct sock *sk, int flag);
-extern int sock_get_timestamp(struct sock *, struct timeval __user *);
-extern int sock_get_timestampns(struct sock *, struct timespec __user *);
-extern int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
-			      int level, int type);
+void sock_enable_timestamp(struct sock *sk, int flag);
+int sock_get_timestamp(struct sock *, struct timeval __user *);
+int sock_get_timestampns(struct sock *, struct timespec __user *);
+int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
+		       int type);
 
 /*
  *	Enable debug/info messages
-- 
cgit 


From f6982299f273b827c8fe80c4c34e9fcdf95af20d Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 22 Sep 2013 10:32:27 -0700
Subject: stp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/stp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/stp.h b/include/net/stp.h
index ad447f105417..3af174d70d9e 100644
--- a/include/net/stp.h
+++ b/include/net/stp.h
@@ -8,7 +8,7 @@ struct stp_proto {
 	void		*data;
 };
 
-extern int stp_proto_register(const struct stp_proto *proto);
-extern void stp_proto_unregister(const struct stp_proto *proto);
+int stp_proto_register(const struct stp_proto *proto);
+void stp_proto_unregister(const struct stp_proto *proto);
 
 #endif /* _NET_STP_H */
-- 
cgit 


From 3f2b9c9cdf389e303b2273679af08aab5f153517 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Tue, 17 Sep 2013 05:48:51 +0930
Subject: module: remove rmmod --wait option.

The option to wait for a module reference count to reach zero was in
the initial module implementation, but it was never supported in
modprobe (you had to use rmmod --wait).  After discussion with Lucas,
It has been deprecated (with a 10 second sleep) in kmod for the last
year.

This finally removes it: the flag will evoke a printk warning and a
normal (non-blocking) remove attempt.

Cc: Lucas De Marchi <lucas.de.marchi@gmail.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h |  3 ---
 kernel/module.c        | 46 ++++++++--------------------------------------
 2 files changed, 8 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 05f2447f8c15..15cd6b1b211e 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -367,9 +367,6 @@ struct module
 	/* What modules do I depend on? */
 	struct list_head target_list;
 
-	/* Who is waiting for us to be unloaded */
-	struct task_struct *waiter;
-
 	/* Destruction function. */
 	void (*exit)(void);
 
diff --git a/kernel/module.c b/kernel/module.c
index dc582749fa13..947105fd4cab 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -644,8 +644,6 @@ static int module_unload_init(struct module *mod)
 
 	/* Hold reference count during initialization. */
 	__this_cpu_write(mod->refptr->incs, 1);
-	/* Backwards compatibility macros put refcount during init. */
-	mod->waiter = current;
 
 	return 0;
 }
@@ -771,16 +769,9 @@ static int __try_stop_module(void *_sref)
 
 static int try_stop_module(struct module *mod, int flags, int *forced)
 {
-	if (flags & O_NONBLOCK) {
-		struct stopref sref = { mod, flags, forced };
+	struct stopref sref = { mod, flags, forced };
 
-		return stop_machine(__try_stop_module, &sref, NULL);
-	} else {
-		/* We don't need to stop the machine for this. */
-		mod->state = MODULE_STATE_GOING;
-		synchronize_sched();
-		return 0;
-	}
+	return stop_machine(__try_stop_module, &sref, NULL);
 }
 
 unsigned long module_refcount(struct module *mod)
@@ -813,21 +804,6 @@ EXPORT_SYMBOL(module_refcount);
 /* This exists whether we can unload or not */
 static void free_module(struct module *mod);
 
-static void wait_for_zero_refcount(struct module *mod)
-{
-	/* Since we might sleep for some time, release the mutex first */
-	mutex_unlock(&module_mutex);
-	for (;;) {
-		pr_debug("Looking at refcount...\n");
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (module_refcount(mod) == 0)
-			break;
-		schedule();
-	}
-	current->state = TASK_RUNNING;
-	mutex_lock(&module_mutex);
-}
-
 SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		unsigned int, flags)
 {
@@ -842,6 +818,11 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
+	if (!(flags & O_NONBLOCK)) {
+		printk(KERN_WARNING
+		       "waiting module removal not supported: please upgrade");
+	}
+
 	if (mutex_lock_interruptible(&module_mutex) != 0)
 		return -EINTR;
 
@@ -859,8 +840,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 
 	/* Doing init or already dying? */
 	if (mod->state != MODULE_STATE_LIVE) {
-		/* FIXME: if (force), slam module count and wake up
-                   waiter --RR */
+		/* FIXME: if (force), slam module count damn the torpedoes */
 		pr_debug("%s already dying\n", mod->name);
 		ret = -EBUSY;
 		goto out;
@@ -876,18 +856,11 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		}
 	}
 
-	/* Set this up before setting mod->state */
-	mod->waiter = current;
-
 	/* Stop the machine so refcounts can't move and disable module. */
 	ret = try_stop_module(mod, flags, &forced);
 	if (ret != 0)
 		goto out;
 
-	/* Never wait if forced. */
-	if (!forced && module_refcount(mod) != 0)
-		wait_for_zero_refcount(mod);
-
 	mutex_unlock(&module_mutex);
 	/* Final destruction now no one is using it. */
 	if (mod->exit != NULL)
@@ -1005,9 +978,6 @@ void module_put(struct module *module)
 		__this_cpu_inc(module->refptr->decs);
 
 		trace_module_put(module, _RET_IP_);
-		/* Maybe they're waiting for us to drop reference? */
-		if (unlikely(!module_is_live(module)))
-			wake_up_process(module->waiter);
 		preempt_enable();
 	}
 }
-- 
cgit 


From cd64647f043e3fd3569bcf068f47f030198ff93a Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Mon, 23 Sep 2013 16:43:58 +0800
Subject: hung_task: Change sysctl_hung_task_check_count to 'int'

As 'sysctl_hung_task_check_count' is 'unsigned long' when this
value is assigned to max_count in check_hung_uninterruptible_tasks(),
it's truncated to 'int' type.

This causes a minor artifact: if we write 2^32 to sysctl.hung_task_check_count,
hung task detection will be effectively disabled.

With this fix, it will still truncate the user input to 32 bits, but
reading sysctl.hung_task_check_count reflects the actual truncated value.

Signed-off-by: Li Zefan <lizefan@huawei.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/523FFF4E.9050401@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/sysctl.h | 2 +-
 kernel/hung_task.c           | 2 +-
 kernel/sysctl.c              | 5 +++--
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index bf8086b2506e..9552afa733d8 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -2,8 +2,8 @@
 #define _SCHED_SYSCTL_H
 
 #ifdef CONFIG_DETECT_HUNG_TASK
+extern int	     sysctl_hung_task_check_count;
 extern unsigned int  sysctl_hung_task_panic;
-extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_warnings;
 extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 3e97fb126e6b..042252383fd2 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -20,7 +20,7 @@
 /*
  * The number of tasks checked:
  */
-unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
 
 /*
  * Limit number of tasks checked in a batch.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2f06f3c6a3f..b24ed7f87a14 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -962,9 +962,10 @@ static struct ctl_table kern_table[] = {
 	{
 		.procname	= "hung_task_check_count",
 		.data		= &sysctl_hung_task_check_count,
-		.maxlen		= sizeof(unsigned long),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
 	},
 	{
 		.procname	= "hung_task_timeout_secs",
-- 
cgit 


From 2a855b644c310d5db5a80b8816c0c7748c167977 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 23 Aug 2013 09:40:42 -0700
Subject: rcu: Make list_splice_init_rcu() account for RCU readers

The list_splice_init_rcu() function allows a list visible to RCU readers
to be spliced into another list visible to RCU readers.  This is OK,
except for the use of INIT_LIST_HEAD(), which does pointer updates
without doing anything to make those updates safe for concurrent readers.

Of course, most of the time INIT_LIST_HEAD() is being used in reader-free
contexts, such as initialization or cleanup, so it is OK for it to update
pointers in an unsafe-for-RCU-readers manner.  This commit therefore
creates an INIT_LIST_HEAD_RCU() that uses ACCESS_ONCE() to make the updates
reader-safe.  The reason that we can use ACCESS_ONCE() instead of the more
typical rcu_assign_pointer() is that list_splice_init_rcu() is updating the
pointers to reference something that is already visible to readers, so
that there is no problem with pre-initialized values.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rculist.h | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 4106721c4e5e..45a0a9e81478 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -18,6 +18,21 @@
  * be used anywhere you would want to use a list_empty_rcu().
  */
 
+/*
+ * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers
+ * @list: list to be initialized
+ *
+ * You should instead use INIT_LIST_HEAD() for normal initialization and
+ * cleanup tasks, when readers have no access to the list being initialized.
+ * However, if the list being initialized is visible to readers, you
+ * need to keep the compiler from being too mischievous.
+ */
+static inline void INIT_LIST_HEAD_RCU(struct list_head *list)
+{
+	ACCESS_ONCE(list->next) = list;
+	ACCESS_ONCE(list->prev) = list;
+}
+
 /*
  * return the ->next pointer of a list_head in an rcu safe
  * way, we must not access it directly
@@ -191,9 +206,13 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	if (list_empty(list))
 		return;
 
-	/* "first" and "last" tracking list, so initialize it. */
+	/*
+	 * "first" and "last" tracking list, so initialize it.  RCU readers
+	 * have access to this list, so we must use INIT_LIST_HEAD_RCU()
+	 * instead of INIT_LIST_HEAD().
+	 */
 
-	INIT_LIST_HEAD(list);
+	INIT_LIST_HEAD_RCU(list);
 
 	/*
 	 * At this point, the list body still points to the source list.
-- 
cgit 


From 63c4db78e80407976e47bccaa2a4d8251b5a10bc Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 9 Aug 2013 12:19:29 -0700
Subject: rcu: Add tracing to rcu_gp_kthread()

This commit adds tracing to the rcu_gp_kthread() function in order to
help trace down hangs potentially involving this kthread.

Reported-by: Clark Williams <williams@redhat.com>
Reported-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 28 +++++++++++++++++++---------
 kernel/rcutree.c           | 18 ++++++++++++++++++
 2 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index ee2376cfaab3..60077e12093c 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -39,15 +39,25 @@ TRACE_EVENT(rcu_utilization,
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 
 /*
- * Tracepoint for grace-period events: starting and ending a grace
- * period ("start" and "end", respectively), a CPU noting the start
- * of a new grace period or the end of an old grace period ("cpustart"
- * and "cpuend", respectively), a CPU passing through a quiescent
- * state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
- * and "cpuofl", respectively), a CPU being kicked for being too
- * long in dyntick-idle mode ("kick"), a CPU accelerating its new
- * callbacks to RCU_NEXT_READY_TAIL ("AccReadyCB"), and a CPU
- * accelerating its new callbacks to RCU_WAIT_TAIL ("AccWaitCB").
+ * Tracepoint for grace-period events.  Takes a string identifying the
+ * RCU flavor, the grace-period number, and a string identifying the
+ * grace-period-related event as follows:
+ *
+ *	"AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL.
+ *	"AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL.
+ *	"start": Start a grace period.
+ *	"cpustart": CPU first notices a grace-period start.
+ *	"cpuqs": CPU passes through a quiescent state.
+ *	"cpuonl": CPU comes online.
+ *	"cpuofl": CPU goes offline.
+ *	"reqwait": GP kthread sleeps waiting for grace-period request.
+ *	"reqwaitsig": GP kthread awakened by signal from reqwait state.
+ *	"fqswait": GP kthread waiting until time to force quiescent states.
+ *	"fqsstart": GP kthread starts forcing quiescent states.
+ *	"fqsend": GP kthread done forcing quiescent states.
+ *	"fqswaitsig": GP kthread awakened by signal from fqswait state.
+ *	"end": End a grace period.
+ *	"cpuend": CPU first notices a grace-period end.
  */
 TRACE_EVENT(rcu_grace_period,
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 6d028fdbf86c..78d371526667 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1480,6 +1480,9 @@ static int __noreturn rcu_gp_kthread(void *arg)
 
 		/* Handle grace-period start. */
 		for (;;) {
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("reqwait"));
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
@@ -1487,6 +1490,9 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				break;
 			cond_resched();
 			flush_signals(current);
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("reqwaitsig"));
 		}
 
 		/* Handle quiescent-state forcing. */
@@ -1500,6 +1506,9 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		for (;;) {
 			if (!ret)
 				rsp->jiffies_force_qs = jiffies + j;
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("fqswait"));
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
 					((gf = ACCESS_ONCE(rsp->gp_flags)) &
 					 RCU_GP_FLAG_FQS) ||
@@ -1513,12 +1522,21 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			/* If time for quiescent-state forcing, do it. */
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqsstart"));
 				fqs_state = rcu_gp_fqs(rsp, fqs_state);
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqsend"));
 				cond_resched();
 			} else {
 				/* Deal with stray signal. */
 				cond_resched();
 				flush_signals(current);
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqswaitsig"));
 			}
 			j = jiffies_till_next_fqs;
 			if (j > HZ) {
-- 
cgit 


From bb311eccbdab974639263060b8452bf304af0b0c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 9 Aug 2013 16:02:09 -0700
Subject: rcu: Add tracing of normal (non-NOCB) grace-period requests

This commit adds tracing to the normal grace-period request points.
These are rcu_gp_cleanup(), which checks for the need for another
grace period at the end of the previous grace period, and
rcu_start_gp_advanced(), which restarts RCU's state machine after
an idle period.  These trace events are intended to help track down
bugs where RCU remains idle despite there being work for it to do.

Reported-by: Clark Williams <williams@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 1 +
 kernel/rcutree.c           | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 60077e12093c..98466c618ebc 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -45,6 +45,7 @@ TRACE_EVENT(rcu_utilization,
  *
  *	"AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL.
  *	"AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL.
+ *	"newreq": Request a new grace period.
  *	"start": Start a grace period.
  *	"cpustart": CPU first notices a grace-period start.
  *	"cpuqs": CPU passes through a quiescent state.
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 78d371526667..54dd6d03dbb5 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1459,8 +1459,12 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
 	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
-	if (cpu_needs_another_gp(rsp, rdp))
+	if (cpu_needs_another_gp(rsp, rdp)) {
 		rsp->gp_flags = 1;
+		trace_rcu_grace_period(rsp->name,
+				       ACCESS_ONCE(rsp->gpnum),
+				       TPS("newreq"));
+	}
 	raw_spin_unlock_irq(&rnp->lock);
 }
 
@@ -1584,6 +1588,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		return;
 	}
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
+	trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+			       TPS("newreq"));
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
-- 
cgit 


From 9261dd0da6c6432f08670719069449c6efe4f7a9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 14 Aug 2013 16:24:26 -0700
Subject: rcu: Add tracing for rcuo no-CBs CPU wakeup handshake

Lost wakeups from call_rcu() to the rcuo kthreads can result in hangs
that are difficult to diagnose.  This commit therefore adds tracing to
help pin down the cause of these hangs.

Reported-by: Clark Williams <williams@redhat.com>
Reported-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Add const per kbuild test robot's advice. ]
---
 include/trace/events/rcu.h | 37 +++++++++++++++++++++++++++++++++++++
 kernel/rcutree_plugin.h    | 14 +++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 98466c618ebc..4301cd9e3ee5 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -171,6 +171,42 @@ TRACE_EVENT(rcu_grace_period_init,
 		  __entry->grplo, __entry->grphi, __entry->qsmask)
 );
 
+/*
+ * Tracepoint for RCU no-CBs CPU callback handoffs.  This event is intended
+ * to assist debugging of these handoffs.
+ *
+ * The first argument is the name of the RCU flavor, and the second is
+ * the number of the offloaded CPU are extracted.  The third and final
+ * argument is a string as follows:
+ *
+ *	"WakeEmpty": Wake rcuo kthread, first CB to empty list.
+ *	"WakeOvf": Wake rcuo kthread, CB list is huge.
+ *	"WakeNot": Don't wake rcuo kthread.
+ *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
+ *	"WokeEmpty": rcuo kthread woke to find empty list.
+ *	"WokeNonEmpty": rcuo kthread woke to find non-empty list.
+ */
+TRACE_EVENT(rcu_nocb_wake,
+
+	TP_PROTO(const char *rcuname, int cpu, const char *reason),
+
+	TP_ARGS(rcuname, cpu, reason),
+
+	TP_STRUCT__entry(
+		__field(const char *, rcuname)
+		__field(int, cpu)
+		__field(const char *, reason)
+	),
+
+	TP_fast_assign(
+		__entry->rcuname = rcuname;
+		__entry->cpu = cpu;
+		__entry->reason = reason;
+	),
+
+	TP_printk("%s %d %s", __entry->rcuname, __entry->cpu, __entry->reason)
+);
+
 /*
  * Tracepoint for tasks blocking within preemptible-RCU read-side
  * critical sections.  Track the type of RCU (which one day might
@@ -667,6 +703,7 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
+#define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
 #define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
 #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
 #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 130c97b027f2..f4ed24b18e77 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -2108,15 +2108,22 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
 	t = ACCESS_ONCE(rdp->nocb_kthread);
-	if (rcu_nocb_poll | !t)
+	if (rcu_nocb_poll | !t) {
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+				    TPS("WakeNotPoll"));
 		return;
+	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
 		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
 		rdp->qlen_last_fqs_check = 0;
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
+	} else {
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
 	}
 	return;
 }
@@ -2233,10 +2240,15 @@ static int rcu_nocb_kthread(void *arg)
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
 		list = ACCESS_ONCE(rdp->nocb_head);
 		if (!list) {
+			if (!rcu_nocb_poll)
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WokeEmpty"));
 			schedule_timeout_interruptible(1);
 			flush_signals(current);
 			continue;
 		}
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+				    TPS("WokeNonEmpty"));
 
 		/*
 		 * Extract queued callbacks, update counts, and wait
-- 
cgit 


From 69a79bb12a81024d718e73c52e886907a3777b34 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 15 Aug 2013 13:23:23 -0700
Subject: rcu: Track rcu_nocb_kthread()'s sleeping and awakening

This commit adds event traces to track all of rcu_nocb_kthread()'s
blocking and awakening.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h |  4 ++++
 kernel/rcutree_plugin.h    | 15 ++++++++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 4301cd9e3ee5..a087d82ed431 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -183,8 +183,12 @@ TRACE_EVENT(rcu_grace_period_init,
  *	"WakeOvf": Wake rcuo kthread, CB list is huge.
  *	"WakeNot": Don't wake rcuo kthread.
  *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
+ *	"Poll": Start of new polling cycle for rcu_nocb_poll.
+ *	"Sleep": Sleep waiting for CBs for !rcu_nocb_poll.
  *	"WokeEmpty": rcuo kthread woke to find empty list.
  *	"WokeNonEmpty": rcuo kthread woke to find non-empty list.
+ *	"WaitQueue": Enqueue partially done, timed wait for it to complete.
+ *	"WokeQueue": Partial enqueue now complete.
  */
 TRACE_EVENT(rcu_nocb_wake,
 
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 24b01b69be92..21205b185340 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -2230,6 +2230,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 static int rcu_nocb_kthread(void *arg)
 {
 	int c, cl;
+	bool firsttime = 1;
 	struct rcu_head *list;
 	struct rcu_head *next;
 	struct rcu_head **tail;
@@ -2238,8 +2239,15 @@ static int rcu_nocb_kthread(void *arg)
 	/* Each pass through this loop invokes one batch of callbacks */
 	for (;;) {
 		/* If not polling, wait for next batch of callbacks. */
-		if (!rcu_nocb_poll)
+		if (!rcu_nocb_poll) {
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("Sleep"));
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+		} else if (firsttime) {
+			firsttime = 0;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("Poll"));
+		}
 		list = ACCESS_ONCE(rdp->nocb_head);
 		if (!list) {
 			if (!rcu_nocb_poll)
@@ -2249,6 +2257,7 @@ static int rcu_nocb_kthread(void *arg)
 			flush_signals(current);
 			continue;
 		}
+		firsttime = 1;
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 				    TPS("WokeNonEmpty"));
 
@@ -2271,7 +2280,11 @@ static int rcu_nocb_kthread(void *arg)
 			next = list->next;
 			/* Wait for enqueuing to complete, if needed. */
 			while (next == NULL && &list->next != tail) {
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WaitQueue"));
 				schedule_timeout_interruptible(1);
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WokeQueue"));
 				next = list->next;
 			}
 			debug_rcu_head_unqueue(list);
-- 
cgit 


From 15f5191b6acbbb38029b06284e8fd20275e7cfe8 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 18 Aug 2013 11:59:25 -0700
Subject: rcu: Avoid sparse warnings in rcu_nocb_wake trace event

The event-tracing macros do not like bool tracing arguments, so this
commit makes them be of type char.  This change has the knock-on effect
of making it illegal to pass a pointer into one of these arguments, so
also change rcutiny's first call to trace_rcu_batch_end() to convert
from pointer to boolean, prefixing with "!!".

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 10 +++++-----
 kernel/rcutiny.c           |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index a087d82ed431..aca382266411 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -591,17 +591,17 @@ TRACE_EVENT(rcu_invoke_kfree_callback,
 TRACE_EVENT(rcu_batch_end,
 
 	TP_PROTO(const char *rcuname, int callbacks_invoked,
-		 bool cb, bool nr, bool iit, bool risk),
+		 char cb, char nr, char iit, char risk),
 
 	TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
 		__field(int, callbacks_invoked)
-		__field(bool, cb)
-		__field(bool, nr)
-		__field(bool, iit)
-		__field(bool, risk)
+		__field(char, cb)
+		__field(char, nr)
+		__field(char, iit)
+		__field(char, risk)
 	),
 
 	TP_fast_assign(
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9ed6075dc562..80b6e273f1c5 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -273,7 +273,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	if (&rcp->rcucblist == rcp->donetail) {
 		RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1));
 		RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
-					      ACCESS_ONCE(rcp->rcucblist),
+					      !!ACCESS_ONCE(rcp->rcucblist),
 					      need_resched(),
 					      is_idle_task(current),
 					      false));
-- 
cgit 


From 774487611c949e6d194877e7147f6eeeec092b53 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Mon, 16 Sep 2013 17:02:00 +0100
Subject: iio: pressure-core: st: Provide support for the Vdd power supply

The power to some of the sensors are controlled by regulators. In most
cases these are 'always on', but if not they will fail to work until
the regulator is enabled using the relevant APIs. This patch allows for
the Vdd power supply to be specified by either platform data or Device
Tree.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/pressure/st_pressure_core.c | 28 ++++++++++++++++++++++++++++
 include/linux/iio/common/st_sensors.h   |  3 +++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 2da411b6925b..baeab109f41d 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -23,6 +23,7 @@
 #include <linux/iio/sysfs.h>
 #include <linux/iio/trigger.h>
 #include <linux/iio/buffer.h>
+#include <linux/regulator/consumer.h>
 #include <asm/unaligned.h>
 
 #include <linux/iio/common/st_sensors.h>
@@ -313,6 +314,29 @@ static const struct iio_trigger_ops st_press_trigger_ops = {
 #define ST_PRESS_TRIGGER_OPS NULL
 #endif
 
+static void st_press_power_enable(struct iio_dev *indio_dev)
+{
+	struct st_sensor_data *pdata = iio_priv(indio_dev);
+	int err;
+
+	/* Regulators not mandatory, but if requested we should enable it. */
+	pdata->vdd = devm_regulator_get_optional(&indio_dev->dev, "vdd");
+	if (!IS_ERR(pdata->vdd)) {
+		err = regulator_enable(pdata->vdd);
+		if (err != 0)
+			dev_warn(&indio_dev->dev,
+				 "Failed to enable specified Vdd supply\n");
+	}
+}
+
+static void st_press_power_disable(struct iio_dev *indio_dev)
+{
+	struct st_sensor_data *pdata = iio_priv(indio_dev);
+
+	if (!IS_ERR(pdata->vdd))
+		regulator_disable(pdata->vdd);
+}
+
 int st_press_common_probe(struct iio_dev *indio_dev,
 				struct st_sensors_platform_data *plat_data)
 {
@@ -323,6 +347,8 @@ int st_press_common_probe(struct iio_dev *indio_dev,
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &press_info;
 
+	st_press_power_enable(indio_dev);
+
 	err = st_sensors_check_device_support(indio_dev,
 					      ARRAY_SIZE(st_press_sensors),
 					      st_press_sensors);
@@ -380,6 +406,8 @@ void st_press_common_remove(struct iio_dev *indio_dev)
 {
 	struct st_sensor_data *pdata = iio_priv(indio_dev);
 
+	st_press_power_disable(indio_dev);
+
 	iio_device_unregister(indio_dev);
 	if (pdata->get_irq_data_ready(indio_dev) > 0)
 		st_sensors_deallocate_trigger(indio_dev);
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index e732fda6c8e6..968b84e5f380 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -16,6 +16,7 @@
 #include <linux/irqreturn.h>
 #include <linux/iio/trigger.h>
 #include <linux/bitops.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/platform_data/st_sensors_pdata.h>
 
@@ -201,6 +202,7 @@ struct st_sensors {
  * @trig: The trigger in use by the core driver.
  * @sensor: Pointer to the current sensor struct in use.
  * @current_fullscale: Maximum range of measure by the sensor.
+ * @vdd: Pointer to sensor's Vdd power supply
  * @enabled: Status of the sensor (false->off, true->on).
  * @multiread_bit: Use or not particular bit for [I2C/SPI] multiread.
  * @buffer_data: Data used by buffer part.
@@ -216,6 +218,7 @@ struct st_sensor_data {
 	struct iio_trigger *trig;
 	struct st_sensors *sensor;
 	struct st_sensor_fullscale_avl *current_fullscale;
+	struct regulator *vdd;
 
 	bool enabled;
 	bool multiread_bit;
-- 
cgit 


From 71e1980c8d465fd304d867d36f2246b72513efed Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Mon, 16 Sep 2013 17:02:00 +0100
Subject: iio: pressure-core: st: Provide support for the Vdd_IO power supply

The power to some of the sensors are controlled by regulators. In most
cases these are 'always on', but if not they will fail to work until
the regulator is enabled using the relevant APIs. This patch allows for
the Vdd_IO power supply to be specified by either platform data or
Device Tree.

Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/pressure/st_pressure_core.c | 13 ++++++++++++-
 include/linux/iio/common/st_sensors.h   |  2 ++
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index baeab109f41d..58083f9d51c5 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -319,7 +319,7 @@ static void st_press_power_enable(struct iio_dev *indio_dev)
 	struct st_sensor_data *pdata = iio_priv(indio_dev);
 	int err;
 
-	/* Regulators not mandatory, but if requested we should enable it. */
+	/* Regulators not mandatory, but if requested we should enable them. */
 	pdata->vdd = devm_regulator_get_optional(&indio_dev->dev, "vdd");
 	if (!IS_ERR(pdata->vdd)) {
 		err = regulator_enable(pdata->vdd);
@@ -327,6 +327,14 @@ static void st_press_power_enable(struct iio_dev *indio_dev)
 			dev_warn(&indio_dev->dev,
 				 "Failed to enable specified Vdd supply\n");
 	}
+
+	pdata->vdd_io = devm_regulator_get_optional(&indio_dev->dev, "vddio");
+	if (!IS_ERR(pdata->vdd_io)) {
+		err = regulator_enable(pdata->vdd_io);
+		if (err != 0)
+			dev_warn(&indio_dev->dev,
+				 "Failed to enable specified Vdd_IO supply\n");
+	}
 }
 
 static void st_press_power_disable(struct iio_dev *indio_dev)
@@ -335,6 +343,9 @@ static void st_press_power_disable(struct iio_dev *indio_dev)
 
 	if (!IS_ERR(pdata->vdd))
 		regulator_disable(pdata->vdd);
+
+	if (!IS_ERR(pdata->vdd_io))
+		regulator_disable(pdata->vdd_io);
 }
 
 int st_press_common_probe(struct iio_dev *indio_dev,
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 968b84e5f380..3c005eb3a0a4 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -203,6 +203,7 @@ struct st_sensors {
  * @sensor: Pointer to the current sensor struct in use.
  * @current_fullscale: Maximum range of measure by the sensor.
  * @vdd: Pointer to sensor's Vdd power supply
+ * @vdd_io: Pointer to sensor's Vdd-IO power supply
  * @enabled: Status of the sensor (false->off, true->on).
  * @multiread_bit: Use or not particular bit for [I2C/SPI] multiread.
  * @buffer_data: Data used by buffer part.
@@ -219,6 +220,7 @@ struct st_sensor_data {
 	struct st_sensors *sensor;
 	struct st_sensor_fullscale_avl *current_fullscale;
 	struct regulator *vdd;
+	struct regulator *vdd_io;
 
 	bool enabled;
 	bool multiread_bit;
-- 
cgit 


From 5c9f30236f53f3fbee170e2452dfa0e5dce4727b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:32 -0700
Subject: tcp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 424 +++++++++++++++++++++++++++---------------------------
 1 file changed, 208 insertions(+), 216 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b1aa324c5e65..0e47551e9bdb 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -50,7 +50,7 @@
 extern struct inet_hashinfo tcp_hashinfo;
 
 extern struct percpu_counter tcp_orphan_count;
-extern void tcp_time_wait(struct sock *sk, int state, int timeo);
+void tcp_time_wait(struct sock *sk, int state, int timeo);
 
 #define MAX_TCP_HEADER	(128 + MAX_HEADER)
 #define MAX_TCP_OPTION_SPACE 40
@@ -325,7 +325,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 	return false;
 }
 
-extern bool tcp_check_oom(struct sock *sk, int shift);
+bool tcp_check_oom(struct sock *sk, int shift);
 
 /* syncookies: remember time of last synqueue overflow */
 static inline void tcp_synq_overflow(struct sock *sk)
@@ -348,38 +348,38 @@ extern struct proto tcp_prot;
 #define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
 #define TCP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
 
-extern void tcp_init_mem(struct net *net);
-
-extern void tcp_tasklet_init(void);
-
-extern void tcp_v4_err(struct sk_buff *skb, u32);
-
-extern void tcp_shutdown (struct sock *sk, int how);
-
-extern void tcp_v4_early_demux(struct sk_buff *skb);
-extern int tcp_v4_rcv(struct sk_buff *skb);
-
-extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
-extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t size);
-extern int tcp_sendpage(struct sock *sk, struct page *page, int offset,
-			size_t size, int flags);
-extern void tcp_release_cb(struct sock *sk);
-extern void tcp_wfree(struct sk_buff *skb);
-extern void tcp_write_timer_handler(struct sock *sk);
-extern void tcp_delack_timer_handler(struct sock *sk);
-extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
-extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
-				 const struct tcphdr *th, unsigned int len);
-extern void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
-				const struct tcphdr *th, unsigned int len);
-extern void tcp_rcv_space_adjust(struct sock *sk);
-extern void tcp_cleanup_rbuf(struct sock *sk, int copied);
-extern int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
-extern void tcp_twsk_destructor(struct sock *sk);
-extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
-			       struct pipe_inode_info *pipe, size_t len,
-			       unsigned int flags);
+void tcp_init_mem(struct net *net);
+
+void tcp_tasklet_init(void);
+
+void tcp_v4_err(struct sk_buff *skb, u32);
+
+void tcp_shutdown(struct sock *sk, int how);
+
+void tcp_v4_early_demux(struct sk_buff *skb);
+int tcp_v4_rcv(struct sk_buff *skb);
+
+int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
+int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		size_t size);
+int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
+		 int flags);
+void tcp_release_cb(struct sock *sk);
+void tcp_wfree(struct sk_buff *skb);
+void tcp_write_timer_handler(struct sock *sk);
+void tcp_delack_timer_handler(struct sock *sk);
+int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
+			  const struct tcphdr *th, unsigned int len);
+void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
+			 const struct tcphdr *th, unsigned int len);
+void tcp_rcv_space_adjust(struct sock *sk);
+void tcp_cleanup_rbuf(struct sock *sk, int copied);
+int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
+void tcp_twsk_destructor(struct sock *sk);
+ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags);
 
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
@@ -409,66 +409,65 @@ enum tcp_tw_status {
 };
 
 
-extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
-						     struct sk_buff *skb,
-						     const struct tcphdr *th);
-extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
-				   struct request_sock *req,
-				   struct request_sock **prev,
-				   bool fastopen);
-extern int tcp_child_process(struct sock *parent, struct sock *child,
-			     struct sk_buff *skb);
-extern void tcp_enter_loss(struct sock *sk, int how);
-extern void tcp_clear_retrans(struct tcp_sock *tp);
-extern void tcp_update_metrics(struct sock *sk);
-extern void tcp_init_metrics(struct sock *sk);
-extern void tcp_metrics_init(void);
-extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check);
-extern bool tcp_remember_stamp(struct sock *sk);
-extern bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
-extern void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
-extern void tcp_disable_fack(struct tcp_sock *tp);
-extern void tcp_close(struct sock *sk, long timeout);
-extern void tcp_init_sock(struct sock *sk);
-extern unsigned int tcp_poll(struct file * file, struct socket *sock,
-			     struct poll_table_struct *wait);
-extern int tcp_getsockopt(struct sock *sk, int level, int optname,
+enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
+					      struct sk_buff *skb,
+					      const struct tcphdr *th);
+struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
+			   struct request_sock *req, struct request_sock **prev,
+			   bool fastopen);
+int tcp_child_process(struct sock *parent, struct sock *child,
+		      struct sk_buff *skb);
+void tcp_enter_loss(struct sock *sk, int how);
+void tcp_clear_retrans(struct tcp_sock *tp);
+void tcp_update_metrics(struct sock *sk);
+void tcp_init_metrics(struct sock *sk);
+void tcp_metrics_init(void);
+bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst,
+			bool paws_check);
+bool tcp_remember_stamp(struct sock *sk);
+bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw);
+void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst);
+void tcp_disable_fack(struct tcp_sock *tp);
+void tcp_close(struct sock *sk, long timeout);
+void tcp_init_sock(struct sock *sk);
+unsigned int tcp_poll(struct file *file, struct socket *sock,
+		      struct poll_table_struct *wait);
+int tcp_getsockopt(struct sock *sk, int level, int optname,
+		   char __user *optval, int __user *optlen);
+int tcp_setsockopt(struct sock *sk, int level, int optname,
+		   char __user *optval, unsigned int optlen);
+int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 			  char __user *optval, int __user *optlen);
-extern int tcp_setsockopt(struct sock *sk, int level, int optname,
+int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
 			  char __user *optval, unsigned int optlen);
-extern int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, int __user *optlen);
-extern int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, unsigned int optlen);
-extern void tcp_set_keepalive(struct sock *sk, int val);
-extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
-extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t len, int nonblock, int flags, int *addr_len);
-extern void tcp_parse_options(const struct sk_buff *skb,
-			      struct tcp_options_received *opt_rx,
-			      int estab, struct tcp_fastopen_cookie *foc);
-extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
+void tcp_set_keepalive(struct sock *sk, int val);
+void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
+int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		size_t len, int nonblock, int flags, int *addr_len);
+void tcp_parse_options(const struct sk_buff *skb,
+		       struct tcp_options_received *opt_rx,
+		       int estab, struct tcp_fastopen_cookie *foc);
+const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 /*
  *	TCP v4 functions exported for the inet6 API
  */
 
-extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
-extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
-extern struct sock * tcp_create_openreq_child(struct sock *sk,
-					      struct request_sock *req,
-					      struct sk_buff *skb);
-extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
-					  struct request_sock *req,
-					  struct dst_entry *dst);
-extern int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
-extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
-			  int addr_len);
-extern int tcp_connect(struct sock *sk);
-extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
-					struct request_sock *req,
-					struct tcp_fastopen_cookie *foc);
-extern int tcp_disconnect(struct sock *sk, int flags);
+void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
+int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
+struct sock *tcp_create_openreq_child(struct sock *sk,
+				      struct request_sock *req,
+				      struct sk_buff *skb);
+struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct dst_entry *dst);
+int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
+int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
+int tcp_connect(struct sock *sk);
+struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+				struct request_sock *req,
+				struct tcp_fastopen_cookie *foc);
+int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_connect_init(struct sock *sk);
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -477,15 +476,14 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 
 /* From syncookies.c */
 extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
-extern int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
-			     u32 cookie);
-extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, 
-				    struct ip_options *opt);
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
+		      u32 cookie);
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
+			     struct ip_options *opt);
 #ifdef CONFIG_SYN_COOKIES
-extern u32 __cookie_v4_init_sequence(const struct iphdr *iph,
-				     const struct tcphdr *th, u16 *mssp);
-extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, 
-				     __u16 *mss);
+u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
+			      u16 *mssp);
+__u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mss);
 #else
 static inline __u32 cookie_v4_init_sequence(struct sock *sk,
 					    struct sk_buff *skb,
@@ -495,19 +493,19 @@ static inline __u32 cookie_v4_init_sequence(struct sock *sk,
 }
 #endif
 
-extern __u32 cookie_init_timestamp(struct request_sock *req);
-extern bool cookie_check_timestamp(struct tcp_options_received *opt,
-				struct net *net, bool *ecn_ok);
+__u32 cookie_init_timestamp(struct request_sock *req);
+bool cookie_check_timestamp(struct tcp_options_received *opt, struct net *net,
+			    bool *ecn_ok);
 
 /* From net/ipv6/syncookies.c */
-extern int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
-			     u32 cookie);
-extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
+int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
+		      u32 cookie);
+struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
 #ifdef CONFIG_SYN_COOKIES
-extern u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
-				     const struct tcphdr *th, u16 *mssp);
-extern __u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb,
-				     __u16 *mss);
+u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
+			      const struct tcphdr *th, u16 *mssp);
+__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb,
+			      __u16 *mss);
 #else
 static inline __u32 cookie_v6_init_sequence(struct sock *sk,
 					    struct sk_buff *skb,
@@ -518,47 +516,46 @@ static inline __u32 cookie_v6_init_sequence(struct sock *sk,
 #endif
 /* tcp_output.c */
 
-extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
-				      int nonagle);
-extern bool tcp_may_send_now(struct sock *sk);
-extern int __tcp_retransmit_skb(struct sock *, struct sk_buff *);
-extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
-extern void tcp_retransmit_timer(struct sock *sk);
-extern void tcp_xmit_retransmit_queue(struct sock *);
-extern void tcp_simple_retransmit(struct sock *);
-extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
-extern int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
-
-extern void tcp_send_probe0(struct sock *);
-extern void tcp_send_partial(struct sock *);
-extern int tcp_write_wakeup(struct sock *);
-extern void tcp_send_fin(struct sock *sk);
-extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
-extern int tcp_send_synack(struct sock *);
-extern bool tcp_syn_flood_action(struct sock *sk,
-				 const struct sk_buff *skb,
-				 const char *proto);
-extern void tcp_push_one(struct sock *, unsigned int mss_now);
-extern void tcp_send_ack(struct sock *sk);
-extern void tcp_send_delayed_ack(struct sock *sk);
-extern void tcp_send_loss_probe(struct sock *sk);
-extern bool tcp_schedule_loss_probe(struct sock *sk);
+void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
+			       int nonagle);
+bool tcp_may_send_now(struct sock *sk);
+int __tcp_retransmit_skb(struct sock *, struct sk_buff *);
+int tcp_retransmit_skb(struct sock *, struct sk_buff *);
+void tcp_retransmit_timer(struct sock *sk);
+void tcp_xmit_retransmit_queue(struct sock *);
+void tcp_simple_retransmit(struct sock *);
+int tcp_trim_head(struct sock *, struct sk_buff *, u32);
+int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
+
+void tcp_send_probe0(struct sock *);
+void tcp_send_partial(struct sock *);
+int tcp_write_wakeup(struct sock *);
+void tcp_send_fin(struct sock *sk);
+void tcp_send_active_reset(struct sock *sk, gfp_t priority);
+int tcp_send_synack(struct sock *);
+bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb,
+			  const char *proto);
+void tcp_push_one(struct sock *, unsigned int mss_now);
+void tcp_send_ack(struct sock *sk);
+void tcp_send_delayed_ack(struct sock *sk);
+void tcp_send_loss_probe(struct sock *sk);
+bool tcp_schedule_loss_probe(struct sock *sk);
 
 /* tcp_input.c */
-extern void tcp_cwnd_application_limited(struct sock *sk);
-extern void tcp_resume_early_retransmit(struct sock *sk);
-extern void tcp_rearm_rto(struct sock *sk);
-extern void tcp_reset(struct sock *sk);
+void tcp_cwnd_application_limited(struct sock *sk);
+void tcp_resume_early_retransmit(struct sock *sk);
+void tcp_rearm_rto(struct sock *sk);
+void tcp_reset(struct sock *sk);
 
 /* tcp_timer.c */
-extern void tcp_init_xmit_timers(struct sock *);
+void tcp_init_xmit_timers(struct sock *);
 static inline void tcp_clear_xmit_timers(struct sock *sk)
 {
 	inet_csk_clear_xmit_timers(sk);
 }
 
-extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
-extern unsigned int tcp_current_mss(struct sock *sk);
+unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
+unsigned int tcp_current_mss(struct sock *sk);
 
 /* Bound MSS / TSO packet size with the half of the window */
 static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
@@ -584,20 +581,20 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
 }
 
 /* tcp.c */
-extern void tcp_get_info(const struct sock *, struct tcp_info *);
+void tcp_get_info(const struct sock *, struct tcp_info *);
 
 /* Read 'sendfile()'-style from a TCP socket */
 typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 				unsigned int, size_t);
-extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
-			 sk_read_actor_t recv_actor);
+int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+		  sk_read_actor_t recv_actor);
 
-extern void tcp_initialize_rcv_mss(struct sock *sk);
+void tcp_initialize_rcv_mss(struct sock *sk);
 
-extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
-extern int tcp_mss_to_mtu(struct sock *sk, int mss);
-extern void tcp_mtup_init(struct sock *sk);
-extern void tcp_init_buffer_space(struct sock *sk);
+int tcp_mtu_to_mss(struct sock *sk, int pmtu);
+int tcp_mss_to_mtu(struct sock *sk, int mss);
+void tcp_mtup_init(struct sock *sk);
+void tcp_init_buffer_space(struct sock *sk);
 
 static inline void tcp_bound_rto(const struct sock *sk)
 {
@@ -610,7 +607,7 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 	return (tp->srtt >> 3) + tp->rttvar;
 }
 
-extern void tcp_set_rto(struct sock *sk);
+void tcp_set_rto(struct sock *sk);
 
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
@@ -663,7 +660,7 @@ static inline u32 tcp_receive_window(const struct tcp_sock *tp)
  * scaling applied to the result.  The caller does these things
  * if necessary.  This is a "raw" window selection.
  */
-extern u32 __tcp_select_window(struct sock *sk);
+u32 __tcp_select_window(struct sock *sk);
 
 void tcp_send_window_probe(struct sock *sk);
 
@@ -800,24 +797,24 @@ struct tcp_congestion_ops {
 	struct module 	*owner;
 };
 
-extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
-extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
+int tcp_register_congestion_control(struct tcp_congestion_ops *type);
+void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
 
-extern void tcp_init_congestion_control(struct sock *sk);
-extern void tcp_cleanup_congestion_control(struct sock *sk);
-extern int tcp_set_default_congestion_control(const char *name);
-extern void tcp_get_default_congestion_control(char *name);
-extern void tcp_get_available_congestion_control(char *buf, size_t len);
-extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
-extern int tcp_set_allowed_congestion_control(char *allowed);
-extern int tcp_set_congestion_control(struct sock *sk, const char *name);
-extern void tcp_slow_start(struct tcp_sock *tp);
-extern void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
+void tcp_init_congestion_control(struct sock *sk);
+void tcp_cleanup_congestion_control(struct sock *sk);
+int tcp_set_default_congestion_control(const char *name);
+void tcp_get_default_congestion_control(char *name);
+void tcp_get_available_congestion_control(char *buf, size_t len);
+void tcp_get_allowed_congestion_control(char *buf, size_t len);
+int tcp_set_allowed_congestion_control(char *allowed);
+int tcp_set_congestion_control(struct sock *sk, const char *name);
+void tcp_slow_start(struct tcp_sock *tp);
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
-extern u32 tcp_reno_ssthresh(struct sock *sk);
-extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
-extern u32 tcp_reno_min_cwnd(const struct sock *sk);
+u32 tcp_reno_ssthresh(struct sock *sk);
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
+u32 tcp_reno_min_cwnd(const struct sock *sk);
 extern struct tcp_congestion_ops tcp_reno;
 
 static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
@@ -936,8 +933,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 /* Use define here intentionally to get WARN_ON location shown at the caller */
 #define tcp_verify_left_out(tp)	WARN_ON(tcp_left_out(tp) > tp->packets_out)
 
-extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
-extern __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);
+void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
+__u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);
 
 /* The maximum number of MSS of available cwnd for which TSO defers
  * sending if not using sysctl_tcp_tso_win_divisor.
@@ -963,7 +960,7 @@ static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
 {
 	return tp->snd_una + tp->snd_wnd;
 }
-extern bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
+bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
 
 static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
 				       const struct sk_buff *skb)
@@ -1028,7 +1025,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
 #endif
 }
 
-extern bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
+bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
 
 #undef STATE_TRACE
 
@@ -1039,9 +1036,9 @@ static const char *statename[]={
 	"Close Wait","Last ACK","Listen","Closing"
 };
 #endif
-extern void tcp_set_state(struct sock *sk, int state);
+void tcp_set_state(struct sock *sk, int state);
 
-extern void tcp_done(struct sock *sk);
+void tcp_done(struct sock *sk);
 
 static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 {
@@ -1049,13 +1046,12 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 	rx_opt->num_sacks = 0;
 }
 
-extern u32 tcp_default_init_rwnd(u32 mss);
+u32 tcp_default_init_rwnd(u32 mss);
 
 /* Determine a window scaling and initial window to offer. */
-extern void tcp_select_initial_window(int __space, __u32 mss,
-				      __u32 *rcv_wnd, __u32 *window_clamp,
-				      int wscale_ok, __u8 *rcv_wscale,
-				      __u32 init_rcv_wnd);
+void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,
+			       __u32 *window_clamp, int wscale_ok,
+			       __u8 *rcv_wscale, __u32 init_rcv_wnd);
 
 static inline int tcp_win_from_space(int space)
 {
@@ -1099,7 +1095,7 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->loc_port = tcp_hdr(skb)->dest;
 }
 
-extern void tcp_enter_memory_pressure(struct sock *sk);
+void tcp_enter_memory_pressure(struct sock *sk);
 
 static inline int keepalive_intvl_when(const struct tcp_sock *tp)
 {
@@ -1252,21 +1248,20 @@ struct tcp_md5sig_pool {
 };
 
 /* - functions */
-extern int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
-			       const struct sock *sk,
-			       const struct request_sock *req,
-			       const struct sk_buff *skb);
-extern int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
-			  int family, const u8 *newkey,
-			  u8 newkeylen, gfp_t gfp);
-extern int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
-			  int family);
-extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
+			const struct sock *sk, const struct request_sock *req,
+			const struct sk_buff *skb);
+int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
+		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp);
+int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
+		   int family);
+struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
 					 struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-extern struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
-			const union tcp_md5_addr *addr, int family);
+struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
+					 const union tcp_md5_addr *addr,
+					 int family);
 #define tcp_twsk_md5_key(twsk)	((twsk)->tw_md5_key)
 #else
 static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
@@ -1278,27 +1273,26 @@ static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk,
 #define tcp_twsk_md5_key(twsk)	NULL
 #endif
 
-extern bool tcp_alloc_md5sig_pool(void);
+bool tcp_alloc_md5sig_pool(void);
 
-extern struct tcp_md5sig_pool	*tcp_get_md5sig_pool(void);
+struct tcp_md5sig_pool *tcp_get_md5sig_pool(void);
 static inline void tcp_put_md5sig_pool(void)
 {
 	local_bh_enable();
 }
 
-extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *);
-extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *,
-				 unsigned int header_len);
-extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
-			    const struct tcp_md5sig_key *key);
+int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *);
+int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *,
+			  unsigned int header_len);
+int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
+		     const struct tcp_md5sig_key *key);
 
 /* From tcp_fastopen.c */
-extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
-				   struct tcp_fastopen_cookie *cookie,
-				   int *syn_loss, unsigned long *last_syn_loss);
-extern void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
-				   struct tcp_fastopen_cookie *cookie,
-				   bool syn_lost);
+void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
+			    struct tcp_fastopen_cookie *cookie, int *syn_loss,
+			    unsigned long *last_syn_loss);
+void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
+			    struct tcp_fastopen_cookie *cookie, bool syn_lost);
 struct tcp_fastopen_request {
 	/* Fast Open cookie. Size 0 means a cookie request */
 	struct tcp_fastopen_cookie	cookie;
@@ -1309,8 +1303,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
 
 extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 int tcp_fastopen_reset_cipher(void *key, unsigned int len);
-extern void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-				    struct tcp_fastopen_cookie *foc);
+void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
+			     struct tcp_fastopen_cookie *foc);
 
 #define TCP_FASTOPEN_KEY_LENGTH 16
 
@@ -1529,22 +1523,20 @@ struct tcp_iter_state {
 	loff_t			last_pos;
 };
 
-extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
-extern void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
+int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
+void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
 
 extern struct request_sock_ops tcp_request_sock_ops;
 extern struct request_sock_ops tcp6_request_sock_ops;
 
-extern void tcp_v4_destroy_sock(struct sock *sk);
+void tcp_v4_destroy_sock(struct sock *sk);
 
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
-				       netdev_features_t features);
-extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb);
-extern int tcp_gro_complete(struct sk_buff *skb);
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+				netdev_features_t features);
+struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int tcp_gro_complete(struct sk_buff *skb);
 
-extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr,
-				__be32 daddr);
+void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 
 static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 {
@@ -1560,8 +1552,8 @@ static inline bool tcp_stream_memory_free(const struct sock *sk)
 }
 
 #ifdef CONFIG_PROC_FS
-extern int tcp4_proc_init(void);
-extern void tcp4_proc_exit(void);
+int tcp4_proc_init(void);
+void tcp4_proc_exit(void);
 #endif
 
 /* TCP af-specific functions */
@@ -1592,9 +1584,9 @@ struct tcp_request_sock_ops {
 #endif
 };
 
-extern int tcpv4_offload_init(void);
+int tcpv4_offload_init(void);
 
-extern void tcp_v4_init(void);
-extern void tcp_init(void);
+void tcp_v4_init(void);
+void tcp_init(void);
 
 #endif	/* _TCP_H */
-- 
cgit 


From 1a50bd064e1825ad0cc049be2d205ac6719f88e5 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:36 -0700
Subject: udp.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h | 94 +++++++++++++++++++++++++++----------------------------
 1 file changed, 47 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/udp.h b/include/net/udp.h
index ef2e0b7843a0..510b8cb4d1a7 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -79,7 +79,7 @@ struct udp_table {
 	unsigned int		log;
 };
 extern struct udp_table udp_table;
-extern void udp_table_init(struct udp_table *, const char *);
+void udp_table_init(struct udp_table *, const char *);
 static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
 					     struct net *net, unsigned int num)
 {
@@ -162,52 +162,52 @@ static inline void udp_lib_hash(struct sock *sk)
 	BUG();
 }
 
-extern void udp_lib_unhash(struct sock *sk);
-extern void udp_lib_rehash(struct sock *sk, u16 new_hash);
+void udp_lib_unhash(struct sock *sk);
+void udp_lib_rehash(struct sock *sk, u16 new_hash);
 
 static inline void udp_lib_close(struct sock *sk, long timeout)
 {
 	sk_common_release(sk);
 }
 
-extern int udp_lib_get_port(struct sock *sk, unsigned short snum,
-			    int (*)(const struct sock *,const struct sock *),
-			    unsigned int hash2_nulladdr);
+int udp_lib_get_port(struct sock *sk, unsigned short snum,
+		     int (*)(const struct sock *, const struct sock *),
+		     unsigned int hash2_nulladdr);
 
 /* net/ipv4/udp.c */
-extern int udp_get_port(struct sock *sk, unsigned short snum,
-			int (*saddr_cmp)(const struct sock *,
-					 const struct sock *));
-extern void udp_err(struct sk_buff *, u32);
-extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk,
-			    struct msghdr *msg, size_t len);
-extern int udp_push_pending_frames(struct sock *sk);
-extern void udp_flush_pending_frames(struct sock *sk);
-extern void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
-extern int udp_rcv(struct sk_buff *skb);
-extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
-extern int udp_disconnect(struct sock *sk, int flags);
-extern unsigned int udp_poll(struct file *file, struct socket *sock,
-			     poll_table *wait);
-extern struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-					      netdev_features_t features);
-extern int udp_lib_getsockopt(struct sock *sk, int level, int optname,
-			      char __user *optval, int __user *optlen);
-extern int udp_lib_setsockopt(struct sock *sk, int level, int optname,
-			      char __user *optval, unsigned int optlen,
-			      int (*push_pending_frames)(struct sock *));
-extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
-				    __be32 daddr, __be16 dport,
-				    int dif);
-extern struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
-				    __be32 daddr, __be16 dport,
-				    int dif, struct udp_table *tbl);
-extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
-				    const struct in6_addr *daddr, __be16 dport,
-				    int dif);
-extern struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
-				    const struct in6_addr *daddr, __be16 dport,
-				    int dif, struct udp_table *tbl);
+int udp_get_port(struct sock *sk, unsigned short snum,
+		 int (*saddr_cmp)(const struct sock *,
+				  const struct sock *));
+void udp_err(struct sk_buff *, u32);
+int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+		size_t len);
+int udp_push_pending_frames(struct sock *sk);
+void udp_flush_pending_frames(struct sock *sk);
+void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
+int udp_rcv(struct sk_buff *skb);
+int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int udp_disconnect(struct sock *sk, int flags);
+unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+				       netdev_features_t features);
+int udp_lib_getsockopt(struct sock *sk, int level, int optname,
+		       char __user *optval, int __user *optlen);
+int udp_lib_setsockopt(struct sock *sk, int level, int optname,
+		       char __user *optval, unsigned int optlen,
+		       int (*push_pending_frames)(struct sock *));
+struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+			     __be32 daddr, __be16 dport, int dif);
+struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+			       __be32 daddr, __be16 dport, int dif,
+			       struct udp_table *tbl);
+struct sock *udp6_lib_lookup(struct net *net,
+			     const struct in6_addr *saddr, __be16 sport,
+			     const struct in6_addr *daddr, __be16 dport,
+			     int dif);
+struct sock *__udp6_lib_lookup(struct net *net,
+			       const struct in6_addr *saddr, __be16 sport,
+			       const struct in6_addr *daddr, __be16 dport,
+			       int dif, struct udp_table *tbl);
 
 /*
  * 	SNMP statistics for UDP and UDP-Lite
@@ -259,19 +259,19 @@ struct udp_iter_state {
 };
 
 #ifdef CONFIG_PROC_FS
-extern int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo);
-extern void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo);
+int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo);
+void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo);
 
-extern int udp4_proc_init(void);
-extern void udp4_proc_exit(void);
+int udp4_proc_init(void);
+void udp4_proc_exit(void);
 #endif
 
-extern int udpv4_offload_init(void);
+int udpv4_offload_init(void);
 
-extern void udp_init(void);
+void udp_init(void);
 
-extern void udp_encap_enable(void);
+void udp_encap_enable(void);
 #if IS_ENABLED(CONFIG_IPV6)
-extern void udpv6_encap_enable(void);
+void udpv6_encap_enable(void);
 #endif
 #endif	/* _UDP_H */
-- 
cgit 


From 160734399f968e4ac4d2f1db844c9c85a4952e05 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:39 -0700
Subject: udplite.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udplite.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/udplite.h b/include/net/udplite.h
index 71375459a884..2caadabcd07b 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -126,7 +126,7 @@ static inline __wsum udplite_csum(struct sk_buff *skb)
 	return skb_checksum(skb, off, len, 0);
 }
 
-extern void	udplite4_register(void);
-extern int 	udplite_get_port(struct sock *sk, unsigned short snum,
-			int (*scmp)(const struct sock *, const struct sock *));
+void udplite4_register(void);
+int udplite_get_port(struct sock *sk, unsigned short snum,
+		     int (*scmp)(const struct sock *, const struct sock *));
 #endif	/* _UDPLITE_H */
-- 
cgit 


From 9e4638cdc894698db6e1de10565ae404748f16c5 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:42 -0700
Subject: wext.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/wext.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/wext.h b/include/net/wext.h
index 4f6e7423174c..345911965dbb 100644
--- a/include/net/wext.h
+++ b/include/net/wext.h
@@ -6,13 +6,13 @@
 struct net;
 
 #ifdef CONFIG_WEXT_CORE
-extern int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd,
-			     void __user *arg);
-extern int compat_wext_handle_ioctl(struct net *net, unsigned int cmd,
-				    unsigned long arg);
+int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd,
+		      void __user *arg);
+int compat_wext_handle_ioctl(struct net *net, unsigned int cmd,
+			     unsigned long arg);
 
-extern struct iw_statistics *get_wireless_stats(struct net_device *dev);
-extern int call_commit_handler(struct net_device *dev);
+struct iw_statistics *get_wireless_stats(struct net_device *dev);
+int call_commit_handler(struct net_device *dev);
 #else
 static inline int wext_handle_ioctl(struct net *net, struct ifreq *ifr, unsigned int cmd,
 				    void __user *arg)
@@ -27,8 +27,8 @@ static inline int compat_wext_handle_ioctl(struct net *net, unsigned int cmd,
 #endif
 
 #ifdef CONFIG_WEXT_PROC
-extern int wext_proc_init(struct net *net);
-extern void wext_proc_exit(struct net *net);
+int wext_proc_init(struct net *net);
+void wext_proc_exit(struct net *net);
 #else
 static inline int wext_proc_init(struct net *net)
 {
-- 
cgit 


From 6dfd43d28c92a6d00a3bbccb2aa978de8c1c96b8 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:45 -0700
Subject: wimax.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/wimax.h | 33 ++++++++++++++++-----------------
 1 file changed, 16 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/wimax.h b/include/net/wimax.h
index bbb74f990cab..98498e1daa06 100644
--- a/include/net/wimax.h
+++ b/include/net/wimax.h
@@ -438,9 +438,9 @@ struct wimax_dev {
  *
  * These functions are not exported to user space.
  */
-extern void wimax_dev_init(struct wimax_dev *);
-extern int wimax_dev_add(struct wimax_dev *, struct net_device *);
-extern void wimax_dev_rm(struct wimax_dev *);
+void wimax_dev_init(struct wimax_dev *);
+int wimax_dev_add(struct wimax_dev *, struct net_device *);
+void wimax_dev_rm(struct wimax_dev *);
 
 static inline
 struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev)
@@ -454,8 +454,8 @@ struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev)
 	return wimax_dev->net_dev->dev.parent;
 }
 
-extern void wimax_state_change(struct wimax_dev *, enum wimax_st);
-extern enum wimax_st wimax_state_get(struct wimax_dev *);
+void wimax_state_change(struct wimax_dev *, enum wimax_st);
+enum wimax_st wimax_state_get(struct wimax_dev *);
 
 /*
  * Radio Switch state reporting.
@@ -463,8 +463,8 @@ extern enum wimax_st wimax_state_get(struct wimax_dev *);
  * enum wimax_rf_state is declared in linux/wimax.h so the exports
  * to user space can use it.
  */
-extern void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
-extern void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
+void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state);
+void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
 
 
 /*
@@ -490,15 +490,14 @@ extern void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state);
  * send diagnostics information that a device-specific diagnostics
  * tool would be interested in.
  */
-extern struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *,
-				       const void *, size_t, gfp_t);
-extern int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
-extern int wimax_msg(struct wimax_dev *, const char *,
-		     const void *, size_t, gfp_t);
+struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *,
+				size_t, gfp_t);
+int wimax_msg_send(struct wimax_dev *, struct sk_buff *);
+int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t);
 
-extern const void *wimax_msg_data_len(struct sk_buff *, size_t *);
-extern const void *wimax_msg_data(struct sk_buff *);
-extern ssize_t wimax_msg_len(struct sk_buff *);
+const void *wimax_msg_data_len(struct sk_buff *, size_t *);
+const void *wimax_msg_data(struct sk_buff *);
+ssize_t wimax_msg_len(struct sk_buff *);
 
 
 /*
@@ -513,7 +512,7 @@ extern ssize_t wimax_msg_len(struct sk_buff *);
  * device's control structure and (as such) the 'struct wimax_dev' is
  * referenced by the caller.
  */
-extern int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
-extern int wimax_reset(struct wimax_dev *);
+int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state);
+int wimax_reset(struct wimax_dev *);
 
 #endif /* #ifndef __NET__WIMAX_H__ */
-- 
cgit 


From 5db50ee6e617c347a24b18ee229e44ba8d4d84a3 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:49 -0700
Subject: x25.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/x25.h | 141 +++++++++++++++++++++++++++---------------------------
 1 file changed, 71 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/net/x25.h b/include/net/x25.h
index b4a8a8923128..c383aa4edbf0 100644
--- a/include/net/x25.h
+++ b/include/net/x25.h
@@ -187,57 +187,57 @@ extern int  sysctl_x25_clear_request_timeout;
 extern int  sysctl_x25_ack_holdback_timeout;
 extern int  sysctl_x25_forward;
 
-extern int x25_parse_address_block(struct sk_buff *skb,
-		struct x25_address *called_addr,
-		struct x25_address *calling_addr);
-
-extern int  x25_addr_ntoa(unsigned char *, struct x25_address *,
-			  struct x25_address *);
-extern int  x25_addr_aton(unsigned char *, struct x25_address *,
-			  struct x25_address *);
-extern struct sock *x25_find_socket(unsigned int, struct x25_neigh *);
-extern void x25_destroy_socket_from_timer(struct sock *);
-extern int  x25_rx_call_request(struct sk_buff *, struct x25_neigh *, unsigned int);
-extern void x25_kill_by_neigh(struct x25_neigh *);
+int x25_parse_address_block(struct sk_buff *skb,
+			    struct x25_address *called_addr,
+			    struct x25_address *calling_addr);
+
+int x25_addr_ntoa(unsigned char *, struct x25_address *, struct x25_address *);
+int x25_addr_aton(unsigned char *, struct x25_address *, struct x25_address *);
+struct sock *x25_find_socket(unsigned int, struct x25_neigh *);
+void x25_destroy_socket_from_timer(struct sock *);
+int x25_rx_call_request(struct sk_buff *, struct x25_neigh *, unsigned int);
+void x25_kill_by_neigh(struct x25_neigh *);
 
 /* x25_dev.c */
-extern void x25_send_frame(struct sk_buff *, struct x25_neigh *);
-extern int  x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *);
-extern void x25_establish_link(struct x25_neigh *);
-extern void x25_terminate_link(struct x25_neigh *);
+void x25_send_frame(struct sk_buff *, struct x25_neigh *);
+int x25_lapb_receive_frame(struct sk_buff *, struct net_device *,
+			   struct packet_type *, struct net_device *);
+void x25_establish_link(struct x25_neigh *);
+void x25_terminate_link(struct x25_neigh *);
 
 /* x25_facilities.c */
-extern int x25_parse_facilities(struct sk_buff *, struct x25_facilities *,
-				struct x25_dte_facilities *, unsigned long *);
-extern int x25_create_facilities(unsigned char *, struct x25_facilities *,
-				struct x25_dte_facilities *, unsigned long);
-extern int x25_negotiate_facilities(struct sk_buff *, struct sock *,
-				struct x25_facilities *,
-				struct x25_dte_facilities *);
-extern void x25_limit_facilities(struct x25_facilities *, struct x25_neigh *);
+int x25_parse_facilities(struct sk_buff *, struct x25_facilities *,
+			 struct x25_dte_facilities *, unsigned long *);
+int x25_create_facilities(unsigned char *, struct x25_facilities *,
+			  struct x25_dte_facilities *, unsigned long);
+int x25_negotiate_facilities(struct sk_buff *, struct sock *,
+			     struct x25_facilities *,
+			     struct x25_dte_facilities *);
+void x25_limit_facilities(struct x25_facilities *, struct x25_neigh *);
 
 /* x25_forward.c */
-extern void x25_clear_forward_by_lci(unsigned int lci);
-extern void x25_clear_forward_by_dev(struct net_device *);
-extern int x25_forward_data(int, struct x25_neigh *, struct sk_buff *);
-extern int x25_forward_call(struct x25_address *, struct x25_neigh *,
-				struct sk_buff *, int);
+void x25_clear_forward_by_lci(unsigned int lci);
+void x25_clear_forward_by_dev(struct net_device *);
+int x25_forward_data(int, struct x25_neigh *, struct sk_buff *);
+int x25_forward_call(struct x25_address *, struct x25_neigh *, struct sk_buff *,
+		     int);
 
 /* x25_in.c */
-extern int  x25_process_rx_frame(struct sock *, struct sk_buff *);
-extern int  x25_backlog_rcv(struct sock *, struct sk_buff *);
+int x25_process_rx_frame(struct sock *, struct sk_buff *);
+int x25_backlog_rcv(struct sock *, struct sk_buff *);
 
 /* x25_link.c */
-extern void x25_link_control(struct sk_buff *, struct x25_neigh *, unsigned short);
-extern void x25_link_device_up(struct net_device *);
-extern void x25_link_device_down(struct net_device *);
-extern void x25_link_established(struct x25_neigh *);
-extern void x25_link_terminated(struct x25_neigh *);
-extern void x25_transmit_clear_request(struct x25_neigh *, unsigned int, unsigned char);
-extern void x25_transmit_link(struct sk_buff *, struct x25_neigh *);
-extern int  x25_subscr_ioctl(unsigned int, void __user *);
-extern struct x25_neigh *x25_get_neigh(struct net_device *);
-extern void x25_link_free(void);
+void x25_link_control(struct sk_buff *, struct x25_neigh *, unsigned short);
+void x25_link_device_up(struct net_device *);
+void x25_link_device_down(struct net_device *);
+void x25_link_established(struct x25_neigh *);
+void x25_link_terminated(struct x25_neigh *);
+void x25_transmit_clear_request(struct x25_neigh *, unsigned int,
+				unsigned char);
+void x25_transmit_link(struct sk_buff *, struct x25_neigh *);
+int x25_subscr_ioctl(unsigned int, void __user *);
+struct x25_neigh *x25_get_neigh(struct net_device *);
+void x25_link_free(void);
 
 /* x25_neigh.c */
 static __inline__ void x25_neigh_hold(struct x25_neigh *nb)
@@ -252,16 +252,16 @@ static __inline__ void x25_neigh_put(struct x25_neigh *nb)
 }
 
 /* x25_out.c */
-extern  int x25_output(struct sock *, struct sk_buff *);
-extern void x25_kick(struct sock *);
-extern void x25_enquiry_response(struct sock *);
+int x25_output(struct sock *, struct sk_buff *);
+void x25_kick(struct sock *);
+void x25_enquiry_response(struct sock *);
 
 /* x25_route.c */
-extern struct x25_route *x25_get_route(struct x25_address *addr);
-extern struct net_device *x25_dev_get(char *);
-extern void x25_route_device_down(struct net_device *dev);
-extern int  x25_route_ioctl(unsigned int, void __user *);
-extern void x25_route_free(void);
+struct x25_route *x25_get_route(struct x25_address *addr);
+struct net_device *x25_dev_get(char *);
+void x25_route_device_down(struct net_device *dev);
+int x25_route_ioctl(unsigned int, void __user *);
+void x25_route_free(void);
 
 static __inline__ void x25_route_hold(struct x25_route *rt)
 {
@@ -275,30 +275,31 @@ static __inline__ void x25_route_put(struct x25_route *rt)
 }
 
 /* x25_subr.c */
-extern void x25_clear_queues(struct sock *);
-extern void x25_frames_acked(struct sock *, unsigned short);
-extern void x25_requeue_frames(struct sock *);
-extern int  x25_validate_nr(struct sock *, unsigned short);
-extern void x25_write_internal(struct sock *, int);
-extern int  x25_decode(struct sock *, struct sk_buff *, int *, int *, int *, int *, int *);
-extern void x25_disconnect(struct sock *, int, unsigned char, unsigned char);
+void x25_clear_queues(struct sock *);
+void x25_frames_acked(struct sock *, unsigned short);
+void x25_requeue_frames(struct sock *);
+int x25_validate_nr(struct sock *, unsigned short);
+void x25_write_internal(struct sock *, int);
+int x25_decode(struct sock *, struct sk_buff *, int *, int *, int *, int *,
+	       int *);
+void x25_disconnect(struct sock *, int, unsigned char, unsigned char);
 
 /* x25_timer.c */
-extern void x25_init_timers(struct sock *sk);
-extern void x25_start_heartbeat(struct sock *);
-extern void x25_start_t2timer(struct sock *);
-extern void x25_start_t21timer(struct sock *);
-extern void x25_start_t22timer(struct sock *);
-extern void x25_start_t23timer(struct sock *);
-extern void x25_stop_heartbeat(struct sock *);
-extern void x25_stop_timer(struct sock *);
-extern unsigned long x25_display_timer(struct sock *);
-extern void x25_check_rbuf(struct sock *);
+void x25_init_timers(struct sock *sk);
+void x25_start_heartbeat(struct sock *);
+void x25_start_t2timer(struct sock *);
+void x25_start_t21timer(struct sock *);
+void x25_start_t22timer(struct sock *);
+void x25_start_t23timer(struct sock *);
+void x25_stop_heartbeat(struct sock *);
+void x25_stop_timer(struct sock *);
+unsigned long x25_display_timer(struct sock *);
+void x25_check_rbuf(struct sock *);
 
 /* sysctl_net_x25.c */
 #ifdef CONFIG_SYSCTL
-extern void x25_register_sysctl(void);
-extern void x25_unregister_sysctl(void);
+void x25_register_sysctl(void);
+void x25_unregister_sysctl(void);
 #else
 static inline void x25_register_sysctl(void) {};
 static inline void x25_unregister_sysctl(void) {};
@@ -318,6 +319,6 @@ extern rwlock_t x25_forward_list_lock;
 extern struct list_head x25_neigh_list;
 extern rwlock_t x25_neigh_list_lock;
 
-extern int x25_proc_init(void);
-extern void x25_proc_exit(void);
+int x25_proc_init(void);
+void x25_proc_exit(void);
 #endif
-- 
cgit 


From d511337a1eda35ac9d8e373e1cca17d6182a75b7 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:33:53 -0700
Subject: xfrm.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/xfrm.h | 375 +++++++++++++++++++++++++++--------------------------
 1 file changed, 190 insertions(+), 185 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index e253bf0cc7ef..765746192724 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -307,15 +307,17 @@ struct xfrm_policy_afinfo {
 	struct dst_entry	*(*blackhole_route)(struct net *net, struct dst_entry *orig);
 };
 
-extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
-extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
-extern void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c);
-extern void km_state_notify(struct xfrm_state *x, const struct km_event *c);
+int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo);
+int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo);
+void km_policy_notify(struct xfrm_policy *xp, int dir,
+		      const struct km_event *c);
+void km_state_notify(struct xfrm_state *x, const struct km_event *c);
 
 struct xfrm_tmpl;
-extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
-extern void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
-extern int __xfrm_state_delete(struct xfrm_state *x);
+int km_query(struct xfrm_state *x, struct xfrm_tmpl *t,
+	     struct xfrm_policy *pol);
+void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
+int __xfrm_state_delete(struct xfrm_state *x);
 
 struct xfrm_state_afinfo {
 	unsigned int		family;
@@ -344,12 +346,12 @@ struct xfrm_state_afinfo {
 	void			(*local_error)(struct sk_buff *skb, u32 mtu);
 };
 
-extern int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
-extern int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
-extern struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
-extern void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
+int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
+int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
+struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
+void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
 
-extern void xfrm_state_delete_tunnel(struct xfrm_state *x);
+void xfrm_state_delete_tunnel(struct xfrm_state *x);
 
 struct xfrm_type {
 	char			*description;
@@ -372,8 +374,8 @@ struct xfrm_type {
 	u32			(*get_mtu)(struct xfrm_state *, int size);
 };
 
-extern int xfrm_register_type(const struct xfrm_type *type, unsigned short family);
-extern int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family);
+int xfrm_register_type(const struct xfrm_type *type, unsigned short family);
+int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family);
 
 struct xfrm_mode {
 	/*
@@ -434,8 +436,8 @@ enum {
 	XFRM_MODE_FLAG_TUNNEL = 1,
 };
 
-extern int xfrm_register_mode(struct xfrm_mode *mode, int family);
-extern int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
+int xfrm_register_mode(struct xfrm_mode *mode, int family);
+int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
 
 static inline int xfrm_af2proto(unsigned int family)
 {
@@ -595,8 +597,8 @@ struct xfrm_mgr {
 					   const struct xfrm_kmaddress *k);
 };
 
-extern int xfrm_register_km(struct xfrm_mgr *km);
-extern int xfrm_unregister_km(struct xfrm_mgr *km);
+int xfrm_register_km(struct xfrm_mgr *km);
+int xfrm_unregister_km(struct xfrm_mgr *km);
 
 /*
  * This structure is used for the duration where packets are being
@@ -713,23 +715,23 @@ static inline void xfrm_audit_helper_usrinfo(kuid_t auid, u32 ses, u32 secid,
 		audit_log_task_context(audit_buf);
 }
 
-extern void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
-				  kuid_t auid, u32 ses, u32 secid);
-extern void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
-				  kuid_t auid, u32 ses, u32 secid);
-extern void xfrm_audit_state_add(struct xfrm_state *x, int result,
-				 kuid_t auid, u32 ses, u32 secid);
-extern void xfrm_audit_state_delete(struct xfrm_state *x, int result,
-				    kuid_t auid, u32 ses, u32 secid);
-extern void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
-					     struct sk_buff *skb);
-extern void xfrm_audit_state_replay(struct xfrm_state *x,
-				    struct sk_buff *skb, __be32 net_seq);
-extern void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family);
-extern void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family,
-				      __be32 net_spi, __be32 net_seq);
-extern void xfrm_audit_state_icvfail(struct xfrm_state *x,
-				     struct sk_buff *skb, u8 proto);
+void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, kuid_t auid,
+			   u32 ses, u32 secid);
+void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, kuid_t auid,
+			      u32 ses, u32 secid);
+void xfrm_audit_state_add(struct xfrm_state *x, int result, kuid_t auid,
+			  u32 ses, u32 secid);
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, kuid_t auid,
+			     u32 ses, u32 secid);
+void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
+				      struct sk_buff *skb);
+void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb,
+			     __be32 net_seq);
+void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family);
+void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi,
+			       __be32 net_seq);
+void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb,
+			      u8 proto);
 #else
 
 static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
@@ -784,7 +786,7 @@ static inline void xfrm_pol_hold(struct xfrm_policy *policy)
 		atomic_inc(&policy->refcnt);
 }
 
-extern void xfrm_policy_destroy(struct xfrm_policy *policy);
+void xfrm_policy_destroy(struct xfrm_policy *policy);
 
 static inline void xfrm_pol_put(struct xfrm_policy *policy)
 {
@@ -799,7 +801,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols)
 		xfrm_pol_put(pols[i]);
 }
 
-extern void __xfrm_state_destroy(struct xfrm_state *);
+void __xfrm_state_destroy(struct xfrm_state *);
 
 static inline void __xfrm_state_put(struct xfrm_state *x)
 {
@@ -903,9 +905,8 @@ __be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli)
 	return port;
 }
 
-extern bool xfrm_selector_match(const struct xfrm_selector *sel,
-				const struct flowi *fl,
-				unsigned short family);
+bool xfrm_selector_match(const struct xfrm_selector *sel,
+			 const struct flowi *fl, unsigned short family);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 /*	If neither has a context --> match
@@ -975,7 +976,7 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 }
 #endif
 
-extern void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
+void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
 
 struct sec_path {
 	atomic_t		refcnt;
@@ -1000,7 +1001,7 @@ secpath_get(struct sec_path *sp)
 	return sp;
 }
 
-extern void __secpath_destroy(struct sec_path *sp);
+void __secpath_destroy(struct sec_path *sp);
 
 static inline void
 secpath_put(struct sec_path *sp)
@@ -1009,7 +1010,7 @@ secpath_put(struct sec_path *sp)
 		__secpath_destroy(sp);
 }
 
-extern struct sec_path *secpath_dup(struct sec_path *src);
+struct sec_path *secpath_dup(struct sec_path *src);
 
 static inline void
 secpath_reset(struct sk_buff *skb)
@@ -1059,7 +1060,8 @@ xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, un
 }
 
 #ifdef CONFIG_XFRM
-extern int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family);
+int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb,
+			unsigned short family);
 
 static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 				       struct sk_buff *skb,
@@ -1103,8 +1105,8 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir,
 	return __xfrm_policy_check2(sk, dir, skb, AF_INET6, 1);
 }
 
-extern int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
-				 unsigned int family, int reverse);
+int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
+			  unsigned int family, int reverse);
 
 static inline int xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 				      unsigned int family)
@@ -1119,7 +1121,7 @@ static inline int xfrm_decode_session_reverse(struct sk_buff *skb,
 	return __xfrm_decode_session(skb, fl, family, 1);
 }
 
-extern int __xfrm_route_forward(struct sk_buff *skb, unsigned short family);
+int __xfrm_route_forward(struct sk_buff *skb, unsigned short family);
 
 static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 {
@@ -1140,7 +1142,7 @@ static inline int xfrm6_route_forward(struct sk_buff *skb)
 	return xfrm_route_forward(skb, AF_INET6);
 }
 
-extern int __xfrm_sk_clone_policy(struct sock *sk);
+int __xfrm_sk_clone_policy(struct sock *sk);
 
 static inline int xfrm_sk_clone_policy(struct sock *sk)
 {
@@ -1149,7 +1151,7 @@ static inline int xfrm_sk_clone_policy(struct sock *sk)
 	return 0;
 }
 
-extern int xfrm_policy_delete(struct xfrm_policy *pol, int dir);
+int xfrm_policy_delete(struct xfrm_policy *pol, int dir);
 
 static inline void xfrm_sk_free_policy(struct sock *sk)
 {
@@ -1163,7 +1165,7 @@ static inline void xfrm_sk_free_policy(struct sock *sk)
 	}
 }
 
-extern void xfrm_garbage_collect(struct net *net);
+void xfrm_garbage_collect(struct net *net);
 
 #else
 
@@ -1363,16 +1365,16 @@ struct xfrm6_tunnel {
 	int priority;
 };
 
-extern void xfrm_init(void);
-extern void xfrm4_init(void);
-extern int xfrm_state_init(struct net *net);
-extern void xfrm_state_fini(struct net *net);
-extern void xfrm4_state_init(void);
+void xfrm_init(void);
+void xfrm4_init(void);
+int xfrm_state_init(struct net *net);
+void xfrm_state_fini(struct net *net);
+void xfrm4_state_init(void);
 #ifdef CONFIG_XFRM
-extern int xfrm6_init(void);
-extern void xfrm6_fini(void);
-extern int xfrm6_state_init(void);
-extern void xfrm6_state_fini(void);
+int xfrm6_init(void);
+void xfrm6_fini(void);
+int xfrm6_state_init(void);
+void xfrm6_state_fini(void);
 #else
 static inline int xfrm6_init(void)
 {
@@ -1385,52 +1387,52 @@ static inline void xfrm6_fini(void)
 #endif
 
 #ifdef CONFIG_XFRM_STATISTICS
-extern int xfrm_proc_init(struct net *net);
-extern void xfrm_proc_fini(struct net *net);
+int xfrm_proc_init(struct net *net);
+void xfrm_proc_fini(struct net *net);
 #endif
 
-extern int xfrm_sysctl_init(struct net *net);
+int xfrm_sysctl_init(struct net *net);
 #ifdef CONFIG_SYSCTL
-extern void xfrm_sysctl_fini(struct net *net);
+void xfrm_sysctl_fini(struct net *net);
 #else
 static inline void xfrm_sysctl_fini(struct net *net)
 {
 }
 #endif
 
-extern void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
-extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
-			   int (*func)(struct xfrm_state *, int, void*), void *);
-extern void xfrm_state_walk_done(struct xfrm_state_walk *walk);
-extern struct xfrm_state *xfrm_state_alloc(struct net *net);
-extern struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
-					  const xfrm_address_t *saddr,
-					  const struct flowi *fl,
-					  struct xfrm_tmpl *tmpl,
-					  struct xfrm_policy *pol, int *err,
-					  unsigned short family);
-extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
-					       xfrm_address_t *daddr,
-					       xfrm_address_t *saddr,
-					       unsigned short family,
-					       u8 mode, u8 proto, u32 reqid);
-extern int xfrm_state_check_expire(struct xfrm_state *x);
-extern void xfrm_state_insert(struct xfrm_state *x);
-extern int xfrm_state_add(struct xfrm_state *x);
-extern int xfrm_state_update(struct xfrm_state *x);
-extern struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark,
-					    const xfrm_address_t *daddr, __be32 spi,
-					    u8 proto, unsigned short family);
-extern struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
-						   const xfrm_address_t *daddr,
-						   const xfrm_address_t *saddr,
-						   u8 proto,
-						   unsigned short family);
+void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto);
+int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk,
+		    int (*func)(struct xfrm_state *, int, void*), void *);
+void xfrm_state_walk_done(struct xfrm_state_walk *walk);
+struct xfrm_state *xfrm_state_alloc(struct net *net);
+struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
+				   const xfrm_address_t *saddr,
+				   const struct flowi *fl,
+				   struct xfrm_tmpl *tmpl,
+				   struct xfrm_policy *pol, int *err,
+				   unsigned short family);
+struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
+				       xfrm_address_t *daddr,
+				       xfrm_address_t *saddr,
+				       unsigned short family,
+				       u8 mode, u8 proto, u32 reqid);
+int xfrm_state_check_expire(struct xfrm_state *x);
+void xfrm_state_insert(struct xfrm_state *x);
+int xfrm_state_add(struct xfrm_state *x);
+int xfrm_state_update(struct xfrm_state *x);
+struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark,
+				     const xfrm_address_t *daddr, __be32 spi,
+				     u8 proto, unsigned short family);
+struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+					    const xfrm_address_t *daddr,
+					    const xfrm_address_t *saddr,
+					    u8 proto,
+					    unsigned short family);
 #ifdef CONFIG_XFRM_SUB_POLICY
-extern int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
-			  int n, unsigned short family);
-extern int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src,
-			   int n, unsigned short family);
+int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
+		   unsigned short family);
+int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
+		    unsigned short family);
 #else
 static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
 				 int n, unsigned short family)
@@ -1462,68 +1464,68 @@ struct xfrmk_spdinfo {
 	u32 spdhmcnt;
 };
 
-extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark,
-					      u32 seq);
-extern int xfrm_state_delete(struct xfrm_state *x);
-extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
-extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
-extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
-extern u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
-extern int xfrm_init_replay(struct xfrm_state *x);
-extern int xfrm_state_mtu(struct xfrm_state *x, int mtu);
-extern int __xfrm_init_state(struct xfrm_state *x, bool init_replay);
-extern int xfrm_init_state(struct xfrm_state *x);
-extern int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi,
-		      int encap_type);
-extern int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
-extern int xfrm_output_resume(struct sk_buff *skb, int err);
-extern int xfrm_output(struct sk_buff *skb);
-extern int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-extern void xfrm_local_error(struct sk_buff *skb, int mtu);
-extern int xfrm4_extract_header(struct sk_buff *skb);
-extern int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
-			   int encap_type);
-extern int xfrm4_transport_finish(struct sk_buff *skb, int async);
-extern int xfrm4_rcv(struct sk_buff *skb);
+struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
+int xfrm_state_delete(struct xfrm_state *x);
+int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
+void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
+void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
+u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
+int xfrm_init_replay(struct xfrm_state *x);
+int xfrm_state_mtu(struct xfrm_state *x, int mtu);
+int __xfrm_init_state(struct xfrm_state *x, bool init_replay);
+int xfrm_init_state(struct xfrm_state *x);
+int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
+int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
+int xfrm_output_resume(struct sk_buff *skb, int err);
+int xfrm_output(struct sk_buff *skb);
+int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+void xfrm_local_error(struct sk_buff *skb, int mtu);
+int xfrm4_extract_header(struct sk_buff *skb);
+int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
+		    int encap_type);
+int xfrm4_transport_finish(struct sk_buff *skb, int async);
+int xfrm4_rcv(struct sk_buff *skb);
 
 static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 {
 	return xfrm4_rcv_encap(skb, nexthdr, spi, 0);
 }
 
-extern int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm4_output(struct sk_buff *skb);
-extern int xfrm4_output_finish(struct sk_buff *skb);
-extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
-extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
-extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler);
-extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler);
-extern void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
-extern int xfrm6_extract_header(struct sk_buff *skb);
-extern int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
-extern int xfrm6_transport_finish(struct sk_buff *skb, int async);
-extern int xfrm6_rcv(struct sk_buff *skb);
-extern int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
-			    xfrm_address_t *saddr, u8 proto);
-extern int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
-extern int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family);
-extern __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
-extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
-extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
-extern int xfrm6_output(struct sk_buff *skb);
-extern int xfrm6_output_finish(struct sk_buff *skb);
-extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
-				 u8 **prevhdr);
-extern void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
+int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm4_output(struct sk_buff *skb);
+int xfrm4_output_finish(struct sk_buff *skb);
+int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
+int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
+int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler);
+int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler);
+void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
+int xfrm6_extract_header(struct sk_buff *skb);
+int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
+int xfrm6_transport_finish(struct sk_buff *skb, int async);
+int xfrm6_rcv(struct sk_buff *skb);
+int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
+		     xfrm_address_t *saddr, u8 proto);
+int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
+int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler,
+			    unsigned short family);
+__be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
+__be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
+int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm6_output(struct sk_buff *skb);
+int xfrm6_output_finish(struct sk_buff *skb);
+int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
+			  u8 **prevhdr);
+void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
 
 #ifdef CONFIG_XFRM
-extern int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb);
-extern int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen);
+int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb);
+int xfrm_user_policy(struct sock *sk, int optname,
+		     u8 __user *optval, int optlen);
 #else
 static inline int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
@@ -1540,59 +1542,62 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
 
 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
 
-extern void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type);
-extern int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
-	int (*func)(struct xfrm_policy *, int, int, void*), void *);
-extern void xfrm_policy_walk_done(struct xfrm_policy_walk *walk);
+void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type);
+int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
+		     int (*func)(struct xfrm_policy *, int, int, void*),
+		     void *);
+void xfrm_policy_walk_done(struct xfrm_policy_walk *walk);
 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
 struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
 					  u8 type, int dir,
 					  struct xfrm_selector *sel,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err);
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, u32 id, int delete, int *err);
+struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir,
+				     u32 id, int delete, int *err);
 int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info);
 u32 xfrm_get_acqseq(void);
-extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
+int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
 struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark,
 				 u8 mode, u32 reqid, u8 proto,
 				 const xfrm_address_t *daddr,
 				 const xfrm_address_t *saddr, int create,
 				 unsigned short family);
-extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
+int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
 
 #ifdef CONFIG_XFRM_MIGRATE
-extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
-		      const struct xfrm_migrate *m, int num_bundles,
-		      const struct xfrm_kmaddress *k);
-extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m);
-extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x,
-					      struct xfrm_migrate *m);
-extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
-			struct xfrm_migrate *m, int num_bundles,
-			struct xfrm_kmaddress *k);
+int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+	       const struct xfrm_migrate *m, int num_bundles,
+	       const struct xfrm_kmaddress *k);
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m);
+struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
+				      struct xfrm_migrate *m);
+int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
+		 struct xfrm_migrate *m, int num_bundles,
+		 struct xfrm_kmaddress *k);
 #endif
 
-extern int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
-extern void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid);
-extern int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr);
-
-extern void xfrm_input_init(void);
-extern int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq);
-
-extern void xfrm_probe_algs(void);
-extern int xfrm_count_pfkey_auth_supported(void);
-extern int xfrm_count_pfkey_enc_supported(void);
-extern struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx);
-extern struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx);
-extern struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id);
-extern struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id);
-extern struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id);
-extern struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe);
-extern struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len,
-						   int probe);
+int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport);
+void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid);
+int km_report(struct net *net, u8 proto, struct xfrm_selector *sel,
+	      xfrm_address_t *addr);
+
+void xfrm_input_init(void);
+int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq);
+
+void xfrm_probe_algs(void);
+int xfrm_count_pfkey_auth_supported(void);
+int xfrm_count_pfkey_enc_supported(void);
+struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx);
+struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx);
+struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id);
+struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id);
+struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id);
+struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe);
+struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe);
+struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe);
+struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len,
+					    int probe);
 
 static inline bool xfrm6_addr_equal(const xfrm_address_t *a,
 				    const xfrm_address_t *b)
-- 
cgit 


From e74e58f8d2015ac6b4e7a65c0acde8a499d46574 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:37:36 -0700
Subject: bluetooth: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/bluetooth/bluetooth.h | 16 ++++++++--------
 include/net/bluetooth/hci_core.h  | 23 +++++++++++------------
 include/net/bluetooth/rfcomm.h    |  4 ++--
 3 files changed, 21 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 10d43d8c7037..13d6c3929759 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -331,16 +331,16 @@ out:
 
 int bt_to_errno(__u16 code);
 
-extern int hci_sock_init(void);
-extern void hci_sock_cleanup(void);
+int hci_sock_init(void);
+void hci_sock_cleanup(void);
 
-extern int bt_sysfs_init(void);
-extern void bt_sysfs_cleanup(void);
+int bt_sysfs_init(void);
+void bt_sysfs_cleanup(void);
 
-extern int  bt_procfs_init(struct net *net, const char *name,
-			   struct bt_sock_list* sk_list,
-			   int (* seq_show)(struct seq_file *, void *));
-extern void bt_procfs_cleanup(struct net *net, const char *name);
+int bt_procfs_init(struct net *net, const char *name,
+		   struct bt_sock_list *sk_list,
+		   int (*seq_show)(struct seq_file *, void *));
+void bt_procfs_cleanup(struct net *net, const char *name);
 
 extern struct dentry *bt_debugfs;
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3ede820d328f..5769061e6533 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -367,18 +367,17 @@ extern rwlock_t hci_dev_list_lock;
 extern rwlock_t hci_cb_list_lock;
 
 /* ----- HCI interface to upper protocols ----- */
-extern int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr);
-extern void l2cap_connect_cfm(struct hci_conn *hcon, u8 status);
-extern int l2cap_disconn_ind(struct hci_conn *hcon);
-extern void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason);
-extern int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt);
-extern int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb,
-			      u16 flags);
-
-extern int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags);
-extern void sco_connect_cfm(struct hci_conn *hcon, __u8 status);
-extern void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason);
-extern int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb);
+int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr);
+void l2cap_connect_cfm(struct hci_conn *hcon, u8 status);
+int l2cap_disconn_ind(struct hci_conn *hcon);
+void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason);
+int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt);
+int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags);
+
+int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags);
+void sco_connect_cfm(struct hci_conn *hcon, __u8 status);
+void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason);
+int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb);
 
 /* ----- Inquiry cache ----- */
 #define INQUIRY_CACHE_AGE_MAX   (HZ*30)   /* 30 seconds */
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 7afd4199d6b6..b7f43e76a5c5 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -256,8 +256,8 @@ static inline void rfcomm_dlc_put(struct rfcomm_dlc *d)
 		rfcomm_dlc_free(d);
 }
 
-extern void __rfcomm_dlc_throttle(struct rfcomm_dlc *d);
-extern void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d);
+void __rfcomm_dlc_throttle(struct rfcomm_dlc *d);
+void __rfcomm_dlc_unthrottle(struct rfcomm_dlc *d);
 
 static inline void rfcomm_dlc_throttle(struct rfcomm_dlc *d)
 {
-- 
cgit 


From a22b8f4b57af5a4bdda2039d82845285b2a2b7ec Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:37:40 -0700
Subject: caif_hsi.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/caif/caif_hsi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/caif/caif_hsi.h b/include/net/caif/caif_hsi.h
index 4795e817afe5..097f69cfaa75 100644
--- a/include/net/caif/caif_hsi.h
+++ b/include/net/caif/caif_hsi.h
@@ -195,6 +195,6 @@ enum ifla_caif_hsi {
 	__IFLA_CAIF_HSI_MAX
 };
 
-extern struct cfhsi_ops *cfhsi_get_ops(void);
+struct cfhsi_ops *cfhsi_get_ops(void);
 
 #endif		/* CAIF_HSI_H_ */
-- 
cgit 


From 0e418f94d3fcdc79c88841f3338e768e1b0966a1 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:37:44 -0700
Subject: irda: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/irda/ircomm_tty.h  | 14 +++++++-------
 include/net/irda/irda.h        | 21 ++++++++++-----------
 include/net/irda/irlap_event.h |  2 +-
 include/net/irda/irlap_frame.h |  4 ++--
 4 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/irda/ircomm_tty.h b/include/net/irda/ircomm_tty.h
index 80ffde3bb164..0224402260a7 100644
--- a/include/net/irda/ircomm_tty.h
+++ b/include/net/irda/ircomm_tty.h
@@ -105,13 +105,13 @@ struct ircomm_tty_cb {
 void ircomm_tty_start(struct tty_struct *tty);
 void ircomm_tty_check_modem_status(struct ircomm_tty_cb *self);
 
-extern int ircomm_tty_tiocmget(struct tty_struct *tty);
-extern int ircomm_tty_tiocmset(struct tty_struct *tty,
-			       unsigned int set, unsigned int clear);
-extern int ircomm_tty_ioctl(struct tty_struct *tty, 
-			    unsigned int cmd, unsigned long arg);
-extern void ircomm_tty_set_termios(struct tty_struct *tty, 
-				   struct ktermios *old_termios);
+int ircomm_tty_tiocmget(struct tty_struct *tty);
+int ircomm_tty_tiocmset(struct tty_struct *tty, unsigned int set,
+			unsigned int clear);
+int ircomm_tty_ioctl(struct tty_struct *tty, unsigned int cmd,
+		     unsigned long arg);
+void ircomm_tty_set_termios(struct tty_struct *tty,
+			    struct ktermios *old_termios);
 
 #endif
 
diff --git a/include/net/irda/irda.h b/include/net/irda/irda.h
index 3bed61d379a8..a059465101ff 100644
--- a/include/net/irda/irda.h
+++ b/include/net/irda/irda.h
@@ -112,20 +112,19 @@ do { if(!(expr)) { \
 struct net_device;
 struct packet_type;
 
-extern void irda_proc_register(void);
-extern void irda_proc_unregister(void);
+void irda_proc_register(void);
+void irda_proc_unregister(void);
 
-extern int irda_sysctl_register(void);
-extern void irda_sysctl_unregister(void);
+int irda_sysctl_register(void);
+void irda_sysctl_unregister(void);
 
-extern int irsock_init(void);
-extern void irsock_cleanup(void);
+int irsock_init(void);
+void irsock_cleanup(void);
 
-extern int irda_nl_register(void);
-extern void irda_nl_unregister(void);
+int irda_nl_register(void);
+void irda_nl_unregister(void);
 
-extern int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
-			    struct packet_type *ptype,
-			    struct net_device *orig_dev);
+int irlap_driver_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *ptype, struct net_device *orig_dev);
 
 #endif /* NET_IRDA_H */
diff --git a/include/net/irda/irlap_event.h b/include/net/irda/irlap_event.h
index 4c90824c50fb..f9d88da97af2 100644
--- a/include/net/irda/irlap_event.h
+++ b/include/net/irda/irlap_event.h
@@ -126,6 +126,6 @@ void irlap_do_event(struct irlap_cb *self, IRLAP_EVENT event,
 		    struct sk_buff *skb, struct irlap_info *info);
 void irlap_print_event(IRLAP_EVENT event);
 
-extern int irlap_qos_negotiate(struct irlap_cb *self, struct sk_buff *skb);
+int irlap_qos_negotiate(struct irlap_cb *self, struct sk_buff *skb);
 
 #endif
diff --git a/include/net/irda/irlap_frame.h b/include/net/irda/irlap_frame.h
index 6b1dc4f8eca5..57173ae398ae 100644
--- a/include/net/irda/irlap_frame.h
+++ b/include/net/irda/irlap_frame.h
@@ -163,7 +163,7 @@ void irlap_resend_rejected_frame(struct irlap_cb *self, int command);
 void irlap_send_ui_frame(struct irlap_cb *self, struct sk_buff *skb,
 			 __u8 caddr, int command);
 
-extern int irlap_insert_qos_negotiation_params(struct irlap_cb *self, 
-					       struct sk_buff *skb);
+int irlap_insert_qos_negotiation_params(struct irlap_cb *self,
+					struct sk_buff *skb);
 
 #endif
-- 
cgit 


From 4e77be4637641c92468dd5de39cba774bed7d6ba Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:37:48 -0700
Subject: netfilter: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/ipv4/nf_conntrack_ipv4.h |  6 +--
 include/net/netfilter/ipv4/nf_defrag_ipv4.h    |  2 +-
 include/net/netfilter/ipv6/nf_defrag_ipv6.h    | 17 +++----
 include/net/netfilter/nf_conntrack.h           | 69 +++++++++++---------------
 include/net/netfilter/nf_conntrack_acct.h      | 12 ++---
 include/net/netfilter/nf_conntrack_core.h      | 69 ++++++++++++--------------
 include/net/netfilter/nf_conntrack_ecache.h    | 22 ++++----
 include/net/netfilter/nf_conntrack_extend.h    |  2 +-
 include/net/netfilter/nf_conntrack_helper.h    | 40 ++++++++-------
 include/net/netfilter/nf_conntrack_l3proto.h   | 16 +++---
 include/net/netfilter/nf_conntrack_l4proto.h   | 32 ++++++------
 include/net/netfilter/nf_conntrack_seqadj.h    | 30 +++++------
 include/net/netfilter/nf_conntrack_synproxy.h  | 28 +++++------
 include/net/netfilter/nf_conntrack_timeout.h   |  4 +-
 include/net/netfilter/nf_conntrack_timestamp.h |  8 +--
 include/net/netfilter/nf_nat.h                 | 10 ++--
 include/net/netfilter/nf_nat_core.h            |  8 ++-
 include/net/netfilter/nf_nat_helper.h          | 29 ++++-------
 include/net/netfilter/nf_nat_l3proto.h         | 23 ++++-----
 include/net/netfilter/nf_nat_l4proto.h         | 30 +++++------
 include/net/netfilter/nf_queue.h               |  2 +-
 include/net/netfilter/xt_rateest.h             |  4 +-
 22 files changed, 217 insertions(+), 246 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index 7573d52a4346..6c3d12e2949f 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -16,9 +16,9 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
 extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
 
-extern int nf_conntrack_ipv4_compat_init(void);
-extern void nf_conntrack_ipv4_compat_fini(void);
+int nf_conntrack_ipv4_compat_init(void);
+void nf_conntrack_ipv4_compat_fini(void);
 
-extern void need_ipv4_conntrack(void);
+void need_ipv4_conntrack(void);
 
 #endif /*_NF_CONNTRACK_IPV4_H*/
diff --git a/include/net/netfilter/ipv4/nf_defrag_ipv4.h b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
index 6b00ea38546b..f01ef208dff6 100644
--- a/include/net/netfilter/ipv4/nf_defrag_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_defrag_ipv4.h
@@ -1,6 +1,6 @@
 #ifndef _NF_DEFRAG_IPV4_H
 #define _NF_DEFRAG_IPV4_H
 
-extern void nf_defrag_ipv4_enable(void);
+void nf_defrag_ipv4_enable(void);
 
 #endif /* _NF_DEFRAG_IPV4_H */
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index fd79c9a1779d..5613412e7dc2 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -1,15 +1,14 @@
 #ifndef _NF_DEFRAG_IPV6_H
 #define _NF_DEFRAG_IPV6_H
 
-extern void nf_defrag_ipv6_enable(void);
-
-extern int nf_ct_frag6_init(void);
-extern void nf_ct_frag6_cleanup(void);
-extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			       struct net_device *in,
-			       struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
+void nf_defrag_ipv6_enable(void);
+
+int nf_ct_frag6_init(void);
+void nf_ct_frag6_cleanup(void);
+struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
+void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
+			struct net_device *in, struct net_device *out,
+			int (*okfn)(struct sk_buff *));
 
 struct inet_frags_ctl;
 
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 0c1288a50e8b..01ea6eed1bb1 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -139,15 +139,13 @@ static inline struct net *nf_ct_net(const struct nf_conn *ct)
 }
 
 /* Alter reply tuple (maybe alter helper). */
-extern void
-nf_conntrack_alter_reply(struct nf_conn *ct,
-			 const struct nf_conntrack_tuple *newreply);
+void nf_conntrack_alter_reply(struct nf_conn *ct,
+			      const struct nf_conntrack_tuple *newreply);
 
 /* Is this tuple taken? (ignoring any belonging to the given
    conntrack). */
-extern int
-nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
-			 const struct nf_conn *ignored_conntrack);
+int nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
+			     const struct nf_conn *ignored_conntrack);
 
 /* Return conntrack_info and tuple hash for given skb. */
 static inline struct nf_conn *
@@ -165,37 +163,34 @@ static inline void nf_ct_put(struct nf_conn *ct)
 }
 
 /* Protocol module loading */
-extern int nf_ct_l3proto_try_module_get(unsigned short l3proto);
-extern void nf_ct_l3proto_module_put(unsigned short l3proto);
+int nf_ct_l3proto_try_module_get(unsigned short l3proto);
+void nf_ct_l3proto_module_put(unsigned short l3proto);
 
 /*
  * Allocate a hashtable of hlist_head (if nulls == 0),
  * or hlist_nulls_head (if nulls == 1)
  */
-extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
 
-extern void nf_ct_free_hashtable(void *hash, unsigned int size);
+void nf_ct_free_hashtable(void *hash, unsigned int size);
 
-extern struct nf_conntrack_tuple_hash *
+struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, u16 zone,
 		    const struct nf_conntrack_tuple *tuple);
 
-extern int nf_conntrack_hash_check_insert(struct nf_conn *ct);
+int nf_conntrack_hash_check_insert(struct nf_conn *ct);
 bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report);
 
-extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
+void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
 
-extern bool nf_ct_get_tuplepr(const struct sk_buff *skb,
-			      unsigned int nhoff, u_int16_t l3num,
-			      struct nf_conntrack_tuple *tuple);
-extern bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
-				 const struct nf_conntrack_tuple *orig);
+bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
+		       u_int16_t l3num, struct nf_conntrack_tuple *tuple);
+bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
+			  const struct nf_conntrack_tuple *orig);
 
-extern void __nf_ct_refresh_acct(struct nf_conn *ct,
-				 enum ip_conntrack_info ctinfo,
-				 const struct sk_buff *skb,
-				 unsigned long extra_jiffies,
-				 int do_acct);
+void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			  const struct sk_buff *skb,
+			  unsigned long extra_jiffies, int do_acct);
 
 /* Refresh conntrack for this many jiffies and do accounting */
 static inline void nf_ct_refresh_acct(struct nf_conn *ct,
@@ -214,10 +209,8 @@ static inline void nf_ct_refresh(struct nf_conn *ct,
 	__nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, 0);
 }
 
-extern bool __nf_ct_kill_acct(struct nf_conn *ct,
-			      enum ip_conntrack_info ctinfo,
-			      const struct sk_buff *skb,
-			      int do_acct);
+bool __nf_ct_kill_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+		       const struct sk_buff *skb, int do_acct);
 
 /* kill conntrack and do accounting */
 static inline bool nf_ct_kill_acct(struct nf_conn *ct,
@@ -244,19 +237,17 @@ static inline struct nf_conn *nf_ct_untracked_get(void)
 {
 	return &__raw_get_cpu_var(nf_conntrack_untracked);
 }
-extern void nf_ct_untracked_status_or(unsigned long bits);
+void nf_ct_untracked_status_or(unsigned long bits);
 
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
-extern void
-nf_ct_iterate_cleanup(struct net *net,
-		      int (*iter)(struct nf_conn *i, void *data),
-		      void *data, u32 portid, int report);
-extern void nf_conntrack_free(struct nf_conn *ct);
-extern struct nf_conn *
-nf_conntrack_alloc(struct net *net, u16 zone,
-		   const struct nf_conntrack_tuple *orig,
-		   const struct nf_conntrack_tuple *repl,
-		   gfp_t gfp);
+void nf_ct_iterate_cleanup(struct net *net,
+			   int (*iter)(struct nf_conn *i, void *data),
+			   void *data, u32 portid, int report);
+void nf_conntrack_free(struct nf_conn *ct);
+struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
+				   const struct nf_conntrack_tuple *orig,
+				   const struct nf_conntrack_tuple *repl,
+				   gfp_t gfp);
 
 static inline int nf_ct_is_template(const struct nf_conn *ct)
 {
@@ -287,7 +278,7 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 
 struct kernel_param;
 
-extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
+int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
 extern unsigned int nf_conntrack_htable_size;
 extern unsigned int nf_conntrack_max;
 extern unsigned int nf_conntrack_hash_rnd;
diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index 2bdb7a15fe06..fef44edf49c1 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -42,8 +42,8 @@ struct nf_conn_counter *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
 	return acct;
 };
 
-extern unsigned int
-seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir);
+unsigned int seq_print_acct(struct seq_file *s, const struct nf_conn *ct,
+			    int dir);
 
 /* Check if connection tracking accounting is enabled */
 static inline bool nf_ct_acct_enabled(struct net *net)
@@ -57,9 +57,9 @@ static inline void nf_ct_set_acct(struct net *net, bool enable)
 	net->ct.sysctl_acct = enable;
 }
 
-extern int nf_conntrack_acct_pernet_init(struct net *net);
-extern void nf_conntrack_acct_pernet_fini(struct net *net);
+int nf_conntrack_acct_pernet_init(struct net *net);
+void nf_conntrack_acct_pernet_fini(struct net *net);
 
-extern int nf_conntrack_acct_init(void);
-extern void nf_conntrack_acct_fini(void);
+int nf_conntrack_acct_init(void);
+void nf_conntrack_acct_fini(void);
 #endif /* _NF_CONNTRACK_ACCT_H */
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index fb2b6234e937..15308b8eb5b5 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -20,49 +20,42 @@
 /* This header is used to share core functionality between the
    standalone connection tracking module, and the compatibility layer's use
    of connection tracking. */
-extern unsigned int nf_conntrack_in(struct net *net,
-				    u_int8_t pf,
-				    unsigned int hooknum,
-				    struct sk_buff *skb);
-
-extern int nf_conntrack_init_net(struct net *net);
-extern void nf_conntrack_cleanup_net(struct net *net);
-extern void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
-
-extern int nf_conntrack_proto_pernet_init(struct net *net);
-extern void nf_conntrack_proto_pernet_fini(struct net *net);
-
-extern int nf_conntrack_proto_init(void);
-extern void nf_conntrack_proto_fini(void);
-
-extern int nf_conntrack_init_start(void);
-extern void nf_conntrack_cleanup_start(void);
-
-extern void nf_conntrack_init_end(void);
-extern void nf_conntrack_cleanup_end(void);
-
-extern bool
-nf_ct_get_tuple(const struct sk_buff *skb,
-		unsigned int nhoff,
-		unsigned int dataoff,
-		u_int16_t l3num,
-		u_int8_t protonum,
-		struct nf_conntrack_tuple *tuple,
-		const struct nf_conntrack_l3proto *l3proto,
-		const struct nf_conntrack_l4proto *l4proto);
-
-extern bool
-nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
-		   const struct nf_conntrack_tuple *orig,
-		   const struct nf_conntrack_l3proto *l3proto,
-		   const struct nf_conntrack_l4proto *l4proto);
+unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
+			     struct sk_buff *skb);
+
+int nf_conntrack_init_net(struct net *net);
+void nf_conntrack_cleanup_net(struct net *net);
+void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
+
+int nf_conntrack_proto_pernet_init(struct net *net);
+void nf_conntrack_proto_pernet_fini(struct net *net);
+
+int nf_conntrack_proto_init(void);
+void nf_conntrack_proto_fini(void);
+
+int nf_conntrack_init_start(void);
+void nf_conntrack_cleanup_start(void);
+
+void nf_conntrack_init_end(void);
+void nf_conntrack_cleanup_end(void);
+
+bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff,
+		     unsigned int dataoff, u_int16_t l3num, u_int8_t protonum,
+		     struct nf_conntrack_tuple *tuple,
+		     const struct nf_conntrack_l3proto *l3proto,
+		     const struct nf_conntrack_l4proto *l4proto);
+
+bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
+			const struct nf_conntrack_tuple *orig,
+			const struct nf_conntrack_l3proto *l3proto,
+			const struct nf_conntrack_l4proto *l4proto);
 
 /* Find a connection corresponding to a tuple. */
-extern struct nf_conntrack_tuple_hash *
+struct nf_conntrack_tuple_hash *
 nf_conntrack_find_get(struct net *net, u16 zone,
 		      const struct nf_conntrack_tuple *tuple);
 
-extern int __nf_conntrack_confirm(struct sk_buff *skb);
+int __nf_conntrack_confirm(struct sk_buff *skb);
 
 /* Confirm a connection: returns NF_DROP if packet must be dropped. */
 static inline int nf_conntrack_confirm(struct sk_buff *skb)
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 092dc651689f..0e3d08e4b1d3 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -68,10 +68,12 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb);
-extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb);
+int nf_conntrack_register_notifier(struct net *net,
+				   struct nf_ct_event_notifier *nb);
+void nf_conntrack_unregister_notifier(struct net *net,
+				      struct nf_ct_event_notifier *nb);
 
-extern void nf_ct_deliver_cached_events(struct nf_conn *ct);
+void nf_ct_deliver_cached_events(struct nf_conn *ct);
 
 static inline void
 nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
@@ -166,8 +168,10 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb);
-extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb);
+int nf_ct_expect_register_notifier(struct net *net,
+				   struct nf_exp_event_notifier *nb);
+void nf_ct_expect_unregister_notifier(struct net *net,
+				      struct nf_exp_event_notifier *nb);
 
 static inline void
 nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
@@ -207,11 +211,11 @@ nf_ct_expect_event(enum ip_conntrack_expect_events event,
 	nf_ct_expect_event_report(event, exp, 0, 0);
 }
 
-extern int nf_conntrack_ecache_pernet_init(struct net *net);
-extern void nf_conntrack_ecache_pernet_fini(struct net *net);
+int nf_conntrack_ecache_pernet_init(struct net *net);
+void nf_conntrack_ecache_pernet_fini(struct net *net);
 
-extern int nf_conntrack_ecache_init(void);
-extern void nf_conntrack_ecache_fini(void);
+int nf_conntrack_ecache_init(void);
+void nf_conntrack_ecache_fini(void);
 #else /* CONFIG_NF_CONNTRACK_EVENTS */
 
 static inline void nf_conntrack_event_cache(enum ip_conntrack_events event,
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 88a1d4060d52..86372ae0ee84 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -73,7 +73,7 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
 	((id##_TYPE *)__nf_ct_ext_find((ext), (id)))
 
 /* Destroy all relationships */
-extern void __nf_ct_ext_destroy(struct nf_conn *ct);
+void __nf_ct_ext_destroy(struct nf_conn *ct);
 static inline void nf_ct_ext_destroy(struct nf_conn *ct)
 {
 	if (ct->ext)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 26c4ae5bfbb8..6cf614bc0029 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -52,21 +52,24 @@ struct nf_conntrack_helper {
 	unsigned int queue_num;		/* For user-space helpers. */
 };
 
-extern struct nf_conntrack_helper *
-__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum);
+struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name,
+						       u16 l3num, u8 protonum);
 
-extern struct nf_conntrack_helper *
-nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum);
+struct nf_conntrack_helper *nf_conntrack_helper_try_module_get(const char *name,
+							       u16 l3num,
+							       u8 protonum);
 
-extern int nf_conntrack_helper_register(struct nf_conntrack_helper *);
-extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
+int nf_conntrack_helper_register(struct nf_conntrack_helper *);
+void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
 
-extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp);
+struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct,
+					  struct nf_conntrack_helper *helper,
+					  gfp_t gfp);
 
-extern int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
-				     gfp_t flags);
+int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
+			      gfp_t flags);
 
-extern void nf_ct_helper_destroy(struct nf_conn *ct);
+void nf_ct_helper_destroy(struct nf_conn *ct);
 
 static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct)
 {
@@ -82,17 +85,16 @@ static inline void *nfct_help_data(const struct nf_conn *ct)
 	return (void *)help->data;
 }
 
-extern int nf_conntrack_helper_pernet_init(struct net *net);
-extern void nf_conntrack_helper_pernet_fini(struct net *net);
+int nf_conntrack_helper_pernet_init(struct net *net);
+void nf_conntrack_helper_pernet_fini(struct net *net);
 
-extern int nf_conntrack_helper_init(void);
-extern void nf_conntrack_helper_fini(void);
+int nf_conntrack_helper_init(void);
+void nf_conntrack_helper_fini(void);
 
-extern int nf_conntrack_broadcast_help(struct sk_buff *skb,
-				       unsigned int protoff,
-				       struct nf_conn *ct,
-				       enum ip_conntrack_info ctinfo,
-				       unsigned int timeout);
+int nf_conntrack_broadcast_help(struct sk_buff *skb, unsigned int protoff,
+				struct nf_conn *ct,
+				enum ip_conntrack_info ctinfo,
+				unsigned int timeout);
 
 struct nf_ct_helper_expectfn {
 	struct list_head head;
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index 3bb89eac3fa1..3efab704b7eb 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -77,17 +77,17 @@ struct nf_conntrack_l3proto {
 extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX];
 
 /* Protocol pernet registration. */
-extern int nf_ct_l3proto_pernet_register(struct net *net,
-					 struct nf_conntrack_l3proto *proto);
-extern void nf_ct_l3proto_pernet_unregister(struct net *net,
-					    struct nf_conntrack_l3proto *proto);
+int nf_ct_l3proto_pernet_register(struct net *net,
+				  struct nf_conntrack_l3proto *proto);
+void nf_ct_l3proto_pernet_unregister(struct net *net,
+				     struct nf_conntrack_l3proto *proto);
 
 /* Protocol global registration. */
-extern int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto);
-extern void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto);
+int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto);
+void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto);
 
-extern struct nf_conntrack_l3proto *nf_ct_l3proto_find_get(u_int16_t l3proto);
-extern void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p);
+struct nf_conntrack_l3proto *nf_ct_l3proto_find_get(u_int16_t l3proto);
+void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p);
 
 /* Existing built-in protocols */
 extern struct nf_conntrack_l3proto nf_conntrack_l3proto_generic;
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index b411d7b17dec..4c8d573830b7 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -114,22 +114,22 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_generic;
 
 #define MAX_NF_CT_PROTO 256
 
-extern struct nf_conntrack_l4proto *
-__nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto);
+struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u_int16_t l3proto,
+						  u_int8_t l4proto);
 
-extern struct nf_conntrack_l4proto *
-nf_ct_l4proto_find_get(u_int16_t l3proto, u_int8_t l4proto);
-extern void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p);
+struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u_int16_t l3proto,
+						    u_int8_t l4proto);
+void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p);
 
 /* Protocol pernet registration. */
-extern int nf_ct_l4proto_pernet_register(struct net *net,
-					 struct nf_conntrack_l4proto *proto);
-extern void nf_ct_l4proto_pernet_unregister(struct net *net,
-					    struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_pernet_register(struct net *net,
+				  struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_pernet_unregister(struct net *net,
+				     struct nf_conntrack_l4proto *proto);
 
 /* Protocol global registration. */
-extern int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto);
-extern void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto);
 
 static inline void nf_ct_kfree_compat_sysctl_table(struct nf_proto_net *pn)
 {
@@ -140,11 +140,11 @@ static inline void nf_ct_kfree_compat_sysctl_table(struct nf_proto_net *pn)
 }
 
 /* Generic netlink helpers */
-extern int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
-				      const struct nf_conntrack_tuple *tuple);
-extern int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
-				      struct nf_conntrack_tuple *t);
-extern int nf_ct_port_nlattr_tuple_size(void);
+int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
+			       const struct nf_conntrack_tuple *tuple);
+int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
+			       struct nf_conntrack_tuple *t);
+int nf_ct_port_nlattr_tuple_size(void);
 extern const struct nla_policy nf_ct_port_nla_policy[];
 
 #ifdef CONFIG_SYSCTL
diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h
index f6177a5fe0ca..4b3362991a25 100644
--- a/include/net/netfilter/nf_conntrack_seqadj.h
+++ b/include/net/netfilter/nf_conntrack_seqadj.h
@@ -30,22 +30,18 @@ static inline struct nf_conn_seqadj *nfct_seqadj_ext_add(struct nf_conn *ct)
 	return nf_ct_ext_add(ct, NF_CT_EXT_SEQADJ, GFP_ATOMIC);
 }
 
-extern int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			     s32 off);
-extern int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			    __be32 seq, s32 off);
-extern void nf_ct_tcp_seqadj_set(struct sk_buff *skb,
-				 struct nf_conn *ct,
-				 enum ip_conntrack_info ctinfo,
-				 s32 off);
-
-extern int nf_ct_seq_adjust(struct sk_buff *skb,
-			    struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			    unsigned int protoff);
-extern s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir,
-			    u32 seq);
-
-extern int nf_conntrack_seqadj_init(void);
-extern void nf_conntrack_seqadj_fini(void);
+int nf_ct_seqadj_init(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+		      s32 off);
+int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+		     __be32 seq, s32 off);
+void nf_ct_tcp_seqadj_set(struct sk_buff *skb, struct nf_conn *ct,
+			  enum ip_conntrack_info ctinfo, s32 off);
+
+int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+		     enum ip_conntrack_info ctinfo, unsigned int protoff);
+s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, u32 seq);
+
+int nf_conntrack_seqadj_init(void);
+void nf_conntrack_seqadj_fini(void);
 
 #endif /* _NF_CONNTRACK_SEQADJ_H */
diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h
index 806f54a290d6..968186642bb1 100644
--- a/include/net/netfilter/nf_conntrack_synproxy.h
+++ b/include/net/netfilter/nf_conntrack_synproxy.h
@@ -56,22 +56,20 @@ struct synproxy_options {
 
 struct tcphdr;
 struct xt_synproxy_info;
-extern void synproxy_parse_options(const struct sk_buff *skb, unsigned int doff,
-				   const struct tcphdr *th,
-				   struct synproxy_options *opts);
-extern unsigned int synproxy_options_size(const struct synproxy_options *opts);
-extern void synproxy_build_options(struct tcphdr *th,
-				   const struct synproxy_options *opts);
+void synproxy_parse_options(const struct sk_buff *skb, unsigned int doff,
+			    const struct tcphdr *th,
+			    struct synproxy_options *opts);
+unsigned int synproxy_options_size(const struct synproxy_options *opts);
+void synproxy_build_options(struct tcphdr *th,
+			    const struct synproxy_options *opts);
 
-extern void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info,
-					   struct synproxy_options *opts);
-extern void synproxy_check_timestamp_cookie(struct synproxy_options *opts);
+void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info,
+				    struct synproxy_options *opts);
+void synproxy_check_timestamp_cookie(struct synproxy_options *opts);
 
-extern unsigned int synproxy_tstamp_adjust(struct sk_buff *skb,
-					   unsigned int protoff,
-					   struct tcphdr *th,
-					   struct nf_conn *ct,
-					   enum ip_conntrack_info ctinfo,
-					   const struct nf_conn_synproxy *synproxy);
+unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, unsigned int protoff,
+				    struct tcphdr *th, struct nf_conn *ct,
+				    enum ip_conntrack_info ctinfo,
+				    const struct nf_conn_synproxy *synproxy);
 
 #endif /* _NF_CONNTRACK_SYNPROXY_H */
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index d23aceb16d94..62308713dd7f 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -76,8 +76,8 @@ nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct,
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-extern int nf_conntrack_timeout_init(void);
-extern void nf_conntrack_timeout_fini(void);
+int nf_conntrack_timeout_init(void);
+void nf_conntrack_timeout_fini(void);
 #else
 static inline int nf_conntrack_timeout_init(void)
 {
diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h
index b00461413efd..300ae2209f25 100644
--- a/include/net/netfilter/nf_conntrack_timestamp.h
+++ b/include/net/netfilter/nf_conntrack_timestamp.h
@@ -48,11 +48,11 @@ static inline void nf_ct_set_tstamp(struct net *net, bool enable)
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
-extern int nf_conntrack_tstamp_pernet_init(struct net *net);
-extern void nf_conntrack_tstamp_pernet_fini(struct net *net);
+int nf_conntrack_tstamp_pernet_init(struct net *net);
+void nf_conntrack_tstamp_pernet_fini(struct net *net);
 
-extern int nf_conntrack_tstamp_init(void);
-extern void nf_conntrack_tstamp_fini(void);
+int nf_conntrack_tstamp_init(void);
+void nf_conntrack_tstamp_fini(void);
 #else
 static inline int nf_conntrack_tstamp_pernet_init(struct net *net)
 {
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index 59a192420053..c29b4e545f87 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -41,13 +41,13 @@ struct nf_conn_nat {
 };
 
 /* Set up the info structure to map into this range. */
-extern unsigned int nf_nat_setup_info(struct nf_conn *ct,
-				      const struct nf_nat_range *range,
-				      enum nf_nat_manip_type maniptype);
+unsigned int nf_nat_setup_info(struct nf_conn *ct,
+			       const struct nf_nat_range *range,
+			       enum nf_nat_manip_type maniptype);
 
 /* Is this tuple already taken? (not by us)*/
-extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
-			     const struct nf_conn *ignored_conntrack);
+int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
+		      const struct nf_conn *ignored_conntrack);
 
 static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct)
 {
diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h
index 972e1e47ec79..fbfd1ba4254e 100644
--- a/include/net/netfilter/nf_nat_core.h
+++ b/include/net/netfilter/nf_nat_core.h
@@ -7,12 +7,10 @@
 /* This header used to share core functionality between the standalone
    NAT module, and the compatibility layer's use of NAT for masquerading. */
 
-extern unsigned int nf_nat_packet(struct nf_conn *ct,
-				  enum ip_conntrack_info ctinfo,
-				  unsigned int hooknum,
-				  struct sk_buff *skb);
+unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
+			   unsigned int hooknum, struct sk_buff *skb);
 
-extern int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family);
+int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family);
 
 static inline int nf_nat_initialized(struct nf_conn *ct,
 				     enum nf_nat_manip_type manip)
diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h
index 404324d1d0c4..01bcc6bfbcc9 100644
--- a/include/net/netfilter/nf_nat_helper.h
+++ b/include/net/netfilter/nf_nat_helper.h
@@ -7,14 +7,11 @@
 struct sk_buff;
 
 /* These return true or false. */
-extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb,
-				      struct nf_conn *ct,
-				      enum ip_conntrack_info ctinfo,
-				      unsigned int protoff,
-				      unsigned int match_offset,
-				      unsigned int match_len,
-				      const char *rep_buffer,
-				      unsigned int rep_len, bool adjust);
+int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct,
+			       enum ip_conntrack_info ctinfo,
+			       unsigned int protoff, unsigned int match_offset,
+			       unsigned int match_len, const char *rep_buffer,
+			       unsigned int rep_len, bool adjust);
 
 static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 					   struct nf_conn *ct,
@@ -30,18 +27,14 @@ static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 					  rep_buffer, rep_len, true);
 }
 
-extern int nf_nat_mangle_udp_packet(struct sk_buff *skb,
-				    struct nf_conn *ct,
-				    enum ip_conntrack_info ctinfo,
-				    unsigned int protoff,
-				    unsigned int match_offset,
-				    unsigned int match_len,
-				    const char *rep_buffer,
-				    unsigned int rep_len);
+int nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct,
+			     enum ip_conntrack_info ctinfo,
+			     unsigned int protoff, unsigned int match_offset,
+			     unsigned int match_len, const char *rep_buffer,
+			     unsigned int rep_len);
 
 /* Setup NAT on this expected conntrack so it follows master, but goes
  * to port ct->master->saved_proto. */
-extern void nf_nat_follow_master(struct nf_conn *ct,
-				 struct nf_conntrack_expect *this);
+void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *this);
 
 #endif
diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h
index bd3b97e02c82..5a2919b2e09a 100644
--- a/include/net/netfilter/nf_nat_l3proto.h
+++ b/include/net/netfilter/nf_nat_l3proto.h
@@ -35,18 +35,15 @@ struct nf_nat_l3proto {
 				   struct nf_nat_range *range);
 };
 
-extern int nf_nat_l3proto_register(const struct nf_nat_l3proto *);
-extern void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *);
-extern const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto);
-
-extern int nf_nat_icmp_reply_translation(struct sk_buff *skb,
-					 struct nf_conn *ct,
-					 enum ip_conntrack_info ctinfo,
-					 unsigned int hooknum);
-extern int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
-					   struct nf_conn *ct,
-					   enum ip_conntrack_info ctinfo,
-					   unsigned int hooknum,
-					   unsigned int hdrlen);
+int nf_nat_l3proto_register(const struct nf_nat_l3proto *);
+void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *);
+const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto);
+
+int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
+				  enum ip_conntrack_info ctinfo,
+				  unsigned int hooknum);
+int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct,
+				    enum ip_conntrack_info ctinfo,
+				    unsigned int hooknum, unsigned int hdrlen);
 
 #endif /* _NF_NAT_L3PROTO_H */
diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h
index 24feb68d1bcc..12f4cc841b6e 100644
--- a/include/net/netfilter/nf_nat_l4proto.h
+++ b/include/net/netfilter/nf_nat_l4proto.h
@@ -42,10 +42,11 @@ struct nf_nat_l4proto {
 };
 
 /* Protocol registration. */
-extern int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto);
-extern void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto);
+int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto);
+void nf_nat_l4proto_unregister(u8 l3proto,
+			       const struct nf_nat_l4proto *l4proto);
 
-extern const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto);
+const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto);
 
 /* Built-in protocols. */
 extern const struct nf_nat_l4proto nf_nat_l4proto_tcp;
@@ -54,19 +55,18 @@ extern const struct nf_nat_l4proto nf_nat_l4proto_icmp;
 extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6;
 extern const struct nf_nat_l4proto nf_nat_l4proto_unknown;
 
-extern bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
-				    enum nf_nat_manip_type maniptype,
-				    const union nf_conntrack_man_proto *min,
-				    const union nf_conntrack_man_proto *max);
+bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple,
+			     enum nf_nat_manip_type maniptype,
+			     const union nf_conntrack_man_proto *min,
+			     const union nf_conntrack_man_proto *max);
 
-extern void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
-					struct nf_conntrack_tuple *tuple,
-					const struct nf_nat_range *range,
-					enum nf_nat_manip_type maniptype,
-					const struct nf_conn *ct,
-					u16 *rover);
+void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto,
+				 struct nf_conntrack_tuple *tuple,
+				 const struct nf_nat_range *range,
+				 enum nf_nat_manip_type maniptype,
+				 const struct nf_conn *ct, u16 *rover);
 
-extern int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
-					  struct nf_nat_range *range);
+int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[],
+				   struct nf_nat_range *range);
 
 #endif /*_NF_NAT_L4PROTO_H*/
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index aaba4bbcdda0..c1d5b3e34a21 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -28,7 +28,7 @@ struct nf_queue_handler {
 
 void nf_register_queue_handler(const struct nf_queue_handler *qh);
 void nf_unregister_queue_handler(void);
-extern void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
+void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
 
 bool nf_queue_entry_get_refs(struct nf_queue_entry *entry);
 void nf_queue_entry_release_refs(struct nf_queue_entry *entry);
diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index 495c71f66e7e..79f45e19f31e 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -16,7 +16,7 @@ struct xt_rateest {
 	struct rcu_head			rcu;
 };
 
-extern struct xt_rateest *xt_rateest_lookup(const char *name);
-extern void xt_rateest_put(struct xt_rateest *est);
+struct xt_rateest *xt_rateest_lookup(const char *name);
+void xt_rateest_put(struct xt_rateest *est);
 
 #endif /* _XT_RATEEST_H */
-- 
cgit 


From 7b584460689d4326d2d1664271ab0c56b56d4328 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 23 Sep 2013 11:37:59 -0700
Subject: sctp: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 3794c5ad20fe..c5fe80697f8d 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -90,12 +90,11 @@
 /*
  * sctp/protocol.c
  */
-extern int sctp_copy_local_addr_list(struct net *, struct sctp_bind_addr *,
-				     sctp_scope_t, gfp_t gfp,
-				     int flags);
-extern struct sctp_pf *sctp_get_pf_specific(sa_family_t family);
-extern int sctp_register_pf(struct sctp_pf *, sa_family_t);
-extern void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
+int sctp_copy_local_addr_list(struct net *, struct sctp_bind_addr *,
+			      sctp_scope_t, gfp_t gfp, int flags);
+struct sctp_pf *sctp_get_pf_specific(sa_family_t family);
+int sctp_register_pf(struct sctp_pf *, sa_family_t);
+void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
 
 /*
  * sctp/socket.c
@@ -110,7 +109,7 @@ void sctp_sock_rfree(struct sk_buff *skb);
 void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 		    struct sctp_association *asoc);
 extern struct percpu_counter sctp_sockets_allocated;
-extern int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
+int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
 
 /*
  * sctp/primitive.c
-- 
cgit 


From eeb446581ba23a5a36b4f5c7bfa2b1f8f7c9fb66 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Wed, 28 Nov 2012 18:17:25 -0500
Subject: ARM: GIC: function to retrieve the physical address of the SGIR

In order to have early assembly code signal other CPUs in the system,
we need to get the physical address for the SGIR register used to
send IPIs.  Because the register will be used with a precomputed CPU
interface ID number, there is no need for any locking in the assembly
code where this register is written to.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 drivers/irqchip/irq-gic.c       | 29 +++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic.h |  1 +
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 6365b59181ee..09fdf3d574cd 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -769,6 +769,33 @@ void gic_migrate_target(unsigned int new_cpu_id)
 		}
 	}
 }
+
+/*
+ * gic_get_sgir_physaddr - get the physical address for the SGI register
+ *
+ * REturn the physical address of the SGI register to be used
+ * by some early assembly code when the kernel is not yet available.
+ */
+static unsigned long gic_dist_physaddr;
+
+unsigned long gic_get_sgir_physaddr(void)
+{
+	if (!gic_dist_physaddr)
+		return 0;
+	return gic_dist_physaddr + GIC_DIST_SOFTINT;
+}
+
+void __init gic_init_physaddr(struct device_node *node)
+{
+	struct resource res;
+	if (of_address_to_resource(node, 0, &res) == 0) {
+		gic_dist_physaddr = res.start;
+		pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
+	}
+}
+
+#else
+#define gic_init_physaddr(node)  do { } while (0)
 #endif
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
@@ -952,6 +979,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 		percpu_offset = 0;
 
 	gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
+	if (!gic_cnt)
+		gic_init_physaddr(node);
 
 	if (parent) {
 		irq = irq_of_parse_and_map(node, 0);
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 46544e381bf9..dc30835099e3 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -78,6 +78,7 @@ static inline void gic_init(unsigned int nr, int start,
 
 int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
+unsigned long gic_get_sgir_physaddr(void);
 
 #endif /* __ASSEMBLY */
 
-- 
cgit 


From 14d2ca615a85e2dbc744c12c296affd35f119fa7 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Wed, 28 Nov 2012 18:48:19 -0500
Subject: ARM: GIC: interface to send a SGI directly

The regular gic_raise_softirq() takes as input a CPU mask which is not
adequate when we need to send an IPI to a CPU which is not represented
in the kernel to GIC mapping.  That is the case with the b.L switcher
when GIC migration to the inbound CPU has not yet occurred.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 drivers/irqchip/irq-gic.c       | 14 ++++++++++++++
 include/linux/irqchip/arm-gic.h |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 09fdf3d574cd..9031171c141b 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -673,6 +673,20 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 #endif
 
 #ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_send_sgi - send a SGI directly to given CPU interface number
+ *
+ * cpu_id: the ID for the destination CPU interface
+ * irq: the IPI number to send a SGI for
+ */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
+{
+	BUG_ON(cpu_id >= NR_GIC_CPU_IF);
+	cpu_id = 1 << cpu_id;
+	/* this always happens on GIC0 */
+	writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+}
+
 /*
  * gic_get_cpu_id - get the CPU interface ID for the specified CPU
  *
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index dc30835099e3..cac496b1e279 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -76,6 +76,7 @@ static inline void gic_init(unsigned int nr, int start,
 	gic_init_bases(nr, start, dist, cpu, 0, NULL);
 }
 
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
 int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
 unsigned long gic_get_sgir_physaddr(void);
-- 
cgit 


From 1bfbddb6f3a0dbb8c3996d1c4d4911d695737c15 Mon Sep 17 00:00:00 2001
From: Dave Martin <dave.martin@linaro.org>
Date: Mon, 14 May 2012 17:40:07 +0100
Subject: ARM: bL_switcher: Basic trace events support

This patch adds simple trace events to the b.L switcher code
to allow tracing of CPU migration events.

To make use of the trace events, you will need:

CONFIG_FTRACE=y
CONFIG_ENABLE_DEFAULT_TRACERS=y

The following events are added:
  * power:cpu_migrate_begin
  * power:cpu_migrate_finish

each with the following data:
    u64     timestamp;
    u32     cpu_hwid;

power:cpu_migrate_begin occurs immediately before the
switcher-specific migration operations start.
power:cpu_migrate_finish occurs immediately when migration is
completed.

The cpu_hwid field contains the ID fields of the MPIDR.

* For power:cpu_migrate_begin, cpu_hwid is the ID of the outbound
  physical CPU (equivalent to (from_phys_cpu,from_phys_cluster)).

* For power:cpu_migrate_finish, cpu_hwid is the ID of the inbound
  physical CPU (equivalent to (to_phys_cpu,to_phys_cluster)).

By design, the cpu_hwid field is masked in the same way as the
device tree cpu node reg property, allowing direct correlation to
the DT description of the hardware.

The timestamp is added in order to minimise timing noise.  An
accurate system-wide clock should be used for generating this
(hopefully getnstimeofday is appropriate, but it could be changed).
It could be any monotonic shared clock, since the aim is to allow
accurate deltas to be computed.  We don't necessarily care about
accurate synchronisation with wall clock time.

In practice, each switch takes place on a single logical CPU,
and the trace infrastructure should guarantee that events are
well-ordered with respect to a single logical CPU.

Signed-off-by: Dave Martin <dave.martin@linaro.org>
Signed-off-by: Nicolas Pitre <nico@linaro.org>
---
 arch/arm/common/bL_switcher.c            | 17 ++++++++
 include/trace/events/power_cpu_migrate.h | 66 ++++++++++++++++++++++++++++++++
 2 files changed, 83 insertions(+)
 create mode 100644 include/trace/events/power_cpu_migrate.h

(limited to 'include')

diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index dc53eb8dcc81..7002de360d23 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -20,6 +20,7 @@
 #include <linux/cpumask.h>
 #include <linux/kthread.h>
 #include <linux/wait.h>
+#include <linux/time.h>
 #include <linux/clockchips.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
@@ -33,10 +34,14 @@
 #include <linux/moduleparam.h>
 
 #include <asm/smp_plat.h>
+#include <asm/cputype.h>
 #include <asm/suspend.h>
 #include <asm/mcpm.h>
 #include <asm/bL_switcher.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/power_cpu_migrate.h>
+
 
 /*
  * Use our own MPIDR accessors as the generic ones in asm/cputype.h have
@@ -51,6 +56,16 @@ static int read_mpidr(void)
 	return id & MPIDR_HWID_BITMASK;
 }
 
+/*
+ * Get a global nanosecond time stamp for tracing.
+ */
+static s64 get_ns(void)
+{
+	struct timespec ts;
+	getnstimeofday(&ts);
+	return timespec_to_ns(&ts);
+}
+
 /*
  * bL switcher core code.
  */
@@ -208,6 +223,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 	 */
 	local_irq_disable();
 	local_fiq_disable();
+	trace_cpu_migrate_begin(get_ns(), ob_mpidr);
 
 	/* redirect GIC's SGIs to our counterpart */
 	gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
@@ -250,6 +266,7 @@ static int bL_switch_to(unsigned int new_cluster_id)
 					  tdev->evtdev->next_event, 1);
 	}
 
+	trace_cpu_migrate_finish(get_ns(), ib_mpidr);
 	local_fiq_enable();
 	local_irq_enable();
 
diff --git a/include/trace/events/power_cpu_migrate.h b/include/trace/events/power_cpu_migrate.h
new file mode 100644
index 000000000000..3694af0f5bc5
--- /dev/null
+++ b/include/trace/events/power_cpu_migrate.h
@@ -0,0 +1,66 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_CPU_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_CPU_MIGRATE_H
+
+#include <linux/tracepoint.h>
+
+#define __cpu_migrate_proto			\
+	TP_PROTO(u64 timestamp,			\
+		 u32 cpu_hwid)
+#define __cpu_migrate_args			\
+	TP_ARGS(timestamp,			\
+		cpu_hwid)
+
+DECLARE_EVENT_CLASS(cpu_migrate,
+
+	__cpu_migrate_proto,
+	__cpu_migrate_args,
+
+	TP_STRUCT__entry(
+		__field(u64,	timestamp		)
+		__field(u32,	cpu_hwid		)
+	),
+
+	TP_fast_assign(
+		__entry->timestamp = timestamp;
+		__entry->cpu_hwid = cpu_hwid;
+	),
+
+	TP_printk("timestamp=%llu cpu_hwid=0x%08lX",
+		(unsigned long long)__entry->timestamp,
+		(unsigned long)__entry->cpu_hwid
+	)
+);
+
+#define __define_cpu_migrate_event(name)		\
+	DEFINE_EVENT(cpu_migrate, cpu_migrate_##name,	\
+		__cpu_migrate_proto,			\
+		__cpu_migrate_args			\
+	)
+
+__define_cpu_migrate_event(begin);
+__define_cpu_migrate_event(finish);
+
+#undef __define_cpu_migrate
+#undef __cpu_migrate_proto
+#undef __cpu_migrate_args
+
+/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
+#ifndef _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+#define _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+
+/*
+ * Set from_phys_cpu and to_phys_cpu to CPU_MIGRATE_ALL_CPUS to indicate
+ * a whole-cluster migration:
+ */
+#define CPU_MIGRATE_ALL_CPUS 0x80000000U
+#endif
+
+#endif /* _TRACE_POWER_CPU_MIGRATE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE power_cpu_migrate
+#include <trace/define_trace.h>
-- 
cgit 


From b09bbe5b1267b6af22a9584d614f5eec5d74f405 Mon Sep 17 00:00:00 2001
From: Dave Martin <dave.martin@linaro.org>
Date: Wed, 6 Feb 2013 15:45:23 +0000
Subject: ARM: bL_switcher/trace: Add trace trigger for trace bootstrapping

When tracing switching, an external tracer needs a way to bootstrap
its knowledge of the logical<->physical CPU mapping.

This patch adds a sysfs attribute trace_trigger.  A write to this
attribute will generate a power:cpu_migrate_current event for each
online CPU, indicating the current physical CPU for each logical
CPU.

Activating or deactivating the switcher also generates these
events, so that the tracer knows about the resulting remapping of
affected CPUs.

Signed-off-by: Dave Martin <dave.martin@linaro.org>
---
 arch/arm/common/bL_switcher.c            | 36 ++++++++++++++++++++++++++++++++
 include/trace/events/power_cpu_migrate.h |  1 +
 2 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index 7002de360d23..f0dc025077d5 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -27,6 +27,7 @@
 #include <linux/notifier.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/sysfs.h>
@@ -531,6 +532,25 @@ static int bL_switcher_halve_cpus(void)
 	return 0;
 }
 
+static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
+{
+	trace_cpu_migrate_current(get_ns(), read_mpidr());
+}
+
+static int bL_switcher_trace_trigger(void)
+{
+	int ret;
+
+	preempt_disable();
+
+	bL_switcher_trace_trigger_cpu(NULL);
+	ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true);
+
+	preempt_enable();
+
+	return ret;
+}
+
 static int bL_switcher_enable(void)
 {
 	int cpu, ret;
@@ -553,6 +573,8 @@ static int bL_switcher_enable(void)
 	if (ret)
 		goto error;
 
+	bL_switcher_trace_trigger();
+
 	for_each_online_cpu(cpu) {
 		struct bL_thread *t = &bL_threads[cpu];
 		spin_lock_init(&t->lock);
@@ -637,6 +659,8 @@ static void bL_switcher_disable(void)
 	}
 
 	bL_switcher_restore_cpus();
+	bL_switcher_trace_trigger();
+
 	bL_activation_notify(BL_NOTIFY_POST_DISABLE);
 
 out:
@@ -670,11 +694,23 @@ static ssize_t bL_switcher_active_store(struct kobject *kobj,
 	return (ret >= 0) ? count : ret;
 }
 
+static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	int ret = bL_switcher_trace_trigger();
+
+	return ret ? ret : count;
+}
+
 static struct kobj_attribute bL_switcher_active_attr =
 	__ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store);
 
+static struct kobj_attribute bL_switcher_trace_trigger_attr =
+	__ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store);
+
 static struct attribute *bL_switcher_attrs[] = {
 	&bL_switcher_active_attr.attr,
+	&bL_switcher_trace_trigger_attr.attr,
 	NULL,
 };
 
diff --git a/include/trace/events/power_cpu_migrate.h b/include/trace/events/power_cpu_migrate.h
index 3694af0f5bc5..f76dd4de625e 100644
--- a/include/trace/events/power_cpu_migrate.h
+++ b/include/trace/events/power_cpu_migrate.h
@@ -42,6 +42,7 @@ DECLARE_EVENT_CLASS(cpu_migrate,
 
 __define_cpu_migrate_event(begin);
 __define_cpu_migrate_event(finish);
+__define_cpu_migrate_event(current);
 
 #undef __define_cpu_migrate
 #undef __cpu_migrate_proto
-- 
cgit 


From ad4d35f865408a494f0a4c02b1c7ebd3f80f5dbf Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Thu, 5 Sep 2013 15:55:26 +0800
Subject: [SCSI] csiostor: Use pcie_capability_clear_and_set_word() to simplify
 code

pci_is_pcie() and pcie_capability_clear_and_set_word() make it trivial
to set the PCIe Completion Timeout, so just fold the
csio_set_pcie_completion_timeout() function into its caller.

[bhelgaas: changelog, fold csio_set_pcie_completion_timeout() into caller]
Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Naresh Kumar Inna <naresh@chelsio.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jesper Juhl <jj@chaosbits.net>
---
 drivers/scsi/csiostor/csio_hw.c | 22 ++++------------------
 include/uapi/linux/pci_regs.h   |  3 ++-
 2 files changed, 6 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index 0eb35b9b3784..0eaec4748957 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -852,22 +852,6 @@ csio_hw_get_flash_params(struct csio_hw *hw)
 	return 0;
 }
 
-static void
-csio_set_pcie_completion_timeout(struct csio_hw *hw, u8 range)
-{
-	uint16_t val;
-	int pcie_cap;
-
-	if (!csio_pci_capability(hw->pdev, PCI_CAP_ID_EXP, &pcie_cap)) {
-		pci_read_config_word(hw->pdev,
-				     pcie_cap + PCI_EXP_DEVCTL2, &val);
-		val &= 0xfff0;
-		val |= range ;
-		pci_write_config_word(hw->pdev,
-				      pcie_cap + PCI_EXP_DEVCTL2, val);
-	}
-}
-
 /*****************************************************************************/
 /* HW State machine assists                                                  */
 /*****************************************************************************/
@@ -2069,8 +2053,10 @@ csio_hw_configure(struct csio_hw *hw)
 		goto out;
 	}
 
-	/* Set pci completion timeout value to 4 seconds. */
-	csio_set_pcie_completion_timeout(hw, 0xd);
+	/* Set PCIe completion timeout to 4 seconds */
+	if (pci_is_pcie(hw->pdev))
+		pcie_capability_clear_and_set_word(hw->pdev, PCI_EXP_DEVCTL2,
+				PCI_EXP_DEVCTL2_COMP_TIMEOUT, 0xd);
 
 	hw->chip_ops->chip_set_mem_win(hw, MEMWIN_CSIOSTOR);
 
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index baa7852468ef..1a38377a0032 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -558,7 +558,8 @@
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
 #define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
-#define  PCI_EXP_DEVCTL2_ARI		0x20	/* Alternative Routing-ID */
+#define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
+#define  PCI_EXP_DEVCTL2_ARI		0x0020	/* Alternative Routing-ID */
 #define  PCI_EXP_DEVCTL2_IDO_REQ_EN	0x0100	/* Allow IDO for requests */
 #define  PCI_EXP_DEVCTL2_IDO_CMP_EN	0x0200	/* Allow IDO for completions */
 #define  PCI_EXP_DEVCTL2_LTR_EN		0x0400	/* Enable LTR mechanism */
-- 
cgit 


From ca9f62ac783bf88c54143f8065adc0fc8df859c1 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@huawei.com>
Date: Mon, 2 Sep 2013 11:57:34 +0800
Subject: ACPI / processor: Introduce apic_id in struct processor to save
 parsed APIC id

For cpu hot add, we evaluate _MAT or parse MADT twice to get APIC id,
here is the code logic:
acpi_processor_add()
	acpi_processor_get_info()
		acpi_get_cpuid() will evaluate _MAT or parse MADT;
	acpi_processor_hotadd_init()
		acpi_map_lsapic() will evaluate _MAT again;

This can be done more effectively, this patch introduces apic_id in struct
processor to save parsed APIC id, and then we can use it and remove the
duplicated _MAT evaluation.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_processor.c |  4 +++-
 drivers/acpi/processor_core.c | 26 +++++++++++++++++++++-----
 include/acpi/processor.h      |  3 +++
 3 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index f29e06efa479..f89f914cb97e 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -270,7 +270,9 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		device_declaration = 1;
 		pr->acpi_id = value;
 	}
-	cpu_index = acpi_get_cpuid(pr->handle, device_declaration, pr->acpi_id);
+	pr->apic_id = acpi_get_apicid(pr->handle, device_declaration,
+					pr->acpi_id);
+	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
 
 	/* Handle UP system running SMP kernel, with no LAPIC in MADT */
 	if (!cpu0_initialized && (cpu_index == -1) &&
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index cf34d903f4fb..b3171f30b319 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -162,16 +162,23 @@ exit:
 	return apic_id;
 }
 
-int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
+int acpi_get_apicid(acpi_handle handle, int type, u32 acpi_id)
 {
-#ifdef CONFIG_SMP
-	int i;
-#endif
-	int apic_id = -1;
+	int apic_id;
 
 	apic_id = map_mat_entry(handle, type, acpi_id);
 	if (apic_id == -1)
 		apic_id = map_madt_entry(type, acpi_id);
+
+	return apic_id;
+}
+
+int acpi_map_cpuid(int apic_id, u32 acpi_id)
+{
+#ifdef CONFIG_SMP
+	int i;
+#endif
+
 	if (apic_id == -1) {
 		/*
 		 * On UP processor, there is no _MAT or MADT table.
@@ -211,6 +218,15 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 #endif
 	return -1;
 }
+
+int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
+{
+	int apic_id;
+
+	apic_id = acpi_get_apicid(handle, type, acpi_id);
+
+	return acpi_map_cpuid(apic_id, acpi_id);
+}
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
 
 static bool __init processor_physically_present(acpi_handle handle)
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 66096d06925e..7816e45f5d5a 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -199,6 +199,7 @@ struct acpi_processor_flags {
 struct acpi_processor {
 	acpi_handle handle;
 	u32 acpi_id;
+	u32 apic_id;
 	u32 id;
 	u32 pblk;
 	int performance_platform_limit;
@@ -314,6 +315,8 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 
 /* in processor_core.c */
 void acpi_processor_set_pdc(acpi_handle handle);
+int acpi_get_apicid(acpi_handle, int type, u32 acpi_id);
+int acpi_map_cpuid(int apic_id, u32 acpi_id);
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
 
 /* in processor_throttling.c */
-- 
cgit 


From d536bf3dc97417471e2c5098837a1cddd7fbb3c7 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@huawei.com>
Date: Mon, 2 Sep 2013 11:57:35 +0800
Subject: ACPI / processor: use apic_id and remove duplicated _MAT evaluation

Since APIC id is saved in processor struct, just use it and
remove the duplicated _MAT evaluation.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/ia64/kernel/acpi.c       | 38 ++++----------------------------------
 arch/x86/kernel/acpi/boot.c   | 38 +++-----------------------------------
 drivers/acpi/acpi_processor.c |  2 +-
 include/linux/acpi.h          |  2 +-
 4 files changed, 9 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 5eb71d22c3d5..59d52e3aef12 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -882,40 +882,10 @@ __init void prefill_possible_map(void)
 		set_cpu_possible(i, true);
 }
 
-static int _acpi_map_lsapic(acpi_handle handle, int *pcpu)
+static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 {
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *obj;
-	struct acpi_madt_local_sapic *lsapic;
 	cpumask_t tmp_map;
-	int cpu, physid;
-
-	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
-		return -EINVAL;
-
-	if (!buffer.length || !buffer.pointer)
-		return -EINVAL;
-
-	obj = buffer.pointer;
-	if (obj->type != ACPI_TYPE_BUFFER)
-	{
-		kfree(buffer.pointer);
-		return -EINVAL;
-	}
-
-	lsapic = (struct acpi_madt_local_sapic *)obj->buffer.pointer;
-
-	if ((lsapic->header.type != ACPI_MADT_TYPE_LOCAL_SAPIC) ||
-	    (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))) {
-		kfree(buffer.pointer);
-		return -EINVAL;
-	}
-
-	physid = ((lsapic->id << 8) | (lsapic->eid));
-
-	kfree(buffer.pointer);
-	buffer.length = ACPI_ALLOCATE_BUFFER;
-	buffer.pointer = NULL;
+	int cpu;
 
 	cpumask_complement(&tmp_map, cpu_present_mask);
 	cpu = cpumask_first(&tmp_map);
@@ -934,9 +904,9 @@ static int _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu)
+int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 {
-	return _acpi_map_lsapic(handle, pcpu);
+	return _acpi_map_lsapic(handle, physid, pcpu);
 }
 EXPORT_SYMBOL(acpi_map_lsapic);
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 40c76604199f..f6dbb2f5e39f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -614,44 +614,12 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 #endif
 }
 
-static int _acpi_map_lsapic(acpi_handle handle, int *pcpu)
+static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 {
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *obj;
-	struct acpi_madt_local_apic *lapic;
 	cpumask_var_t tmp_map, new_map;
-	u8 physid;
 	int cpu;
 	int retval = -ENOMEM;
 
-	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
-		return -EINVAL;
-
-	if (!buffer.length || !buffer.pointer)
-		return -EINVAL;
-
-	obj = buffer.pointer;
-	if (obj->type != ACPI_TYPE_BUFFER ||
-	    obj->buffer.length < sizeof(*lapic)) {
-		kfree(buffer.pointer);
-		return -EINVAL;
-	}
-
-	lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer;
-
-	if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC ||
-	    !(lapic->lapic_flags & ACPI_MADT_ENABLED)) {
-		kfree(buffer.pointer);
-		return -EINVAL;
-	}
-
-	physid = lapic->id;
-
-	kfree(buffer.pointer);
-	buffer.length = ACPI_ALLOCATE_BUFFER;
-	buffer.pointer = NULL;
-	lapic = NULL;
-
 	if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL))
 		goto out;
 
@@ -689,9 +657,9 @@ out:
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int *pcpu)
+int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 {
-	return _acpi_map_lsapic(handle, pcpu);
+	return _acpi_map_lsapic(handle, physid, pcpu);
 }
 EXPORT_SYMBOL(acpi_map_lsapic);
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index f89f914cb97e..66c9b702894b 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -181,7 +181,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	cpu_maps_update_begin();
 	cpu_hotplug_begin();
 
-	ret = acpi_map_lsapic(pr->handle, &pr->id);
+	ret = acpi_map_lsapic(pr->handle, pr->apic_id, &pr->id);
 	if (ret)
 		goto out;
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a5db4aeefa36..3bc74141453f 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -116,7 +116,7 @@ void acpi_numa_arch_fixup(void);
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
-int acpi_map_lsapic(acpi_handle handle, int *pcpu);
+int acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu);
 int acpi_unmap_lsapic(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
-- 
cgit 


From dedf1e4dfd5477b4315ad451b4be0ff8d9f7e85f Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:05:53 -0600
Subject: ACPI: Write _OSC bit field definitions in hex

Update _OSC definition comments to correspond to the 1-based spec wording
(DWORD 1, etc.)  Write _OSC field #defines as hex to make clear that they
are bits in a 32-bit DWORD, not arbitrary values.  No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 54 ++++++++++++++++++++++++++--------------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a5db4aeefa36..164ba10ddcb3 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -304,39 +304,39 @@ struct acpi_osc_context {
 #define OSC_SUPPORT_TYPE 		1
 #define OSC_CONTROL_TYPE		2
 
-/* _OSC DW0 Definition */
-#define OSC_QUERY_ENABLE		1
-#define OSC_REQUEST_ERROR		2
-#define OSC_INVALID_UUID_ERROR		4
-#define OSC_INVALID_REVISION_ERROR	8
-#define OSC_CAPABILITIES_MASK_ERROR	16
+/* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */
+#define OSC_QUERY_ENABLE			0x00000001  /* input */
+#define OSC_REQUEST_ERROR			0x00000002  /* return */
+#define OSC_INVALID_UUID_ERROR			0x00000004  /* return */
+#define OSC_INVALID_REVISION_ERROR		0x00000008  /* return */
+#define OSC_CAPABILITIES_MASK_ERROR		0x00000010  /* return */
 
 acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 
-/* platform-wide _OSC bits */
-#define OSC_SB_PAD_SUPPORT		1
-#define OSC_SB_PPC_OST_SUPPORT		2
-#define OSC_SB_PR3_SUPPORT		4
-#define OSC_SB_HOTPLUG_OST_SUPPORT	8
-#define OSC_SB_APEI_SUPPORT		16
+/* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */
+#define OSC_SB_PAD_SUPPORT			0x00000001
+#define OSC_SB_PPC_OST_SUPPORT			0x00000002
+#define OSC_SB_PR3_SUPPORT			0x00000004
+#define OSC_SB_HOTPLUG_OST_SUPPORT		0x00000008
+#define OSC_SB_APEI_SUPPORT			0x00000010
+#define OSC_SB_CPC_SUPPORT			0x00000020
 
 extern bool osc_sb_apei_support_acked;
 
-/* PCI defined _OSC bits */
-/* _OSC DW1 Definition (OS Support Fields) */
-#define OSC_EXT_PCI_CONFIG_SUPPORT		1
-#define OSC_ACTIVE_STATE_PWR_SUPPORT 		2
-#define OSC_CLOCK_PWR_CAPABILITY_SUPPORT	4
-#define OSC_PCI_SEGMENT_GROUPS_SUPPORT		8
-#define OSC_MSI_SUPPORT				16
-#define OSC_PCI_SUPPORT_MASKS			0x1f
-
-/* _OSC DW1 Definition (OS Control Fields) */
-#define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL	1
-#define OSC_SHPC_NATIVE_HP_CONTROL 		2
-#define OSC_PCI_EXPRESS_PME_CONTROL		4
-#define OSC_PCI_EXPRESS_AER_CONTROL		8
-#define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL	16
+/* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */
+#define OSC_EXT_PCI_CONFIG_SUPPORT		0x00000001
+#define OSC_ACTIVE_STATE_PWR_SUPPORT		0x00000002
+#define OSC_CLOCK_PWR_CAPABILITY_SUPPORT	0x00000004
+#define OSC_PCI_SEGMENT_GROUPS_SUPPORT		0x00000008
+#define OSC_MSI_SUPPORT				0x00000010
+#define OSC_PCI_SUPPORT_MASKS			0x0000001f
+
+/* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */
+#define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL	0x00000001
+#define OSC_SHPC_NATIVE_HP_CONTROL		0x00000002
+#define OSC_PCI_EXPRESS_PME_CONTROL		0x00000004
+#define OSC_PCI_EXPRESS_AER_CONTROL		0x00000008
+#define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL	0x00000010
 
 #define OSC_PCI_CONTROL_MASKS 	(OSC_PCI_EXPRESS_NATIVE_HP_CONTROL | 	\
 				OSC_SHPC_NATIVE_HP_CONTROL | 		\
-- 
cgit 


From b938a229c85a567de7dba2d806d9f63a7c90483e Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:05:54 -0600
Subject: ACPI: Rename OSC_QUERY_TYPE to OSC_QUERY_DWORD

OSC_QUERY_TYPE isn't a "type"; it's an index into the _OSC Capabilities
Buffer of DWORDs.  Rename OSC_QUERY_TYPE, OSC_SUPPORT_TYPE, and
OSC_CONTROL_TYPE to OSC_QUERY_DWORD, etc., to make this clear.
No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/apei-base.c |  6 +++---
 drivers/acpi/bus.c            | 18 +++++++++---------
 drivers/acpi/pci_root.c       | 14 +++++++-------
 include/linux/acpi.h          |  7 ++++---
 4 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 46f80e2c92f7..6d2c49b86b7f 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -758,9 +758,9 @@ int apei_osc_setup(void)
 		.cap.pointer	= capbuf,
 	};
 
-	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	capbuf[OSC_SUPPORT_TYPE] = 1;
-	capbuf[OSC_CONTROL_TYPE] = 0;
+	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
+	capbuf[OSC_SUPPORT_DWORD] = 1;
+	capbuf[OSC_CONTROL_DWORD] = 0;
 
 	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle))
 	    || ACPI_FAILURE(acpi_run_osc(handle, &context)))
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index b587ec8257b2..fbcfaa682c15 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -255,7 +255,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context)
 			acpi_print_osc_error(handle, context,
 				"_OSC invalid revision");
 		if (errors & OSC_CAPABILITIES_MASK_ERROR) {
-			if (((u32 *)context->cap.pointer)[OSC_QUERY_TYPE]
+			if (((u32 *)context->cap.pointer)[OSC_QUERY_DWORD]
 			    & OSC_QUERY_ENABLE)
 				goto out_success;
 			status = AE_SUPPORT;
@@ -295,30 +295,30 @@ static void acpi_bus_osc_support(void)
 	};
 	acpi_handle handle;
 
-	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	capbuf[OSC_SUPPORT_TYPE] = OSC_SB_PR3_SUPPORT; /* _PR3 is in use */
+	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
+	capbuf[OSC_SUPPORT_DWORD] = OSC_SB_PR3_SUPPORT; /* _PR3 is in use */
 #if defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) ||\
 			defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
-	capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PAD_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT;
 #endif
 
 #if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE)
-	capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_PPC_OST_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT;
 #endif
 
 #ifdef ACPI_HOTPLUG_OST
-	capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_HOTPLUG_OST_SUPPORT;
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 #endif
 
 	if (!ghes_disable)
-		capbuf[OSC_SUPPORT_TYPE] |= OSC_SB_APEI_SUPPORT;
+		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_APEI_SUPPORT;
 	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
 		return;
 	if (ACPI_SUCCESS(acpi_run_osc(handle, &context))) {
 		u32 *capbuf_ret = context.ret.pointer;
-		if (context.ret.length > OSC_SUPPORT_TYPE)
+		if (context.ret.length > OSC_SUPPORT_DWORD)
 			osc_sb_apei_support_acked =
-				capbuf_ret[OSC_SUPPORT_TYPE] & OSC_SB_APEI_SUPPORT;
+				capbuf_ret[OSC_SUPPORT_DWORD] & OSC_SB_APEI_SUPPORT;
 		kfree(context.ret.pointer);
 	}
 	/* do we need to check other returned cap? Sounds no */
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index d3874f425653..323afd7ccfbf 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -158,14 +158,14 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
 	support &= OSC_PCI_SUPPORT_MASKS;
 	support |= root->osc_support_set;
 
-	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	capbuf[OSC_SUPPORT_TYPE] = support;
+	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
+	capbuf[OSC_SUPPORT_DWORD] = support;
 	if (control) {
 		*control &= OSC_PCI_CONTROL_MASKS;
-		capbuf[OSC_CONTROL_TYPE] = *control | root->osc_control_set;
+		capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set;
 	} else {
 		/* Run _OSC query only with existing controls. */
-		capbuf[OSC_CONTROL_TYPE] = root->osc_control_set;
+		capbuf[OSC_CONTROL_DWORD] = root->osc_control_set;
 	}
 
 	status = acpi_pci_run_osc(root->device->handle, capbuf, &result);
@@ -357,9 +357,9 @@ acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req)
 		goto out;
 	}
 
-	capbuf[OSC_QUERY_TYPE] = 0;
-	capbuf[OSC_SUPPORT_TYPE] = root->osc_support_set;
-	capbuf[OSC_CONTROL_TYPE] = ctrl;
+	capbuf[OSC_QUERY_DWORD] = 0;
+	capbuf[OSC_SUPPORT_DWORD] = root->osc_support_set;
+	capbuf[OSC_CONTROL_DWORD] = ctrl;
 	status = acpi_pci_run_osc(handle, capbuf, mask);
 	if (ACPI_SUCCESS(status))
 		root->osc_control_set = *mask;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 164ba10ddcb3..d220d1465d9b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -300,9 +300,10 @@ struct acpi_osc_context {
 	struct acpi_buffer ret; /* free by caller if success */
 };
 
-#define OSC_QUERY_TYPE			0
-#define OSC_SUPPORT_TYPE 		1
-#define OSC_CONTROL_TYPE		2
+/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
+#define OSC_QUERY_DWORD				0	/* DWORD 1 */
+#define OSC_SUPPORT_DWORD			1	/* DWORD 2 */
+#define OSC_CONTROL_DWORD			2	/* DWORD 3 */
 
 /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */
 #define OSC_QUERY_ENABLE			0x00000001  /* input */
-- 
cgit 


From c8678473609b0271ffa0963af82e575312e882cb Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:05:55 -0600
Subject: ACPI: Tidy acpi_run_osc() declarations

Move the acpi_run_osc() prototype next to the related structure and
update comments.  No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d220d1465d9b..a2f501c0a4f4 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -294,12 +294,14 @@ void __init acpi_nvs_nosave_s3(void);
 #endif /* CONFIG_PM_SLEEP */
 
 struct acpi_osc_context {
-	char *uuid_str; /* uuid string */
+	char *uuid_str;			/* UUID string */
 	int rev;
-	struct acpi_buffer cap; /* arg2/arg3 */
-	struct acpi_buffer ret; /* free by caller if success */
+	struct acpi_buffer cap;		/* list of DWORD capabilities */
+	struct acpi_buffer ret;		/* free by caller if success */
 };
 
+acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
+
 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
 #define OSC_QUERY_DWORD				0	/* DWORD 1 */
 #define OSC_SUPPORT_DWORD			1	/* DWORD 2 */
@@ -312,8 +314,6 @@ struct acpi_osc_context {
 #define OSC_INVALID_REVISION_ERROR		0x00000008  /* return */
 #define OSC_CAPABILITIES_MASK_ERROR		0x00000010  /* return */
 
-acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
-
 /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */
 #define OSC_SB_PAD_SUPPORT			0x00000001
 #define OSC_SB_PPC_OST_SUPPORT			0x00000002
-- 
cgit 


From b4481934167430d82ea9c857cf95276460e4b607 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:22:11 -0600
Subject: ACPI: Remove unused OSC_PCI_NATIVE_HOTPLUG

OSC_PCI_NATIVE_HOTPLUG is completely unused, so remove it.  No functional
change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a2f501c0a4f4..ca072e3927a2 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -345,9 +345,6 @@ extern bool osc_sb_apei_support_acked;
 				OSC_PCI_EXPRESS_AER_CONTROL |		\
 				OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL)
 
-#define OSC_PCI_NATIVE_HOTPLUG	(OSC_PCI_EXPRESS_NATIVE_HP_CONTROL |	\
-				OSC_SHPC_NATIVE_HP_CONTROL)
-
 extern acpi_status acpi_pci_osc_control_set(acpi_handle handle,
 					     u32 *mask, u32 req);
 
-- 
cgit 


From 335b15097d571007b125eb9fe4ef1f84e61bd31d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:24:24 -0600
Subject: ACPI: Write OSC_PCI_CONTROL_MASKS like OSC_PCI_SUPPORT_MASKS

We write OSC_PCI_SUPPORT_MASKS as a simple 0x1f, so do the same
for OSC_PCI_CONTROL_MASKS.  No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index ca072e3927a2..bb4e7701b26b 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -338,12 +338,7 @@ extern bool osc_sb_apei_support_acked;
 #define OSC_PCI_EXPRESS_PME_CONTROL		0x00000004
 #define OSC_PCI_EXPRESS_AER_CONTROL		0x00000008
 #define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL	0x00000010
-
-#define OSC_PCI_CONTROL_MASKS 	(OSC_PCI_EXPRESS_NATIVE_HP_CONTROL | 	\
-				OSC_SHPC_NATIVE_HP_CONTROL | 		\
-				OSC_PCI_EXPRESS_PME_CONTROL |		\
-				OSC_PCI_EXPRESS_AER_CONTROL |		\
-				OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL)
+#define OSC_PCI_CONTROL_MASKS			0x0000001f
 
 extern acpi_status acpi_pci_osc_control_set(acpi_handle handle,
 					     u32 *mask, u32 req);
-- 
cgit 


From 7dab9ef4f0823072a3c9afdb3b373c9f2f38848b Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 5 Sep 2013 15:07:39 -0600
Subject: PCI/ACPI: Name _OSC #defines more consistently

Make PCI Host Bridge _OSC #defines more consistent.  No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/pci_root.c          | 19 +++++++++----------
 drivers/pci/hotplug/acpi_pcihp.c |  2 +-
 drivers/pci/hotplug/shpchp.h     |  2 +-
 include/linux/acpi.h             | 12 ++++++------
 4 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 323afd7ccfbf..28dd55509789 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -49,10 +49,10 @@ static int acpi_pci_root_add(struct acpi_device *device,
 			     const struct acpi_device_id *not_used);
 static void acpi_pci_root_remove(struct acpi_device *device);
 
-#define ACPI_PCIE_REQ_SUPPORT (OSC_EXT_PCI_CONFIG_SUPPORT \
-				| OSC_ACTIVE_STATE_PWR_SUPPORT \
-				| OSC_CLOCK_PWR_CAPABILITY_SUPPORT \
-				| OSC_MSI_SUPPORT)
+#define ACPI_PCIE_REQ_SUPPORT (OSC_PCI_EXT_CONFIG_SUPPORT \
+				| OSC_PCI_ASPM_SUPPORT \
+				| OSC_PCI_CLOCK_PM_SUPPORT \
+				| OSC_PCI_MSI_SUPPORT)
 
 static const struct acpi_device_id root_device_ids[] = {
 	{"PNP0A03", 0},
@@ -439,13 +439,12 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	acpi_pci_osc_support(root, flags);
 
 	if (pci_ext_cfg_avail())
-		flags |= OSC_EXT_PCI_CONFIG_SUPPORT;
+		flags |= OSC_PCI_EXT_CONFIG_SUPPORT;
 	if (pcie_aspm_support_enabled()) {
-		flags |= OSC_ACTIVE_STATE_PWR_SUPPORT |
-		OSC_CLOCK_PWR_CAPABILITY_SUPPORT;
+		flags |= OSC_PCI_ASPM_SUPPORT | OSC_PCI_CLOCK_PM_SUPPORT;
 	}
 	if (pci_msi_enabled())
-		flags |= OSC_MSI_SUPPORT;
+		flags |= OSC_PCI_MSI_SUPPORT;
 	if (flags != base_flags) {
 		status = acpi_pci_osc_support(root, flags);
 		if (ACPI_FAILURE(status)) {
@@ -458,7 +457,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 
 	if (!pcie_ports_disabled
 	    && (flags & ACPI_PCIE_REQ_SUPPORT) == ACPI_PCIE_REQ_SUPPORT) {
-		flags = OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL
+		flags = OSC_PCI_EXPRESS_CAPABILITY_CONTROL
 			| OSC_PCI_EXPRESS_NATIVE_HP_CONTROL
 			| OSC_PCI_EXPRESS_PME_CONTROL;
 
@@ -474,7 +473,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 			"Requesting ACPI _OSC control (0x%02x)\n", flags);
 
 		status = acpi_pci_osc_control_set(handle, &flags,
-				       OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
+				       OSC_PCI_EXPRESS_CAPABILITY_CONTROL);
 		if (ACPI_SUCCESS(status)) {
 			dev_info(&device->dev,
 				"ACPI _OSC control (0x%02x) granted\n", flags);
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 2a47e82821da..f8140164ec0b 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -338,7 +338,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
 	acpi_handle chandle, handle;
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 
-	flags &= OSC_SHPC_NATIVE_HP_CONTROL;
+	flags &= OSC_PCI_SHPC_NATIVE_HP_CONTROL;
 	if (!flags) {
 		err("Invalid flags %u specified!\n", flags);
 		return -EINVAL;
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index e260f207a90e..d876e4b3c6a9 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -191,7 +191,7 @@ static inline const char *slot_name(struct slot *slot)
 #include <linux/pci-acpi.h>
 static inline int get_hp_hw_control_from_firmware(struct pci_dev *dev)
 {
-	u32 flags = OSC_SHPC_NATIVE_HP_CONTROL;
+	u32 flags = OSC_PCI_SHPC_NATIVE_HP_CONTROL;
 	return acpi_get_hp_hw_control_from_firmware(dev, flags);
 }
 #else
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index bb4e7701b26b..e2e52cf53224 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -325,19 +325,19 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 extern bool osc_sb_apei_support_acked;
 
 /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */
-#define OSC_EXT_PCI_CONFIG_SUPPORT		0x00000001
-#define OSC_ACTIVE_STATE_PWR_SUPPORT		0x00000002
-#define OSC_CLOCK_PWR_CAPABILITY_SUPPORT	0x00000004
+#define OSC_PCI_EXT_CONFIG_SUPPORT		0x00000001
+#define OSC_PCI_ASPM_SUPPORT			0x00000002
+#define OSC_PCI_CLOCK_PM_SUPPORT		0x00000004
 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT		0x00000008
-#define OSC_MSI_SUPPORT				0x00000010
+#define OSC_PCI_MSI_SUPPORT			0x00000010
 #define OSC_PCI_SUPPORT_MASKS			0x0000001f
 
 /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */
 #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL	0x00000001
-#define OSC_SHPC_NATIVE_HP_CONTROL		0x00000002
+#define OSC_PCI_SHPC_NATIVE_HP_CONTROL		0x00000002
 #define OSC_PCI_EXPRESS_PME_CONTROL		0x00000004
 #define OSC_PCI_EXPRESS_AER_CONTROL		0x00000008
-#define OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL	0x00000010
+#define OSC_PCI_EXPRESS_CAPABILITY_CONTROL	0x00000010
 #define OSC_PCI_CONTROL_MASKS			0x0000001f
 
 extern acpi_status acpi_pci_osc_control_set(acpi_handle handle,
-- 
cgit 


From 30095207072665503a5f6c769d16be26de38fa6a Mon Sep 17 00:00:00 2001
From: Naresh Bhat <naresh.bhat@linaro.org>
Date: Mon, 23 Sep 2013 09:51:46 +0800
Subject: ACPICA: Linux-specific header: enable "aarch64" 64-bit build.

Add support for the __aarch64__ define for 64-bit builds.

Signed-off-by: Naresh Bhat <naresh.bhat@linaro.org>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/platform/aclinux.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 68534ef86ec8..fda0f3e35c03 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -87,7 +87,7 @@
 #define ACPI_FLUSH_CPU_CACHE()
 #define ACPI_CAST_PTHREAD_T(pthread) ((acpi_thread_id) (pthread))
 
-#if defined(__ia64__) || defined(__x86_64__)
+#if defined(__ia64__) || defined(__x86_64__) || defined(__aarch64__)
 #define ACPI_MACHINE_WIDTH          64
 #define COMPILER_DEPENDENT_INT64    long
 #define COMPILER_DEPENDENT_UINT64   unsigned long
-- 
cgit 


From a2fd4b4b4e2884405c54a91514b0fad3853aea01 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Mon, 23 Sep 2013 09:52:05 +0800
Subject: ACPICA: Add support for host-installed SCI handlers.

This change adds support to allow hosts to install System Control
Interrupt handlers. Certain ACPI functionality requires the host
to handle raw SCIs. For example, the "SCI Doorbell" that is defined
for memory power state support requires the host device driver to
handle SCIs to examine if the doorbell has been activated. Multiple
SCI handlers can be installed to allow for future expansion.
Debugger support is included.
Lv Zheng, Bob Moore. ACPICA BZ 1032.

Bug summary:
It is reported when the PCC (Platform Communication Channel, via
MPST table, defined in ACPI specification 5.0) subchannel responds
to the host, it issues an SCI and the host must probe the subchannel
for channel status.

Buglink: http://bugs.acpica.org/show_bug.cgi?id=1032
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acdebug.h   |   3 +-
 drivers/acpi/acpica/acevents.h  |   6 +-
 drivers/acpi/acpica/acglobal.h  |   1 +
 drivers/acpi/acpica/aclocal.h   |   8 +++
 drivers/acpi/acpica/evgpeutil.c |   2 +-
 drivers/acpi/acpica/evmisc.c    |  14 ++--
 drivers/acpi/acpica/evsci.c     |  80 +++++++++++++++++++++--
 drivers/acpi/acpica/evxface.c   | 139 ++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/acpica/utglobal.c  |   3 +-
 include/acpi/acpixf.h           |  13 +++-
 include/acpi/actypes.h          |   3 +
 11 files changed, 249 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 9feba08c29fe..30c2d6911386 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -113,11 +113,12 @@ void acpi_db_display_handlers(void);
 ACPI_HW_DEPENDENT_RETURN_VOID(void
 			      acpi_db_generate_gpe(char *gpe_arg,
 						   char *block_arg))
+ ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_generate_sci(void))
 
 /*
  * dbconvert - miscellaneous conversion routines
  */
- acpi_status acpi_db_hex_char_to_value(int hex_char, u8 *return_value);
+acpi_status acpi_db_hex_char_to_value(int hex_char, u8 *return_value);
 
 acpi_status acpi_db_convert_to_package(char *string, union acpi_object *object);
 
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index ab0e97710381..3ae5fd02ae64 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -242,11 +242,11 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
  */
 u32 ACPI_SYSTEM_XFACE acpi_ev_gpe_xrupt_handler(void *context);
 
-u32 acpi_ev_install_sci_handler(void);
+u32 acpi_ev_sci_dispatch(void);
 
-acpi_status acpi_ev_remove_sci_handler(void);
+u32 acpi_ev_install_sci_handler(void);
 
-u32 acpi_ev_initialize_SCI(u32 program_SCI);
+acpi_status acpi_ev_remove_all_sci_handlers(void);
 
 ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_ev_terminate(void))
 #endif				/* __ACEVENTS_H__  */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index c9ad2e1f1ee1..0fba431f4fcb 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -269,6 +269,7 @@ ACPI_EXTERN acpi_table_handler acpi_gbl_table_handler;
 ACPI_EXTERN void *acpi_gbl_table_handler_context;
 ACPI_EXTERN struct acpi_walk_state *acpi_gbl_breakpoint_walk;
 ACPI_EXTERN acpi_interface_handler acpi_gbl_interface_handler;
+ACPI_EXTERN struct acpi_sci_handler_info *acpi_gbl_sci_handler_list;
 
 /* Owner ID support */
 
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 0ed00669cd21..be9e30ee6048 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -398,6 +398,14 @@ struct acpi_simple_repair_info {
  *
  ****************************************************************************/
 
+/* Dispatch info for each host-installed SCI handler */
+
+struct acpi_sci_handler_info {
+	struct acpi_sci_handler_info *next;
+	acpi_sci_handler address;	/* Address of handler */
+	void *context;		/* Context to be passed to handler */
+};
+
 /* Dispatch info for each GPE -- either a method or handler, cannot be both */
 
 struct acpi_gpe_handler_info {
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index b24dbb80fab8..d52339090b60 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -196,7 +196,7 @@ acpi_ev_get_gpe_device(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
  *
  * FUNCTION:    acpi_ev_get_gpe_xrupt_block
  *
- * PARAMETERS:  interrupt_number     - Interrupt for a GPE block
+ * PARAMETERS:  interrupt_number            - Interrupt for a GPE block
  *
  * RETURN:      A GPE interrupt block
  *
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index 1b111ef74903..a5687540e9a6 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -264,13 +264,6 @@ void acpi_ev_terminate(void)
 
 		status = acpi_ev_walk_gpe_list(acpi_hw_disable_gpe_block, NULL);
 
-		/* Remove SCI handler */
-
-		status = acpi_ev_remove_sci_handler();
-		if (ACPI_FAILURE(status)) {
-			ACPI_ERROR((AE_INFO, "Could not remove SCI handler"));
-		}
-
 		status = acpi_ev_remove_global_lock_handler();
 		if (ACPI_FAILURE(status)) {
 			ACPI_ERROR((AE_INFO,
@@ -280,6 +273,13 @@ void acpi_ev_terminate(void)
 		acpi_gbl_events_initialized = FALSE;
 	}
 
+	/* Remove SCI handlers */
+
+	status = acpi_ev_remove_all_sci_handlers();
+	if (ACPI_FAILURE(status)) {
+		ACPI_ERROR((AE_INFO, "Could not remove SCI handler"));
+	}
+
 	/* Deallocate all handler objects installed within GPE info structs */
 
 	status = acpi_ev_walk_gpe_list(acpi_ev_delete_gpe_handlers, NULL);
diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index b905acf7aacd..b2f0fb2f57b4 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -52,6 +52,52 @@ ACPI_MODULE_NAME("evsci")
 /* Local prototypes */
 static u32 ACPI_SYSTEM_XFACE acpi_ev_sci_xrupt_handler(void *context);
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_sci_dispatch
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status code indicates whether interrupt was handled.
+ *
+ * DESCRIPTION: Dispatch the SCI to all host-installed SCI handlers.
+ *
+ ******************************************************************************/
+
+u32 acpi_ev_sci_dispatch(void)
+{
+	struct acpi_sci_handler_info *sci_handler;
+	acpi_cpu_flags flags;
+	u32 int_status = ACPI_INTERRUPT_NOT_HANDLED;
+
+	ACPI_FUNCTION_NAME(ev_sci_dispatch);
+
+	/* Are there any host-installed SCI handlers? */
+
+	if (!acpi_gbl_sci_handler_list) {
+		return (int_status);
+	}
+
+	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+
+	/* Invoke all host-installed SCI handlers */
+
+	sci_handler = acpi_gbl_sci_handler_list;
+	while (sci_handler) {
+
+		/* Invoke the installed handler (at interrupt level) */
+
+		int_status |= sci_handler->address((u32)acpi_gbl_FADT.
+						   sci_interrupt,
+						   sci_handler->context);
+
+		sci_handler = sci_handler->next;
+	}
+
+	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
+	return (int_status);
+}
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ev_sci_xrupt_handler
@@ -89,6 +135,10 @@ static u32 ACPI_SYSTEM_XFACE acpi_ev_sci_xrupt_handler(void *context)
 	 */
 	interrupt_handled |= acpi_ev_gpe_detect(gpe_xrupt_list);
 
+	/* Invoke all host-installed SCI handlers */
+
+	interrupt_handled |= acpi_ev_sci_dispatch();
+
 	return_UINT32(interrupt_handled);
 }
 
@@ -112,14 +162,13 @@ u32 ACPI_SYSTEM_XFACE acpi_ev_gpe_xrupt_handler(void *context)
 	ACPI_FUNCTION_TRACE(ev_gpe_xrupt_handler);
 
 	/*
-	 * We are guaranteed by the ACPI CA initialization/shutdown code that
+	 * We are guaranteed by the ACPICA initialization/shutdown code that
 	 * if this interrupt handler is installed, ACPI is enabled.
 	 */
 
 	/* GPEs: Check for and dispatch any GPEs that have occurred */
 
 	interrupt_handled |= acpi_ev_gpe_detect(gpe_xrupt_list);
-
 	return_UINT32(interrupt_handled);
 }
 
@@ -150,15 +199,15 @@ u32 acpi_ev_install_sci_handler(void)
 
 /******************************************************************************
  *
- * FUNCTION:    acpi_ev_remove_sci_handler
+ * FUNCTION:    acpi_ev_remove_all_sci_handlers
  *
  * PARAMETERS:  none
  *
- * RETURN:      E_OK if handler uninstalled OK, E_ERROR if handler was not
+ * RETURN:      AE_OK if handler uninstalled, AE_ERROR if handler was not
  *              installed to begin with
  *
  * DESCRIPTION: Remove the SCI interrupt handler. No further SCIs will be
- *              taken.
+ *              taken. Remove all host-installed SCI handlers.
  *
  * Note:  It doesn't seem important to disable all events or set the event
  *        enable registers to their original values. The OS should disable
@@ -167,11 +216,13 @@ u32 acpi_ev_install_sci_handler(void)
  *
  ******************************************************************************/
 
-acpi_status acpi_ev_remove_sci_handler(void)
+acpi_status acpi_ev_remove_all_sci_handlers(void)
 {
+	struct acpi_sci_handler_info *sci_handler;
+	acpi_cpu_flags flags;
 	acpi_status status;
 
-	ACPI_FUNCTION_TRACE(ev_remove_sci_handler);
+	ACPI_FUNCTION_TRACE(ev_remove_all_sci_handlers);
 
 	/* Just let the OS remove the handler and disable the level */
 
@@ -179,6 +230,21 @@ acpi_status acpi_ev_remove_sci_handler(void)
 	    acpi_os_remove_interrupt_handler((u32) acpi_gbl_FADT.sci_interrupt,
 					     acpi_ev_sci_xrupt_handler);
 
+	if (!acpi_gbl_sci_handler_list) {
+		return (status);
+	}
+
+	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+
+	/* Free all host-installed SCI handlers */
+
+	while (acpi_gbl_sci_handler_list) {
+		sci_handler = acpi_gbl_sci_handler_list;
+		acpi_gbl_sci_handler_list = sci_handler->next;
+		ACPI_FREE(sci_handler);
+	}
+
+	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index ca5fba99c33b..6f56146a6f88 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -383,6 +383,144 @@ ACPI_EXPORT_SYMBOL(acpi_install_exception_handler)
 #endif				/*  ACPI_FUTURE_USAGE  */
 
 #if (!ACPI_REDUCED_HARDWARE)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_install_sci_handler
+ *
+ * PARAMETERS:  address             - Address of the handler
+ *              context             - Value passed to the handler on each SCI
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Install a handler for a System Control Interrupt.
+ *
+ ******************************************************************************/
+acpi_status acpi_install_sci_handler(acpi_sci_handler address, void *context)
+{
+	struct acpi_sci_handler_info *new_sci_handler;
+	struct acpi_sci_handler_info *sci_handler;
+	acpi_cpu_flags flags;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_sci_handler);
+
+	if (!address) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	/* Allocate and init a handler object */
+
+	new_sci_handler = ACPI_ALLOCATE(sizeof(struct acpi_sci_handler_info));
+	if (!new_sci_handler) {
+		return_ACPI_STATUS(AE_NO_MEMORY);
+	}
+
+	new_sci_handler->address = address;
+	new_sci_handler->context = context;
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		goto exit;
+	}
+
+	/* Lock list during installation */
+
+	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+	sci_handler = acpi_gbl_sci_handler_list;
+
+	/* Ensure handler does not already exist */
+
+	while (sci_handler) {
+		if (address == sci_handler->address) {
+			status = AE_ALREADY_EXISTS;
+			goto unlock_and_exit;
+		}
+
+		sci_handler = sci_handler->next;
+	}
+
+	/* Install the new handler into the global list (at head) */
+
+	new_sci_handler->next = acpi_gbl_sci_handler_list;
+	acpi_gbl_sci_handler_list = new_sci_handler;
+
+      unlock_and_exit:
+
+	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+
+      exit:
+	if (ACPI_FAILURE(status)) {
+		ACPI_FREE(new_sci_handler);
+	}
+	return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_remove_sci_handler
+ *
+ * PARAMETERS:  address             - Address of the handler
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Remove a handler for a System Control Interrupt.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_remove_sci_handler(acpi_sci_handler address)
+{
+	struct acpi_sci_handler_info *prev_sci_handler;
+	struct acpi_sci_handler_info *next_sci_handler;
+	acpi_cpu_flags flags;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_remove_sci_handler);
+
+	if (!address) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Remove the SCI handler with lock */
+
+	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
+
+	prev_sci_handler = NULL;
+	next_sci_handler = acpi_gbl_sci_handler_list;
+	while (next_sci_handler) {
+		if (next_sci_handler->address == address) {
+
+			/* Unlink and free the SCI handler info block */
+
+			if (prev_sci_handler) {
+				prev_sci_handler->next = next_sci_handler->next;
+			} else {
+				acpi_gbl_sci_handler_list =
+				    next_sci_handler->next;
+			}
+
+			acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
+			ACPI_FREE(next_sci_handler);
+			goto unlock_and_exit;
+		}
+
+		prev_sci_handler = next_sci_handler;
+		next_sci_handler = next_sci_handler->next;
+	}
+
+	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
+	status = AE_NOT_EXIST;
+
+      unlock_and_exit:
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+	return_ACPI_STATUS(status);
+}
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_global_event_handler
@@ -398,6 +536,7 @@ ACPI_EXPORT_SYMBOL(acpi_install_exception_handler)
  *              Can be used to update event counters, etc.
  *
  ******************************************************************************/
+
 acpi_status
 acpi_install_global_event_handler(acpi_gbl_event_handler handler, void *context)
 {
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index d6f26bf8a062..046d5b059c07 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -291,7 +291,7 @@ acpi_status acpi_ut_init_globals(void)
 
 #if (!ACPI_REDUCED_HARDWARE)
 
-	/* GPE support */
+	/* GPE/SCI support */
 
 	acpi_gbl_all_gpes_initialized = FALSE;
 	acpi_gbl_gpe_xrupt_list_head = NULL;
@@ -300,6 +300,7 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_current_gpe_count = 0;
 
 	acpi_gbl_global_event_handler = NULL;
+	acpi_gbl_sci_handler_list = NULL;
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 85bfdbe17805..55a4d3ae1477 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -280,9 +280,16 @@ acpi_status
 acpi_install_initialization_handler(acpi_init_handler handler, u32 function);
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
-				acpi_install_global_event_handler
-				(acpi_gbl_event_handler handler, void *context))
-
+				acpi_install_sci_handler(acpi_sci_handler
+							 address,
+							 void *context))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_remove_sci_handler(acpi_sci_handler
+							 address))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_install_global_event_handler
+				 (acpi_gbl_event_handler handler,
+				  void *context))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_install_fixed_event_handler(u32
 								  acpi_event,
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index b748aefce929..850f75027fb6 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -945,6 +945,9 @@ typedef void
 /*
  * Various handlers and callback procedures
  */
+typedef
+u32 (*acpi_sci_handler) (u32 interrupt_number, void *context);
+
 typedef
 void (*acpi_gbl_event_handler) (u32 event_type,
 			       acpi_handle device,
-- 
cgit 


From cacba8657351f709ab3cb53a2b207f513f14054c Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Mon, 23 Sep 2013 09:52:34 +0800
Subject: ACPICA: Tables: Cleanup RSDP signature codes.

This patch introduces new macors to handle RSDP signature and cleans up the
affected codes.  Lv Zheng.
Some updates are only used for ACPICA utilities which are not shipped in
the kernel yet.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/tbprint.c  | 2 +-
 drivers/acpi/acpica/tbxfroot.c | 3 +--
 include/acpi/actypes.h         | 5 +++++
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 499759a23b41..9a47715af1f3 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -138,7 +138,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 		ACPI_INFO((AE_INFO, "%4.4s %p %05X",
 			   header->signature, ACPI_CAST_PTR(void, address),
 			   header->length));
-	} else if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_RSDP)) {
+	} else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) {
 
 		/* RSDP has no common fields */
 
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 948c95e80d44..1c95fabbe6a4 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -68,8 +68,7 @@ acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
 	 * Note: Sometimes there exists more than one RSDP in memory; the valid
 	 * RSDP has a valid checksum, all others have an invalid checksum.
 	 */
-	if (ACPI_STRNCMP((char *)rsdp->signature, ACPI_SIG_RSDP,
-			 sizeof(ACPI_SIG_RSDP) - 1) != 0) {
+	if (!ACPI_VALIDATE_RSDP_SIG(rsdp->signature)) {
 
 		/* Nope, BAD Signature */
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 850f75027fb6..54006720af8e 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -474,6 +474,11 @@ typedef u64 acpi_integer;
 #define ACPI_MOVE_NAME(dest,src)        (ACPI_STRNCPY (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
 #endif
 
+/* Support for the special RSDP signature (8 characters) */
+
+#define ACPI_VALIDATE_RSDP_SIG(a)       (!ACPI_STRNCMP (ACPI_CAST_PTR (char, (a)), ACPI_SIG_RSDP, 8))
+#define ACPI_MAKE_RSDP_SIG(dest)        (ACPI_MEMCPY (ACPI_CAST_PTR (char, (dest)), ACPI_SIG_RSDP, 8))
+
 /*******************************************************************************
  *
  * Miscellaneous constants
-- 
cgit 


From 31e93a166c7cfa6d5ff0bae0c19f0541f06f2260 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Mon, 23 Sep 2013 09:52:40 +0800
Subject: ACPICA: Cleanup exception codes.

This patch adds AE_ACCESS for EACCES or EPERM.  Some error prompts are
also cleaned up in this patch.  Lv Zheng.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acexcep.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index cf051e05a8fe..4e280bd226dd 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -125,8 +125,9 @@ struct acpi_exception_info {
 #define AE_NO_HANDLER                   EXCEP_ENV (0x001A)
 #define AE_OWNER_ID_LIMIT               EXCEP_ENV (0x001B)
 #define AE_NOT_CONFIGURED               EXCEP_ENV (0x001C)
+#define AE_ACCESS                       EXCEP_ENV (0x001D)
 
-#define AE_CODE_ENV_MAX                 0x001C
+#define AE_CODE_ENV_MAX                 0x001D
 
 /*
  * Programmer exceptions
@@ -227,7 +228,7 @@ static const struct acpi_exception_info acpi_gbl_exception_names_env[] = {
 	EXCEP_TXT("AE_NO_ACPI_TABLES", "ACPI tables could not be found"),
 	EXCEP_TXT("AE_NO_NAMESPACE", "A namespace has not been loaded"),
 	EXCEP_TXT("AE_NO_MEMORY", "Insufficient dynamic memory"),
-	EXCEP_TXT("AE_NOT_FOUND", "The name was not found in the namespace"),
+	EXCEP_TXT("AE_NOT_FOUND", "A requested entity is not found"),
 	EXCEP_TXT("AE_NOT_EXIST", "A required entity does not exist"),
 	EXCEP_TXT("AE_ALREADY_EXISTS", "An entity already exists"),
 	EXCEP_TXT("AE_TYPE", "The object type is incorrect"),
@@ -259,7 +260,8 @@ static const struct acpi_exception_info acpi_gbl_exception_names_env[] = {
 	EXCEP_TXT("AE_OWNER_ID_LIMIT",
 		  "There are no more Owner IDs available for ACPI tables or control methods"),
 	EXCEP_TXT("AE_NOT_CONFIGURED",
-		  "The interface is not part of the current subsystem configuration")
+		  "The interface is not part of the current subsystem configuration"),
+	EXCEP_TXT("AE_ACCESS", "Permission denied for the requested operation")
 };
 
 static const struct acpi_exception_info acpi_gbl_exception_names_pgm[] = {
-- 
cgit 


From c53ae3a60c2494a160140d09637f543562626365 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 23 Sep 2013 09:52:45 +0800
Subject: ACPICA: SCI Handlers: Update handler interface, eliminate unnecessary
 argument.

The SCI interrupt number is not needed for the SCI handlers, and was
just unnecessary overhead.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/evsci.c | 4 +---
 include/acpi/actypes.h      | 2 +-
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index b2f0fb2f57b4..94d9ebddf575 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -87,9 +87,7 @@ u32 acpi_ev_sci_dispatch(void)
 
 		/* Invoke the installed handler (at interrupt level) */
 
-		int_status |= sci_handler->address((u32)acpi_gbl_FADT.
-						   sci_interrupt,
-						   sci_handler->context);
+		int_status |= sci_handler->address(sci_handler->context);
 
 		sci_handler = sci_handler->next;
 	}
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 54006720af8e..f6abf23ad0a7 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -951,7 +951,7 @@ typedef void
  * Various handlers and callback procedures
  */
 typedef
-u32 (*acpi_sci_handler) (u32 interrupt_number, void *context);
+u32 (*acpi_sci_handler) (void *context);
 
 typedef
 void (*acpi_gbl_event_handler) (u32 event_type,
-- 
cgit 


From 94d7ba991fe0dd245babc8f227ad5fabe234303f Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 23 Sep 2013 09:52:53 +0800
Subject: ACPICA: Update version to 20130823.

Version 20130823.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 55a4d3ae1477..c7b1475422b3 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20130725
+#define ACPI_CA_VERSION                 0x20130823
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit 


From 2ff2a7d03bbe472ed44a8380dbdbea490d81c59d Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Mon, 23 Sep 2013 16:57:03 +0800
Subject: cgroup: kill css_id

The only user of css_id was memcg, and it has been convered to use
cgroup->id, so kill css_id.

Signed-off-by: Li Zefan <lizefan@huwei.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h |  37 --------
 kernel/cgroup.c        | 248 +------------------------------------------------
 2 files changed, 1 insertion(+), 284 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3561d305b1e0..39c1d9469677 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -612,11 +612,6 @@ struct cgroup_subsys {
 	int subsys_id;
 	int disabled;
 	int early_init;
-	/*
-	 * True if this subsys uses ID. ID is not available before cgroup_init()
-	 * (not available in early_init time.)
-	 */
-	bool use_id;
 
 	/*
 	 * If %false, this subsystem is properly hierarchical -
@@ -642,9 +637,6 @@ struct cgroup_subsys {
 	 */
 	struct cgroupfs_root *root;
 	struct list_head sibling;
-	/* used when use_id == true */
-	struct idr idr;
-	spinlock_t id_lock;
 
 	/* list of cftype_sets */
 	struct list_head cftsets;
@@ -875,35 +867,6 @@ int css_scan_tasks(struct cgroup_subsys_state *css,
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
-/*
- * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
- * if cgroup_subsys.use_id == true. It can be used for looking up and scanning.
- * CSS ID is assigned at cgroup allocation (create) automatically
- * and removed when subsys calls free_css_id() function. This is because
- * the lifetime of cgroup_subsys_state is subsys's matter.
- *
- * Looking up and scanning function should be called under rcu_read_lock().
- * Taking cgroup_mutex is not necessary for following calls.
- * But the css returned by this routine can be "not populated yet" or "being
- * destroyed". The caller should check css and cgroup's status.
- */
-
-/*
- * Typically Called at ->destroy(), or somewhere the subsys frees
- * cgroup_subsys_state.
- */
-void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css);
-
-/* Find a cgroup_subsys_state which has given ID */
-
-struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id);
-
-/* Returns true if root is ancestor of cg */
-bool css_is_ancestor(struct cgroup_subsys_state *cg,
-		     const struct cgroup_subsys_state *root);
-
-/* Get id and depth of css */
-unsigned short css_id(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
 					 struct cgroup_subsys *ss);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2418b6e71a85..a5629f1df13a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -124,38 +124,6 @@ struct cfent {
 	struct simple_xattrs		xattrs;
 };
 
-/*
- * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
- * cgroup_subsys->use_id != 0.
- */
-#define CSS_ID_MAX	(65535)
-struct css_id {
-	/*
-	 * The css to which this ID points. This pointer is set to valid value
-	 * after cgroup is populated. If cgroup is removed, this will be NULL.
-	 * This pointer is expected to be RCU-safe because destroy()
-	 * is called after synchronize_rcu(). But for safe use, css_tryget()
-	 * should be used for avoiding race.
-	 */
-	struct cgroup_subsys_state __rcu *css;
-	/*
-	 * ID of this css.
-	 */
-	unsigned short id;
-	/*
-	 * Depth in hierarchy which this ID belongs to.
-	 */
-	unsigned short depth;
-	/*
-	 * ID is freed by RCU. (and lookup routine is RCU safe.)
-	 */
-	struct rcu_head rcu_head;
-	/*
-	 * Hierarchy of CSS ID belongs to.
-	 */
-	unsigned short stack[0]; /* Array of Length (depth+1) */
-};
-
 /*
  * cgroup_event represents events which userspace want to receive.
  */
@@ -387,9 +355,6 @@ struct cgrp_cset_link {
 static struct css_set init_css_set;
 static struct cgrp_cset_link init_cgrp_cset_link;
 
-static int cgroup_init_idr(struct cgroup_subsys *ss,
-			   struct cgroup_subsys_state *css);
-
 /*
  * css_set_lock protects the list of css_set objects, and the chain of
  * tasks off each css_set.  Nests outside task->alloc_lock due to
@@ -841,8 +806,6 @@ static struct backing_dev_info cgroup_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
-static int alloc_css_id(struct cgroup_subsys_state *child_css);
-
 static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -4242,21 +4205,6 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 				goto err;
 		}
 	}
-
-	/* This cgroup is ready now */
-	for_each_root_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-		struct css_id *id = rcu_dereference_protected(css->id, true);
-
-		/*
-		 * Update id->css pointer and make this css visible from
-		 * CSS ID functions. This pointer will be dereferened
-		 * from RCU-read-side without locks.
-		 */
-		if (id)
-			rcu_assign_pointer(id->css, css);
-	}
-
 	return 0;
 err:
 	cgroup_clear_dir(cgrp, subsys_mask);
@@ -4325,7 +4273,6 @@ static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss,
 	css->cgroup = cgrp;
 	css->ss = ss;
 	css->flags = 0;
-	css->id = NULL;
 
 	if (cgrp->parent)
 		css->parent = cgroup_css(cgrp->parent, ss);
@@ -4457,12 +4404,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			goto err_free_all;
 
 		init_css(css, ss, cgrp);
-
-		if (ss->use_id) {
-			err = alloc_css_id(css);
-			if (err)
-				goto err_free_all;
-		}
 	}
 
 	/*
@@ -4927,12 +4868,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 
 	/* our new subsystem will be attached to the dummy hierarchy. */
 	init_css(css, ss, cgroup_dummy_top);
-	/* init_idr must be after init_css() because it sets css->id. */
-	if (ss->use_id) {
-		ret = cgroup_init_idr(ss, css);
-		if (ret)
-			goto err_unload;
-	}
 
 	/*
 	 * Now we need to entangle the css into the existing css_sets. unlike
@@ -4998,9 +4933,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 
 	offline_css(cgroup_css(cgroup_dummy_top, ss));
 
-	if (ss->use_id)
-		idr_destroy(&ss->idr);
-
 	/* deassign the subsys_id */
 	cgroup_subsys[ss->subsys_id] = NULL;
 
@@ -5027,8 +4959,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	/*
 	 * remove subsystem's css from the cgroup_dummy_top and free it -
 	 * need to free before marking as null because ss->css_free needs
-	 * the cgrp->subsys pointer to find their state. note that this
-	 * also takes care of freeing the css_id.
+	 * the cgrp->subsys pointer to find their state.
 	 */
 	ss->css_free(cgroup_css(cgroup_dummy_top, ss));
 	RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
@@ -5099,8 +5030,6 @@ int __init cgroup_init(void)
 	for_each_builtin_subsys(ss, i) {
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
-		if (ss->use_id)
-			cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
 	}
 
 	/* allocate id for the dummy hierarchy */
@@ -5520,181 +5449,6 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
-/*
- * Functons for CSS ID.
- */
-
-/* to get ID other than 0, this should be called when !cgroup_is_dead() */
-unsigned short css_id(struct cgroup_subsys_state *css)
-{
-	struct css_id *cssid;
-
-	/*
-	 * This css_id() can return correct value when somone has refcnt
-	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
-	 * it's unchanged until freed.
-	 */
-	cssid = rcu_dereference_raw(css->id);
-
-	if (cssid)
-		return cssid->id;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(css_id);
-
-/**
- *  css_is_ancestor - test "root" css is an ancestor of "child"
- * @child: the css to be tested.
- * @root: the css supporsed to be an ancestor of the child.
- *
- * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
- * this function reads css->id, the caller must hold rcu_read_lock().
- * But, considering usual usage, the csses should be valid objects after test.
- * Assuming that the caller will do some action to the child if this returns
- * returns true, the caller must take "child";s reference count.
- * If "child" is valid object and this returns true, "root" is valid, too.
- */
-
-bool css_is_ancestor(struct cgroup_subsys_state *child,
-		    const struct cgroup_subsys_state *root)
-{
-	struct css_id *child_id;
-	struct css_id *root_id;
-
-	child_id  = rcu_dereference(child->id);
-	if (!child_id)
-		return false;
-	root_id = rcu_dereference(root->id);
-	if (!root_id)
-		return false;
-	if (child_id->depth < root_id->depth)
-		return false;
-	if (child_id->stack[root_id->depth] != root_id->id)
-		return false;
-	return true;
-}
-
-void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
-{
-	struct css_id *id = rcu_dereference_protected(css->id, true);
-
-	/* When this is called before css_id initialization, id can be NULL */
-	if (!id)
-		return;
-
-	BUG_ON(!ss->use_id);
-
-	rcu_assign_pointer(id->css, NULL);
-	rcu_assign_pointer(css->id, NULL);
-	spin_lock(&ss->id_lock);
-	idr_remove(&ss->idr, id->id);
-	spin_unlock(&ss->id_lock);
-	kfree_rcu(id, rcu_head);
-}
-EXPORT_SYMBOL_GPL(free_css_id);
-
-/*
- * This is called by init or create(). Then, calls to this function are
- * always serialized (By cgroup_mutex() at create()).
- */
-
-static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
-{
-	struct css_id *newid;
-	int ret, size;
-
-	BUG_ON(!ss->use_id);
-
-	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
-	newid = kzalloc(size, GFP_KERNEL);
-	if (!newid)
-		return ERR_PTR(-ENOMEM);
-
-	idr_preload(GFP_KERNEL);
-	spin_lock(&ss->id_lock);
-	/* Don't use 0. allocates an ID of 1-65535 */
-	ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT);
-	spin_unlock(&ss->id_lock);
-	idr_preload_end();
-
-	/* Returns error when there are no free spaces for new ID.*/
-	if (ret < 0)
-		goto err_out;
-
-	newid->id = ret;
-	newid->depth = depth;
-	return newid;
-err_out:
-	kfree(newid);
-	return ERR_PTR(ret);
-
-}
-
-static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
-					    struct cgroup_subsys_state *rootcss)
-{
-	struct css_id *newid;
-
-	spin_lock_init(&ss->id_lock);
-	idr_init(&ss->idr);
-
-	newid = get_new_cssid(ss, 0);
-	if (IS_ERR(newid))
-		return PTR_ERR(newid);
-
-	newid->stack[0] = newid->id;
-	RCU_INIT_POINTER(newid->css, rootcss);
-	RCU_INIT_POINTER(rootcss->id, newid);
-	return 0;
-}
-
-static int alloc_css_id(struct cgroup_subsys_state *child_css)
-{
-	struct cgroup_subsys_state *parent_css = css_parent(child_css);
-	struct css_id *child_id, *parent_id;
-	int i, depth;
-
-	parent_id = rcu_dereference_protected(parent_css->id, true);
-	depth = parent_id->depth + 1;
-
-	child_id = get_new_cssid(child_css->ss, depth);
-	if (IS_ERR(child_id))
-		return PTR_ERR(child_id);
-
-	for (i = 0; i < depth; i++)
-		child_id->stack[i] = parent_id->stack[i];
-	child_id->stack[depth] = child_id->id;
-	/*
-	 * child_id->css pointer will be set after this cgroup is available
-	 * see cgroup_populate_dir()
-	 */
-	rcu_assign_pointer(child_css->id, child_id);
-
-	return 0;
-}
-
-/**
- * css_lookup - lookup css by id
- * @ss: cgroup subsys to be looked into.
- * @id: the id
- *
- * Returns pointer to cgroup_subsys_state if there is valid one with id.
- * NULL if not. Should be called under rcu_read_lock()
- */
-struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
-{
-	struct css_id *cssid = NULL;
-
-	BUG_ON(!ss->use_id);
-	cssid = idr_find(&ss->idr, id);
-
-	if (unlikely(!cssid))
-		return NULL;
-
-	return rcu_dereference(cssid->css);
-}
-EXPORT_SYMBOL_GPL(css_lookup);
-
 /**
  * css_from_dir - get corresponding css from the dentry of a cgroup dir
  * @dentry: directory dentry of interest
-- 
cgit 


From 118150f22d6b4431a1fe2e715de314a5d93836f5 Mon Sep 17 00:00:00 2001
From: KV Sujith <sujithkv@ti.com>
Date: Sun, 18 Aug 2013 10:48:58 +0530
Subject: gpio: davinci: move to platform device

Modify DaVinci GPIO driver to become a platform device
driver.

The driver does not have platform driver structure or
a probe. Instead, it has pure_initcall function for
initialization. The platform specific informaiton is
obtained using the DaVinci specific davinci_soc_info
structure. This is a problem for Device Tree (DT)
implementation.

As a first stage of DT conversion, we implement a probe.

Additional notes:

- The driver registration happens as  postcore_initcall.
  This is required since machine init functions like
  da850_lcd_hw_init() make use of GPIO.
- Start using devres APIs for simpler error handling.

Signed-off-by: KV Sujith <sujithkv@ti.com>
[avinashphilip@ti.com: Move global definition of
		       "davinci_gpio_controller" to local]
Signed-off-by: Philip Avinash <avinashphilip@ti.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
[nsekhar@ti.com: drop unused structure member, rebase to new
		 clean-up patch and fix error messages]
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
---
 arch/arm/mach-davinci/include/mach/gpio-davinci.h |   1 +
 drivers/gpio/gpio-davinci.c                       | 119 +++++++++++++++-------
 include/linux/platform_data/gpio-davinci.h        |  25 +++++
 3 files changed, 107 insertions(+), 38 deletions(-)
 create mode 100644 include/linux/platform_data/gpio-davinci.h

(limited to 'include')

diff --git a/arch/arm/mach-davinci/include/mach/gpio-davinci.h b/arch/arm/mach-davinci/include/mach/gpio-davinci.h
index 1fdd1fd35448..551ba43a763e 100644
--- a/arch/arm/mach-davinci/include/mach/gpio-davinci.h
+++ b/arch/arm/mach-davinci/include/mach/gpio-davinci.h
@@ -60,6 +60,7 @@ struct davinci_gpio_controller {
 	void __iomem		*set_data;
 	void __iomem		*clr_data;
 	void __iomem		*in_data;
+	unsigned		gpio_irq;
 };
 
 /* The __gpio_to_controller() and __gpio_mask() functions inline to constants
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index cb947a1266ae..8847adf392b7 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -15,8 +15,9 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-
-#include <asm/mach/irq.h>
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/gpio-davinci.h>
 
 struct davinci_gpio_regs {
 	u32	dir;
@@ -36,10 +37,9 @@ struct davinci_gpio_regs {
 #define chip2controller(chip)	\
 	container_of(chip, struct davinci_gpio_controller, chip)
 
-static struct davinci_gpio_controller chips[DIV_ROUND_UP(DAVINCI_N_GPIO, 32)];
 static void __iomem *gpio_base;
 
-static struct davinci_gpio_regs __iomem __init *gpio2regs(unsigned gpio)
+static struct davinci_gpio_regs __iomem *gpio2regs(unsigned gpio)
 {
 	void __iomem *ptr;
 
@@ -67,7 +67,7 @@ static inline struct davinci_gpio_regs __iomem *irq2regs(int irq)
 	return g;
 }
 
-static int __init davinci_gpio_irq_setup(void);
+static int davinci_gpio_irq_setup(struct platform_device *pdev);
 
 /*--------------------------------------------------------------------------*/
 
@@ -133,33 +133,53 @@ davinci_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	__raw_writel((1 << offset), value ? &g->set_data : &g->clr_data);
 }
 
-static int __init davinci_gpio_setup(void)
+static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	int i, base;
 	unsigned ngpio;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
-	struct davinci_gpio_regs *regs;
-
-	if (soc_info->gpio_type != GPIO_TYPE_DAVINCI)
-		return 0;
+	struct davinci_gpio_controller *chips;
+	struct davinci_gpio_platform_data *pdata;
+	struct davinci_gpio_regs __iomem *regs;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+
+	pdata = dev->platform_data;
+	if (!pdata) {
+		dev_err(dev, "No platform data found\n");
+		return -EINVAL;
+	}
 
 	/*
 	 * The gpio banks conceptually expose a segmented bitmap,
 	 * and "ngpio" is one more than the largest zero-based
 	 * bit index that's valid.
 	 */
-	ngpio = soc_info->gpio_num;
+	ngpio = pdata->ngpio;
 	if (ngpio == 0) {
-		pr_err("GPIO setup:  how many GPIOs?\n");
+		dev_err(dev, "How many GPIOs?\n");
 		return -EINVAL;
 	}
 
 	if (WARN_ON(DAVINCI_N_GPIO < ngpio))
 		ngpio = DAVINCI_N_GPIO;
 
-	gpio_base = ioremap(soc_info->gpio_base, SZ_4K);
-	if (WARN_ON(!gpio_base))
+	chips = devm_kzalloc(dev,
+			     ngpio * sizeof(struct davinci_gpio_controller),
+			     GFP_KERNEL);
+	if (!chips) {
+		dev_err(dev, "Memory allocation failed\n");
 		return -ENOMEM;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "Invalid memory resource\n");
+		return -EBUSY;
+	}
+
+	gpio_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(gpio_base))
+		return PTR_ERR(gpio_base);
 
 	for (i = 0, base = 0; base < ngpio; i++, base += 32) {
 		chips[i].chip.label = "DaVinci";
@@ -185,13 +205,10 @@ static int __init davinci_gpio_setup(void)
 		gpiochip_add(&chips[i].chip);
 	}
 
-	soc_info->gpio_ctlrs = chips;
-	soc_info->gpio_ctlrs_num = DIV_ROUND_UP(ngpio, 32);
-
-	davinci_gpio_irq_setup();
+	platform_set_drvdata(pdev, chips);
+	davinci_gpio_irq_setup(pdev);
 	return 0;
 }
-pure_initcall(davinci_gpio_setup);
 
 /*--------------------------------------------------------------------------*/
 /*
@@ -304,14 +321,14 @@ static int gpio_to_irq_banked(struct gpio_chip *chip, unsigned offset)
 
 static int gpio_to_irq_unbanked(struct gpio_chip *chip, unsigned offset)
 {
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
+	struct davinci_gpio_controller *d = chip2controller(chip);
 
 	/*
 	 * NOTE:  we assume for now that only irqs in the first gpio_chip
 	 * can provide direct-mapped IRQs to AINTC (up to 32 GPIOs).
 	 */
-	if (offset < soc_info->gpio_unbanked)
-		return soc_info->gpio_irq + offset;
+	if (offset < d->irq_base)
+		return d->gpio_irq + offset;
 	else
 		return -ENODEV;
 }
@@ -320,12 +337,11 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 {
 	struct davinci_gpio_controller *d;
 	struct davinci_gpio_regs __iomem *g;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
 	u32 mask;
 
 	d = (struct davinci_gpio_controller *)data->handler_data;
 	g = (struct davinci_gpio_regs __iomem *)d->regs;
-	mask = __gpio_mask(data->irq - soc_info->gpio_irq);
+	mask = __gpio_mask(data->irq - d->gpio_irq);
 
 	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		return -EINVAL;
@@ -346,24 +362,33 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
  * (dm6446) can be set appropriately for GPIOV33 pins.
  */
 
-static int __init davinci_gpio_irq_setup(void)
+static int davinci_gpio_irq_setup(struct platform_device *pdev)
 {
 	unsigned	gpio, irq, bank;
 	struct clk	*clk;
 	u32		binten = 0;
 	unsigned	ngpio, bank_irq;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
-	struct davinci_gpio_regs	__iomem *g;
+	struct device *dev = &pdev->dev;
+	struct resource	*res;
+	struct davinci_gpio_controller *chips = platform_get_drvdata(pdev);
+	struct davinci_gpio_platform_data *pdata = dev->platform_data;
+	struct davinci_gpio_regs __iomem *g;
 
-	ngpio = soc_info->gpio_num;
+	ngpio = pdata->ngpio;
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(dev, "Invalid IRQ resource\n");
+		return -EBUSY;
+	}
 
-	bank_irq = soc_info->gpio_irq;
-	if (bank_irq == 0) {
-		printk(KERN_ERR "Don't know first GPIO bank IRQ.\n");
-		return -EINVAL;
+	bank_irq = res->start;
+
+	if (!bank_irq) {
+		dev_err(dev, "Invalid IRQ resource\n");
+		return -ENODEV;
 	}
 
-	clk = clk_get(NULL, "gpio");
+	clk = devm_clk_get(dev, "gpio");
 	if (IS_ERR(clk)) {
 		printk(KERN_ERR "Error %ld getting gpio clock?\n",
 		       PTR_ERR(clk));
@@ -379,9 +404,9 @@ static int __init davinci_gpio_irq_setup(void)
 	 */
 	for (gpio = 0, bank = 0; gpio < ngpio; bank++, gpio += 32) {
 		chips[bank].chip.to_irq = gpio_to_irq_banked;
-		chips[bank].irq_base = soc_info->gpio_unbanked
+		chips[bank].irq_base = pdata->gpio_unbanked
 			? -EINVAL
-			: (soc_info->intc_irq_num + gpio);
+			: (pdata->intc_irq_num + gpio);
 	}
 
 	/*
@@ -389,7 +414,7 @@ static int __init davinci_gpio_irq_setup(void)
 	 * controller only handling trigger modes.  We currently assume no
 	 * IRQ mux conflicts; gpio_irq_type_unbanked() is only for GPIOs.
 	 */
-	if (soc_info->gpio_unbanked) {
+	if (pdata->gpio_unbanked) {
 		static struct irq_chip_type gpio_unbanked;
 
 		/* pass "bank 0" GPIO IRQs to AINTC */
@@ -409,7 +434,7 @@ static int __init davinci_gpio_irq_setup(void)
 		__raw_writel(~0, &g->set_rising);
 
 		/* set the direct IRQs up to use that irqchip */
-		for (gpio = 0; gpio < soc_info->gpio_unbanked; gpio++, irq++) {
+		for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++, irq++) {
 			irq_set_chip(irq, &gpio_unbanked.chip);
 			irq_set_handler_data(irq, &chips[gpio / 32]);
 			irq_set_status_flags(irq, IRQ_TYPE_EDGE_BOTH);
@@ -464,3 +489,21 @@ done:
 
 	return 0;
 }
+
+static struct platform_driver davinci_gpio_driver = {
+	.probe		= davinci_gpio_probe,
+	.driver		= {
+		.name	= "davinci_gpio",
+		.owner	= THIS_MODULE,
+	},
+};
+
+/**
+ * GPIO driver registration needs to be done before machine_init functions
+ * access GPIO. Hence davinci_gpio_drv_reg() is a postcore_initcall.
+ */
+static int __init davinci_gpio_drv_reg(void)
+{
+	return platform_driver_register(&davinci_gpio_driver);
+}
+postcore_initcall(davinci_gpio_drv_reg);
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
new file mode 100644
index 000000000000..2fcc125af1aa
--- /dev/null
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -0,0 +1,25 @@
+/*
+ * DaVinci GPIO Platform Related Defines
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DAVINCI_GPIO_PLATFORM_H
+#define __DAVINCI_GPIO_PLATFORM_H
+
+struct davinci_gpio_platform_data {
+	u32	ngpio;
+	u32	gpio_unbanked;
+	u32	intc_irq_num;
+};
+
+#endif
-- 
cgit 


From a5b4bd2874d9032b42db8cc4880058576c561b06 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:14 +0100
Subject: KEYS: Use bool in make_key_ref() and is_key_possessed()

Make make_key_ref() take a bool possession parameter and make
is_key_possessed() return a bool.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/security/keys.txt | 7 +++----
 include/linux/key.h             | 4 ++--
 security/keys/keyring.c         | 5 +++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 7b4145d00452..9ede67084f0b 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -865,15 +865,14 @@ encountered:
      calling processes has a searchable link to the key from one of its
      keyrings. There are three functions for dealing with these:
 
-	key_ref_t make_key_ref(const struct key *key,
-			       unsigned long possession);
+	key_ref_t make_key_ref(const struct key *key, bool possession);
 
 	struct key *key_ref_to_ptr(const key_ref_t key_ref);
 
-	unsigned long is_key_possessed(const key_ref_t key_ref);
+	bool is_key_possessed(const key_ref_t key_ref);
 
      The first function constructs a key reference from a key pointer and
-     possession information (which must be 0 or 1 and not any other value).
+     possession information (which must be true or false).
 
      The second function retrieves the key pointer from a reference and the
      third retrieves the possession flag.
diff --git a/include/linux/key.h b/include/linux/key.h
index 4dfde1161c5e..51bce2950de4 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -99,7 +99,7 @@ struct keyring_name;
 typedef struct __key_reference_with_attributes *key_ref_t;
 
 static inline key_ref_t make_key_ref(const struct key *key,
-				     unsigned long possession)
+				     bool possession)
 {
 	return (key_ref_t) ((unsigned long) key | possession);
 }
@@ -109,7 +109,7 @@ static inline struct key *key_ref_to_ptr(const key_ref_t key_ref)
 	return (struct key *) ((unsigned long) key_ref & ~1UL);
 }
 
-static inline unsigned long is_key_possessed(const key_ref_t key_ref)
+static inline bool is_key_possessed(const key_ref_t key_ref)
 {
 	return (unsigned long) key_ref & 1UL;
 }
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 6ece7f2e5707..f78406372ebe 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -329,9 +329,10 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	struct keyring_list *keylist;
 	struct timespec now;
-	unsigned long possessed, kflags;
+	unsigned long kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
+	bool possessed;
 	long err;
 	int sp, nkeys, kix;
 
@@ -542,8 +543,8 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 			       key_perm_t perm)
 {
 	struct keyring_list *klist;
-	unsigned long possessed;
 	struct key *keyring, *key;
+	bool possessed;
 	int nkeys, loop;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-- 
cgit 


From 16feef4340172b7dbb9cba60850e78fa6388adf1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:15 +0100
Subject: KEYS: Consolidate the concept of an 'index key' for key access

Consolidate the concept of an 'index key' for accessing keys.  The index key
is the search term needed to find a key directly - basically the key type and
the key description.  We can add to that the description length.

This will be useful when turning a keyring into an associative array rather
than just a pointer block.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/key.h         | 21 +++++++++----
 security/keys/internal.h    |  8 ++---
 security/keys/key.c         | 72 +++++++++++++++++++++++----------------------
 security/keys/keyring.c     | 37 +++++++++++------------
 security/keys/request_key.c | 12 +++++---
 5 files changed, 83 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/include/linux/key.h b/include/linux/key.h
index 51bce2950de4..d573e820a23d 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -82,6 +82,12 @@ struct key_owner;
 struct keyring_list;
 struct keyring_name;
 
+struct keyring_index_key {
+	struct key_type		*type;
+	const char		*description;
+	size_t			desc_len;
+};
+
 /*****************************************************************************/
 /*
  * key reference with possession attribute handling
@@ -129,7 +135,6 @@ struct key {
 		struct list_head graveyard_link;
 		struct rb_node	serial_node;
 	};
-	struct key_type		*type;		/* type of key */
 	struct rw_semaphore	sem;		/* change vs change sem */
 	struct key_user		*user;		/* owner of this key */
 	void			*security;	/* security data for this key */
@@ -163,12 +168,18 @@ struct key {
 #define KEY_FLAG_ROOT_CAN_CLEAR	6	/* set if key can be cleared by root without permission */
 #define KEY_FLAG_INVALIDATED	7	/* set if key has been invalidated */
 
-	/* the description string
-	 * - this is used to match a key against search criteria
-	 * - this should be a printable string
+	/* the key type and key description string
+	 * - the desc is used to match a key against search criteria
+	 * - it should be a printable string
 	 * - eg: for krb5 AFS, this might be "afs@REDHAT.COM"
 	 */
-	char			*description;
+	union {
+		struct keyring_index_key index_key;
+		struct {
+			struct key_type	*type;		/* type of key */
+			char		*description;
+		};
+	};
 
 	/* type specific data
 	 * - this is used by the keyring type to index the name
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 490aef5ba34b..77441dd1f9d4 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -89,19 +89,17 @@ extern struct key_type *key_type_lookup(const char *type);
 extern void key_type_put(struct key_type *ktype);
 
 extern int __key_link_begin(struct key *keyring,
-			    const struct key_type *type,
-			    const char *description,
+			    const struct keyring_index_key *index_key,
 			    unsigned long *_prealloc);
 extern int __key_link_check_live_key(struct key *keyring, struct key *key);
 extern void __key_link(struct key *keyring, struct key *key,
 		       unsigned long *_prealloc);
 extern void __key_link_end(struct key *keyring,
-			   struct key_type *type,
+			   const struct keyring_index_key *index_key,
 			   unsigned long prealloc);
 
 extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-				      const struct key_type *type,
-				      const char *description,
+				      const struct keyring_index_key *index_key,
 				      key_perm_t perm);
 
 extern struct key *keyring_search_instkey(struct key *keyring,
diff --git a/security/keys/key.c b/security/keys/key.c
index 8fb7c7bd4657..7e6bc396bb23 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -242,8 +242,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 		}
 	}
 
-	desclen = strlen(desc) + 1;
-	quotalen = desclen + type->def_datalen;
+	desclen = strlen(desc);
+	quotalen = desclen + 1 + type->def_datalen;
 
 	/* get hold of the key tracking for this user */
 	user = key_user_lookup(uid);
@@ -277,7 +277,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 		goto no_memory_2;
 
 	if (desc) {
-		key->description = kmemdup(desc, desclen, GFP_KERNEL);
+		key->index_key.desc_len = desclen;
+		key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL);
 		if (!key->description)
 			goto no_memory_3;
 	}
@@ -285,7 +286,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	atomic_set(&key->usage, 1);
 	init_rwsem(&key->sem);
 	lockdep_set_class(&key->sem, &type->lock_class);
-	key->type = type;
+	key->index_key.type = type;
 	key->user = user;
 	key->quotalen = quotalen;
 	key->datalen = type->def_datalen;
@@ -489,8 +490,7 @@ int key_instantiate_and_link(struct key *key,
 	}
 
 	if (keyring) {
-		ret = __key_link_begin(keyring, key->type, key->description,
-				       &prealloc);
+		ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 		if (ret < 0)
 			goto error_free_preparse;
 	}
@@ -499,7 +499,7 @@ int key_instantiate_and_link(struct key *key,
 					 &prealloc);
 
 	if (keyring)
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 
 error_free_preparse:
 	if (key->type->preparse)
@@ -548,8 +548,7 @@ int key_reject_and_link(struct key *key,
 	ret = -EBUSY;
 
 	if (keyring)
-		link_ret = __key_link_begin(keyring, key->type,
-					    key->description, &prealloc);
+		link_ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 
 	mutex_lock(&key_construction_mutex);
 
@@ -581,7 +580,7 @@ int key_reject_and_link(struct key *key,
 	mutex_unlock(&key_construction_mutex);
 
 	if (keyring)
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 
 	/* wake up anyone waiting for a key to be constructed */
 	if (awaken)
@@ -780,25 +779,27 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 			       key_perm_t perm,
 			       unsigned long flags)
 {
-	unsigned long prealloc;
+	struct keyring_index_key index_key = {
+		.description	= description,
+	};
 	struct key_preparsed_payload prep;
 	const struct cred *cred = current_cred();
-	struct key_type *ktype;
+	unsigned long prealloc;
 	struct key *keyring, *key = NULL;
 	key_ref_t key_ref;
 	int ret;
 
 	/* look up the key type to see if it's one of the registered kernel
 	 * types */
-	ktype = key_type_lookup(type);
-	if (IS_ERR(ktype)) {
+	index_key.type = key_type_lookup(type);
+	if (IS_ERR(index_key.type)) {
 		key_ref = ERR_PTR(-ENODEV);
 		goto error;
 	}
 
 	key_ref = ERR_PTR(-EINVAL);
-	if (!ktype->match || !ktype->instantiate ||
-	    (!description && !ktype->preparse))
+	if (!index_key.type->match || !index_key.type->instantiate ||
+	    (!index_key.description && !index_key.type->preparse))
 		goto error_put_type;
 
 	keyring = key_ref_to_ptr(keyring_ref);
@@ -812,21 +813,22 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	memset(&prep, 0, sizeof(prep));
 	prep.data = payload;
 	prep.datalen = plen;
-	prep.quotalen = ktype->def_datalen;
-	if (ktype->preparse) {
-		ret = ktype->preparse(&prep);
+	prep.quotalen = index_key.type->def_datalen;
+	if (index_key.type->preparse) {
+		ret = index_key.type->preparse(&prep);
 		if (ret < 0) {
 			key_ref = ERR_PTR(ret);
 			goto error_put_type;
 		}
-		if (!description)
-			description = prep.description;
+		if (!index_key.description)
+			index_key.description = prep.description;
 		key_ref = ERR_PTR(-EINVAL);
-		if (!description)
+		if (!index_key.description)
 			goto error_free_prep;
 	}
+	index_key.desc_len = strlen(index_key.description);
 
-	ret = __key_link_begin(keyring, ktype, description, &prealloc);
+	ret = __key_link_begin(keyring, &index_key, &prealloc);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
 		goto error_free_prep;
@@ -844,9 +846,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * key of the same type and description in the destination keyring and
 	 * update that instead if possible
 	 */
-	if (ktype->update) {
-		key_ref = __keyring_search_one(keyring_ref, ktype, description,
-					       0);
+	if (index_key.type->update) {
+		key_ref = __keyring_search_one(keyring_ref, &index_key, 0);
 		if (!IS_ERR(key_ref))
 			goto found_matching_key;
 	}
@@ -856,16 +857,17 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
 		perm |= KEY_USR_VIEW;
 
-		if (ktype->read)
+		if (index_key.type->read)
 			perm |= KEY_POS_READ;
 
-		if (ktype == &key_type_keyring || ktype->update)
+		if (index_key.type == &key_type_keyring ||
+		    index_key.type->update)
 			perm |= KEY_POS_WRITE;
 	}
 
 	/* allocate a new key */
-	key = key_alloc(ktype, description, cred->fsuid, cred->fsgid, cred,
-			perm, flags);
+	key = key_alloc(index_key.type, index_key.description,
+			cred->fsuid, cred->fsgid, cred, perm, flags);
 	if (IS_ERR(key)) {
 		key_ref = ERR_CAST(key);
 		goto error_link_end;
@@ -882,12 +884,12 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
 
 error_link_end:
-	__key_link_end(keyring, ktype, prealloc);
+	__key_link_end(keyring, &index_key, prealloc);
 error_free_prep:
-	if (ktype->preparse)
-		ktype->free_preparse(&prep);
+	if (index_key.type->preparse)
+		index_key.type->free_preparse(&prep);
 error_put_type:
-	key_type_put(ktype);
+	key_type_put(index_key.type);
 error:
 	return key_ref;
 
@@ -895,7 +897,7 @@ error:
 	/* we found a matching key, so we're going to try to update it
 	 * - we can drop the locks first as we have the key pinned
 	 */
-	__key_link_end(keyring, ktype, prealloc);
+	__key_link_end(keyring, &index_key, prealloc);
 
 	key_ref = __key_update(key_ref, &prep);
 	goto error_free_prep;
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index f78406372ebe..c7f59f9dd7b6 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -538,8 +538,7 @@ EXPORT_SYMBOL(keyring_search);
  * to the returned key reference.
  */
 key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-			       const struct key_type *ktype,
-			       const char *description,
+			       const struct keyring_index_key *index_key,
 			       key_perm_t perm)
 {
 	struct keyring_list *klist;
@@ -558,9 +557,9 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 		smp_rmb();
 		for (loop = 0; loop < nkeys ; loop++) {
 			key = rcu_dereference(klist->keys[loop]);
-			if (key->type == ktype &&
+			if (key->type == index_key->type &&
 			    (!key->type->match ||
-			     key->type->match(key, description)) &&
+			     key->type->match(key, index_key->description)) &&
 			    key_permission(make_key_ref(key, possessed),
 					   perm) == 0 &&
 			    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
@@ -747,8 +746,8 @@ static void keyring_unlink_rcu_disposal(struct rcu_head *rcu)
 /*
  * Preallocate memory so that a key can be linked into to a keyring.
  */
-int __key_link_begin(struct key *keyring, const struct key_type *type,
-		     const char *description, unsigned long *_prealloc)
+int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key,
+		     unsigned long *_prealloc)
 	__acquires(&keyring->sem)
 	__acquires(&keyring_serialise_link_sem)
 {
@@ -759,7 +758,8 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 	size_t size;
 	int loop, lru, ret;
 
-	kenter("%d,%s,%s,", key_serial(keyring), type->name, description);
+	kenter("%d,%s,%s,",
+	       key_serial(keyring), index_key->type->name, index_key->description);
 
 	if (keyring->type != &key_type_keyring)
 		return -ENOTDIR;
@@ -772,7 +772,7 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 
 	/* serialise link/link calls to prevent parallel calls causing a cycle
 	 * when linking two keyring in opposite orders */
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		down_write(&keyring_serialise_link_sem);
 
 	klist = rcu_dereference_locked_keyring(keyring);
@@ -784,8 +784,8 @@ int __key_link_begin(struct key *keyring, const struct key_type *type,
 		for (loop = klist->nkeys - 1; loop >= 0; loop--) {
 			struct key *key = rcu_deref_link_locked(klist, loop,
 								keyring);
-			if (key->type == type &&
-			    strcmp(key->description, description) == 0) {
+			if (key->type == index_key->type &&
+			    strcmp(key->description, index_key->description) == 0) {
 				/* Found a match - we'll replace the link with
 				 * one to the new key.  We record the slot
 				 * position.
@@ -865,7 +865,7 @@ error_quota:
 	key_payload_reserve(keyring,
 			    keyring->datalen - KEYQUOTA_LINK_BYTES);
 error_sem:
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 error_krsem:
 	up_write(&keyring->sem);
@@ -957,16 +957,17 @@ void __key_link(struct key *keyring, struct key *key,
  *
  * Must be called with __key_link_begin() having being called.
  */
-void __key_link_end(struct key *keyring, struct key_type *type,
+void __key_link_end(struct key *keyring,
+		    const struct keyring_index_key *index_key,
 		    unsigned long prealloc)
 	__releases(&keyring->sem)
 	__releases(&keyring_serialise_link_sem)
 {
-	BUG_ON(type == NULL);
-	BUG_ON(type->name == NULL);
-	kenter("%d,%s,%lx", keyring->serial, type->name, prealloc);
+	BUG_ON(index_key->type == NULL);
+	BUG_ON(index_key->type->name == NULL);
+	kenter("%d,%s,%lx", keyring->serial, index_key->type->name, prealloc);
 
-	if (type == &key_type_keyring)
+	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
 	if (prealloc) {
@@ -1007,12 +1008,12 @@ int key_link(struct key *keyring, struct key *key)
 	key_check(keyring);
 	key_check(key);
 
-	ret = __key_link_begin(keyring, key->type, key->description, &prealloc);
+	ret = __key_link_begin(keyring, &key->index_key, &prealloc);
 	if (ret == 0) {
 		ret = __key_link_check_live_key(keyring, key);
 		if (ret == 0)
 			__key_link(keyring, key, &prealloc);
-		__key_link_end(keyring, key->type, prealloc);
+		__key_link_end(keyring, &key->index_key, prealloc);
 	}
 
 	return ret;
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 172115b38054..586cb79ee82d 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -352,6 +352,11 @@ static int construct_alloc_key(struct key_type *type,
 			       struct key_user *user,
 			       struct key **_key)
 {
+	const struct keyring_index_key index_key = {
+		.type		= type,
+		.description	= description,
+		.desc_len	= strlen(description),
+	};
 	const struct cred *cred = current_cred();
 	unsigned long prealloc;
 	struct key *key;
@@ -379,8 +384,7 @@ static int construct_alloc_key(struct key_type *type,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, type, description,
-				       &prealloc);
+		ret = __key_link_begin(dest_keyring, &index_key, &prealloc);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -400,7 +404,7 @@ static int construct_alloc_key(struct key_type *type,
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, type, prealloc);
+		__key_link_end(dest_keyring, &index_key, prealloc);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -416,7 +420,7 @@ key_already_present:
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
 			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, type, prealloc);
+		__key_link_end(dest_keyring, &index_key, prealloc);
 		if (ret < 0)
 			goto link_check_failed;
 	}
-- 
cgit 


From 4bdf0bc300314141e5475e145acb8b5ad846f00d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:15 +0100
Subject: KEYS: Introduce a search context structure

Search functions pass around a bunch of arguments, each of which gets copied
with each call.  Introduce a search context structure to hold these.

Whilst we're at it, create a search flag that indicates whether the search
should be directly to the description or whether it should iterate through all
keys looking for a non-description match.

This will be useful when keyrings use a generic data struct with generic
routines to manage their content as the search terms can just be passed
through to the iterator callback function.

Also, for future use, the data to be supplied to the match function is
separated from the description pointer in the search context.  This makes it
clear which is being supplied.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/linux/key-type.h         |   5 ++
 security/keys/internal.h         |  40 +++++++------
 security/keys/keyring.c          |  70 +++++++++++------------
 security/keys/proc.c             |  17 ++++--
 security/keys/process_keys.c     | 117 +++++++++++++++++++--------------------
 security/keys/request_key.c      |  56 +++++++++----------
 security/keys/request_key_auth.c |  14 +++--
 security/keys/user_defined.c     |  18 +++---
 8 files changed, 179 insertions(+), 158 deletions(-)

(limited to 'include')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 518a53afb9ea..f58737bcb050 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -63,6 +63,11 @@ struct key_type {
 	 */
 	size_t def_datalen;
 
+	/* Default key search algorithm. */
+	unsigned def_lookup_type;
+#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
+#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
+
 	/* vet a description */
 	int (*vet_description)(const char *description);
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 77441dd1f9d4..f4bf938b68b4 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -107,23 +107,31 @@ extern struct key *keyring_search_instkey(struct key *keyring,
 
 typedef int (*key_match_func_t)(const struct key *, const void *);
 
+struct keyring_search_context {
+	struct keyring_index_key index_key;
+	const struct cred	*cred;
+	key_match_func_t	match;
+	const void		*match_data;
+	unsigned		flags;
+#define KEYRING_SEARCH_LOOKUP_TYPE	0x0001	/* [as type->def_lookup_type] */
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0002	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0004	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0008	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
+
+	/* Internal stuff */
+	int			skipped_ret;
+	bool			possessed;
+	key_ref_t		result;
+	struct timespec		now;
+};
+
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-				    const struct cred *cred,
-				    struct key_type *type,
-				    const void *description,
-				    key_match_func_t match,
-				    bool no_state_check);
-
-extern key_ref_t search_my_process_keyrings(struct key_type *type,
-					    const void *description,
-					    key_match_func_t match,
-					    bool no_state_check,
-					    const struct cred *cred);
-extern key_ref_t search_process_keyrings(struct key_type *type,
-					 const void *description,
-					 key_match_func_t match,
-					 bool no_state_check,
-					 const struct cred *cred);
+				    struct keyring_search_context *ctx);
+
+extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
+extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
 
 extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
 
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index c7f59f9dd7b6..b42f2d4f7f83 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -280,11 +280,7 @@ EXPORT_SYMBOL(keyring_alloc);
 /**
  * keyring_search_aux - Search a keyring tree for a key matching some criteria
  * @keyring_ref: A pointer to the keyring with possession indicator.
- * @cred: The credentials to use for permissions checks.
- * @type: The type of key to search for.
- * @description: Parameter for @match.
- * @match: Function to rule on whether or not a key is the one required.
- * @no_state_check: Don't check if a matching key is bad
+ * @ctx: The keyring search context.
  *
  * Search the supplied keyring tree for a key that matches the criteria given.
  * The root keyring and any linked keyrings must grant Search permission to the
@@ -314,11 +310,7 @@ EXPORT_SYMBOL(keyring_alloc);
  * @keyring_ref is propagated to the returned key reference.
  */
 key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-			     const struct cred *cred,
-			     struct key_type *type,
-			     const void *description,
-			     key_match_func_t match,
-			     bool no_state_check)
+			     struct keyring_search_context *ctx)
 {
 	struct {
 		/* Need a separate keylist pointer for RCU purposes */
@@ -328,20 +320,18 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	} stack[KEYRING_SEARCH_MAX_DEPTH];
 
 	struct keyring_list *keylist;
-	struct timespec now;
 	unsigned long kflags;
 	struct key *keyring, *key;
 	key_ref_t key_ref;
-	bool possessed;
 	long err;
 	int sp, nkeys, kix;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-	possessed = is_key_possessed(keyring_ref);
+	ctx->possessed = is_key_possessed(keyring_ref);
 	key_check(keyring);
 
 	/* top keyring must have search permission to begin the search */
-	err = key_task_permission(keyring_ref, cred, KEY_SEARCH);
+	err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
 	if (err < 0) {
 		key_ref = ERR_PTR(err);
 		goto error;
@@ -353,7 +343,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 
 	rcu_read_lock();
 
-	now = current_kernel_time();
+	ctx->now = current_kernel_time();
 	err = -EAGAIN;
 	sp = 0;
 
@@ -361,16 +351,17 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	 * are looking for */
 	key_ref = ERR_PTR(-EAGAIN);
 	kflags = keyring->flags;
-	if (keyring->type == type && match(keyring, description)) {
+	if (keyring->type == ctx->index_key.type &&
+	    ctx->match(keyring, ctx->match_data)) {
 		key = keyring;
-		if (no_state_check)
+		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
 			goto found;
 
 		/* check it isn't negative and hasn't expired or been
 		 * revoked */
 		if (kflags & (1 << KEY_FLAG_REVOKED))
 			goto error_2;
-		if (key->expiry && now.tv_sec >= key->expiry)
+		if (key->expiry && ctx->now.tv_sec >= key->expiry)
 			goto error_2;
 		key_ref = ERR_PTR(key->type_data.reject_error);
 		if (kflags & (1 << KEY_FLAG_NEGATIVE))
@@ -384,7 +375,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
 		      (1 << KEY_FLAG_REVOKED) |
 		      (1 << KEY_FLAG_NEGATIVE)) ||
-	    (keyring->expiry && now.tv_sec >= keyring->expiry))
+	    (keyring->expiry && ctx->now.tv_sec >= keyring->expiry))
 		goto error_2;
 
 	/* start processing a new keyring */
@@ -406,29 +397,29 @@ descend:
 		kflags = key->flags;
 
 		/* ignore keys not of this type */
-		if (key->type != type)
+		if (key->type != ctx->index_key.type)
 			continue;
 
 		/* skip invalidated, revoked and expired keys */
-		if (!no_state_check) {
+		if (!(ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)) {
 			if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
 				      (1 << KEY_FLAG_REVOKED)))
 				continue;
 
-			if (key->expiry && now.tv_sec >= key->expiry)
+			if (key->expiry && ctx->now.tv_sec >= key->expiry)
 				continue;
 		}
 
 		/* keys that don't match */
-		if (!match(key, description))
+		if (!ctx->match(key, ctx->match_data))
 			continue;
 
 		/* key must have search permissions */
-		if (key_task_permission(make_key_ref(key, possessed),
-					cred, KEY_SEARCH) < 0)
+		if (key_task_permission(make_key_ref(key, ctx->possessed),
+					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
-		if (no_state_check)
+		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
 			goto found;
 
 		/* we set a different error code if we pass a negative key */
@@ -456,8 +447,8 @@ ascend:
 		if (sp >= KEYRING_SEARCH_MAX_DEPTH)
 			continue;
 
-		if (key_task_permission(make_key_ref(key, possessed),
-					cred, KEY_SEARCH) < 0)
+		if (key_task_permission(make_key_ref(key, ctx->possessed),
+					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
@@ -489,12 +480,12 @@ not_this_keyring:
 	/* we found a viable match */
 found:
 	atomic_inc(&key->usage);
-	key->last_used_at = now.tv_sec;
-	keyring->last_used_at = now.tv_sec;
+	key->last_used_at = ctx->now.tv_sec;
+	keyring->last_used_at = ctx->now.tv_sec;
 	while (sp > 0)
-		stack[--sp].keyring->last_used_at = now.tv_sec;
+		stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
 	key_check(key);
-	key_ref = make_key_ref(key, possessed);
+	key_ref = make_key_ref(key, ctx->possessed);
 error_2:
 	rcu_read_unlock();
 error:
@@ -514,11 +505,20 @@ key_ref_t keyring_search(key_ref_t keyring,
 			 struct key_type *type,
 			 const char *description)
 {
-	if (!type->match)
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match			= type->match,
+		.match_data		= description,
+		.flags			= (type->def_lookup_type |
+					   KEYRING_SEARCH_DO_STATE_CHECK),
+	};
+
+	if (!ctx.match)
 		return ERR_PTR(-ENOKEY);
 
-	return keyring_search_aux(keyring, current->cred,
-				  type, description, type->match, false);
+	return keyring_search_aux(keyring, &ctx);
 }
 EXPORT_SYMBOL(keyring_search);
 
diff --git a/security/keys/proc.c b/security/keys/proc.c
index 217b6855e815..88e9a466940f 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -182,7 +182,6 @@ static void proc_keys_stop(struct seq_file *p, void *v)
 
 static int proc_keys_show(struct seq_file *m, void *v)
 {
-	const struct cred *cred = current_cred();
 	struct rb_node *_p = v;
 	struct key *key = rb_entry(_p, struct key, serial_node);
 	struct timespec now;
@@ -191,15 +190,23 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	char xbuf[12];
 	int rc;
 
+	struct keyring_search_context ctx = {
+		.index_key.type		= key->type,
+		.index_key.description	= key->description,
+		.cred			= current_cred(),
+		.match			= lookup_user_key_possessed,
+		.match_data		= key,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_LOOKUP_DIRECT),
+	};
+
 	key_ref = make_key_ref(key, 0);
 
 	/* determine if the key is possessed by this process (a test we can
 	 * skip if the key does not indicate the possessor can view it
 	 */
 	if (key->perm & KEY_POS_VIEW) {
-		skey_ref = search_my_process_keyrings(key->type, key,
-						      lookup_user_key_possessed,
-						      true, cred);
+		skey_ref = search_my_process_keyrings(&ctx);
 		if (!IS_ERR(skey_ref)) {
 			key_ref_put(skey_ref);
 			key_ref = make_key_ref(key, 1);
@@ -211,7 +218,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	 * - the caller holds a spinlock, and thus the RCU read lock, making our
 	 *   access to __current_cred() safe
 	 */
-	rc = key_task_permission(key_ref, cred, KEY_VIEW);
+	rc = key_task_permission(key_ref, ctx.cred, KEY_VIEW);
 	if (rc < 0)
 		return 0;
 
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index a3410d605849..e68a3e0e7aa0 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -319,11 +319,7 @@ void key_fsgid_changed(struct task_struct *tsk)
  * In the case of a successful return, the possession attribute is set on the
  * returned key reference.
  */
-key_ref_t search_my_process_keyrings(struct key_type *type,
-				     const void *description,
-				     key_match_func_t match,
-				     bool no_state_check,
-				     const struct cred *cred)
+key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx)
 {
 	key_ref_t key_ref, ret, err;
 
@@ -339,10 +335,9 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	err = ERR_PTR(-EAGAIN);
 
 	/* search the thread keyring first */
-	if (cred->thread_keyring) {
+	if (ctx->cred->thread_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->thread_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->thread_keyring, 1), ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -358,10 +353,9 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the process keyring second */
-	if (cred->process_keyring) {
+	if (ctx->cred->process_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->process_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->process_keyring, 1), ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -379,11 +373,11 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 	}
 
 	/* search the session keyring */
-	if (cred->session_keyring) {
+	if (ctx->cred->session_keyring) {
 		rcu_read_lock();
 		key_ref = keyring_search_aux(
-			make_key_ref(rcu_dereference(cred->session_keyring), 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(rcu_dereference(ctx->cred->session_keyring), 1),
+			ctx);
 		rcu_read_unlock();
 
 		if (!IS_ERR(key_ref))
@@ -402,10 +396,10 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 		}
 	}
 	/* or search the user-session keyring */
-	else if (cred->user->session_keyring) {
+	else if (ctx->cred->user->session_keyring) {
 		key_ref = keyring_search_aux(
-			make_key_ref(cred->user->session_keyring, 1),
-			cred, type, description, match, no_state_check);
+			make_key_ref(ctx->cred->user->session_keyring, 1),
+			ctx);
 		if (!IS_ERR(key_ref))
 			goto found;
 
@@ -437,19 +431,14 @@ found:
  *
  * Return same as search_my_process_keyrings().
  */
-key_ref_t search_process_keyrings(struct key_type *type,
-				  const void *description,
-				  key_match_func_t match,
-				  bool no_state_check,
-				  const struct cred *cred)
+key_ref_t search_process_keyrings(struct keyring_search_context *ctx)
 {
 	struct request_key_auth *rka;
 	key_ref_t key_ref, ret = ERR_PTR(-EACCES), err;
 
 	might_sleep();
 
-	key_ref = search_my_process_keyrings(type, description, match,
-					     no_state_check, cred);
+	key_ref = search_my_process_keyrings(ctx);
 	if (!IS_ERR(key_ref))
 		goto found;
 	err = key_ref;
@@ -458,19 +447,21 @@ key_ref_t search_process_keyrings(struct key_type *type,
 	 * search the keyrings of the process mentioned there
 	 * - we don't permit access to request_key auth keys via this method
 	 */
-	if (cred->request_key_auth &&
-	    cred == current_cred() &&
-	    type != &key_type_request_key_auth
+	if (ctx->cred->request_key_auth &&
+	    ctx->cred == current_cred() &&
+	    ctx->index_key.type != &key_type_request_key_auth
 	    ) {
+		const struct cred *cred = ctx->cred;
+
 		/* defend against the auth key being revoked */
 		down_read(&cred->request_key_auth->sem);
 
-		if (key_validate(cred->request_key_auth) == 0) {
-			rka = cred->request_key_auth->payload.data;
+		if (key_validate(ctx->cred->request_key_auth) == 0) {
+			rka = ctx->cred->request_key_auth->payload.data;
 
-			key_ref = search_process_keyrings(type, description,
-							  match, no_state_check,
-							  rka->cred);
+			ctx->cred = rka->cred;
+			key_ref = search_process_keyrings(ctx);
+			ctx->cred = cred;
 
 			up_read(&cred->request_key_auth->sem);
 
@@ -524,19 +515,23 @@ int lookup_user_key_possessed(const struct key *key, const void *target)
 key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
 			  key_perm_t perm)
 {
+	struct keyring_search_context ctx = {
+		.match	= lookup_user_key_possessed,
+		.flags	= (KEYRING_SEARCH_NO_STATE_CHECK |
+			   KEYRING_SEARCH_LOOKUP_DIRECT),
+	};
 	struct request_key_auth *rka;
-	const struct cred *cred;
 	struct key *key;
 	key_ref_t key_ref, skey_ref;
 	int ret;
 
 try_again:
-	cred = get_current_cred();
+	ctx.cred = get_current_cred();
 	key_ref = ERR_PTR(-ENOKEY);
 
 	switch (id) {
 	case KEY_SPEC_THREAD_KEYRING:
-		if (!cred->thread_keyring) {
+		if (!ctx.cred->thread_keyring) {
 			if (!(lflags & KEY_LOOKUP_CREATE))
 				goto error;
 
@@ -548,13 +543,13 @@ try_again:
 			goto reget_creds;
 		}
 
-		key = cred->thread_keyring;
+		key = ctx.cred->thread_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_PROCESS_KEYRING:
-		if (!cred->process_keyring) {
+		if (!ctx.cred->process_keyring) {
 			if (!(lflags & KEY_LOOKUP_CREATE))
 				goto error;
 
@@ -566,13 +561,13 @@ try_again:
 			goto reget_creds;
 		}
 
-		key = cred->process_keyring;
+		key = ctx.cred->process_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_SESSION_KEYRING:
-		if (!cred->session_keyring) {
+		if (!ctx.cred->session_keyring) {
 			/* always install a session keyring upon access if one
 			 * doesn't exist yet */
 			ret = install_user_keyrings();
@@ -582,13 +577,13 @@ try_again:
 				ret = join_session_keyring(NULL);
 			else
 				ret = install_session_keyring(
-					cred->user->session_keyring);
+					ctx.cred->user->session_keyring);
 
 			if (ret < 0)
 				goto error;
 			goto reget_creds;
-		} else if (cred->session_keyring ==
-			   cred->user->session_keyring &&
+		} else if (ctx.cred->session_keyring ==
+			   ctx.cred->user->session_keyring &&
 			   lflags & KEY_LOOKUP_CREATE) {
 			ret = join_session_keyring(NULL);
 			if (ret < 0)
@@ -597,32 +592,32 @@ try_again:
 		}
 
 		rcu_read_lock();
-		key = rcu_dereference(cred->session_keyring);
+		key = rcu_dereference(ctx.cred->session_keyring);
 		atomic_inc(&key->usage);
 		rcu_read_unlock();
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_USER_KEYRING:
-		if (!cred->user->uid_keyring) {
+		if (!ctx.cred->user->uid_keyring) {
 			ret = install_user_keyrings();
 			if (ret < 0)
 				goto error;
 		}
 
-		key = cred->user->uid_keyring;
+		key = ctx.cred->user->uid_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
 
 	case KEY_SPEC_USER_SESSION_KEYRING:
-		if (!cred->user->session_keyring) {
+		if (!ctx.cred->user->session_keyring) {
 			ret = install_user_keyrings();
 			if (ret < 0)
 				goto error;
 		}
 
-		key = cred->user->session_keyring;
+		key = ctx.cred->user->session_keyring;
 		atomic_inc(&key->usage);
 		key_ref = make_key_ref(key, 1);
 		break;
@@ -633,7 +628,7 @@ try_again:
 		goto error;
 
 	case KEY_SPEC_REQKEY_AUTH_KEY:
-		key = cred->request_key_auth;
+		key = ctx.cred->request_key_auth;
 		if (!key)
 			goto error;
 
@@ -642,20 +637,20 @@ try_again:
 		break;
 
 	case KEY_SPEC_REQUESTOR_KEYRING:
-		if (!cred->request_key_auth)
+		if (!ctx.cred->request_key_auth)
 			goto error;
 
-		down_read(&cred->request_key_auth->sem);
+		down_read(&ctx.cred->request_key_auth->sem);
 		if (test_bit(KEY_FLAG_REVOKED,
-			     &cred->request_key_auth->flags)) {
+			     &ctx.cred->request_key_auth->flags)) {
 			key_ref = ERR_PTR(-EKEYREVOKED);
 			key = NULL;
 		} else {
-			rka = cred->request_key_auth->payload.data;
+			rka = ctx.cred->request_key_auth->payload.data;
 			key = rka->dest_keyring;
 			atomic_inc(&key->usage);
 		}
-		up_read(&cred->request_key_auth->sem);
+		up_read(&ctx.cred->request_key_auth->sem);
 		if (!key)
 			goto error;
 		key_ref = make_key_ref(key, 1);
@@ -675,9 +670,13 @@ try_again:
 		key_ref = make_key_ref(key, 0);
 
 		/* check to see if we possess the key */
-		skey_ref = search_process_keyrings(key->type, key,
-						   lookup_user_key_possessed,
-						   true, cred);
+		ctx.index_key.type		= key->type;
+		ctx.index_key.description	= key->description;
+		ctx.index_key.desc_len		= strlen(key->description);
+		ctx.match_data			= key;
+		kdebug("check possessed");
+		skey_ref = search_process_keyrings(&ctx);
+		kdebug("possessed=%p", skey_ref);
 
 		if (!IS_ERR(skey_ref)) {
 			key_put(key);
@@ -717,14 +716,14 @@ try_again:
 		goto invalid_key;
 
 	/* check the permissions */
-	ret = key_task_permission(key_ref, cred, perm);
+	ret = key_task_permission(key_ref, ctx.cred, perm);
 	if (ret < 0)
 		goto invalid_key;
 
 	key->last_used_at = current_kernel_time().tv_sec;
 
 error:
-	put_cred(cred);
+	put_cred(ctx.cred);
 	return key_ref;
 
 invalid_key:
@@ -735,7 +734,7 @@ invalid_key:
 	/* if we attempted to install a keyring, then it may have caused new
 	 * creds to be installed */
 reget_creds:
-	put_cred(cred);
+	put_cred(ctx.cred);
 	goto try_again;
 }
 
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 586cb79ee82d..ab75df4745af 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -345,38 +345,34 @@ static void construct_get_dest_keyring(struct key **_dest_keyring)
  * May return a key that's already under construction instead if there was a
  * race between two thread calling request_key().
  */
-static int construct_alloc_key(struct key_type *type,
-			       const char *description,
+static int construct_alloc_key(struct keyring_search_context *ctx,
 			       struct key *dest_keyring,
 			       unsigned long flags,
 			       struct key_user *user,
 			       struct key **_key)
 {
-	const struct keyring_index_key index_key = {
-		.type		= type,
-		.description	= description,
-		.desc_len	= strlen(description),
-	};
-	const struct cred *cred = current_cred();
 	unsigned long prealloc;
 	struct key *key;
 	key_perm_t perm;
 	key_ref_t key_ref;
 	int ret;
 
-	kenter("%s,%s,,,", type->name, description);
+	kenter("%s,%s,,,",
+	       ctx->index_key.type->name, ctx->index_key.description);
 
 	*_key = NULL;
 	mutex_lock(&user->cons_lock);
 
 	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
 	perm |= KEY_USR_VIEW;
-	if (type->read)
+	if (ctx->index_key.type->read)
 		perm |= KEY_POS_READ;
-	if (type == &key_type_keyring || type->update)
+	if (ctx->index_key.type == &key_type_keyring ||
+	    ctx->index_key.type->update)
 		perm |= KEY_POS_WRITE;
 
-	key = key_alloc(type, description, cred->fsuid, cred->fsgid, cred,
+	key = key_alloc(ctx->index_key.type, ctx->index_key.description,
+			ctx->cred->fsuid, ctx->cred->fsgid, ctx->cred,
 			perm, flags);
 	if (IS_ERR(key))
 		goto alloc_failed;
@@ -384,7 +380,7 @@ static int construct_alloc_key(struct key_type *type,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, &index_key, &prealloc);
+		ret = __key_link_begin(dest_keyring, &ctx->index_key, &prealloc);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -394,8 +390,7 @@ static int construct_alloc_key(struct key_type *type,
 	 * waited for locks */
 	mutex_lock(&key_construction_mutex);
 
-	key_ref = search_process_keyrings(type, description, type->match,
-					  false, cred);
+	key_ref = search_process_keyrings(ctx);
 	if (!IS_ERR(key_ref))
 		goto key_already_present;
 
@@ -404,7 +399,7 @@ static int construct_alloc_key(struct key_type *type,
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, &index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -420,7 +415,7 @@ key_already_present:
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
 			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, &index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
 		if (ret < 0)
 			goto link_check_failed;
 	}
@@ -449,8 +444,7 @@ alloc_failed:
 /*
  * Commence key construction.
  */
-static struct key *construct_key_and_link(struct key_type *type,
-					  const char *description,
+static struct key *construct_key_and_link(struct keyring_search_context *ctx,
 					  const char *callout_info,
 					  size_t callout_len,
 					  void *aux,
@@ -469,8 +463,7 @@ static struct key *construct_key_and_link(struct key_type *type,
 
 	construct_get_dest_keyring(&dest_keyring);
 
-	ret = construct_alloc_key(type, description, dest_keyring, flags, user,
-				  &key);
+	ret = construct_alloc_key(ctx, dest_keyring, flags, user, &key);
 	key_user_put(user);
 
 	if (ret == 0) {
@@ -534,18 +527,24 @@ struct key *request_key_and_link(struct key_type *type,
 				 struct key *dest_keyring,
 				 unsigned long flags)
 {
-	const struct cred *cred = current_cred();
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match			= type->match,
+		.match_data		= description,
+		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+	};
 	struct key *key;
 	key_ref_t key_ref;
 	int ret;
 
 	kenter("%s,%s,%p,%zu,%p,%p,%lx",
-	       type->name, description, callout_info, callout_len, aux,
-	       dest_keyring, flags);
+	       ctx.index_key.type->name, ctx.index_key.description,
+	       callout_info, callout_len, aux, dest_keyring, flags);
 
 	/* search all the process keyrings for a key */
-	key_ref = search_process_keyrings(type, description, type->match,
-					  false, cred);
+	key_ref = search_process_keyrings(&ctx);
 
 	if (!IS_ERR(key_ref)) {
 		key = key_ref_to_ptr(key_ref);
@@ -568,9 +567,8 @@ struct key *request_key_and_link(struct key_type *type,
 		if (!callout_info)
 			goto error;
 
-		key = construct_key_and_link(type, description, callout_info,
-					     callout_len, aux, dest_keyring,
-					     flags);
+		key = construct_key_and_link(&ctx, callout_info, callout_len,
+					     aux, dest_keyring, flags);
 	}
 
 error:
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 92077de555df..8d09852854ca 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -239,15 +239,17 @@ static int key_get_instantiation_authkey_match(const struct key *key,
  */
 struct key *key_get_instantiation_authkey(key_serial_t target_id)
 {
-	const struct cred *cred = current_cred();
+	struct keyring_search_context ctx = {
+		.index_key.type		= &key_type_request_key_auth,
+		.cred			= current_cred(),
+		.match			= key_get_instantiation_authkey_match,
+		.match_data		= (void *)(unsigned long)target_id,
+		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+	};
 	struct key *authkey;
 	key_ref_t authkey_ref;
 
-	authkey_ref = search_process_keyrings(
-		&key_type_request_key_auth,
-		(void *) (unsigned long) target_id,
-		key_get_instantiation_authkey_match,
-		false, cred);
+	authkey_ref = search_process_keyrings(&ctx);
 
 	if (IS_ERR(authkey_ref)) {
 		authkey = ERR_CAST(authkey_ref);
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 55dc88939185..faa2caeb593f 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -25,14 +25,15 @@ static int logon_vet_description(const char *desc);
  * arbitrary blob of data as the payload
  */
 struct key_type key_type_user = {
-	.name		= "user",
-	.instantiate	= user_instantiate,
-	.update		= user_update,
-	.match		= user_match,
-	.revoke		= user_revoke,
-	.destroy	= user_destroy,
-	.describe	= user_describe,
-	.read		= user_read,
+	.name			= "user",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+	.instantiate		= user_instantiate,
+	.update			= user_update,
+	.match			= user_match,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.read			= user_read,
 };
 
 EXPORT_SYMBOL_GPL(key_type_user);
@@ -45,6 +46,7 @@ EXPORT_SYMBOL_GPL(key_type_user);
  */
 struct key_type key_type_logon = {
 	.name			= "logon",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.instantiate		= user_instantiate,
 	.update			= user_update,
 	.match			= user_match,
-- 
cgit 


From ccc3e6d9c9aea07a0b60b2b0bfc5b05a704b66d5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:16 +0100
Subject: KEYS: Define a __key_get() wrapper to use rather than atomic_inc()

Define a __key_get() wrapper to use rather than atomic_inc() on the key usage
count as this makes it easier to hook in refcount error debugging.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/security/keys.txt | 13 ++++++++-----
 include/linux/key.h             | 10 +++++++---
 security/keys/key.c             |  2 +-
 security/keys/keyring.c         |  6 +++---
 security/keys/process_keys.c    | 16 ++++++++--------
 5 files changed, 27 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 9ede67084f0b..a4c33f1a7c6d 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -960,14 +960,17 @@ payload contents" for more information.
     the argument will not be parsed.
 
 
-(*) Extra references can be made to a key by calling the following function:
+(*) Extra references can be made to a key by calling one of the following
+    functions:
 
+	struct key *__key_get(struct key *key);
 	struct key *key_get(struct key *key);
 
-    These need to be disposed of by calling key_put() when they've been
-    finished with. The key pointer passed in will be returned. If the pointer
-    is NULL or CONFIG_KEYS is not set then the key will not be dereferenced and
-    no increment will take place.
+    Keys so references will need to be disposed of by calling key_put() when
+    they've been finished with.  The key pointer passed in will be returned.
+
+    In the case of key_get(), if the pointer is NULL or CONFIG_KEYS is not set
+    then the key will not be dereferenced and no increment will take place.
 
 
 (*) A key's serial number can be obtained by calling:
diff --git a/include/linux/key.h b/include/linux/key.h
index d573e820a23d..ef596c7af585 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -219,13 +219,17 @@ extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);
 extern void key_put(struct key *key);
 
-static inline struct key *key_get(struct key *key)
+static inline struct key *__key_get(struct key *key)
 {
-	if (key)
-		atomic_inc(&key->usage);
+	atomic_inc(&key->usage);
 	return key;
 }
 
+static inline struct key *key_get(struct key *key)
+{
+	return key ? __key_get(key) : key;
+}
+
 static inline void key_ref_put(key_ref_t key_ref)
 {
 	key_put(key_ref_to_ptr(key_ref));
diff --git a/security/keys/key.c b/security/keys/key.c
index 7e6bc396bb23..1e23cc288106 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -644,7 +644,7 @@ found:
 	/* this races with key_put(), but that doesn't matter since key_put()
 	 * doesn't actually change the key
 	 */
-	atomic_inc(&key->usage);
+	__key_get(key);
 
 error:
 	spin_unlock(&key_serial_lock);
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index b42f2d4f7f83..87eff32b53f4 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -479,7 +479,7 @@ not_this_keyring:
 
 	/* we found a viable match */
 found:
-	atomic_inc(&key->usage);
+	__key_get(key);
 	key->last_used_at = ctx->now.tv_sec;
 	keyring->last_used_at = ctx->now.tv_sec;
 	while (sp > 0)
@@ -573,7 +573,7 @@ key_ref_t __keyring_search_one(key_ref_t keyring_ref,
 	return ERR_PTR(-ENOKEY);
 
 found:
-	atomic_inc(&key->usage);
+	__key_get(key);
 	keyring->last_used_at = key->last_used_at =
 		current_kernel_time().tv_sec;
 	rcu_read_unlock();
@@ -909,7 +909,7 @@ void __key_link(struct key *keyring, struct key *key,
 
 	klist = rcu_dereference_locked_keyring(keyring);
 
-	atomic_inc(&key->usage);
+	__key_get(key);
 	keyring->last_used_at = key->last_used_at =
 		current_kernel_time().tv_sec;
 
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index e68a3e0e7aa0..68548ea6fe01 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -235,7 +235,7 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
 		if (IS_ERR(keyring))
 			return PTR_ERR(keyring);
 	} else {
-		atomic_inc(&keyring->usage);
+		__key_get(keyring);
 	}
 
 	/* install the keyring */
@@ -544,7 +544,7 @@ try_again:
 		}
 
 		key = ctx.cred->thread_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -562,7 +562,7 @@ try_again:
 		}
 
 		key = ctx.cred->process_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -593,7 +593,7 @@ try_again:
 
 		rcu_read_lock();
 		key = rcu_dereference(ctx.cred->session_keyring);
-		atomic_inc(&key->usage);
+		__key_get(key);
 		rcu_read_unlock();
 		key_ref = make_key_ref(key, 1);
 		break;
@@ -606,7 +606,7 @@ try_again:
 		}
 
 		key = ctx.cred->user->uid_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -618,7 +618,7 @@ try_again:
 		}
 
 		key = ctx.cred->user->session_keyring;
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -632,7 +632,7 @@ try_again:
 		if (!key)
 			goto error;
 
-		atomic_inc(&key->usage);
+		__key_get(key);
 		key_ref = make_key_ref(key, 1);
 		break;
 
@@ -648,7 +648,7 @@ try_again:
 		} else {
 			rka = ctx.cred->request_key_auth->payload.data;
 			key = rka->dest_keyring;
-			atomic_inc(&key->usage);
+			__key_get(key);
 		}
 		up_read(&ctx.cred->request_key_auth->sem);
 		if (!key)
-- 
cgit 


From 3cb989501c2688cacbb7dc4b0d353faf838f53a1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:17 +0100
Subject: Add a generic associative array implementation.

Add a generic associative array implementation that can be used as the
container for keyrings, thereby massively increasing the capacity available
whilst also speeding up searching in keyrings that contain a lot of keys.

This may also be useful in FS-Cache for tracking cookies.

Documentation is added into Documentation/associative_array.txt

Some of the properties of the implementation are:

 (1) Objects are opaque pointers.  The implementation does not care where they
     point (if anywhere) or what they point to (if anything).

     [!] NOTE: Pointers to objects _must_ be zero in the two least significant
     	       bits.

 (2) Objects do not need to contain linkage blocks for use by the array.  This
     permits an object to be located in multiple arrays simultaneously.
     Rather, the array is made up of metadata blocks that point to objects.

 (3) Objects are labelled as being one of two types (the type is a bool value).
     This information is stored in the array, but has no consequence to the
     array itself or its algorithms.

 (4) Objects require index keys to locate them within the array.

 (5) Index keys must be unique.  Inserting an object with the same key as one
     already in the array will replace the old object.

 (6) Index keys can be of any length and can be of different lengths.

 (7) Index keys should encode the length early on, before any variation due to
     length is seen.

 (8) Index keys can include a hash to scatter objects throughout the array.

 (9) The array can iterated over.  The objects will not necessarily come out in
     key order.

(10) The array can be iterated whilst it is being modified, provided the RCU
     readlock is being held by the iterator.  Note, however, under these
     circumstances, some objects may be seen more than once.  If this is a
     problem, the iterator should lock against modification.  Objects will not
     be missed, however, unless deleted.

(11) Objects in the array can be looked up by means of their index key.

(12) Objects can be looked up whilst the array is being modified, provided the
     RCU readlock is being held by the thread doing the look up.

The implementation uses a tree of 16-pointer nodes internally that are indexed
on each level by nibbles from the index key.  To improve memory efficiency,
shortcuts can be emplaced to skip over what would otherwise be a series of
single-occupancy nodes.  Further, nodes pack leaf object pointers into spare
space in the node rather than making an extra branch until as such time an
object needs to be added to a full node.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 Documentation/assoc_array.txt    |  574 +++++++++++++
 include/linux/assoc_array.h      |   92 ++
 include/linux/assoc_array_priv.h |  182 ++++
 lib/Kconfig                      |   14 +
 lib/Makefile                     |    1 +
 lib/assoc_array.c                | 1745 ++++++++++++++++++++++++++++++++++++++
 6 files changed, 2608 insertions(+)
 create mode 100644 Documentation/assoc_array.txt
 create mode 100644 include/linux/assoc_array.h
 create mode 100644 include/linux/assoc_array_priv.h
 create mode 100644 lib/assoc_array.c

(limited to 'include')

diff --git a/Documentation/assoc_array.txt b/Documentation/assoc_array.txt
new file mode 100644
index 000000000000..f4faec0f66e4
--- /dev/null
+++ b/Documentation/assoc_array.txt
@@ -0,0 +1,574 @@
+		   ========================================
+		   GENERIC ASSOCIATIVE ARRAY IMPLEMENTATION
+		   ========================================
+
+Contents:
+
+ - Overview.
+
+ - The public API.
+   - Edit script.
+   - Operations table.
+   - Manipulation functions.
+   - Access functions.
+   - Index key form.
+
+ - Internal workings.
+   - Basic internal tree layout.
+   - Shortcuts.
+   - Splitting and collapsing nodes.
+   - Non-recursive iteration.
+   - Simultaneous alteration and iteration.
+
+
+========
+OVERVIEW
+========
+
+This associative array implementation is an object container with the following
+properties:
+
+ (1) Objects are opaque pointers.  The implementation does not care where they
+     point (if anywhere) or what they point to (if anything).
+
+     [!] NOTE: Pointers to objects _must_ be zero in the least significant bit.
+
+ (2) Objects do not need to contain linkage blocks for use by the array.  This
+     permits an object to be located in multiple arrays simultaneously.
+     Rather, the array is made up of metadata blocks that point to objects.
+
+ (3) Objects require index keys to locate them within the array.
+
+ (4) Index keys must be unique.  Inserting an object with the same key as one
+     already in the array will replace the old object.
+
+ (5) Index keys can be of any length and can be of different lengths.
+
+ (6) Index keys should encode the length early on, before any variation due to
+     length is seen.
+
+ (7) Index keys can include a hash to scatter objects throughout the array.
+
+ (8) The array can iterated over.  The objects will not necessarily come out in
+     key order.
+
+ (9) The array can be iterated over whilst it is being modified, provided the
+     RCU readlock is being held by the iterator.  Note, however, under these
+     circumstances, some objects may be seen more than once.  If this is a
+     problem, the iterator should lock against modification.  Objects will not
+     be missed, however, unless deleted.
+
+(10) Objects in the array can be looked up by means of their index key.
+
+(11) Objects can be looked up whilst the array is being modified, provided the
+     RCU readlock is being held by the thread doing the look up.
+
+The implementation uses a tree of 16-pointer nodes internally that are indexed
+on each level by nibbles from the index key in the same manner as in a radix
+tree.  To improve memory efficiency, shortcuts can be emplaced to skip over
+what would otherwise be a series of single-occupancy nodes.  Further, nodes
+pack leaf object pointers into spare space in the node rather than making an
+extra branch until as such time an object needs to be added to a full node.
+
+
+==============
+THE PUBLIC API
+==============
+
+The public API can be found in <linux/assoc_array.h>.  The associative array is
+rooted on the following structure:
+
+	struct assoc_array {
+		...
+	};
+
+The code is selected by enabling CONFIG_ASSOCIATIVE_ARRAY.
+
+
+EDIT SCRIPT
+-----------
+
+The insertion and deletion functions produce an 'edit script' that can later be
+applied to effect the changes without risking ENOMEM.  This retains the
+preallocated metadata blocks that will be installed in the internal tree and
+keeps track of the metadata blocks that will be removed from the tree when the
+script is applied.
+
+This is also used to keep track of dead blocks and dead objects after the
+script has been applied so that they can be freed later.  The freeing is done
+after an RCU grace period has passed - thus allowing access functions to
+proceed under the RCU read lock.
+
+The script appears as outside of the API as a pointer of the type:
+
+	struct assoc_array_edit;
+
+There are two functions for dealing with the script:
+
+ (1) Apply an edit script.
+
+	void assoc_array_apply_edit(struct assoc_array_edit *edit);
+
+     This will perform the edit functions, interpolating various write barriers
+     to permit accesses under the RCU read lock to continue.  The edit script
+     will then be passed to call_rcu() to free it and any dead stuff it points
+     to.
+
+ (2) Cancel an edit script.
+
+	void assoc_array_cancel_edit(struct assoc_array_edit *edit);
+
+     This frees the edit script and all preallocated memory immediately.  If
+     this was for insertion, the new object is _not_ released by this function,
+     but must rather be released by the caller.
+
+These functions are guaranteed not to fail.
+
+
+OPERATIONS TABLE
+----------------
+
+Various functions take a table of operations:
+
+	struct assoc_array_ops {
+		...
+	};
+
+This points to a number of methods, all of which need to be provided:
+
+ (1) Get a chunk of index key from caller data:
+
+	unsigned long (*get_key_chunk)(const void *index_key, int level);
+
+     This should return a chunk of caller-supplied index key starting at the
+     *bit* position given by the level argument.  The level argument will be a
+     multiple of ASSOC_ARRAY_KEY_CHUNK_SIZE and the function should return
+     ASSOC_ARRAY_KEY_CHUNK_SIZE bits.  No error is possible.
+
+
+ (2) Get a chunk of an object's index key.
+
+	unsigned long (*get_object_key_chunk)(const void *object, int level);
+
+     As the previous function, but gets its data from an object in the array
+     rather than from a caller-supplied index key.
+
+
+ (3) See if this is the object we're looking for.
+
+	bool (*compare_object)(const void *object, const void *index_key);
+
+     Compare the object against an index key and return true if it matches and
+     false if it doesn't.
+
+
+ (4) Diff the index keys of two objects.
+
+	int (*diff_objects)(const void *a, const void *b);
+
+     Return the bit position at which the index keys of two objects differ or
+     -1 if they are the same.
+
+
+ (5) Free an object.
+
+	void (*free_object)(void *object);
+
+     Free the specified object.  Note that this may be called an RCU grace
+     period after assoc_array_apply_edit() was called, so synchronize_rcu() may
+     be necessary on module unloading.
+
+
+MANIPULATION FUNCTIONS
+----------------------
+
+There are a number of functions for manipulating an associative array:
+
+ (1) Initialise an associative array.
+
+	void assoc_array_init(struct assoc_array *array);
+
+     This initialises the base structure for an associative array.  It can't
+     fail.
+
+
+ (2) Insert/replace an object in an associative array.
+
+	struct assoc_array_edit *
+	assoc_array_insert(struct assoc_array *array,
+			   const struct assoc_array_ops *ops,
+			   const void *index_key,
+			   void *object);
+
+     This inserts the given object into the array.  Note that the least
+     significant bit of the pointer must be zero as it's used to type-mark
+     pointers internally.
+
+     If an object already exists for that key then it will be replaced with the
+     new object and the old one will be freed automatically.
+
+     The index_key argument should hold index key information and is
+     passed to the methods in the ops table when they are called.
+
+     This function makes no alteration to the array itself, but rather returns
+     an edit script that must be applied.  -ENOMEM is returned in the case of
+     an out-of-memory error.
+
+     The caller should lock exclusively against other modifiers of the array.
+
+
+ (3) Delete an object from an associative array.
+
+	struct assoc_array_edit *
+	assoc_array_delete(struct assoc_array *array,
+			   const struct assoc_array_ops *ops,
+			   const void *index_key);
+
+     This deletes an object that matches the specified data from the array.
+
+     The index_key argument should hold index key information and is
+     passed to the methods in the ops table when they are called.
+
+     This function makes no alteration to the array itself, but rather returns
+     an edit script that must be applied.  -ENOMEM is returned in the case of
+     an out-of-memory error.  NULL will be returned if the specified object is
+     not found within the array.
+
+     The caller should lock exclusively against other modifiers of the array.
+
+
+ (4) Delete all objects from an associative array.
+
+	struct assoc_array_edit *
+	assoc_array_clear(struct assoc_array *array,
+			  const struct assoc_array_ops *ops);
+
+     This deletes all the objects from an associative array and leaves it
+     completely empty.
+
+     This function makes no alteration to the array itself, but rather returns
+     an edit script that must be applied.  -ENOMEM is returned in the case of
+     an out-of-memory error.
+
+     The caller should lock exclusively against other modifiers of the array.
+
+
+ (5) Destroy an associative array, deleting all objects.
+
+	void assoc_array_destroy(struct assoc_array *array,
+				 const struct assoc_array_ops *ops);
+
+     This destroys the contents of the associative array and leaves it
+     completely empty.  It is not permitted for another thread to be traversing
+     the array under the RCU read lock at the same time as this function is
+     destroying it as no RCU deferral is performed on memory release -
+     something that would require memory to be allocated.
+
+     The caller should lock exclusively against other modifiers and accessors
+     of the array.
+
+
+ (6) Garbage collect an associative array.
+
+	int assoc_array_gc(struct assoc_array *array,
+			   const struct assoc_array_ops *ops,
+			   bool (*iterator)(void *object, void *iterator_data),
+			   void *iterator_data);
+
+     This iterates over the objects in an associative array and passes each one
+     to iterator().  If iterator() returns true, the object is kept.  If it
+     returns false, the object will be freed.  If the iterator() function
+     returns true, it must perform any appropriate refcount incrementing on the
+     object before returning.
+
+     The internal tree will be packed down if possible as part of the iteration
+     to reduce the number of nodes in it.
+
+     The iterator_data is passed directly to iterator() and is otherwise
+     ignored by the function.
+
+     The function will return 0 if successful and -ENOMEM if there wasn't
+     enough memory.
+
+     It is possible for other threads to iterate over or search the array under
+     the RCU read lock whilst this function is in progress.  The caller should
+     lock exclusively against other modifiers of the array.
+
+
+ACCESS FUNCTIONS
+----------------
+
+There are two functions for accessing an associative array:
+
+ (1) Iterate over all the objects in an associative array.
+
+	int assoc_array_iterate(const struct assoc_array *array,
+				int (*iterator)(const void *object,
+						void *iterator_data),
+				void *iterator_data);
+
+     This passes each object in the array to the iterator callback function.
+     iterator_data is private data for that function.
+
+     This may be used on an array at the same time as the array is being
+     modified, provided the RCU read lock is held.  Under such circumstances,
+     it is possible for the iteration function to see some objects twice.  If
+     this is a problem, then modification should be locked against.  The
+     iteration algorithm should not, however, miss any objects.
+
+     The function will return 0 if no objects were in the array or else it will
+     return the result of the last iterator function called.  Iteration stops
+     immediately if any call to the iteration function results in a non-zero
+     return.
+
+
+ (2) Find an object in an associative array.
+
+	void *assoc_array_find(const struct assoc_array *array,
+			       const struct assoc_array_ops *ops,
+			       const void *index_key);
+
+     This walks through the array's internal tree directly to the object
+     specified by the index key..
+
+     This may be used on an array at the same time as the array is being
+     modified, provided the RCU read lock is held.
+
+     The function will return the object if found (and set *_type to the object
+     type) or will return NULL if the object was not found.
+
+
+INDEX KEY FORM
+--------------
+
+The index key can be of any form, but since the algorithms aren't told how long
+the key is, it is strongly recommended that the index key includes its length
+very early on before any variation due to the length would have an effect on
+comparisons.
+
+This will cause leaves with different length keys to scatter away from each
+other - and those with the same length keys to cluster together.
+
+It is also recommended that the index key begin with a hash of the rest of the
+key to maximise scattering throughout keyspace.
+
+The better the scattering, the wider and lower the internal tree will be.
+
+Poor scattering isn't too much of a problem as there are shortcuts and nodes
+can contain mixtures of leaves and metadata pointers.
+
+The index key is read in chunks of machine word.  Each chunk is subdivided into
+one nibble (4 bits) per level, so on a 32-bit CPU this is good for 8 levels and
+on a 64-bit CPU, 16 levels.  Unless the scattering is really poor, it is
+unlikely that more than one word of any particular index key will have to be
+used.
+
+
+=================
+INTERNAL WORKINGS
+=================
+
+The associative array data structure has an internal tree.  This tree is
+constructed of two types of metadata blocks: nodes and shortcuts.
+
+A node is an array of slots.  Each slot can contain one of four things:
+
+ (*) A NULL pointer, indicating that the slot is empty.
+
+ (*) A pointer to an object (a leaf).
+
+ (*) A pointer to a node at the next level.
+
+ (*) A pointer to a shortcut.
+
+
+BASIC INTERNAL TREE LAYOUT
+--------------------------
+
+Ignoring shortcuts for the moment, the nodes form a multilevel tree.  The index
+key space is strictly subdivided by the nodes in the tree and nodes occur on
+fixed levels.  For example:
+
+ Level:	0		1		2		3
+	===============	===============	===============	===============
+							NODE D
+			NODE B		NODE C	+------>+---+
+		+------>+---+	+------>+---+	|	| 0 |
+	NODE A	|	| 0 |	|	| 0 |	|	+---+
+	+---+	|	+---+	|	+---+	|	:   :
+	| 0 |	|	:   :	|	:   :	|	+---+
+	+---+	|	+---+	|	+---+	|	| f |
+	| 1 |---+	| 3 |---+	| 7 |---+	+---+
+	+---+		+---+		+---+
+	:   :		:   :		| 8 |---+
+	+---+		+---+		+---+	|	NODE E
+	| e |---+	| f |		:   :   +------>+---+
+	+---+	|	+---+		+---+		| 0 |
+	| f |	|			| f |		+---+
+	+---+	|			+---+		:   :
+		|	NODE F				+---+
+		+------>+---+				| f |
+			| 0 |		NODE G		+---+
+			+---+	+------>+---+
+			:   :	|	| 0 |
+			+---+	|	+---+
+			| 6 |---+	:   :
+			+---+		+---+
+			:   :		| f |
+			+---+		+---+
+			| f |
+			+---+
+
+In the above example, there are 7 nodes (A-G), each with 16 slots (0-f).
+Assuming no other meta data nodes in the tree, the key space is divided thusly:
+
+	KEY PREFIX	NODE
+	==========	====
+	137*		D
+	138*		E
+	13[0-69-f]*	C
+	1[0-24-f]*	B
+	e6*		G
+	e[0-57-f]*	F
+	[02-df]*	A
+
+So, for instance, keys with the following example index keys will be found in
+the appropriate nodes:
+
+	INDEX KEY	PREFIX	NODE
+	===============	=======	====
+	13694892892489	13	C
+	13795289025897	137	D
+	13889dde88793	138	E
+	138bbb89003093	138	E
+	1394879524789	12	C
+	1458952489	1	B
+	9431809de993ba	-	A
+	b4542910809cd	-	A
+	e5284310def98	e	F
+	e68428974237	e6	G
+	e7fffcbd443	e	F
+	f3842239082	-	A
+
+To save memory, if a node can hold all the leaves in its portion of keyspace,
+then the node will have all those leaves in it and will not have any metadata
+pointers - even if some of those leaves would like to be in the same slot.
+
+A node can contain a heterogeneous mix of leaves and metadata pointers.
+Metadata pointers must be in the slots that match their subdivisions of key
+space.  The leaves can be in any slot not occupied by a metadata pointer.  It
+is guaranteed that none of the leaves in a node will match a slot occupied by a
+metadata pointer.  If the metadata pointer is there, any leaf whose key matches
+the metadata key prefix must be in the subtree that the metadata pointer points
+to.
+
+In the above example list of index keys, node A will contain:
+
+	SLOT	CONTENT		INDEX KEY (PREFIX)
+	====	===============	==================
+	1	PTR TO NODE B	1*
+	any	LEAF		9431809de993ba
+	any	LEAF		b4542910809cd
+	e	PTR TO NODE F	e*
+	any	LEAF		f3842239082
+
+and node B:
+
+	3	PTR TO NODE C	13*
+	any	LEAF		1458952489
+
+
+SHORTCUTS
+---------
+
+Shortcuts are metadata records that jump over a piece of keyspace.  A shortcut
+is a replacement for a series of single-occupancy nodes ascending through the
+levels.  Shortcuts exist to save memory and to speed up traversal.
+
+It is possible for the root of the tree to be a shortcut - say, for example,
+the tree contains at least 17 nodes all with key prefix '1111'.  The insertion
+algorithm will insert a shortcut to skip over the '1111' keyspace in a single
+bound and get to the fourth level where these actually become different.
+
+
+SPLITTING AND COLLAPSING NODES
+------------------------------
+
+Each node has a maximum capacity of 16 leaves and metadata pointers.  If the
+insertion algorithm finds that it is trying to insert a 17th object into a
+node, that node will be split such that at least two leaves that have a common
+key segment at that level end up in a separate node rooted on that slot for
+that common key segment.
+
+If the leaves in a full node and the leaf that is being inserted are
+sufficiently similar, then a shortcut will be inserted into the tree.
+
+When the number of objects in the subtree rooted at a node falls to 16 or
+fewer, then the subtree will be collapsed down to a single node - and this will
+ripple towards the root if possible.
+
+
+NON-RECURSIVE ITERATION
+-----------------------
+
+Each node and shortcut contains a back pointer to its parent and the number of
+slot in that parent that points to it.  None-recursive iteration uses these to
+proceed rootwards through the tree, going to the parent node, slot N + 1 to
+make sure progress is made without the need for a stack.
+
+The backpointers, however, make simultaneous alteration and iteration tricky.
+
+
+SIMULTANEOUS ALTERATION AND ITERATION
+-------------------------------------
+
+There are a number of cases to consider:
+
+ (1) Simple insert/replace.  This involves simply replacing a NULL or old
+     matching leaf pointer with the pointer to the new leaf after a barrier.
+     The metadata blocks don't change otherwise.  An old leaf won't be freed
+     until after the RCU grace period.
+
+ (2) Simple delete.  This involves just clearing an old matching leaf.  The
+     metadata blocks don't change otherwise.  The old leaf won't be freed until
+     after the RCU grace period.
+
+ (3) Insertion replacing part of a subtree that we haven't yet entered.  This
+     may involve replacement of part of that subtree - but that won't affect
+     the iteration as we won't have reached the pointer to it yet and the
+     ancestry blocks are not replaced (the layout of those does not change).
+
+ (4) Insertion replacing nodes that we're actively processing.  This isn't a
+     problem as we've passed the anchoring pointer and won't switch onto the
+     new layout until we follow the back pointers - at which point we've
+     already examined the leaves in the replaced node (we iterate over all the
+     leaves in a node before following any of its metadata pointers).
+
+     We might, however, re-see some leaves that have been split out into a new
+     branch that's in a slot further along than we were at.
+
+ (5) Insertion replacing nodes that we're processing a dependent branch of.
+     This won't affect us until we follow the back pointers.  Similar to (4).
+
+ (6) Deletion collapsing a branch under us.  This doesn't affect us because the
+     back pointers will get us back to the parent of the new node before we
+     could see the new node.  The entire collapsed subtree is thrown away
+     unchanged - and will still be rooted on the same slot, so we shouldn't
+     process it a second time as we'll go back to slot + 1.
+
+Note:
+
+ (*) Under some circumstances, we need to simultaneously change the parent
+     pointer and the parent slot pointer on a node (say, for example, we
+     inserted another node before it and moved it up a level).  We cannot do
+     this without locking against a read - so we have to replace that node too.
+
+     However, when we're changing a shortcut into a node this isn't a problem
+     as shortcuts only have one slot and so the parent slot number isn't used
+     when traversing backwards over one.  This means that it's okay to change
+     the slot number first - provided suitable barriers are used to make sure
+     the parent slot number is read after the back pointer.
+
+Obsolete blocks and leaves are freed up after an RCU grace period has passed,
+so as long as anyone doing walking or iteration holds the RCU read lock, the
+old superstructure should not go away on them.
diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h
new file mode 100644
index 000000000000..9a193b84238a
--- /dev/null
+++ b/include/linux/assoc_array.h
@@ -0,0 +1,92 @@
+/* Generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_H
+#define _LINUX_ASSOC_ARRAY_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/types.h>
+
+#define ASSOC_ARRAY_KEY_CHUNK_SIZE BITS_PER_LONG /* Key data retrieved in chunks of this size */
+
+/*
+ * Generic associative array.
+ */
+struct assoc_array {
+	struct assoc_array_ptr	*root;		/* The node at the root of the tree */
+	unsigned long		nr_leaves_on_tree;
+};
+
+/*
+ * Operations on objects and index keys for use by array manipulation routines.
+ */
+struct assoc_array_ops {
+	/* Method to get a chunk of an index key from caller-supplied data */
+	unsigned long (*get_key_chunk)(const void *index_key, int level);
+
+	/* Method to get a piece of an object's index key */
+	unsigned long (*get_object_key_chunk)(const void *object, int level);
+
+	/* Is this the object we're looking for? */
+	bool (*compare_object)(const void *object, const void *index_key);
+
+	/* How different are two objects, to a bit position in their keys? (or
+	 * -1 if they're the same)
+	 */
+	int (*diff_objects)(const void *a, const void *b);
+
+	/* Method to free an object. */
+	void (*free_object)(void *object);
+};
+
+/*
+ * Access and manipulation functions.
+ */
+struct assoc_array_edit;
+
+static inline void assoc_array_init(struct assoc_array *array)
+{
+	array->root = NULL;
+	array->nr_leaves_on_tree = 0;
+}
+
+extern int assoc_array_iterate(const struct assoc_array *array,
+			       int (*iterator)(const void *object,
+					       void *iterator_data),
+			       void *iterator_data);
+extern void *assoc_array_find(const struct assoc_array *array,
+			      const struct assoc_array_ops *ops,
+			      const void *index_key);
+extern void assoc_array_destroy(struct assoc_array *array,
+				const struct assoc_array_ops *ops);
+extern struct assoc_array_edit *assoc_array_insert(struct assoc_array *array,
+						   const struct assoc_array_ops *ops,
+						   const void *index_key,
+						   void *object);
+extern void assoc_array_insert_set_object(struct assoc_array_edit *edit,
+					  void *object);
+extern struct assoc_array_edit *assoc_array_delete(struct assoc_array *array,
+						   const struct assoc_array_ops *ops,
+						   const void *index_key);
+extern struct assoc_array_edit *assoc_array_clear(struct assoc_array *array,
+						  const struct assoc_array_ops *ops);
+extern void assoc_array_apply_edit(struct assoc_array_edit *edit);
+extern void assoc_array_cancel_edit(struct assoc_array_edit *edit);
+extern int assoc_array_gc(struct assoc_array *array,
+			  const struct assoc_array_ops *ops,
+			  bool (*iterator)(void *object, void *iterator_data),
+			  void *iterator_data);
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_H */
diff --git a/include/linux/assoc_array_priv.h b/include/linux/assoc_array_priv.h
new file mode 100644
index 000000000000..711275e6681c
--- /dev/null
+++ b/include/linux/assoc_array_priv.h
@@ -0,0 +1,182 @@
+/* Private definitions for the generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _LINUX_ASSOC_ARRAY_PRIV_H
+#define _LINUX_ASSOC_ARRAY_PRIV_H
+
+#ifdef CONFIG_ASSOCIATIVE_ARRAY
+
+#include <linux/assoc_array.h>
+
+#define ASSOC_ARRAY_FAN_OUT		16	/* Number of slots per node */
+#define ASSOC_ARRAY_FAN_MASK		(ASSOC_ARRAY_FAN_OUT - 1)
+#define ASSOC_ARRAY_LEVEL_STEP		(ilog2(ASSOC_ARRAY_FAN_OUT))
+#define ASSOC_ARRAY_LEVEL_STEP_MASK	(ASSOC_ARRAY_LEVEL_STEP - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_MASK	(ASSOC_ARRAY_KEY_CHUNK_SIZE - 1)
+#define ASSOC_ARRAY_KEY_CHUNK_SHIFT	(ilog2(BITS_PER_LONG))
+
+/*
+ * Undefined type representing a pointer with type information in the bottom
+ * two bits.
+ */
+struct assoc_array_ptr;
+
+/*
+ * An N-way node in the tree.
+ *
+ * Each slot contains one of four things:
+ *
+ *	(1) Nothing (NULL).
+ *
+ *	(2) A leaf object (pointer types 0).
+ *
+ *	(3) A next-level node (pointer type 1, subtype 0).
+ *
+ *	(4) A shortcut (pointer type 1, subtype 1).
+ *
+ * The tree is optimised for search-by-ID, but permits reasonable iteration
+ * also.
+ *
+ * The tree is navigated by constructing an index key consisting of an array of
+ * segments, where each segment is ilog2(ASSOC_ARRAY_FAN_OUT) bits in size.
+ *
+ * The segments correspond to levels of the tree (the first segment is used at
+ * level 0, the second at level 1, etc.).
+ */
+struct assoc_array_node {
+	struct assoc_array_ptr	*back_pointer;
+	u8			parent_slot;
+	struct assoc_array_ptr	*slots[ASSOC_ARRAY_FAN_OUT];
+	unsigned long		nr_leaves_on_branch;
+};
+
+/*
+ * A shortcut through the index space out to where a collection of nodes/leaves
+ * with the same IDs live.
+ */
+struct assoc_array_shortcut {
+	struct assoc_array_ptr	*back_pointer;
+	int			parent_slot;
+	int			skip_to_level;
+	struct assoc_array_ptr	*next_node;
+	unsigned long		index_key[];
+};
+
+/*
+ * Preallocation cache.
+ */
+struct assoc_array_edit {
+	struct rcu_head			rcu;
+	struct assoc_array		*array;
+	const struct assoc_array_ops	*ops;
+	const struct assoc_array_ops	*ops_for_excised_subtree;
+	struct assoc_array_ptr		*leaf;
+	struct assoc_array_ptr		**leaf_p;
+	struct assoc_array_ptr		*dead_leaf;
+	struct assoc_array_ptr		*new_meta[3];
+	struct assoc_array_ptr		*excised_meta[1];
+	struct assoc_array_ptr		*excised_subtree;
+	struct assoc_array_ptr		**set_backpointers[ASSOC_ARRAY_FAN_OUT];
+	struct assoc_array_ptr		*set_backpointers_to;
+	struct assoc_array_node		*adjust_count_on;
+	long				adjust_count_by;
+	struct {
+		struct assoc_array_ptr	**ptr;
+		struct assoc_array_ptr	*to;
+	} set[2];
+	struct {
+		u8			*p;
+		u8			to;
+	} set_parent_slot[1];
+	u8				segment_cache[ASSOC_ARRAY_FAN_OUT + 1];
+};
+
+/*
+ * Internal tree member pointers are marked in the bottom one or two bits to
+ * indicate what type they are so that we don't have to look behind every
+ * pointer to see what it points to.
+ *
+ * We provide functions to test type annotations and to create and translate
+ * the annotated pointers.
+ */
+#define ASSOC_ARRAY_PTR_TYPE_MASK 0x1UL
+#define ASSOC_ARRAY_PTR_LEAF_TYPE 0x0UL	/* Points to leaf (or nowhere) */
+#define ASSOC_ARRAY_PTR_META_TYPE 0x1UL	/* Points to node or shortcut */
+#define ASSOC_ARRAY_PTR_SUBTYPE_MASK	0x2UL
+#define ASSOC_ARRAY_PTR_NODE_SUBTYPE	0x0UL
+#define ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE 0x2UL
+
+static inline bool assoc_array_ptr_is_meta(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & ASSOC_ARRAY_PTR_TYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_leaf(const struct assoc_array_ptr *x)
+{
+	return !assoc_array_ptr_is_meta(x);
+}
+static inline bool assoc_array_ptr_is_shortcut(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & ASSOC_ARRAY_PTR_SUBTYPE_MASK;
+}
+static inline bool assoc_array_ptr_is_node(const struct assoc_array_ptr *x)
+{
+	return !assoc_array_ptr_is_shortcut(x);
+}
+
+static inline void *assoc_array_ptr_to_leaf(const struct assoc_array_ptr *x)
+{
+	return (void *)((unsigned long)x & ~ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+
+static inline
+unsigned long __assoc_array_ptr_to_meta(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x &
+		~(ASSOC_ARRAY_PTR_SUBTYPE_MASK | ASSOC_ARRAY_PTR_TYPE_MASK);
+}
+static inline
+struct assoc_array_node *assoc_array_ptr_to_node(const struct assoc_array_ptr *x)
+{
+	return (struct assoc_array_node *)__assoc_array_ptr_to_meta(x);
+}
+static inline
+struct assoc_array_shortcut *assoc_array_ptr_to_shortcut(const struct assoc_array_ptr *x)
+{
+	return (struct assoc_array_shortcut *)__assoc_array_ptr_to_meta(x);
+}
+
+static inline
+struct assoc_array_ptr *__assoc_array_x_to_ptr(const void *p, unsigned long t)
+{
+	return (struct assoc_array_ptr *)((unsigned long)p | t);
+}
+static inline
+struct assoc_array_ptr *assoc_array_leaf_to_ptr(const void *p)
+{
+	return __assoc_array_x_to_ptr(p, ASSOC_ARRAY_PTR_LEAF_TYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_node_to_ptr(const struct assoc_array_node *p)
+{
+	return __assoc_array_x_to_ptr(
+		p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_NODE_SUBTYPE);
+}
+static inline
+struct assoc_array_ptr *assoc_array_shortcut_to_ptr(const struct assoc_array_shortcut *p)
+{
+	return __assoc_array_x_to_ptr(
+		p, ASSOC_ARRAY_PTR_META_TYPE | ASSOC_ARRAY_PTR_SHORTCUT_SUBTYPE);
+}
+
+#endif /* CONFIG_ASSOCIATIVE_ARRAY */
+#endif /* _LINUX_ASSOC_ARRAY_PRIV_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index b3c8be0da17f..3cb879b1f282 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -322,6 +322,20 @@ config TEXTSEARCH_FSM
 config BTREE
 	boolean
 
+config ASSOCIATIVE_ARRAY
+	bool
+	help
+	  Generic associative array.  Can be searched and iterated over whilst
+	  it is being modified.  It is also reasonably quick to search and
+	  modify.  The algorithms are non-recursive, and the trees are highly
+	  capacious.
+
+	  See:
+
+		Documentation/assoc_array.txt
+
+	  for more information.
+
 config HAS_IOMEM
 	boolean
 	depends on !NO_IOMEM
diff --git a/lib/Makefile b/lib/Makefile
index f3bb2cb98adf..1e806477e472 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -51,6 +51,7 @@ CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
 obj-$(CONFIG_BTREE) += btree.o
+obj-$(CONFIG_ASSOCIATIVE_ARRAY) += assoc_array.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
new file mode 100644
index 000000000000..a0952818f938
--- /dev/null
+++ b/lib/assoc_array.c
@@ -0,0 +1,1745 @@
+/* Generic associative array implementation.
+ *
+ * See Documentation/assoc_array.txt for information.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+//#define DEBUG
+#include <linux/slab.h>
+#include <linux/assoc_array_priv.h>
+
+/*
+ * Iterate over an associative array.  The caller must hold the RCU read lock
+ * or better.
+ */
+static int assoc_array_subtree_iterate(const struct assoc_array_ptr *root,
+				       const struct assoc_array_ptr *stop,
+				       int (*iterator)(const void *leaf,
+						       void *iterator_data),
+				       void *iterator_data)
+{
+	const struct assoc_array_shortcut *shortcut;
+	const struct assoc_array_node *node;
+	const struct assoc_array_ptr *cursor, *ptr, *parent;
+	unsigned long has_meta;
+	int slot, ret;
+
+	cursor = root;
+
+begin_node:
+	if (assoc_array_ptr_is_shortcut(cursor)) {
+		/* Descend through a shortcut */
+		shortcut = assoc_array_ptr_to_shortcut(cursor);
+		smp_read_barrier_depends();
+		cursor = ACCESS_ONCE(shortcut->next_node);
+	}
+
+	node = assoc_array_ptr_to_node(cursor);
+	smp_read_barrier_depends();
+	slot = 0;
+
+	/* We perform two passes of each node.
+	 *
+	 * The first pass does all the leaves in this node.  This means we
+	 * don't miss any leaves if the node is split up by insertion whilst
+	 * we're iterating over the branches rooted here (we may, however, see
+	 * some leaves twice).
+	 */
+	has_meta = 0;
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = ACCESS_ONCE(node->slots[slot]);
+		has_meta |= (unsigned long)ptr;
+		if (ptr && assoc_array_ptr_is_leaf(ptr)) {
+			/* We need a barrier between the read of the pointer
+			 * and dereferencing the pointer - but only if we are
+			 * actually going to dereference it.
+			 */
+			smp_read_barrier_depends();
+
+			/* Invoke the callback */
+			ret = iterator(assoc_array_ptr_to_leaf(ptr),
+				       iterator_data);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* The second pass attends to all the metadata pointers.  If we follow
+	 * one of these we may find that we don't come back here, but rather go
+	 * back to a replacement node with the leaves in a different layout.
+	 *
+	 * We are guaranteed to make progress, however, as the slot number for
+	 * a particular portion of the key space cannot change - and we
+	 * continue at the back pointer + 1.
+	 */
+	if (!(has_meta & ASSOC_ARRAY_PTR_META_TYPE))
+		goto finished_node;
+	slot = 0;
+
+continue_node:
+	node = assoc_array_ptr_to_node(cursor);
+	smp_read_barrier_depends();
+
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = ACCESS_ONCE(node->slots[slot]);
+		if (assoc_array_ptr_is_meta(ptr)) {
+			cursor = ptr;
+			goto begin_node;
+		}
+	}
+
+finished_node:
+	/* Move up to the parent (may need to skip back over a shortcut) */
+	parent = ACCESS_ONCE(node->back_pointer);
+	slot = node->parent_slot;
+	if (parent == stop)
+		return 0;
+
+	if (assoc_array_ptr_is_shortcut(parent)) {
+		shortcut = assoc_array_ptr_to_shortcut(parent);
+		smp_read_barrier_depends();
+		cursor = parent;
+		parent = ACCESS_ONCE(shortcut->back_pointer);
+		slot = shortcut->parent_slot;
+		if (parent == stop)
+			return 0;
+	}
+
+	/* Ascend to next slot in parent node */
+	cursor = parent;
+	slot++;
+	goto continue_node;
+}
+
+/**
+ * assoc_array_iterate - Pass all objects in the array to a callback
+ * @array: The array to iterate over.
+ * @iterator: The callback function.
+ * @iterator_data: Private data for the callback function.
+ *
+ * Iterate over all the objects in an associative array.  Each one will be
+ * presented to the iterator function.
+ *
+ * If the array is being modified concurrently with the iteration then it is
+ * possible that some objects in the array will be passed to the iterator
+ * callback more than once - though every object should be passed at least
+ * once.  If this is undesirable then the caller must lock against modification
+ * for the duration of this function.
+ *
+ * The function will return 0 if no objects were in the array or else it will
+ * return the result of the last iterator function called.  Iteration stops
+ * immediately if any call to the iteration function results in a non-zero
+ * return.
+ *
+ * The caller should hold the RCU read lock or better if concurrent
+ * modification is possible.
+ */
+int assoc_array_iterate(const struct assoc_array *array,
+			int (*iterator)(const void *object,
+					void *iterator_data),
+			void *iterator_data)
+{
+	struct assoc_array_ptr *root = ACCESS_ONCE(array->root);
+
+	if (!root)
+		return 0;
+	return assoc_array_subtree_iterate(root, NULL, iterator, iterator_data);
+}
+
+enum assoc_array_walk_status {
+	assoc_array_walk_tree_empty,
+	assoc_array_walk_found_terminal_node,
+	assoc_array_walk_found_wrong_shortcut,
+} status;
+
+struct assoc_array_walk_result {
+	struct {
+		struct assoc_array_node	*node;	/* Node in which leaf might be found */
+		int		level;
+		int		slot;
+	} terminal_node;
+	struct {
+		struct assoc_array_shortcut *shortcut;
+		int		level;
+		int		sc_level;
+		unsigned long	sc_segments;
+		unsigned long	dissimilarity;
+	} wrong_shortcut;
+};
+
+/*
+ * Navigate through the internal tree looking for the closest node to the key.
+ */
+static enum assoc_array_walk_status
+assoc_array_walk(const struct assoc_array *array,
+		 const struct assoc_array_ops *ops,
+		 const void *index_key,
+		 struct assoc_array_walk_result *result)
+{
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *cursor, *ptr;
+	unsigned long sc_segments, dissimilarity;
+	unsigned long segments;
+	int level, sc_level, next_sc_level;
+	int slot;
+
+	pr_devel("-->%s()\n", __func__);
+
+	cursor = ACCESS_ONCE(array->root);
+	if (!cursor)
+		return assoc_array_walk_tree_empty;
+
+	level = 0;
+
+	/* Use segments from the key for the new leaf to navigate through the
+	 * internal tree, skipping through nodes and shortcuts that are on
+	 * route to the destination.  Eventually we'll come to a slot that is
+	 * either empty or contains a leaf at which point we've found a node in
+	 * which the leaf we're looking for might be found or into which it
+	 * should be inserted.
+	 */
+jumped:
+	segments = ops->get_key_chunk(index_key, level);
+	pr_devel("segments[%d]: %lx\n", level, segments);
+
+	if (assoc_array_ptr_is_shortcut(cursor))
+		goto follow_shortcut;
+
+consider_node:
+	node = assoc_array_ptr_to_node(cursor);
+	smp_read_barrier_depends();
+
+	slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
+	slot &= ASSOC_ARRAY_FAN_MASK;
+	ptr = ACCESS_ONCE(node->slots[slot]);
+
+	pr_devel("consider slot %x [ix=%d type=%lu]\n",
+		 slot, level, (unsigned long)ptr & 3);
+
+	if (!assoc_array_ptr_is_meta(ptr)) {
+		/* The node doesn't have a node/shortcut pointer in the slot
+		 * corresponding to the index key that we have to follow.
+		 */
+		result->terminal_node.node = node;
+		result->terminal_node.level = level;
+		result->terminal_node.slot = slot;
+		pr_devel("<--%s() = terminal_node\n", __func__);
+		return assoc_array_walk_found_terminal_node;
+	}
+
+	if (assoc_array_ptr_is_node(ptr)) {
+		/* There is a pointer to a node in the slot corresponding to
+		 * this index key segment, so we need to follow it.
+		 */
+		cursor = ptr;
+		level += ASSOC_ARRAY_LEVEL_STEP;
+		if ((level & ASSOC_ARRAY_KEY_CHUNK_MASK) != 0)
+			goto consider_node;
+		goto jumped;
+	}
+
+	/* There is a shortcut in the slot corresponding to the index key
+	 * segment.  We follow the shortcut if its partial index key matches
+	 * this leaf's.  Otherwise we need to split the shortcut.
+	 */
+	cursor = ptr;
+follow_shortcut:
+	shortcut = assoc_array_ptr_to_shortcut(cursor);
+	smp_read_barrier_depends();
+	pr_devel("shortcut to %d\n", shortcut->skip_to_level);
+	sc_level = level + ASSOC_ARRAY_LEVEL_STEP;
+	BUG_ON(sc_level > shortcut->skip_to_level);
+
+	do {
+		/* Check the leaf against the shortcut's index key a word at a
+		 * time, trimming the final word (the shortcut stores the index
+		 * key completely from the root to the shortcut's target).
+		 */
+		if ((sc_level & ASSOC_ARRAY_KEY_CHUNK_MASK) == 0)
+			segments = ops->get_key_chunk(index_key, sc_level);
+
+		sc_segments = shortcut->index_key[sc_level >> ASSOC_ARRAY_KEY_CHUNK_SHIFT];
+		dissimilarity = segments ^ sc_segments;
+
+		if (round_up(sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE) > shortcut->skip_to_level) {
+			/* Trim segments that are beyond the shortcut */
+			int shift = shortcut->skip_to_level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+			dissimilarity &= ~(ULONG_MAX << shift);
+			next_sc_level = shortcut->skip_to_level;
+		} else {
+			next_sc_level = sc_level + ASSOC_ARRAY_KEY_CHUNK_SIZE;
+			next_sc_level = round_down(next_sc_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+		}
+
+		if (dissimilarity != 0) {
+			/* This shortcut points elsewhere */
+			result->wrong_shortcut.shortcut = shortcut;
+			result->wrong_shortcut.level = level;
+			result->wrong_shortcut.sc_level = sc_level;
+			result->wrong_shortcut.sc_segments = sc_segments;
+			result->wrong_shortcut.dissimilarity = dissimilarity;
+			return assoc_array_walk_found_wrong_shortcut;
+		}
+
+		sc_level = next_sc_level;
+	} while (sc_level < shortcut->skip_to_level);
+
+	/* The shortcut matches the leaf's index to this point. */
+	cursor = ACCESS_ONCE(shortcut->next_node);
+	if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) {
+		level = sc_level;
+		goto jumped;
+	} else {
+		level = sc_level;
+		goto consider_node;
+	}
+}
+
+/**
+ * assoc_array_find - Find an object by index key
+ * @array: The associative array to search.
+ * @ops: The operations to use.
+ * @index_key: The key to the object.
+ *
+ * Find an object in an associative array by walking through the internal tree
+ * to the node that should contain the object and then searching the leaves
+ * there.  NULL is returned if the requested object was not found in the array.
+ *
+ * The caller must hold the RCU read lock or better.
+ */
+void *assoc_array_find(const struct assoc_array *array,
+		       const struct assoc_array_ops *ops,
+		       const void *index_key)
+{
+	struct assoc_array_walk_result result;
+	const struct assoc_array_node *node;
+	const struct assoc_array_ptr *ptr;
+	const void *leaf;
+	int slot;
+
+	if (assoc_array_walk(array, ops, index_key, &result) !=
+	    assoc_array_walk_found_terminal_node)
+		return NULL;
+
+	node = result.terminal_node.node;
+	smp_read_barrier_depends();
+
+	/* If the target key is available to us, it's has to be pointed to by
+	 * the terminal node.
+	 */
+	for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = ACCESS_ONCE(node->slots[slot]);
+		if (ptr && assoc_array_ptr_is_leaf(ptr)) {
+			/* We need a barrier between the read of the pointer
+			 * and dereferencing the pointer - but only if we are
+			 * actually going to dereference it.
+			 */
+			leaf = assoc_array_ptr_to_leaf(ptr);
+			smp_read_barrier_depends();
+			if (ops->compare_object(leaf, index_key))
+				return (void *)leaf;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Destructively iterate over an associative array.  The caller must prevent
+ * other simultaneous accesses.
+ */
+static void assoc_array_destroy_subtree(struct assoc_array_ptr *root,
+					const struct assoc_array_ops *ops)
+{
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *cursor, *parent = NULL;
+	int slot = -1;
+
+	pr_devel("-->%s()\n", __func__);
+
+	cursor = root;
+	if (!cursor) {
+		pr_devel("empty\n");
+		return;
+	}
+
+move_to_meta:
+	if (assoc_array_ptr_is_shortcut(cursor)) {
+		/* Descend through a shortcut */
+		pr_devel("[%d] shortcut\n", slot);
+		BUG_ON(!assoc_array_ptr_is_shortcut(cursor));
+		shortcut = assoc_array_ptr_to_shortcut(cursor);
+		BUG_ON(shortcut->back_pointer != parent);
+		BUG_ON(slot != -1 && shortcut->parent_slot != slot);
+		parent = cursor;
+		cursor = shortcut->next_node;
+		slot = -1;
+		BUG_ON(!assoc_array_ptr_is_node(cursor));
+	}
+
+	pr_devel("[%d] node\n", slot);
+	node = assoc_array_ptr_to_node(cursor);
+	BUG_ON(node->back_pointer != parent);
+	BUG_ON(slot != -1 && node->parent_slot != slot);
+	slot = 0;
+
+continue_node:
+	pr_devel("Node %p [back=%p]\n", node, node->back_pointer);
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		struct assoc_array_ptr *ptr = node->slots[slot];
+		if (!ptr)
+			continue;
+		if (assoc_array_ptr_is_meta(ptr)) {
+			parent = cursor;
+			cursor = ptr;
+			goto move_to_meta;
+		}
+
+		if (ops) {
+			pr_devel("[%d] free leaf\n", slot);
+			ops->free_object(assoc_array_ptr_to_leaf(ptr));
+		}
+	}
+
+	parent = node->back_pointer;
+	slot = node->parent_slot;
+	pr_devel("free node\n");
+	kfree(node);
+	if (!parent)
+		return; /* Done */
+
+	/* Move back up to the parent (may need to free a shortcut on
+	 * the way up) */
+	if (assoc_array_ptr_is_shortcut(parent)) {
+		shortcut = assoc_array_ptr_to_shortcut(parent);
+		BUG_ON(shortcut->next_node != cursor);
+		cursor = parent;
+		parent = shortcut->back_pointer;
+		slot = shortcut->parent_slot;
+		pr_devel("free shortcut\n");
+		kfree(shortcut);
+		if (!parent)
+			return;
+
+		BUG_ON(!assoc_array_ptr_is_node(parent));
+	}
+
+	/* Ascend to next slot in parent node */
+	pr_devel("ascend to %p[%d]\n", parent, slot);
+	cursor = parent;
+	node = assoc_array_ptr_to_node(cursor);
+	slot++;
+	goto continue_node;
+}
+
+/**
+ * assoc_array_destroy - Destroy an associative array
+ * @array: The array to destroy.
+ * @ops: The operations to use.
+ *
+ * Discard all metadata and free all objects in an associative array.  The
+ * array will be empty and ready to use again upon completion.  This function
+ * cannot fail.
+ *
+ * The caller must prevent all other accesses whilst this takes place as no
+ * attempt is made to adjust pointers gracefully to permit RCU readlock-holding
+ * accesses to continue.  On the other hand, no memory allocation is required.
+ */
+void assoc_array_destroy(struct assoc_array *array,
+			 const struct assoc_array_ops *ops)
+{
+	assoc_array_destroy_subtree(array->root, ops);
+	array->root = NULL;
+}
+
+/*
+ * Handle insertion into an empty tree.
+ */
+static bool assoc_array_insert_in_empty_tree(struct assoc_array_edit *edit)
+{
+	struct assoc_array_node *new_n0;
+
+	pr_devel("-->%s()\n", __func__);
+
+	new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+	if (!new_n0)
+		return false;
+
+	edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+	edit->leaf_p = &new_n0->slots[0];
+	edit->adjust_count_on = new_n0;
+	edit->set[0].ptr = &edit->array->root;
+	edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+
+	pr_devel("<--%s() = ok [no root]\n", __func__);
+	return true;
+}
+
+/*
+ * Handle insertion into a terminal node.
+ */
+static bool assoc_array_insert_into_terminal_node(struct assoc_array_edit *edit,
+						  const struct assoc_array_ops *ops,
+						  const void *index_key,
+						  struct assoc_array_walk_result *result)
+{
+	struct assoc_array_shortcut *shortcut, *new_s0;
+	struct assoc_array_node *node, *new_n0, *new_n1, *side;
+	struct assoc_array_ptr *ptr;
+	unsigned long dissimilarity, base_seg, blank;
+	size_t keylen;
+	bool have_meta;
+	int level, diff;
+	int slot, next_slot, free_slot, i, j;
+
+	node	= result->terminal_node.node;
+	level	= result->terminal_node.level;
+	edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = result->terminal_node.slot;
+
+	pr_devel("-->%s()\n", __func__);
+
+	/* We arrived at a node which doesn't have an onward node or shortcut
+	 * pointer that we have to follow.  This means that (a) the leaf we
+	 * want must go here (either by insertion or replacement) or (b) we
+	 * need to split this node and insert in one of the fragments.
+	 */
+	free_slot = -1;
+
+	/* Firstly, we have to check the leaves in this node to see if there's
+	 * a matching one we should replace in place.
+	 */
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		ptr = node->slots[i];
+		if (!ptr) {
+			free_slot = i;
+			continue;
+		}
+		if (ops->compare_object(assoc_array_ptr_to_leaf(ptr), index_key)) {
+			pr_devel("replace in slot %d\n", i);
+			edit->leaf_p = &node->slots[i];
+			edit->dead_leaf = node->slots[i];
+			pr_devel("<--%s() = ok [replace]\n", __func__);
+			return true;
+		}
+	}
+
+	/* If there is a free slot in this node then we can just insert the
+	 * leaf here.
+	 */
+	if (free_slot >= 0) {
+		pr_devel("insert in free slot %d\n", free_slot);
+		edit->leaf_p = &node->slots[free_slot];
+		edit->adjust_count_on = node;
+		pr_devel("<--%s() = ok [insert]\n", __func__);
+		return true;
+	}
+
+	/* The node has no spare slots - so we're either going to have to split
+	 * it or insert another node before it.
+	 *
+	 * Whatever, we're going to need at least two new nodes - so allocate
+	 * those now.  We may also need a new shortcut, but we deal with that
+	 * when we need it.
+	 */
+	new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+	if (!new_n0)
+		return false;
+	edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+	new_n1 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+	if (!new_n1)
+		return false;
+	edit->new_meta[1] = assoc_array_node_to_ptr(new_n1);
+
+	/* We need to find out how similar the leaves are. */
+	pr_devel("no spare slots\n");
+	have_meta = false;
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		ptr = node->slots[i];
+		if (assoc_array_ptr_is_meta(ptr)) {
+			edit->segment_cache[i] = 0xff;
+			have_meta = true;
+			continue;
+		}
+		base_seg = ops->get_object_key_chunk(
+			assoc_array_ptr_to_leaf(ptr), level);
+		base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+		edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK;
+	}
+
+	if (have_meta) {
+		pr_devel("have meta\n");
+		goto split_node;
+	}
+
+	/* The node contains only leaves */
+	dissimilarity = 0;
+	base_seg = edit->segment_cache[0];
+	for (i = 1; i < ASSOC_ARRAY_FAN_OUT; i++)
+		dissimilarity |= edit->segment_cache[i] ^ base_seg;
+
+	pr_devel("only leaves; dissimilarity=%lx\n", dissimilarity);
+
+	if ((dissimilarity & ASSOC_ARRAY_FAN_MASK) == 0) {
+		/* The old leaves all cluster in the same slot.  We will need
+		 * to insert a shortcut if the new node wants to cluster with them.
+		 */
+		if ((edit->segment_cache[ASSOC_ARRAY_FAN_OUT] ^ base_seg) == 0)
+			goto all_leaves_cluster_together;
+
+		/* Otherwise we can just insert a new node ahead of the old
+		 * one.
+		 */
+		goto present_leaves_cluster_but_not_new_leaf;
+	}
+
+split_node:
+	pr_devel("split node\n");
+
+	/* We need to split the current node; we know that the node doesn't
+	 * simply contain a full set of leaves that cluster together (it
+	 * contains meta pointers and/or non-clustering leaves).
+	 *
+	 * We need to expel at least two leaves out of a set consisting of the
+	 * leaves in the node and the new leaf.
+	 *
+	 * We need a new node (n0) to replace the current one and a new node to
+	 * take the expelled nodes (n1).
+	 */
+	edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+	new_n0->back_pointer = node->back_pointer;
+	new_n0->parent_slot = node->parent_slot;
+	new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+	new_n1->parent_slot = -1; /* Need to calculate this */
+
+do_split_node:
+	pr_devel("do_split_node\n");
+
+	new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+	new_n1->nr_leaves_on_branch = 0;
+
+	/* Begin by finding two matching leaves.  There have to be at least two
+	 * that match - even if there are meta pointers - because any leaf that
+	 * would match a slot with a meta pointer in it must be somewhere
+	 * behind that meta pointer and cannot be here.  Further, given N
+	 * remaining leaf slots, we now have N+1 leaves to go in them.
+	 */
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		slot = edit->segment_cache[i];
+		if (slot != 0xff)
+			for (j = i + 1; j < ASSOC_ARRAY_FAN_OUT + 1; j++)
+				if (edit->segment_cache[j] == slot)
+					goto found_slot_for_multiple_occupancy;
+	}
+found_slot_for_multiple_occupancy:
+	pr_devel("same slot: %x %x [%02x]\n", i, j, slot);
+	BUG_ON(i >= ASSOC_ARRAY_FAN_OUT);
+	BUG_ON(j >= ASSOC_ARRAY_FAN_OUT + 1);
+	BUG_ON(slot >= ASSOC_ARRAY_FAN_OUT);
+
+	new_n1->parent_slot = slot;
+
+	/* Metadata pointers cannot change slot */
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++)
+		if (assoc_array_ptr_is_meta(node->slots[i]))
+			new_n0->slots[i] = node->slots[i];
+		else
+			new_n0->slots[i] = NULL;
+	BUG_ON(new_n0->slots[slot] != NULL);
+	new_n0->slots[slot] = assoc_array_node_to_ptr(new_n1);
+
+	/* Filter the leaf pointers between the new nodes */
+	free_slot = -1;
+	next_slot = 0;
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		if (assoc_array_ptr_is_meta(node->slots[i]))
+			continue;
+		if (edit->segment_cache[i] == slot) {
+			new_n1->slots[next_slot++] = node->slots[i];
+			new_n1->nr_leaves_on_branch++;
+		} else {
+			do {
+				free_slot++;
+			} while (new_n0->slots[free_slot] != NULL);
+			new_n0->slots[free_slot] = node->slots[i];
+		}
+	}
+
+	pr_devel("filtered: f=%x n=%x\n", free_slot, next_slot);
+
+	if (edit->segment_cache[ASSOC_ARRAY_FAN_OUT] != slot) {
+		do {
+			free_slot++;
+		} while (new_n0->slots[free_slot] != NULL);
+		edit->leaf_p = &new_n0->slots[free_slot];
+		edit->adjust_count_on = new_n0;
+	} else {
+		edit->leaf_p = &new_n1->slots[next_slot++];
+		edit->adjust_count_on = new_n1;
+	}
+
+	BUG_ON(next_slot <= 1);
+
+	edit->set_backpointers_to = assoc_array_node_to_ptr(new_n0);
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		if (edit->segment_cache[i] == 0xff) {
+			ptr = node->slots[i];
+			BUG_ON(assoc_array_ptr_is_leaf(ptr));
+			if (assoc_array_ptr_is_node(ptr)) {
+				side = assoc_array_ptr_to_node(ptr);
+				edit->set_backpointers[i] = &side->back_pointer;
+			} else {
+				shortcut = assoc_array_ptr_to_shortcut(ptr);
+				edit->set_backpointers[i] = &shortcut->back_pointer;
+			}
+		}
+	}
+
+	ptr = node->back_pointer;
+	if (!ptr)
+		edit->set[0].ptr = &edit->array->root;
+	else if (assoc_array_ptr_is_node(ptr))
+		edit->set[0].ptr = &assoc_array_ptr_to_node(ptr)->slots[node->parent_slot];
+	else
+		edit->set[0].ptr = &assoc_array_ptr_to_shortcut(ptr)->next_node;
+	edit->excised_meta[0] = assoc_array_node_to_ptr(node);
+	pr_devel("<--%s() = ok [split node]\n", __func__);
+	return true;
+
+present_leaves_cluster_but_not_new_leaf:
+	/* All the old leaves cluster in the same slot, but the new leaf wants
+	 * to go into a different slot, so we create a new node to hold the new
+	 * leaf and a pointer to a new node holding all the old leaves.
+	 */
+	pr_devel("present leaves cluster but not new leaf\n");
+
+	new_n0->back_pointer = node->back_pointer;
+	new_n0->parent_slot = node->parent_slot;
+	new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+	new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+	new_n1->parent_slot = edit->segment_cache[0];
+	new_n1->nr_leaves_on_branch = node->nr_leaves_on_branch;
+	edit->adjust_count_on = new_n0;
+
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++)
+		new_n1->slots[i] = node->slots[i];
+
+	new_n0->slots[edit->segment_cache[0]] = assoc_array_node_to_ptr(new_n0);
+	edit->leaf_p = &new_n0->slots[edit->segment_cache[ASSOC_ARRAY_FAN_OUT]];
+
+	edit->set[0].ptr = &assoc_array_ptr_to_node(node->back_pointer)->slots[node->parent_slot];
+	edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+	edit->excised_meta[0] = assoc_array_node_to_ptr(node);
+	pr_devel("<--%s() = ok [insert node before]\n", __func__);
+	return true;
+
+all_leaves_cluster_together:
+	/* All the leaves, new and old, want to cluster together in this node
+	 * in the same slot, so we have to replace this node with a shortcut to
+	 * skip over the identical parts of the key and then place a pair of
+	 * nodes, one inside the other, at the end of the shortcut and
+	 * distribute the keys between them.
+	 *
+	 * Firstly we need to work out where the leaves start diverging as a
+	 * bit position into their keys so that we know how big the shortcut
+	 * needs to be.
+	 *
+	 * We only need to make a single pass of N of the N+1 leaves because if
+	 * any keys differ between themselves at bit X then at least one of
+	 * them must also differ with the base key at bit X or before.
+	 */
+	pr_devel("all leaves cluster together\n");
+	diff = INT_MAX;
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		int x = ops->diff_objects(assoc_array_ptr_to_leaf(edit->leaf),
+					  assoc_array_ptr_to_leaf(node->slots[i]));
+		if (x < diff) {
+			BUG_ON(x < 0);
+			diff = x;
+		}
+	}
+	BUG_ON(diff == INT_MAX);
+	BUG_ON(diff < level + ASSOC_ARRAY_LEVEL_STEP);
+
+	keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+	keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+	new_s0 = kzalloc(sizeof(struct assoc_array_shortcut) +
+			 keylen * sizeof(unsigned long), GFP_KERNEL);
+	if (!new_s0)
+		return false;
+	edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s0);
+
+	edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0);
+	new_s0->back_pointer = node->back_pointer;
+	new_s0->parent_slot = node->parent_slot;
+	new_s0->next_node = assoc_array_node_to_ptr(new_n0);
+	new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0);
+	new_n0->parent_slot = 0;
+	new_n1->back_pointer = assoc_array_node_to_ptr(new_n0);
+	new_n1->parent_slot = -1; /* Need to calculate this */
+
+	new_s0->skip_to_level = level = diff & ~ASSOC_ARRAY_LEVEL_STEP_MASK;
+	pr_devel("skip_to_level = %d [diff %d]\n", level, diff);
+	BUG_ON(level <= 0);
+
+	for (i = 0; i < keylen; i++)
+		new_s0->index_key[i] =
+			ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE);
+
+	blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK);
+	pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank);
+	new_s0->index_key[keylen - 1] &= ~blank;
+
+	/* This now reduces to a node splitting exercise for which we'll need
+	 * to regenerate the disparity table.
+	 */
+	for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+		ptr = node->slots[i];
+		base_seg = ops->get_object_key_chunk(assoc_array_ptr_to_leaf(ptr),
+						     level);
+		base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+		edit->segment_cache[i] = base_seg & ASSOC_ARRAY_FAN_MASK;
+	}
+
+	base_seg = ops->get_key_chunk(index_key, level);
+	base_seg >>= level & ASSOC_ARRAY_KEY_CHUNK_MASK;
+	edit->segment_cache[ASSOC_ARRAY_FAN_OUT] = base_seg & ASSOC_ARRAY_FAN_MASK;
+	goto do_split_node;
+}
+
+/*
+ * Handle insertion into the middle of a shortcut.
+ */
+static bool assoc_array_insert_mid_shortcut(struct assoc_array_edit *edit,
+					    const struct assoc_array_ops *ops,
+					    struct assoc_array_walk_result *result)
+{
+	struct assoc_array_shortcut *shortcut, *new_s0, *new_s1;
+	struct assoc_array_node *node, *new_n0, *side;
+	unsigned long sc_segments, dissimilarity, blank;
+	size_t keylen;
+	int level, sc_level, diff;
+	int sc_slot;
+
+	shortcut	= result->wrong_shortcut.shortcut;
+	level		= result->wrong_shortcut.level;
+	sc_level	= result->wrong_shortcut.sc_level;
+	sc_segments	= result->wrong_shortcut.sc_segments;
+	dissimilarity	= result->wrong_shortcut.dissimilarity;
+
+	pr_devel("-->%s(ix=%d dis=%lx scix=%d)\n",
+		 __func__, level, dissimilarity, sc_level);
+
+	/* We need to split a shortcut and insert a node between the two
+	 * pieces.  Zero-length pieces will be dispensed with entirely.
+	 *
+	 * First of all, we need to find out in which level the first
+	 * difference was.
+	 */
+	diff = __ffs(dissimilarity);
+	diff &= ~ASSOC_ARRAY_LEVEL_STEP_MASK;
+	diff += sc_level & ~ASSOC_ARRAY_KEY_CHUNK_MASK;
+	pr_devel("diff=%d\n", diff);
+
+	if (!shortcut->back_pointer) {
+		edit->set[0].ptr = &edit->array->root;
+	} else if (assoc_array_ptr_is_node(shortcut->back_pointer)) {
+		node = assoc_array_ptr_to_node(shortcut->back_pointer);
+		edit->set[0].ptr = &node->slots[shortcut->parent_slot];
+	} else {
+		BUG();
+	}
+
+	edit->excised_meta[0] = assoc_array_shortcut_to_ptr(shortcut);
+
+	/* Create a new node now since we're going to need it anyway */
+	new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+	if (!new_n0)
+		return false;
+	edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+	edit->adjust_count_on = new_n0;
+
+	/* Insert a new shortcut before the new node if this segment isn't of
+	 * zero length - otherwise we just connect the new node directly to the
+	 * parent.
+	 */
+	level += ASSOC_ARRAY_LEVEL_STEP;
+	if (diff > level) {
+		pr_devel("pre-shortcut %d...%d\n", level, diff);
+		keylen = round_up(diff, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+		keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+		new_s0 = kzalloc(sizeof(struct assoc_array_shortcut) +
+				 keylen * sizeof(unsigned long), GFP_KERNEL);
+		if (!new_s0)
+			return false;
+		edit->new_meta[1] = assoc_array_shortcut_to_ptr(new_s0);
+		edit->set[0].to = assoc_array_shortcut_to_ptr(new_s0);
+		new_s0->back_pointer = shortcut->back_pointer;
+		new_s0->parent_slot = shortcut->parent_slot;
+		new_s0->next_node = assoc_array_node_to_ptr(new_n0);
+		new_s0->skip_to_level = diff;
+
+		new_n0->back_pointer = assoc_array_shortcut_to_ptr(new_s0);
+		new_n0->parent_slot = 0;
+
+		memcpy(new_s0->index_key, shortcut->index_key,
+		       keylen * sizeof(unsigned long));
+
+		blank = ULONG_MAX << (diff & ASSOC_ARRAY_KEY_CHUNK_MASK);
+		pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, diff, blank);
+		new_s0->index_key[keylen - 1] &= ~blank;
+	} else {
+		pr_devel("no pre-shortcut\n");
+		edit->set[0].to = assoc_array_node_to_ptr(new_n0);
+		new_n0->back_pointer = shortcut->back_pointer;
+		new_n0->parent_slot = shortcut->parent_slot;
+	}
+
+	side = assoc_array_ptr_to_node(shortcut->next_node);
+	new_n0->nr_leaves_on_branch = side->nr_leaves_on_branch;
+
+	/* We need to know which slot in the new node is going to take a
+	 * metadata pointer.
+	 */
+	sc_slot = sc_segments >> (diff & ASSOC_ARRAY_KEY_CHUNK_MASK);
+	sc_slot &= ASSOC_ARRAY_FAN_MASK;
+
+	pr_devel("new slot %lx >> %d -> %d\n",
+		 sc_segments, diff & ASSOC_ARRAY_KEY_CHUNK_MASK, sc_slot);
+
+	/* Determine whether we need to follow the new node with a replacement
+	 * for the current shortcut.  We could in theory reuse the current
+	 * shortcut if its parent slot number doesn't change - but that's a
+	 * 1-in-16 chance so not worth expending the code upon.
+	 */
+	level = diff + ASSOC_ARRAY_LEVEL_STEP;
+	if (level < shortcut->skip_to_level) {
+		pr_devel("post-shortcut %d...%d\n", level, shortcut->skip_to_level);
+		keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+		keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+
+		new_s1 = kzalloc(sizeof(struct assoc_array_shortcut) +
+				 keylen * sizeof(unsigned long), GFP_KERNEL);
+		if (!new_s1)
+			return false;
+		edit->new_meta[2] = assoc_array_shortcut_to_ptr(new_s1);
+
+		new_s1->back_pointer = assoc_array_node_to_ptr(new_n0);
+		new_s1->parent_slot = sc_slot;
+		new_s1->next_node = shortcut->next_node;
+		new_s1->skip_to_level = shortcut->skip_to_level;
+
+		new_n0->slots[sc_slot] = assoc_array_shortcut_to_ptr(new_s1);
+
+		memcpy(new_s1->index_key, shortcut->index_key,
+		       keylen * sizeof(unsigned long));
+
+		edit->set[1].ptr = &side->back_pointer;
+		edit->set[1].to = assoc_array_shortcut_to_ptr(new_s1);
+	} else {
+		pr_devel("no post-shortcut\n");
+
+		/* We don't have to replace the pointed-to node as long as we
+		 * use memory barriers to make sure the parent slot number is
+		 * changed before the back pointer (the parent slot number is
+		 * irrelevant to the old parent shortcut).
+		 */
+		new_n0->slots[sc_slot] = shortcut->next_node;
+		edit->set_parent_slot[0].p = &side->parent_slot;
+		edit->set_parent_slot[0].to = sc_slot;
+		edit->set[1].ptr = &side->back_pointer;
+		edit->set[1].to = assoc_array_node_to_ptr(new_n0);
+	}
+
+	/* Install the new leaf in a spare slot in the new node. */
+	if (sc_slot == 0)
+		edit->leaf_p = &new_n0->slots[1];
+	else
+		edit->leaf_p = &new_n0->slots[0];
+
+	pr_devel("<--%s() = ok [split shortcut]\n", __func__);
+	return edit;
+}
+
+/**
+ * assoc_array_insert - Script insertion of an object into an associative array
+ * @array: The array to insert into.
+ * @ops: The operations to use.
+ * @index_key: The key to insert at.
+ * @object: The object to insert.
+ *
+ * Precalculate and preallocate a script for the insertion or replacement of an
+ * object in an associative array.  This results in an edit script that can
+ * either be applied or cancelled.
+ *
+ * The function returns a pointer to an edit script or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_insert(struct assoc_array *array,
+					    const struct assoc_array_ops *ops,
+					    const void *index_key,
+					    void *object)
+{
+	struct assoc_array_walk_result result;
+	struct assoc_array_edit *edit;
+
+	pr_devel("-->%s()\n", __func__);
+
+	/* The leaf pointer we're given must not have the bottom bit set as we
+	 * use those for type-marking the pointer.  NULL pointers are also not
+	 * allowed as they indicate an empty slot but we have to allow them
+	 * here as they can be updated later.
+	 */
+	BUG_ON(assoc_array_ptr_is_meta(object));
+
+	edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+	if (!edit)
+		return ERR_PTR(-ENOMEM);
+	edit->array = array;
+	edit->ops = ops;
+	edit->leaf = assoc_array_leaf_to_ptr(object);
+	edit->adjust_count_by = 1;
+
+	switch (assoc_array_walk(array, ops, index_key, &result)) {
+	case assoc_array_walk_tree_empty:
+		/* Allocate a root node if there isn't one yet */
+		if (!assoc_array_insert_in_empty_tree(edit))
+			goto enomem;
+		return edit;
+
+	case assoc_array_walk_found_terminal_node:
+		/* We found a node that doesn't have a node/shortcut pointer in
+		 * the slot corresponding to the index key that we have to
+		 * follow.
+		 */
+		if (!assoc_array_insert_into_terminal_node(edit, ops, index_key,
+							   &result))
+			goto enomem;
+		return edit;
+
+	case assoc_array_walk_found_wrong_shortcut:
+		/* We found a shortcut that didn't match our key in a slot we
+		 * needed to follow.
+		 */
+		if (!assoc_array_insert_mid_shortcut(edit, ops, &result))
+			goto enomem;
+		return edit;
+	}
+
+enomem:
+	/* Clean up after an out of memory error */
+	pr_devel("enomem\n");
+	assoc_array_cancel_edit(edit);
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * assoc_array_insert_set_object - Set the new object pointer in an edit script
+ * @edit: The edit script to modify.
+ * @object: The object pointer to set.
+ *
+ * Change the object to be inserted in an edit script.  The object pointed to
+ * by the old object is not freed.  This must be done prior to applying the
+ * script.
+ */
+void assoc_array_insert_set_object(struct assoc_array_edit *edit, void *object)
+{
+	BUG_ON(!object);
+	edit->leaf = assoc_array_leaf_to_ptr(object);
+}
+
+struct assoc_array_delete_collapse_context {
+	struct assoc_array_node	*node;
+	const void		*skip_leaf;
+	int			slot;
+};
+
+/*
+ * Subtree collapse to node iterator.
+ */
+static int assoc_array_delete_collapse_iterator(const void *leaf,
+						void *iterator_data)
+{
+	struct assoc_array_delete_collapse_context *collapse = iterator_data;
+
+	if (leaf == collapse->skip_leaf)
+		return 0;
+
+	BUG_ON(collapse->slot >= ASSOC_ARRAY_FAN_OUT);
+
+	collapse->node->slots[collapse->slot++] = assoc_array_leaf_to_ptr(leaf);
+	return 0;
+}
+
+/**
+ * assoc_array_delete - Script deletion of an object from an associative array
+ * @array: The array to search.
+ * @ops: The operations to use.
+ * @index_key: The key to the object.
+ *
+ * Precalculate and preallocate a script for the deletion of an object from an
+ * associative array.  This results in an edit script that can either be
+ * applied or cancelled.
+ *
+ * The function returns a pointer to an edit script if the object was found,
+ * NULL if the object was not found or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_delete(struct assoc_array *array,
+					    const struct assoc_array_ops *ops,
+					    const void *index_key)
+{
+	struct assoc_array_delete_collapse_context collapse;
+	struct assoc_array_walk_result result;
+	struct assoc_array_node *node, *new_n0;
+	struct assoc_array_edit *edit;
+	struct assoc_array_ptr *ptr;
+	bool has_meta;
+	int slot, i;
+
+	pr_devel("-->%s()\n", __func__);
+
+	edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+	if (!edit)
+		return ERR_PTR(-ENOMEM);
+	edit->array = array;
+	edit->ops = ops;
+	edit->adjust_count_by = -1;
+
+	switch (assoc_array_walk(array, ops, index_key, &result)) {
+	case assoc_array_walk_found_terminal_node:
+		/* We found a node that should contain the leaf we've been
+		 * asked to remove - *if* it's in the tree.
+		 */
+		pr_devel("terminal_node\n");
+		node = result.terminal_node.node;
+
+		for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+			ptr = node->slots[slot];
+			if (ptr &&
+			    assoc_array_ptr_is_leaf(ptr) &&
+			    ops->compare_object(assoc_array_ptr_to_leaf(ptr),
+						index_key))
+				goto found_leaf;
+		}
+	case assoc_array_walk_tree_empty:
+	case assoc_array_walk_found_wrong_shortcut:
+	default:
+		assoc_array_cancel_edit(edit);
+		pr_devel("not found\n");
+		return NULL;
+	}
+
+found_leaf:
+	BUG_ON(array->nr_leaves_on_tree <= 0);
+
+	/* In the simplest form of deletion we just clear the slot and release
+	 * the leaf after a suitable interval.
+	 */
+	edit->dead_leaf = node->slots[slot];
+	edit->set[0].ptr = &node->slots[slot];
+	edit->set[0].to = NULL;
+	edit->adjust_count_on = node;
+
+	/* If that concludes erasure of the last leaf, then delete the entire
+	 * internal array.
+	 */
+	if (array->nr_leaves_on_tree == 1) {
+		edit->set[1].ptr = &array->root;
+		edit->set[1].to = NULL;
+		edit->adjust_count_on = NULL;
+		edit->excised_subtree = array->root;
+		pr_devel("all gone\n");
+		return edit;
+	}
+
+	/* However, we'd also like to clear up some metadata blocks if we
+	 * possibly can.
+	 *
+	 * We go for a simple algorithm of: if this node has FAN_OUT or fewer
+	 * leaves in it, then attempt to collapse it - and attempt to
+	 * recursively collapse up the tree.
+	 *
+	 * We could also try and collapse in partially filled subtrees to take
+	 * up space in this node.
+	 */
+	if (node->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) {
+		struct assoc_array_node *parent, *grandparent;
+		struct assoc_array_ptr *ptr;
+
+		/* First of all, we need to know if this node has metadata so
+		 * that we don't try collapsing if all the leaves are already
+		 * here.
+		 */
+		has_meta = false;
+		for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+			ptr = node->slots[i];
+			if (assoc_array_ptr_is_meta(ptr)) {
+				has_meta = true;
+				break;
+			}
+		}
+
+		pr_devel("leaves: %ld [m=%d]\n",
+			 node->nr_leaves_on_branch - 1, has_meta);
+
+		/* Look further up the tree to see if we can collapse this node
+		 * into a more proximal node too.
+		 */
+		parent = node;
+	collapse_up:
+		pr_devel("collapse subtree: %ld\n", parent->nr_leaves_on_branch);
+
+		ptr = parent->back_pointer;
+		if (!ptr)
+			goto do_collapse;
+		if (assoc_array_ptr_is_shortcut(ptr)) {
+			struct assoc_array_shortcut *s = assoc_array_ptr_to_shortcut(ptr);
+			ptr = s->back_pointer;
+			if (!ptr)
+				goto do_collapse;
+		}
+
+		grandparent = assoc_array_ptr_to_node(ptr);
+		if (grandparent->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT + 1) {
+			parent = grandparent;
+			goto collapse_up;
+		}
+
+	do_collapse:
+		/* There's no point collapsing if the original node has no meta
+		 * pointers to discard and if we didn't merge into one of that
+		 * node's ancestry.
+		 */
+		if (has_meta || parent != node) {
+			node = parent;
+
+			/* Create a new node to collapse into */
+			new_n0 = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+			if (!new_n0)
+				goto enomem;
+			edit->new_meta[0] = assoc_array_node_to_ptr(new_n0);
+
+			new_n0->back_pointer = node->back_pointer;
+			new_n0->parent_slot = node->parent_slot;
+			new_n0->nr_leaves_on_branch = node->nr_leaves_on_branch;
+			edit->adjust_count_on = new_n0;
+
+			collapse.node = new_n0;
+			collapse.skip_leaf = assoc_array_ptr_to_leaf(edit->dead_leaf);
+			collapse.slot = 0;
+			assoc_array_subtree_iterate(assoc_array_node_to_ptr(node),
+						    node->back_pointer,
+						    assoc_array_delete_collapse_iterator,
+						    &collapse);
+			pr_devel("collapsed %d,%lu\n", collapse.slot, new_n0->nr_leaves_on_branch);
+			BUG_ON(collapse.slot != new_n0->nr_leaves_on_branch - 1);
+
+			if (!node->back_pointer) {
+				edit->set[1].ptr = &array->root;
+			} else if (assoc_array_ptr_is_leaf(node->back_pointer)) {
+				BUG();
+			} else if (assoc_array_ptr_is_node(node->back_pointer)) {
+				struct assoc_array_node *p =
+					assoc_array_ptr_to_node(node->back_pointer);
+				edit->set[1].ptr = &p->slots[node->parent_slot];
+			} else if (assoc_array_ptr_is_shortcut(node->back_pointer)) {
+				struct assoc_array_shortcut *s =
+					assoc_array_ptr_to_shortcut(node->back_pointer);
+				edit->set[1].ptr = &s->next_node;
+			}
+			edit->set[1].to = assoc_array_node_to_ptr(new_n0);
+			edit->excised_subtree = assoc_array_node_to_ptr(node);
+		}
+	}
+
+	return edit;
+
+enomem:
+	/* Clean up after an out of memory error */
+	pr_devel("enomem\n");
+	assoc_array_cancel_edit(edit);
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * assoc_array_clear - Script deletion of all objects from an associative array
+ * @array: The array to clear.
+ * @ops: The operations to use.
+ *
+ * Precalculate and preallocate a script for the deletion of all the objects
+ * from an associative array.  This results in an edit script that can either
+ * be applied or cancelled.
+ *
+ * The function returns a pointer to an edit script if there are objects to be
+ * deleted, NULL if there are no objects in the array or -ENOMEM.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+struct assoc_array_edit *assoc_array_clear(struct assoc_array *array,
+					   const struct assoc_array_ops *ops)
+{
+	struct assoc_array_edit *edit;
+
+	pr_devel("-->%s()\n", __func__);
+
+	if (!array->root)
+		return NULL;
+
+	edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+	if (!edit)
+		return ERR_PTR(-ENOMEM);
+	edit->array = array;
+	edit->ops = ops;
+	edit->set[1].ptr = &array->root;
+	edit->set[1].to = NULL;
+	edit->excised_subtree = array->root;
+	edit->ops_for_excised_subtree = ops;
+	pr_devel("all gone\n");
+	return edit;
+}
+
+/*
+ * Handle the deferred destruction after an applied edit.
+ */
+static void assoc_array_rcu_cleanup(struct rcu_head *head)
+{
+	struct assoc_array_edit *edit =
+		container_of(head, struct assoc_array_edit, rcu);
+	int i;
+
+	pr_devel("-->%s()\n", __func__);
+
+	if (edit->dead_leaf)
+		edit->ops->free_object(assoc_array_ptr_to_leaf(edit->dead_leaf));
+	for (i = 0; i < ARRAY_SIZE(edit->excised_meta); i++)
+		if (edit->excised_meta[i])
+			kfree(assoc_array_ptr_to_node(edit->excised_meta[i]));
+
+	if (edit->excised_subtree) {
+		BUG_ON(assoc_array_ptr_is_leaf(edit->excised_subtree));
+		if (assoc_array_ptr_is_node(edit->excised_subtree)) {
+			struct assoc_array_node *n =
+				assoc_array_ptr_to_node(edit->excised_subtree);
+			n->back_pointer = NULL;
+		} else {
+			struct assoc_array_shortcut *s =
+				assoc_array_ptr_to_shortcut(edit->excised_subtree);
+			s->back_pointer = NULL;
+		}
+		assoc_array_destroy_subtree(edit->excised_subtree,
+					    edit->ops_for_excised_subtree);
+	}
+
+	kfree(edit);
+}
+
+/**
+ * assoc_array_apply_edit - Apply an edit script to an associative array
+ * @edit: The script to apply.
+ *
+ * Apply an edit script to an associative array to effect an insertion,
+ * deletion or clearance.  As the edit script includes preallocated memory,
+ * this is guaranteed not to fail.
+ *
+ * The edit script, dead objects and dead metadata will be scheduled for
+ * destruction after an RCU grace period to permit those doing read-only
+ * accesses on the array to continue to do so under the RCU read lock whilst
+ * the edit is taking place.
+ */
+void assoc_array_apply_edit(struct assoc_array_edit *edit)
+{
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *ptr;
+	int i;
+
+	pr_devel("-->%s()\n", __func__);
+
+	smp_wmb();
+	if (edit->leaf_p)
+		*edit->leaf_p = edit->leaf;
+
+	smp_wmb();
+	for (i = 0; i < ARRAY_SIZE(edit->set_parent_slot); i++)
+		if (edit->set_parent_slot[i].p)
+			*edit->set_parent_slot[i].p = edit->set_parent_slot[i].to;
+
+	smp_wmb();
+	for (i = 0; i < ARRAY_SIZE(edit->set_backpointers); i++)
+		if (edit->set_backpointers[i])
+			*edit->set_backpointers[i] = edit->set_backpointers_to;
+
+	smp_wmb();
+	for (i = 0; i < ARRAY_SIZE(edit->set); i++)
+		if (edit->set[i].ptr)
+			*edit->set[i].ptr = edit->set[i].to;
+
+	if (edit->array->root == NULL) {
+		edit->array->nr_leaves_on_tree = 0;
+	} else if (edit->adjust_count_on) {
+		node = edit->adjust_count_on;
+		for (;;) {
+			node->nr_leaves_on_branch += edit->adjust_count_by;
+
+			ptr = node->back_pointer;
+			if (!ptr)
+				break;
+			if (assoc_array_ptr_is_shortcut(ptr)) {
+				shortcut = assoc_array_ptr_to_shortcut(ptr);
+				ptr = shortcut->back_pointer;
+				if (!ptr)
+					break;
+			}
+			BUG_ON(!assoc_array_ptr_is_node(ptr));
+			node = assoc_array_ptr_to_node(ptr);
+		}
+
+		edit->array->nr_leaves_on_tree += edit->adjust_count_by;
+	}
+
+	call_rcu(&edit->rcu, assoc_array_rcu_cleanup);
+}
+
+/**
+ * assoc_array_cancel_edit - Discard an edit script.
+ * @edit: The script to discard.
+ *
+ * Free an edit script and all the preallocated data it holds without making
+ * any changes to the associative array it was intended for.
+ *
+ * NOTE!  In the case of an insertion script, this does _not_ release the leaf
+ * that was to be inserted.  That is left to the caller.
+ */
+void assoc_array_cancel_edit(struct assoc_array_edit *edit)
+{
+	struct assoc_array_ptr *ptr;
+	int i;
+
+	pr_devel("-->%s()\n", __func__);
+
+	/* Clean up after an out of memory error */
+	for (i = 0; i < ARRAY_SIZE(edit->new_meta); i++) {
+		ptr = edit->new_meta[i];
+		if (ptr) {
+			if (assoc_array_ptr_is_node(ptr))
+				kfree(assoc_array_ptr_to_node(ptr));
+			else
+				kfree(assoc_array_ptr_to_shortcut(ptr));
+		}
+	}
+	kfree(edit);
+}
+
+/**
+ * assoc_array_gc - Garbage collect an associative array.
+ * @array: The array to clean.
+ * @ops: The operations to use.
+ * @iterator: A callback function to pass judgement on each object.
+ * @iterator_data: Private data for the callback function.
+ *
+ * Collect garbage from an associative array and pack down the internal tree to
+ * save memory.
+ *
+ * The iterator function is asked to pass judgement upon each object in the
+ * array.  If it returns false, the object is discard and if it returns true,
+ * the object is kept.  If it returns true, it must increment the object's
+ * usage count (or whatever it needs to do to retain it) before returning.
+ *
+ * This function returns 0 if successful or -ENOMEM if out of memory.  In the
+ * latter case, the array is not changed.
+ *
+ * The caller should lock against other modifications and must continue to hold
+ * the lock until assoc_array_apply_edit() has been called.
+ *
+ * Accesses to the tree may take place concurrently with this function,
+ * provided they hold the RCU read lock.
+ */
+int assoc_array_gc(struct assoc_array *array,
+		   const struct assoc_array_ops *ops,
+		   bool (*iterator)(void *object, void *iterator_data),
+		   void *iterator_data)
+{
+	struct assoc_array_shortcut *shortcut, *new_s;
+	struct assoc_array_node *node, *new_n;
+	struct assoc_array_edit *edit;
+	struct assoc_array_ptr *cursor, *ptr;
+	struct assoc_array_ptr *new_root, *new_parent, **new_ptr_pp;
+	unsigned long nr_leaves_on_tree;
+	int keylen, slot, nr_free, next_slot, i;
+
+	pr_devel("-->%s()\n", __func__);
+
+	if (!array->root)
+		return 0;
+
+	edit = kzalloc(sizeof(struct assoc_array_edit), GFP_KERNEL);
+	if (!edit)
+		return -ENOMEM;
+	edit->array = array;
+	edit->ops = ops;
+	edit->ops_for_excised_subtree = ops;
+	edit->set[0].ptr = &array->root;
+	edit->excised_subtree = array->root;
+
+	new_root = new_parent = NULL;
+	new_ptr_pp = &new_root;
+	cursor = array->root;
+
+descend:
+	/* If this point is a shortcut, then we need to duplicate it and
+	 * advance the target cursor.
+	 */
+	if (assoc_array_ptr_is_shortcut(cursor)) {
+		shortcut = assoc_array_ptr_to_shortcut(cursor);
+		keylen = round_up(shortcut->skip_to_level, ASSOC_ARRAY_KEY_CHUNK_SIZE);
+		keylen >>= ASSOC_ARRAY_KEY_CHUNK_SHIFT;
+		new_s = kmalloc(sizeof(struct assoc_array_shortcut) +
+				keylen * sizeof(unsigned long), GFP_KERNEL);
+		if (!new_s)
+			goto enomem;
+		pr_devel("dup shortcut %p -> %p\n", shortcut, new_s);
+		memcpy(new_s, shortcut, (sizeof(struct assoc_array_shortcut) +
+					 keylen * sizeof(unsigned long)));
+		new_s->back_pointer = new_parent;
+		new_s->parent_slot = shortcut->parent_slot;
+		*new_ptr_pp = new_parent = assoc_array_shortcut_to_ptr(new_s);
+		new_ptr_pp = &new_s->next_node;
+		cursor = shortcut->next_node;
+	}
+
+	/* Duplicate the node at this position */
+	node = assoc_array_ptr_to_node(cursor);
+	new_n = kzalloc(sizeof(struct assoc_array_node), GFP_KERNEL);
+	if (!new_n)
+		goto enomem;
+	pr_devel("dup node %p -> %p\n", node, new_n);
+	new_n->back_pointer = new_parent;
+	new_n->parent_slot = node->parent_slot;
+	*new_ptr_pp = new_parent = assoc_array_node_to_ptr(new_n);
+	new_ptr_pp = NULL;
+	slot = 0;
+
+continue_node:
+	/* Filter across any leaves and gc any subtrees */
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = node->slots[slot];
+		if (!ptr)
+			continue;
+
+		if (assoc_array_ptr_is_leaf(ptr)) {
+			if (iterator(assoc_array_ptr_to_leaf(ptr),
+				     iterator_data))
+				/* The iterator will have done any reference
+				 * counting on the object for us.
+				 */
+				new_n->slots[slot] = ptr;
+			continue;
+		}
+
+		new_ptr_pp = &new_n->slots[slot];
+		cursor = ptr;
+		goto descend;
+	}
+
+	pr_devel("-- compress node %p --\n", new_n);
+
+	/* Count up the number of empty slots in this node and work out the
+	 * subtree leaf count.
+	 */
+	new_n->nr_leaves_on_branch = 0;
+	nr_free = 0;
+	for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = new_n->slots[slot];
+		if (!ptr)
+			nr_free++;
+		else if (assoc_array_ptr_is_leaf(ptr))
+			new_n->nr_leaves_on_branch++;
+	}
+	pr_devel("free=%d, leaves=%lu\n", nr_free, new_n->nr_leaves_on_branch);
+
+	/* See what we can fold in */
+	next_slot = 0;
+	for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		struct assoc_array_shortcut *s;
+		struct assoc_array_node *child;
+
+		ptr = new_n->slots[slot];
+		if (!ptr || assoc_array_ptr_is_leaf(ptr))
+			continue;
+
+		s = NULL;
+		if (assoc_array_ptr_is_shortcut(ptr)) {
+			s = assoc_array_ptr_to_shortcut(ptr);
+			ptr = s->next_node;
+		}
+
+		child = assoc_array_ptr_to_node(ptr);
+		new_n->nr_leaves_on_branch += child->nr_leaves_on_branch;
+
+		if (child->nr_leaves_on_branch <= nr_free + 1) {
+			/* Fold the child node into this one */
+			pr_devel("[%d] fold node %lu/%d [nx %d]\n",
+				 slot, child->nr_leaves_on_branch, nr_free + 1,
+				 next_slot);
+
+			/* We would already have reaped an intervening shortcut
+			 * on the way back up the tree.
+			 */
+			BUG_ON(s);
+
+			new_n->slots[slot] = NULL;
+			nr_free++;
+			if (slot < next_slot)
+				next_slot = slot;
+			for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) {
+				struct assoc_array_ptr *p = child->slots[i];
+				if (!p)
+					continue;
+				BUG_ON(assoc_array_ptr_is_meta(p));
+				while (new_n->slots[next_slot])
+					next_slot++;
+				BUG_ON(next_slot >= ASSOC_ARRAY_FAN_OUT);
+				new_n->slots[next_slot++] = p;
+				nr_free--;
+			}
+			kfree(child);
+		} else {
+			pr_devel("[%d] retain node %lu/%d [nx %d]\n",
+				 slot, child->nr_leaves_on_branch, nr_free + 1,
+				 next_slot);
+		}
+	}
+
+	pr_devel("after: %lu\n", new_n->nr_leaves_on_branch);
+
+	nr_leaves_on_tree = new_n->nr_leaves_on_branch;
+
+	/* Excise this node if it is singly occupied by a shortcut */
+	if (nr_free == ASSOC_ARRAY_FAN_OUT - 1) {
+		for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++)
+			if ((ptr = new_n->slots[slot]))
+				break;
+
+		if (assoc_array_ptr_is_meta(ptr) &&
+		    assoc_array_ptr_is_shortcut(ptr)) {
+			pr_devel("excise node %p with 1 shortcut\n", new_n);
+			new_s = assoc_array_ptr_to_shortcut(ptr);
+			new_parent = new_n->back_pointer;
+			slot = new_n->parent_slot;
+			kfree(new_n);
+			if (!new_parent) {
+				new_s->back_pointer = NULL;
+				new_s->parent_slot = 0;
+				new_root = ptr;
+				goto gc_complete;
+			}
+
+			if (assoc_array_ptr_is_shortcut(new_parent)) {
+				/* We can discard any preceding shortcut also */
+				struct assoc_array_shortcut *s =
+					assoc_array_ptr_to_shortcut(new_parent);
+
+				pr_devel("excise preceding shortcut\n");
+
+				new_parent = new_s->back_pointer = s->back_pointer;
+				slot = new_s->parent_slot = s->parent_slot;
+				kfree(s);
+				if (!new_parent) {
+					new_s->back_pointer = NULL;
+					new_s->parent_slot = 0;
+					new_root = ptr;
+					goto gc_complete;
+				}
+			}
+
+			new_s->back_pointer = new_parent;
+			new_s->parent_slot = slot;
+			new_n = assoc_array_ptr_to_node(new_parent);
+			new_n->slots[slot] = ptr;
+			goto ascend_old_tree;
+		}
+	}
+
+	/* Excise any shortcuts we might encounter that point to nodes that
+	 * only contain leaves.
+	 */
+	ptr = new_n->back_pointer;
+	if (!ptr)
+		goto gc_complete;
+
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		new_s = assoc_array_ptr_to_shortcut(ptr);
+		new_parent = new_s->back_pointer;
+		slot = new_s->parent_slot;
+
+		if (new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) {
+			struct assoc_array_node *n;
+
+			pr_devel("excise shortcut\n");
+			new_n->back_pointer = new_parent;
+			new_n->parent_slot = slot;
+			kfree(new_s);
+			if (!new_parent) {
+				new_root = assoc_array_node_to_ptr(new_n);
+				goto gc_complete;
+			}
+
+			n = assoc_array_ptr_to_node(new_parent);
+			n->slots[slot] = assoc_array_node_to_ptr(new_n);
+		}
+	} else {
+		new_parent = ptr;
+	}
+	new_n = assoc_array_ptr_to_node(new_parent);
+
+ascend_old_tree:
+	ptr = node->back_pointer;
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		slot = shortcut->parent_slot;
+		cursor = shortcut->back_pointer;
+	} else {
+		slot = node->parent_slot;
+		cursor = ptr;
+	}
+	BUG_ON(!ptr);
+	node = assoc_array_ptr_to_node(cursor);
+	slot++;
+	goto continue_node;
+
+gc_complete:
+	edit->set[0].to = new_root;
+	assoc_array_apply_edit(edit);
+	edit->array->nr_leaves_on_tree = nr_leaves_on_tree;
+	return 0;
+
+enomem:
+	pr_devel("enomem\n");
+	assoc_array_destroy_subtree(new_root, edit->ops);
+	kfree(edit);
+	return -ENOMEM;
+}
-- 
cgit 


From b2a4df200d570b2c33a57e1ebfa5896e4bc81b69 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:18 +0100
Subject: KEYS: Expand the capacity of a keyring

Expand the capacity of a keyring to be able to hold a lot more keys by using
the previously added associative array implementation.  Currently the maximum
capacity is:

	(PAGE_SIZE - sizeof(header)) / sizeof(struct key *)

which, on a 64-bit system, is a little more 500.  However, since this is being
used for the NFS uid mapper, we need more than that.  The new implementation
gives us effectively unlimited capacity.

With some alterations, the keyutils testsuite runs successfully to completion
after this patch is applied.  The alterations are because (a) keyrings that
are simply added to no longer appear ordered and (b) some of the errors have
changed a bit.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/keys/keyring-type.h |   17 +-
 include/linux/key.h         |   13 +-
 lib/assoc_array.c           |    1 +
 security/keys/Kconfig       |    1 +
 security/keys/gc.c          |   33 +-
 security/keys/internal.h    |   17 +-
 security/keys/key.c         |   35 +-
 security/keys/keyring.c     | 1436 ++++++++++++++++++++++---------------------
 security/keys/request_key.c |   12 +-
 9 files changed, 803 insertions(+), 762 deletions(-)

(limited to 'include')

diff --git a/include/keys/keyring-type.h b/include/keys/keyring-type.h
index cf49159b0e3a..fca5c62340a4 100644
--- a/include/keys/keyring-type.h
+++ b/include/keys/keyring-type.h
@@ -1,6 +1,6 @@
 /* Keyring key type
  *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008, 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -13,19 +13,6 @@
 #define _KEYS_KEYRING_TYPE_H
 
 #include <linux/key.h>
-#include <linux/rcupdate.h>
-
-/*
- * the keyring payload contains a list of the keys to which the keyring is
- * subscribed
- */
-struct keyring_list {
-	struct rcu_head	rcu;		/* RCU deletion hook */
-	unsigned short	maxkeys;	/* max keys this list can hold */
-	unsigned short	nkeys;		/* number of keys currently held */
-	unsigned short	delkey;		/* key to be unlinked by RCU */
-	struct key __rcu *keys[0];
-};
-
+#include <linux/assoc_array.h>
 
 #endif /* _KEYS_KEYRING_TYPE_H */
diff --git a/include/linux/key.h b/include/linux/key.h
index ef596c7af585..2417f789d29b 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -22,6 +22,7 @@
 #include <linux/sysctl.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <linux/assoc_array.h>
 
 #ifdef __KERNEL__
 #include <linux/uidgid.h>
@@ -196,11 +197,13 @@ struct key {
 	 *   whatever
 	 */
 	union {
-		unsigned long		value;
-		void __rcu		*rcudata;
-		void			*data;
-		struct keyring_list __rcu *subscriptions;
-	} payload;
+		union {
+			unsigned long		value;
+			void __rcu		*rcudata;
+			void			*data;
+		} payload;
+		struct assoc_array keys;
+	};
 };
 
 extern struct key *key_alloc(struct key_type *type,
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index a0952818f938..17edeaf19180 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -12,6 +12,7 @@
  */
 //#define DEBUG
 #include <linux/slab.h>
+#include <linux/err.h>
 #include <linux/assoc_array_priv.h>
 
 /*
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index a90d6d300dbd..15e0dfe8c80f 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -4,6 +4,7 @@
 
 config KEYS
 	bool "Enable access key retention support"
+	select ASSOCIATIVE_ARRAY
 	help
 	  This option provides support for retaining authentication tokens and
 	  access keys in the kernel.
diff --git a/security/keys/gc.c b/security/keys/gc.c
index d67c97bb1025..cce621c33dce 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -130,6 +130,13 @@ void key_gc_keytype(struct key_type *ktype)
 	kleave("");
 }
 
+static int key_gc_keyring_func(const void *object, void *iterator_data)
+{
+	const struct key *key = object;
+	time_t *limit = iterator_data;
+	return key_is_dead(key, *limit);
+}
+
 /*
  * Garbage collect pointers from a keyring.
  *
@@ -138,10 +145,9 @@ void key_gc_keytype(struct key_type *ktype)
  */
 static void key_gc_keyring(struct key *keyring, time_t limit)
 {
-	struct keyring_list *klist;
-	int loop;
+	int result;
 
-	kenter("%x", key_serial(keyring));
+	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
 
 	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
 			      (1 << KEY_FLAG_REVOKED)))
@@ -149,27 +155,17 @@ static void key_gc_keyring(struct key *keyring, time_t limit)
 
 	/* scan the keyring looking for dead keys */
 	rcu_read_lock();
-	klist = rcu_dereference(keyring->payload.subscriptions);
-	if (!klist)
-		goto unlock_dont_gc;
-
-	loop = klist->nkeys;
-	smp_rmb();
-	for (loop--; loop >= 0; loop--) {
-		struct key *key = rcu_dereference(klist->keys[loop]);
-		if (key_is_dead(key, limit))
-			goto do_gc;
-	}
-
-unlock_dont_gc:
+	result = assoc_array_iterate(&keyring->keys,
+				     key_gc_keyring_func, &limit);
 	rcu_read_unlock();
+	if (result == true)
+		goto do_gc;
+
 dont_gc:
 	kleave(" [no gc]");
 	return;
 
 do_gc:
-	rcu_read_unlock();
-
 	keyring_gc(keyring, limit);
 	kleave(" [gc]");
 }
@@ -392,7 +388,6 @@ found_unreferenced_key:
 	 */
 found_keyring:
 	spin_unlock(&key_serial_lock);
-	kdebug("scan keyring %d", key->serial);
 	key_gc_keyring(key, limit);
 	goto maybe_resched;
 
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 73950bf8f875..581c6f688352 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -90,20 +90,23 @@ extern void key_type_put(struct key_type *ktype);
 
 extern int __key_link_begin(struct key *keyring,
 			    const struct keyring_index_key *index_key,
-			    unsigned long *_prealloc);
+			    struct assoc_array_edit **_edit);
 extern int __key_link_check_live_key(struct key *keyring, struct key *key);
-extern void __key_link(struct key *keyring, struct key *key,
-		       unsigned long *_prealloc);
+extern void __key_link(struct key *key, struct assoc_array_edit **_edit);
 extern void __key_link_end(struct key *keyring,
 			   const struct keyring_index_key *index_key,
-			   unsigned long prealloc);
+			   struct assoc_array_edit *edit);
 
-extern key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-				      const struct keyring_index_key *index_key);
+extern key_ref_t find_key_to_update(key_ref_t keyring_ref,
+				    const struct keyring_index_key *index_key);
 
 extern struct key *keyring_search_instkey(struct key *keyring,
 					  key_serial_t target_id);
 
+extern int iterate_over_keyring(const struct key *keyring,
+				int (*func)(const struct key *key, void *data),
+				void *data);
+
 typedef int (*key_match_func_t)(const struct key *, const void *);
 
 struct keyring_search_context {
@@ -119,6 +122,8 @@ struct keyring_search_context {
 #define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
 #define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
 
+	int (*iterator)(const void *object, void *iterator_data);
+
 	/* Internal stuff */
 	int			skipped_ret;
 	bool			possessed;
diff --git a/security/keys/key.c b/security/keys/key.c
index 7d716b82a61e..a819b5c7d4ec 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -409,7 +409,7 @@ static int __key_instantiate_and_link(struct key *key,
 				      struct key_preparsed_payload *prep,
 				      struct key *keyring,
 				      struct key *authkey,
-				      unsigned long *_prealloc)
+				      struct assoc_array_edit **_edit)
 {
 	int ret, awaken;
 
@@ -436,7 +436,7 @@ static int __key_instantiate_and_link(struct key *key,
 
 			/* and link it into the destination keyring */
 			if (keyring)
-				__key_link(keyring, key, _prealloc);
+				__key_link(key, _edit);
 
 			/* disable the authorisation key */
 			if (authkey)
@@ -476,7 +476,7 @@ int key_instantiate_and_link(struct key *key,
 			     struct key *authkey)
 {
 	struct key_preparsed_payload prep;
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	int ret;
 
 	memset(&prep, 0, sizeof(prep));
@@ -490,16 +490,15 @@ int key_instantiate_and_link(struct key *key,
 	}
 
 	if (keyring) {
-		ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+		ret = __key_link_begin(keyring, &key->index_key, &edit);
 		if (ret < 0)
 			goto error_free_preparse;
 	}
 
-	ret = __key_instantiate_and_link(key, &prep, keyring, authkey,
-					 &prealloc);
+	ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit);
 
 	if (keyring)
-		__key_link_end(keyring, &key->index_key, prealloc);
+		__key_link_end(keyring, &key->index_key, edit);
 
 error_free_preparse:
 	if (key->type->preparse)
@@ -537,7 +536,7 @@ int key_reject_and_link(struct key *key,
 			struct key *keyring,
 			struct key *authkey)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	struct timespec now;
 	int ret, awaken, link_ret = 0;
 
@@ -548,7 +547,7 @@ int key_reject_and_link(struct key *key,
 	ret = -EBUSY;
 
 	if (keyring)
-		link_ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+		link_ret = __key_link_begin(keyring, &key->index_key, &edit);
 
 	mutex_lock(&key_construction_mutex);
 
@@ -570,7 +569,7 @@ int key_reject_and_link(struct key *key,
 
 		/* and link it into the destination keyring */
 		if (keyring && link_ret == 0)
-			__key_link(keyring, key, &prealloc);
+			__key_link(key, &edit);
 
 		/* disable the authorisation key */
 		if (authkey)
@@ -580,7 +579,7 @@ int key_reject_and_link(struct key *key,
 	mutex_unlock(&key_construction_mutex);
 
 	if (keyring)
-		__key_link_end(keyring, &key->index_key, prealloc);
+		__key_link_end(keyring, &key->index_key, edit);
 
 	/* wake up anyone waiting for a key to be constructed */
 	if (awaken)
@@ -783,8 +782,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 		.description	= description,
 	};
 	struct key_preparsed_payload prep;
+	struct assoc_array_edit *edit;
 	const struct cred *cred = current_cred();
-	unsigned long prealloc;
 	struct key *keyring, *key = NULL;
 	key_ref_t key_ref;
 	int ret;
@@ -828,7 +827,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 	index_key.desc_len = strlen(index_key.description);
 
-	ret = __key_link_begin(keyring, &index_key, &prealloc);
+	ret = __key_link_begin(keyring, &index_key, &edit);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
 		goto error_free_prep;
@@ -847,8 +846,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	 * update that instead if possible
 	 */
 	if (index_key.type->update) {
-		key_ref = __keyring_search_one(keyring_ref, &index_key);
-		if (!IS_ERR(key_ref))
+		key_ref = find_key_to_update(keyring_ref, &index_key);
+		if (key_ref)
 			goto found_matching_key;
 	}
 
@@ -874,7 +873,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 
 	/* instantiate it and link it into the target keyring */
-	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &prealloc);
+	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit);
 	if (ret < 0) {
 		key_put(key);
 		key_ref = ERR_PTR(ret);
@@ -884,7 +883,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
 
 error_link_end:
-	__key_link_end(keyring, &index_key, prealloc);
+	__key_link_end(keyring, &index_key, edit);
 error_free_prep:
 	if (index_key.type->preparse)
 		index_key.type->free_preparse(&prep);
@@ -897,7 +896,7 @@ error:
 	/* we found a matching key, so we're going to try to update it
 	 * - we can drop the locks first as we have the key pinned
 	 */
-	__key_link_end(keyring, &index_key, prealloc);
+	__key_link_end(keyring, &index_key, edit);
 
 	key_ref = __key_update(key_ref, &prep);
 	goto error_free_prep;
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index eeef1a073db4..f7cdea22214f 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1,6 +1,6 @@
 /* Keyring handling
  *
- * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -17,25 +17,11 @@
 #include <linux/seq_file.h>
 #include <linux/err.h>
 #include <keys/keyring-type.h>
+#include <keys/user-type.h>
+#include <linux/assoc_array_priv.h>
 #include <linux/uaccess.h>
 #include "internal.h"
 
-#define rcu_dereference_locked_keyring(keyring)				\
-	(rcu_dereference_protected(					\
-		(keyring)->payload.subscriptions,			\
-		rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define rcu_deref_link_locked(klist, index, keyring)			\
-	(rcu_dereference_protected(					\
-		(klist)->keys[index],					\
-		rwsem_is_locked((struct rw_semaphore *)&(keyring)->sem)))
-
-#define MAX_KEYRING_LINKS						\
-	min_t(size_t, USHRT_MAX - 1,					\
-	      ((PAGE_SIZE - sizeof(struct keyring_list)) / sizeof(struct key *)))
-
-#define KEY_LINK_FIXQUOTA 1UL
-
 /*
  * When plumbing the depths of the key tree, this sets a hard limit
  * set on how deep we're willing to go.
@@ -47,6 +33,28 @@
  */
 #define KEYRING_NAME_HASH_SIZE	(1 << 5)
 
+/*
+ * We mark pointers we pass to the associative array with bit 1 set if
+ * they're keyrings and clear otherwise.
+ */
+#define KEYRING_PTR_SUBTYPE	0x2UL
+
+static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & KEYRING_PTR_SUBTYPE;
+}
+static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
+{
+	void *object = assoc_array_ptr_to_leaf(x);
+	return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
+}
+static inline void *keyring_key_to_ptr(struct key *key)
+{
+	if (key->type == &key_type_keyring)
+		return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
+	return key;
+}
+
 static struct list_head	keyring_name_hash[KEYRING_NAME_HASH_SIZE];
 static DEFINE_RWLOCK(keyring_name_lock);
 
@@ -67,7 +75,6 @@ static inline unsigned keyring_hash(const char *desc)
  */
 static int keyring_instantiate(struct key *keyring,
 			       struct key_preparsed_payload *prep);
-static int keyring_match(const struct key *keyring, const void *criterion);
 static void keyring_revoke(struct key *keyring);
 static void keyring_destroy(struct key *keyring);
 static void keyring_describe(const struct key *keyring, struct seq_file *m);
@@ -76,9 +83,9 @@ static long keyring_read(const struct key *keyring,
 
 struct key_type key_type_keyring = {
 	.name		= "keyring",
-	.def_datalen	= sizeof(struct keyring_list),
+	.def_datalen	= 0,
 	.instantiate	= keyring_instantiate,
-	.match		= keyring_match,
+	.match		= user_match,
 	.revoke		= keyring_revoke,
 	.destroy	= keyring_destroy,
 	.describe	= keyring_describe,
@@ -127,6 +134,7 @@ static int keyring_instantiate(struct key *keyring,
 
 	ret = -EINVAL;
 	if (prep->datalen == 0) {
+		assoc_array_init(&keyring->keys);
 		/* make the keyring available by name if it has one */
 		keyring_publish_name(keyring);
 		ret = 0;
@@ -136,14 +144,225 @@ static int keyring_instantiate(struct key *keyring,
 }
 
 /*
- * Match keyrings on their name
+ * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit.  Ideally we'd
+ * fold the carry back too, but that requires inline asm.
+ */
+static u64 mult_64x32_and_fold(u64 x, u32 y)
+{
+	u64 hi = (u64)(u32)(x >> 32) * y;
+	u64 lo = (u64)(u32)(x) * y;
+	return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
+}
+
+/*
+ * Hash a key type and description.
+ */
+static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key)
+{
+	const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
+	const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK;
+	const char *description = index_key->description;
+	unsigned long hash, type;
+	u32 piece;
+	u64 acc;
+	int n, desc_len = index_key->desc_len;
+
+	type = (unsigned long)index_key->type;
+
+	acc = mult_64x32_and_fold(type, desc_len + 13);
+	acc = mult_64x32_and_fold(acc, 9207);
+	for (;;) {
+		n = desc_len;
+		if (n <= 0)
+			break;
+		if (n > 4)
+			n = 4;
+		piece = 0;
+		memcpy(&piece, description, n);
+		description += n;
+		desc_len -= n;
+		acc = mult_64x32_and_fold(acc, piece);
+		acc = mult_64x32_and_fold(acc, 9207);
+	}
+
+	/* Fold the hash down to 32 bits if need be. */
+	hash = acc;
+	if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
+		hash ^= acc >> 32;
+
+	/* Squidge all the keyrings into a separate part of the tree to
+	 * ordinary keys by making sure the lowest level segment in the hash is
+	 * zero for keyrings and non-zero otherwise.
+	 */
+	if (index_key->type != &key_type_keyring && (hash & level_mask) == 0)
+		return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
+	if (index_key->type == &key_type_keyring && (hash & level_mask) != 0)
+		return (hash + (hash << level_shift)) & ~level_mask;
+	return hash;
+}
+
+/*
+ * Build the next index key chunk.
+ *
+ * On 32-bit systems the index key is laid out as:
+ *
+ *	0	4	5	9...
+ *	hash	desclen	typeptr	desc[]
+ *
+ * On 64-bit systems:
+ *
+ *	0	8	9	17...
+ *	hash	desclen	typeptr	desc[]
+ *
+ * We return it one word-sized chunk at a time.
  */
-static int keyring_match(const struct key *keyring, const void *description)
+static unsigned long keyring_get_key_chunk(const void *data, int level)
+{
+	const struct keyring_index_key *index_key = data;
+	unsigned long chunk = 0;
+	long offset = 0;
+	int desc_len = index_key->desc_len, n = sizeof(chunk);
+
+	level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
+	switch (level) {
+	case 0:
+		return hash_key_type_and_desc(index_key);
+	case 1:
+		return ((unsigned long)index_key->type << 8) | desc_len;
+	case 2:
+		if (desc_len == 0)
+			return (u8)((unsigned long)index_key->type >>
+				    (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+		n--;
+		offset = 1;
+	default:
+		offset += sizeof(chunk) - 1;
+		offset += (level - 3) * sizeof(chunk);
+		if (offset >= desc_len)
+			return 0;
+		desc_len -= offset;
+		if (desc_len > n)
+			desc_len = n;
+		offset += desc_len;
+		do {
+			chunk <<= 8;
+			chunk |= ((u8*)index_key->description)[--offset];
+		} while (--desc_len > 0);
+
+		if (level == 2) {
+			chunk <<= 8;
+			chunk |= (u8)((unsigned long)index_key->type >>
+				      (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8));
+		}
+		return chunk;
+	}
+}
+
+static unsigned long keyring_get_object_key_chunk(const void *object, int level)
+{
+	const struct key *key = keyring_ptr_to_key(object);
+	return keyring_get_key_chunk(&key->index_key, level);
+}
+
+static bool keyring_compare_object(const void *object, const void *data)
 {
-	return keyring->description &&
-		strcmp(keyring->description, description) == 0;
+	const struct keyring_index_key *index_key = data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	return key->index_key.type == index_key->type &&
+		key->index_key.desc_len == index_key->desc_len &&
+		memcmp(key->index_key.description, index_key->description,
+		       index_key->desc_len) == 0;
 }
 
+/*
+ * Compare the index keys of a pair of objects and determine the bit position
+ * at which they differ - if they differ.
+ */
+static int keyring_diff_objects(const void *_a, const void *_b)
+{
+	const struct key *key_a = keyring_ptr_to_key(_a);
+	const struct key *key_b = keyring_ptr_to_key(_b);
+	const struct keyring_index_key *a = &key_a->index_key;
+	const struct keyring_index_key *b = &key_b->index_key;
+	unsigned long seg_a, seg_b;
+	int level, i;
+
+	level = 0;
+	seg_a = hash_key_type_and_desc(a);
+	seg_b = hash_key_type_and_desc(b);
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	/* The number of bits contributed by the hash is controlled by a
+	 * constant in the assoc_array headers.  Everything else thereafter we
+	 * can deal with as being machine word-size dependent.
+	 */
+	level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;
+	seg_a = a->desc_len;
+	seg_b = b->desc_len;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	/* The next bit may not work on big endian */
+	level++;
+	seg_a = (unsigned long)a->type;
+	seg_b = (unsigned long)b->type;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+
+	level += sizeof(unsigned long);
+	if (a->desc_len == 0)
+		goto same;
+
+	i = 0;
+	if (((unsigned long)a->description | (unsigned long)b->description) &
+	    (sizeof(unsigned long) - 1)) {
+		do {
+			seg_a = *(unsigned long *)(a->description + i);
+			seg_b = *(unsigned long *)(b->description + i);
+			if ((seg_a ^ seg_b) != 0)
+				goto differ_plus_i;
+			i += sizeof(unsigned long);
+		} while (i < (a->desc_len & (sizeof(unsigned long) - 1)));
+	}
+
+	for (; i < a->desc_len; i++) {
+		seg_a = *(unsigned char *)(a->description + i);
+		seg_b = *(unsigned char *)(b->description + i);
+		if ((seg_a ^ seg_b) != 0)
+			goto differ_plus_i;
+	}
+
+same:
+	return -1;
+
+differ_plus_i:
+	level += i;
+differ:
+	i = level * 8 + __ffs(seg_a ^ seg_b);
+	return i;
+}
+
+/*
+ * Free an object after stripping the keyring flag off of the pointer.
+ */
+static void keyring_free_object(void *object)
+{
+	key_put(keyring_ptr_to_key(object));
+}
+
+/*
+ * Operations for keyring management by the index-tree routines.
+ */
+static const struct assoc_array_ops keyring_assoc_array_ops = {
+	.get_key_chunk		= keyring_get_key_chunk,
+	.get_object_key_chunk	= keyring_get_object_key_chunk,
+	.compare_object		= keyring_compare_object,
+	.diff_objects		= keyring_diff_objects,
+	.free_object		= keyring_free_object,
+};
+
 /*
  * Clean up a keyring when it is destroyed.  Unpublish its name if it had one
  * and dispose of its data.
@@ -155,9 +374,6 @@ static int keyring_match(const struct key *keyring, const void *description)
  */
 static void keyring_destroy(struct key *keyring)
 {
-	struct keyring_list *klist;
-	int loop;
-
 	if (keyring->description) {
 		write_lock(&keyring_name_lock);
 
@@ -168,12 +384,7 @@ static void keyring_destroy(struct key *keyring)
 		write_unlock(&keyring_name_lock);
 	}
 
-	klist = rcu_access_pointer(keyring->payload.subscriptions);
-	if (klist) {
-		for (loop = klist->nkeys - 1; loop >= 0; loop--)
-			key_put(rcu_access_pointer(klist->keys[loop]));
-		kfree(klist);
-	}
+	assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
 }
 
 /*
@@ -181,76 +392,88 @@ static void keyring_destroy(struct key *keyring)
  */
 static void keyring_describe(const struct key *keyring, struct seq_file *m)
 {
-	struct keyring_list *klist;
-
 	if (keyring->description)
 		seq_puts(m, keyring->description);
 	else
 		seq_puts(m, "[anon]");
 
 	if (key_is_instantiated(keyring)) {
-		rcu_read_lock();
-		klist = rcu_dereference(keyring->payload.subscriptions);
-		if (klist)
-			seq_printf(m, ": %u/%u", klist->nkeys, klist->maxkeys);
+		if (keyring->keys.nr_leaves_on_tree != 0)
+			seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
 		else
 			seq_puts(m, ": empty");
-		rcu_read_unlock();
 	}
 }
 
+struct keyring_read_iterator_context {
+	size_t			qty;
+	size_t			count;
+	key_serial_t __user	*buffer;
+};
+
+static int keyring_read_iterator(const void *object, void *data)
+{
+	struct keyring_read_iterator_context *ctx = data;
+	const struct key *key = keyring_ptr_to_key(object);
+	int ret;
+
+	kenter("{%s,%d},,{%zu/%zu}",
+	       key->type->name, key->serial, ctx->count, ctx->qty);
+
+	if (ctx->count >= ctx->qty)
+		return 1;
+
+	ret = put_user(key->serial, ctx->buffer);
+	if (ret < 0)
+		return ret;
+	ctx->buffer++;
+	ctx->count += sizeof(key->serial);
+	return 0;
+}
+
 /*
  * Read a list of key IDs from the keyring's contents in binary form
  *
- * The keyring's semaphore is read-locked by the caller.
+ * The keyring's semaphore is read-locked by the caller.  This prevents someone
+ * from modifying it under us - which could cause us to read key IDs multiple
+ * times.
  */
 static long keyring_read(const struct key *keyring,
 			 char __user *buffer, size_t buflen)
 {
-	struct keyring_list *klist;
-	struct key *key;
-	size_t qty, tmp;
-	int loop, ret;
+	struct keyring_read_iterator_context ctx;
+	unsigned long nr_keys;
+	int ret;
 
-	ret = 0;
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (klist) {
-		/* calculate how much data we could return */
-		qty = klist->nkeys * sizeof(key_serial_t);
-
-		if (buffer && buflen > 0) {
-			if (buflen > qty)
-				buflen = qty;
-
-			/* copy the IDs of the subscribed keys into the
-			 * buffer */
-			ret = -EFAULT;
-
-			for (loop = 0; loop < klist->nkeys; loop++) {
-				key = rcu_deref_link_locked(klist, loop,
-							    keyring);
-
-				tmp = sizeof(key_serial_t);
-				if (tmp > buflen)
-					tmp = buflen;
-
-				if (copy_to_user(buffer,
-						 &key->serial,
-						 tmp) != 0)
-					goto error;
-
-				buflen -= tmp;
-				if (buflen == 0)
-					break;
-				buffer += tmp;
-			}
-		}
+	kenter("{%d},,%zu", key_serial(keyring), buflen);
+
+	if (buflen & (sizeof(key_serial_t) - 1))
+		return -EINVAL;
+
+	nr_keys = keyring->keys.nr_leaves_on_tree;
+	if (nr_keys == 0)
+		return 0;
 
-		ret = qty;
+	/* Calculate how much data we could return */
+	ctx.qty = nr_keys * sizeof(key_serial_t);
+
+	if (!buffer || !buflen)
+		return ctx.qty;
+
+	if (buflen > ctx.qty)
+		ctx.qty = buflen;
+
+	/* Copy the IDs of the subscribed keys into the buffer */
+	ctx.buffer = (key_serial_t __user *)buffer;
+	ctx.count = 0;
+	ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
+	if (ret < 0) {
+		kleave(" = %d [iterate]", ret);
+		return ret;
 	}
 
-error:
-	return ret;
+	kleave(" = %zu [ok]", ctx.count);
+	return ctx.count;
 }
 
 /*
@@ -277,219 +500,360 @@ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
 }
 EXPORT_SYMBOL(keyring_alloc);
 
-/**
- * keyring_search_aux - Search a keyring tree for a key matching some criteria
- * @keyring_ref: A pointer to the keyring with possession indicator.
- * @ctx: The keyring search context.
- *
- * Search the supplied keyring tree for a key that matches the criteria given.
- * The root keyring and any linked keyrings must grant Search permission to the
- * caller to be searchable and keys can only be found if they too grant Search
- * to the caller. The possession flag on the root keyring pointer controls use
- * of the possessor bits in permissions checking of the entire tree.  In
- * addition, the LSM gets to forbid keyring searches and key matches.
- *
- * The search is performed as a breadth-then-depth search up to the prescribed
- * limit (KEYRING_SEARCH_MAX_DEPTH).
- *
- * Keys are matched to the type provided and are then filtered by the match
- * function, which is given the description to use in any way it sees fit.  The
- * match function may use any attributes of a key that it wishes to to
- * determine the match.  Normally the match function from the key type would be
- * used.
- *
- * RCU is used to prevent the keyring key lists from disappearing without the
- * need to take lots of locks.
- *
- * Returns a pointer to the found key and increments the key usage count if
- * successful; -EAGAIN if no matching keys were found, or if expired or revoked
- * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
- * specified keyring wasn't a keyring.
- *
- * In the case of a successful return, the possession attribute from
- * @keyring_ref is propagated to the returned key reference.
+/*
+ * Iteration function to consider each key found.
  */
-key_ref_t keyring_search_aux(key_ref_t keyring_ref,
-			     struct keyring_search_context *ctx)
+static int keyring_search_iterator(const void *object, void *iterator_data)
 {
-	struct {
-		/* Need a separate keylist pointer for RCU purposes */
-		struct key *keyring;
-		struct keyring_list *keylist;
-		int kix;
-	} stack[KEYRING_SEARCH_MAX_DEPTH];
-
-	struct keyring_list *keylist;
-	unsigned long kflags;
-	struct key *keyring, *key;
-	key_ref_t key_ref;
-	long err;
-	int sp, nkeys, kix;
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+	unsigned long kflags = key->flags;
 
-	keyring = key_ref_to_ptr(keyring_ref);
-	ctx->possessed = is_key_possessed(keyring_ref);
-	key_check(keyring);
+	kenter("{%d}", key->serial);
 
-	/* top keyring must have search permission to begin the search */
-	err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
-	if (err < 0) {
-		key_ref = ERR_PTR(err);
-		goto error;
+	/* ignore keys not of this type */
+	if (key->type != ctx->index_key.type) {
+		kleave(" = 0 [!type]");
+		return 0;
 	}
 
-	key_ref = ERR_PTR(-ENOTDIR);
-	if (keyring->type != &key_type_keyring)
-		goto error;
+	/* skip invalidated, revoked and expired keys */
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED))) {
+			ctx->result = ERR_PTR(-EKEYREVOKED);
+			kleave(" = %d [invrev]", ctx->skipped_ret);
+			goto skipped;
+		}
 
-	rcu_read_lock();
+		if (key->expiry && ctx->now.tv_sec >= key->expiry) {
+			ctx->result = ERR_PTR(-EKEYEXPIRED);
+			kleave(" = %d [expire]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
 
-	ctx->now = current_kernel_time();
-	err = -EAGAIN;
-	sp = 0;
-
-	/* firstly we should check to see if this top-level keyring is what we
-	 * are looking for */
-	key_ref = ERR_PTR(-EAGAIN);
-	kflags = keyring->flags;
-	if (keyring->type == ctx->index_key.type &&
-	    ctx->match(keyring, ctx->match_data)) {
-		key = keyring;
-		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
-			goto found;
+	/* keys that don't match */
+	if (!ctx->match(key, ctx->match_data)) {
+		kleave(" = 0 [!match]");
+		return 0;
+	}
 
-		/* check it isn't negative and hasn't expired or been
-		 * revoked */
-		if (kflags & (1 << KEY_FLAG_REVOKED))
-			goto error_2;
-		if (key->expiry && ctx->now.tv_sec >= key->expiry)
-			goto error_2;
-		key_ref = ERR_PTR(key->type_data.reject_error);
-		if (kflags & (1 << KEY_FLAG_NEGATIVE))
-			goto error_2;
-		goto found;
+	/* key must have search permissions */
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+	    key_task_permission(make_key_ref(key, ctx->possessed),
+				ctx->cred, KEY_SEARCH) < 0) {
+		ctx->result = ERR_PTR(-EACCES);
+		kleave(" = %d [!perm]", ctx->skipped_ret);
+		goto skipped;
 	}
 
-	/* otherwise, the top keyring must not be revoked, expired, or
-	 * negatively instantiated if we are to search it */
-	key_ref = ERR_PTR(-EAGAIN);
-	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-		      (1 << KEY_FLAG_REVOKED) |
-		      (1 << KEY_FLAG_NEGATIVE)) ||
-	    (keyring->expiry && ctx->now.tv_sec >= keyring->expiry))
-		goto error_2;
-
-	/* start processing a new keyring */
-descend:
-	kflags = keyring->flags;
-	if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-		      (1 << KEY_FLAG_REVOKED)))
-		goto not_this_keyring;
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		/* we set a different error code if we pass a negative key */
+		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
+			ctx->result = ERR_PTR(key->type_data.reject_error);
+			kleave(" = %d [neg]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
 
-	keylist = rcu_dereference(keyring->payload.subscriptions);
-	if (!keylist)
-		goto not_this_keyring;
+	/* Found */
+	ctx->result = make_key_ref(key, ctx->possessed);
+	kleave(" = 1 [found]");
+	return 1;
 
-	/* iterate through the keys in this keyring first */
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (kix = 0; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-		kflags = key->flags;
+skipped:
+	return ctx->skipped_ret;
+}
 
-		/* ignore keys not of this type */
-		if (key->type != ctx->index_key.type)
-			continue;
+/*
+ * Search inside a keyring for a key.  We can search by walking to it
+ * directly based on its index-key or we can iterate over the entire
+ * tree looking for it, based on the match function.
+ */
+static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
+{
+	if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
+	    KEYRING_SEARCH_LOOKUP_DIRECT) {
+		const void *object;
+
+		object = assoc_array_find(&keyring->keys,
+					  &keyring_assoc_array_ops,
+					  &ctx->index_key);
+		return object ? ctx->iterator(object, ctx) : 0;
+	}
+	return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
+}
 
-		/* skip invalidated, revoked and expired keys */
-		if (!(ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)) {
-			if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
-				      (1 << KEY_FLAG_REVOKED)))
-				continue;
+/*
+ * Search a tree of keyrings that point to other keyrings up to the maximum
+ * depth.
+ */
+static bool search_nested_keyrings(struct key *keyring,
+				   struct keyring_search_context *ctx)
+{
+	struct {
+		struct key *keyring;
+		struct assoc_array_node *node;
+		int slot;
+	} stack[KEYRING_SEARCH_MAX_DEPTH];
 
-			if (key->expiry && ctx->now.tv_sec >= key->expiry)
-				continue;
-		}
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *ptr;
+	struct key *key;
+	int sp = 0, slot;
 
-		/* keys that don't match */
-		if (!ctx->match(key, ctx->match_data))
-			continue;
+	kenter("{%d},{%s,%s}",
+	       keyring->serial,
+	       ctx->index_key.type->name,
+	       ctx->index_key.description);
 
-		/* key must have search permissions */
-		if (key_task_permission(make_key_ref(key, ctx->possessed),
-					ctx->cred, KEY_SEARCH) < 0)
-			continue;
+	if (ctx->index_key.description)
+		ctx->index_key.desc_len = strlen(ctx->index_key.description);
 
-		if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
+	/* Check to see if this top-level keyring is what we are looking for
+	 * and whether it is valid or not.
+	 */
+	if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
+	    keyring_compare_object(keyring, &ctx->index_key)) {
+		ctx->skipped_ret = 2;
+		ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
+		switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
+		case 1:
 			goto found;
-
-		/* we set a different error code if we pass a negative key */
-		if (kflags & (1 << KEY_FLAG_NEGATIVE)) {
-			err = key->type_data.reject_error;
-			continue;
+		case 2:
+			return false;
+		default:
+			break;
 		}
+	}
 
+	ctx->skipped_ret = 0;
+	if (ctx->flags & KEYRING_SEARCH_NO_STATE_CHECK)
+		ctx->flags &= ~KEYRING_SEARCH_DO_STATE_CHECK;
+
+	/* Start processing a new keyring */
+descend_to_keyring:
+	kdebug("descend to %d", keyring->serial);
+	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED)))
+		goto not_this_keyring;
+
+	/* Search through the keys in this keyring before its searching its
+	 * subtrees.
+	 */
+	if (search_keyring(keyring, ctx))
 		goto found;
-	}
 
-	/* search through the keyrings nested in this one */
-	kix = 0;
-ascend:
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-		if (key->type != &key_type_keyring)
-			continue;
+	/* Then manually iterate through the keyrings nested in this one.
+	 *
+	 * Start from the root node of the index tree.  Because of the way the
+	 * hash function has been set up, keyrings cluster on the leftmost
+	 * branch of the root node (root slot 0) or in the root node itself.
+	 * Non-keyrings avoid the leftmost branch of the root entirely (root
+	 * slots 1-15).
+	 */
+	ptr = ACCESS_ONCE(keyring->keys.root);
+	if (!ptr)
+		goto not_this_keyring;
 
-		/* recursively search nested keyrings
-		 * - only search keyrings for which we have search permission
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		/* If the root is a shortcut, either the keyring only contains
+		 * keyring pointers (everything clusters behind root slot 0) or
+		 * doesn't contain any keyring pointers.
 		 */
-		if (sp >= KEYRING_SEARCH_MAX_DEPTH)
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
+			goto not_this_keyring;
+
+		ptr = ACCESS_ONCE(shortcut->next_node);
+		node = assoc_array_ptr_to_node(ptr);
+		goto begin_node;
+	}
+
+	node = assoc_array_ptr_to_node(ptr);
+	smp_read_barrier_depends();
+
+	ptr = node->slots[0];
+	if (!assoc_array_ptr_is_meta(ptr))
+		goto begin_node;
+
+descend_to_node:
+	/* Descend to a more distal node in this keyring's content tree and go
+	 * through that.
+	 */
+	kdebug("descend");
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		ptr = ACCESS_ONCE(shortcut->next_node);
+		BUG_ON(!assoc_array_ptr_is_node(ptr));
+		node = assoc_array_ptr_to_node(ptr);
+	}
+
+begin_node:
+	kdebug("begin_node");
+	smp_read_barrier_depends();
+	slot = 0;
+ascend_to_node:
+	/* Go through the slots in a node */
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = ACCESS_ONCE(node->slots[slot]);
+
+		if (assoc_array_ptr_is_meta(ptr) && node->back_pointer)
+			goto descend_to_node;
+
+		if (!keyring_ptr_is_keyring(ptr))
 			continue;
 
-		if (key_task_permission(make_key_ref(key, ctx->possessed),
+		key = keyring_ptr_to_key(ptr);
+
+		if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
+			if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
+				ctx->result = ERR_PTR(-ELOOP);
+				return false;
+			}
+			goto not_this_keyring;
+		}
+
+		/* Search a nested keyring */
+		if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+		    key_task_permission(make_key_ref(key, ctx->possessed),
 					ctx->cred, KEY_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
 		stack[sp].keyring = keyring;
-		stack[sp].keylist = keylist;
-		stack[sp].kix = kix;
+		stack[sp].node = node;
+		stack[sp].slot = slot;
 		sp++;
 
 		/* begin again with the new keyring */
 		keyring = key;
-		goto descend;
+		goto descend_to_keyring;
+	}
+
+	/* We've dealt with all the slots in the current node, so now we need
+	 * to ascend to the parent and continue processing there.
+	 */
+	ptr = ACCESS_ONCE(node->back_pointer);
+	slot = node->parent_slot;
+
+	if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		smp_read_barrier_depends();
+		ptr = ACCESS_ONCE(shortcut->back_pointer);
+		slot = shortcut->parent_slot;
+	}
+	if (!ptr)
+		goto not_this_keyring;
+	node = assoc_array_ptr_to_node(ptr);
+	smp_read_barrier_depends();
+	slot++;
+
+	/* If we've ascended to the root (zero backpointer), we must have just
+	 * finished processing the leftmost branch rather than the root slots -
+	 * so there can't be any more keyrings for us to find.
+	 */
+	if (node->back_pointer) {
+		kdebug("ascend %d", slot);
+		goto ascend_to_node;
 	}
 
-	/* the keyring we're looking at was disqualified or didn't contain a
-	 * matching key */
+	/* The keyring we're looking at was disqualified or didn't contain a
+	 * matching key.
+	 */
 not_this_keyring:
-	if (sp > 0) {
-		/* resume the processing of a keyring higher up in the tree */
-		sp--;
-		keyring = stack[sp].keyring;
-		keylist = stack[sp].keylist;
-		kix = stack[sp].kix + 1;
-		goto ascend;
+	kdebug("not_this_keyring %d", sp);
+	if (sp <= 0) {
+		kleave(" = false");
+		return false;
 	}
 
-	key_ref = ERR_PTR(err);
-	goto error_2;
+	/* Resume the processing of a keyring higher up in the tree */
+	sp--;
+	keyring = stack[sp].keyring;
+	node = stack[sp].node;
+	slot = stack[sp].slot + 1;
+	kdebug("ascend to %d [%d]", keyring->serial, slot);
+	goto ascend_to_node;
 
-	/* we found a viable match */
+	/* We found a viable match */
 found:
-	__key_get(key);
-	key->last_used_at = ctx->now.tv_sec;
-	keyring->last_used_at = ctx->now.tv_sec;
-	while (sp > 0)
-		stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
+	key = key_ref_to_ptr(ctx->result);
 	key_check(key);
-	key_ref = make_key_ref(key, ctx->possessed);
-error_2:
+	if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
+		key->last_used_at = ctx->now.tv_sec;
+		keyring->last_used_at = ctx->now.tv_sec;
+		while (sp > 0)
+			stack[--sp].keyring->last_used_at = ctx->now.tv_sec;
+	}
+	kleave(" = true");
+	return true;
+}
+
+/**
+ * keyring_search_aux - Search a keyring tree for a key matching some criteria
+ * @keyring_ref: A pointer to the keyring with possession indicator.
+ * @ctx: The keyring search context.
+ *
+ * Search the supplied keyring tree for a key that matches the criteria given.
+ * The root keyring and any linked keyrings must grant Search permission to the
+ * caller to be searchable and keys can only be found if they too grant Search
+ * to the caller. The possession flag on the root keyring pointer controls use
+ * of the possessor bits in permissions checking of the entire tree.  In
+ * addition, the LSM gets to forbid keyring searches and key matches.
+ *
+ * The search is performed as a breadth-then-depth search up to the prescribed
+ * limit (KEYRING_SEARCH_MAX_DEPTH).
+ *
+ * Keys are matched to the type provided and are then filtered by the match
+ * function, which is given the description to use in any way it sees fit.  The
+ * match function may use any attributes of a key that it wishes to to
+ * determine the match.  Normally the match function from the key type would be
+ * used.
+ *
+ * RCU can be used to prevent the keyring key lists from disappearing without
+ * the need to take lots of locks.
+ *
+ * Returns a pointer to the found key and increments the key usage count if
+ * successful; -EAGAIN if no matching keys were found, or if expired or revoked
+ * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
+ * specified keyring wasn't a keyring.
+ *
+ * In the case of a successful return, the possession attribute from
+ * @keyring_ref is propagated to the returned key reference.
+ */
+key_ref_t keyring_search_aux(key_ref_t keyring_ref,
+			     struct keyring_search_context *ctx)
+{
+	struct key *keyring;
+	long err;
+
+	ctx->iterator = keyring_search_iterator;
+	ctx->possessed = is_key_possessed(keyring_ref);
+	ctx->result = ERR_PTR(-EAGAIN);
+
+	keyring = key_ref_to_ptr(keyring_ref);
+	key_check(keyring);
+
+	if (keyring->type != &key_type_keyring)
+		return ERR_PTR(-ENOTDIR);
+
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
+		err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	rcu_read_lock();
+	ctx->now = current_kernel_time();
+	if (search_nested_keyrings(keyring, ctx))
+		__key_get(key_ref_to_ptr(ctx->result));
 	rcu_read_unlock();
-error:
-	return key_ref;
+	return ctx->result;
 }
 
 /**
@@ -499,7 +863,7 @@ error:
  * @description: The name of the keyring we want to find.
  *
  * As keyring_search_aux() above, but using the current task's credentials and
- * type's default matching function.
+ * type's default matching function and preferred search method.
  */
 key_ref_t keyring_search(key_ref_t keyring,
 			 struct key_type *type,
@@ -523,58 +887,49 @@ key_ref_t keyring_search(key_ref_t keyring,
 EXPORT_SYMBOL(keyring_search);
 
 /*
- * Search the given keyring only (no recursion).
+ * Search the given keyring for a key that might be updated.
  *
  * The caller must guarantee that the keyring is a keyring and that the
- * permission is granted to search the keyring as no check is made here.
- *
- * RCU is used to make it unnecessary to lock the keyring key list here.
+ * permission is granted to modify the keyring as no check is made here.  The
+ * caller must also hold a lock on the keyring semaphore.
  *
  * Returns a pointer to the found key with usage count incremented if
- * successful and returns -ENOKEY if not found.  Revoked and invalidated keys
- * are skipped over.
+ * successful and returns NULL if not found.  Revoked and invalidated keys are
+ * skipped over.
  *
  * If successful, the possession indicator is propagated from the keyring ref
  * to the returned key reference.
  */
-key_ref_t __keyring_search_one(key_ref_t keyring_ref,
-			       const struct keyring_index_key *index_key)
+key_ref_t find_key_to_update(key_ref_t keyring_ref,
+			     const struct keyring_index_key *index_key)
 {
-	struct keyring_list *klist;
 	struct key *keyring, *key;
-	bool possessed;
-	int nkeys, loop;
+	const void *object;
 
 	keyring = key_ref_to_ptr(keyring_ref);
-	possessed = is_key_possessed(keyring_ref);
 
-	rcu_read_lock();
+	kenter("{%d},{%s,%s}",
+	       keyring->serial, index_key->type->name, index_key->description);
 
-	klist = rcu_dereference(keyring->payload.subscriptions);
-	if (klist) {
-		nkeys = klist->nkeys;
-		smp_rmb();
-		for (loop = 0; loop < nkeys ; loop++) {
-			key = rcu_dereference(klist->keys[loop]);
-			if (key->type == index_key->type &&
-			    (!key->type->match ||
-			     key->type->match(key, index_key->description)) &&
-			    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					    (1 << KEY_FLAG_REVOKED)))
-			    )
-				goto found;
-		}
-	}
+	object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
+				  index_key);
 
-	rcu_read_unlock();
-	return ERR_PTR(-ENOKEY);
+	if (object)
+		goto found;
+
+	kleave(" = NULL");
+	return NULL;
 
 found:
+	key = keyring_ptr_to_key(object);
+	if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			  (1 << KEY_FLAG_REVOKED))) {
+		kleave(" = NULL [x]");
+		return NULL;
+	}
 	__key_get(key);
-	keyring->last_used_at = key->last_used_at =
-		current_kernel_time().tv_sec;
-	rcu_read_unlock();
-	return make_key_ref(key, possessed);
+	kleave(" = {%d}", key->serial);
+	return make_key_ref(key, is_key_possessed(keyring_ref));
 }
 
 /*
@@ -637,6 +992,19 @@ out:
 	return keyring;
 }
 
+static int keyring_detect_cycle_iterator(const void *object,
+					 void *iterator_data)
+{
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	kenter("{%d}", key->serial);
+
+	BUG_ON(key != ctx->match_data);
+	ctx->result = ERR_PTR(-EDEADLK);
+	return 1;
+}
+
 /*
  * See if a cycle will will be created by inserting acyclic tree B in acyclic
  * tree A at the topmost level (ie: as a direct child of A).
@@ -646,117 +1014,39 @@ out:
  */
 static int keyring_detect_cycle(struct key *A, struct key *B)
 {
-	struct {
-		struct keyring_list *keylist;
-		int kix;
-	} stack[KEYRING_SEARCH_MAX_DEPTH];
-
-	struct keyring_list *keylist;
-	struct key *subtree, *key;
-	int sp, nkeys, kix, ret;
+	struct keyring_search_context ctx = {
+		.index_key	= A->index_key,
+		.match_data	= A,
+		.iterator	= keyring_detect_cycle_iterator,
+		.flags		= (KEYRING_SEARCH_LOOKUP_DIRECT |
+				   KEYRING_SEARCH_NO_STATE_CHECK |
+				   KEYRING_SEARCH_NO_UPDATE_TIME |
+				   KEYRING_SEARCH_NO_CHECK_PERM |
+				   KEYRING_SEARCH_DETECT_TOO_DEEP),
+	};
 
 	rcu_read_lock();
-
-	ret = -EDEADLK;
-	if (A == B)
-		goto cycle_detected;
-
-	subtree = B;
-	sp = 0;
-
-	/* start processing a new keyring */
-descend:
-	if (test_bit(KEY_FLAG_REVOKED, &subtree->flags))
-		goto not_this_keyring;
-
-	keylist = rcu_dereference(subtree->payload.subscriptions);
-	if (!keylist)
-		goto not_this_keyring;
-	kix = 0;
-
-ascend:
-	/* iterate through the remaining keys in this keyring */
-	nkeys = keylist->nkeys;
-	smp_rmb();
-	for (; kix < nkeys; kix++) {
-		key = rcu_dereference(keylist->keys[kix]);
-
-		if (key == A)
-			goto cycle_detected;
-
-		/* recursively check nested keyrings */
-		if (key->type == &key_type_keyring) {
-			if (sp >= KEYRING_SEARCH_MAX_DEPTH)
-				goto too_deep;
-
-			/* stack the current position */
-			stack[sp].keylist = keylist;
-			stack[sp].kix = kix;
-			sp++;
-
-			/* begin again with the new keyring */
-			subtree = key;
-			goto descend;
-		}
-	}
-
-	/* the keyring we're looking at was disqualified or didn't contain a
-	 * matching key */
-not_this_keyring:
-	if (sp > 0) {
-		/* resume the checking of a keyring higher up in the tree */
-		sp--;
-		keylist = stack[sp].keylist;
-		kix = stack[sp].kix + 1;
-		goto ascend;
-	}
-
-	ret = 0; /* no cycles detected */
-
-error:
+	search_nested_keyrings(B, &ctx);
 	rcu_read_unlock();
-	return ret;
-
-too_deep:
-	ret = -ELOOP;
-	goto error;
-
-cycle_detected:
-	ret = -EDEADLK;
-	goto error;
-}
-
-/*
- * Dispose of a keyring list after the RCU grace period, freeing the unlinked
- * key
- */
-static void keyring_unlink_rcu_disposal(struct rcu_head *rcu)
-{
-	struct keyring_list *klist =
-		container_of(rcu, struct keyring_list, rcu);
-
-	if (klist->delkey != USHRT_MAX)
-		key_put(rcu_access_pointer(klist->keys[klist->delkey]));
-	kfree(klist);
+	return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
 }
 
 /*
  * Preallocate memory so that a key can be linked into to a keyring.
  */
-int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key,
-		     unsigned long *_prealloc)
+int __key_link_begin(struct key *keyring,
+		     const struct keyring_index_key *index_key,
+		     struct assoc_array_edit **_edit)
 	__acquires(&keyring->sem)
 	__acquires(&keyring_serialise_link_sem)
 {
-	struct keyring_list *klist, *nklist;
-	unsigned long prealloc;
-	unsigned max;
-	time_t lowest_lru;
-	size_t size;
-	int loop, lru, ret;
+	struct assoc_array_edit *edit;
+	int ret;
 
 	kenter("%d,%s,%s,",
-	       key_serial(keyring), index_key->type->name, index_key->description);
+	       keyring->serial, index_key->type->name, index_key->description);
+
+	BUG_ON(index_key->desc_len == 0);
 
 	if (keyring->type != &key_type_keyring)
 		return -ENOTDIR;
@@ -772,88 +1062,25 @@ int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_
 	if (index_key->type == &key_type_keyring)
 		down_write(&keyring_serialise_link_sem);
 
-	klist = rcu_dereference_locked_keyring(keyring);
-
-	/* see if there's a matching key we can displace */
-	lru = -1;
-	if (klist && klist->nkeys > 0) {
-		lowest_lru = TIME_T_MAX;
-		for (loop = klist->nkeys - 1; loop >= 0; loop--) {
-			struct key *key = rcu_deref_link_locked(klist, loop,
-								keyring);
-			if (key->type == index_key->type &&
-			    strcmp(key->description, index_key->description) == 0) {
-				/* Found a match - we'll replace the link with
-				 * one to the new key.  We record the slot
-				 * position.
-				 */
-				klist->delkey = loop;
-				prealloc = 0;
-				goto done;
-			}
-			if (key->last_used_at < lowest_lru) {
-				lowest_lru = key->last_used_at;
-				lru = loop;
-			}
-		}
-	}
-
-	/* If the keyring is full then do an LRU discard */
-	if (klist &&
-	    klist->nkeys == klist->maxkeys &&
-	    klist->maxkeys >= MAX_KEYRING_LINKS) {
-		kdebug("LRU discard %d\n", lru);
-		klist->delkey = lru;
-		prealloc = 0;
-		goto done;
-	}
-
 	/* check that we aren't going to overrun the user's quota */
 	ret = key_payload_reserve(keyring,
 				  keyring->datalen + KEYQUOTA_LINK_BYTES);
 	if (ret < 0)
 		goto error_sem;
 
-	if (klist && klist->nkeys < klist->maxkeys) {
-		/* there's sufficient slack space to append directly */
-		klist->delkey = klist->nkeys;
-		prealloc = KEY_LINK_FIXQUOTA;
-	} else {
-		/* grow the key list */
-		max = 4;
-		if (klist) {
-			max += klist->maxkeys;
-			if (max > MAX_KEYRING_LINKS)
-				max = MAX_KEYRING_LINKS;
-			BUG_ON(max <= klist->maxkeys);
-		}
-
-		size = sizeof(*klist) + sizeof(struct key *) * max;
-
-		ret = -ENOMEM;
-		nklist = kmalloc(size, GFP_KERNEL);
-		if (!nklist)
-			goto error_quota;
-
-		nklist->maxkeys = max;
-		if (klist) {
-			memcpy(nklist->keys, klist->keys,
-			       sizeof(struct key *) * klist->nkeys);
-			nklist->delkey = klist->nkeys;
-			nklist->nkeys = klist->nkeys + 1;
-			klist->delkey = USHRT_MAX;
-		} else {
-			nklist->nkeys = 1;
-			nklist->delkey = 0;
-		}
-
-		/* add the key into the new space */
-		RCU_INIT_POINTER(nklist->keys[nklist->delkey], NULL);
-		prealloc = (unsigned long)nklist | KEY_LINK_FIXQUOTA;
+	/* Create an edit script that will insert/replace the key in the
+	 * keyring tree.
+	 */
+	edit = assoc_array_insert(&keyring->keys,
+				  &keyring_assoc_array_ops,
+				  index_key,
+				  NULL);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+		goto error_quota;
 	}
 
-done:
-	*_prealloc = prealloc;
+	*_edit = edit;
 	kleave(" = 0");
 	return 0;
 
@@ -893,60 +1120,12 @@ int __key_link_check_live_key(struct key *keyring, struct key *key)
  * holds at most one link to any given key of a particular type+description
  * combination.
  */
-void __key_link(struct key *keyring, struct key *key,
-		unsigned long *_prealloc)
+void __key_link(struct key *key, struct assoc_array_edit **_edit)
 {
-	struct keyring_list *klist, *nklist;
-	struct key *discard;
-
-	nklist = (struct keyring_list *)(*_prealloc & ~KEY_LINK_FIXQUOTA);
-	*_prealloc = 0;
-
-	kenter("%d,%d,%p", keyring->serial, key->serial, nklist);
-
-	klist = rcu_dereference_locked_keyring(keyring);
-
 	__key_get(key);
-	keyring->last_used_at = key->last_used_at =
-		current_kernel_time().tv_sec;
-
-	/* there's a matching key we can displace or an empty slot in a newly
-	 * allocated list we can fill */
-	if (nklist) {
-		kdebug("reissue %hu/%hu/%hu",
-		       nklist->delkey, nklist->nkeys, nklist->maxkeys);
-
-		RCU_INIT_POINTER(nklist->keys[nklist->delkey], key);
-
-		rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
-		/* dispose of the old keyring list and, if there was one, the
-		 * displaced key */
-		if (klist) {
-			kdebug("dispose %hu/%hu/%hu",
-			       klist->delkey, klist->nkeys, klist->maxkeys);
-			call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
-		}
-	} else if (klist->delkey < klist->nkeys) {
-		kdebug("replace %hu/%hu/%hu",
-		       klist->delkey, klist->nkeys, klist->maxkeys);
-
-		discard = rcu_dereference_protected(
-			klist->keys[klist->delkey],
-			rwsem_is_locked(&keyring->sem));
-		rcu_assign_pointer(klist->keys[klist->delkey], key);
-		/* The garbage collector will take care of RCU
-		 * synchronisation */
-		key_put(discard);
-	} else {
-		/* there's sufficient slack space to append directly */
-		kdebug("append %hu/%hu/%hu",
-		       klist->delkey, klist->nkeys, klist->maxkeys);
-
-		RCU_INIT_POINTER(klist->keys[klist->delkey], key);
-		smp_wmb();
-		klist->nkeys++;
-	}
+	assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
+	assoc_array_apply_edit(*_edit);
+	*_edit = NULL;
 }
 
 /*
@@ -956,23 +1135,20 @@ void __key_link(struct key *keyring, struct key *key,
  */
 void __key_link_end(struct key *keyring,
 		    const struct keyring_index_key *index_key,
-		    unsigned long prealloc)
+		    struct assoc_array_edit *edit)
 	__releases(&keyring->sem)
 	__releases(&keyring_serialise_link_sem)
 {
 	BUG_ON(index_key->type == NULL);
-	BUG_ON(index_key->type->name == NULL);
-	kenter("%d,%s,%lx", keyring->serial, index_key->type->name, prealloc);
+	kenter("%d,%s,", keyring->serial, index_key->type->name);
 
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
-	if (prealloc) {
-		if (prealloc & KEY_LINK_FIXQUOTA)
-			key_payload_reserve(keyring,
-					    keyring->datalen -
-					    KEYQUOTA_LINK_BYTES);
-		kfree((struct keyring_list *)(prealloc & ~KEY_LINK_FIXQUOTA));
+	if (edit) {
+		key_payload_reserve(keyring,
+				    keyring->datalen - KEYQUOTA_LINK_BYTES);
+		assoc_array_cancel_edit(edit);
 	}
 	up_write(&keyring->sem);
 }
@@ -999,20 +1175,24 @@ void __key_link_end(struct key *keyring,
  */
 int key_link(struct key *keyring, struct key *key)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	int ret;
 
+	kenter("{%d,%d}", keyring->serial, atomic_read(&keyring->usage));
+
 	key_check(keyring);
 	key_check(key);
 
-	ret = __key_link_begin(keyring, &key->index_key, &prealloc);
+	ret = __key_link_begin(keyring, &key->index_key, &edit);
 	if (ret == 0) {
+		kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
 		ret = __key_link_check_live_key(keyring, key);
 		if (ret == 0)
-			__key_link(keyring, key, &prealloc);
-		__key_link_end(keyring, &key->index_key, prealloc);
+			__key_link(key, &edit);
+		__key_link_end(keyring, &key->index_key, edit);
 	}
 
+	kleave(" = %d {%d,%d}", ret, keyring->serial, atomic_read(&keyring->usage));
 	return ret;
 }
 EXPORT_SYMBOL(key_link);
@@ -1036,90 +1216,36 @@ EXPORT_SYMBOL(key_link);
  */
 int key_unlink(struct key *keyring, struct key *key)
 {
-	struct keyring_list *klist, *nklist;
-	int loop, ret;
+	struct assoc_array_edit *edit;
+	int ret;
 
 	key_check(keyring);
 	key_check(key);
 
-	ret = -ENOTDIR;
 	if (keyring->type != &key_type_keyring)
-		goto error;
+		return -ENOTDIR;
 
 	down_write(&keyring->sem);
 
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (klist) {
-		/* search the keyring for the key */
-		for (loop = 0; loop < klist->nkeys; loop++)
-			if (rcu_access_pointer(klist->keys[loop]) == key)
-				goto key_is_present;
+	edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
+				  &key->index_key);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+		goto error;
 	}
-
-	up_write(&keyring->sem);
 	ret = -ENOENT;
-	goto error;
-
-key_is_present:
-	/* we need to copy the key list for RCU purposes */
-	nklist = kmalloc(sizeof(*klist) +
-			 sizeof(struct key *) * klist->maxkeys,
-			 GFP_KERNEL);
-	if (!nklist)
-		goto nomem;
-	nklist->maxkeys = klist->maxkeys;
-	nklist->nkeys = klist->nkeys - 1;
-
-	if (loop > 0)
-		memcpy(&nklist->keys[0],
-		       &klist->keys[0],
-		       loop * sizeof(struct key *));
-
-	if (loop < nklist->nkeys)
-		memcpy(&nklist->keys[loop],
-		       &klist->keys[loop + 1],
-		       (nklist->nkeys - loop) * sizeof(struct key *));
-
-	/* adjust the user's quota */
-	key_payload_reserve(keyring,
-			    keyring->datalen - KEYQUOTA_LINK_BYTES);
-
-	rcu_assign_pointer(keyring->payload.subscriptions, nklist);
-
-	up_write(&keyring->sem);
-
-	/* schedule for later cleanup */
-	klist->delkey = loop;
-	call_rcu(&klist->rcu, keyring_unlink_rcu_disposal);
+	if (edit == NULL)
+		goto error;
 
+	assoc_array_apply_edit(edit);
 	ret = 0;
 
 error:
-	return ret;
-nomem:
-	ret = -ENOMEM;
 	up_write(&keyring->sem);
-	goto error;
+	return ret;
 }
 EXPORT_SYMBOL(key_unlink);
 
-/*
- * Dispose of a keyring list after the RCU grace period, releasing the keys it
- * links to.
- */
-static void keyring_clear_rcu_disposal(struct rcu_head *rcu)
-{
-	struct keyring_list *klist;
-	int loop;
-
-	klist = container_of(rcu, struct keyring_list, rcu);
-
-	for (loop = klist->nkeys - 1; loop >= 0; loop--)
-		key_put(rcu_access_pointer(klist->keys[loop]));
-
-	kfree(klist);
-}
-
 /**
  * keyring_clear - Clear a keyring
  * @keyring: The keyring to clear.
@@ -1130,33 +1256,25 @@ static void keyring_clear_rcu_disposal(struct rcu_head *rcu)
  */
 int keyring_clear(struct key *keyring)
 {
-	struct keyring_list *klist;
+	struct assoc_array_edit *edit;
 	int ret;
 
-	ret = -ENOTDIR;
-	if (keyring->type == &key_type_keyring) {
-		/* detach the pointer block with the locks held */
-		down_write(&keyring->sem);
-
-		klist = rcu_dereference_locked_keyring(keyring);
-		if (klist) {
-			/* adjust the quota */
-			key_payload_reserve(keyring,
-					    sizeof(struct keyring_list));
-
-			rcu_assign_pointer(keyring->payload.subscriptions,
-					   NULL);
-		}
-
-		up_write(&keyring->sem);
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
 
-		/* free the keys after the locks have been dropped */
-		if (klist)
-			call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
+	down_write(&keyring->sem);
 
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+	} else {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		key_payload_reserve(keyring, 0);
 		ret = 0;
 	}
 
+	up_write(&keyring->sem);
 	return ret;
 }
 EXPORT_SYMBOL(keyring_clear);
@@ -1168,17 +1286,25 @@ EXPORT_SYMBOL(keyring_clear);
  */
 static void keyring_revoke(struct key *keyring)
 {
-	struct keyring_list *klist;
+	struct assoc_array_edit *edit;
 
-	klist = rcu_dereference_locked_keyring(keyring);
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (!IS_ERR(edit)) {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		key_payload_reserve(keyring, 0);
+	}
+}
 
-	/* adjust the quota */
-	key_payload_reserve(keyring, 0);
+static bool gc_iterator(void *object, void *iterator_data)
+{
+	struct key *key = keyring_ptr_to_key(object);
+	time_t *limit = iterator_data;
 
-	if (klist) {
-		rcu_assign_pointer(keyring->payload.subscriptions, NULL);
-		call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
-	}
+	if (key_is_dead(key, *limit))
+		return false;
+	key_get(key);
+	return true;
 }
 
 /*
@@ -1191,88 +1317,12 @@ static void keyring_revoke(struct key *keyring)
  */
 void keyring_gc(struct key *keyring, time_t limit)
 {
-	struct keyring_list *klist, *new;
-	struct key *key;
-	int loop, keep, max;
-
 	kenter("{%x,%s}", key_serial(keyring), keyring->description);
 
 	down_write(&keyring->sem);
-
-	klist = rcu_dereference_locked_keyring(keyring);
-	if (!klist)
-		goto no_klist;
-
-	/* work out how many subscriptions we're keeping */
-	keep = 0;
-	for (loop = klist->nkeys - 1; loop >= 0; loop--)
-		if (!key_is_dead(rcu_deref_link_locked(klist, loop, keyring),
-				 limit))
-			keep++;
-
-	if (keep == klist->nkeys)
-		goto just_return;
-
-	/* allocate a new keyring payload */
-	max = roundup(keep, 4);
-	new = kmalloc(sizeof(struct keyring_list) + max * sizeof(struct key *),
-		      GFP_KERNEL);
-	if (!new)
-		goto nomem;
-	new->maxkeys = max;
-	new->nkeys = 0;
-	new->delkey = 0;
-
-	/* install the live keys
-	 * - must take care as expired keys may be updated back to life
-	 */
-	keep = 0;
-	for (loop = klist->nkeys - 1; loop >= 0; loop--) {
-		key = rcu_deref_link_locked(klist, loop, keyring);
-		if (!key_is_dead(key, limit)) {
-			if (keep >= max)
-				goto discard_new;
-			RCU_INIT_POINTER(new->keys[keep++], key_get(key));
-		}
-	}
-	new->nkeys = keep;
-
-	/* adjust the quota */
-	key_payload_reserve(keyring,
-			    sizeof(struct keyring_list) +
-			    KEYQUOTA_LINK_BYTES * keep);
-
-	if (keep == 0) {
-		rcu_assign_pointer(keyring->payload.subscriptions, NULL);
-		kfree(new);
-	} else {
-		rcu_assign_pointer(keyring->payload.subscriptions, new);
-	}
-
-	up_write(&keyring->sem);
-
-	call_rcu(&klist->rcu, keyring_clear_rcu_disposal);
-	kleave(" [yes]");
-	return;
-
-discard_new:
-	new->nkeys = keep;
-	keyring_clear_rcu_disposal(&new->rcu);
+	assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
+		       gc_iterator, &limit);
 	up_write(&keyring->sem);
-	kleave(" [discard]");
-	return;
 
-just_return:
-	up_write(&keyring->sem);
-	kleave(" [no dead]");
-	return;
-
-no_klist:
-	up_write(&keyring->sem);
-	kleave(" [no_klist]");
-	return;
-
-nomem:
-	up_write(&keyring->sem);
-	kleave(" [oom]");
+	kleave("");
 }
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index ab75df4745af..df94827103d0 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -351,7 +351,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 			       struct key_user *user,
 			       struct key **_key)
 {
-	unsigned long prealloc;
+	struct assoc_array_edit *edit;
 	struct key *key;
 	key_perm_t perm;
 	key_ref_t key_ref;
@@ -380,7 +380,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
 
 	if (dest_keyring) {
-		ret = __key_link_begin(dest_keyring, &ctx->index_key, &prealloc);
+		ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit);
 		if (ret < 0)
 			goto link_prealloc_failed;
 	}
@@ -395,11 +395,11 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
 		goto key_already_present;
 
 	if (dest_keyring)
-		__key_link(dest_keyring, key, &prealloc);
+		__key_link(key, &edit);
 
 	mutex_unlock(&key_construction_mutex);
 	if (dest_keyring)
-		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
 	mutex_unlock(&user->cons_lock);
 	*_key = key;
 	kleave(" = 0 [%d]", key_serial(key));
@@ -414,8 +414,8 @@ key_already_present:
 	if (dest_keyring) {
 		ret = __key_link_check_live_key(dest_keyring, key);
 		if (ret == 0)
-			__key_link(dest_keyring, key, &prealloc);
-		__key_link_end(dest_keyring, &ctx->index_key, prealloc);
+			__key_link(key, &edit);
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
 		if (ret < 0)
 			goto link_check_failed;
 	}
-- 
cgit 


From ab3c3587f8cda9083209a61dbe3a4407d3cada10 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:18 +0100
Subject: KEYS: Implement a big key type that can save to tmpfs

Implement a big key type that can save its contents to tmpfs and thus
swapspace when memory is tight.  This is useful for Kerberos ticket caches.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Simo Sorce <simo@redhat.com>
---
 include/keys/big_key-type.h |  25 ++++++
 include/linux/key.h         |   1 +
 security/keys/Kconfig       |  11 +++
 security/keys/Makefile      |   1 +
 security/keys/big_key.c     | 204 ++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 242 insertions(+)
 create mode 100644 include/keys/big_key-type.h
 create mode 100644 security/keys/big_key.c

(limited to 'include')

diff --git a/include/keys/big_key-type.h b/include/keys/big_key-type.h
new file mode 100644
index 000000000000..d69bc8af3292
--- /dev/null
+++ b/include/keys/big_key-type.h
@@ -0,0 +1,25 @@
+/* Big capacity key type.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _KEYS_BIG_KEY_TYPE_H
+#define _KEYS_BIG_KEY_TYPE_H
+
+#include <linux/key-type.h>
+
+extern struct key_type key_type_big_key;
+
+extern int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep);
+extern void big_key_revoke(struct key *key);
+extern void big_key_destroy(struct key *key);
+extern void big_key_describe(const struct key *big_key, struct seq_file *m);
+extern long big_key_read(const struct key *key, char __user *buffer, size_t buflen);
+
+#endif /* _KEYS_BIG_KEY_TYPE_H */
diff --git a/include/linux/key.h b/include/linux/key.h
index 2417f789d29b..010dbb618aca 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -201,6 +201,7 @@ struct key {
 			unsigned long		value;
 			void __rcu		*rcudata;
 			void			*data;
+			void			*data2[2];
 		} payload;
 		struct assoc_array keys;
 	};
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index 15e0dfe8c80f..b56362275ec8 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -20,6 +20,17 @@ config KEYS
 
 	  If you are unsure as to whether this is required, answer N.
 
+config BIG_KEYS
+	tristate "Large payload keys"
+	depends on KEYS
+	depends on TMPFS
+	help
+	  This option provides support for holding large keys within the kernel
+	  (for example Kerberos ticket caches).  The data may be stored out to
+	  swapspace by tmpfs.
+
+	  If you are unsure as to whether this is required, answer N.
+
 config TRUSTED_KEYS
 	tristate "TRUSTED KEYS"
 	depends on KEYS && TCG_TPM
diff --git a/security/keys/Makefile b/security/keys/Makefile
index 504aaa008388..c487c77a00be 100644
--- a/security/keys/Makefile
+++ b/security/keys/Makefile
@@ -22,5 +22,6 @@ obj-$(CONFIG_SYSCTL) += sysctl.o
 #
 # Key types
 #
+obj-$(CONFIG_BIG_KEYS) += big_key.o
 obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
 obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
new file mode 100644
index 000000000000..5f9defc4a807
--- /dev/null
+++ b/security/keys/big_key.c
@@ -0,0 +1,204 @@
+/* Large capacity key type
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+
+MODULE_LICENSE("GPL");
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+	.name			= "big_key",
+	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+	.instantiate		= big_key_instantiate,
+	.match			= user_match,
+	.revoke			= big_key_revoke,
+	.destroy		= big_key_destroy,
+	.describe		= big_key_describe,
+	.read			= big_key_read,
+};
+
+/*
+ * Instantiate a big key
+ */
+int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct path *path = (struct path *)&key->payload.data2;
+	struct file *file;
+	ssize_t written;
+	size_t datalen = prep->datalen;
+	int ret;
+
+	ret = -EINVAL;
+	if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data)
+		goto error;
+
+	/* Set an arbitrary quota */
+	ret = key_payload_reserve(key, 16);
+	if (ret < 0)
+		goto error;
+
+	key->type_data.x[1] = datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		/* Create a shmem file to store the data in.  This will permit the data
+		 * to be swapped out if needed.
+		 *
+		 * TODO: Encrypt the stored data with a temporary key.
+		 */
+		file = shmem_file_setup("", datalen, 0);
+		if (IS_ERR(file))
+			goto err_quota;
+
+		written = kernel_write(file, prep->data, prep->datalen, 0);
+		if (written != datalen) {
+			if (written >= 0)
+				ret = -ENOMEM;
+			goto err_fput;
+		}
+
+		/* Pin the mount and dentry to the key so that we can open it again
+		 * later
+		 */
+		*path = file->f_path;
+		path_get(path);
+		fput(file);
+	} else {
+		/* Just store the data in a buffer */
+		void *data = kmalloc(datalen, GFP_KERNEL);
+		if (!data) {
+			ret = -ENOMEM;
+			goto err_quota;
+		}
+
+		key->payload.data = memcpy(data, prep->data, prep->datalen);
+	}
+	return 0;
+
+err_fput:
+	fput(file);
+err_quota:
+	key_payload_reserve(key, 0);
+error:
+	return ret;
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+	struct path *path = (struct path *)&key->payload.data2;
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+	if (key_is_instantiated(key) && key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD)
+		vfs_truncate(path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+	if (key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		path_put(path);
+		path->mnt = NULL;
+		path->dentry = NULL;
+	} else {
+		kfree(key->payload.data);
+		key->payload.data = NULL;
+	}
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+	unsigned long datalen = key->type_data.x[1];
+
+	seq_puts(m, key->description);
+
+	if (key_is_instantiated(key))
+		seq_printf(m, ": %lu [%s]",
+			   datalen,
+			   datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
+{
+	unsigned long datalen = key->type_data.x[1];
+	long ret;
+
+	if (!buffer || buflen < datalen)
+		return datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		struct file *file;
+		loff_t pos;
+
+		file = dentry_open(path, O_RDONLY, current_cred());
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+
+		pos = 0;
+		ret = vfs_read(file, buffer, datalen, &pos);
+		fput(file);
+		if (ret >= 0 && ret != datalen)
+			ret = -EIO;
+	} else {
+		ret = datalen;
+		if (copy_to_user(buffer, key->payload.data, datalen) != 0)
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+/*
+ * Module stuff
+ */
+static int __init big_key_init(void)
+{
+	return register_key_type(&key_type_big_key);
+}
+
+static void __exit big_key_cleanup(void)
+{
+	unregister_key_type(&key_type_big_key);
+}
+
+module_init(big_key_init);
+module_exit(big_key_cleanup);
-- 
cgit 


From f36f8c75ae2e7d4da34f4c908cebdb4aa42c977e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 24 Sep 2013 10:35:19 +0100
Subject: KEYS: Add per-user_namespace registers for persistent per-UID
 kerberos caches

Add support for per-user_namespace registers of persistent per-UID kerberos
caches held within the kernel.

This allows the kerberos cache to be retained beyond the life of all a user's
processes so that the user's cron jobs can work.

The kerberos cache is envisioned as a keyring/key tree looking something like:

	struct user_namespace
	  \___ .krb_cache keyring		- The register
		\___ _krb.0 keyring		- Root's Kerberos cache
		\___ _krb.5000 keyring		- User 5000's Kerberos cache
		\___ _krb.5001 keyring		- User 5001's Kerberos cache
			\___ tkt785 big_key	- A ccache blob
			\___ tkt12345 big_key	- Another ccache blob

Or possibly:

	struct user_namespace
	  \___ .krb_cache keyring		- The register
		\___ _krb.0 keyring		- Root's Kerberos cache
		\___ _krb.5000 keyring		- User 5000's Kerberos cache
		\___ _krb.5001 keyring		- User 5001's Kerberos cache
			\___ tkt785 keyring	- A ccache
				\___ krbtgt/REDHAT.COM@REDHAT.COM big_key
				\___ http/REDHAT.COM@REDHAT.COM user
				\___ afs/REDHAT.COM@REDHAT.COM user
				\___ nfs/REDHAT.COM@REDHAT.COM user
				\___ krbtgt/KERNEL.ORG@KERNEL.ORG big_key
				\___ http/KERNEL.ORG@KERNEL.ORG big_key

What goes into a particular Kerberos cache is entirely up to userspace.  Kernel
support is limited to giving you the Kerberos cache keyring that you want.

The user asks for their Kerberos cache by:

	krb_cache = keyctl_get_krbcache(uid, dest_keyring);

The uid is -1 or the user's own UID for the user's own cache or the uid of some
other user's cache (requires CAP_SETUID).  This permits rpc.gssd or whatever to
mess with the cache.

The cache returned is a keyring named "_krb.<uid>" that the possessor can read,
search, clear, invalidate, unlink from and add links to.  Active LSMs get a
chance to rule on whether the caller is permitted to make a link.

Each uid's cache keyring is created when it first accessed and is given a
timeout that is extended each time this function is called so that the keyring
goes away after a while.  The timeout is configurable by sysctl but defaults to
three days.

Each user_namespace struct gets a lazily-created keyring that serves as the
register.  The cache keyrings are added to it.  This means that standard key
search and garbage collection facilities are available.

The user_namespace struct's register goes away when it does and anything left
in it is then automatically gc'd.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Simo Sorce <simo@redhat.com>
cc: Serge E. Hallyn <serge.hallyn@ubuntu.com>
cc: Eric W. Biederman <ebiederm@xmission.com>
---
 include/linux/user_namespace.h |   6 ++
 include/uapi/linux/keyctl.h    |   1 +
 kernel/user.c                  |   4 +
 kernel/user_namespace.c        |   6 ++
 security/keys/Kconfig          |  17 +++++
 security/keys/Makefile         |   1 +
 security/keys/compat.c         |   3 +
 security/keys/internal.h       |   9 +++
 security/keys/keyctl.c         |   3 +
 security/keys/persistent.c     | 169 +++++++++++++++++++++++++++++++++++++++++
 security/keys/sysctl.c         |  11 +++
 11 files changed, 230 insertions(+)
 create mode 100644 security/keys/persistent.c

(limited to 'include')

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4db29859464f..4836ba3c1cd8 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -27,6 +27,12 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+
+	/* Register of per-UID persistent keyrings for this namespace */
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	struct key		*persistent_keyring_register;
+	struct rw_semaphore	persistent_keyring_register_sem;
+#endif
 };
 
 extern struct user_namespace init_user_ns;
diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h
index c9b7f4faf97a..840cb990abe2 100644
--- a/include/uapi/linux/keyctl.h
+++ b/include/uapi/linux/keyctl.h
@@ -56,5 +56,6 @@
 #define KEYCTL_REJECT			19	/* reject a partially constructed key */
 #define KEYCTL_INSTANTIATE_IOV		20	/* instantiate a partially constructed key */
 #define KEYCTL_INVALIDATE		21	/* invalidate a key */
+#define KEYCTL_GET_PERSISTENT		22	/* get a user's persistent keyring */
 
 #endif /*  _LINUX_KEYCTL_H */
diff --git a/kernel/user.c b/kernel/user.c
index 5bbb91988e69..a3a0dbfda329 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,10 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_KEYS_KERBEROS_CACHE
+	.krb_cache_register_sem =
+	__RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 13fb1134ba58..240fb62cf394 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -101,6 +101,9 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	init_rwsem(&ns->persistent_keyring_register_sem);
+#endif
 	return 0;
 }
 
@@ -130,6 +133,9 @@ void free_user_ns(struct user_namespace *ns)
 
 	do {
 		parent = ns->parent;
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+		key_put(ns->persistent_keyring_register);
+#endif
 		proc_free_inum(ns->proc_inum);
 		kmem_cache_free(user_ns_cachep, ns);
 		ns = parent;
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index b56362275ec8..53d8748c9564 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -20,6 +20,23 @@ config KEYS
 
 	  If you are unsure as to whether this is required, answer N.
 
+config PERSISTENT_KEYRINGS
+	bool "Enable register of persistent per-UID keyrings"
+	depends on KEYS
+	help
+	  This option provides a register of persistent per-UID keyrings,
+	  primarily aimed at Kerberos key storage.  The keyrings are persistent
+	  in the sense that they stay around after all processes of that UID
+	  have exited, not that they survive the machine being rebooted.
+
+	  A particular keyring may be accessed by either the user whose keyring
+	  it is or by a process with administrative privileges.  The active
+	  LSMs gets to rule on which admin-level processes get to access the
+	  cache.
+
+	  Keyrings are created and added into the register upon demand and get
+	  removed if they expire (a default timeout is set upon creation).
+
 config BIG_KEYS
 	tristate "Large payload keys"
 	depends on KEYS
diff --git a/security/keys/Makefile b/security/keys/Makefile
index c487c77a00be..dfb3a7bededf 100644
--- a/security/keys/Makefile
+++ b/security/keys/Makefile
@@ -18,6 +18,7 @@ obj-y := \
 obj-$(CONFIG_KEYS_COMPAT) += compat.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_SYSCTL) += sysctl.o
+obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o
 
 #
 # Key types
diff --git a/security/keys/compat.c b/security/keys/compat.c
index d65fa7fa29ba..bbd32c729dbb 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -138,6 +138,9 @@ asmlinkage long compat_sys_keyctl(u32 option,
 	case KEYCTL_INVALIDATE:
 		return keyctl_invalidate_key(arg2);
 
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent(arg2, arg3);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 581c6f688352..80b2aac4f50c 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -255,6 +255,15 @@ extern long keyctl_invalidate_key(key_serial_t);
 extern long keyctl_instantiate_key_common(key_serial_t,
 					  const struct iovec *,
 					  unsigned, size_t, key_serial_t);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+extern long keyctl_get_persistent(uid_t, key_serial_t);
+extern unsigned persistent_keyring_expiry;
+#else
+static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
+{
+	return -EOPNOTSUPP;
+}
+#endif
 
 /*
  * Debugging key validation
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 33cfd27b4de2..cee72ce64222 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1667,6 +1667,9 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case KEYCTL_INVALIDATE:
 		return keyctl_invalidate_key((key_serial_t) arg2);
 
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent((uid_t)arg2, (key_serial_t)arg3);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/security/keys/persistent.c b/security/keys/persistent.c
new file mode 100644
index 000000000000..82f4957a7acf
--- /dev/null
+++ b/security/keys/persistent.c
@@ -0,0 +1,169 @@
+/* General persistent per-UID keyrings register
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
+
+/*
+ * Create the persistent keyring register for the current user namespace.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static int key_create_persistent_register(struct user_namespace *ns)
+{
+	struct key *reg = keyring_alloc(".persistent_register",
+					KUIDT_INIT(0), KGIDT_INIT(0),
+					current_cred(),
+					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					 KEY_USR_VIEW | KEY_USR_READ),
+					KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	ns->persistent_keyring_register = reg;
+	return 0;
+}
+
+/*
+ * Create the persistent keyring for the specified user.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid,
+				       struct keyring_index_key *index_key)
+{
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+
+	if (!ns->persistent_keyring_register) {
+		long err = key_create_persistent_register(ns);
+		if (err < 0)
+			return ERR_PTR(err);
+	} else {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		persistent_ref = find_key_to_update(reg_ref, index_key);
+		if (persistent_ref)
+			return persistent_ref;
+	}
+
+	persistent = keyring_alloc(index_key->description,
+				   uid, INVALID_GID, current_cred(),
+				   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				    KEY_USR_VIEW | KEY_USR_READ),
+				   KEY_ALLOC_NOT_IN_QUOTA,
+				   ns->persistent_keyring_register);
+	if (IS_ERR(persistent))
+		return ERR_CAST(persistent);
+
+	return make_key_ref(persistent, true);
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
+			       key_ref_t dest_ref)
+{
+	struct keyring_index_key index_key;
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+	char buf[32];
+	long ret;
+
+	/* Look in the register if it exists */
+	index_key.type = &key_type_keyring;
+	index_key.description = buf;
+	index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid));
+
+	if (ns->persistent_keyring_register) {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		down_read(&ns->persistent_keyring_register_sem);
+		persistent_ref = find_key_to_update(reg_ref, &index_key);
+		up_read(&ns->persistent_keyring_register_sem);
+
+		if (persistent_ref)
+			goto found;
+	}
+
+	/* It wasn't in the register, so we'll need to create it.  We might
+	 * also need to create the register.
+	 */
+	down_write(&ns->persistent_keyring_register_sem);
+	persistent_ref = key_create_persistent(ns, uid, &index_key);
+	up_write(&ns->persistent_keyring_register_sem);
+	if (!IS_ERR(persistent_ref))
+		goto found;
+
+	return PTR_ERR(persistent_ref);
+
+found:
+	ret = key_task_permission(persistent_ref, current_cred(), KEY_LINK);
+	if (ret == 0) {
+		persistent = key_ref_to_ptr(persistent_ref);
+		ret = key_link(key_ref_to_ptr(dest_ref), persistent);
+		if (ret == 0) {
+			key_set_timeout(persistent, persistent_keyring_expiry);
+			ret = persistent->serial;		
+		}
+	}
+
+	key_ref_put(persistent_ref);
+	return ret;
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
+{
+	struct user_namespace *ns = current_user_ns();
+	key_ref_t dest_ref;
+	kuid_t uid;
+	long ret;
+
+	/* -1 indicates the current user */
+	if (_uid == (uid_t)-1) {
+		uid = current_uid();
+	} else {
+		uid = make_kuid(ns, _uid);
+		if (!uid_valid(uid))
+			return -EINVAL;
+
+		/* You can only see your own persistent cache if you're not
+		 * sufficiently privileged.
+		 */
+		if (uid_eq(uid, current_uid()) &&
+		    uid_eq(uid, current_suid()) &&
+		    uid_eq(uid, current_euid()) &&
+		    uid_eq(uid, current_fsuid()) &&
+		    !ns_capable(ns, CAP_SETUID))
+			return -EPERM;
+	}
+
+	/* There must be a destination keyring */
+	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	if (IS_ERR(dest_ref))
+		return PTR_ERR(dest_ref);
+	if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
+		ret = -ENOTDIR;
+		goto out_put_dest;
+	}
+
+	ret = key_get_persistent(ns, uid, dest_ref);
+
+out_put_dest:
+	key_ref_put(dest_ref);
+	return ret;
+}
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
index ee32d181764a..8c0af08760c8 100644
--- a/security/keys/sysctl.c
+++ b/security/keys/sysctl.c
@@ -61,5 +61,16 @@ ctl_table key_sysctls[] = {
 		.extra1 = (void *) &zero,
 		.extra2 = (void *) &max,
 	},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	{
+		.procname = "persistent_keyring_expiry",
+		.data = &persistent_keyring_expiry,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &zero,
+		.extra2 = (void *) &max,
+	},
+#endif
 	{ }
 };
-- 
cgit 


From 7f6db1717235bd45d265766dad53c10d30899d41 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuah.kh@samsung.com>
Date: Thu, 15 Aug 2013 11:59:23 -0600
Subject: iommu: Add event tracing feature to iommu

Add tracing feature to iommu to report various iommu events. Classes
iommu_group, iommu_device, and iommu_map_unmap are defined.

iommu_group class events can be enabled to trigger when devices get added
to and removed from an iommu group. Trace information includes iommu group
id and device name.

iommu:add_device_to_group
iommu:remove_device_from_group

iommu_device class events can be enabled to trigger when devices are attached
to and detached from a domain. Trace information includes device name.

iommu:attach_device_to_domain
iommu:detach_device_from_domain

iommu_map_unmap class events can be enabled to trigger when iommu map and
unmap iommu ops. Trace information includes iova, physical address (map event
only), and size.

iommu:map
iommu:unmap

Signed-off-by: Shuah Khan <shuah.kh@samsung.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/Makefile       |   1 +
 drivers/iommu/iommu-traces.c |  24 ++++++++
 drivers/iommu/iommu.c        |   1 +
 include/trace/events/iommu.h | 129 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 155 insertions(+)
 create mode 100644 drivers/iommu/iommu-traces.c
 create mode 100644 include/trace/events/iommu.h

(limited to 'include')

diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 14c1f474cf11..5d58bf16e9e3 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
+obj-$(CONFIG_IOMMU_API) += iommu-traces.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c
new file mode 100644
index 000000000000..a2af60f31810
--- /dev/null
+++ b/drivers/iommu/iommu-traces.c
@@ -0,0 +1,24 @@
+/*
+ * iommu trace points
+ *
+ * Copyright (C) 2013 Shuah Khan <shuah.kh@samsung.com>
+ *
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/iommu.h>
+
+/* iommu_group_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(add_device_to_group);
+EXPORT_TRACEPOINT_SYMBOL_GPL(remove_device_from_group);
+
+/* iommu_device_event */
+EXPORT_TRACEPOINT_SYMBOL_GPL(attach_device_to_domain);
+EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain);
+
+/* iommu_map_unmap */
+EXPORT_TRACEPOINT_SYMBOL_GPL(map);
+EXPORT_TRACEPOINT_SYMBOL_GPL(unmap);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index fbe9ca734f8f..58f6a16b2e1a 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -29,6 +29,7 @@
 #include <linux/idr.h>
 #include <linux/notifier.h>
 #include <linux/err.h>
+#include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
 static struct ida iommu_group_ida;
diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h
new file mode 100644
index 000000000000..86bcc5a9fedc
--- /dev/null
+++ b/include/trace/events/iommu.h
@@ -0,0 +1,129 @@
+/*
+ * iommu trace points
+ *
+ * Copyright (C) 2013 Shuah Khan <shuah.kh@samsung.com>
+ *
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iommu
+
+#if !defined(_TRACE_IOMMU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IOMMU_H
+
+#include <linux/tracepoint.h>
+#include <linux/pci.h>
+
+struct device;
+
+DECLARE_EVENT_CLASS(iommu_group_event,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev),
+
+	TP_STRUCT__entry(
+		__field(int, gid)
+		__string(device, dev_name(dev))
+	),
+
+	TP_fast_assign(
+		__entry->gid = group_id;
+		__assign_str(device, dev_name(dev));
+	),
+
+	TP_printk("IOMMU: groupID=%d device=%s",
+			__entry->gid, __get_str(device)
+	)
+);
+
+DEFINE_EVENT(iommu_group_event, add_device_to_group,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev)
+
+);
+
+DEFINE_EVENT(iommu_group_event, remove_device_from_group,
+
+	TP_PROTO(int group_id, struct device *dev),
+
+	TP_ARGS(group_id, dev)
+);
+
+DECLARE_EVENT_CLASS(iommu_device_event,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+	),
+
+	TP_fast_assign(
+		__assign_str(device, dev_name(dev));
+	),
+
+	TP_printk("IOMMU: device=%s", __get_str(device)
+	)
+);
+
+DEFINE_EVENT(iommu_device_event, attach_device_to_domain,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev)
+);
+
+DEFINE_EVENT(iommu_device_event, detach_device_from_domain,
+
+	TP_PROTO(struct device *dev),
+
+	TP_ARGS(dev)
+);
+
+DECLARE_EVENT_CLASS(iommu_map_unmap,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size),
+
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(u64, paddr)
+		__field(int, size)
+	),
+
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->paddr = paddr;
+		__entry->size = size;
+	),
+
+	TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=0x%x",
+			__entry->iova, __entry->paddr, __entry->size
+	)
+);
+
+DEFINE_EVENT(iommu_map_unmap, map,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size)
+);
+
+DEFINE_EVENT_PRINT(iommu_map_unmap, unmap,
+
+	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+
+	TP_ARGS(iova, paddr, size),
+
+	TP_printk("IOMMU: iova=0x%016llx size=0x%x",
+			__entry->iova, __entry->size
+	)
+);
+#endif /* _TRACE_IOMMU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit 


From 8c27bd75f04fb9cb70c69c3cfe24f4e6d8e15906 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 20 Sep 2013 22:32:55 +0200
Subject: tcp: syncookies: reduce cookie lifetime to 128 seconds

We currently accept cookies that were created less than 4 minutes ago
(ie, cookies with counter delta 0-3).  Combined with the 8 mss table
values, this yields 32 possible values (out of 2**32) that will be valid.

Reducing the lifetime to < 2 minutes halves the guessing chance while
still providing a large enough period.

While at it, get rid of jiffies value -- they overflow too quickly on
32 bit platforms.

getnstimeofday is used to create a counter that increments every 64s.
perf shows getnstimeofday cost is negible compared to sha_transform;
normal tcp initial sequence number generation uses getnstimeofday, too.

Reported-by: Jakob Lell <jakob@jakoblell.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 18 ++++++++++++++++++
 net/ipv4/syncookies.c | 31 ++++++++++---------------------
 net/ipv6/syncookies.c | 24 +++++++-----------------
 3 files changed, 35 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0e47551e9bdb..de870ee5582d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -481,6 +481,24 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt);
 #ifdef CONFIG_SYN_COOKIES
+#include <linux/ktime.h>
+
+/* Syncookies use a monotonic timer which increments every 64 seconds.
+ * This counter is used both as a hash input and partially encoded into
+ * the cookie value.  A cookie is only validated further if the delta
+ * between the current counter value and the encoded one is less than this,
+ * i.e. a sent cookie is valid only at most for 128 seconds (or less if
+ * the counter advances immediately after a cookie is generated).
+ */
+#define MAX_SYNCOOKIE_AGE 2
+
+static inline u32 tcp_cookie_time(void)
+{
+	struct timespec now;
+	getnstimeofday(&now);
+	return now.tv_sec >> 6; /* 64 seconds granularity */
+}
+
 u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 			      u16 *mssp);
 __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mss);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 14a15c49129d..b6ea2979a2b7 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -89,8 +89,7 @@ __u32 cookie_init_timestamp(struct request_sock *req)
 
 
 static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
-				   __be16 dport, __u32 sseq, __u32 count,
-				   __u32 data)
+				   __be16 dport, __u32 sseq, __u32 data)
 {
 	/*
 	 * Compute the secure sequence number.
@@ -102,7 +101,7 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
 	 * As an extra hack, we add a small "data" value that encodes the
 	 * MSS into the second hash value.
 	 */
-
+	u32 count = tcp_cookie_time();
 	return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
 		sseq + (count << COOKIEBITS) +
 		((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -114,22 +113,21 @@ static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
  * If the syncookie is bad, the data returned will be out of
  * range.  This must be checked by the caller.
  *
- * The count value used to generate the cookie must be within
- * "maxdiff" if the current (passed-in) "count".  The return value
- * is (__u32)-1 if this test fails.
+ * The count value used to generate the cookie must be less than
+ * MAX_SYNCOOKIE_AGE minutes in the past.
+ * The return value (__u32)-1 if this test fails.
  */
 static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
-				  __be16 sport, __be16 dport, __u32 sseq,
-				  __u32 count, __u32 maxdiff)
+				  __be16 sport, __be16 dport, __u32 sseq)
 {
-	__u32 diff;
+	u32 diff, count = tcp_cookie_time();
 
 	/* Strip away the layers from the cookie */
 	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
 
 	/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
 	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
-	if (diff >= maxdiff)
+	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
 	return (cookie -
@@ -173,7 +171,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
 
 	return secure_tcp_syn_cookie(iph->saddr, iph->daddr,
 				     th->source, th->dest, ntohl(th->seq),
-				     jiffies / (HZ * 60), mssind);
+				     mssind);
 }
 EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence);
 
@@ -188,13 +186,6 @@ __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb, __u16 *mssp)
 	return __cookie_v4_init_sequence(iph, th, mssp);
 }
 
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
 /*
  * Check if a ack sequence number is a valid syncookie.
  * Return the decoded mss if it is, or 0 if not.
@@ -204,9 +195,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 {
 	__u32 seq = ntohl(th->seq) - 1;
 	__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
-					    th->source, th->dest, seq,
-					    jiffies / (HZ * 60),
-					    COUNTER_TRIES);
+					    th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bf63ac8a49b9..13ca0a0ea680 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -36,14 +36,6 @@ static __u16 const msstab[] = {
 	9000 - 60,
 };
 
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-
 static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 					   struct request_sock *req,
 					   struct dst_entry *dst)
@@ -86,8 +78,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
 static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
 				   const struct in6_addr *daddr,
 				   __be16 sport, __be16 dport, __u32 sseq,
-				   __u32 count, __u32 data)
+				   __u32 data)
 {
+	u32 count = tcp_cookie_time();
 	return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
 		sseq + (count << COOKIEBITS) +
 		((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -96,15 +89,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
 
 static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
 				  const struct in6_addr *daddr, __be16 sport,
-				  __be16 dport, __u32 sseq, __u32 count,
-				  __u32 maxdiff)
+				  __be16 dport, __u32 sseq)
 {
-	__u32 diff;
+	__u32 diff, count = tcp_cookie_time();
 
 	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
 
 	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
-	if (diff >= maxdiff)
+	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
 	return (cookie -
@@ -125,8 +117,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
 	*mssp = msstab[mssind];
 
 	return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
-				     th->dest, ntohl(th->seq),
-				     jiffies / (HZ * 60), mssind);
+				     th->dest, ntohl(th->seq), mssind);
 }
 EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
 
@@ -146,8 +137,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
 {
 	__u32 seq = ntohl(th->seq) - 1;
 	__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
-					    th->source, th->dest, seq,
-					    jiffies / (HZ * 60), COUNTER_TRIES);
+					    th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
-- 
cgit 


From 98fda169290b3b28c0f2db2b8f02290c13da50ef Mon Sep 17 00:00:00 2001
From: Radim Krčmář <rkrcmar@redhat.com>
Date: Wed, 4 Sep 2013 22:32:24 +0200
Subject: kvm: remove .done from struct kvm_async_pf
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'.done' is used to mark the completion of 'async_pf_execute()', but
'cancel_work_sync()' returns true when the work was canceled, so we
use it instead.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 1 -
 virt/kvm/async_pf.c      | 5 +----
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0fbbc7aa02cb..749bdb12cd15 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -190,7 +190,6 @@ struct kvm_async_pf {
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
 	struct page *page;
-	bool done;
 };
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8a39dda7a325..b197950ac4d5 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -75,7 +75,6 @@ static void async_pf_execute(struct work_struct *work)
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
 	apf->page = page;
-	apf->done = true;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -99,9 +98,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 		struct kvm_async_pf *work =
 			list_entry(vcpu->async_pf.queue.next,
 				   typeof(*work), queue);
-		cancel_work_sync(&work->work);
 		list_del(&work->queue);
-		if (!work->done) { /* work was canceled */
+		if (cancel_work_sync(&work->work)) {
 			mmdrop(work->mm);
 			kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
 			kmem_cache_free(async_pf_cache, work);
@@ -166,7 +164,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 		return 0;
 
 	work->page = NULL;
-	work->done = false;
 	work->vcpu = vcpu;
 	work->gva = gva;
 	work->addr = gfn_to_hva(vcpu->kvm, gfn);
-- 
cgit 


From f1a4c52ff5913378b7baf05ac71f10282b341cf7 Mon Sep 17 00:00:00 2001
From: Philip Avinash <avinashphilip@ti.com>
Date: Sun, 18 Aug 2013 10:49:03 +0530
Subject: ARM: davinci: gpio: use gpiolib API instead of inline functions

Remove NEED_MACH_GPIO_H config select option for ARCH_DAVINCI
to start using gpiolib interface for davinci platforms. This makes
it easier to use the gpio driver on other platforms as it breaks
dependency on mach-davinci.

Latencies for gpio_get/set APIs will increase. On measurement,
latency was found to have increased by 18 microsecond with
gpiolib API as compared to inline APIs.

Measurement was done on DA850 EVM for gpio_get_value() API by
taking the printk timing across the call with interrupts disabled.

  inline gpio API with interrupt disabled
  [   29.734337] before gpio_get
  [   29.736847] after gpio_get

  Time difference 0.00251

  gpio library with interrupt disabled
  [  272.876763] before gpio_get
  [  272.879291] after gpio_get

  Time difference 0.002528
  Latency increased by (0.002528 -  0.00251) = 18 microsecond.

While at it, remove GPIO_TYPE_DAVINCI enum definition as
gpio-davinci.c is converted to Linux device driver model.

Signed-off-by: Philip Avinash <avinashphilip@ti.com>
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
[nsekhar@ti.com: minor edits to commit message]
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
---
 arch/arm/Kconfig                                  |  1 -
 arch/arm/mach-davinci/include/mach/gpio-davinci.h | 90 -----------------------
 arch/arm/mach-davinci/include/mach/gpio.h         | 88 ----------------------
 drivers/gpio/gpio-tnetv107x.c                     |  1 +
 include/linux/platform_data/gpio-davinci.h        | 35 +++++++++
 5 files changed, 36 insertions(+), 179 deletions(-)
 delete mode 100644 arch/arm/mach-davinci/include/mach/gpio-davinci.h
 delete mode 100644 arch/arm/mach-davinci/include/mach/gpio.h

(limited to 'include')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3f7714d8d2d2..ad3767095422 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -847,7 +847,6 @@ config ARCH_DAVINCI
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
 	select HAVE_IDE
-	select NEED_MACH_GPIO_H
 	select TI_PRIV_EDMA
 	select USE_OF
 	select ZONE_DMA
diff --git a/arch/arm/mach-davinci/include/mach/gpio-davinci.h b/arch/arm/mach-davinci/include/mach/gpio-davinci.h
deleted file mode 100644
index 0d63b24cefc9..000000000000
--- a/arch/arm/mach-davinci/include/mach/gpio-davinci.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * TI DaVinci GPIO Support
- *
- * Copyright (c) 2006 David Brownell
- * Copyright (c) 2007, MontaVista Software, Inc. <source@mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef	__DAVINCI_DAVINCI_GPIO_H
-#define	__DAVINCI_DAVINCI_GPIO_H
-
-#include <linux/io.h>
-#include <linux/spinlock.h>
-
-#include <asm-generic/gpio.h>
-
-#include <mach/irqs.h>
-#include <mach/common.h>
-
-enum davinci_gpio_type {
-	GPIO_TYPE_DAVINCI = 0,
-	GPIO_TYPE_TNETV107X,
-};
-
-/*
- * basic gpio routines
- *
- * board-specific init should be done by arch/.../.../board-XXX.c (maybe
- * initializing banks together) rather than boot loaders; kexec() won't
- * go through boot loaders.
- *
- * the gpio clock will be turned on when gpios are used, and you may also
- * need to pay attention to PINMUX registers to be sure those pins are
- * used as gpios, not with other peripherals.
- *
- * On-chip GPIOs are numbered 0..(DAVINCI_N_GPIO-1).  For documentation,
- * and maybe for later updates, code may write GPIO(N).  These may be
- * all 1.8V signals, all 3.3V ones, or a mix of the two.  A given chip
- * may not support all the GPIOs in that range.
- *
- * GPIOs can also be on external chips, numbered after the ones built-in
- * to the DaVinci chip.  For now, they won't be usable as IRQ sources.
- */
-#define	GPIO(X)		(X)		/* 0 <= X <= (DAVINCI_N_GPIO - 1) */
-
-/* Convert GPIO signal to GPIO pin number */
-#define GPIO_TO_PIN(bank, gpio)	(16 * (bank) + (gpio))
-
-struct davinci_gpio_controller {
-	struct gpio_chip	chip;
-	int			irq_base;
-	spinlock_t		lock;
-	void __iomem		*regs;
-	void __iomem		*set_data;
-	void __iomem		*clr_data;
-	void __iomem		*in_data;
-	unsigned		gpio_irq;
-};
-
-/* The __gpio_to_controller() and __gpio_mask() functions inline to constants
- * with constant parameters; or in outlined code they execute at runtime.
- *
- * You'd access the controller directly when reading or writing more than
- * one gpio value at a time, and to support wired logic where the value
- * being driven by the cpu need not match the value read back.
- *
- * These are NOT part of the cross-platform GPIO interface
- */
-static inline struct davinci_gpio_controller *
-__gpio_to_controller(unsigned gpio)
-{
-	struct davinci_gpio_controller *ctlrs = davinci_soc_info.gpio_ctlrs;
-	int index = gpio / 32;
-
-	if (!ctlrs || index >= davinci_soc_info.gpio_ctlrs_num)
-		return NULL;
-
-	return ctlrs + index;
-}
-
-static inline u32 __gpio_mask(unsigned gpio)
-{
-	return 1 << (gpio % 32);
-}
-
-#endif	/* __DAVINCI_DAVINCI_GPIO_H */
diff --git a/arch/arm/mach-davinci/include/mach/gpio.h b/arch/arm/mach-davinci/include/mach/gpio.h
deleted file mode 100644
index 960e9de47e1e..000000000000
--- a/arch/arm/mach-davinci/include/mach/gpio.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * TI DaVinci GPIO Support
- *
- * Copyright (c) 2006 David Brownell
- * Copyright (c) 2007, MontaVista Software, Inc. <source@mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef	__DAVINCI_GPIO_H
-#define	__DAVINCI_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#define __ARM_GPIOLIB_COMPLEX
-
-/* The inline versions use the static inlines in the driver header */
-#include "gpio-davinci.h"
-
-/*
- * The get/set/clear functions will inline when called with constant
- * parameters referencing built-in GPIOs, for low-overhead bitbanging.
- *
- * gpio_set_value() will inline only on traditional Davinci style controllers
- * with distinct set/clear registers.
- *
- * Otherwise, calls with variable parameters or referencing external
- * GPIOs (e.g. on GPIO expander chips) use outlined functions.
- */
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-	if (__builtin_constant_p(value) && gpio < davinci_soc_info.gpio_num) {
-		struct davinci_gpio_controller *ctlr;
-		u32				mask;
-
-		ctlr = __gpio_to_controller(gpio);
-
-		if (ctlr->set_data != ctlr->clr_data) {
-			mask = __gpio_mask(gpio);
-			if (value)
-				__raw_writel(mask, ctlr->set_data);
-			else
-				__raw_writel(mask, ctlr->clr_data);
-			return;
-		}
-	}
-
-	__gpio_set_value(gpio, value);
-}
-
-/* Returns zero or nonzero; works for gpios configured as inputs OR
- * as outputs, at least for built-in GPIOs.
- *
- * NOTE: for built-in GPIOs, changes in reported values are synchronized
- * to the GPIO clock.  This is easily seen after calling gpio_set_value()
- * and then immediately gpio_get_value(), where the gpio_get_value() will
- * return the old value until the GPIO clock ticks and the new value gets
- * latched.
- */
-static inline int gpio_get_value(unsigned gpio)
-{
-	struct davinci_gpio_controller *ctlr;
-
-	if (!__builtin_constant_p(gpio) || gpio >= davinci_soc_info.gpio_num)
-		return __gpio_get_value(gpio);
-
-	ctlr = __gpio_to_controller(gpio);
-	return __gpio_mask(gpio) & __raw_readl(ctlr->in_data);
-}
-
-static inline int gpio_cansleep(unsigned gpio)
-{
-	if (__builtin_constant_p(gpio) && gpio < davinci_soc_info.gpio_num)
-		return 0;
-	else
-		return __gpio_cansleep(gpio);
-}
-
-static inline int irq_to_gpio(unsigned irq)
-{
-	/* don't support the reverse mapping */
-	return -ENOSYS;
-}
-
-#endif				/* __DAVINCI_GPIO_H */
diff --git a/drivers/gpio/gpio-tnetv107x.c b/drivers/gpio/gpio-tnetv107x.c
index 3fa3e2867e19..58445bb69106 100644
--- a/drivers/gpio/gpio-tnetv107x.c
+++ b/drivers/gpio/gpio-tnetv107x.c
@@ -15,6 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
+#include <linux/platform_data/gpio-davinci.h>
 
 #include <mach/common.h>
 #include <mach/tnetv107x.h>
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
index 2fcc125af1aa..6efd20264585 100644
--- a/include/linux/platform_data/gpio-davinci.h
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -16,10 +16,45 @@
 #ifndef __DAVINCI_GPIO_PLATFORM_H
 #define __DAVINCI_GPIO_PLATFORM_H
 
+#include <linux/io.h>
+#include <linux/spinlock.h>
+
+#include <asm-generic/gpio.h>
+
+enum davinci_gpio_type {
+	GPIO_TYPE_TNETV107X = 0,
+};
+
 struct davinci_gpio_platform_data {
 	u32	ngpio;
 	u32	gpio_unbanked;
 	u32	intc_irq_num;
 };
 
+
+struct davinci_gpio_controller {
+	struct gpio_chip	chip;
+	int			irq_base;
+	/* Serialize access to GPIO registers */
+	spinlock_t		lock;
+	void __iomem		*regs;
+	void __iomem		*set_data;
+	void __iomem		*clr_data;
+	void __iomem		*in_data;
+	int			gpio_unbanked;
+	unsigned		gpio_irq;
+};
+
+/*
+ * basic gpio routines
+ */
+#define	GPIO(X)		(X)	/* 0 <= X <= (DAVINCI_N_GPIO - 1) */
+
+/* Convert GPIO signal to GPIO pin number */
+#define GPIO_TO_PIN(bank, gpio)	(16 * (bank) + (gpio))
+
+static inline u32 __gpio_mask(unsigned gpio)
+{
+	return 1 << (gpio % 32);
+}
 #endif
-- 
cgit 


From d8eb18eecaf358e37f4941c2b8cba3c4b8122b7f Mon Sep 17 00:00:00 2001
From: Arron Wang <arron.wang@intel.com>
Date: Fri, 23 Aug 2013 16:02:08 +0800
Subject: NFC: Export nfc_find_se()

This will be needed by all NFC driver implementing the SE ops.

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nfc.h | 1 +
 net/nfc/core.c        | 9 +++++----
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index f68ee68e4e3e..e34859423105 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -243,5 +243,6 @@ void nfc_driver_failure(struct nfc_dev *dev, int err);
 
 int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type);
 int nfc_remove_se(struct nfc_dev *dev, u32 se_idx);
+struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx);
 
 #endif /* __NET_NFC_H */
diff --git a/net/nfc/core.c b/net/nfc/core.c
index e92923cf3e03..269ffc5288d0 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -536,7 +536,7 @@ error:
 	return rc;
 }
 
-static struct nfc_se *find_se(struct nfc_dev *dev, u32 se_idx)
+struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx)
 {
 	struct nfc_se *se, *n;
 
@@ -546,6 +546,7 @@ static struct nfc_se *find_se(struct nfc_dev *dev, u32 se_idx)
 
 	return NULL;
 }
+EXPORT_SYMBOL(nfc_find_se);
 
 int nfc_enable_se(struct nfc_dev *dev, u32 se_idx)
 {
@@ -577,7 +578,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx)
 		goto error;
 	}
 
-	se = find_se(dev, se_idx);
+	se = nfc_find_se(dev, se_idx);
 	if (!se) {
 		rc = -EINVAL;
 		goto error;
@@ -622,7 +623,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx)
 		goto error;
 	}
 
-	se = find_se(dev, se_idx);
+	se = nfc_find_se(dev, se_idx);
 	if (!se) {
 		rc = -EINVAL;
 		goto error;
@@ -881,7 +882,7 @@ int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type)
 
 	pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx);
 
-	se = find_se(dev, se_idx);
+	se = nfc_find_se(dev, se_idx);
 	if (se)
 		return -EALREADY;
 
-- 
cgit 


From b48348395ff665f49c7c684c93c5ce09fd0a0307 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 5 Apr 2013 12:27:37 -0700
Subject: NFC: Replace nfc_dev_dbg with dev_dbg

Use the generic kernel function instead of a home-grown
one that does the same thing.

Add \n to uses not at the macro.  Don't add \n where
the nfc_dev_dbg macro mistakenly had them already.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/nfcsim.c    |  24 ++++-----
 drivers/nfc/nfcwilink.c |  51 ++++++------------
 drivers/nfc/pn533.c     | 137 ++++++++++++++++++++++--------------------------
 include/net/nfc/nfc.h   |   1 -
 4 files changed, 91 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c
index 9a53f13c88df..4a614794ea61 100644
--- a/drivers/nfc/nfcsim.c
+++ b/drivers/nfc/nfcsim.c
@@ -22,7 +22,7 @@
 #define DEV_ERR(_dev, fmt, args...) nfc_dev_err(&_dev->nfc_dev->dev, \
 						"%s: " fmt, __func__, ## args)
 
-#define DEV_DBG(_dev, fmt, args...) nfc_dev_dbg(&_dev->nfc_dev->dev, \
+#define DEV_DBG(_dev, fmt, args...) dev_dbg(&_dev->nfc_dev->dev, \
 						"%s: " fmt, __func__, ## args)
 
 #define NFCSIM_VERSION "0.1"
@@ -64,7 +64,7 @@ static struct workqueue_struct *wq;
 
 static void nfcsim_cleanup_dev(struct nfcsim *dev, u8 shutdown)
 {
-	DEV_DBG(dev, "shutdown=%d", shutdown);
+	DEV_DBG(dev, "shutdown=%d\n", shutdown);
 
 	mutex_lock(&dev->lock);
 
@@ -84,7 +84,7 @@ static int nfcsim_target_found(struct nfcsim *dev)
 {
 	struct nfc_target nfc_tgt;
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 
 	memset(&nfc_tgt, 0, sizeof(struct nfc_target));
 
@@ -98,7 +98,7 @@ static int nfcsim_dev_up(struct nfc_dev *nfc_dev)
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 
 	mutex_lock(&dev->lock);
 
@@ -113,7 +113,7 @@ static int nfcsim_dev_down(struct nfc_dev *nfc_dev)
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 
 	mutex_lock(&dev->lock);
 
@@ -172,7 +172,7 @@ static int nfcsim_dep_link_down(struct nfc_dev *nfc_dev)
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 
 	nfcsim_cleanup_dev(dev, 0);
 
@@ -210,7 +210,7 @@ static int nfcsim_start_poll(struct nfc_dev *nfc_dev,
 
 	queue_delayed_work(wq, &dev->poll_work, 0);
 
-	DEV_DBG(dev, "Start polling: im: 0x%X, tm: 0x%X", im_protocols,
+	DEV_DBG(dev, "Start polling: im: 0x%X, tm: 0x%X\n", im_protocols,
 		tm_protocols);
 
 	rc = 0;
@@ -224,7 +224,7 @@ static void nfcsim_stop_poll(struct nfc_dev *nfc_dev)
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "Stop poll");
+	DEV_DBG(dev, "Stop poll\n");
 
 	mutex_lock(&dev->lock);
 
@@ -240,7 +240,7 @@ static int nfcsim_activate_target(struct nfc_dev *nfc_dev,
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 
 	return -ENOTSUPP;
 }
@@ -250,7 +250,7 @@ static void nfcsim_deactivate_target(struct nfc_dev *nfc_dev,
 {
 	struct nfcsim *dev = nfc_get_drvdata(nfc_dev);
 
-	DEV_DBG(dev, "");
+	DEV_DBG(dev, "\n");
 }
 
 static void nfcsim_wq_recv(struct work_struct *work)
@@ -397,13 +397,13 @@ static void nfcsim_wq_poll(struct work_struct *work)
 	nfcsim_set_polling_mode(dev);
 
 	if (dev->curr_polling_mode == NFCSIM_POLL_NONE) {
-		DEV_DBG(dev, "Not polling");
+		DEV_DBG(dev, "Not polling\n");
 		goto unlock;
 	}
 
 	DEV_DBG(dev, "Polling as %s",
 		dev->curr_polling_mode == NFCSIM_POLL_INITIATOR ?
-		"initiator" : "target");
+		"initiator\n" : "target\n");
 
 	if (dev->curr_polling_mode == NFCSIM_POLL_TARGET)
 		goto sched_work;
diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c
index 59f95d8fc98c..ec9dbf4fad83 100644
--- a/drivers/nfc/nfcwilink.c
+++ b/drivers/nfc/nfcwilink.c
@@ -146,8 +146,6 @@ static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
 	unsigned long comp_ret;
 	int rc;
 
-	nfc_dev_dbg(&drv->pdev->dev, "get_bts_file_name entry");
-
 	skb = nfcwilink_skb_alloc(sizeof(struct nci_vs_nfcc_info_cmd),
 					GFP_KERNEL);
 	if (!skb) {
@@ -170,17 +168,16 @@ static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
 
 	comp_ret = wait_for_completion_timeout(&drv->completed,
 				msecs_to_jiffies(NFCWILINK_CMD_TIMEOUT));
-	nfc_dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld",
-			comp_ret);
+	dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld\n",
+		comp_ret);
 	if (comp_ret == 0) {
-		nfc_dev_err(&drv->pdev->dev,
-				"timeout on wait_for_completion_timeout");
+		dev_err(&drv->pdev->dev,
+			"timeout on wait_for_completion_timeout\n");
 		return -ETIMEDOUT;
 	}
 
-	nfc_dev_dbg(&drv->pdev->dev, "nci_vs_nfcc_info_rsp: plen %d, status %d",
-			drv->nfcc_info.plen,
-			drv->nfcc_info.status);
+	dev_dbg(&drv->pdev->dev, "nci_vs_nfcc_info_rsp: plen %d, status %d\n",
+		drv->nfcc_info.plen, drv->nfcc_info.status);
 
 	if ((drv->nfcc_info.plen != 5) || (drv->nfcc_info.status != 0)) {
 		nfc_dev_err(&drv->pdev->dev,
@@ -207,8 +204,6 @@ static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
 	unsigned long comp_ret;
 	int rc;
 
-	nfc_dev_dbg(&drv->pdev->dev, "send_bts_cmd entry");
-
 	/* verify valid cmd for the NFC channel */
 	if ((len <= sizeof(struct nfcwilink_hdr)) ||
 		(len > BTS_FILE_CMD_MAX_LEN) ||
@@ -238,8 +233,8 @@ static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
 
 	comp_ret = wait_for_completion_timeout(&drv->completed,
 				msecs_to_jiffies(NFCWILINK_CMD_TIMEOUT));
-	nfc_dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld",
-			comp_ret);
+	dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld\n",
+		comp_ret);
 	if (comp_ret == 0) {
 		nfc_dev_err(&drv->pdev->dev,
 				"timeout on wait_for_completion_timeout");
@@ -257,8 +252,6 @@ static int nfcwilink_download_fw(struct nfcwilink *drv)
 	__u8 *ptr;
 	int len, rc;
 
-	nfc_dev_dbg(&drv->pdev->dev, "download_fw entry");
-
 	set_bit(NFCWILINK_FW_DOWNLOAD, &drv->flags);
 
 	rc = nfcwilink_get_bts_file_name(drv, file_name);
@@ -280,8 +273,8 @@ static int nfcwilink_download_fw(struct nfcwilink *drv)
 	ptr = (__u8 *)fw->data;
 
 	if ((len == 0) || (ptr == NULL)) {
-		nfc_dev_dbg(&drv->pdev->dev,
-				"request_firmware returned size %d", len);
+		dev_dbg(&drv->pdev->dev,
+			"request_firmware returned size %d\n", len);
 		goto release_fw;
 	}
 
@@ -302,8 +295,8 @@ static int nfcwilink_download_fw(struct nfcwilink *drv)
 		action_len =
 			__le16_to_cpu(((struct bts_file_action *)ptr)->len);
 
-		nfc_dev_dbg(&drv->pdev->dev, "bts_file_action type %d, len %d",
-				action_type, action_len);
+		dev_dbg(&drv->pdev->dev, "bts_file_action type %d, len %d\n",
+			action_type, action_len);
 
 		switch (action_type) {
 		case BTS_FILE_ACTION_TYPE_SEND_CMD:
@@ -333,8 +326,6 @@ static void nfcwilink_register_complete(void *priv_data, char data)
 {
 	struct nfcwilink *drv = priv_data;
 
-	nfc_dev_dbg(&drv->pdev->dev, "register_complete entry");
-
 	/* store ST registration status */
 	drv->st_register_cb_status = data;
 
@@ -356,7 +347,7 @@ static long nfcwilink_receive(void *priv_data, struct sk_buff *skb)
 		return -EFAULT;
 	}
 
-	nfc_dev_dbg(&drv->pdev->dev, "receive entry, len %d", skb->len);
+	dev_dbg(&drv->pdev->dev, "receive entry, len %d\n", skb->len);
 
 	/* strip the ST header
 	(apart for the chnl byte, which is not received in the hdr) */
@@ -396,8 +387,6 @@ static int nfcwilink_open(struct nci_dev *ndev)
 	unsigned long comp_ret;
 	int rc;
 
-	nfc_dev_dbg(&drv->pdev->dev, "open entry");
-
 	if (test_and_set_bit(NFCWILINK_RUNNING, &drv->flags)) {
 		rc = -EBUSY;
 		goto exit;
@@ -415,9 +404,9 @@ static int nfcwilink_open(struct nci_dev *ndev)
 			&drv->completed,
 			msecs_to_jiffies(NFCWILINK_REGISTER_TIMEOUT));
 
-			nfc_dev_dbg(&drv->pdev->dev,
-			"wait_for_completion_timeout returned %ld",
-			comp_ret);
+			dev_dbg(&drv->pdev->dev,
+				"wait_for_completion_timeout returned %ld\n",
+				comp_ret);
 
 			if (comp_ret == 0) {
 				/* timeout */
@@ -460,8 +449,6 @@ static int nfcwilink_close(struct nci_dev *ndev)
 	struct nfcwilink *drv = nci_get_drvdata(ndev);
 	int rc;
 
-	nfc_dev_dbg(&drv->pdev->dev, "close entry");
-
 	if (!test_and_clear_bit(NFCWILINK_RUNNING, &drv->flags))
 		return 0;
 
@@ -480,7 +467,7 @@ static int nfcwilink_send(struct nci_dev *ndev, struct sk_buff *skb)
 	struct nfcwilink_hdr hdr = {NFCWILINK_CHNL, NFCWILINK_OPCODE, 0x0000};
 	long len;
 
-	nfc_dev_dbg(&drv->pdev->dev, "send entry, len %d", skb->len);
+	dev_dbg(&drv->pdev->dev, "send entry, len %d\n", skb->len);
 
 	if (!test_bit(NFCWILINK_RUNNING, &drv->flags)) {
 		kfree_skb(skb);
@@ -517,8 +504,6 @@ static int nfcwilink_probe(struct platform_device *pdev)
 	int rc;
 	__u32 protocols;
 
-	nfc_dev_dbg(&pdev->dev, "probe entry");
-
 	drv = devm_kzalloc(&pdev->dev, sizeof(struct nfcwilink), GFP_KERNEL);
 	if (!drv) {
 		rc = -ENOMEM;
@@ -568,8 +553,6 @@ static int nfcwilink_remove(struct platform_device *pdev)
 	struct nfcwilink *drv = dev_get_drvdata(&pdev->dev);
 	struct nci_dev *ndev;
 
-	nfc_dev_dbg(&pdev->dev, "remove entry");
-
 	if (!drv)
 		return -EFAULT;
 
diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c
index 5df730be88a3..e64bea53f0c8 100644
--- a/drivers/nfc/pn533.c
+++ b/drivers/nfc/pn533.c
@@ -722,9 +722,9 @@ static void pn533_recv_response(struct urb *urb)
 		break; /* success */
 	case -ECONNRESET:
 	case -ENOENT:
-		nfc_dev_dbg(&dev->interface->dev,
-			    "The urb has been canceled (status %d)",
-			    urb->status);
+		dev_dbg(&dev->interface->dev,
+			"The urb has been canceled (status %d)\n",
+			urb->status);
 		goto sched_wq;
 	case -ESHUTDOWN:
 	default:
@@ -735,7 +735,7 @@ static void pn533_recv_response(struct urb *urb)
 
 	in_frame = dev->in_urb->transfer_buffer;
 
-	nfc_dev_dbg(&dev->interface->dev, "Received a frame.");
+	dev_dbg(&dev->interface->dev, "Received a frame\n");
 	print_hex_dump_debug("PN533 RX: ", DUMP_PREFIX_NONE, 16, 1, in_frame,
 			     dev->ops->rx_frame_size(in_frame), false);
 
@@ -777,9 +777,9 @@ static void pn533_recv_ack(struct urb *urb)
 		break; /* success */
 	case -ECONNRESET:
 	case -ENOENT:
-		nfc_dev_dbg(&dev->interface->dev,
-			    "The urb has been stopped (status %d)",
-			    urb->status);
+		dev_dbg(&dev->interface->dev,
+			"The urb has been stopped (status %d)\n",
+			urb->status);
 		goto sched_wq;
 	case -ESHUTDOWN:
 	default:
@@ -823,8 +823,6 @@ static int pn533_send_ack(struct pn533 *dev, gfp_t flags)
 	/* spec 7.1.1.3:  Preamble, SoPC (2), ACK Code (2), Postamble */
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
-
 	dev->out_urb->transfer_buffer = ack;
 	dev->out_urb->transfer_buffer_length = sizeof(ack);
 	rc = usb_submit_urb(dev->out_urb, flags);
@@ -927,7 +925,7 @@ static int __pn533_send_async(struct pn533 *dev, u8 cmd_code,
 	struct pn533_cmd *cmd;
 	int rc = 0;
 
-	nfc_dev_dbg(&dev->interface->dev, "Sending command 0x%x", cmd_code);
+	dev_dbg(&dev->interface->dev, "Sending command 0x%x\n", cmd_code);
 
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	if (!cmd)
@@ -954,8 +952,8 @@ static int __pn533_send_async(struct pn533 *dev, u8 cmd_code,
 		goto unlock;
 	}
 
-	nfc_dev_dbg(&dev->interface->dev, "%s Queueing command 0x%x", __func__,
-		    cmd_code);
+	dev_dbg(&dev->interface->dev, "%s Queueing command 0x%x\n",
+		__func__, cmd_code);
 
 	INIT_LIST_HEAD(&cmd->queue);
 	list_add_tail(&cmd->queue, &dev->cmd_queue);
@@ -1168,9 +1166,9 @@ static void pn533_send_complete(struct urb *urb)
 		break; /* success */
 	case -ECONNRESET:
 	case -ENOENT:
-		nfc_dev_dbg(&dev->interface->dev,
-			    "The urb has been stopped (status %d)",
-			    urb->status);
+		dev_dbg(&dev->interface->dev,
+			"The urb has been stopped (status %d)\n",
+			urb->status);
 		break;
 	case -ESHUTDOWN:
 	default:
@@ -1452,8 +1450,8 @@ static int pn533_target_found(struct pn533 *dev, u8 tg, u8 *tgdata,
 	struct nfc_target nfc_tgt;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s - modulation=%d", __func__,
-		    dev->poll_mod_curr);
+	dev_dbg(&dev->interface->dev, "%s - modulation=%d\n",
+		__func__, dev->poll_mod_curr);
 
 	if (tg != 1)
 		return -EPROTO;
@@ -1484,14 +1482,14 @@ static int pn533_target_found(struct pn533 *dev, u8 tg, u8 *tgdata,
 		return rc;
 
 	if (!(nfc_tgt.supported_protocols & dev->poll_protocols)) {
-		nfc_dev_dbg(&dev->interface->dev,
-			    "The Tg found doesn't have the desired protocol");
+		dev_dbg(&dev->interface->dev,
+			"The Tg found doesn't have the desired protocol\n");
 		return -EAGAIN;
 	}
 
-	nfc_dev_dbg(&dev->interface->dev,
-		    "Target found - supported protocols: 0x%x",
-		    nfc_tgt.supported_protocols);
+	dev_dbg(&dev->interface->dev,
+		"Target found - supported protocols: 0x%x\n",
+		nfc_tgt.supported_protocols);
 
 	dev->tgt_available_prots = nfc_tgt.supported_protocols;
 
@@ -1548,8 +1546,6 @@ static int pn533_start_poll_complete(struct pn533 *dev, struct sk_buff *resp)
 	u8 nbtg, tg, *tgdata;
 	int rc, tgdata_len;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
-
 	nbtg = resp->data[0];
 	tg = resp->data[1];
 	tgdata = &resp->data[2];
@@ -1629,7 +1625,7 @@ static int pn533_tm_get_data_complete(struct pn533 *dev, void *arg,
 {
 	u8 status;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (IS_ERR(resp))
 		return PTR_ERR(resp);
@@ -1650,11 +1646,10 @@ static int pn533_tm_get_data_complete(struct pn533 *dev, void *arg,
 static void pn533_wq_tg_get_data(struct work_struct *work)
 {
 	struct pn533 *dev = container_of(work, struct pn533, tg_work);
-
 	struct sk_buff *skb;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb = pn533_alloc_skb(dev, 0);
 	if (!skb)
@@ -1676,7 +1671,7 @@ static int pn533_init_target_complete(struct pn533 *dev, struct sk_buff *resp)
 	size_t gb_len;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (resp->len < ATR_REQ_GB_OFFSET + 1)
 		return -EINVAL;
@@ -1684,8 +1679,8 @@ static int pn533_init_target_complete(struct pn533 *dev, struct sk_buff *resp)
 	mode = resp->data[0];
 	cmd = &resp->data[1];
 
-	nfc_dev_dbg(&dev->interface->dev, "Target mode 0x%x len %d\n",
-		    mode, resp->len);
+	dev_dbg(&dev->interface->dev, "Target mode 0x%x len %d\n",
+		mode, resp->len);
 
 	if ((mode & PN533_INIT_TARGET_RESP_FRAME_MASK) ==
 	    PN533_INIT_TARGET_RESP_ACTIVE)
@@ -1715,7 +1710,7 @@ static void pn533_listen_mode_timer(unsigned long data)
 {
 	struct pn533 *dev = (struct pn533 *)data;
 
-	nfc_dev_dbg(&dev->interface->dev, "Listen mode timeout");
+	dev_dbg(&dev->interface->dev, "Listen mode timeout\n");
 
 	dev->cancel_listen = 1;
 
@@ -1730,7 +1725,7 @@ static int pn533_rf_complete(struct pn533 *dev, void *arg,
 {
 	int rc = 0;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -1754,7 +1749,7 @@ static void pn533_wq_rf(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb = pn533_alloc_skb(dev, 2);
 	if (!skb)
@@ -1779,7 +1774,7 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg,
 	struct pn533_poll_modulations *cur_mod;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -1813,7 +1808,7 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg,
 		goto done;
 
 	if (!dev->poll_mod_count) {
-		nfc_dev_dbg(&dev->interface->dev, "Polling has been stopped.");
+		dev_dbg(&dev->interface->dev, "Polling has been stopped\n");
 		goto done;
 	}
 
@@ -1856,8 +1851,8 @@ static int pn533_send_poll_frame(struct pn533 *dev)
 
 	mod = dev->poll_mod_active[dev->poll_mod_curr];
 
-	nfc_dev_dbg(&dev->interface->dev, "%s mod len %d\n",
-		    __func__, mod->len);
+	dev_dbg(&dev->interface->dev, "%s mod len %d\n",
+		__func__, mod->len);
 
 	if (mod->len == 0) {  /* Listen mode */
 		cmd_code = PN533_CMD_TG_INIT_AS_TARGET;
@@ -1890,9 +1885,9 @@ static void pn533_wq_poll(struct work_struct *work)
 
 	cur_mod = dev->poll_mod_active[dev->poll_mod_curr];
 
-	nfc_dev_dbg(&dev->interface->dev,
-		    "%s cancel_listen %d modulation len %d",
-		    __func__, dev->cancel_listen, cur_mod->len);
+	dev_dbg(&dev->interface->dev,
+		"%s cancel_listen %d modulation len %d\n",
+		__func__, dev->cancel_listen, cur_mod->len);
 
 	if (dev->cancel_listen == 1) {
 		dev->cancel_listen = 0;
@@ -1915,9 +1910,9 @@ static int pn533_start_poll(struct nfc_dev *nfc_dev,
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 	u8 rand_mod;
 
-	nfc_dev_dbg(&dev->interface->dev,
-		    "%s: im protocols 0x%x tm protocols 0x%x",
-		    __func__, im_protocols, tm_protocols);
+	dev_dbg(&dev->interface->dev,
+		"%s: im protocols 0x%x tm protocols 0x%x\n",
+		__func__, im_protocols, tm_protocols);
 
 	if (dev->tgt_active_prot) {
 		nfc_dev_err(&dev->interface->dev,
@@ -1953,13 +1948,11 @@ static void pn533_stop_poll(struct nfc_dev *nfc_dev)
 {
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
-
 	del_timer(&dev->listen_timer);
 
 	if (!dev->poll_mod_count) {
-		nfc_dev_dbg(&dev->interface->dev,
-			    "Polling operation was not running");
+		dev_dbg(&dev->interface->dev,
+			"Polling operation was not running\n");
 		return;
 	}
 
@@ -1973,11 +1966,10 @@ static int pn533_activate_target_nfcdep(struct pn533 *dev)
 	struct pn533_cmd_activate_response *rsp;
 	u16 gt_len;
 	int rc;
-
 	struct sk_buff *skb;
 	struct sk_buff *resp;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb = pn533_alloc_skb(dev, sizeof(u8) * 2); /*TG + Next*/
 	if (!skb)
@@ -2013,12 +2005,12 @@ static int pn533_activate_target(struct nfc_dev *nfc_dev,
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s - protocol=%u", __func__,
-		    protocol);
+	dev_dbg(&dev->interface->dev, "%s - protocol=%u\n",
+		__func__, protocol);
 
 	if (dev->poll_mod_count) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Cannot activate while polling");
+		dev_err(&dev->interface->dev,
+			"Cannot activate while polling\n");
 		return -EBUSY;
 	}
 
@@ -2060,13 +2052,11 @@ static void pn533_deactivate_target(struct nfc_dev *nfc_dev,
 				    struct nfc_target *target)
 {
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
-
 	struct sk_buff *skb;
 	struct sk_buff *resp;
-
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (!dev->tgt_active_prot) {
 		nfc_dev_err(&dev->interface->dev, "There is no active target");
@@ -2129,7 +2119,7 @@ static int pn533_in_dep_link_up_complete(struct pn533 *dev, void *arg,
 	if (!dev->tgt_available_prots) {
 		struct nfc_target nfc_target;
 
-		nfc_dev_dbg(&dev->interface->dev, "Creating new target");
+		dev_dbg(&dev->interface->dev, "Creating new target\n");
 
 		nfc_target.supported_protocols = NFC_PROTO_NFC_DEP_MASK;
 		nfc_target.nfcid1_len = 10;
@@ -2166,10 +2156,9 @@ static int pn533_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	struct sk_buff *skb;
 	int rc, skb_len;
 	u8 *next, *arg, nfcid3[NFC_NFCID3_MAXSIZE];
-
 	u8 passive_data[PASSIVE_DATA_LEN] = {0x00, 0xff, 0xff, 0x00, 0x3};
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (dev->poll_mod_count) {
 		nfc_dev_err(&dev->interface->dev,
@@ -2249,7 +2238,7 @@ static int pn533_dep_link_down(struct nfc_dev *nfc_dev)
 {
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	pn533_poll_reset_mod_list(dev);
 
@@ -2274,7 +2263,7 @@ static struct sk_buff *pn533_build_response(struct pn533 *dev)
 	struct sk_buff *skb, *tmp, *t;
 	unsigned int skb_len = 0, tmp_len = 0;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (skb_queue_empty(&dev->resp_q))
 		return NULL;
@@ -2287,8 +2276,8 @@ static struct sk_buff *pn533_build_response(struct pn533 *dev)
 	skb_queue_walk_safe(&dev->resp_q, tmp, t)
 		skb_len += tmp->len;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s total length %d\n",
-		    __func__, skb_len);
+	dev_dbg(&dev->interface->dev, "%s total length %d\n",
+		__func__, skb_len);
 
 	skb = alloc_skb(skb_len, GFP_KERNEL);
 	if (skb == NULL)
@@ -2315,7 +2304,7 @@ static int pn533_data_exchange_complete(struct pn533 *dev, void *_arg,
 	int rc = 0;
 	u8 status, ret, mi;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
@@ -2420,7 +2409,7 @@ static int pn533_transceive(struct nfc_dev *nfc_dev,
 	struct pn533_data_exchange_arg *arg = NULL;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (!dev->tgt_active_prot) {
 		nfc_dev_err(&dev->interface->dev,
@@ -2487,7 +2476,7 @@ static int pn533_tm_send_complete(struct pn533 *dev, void *arg,
 {
 	u8 status;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (IS_ERR(resp))
 		return PTR_ERR(resp);
@@ -2514,7 +2503,7 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 	struct pn533 *dev = nfc_get_drvdata(nfc_dev);
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
 		nfc_dev_err(&dev->interface->dev,
@@ -2534,11 +2523,10 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 static void pn533_wq_mi_recv(struct work_struct *work)
 {
 	struct pn533 *dev = container_of(work, struct pn533, mi_rx_work);
-
 	struct sk_buff *skb;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb = pn533_alloc_skb(dev, PN533_CMD_DATAEXCH_HEAD_LEN);
 	if (!skb)
@@ -2587,7 +2575,7 @@ static void pn533_wq_mi_send(struct work_struct *work)
 	struct sk_buff *skb;
 	int rc;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	/* Grab the first skb in the queue */
 	skb = skb_dequeue(&dev->fragment_skb);
@@ -2641,10 +2629,9 @@ static int pn533_set_configuration(struct pn533 *dev, u8 cfgitem, u8 *cfgdata,
 {
 	struct sk_buff *skb;
 	struct sk_buff *resp;
-
 	int skb_len;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb_len = sizeof(cfgitem) + cfgdata_len; /* cfgitem + cfgdata */
 
@@ -2691,7 +2678,7 @@ static int pn533_pasori_fw_reset(struct pn533 *dev)
 	struct sk_buff *skb;
 	struct sk_buff *resp;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	skb = pn533_alloc_skb(dev, sizeof(u8));
 	if (!skb)
@@ -2717,7 +2704,7 @@ static void pn533_acr122_poweron_rdr_resp(struct urb *urb)
 {
 	struct pn533_acr122_poweron_rdr_arg *arg = urb->context;
 
-	nfc_dev_dbg(&urb->dev->dev, "%s", __func__);
+	dev_dbg(&urb->dev->dev, "%s\n", __func__);
 
 	print_hex_dump_debug("ACR122 RX: ", DUMP_PREFIX_NONE, 16, 1,
 		       urb->transfer_buffer, urb->transfer_buffer_length,
@@ -2737,7 +2724,7 @@ static int pn533_acr122_poweron_rdr(struct pn533 *dev)
 	void *cntx;
 	struct pn533_acr122_poweron_rdr_arg arg;
 
-	nfc_dev_dbg(&dev->interface->dev, "%s", __func__);
+	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	init_completion(&arg.done);
 	cntx = dev->in_urb->context;  /* backup context */
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index e34859423105..a164c46bed7e 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -30,7 +30,6 @@
 
 #define nfc_dev_info(dev, fmt, arg...) dev_info((dev), "NFC: " fmt "\n", ## arg)
 #define nfc_dev_err(dev, fmt, arg...) dev_err((dev), "NFC: " fmt "\n", ## arg)
-#define nfc_dev_dbg(dev, fmt, arg...) dev_dbg((dev), fmt "\n", ## arg)
 
 struct nfc_dev;
 
-- 
cgit 


From 073a625f0b80fb7613220a56375b0f3d2831af1b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 5 Apr 2013 12:27:38 -0700
Subject: NFC: Convert nfc_dev_info and nfc_dev_err to nfc_<level>

Use a more standard kernel style macro logging name.

Standardize the spacing of the "NFC: " prefix.
Add \n to uses, remove from macro.
Fix the defective uses that already had a \n.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/nfcsim.c    |  14 ++--
 drivers/nfc/nfcwilink.c |  44 ++++++------
 drivers/nfc/pn533.c     | 175 +++++++++++++++++++++++-------------------------
 include/net/nfc/nfc.h   |   4 +-
 4 files changed, 115 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c
index 4a614794ea61..93111fa8d282 100644
--- a/drivers/nfc/nfcsim.c
+++ b/drivers/nfc/nfcsim.c
@@ -19,7 +19,7 @@
 #include <linux/nfc.h>
 #include <net/nfc/nfc.h>
 
-#define DEV_ERR(_dev, fmt, args...) nfc_dev_err(&_dev->nfc_dev->dev, \
+#define DEV_ERR(_dev, fmt, args...) nfc_err(&_dev->nfc_dev->dev, \
 						"%s: " fmt, __func__, ## args)
 
 #define DEV_DBG(_dev, fmt, args...) dev_dbg(&_dev->nfc_dev->dev, \
@@ -143,7 +143,7 @@ static int nfcsim_dep_link_up(struct nfc_dev *nfc_dev,
 
 	remote_gb = nfc_get_local_general_bytes(peer->nfc_dev, &remote_gb_len);
 	if (!remote_gb) {
-		DEV_ERR(peer, "Can't get remote general bytes");
+		DEV_ERR(peer, "Can't get remote general bytes\n");
 
 		mutex_unlock(&peer->lock);
 		return -EINVAL;
@@ -155,7 +155,7 @@ static int nfcsim_dep_link_up(struct nfc_dev *nfc_dev,
 
 	rc = nfc_set_remote_general_bytes(nfc_dev, remote_gb, remote_gb_len);
 	if (rc) {
-		DEV_ERR(dev, "Can't set remote general bytes");
+		DEV_ERR(dev, "Can't set remote general bytes\n");
 		mutex_unlock(&dev->lock);
 		return rc;
 	}
@@ -188,7 +188,7 @@ static int nfcsim_start_poll(struct nfc_dev *nfc_dev,
 	mutex_lock(&dev->lock);
 
 	if (dev->polling_mode != NFCSIM_POLL_NONE) {
-		DEV_ERR(dev, "Already in polling mode");
+		DEV_ERR(dev, "Already in polling mode\n");
 		rc = -EBUSY;
 		goto exit;
 	}
@@ -200,7 +200,7 @@ static int nfcsim_start_poll(struct nfc_dev *nfc_dev,
 		dev->polling_mode |= NFCSIM_POLL_TARGET;
 
 	if (dev->polling_mode == NFCSIM_POLL_NONE) {
-		DEV_ERR(dev, "Unsupported polling mode");
+		DEV_ERR(dev, "Unsupported polling mode\n");
 		rc = -EINVAL;
 		goto exit;
 	}
@@ -267,7 +267,7 @@ static void nfcsim_wq_recv(struct work_struct *work)
 
 	if (dev->initiator) {
 		if (!dev->cb) {
-			DEV_ERR(dev, "Null recv callback");
+			DEV_ERR(dev, "Null recv callback\n");
 			dev_kfree_skb(dev->clone_skb);
 			goto exit;
 		}
@@ -310,7 +310,7 @@ static int nfcsim_tx(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	peer->clone_skb = skb_clone(skb, GFP_KERNEL);
 
 	if (!peer->clone_skb) {
-		DEV_ERR(dev, "skb_clone failed");
+		DEV_ERR(dev, "skb_clone failed\n");
 		mutex_unlock(&peer->lock);
 		err = -ENOMEM;
 		goto exit;
diff --git a/drivers/nfc/nfcwilink.c b/drivers/nfc/nfcwilink.c
index ec9dbf4fad83..ebf6da75bd40 100644
--- a/drivers/nfc/nfcwilink.c
+++ b/drivers/nfc/nfcwilink.c
@@ -149,8 +149,8 @@ static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
 	skb = nfcwilink_skb_alloc(sizeof(struct nci_vs_nfcc_info_cmd),
 					GFP_KERNEL);
 	if (!skb) {
-		nfc_dev_err(&drv->pdev->dev,
-				"no memory for nci_vs_nfcc_info_cmd");
+		nfc_err(&drv->pdev->dev,
+			"no memory for nci_vs_nfcc_info_cmd\n");
 		return -ENOMEM;
 	}
 
@@ -180,8 +180,7 @@ static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
 		drv->nfcc_info.plen, drv->nfcc_info.status);
 
 	if ((drv->nfcc_info.plen != 5) || (drv->nfcc_info.status != 0)) {
-		nfc_dev_err(&drv->pdev->dev,
-				"invalid nci_vs_nfcc_info_rsp");
+		nfc_err(&drv->pdev->dev, "invalid nci_vs_nfcc_info_rsp\n");
 		return -EINVAL;
 	}
 
@@ -192,7 +191,7 @@ static int nfcwilink_get_bts_file_name(struct nfcwilink *drv, char *file_name)
 			drv->nfcc_info.sw_ver_z,
 			drv->nfcc_info.patch_id);
 
-	nfc_dev_info(&drv->pdev->dev, "nfcwilink FW file name: %s", file_name);
+	nfc_info(&drv->pdev->dev, "nfcwilink FW file name: %s\n", file_name);
 
 	return 0;
 }
@@ -209,8 +208,8 @@ static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
 		(len > BTS_FILE_CMD_MAX_LEN) ||
 		(hdr->chnl != NFCWILINK_CHNL) ||
 		(hdr->opcode != NFCWILINK_OPCODE)) {
-		nfc_dev_err(&drv->pdev->dev,
-			"ignoring invalid bts cmd, len %d, chnl %d, opcode %d",
+		nfc_err(&drv->pdev->dev,
+			"ignoring invalid bts cmd, len %d, chnl %d, opcode %d\n",
 			len, hdr->chnl, hdr->opcode);
 		return 0;
 	}
@@ -221,7 +220,7 @@ static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
 
 	skb = nfcwilink_skb_alloc(len, GFP_KERNEL);
 	if (!skb) {
-		nfc_dev_err(&drv->pdev->dev, "no memory for bts cmd");
+		nfc_err(&drv->pdev->dev, "no memory for bts cmd\n");
 		return -ENOMEM;
 	}
 
@@ -236,8 +235,8 @@ static int nfcwilink_send_bts_cmd(struct nfcwilink *drv, __u8 *data, int len)
 	dev_dbg(&drv->pdev->dev, "wait_for_completion_timeout returned %ld\n",
 		comp_ret);
 	if (comp_ret == 0) {
-		nfc_dev_err(&drv->pdev->dev,
-				"timeout on wait_for_completion_timeout");
+		nfc_err(&drv->pdev->dev,
+			"timeout on wait_for_completion_timeout\n");
 		return -ETIMEDOUT;
 	}
 
@@ -260,7 +259,7 @@ static int nfcwilink_download_fw(struct nfcwilink *drv)
 
 	rc = request_firmware(&fw, file_name, &drv->pdev->dev);
 	if (rc) {
-		nfc_dev_err(&drv->pdev->dev, "request_firmware failed %d", rc);
+		nfc_err(&drv->pdev->dev, "request_firmware failed %d\n", rc);
 
 		/* if the file is not found, don't exit with failure */
 		if (rc == -ENOENT)
@@ -280,7 +279,7 @@ static int nfcwilink_download_fw(struct nfcwilink *drv)
 
 	if (__le32_to_cpu(((struct bts_file_hdr *)ptr)->magic) !=
 			BTS_FILE_HDR_MAGIC) {
-		nfc_dev_err(&drv->pdev->dev, "wrong bts magic number");
+		nfc_err(&drv->pdev->dev, "wrong bts magic number\n");
 		rc = -EINVAL;
 		goto release_fw;
 	}
@@ -361,7 +360,7 @@ static long nfcwilink_receive(void *priv_data, struct sk_buff *skb)
 	/* Forward skb to NCI core layer */
 	rc = nci_recv_frame(drv->ndev, skb);
 	if (rc < 0) {
-		nfc_dev_err(&drv->pdev->dev, "nci_recv_frame failed %d", rc);
+		nfc_err(&drv->pdev->dev, "nci_recv_frame failed %d\n", rc);
 		return rc;
 	}
 
@@ -414,13 +413,12 @@ static int nfcwilink_open(struct nci_dev *ndev)
 				goto clear_exit;
 			} else if (drv->st_register_cb_status != 0) {
 				rc = drv->st_register_cb_status;
-				nfc_dev_err(&drv->pdev->dev,
-				"st_register_cb failed %d", rc);
+				nfc_err(&drv->pdev->dev,
+					"st_register_cb failed %d\n", rc);
 				goto clear_exit;
 			}
 		} else {
-			nfc_dev_err(&drv->pdev->dev,
-				"st_register failed %d", rc);
+			nfc_err(&drv->pdev->dev, "st_register failed %d\n", rc);
 			goto clear_exit;
 		}
 	}
@@ -430,8 +428,8 @@ static int nfcwilink_open(struct nci_dev *ndev)
 	drv->st_write = nfcwilink_proto.write;
 
 	if (nfcwilink_download_fw(drv)) {
-		nfc_dev_err(&drv->pdev->dev, "nfcwilink_download_fw failed %d",
-				rc);
+		nfc_err(&drv->pdev->dev, "nfcwilink_download_fw failed %d\n",
+			rc);
 		/* open should succeed, even if the FW download failed */
 	}
 
@@ -454,7 +452,7 @@ static int nfcwilink_close(struct nci_dev *ndev)
 
 	rc = st_unregister(&nfcwilink_proto);
 	if (rc)
-		nfc_dev_err(&drv->pdev->dev, "st_unregister failed %d", rc);
+		nfc_err(&drv->pdev->dev, "st_unregister failed %d\n", rc);
 
 	drv->st_write = NULL;
 
@@ -485,7 +483,7 @@ static int nfcwilink_send(struct nci_dev *ndev, struct sk_buff *skb)
 	len = drv->st_write(skb);
 	if (len < 0) {
 		kfree_skb(skb);
-		nfc_dev_err(&drv->pdev->dev, "st_write failed %ld", len);
+		nfc_err(&drv->pdev->dev, "st_write failed %ld\n", len);
 		return -EFAULT;
 	}
 
@@ -523,7 +521,7 @@ static int nfcwilink_probe(struct platform_device *pdev)
 					NFCWILINK_HDR_LEN,
 					0);
 	if (!drv->ndev) {
-		nfc_dev_err(&pdev->dev, "nci_allocate_device failed");
+		nfc_err(&pdev->dev, "nci_allocate_device failed\n");
 		rc = -ENOMEM;
 		goto exit;
 	}
@@ -533,7 +531,7 @@ static int nfcwilink_probe(struct platform_device *pdev)
 
 	rc = nci_register_device(drv->ndev);
 	if (rc < 0) {
-		nfc_dev_err(&pdev->dev, "nci_register_device failed %d", rc);
+		nfc_err(&pdev->dev, "nci_register_device failed %d\n", rc);
 		goto free_dev_exit;
 	}
 
diff --git a/drivers/nfc/pn533.c b/drivers/nfc/pn533.c
index e64bea53f0c8..a66dff6ed51c 100644
--- a/drivers/nfc/pn533.c
+++ b/drivers/nfc/pn533.c
@@ -728,8 +728,8 @@ static void pn533_recv_response(struct urb *urb)
 		goto sched_wq;
 	case -ESHUTDOWN:
 	default:
-		nfc_dev_err(&dev->interface->dev,
-			    "Urb failure (status %d)", urb->status);
+		nfc_err(&dev->interface->dev,
+			"Urb failure (status %d)\n", urb->status);
 		goto sched_wq;
 	}
 
@@ -740,14 +740,14 @@ static void pn533_recv_response(struct urb *urb)
 			     dev->ops->rx_frame_size(in_frame), false);
 
 	if (!dev->ops->rx_is_frame_valid(in_frame, dev)) {
-		nfc_dev_err(&dev->interface->dev, "Received an invalid frame");
+		nfc_err(&dev->interface->dev, "Received an invalid frame\n");
 		cmd->status = -EIO;
 		goto sched_wq;
 	}
 
 	if (!pn533_rx_frame_is_cmd_response(dev, in_frame)) {
-		nfc_dev_err(&dev->interface->dev,
-			    "It it not the response to the last command");
+		nfc_err(&dev->interface->dev,
+			"It it not the response to the last command\n");
 		cmd->status = -EIO;
 		goto sched_wq;
 	}
@@ -783,23 +783,23 @@ static void pn533_recv_ack(struct urb *urb)
 		goto sched_wq;
 	case -ESHUTDOWN:
 	default:
-		nfc_dev_err(&dev->interface->dev,
-			    "Urb failure (status %d)", urb->status);
+		nfc_err(&dev->interface->dev,
+			"Urb failure (status %d)\n", urb->status);
 		goto sched_wq;
 	}
 
 	in_frame = dev->in_urb->transfer_buffer;
 
 	if (!pn533_std_rx_frame_is_ack(in_frame)) {
-		nfc_dev_err(&dev->interface->dev, "Received an invalid ack");
+		nfc_err(&dev->interface->dev, "Received an invalid ack\n");
 		cmd->status = -EIO;
 		goto sched_wq;
 	}
 
 	rc = pn533_submit_urb_for_response(dev, GFP_ATOMIC);
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "usb_submit_urb failed with result %d", rc);
+		nfc_err(&dev->interface->dev,
+			"usb_submit_urb failed with result %d\n", rc);
 		cmd->status = rc;
 		goto sched_wq;
 	}
@@ -1172,8 +1172,8 @@ static void pn533_send_complete(struct urb *urb)
 		break;
 	case -ESHUTDOWN:
 	default:
-		nfc_dev_err(&dev->interface->dev,
-			    "Urb failure (status %d)", urb->status);
+		nfc_err(&dev->interface->dev, "Urb failure (status %d)\n",
+			urb->status);
 	}
 }
 
@@ -1473,8 +1473,8 @@ static int pn533_target_found(struct pn533 *dev, u8 tg, u8 *tgdata,
 		rc = pn533_target_found_type_b(&nfc_tgt, tgdata, tgdata_len);
 		break;
 	default:
-		nfc_dev_err(&dev->interface->dev,
-			    "Unknown current poll modulation");
+		nfc_err(&dev->interface->dev,
+			"Unknown current poll modulation\n");
 		return -EPROTO;
 	}
 
@@ -1695,8 +1695,8 @@ static int pn533_init_target_complete(struct pn533 *dev, struct sk_buff *resp)
 	rc = nfc_tm_activated(dev->nfc_dev, NFC_PROTO_NFC_DEP_MASK,
 			      comm_mode, gb, gb_len);
 	if (rc < 0) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Error when signaling target activation");
+		nfc_err(&dev->interface->dev,
+			"Error when signaling target activation\n");
 		return rc;
 	}
 
@@ -1730,8 +1730,7 @@ static int pn533_rf_complete(struct pn533 *dev, void *arg,
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 
-		nfc_dev_err(&dev->interface->dev, "%s RF setting error %d",
-			    __func__, rc);
+		nfc_err(&dev->interface->dev, "RF setting error %d", rc);
 
 		return rc;
 	}
@@ -1762,7 +1761,7 @@ static void pn533_wq_rf(struct work_struct *work)
 				  pn533_rf_complete, NULL);
 	if (rc < 0) {
 		dev_kfree_skb(skb);
-		nfc_dev_err(&dev->interface->dev, "RF setting error %d", rc);
+		nfc_err(&dev->interface->dev, "RF setting error %d\n", rc);
 	}
 
 	return;
@@ -1779,8 +1778,8 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg,
 	if (IS_ERR(resp)) {
 		rc = PTR_ERR(resp);
 
-		nfc_dev_err(&dev->interface->dev, "%s  Poll complete error %d",
-			    __func__, rc);
+		nfc_err(&dev->interface->dev, "%s  Poll complete error %d\n",
+			__func__, rc);
 
 		if (rc == -ENOENT) {
 			if (dev->poll_mod_count != 0)
@@ -1788,8 +1787,8 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg,
 			else
 				goto stop_poll;
 		} else if (rc < 0) {
-			nfc_dev_err(&dev->interface->dev,
-				    "Error %d when running poll", rc);
+			nfc_err(&dev->interface->dev,
+				"Error %d when running poll\n", rc);
 			goto stop_poll;
 		}
 	}
@@ -1821,7 +1820,7 @@ done:
 	return rc;
 
 stop_poll:
-	nfc_dev_err(&dev->interface->dev, "Polling operation has been stopped");
+	nfc_err(&dev->interface->dev, "Polling operation has been stopped\n");
 
 	pn533_poll_reset_mod_list(dev);
 	dev->poll_protocols = 0;
@@ -1863,7 +1862,7 @@ static int pn533_send_poll_frame(struct pn533 *dev)
 	}
 
 	if (!skb) {
-		nfc_dev_err(&dev->interface->dev, "Failed to allocate skb.");
+		nfc_err(&dev->interface->dev, "Failed to allocate skb\n");
 		return -ENOMEM;
 	}
 
@@ -1871,7 +1870,7 @@ static int pn533_send_poll_frame(struct pn533 *dev)
 				  NULL);
 	if (rc < 0) {
 		dev_kfree_skb(skb);
-		nfc_dev_err(&dev->interface->dev, "Polling loop error %d", rc);
+		nfc_err(&dev->interface->dev, "Polling loop error %d\n", rc);
 	}
 
 	return rc;
@@ -1915,14 +1914,14 @@ static int pn533_start_poll(struct nfc_dev *nfc_dev,
 		__func__, im_protocols, tm_protocols);
 
 	if (dev->tgt_active_prot) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Cannot poll with a target already activated");
+		nfc_err(&dev->interface->dev,
+			"Cannot poll with a target already activated\n");
 		return -EBUSY;
 	}
 
 	if (dev->tgt_mode) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Cannot poll while already being activated");
+		nfc_err(&dev->interface->dev,
+			"Cannot poll while already being activated\n");
 		return -EBUSY;
 	}
 
@@ -1985,8 +1984,8 @@ static int pn533_activate_target_nfcdep(struct pn533 *dev)
 	rsp = (struct pn533_cmd_activate_response *)resp->data;
 	rc = rsp->status & PN533_CMD_RET_MASK;
 	if (rc != PN533_CMD_RET_SUCCESS) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Target activation failed (error 0x%x)", rc);
+		nfc_err(&dev->interface->dev,
+			"Target activation failed (error 0x%x)\n", rc);
 		dev_kfree_skb(resp);
 		return -EIO;
 	}
@@ -2009,35 +2008,35 @@ static int pn533_activate_target(struct nfc_dev *nfc_dev,
 		__func__, protocol);
 
 	if (dev->poll_mod_count) {
-		dev_err(&dev->interface->dev,
+		nfc_err(&dev->interface->dev,
 			"Cannot activate while polling\n");
 		return -EBUSY;
 	}
 
 	if (dev->tgt_active_prot) {
-		nfc_dev_err(&dev->interface->dev,
-			    "There is already an active target");
+		nfc_err(&dev->interface->dev,
+			"There is already an active target\n");
 		return -EBUSY;
 	}
 
 	if (!dev->tgt_available_prots) {
-		nfc_dev_err(&dev->interface->dev,
-			    "There is no available target to activate");
+		nfc_err(&dev->interface->dev,
+			"There is no available target to activate\n");
 		return -EINVAL;
 	}
 
 	if (!(dev->tgt_available_prots & (1 << protocol))) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Target doesn't support requested proto %u",
-			    protocol);
+		nfc_err(&dev->interface->dev,
+			"Target doesn't support requested proto %u\n",
+			protocol);
 		return -EINVAL;
 	}
 
 	if (protocol == NFC_PROTO_NFC_DEP) {
 		rc = pn533_activate_target_nfcdep(dev);
 		if (rc) {
-			nfc_dev_err(&dev->interface->dev,
-				    "Activating target with DEP failed %d", rc);
+			nfc_err(&dev->interface->dev,
+				"Activating target with DEP failed %d\n", rc);
 			return rc;
 		}
 	}
@@ -2059,7 +2058,7 @@ static void pn533_deactivate_target(struct nfc_dev *nfc_dev,
 	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (!dev->tgt_active_prot) {
-		nfc_dev_err(&dev->interface->dev, "There is no active target");
+		nfc_err(&dev->interface->dev, "There is no active target\n");
 		return;
 	}
 
@@ -2078,8 +2077,8 @@ static void pn533_deactivate_target(struct nfc_dev *nfc_dev,
 
 	rc = resp->data[0] & PN533_CMD_RET_MASK;
 	if (rc != PN533_CMD_RET_SUCCESS)
-		nfc_dev_err(&dev->interface->dev,
-			    "Error 0x%x when releasing the target", rc);
+		nfc_err(&dev->interface->dev,
+			"Error 0x%x when releasing the target\n", rc);
 
 	dev_kfree_skb(resp);
 	return;
@@ -2101,8 +2100,8 @@ static int pn533_in_dep_link_up_complete(struct pn533 *dev, void *arg,
 
 	if (dev->tgt_available_prots &&
 	    !(dev->tgt_available_prots & (1 << NFC_PROTO_NFC_DEP))) {
-		nfc_dev_err(&dev->interface->dev,
-			    "The target does not support DEP");
+		nfc_err(&dev->interface->dev,
+			"The target does not support DEP\n");
 		rc =  -EINVAL;
 		goto error;
 	}
@@ -2111,8 +2110,8 @@ static int pn533_in_dep_link_up_complete(struct pn533 *dev, void *arg,
 
 	rc = rsp->status & PN533_CMD_RET_MASK;
 	if (rc != PN533_CMD_RET_SUCCESS) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Bringing DEP link up failed (error 0x%x)", rc);
+		nfc_err(&dev->interface->dev,
+			"Bringing DEP link up failed (error 0x%x)\n", rc);
 		goto error;
 	}
 
@@ -2161,14 +2160,14 @@ static int pn533_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (dev->poll_mod_count) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Cannot bring the DEP link up while polling");
+		nfc_err(&dev->interface->dev,
+			"Cannot bring the DEP link up while polling\n");
 		return -EBUSY;
 	}
 
 	if (dev->tgt_active_prot) {
-		nfc_dev_err(&dev->interface->dev,
-			    "There is already an active target");
+		nfc_err(&dev->interface->dev,
+			"There is already an active target\n");
 		return -EBUSY;
 	}
 
@@ -2318,8 +2317,8 @@ static int pn533_data_exchange_complete(struct pn533 *dev, void *_arg,
 	skb_pull(resp, sizeof(status));
 
 	if (ret != PN533_CMD_RET_SUCCESS) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Exchanging data failed (error 0x%x)", ret);
+		nfc_err(&dev->interface->dev,
+			"Exchanging data failed (error 0x%x)\n", ret);
 		rc = -EIO;
 		goto error;
 	}
@@ -2412,8 +2411,8 @@ static int pn533_transceive(struct nfc_dev *nfc_dev,
 	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (!dev->tgt_active_prot) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Can't exchange data if there is no active target");
+		nfc_err(&dev->interface->dev,
+			"Can't exchange data if there is no active target\n");
 		rc = -EINVAL;
 		goto error;
 	}
@@ -2506,9 +2505,9 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 	dev_dbg(&dev->interface->dev, "%s\n", __func__);
 
 	if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Data length greater than the max allowed: %d",
-			    PN533_CMD_DATAEXCH_DATA_MAXLEN);
+		nfc_err(&dev->interface->dev,
+			"Data length greater than the max allowed: %d\n",
+			PN533_CMD_DATAEXCH_DATA_MAXLEN);
 		return -ENOSYS;
 	}
 
@@ -2558,8 +2557,8 @@ static void pn533_wq_mi_recv(struct work_struct *work)
 	if (rc == 0) /* success */
 		return;
 
-	nfc_dev_err(&dev->interface->dev,
-		    "Error %d when trying to perform data_exchange", rc);
+	nfc_err(&dev->interface->dev,
+		"Error %d when trying to perform data_exchange\n", rc);
 
 	dev_kfree_skb(skb);
 	kfree(dev->cmd_complete_mi_arg);
@@ -2613,8 +2612,8 @@ static void pn533_wq_mi_send(struct work_struct *work)
 	if (rc == 0) /* success */
 		return;
 
-	nfc_dev_err(&dev->interface->dev,
-		    "Error %d when trying to perform data_exchange", rc);
+	nfc_err(&dev->interface->dev,
+		"Error %d when trying to perform data_exchange\n", rc);
 
 	dev_kfree_skb(skb);
 	kfree(dev->cmd_complete_dep_arg);
@@ -2742,16 +2741,15 @@ static int pn533_acr122_poweron_rdr(struct pn533 *dev)
 
 	rc = usb_submit_urb(dev->out_urb, GFP_KERNEL);
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Reader power on cmd error %d", rc);
+		nfc_err(&dev->interface->dev,
+			"Reader power on cmd error %d\n", rc);
 		return rc;
 	}
 
 	rc =  usb_submit_urb(dev->in_urb, GFP_KERNEL);
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Can't submit for reader power on cmd response %d",
-			    rc);
+		nfc_err(&dev->interface->dev,
+			"Can't submit reader poweron cmd response %d\n", rc);
 		return rc;
 	}
 
@@ -2772,8 +2770,7 @@ static int pn533_rf_field(struct nfc_dev *nfc_dev, u8 rf)
 	rc = pn533_set_configuration(dev, PN533_CFGITEM_RF_FIELD,
 				     (u8 *)&rf_field, 1);
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Error on setting RF field");
+		nfc_err(&dev->interface->dev, "Error on setting RF field\n");
 		return rc;
 	}
 
@@ -2826,16 +2823,16 @@ static int pn533_setup(struct pn533 *dev)
 		break;
 
 	default:
-		nfc_dev_err(&dev->interface->dev, "Unknown device type %d\n",
-			    dev->device_type);
+		nfc_err(&dev->interface->dev, "Unknown device type %d\n",
+			dev->device_type);
 		return -EINVAL;
 	}
 
 	rc = pn533_set_configuration(dev, PN533_CFGITEM_MAX_RETRIES,
 				     (u8 *)&max_retries, sizeof(max_retries));
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Error on setting MAX_RETRIES config");
+		nfc_err(&dev->interface->dev,
+			"Error on setting MAX_RETRIES config\n");
 		return rc;
 	}
 
@@ -2843,8 +2840,7 @@ static int pn533_setup(struct pn533 *dev)
 	rc = pn533_set_configuration(dev, PN533_CFGITEM_TIMING,
 				     (u8 *)&timing, sizeof(timing));
 	if (rc) {
-		nfc_dev_err(&dev->interface->dev,
-			    "Error on setting RF timings");
+		nfc_err(&dev->interface->dev, "Error on setting RF timings\n");
 		return rc;
 	}
 
@@ -2858,8 +2854,8 @@ static int pn533_setup(struct pn533 *dev)
 		rc = pn533_set_configuration(dev, PN533_CFGITEM_PASORI,
 					     pasori_cfg, 3);
 		if (rc) {
-			nfc_dev_err(&dev->interface->dev,
-				    "Error while settings PASORI config");
+			nfc_err(&dev->interface->dev,
+				"Error while settings PASORI config\n");
 			return rc;
 		}
 
@@ -2904,8 +2900,8 @@ static int pn533_probe(struct usb_interface *interface,
 	}
 
 	if (!in_endpoint || !out_endpoint) {
-		nfc_dev_err(&interface->dev,
-			    "Could not find bulk-in or bulk-out endpoint");
+		nfc_err(&interface->dev,
+			"Could not find bulk-in or bulk-out endpoint\n");
 		rc = -ENODEV;
 		goto error;
 	}
@@ -2965,16 +2961,15 @@ static int pn533_probe(struct usb_interface *interface,
 
 		rc = pn533_acr122_poweron_rdr(dev);
 		if (rc < 0) {
-			nfc_dev_err(&dev->interface->dev,
-				    "Couldn't poweron the reader (error %d)",
-				    rc);
+			nfc_err(&dev->interface->dev,
+				"Couldn't poweron the reader (error %d)\n", rc);
 			goto destroy_wq;
 		}
 		break;
 
 	default:
-		nfc_dev_err(&dev->interface->dev, "Unknown device type %d\n",
-			    dev->device_type);
+		nfc_err(&dev->interface->dev, "Unknown device type %d\n",
+			dev->device_type);
 		rc = -EINVAL;
 		goto destroy_wq;
 	}
@@ -2984,9 +2979,9 @@ static int pn533_probe(struct usb_interface *interface,
 	if (rc < 0)
 		goto destroy_wq;
 
-	nfc_dev_info(&dev->interface->dev,
-		     "NXP PN5%02X firmware ver %d.%d now attached",
-		     fw_ver.ic, fw_ver.ver, fw_ver.rev);
+	nfc_info(&dev->interface->dev,
+		 "NXP PN5%02X firmware ver %d.%d now attached\n",
+		 fw_ver.ic, fw_ver.ver, fw_ver.rev);
 
 
 	dev->nfc_dev = nfc_allocate_device(&pn533_nfc_ops, protocols,
@@ -3057,7 +3052,7 @@ static void pn533_disconnect(struct usb_interface *interface)
 	usb_free_urb(dev->out_urb);
 	kfree(dev);
 
-	nfc_dev_info(&interface->dev, "NXP PN533 NFC device disconnected");
+	nfc_info(&interface->dev, "NXP PN533 NFC device disconnected\n");
 }
 
 static struct usb_driver pn533_driver = {
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index a164c46bed7e..f5c6a23636f1 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -28,8 +28,8 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 
-#define nfc_dev_info(dev, fmt, arg...) dev_info((dev), "NFC: " fmt "\n", ## arg)
-#define nfc_dev_err(dev, fmt, arg...) dev_err((dev), "NFC: " fmt "\n", ## arg)
+#define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__)
+#define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__)
 
 struct nfc_dev;
 
-- 
cgit 


From d593751129ec26762412b2fa7afe9c9258923340 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade <eric.lapuyade@linux.intel.com>
Date: Mon, 2 Sep 2013 12:35:39 +0200
Subject: NFC: NCI: Rename spi ndev -> nsdev and nci_dev -> ndev for
 consistency

An hci dev is an hdev. An nci dev is an ndev. Calling an nci spi dev an
ndev is misleading since it's not the same thing. The nci dev contained
in the nci spi dev is also named inconsistently.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h |  26 ++++-----
 net/nfc/nci/spi.c          | 128 ++++++++++++++++++++++-----------------------
 2 files changed, 77 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 99fc1f3a392a..c08399621c8b 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -210,14 +210,14 @@ int nci_to_errno(__u8 code);
 struct nci_spi_dev;
 
 struct nci_spi_ops {
-	int (*open)(struct nci_spi_dev *ndev);
-	int (*close)(struct nci_spi_dev *ndev);
-	void (*assert_int)(struct nci_spi_dev *ndev);
-	void (*deassert_int)(struct nci_spi_dev *ndev);
+	int (*open)(struct nci_spi_dev *nsdev);
+	int (*close)(struct nci_spi_dev *nsdev);
+	void (*assert_int)(struct nci_spi_dev *nsdev);
+	void (*deassert_int)(struct nci_spi_dev *nsdev);
 };
 
 struct nci_spi_dev {
-	struct nci_dev		*nci_dev;
+	struct nci_dev		*ndev;
 	struct spi_device	*spi;
 	struct nci_spi_ops	*ops;
 
@@ -238,20 +238,20 @@ struct nci_spi_dev *nci_spi_allocate_device(struct spi_device *spi,
 						u32 supported_se,
 						u8 acknowledge_mode,
 						unsigned int delay);
-void nci_spi_free_device(struct nci_spi_dev *ndev);
-int nci_spi_register_device(struct nci_spi_dev *ndev);
-void nci_spi_unregister_device(struct nci_spi_dev *ndev);
-int nci_spi_recv_frame(struct nci_spi_dev *ndev);
+void nci_spi_free_device(struct nci_spi_dev *nsdev);
+int nci_spi_register_device(struct nci_spi_dev *nsdev);
+void nci_spi_unregister_device(struct nci_spi_dev *nsdev);
+int nci_spi_recv_frame(struct nci_spi_dev *nsdev);
 
-static inline void nci_spi_set_drvdata(struct nci_spi_dev *ndev,
+static inline void nci_spi_set_drvdata(struct nci_spi_dev *nsdev,
 					    void *data)
 {
-	ndev->driver_data = data;
+	nsdev->driver_data = data;
 }
 
-static inline void *nci_spi_get_drvdata(struct nci_spi_dev *ndev)
+static inline void *nci_spi_get_drvdata(struct nci_spi_dev *nsdev)
 {
-	return ndev->driver_data;
+	return nsdev->driver_data;
 }
 
 #endif /* __NCI_CORE_H */
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index b6795955432d..e66fda4d9ede 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -41,21 +41,21 @@
 
 #define CRC_INIT		0xFFFF
 
-static int nci_spi_open(struct nci_dev *nci_dev)
+static int nci_spi_open(struct nci_dev *ndev)
 {
-	struct nci_spi_dev *ndev = nci_get_drvdata(nci_dev);
+	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
 
-	return ndev->ops->open(ndev);
+	return nsdev->ops->open(nsdev);
 }
 
-static int nci_spi_close(struct nci_dev *nci_dev)
+static int nci_spi_close(struct nci_dev *ndev)
 {
-	struct nci_spi_dev *ndev = nci_get_drvdata(nci_dev);
+	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
 
-	return ndev->ops->close(ndev);
+	return nsdev->ops->close(nsdev);
 }
 
-static int __nci_spi_send(struct nci_spi_dev *ndev, struct sk_buff *skb)
+static int __nci_spi_send(struct nci_spi_dev *nsdev, struct sk_buff *skb)
 {
 	struct spi_message m;
 	struct spi_transfer t;
@@ -63,32 +63,32 @@ static int __nci_spi_send(struct nci_spi_dev *ndev, struct sk_buff *skb)
 	t.tx_buf = skb->data;
 	t.len = skb->len;
 	t.cs_change = 0;
-	t.delay_usecs = ndev->xfer_udelay;
+	t.delay_usecs = nsdev->xfer_udelay;
 
 	spi_message_init(&m);
 	spi_message_add_tail(&t, &m);
 
-	return spi_sync(ndev->spi, &m);
+	return spi_sync(nsdev->spi, &m);
 }
 
-static int nci_spi_send(struct nci_dev *nci_dev, struct sk_buff *skb)
+static int nci_spi_send(struct nci_dev *ndev, struct sk_buff *skb)
 {
-	struct nci_spi_dev *ndev = nci_get_drvdata(nci_dev);
+	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
 	unsigned int payload_len = skb->len;
 	unsigned char *hdr;
 	int ret;
 	long completion_rc;
 
-	ndev->ops->deassert_int(ndev);
+	nsdev->ops->deassert_int(nsdev);
 
 	/* add the NCI SPI header to the start of the buffer */
 	hdr = skb_push(skb, NCI_SPI_HDR_LEN);
 	hdr[0] = NCI_SPI_DIRECT_WRITE;
-	hdr[1] = ndev->acknowledge_mode;
+	hdr[1] = nsdev->acknowledge_mode;
 	hdr[2] = payload_len >> 8;
 	hdr[3] = payload_len & 0xFF;
 
-	if (ndev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		u16 crc;
 
 		crc = crc_ccitt(CRC_INIT, skb->data, skb->len);
@@ -96,20 +96,20 @@ static int nci_spi_send(struct nci_dev *nci_dev, struct sk_buff *skb)
 		*skb_put(skb, 1) = crc & 0xFF;
 	}
 
-	ret = __nci_spi_send(ndev, skb);
+	ret = __nci_spi_send(nsdev, skb);
 
 	kfree_skb(skb);
-	ndev->ops->assert_int(ndev);
+	nsdev->ops->assert_int(nsdev);
 
-	if (ret != 0 || ndev->acknowledge_mode == NCI_SPI_CRC_DISABLED)
+	if (ret != 0 || nsdev->acknowledge_mode == NCI_SPI_CRC_DISABLED)
 		goto done;
 
-	init_completion(&ndev->req_completion);
-	completion_rc =
-		wait_for_completion_interruptible_timeout(&ndev->req_completion,
-							  NCI_SPI_SEND_TIMEOUT);
+	init_completion(&nsdev->req_completion);
+	completion_rc =	wait_for_completion_interruptible_timeout(
+							&nsdev->req_completion,
+							NCI_SPI_SEND_TIMEOUT);
 
-	if (completion_rc <= 0 || ndev->req_result == ACKNOWLEDGE_NACK)
+	if (completion_rc <= 0 || nsdev->req_result == ACKNOWLEDGE_NACK)
 		ret = -EIO;
 
 done:
@@ -141,7 +141,7 @@ struct nci_spi_dev *nci_spi_allocate_device(struct spi_device *spi,
 						u8 acknowledge_mode,
 						unsigned int delay)
 {
-	struct nci_spi_dev *ndev;
+	struct nci_spi_dev *nsdev;
 	int tailroom = 0;
 
 	if (!ops->open || !ops->close || !ops->assert_int || !ops->deassert_int)
@@ -150,36 +150,36 @@ struct nci_spi_dev *nci_spi_allocate_device(struct spi_device *spi,
 	if (!supported_protocols)
 		return NULL;
 
-	ndev = devm_kzalloc(&spi->dev, sizeof(struct nci_spi_dev), GFP_KERNEL);
-	if (!ndev)
+	nsdev = devm_kzalloc(&spi->dev, sizeof(struct nci_spi_dev), GFP_KERNEL);
+	if (!nsdev)
 		return NULL;
 
-	ndev->ops = ops;
-	ndev->acknowledge_mode = acknowledge_mode;
-	ndev->xfer_udelay = delay;
+	nsdev->ops = ops;
+	nsdev->acknowledge_mode = acknowledge_mode;
+	nsdev->xfer_udelay = delay;
 
 	if (acknowledge_mode == NCI_SPI_CRC_ENABLED)
 		tailroom += NCI_SPI_CRC_LEN;
 
-	ndev->nci_dev = nci_allocate_device(&nci_spi_ops, supported_protocols,
-					    NCI_SPI_HDR_LEN, tailroom);
-	if (!ndev->nci_dev)
+	nsdev->ndev = nci_allocate_device(&nci_spi_ops, supported_protocols,
+					  NCI_SPI_HDR_LEN, tailroom);
+	if (!nsdev->ndev)
 		return NULL;
 
-	nci_set_drvdata(ndev->nci_dev, ndev);
+	nci_set_drvdata(nsdev->ndev, nsdev);
 
-	return ndev;
+	return nsdev;
 }
 EXPORT_SYMBOL_GPL(nci_spi_allocate_device);
 
 /**
  * nci_spi_free_device - deallocate nci spi device
  *
- * @ndev: The nci spi device to deallocate
+ * @nsdev: The nci spi device to deallocate
  */
-void nci_spi_free_device(struct nci_spi_dev *ndev)
+void nci_spi_free_device(struct nci_spi_dev *nsdev)
 {
-	nci_free_device(ndev->nci_dev);
+	nci_free_device(nsdev->ndev);
 }
 EXPORT_SYMBOL_GPL(nci_spi_free_device);
 
@@ -188,9 +188,9 @@ EXPORT_SYMBOL_GPL(nci_spi_free_device);
  *
  * @pdev: The nci spi device to register
  */
-int nci_spi_register_device(struct nci_spi_dev *ndev)
+int nci_spi_register_device(struct nci_spi_dev *nsdev)
 {
-	return nci_register_device(ndev->nci_dev);
+	return nci_register_device(nsdev->ndev);
 }
 EXPORT_SYMBOL_GPL(nci_spi_register_device);
 
@@ -199,20 +199,20 @@ EXPORT_SYMBOL_GPL(nci_spi_register_device);
  *
  * @dev: The nci spi device to unregister
  */
-void nci_spi_unregister_device(struct nci_spi_dev *ndev)
+void nci_spi_unregister_device(struct nci_spi_dev *nsdev)
 {
-	nci_unregister_device(ndev->nci_dev);
+	nci_unregister_device(nsdev->ndev);
 }
 EXPORT_SYMBOL_GPL(nci_spi_unregister_device);
 
-static int send_acknowledge(struct nci_spi_dev *ndev, u8 acknowledge)
+static int send_acknowledge(struct nci_spi_dev *nsdev, u8 acknowledge)
 {
 	struct sk_buff *skb;
 	unsigned char *hdr;
 	u16 crc;
 	int ret;
 
-	skb = nci_skb_alloc(ndev->nci_dev, 0, GFP_KERNEL);
+	skb = nci_skb_alloc(nsdev->ndev, 0, GFP_KERNEL);
 
 	/* add the NCI SPI header to the start of the buffer */
 	hdr = skb_push(skb, NCI_SPI_HDR_LEN);
@@ -225,14 +225,14 @@ static int send_acknowledge(struct nci_spi_dev *ndev, u8 acknowledge)
 	*skb_put(skb, 1) = crc >> 8;
 	*skb_put(skb, 1) = crc & 0xFF;
 
-	ret = __nci_spi_send(ndev, skb);
+	ret = __nci_spi_send(nsdev, skb);
 
 	kfree_skb(skb);
 
 	return ret;
 }
 
-static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *ndev)
+static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 {
 	struct sk_buff *skb;
 	struct spi_message m;
@@ -243,7 +243,7 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *ndev)
 
 	spi_message_init(&m);
 	req[0] = NCI_SPI_DIRECT_READ;
-	req[1] = ndev->acknowledge_mode;
+	req[1] = nsdev->acknowledge_mode;
 	tx.tx_buf = req;
 	tx.len = 2;
 	tx.cs_change = 0;
@@ -252,18 +252,18 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *ndev)
 	rx.len = 2;
 	rx.cs_change = 1;
 	spi_message_add_tail(&rx, &m);
-	ret = spi_sync(ndev->spi, &m);
+	ret = spi_sync(nsdev->spi, &m);
 
 	if (ret)
 		return NULL;
 
-	if (ndev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
+	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
 		rx_len = ((resp_hdr[0] & NCI_SPI_MSB_PAYLOAD_MASK) << 8) +
 				resp_hdr[1] + NCI_SPI_CRC_LEN;
 	else
 		rx_len = (resp_hdr[0] << 8) | resp_hdr[1];
 
-	skb = nci_skb_alloc(ndev->nci_dev, rx_len, GFP_KERNEL);
+	skb = nci_skb_alloc(nsdev->ndev, rx_len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -271,14 +271,14 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *ndev)
 	rx.rx_buf = skb_put(skb, rx_len);
 	rx.len = rx_len;
 	rx.cs_change = 0;
-	rx.delay_usecs = ndev->xfer_udelay;
+	rx.delay_usecs = nsdev->xfer_udelay;
 	spi_message_add_tail(&rx, &m);
-	ret = spi_sync(ndev->spi, &m);
+	ret = spi_sync(nsdev->spi, &m);
 
 	if (ret)
 		goto receive_error;
 
-	if (ndev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		*skb_push(skb, 1) = resp_hdr[1];
 		*skb_push(skb, 1) = resp_hdr[0];
 	}
@@ -320,7 +320,7 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
 /**
  * nci_spi_recv_frame - receive frame from NCI SPI drivers
  *
- * @ndev: The nci spi device
+ * @nsdev: The nci spi device
  * Context: can sleep
  *
  * This call may only be used from a context that may sleep.  The sleep
@@ -328,32 +328,32 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
  *
  * It returns zero on success, else a negative error code.
  */
-int nci_spi_recv_frame(struct nci_spi_dev *ndev)
+int nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 {
 	struct sk_buff *skb;
 	int ret = 0;
 
-	ndev->ops->deassert_int(ndev);
+	nsdev->ops->deassert_int(nsdev);
 
 	/* Retrieve frame from SPI */
-	skb = __nci_spi_recv_frame(ndev);
+	skb = __nci_spi_recv_frame(nsdev);
 	if (!skb) {
 		ret = -EIO;
 		goto done;
 	}
 
-	if (ndev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		if (!nci_spi_check_crc(skb)) {
-			send_acknowledge(ndev, ACKNOWLEDGE_NACK);
+			send_acknowledge(nsdev, ACKNOWLEDGE_NACK);
 			goto done;
 		}
 
 		/* In case of acknowledged mode: if ACK or NACK received,
 		 * unblock completion of latest frame sent.
 		 */
-		ndev->req_result = nci_spi_get_ack(skb);
-		if (ndev->req_result)
-			complete(&ndev->req_completion);
+		nsdev->req_result = nci_spi_get_ack(skb);
+		if (nsdev->req_result)
+			complete(&nsdev->req_completion);
 	}
 
 	/* If there is no payload (ACK/NACK only frame),
@@ -364,14 +364,14 @@ int nci_spi_recv_frame(struct nci_spi_dev *ndev)
 		goto done;
 	}
 
-	if (ndev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
-		send_acknowledge(ndev, ACKNOWLEDGE_ACK);
+	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
+		send_acknowledge(nsdev, ACKNOWLEDGE_ACK);
 
 	/* Forward skb to NCI core layer */
-	ret = nci_recv_frame(ndev->nci_dev, skb);
+	ret = nci_recv_frame(nsdev->ndev, skb);
 
 done:
-	ndev->ops->assert_int(ndev);
+	nsdev->ops->assert_int(nsdev);
 
 	return ret;
 }
-- 
cgit 


From 08f13acff960d6c95a371f67ab98785aa9969179 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade <eric.lapuyade@linux.intel.com>
Date: Tue, 3 Sep 2013 11:51:00 +0200
Subject: NFC: Move struct nfc_phy_ops out of HCI up to nfc core level

struct nfc_phy_ops is not an HCI structure only, it can also be used by
NCI or direct NFC Core drivers.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 6 ------
 include/net/nfc/nfc.h | 6 ++++++
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index b64b7bce4b94..2eca2960ca9c 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -24,12 +24,6 @@
 
 #include <net/nfc/nfc.h>
 
-struct nfc_phy_ops {
-	int (*write)(void *dev_id, struct sk_buff *skb);
-	int (*enable)(void *dev_id);
-	void (*disable)(void *dev_id);
-};
-
 struct nfc_hci_dev;
 
 struct nfc_hci_ops {
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index f5c6a23636f1..c2aee4875b65 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -31,6 +31,12 @@
 #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__)
 #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__)
 
+struct nfc_phy_ops {
+	int (*write)(void *dev_id, struct sk_buff *skb);
+	int (*enable)(void *dev_id);
+	void (*disable)(void *dev_id);
+};
+
 struct nfc_dev;
 
 /**
-- 
cgit 


From fa544fff62aeeb0cf8008c61077aae10fb1407a9 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade <eric.lapuyade@linux.intel.com>
Date: Thu, 5 Sep 2013 11:02:21 +0200
Subject: NFC: NCI: Simplify NCI SPI to become a simple framing/checking layer

NCI SPI layer should not manage the nci dev, this is the job of the nci
chipset driver. This layer should be limited to frame/deframe nci
packets, and optionnaly check integrity (crc) and manage the ack/nak
protocol.

The NCI SPI must not be mixed up with an NCI dev. spi_[dev|device] are
therefore renamed to a simple spi for more clarity.
The header and crc sizes are moved to nci.h so that drivers can use
them to reserve space in outgoing skbs.
nci_spi_send() is exported to be accessible by drivers.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h      |   4 +
 include/net/nfc/nci_core.h |  41 +++--------
 net/nfc/nci/spi.c          | 180 ++++++++++++++-------------------------------
 3 files changed, 70 insertions(+), 155 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 88785e5c6b2c..e5aa5acafea0 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -166,6 +166,10 @@
 #define NCI_GID_NFCEE_MGMT					0x2
 #define NCI_GID_PROPRIETARY					0xf
 
+/* ----- NCI over SPI head/crc(tail) room needed for outgoing frames ----- */
+#define NCI_SPI_HDR_LEN						4
+#define NCI_SPI_CRC_LEN						2
+
 /* ---- NCI Packet structures ---- */
 #define NCI_CTRL_HDR_SIZE					3
 #define NCI_DATA_HDR_SIZE					3
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index c08399621c8b..37ba06f2dfa9 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -207,16 +207,14 @@ int nci_to_errno(__u8 code);
 #define NCI_SPI_CRC_ENABLED	0x01
 
 /* ----- NCI SPI structures ----- */
-struct nci_spi_dev;
+struct nci_spi;
 
 struct nci_spi_ops {
-	int (*open)(struct nci_spi_dev *nsdev);
-	int (*close)(struct nci_spi_dev *nsdev);
-	void (*assert_int)(struct nci_spi_dev *nsdev);
-	void (*deassert_int)(struct nci_spi_dev *nsdev);
+	void (*assert_int)(struct nci_spi *nspi);
+	void (*deassert_int)(struct nci_spi *nspi);
 };
 
-struct nci_spi_dev {
+struct nci_spi {
 	struct nci_dev		*ndev;
 	struct spi_device	*spi;
 	struct nci_spi_ops	*ops;
@@ -227,31 +225,14 @@ struct nci_spi_dev {
 
 	struct completion	req_completion;
 	u8			req_result;
-
-	void			*driver_data;
 };
 
-/* ----- NCI SPI Devices ----- */
-struct nci_spi_dev *nci_spi_allocate_device(struct spi_device *spi,
-						struct nci_spi_ops *ops,
-						u32 supported_protocols,
-						u32 supported_se,
-						u8 acknowledge_mode,
-						unsigned int delay);
-void nci_spi_free_device(struct nci_spi_dev *nsdev);
-int nci_spi_register_device(struct nci_spi_dev *nsdev);
-void nci_spi_unregister_device(struct nci_spi_dev *nsdev);
-int nci_spi_recv_frame(struct nci_spi_dev *nsdev);
-
-static inline void nci_spi_set_drvdata(struct nci_spi_dev *nsdev,
-					    void *data)
-{
-	nsdev->driver_data = data;
-}
-
-static inline void *nci_spi_get_drvdata(struct nci_spi_dev *nsdev)
-{
-	return nsdev->driver_data;
-}
+/* ----- NCI SPI ----- */
+struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
+				     struct nci_spi_ops *ops,
+				     u8 acknowledge_mode, unsigned int delay,
+				     struct nci_dev *ndev);
+int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb);
+int nci_spi_recv_frame(struct nci_spi *nspi);
 
 #endif /* __NCI_CORE_H */
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index e66fda4d9ede..910dfd8015f4 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -24,8 +24,6 @@
 #include <linux/nfc.h>
 #include <net/nfc/nci_core.h>
 
-#define NCI_SPI_HDR_LEN			4
-#define NCI_SPI_CRC_LEN			2
 #define NCI_SPI_ACK_SHIFT		6
 #define NCI_SPI_MSB_PAYLOAD_MASK	0x3F
 
@@ -41,21 +39,7 @@
 
 #define CRC_INIT		0xFFFF
 
-static int nci_spi_open(struct nci_dev *ndev)
-{
-	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
-
-	return nsdev->ops->open(nsdev);
-}
-
-static int nci_spi_close(struct nci_dev *ndev)
-{
-	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
-
-	return nsdev->ops->close(nsdev);
-}
-
-static int __nci_spi_send(struct nci_spi_dev *nsdev, struct sk_buff *skb)
+static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
 {
 	struct spi_message m;
 	struct spi_transfer t;
@@ -63,32 +47,31 @@ static int __nci_spi_send(struct nci_spi_dev *nsdev, struct sk_buff *skb)
 	t.tx_buf = skb->data;
 	t.len = skb->len;
 	t.cs_change = 0;
-	t.delay_usecs = nsdev->xfer_udelay;
+	t.delay_usecs = nspi->xfer_udelay;
 
 	spi_message_init(&m);
 	spi_message_add_tail(&t, &m);
 
-	return spi_sync(nsdev->spi, &m);
+	return spi_sync(nspi->spi, &m);
 }
 
-static int nci_spi_send(struct nci_dev *ndev, struct sk_buff *skb)
+int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
 {
-	struct nci_spi_dev *nsdev = nci_get_drvdata(ndev);
 	unsigned int payload_len = skb->len;
 	unsigned char *hdr;
 	int ret;
 	long completion_rc;
 
-	nsdev->ops->deassert_int(nsdev);
+	nspi->ops->deassert_int(nspi);
 
 	/* add the NCI SPI header to the start of the buffer */
 	hdr = skb_push(skb, NCI_SPI_HDR_LEN);
 	hdr[0] = NCI_SPI_DIRECT_WRITE;
-	hdr[1] = nsdev->acknowledge_mode;
+	hdr[1] = nspi->acknowledge_mode;
 	hdr[2] = payload_len >> 8;
 	hdr[3] = payload_len & 0xFF;
 
-	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		u16 crc;
 
 		crc = crc_ccitt(CRC_INIT, skb->data, skb->len);
@@ -96,123 +79,70 @@ static int nci_spi_send(struct nci_dev *ndev, struct sk_buff *skb)
 		*skb_put(skb, 1) = crc & 0xFF;
 	}
 
-	ret = __nci_spi_send(nsdev, skb);
+	ret = __nci_spi_send(nspi, skb);
 
 	kfree_skb(skb);
-	nsdev->ops->assert_int(nsdev);
+	nspi->ops->assert_int(nspi);
 
-	if (ret != 0 || nsdev->acknowledge_mode == NCI_SPI_CRC_DISABLED)
+	if (ret != 0 || nspi->acknowledge_mode == NCI_SPI_CRC_DISABLED)
 		goto done;
 
-	init_completion(&nsdev->req_completion);
+	init_completion(&nspi->req_completion);
 	completion_rc =	wait_for_completion_interruptible_timeout(
-							&nsdev->req_completion,
+							&nspi->req_completion,
 							NCI_SPI_SEND_TIMEOUT);
 
-	if (completion_rc <= 0 || nsdev->req_result == ACKNOWLEDGE_NACK)
+	if (completion_rc <= 0 || nspi->req_result == ACKNOWLEDGE_NACK)
 		ret = -EIO;
 
 done:
 	return ret;
 }
-
-static struct nci_ops nci_spi_ops = {
-	.open = nci_spi_open,
-	.close = nci_spi_close,
-	.send = nci_spi_send,
-};
+EXPORT_SYMBOL_GPL(nci_spi_send);
 
 /* ---- Interface to NCI SPI drivers ---- */
 
 /**
- * nci_spi_allocate_device - allocate a new nci spi device
+ * nci_spi_allocate_spi - allocate a new nci spi
  *
  * @spi: SPI device
  * @ops: device operations
- * @supported_protocols: NFC protocols supported by the device
- * @supported_se: NFC Secure Elements supported by the device
- * @acknowledge_mode: Acknowledge mode used by the device
+ * @acknowledge_mode: Acknowledge mode used by the NFC device
  * @delay: delay between transactions in us
+ * @ndev: nci dev to send incoming nci frames to
  */
-struct nci_spi_dev *nci_spi_allocate_device(struct spi_device *spi,
-						struct nci_spi_ops *ops,
-						u32 supported_protocols,
-						u32 supported_se,
-						u8 acknowledge_mode,
-						unsigned int delay)
+struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
+				     struct nci_spi_ops *ops,
+				     u8 acknowledge_mode, unsigned int delay,
+				     struct nci_dev *ndev)
 {
-	struct nci_spi_dev *nsdev;
-	int tailroom = 0;
-
-	if (!ops->open || !ops->close || !ops->assert_int || !ops->deassert_int)
-		return NULL;
-
-	if (!supported_protocols)
-		return NULL;
+	struct nci_spi *nspi;
 
-	nsdev = devm_kzalloc(&spi->dev, sizeof(struct nci_spi_dev), GFP_KERNEL);
-	if (!nsdev)
+	if (!ops->assert_int || !ops->deassert_int)
 		return NULL;
 
-	nsdev->ops = ops;
-	nsdev->acknowledge_mode = acknowledge_mode;
-	nsdev->xfer_udelay = delay;
-
-	if (acknowledge_mode == NCI_SPI_CRC_ENABLED)
-		tailroom += NCI_SPI_CRC_LEN;
-
-	nsdev->ndev = nci_allocate_device(&nci_spi_ops, supported_protocols,
-					  NCI_SPI_HDR_LEN, tailroom);
-	if (!nsdev->ndev)
+	nspi = devm_kzalloc(&spi->dev, sizeof(struct nci_spi), GFP_KERNEL);
+	if (!nspi)
 		return NULL;
 
-	nci_set_drvdata(nsdev->ndev, nsdev);
-
-	return nsdev;
-}
-EXPORT_SYMBOL_GPL(nci_spi_allocate_device);
-
-/**
- * nci_spi_free_device - deallocate nci spi device
- *
- * @nsdev: The nci spi device to deallocate
- */
-void nci_spi_free_device(struct nci_spi_dev *nsdev)
-{
-	nci_free_device(nsdev->ndev);
-}
-EXPORT_SYMBOL_GPL(nci_spi_free_device);
+	nspi->ops = ops;
+	nspi->acknowledge_mode = acknowledge_mode;
+	nspi->xfer_udelay = delay;
 
-/**
- * nci_spi_register_device - register a nci spi device in the nfc subsystem
- *
- * @pdev: The nci spi device to register
- */
-int nci_spi_register_device(struct nci_spi_dev *nsdev)
-{
-	return nci_register_device(nsdev->ndev);
-}
-EXPORT_SYMBOL_GPL(nci_spi_register_device);
+	nspi->ndev = ndev;
 
-/**
- * nci_spi_unregister_device - unregister a nci spi device in the nfc subsystem
- *
- * @dev: The nci spi device to unregister
- */
-void nci_spi_unregister_device(struct nci_spi_dev *nsdev)
-{
-	nci_unregister_device(nsdev->ndev);
+	return nspi;
 }
-EXPORT_SYMBOL_GPL(nci_spi_unregister_device);
+EXPORT_SYMBOL_GPL(nci_spi_allocate_spi);
 
-static int send_acknowledge(struct nci_spi_dev *nsdev, u8 acknowledge)
+static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
 {
 	struct sk_buff *skb;
 	unsigned char *hdr;
 	u16 crc;
 	int ret;
 
-	skb = nci_skb_alloc(nsdev->ndev, 0, GFP_KERNEL);
+	skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL);
 
 	/* add the NCI SPI header to the start of the buffer */
 	hdr = skb_push(skb, NCI_SPI_HDR_LEN);
@@ -225,14 +155,14 @@ static int send_acknowledge(struct nci_spi_dev *nsdev, u8 acknowledge)
 	*skb_put(skb, 1) = crc >> 8;
 	*skb_put(skb, 1) = crc & 0xFF;
 
-	ret = __nci_spi_send(nsdev, skb);
+	ret = __nci_spi_send(nspi, skb);
 
 	kfree_skb(skb);
 
 	return ret;
 }
 
-static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *nsdev)
+static struct sk_buff *__nci_spi_recv_frame(struct nci_spi *nspi)
 {
 	struct sk_buff *skb;
 	struct spi_message m;
@@ -243,7 +173,7 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 
 	spi_message_init(&m);
 	req[0] = NCI_SPI_DIRECT_READ;
-	req[1] = nsdev->acknowledge_mode;
+	req[1] = nspi->acknowledge_mode;
 	tx.tx_buf = req;
 	tx.len = 2;
 	tx.cs_change = 0;
@@ -252,18 +182,18 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 	rx.len = 2;
 	rx.cs_change = 1;
 	spi_message_add_tail(&rx, &m);
-	ret = spi_sync(nsdev->spi, &m);
+	ret = spi_sync(nspi->spi, &m);
 
 	if (ret)
 		return NULL;
 
-	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
+	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED)
 		rx_len = ((resp_hdr[0] & NCI_SPI_MSB_PAYLOAD_MASK) << 8) +
 				resp_hdr[1] + NCI_SPI_CRC_LEN;
 	else
 		rx_len = (resp_hdr[0] << 8) | resp_hdr[1];
 
-	skb = nci_skb_alloc(nsdev->ndev, rx_len, GFP_KERNEL);
+	skb = nci_skb_alloc(nspi->ndev, rx_len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -271,14 +201,14 @@ static struct sk_buff *__nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 	rx.rx_buf = skb_put(skb, rx_len);
 	rx.len = rx_len;
 	rx.cs_change = 0;
-	rx.delay_usecs = nsdev->xfer_udelay;
+	rx.delay_usecs = nspi->xfer_udelay;
 	spi_message_add_tail(&rx, &m);
-	ret = spi_sync(nsdev->spi, &m);
+	ret = spi_sync(nspi->spi, &m);
 
 	if (ret)
 		goto receive_error;
 
-	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		*skb_push(skb, 1) = resp_hdr[1];
 		*skb_push(skb, 1) = resp_hdr[0];
 	}
@@ -320,7 +250,7 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
 /**
  * nci_spi_recv_frame - receive frame from NCI SPI drivers
  *
- * @nsdev: The nci spi device
+ * @nspi: The nci spi
  * Context: can sleep
  *
  * This call may only be used from a context that may sleep.  The sleep
@@ -328,32 +258,32 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
  *
  * It returns zero on success, else a negative error code.
  */
-int nci_spi_recv_frame(struct nci_spi_dev *nsdev)
+int nci_spi_recv_frame(struct nci_spi *nspi)
 {
 	struct sk_buff *skb;
 	int ret = 0;
 
-	nsdev->ops->deassert_int(nsdev);
+	nspi->ops->deassert_int(nspi);
 
 	/* Retrieve frame from SPI */
-	skb = __nci_spi_recv_frame(nsdev);
+	skb = __nci_spi_recv_frame(nspi);
 	if (!skb) {
 		ret = -EIO;
 		goto done;
 	}
 
-	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
+	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		if (!nci_spi_check_crc(skb)) {
-			send_acknowledge(nsdev, ACKNOWLEDGE_NACK);
+			send_acknowledge(nspi, ACKNOWLEDGE_NACK);
 			goto done;
 		}
 
 		/* In case of acknowledged mode: if ACK or NACK received,
 		 * unblock completion of latest frame sent.
 		 */
-		nsdev->req_result = nci_spi_get_ack(skb);
-		if (nsdev->req_result)
-			complete(&nsdev->req_completion);
+		nspi->req_result = nci_spi_get_ack(skb);
+		if (nspi->req_result)
+			complete(&nspi->req_completion);
 	}
 
 	/* If there is no payload (ACK/NACK only frame),
@@ -364,14 +294,14 @@ int nci_spi_recv_frame(struct nci_spi_dev *nsdev)
 		goto done;
 	}
 
-	if (nsdev->acknowledge_mode == NCI_SPI_CRC_ENABLED)
-		send_acknowledge(nsdev, ACKNOWLEDGE_ACK);
+	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED)
+		send_acknowledge(nspi, ACKNOWLEDGE_ACK);
 
 	/* Forward skb to NCI core layer */
-	ret = nci_recv_frame(nsdev->ndev, skb);
+	ret = nci_recv_frame(nspi->ndev, skb);
 
 done:
-	nsdev->ops->assert_int(nsdev);
+	nspi->ops->assert_int(nspi);
 
 	return ret;
 }
-- 
cgit 


From 4b10884eb428c243ae2070a539612e645f3d9b93 Mon Sep 17 00:00:00 2001
From: Thierry Escande <thierry.escande@linux.intel.com>
Date: Thu, 19 Sep 2013 17:55:25 +0200
Subject: NFC: Digital Protocol stack implementation

This is the initial commit of the NFC Digital Protocol stack
implementation.

It offers an interface for devices that don't have an embedded NFC
Digital protocol stack. The driver instantiates the digital stack by
calling nfc_digital_allocate_device(). Within the nfc_digital_ops
structure, the driver specifies a set of function pointers for driver
operations. These functions must be implemented by the driver and are:

in_configure_hw:
Hardware configuration for RF technology and communication framing in
initiator mode. This is a synchronous function.

in_send_cmd:
Initiator mode data exchange using RF technology and framing previously
set with in_configure_hw. The peer response is returned through
callback cb. If an io error occurs or the peer didn't reply within the
specified timeout (ms), the error code is passed back through the resp
pointer. This is an asynchronous function.

tg_configure_hw:
Hardware configuration for RF technology and communication framing in
target mode. This is a synchronous function.

tg_send_cmd:
Target mode data exchange using RF technology and framing previously
set with tg_configure_hw. The peer next command is returned through
callback cb. If an io error occurs or the peer didn't reply within the
specified timeout (ms), the error code is passed back through the resp
pointer. This is an asynchronous function.

tg_listen:
Put the device in listen mode waiting for data from the peer device.
This is an asynchronous function.

tg_listen_mdaa:
If supported, put the device in automatic listen mode with mode
detection and automatic anti-collision. In this mode, the device
automatically detects the RF technology and executes the
anti-collision detection using the command responses specified in
mdaa_params. The mdaa_params structure contains SENS_RES, NFCID1, and
SEL_RES for 106A RF tech. NFCID2 and system code (sc) for 212F and
424F. The driver returns the NFC-DEP ATR_REQ command through cb. The
digital stack deducts the RF tech by analyzing the SoD of the frame
containing the ATR_REQ command. This is an asynchronous function.

switch_rf:
Turns device radio on or off. The stack does not call explicitly
switch_rf to turn the radio on. A call to in|tg_configure_hw must turn
the device radio on.

abort_cmd:
Discard the last sent command.

Then the driver registers itself against the digital stack by using
nfc_digital_register_device() which in turn registers the digital stack
against the NFC core layer. The digital stack implements common NFC
operations like dev_up(), dev_down(), start_poll(), stop_poll(), etc.

This patch is only a skeleton and NFC operations are just stubs.

Signed-off-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h | 199 ++++++++++++++++++++++++++++++++++++++++++++++
 net/nfc/Kconfig           |  12 +++
 net/nfc/Makefile          |   2 +
 net/nfc/digital.h         |  27 +++++++
 net/nfc/digital_core.c    | 151 +++++++++++++++++++++++++++++++++++
 5 files changed, 391 insertions(+)
 create mode 100644 include/net/nfc/digital.h
 create mode 100644 net/nfc/digital.h
 create mode 100644 net/nfc/digital_core.c

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
new file mode 100644
index 000000000000..8e16b6e0265a
--- /dev/null
+++ b/include/net/nfc/digital.h
@@ -0,0 +1,199 @@
+/*
+ * NFC Digital Protocol stack
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __NFC_DIGITAL_H
+#define __NFC_DIGITAL_H
+
+#include <linux/skbuff.h>
+#include <net/nfc/nfc.h>
+
+/**
+ * Configuration types for in_configure_hw and tg_configure_hw.
+ */
+enum {
+	NFC_DIGITAL_CONFIG_RF_TECH = 0,
+	NFC_DIGITAL_CONFIG_FRAMING,
+};
+
+/**
+ * RF technology values passed as param argument to in_configure_hw and
+ * tg_configure_hw for NFC_DIGITAL_CONFIG_RF_TECH configuration type.
+ */
+enum {
+	NFC_DIGITAL_RF_TECH_106A = 0,
+	NFC_DIGITAL_RF_TECH_212F,
+	NFC_DIGITAL_RF_TECH_424F,
+
+	NFC_DIGITAL_RF_TECH_LAST,
+};
+
+/**
+ * Framing configuration passed as param argument to in_configure_hw and
+ * tg_configure_hw for NFC_DIGITAL_CONFIG_FRAMING configuration type.
+ */
+enum {
+	NFC_DIGITAL_FRAMING_NFCA_SHORT = 0,
+	NFC_DIGITAL_FRAMING_NFCA_STANDARD,
+	NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A,
+
+	NFC_DIGITAL_FRAMING_NFCA_T1T,
+	NFC_DIGITAL_FRAMING_NFCA_T2T,
+	NFC_DIGITAL_FRAMING_NFCA_NFC_DEP,
+
+	NFC_DIGITAL_FRAMING_NFCF,
+	NFC_DIGITAL_FRAMING_NFCF_T3T,
+	NFC_DIGITAL_FRAMING_NFCF_NFC_DEP,
+	NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED,
+
+	NFC_DIGITAL_FRAMING_LAST,
+};
+
+#define DIGITAL_MDAA_NFCID1_SIZE 3
+
+struct digital_tg_mdaa_params {
+	u16 sens_res;
+	u8 nfcid1[DIGITAL_MDAA_NFCID1_SIZE];
+	u8 sel_res;
+
+	u8 nfcid2[NFC_NFCID2_MAXSIZE];
+	u16 sc;
+};
+
+struct nfc_digital_dev;
+
+/**
+ * nfc_digital_cmd_complete_t - Definition of command result callback
+ *
+ * @ddev: nfc_digital_device ref
+ * @arg: user data
+ * @resp: response data
+ *
+ * resp pointer can be an error code and will be checked with IS_ERR() macro.
+ * The callback is responsible for freeing resp sk_buff.
+ */
+typedef void (*nfc_digital_cmd_complete_t)(struct nfc_digital_dev *ddev,
+					   void *arg, struct sk_buff *resp);
+
+/**
+ * Device side NFC Digital operations
+ *
+ * Initiator mode:
+ * @in_configure_hw: Hardware configuration for RF technology and communication
+ *	framing in initiator mode. This is a synchronous function.
+ * @in_send_cmd: Initiator mode data exchange using RF technology and framing
+ *	previously set with in_configure_hw. The peer response is returned
+ *	through callback cb. If an io error occurs or the peer didn't reply
+ *	within the specified timeout (ms), the error code is passed back through
+ *	the resp pointer. This is an asynchronous function.
+ *
+ * Target mode: Only NFC-DEP protocol is supported in target mode.
+ * @tg_configure_hw: Hardware configuration for RF technology and communication
+ *	framing in target mode. This is a synchronous function.
+ * @tg_send_cmd: Target mode data exchange using RF technology and framing
+ *	previously set with tg_configure_hw. The peer next command is returned
+ *	through callback cb. If an io error occurs or the peer didn't reply
+ *	within the specified timeout (ms), the error code is passed back through
+ *	the resp pointer. This is an asynchronous function.
+ * @tg_listen: Put the device in listen mode waiting for data from the peer
+ *	device. This is an asynchronous function.
+ * @tg_listen_mdaa: If supported, put the device in automatic listen mode with
+ *	mode detection and automatic anti-collision. In this mode, the device
+ *	automatically detects the RF technology and executes the anti-collision
+ *	detection using the command responses specified in mdaa_params. The
+ *	mdaa_params structure contains SENS_RES, NFCID1, and SEL_RES for 106A RF
+ *	tech. NFCID2 and system code (sc) for 212F and 424F. The driver returns
+ *	the NFC-DEP ATR_REQ command through cb. The digital stack deducts the RF
+ *	tech by analyzing the SoD of the frame containing the ATR_REQ command.
+ *	This is an asynchronous function.
+ *
+ * @switch_rf: Turns device radio on or off. The stack does not call explicitly
+ *	switch_rf to turn the radio on. A call to in|tg_configure_hw must turn
+ *	the device radio on.
+ * @abort_cmd: Discard the last sent command.
+ */
+struct nfc_digital_ops {
+	int (*in_configure_hw)(struct nfc_digital_dev *ddev, int type,
+			       int param);
+	int (*in_send_cmd)(struct nfc_digital_dev *ddev, struct sk_buff *skb,
+			   u16 timeout, nfc_digital_cmd_complete_t cb,
+			   void *arg);
+
+	int (*tg_configure_hw)(struct nfc_digital_dev *ddev, int type,
+			       int param);
+	int (*tg_send_cmd)(struct nfc_digital_dev *ddev, struct sk_buff *skb,
+			   u16 timeout, nfc_digital_cmd_complete_t cb,
+			   void *arg);
+	int (*tg_listen)(struct nfc_digital_dev *ddev, u16 timeout,
+			 nfc_digital_cmd_complete_t cb, void *arg);
+	int (*tg_listen_mdaa)(struct nfc_digital_dev *ddev,
+			      struct digital_tg_mdaa_params *mdaa_params,
+			      u16 timeout, nfc_digital_cmd_complete_t cb,
+			      void *arg);
+
+	int (*switch_rf)(struct nfc_digital_dev *ddev, bool on);
+	void (*abort_cmd)(struct nfc_digital_dev *ddev);
+};
+
+/**
+ * Driver capabilities - bit mask made of the following values
+ *
+ * @NFC_DIGITAL_DRV_CAPS_IN_CRC: The driver handles CRC calculation in initiator
+ *	mode.
+ * @NFC_DIGITAL_DRV_CAPS_TG_CRC: The driver handles CRC calculation in target
+ *	mode.
+ */
+#define NFC_DIGITAL_DRV_CAPS_IN_CRC	0x0001
+#define NFC_DIGITAL_DRV_CAPS_TG_CRC	0x0002
+
+struct nfc_digital_dev {
+	struct nfc_dev *nfc_dev;
+	struct nfc_digital_ops *ops;
+
+	u32 protocols;
+
+	int tx_headroom;
+	int tx_tailroom;
+
+	u32 driver_capabilities;
+	void *driver_data;
+};
+
+struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
+						    __u32 supported_protocols,
+						    __u32 driver_capabilities,
+						    int tx_headroom,
+						    int tx_tailroom);
+void nfc_digital_free_device(struct nfc_digital_dev *ndev);
+int nfc_digital_register_device(struct nfc_digital_dev *ndev);
+void nfc_digital_unregister_device(struct nfc_digital_dev *ndev);
+
+static inline void nfc_digital_set_parent_dev(struct nfc_digital_dev *ndev,
+					      struct device *dev)
+{
+	nfc_set_parent_dev(ndev->nfc_dev, dev);
+}
+
+static inline void nfc_digital_set_drvdata(struct nfc_digital_dev *dev,
+					   void *data)
+{
+	dev->driver_data = data;
+}
+
+static inline void *nfc_digital_get_drvdata(struct nfc_digital_dev *dev)
+{
+	return dev->driver_data;
+}
+
+#endif /* __NFC_DIGITAL_H */
diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig
index 5948b2fc72f6..13e1237e1ea1 100644
--- a/net/nfc/Kconfig
+++ b/net/nfc/Kconfig
@@ -14,6 +14,18 @@ menuconfig NFC
 	  To compile this support as a module, choose M here: the module will
 	  be called nfc.
 
+config NFC_DIGITAL
+	depends on NFC
+	tristate "NFC Digital Protocol stack support"
+	default n
+	help
+	  Say Y if you want to build NFC digital protocol stack support.
+	  This is needed by NFC chipsets whose firmware only implement
+	  the NFC analog layer.
+
+	  To compile this support as a module, choose M here: the module will
+	  be called nfc_digital.
+
 source "net/nfc/nci/Kconfig"
 source "net/nfc/hci/Kconfig"
 
diff --git a/net/nfc/Makefile b/net/nfc/Makefile
index a76f4533cb6c..8e0cabd85e99 100644
--- a/net/nfc/Makefile
+++ b/net/nfc/Makefile
@@ -5,7 +5,9 @@
 obj-$(CONFIG_NFC) += nfc.o
 obj-$(CONFIG_NFC_NCI) += nci/
 obj-$(CONFIG_NFC_HCI) += hci/
+obj-$(CONFIG_NFC_DIGITAL) += nfc_digital.o
 
 nfc-objs := core.o netlink.o af_nfc.o rawsock.o llcp_core.o llcp_commands.o \
 		llcp_sock.o
 
+nfc_digital-objs := digital_core.o
diff --git a/net/nfc/digital.h b/net/nfc/digital.h
new file mode 100644
index 000000000000..8d91ed820912
--- /dev/null
+++ b/net/nfc/digital.h
@@ -0,0 +1,27 @@
+/*
+ * NFC Digital Protocol stack
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __DIGITAL_H
+#define __DIGITAL_H
+
+#include <net/nfc/nfc.h>
+#include <net/nfc/digital.h>
+
+#define PR_DBG(fmt, ...)  pr_debug("%s: " fmt "\n", __func__, ##__VA_ARGS__)
+#define PR_ERR(fmt, ...)  pr_err("%s: " fmt "\n", __func__, ##__VA_ARGS__)
+#define PROTOCOL_ERR(req) pr_err("%s:%d: NFC Digital Protocol error: %s\n", \
+				 __func__, __LINE__, req)
+
+#endif /* __DIGITAL_H */
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
new file mode 100644
index 000000000000..471188a0d2e0
--- /dev/null
+++ b/net/nfc/digital_core.c
@@ -0,0 +1,151 @@
+/*
+ * NFC Digital Protocol stack
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+
+#include "digital.h"
+
+static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols,
+			      __u32 tm_protocols)
+{
+	return -EOPNOTSUPP;
+}
+
+static void digital_stop_poll(struct nfc_dev *nfc_dev)
+{
+}
+
+static int digital_dev_up(struct nfc_dev *nfc_dev)
+{
+	return -EOPNOTSUPP;
+}
+
+static int digital_dev_down(struct nfc_dev *nfc_dev)
+{
+	return -EOPNOTSUPP;
+}
+
+static int digital_dep_link_up(struct nfc_dev *nfc_dev,
+			       struct nfc_target *target,
+			       __u8 comm_mode, __u8 *gb, size_t gb_len)
+{
+	return -EOPNOTSUPP;
+}
+
+static int digital_dep_link_down(struct nfc_dev *nfc_dev)
+{
+	return -EOPNOTSUPP;
+}
+
+static int digital_activate_target(struct nfc_dev *nfc_dev,
+				   struct nfc_target *target, __u32 protocol)
+{
+	return -EOPNOTSUPP;
+}
+
+static void digital_deactivate_target(struct nfc_dev *nfc_dev,
+				      struct nfc_target *target)
+{
+}
+
+static int digital_tg_send(struct nfc_dev *dev, struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
+static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
+			   struct sk_buff *skb, data_exchange_cb_t cb,
+			   void *cb_context)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct nfc_ops digital_nfc_ops = {
+	.dev_up = digital_dev_up,
+	.dev_down = digital_dev_down,
+	.start_poll = digital_start_poll,
+	.stop_poll = digital_stop_poll,
+	.dep_link_up = digital_dep_link_up,
+	.dep_link_down = digital_dep_link_down,
+	.activate_target = digital_activate_target,
+	.deactivate_target = digital_deactivate_target,
+	.tm_send = digital_tg_send,
+	.im_transceive = digital_in_send,
+};
+
+struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
+					    __u32 supported_protocols,
+					    __u32 driver_capabilities,
+					    int tx_headroom, int tx_tailroom)
+{
+	struct nfc_digital_dev *ddev;
+
+	if (!ops->in_configure_hw || !ops->in_send_cmd || !ops->tg_listen ||
+	    !ops->tg_configure_hw || !ops->tg_send_cmd || !ops->abort_cmd ||
+	    !ops->switch_rf)
+		return NULL;
+
+	ddev = kzalloc(sizeof(struct nfc_digital_dev), GFP_KERNEL);
+	if (!ddev) {
+		PR_ERR("kzalloc failed");
+		return NULL;
+	}
+
+	ddev->driver_capabilities = driver_capabilities;
+	ddev->ops = ops;
+
+	ddev->tx_headroom = tx_headroom;
+	ddev->tx_tailroom = tx_tailroom;
+
+	ddev->nfc_dev = nfc_allocate_device(&digital_nfc_ops, ddev->protocols,
+					    ddev->tx_headroom,
+					    ddev->tx_tailroom);
+	if (!ddev->nfc_dev) {
+		PR_ERR("nfc_allocate_device failed");
+		goto free_dev;
+	}
+
+	nfc_set_drvdata(ddev->nfc_dev, ddev);
+
+	return ddev;
+
+free_dev:
+	kfree(ddev);
+
+	return NULL;
+}
+EXPORT_SYMBOL(nfc_digital_allocate_device);
+
+void nfc_digital_free_device(struct nfc_digital_dev *ddev)
+{
+	nfc_free_device(ddev->nfc_dev);
+
+	kfree(ddev);
+}
+EXPORT_SYMBOL(nfc_digital_free_device);
+
+int nfc_digital_register_device(struct nfc_digital_dev *ddev)
+{
+	return nfc_register_device(ddev->nfc_dev);
+}
+EXPORT_SYMBOL(nfc_digital_register_device);
+
+void nfc_digital_unregister_device(struct nfc_digital_dev *ddev)
+{
+	nfc_unregister_device(ddev->nfc_dev);
+}
+EXPORT_SYMBOL(nfc_digital_unregister_device);
+
+MODULE_LICENSE("GPL");
-- 
cgit 


From 59ee2361c9248f07846f7a6e585768dcce18fb16 Mon Sep 17 00:00:00 2001
From: Thierry Escande <thierry.escande@linux.intel.com>
Date: Thu, 19 Sep 2013 17:55:26 +0200
Subject: NFC Digital: Implement driver commands mechanism

This implements the mechanism used to send commands to the driver in
initiator mode through in_send_cmd().

Commands are serialized and sent to the driver by using a work item
on the system workqueue. Responses are handled asynchronously by
another work item. Once the digital stack receives the response through
the command_complete callback, the next command is sent to the driver.

This also implements the polling mechanism. It's handled by a work item
cycling on all supported protocols. The start poll command for a given
protocol is sent to the driver using the mechanism described above.
The process continues until a peer is discovered or stop_poll is
called. This patch implements the poll function for NFC-A that sends a
SENS_REQ command and waits for the SENS_RES response.

Signed-off-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h    |  25 ++++
 net/nfc/Makefile             |   2 +-
 net/nfc/digital.h            |  29 ++++
 net/nfc/digital_core.c       | 340 ++++++++++++++++++++++++++++++++++++++++++-
 net/nfc/digital_technology.c |  64 ++++++++
 5 files changed, 452 insertions(+), 8 deletions(-)
 create mode 100644 net/nfc/digital_technology.c

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 8e16b6e0265a..aabd89400d23 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -146,6 +146,15 @@ struct nfc_digital_ops {
 	void (*abort_cmd)(struct nfc_digital_dev *ddev);
 };
 
+#define NFC_DIGITAL_POLL_MODE_COUNT_MAX	6 /* 106A, 212F, and 424F in & tg */
+
+typedef int (*digital_poll_t)(struct nfc_digital_dev *ddev, u8 rf_tech);
+
+struct digital_poll_tech {
+	u8 rf_tech;
+	digital_poll_t poll_func;
+};
+
 /**
  * Driver capabilities - bit mask made of the following values
  *
@@ -168,6 +177,22 @@ struct nfc_digital_dev {
 
 	u32 driver_capabilities;
 	void *driver_data;
+
+	struct digital_poll_tech poll_techs[NFC_DIGITAL_POLL_MODE_COUNT_MAX];
+	u8 poll_tech_count;
+	u8 poll_tech_index;
+	struct mutex poll_lock;
+
+	struct work_struct cmd_work;
+	struct work_struct cmd_complete_work;
+	struct list_head cmd_queue;
+	struct mutex cmd_lock;
+
+	struct work_struct poll_work;
+
+	u8 curr_protocol;
+	u8 curr_rf_tech;
+	u8 curr_nfc_dep_pni;
 };
 
 struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
diff --git a/net/nfc/Makefile b/net/nfc/Makefile
index 8e0cabd85e99..2db39713a907 100644
--- a/net/nfc/Makefile
+++ b/net/nfc/Makefile
@@ -10,4 +10,4 @@ obj-$(CONFIG_NFC_DIGITAL) += nfc_digital.o
 nfc-objs := core.o netlink.o af_nfc.o rawsock.o llcp_core.o llcp_commands.o \
 		llcp_sock.o
 
-nfc_digital-objs := digital_core.o
+nfc_digital-objs := digital_core.o digital_technology.o
diff --git a/net/nfc/digital.h b/net/nfc/digital.h
index 8d91ed820912..0a2767098daa 100644
--- a/net/nfc/digital.h
+++ b/net/nfc/digital.h
@@ -24,4 +24,33 @@
 #define PROTOCOL_ERR(req) pr_err("%s:%d: NFC Digital Protocol error: %s\n", \
 				 __func__, __LINE__, req)
 
+#define DIGITAL_CMD_IN_SEND        0
+#define DIGITAL_CMD_TG_SEND        1
+#define DIGITAL_CMD_TG_LISTEN      2
+#define DIGITAL_CMD_TG_LISTEN_MDAA 3
+
+#define DIGITAL_MAX_HEADER_LEN 7
+#define DIGITAL_CRC_LEN        2
+
+struct sk_buff *digital_skb_alloc(struct nfc_digital_dev *ddev,
+				  unsigned int len);
+
+int digital_send_cmd(struct nfc_digital_dev *ddev, u8 cmd_type,
+		     struct sk_buff *skb, u16 timeout,
+		     nfc_digital_cmd_complete_t cmd_cb, void *cb_context);
+
+int digital_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param);
+static inline int digital_in_send_cmd(struct nfc_digital_dev *ddev,
+				      struct sk_buff *skb, u16 timeout,
+				      nfc_digital_cmd_complete_t cmd_cb,
+				      void *cb_context)
+{
+	return digital_send_cmd(ddev, DIGITAL_CMD_IN_SEND, skb, timeout, cmd_cb,
+				cb_context);
+}
+
+void digital_poll_next_tech(struct nfc_digital_dev *ddev);
+
+int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech);
+
 #endif /* __DIGITAL_H */
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index 471188a0d2e0..13abd293ca37 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -17,24 +17,319 @@
 
 #include "digital.h"
 
+#define DIGITAL_PROTO_NFCA_RF_TECH \
+	(NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK)
+
+struct digital_cmd {
+	struct list_head queue;
+
+	u8 type;
+	u8 pending;
+
+	u16 timeout;
+	struct sk_buff *req;
+	struct sk_buff *resp;
+
+	nfc_digital_cmd_complete_t cmd_cb;
+	void *cb_context;
+};
+
+struct sk_buff *digital_skb_alloc(struct nfc_digital_dev *ddev,
+				  unsigned int len)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(len + ddev->tx_headroom + ddev->tx_tailroom,
+			GFP_KERNEL);
+	if (skb)
+		skb_reserve(skb, ddev->tx_headroom);
+
+	return skb;
+}
+
+static inline void digital_switch_rf(struct nfc_digital_dev *ddev, bool on)
+{
+	ddev->ops->switch_rf(ddev, on);
+}
+
+static inline void digital_abort_cmd(struct nfc_digital_dev *ddev)
+{
+	ddev->ops->abort_cmd(ddev);
+}
+
+static void digital_wq_cmd_complete(struct work_struct *work)
+{
+	struct digital_cmd *cmd;
+	struct nfc_digital_dev *ddev = container_of(work,
+						    struct nfc_digital_dev,
+						    cmd_complete_work);
+
+	mutex_lock(&ddev->cmd_lock);
+
+	cmd = list_first_entry_or_null(&ddev->cmd_queue, struct digital_cmd,
+				       queue);
+	if (!cmd) {
+		mutex_unlock(&ddev->cmd_lock);
+		return;
+	}
+
+	list_del(&cmd->queue);
+
+	mutex_unlock(&ddev->cmd_lock);
+
+	if (!IS_ERR(cmd->resp))
+		print_hex_dump_debug("DIGITAL RX: ", DUMP_PREFIX_NONE, 16, 1,
+				     cmd->resp->data, cmd->resp->len, false);
+
+	cmd->cmd_cb(ddev, cmd->cb_context, cmd->resp);
+
+	kfree(cmd);
+
+	schedule_work(&ddev->cmd_work);
+}
+
+static void digital_send_cmd_complete(struct nfc_digital_dev *ddev,
+				      void *arg, struct sk_buff *resp)
+{
+	struct digital_cmd *cmd = arg;
+
+	cmd->resp = resp;
+
+	schedule_work(&ddev->cmd_complete_work);
+}
+
+static void digital_wq_cmd(struct work_struct *work)
+{
+	int rc;
+	struct digital_cmd *cmd;
+	struct nfc_digital_dev *ddev = container_of(work,
+						    struct nfc_digital_dev,
+						    cmd_work);
+
+	mutex_lock(&ddev->cmd_lock);
+
+	cmd = list_first_entry_or_null(&ddev->cmd_queue, struct digital_cmd,
+				       queue);
+	if (!cmd || cmd->pending) {
+		mutex_unlock(&ddev->cmd_lock);
+		return;
+	}
+
+	mutex_unlock(&ddev->cmd_lock);
+
+	if (cmd->req)
+		print_hex_dump_debug("DIGITAL TX: ", DUMP_PREFIX_NONE, 16, 1,
+				     cmd->req->data, cmd->req->len, false);
+
+	switch (cmd->type) {
+	case DIGITAL_CMD_IN_SEND:
+		rc = ddev->ops->in_send_cmd(ddev, cmd->req, cmd->timeout,
+					    digital_send_cmd_complete, cmd);
+		break;
+	default:
+		PR_ERR("Unknown cmd type %d", cmd->type);
+		return;
+	}
+
+	if (!rc)
+		return;
+
+	PR_ERR("in_send_command returned err %d", rc);
+
+	mutex_lock(&ddev->cmd_lock);
+	list_del(&cmd->queue);
+	mutex_unlock(&ddev->cmd_lock);
+
+	kfree_skb(cmd->req);
+	kfree(cmd);
+
+	schedule_work(&ddev->cmd_work);
+}
+
+int digital_send_cmd(struct nfc_digital_dev *ddev, u8 cmd_type,
+		     struct sk_buff *skb, u16 timeout,
+		     nfc_digital_cmd_complete_t cmd_cb, void *cb_context)
+{
+	struct digital_cmd *cmd;
+
+	cmd = kzalloc(sizeof(struct digital_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->type = cmd_type;
+	cmd->timeout = timeout;
+	cmd->req = skb;
+	cmd->cmd_cb = cmd_cb;
+	cmd->cb_context = cb_context;
+	INIT_LIST_HEAD(&cmd->queue);
+
+	mutex_lock(&ddev->cmd_lock);
+	list_add_tail(&cmd->queue, &ddev->cmd_queue);
+	mutex_unlock(&ddev->cmd_lock);
+
+	schedule_work(&ddev->cmd_work);
+
+	return 0;
+}
+
+int digital_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param)
+{
+	int rc;
+
+	rc = ddev->ops->in_configure_hw(ddev, type, param);
+	if (rc)
+		PR_ERR("in_configure_hw failed: %d", rc);
+
+	return rc;
+}
+
+void digital_poll_next_tech(struct nfc_digital_dev *ddev)
+{
+	digital_switch_rf(ddev, 0);
+
+	mutex_lock(&ddev->poll_lock);
+
+	if (!ddev->poll_tech_count) {
+		mutex_unlock(&ddev->poll_lock);
+		return;
+	}
+
+	ddev->poll_tech_index = (ddev->poll_tech_index + 1) %
+				ddev->poll_tech_count;
+
+	mutex_unlock(&ddev->poll_lock);
+
+	schedule_work(&ddev->poll_work);
+}
+
+static void digital_wq_poll(struct work_struct *work)
+{
+	int rc;
+	struct digital_poll_tech *poll_tech;
+	struct nfc_digital_dev *ddev = container_of(work,
+						    struct nfc_digital_dev,
+						    poll_work);
+	mutex_lock(&ddev->poll_lock);
+
+	if (!ddev->poll_tech_count) {
+		mutex_unlock(&ddev->poll_lock);
+		return;
+	}
+
+	poll_tech = &ddev->poll_techs[ddev->poll_tech_index];
+
+	mutex_unlock(&ddev->poll_lock);
+
+	rc = poll_tech->poll_func(ddev, poll_tech->rf_tech);
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+static void digital_add_poll_tech(struct nfc_digital_dev *ddev, u8 rf_tech,
+				  digital_poll_t poll_func)
+{
+	struct digital_poll_tech *poll_tech;
+
+	if (ddev->poll_tech_count >= NFC_DIGITAL_POLL_MODE_COUNT_MAX)
+		return;
+
+	poll_tech = &ddev->poll_techs[ddev->poll_tech_count++];
+
+	poll_tech->rf_tech = rf_tech;
+	poll_tech->poll_func = poll_func;
+}
+
+/**
+ * start_poll operation
+ *
+ * For every supported protocol, the corresponding polling function is added
+ * to the table of polling technologies (ddev->poll_techs[]) using
+ * digital_add_poll_tech().
+ * When a polling function fails (by timeout or protocol error) the next one is
+ * schedule by digital_poll_next_tech() on the poll workqueue (ddev->poll_work).
+ */
 static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols,
 			      __u32 tm_protocols)
 {
-	return -EOPNOTSUPP;
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+	u32 matching_im_protocols, matching_tm_protocols;
+
+	PR_DBG("protocols: im 0x%x, tm 0x%x, supported 0x%x", im_protocols,
+	       tm_protocols, ddev->protocols);
+
+	matching_im_protocols = ddev->protocols & im_protocols;
+	matching_tm_protocols = ddev->protocols & tm_protocols;
+
+	if (!matching_im_protocols && !matching_tm_protocols) {
+		PR_ERR("No known protocol");
+		return -EINVAL;
+	}
+
+	if (ddev->poll_tech_count) {
+		PR_ERR("Already polling");
+		return -EBUSY;
+	}
+
+	if (ddev->curr_protocol) {
+		PR_ERR("A target is already active");
+		return -EBUSY;
+	}
+
+	ddev->poll_tech_count = 0;
+	ddev->poll_tech_index = 0;
+
+	if (matching_im_protocols & DIGITAL_PROTO_NFCA_RF_TECH)
+		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A,
+				      digital_in_send_sens_req);
+
+	if (!ddev->poll_tech_count) {
+		PR_ERR("Unsupported protocols: im=0x%x, tm=0x%x",
+		       matching_im_protocols, matching_tm_protocols);
+		return -EINVAL;
+	}
+
+	schedule_work(&ddev->poll_work);
+
+	return 0;
 }
 
 static void digital_stop_poll(struct nfc_dev *nfc_dev)
 {
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+
+	mutex_lock(&ddev->poll_lock);
+
+	if (!ddev->poll_tech_count) {
+		PR_ERR("Polling operation was not running");
+		mutex_unlock(&ddev->poll_lock);
+		return;
+	}
+
+	ddev->poll_tech_count = 0;
+
+	mutex_unlock(&ddev->poll_lock);
+
+	cancel_work_sync(&ddev->poll_work);
+
+	digital_abort_cmd(ddev);
 }
 
 static int digital_dev_up(struct nfc_dev *nfc_dev)
 {
-	return -EOPNOTSUPP;
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+
+	digital_switch_rf(ddev, 1);
+
+	return 0;
 }
 
 static int digital_dev_down(struct nfc_dev *nfc_dev)
 {
-	return -EOPNOTSUPP;
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+
+	digital_switch_rf(ddev, 0);
+
+	return 0;
 }
 
 static int digital_dep_link_up(struct nfc_dev *nfc_dev,
@@ -52,12 +347,15 @@ static int digital_dep_link_down(struct nfc_dev *nfc_dev)
 static int digital_activate_target(struct nfc_dev *nfc_dev,
 				   struct nfc_target *target, __u32 protocol)
 {
-	return -EOPNOTSUPP;
+	return 0;
 }
 
 static void digital_deactivate_target(struct nfc_dev *nfc_dev,
 				      struct nfc_target *target)
 {
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+
+	ddev->curr_protocol = 0;
 }
 
 static int digital_tg_send(struct nfc_dev *dev, struct sk_buff *skb)
@@ -106,8 +404,22 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
 	ddev->driver_capabilities = driver_capabilities;
 	ddev->ops = ops;
 
-	ddev->tx_headroom = tx_headroom;
-	ddev->tx_tailroom = tx_tailroom;
+	mutex_init(&ddev->cmd_lock);
+	INIT_LIST_HEAD(&ddev->cmd_queue);
+
+	INIT_WORK(&ddev->cmd_work, digital_wq_cmd);
+	INIT_WORK(&ddev->cmd_complete_work, digital_wq_cmd_complete);
+
+	mutex_init(&ddev->poll_lock);
+	INIT_WORK(&ddev->poll_work, digital_wq_poll);
+
+	if (supported_protocols & NFC_PROTO_JEWEL_MASK)
+		ddev->protocols |= NFC_PROTO_JEWEL_MASK;
+	if (supported_protocols & NFC_PROTO_MIFARE_MASK)
+		ddev->protocols |= NFC_PROTO_MIFARE_MASK;
+
+	ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN;
+	ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN;
 
 	ddev->nfc_dev = nfc_allocate_device(&digital_nfc_ops, ddev->protocols,
 					    ddev->tx_headroom,
@@ -131,7 +443,6 @@ EXPORT_SYMBOL(nfc_digital_allocate_device);
 void nfc_digital_free_device(struct nfc_digital_dev *ddev)
 {
 	nfc_free_device(ddev->nfc_dev);
-
 	kfree(ddev);
 }
 EXPORT_SYMBOL(nfc_digital_free_device);
@@ -144,7 +455,22 @@ EXPORT_SYMBOL(nfc_digital_register_device);
 
 void nfc_digital_unregister_device(struct nfc_digital_dev *ddev)
 {
+	struct digital_cmd *cmd, *n;
+
 	nfc_unregister_device(ddev->nfc_dev);
+
+	mutex_lock(&ddev->poll_lock);
+	ddev->poll_tech_count = 0;
+	mutex_unlock(&ddev->poll_lock);
+
+	cancel_work_sync(&ddev->poll_work);
+	cancel_work_sync(&ddev->cmd_work);
+	cancel_work_sync(&ddev->cmd_complete_work);
+
+	list_for_each_entry_safe(cmd, n, &ddev->cmd_queue, queue) {
+		list_del(&cmd->queue);
+		kfree(cmd);
+	}
 }
 EXPORT_SYMBOL(nfc_digital_unregister_device);
 
diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c
new file mode 100644
index 000000000000..084b0fba5f4d
--- /dev/null
+++ b/net/nfc/digital_technology.c
@@ -0,0 +1,64 @@
+/*
+ * NFC Digital Protocol stack
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "digital.h"
+
+#define DIGITAL_CMD_SENS_REQ    0x26
+#define DIGITAL_CMD_ALL_REQ     0x52
+#define DIGITAL_CMD_SEL_REQ_CL1 0x93
+#define DIGITAL_CMD_SEL_REQ_CL2 0x95
+#define DIGITAL_CMD_SEL_REQ_CL3 0x97
+
+#define DIGITAL_SDD_REQ_SEL_PAR 0x20
+
+#define DIGITAL_SDD_RES_CT  0x88
+#define DIGITAL_SDD_RES_LEN 5
+
+static void digital_in_recv_sens_res(struct nfc_digital_dev *ddev, void *arg,
+				     struct sk_buff *resp)
+{
+	if (!IS_ERR(resp))
+		dev_kfree_skb(resp);
+
+	digital_poll_next_tech(ddev);
+}
+
+int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech)
+{
+	struct sk_buff *skb;
+	int rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH,
+				     NFC_DIGITAL_RF_TECH_106A);
+	if (rc)
+		return rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				     NFC_DIGITAL_FRAMING_NFCA_SHORT);
+	if (rc)
+		return rc;
+
+	skb = digital_skb_alloc(ddev, 1);
+	if (!skb)
+		return -ENOMEM;
+
+	*skb_put(skb, sizeof(u8)) = DIGITAL_CMD_SENS_REQ;
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sens_res, NULL);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
-- 
cgit 


From 2c66daecc4092e6049673c281b2e6f0d5e59a94c Mon Sep 17 00:00:00 2001
From: Thierry Escande <thierry.escande@linux.intel.com>
Date: Thu, 19 Sep 2013 17:55:27 +0200
Subject: NFC Digital: Add NFC-A technology support

This adds support for NFC-A technology at 106 kbits/s. The stack can
detect tags of type 1 and 2. There is no support for collision
detection. Tags can be read and written by using a user space
application or a daemon like neard.

The flow of polling operations for NFC-A detection is as follow:

1 - The digital stack sends the SENS_REQ command to the NFC device.
2 - The NFC device receives a SENS_RES response from a peer device and
    passes it to the digital stack.
3   - If the SENS_RES response identifies a type 1 tag, detection ends.
      NFC core is notified through nfc_targets_found().
4   - Otherwise, the digital stack sets the cascade level of NFCID1 to
      CL1 and sends the SDD_REQ command.
5 - The digital stack selects SEL_CMD and SEL_PAR according to the
    cascade level and sends the SDD_REQ command.
4 - The digital stack receives a SDD_RES response for the cascade level
    passed in the SDD_REQ command.
5 - The digital stack analyses (part of) NFCID1 and verify BCC.
6 - The digital stack sends the SEL_REQ command with the NFCID1
    received in the SDD_RES.
6 - The peer device replies with a SEL_RES response
7   - Detection ends if NFCID1 is complete. NFC core notified of new
      target by nfc_targets_found().
8   - If NFCID1 is not complete, the cascade level is incremented (up
      to and including CL3) and the execution continues at step 5 to
      get the remaining bytes of NFCID1.

Once target detection is done, type 1 and 2 tag commands must be
handled by a user space application (i.e neard) through the NFC core.
Responses for type 1 tag are returned directly to user space via NFC
core.
Responses of type 2 commands are handled differently. The digital stack
doesn't analyse the type of commands sent through im_transceive() and
must differentiate valid responses from error ones.
The response process flow is as follow:

1 - If the response length is 16 bytes, it is a valid response of a
    READ command. the packet is returned to the NFC core through the
    callback passed to im_transceive(). Processing stops.
2 - If the response is 1 byte long and is a ACK byte (0x0A), it is a
    valid response of a WRITE command for example. First packet byte
    is set to 0 for no-error and passed back to the NFC core.
    Processing stops.
3 - Any other response is treated as an error and -EIO error code is
    returned to the NFC core through the response callback.

Moreover, since the driver can't differentiate success response from a
NACK response, the digital stack has to handle CRC calculation.

Thus, this patch also adds support for CRC calculation. If the driver
doesn't handle it, the digital stack will calculate CRC and will add it
to sent frames. CRC will also be checked and removed from received
frames. Pointers to the correct CRC calculation functions are stored in
the digital stack device structure when a target is detected. This
avoids the need to check the current target type for every call to
im_transceive() and for every response received from a peer device.

Signed-off-by: Thierry Escande <thierry.escande@linux.intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/digital.h    |   3 +
 net/nfc/Kconfig              |   1 +
 net/nfc/digital.h            |  58 +++++++++
 net/nfc/digital_core.c       | 145 +++++++++++++++++++++-
 net/nfc/digital_technology.c | 288 ++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 491 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index aabd89400d23..36acecd5f06c 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -193,6 +193,9 @@ struct nfc_digital_dev {
 	u8 curr_protocol;
 	u8 curr_rf_tech;
 	u8 curr_nfc_dep_pni;
+
+	int (*skb_check_crc)(struct sk_buff *skb);
+	void (*skb_add_crc)(struct sk_buff *skb);
 };
 
 struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig
index 13e1237e1ea1..4f4d2481325a 100644
--- a/net/nfc/Kconfig
+++ b/net/nfc/Kconfig
@@ -16,6 +16,7 @@ menuconfig NFC
 
 config NFC_DIGITAL
 	depends on NFC
+	select CRC_CCITT
 	tristate "NFC Digital Protocol stack support"
 	default n
 	help
diff --git a/net/nfc/digital.h b/net/nfc/digital.h
index 0a2767098daa..fb5324b792de 100644
--- a/net/nfc/digital.h
+++ b/net/nfc/digital.h
@@ -19,6 +19,8 @@
 #include <net/nfc/nfc.h>
 #include <net/nfc/digital.h>
 
+#include <linux/crc-ccitt.h>
+
 #define PR_DBG(fmt, ...)  pr_debug("%s: " fmt "\n", __func__, ##__VA_ARGS__)
 #define PR_ERR(fmt, ...)  pr_err("%s: " fmt "\n", __func__, ##__VA_ARGS__)
 #define PROTOCOL_ERR(req) pr_err("%s:%d: NFC Digital Protocol error: %s\n", \
@@ -32,6 +34,16 @@
 #define DIGITAL_MAX_HEADER_LEN 7
 #define DIGITAL_CRC_LEN        2
 
+#define DIGITAL_DRV_CAPS_IN_CRC(ddev) \
+	((ddev)->driver_capabilities & NFC_DIGITAL_DRV_CAPS_IN_CRC)
+#define DIGITAL_DRV_CAPS_TG_CRC(ddev) \
+	((ddev)->driver_capabilities & NFC_DIGITAL_DRV_CAPS_TG_CRC)
+
+struct digital_data_exch {
+	data_exchange_cb_t cb;
+	void *cb_context;
+};
+
 struct sk_buff *digital_skb_alloc(struct nfc_digital_dev *ddev,
 				  unsigned int len);
 
@@ -53,4 +65,50 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev);
 
 int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech);
 
+int digital_target_found(struct nfc_digital_dev *ddev,
+			 struct nfc_target *target, u8 protocol);
+
+int digital_in_recv_mifare_res(struct sk_buff *resp);
+
+typedef u16 (*crc_func_t)(u16, const u8 *, size_t);
+
+#define CRC_A_INIT 0x6363
+#define CRC_B_INIT 0xFFFF
+
+void digital_skb_add_crc(struct sk_buff *skb, crc_func_t crc_func, u16 init,
+			 u8 bitwise_inv, u8 msb_first);
+
+static inline void digital_skb_add_crc_a(struct sk_buff *skb)
+{
+	digital_skb_add_crc(skb, crc_ccitt, CRC_A_INIT, 0, 0);
+}
+
+static inline void digital_skb_add_crc_b(struct sk_buff *skb)
+{
+	digital_skb_add_crc(skb, crc_ccitt, CRC_B_INIT, 1, 0);
+}
+
+static inline void digital_skb_add_crc_none(struct sk_buff *skb)
+{
+	return;
+}
+
+int digital_skb_check_crc(struct sk_buff *skb, crc_func_t crc_func,
+			  u16 crc_init, u8 bitwise_inv, u8 msb_first);
+
+static inline int digital_skb_check_crc_a(struct sk_buff *skb)
+{
+	return digital_skb_check_crc(skb, crc_ccitt, CRC_A_INIT, 0, 0);
+}
+
+static inline int digital_skb_check_crc_b(struct sk_buff *skb)
+{
+	return digital_skb_check_crc(skb, crc_ccitt, CRC_B_INIT, 1, 0);
+}
+
+static inline int digital_skb_check_crc_none(struct sk_buff *skb)
+{
+	return 0;
+}
+
 #endif /* __DIGITAL_H */
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index 13abd293ca37..4b3ceb45834b 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -47,6 +47,51 @@ struct sk_buff *digital_skb_alloc(struct nfc_digital_dev *ddev,
 	return skb;
 }
 
+void digital_skb_add_crc(struct sk_buff *skb, crc_func_t crc_func, u16 init,
+			 u8 bitwise_inv, u8 msb_first)
+{
+	u16 crc;
+
+	crc = crc_func(init, skb->data, skb->len);
+
+	if (bitwise_inv)
+		crc = ~crc;
+
+	if (msb_first)
+		crc = __fswab16(crc);
+
+	*skb_put(skb, 1) = crc & 0xFF;
+	*skb_put(skb, 1) = (crc >> 8) & 0xFF;
+}
+
+int digital_skb_check_crc(struct sk_buff *skb, crc_func_t crc_func,
+			  u16 crc_init, u8 bitwise_inv, u8 msb_first)
+{
+	int rc;
+	u16 crc;
+
+	if (skb->len <= 2)
+		return -EIO;
+
+	crc = crc_func(crc_init, skb->data, skb->len - 2);
+
+	if (bitwise_inv)
+		crc = ~crc;
+
+	if (msb_first)
+		crc = __swab16(crc);
+
+	rc = (skb->data[skb->len - 2] - (crc & 0xFF)) +
+	     (skb->data[skb->len - 1] - ((crc >> 8) & 0xFF));
+
+	if (rc)
+		return -EIO;
+
+	skb_trim(skb, skb->len - 2);
+
+	return 0;
+}
+
 static inline void digital_switch_rf(struct nfc_digital_dev *ddev, bool on)
 {
 	ddev->ops->switch_rf(ddev, on);
@@ -183,6 +228,62 @@ int digital_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param)
 	return rc;
 }
 
+int digital_target_found(struct nfc_digital_dev *ddev,
+			 struct nfc_target *target, u8 protocol)
+{
+	int rc;
+	u8 framing;
+	u8 rf_tech;
+	int (*check_crc)(struct sk_buff *skb);
+	void (*add_crc)(struct sk_buff *skb);
+
+	rf_tech = ddev->poll_techs[ddev->poll_tech_index].rf_tech;
+
+	switch (protocol) {
+	case NFC_PROTO_JEWEL:
+		framing = NFC_DIGITAL_FRAMING_NFCA_T1T;
+		check_crc = digital_skb_check_crc_b;
+		add_crc = digital_skb_add_crc_b;
+		break;
+
+	case NFC_PROTO_MIFARE:
+		framing = NFC_DIGITAL_FRAMING_NFCA_T2T;
+		check_crc = digital_skb_check_crc_a;
+		add_crc = digital_skb_add_crc_a;
+		break;
+
+	default:
+		PR_ERR("Invalid protocol %d", protocol);
+		return -EINVAL;
+	}
+
+	PR_DBG("rf_tech=%d, protocol=%d", rf_tech, protocol);
+
+	ddev->curr_rf_tech = rf_tech;
+	ddev->curr_protocol = protocol;
+
+	if (DIGITAL_DRV_CAPS_IN_CRC(ddev)) {
+		ddev->skb_add_crc = digital_skb_add_crc_none;
+		ddev->skb_check_crc = digital_skb_check_crc_none;
+	} else {
+		ddev->skb_add_crc = add_crc;
+		ddev->skb_check_crc = check_crc;
+	}
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, framing);
+	if (rc)
+		return rc;
+
+	target->supported_protocols = (1 << protocol);
+	rc = nfc_targets_found(ddev->nfc_dev, target, 1);
+	if (rc)
+		return rc;
+
+	ddev->poll_tech_count = 0;
+
+	return 0;
+}
+
 void digital_poll_next_tech(struct nfc_digital_dev *ddev)
 {
 	digital_switch_rf(ddev, 0);
@@ -363,11 +464,53 @@ static int digital_tg_send(struct nfc_dev *dev, struct sk_buff *skb)
 	return -EOPNOTSUPP;
 }
 
+static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg,
+				     struct sk_buff *resp)
+{
+	struct digital_data_exch *data_exch = arg;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		goto done;
+	}
+
+	if (ddev->curr_protocol == NFC_PROTO_MIFARE)
+		rc = digital_in_recv_mifare_res(resp);
+	else
+		rc = ddev->skb_check_crc(resp);
+
+	if (rc) {
+		kfree_skb(resp);
+		resp = NULL;
+	}
+
+done:
+	data_exch->cb(data_exch->cb_context, resp, rc);
+
+	kfree(data_exch);
+}
+
 static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 			   struct sk_buff *skb, data_exchange_cb_t cb,
 			   void *cb_context)
 {
-	return -EOPNOTSUPP;
+	struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev);
+	struct digital_data_exch *data_exch;
+
+	data_exch = kzalloc(sizeof(struct digital_data_exch), GFP_KERNEL);
+	if (!data_exch) {
+		PR_ERR("Failed to allocate data_exch struct");
+		return -ENOMEM;
+	}
+
+	data_exch->cb = cb;
+	data_exch->cb_context = cb_context;
+
+	ddev->skb_add_crc(skb);
+
+	return digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete,
+				   data_exch);
 }
 
 static struct nfc_ops digital_nfc_ops = {
diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c
index 084b0fba5f4d..0cad38001c5f 100644
--- a/net/nfc/digital_technology.c
+++ b/net/nfc/digital_technology.c
@@ -26,13 +26,269 @@
 #define DIGITAL_SDD_RES_CT  0x88
 #define DIGITAL_SDD_RES_LEN 5
 
+#define DIGITAL_SEL_RES_NFCID1_COMPLETE(sel_res) (!((sel_res) & 0x04))
+#define DIGITAL_SEL_RES_IS_T2T(sel_res) (!((sel_res) & 0x60))
+
+#define DIGITAL_SENS_RES_IS_T1T(sens_res) (((sens_res) & 0x000C) == 0x000C)
+#define DIGITAL_SENS_RES_IS_VALID(sens_res) \
+	((!((sens_res) & 0x1F00) && (((sens_res) & 0x000C) == 0x000C)) || \
+	(((sens_res) & 0x1F00) && ((sens_res) & 0x000C) != 0x000C))
+
+#define DIGITAL_MIFARE_READ_RES_LEN 16
+#define DIGITAL_MIFARE_ACK_RES	0x0A
+
+struct digital_sdd_res {
+	u8 nfcid1[4];
+	u8 bcc;
+} __packed;
+
+struct digital_sel_req {
+	u8 sel_cmd;
+	u8 b2;
+	u8 nfcid1[4];
+	u8 bcc;
+} __packed;
+
+static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev,
+				   struct nfc_target *target);
+
+static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg,
+				    struct sk_buff *resp)
+{
+	struct nfc_target *target = arg;
+	int rc;
+	u8 sel_res;
+	u8 nfc_proto;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (!DIGITAL_DRV_CAPS_IN_CRC(ddev)) {
+		rc = digital_skb_check_crc_a(resp);
+		if (rc) {
+			PROTOCOL_ERR("4.4.1.3");
+			goto exit;
+		}
+	}
+
+	if (!resp->len) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	sel_res = resp->data[0];
+
+	if (!DIGITAL_SEL_RES_NFCID1_COMPLETE(sel_res)) {
+		rc = digital_in_send_sdd_req(ddev, target);
+		if (rc)
+			goto exit;
+
+		goto exit_free_skb;
+	}
+
+	if (DIGITAL_SEL_RES_IS_T2T(sel_res)) {
+		nfc_proto = NFC_PROTO_MIFARE;
+	} else {
+		rc = -EOPNOTSUPP;
+		goto exit;
+	}
+
+	target->sel_res = sel_res;
+
+	rc = digital_target_found(ddev, target, nfc_proto);
+
+exit:
+	kfree(target);
+
+exit_free_skb:
+	dev_kfree_skb(resp);
+
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+static int digital_in_send_sel_req(struct nfc_digital_dev *ddev,
+				   struct nfc_target *target,
+				   struct digital_sdd_res *sdd_res)
+{
+	struct sk_buff *skb;
+	struct digital_sel_req *sel_req;
+	u8 sel_cmd;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(struct digital_sel_req));
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put(skb, sizeof(struct digital_sel_req));
+	sel_req = (struct digital_sel_req *)skb->data;
+
+	if (target->nfcid1_len <= 4)
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL1;
+	else if (target->nfcid1_len < 10)
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL2;
+	else
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL3;
+
+	sel_req->sel_cmd = sel_cmd;
+	sel_req->b2 = 0x70;
+	memcpy(sel_req->nfcid1, sdd_res->nfcid1, 4);
+	sel_req->bcc = sdd_res->bcc;
+
+	if (DIGITAL_DRV_CAPS_IN_CRC(ddev)) {
+		rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A);
+		if (rc)
+			goto exit;
+	} else {
+		digital_skb_add_crc_a(skb);
+	}
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sel_res,
+				 target);
+exit:
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static void digital_in_recv_sdd_res(struct nfc_digital_dev *ddev, void *arg,
+				    struct sk_buff *resp)
+{
+	struct nfc_target *target = arg;
+	struct digital_sdd_res *sdd_res;
+	int rc;
+	u8 offset, size;
+	u8 i, bcc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len < DIGITAL_SDD_RES_LEN) {
+		PROTOCOL_ERR("4.7.2.8");
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	sdd_res = (struct digital_sdd_res *)resp->data;
+
+	for (i = 0, bcc = 0; i < 4; i++)
+		bcc ^= sdd_res->nfcid1[i];
+
+	if (bcc != sdd_res->bcc) {
+		PROTOCOL_ERR("4.7.2.6");
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	if (sdd_res->nfcid1[0] == DIGITAL_SDD_RES_CT) {
+		offset = 1;
+		size = 3;
+	} else {
+		offset = 0;
+		size = 4;
+	}
+
+	memcpy(target->nfcid1 + target->nfcid1_len, sdd_res->nfcid1 + offset,
+	       size);
+	target->nfcid1_len += size;
+
+	rc = digital_in_send_sel_req(ddev, target, sdd_res);
+
+exit:
+	dev_kfree_skb(resp);
+
+	if (rc) {
+		kfree(target);
+		digital_poll_next_tech(ddev);
+	}
+}
+
+static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev,
+				   struct nfc_target *target)
+{
+	int rc;
+	struct sk_buff *skb;
+	u8 sel_cmd;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				     NFC_DIGITAL_FRAMING_NFCA_STANDARD);
+	if (rc)
+		return rc;
+
+	skb = digital_skb_alloc(ddev, 2);
+	if (!skb) {
+		PR_ERR("alloc_skb failed");
+		return -ENOMEM;
+	}
+
+	if (target->nfcid1_len == 0)
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL1;
+	else if (target->nfcid1_len == 3)
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL2;
+	else
+		sel_cmd = DIGITAL_CMD_SEL_REQ_CL3;
+
+	*skb_put(skb, sizeof(u8)) = sel_cmd;
+	*skb_put(skb, sizeof(u8)) = DIGITAL_SDD_REQ_SEL_PAR;
+
+	return digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res,
+				   target);
+}
+
 static void digital_in_recv_sens_res(struct nfc_digital_dev *ddev, void *arg,
 				     struct sk_buff *resp)
 {
-	if (!IS_ERR(resp))
-		dev_kfree_skb(resp);
+	struct nfc_target *target = NULL;
+	u16 sens_res;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len < sizeof(u16)) {
+		rc = -EIO;
+		goto exit;
+	}
+
+	target = kzalloc(sizeof(struct nfc_target), GFP_KERNEL);
+	if (!target) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	memcpy(&target->sens_res, resp->data, sizeof(u16));
 
-	digital_poll_next_tech(ddev);
+	sens_res = be16_to_cpu(target->sens_res);
+
+	if (!DIGITAL_SENS_RES_IS_VALID(sens_res)) {
+		PROTOCOL_ERR("4.6.3.3");
+		rc = -EINVAL;
+		goto exit;
+	}
+
+	if (DIGITAL_SENS_RES_IS_T1T(sens_res))
+		rc = digital_target_found(ddev, target, NFC_PROTO_JEWEL);
+	else
+		rc = digital_in_send_sdd_req(ddev, target);
+
+exit:
+	dev_kfree_skb(resp);
+
+	if (rc) {
+		kfree(target);
+		digital_poll_next_tech(ddev);
+	}
 }
 
 int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech)
@@ -62,3 +318,29 @@ int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech)
 
 	return rc;
 }
+
+int digital_in_recv_mifare_res(struct sk_buff *resp)
+{
+	/* Successful READ command response is 16 data bytes + 2 CRC bytes long.
+	 * Since the driver can't differentiate a ACK/NACK response from a valid
+	 * READ response, the CRC calculation must be handled at digital level
+	 * even if the driver supports it for this technology.
+	 */
+	if (resp->len == DIGITAL_MIFARE_READ_RES_LEN + DIGITAL_CRC_LEN) {
+		if (digital_skb_check_crc_a(resp)) {
+			PROTOCOL_ERR("9.4.1.2");
+			return -EIO;
+		}
+
+		return 0;
+	}
+
+	/* ACK response (i.e. successful WRITE). */
+	if (resp->len == 1 && resp->data[0] == DIGITAL_MIFARE_ACK_RES) {
+		resp->data[0] = 0;
+		return 0;
+	}
+
+	/* NACK and any other responses are treated as error. */
+	return -EIO;
+}
-- 
cgit 


From b9c0c678f7267831b73e1d73fb30c9b4658e91ec Mon Sep 17 00:00:00 2001
From: Samuel Ortiz <sameo@linux.intel.com>
Date: Tue, 24 Sep 2013 12:40:44 +0200
Subject: NFC: Document NFC targets sens_res field

SENS_RES has no specific endiannes attached to it, the kernel ABI is the
following one: Byte 2 (As described by the NFC Forum Digital spec) is
the u16 most significant byte.

Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nfc.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index c2aee4875b65..5329804ebb70 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -85,6 +85,14 @@ struct nfc_ops {
 #define NFC_MAX_GT_LEN 48
 #define NFC_ATR_RES_GT_OFFSET 15
 
+/**
+ * struct nfc_target - NFC target descriptiom
+ *
+ * @sens_res: 2 bytes describing the target SENS_RES response, if the target
+ *	is a type A one. The %sens_res most significant byte must be byte 2
+ *	as described by the NFC Forum digital specification (i.e. the platform
+ *	configuration one) while %sens_res least significant byte is byte 1.
+ */
 struct nfc_target {
 	u32 idx;
 	u32 supported_protocols;
-- 
cgit 


From 72b70b6ec4fa7da86a3ac0aacee699b18d94fc3b Mon Sep 17 00:00:00 2001
From: Samuel Ortiz <sameo@linux.intel.com>
Date: Wed, 28 Aug 2013 00:39:48 +0200
Subject: NFC: Define secure element IO API and commands

In order to send and receive ISO7816 APDUs to and from NFC embedded
secure elements, we define a specific netlink command.
On a typical SE use case, host applications will send very few APDUs
(Less than 10) per transaction. This is why we decided to go for a
simple netlink API. Defining another NFC socket protocol for such low
traffic would have been overengineered.

Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nfc.h    | 5 +++++
 include/uapi/linux/nfc.h | 4 ++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 5329804ebb70..82fc4e43fc6e 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -53,6 +53,8 @@ struct nfc_dev;
 typedef void (*data_exchange_cb_t)(void *context, struct sk_buff *skb,
 								int err);
 
+typedef void (*se_io_cb_t)(void *context, u8 *apdu, size_t apdu_len, int err);
+
 struct nfc_target;
 
 struct nfc_ops {
@@ -79,6 +81,9 @@ struct nfc_ops {
 	int (*discover_se)(struct nfc_dev *dev);
 	int (*enable_se)(struct nfc_dev *dev, u32 se_idx);
 	int (*disable_se)(struct nfc_dev *dev, u32 se_idx);
+	int (*se_io) (struct nfc_dev *dev, u32 se_idx,
+		      u8 *apdu, size_t apdu_length,
+		      se_io_cb_t cb, void *cb_context);
 };
 
 #define NFC_TARGET_IDX_ANY -1
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 29bed72a4ac4..6ad6cc03ccd3 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -85,6 +85,7 @@
  *	a specific SE notifies us about the end of a transaction. The parameter
  *	for this event is the application ID (AID).
  * @NFC_CMD_GET_SE: Dump all discovered secure elements from an NFC controller.
+ * @NFC_CMD_SE_IO: Send/Receive APDUs to/from the selected secure element.
  */
 enum nfc_commands {
 	NFC_CMD_UNSPEC,
@@ -114,6 +115,7 @@ enum nfc_commands {
 	NFC_EVENT_SE_CONNECTIVITY,
 	NFC_EVENT_SE_TRANSACTION,
 	NFC_CMD_GET_SE,
+	NFC_CMD_SE_IO,
 /* private: internal use only */
 	__NFC_CMD_AFTER_LAST
 };
@@ -147,6 +149,7 @@ enum nfc_commands {
  * @NFC_ATTR_SE_INDEX: Secure element index
  * @NFC_ATTR_SE_TYPE: Secure element type (UICC or EMBEDDED)
  * @NFC_ATTR_FIRMWARE_DOWNLOAD_STATUS: Firmware download operation status
+ * @NFC_ATTR_APDU: Secure element APDU
  */
 enum nfc_attrs {
 	NFC_ATTR_UNSPEC,
@@ -174,6 +177,7 @@ enum nfc_attrs {
 	NFC_ATTR_SE_TYPE,
 	NFC_ATTR_SE_AID,
 	NFC_ATTR_FIRMWARE_DOWNLOAD_STATUS,
+	NFC_ATTR_SE_APDU,
 /* private: internal use only */
 	__NFC_ATTR_AFTER_LAST
 };
-- 
cgit 


From 04fa2f7f837601903e5fe0f93bc2af8559d8c035 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuah.kh@samsung.com>
Date: Tue, 24 Sep 2013 15:21:19 -0600
Subject: iommu: Add iommu_error class event to iommu trace

iommu_error class event can be enabled to trigger when an iommu
error occurs. This trace event is intended to be called to report the
error information. Trace information includes driver name, device name,
iova, and flags.

iommu_error:io_page_fault

Signed-off-by: Shuah Khan <shuah.kh@samsung.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/iommu-traces.c |  3 +++
 include/trace/events/iommu.h | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/iommu-traces.c b/drivers/iommu/iommu-traces.c
index a2af60f31810..bf3b317ff0c1 100644
--- a/drivers/iommu/iommu-traces.c
+++ b/drivers/iommu/iommu-traces.c
@@ -22,3 +22,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(detach_device_from_domain);
 /* iommu_map_unmap */
 EXPORT_TRACEPOINT_SYMBOL_GPL(map);
 EXPORT_TRACEPOINT_SYMBOL_GPL(unmap);
+
+/* iommu_error */
+EXPORT_TRACEPOINT_SYMBOL_GPL(io_page_fault);
diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h
index 86bcc5a9fedc..a8f5c32d174b 100644
--- a/include/trace/events/iommu.h
+++ b/include/trace/events/iommu.h
@@ -123,6 +123,39 @@ DEFINE_EVENT_PRINT(iommu_map_unmap, unmap,
 			__entry->iova, __entry->size
 	)
 );
+
+DECLARE_EVENT_CLASS(iommu_error,
+
+	TP_PROTO(struct device *dev, unsigned long iova, int flags),
+
+	TP_ARGS(dev, iova, flags),
+
+	TP_STRUCT__entry(
+		__string(device, dev_name(dev))
+		__string(driver, dev_driver_string(dev))
+		__field(u64, iova)
+		__field(int, flags)
+	),
+
+	TP_fast_assign(
+		__assign_str(device, dev_name(dev));
+		__assign_str(driver, dev_driver_string(dev));
+		__entry->iova = iova;
+		__entry->flags = flags;
+	),
+
+	TP_printk("IOMMU:%s %s iova=0x%016llx flags=0x%04x",
+			__get_str(driver), __get_str(device),
+			__entry->iova, __entry->flags
+	)
+);
+
+DEFINE_EVENT(iommu_error, io_page_fault,
+
+	TP_PROTO(struct device *dev, unsigned long iova, int flags),
+
+	TP_ARGS(dev, iova, flags)
+);
 #endif /* _TRACE_IOMMU_H */
 
 /* This part must be outside protection */
-- 
cgit 


From 56fa484969c367e3ae43a012a7b99f75bb4f3bdb Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuah.kh@samsung.com>
Date: Tue, 24 Sep 2013 15:21:20 -0600
Subject: iommu: Change iommu driver to call io_page_fault trace event

Change iommu driver call io_page_fault trace event. This iommu_error class
event can be enabled to trigger when an iommu error occurs. Trace information
includes driver name, device name, iova, and flags.

Testing:
Added trace calls to iommu_prepare_identity_map() for testing some of the
conditions that are hard to trigger. Here is the trace from the testing:

       swapper/0-1     [003] ....     2.003774: io_page_fault: IOMMU:pci 0000:00:02.0 iova=0x00000000cb800000 flags=0x0002
       swapper/0-1     [003] ....     2.004098: io_page_fault: IOMMU:pci 0000:00:1d.0 iova=0x00000000cadc6000 flags=0x0002
       swapper/0-1     [003] ....     2.004115: io_page_fault: IOMMU:pci 0000:00:1a.0 iova=0x00000000cadc6000 flags=0x0002
       swapper/0-1     [003] ....     2.004129: io_page_fault: IOMMU:pci 0000:00:1f.0 iova=0x0000000000000000 flags=0x0002

Signed-off-by: Shuah Khan <shuah.kh@samsung.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 include/linux/iommu.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 7ea319e95b47..a444c790fa72 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/types.h>
+#include <trace/events/iommu.h>
 
 #define IOMMU_READ	(1)
 #define IOMMU_WRITE	(2)
@@ -227,6 +228,7 @@ static inline int report_iommu_fault(struct iommu_domain *domain,
 		ret = domain->handler(domain, dev, iova, flags,
 						domain->handler_token);
 
+	trace_io_page_fault(dev, iova, flags);
 	return ret;
 }
 
-- 
cgit 


From ed37ddffe201bfad7be3c45bc08bd65b5298adca Mon Sep 17 00:00:00 2001
From: Roy Franz <roy.franz@linaro.org>
Date: Sun, 22 Sep 2013 15:45:26 -0700
Subject: efi: Add proper definitions for some EFI function pointers.

The x86/AMD64 EFI stubs must use a call wrapper to convert between
the Linux and EFI ABIs, so void pointers are sufficient.  For ARM,
the ABIs are compatible, so we can directly invoke the function
pointers.  The functions that are used by the ARM stub are updated
to match the EFI definitions.
Also add some EFI types used by EFI functions.

Signed-off-by: Roy Franz <roy.franz@linaro.org>
Acked-by: Mark Salter <msalter@redhat.com>
Reviewed-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 arch/x86/boot/compressed/eboot.h |  8 -------
 include/linux/efi.h              | 50 +++++++++++++++++++++++++++-------------
 2 files changed, 34 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f91c5f..02265107cce3 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -10,8 +10,6 @@
 #define SEG_GRANULARITY_4KB	(1 << 0)
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
-
-#define EFI_PAGE_SIZE		(1UL << EFI_PAGE_SHIFT)
 #define EFI_READ_CHUNK_SIZE	(1024 * 1024)
 
 #define EFI_CONSOLE_OUT_DEVICE_GUID    \
@@ -62,10 +60,4 @@ struct efi_uga_draw_protocol {
 	void *blt;
 };
 
-struct efi_simple_text_output_protocol {
-	void *reset;
-	void *output_string;
-	void *test_string;
-};
-
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index c084b6d942c3..bc5687d0f315 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -39,6 +39,8 @@
 typedef unsigned long efi_status_t;
 typedef u8 efi_bool_t;
 typedef u16 efi_char16_t;		/* UNICODE character */
+typedef u64 efi_physical_addr_t;
+typedef void *efi_handle_t;
 
 
 typedef struct {
@@ -96,6 +98,7 @@ typedef	struct {
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
 #define EFI_PAGE_SHIFT		12
+#define EFI_PAGE_SIZE		(1UL << EFI_PAGE_SHIFT)
 
 typedef struct {
 	u32 type;
@@ -157,11 +160,13 @@ typedef struct {
 	efi_table_hdr_t hdr;
 	void *raise_tpl;
 	void *restore_tpl;
-	void *allocate_pages;
-	void *free_pages;
-	void *get_memory_map;
-	void *allocate_pool;
-	void *free_pool;
+	efi_status_t (*allocate_pages)(int, int, unsigned long,
+				       efi_physical_addr_t *);
+	efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long);
+	efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *,
+				       unsigned long *, u32 *);
+	efi_status_t (*allocate_pool)(int, unsigned long, void **);
+	efi_status_t (*free_pool)(void *);
 	void *create_event;
 	void *set_timer;
 	void *wait_for_event;
@@ -171,7 +176,7 @@ typedef struct {
 	void *install_protocol_interface;
 	void *reinstall_protocol_interface;
 	void *uninstall_protocol_interface;
-	void *handle_protocol;
+	efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **);
 	void *__reserved;
 	void *register_protocol_notify;
 	void *locate_handle;
@@ -181,7 +186,7 @@ typedef struct {
 	void *start_image;
 	void *exit;
 	void *unload_image;
-	void *exit_boot_services;
+	efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long);
 	void *get_next_monotonic_count;
 	void *stall;
 	void *set_watchdog_timer;
@@ -494,10 +499,6 @@ typedef struct {
 	unsigned long unload;
 } efi_loaded_image_t;
 
-typedef struct {
-	u64 revision;
-	void *open_volume;
-} efi_file_io_interface_t;
 
 typedef struct {
 	u64 size;
@@ -510,20 +511,30 @@ typedef struct {
 	efi_char16_t filename[1];
 } efi_file_info_t;
 
-typedef struct {
+typedef struct _efi_file_handle {
 	u64 revision;
-	void *open;
-	void *close;
+	efi_status_t (*open)(struct _efi_file_handle *,
+			     struct _efi_file_handle **,
+			     efi_char16_t *, u64, u64);
+	efi_status_t (*close)(struct _efi_file_handle *);
 	void *delete;
-	void *read;
+	efi_status_t (*read)(struct _efi_file_handle *, unsigned long *,
+			     void *);
 	void *write;
 	void *get_position;
 	void *set_position;
-	void *get_info;
+	efi_status_t (*get_info)(struct _efi_file_handle *, efi_guid_t *,
+			unsigned long *, void *);
 	void *set_info;
 	void *flush;
 } efi_file_handle_t;
 
+typedef struct _efi_file_io_interface {
+	u64 revision;
+	int (*open_volume)(struct _efi_file_io_interface *,
+			   efi_file_handle_t **);
+} efi_file_io_interface_t;
+
 #define EFI_FILE_MODE_READ	0x0000000000000001
 #define EFI_FILE_MODE_WRITE	0x0000000000000002
 #define EFI_FILE_MODE_CREATE	0x8000000000000000
@@ -792,6 +803,13 @@ struct efivar_entry {
 	struct kobject kobj;
 };
 
+
+struct efi_simple_text_output_protocol {
+	void *reset;
+	efi_status_t (*output_string)(void *, void *);
+	void *test_string;
+};
+
 extern struct list_head efivar_sysfs_list;
 
 static inline void
-- 
cgit 


From 3150398626466c6cc626732f60bc901d58f40677 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 12 Sep 2013 15:10:31 +0200
Subject: sched: Remove {set,clear}_need_resched

Preemption semantics are going to change which mandate a change.

All DRM usage sites are already broken and will not be affected (much)
by this change. DRM people are aware and will remove the last few
stragglers.

For now, leave an empty stub that generates a warning, once all users
are gone we can remove this.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: airlied@linux.ie
Cc: daniel.vetter@ffwll.ch
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/n/tip-qfc1el2zvhxiyut4ai99ij4n@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/thread_info.h | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e7e04736802f..a629e4b23217 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -104,8 +104,19 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
-#define set_need_resched()	set_thread_flag(TIF_NEED_RESCHED)
-#define clear_need_resched()	clear_thread_flag(TIF_NEED_RESCHED)
+static inline __deprecated void set_need_resched(void)
+{
+	/*
+	 * Use of this function in deprecated.
+	 *
+	 * As of this writing there are only a few users in the DRM tree left
+	 * all of which are wrong and can be removed without causing too much
+	 * grief.
+	 *
+	 * The DRM people are aware and are working on removing the last few
+	 * instances.
+	 */
+}
 
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*
-- 
cgit 


From ea8117478918a4734586d35ff530721b682425be Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Sep 2013 12:43:13 +0200
Subject: sched, idle: Fix the idle polling state logic

Mike reported that commit 7d1a9417 ("x86: Use generic idle loop")
regressed several workloads and caused excessive reschedule
interrupts.

The patch in question failed to notice that the x86 code had an
inverted sense of the polling state versus the new generic code (x86:
default polling, generic: default !polling).

Fix the two prominent x86 mwait based idle drivers and introduce a few
new generic polling helpers (fixing the wrong smp_mb__after_clear_bit
usage).

Also switch the idle routines to using tif_need_resched() which is an
immediate TIF_NEED_RESCHED test as opposed to need_resched which will
end up being slightly different.

Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: lenb@kernel.org
Cc: tglx@linutronix.de
Link: http://lkml.kernel.org/n/tip-nc03imb0etuefmzybzj7sprf@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/process.c     |  6 ++--
 drivers/acpi/processor_idle.c | 46 ++++++-------------------
 drivers/idle/intel_idle.c     |  2 +-
 include/linux/sched.h         | 78 +++++++++++++++++++++++++++++++++++++++----
 include/linux/thread_info.h   |  2 ++
 kernel/cpu/idle.c             |  9 +++--
 6 files changed, 91 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c83516be1052..3fb8d95ab8b5 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -391,9 +391,9 @@ static void amd_e400_idle(void)
 		 * The switch back from broadcast mode needs to be
 		 * called with interrupts disabled.
 		 */
-		 local_irq_disable();
-		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		 local_irq_enable();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
 	} else
 		default_idle();
 }
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f98dd00b51a9..c7414a545a4f 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -119,17 +119,10 @@ static struct dmi_system_id processor_power_dmi_table[] = {
  */
 static void acpi_safe_halt(void)
 {
-	current_thread_info()->status &= ~TS_POLLING;
-	/*
-	 * TS_POLLING-cleared state must be visible before we
-	 * test NEED_RESCHED:
-	 */
-	smp_mb();
-	if (!need_resched()) {
+	if (!tif_need_resched()) {
 		safe_halt();
 		local_irq_disable();
 	}
-	current_thread_info()->status |= TS_POLLING;
 }
 
 #ifdef ARCH_APICTIMER_STOPS_ON_C3
@@ -737,6 +730,11 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
+			return -EINVAL;
+	}
+
 	lapic_timer_state_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 
@@ -790,18 +788,9 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	/*
@@ -819,9 +808,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
@@ -858,18 +844,9 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		}
 	}
 
-	if (cx->entry_method != ACPI_CSTATE_FFH) {
-		current_thread_info()->status &= ~TS_POLLING;
-		/*
-		 * TS_POLLING-cleared state must be visible before we test
-		 * NEED_RESCHED:
-		 */
-		smp_mb();
-
-		if (unlikely(need_resched())) {
-			current_thread_info()->status |= TS_POLLING;
+	if (cx->entry_method == ACPI_CSTATE_FFH) {
+		if (current_set_polling_and_test())
 			return -EINVAL;
-		}
 	}
 
 	acpi_unlazy_tlb(smp_processor_id());
@@ -915,9 +892,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 
 	sched_clock_idle_wakeup_event(0);
 
-	if (cx->entry_method != ACPI_CSTATE_FFH)
-		current_thread_info()->status |= TS_POLLING;
-
 	lapic_timer_state_broadcast(pr, cx, 0);
 	return index;
 }
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index fa6964d8681a..f116d664b473 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -359,7 +359,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!need_resched()) {
+	if (!current_set_polling_and_test()) {
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b5344de1658b..e783ec52295a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2479,34 +2479,98 @@ static inline int tsk_is_polling(struct task_struct *p)
 {
 	return task_thread_info(p)->status & TS_POLLING;
 }
-static inline void current_set_polling(void)
+static inline void __current_set_polling(void)
 {
 	current_thread_info()->status |= TS_POLLING;
 }
 
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
 {
 	current_thread_info()->status &= ~TS_POLLING;
-	smp_mb__after_clear_bit();
+}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb();
+
+	return unlikely(tif_need_resched());
 }
 #elif defined(TIF_POLLING_NRFLAG)
 static inline int tsk_is_polling(struct task_struct *p)
 {
 	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
 }
-static inline void current_set_polling(void)
+
+static inline void __current_set_polling(void)
 {
 	set_thread_flag(TIF_POLLING_NRFLAG);
 }
 
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	__current_set_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 *
+	 * XXX: assumes set/clear bit are identical barrier wise.
+	 */
+	smp_mb__after_clear_bit();
+
+	return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
 {
 	clear_thread_flag(TIF_POLLING_NRFLAG);
 }
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Polling state must be visible before we test NEED_RESCHED,
+	 * paired by resched_task()
+	 */
+	smp_mb__after_clear_bit();
+
+	return unlikely(tif_need_resched());
+}
+
 #else
 static inline int tsk_is_polling(struct task_struct *p) { return 0; }
-static inline void current_set_polling(void) { }
-static inline void current_clr_polling(void) { }
+static inline void __current_set_polling(void) { }
+static inline void __current_clr_polling(void) { }
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+	return unlikely(tif_need_resched());
+}
 #endif
 
 /*
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index a629e4b23217..fddbe2023a5d 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -118,6 +118,8 @@ static inline __deprecated void set_need_resched(void)
 	 */
 }
 
+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*
  * An arch can define its own version of set_restore_sigmask() to get the
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a0bcb5..c261409500e4 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@ static inline int cpu_idle_poll(void)
 	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	while (!need_resched())
+	while (!tif_need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	rcu_idle_exit();
@@ -92,8 +92,7 @@ static void cpu_idle_loop(void)
 			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
 				cpu_idle_poll();
 			} else {
-				current_clr_polling();
-				if (!need_resched()) {
+				if (!current_clr_polling_and_test()) {
 					stop_critical_timings();
 					rcu_idle_enter();
 					arch_cpu_idle();
@@ -103,7 +102,7 @@ static void cpu_idle_loop(void)
 				} else {
 					local_irq_enable();
 				}
-				current_set_polling();
+				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
 		}
@@ -129,7 +128,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	current_set_polling();
+	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }
-- 
cgit 


From 4a2b4b222743bb07fedf985b884550f2ca067ea9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Aug 2013 14:55:24 +0200
Subject: sched: Introduce preempt_count accessor functions

Replace the single preempt_count() 'function' that's an lvalue with
two proper functions:

 preempt_count() - returns the preempt_count value as rvalue
 preempt_count_set() - Allows setting the preempt-count value

Also provide preempt_count_ptr() as a convenience wrapper to implement
all modifying operations.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-orxrbycjozopqfhb4dxdkdvb@git.kernel.org
[ Fixed build failure. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/preempt.h | 25 +++++++++++++++++++------
 init/main.c             |  2 +-
 kernel/sched/core.c     |  4 ++--
 kernel/softirq.c        |  4 ++--
 kernel/timer.c          |  8 ++++----
 lib/locking-selftest.c  |  2 +-
 lib/smp_processor_id.c  |  3 +--
 7 files changed, 30 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index f5d4723cdb3d..eaac52a8fe6a 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -10,19 +10,32 @@
 #include <linux/linkage.h>
 #include <linux/list.h>
 
+static __always_inline int preempt_count(void)
+{
+	return current_thread_info()->preempt_count;
+}
+
+static __always_inline int *preempt_count_ptr(void)
+{
+	return &current_thread_info()->preempt_count;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	*preempt_count_ptr() = pc;
+}
+
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
   extern void add_preempt_count(int val);
   extern void sub_preempt_count(int val);
 #else
-# define add_preempt_count(val)	do { preempt_count() += (val); } while (0)
-# define sub_preempt_count(val)	do { preempt_count() -= (val); } while (0)
+# define add_preempt_count(val)	do { *preempt_count_ptr() += (val); } while (0)
+# define sub_preempt_count(val)	do { *preempt_count_ptr() -= (val); } while (0)
 #endif
 
 #define inc_preempt_count() add_preempt_count(1)
 #define dec_preempt_count() sub_preempt_count(1)
 
-#define preempt_count()	(current_thread_info()->preempt_count)
-
 #ifdef CONFIG_PREEMPT
 
 asmlinkage void preempt_schedule(void);
@@ -81,9 +94,9 @@ do { \
 
 /* For debugging and tracer internals only! */
 #define add_preempt_count_notrace(val)			\
-	do { preempt_count() += (val); } while (0)
+	do { *preempt_count_ptr() += (val); } while (0)
 #define sub_preempt_count_notrace(val)			\
-	do { preempt_count() -= (val); } while (0)
+	do { *preempt_count_ptr() -= (val); } while (0)
 #define inc_preempt_count_notrace() add_preempt_count_notrace(1)
 #define dec_preempt_count_notrace() sub_preempt_count_notrace(1)
 
diff --git a/init/main.c b/init/main.c
index af310afbef28..7cc4b7889a88 100644
--- a/init/main.c
+++ b/init/main.c
@@ -692,7 +692,7 @@ int __init_or_module do_one_initcall(initcall_t fn)
 
 	if (preempt_count() != count) {
 		sprintf(msgbuf, "preemption imbalance ");
-		preempt_count() = count;
+		preempt_count_set(count);
 	}
 	if (irqs_disabled()) {
 		strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 242da0c03aba..fe89afac4d09 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2219,7 +2219,7 @@ void __kprobes add_preempt_count(int val)
 	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
 		return;
 #endif
-	preempt_count() += val;
+	add_preempt_count_notrace(val);
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
 	 * Spinlock count overflowing soon?
@@ -2250,7 +2250,7 @@ void __kprobes sub_preempt_count(int val)
 
 	if (preempt_count() == val)
 		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
-	preempt_count() -= val;
+	sub_preempt_count_notrace(val);
 }
 EXPORT_SYMBOL(sub_preempt_count);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 53cc09ceb0b8..a90de70cf1f3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -106,7 +106,7 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 	 * We must manually increment preempt_count here and manually
 	 * call the trace_preempt_off later.
 	 */
-	preempt_count() += cnt;
+	add_preempt_count_notrace(cnt);
 	/*
 	 * Were softirqs turned off above:
 	 */
@@ -256,7 +256,7 @@ restart:
 				       " exited with %08x?\n", vec_nr,
 				       softirq_to_name[vec_nr], h->action,
 				       prev_count, preempt_count());
-				preempt_count() = prev_count;
+				preempt_count_set(prev_count);
 			}
 
 			rcu_bh_qs(cpu);
diff --git a/kernel/timer.c b/kernel/timer.c
index 4296d13db3d1..6582b82fa966 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1092,7 +1092,7 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index)
 static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
 			  unsigned long data)
 {
-	int preempt_count = preempt_count();
+	int count = preempt_count();
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1119,16 +1119,16 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long),
 
 	lock_map_release(&lockdep_map);
 
-	if (preempt_count != preempt_count()) {
+	if (count != preempt_count()) {
 		WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
-			  fn, preempt_count, preempt_count());
+			  fn, count, preempt_count());
 		/*
 		 * Restore the preempt count. That gives us a decent
 		 * chance to survive and extract information. If the
 		 * callback kept a lock held, bad luck, but not worse
 		 * than the BUG() we had.
 		 */
-		preempt_count() = preempt_count;
+		preempt_count_set(count);
 	}
 }
 
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 6dc09d8f4c24..872a15a2a637 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -1002,7 +1002,7 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
 	 * Some tests (e.g. double-unlock) might corrupt the preemption
 	 * count, so restore it:
 	 */
-	preempt_count() = saved_preempt_count;
+	preempt_count_set(saved_preempt_count);
 #ifdef CONFIG_TRACE_IRQFLAGS
 	if (softirq_count())
 		current->softirqs_enabled = 0;
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 4c0d0e51d49e..04abe53f12a1 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -9,10 +9,9 @@
 
 notrace unsigned int debug_smp_processor_id(void)
 {
-	unsigned long preempt_count = preempt_count();
 	int this_cpu = raw_smp_processor_id();
 
-	if (likely(preempt_count))
+	if (likely(preempt_count()))
 		goto out;
 
 	if (irqs_disabled())
-- 
cgit 


From f27dde8deef33c9e58027df11ceab2198601d6a6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Aug 2013 14:55:31 +0200
Subject: sched: Add NEED_RESCHED to the preempt_count

In order to combine the preemption and need_resched test we need to
fold the need_resched information into the preempt_count value.

Since the NEED_RESCHED flag is set across CPUs this needs to be an
atomic operation, however we very much want to avoid making
preempt_count atomic, therefore we keep the existing TIF_NEED_RESCHED
infrastructure in place but at 3 sites test it and fold its value into
preempt_count; namely:

 - resched_task() when setting TIF_NEED_RESCHED on the current task
 - scheduler_ipi() when resched_task() sets TIF_NEED_RESCHED on a
                   remote task it follows it up with a reschedule IPI
                   and we can modify the cpu local preempt_count from
                   there.
 - cpu_idle_loop() for when resched_task() found tsk_is_polling().

We use an inverted bitmask to indicate need_resched so that a 0 means
both need_resched and !atomic.

Also remove the barrier() in preempt_enable() between
preempt_enable_no_resched() and preempt_check_resched() to avoid
having to reload the preemption value and allow the compiler to use
the flags of the previuos decrement. I couldn't come up with any sane
reason for this barrier() to be there as preempt_enable_no_resched()
already has a barrier() before doing the decrement.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-7a7m5qqbn5pmwnd4wko9u6da@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/preempt.h | 47 ++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/sched.h   |  7 +++++--
 kernel/cpu/idle.c       |  7 +++++++
 kernel/sched/core.c     | 20 +++++++++++++++-----
 4 files changed, 69 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index eaac52a8fe6a..92e341853e4b 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -10,9 +10,19 @@
 #include <linux/linkage.h>
 #include <linux/list.h>
 
+/*
+ * We use the MSB mostly because its available; see <linux/preempt_mask.h> for
+ * the other bits -- can't include that header due to inclusion hell.
+ */
+#define PREEMPT_NEED_RESCHED	0x80000000
+
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
 static __always_inline int preempt_count(void)
 {
-	return current_thread_info()->preempt_count;
+	return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline int *preempt_count_ptr(void)
@@ -20,11 +30,40 @@ static __always_inline int *preempt_count_ptr(void)
 	return &current_thread_info()->preempt_count;
 }
 
+/*
+ * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
+ * alternative is loosing a reschedule. Better schedule too often -- also this
+ * should be a very rare operation.
+ */
 static __always_inline void preempt_count_set(int pc)
 {
 	*preempt_count_ptr() = pc;
 }
 
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * single instruction.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
+static __always_inline void set_preempt_need_resched(void)
+{
+	*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+	*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
+}
+
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
   extern void add_preempt_count(int val);
   extern void sub_preempt_count(int val);
@@ -42,7 +81,7 @@ asmlinkage void preempt_schedule(void);
 
 #define preempt_check_resched() \
 do { \
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
+	if (unlikely(!*preempt_count_ptr())) \
 		preempt_schedule(); \
 } while (0)
 
@@ -52,7 +91,7 @@ void preempt_schedule_context(void);
 
 #define preempt_check_resched_context() \
 do { \
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
+	if (unlikely(!*preempt_count_ptr())) \
 		preempt_schedule_context(); \
 } while (0)
 #else
@@ -88,7 +127,6 @@ do { \
 #define preempt_enable() \
 do { \
 	preempt_enable_no_resched(); \
-	barrier(); \
 	preempt_check_resched(); \
 } while (0)
 
@@ -116,7 +154,6 @@ do { \
 #define preempt_enable_notrace() \
 do { \
 	preempt_enable_no_resched_notrace(); \
-	barrier(); \
 	preempt_check_resched_context(); \
 } while (0)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e783ec52295a..9fa151fb968e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -22,6 +22,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
+#include <linux/preempt.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -434,7 +435,9 @@ struct task_cputime {
  * We include PREEMPT_ACTIVE to avoid cond_resched() from working
  * before the scheduler is active -- see should_resched().
  */
-#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
+#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE + PREEMPT_NEED_RESCHED)
+#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
+#define PREEMPT_DISABLED	(1 + PREEMPT_NEED_RESCHED)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
@@ -2408,7 +2411,7 @@ static inline int signal_pending_state(long state, struct task_struct *p)
 
 static inline int need_resched(void)
 {
-	return unlikely(test_thread_flag(TIF_NEED_RESCHED));
+	return unlikely(test_preempt_need_resched());
 }
 
 /*
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index c261409500e4..988573a9a387 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -105,6 +105,13 @@ static void cpu_idle_loop(void)
 				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
+			/*
+			 * We need to test and propagate the TIF_NEED_RESCHED
+			 * bit here because we might not have send the
+			 * reschedule IPI to idle tasks.
+			 */
+			if (tif_need_resched())
+				set_preempt_need_resched();
 		}
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe89afac4d09..ee61f5affd20 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -525,8 +525,10 @@ void resched_task(struct task_struct *p)
 	set_tsk_need_resched(p);
 
 	cpu = task_cpu(p);
-	if (cpu == smp_processor_id())
+	if (cpu == smp_processor_id()) {
+		set_preempt_need_resched();
 		return;
+	}
 
 	/* NEED_RESCHED must be visible before we test polling */
 	smp_mb();
@@ -1391,6 +1393,14 @@ static void sched_ttwu_pending(void)
 
 void scheduler_ipi(void)
 {
+	/*
+	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
+	 * TIF_NEED_RESCHED remotely (for the first time) will also send
+	 * this IPI.
+	 */
+	if (tif_need_resched())
+		set_preempt_need_resched();
+
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
 			&& !got_nohz_idle_kick())
@@ -1714,7 +1724,7 @@ void sched_fork(struct task_struct *p)
 #endif
 #ifdef CONFIG_PREEMPT_COUNT
 	/* Want to start with kernel preemption disabled. */
-	task_thread_info(p)->preempt_count = 1;
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED;
 #endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
@@ -2425,6 +2435,7 @@ need_resched:
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
 	clear_tsk_need_resched(prev);
+	clear_preempt_need_resched();
 	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
@@ -2536,11 +2547,10 @@ EXPORT_SYMBOL(preempt_schedule);
  */
 asmlinkage void __sched preempt_schedule_irq(void)
 {
-	struct thread_info *ti = current_thread_info();
 	enum ctx_state prev_state;
 
 	/* Catch callers which need to be fixed */
-	BUG_ON(ti->preempt_count || !irqs_disabled());
+	BUG_ON(preempt_count() || !irqs_disabled());
 
 	prev_state = exception_enter();
 
@@ -4207,7 +4217,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-	task_thread_info(idle)->preempt_count = 0;
+	task_thread_info(idle)->preempt_count = PREEMPT_ENABLED;
 
 	/*
 	 * The idle tasks have their own, simple scheduling class:
-- 
cgit 


From a787870924dbd6f321661e06d4ec1c7a408c9ccf Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Aug 2013 14:55:40 +0200
Subject: sched, arch: Create asm/preempt.h

In order to prepare to per-arch implementations of preempt_count move
the required bits into an asm-generic header and use this for all
archs.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-h5j0c1r3e3fk015m30h8f1zx@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/Kbuild      |  1 +
 arch/arc/include/asm/Kbuild        |  1 +
 arch/arm/include/asm/Kbuild        |  1 +
 arch/arm64/include/asm/Kbuild      |  1 +
 arch/avr32/include/asm/Kbuild      |  1 +
 arch/blackfin/include/asm/Kbuild   |  1 +
 arch/c6x/include/asm/Kbuild        |  1 +
 arch/cris/include/asm/Kbuild       |  1 +
 arch/frv/include/asm/Kbuild        |  1 +
 arch/h8300/include/asm/Kbuild      |  1 +
 arch/hexagon/include/asm/Kbuild    |  1 +
 arch/ia64/include/asm/Kbuild       |  1 +
 arch/m32r/include/asm/Kbuild       |  1 +
 arch/m68k/include/asm/Kbuild       |  1 +
 arch/metag/include/asm/Kbuild      |  1 +
 arch/microblaze/include/asm/Kbuild |  1 +
 arch/mips/include/asm/Kbuild       |  1 +
 arch/mn10300/include/asm/Kbuild    |  1 +
 arch/openrisc/include/asm/Kbuild   |  1 +
 arch/parisc/include/asm/Kbuild     |  1 +
 arch/powerpc/include/asm/Kbuild    |  1 +
 arch/s390/include/asm/Kbuild       |  1 +
 arch/score/include/asm/Kbuild      |  1 +
 arch/sh/include/asm/Kbuild         |  1 +
 arch/sparc/include/asm/Kbuild      |  1 +
 arch/tile/include/asm/Kbuild       |  1 +
 arch/um/include/asm/Kbuild         |  1 +
 arch/unicore32/include/asm/Kbuild  |  1 +
 arch/x86/include/asm/Kbuild        |  1 +
 arch/xtensa/include/asm/Kbuild     |  1 +
 include/asm-generic/preempt.h      | 54 ++++++++++++++++++++++++++++++++++++++
 include/linux/preempt.h            | 49 +---------------------------------
 32 files changed, 85 insertions(+), 48 deletions(-)
 create mode 100644 include/asm-generic/preempt.h

(limited to 'include')

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index a6e85f448c1c..f01fb505ad52 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index d8dd660898b9..5943f7f9d325 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -46,3 +46,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index d3db39860b9c..4e6838d4ddf6 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -33,3 +33,4 @@ generic-y += timex.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
+generic-y += preempt.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 79a642d199f2..519f89f5b6a3 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -50,3 +50,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index d22af851f3f6..b946080ee8bb 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y	+= clkdev.h
 generic-y	+= exec.h
 generic-y	+= trace_clock.h
 generic-y	+= param.h
+generic-y += preempt.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 127826f8a375..f2b43474b0e2 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -44,3 +44,4 @@ generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index e49f918531ad..fc0b3c356027 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -56,3 +56,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index c8325455520e..b06caf649a95 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -11,3 +11,4 @@ generic-y += module.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index c5d767028306..74742dc6a3da 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 8ada3cf0c98d..7e0e7213a481 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -6,3 +6,4 @@ generic-y += mmu.h
 generic-y += module.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 1da17caac23c..67c3450309b7 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -53,3 +53,4 @@ generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index a3456f34f672..f93ee087e8fe 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -3,4 +3,5 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += vtime.h
\ No newline at end of file
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index bebdc36ebb0a..2b58c5f0bc38 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 09d77a862da3..a5d27f272a59 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -31,3 +31,4 @@ generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 6ae0ccb632cb..84d0c1d6b9b3 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -52,3 +52,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index d3c51a6a601d..ce0bbf8f5640 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += syscalls.h
+generic-y += preempt.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 454ddf9bb76f..1acbb8b77a71 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -11,5 +11,6 @@ generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += ucontext.h
 generic-y += xor.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index c5d767028306..74742dc6a3da 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 195653e851da..78405625e799 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -67,3 +67,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index ff4c9faed546..a603b9ebe54c 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -4,3 +4,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
 	  poll.h xor.h clkdev.h exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 704e6f10ae80..d8f9d2f18a23 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -2,4 +2,5 @@
 generic-y += clkdev.h
 generic-y += rwsem.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += vtime.h
\ No newline at end of file
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index f313f9cbcf44..7a5288f3479a 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -2,3 +2,4 @@
 
 generic-y += clkdev.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index e1c7bb999b06..f3414ade77a3 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -4,3 +4,4 @@ header-y +=
 generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 280bea9e5e2b..231efbb68108 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -34,3 +34,4 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 7e4a97fbded4..bf390667657a 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -16,3 +16,4 @@ generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
+generic-y += preempt.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 664d6ad23f80..22f3bd147fa7 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -38,3 +38,4 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index b30f34a79882..fdde187e6087 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
 generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
 generic-y += switch_to.h clkdev.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 89d8b6c4e39a..00045cbe5c63 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -60,3 +60,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 7f669853317a..eca20286a91c 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -5,3 +5,4 @@ genhdr-y += unistd_64.h
 genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
+generic-y += preempt.h
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 1b982641ec35..228d6aee3a16 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -28,3 +28,4 @@ generic-y += termios.h
 generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
new file mode 100644
index 000000000000..a1fc6590a743
--- /dev/null
+++ b/include/asm-generic/preempt.h
@@ -0,0 +1,54 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <linux/thread_info.h>
+
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
+static __always_inline int preempt_count(void)
+{
+	return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline int *preempt_count_ptr(void)
+{
+	return &current_thread_info()->preempt_count;
+}
+
+/*
+ * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
+ * alternative is loosing a reschedule. Better schedule too often -- also this
+ * should be a very rare operation.
+ */
+static __always_inline void preempt_count_set(int pc)
+{
+	*preempt_count_ptr() = pc;
+}
+
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * single instruction.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
+static __always_inline void set_preempt_need_resched(void)
+{
+	*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+	*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
+}
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 92e341853e4b..df8e245e8729 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -6,7 +6,6 @@
  * preempt_count (used for kernel preemption, interrupt count, etc.)
  */
 
-#include <linux/thread_info.h>
 #include <linux/linkage.h>
 #include <linux/list.h>
 
@@ -16,53 +15,7 @@
  */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
-/*
- * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
- * that think a non-zero value indicates we cannot preempt.
- */
-static __always_inline int preempt_count(void)
-{
-	return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
-}
-
-static __always_inline int *preempt_count_ptr(void)
-{
-	return &current_thread_info()->preempt_count;
-}
-
-/*
- * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
- * alternative is loosing a reschedule. Better schedule too often -- also this
- * should be a very rare operation.
- */
-static __always_inline void preempt_count_set(int pc)
-{
-	*preempt_count_ptr() = pc;
-}
-
-/*
- * We fold the NEED_RESCHED bit into the preempt count such that
- * preempt_enable() can decrement and test for needing to reschedule with a
- * single instruction.
- *
- * We invert the actual bit, so that when the decrement hits 0 we know we both
- * need to resched (the bit is cleared) and can resched (no preempt count).
- */
-
-static __always_inline void set_preempt_need_resched(void)
-{
-	*preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
-}
-
-static __always_inline void clear_preempt_need_resched(void)
-{
-	*preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
-}
-
-static __always_inline bool test_preempt_need_resched(void)
-{
-	return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
-}
+#include <asm/preempt.h>
 
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
   extern void add_preempt_count(int val);
-- 
cgit 


From 01028747559ac6c6f642a7bbd2875cc4f66b2feb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Aug 2013 14:55:46 +0200
Subject: sched: Create more preempt_count accessors

We need a few special preempt_count accessors:
 - task_preempt_count() for when we're interested in the preemption
   count of another (non-running) task.
 - init_task_preempt_count() for properly initializing the preemption
   count.
 - init_idle_preempt_count() a special case of the above for the idle
   threads.

With these no generic code ever touches thread_info::preempt_count
anymore and architectures could choose to remove it.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-jf5swrio8l78j37d06fzmo4r@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/preempt.h | 14 ++++++++++++++
 include/trace/events/sched.h  |  2 +-
 kernel/sched/core.c           |  7 +++----
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index a1fc6590a743..8100b1ec1715 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -27,6 +27,20 @@ static __always_inline void preempt_count_set(int pc)
 	*preempt_count_ptr() = pc;
 }
 
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define task_preempt_count(p) \
+	(task_thread_info(p)->preempt_count & ~PREEMPT_NEED_RESCHED)
+
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+} while (0)
+
 /*
  * We fold the NEED_RESCHED bit into the preempt count such that
  * preempt_enable() can decrement and test for needing to reschedule with a
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 2e7d9947a10d..613381bcde40 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
+	if (task_preempt_count(p) & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee61f5affd20..0ba4e4192390 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -983,7 +983,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
+			!(task_preempt_count(p) & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1723,8 +1723,7 @@ void sched_fork(struct task_struct *p)
 	p->on_cpu = 0;
 #endif
 #ifdef CONFIG_PREEMPT_COUNT
-	/* Want to start with kernel preemption disabled. */
-	task_thread_info(p)->preempt_count = PREEMPT_DISABLED;
+	init_task_preempt_count(p);
 #endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
@@ -4217,7 +4216,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
-	task_thread_info(idle)->preempt_count = PREEMPT_ENABLED;
+	init_idle_preempt_count(idle, cpu);
 
 	/*
 	 * The idle tasks have their own, simple scheduling class:
-- 
cgit 


From bdb43806589096ac4272fe1307e789846ac08d7c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Sep 2013 12:15:23 +0200
Subject: sched: Extract the basic add/sub preempt_count modifiers

Rewrite the preempt_count macros in order to extract the 3 basic
preempt_count value modifiers:

  __preempt_count_add()
  __preempt_count_sub()

and the new:

  __preempt_count_dec_and_test()

And since we're at it anyway, replace the unconventional
$op_preempt_count names with the more conventional preempt_count_$op.

Since these basic operators are equivalent to the previous _notrace()
variants, do away with the _notrace() versions.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-ewbpdbupy9xpsjhg960zwbv8@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/mm/init.c           |   5 +-
 arch/x86/kernel/traps.c       |   4 +-
 include/asm-generic/preempt.h |  35 ++++++++++++++
 include/linux/hardirq.h       |   8 ++--
 include/linux/preempt.h       | 106 +++++++++++++++++++-----------------------
 include/linux/sched.h         |   5 --
 include/linux/uaccess.h       |   8 +---
 kernel/context_tracking.c     |   2 +-
 kernel/sched/core.c           |  29 +++++-------
 kernel/softirq.c              |  14 +++---
 10 files changed, 113 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index e205ef598e97..12156176c7ca 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -124,7 +124,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	BUG_ON(Page_dcache_dirty(page));
 
-	inc_preempt_count();
+	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 #ifdef CONFIG_MIPS_MT_SMTC
 	idx += FIX_N_COLOURS * smp_processor_id() +
@@ -193,8 +193,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	EXIT_CRITICAL(flags);
 #endif
-	dec_preempt_count();
-	preempt_check_resched();
+	pagefault_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8c8093b146ca..729aa779ff75 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -88,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs)
 
 static inline void preempt_conditional_sti(struct pt_regs *regs)
 {
-	inc_preempt_count();
+	preempt_count_inc();
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
@@ -103,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
-	dec_preempt_count();
+	preempt_count_dec();
 }
 
 static int __kprobes
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 8100b1ec1715..82d958fc3823 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -65,4 +65,39 @@ static __always_inline bool test_preempt_need_resched(void)
 	return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
 }
 
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	*preempt_count_ptr() += val;
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	*preempt_count_ptr() -= val;
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	return !--*preempt_count_ptr();
+}
+
+/*
+ * Returns true when we need to resched -- even if we can not.
+ */
+static __always_inline bool need_resched(void)
+{
+	return unlikely(test_preempt_need_resched());
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(void)
+{
+	return unlikely(!*preempt_count_ptr());
+}
+
 #endif /* __ASM_PREEMPT_H */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 1e041063b226..d9cf963ac832 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -33,7 +33,7 @@ extern void rcu_nmi_exit(void);
 #define __irq_enter()					\
 	do {						\
 		account_irq_enter_time(current);	\
-		add_preempt_count(HARDIRQ_OFFSET);	\
+		preempt_count_add(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)
 
@@ -49,7 +49,7 @@ extern void irq_enter(void);
 	do {						\
 		trace_hardirq_exit();			\
 		account_irq_exit_time(current);		\
-		sub_preempt_count(HARDIRQ_OFFSET);	\
+		preempt_count_sub(HARDIRQ_OFFSET);	\
 	} while (0)
 
 /*
@@ -62,7 +62,7 @@ extern void irq_exit(void);
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
 		BUG_ON(in_nmi());				\
-		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		rcu_nmi_enter();				\
 		trace_hardirq_enter();				\
 	} while (0)
@@ -72,7 +72,7 @@ extern void irq_exit(void);
 		trace_hardirq_exit();				\
 		rcu_nmi_exit();					\
 		BUG_ON(!in_nmi());				\
-		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
 	} while (0)
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index df8e245e8729..2343d8715299 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -18,97 +18,86 @@
 #include <asm/preempt.h>
 
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
-  extern void add_preempt_count(int val);
-  extern void sub_preempt_count(int val);
+extern void preempt_count_add(int val);
+extern void preempt_count_sub(int val);
+#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); })
 #else
-# define add_preempt_count(val)	do { *preempt_count_ptr() += (val); } while (0)
-# define sub_preempt_count(val)	do { *preempt_count_ptr() -= (val); } while (0)
+#define preempt_count_add(val)	__preempt_count_add(val)
+#define preempt_count_sub(val)	__preempt_count_sub(val)
+#define preempt_count_dec_and_test() __preempt_count_dec_and_test()
 #endif
 
-#define inc_preempt_count() add_preempt_count(1)
-#define dec_preempt_count() sub_preempt_count(1)
-
-#ifdef CONFIG_PREEMPT
-
-asmlinkage void preempt_schedule(void);
-
-#define preempt_check_resched() \
-do { \
-	if (unlikely(!*preempt_count_ptr())) \
-		preempt_schedule(); \
-} while (0)
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-void preempt_schedule_context(void);
-
-#define preempt_check_resched_context() \
-do { \
-	if (unlikely(!*preempt_count_ptr())) \
-		preempt_schedule_context(); \
-} while (0)
-#else
-
-#define preempt_check_resched_context() preempt_check_resched()
-
-#endif /* CONFIG_CONTEXT_TRACKING */
-
-#else /* !CONFIG_PREEMPT */
-
-#define preempt_check_resched()		do { } while (0)
-#define preempt_check_resched_context()	do { } while (0)
-
-#endif /* CONFIG_PREEMPT */
+#define __preempt_count_inc() __preempt_count_add(1)
+#define __preempt_count_dec() __preempt_count_sub(1)
 
+#define preempt_count_inc() preempt_count_add(1)
+#define preempt_count_dec() preempt_count_sub(1)
 
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
 do { \
-	inc_preempt_count(); \
+	preempt_count_inc(); \
 	barrier(); \
 } while (0)
 
 #define sched_preempt_enable_no_resched() \
 do { \
 	barrier(); \
-	dec_preempt_count(); \
+	preempt_count_dec(); \
 } while (0)
 
-#define preempt_enable_no_resched()	sched_preempt_enable_no_resched()
+#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
 
+#ifdef CONFIG_PREEMPT
+asmlinkage void preempt_schedule(void);
 #define preempt_enable() \
 do { \
-	preempt_enable_no_resched(); \
-	preempt_check_resched(); \
+	barrier(); \
+	if (unlikely(preempt_count_dec_and_test())) \
+		preempt_schedule(); \
 } while (0)
 
-/* For debugging and tracer internals only! */
-#define add_preempt_count_notrace(val)			\
-	do { *preempt_count_ptr() += (val); } while (0)
-#define sub_preempt_count_notrace(val)			\
-	do { *preempt_count_ptr() -= (val); } while (0)
-#define inc_preempt_count_notrace() add_preempt_count_notrace(1)
-#define dec_preempt_count_notrace() sub_preempt_count_notrace(1)
+#define preempt_check_resched() \
+do { \
+	if (should_resched()) \
+		preempt_schedule(); \
+} while (0)
+
+#else
+#define preempt_enable() preempt_enable_no_resched()
+#define preempt_check_resched() do { } while (0)
+#endif
 
 #define preempt_disable_notrace() \
 do { \
-	inc_preempt_count_notrace(); \
+	__preempt_count_inc(); \
 	barrier(); \
 } while (0)
 
 #define preempt_enable_no_resched_notrace() \
 do { \
 	barrier(); \
-	dec_preempt_count_notrace(); \
+	__preempt_count_dec(); \
 } while (0)
 
-/* preempt_check_resched is OK to trace */
+#ifdef CONFIG_PREEMPT
+
+#ifdef CONFIG_CONTEXT_TRACKING
+asmlinkage void preempt_schedule_context(void);
+#else
+#define preempt_schedule_context() preempt_schedule()
+#endif
+
 #define preempt_enable_notrace() \
 do { \
-	preempt_enable_no_resched_notrace(); \
-	preempt_check_resched_context(); \
+	barrier(); \
+	if (unlikely(__preempt_count_dec_and_test())) \
+		preempt_schedule_context(); \
 } while (0)
+#else
+#define preempt_enable_notrace() preempt_enable_no_resched_notrace()
+#endif
 
 #else /* !CONFIG_PREEMPT_COUNT */
 
@@ -118,10 +107,11 @@ do { \
  * that can cause faults and scheduling migrate into our preempt-protected
  * region.
  */
-#define preempt_disable()		barrier()
+#define preempt_disable()			barrier()
 #define sched_preempt_enable_no_resched()	barrier()
-#define preempt_enable_no_resched()	barrier()
-#define preempt_enable()		barrier()
+#define preempt_enable_no_resched()		barrier()
+#define preempt_enable()			barrier()
+#define preempt_check_resched()			do { } while (0)
 
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9fa151fb968e..06ac17c7e639 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2409,11 +2409,6 @@ static inline int signal_pending_state(long state, struct task_struct *p)
 	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
 }
 
-static inline int need_resched(void)
-{
-	return unlikely(test_preempt_need_resched());
-}
-
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 5ca0951e1855..9d8cf056e661 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -15,7 +15,7 @@
  */
 static inline void pagefault_disable(void)
 {
-	inc_preempt_count();
+	preempt_count_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
 	 * can hit.
@@ -30,11 +30,7 @@ static inline void pagefault_enable(void)
 	 * the pagefault handler again.
 	 */
 	barrier();
-	dec_preempt_count();
-	/*
-	 * make sure we do..
-	 */
-	barrier();
+	preempt_count_dec();
 	preempt_check_resched();
 }
 
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 247091bf0587..013161f1c807 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -111,7 +111,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-void __sched notrace preempt_schedule_context(void)
+asmlinkage void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0ba4e4192390..9c84a9ab1892 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2219,7 +2219,7 @@ notrace unsigned long get_parent_ip(unsigned long addr)
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
-void __kprobes add_preempt_count(int val)
+void __kprobes preempt_count_add(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2228,7 +2228,7 @@ void __kprobes add_preempt_count(int val)
 	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
 		return;
 #endif
-	add_preempt_count_notrace(val);
+	__preempt_count_add(val);
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
 	 * Spinlock count overflowing soon?
@@ -2239,9 +2239,9 @@ void __kprobes add_preempt_count(int val)
 	if (preempt_count() == val)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
-EXPORT_SYMBOL(add_preempt_count);
+EXPORT_SYMBOL(preempt_count_add);
 
-void __kprobes sub_preempt_count(int val)
+void __kprobes preempt_count_sub(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2259,9 +2259,9 @@ void __kprobes sub_preempt_count(int val)
 
 	if (preempt_count() == val)
 		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
-	sub_preempt_count_notrace(val);
+	__preempt_count_sub(val);
 }
-EXPORT_SYMBOL(sub_preempt_count);
+EXPORT_SYMBOL(preempt_count_sub);
 
 #endif
 
@@ -2525,9 +2525,9 @@ asmlinkage void __sched notrace preempt_schedule(void)
 		return;
 
 	do {
-		add_preempt_count_notrace(PREEMPT_ACTIVE);
+		__preempt_count_add(PREEMPT_ACTIVE);
 		__schedule();
-		sub_preempt_count_notrace(PREEMPT_ACTIVE);
+		__preempt_count_sub(PREEMPT_ACTIVE);
 
 		/*
 		 * Check again in case we missed a preemption opportunity
@@ -2554,11 +2554,11 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	prev_state = exception_enter();
 
 	do {
-		add_preempt_count(PREEMPT_ACTIVE);
+		__preempt_count_add(PREEMPT_ACTIVE);
 		local_irq_enable();
 		__schedule();
 		local_irq_disable();
-		sub_preempt_count(PREEMPT_ACTIVE);
+		__preempt_count_sub(PREEMPT_ACTIVE);
 
 		/*
 		 * Check again in case we missed a preemption opportunity
@@ -3798,16 +3798,11 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
-static inline int should_resched(void)
-{
-	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
-}
-
 static void __cond_resched(void)
 {
-	add_preempt_count(PREEMPT_ACTIVE);
+	__preempt_count_add(PREEMPT_ACTIVE);
 	__schedule();
-	sub_preempt_count(PREEMPT_ACTIVE);
+	__preempt_count_sub(PREEMPT_ACTIVE);
 }
 
 int __sched _cond_resched(void)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index a90de70cf1f3..3e88612fc87e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -100,13 +100,13 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 
 	raw_local_irq_save(flags);
 	/*
-	 * The preempt tracer hooks into add_preempt_count and will break
+	 * The preempt tracer hooks into preempt_count_add and will break
 	 * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
 	 * is set and before current->softirq_enabled is cleared.
 	 * We must manually increment preempt_count here and manually
 	 * call the trace_preempt_off later.
 	 */
-	add_preempt_count_notrace(cnt);
+	__preempt_count_add(cnt);
 	/*
 	 * Were softirqs turned off above:
 	 */
@@ -120,7 +120,7 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 #else /* !CONFIG_TRACE_IRQFLAGS */
 static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
-	add_preempt_count(cnt);
+	preempt_count_add(cnt);
 	barrier();
 }
 #endif /* CONFIG_TRACE_IRQFLAGS */
@@ -139,7 +139,7 @@ static void __local_bh_enable(unsigned int cnt)
 
 	if (softirq_count() == cnt)
 		trace_softirqs_on(_RET_IP_);
-	sub_preempt_count(cnt);
+	preempt_count_sub(cnt);
 }
 
 /*
@@ -169,12 +169,12 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
  	 */
-	sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
+	preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending()))
 		do_softirq();
 
-	dec_preempt_count();
+	preempt_count_dec();
 #ifdef CONFIG_TRACE_IRQFLAGS
 	local_irq_enable();
 #endif
@@ -360,7 +360,7 @@ void irq_exit(void)
 
 	account_irq_exit_time(current);
 	trace_hardirq_exit();
-	sub_preempt_count(HARDIRQ_OFFSET);
+	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
-- 
cgit 


From a233f1120c37724938f7201fe2353b2577adaaf9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 23 Sep 2013 19:04:26 +0200
Subject: sched: Prepare for per-cpu preempt_count

When using per-cpu preempt_count variables we need to save/restore the
preempt_count on context switch (into per task storage; for instance
the old thread_info::preempt_count variable) because of
PREEMPT_ACTIVE.

However, this means that on fork() the preempt_count value of the last
context switch gets copied and if we had a PREEMPT_ACTIVE switch right
before cloning a child task the child task will now too have
PREEMPT_ACTIVE set and start its life with an extra PREEMPT_ACTIVE
count.

Therefore we need to make init_task_preempt_count() unconditional;
this resets whatever preempt_count we inherited from our parent
process.

Doing so for !per-cpu implementations is harmless.

For !PREEMPT_COUNT kernels we need to be careful not to start life
with an increased preempt_count.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-4k0b7oy1rcdyzochwiixuwi9@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 12 +++++++++---
 kernel/sched/core.c   |  2 --
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 06ac17c7e639..b09798b672f3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -428,6 +428,14 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
+
+#ifdef CONFIG_PREEMPT_COUNT
+#define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
+#else
+#define PREEMPT_DISABLED	PREEMPT_ENABLED
+#endif
+
 /*
  * Disable preemption until the scheduler is running.
  * Reset by start_kernel()->sched_init()->init_idle().
@@ -435,9 +443,7 @@ struct task_cputime {
  * We include PREEMPT_ACTIVE to avoid cond_resched() from working
  * before the scheduler is active -- see should_resched().
  */
-#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE + PREEMPT_NEED_RESCHED)
-#define PREEMPT_ENABLED		(PREEMPT_NEED_RESCHED)
-#define PREEMPT_DISABLED	(1 + PREEMPT_NEED_RESCHED)
+#define INIT_PREEMPT_COUNT	(PREEMPT_DISABLED + PREEMPT_ACTIVE)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9c84a9ab1892..f575d5bd7e7a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1722,9 +1722,7 @@ void sched_fork(struct task_struct *p)
 #if defined(CONFIG_SMP)
 	p->on_cpu = 0;
 #endif
-#ifdef CONFIG_PREEMPT_COUNT
 	init_task_preempt_count(p);
-#endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 #endif
-- 
cgit 


From 1a338ac32ca630f67df25b4a16436cccc314e997 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 14 Aug 2013 14:51:00 +0200
Subject: sched, x86: Optimize the preempt_schedule() call

Remove the bloat of the C calling convention out of the
preempt_enable() sites by creating an ASM wrapper which allows us to
do an asm("call ___preempt_schedule") instead.

calling.h bits by Andi Kleen

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-tk7xdi1cvvxewixzke8t8le1@git.kernel.org
[ Fixed build error. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/calling.h   | 50 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/preempt.h   | 10 ++++++++
 arch/x86/kernel/Makefile         |  2 ++
 arch/x86/kernel/i386_ksyms_32.c  |  7 ++++++
 arch/x86/kernel/preempt.S        | 25 ++++++++++++++++++++
 arch/x86/kernel/x8664_ksyms_64.c |  7 ++++++
 include/asm-generic/preempt.h    | 10 ++++++++
 include/linux/preempt.h          | 13 ++++-------
 8 files changed, 116 insertions(+), 8 deletions(-)
 create mode 100644 arch/x86/kernel/preempt.S

(limited to 'include')

diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0fa675033912..cb4c73bfeb48 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,6 +48,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 #include <asm/dwarf2.h>
 
+#ifdef CONFIG_X86_64
+
 /*
  * 64-bit system call stack frame layout defines and helpers,
  * for assembly code:
@@ -192,3 +194,51 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro icebp
 	.byte 0xf1
 	.endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+	.macro SAVE_ALL
+	pushl_cfi %eax
+	CFI_REL_OFFSET eax, 0
+	pushl_cfi %ebp
+	CFI_REL_OFFSET ebp, 0
+	pushl_cfi %edi
+	CFI_REL_OFFSET edi, 0
+	pushl_cfi %esi
+	CFI_REL_OFFSET esi, 0
+	pushl_cfi %edx
+	CFI_REL_OFFSET edx, 0
+	pushl_cfi %ecx
+	CFI_REL_OFFSET ecx, 0
+	pushl_cfi %ebx
+	CFI_REL_OFFSET ebx, 0
+	.endm
+
+	.macro RESTORE_ALL
+	popl_cfi %ebx
+	CFI_RESTORE ebx
+	popl_cfi %ecx
+	CFI_RESTORE ecx
+	popl_cfi %edx
+	CFI_RESTORE edx
+	popl_cfi %esi
+	CFI_RESTORE esi
+	popl_cfi %edi
+	CFI_RESTORE edi
+	popl_cfi %ebp
+	CFI_RESTORE ebp
+	popl_cfi %eax
+	CFI_RESTORE eax
+	.endm
+
+#endif /* CONFIG_X86_64 */
+
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 1309942b95e5..1de41690ff99 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -95,4 +95,14 @@ static __always_inline bool should_resched(void)
 	return unlikely(!__this_cpu_read_4(__preempt_count));
 }
 
+#ifdef CONFIG_PREEMPT
+  extern asmlinkage void ___preempt_schedule(void);
+# define __preempt_schedule() asm ("call ___preempt_schedule")
+  extern asmlinkage void preempt_schedule(void);
+# ifdef CONFIG_CONTEXT_TRACKING
+    extern asmlinkage void ___preempt_schedule_context(void);
+#   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+# endif
+#endif
+
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a5408b965c9d..9b0a34e2cd79 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -36,6 +36,8 @@ obj-y			+= tsc.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
+obj-$(CONFIG_PREEMPT)	+= preempt.o
+
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 0fa69127209a..05fd74f537d6 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr);
 
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
new file mode 100644
index 000000000000..ca7f0d58a87d
--- /dev/null
+++ b/arch/x86/kernel/preempt.S
@@ -0,0 +1,25 @@
+
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/asm.h>
+#include <asm/calling.h>
+
+ENTRY(___preempt_schedule)
+	CFI_STARTPROC
+	SAVE_ALL
+	call preempt_schedule
+	RESTORE_ALL
+	ret
+	CFI_ENDPROC
+
+#ifdef CONFIG_CONTEXT_TRACKING
+
+ENTRY(___preempt_schedule_context)
+	CFI_STARTPROC
+	SAVE_ALL
+	call preempt_schedule_context
+	RESTORE_ALL
+	ret
+	CFI_ENDPROC
+
+#endif
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index b014d9414d08..040681928e9d 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page);
 #ifndef CONFIG_PARAVIRT
 EXPORT_SYMBOL(native_load_gs_index);
 #endif
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 82d958fc3823..5dc14ed3791c 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -100,4 +100,14 @@ static __always_inline bool should_resched(void)
 	return unlikely(!*preempt_count_ptr());
 }
 
+#ifdef CONFIG_PREEMPT
+extern asmlinkage void preempt_schedule(void);
+#define __preempt_schedule() preempt_schedule()
+
+#ifdef CONFIG_CONTEXT_TRACKING
+extern asmlinkage void preempt_schedule_context(void);
+#define __preempt_schedule_context() preempt_schedule_context()
+#endif
+#endif /* CONFIG_PREEMPT */
+
 #endif /* __ASM_PREEMPT_H */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 2343d8715299..a3d9dc8c2c00 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -50,18 +50,17 @@ do { \
 #define preempt_enable_no_resched() sched_preempt_enable_no_resched()
 
 #ifdef CONFIG_PREEMPT
-asmlinkage void preempt_schedule(void);
 #define preempt_enable() \
 do { \
 	barrier(); \
 	if (unlikely(preempt_count_dec_and_test())) \
-		preempt_schedule(); \
+		__preempt_schedule(); \
 } while (0)
 
 #define preempt_check_resched() \
 do { \
 	if (should_resched()) \
-		preempt_schedule(); \
+		__preempt_schedule(); \
 } while (0)
 
 #else
@@ -83,17 +82,15 @@ do { \
 
 #ifdef CONFIG_PREEMPT
 
-#ifdef CONFIG_CONTEXT_TRACKING
-asmlinkage void preempt_schedule_context(void);
-#else
-#define preempt_schedule_context() preempt_schedule()
+#ifndef CONFIG_CONTEXT_TRACKING
+#define __preempt_schedule_context() __preempt_schedule()
 #endif
 
 #define preempt_enable_notrace() \
 do { \
 	barrier(); \
 	if (unlikely(__preempt_count_dec_and_test())) \
-		preempt_schedule_context(); \
+		__preempt_schedule_context(); \
 } while (0)
 #else
 #define preempt_enable_notrace() preempt_enable_no_resched_notrace()
-- 
cgit 


From 22d4aae5897fb8355130b8f7d9a3af153eac9714 Mon Sep 17 00:00:00 2001
From: Eric Lapuyade <eric.lapuyade@linux.intel.com>
Date: Mon, 23 Sep 2013 17:56:31 +0200
Subject: NFC: NCI: nci_spi_recv_frame() now returns (not forward) the read
 frame

Previously, nci_spi_recv_frame() would directly transmit incoming frames
to the NCI Core. However, it turns out that some NFC NCI Chips will add
additional proprietary headers that must be handled/removed before NCI
Core gets a chance to handle the frame. With this modification, the chip
phy or driver are now responsible to transmit incoming frames to NCI
Core after proper treatment, and NCI SPI becomes a driver helper instead
of sitting between the NFC driver and NCI Core.

As a general rule in NFC, *_recv_frame() APIs are used to deliver an
incoming frame to an upper layer. To better suit the actual purpose of
nci_spi_recv_frame(), and go along with its nci_spi_send()
counterpart, the function is renamed to nci_spi_read()

The skb is returned as the function result

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h |  2 +-
 net/nfc/nci/spi.c          | 26 ++++++++++----------------
 2 files changed, 11 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 37ba06f2dfa9..1d505317dc67 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -233,6 +233,6 @@ struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
 				     u8 acknowledge_mode, unsigned int delay,
 				     struct nci_dev *ndev);
 int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb);
-int nci_spi_recv_frame(struct nci_spi *nspi);
+struct sk_buff *nci_spi_read(struct nci_spi *nspi);
 
 #endif /* __NCI_CORE_H */
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index c111506b36d1..734c6dde7751 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -21,7 +21,6 @@
 #include <linux/export.h>
 #include <linux/spi/spi.h>
 #include <linux/crc-ccitt.h>
-#include <linux/nfc.h>
 #include <net/nfc/nci_core.h>
 
 #define NCI_SPI_ACK_SHIFT		6
@@ -164,7 +163,7 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
 	return ret;
 }
 
-static struct sk_buff *__nci_spi_recv_frame(struct nci_spi *nspi)
+static struct sk_buff *__nci_spi_read(struct nci_spi *nspi)
 {
 	struct sk_buff *skb;
 	struct spi_message m;
@@ -258,7 +257,7 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
 }
 
 /**
- * nci_spi_recv_frame - receive frame from NCI SPI drivers
+ * nci_spi_read - read frame from NCI SPI drivers
  *
  * @nspi: The nci spi
  * Context: can sleep
@@ -266,21 +265,18 @@ static u8 nci_spi_get_ack(struct sk_buff *skb)
  * This call may only be used from a context that may sleep.  The sleep
  * is non-interruptible, and has no timeout.
  *
- * It returns zero on success, else a negative error code.
+ * It returns an allocated skb containing the frame on success, or NULL.
  */
-int nci_spi_recv_frame(struct nci_spi *nspi)
+struct sk_buff *nci_spi_read(struct nci_spi *nspi)
 {
 	struct sk_buff *skb;
-	int ret = 0;
 
 	nspi->ops->deassert_int(nspi);
 
 	/* Retrieve frame from SPI */
-	skb = __nci_spi_recv_frame(nspi);
-	if (!skb) {
-		ret = -EIO;
+	skb = __nci_spi_read(nspi);
+	if (!skb)
 		goto done;
-	}
 
 	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED) {
 		if (!nci_spi_check_crc(skb)) {
@@ -299,20 +295,18 @@ int nci_spi_recv_frame(struct nci_spi *nspi)
 	/* If there is no payload (ACK/NACK only frame),
 	 * free the socket buffer
 	 */
-	if (skb->len == 0) {
+	if (!skb->len) {
 		kfree_skb(skb);
+		skb = NULL;
 		goto done;
 	}
 
 	if (nspi->acknowledge_mode == NCI_SPI_CRC_ENABLED)
 		send_acknowledge(nspi, ACKNOWLEDGE_ACK);
 
-	/* Forward skb to NCI core layer */
-	ret = nci_recv_frame(nspi->ndev, skb);
-
 done:
 	nspi->ops->assert_int(nspi);
 
-	return ret;
+	return skb;
 }
-EXPORT_SYMBOL_GPL(nci_spi_recv_frame);
+EXPORT_SYMBOL_GPL(nci_spi_read);
-- 
cgit 


From 2bed27851767d93b5d2823eee110857f350a9fbe Mon Sep 17 00:00:00 2001
From: Eric Lapuyade <eric.lapuyade@linux.intel.com>
Date: Mon, 23 Sep 2013 17:56:43 +0200
Subject: NFC: NCI: Modify NCI SPI to implement CS/INT handshake per the spec
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The NFC Forum NCI specification defines both a hardware and software
protocol when using a SPI physical transport to connect an NFC NCI
Chipset. The hardware requirement is that, after having raised the chip
select line, the SPI driver must wait for an INT line from the NFC
chipset to raise before it sends the data. The chip select must be
raised first though, because this is the signal that the NFC chipset
will detect to wake up and then raise its INT line. If the INT line
doesn't raise in a timely fashion, the SPI driver should abort
operation.

When data is transferred from Device host (DH) to NFC Controller (NFCC),
the signaling sequence is the following:

Data Transfer from DH to NFCC
• 1-Master asserts SPI_CSN
• 2-Slave asserts SPI_INT
• 3-Master sends NCI-over-SPI protocol header and payload data
• 4-Slave deasserts SPI_INT
• 5-Master deasserts SPI_CSN

When data must be transferred from NFCC to DH, things are a little bit
different.

Data Transfer from NFCC to DH
• 1-Slave asserts SPI_INT -> NFC chipset irq handler called -> process
reading from SPI
• 2-Master asserts SPI_CSN
• 3-Master send 2-octet NCI-over-SPI protocol header
• 4-Slave sends 2-octet NCI-over-SPI protocol payload length
• 5-Slave sends NCI-over-SPI protocol payload
• 6-Master deasserts SPI_CSN

In this case, SPI driver should function normally as it does today. Note
that the INT line can and will be lowered anytime between beginning of
step 3 and end of step 5. A low INT is therefore valid after chip select
has been raised.

This would be easily implemented in a single driver. Unfortunately, we
don't write the SPI driver and I had to imagine some workaround trick to
get the SPI and NFC drivers to work in a synchronized fashion. The trick
is the following:

- send an empty spi message: this will raise the chip select line, and
send nothing. We expect the /CS line will stay arisen because we asked
for it in the spi_transfer cs_change field
- wait for a completion, that will be completed by the NFC driver IRQ
handler when it knows we are in the process of sending data (NFC spec
says that we use SPI in a half duplex mode, so we are either sending or
receiving).
- when completed, proceed with the normal data send.

This has been tested and verified to work very consistently on a Nexus
10 (spi-s3c64xx driver). It may not work the same with other spi
drivers.

The previously defined nci_spi_ops{} whose intended purpose were to
address this problem are not used anymore and therefore totally removed.

The nci_spi_send() takes a new optional write_handshake_completion
completion pointer. If non NULL, the nci spi layer will run the above
trick when sending data to the NFC Chip. If NULL, the data is sent
normally all at once and it is then the NFC driver responsibility to
know what it's doing.

Signed-off-by: Eric Lapuyade <eric.lapuyade@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 13 +++---------
 net/nfc/nci/spi.c          | 53 +++++++++++++++++++++++++++-------------------
 2 files changed, 34 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 1d505317dc67..6126f1f992b4 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -207,17 +207,9 @@ int nci_to_errno(__u8 code);
 #define NCI_SPI_CRC_ENABLED	0x01
 
 /* ----- NCI SPI structures ----- */
-struct nci_spi;
-
-struct nci_spi_ops {
-	void (*assert_int)(struct nci_spi *nspi);
-	void (*deassert_int)(struct nci_spi *nspi);
-};
-
 struct nci_spi {
 	struct nci_dev		*ndev;
 	struct spi_device	*spi;
-	struct nci_spi_ops	*ops;
 
 	unsigned int		xfer_udelay;	/* microseconds delay between
 						  transactions */
@@ -229,10 +221,11 @@ struct nci_spi {
 
 /* ----- NCI SPI ----- */
 struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
-				     struct nci_spi_ops *ops,
 				     u8 acknowledge_mode, unsigned int delay,
 				     struct nci_dev *ndev);
-int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb);
+int nci_spi_send(struct nci_spi *nspi,
+		 struct completion *write_handshake_completion,
+		 struct sk_buff *skb);
 struct sk_buff *nci_spi_read(struct nci_spi *nspi);
 
 #endif /* __NCI_CORE_H */
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index 734c6dde7751..f1d426f10cce 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -38,15 +38,23 @@
 
 #define CRC_INIT		0xFFFF
 
-static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
+static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb,
+			  int cs_change)
 {
 	struct spi_message m;
 	struct spi_transfer t;
 
 	memset(&t, 0, sizeof(struct spi_transfer));
-	t.tx_buf = skb->data;
-	t.len = skb->len;
-	t.cs_change = 0;
+	/* a NULL skb means we just want the SPI chip select line to raise */
+	if (skb) {
+		t.tx_buf = skb->data;
+		t.len = skb->len;
+	} else {
+		/* still set tx_buf non NULL to make the driver happy */
+		t.tx_buf = &t;
+		t.len = 0;
+	}
+	t.cs_change = cs_change;
 	t.delay_usecs = nspi->xfer_udelay;
 
 	spi_message_init(&m);
@@ -55,15 +63,15 @@ static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
 	return spi_sync(nspi->spi, &m);
 }
 
-int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
+int nci_spi_send(struct nci_spi *nspi,
+		 struct completion *write_handshake_completion,
+		 struct sk_buff *skb)
 {
 	unsigned int payload_len = skb->len;
 	unsigned char *hdr;
 	int ret;
 	long completion_rc;
 
-	nspi->ops->deassert_int(nspi);
-
 	/* add the NCI SPI header to the start of the buffer */
 	hdr = skb_push(skb, NCI_SPI_HDR_LEN);
 	hdr[0] = NCI_SPI_DIRECT_WRITE;
@@ -79,11 +87,21 @@ int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
 		*skb_put(skb, 1) = crc & 0xFF;
 	}
 
-	ret = __nci_spi_send(nspi, skb);
+	if (write_handshake_completion)	{
+		/* Trick SPI driver to raise chip select */
+		ret = __nci_spi_send(nspi, NULL, 1);
+		if (ret)
+			goto done;
 
-	kfree_skb(skb);
-	nspi->ops->assert_int(nspi);
+		/* wait for NFC chip hardware handshake to complete */
+		if (wait_for_completion_timeout(write_handshake_completion,
+						msecs_to_jiffies(1000)) == 0) {
+			ret = -ETIME;
+			goto done;
+		}
+	}
 
+	ret = __nci_spi_send(nspi, skb, 0);
 	if (ret != 0 || nspi->acknowledge_mode == NCI_SPI_CRC_DISABLED)
 		goto done;
 
@@ -96,6 +114,8 @@ int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb)
 		ret = -EIO;
 
 done:
+	kfree_skb(skb);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nci_spi_send);
@@ -106,26 +126,20 @@ EXPORT_SYMBOL_GPL(nci_spi_send);
  * nci_spi_allocate_spi - allocate a new nci spi
  *
  * @spi: SPI device
- * @ops: device operations
  * @acknowledge_mode: Acknowledge mode used by the NFC device
  * @delay: delay between transactions in us
  * @ndev: nci dev to send incoming nci frames to
  */
 struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi,
-				     struct nci_spi_ops *ops,
 				     u8 acknowledge_mode, unsigned int delay,
 				     struct nci_dev *ndev)
 {
 	struct nci_spi *nspi;
 
-	if (!ops->assert_int || !ops->deassert_int)
-		return NULL;
-
 	nspi = devm_kzalloc(&spi->dev, sizeof(struct nci_spi), GFP_KERNEL);
 	if (!nspi)
 		return NULL;
 
-	nspi->ops = ops;
 	nspi->acknowledge_mode = acknowledge_mode;
 	nspi->xfer_udelay = delay;
 
@@ -156,7 +170,7 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
 	*skb_put(skb, 1) = crc >> 8;
 	*skb_put(skb, 1) = crc & 0xFF;
 
-	ret = __nci_spi_send(nspi, skb);
+	ret = __nci_spi_send(nspi, skb, 0);
 
 	kfree_skb(skb);
 
@@ -189,7 +203,6 @@ static struct sk_buff *__nci_spi_read(struct nci_spi *nspi)
 	spi_message_add_tail(&rx, &m);
 
 	ret = spi_sync(nspi->spi, &m);
-
 	if (ret)
 		return NULL;
 
@@ -213,7 +226,6 @@ static struct sk_buff *__nci_spi_read(struct nci_spi *nspi)
 	spi_message_add_tail(&rx, &m);
 
 	ret = spi_sync(nspi->spi, &m);
-
 	if (ret)
 		goto receive_error;
 
@@ -271,8 +283,6 @@ struct sk_buff *nci_spi_read(struct nci_spi *nspi)
 {
 	struct sk_buff *skb;
 
-	nspi->ops->deassert_int(nspi);
-
 	/* Retrieve frame from SPI */
 	skb = __nci_spi_read(nspi);
 	if (!skb)
@@ -305,7 +315,6 @@ struct sk_buff *nci_spi_read(struct nci_spi *nspi)
 		send_acknowledge(nspi, ACKNOWLEDGE_ACK);
 
 done:
-	nspi->ops->assert_int(nspi);
 
 	return skb;
 }
-- 
cgit 


From cc6783f788d8fe8b23ec6fc2762f5e8c9a418eee Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 6 Sep 2013 17:39:49 -0700
Subject: rcu: Is it safe to enter an RCU read-side critical section?

There is currently no way for kernel code to determine whether it
is safe to enter an RCU read-side critical section, in other words,
whether or not RCU is paying attention to the currently running CPU.
Given the large and increasing quantity of code shared by the idle loop
and non-idle code, the this shortcoming is becoming increasingly painful.

This commit therefore adds __rcu_is_watching(), which returns true if
it is safe to enter an RCU read-side critical section on the currently
running CPU.  This function is quite fast, using only a __this_cpu_read().
However, the caller must disable preemption.

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 include/linux/rcupdate.h |  8 ++++----
 include/linux/rcutiny.h  |  9 +++++++++
 include/linux/rcutree.h  |  2 ++
 kernel/rcutiny.c         |  4 ++--
 kernel/rcutree.c         | 13 +++++++++++++
 5 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f1f1bc39346b..a53a21a2808c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -261,6 +261,10 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 		rcu_irq_exit(); \
 	} while (0)
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
+extern int rcu_is_cpu_idle(void);
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
+
 /*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
@@ -297,10 +301,6 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP)
-extern int rcu_is_cpu_idle(void);
-#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */
-
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU)
 bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index e31005ee339e..bee665964878 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -132,4 +132,13 @@ static inline void rcu_scheduler_starting(void)
 }
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+#ifdef CONFIG_RCU_TRACE
+
+static inline bool __rcu_is_watching(void)
+{
+	return !rcu_is_cpu_idle();
+}
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 226169d1bd2b..293613dfd2a5 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -90,4 +90,6 @@ extern void exit_rcu(void);
 extern void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
+extern bool __rcu_is_watching(void);
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9ed6075dc562..b4bc61874d77 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -174,7 +174,7 @@ void rcu_irq_enter(void)
 }
 EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
  * Test whether RCU thinks that the current CPU is idle.
@@ -185,7 +185,7 @@ int rcu_is_cpu_idle(void)
 }
 EXPORT_SYMBOL(rcu_is_cpu_idle);
 
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
 /*
  * Test whether the current CPU was interrupted from idle.  Nested
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 32618b3fe4e6..910d868808dc 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -671,6 +671,19 @@ int rcu_is_cpu_idle(void)
 }
 EXPORT_SYMBOL(rcu_is_cpu_idle);
 
+/**
+ * __rcu_is_watching - are RCU read-side critical sections safe?
+ *
+ * Return true if RCU is watching the running CPU, which means that
+ * this CPU can safely enter RCU read-side critical sections.  Unlike
+ * rcu_is_cpu_idle(), the caller of __rcu_is_watching() must have at
+ * least disabled preemption.
+ */
+bool __rcu_is_watching(void)
+{
+	return !!(atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1);
+}
+
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
-- 
cgit 


From 5c173eb8bcb9c1aa888bd6d14a4cb746f3dd2420 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 13 Sep 2013 17:20:11 -0700
Subject: rcu: Consistent rcu_is_watching() naming

The old rcu_is_cpu_idle() function is just __rcu_is_watching() with
preemption disabled.  This commit therefore renames rcu_is_cpu_idle()
to rcu_is_watching.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
 include/linux/rcupdate.h | 18 +++++++++---------
 include/linux/rcutiny.h  | 16 ++++++++++++----
 include/linux/rcutree.h  |  2 +-
 kernel/lockdep.c         |  4 ++--
 kernel/rcupdate.c        |  2 +-
 kernel/rcutiny.c         |  6 +++---
 kernel/rcutree.c         | 36 ++++++++++++++++++------------------
 7 files changed, 46 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a53a21a2808c..39cbb889e20d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -262,7 +262,7 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 	} while (0)
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
-extern int rcu_is_cpu_idle(void);
+extern bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
@@ -351,7 +351,7 @@ static inline int rcu_read_lock_held(void)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		return 0;
 	if (!rcu_lockdep_current_cpu_online())
 		return 0;
@@ -402,7 +402,7 @@ static inline int rcu_read_lock_sched_held(void)
 
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		return 0;
 	if (!rcu_lockdep_current_cpu_online())
 		return 0;
@@ -771,7 +771,7 @@ static inline void rcu_read_lock(void)
 	__rcu_read_lock();
 	__acquire(RCU);
 	rcu_lock_acquire(&rcu_lock_map);
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_lock() used illegally while idle");
 }
 
@@ -792,7 +792,7 @@ static inline void rcu_read_lock(void)
  */
 static inline void rcu_read_unlock(void)
 {
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_unlock() used illegally while idle");
 	rcu_lock_release(&rcu_lock_map);
 	__release(RCU);
@@ -821,7 +821,7 @@ static inline void rcu_read_lock_bh(void)
 	local_bh_disable();
 	__acquire(RCU_BH);
 	rcu_lock_acquire(&rcu_bh_lock_map);
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_lock_bh() used illegally while idle");
 }
 
@@ -832,7 +832,7 @@ static inline void rcu_read_lock_bh(void)
  */
 static inline void rcu_read_unlock_bh(void)
 {
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_unlock_bh() used illegally while idle");
 	rcu_lock_release(&rcu_bh_lock_map);
 	__release(RCU_BH);
@@ -857,7 +857,7 @@ static inline void rcu_read_lock_sched(void)
 	preempt_disable();
 	__acquire(RCU_SCHED);
 	rcu_lock_acquire(&rcu_sched_lock_map);
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_lock_sched() used illegally while idle");
 }
 
@@ -875,7 +875,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void)
  */
 static inline void rcu_read_unlock_sched(void)
 {
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
+	rcu_lockdep_assert(rcu_is_watching(),
 			   "rcu_read_unlock_sched() used illegally while idle");
 	rcu_lock_release(&rcu_sched_lock_map);
 	__release(RCU_SCHED);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index bee665964878..09ebcbe9fd78 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -132,13 +132,21 @@ static inline void rcu_scheduler_starting(void)
 }
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
-#ifdef CONFIG_RCU_TRACE
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
-static inline bool __rcu_is_watching(void)
+static inline bool rcu_is_watching(void)
 {
-	return !rcu_is_cpu_idle();
+	return __rcu_is_watching();
 }
 
-#endif /* #ifdef CONFIG_RCU_TRACE */
+#else /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
+
+static inline bool rcu_is_watching(void)
+{
+	return true;
+}
+
+
+#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 293613dfd2a5..4b9c81548742 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -90,6 +90,6 @@ extern void exit_rcu(void);
 extern void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
-extern bool __rcu_is_watching(void);
+extern bool rcu_is_watching(void);
 
 #endif /* __LINUX_RCUTREE_H */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e16c45b9ee77..4e8e14c34e42 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4224,7 +4224,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
-			: rcu_is_cpu_idle()
+			: !rcu_is_watching()
 				? "RCU used illegally from idle CPU!\n"
 				: "",
 	       rcu_scheduler_active, debug_locks);
@@ -4247,7 +4247,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	 * So complain bitterly if someone does call rcu_read_lock(),
 	 * rcu_read_lock_bh() and so on from extended quiescent states.
 	 */
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		printk("RCU used illegally from extended quiescent state!\n");
 
 	lockdep_print_held_locks(curr);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index b02a339836b4..3b3c0464d1eb 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -148,7 +148,7 @@ int rcu_read_lock_bh_held(void)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		return 0;
 	if (!rcu_lockdep_current_cpu_online())
 		return 0;
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index b4bc61874d77..0fa061dfa55d 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -179,11 +179,11 @@ EXPORT_SYMBOL_GPL(rcu_irq_enter);
 /*
  * Test whether RCU thinks that the current CPU is idle.
  */
-int rcu_is_cpu_idle(void)
+bool __rcu_is_watching(void)
 {
-	return !rcu_dynticks_nesting;
+	return rcu_dynticks_nesting;
 }
-EXPORT_SYMBOL(rcu_is_cpu_idle);
+EXPORT_SYMBOL(__rcu_is_watching);
 
 #endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1b123e179d71..981d0c15a389 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -655,34 +655,34 @@ void rcu_nmi_exit(void)
 }
 
 /**
- * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
+ * __rcu_is_watching - are RCU read-side critical sections safe?
+ *
+ * Return true if RCU is watching the running CPU, which means that
+ * this CPU can safely enter RCU read-side critical sections.  Unlike
+ * rcu_is_watching(), the caller of __rcu_is_watching() must have at
+ * least disabled preemption.
+ */
+bool __rcu_is_watching(void)
+{
+	return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+}
+
+/**
+ * rcu_is_watching - see if RCU thinks that the current CPU is idle
  *
  * If the current CPU is in its idle loop and is neither in an interrupt
  * or NMI handler, return true.
  */
-int rcu_is_cpu_idle(void)
+bool rcu_is_watching(void)
 {
 	int ret;
 
 	preempt_disable();
-	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
+	ret = __rcu_is_watching();
 	preempt_enable();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(rcu_is_cpu_idle);
-
-/**
- * __rcu_is_watching - are RCU read-side critical sections safe?
- *
- * Return true if RCU is watching the running CPU, which means that
- * this CPU can safely enter RCU read-side critical sections.  Unlike
- * rcu_is_cpu_idle(), the caller of __rcu_is_watching() must have at
- * least disabled preemption.
- */
-bool __rcu_is_watching(void)
-{
-	return !!(atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1);
-}
+EXPORT_SYMBOL_GPL(rcu_is_watching);
 
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
@@ -2268,7 +2268,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
 	 */
-	if (rcu_is_cpu_idle() && cpu_online(smp_processor_id()))
+	if (!rcu_is_watching() && cpu_online(smp_processor_id()))
 		invoke_rcu_core();
 
 	/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
-- 
cgit 


From 9abc4e66eb839c28516916543768be08c814a3c8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:15:10 +0100
Subject: KEYS: Rename public key parameter name arrays

Rename the arrays of public key parameters (public key algorithm names, hash
algorithm names and ID type names) so that the array name ends in "_name".

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Josh Boyer <jwboyer@redhat.com>
---
 crypto/asymmetric_keys/public_key.c      | 14 +++++++-------
 crypto/asymmetric_keys/x509_public_key.c |  8 ++++----
 include/crypto/public_key.h              |  6 +++---
 kernel/module_signing.c                  |  4 ++--
 4 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index cb2e29180a87..b313df1bd253 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -22,13 +22,13 @@
 
 MODULE_LICENSE("GPL");
 
-const char *const pkey_algo[PKEY_ALGO__LAST] = {
+const char *const pkey_algo_name[PKEY_ALGO__LAST] = {
 	[PKEY_ALGO_DSA]		= "DSA",
 	[PKEY_ALGO_RSA]		= "RSA",
 };
-EXPORT_SYMBOL_GPL(pkey_algo);
+EXPORT_SYMBOL_GPL(pkey_algo_name);
 
-const char *const pkey_hash_algo[PKEY_HASH__LAST] = {
+const char *const pkey_hash_algo_name[PKEY_HASH__LAST] = {
 	[PKEY_HASH_MD4]		= "md4",
 	[PKEY_HASH_MD5]		= "md5",
 	[PKEY_HASH_SHA1]	= "sha1",
@@ -38,13 +38,13 @@ const char *const pkey_hash_algo[PKEY_HASH__LAST] = {
 	[PKEY_HASH_SHA512]	= "sha512",
 	[PKEY_HASH_SHA224]	= "sha224",
 };
-EXPORT_SYMBOL_GPL(pkey_hash_algo);
+EXPORT_SYMBOL_GPL(pkey_hash_algo_name);
 
-const char *const pkey_id_type[PKEY_ID_TYPE__LAST] = {
+const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST] = {
 	[PKEY_ID_PGP]		= "PGP",
 	[PKEY_ID_X509]		= "X509",
 };
-EXPORT_SYMBOL_GPL(pkey_id_type);
+EXPORT_SYMBOL_GPL(pkey_id_type_name);
 
 /*
  * Provide a part of a description of the key for /proc/keys.
@@ -56,7 +56,7 @@ static void public_key_describe(const struct key *asymmetric_key,
 
 	if (key)
 		seq_printf(m, "%s.%s",
-			   pkey_id_type[key->id_type], key->algo->name);
+			   pkey_id_type_name[key->id_type], key->algo->name);
 }
 
 /*
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 06007f0e880c..afbbc362f85a 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -49,7 +49,7 @@ static int x509_check_signature(const struct public_key *pub,
 	/* Allocate the hashing algorithm we're going to need and find out how
 	 * big the hash operational data will be.
 	 */
-	tfm = crypto_alloc_shash(pkey_hash_algo[cert->sig_hash_algo], 0, 0);
+	tfm = crypto_alloc_shash(pkey_hash_algo_name[cert->sig_hash_algo], 0, 0);
 	if (IS_ERR(tfm))
 		return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm);
 
@@ -117,7 +117,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 
 	pr_devel("Cert Issuer: %s\n", cert->issuer);
 	pr_devel("Cert Subject: %s\n", cert->subject);
-	pr_devel("Cert Key Algo: %s\n", pkey_algo[cert->pkey_algo]);
+	pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pkey_algo]);
 	pr_devel("Cert Valid From: %04ld-%02d-%02d %02d:%02d:%02d\n",
 		 cert->valid_from.tm_year + 1900, cert->valid_from.tm_mon + 1,
 		 cert->valid_from.tm_mday, cert->valid_from.tm_hour,
@@ -127,8 +127,8 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		 cert->valid_to.tm_mday, cert->valid_to.tm_hour,
 		 cert->valid_to.tm_min,  cert->valid_to.tm_sec);
 	pr_devel("Cert Signature: %s + %s\n",
-		 pkey_algo[cert->sig_pkey_algo],
-		 pkey_hash_algo[cert->sig_hash_algo]);
+		 pkey_algo_name[cert->sig_pkey_algo],
+		 pkey_hash_algo_name[cert->sig_hash_algo]);
 
 	if (!cert->fingerprint || !cert->authority) {
 		pr_warn("Cert for '%s' must have SubjKeyId and AuthKeyId extensions\n",
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index f5b0224c9967..619d5706d837 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -22,7 +22,7 @@ enum pkey_algo {
 	PKEY_ALGO__LAST
 };
 
-extern const char *const pkey_algo[PKEY_ALGO__LAST];
+extern const char *const pkey_algo_name[PKEY_ALGO__LAST];
 
 enum pkey_hash_algo {
 	PKEY_HASH_MD4,
@@ -36,7 +36,7 @@ enum pkey_hash_algo {
 	PKEY_HASH__LAST
 };
 
-extern const char *const pkey_hash_algo[PKEY_HASH__LAST];
+extern const char *const pkey_hash_algo_name[PKEY_HASH__LAST];
 
 enum pkey_id_type {
 	PKEY_ID_PGP,		/* OpenPGP generated key ID */
@@ -44,7 +44,7 @@ enum pkey_id_type {
 	PKEY_ID_TYPE__LAST
 };
 
-extern const char *const pkey_id_type[PKEY_ID_TYPE__LAST];
+extern const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST];
 
 /*
  * Cryptographic data for the public-key subtype of the asymmetric key type.
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index f2970bddc5ea..ee476404167b 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -54,7 +54,7 @@ static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
 	/* Allocate the hashing algorithm we're going to need and find out how
 	 * big the hash operational data will be.
 	 */
-	tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0);
+	tfm = crypto_alloc_shash(pkey_hash_algo_name[hash], 0, 0);
 	if (IS_ERR(tfm))
 		return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm);
 
@@ -217,7 +217,7 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
 		return -ENOPKG;
 
 	if (ms.hash >= PKEY_HASH__LAST ||
-	    !pkey_hash_algo[ms.hash])
+	    !pkey_hash_algo_name[ms.hash])
 		return -ENOPKG;
 
 	key = request_asymmetric_key(sig, ms.signer_len,
-- 
cgit 


From 206ce59a109f3b4bb352845bcd04f3cf504ae592 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:15:18 +0100
Subject: KEYS: Move the algorithm pointer array from x509 to public_key.c

Move the public-key algorithm pointer array from x509_public_key.c to
public_key.c as it isn't X.509 specific.

Note that to make this configure correctly, the public key part must be
dependent on the RSA module rather than the other way round.  This needs a
further patch to make use of the crypto module loading stuff rather than using
a fixed table.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Josh Boyer <jwboyer@redhat.com>
---
 crypto/asymmetric_keys/Kconfig           |  2 +-
 crypto/asymmetric_keys/public_key.c      |  8 ++++++++
 crypto/asymmetric_keys/x509_public_key.c | 11 +----------
 include/crypto/public_key.h              |  1 +
 4 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig
index 6d2c2ea12559..862b01fe6172 100644
--- a/crypto/asymmetric_keys/Kconfig
+++ b/crypto/asymmetric_keys/Kconfig
@@ -12,6 +12,7 @@ if ASYMMETRIC_KEY_TYPE
 config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
 	tristate "Asymmetric public-key crypto algorithm subtype"
 	select MPILIB
+	select PUBLIC_KEY_ALGO_RSA
 	help
 	  This option provides support for asymmetric public key type handling.
 	  If signature generation and/or verification are to be used,
@@ -20,7 +21,6 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
 
 config PUBLIC_KEY_ALGO_RSA
 	tristate "RSA public-key algorithm"
-	depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE
 	select MPILIB_EXTRA
 	help
 	  This option enables support for the RSA algorithm (PKCS#1, RFC3447).
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index b313df1bd253..796ce0802aa0 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -28,6 +28,14 @@ const char *const pkey_algo_name[PKEY_ALGO__LAST] = {
 };
 EXPORT_SYMBOL_GPL(pkey_algo_name);
 
+const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST] = {
+#if defined(CONFIG_PUBLIC_KEY_ALGO_RSA) || \
+	defined(CONFIG_PUBLIC_KEY_ALGO_RSA_MODULE)
+	[PKEY_ALGO_RSA]		= &RSA_public_key_algorithm,
+#endif
+};
+EXPORT_SYMBOL_GPL(pkey_algo);
+
 const char *const pkey_hash_algo_name[PKEY_HASH__LAST] = {
 	[PKEY_HASH_MD4]		= "md4",
 	[PKEY_HASH_MD5]		= "md5",
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index afbbc362f85a..fe38628adae9 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -23,15 +23,6 @@
 #include "public_key.h"
 #include "x509_parser.h"
 
-static const
-struct public_key_algorithm *x509_public_key_algorithms[PKEY_ALGO__LAST] = {
-	[PKEY_ALGO_DSA]		= NULL,
-#if defined(CONFIG_PUBLIC_KEY_ALGO_RSA) || \
-	defined(CONFIG_PUBLIC_KEY_ALGO_RSA_MODULE)
-	[PKEY_ALGO_RSA]		= &RSA_public_key_algorithm,
-#endif
-};
-
 /*
  * Check the signature on a certificate using the provided public key
  */
@@ -174,7 +165,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		goto error_free_cert;
 	}
 
-	cert->pub->algo = x509_public_key_algorithms[cert->pkey_algo];
+	cert->pub->algo = pkey_algo[cert->pkey_algo];
 	cert->pub->id_type = PKEY_ID_X509;
 
 	/* Check the signature on the key */
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 619d5706d837..46bde250bfae 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -23,6 +23,7 @@ enum pkey_algo {
 };
 
 extern const char *const pkey_algo_name[PKEY_ALGO__LAST];
+extern const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST];
 
 enum pkey_hash_algo {
 	PKEY_HASH_MD4,
-- 
cgit 


From 67f7d60b3a08a3e3ec51c29c25767a9d9d0bd2b1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:15:24 +0100
Subject: KEYS: Store public key algo ID in public_key struct

Store public key algo ID in public_key struct for reference purposes.  This
allows it to be removed from the x509_certificate struct and used to find a
default in public_key_verify_signature().

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Josh Boyer <jwboyer@redhat.com>
---
 crypto/asymmetric_keys/x509_cert_parser.c | 5 +++--
 crypto/asymmetric_keys/x509_parser.h      | 1 -
 crypto/asymmetric_keys/x509_public_key.c  | 4 ++--
 include/crypto/public_key.h               | 1 +
 4 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index facbf26bc6bb..8cc253d2dc92 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -343,8 +343,9 @@ int x509_extract_key_data(void *context, size_t hdrlen,
 	if (ctx->last_oid != OID_rsaEncryption)
 		return -ENOPKG;
 
-	/* There seems to be an extraneous 0 byte on the front of the data */
-	ctx->cert->pkey_algo = PKEY_ALGO_RSA;
+	ctx->cert->pub->pkey_algo = PKEY_ALGO_RSA;
+
+	/* Discard the BIT STRING metadata */
 	ctx->key = value + 1;
 	ctx->key_size = vlen - 1;
 	return 0;
diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index f86dc5fcc4ad..e583ad09e5a1 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -20,7 +20,6 @@ struct x509_certificate {
 	char		*authority;		/* Authority key fingerprint as hex */
 	struct tm	valid_from;
 	struct tm	valid_to;
-	enum pkey_algo	pkey_algo : 8;		/* Public key algorithm */
 	enum pkey_algo	sig_pkey_algo : 8;	/* Signature public key algorithm */
 	enum pkey_hash_algo sig_hash_algo : 8;	/* Signature hash algorithm */
 	const void	*tbs;			/* Signed data */
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index fe38628adae9..fac574c457b3 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -108,7 +108,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 
 	pr_devel("Cert Issuer: %s\n", cert->issuer);
 	pr_devel("Cert Subject: %s\n", cert->subject);
-	pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pkey_algo]);
+	pr_devel("Cert Key Algo: %s\n", pkey_algo_name[cert->pub->pkey_algo]);
 	pr_devel("Cert Valid From: %04ld-%02d-%02d %02d:%02d:%02d\n",
 		 cert->valid_from.tm_year + 1900, cert->valid_from.tm_mon + 1,
 		 cert->valid_from.tm_mday, cert->valid_from.tm_hour,
@@ -165,7 +165,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		goto error_free_cert;
 	}
 
-	cert->pub->algo = pkey_algo[cert->pkey_algo];
+	cert->pub->algo = pkey_algo[cert->pub->pkey_algo];
 	cert->pub->id_type = PKEY_ID_X509;
 
 	/* Check the signature on the key */
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 46bde250bfae..05778df0e3b4 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -60,6 +60,7 @@ struct public_key {
 #define PKEY_CAN_DECRYPT	0x02
 #define PKEY_CAN_SIGN		0x04
 #define PKEY_CAN_VERIFY		0x08
+	enum pkey_algo pkey_algo : 8;
 	enum pkey_id_type id_type : 8;
 	union {
 		MPI	mpi[5];
-- 
cgit 


From 1573801fa89d022b9f5bd1b189d23221335f9f56 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:15:37 +0100
Subject: KEYS: Store public key algo ID in public_key_signature struct

Store public key algorithm ID in public_key_signature struct for reference
purposes.  This allows a public_key_signature struct to be embedded in
struct x509_certificate and other places more easily.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Josh Boyer <jwboyer@redhat.com>
---
 include/crypto/public_key.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 05778df0e3b4..b34fda4dcabf 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -90,6 +90,7 @@ struct public_key_signature {
 	u8 *digest;
 	u8 digest_size;			/* Number of bytes in digest */
 	u8 nr_mpi;			/* Occupancy of mpi[] */
+	enum pkey_algo pkey_algo : 8;
 	enum pkey_hash_algo pkey_hash_algo : 8;
 	union {
 		MPI mpi[2];
-- 
cgit 


From b56e5a17b6b9acd16997960504b9940d0d7984e7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:07:30 +0100
Subject: KEYS: Separate the kernel signature checking keyring from module
 signing

Separate the kernel signature checking keyring from module signing so that it
can be used by code other than the module-signing code.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/keys/system_keyring.h |  23 ++++++++++
 init/Kconfig                  |  13 ++++++
 kernel/Makefile               |  15 ++++--
 kernel/modsign_certificate.S  |  11 -----
 kernel/modsign_pubkey.c       | 104 ------------------------------------------
 kernel/module-internal.h      |   2 -
 kernel/module_signing.c       |   3 +-
 kernel/system_certificates.S  |  12 +++++
 kernel/system_keyring.c       | 103 +++++++++++++++++++++++++++++++++++++++++
 9 files changed, 163 insertions(+), 123 deletions(-)
 create mode 100644 include/keys/system_keyring.h
 delete mode 100644 kernel/modsign_certificate.S
 delete mode 100644 kernel/modsign_pubkey.c
 create mode 100644 kernel/system_certificates.S
 create mode 100644 kernel/system_keyring.c

(limited to 'include')

diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h
new file mode 100644
index 000000000000..8dabc399bd1d
--- /dev/null
+++ b/include/keys/system_keyring.h
@@ -0,0 +1,23 @@
+/* System keyring containing trusted public keys.
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _KEYS_SYSTEM_KEYRING_H
+#define _KEYS_SYSTEM_KEYRING_H
+
+#ifdef CONFIG_SYSTEM_TRUSTED_KEYRING
+
+#include <linux/key.h>
+
+extern struct key *system_trusted_keyring;
+
+#endif
+
+#endif /* _KEYS_SYSTEM_KEYRING_H */
diff --git a/init/Kconfig b/init/Kconfig
index 3ecd8a1178f1..0ff5407a8378 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1668,6 +1668,18 @@ config BASE_SMALL
 	default 0 if BASE_FULL
 	default 1 if !BASE_FULL
 
+config SYSTEM_TRUSTED_KEYRING
+	bool "Provide system-wide ring of trusted keys"
+	depends on KEYS
+	help
+	  Provide a system keyring to which trusted keys can be added.  Keys in
+	  the keyring are considered to be trusted.  Keys may be added at will
+	  by the kernel from compiled-in data and from hardware key stores, but
+	  userspace may only add extra keys if those keys can be verified by
+	  keys already in the keyring.
+
+	  Keys in this keyring are used by module signature checking.
+
 menuconfig MODULES
 	bool "Enable loadable module support"
 	option modules
@@ -1741,6 +1753,7 @@ config MODULE_SRCVERSION_ALL
 config MODULE_SIG
 	bool "Module signature verification"
 	depends on MODULES
+	select SYSTEM_TRUSTED_KEYRING
 	select KEYS
 	select CRYPTO
 	select ASYMMETRIC_KEY_TYPE
diff --git a/kernel/Makefile b/kernel/Makefile
index 2c24195249d5..63136989c132 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -54,8 +54,9 @@ obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
 obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
@@ -141,11 +142,11 @@ targets += timeconst.h
 $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
 	$(call if_changed,bc)
 
-ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
 #
 # Roll all the X.509 certificates that we can find together and pull them into
-# the kernel.
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
 #
 # We look in the source root and the build root for all files whose name ends
 # in ".x509".  Unfortunately, this will generate duplicate filenames, so we
@@ -153,6 +154,7 @@ ifeq ($(CONFIG_MODULE_SIG),y)
 # duplicates.
 #
 ###############################################################################
+ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
 X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
 X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
 X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
@@ -169,10 +171,11 @@ $(shell rm $(obj)/.x509.list)
 endif
 endif
 
-kernel/modsign_certificate.o: $(obj)/x509_certificate_list
+kernel/system_certificates.o: $(obj)/x509_certificate_list
 
 quiet_cmd_x509certs  = CERTS   $@
-      cmd_x509certs  = cat $(X509_CERTIFICATES) /dev/null >$@
+      cmd_x509certs  = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo "  - Including cert $(X509)")
+
 targets += $(obj)/x509_certificate_list
 $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
 	$(call if_changed,x509certs)
@@ -182,7 +185,9 @@ $(obj)/.x509.list:
 	@echo $(X509_CERTIFICATES) >$@
 
 clean-files := x509_certificate_list .x509.list
+endif
 
+ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
 #
 # If module signing is requested, say by allyesconfig, but a key has not been
diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S
deleted file mode 100644
index 6fe03c7ffe72..000000000000
--- a/kernel/modsign_certificate.S
+++ /dev/null
@@ -1,11 +0,0 @@
-#include <linux/export.h>
-
-#define GLOBAL(name)	\
-	.globl VMLINUX_SYMBOL(name);	\
-	VMLINUX_SYMBOL(name):
-
-	.section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
-	.incbin "kernel/x509_certificate_list"
-GLOBAL(modsign_certificate_list_end)
diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c
deleted file mode 100644
index 7cbd4507a7e6..000000000000
--- a/kernel/modsign_pubkey.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/* Public keys for module signature verification
- *
- * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cred.h>
-#include <linux/err.h>
-#include <keys/asymmetric-type.h>
-#include "module-internal.h"
-
-struct key *modsign_keyring;
-
-extern __initconst const u8 modsign_certificate_list[];
-extern __initconst const u8 modsign_certificate_list_end[];
-
-/*
- * We need to make sure ccache doesn't cache the .o file as it doesn't notice
- * if modsign.pub changes.
- */
-static __initconst const char annoy_ccache[] = __TIME__ "foo";
-
-/*
- * Load the compiled-in keys
- */
-static __init int module_verify_init(void)
-{
-	pr_notice("Initialise module verification\n");
-
-	modsign_keyring = keyring_alloc(".module_sign",
-					KUIDT_INIT(0), KGIDT_INIT(0),
-					current_cred(),
-					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
-					 KEY_USR_VIEW | KEY_USR_READ),
-					KEY_ALLOC_NOT_IN_QUOTA, NULL);
-	if (IS_ERR(modsign_keyring))
-		panic("Can't allocate module signing keyring\n");
-
-	return 0;
-}
-
-/*
- * Must be initialised before we try and load the keys into the keyring.
- */
-device_initcall(module_verify_init);
-
-/*
- * Load the compiled-in keys
- */
-static __init int load_module_signing_keys(void)
-{
-	key_ref_t key;
-	const u8 *p, *end;
-	size_t plen;
-
-	pr_notice("Loading module verification certificates\n");
-
-	end = modsign_certificate_list_end;
-	p = modsign_certificate_list;
-	while (p < end) {
-		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
-		 * than 256 bytes in size.
-		 */
-		if (end - p < 4)
-			goto dodgy_cert;
-		if (p[0] != 0x30 &&
-		    p[1] != 0x82)
-			goto dodgy_cert;
-		plen = (p[2] << 8) | p[3];
-		plen += 4;
-		if (plen > end - p)
-			goto dodgy_cert;
-
-		key = key_create_or_update(make_key_ref(modsign_keyring, 1),
-					   "asymmetric",
-					   NULL,
-					   p,
-					   plen,
-					   (KEY_POS_ALL & ~KEY_POS_SETATTR) |
-					   KEY_USR_VIEW,
-					   KEY_ALLOC_NOT_IN_QUOTA);
-		if (IS_ERR(key))
-			pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n",
-			       PTR_ERR(key));
-		else
-			pr_notice("MODSIGN: Loaded cert '%s'\n",
-				  key_ref_to_ptr(key)->description);
-		p += plen;
-	}
-
-	return 0;
-
-dodgy_cert:
-	pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n");
-	return 0;
-}
-late_initcall(load_module_signing_keys);
diff --git a/kernel/module-internal.h b/kernel/module-internal.h
index 24f9247b7d02..915e123a430f 100644
--- a/kernel/module-internal.h
+++ b/kernel/module-internal.h
@@ -9,6 +9,4 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-extern struct key *modsign_keyring;
-
 extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index ee476404167b..0b6b870dc5e4 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -14,6 +14,7 @@
 #include <crypto/public_key.h>
 #include <crypto/hash.h>
 #include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
 #include "module-internal.h"
 
 /*
@@ -157,7 +158,7 @@ static struct key *request_asymmetric_key(const char *signer, size_t signer_len,
 
 	pr_debug("Look up: \"%s\"\n", id);
 
-	key = keyring_search(make_key_ref(modsign_keyring, 1),
+	key = keyring_search(make_key_ref(system_trusted_keyring, 1),
 			     &key_type_asymmetric, id);
 	if (IS_ERR(key))
 		pr_warn("Request for unknown module key '%s' err %ld\n",
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
new file mode 100644
index 000000000000..552d47b2d463
--- /dev/null
+++ b/kernel/system_certificates.S
@@ -0,0 +1,12 @@
+#include <linux/export.h>
+#include <linux/init.h>
+
+#define GLOBAL(name)	\
+	.globl VMLINUX_SYMBOL(name);	\
+	VMLINUX_SYMBOL(name):
+
+	__INITRODATA
+
+GLOBAL(system_certificate_list)
+	.incbin "kernel/x509_certificate_list"
+GLOBAL(system_certificate_list_end)
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
new file mode 100644
index 000000000000..51c35141a13a
--- /dev/null
+++ b/kernel/system_keyring.c
@@ -0,0 +1,103 @@
+/* System trusted keyring for trusted public keys
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "module-internal.h"
+
+struct key *system_trusted_keyring;
+EXPORT_SYMBOL_GPL(system_trusted_keyring);
+
+extern __initconst const u8 system_certificate_list[];
+extern __initconst const u8 system_certificate_list_end[];
+
+/*
+ * Load the compiled-in keys
+ */
+static __init int system_trusted_keyring_init(void)
+{
+	pr_notice("Initialise system trusted keyring\n");
+
+	system_trusted_keyring =
+		keyring_alloc(".system_keyring",
+			      KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+			      ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			       KEY_USR_VIEW | KEY_USR_READ),
+			      KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(system_trusted_keyring))
+		panic("Can't allocate system trusted keyring\n");
+
+	return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(system_trusted_keyring_init);
+
+/*
+ * Load the compiled-in list of X.509 certificates.
+ */
+static __init int load_system_certificate_list(void)
+{
+	key_ref_t key;
+	const u8 *p, *end;
+	size_t plen;
+
+	pr_notice("Loading compiled-in X.509 certificates\n");
+
+	end = system_certificate_list_end;
+	p = system_certificate_list;
+	while (p < end) {
+		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+		 * than 256 bytes in size.
+		 */
+		if (end - p < 4)
+			goto dodgy_cert;
+		if (p[0] != 0x30 &&
+		    p[1] != 0x82)
+			goto dodgy_cert;
+		plen = (p[2] << 8) | p[3];
+		plen += 4;
+		if (plen > end - p)
+			goto dodgy_cert;
+
+		key = key_create_or_update(make_key_ref(system_trusted_keyring, 1),
+					   "asymmetric",
+					   NULL,
+					   p,
+					   plen,
+					   (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					   KEY_USR_VIEW,
+					   KEY_ALLOC_NOT_IN_QUOTA);
+		if (IS_ERR(key)) {
+			pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+			       PTR_ERR(key));
+		} else {
+			pr_notice("Loaded X.509 cert '%s'\n",
+				  key_ref_to_ptr(key)->description);
+			key_ref_put(key);
+		}
+		p += plen;
+	}
+
+	return 0;
+
+dodgy_cert:
+	pr_err("Problem parsing in-kernel X.509 certificate list\n");
+	return 0;
+}
+late_initcall(load_system_certificate_list);
-- 
cgit 


From 008643b86c5f33c115c84ccdda1725cac3ad50ad Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 30 Aug 2013 16:07:37 +0100
Subject: KEYS: Add a 'trusted' flag and a 'trusted only' flag

Add KEY_FLAG_TRUSTED to indicate that a key either comes from a trusted source
or had a cryptographic signature chain that led back to a trusted key the
kernel already possessed.

Add KEY_FLAGS_TRUSTED_ONLY to indicate that a keyring will only accept links to
keys marked with KEY_FLAGS_TRUSTED.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 include/linux/key-type.h | 1 +
 include/linux/key.h      | 3 +++
 kernel/system_keyring.c  | 4 +++-
 security/keys/key.c      | 8 ++++++++
 security/keys/keyring.c  | 4 ++++
 5 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index f58737bcb050..a74c3a84dfdd 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -45,6 +45,7 @@ struct key_preparsed_payload {
 	const void	*data;		/* Raw data */
 	size_t		datalen;	/* Raw datalen */
 	size_t		quotalen;	/* Quota length for proposed payload */
+	bool		trusted;	/* True if key is trusted */
 };
 
 typedef int (*request_key_actor_t)(struct key_construction *key,
diff --git a/include/linux/key.h b/include/linux/key.h
index 010dbb618aca..80d677483e31 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -168,6 +168,8 @@ struct key {
 #define KEY_FLAG_NEGATIVE	5	/* set if key is negative */
 #define KEY_FLAG_ROOT_CAN_CLEAR	6	/* set if key can be cleared by root without permission */
 #define KEY_FLAG_INVALIDATED	7	/* set if key has been invalidated */
+#define KEY_FLAG_TRUSTED	8	/* set if key is trusted */
+#define KEY_FLAG_TRUSTED_ONLY	9	/* set if keyring only accepts links to trusted keys */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
@@ -218,6 +220,7 @@ extern struct key *key_alloc(struct key_type *type,
 #define KEY_ALLOC_IN_QUOTA	0x0000	/* add to quota, reject if would overrun */
 #define KEY_ALLOC_QUOTA_OVERRUN	0x0001	/* add to quota, permit even if overrun */
 #define KEY_ALLOC_NOT_IN_QUOTA	0x0002	/* not in quota */
+#define KEY_ALLOC_TRUSTED	0x0004	/* Key should be flagged as trusted */
 
 extern void key_revoke(struct key *key);
 extern void key_invalidate(struct key *key);
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
index 51c35141a13a..5296721eca5b 100644
--- a/kernel/system_keyring.c
+++ b/kernel/system_keyring.c
@@ -40,6 +40,7 @@ static __init int system_trusted_keyring_init(void)
 	if (IS_ERR(system_trusted_keyring))
 		panic("Can't allocate system trusted keyring\n");
 
+	set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags);
 	return 0;
 }
 
@@ -82,7 +83,8 @@ static __init int load_system_certificate_list(void)
 					   plen,
 					   (KEY_POS_ALL & ~KEY_POS_SETATTR) |
 					   KEY_USR_VIEW,
-					   KEY_ALLOC_NOT_IN_QUOTA);
+					   KEY_ALLOC_NOT_IN_QUOTA |
+					   KEY_ALLOC_TRUSTED);
 		if (IS_ERR(key)) {
 			pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
 			       PTR_ERR(key));
diff --git a/security/keys/key.c b/security/keys/key.c
index a819b5c7d4ec..d331ea9ef380 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -300,6 +300,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
+	if (flags & KEY_ALLOC_TRUSTED)
+		key->flags |= 1 << KEY_FLAG_TRUSTED;
 
 	memset(&key->type_data, 0, sizeof(key->type_data));
 
@@ -813,6 +815,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	prep.data = payload;
 	prep.datalen = plen;
 	prep.quotalen = index_key.type->def_datalen;
+	prep.trusted = flags & KEY_ALLOC_TRUSTED;
 	if (index_key.type->preparse) {
 		ret = index_key.type->preparse(&prep);
 		if (ret < 0) {
@@ -827,6 +830,11 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 	index_key.desc_len = strlen(index_key.description);
 
+	key_ref = ERR_PTR(-EPERM);
+	if (!prep.trusted && test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags))
+		goto error_free_prep;
+	flags |= prep.trusted ? KEY_ALLOC_TRUSTED : 0;
+
 	ret = __key_link_begin(keyring, &index_key, &edit);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index f7cdea22214f..9b6f6e09b50c 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1183,6 +1183,10 @@ int key_link(struct key *keyring, struct key *key)
 	key_check(keyring);
 	key_check(key);
 
+	if (test_bit(KEY_FLAG_TRUSTED_ONLY, &keyring->flags) &&
+	    !test_bit(KEY_FLAG_TRUSTED, &key->flags))
+		return -EPERM;
+
 	ret = __key_link_begin(keyring, &key->index_key, &edit);
 	if (ret == 0) {
 		kdebug("begun {%d,%d}", keyring->serial, atomic_read(&keyring->usage));
-- 
cgit 


From 416a4ae56b7a37407ca1155805c05b638f845778 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 25 Sep 2013 13:26:08 +0300
Subject: Bluetooth: Use async request for LE enable/disable

This patch updates the code to use an asynchronous request for handling
the enabling and disabling of LE support. This refactoring is necessary
as a preparation for adding advertising support, since when LE is
disabled we should also disable advertising, and the cleanest way to do
this is to perform the two respective HCI commands in the same
asynchronous request.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_event.c        | 11 +++----
 net/bluetooth/mgmt.c             | 67 ++++++++++++++++------------------------
 3 files changed, 32 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3ede820d328f..26cc9f7858cd 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1168,7 +1168,6 @@ int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
 int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 					    u8 *randomizer, u8 status);
-int mgmt_le_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
 		      u8 ssp, u8 *eir, u16 eir_len);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 94aab73f89d4..48db81f8a337 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -994,20 +994,19 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 		return;
 
 	if (!status) {
-		if (sent->le)
+		if (sent->le) {
 			hdev->features[1][0] |= LMP_HOST_LE;
-		else
+			set_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+		} else {
 			hdev->features[1][0] &= ~LMP_HOST_LE;
+			clear_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+		}
 
 		if (sent->simul)
 			hdev->features[1][0] |= LMP_HOST_LE_BREDR;
 		else
 			hdev->features[1][0] &= ~LMP_HOST_LE_BREDR;
 	}
-
-	if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
-	    !test_bit(HCI_INIT, &hdev->flags))
-		mgmt_le_enable_complete(hdev, sent->le, status);
 }
 
 static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 61d4b190eebf..4c3984ee1114 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1354,11 +1354,32 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	return send_settings_rsp(sk, MGMT_OP_SET_HS, hdev);
 }
 
+static void le_enable_complete(struct hci_dev *hdev, u8 status)
+{
+	struct cmd_lookup match = { NULL, hdev };
+
+	if (status) {
+		u8 mgmt_err = mgmt_status(status);
+
+		mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
+				     &mgmt_err);
+		return;
+	}
+
+	mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
+
+	new_settings(hdev, match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+}
+
 static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
 	struct hci_cp_write_le_host_supported hci_cp;
 	struct pending_cmd *cmd;
+	struct hci_request req;
 	int err;
 	u8 val, enabled;
 
@@ -1419,8 +1440,12 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		hci_cp.simul = lmp_le_br_capable(hdev);
 	}
 
-	err = hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
-			   &hci_cp);
+	hci_req_init(&req, hdev);
+
+	hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
+		    &hci_cp);
+
+	err = hci_req_run(&req, le_enable_complete);
 	if (err < 0)
 		mgmt_pending_remove(cmd);
 
@@ -4141,44 +4166,6 @@ int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 	return err;
 }
 
-int mgmt_le_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
-{
-	struct cmd_lookup match = { NULL, hdev };
-	bool changed = false;
-	int err = 0;
-
-	if (status) {
-		u8 mgmt_err = mgmt_status(status);
-
-		if (enable && test_and_clear_bit(HCI_LE_ENABLED,
-						 &hdev->dev_flags))
-			err = new_settings(hdev, NULL);
-
-		mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
-				     &mgmt_err);
-
-		return err;
-	}
-
-	if (enable) {
-		if (!test_and_set_bit(HCI_LE_ENABLED, &hdev->dev_flags))
-			changed = true;
-	} else {
-		if (test_and_clear_bit(HCI_LE_ENABLED, &hdev->dev_flags))
-			changed = true;
-	}
-
-	mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
-
-	if (changed)
-		err = new_settings(hdev, match.sk);
-
-	if (match.sk)
-		sock_put(match.sk);
-
-	return err;
-}
-
 int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
 		      ssp, u8 *eir, u16 eir_len)
-- 
cgit 


From eeca6f891305a80378da978f803821c2a0b648b6 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 25 Sep 2013 13:26:09 +0300
Subject: Bluetooth: Add new mgmt setting for LE advertising

This patch adds a new mgmt setting for LE advertising and hooks up the
necessary places in the mgmt code to operate on the HCI_LE_PERIPHERAL
flag (which corresponds to this setting). This patch does not yet add
any new command for enabling the setting - that is left for a subsequent
patch.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/mgmt.h |  1 +
 net/bluetooth/hci_event.c    |  1 +
 net/bluetooth/mgmt.c         | 21 ++++++++++++++++++++-
 3 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 9944c3e68c5d..6cc72b69e014 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -93,6 +93,7 @@ struct mgmt_rp_read_index_list {
 #define MGMT_SETTING_BREDR		0x00000080
 #define MGMT_SETTING_HS			0x00000100
 #define MGMT_SETTING_LE			0x00000200
+#define MGMT_SETTING_ADVERTISING	0x00000400
 
 #define MGMT_OP_READ_INFO		0x0004
 #define MGMT_READ_INFO_SIZE		0
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 48db81f8a337..917c7c833f69 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1000,6 +1000,7 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 		} else {
 			hdev->features[1][0] &= ~LMP_HOST_LE;
 			clear_bit(HCI_LE_ENABLED, &hdev->dev_flags);
+			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
 		}
 
 		if (sent->simul)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 4c3984ee1114..9a2faa310b7c 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -384,8 +384,10 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 	if (enable_hs)
 		settings |= MGMT_SETTING_HS;
 
-	if (lmp_le_capable(hdev))
+	if (lmp_le_capable(hdev)) {
 		settings |= MGMT_SETTING_LE;
+		settings |= MGMT_SETTING_ADVERTISING;
+	}
 
 	return settings;
 }
@@ -424,6 +426,9 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (test_bit(HCI_HS_ENABLED, &hdev->dev_flags))
 		settings |= MGMT_SETTING_HS;
 
+	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
+		settings |= MGMT_SETTING_ADVERTISING;
+
 	return settings;
 }
 
@@ -1411,6 +1416,11 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 			changed = true;
 		}
 
+		if (!val && test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+			changed = true;
+		}
+
 		err = send_settings_rsp(sk, MGMT_OP_SET_LE, hdev);
 		if (err < 0)
 			goto unlock;
@@ -1442,6 +1452,9 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	hci_req_init(&req, hdev);
 
+	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags) && !val)
+		hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(val), &val);
+
 	hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
 		    &hci_cp);
 
@@ -3517,6 +3530,12 @@ static int powered_update_hci(struct hci_dev *hdev)
 				    sizeof(cp), &cp);
 	}
 
+	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+		u8 adv = 0x01;
+
+		hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(adv), &adv);
+	}
+
 	link_sec = test_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
 	if (link_sec != test_bit(HCI_AUTH, &hdev->flags))
 		hci_req_add(&req, HCI_OP_WRITE_AUTH_ENABLE,
-- 
cgit 


From 4375f1037d52602413142e290608d0d84671ad36 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 25 Sep 2013 13:26:10 +0300
Subject: Bluetooth: Add new mgmt_set_advertising command

This patch adds a new mgmt command for enabling and disabling
LE advertising. The command depends on the LE setting being enabled
first and will return a "rejected" response otherwise. The patch also
adds safeguards so that there will ever only be one set_le or
set_advertising command pending per adapter.

The response handling and new_settings event sending is done in an
asynchronous request callback, meaning raw HCI access from user space to
enable advertising (e.g. hciconfig leadv) will not trigger the
new_settings event. This is intentional since trying to support mixed
raw HCI and mgmt access would mean adding extra state tracking or new
helper functions, essentially negating the benefit of using the
asynchronous request framework. The HCI_LE_ENABLED and HCI_LE_PERIPHERAL
flags however are updated correctly even with raw HCI access so this
will not completely break subsequent access over mgmt.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/mgmt.h |  2 +
 net/bluetooth/mgmt.c         | 97 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 98 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 6cc72b69e014..421d7633a91f 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -352,6 +352,8 @@ struct mgmt_cp_set_device_id {
 } __packed;
 #define MGMT_SET_DEVICE_ID_SIZE		8
 
+#define MGMT_OP_SET_ADVERTISING		0x0029
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9a2faa310b7c..1b5b10fab545 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -76,6 +76,7 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_BLOCK_DEVICE,
 	MGMT_OP_UNBLOCK_DEVICE,
 	MGMT_OP_SET_DEVICE_ID,
+	MGMT_OP_SET_ADVERTISING,
 };
 
 static const u16 mgmt_events[] = {
@@ -1431,7 +1432,8 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto unlock;
 	}
 
-	if (mgmt_pending_find(MGMT_OP_SET_LE, hdev)) {
+	if (mgmt_pending_find(MGMT_OP_SET_LE, hdev) ||
+	    mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev)) {
 		err = cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
 				 MGMT_STATUS_BUSY);
 		goto unlock;
@@ -3136,6 +3138,98 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
 	return err;
 }
 
+static void set_advertising_complete(struct hci_dev *hdev, u8 status)
+{
+	struct cmd_lookup match = { NULL, hdev };
+
+	if (status) {
+		u8 mgmt_err = mgmt_status(status);
+
+		mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev,
+				     cmd_status_rsp, &mgmt_err);
+		return;
+	}
+
+	mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp,
+			     &match);
+
+	new_settings(hdev, match.sk);
+
+	if (match.sk)
+		sock_put(match.sk);
+}
+
+static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
+{
+	struct mgmt_mode *cp = data;
+	struct pending_cmd *cmd;
+	struct hci_request req;
+	u8 val, enabled;
+	int err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				  MGMT_STATUS_REJECTED);
+
+	if (cp->val != 0x00 && cp->val != 0x01)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	val = !!cp->val;
+	enabled = test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+
+	if (!hdev_is_powered(hdev) || val == enabled) {
+		bool changed = false;
+
+		if (val != test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+			change_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+			changed = true;
+		}
+
+		err = send_settings_rsp(sk, MGMT_OP_SET_ADVERTISING, hdev);
+		if (err < 0)
+			goto unlock;
+
+		if (changed)
+			err = new_settings(hdev, sk);
+
+		goto unlock;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_ADVERTISING, hdev) ||
+	    mgmt_pending_find(MGMT_OP_SET_LE, hdev)) {
+		err = cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
+				 MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_ADVERTISING, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	hci_req_init(&req, hdev);
+
+	hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(val), &val);
+
+	err = hci_req_run(&req, set_advertising_complete);
+	if (err < 0)
+		mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
 static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -3347,6 +3441,7 @@ static const struct mgmt_handler {
 	{ block_device,           false, MGMT_BLOCK_DEVICE_SIZE },
 	{ unblock_device,         false, MGMT_UNBLOCK_DEVICE_SIZE },
 	{ set_device_id,          false, MGMT_SET_DEVICE_ID_SIZE },
+	{ set_advertising,        false, MGMT_SETTING_SIZE },
 };
 
 
-- 
cgit 


From a895c28a1f5d761679cb229b19fb08ca2067211e Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 3 Sep 2013 13:31:05 -0700
Subject: PCI: Fix comment typo, remove unnecessary !! in pci_is_pcie()

Use normal kernel-doc "Returns:" instead of "retrun"
Assignment to bool is always 1 or 0 so the !! isn't necessary.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index da172f956ad6..ee0f3b60af22 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1749,11 +1749,11 @@ static inline int pci_pcie_cap(struct pci_dev *dev)
  * pci_is_pcie - check if the PCI device is PCI Express capable
  * @dev: PCI device
  *
- * Retrun true if the PCI device is PCI Express capable, false otherwise.
+ * Returns: true if the PCI device is PCI Express capable, false otherwise.
  */
 static inline bool pci_is_pcie(struct pci_dev *dev)
 {
-	return !!pci_pcie_cap(dev);
+	return pci_pcie_cap(dev);
 }
 
 /**
-- 
cgit 


From 115e3bc5e23e7ec3c85a2014bfa96c0ddd036083 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Tue, 3 Sep 2013 10:02:09 +0800
Subject: PCI: Remove unused "is_pcie" from pci_dev structure

No one uses "is_pcie" now; remove this obsolete member.

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 1 -
 include/linux/pci.h | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 7ef0f868b3e0..2372babe2fc5 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -984,7 +984,6 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
 	if (!pos)
 		return;
-	pdev->is_pcie = 1;
 	pdev->pcie_cap = pos;
 	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
 	pdev->pcie_flags_reg = reg16;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee0f3b60af22..197e2d21f2cb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -330,8 +330,6 @@ struct pci_dev {
 	unsigned int	msix_enabled:1;
 	unsigned int	ari_enabled:1;	/* ARI forwarding */
 	unsigned int	is_managed:1;
-	unsigned int	is_pcie:1;	/* Obsolete. Will be removed.
-					   Use pci_is_pcie() instead */
 	unsigned int    needs_freset:1; /* Dev requires fundamental reset */
 	unsigned int	state_saved:1;
 	unsigned int	is_physfn:1;
-- 
cgit 


From 77a0dfcd8a4d9a93a21c8be56eaeb65cd69b351d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 24 Sep 2013 15:14:57 -0600
Subject: PCI: Document reason for using pci_is_root_bus()

Some code assumes "bus->self == NULL" means the bus is a root bus.  This
adds a comment explaining why this is incorrect ("virtual" buses added for
SR-IOV have "bus->self == NULL" but are not root buses).

No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 197e2d21f2cb..d3a888ae4b2e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -470,6 +470,10 @@ struct pci_bus {
 /*
  * Returns true if the pci bus is root (behind host-pci bridge),
  * false otherwise
+ *
+ * Some code assumes that "bus->self == NULL" means that bus is a root bus.
+ * This is incorrect because "virtual" buses added for SR-IOV (via
+ * virtfn_add_bus()) have "bus->self == NULL" but are not root buses.
  */
 static inline bool pci_is_root_bus(struct pci_bus *pbus)
 {
-- 
cgit 


From 7868943db1668fba898cf71bed1506c19d6958aa Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Mon, 16 Sep 2013 23:47:28 +0800
Subject: usb: core: implement AMD remote wakeup quirk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The following patch is required to resolve remote wake issues with
certain devices.

Issue description:
If the remote wake is issued from the device in a specific timing
condition while the system is entering sleep state then it may cause
system to auto wake on subsequent sleep cycle.

Root cause:
Host controller rebroadcasts the Resume signal > 100 µseconds after
receiving the original resume event from the device. For proper
function, some devices may require the rebroadcast of resume event
within the USB spec of 100µS.

Workaroud:
1. Filter the AMD platforms with Yangtze chipset, then judge of all the usb
devices are mouse or not. And get out the port id which attached a mouse
with Pixart controller.
2. Then reset the port which attached issue device during system resume
from S3.

[Q] Why the special devices are only mice? Would high speed devices
such as 3G modem or USB Bluetooth adapter trigger this issue?
- Current this sensitivity is only confined to devices that use Pixart
  controllers. This controller is designed for use with LS mouse
devices only. We have not observed any other devices failing. There
may be a small risk for other devices also but this patch (reset
device in resume phase) will cover the cases if required.

[Q] Shouldn’t the resume signal be sent within 100 us for every
device?
- The Host controller may not send the resume signal within 100us,
  this our host controller specification change. This is why we
require the patch to prevent side effects on certain known devices.

[Q] Why would clicking mouse INTENSELY to wake the system up trigger
this issue?
- This behavior is specific to the devices that use Pixart controller.
  It is timing dependent on when the resume event is triggered during
the sleep state.

[Q] Is it a host controller issue or mouse?
- It is the host controller behavior during resume that triggers the
  device incorrect behavior on the next resume.

This patch sets USB_QUIRK_RESET_RESUME flag for these Pixart-based mice
when they attached to platforms with AMD Yangtze chipset.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd-pci.c    |  3 +++
 drivers/usb/core/quirks.c     | 37 +++++++++++++++++++++++++++++++++++++
 drivers/usb/host/pci-quirks.c | 12 ++++++++++++
 include/linux/usb/hcd.h       |  3 +++
 4 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index b9d3c43e3859..dfe9d0f22978 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -215,6 +215,9 @@ int usb_hcd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto disable_pci;
 	}
 
+	hcd->amd_resume_bug = (usb_hcd_amd_remote_wakeup_quirk(dev) &&
+			driver->flags & (HCD_USB11 | HCD_USB3)) ? 1 : 0;
+
 	if (driver->flags & HCD_MEMORY) {
 		/* EHCI, OHCI */
 		hcd->rsrc_start = pci_resource_start(dev, 0);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 5b44cd47da5b..74d18c8b7a88 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -13,6 +13,7 @@
 
 #include <linux/usb.h>
 #include <linux/usb/quirks.h>
+#include <linux/usb/hcd.h>
 #include "usb.h"
 
 /* Lists of quirky USB devices, split in device quirks and interface quirks.
@@ -155,6 +156,21 @@ static const struct usb_device_id usb_interface_quirk_list[] = {
 	{ }  /* terminating entry must be last */
 };
 
+static const struct usb_device_id usb_amd_resume_quirk_list[] = {
+	/* Lenovo Mouse with Pixart controller */
+	{ USB_DEVICE(0x17ef, 0x602e), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Pixart Mouse */
+	{ USB_DEVICE(0x093a, 0x2500), .driver_info = USB_QUIRK_RESET_RESUME },
+	{ USB_DEVICE(0x093a, 0x2510), .driver_info = USB_QUIRK_RESET_RESUME },
+	{ USB_DEVICE(0x093a, 0x2521), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Optical Mouse M90/M100 */
+	{ USB_DEVICE(0x046d, 0xc05a), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	{ }  /* terminating entry must be last */
+};
+
 static bool usb_match_any_interface(struct usb_device *udev,
 				    const struct usb_device_id *id)
 {
@@ -181,6 +197,18 @@ static bool usb_match_any_interface(struct usb_device *udev,
 	return false;
 }
 
+int usb_amd_resume_quirk(struct usb_device *udev)
+{
+	struct usb_hcd *hcd;
+
+	hcd = bus_to_hcd(udev->bus);
+	/* The device should be attached directly to root hub */
+	if (udev->level == 1 && hcd->amd_resume_bug == 1)
+		return 1;
+
+	return 0;
+}
+
 static u32 __usb_detect_quirks(struct usb_device *udev,
 			       const struct usb_device_id *id)
 {
@@ -206,6 +234,15 @@ static u32 __usb_detect_quirks(struct usb_device *udev,
 void usb_detect_quirks(struct usb_device *udev)
 {
 	udev->quirks = __usb_detect_quirks(udev, usb_quirk_list);
+
+	/*
+	 * Pixart-based mice would trigger remote wakeup issue on AMD
+	 * Yangtze chipset, so set them as RESET_RESUME flag.
+	 */
+	if (usb_amd_resume_quirk(udev))
+		udev->quirks |= __usb_detect_quirks(udev,
+				usb_amd_resume_quirk_list);
+
 	if (udev->quirks)
 		dev_dbg(&udev->dev, "USB quirks for this device: %x\n",
 			udev->quirks);
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index d1e68d887f6e..17eb1916e65e 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -250,6 +250,18 @@ commit:
 }
 EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info);
 
+int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev)
+{
+	/* Make sure amd chipset type has already been initialized */
+	usb_amd_find_chipset_info();
+	if (amd_chipset.sb_type.gen != AMD_CHIPSET_YANGTZE)
+		return 0;
+
+	dev_dbg(&pdev->dev, "QUIRK: Enable AMD remote wakeup fix\n");
+	return 1;
+}
+EXPORT_SYMBOL_GPL(usb_hcd_amd_remote_wakeup_quirk);
+
 /*
  * The hardware normally enables the A-link power management feature, which
  * lets the system lower the power consumption in idle states.
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 8c865134c881..fc64b6825f5e 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -141,6 +141,7 @@ struct usb_hcd {
 	unsigned		wireless:1;	/* Wireless USB HCD */
 	unsigned		authorized_default:1;
 	unsigned		has_tt:1;	/* Integrated TT in root hub */
+	unsigned		amd_resume_bug:1; /* AMD remote wakeup quirk */
 
 	unsigned int		irq;		/* irq allocated */
 	void __iomem		*regs;		/* device memory/io */
@@ -435,6 +436,8 @@ extern int usb_hcd_pci_probe(struct pci_dev *dev,
 extern void usb_hcd_pci_remove(struct pci_dev *dev);
 extern void usb_hcd_pci_shutdown(struct pci_dev *dev);
 
+extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev);
+
 #ifdef CONFIG_PM
 extern const struct dev_pm_ops usb_hcd_pci_pm_ops;
 #endif
-- 
cgit 


From 469d6d0631386e6865a30c9ded87a5cc0fdf8e2e Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Wed, 18 Sep 2013 20:47:06 -0400
Subject: tty: Remove unused drop() method from tty_port interface

Although originally conceived as a hook for port drivers to know
when a port reference is dropped, no driver uses this method.

Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_port.c | 6 +-----
 include/linux/tty.h    | 1 -
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 7efbca474689..c94d2349dd06 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -484,8 +484,6 @@ int tty_port_close_start(struct tty_port *port,
 
 	if (port->count) {
 		spin_unlock_irqrestore(&port->lock, flags);
-		if (port->ops->drop)
-			port->ops->drop(port);
 		return 0;
 	}
 	set_bit(ASYNCB_CLOSING, &port->flags);
@@ -504,9 +502,7 @@ int tty_port_close_start(struct tty_port *port,
 	/* Flush the ldisc buffering */
 	tty_ldisc_flush(tty);
 
-	/* Don't call port->drop for the last reference. Callers will want
-	   to drop the last active reference in ->shutdown() or the tty
-	   shutdown path */
+	/* Report to caller this is the last port reference */
 	return 1;
 }
 EXPORT_SYMBOL(tty_port_close_start);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 64f864651d86..2f47989d8288 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -180,7 +180,6 @@ struct tty_port_operations {
 	   IFF the port was initialized. Do not use to free resources. Called
 	   under the port mutex to serialize against activate/shutdowns */
 	void (*shutdown)(struct tty_port *port);
-	void (*drop)(struct tty_port *port);
 	/* Called under the port mutex from tty_port_open, serialized using
 	   the port mutex */
         /* FIXME: long term getting the tty argument *out* of this would be
-- 
cgit 


From b83e867026caedd6d67fccfbe6e9a621edd79b21 Mon Sep 17 00:00:00 2001
From: Grant Grundler <grundler@chromium.org>
Date: Thu, 19 Sep 2013 18:21:36 -0700
Subject: mmc: core: remove dead function mmc_try_claim_host

cscope says there are no callers for mmc_try_claim_host in the kernel.
No reason to keep it.

Signed-off-by: Grant Grundler <grundler@chromium.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/core.c  | 25 -------------------------
 include/linux/mmc/core.h |  1 -
 2 files changed, 26 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index bf18b6bfce48..006ead2fb701 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -917,31 +917,6 @@ int __mmc_claim_host(struct mmc_host *host, atomic_t *abort)
 
 EXPORT_SYMBOL(__mmc_claim_host);
 
-/**
- *	mmc_try_claim_host - try exclusively to claim a host
- *	@host: mmc host to claim
- *
- *	Returns %1 if the host is claimed, %0 otherwise.
- */
-int mmc_try_claim_host(struct mmc_host *host)
-{
-	int claimed_host = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->lock, flags);
-	if (!host->claimed || host->claimer == current) {
-		host->claimed = 1;
-		host->claimer = current;
-		host->claim_cnt += 1;
-		claimed_host = 1;
-	}
-	spin_unlock_irqrestore(&host->lock, flags);
-	if (host->ops->enable && claimed_host && host->claim_cnt == 1)
-		host->ops->enable(host);
-	return claimed_host;
-}
-EXPORT_SYMBOL(mmc_try_claim_host);
-
 /**
  *	mmc_release_host - release a host
  *	@host: mmc host to release
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index da51bec578c3..a00fc49c8434 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -188,7 +188,6 @@ extern unsigned int mmc_align_data_size(struct mmc_card *, unsigned int);
 
 extern int __mmc_claim_host(struct mmc_host *host, atomic_t *abort);
 extern void mmc_release_host(struct mmc_host *host);
-extern int mmc_try_claim_host(struct mmc_host *host);
 
 extern void mmc_get_card(struct mmc_card *card);
 extern void mmc_put_card(struct mmc_card *card);
-- 
cgit 


From 524268990e54dab9bd71a984b70c13ce0eb1c525 Mon Sep 17 00:00:00 2001
From: Seungwon Jeon <tgih.jun@samsung.com>
Date: Sat, 31 Aug 2013 00:13:42 +0900
Subject: mmc: dw_mmc: adjust the fifoth with block size

This change helps to choose msize, rx_watermark and tx_watermark
depending on block size for IDMAC mode.  For SDIO block size can be
variable, so if these values are set incorrectly, card clock may stop.

Signed-off-by: Seungwon Jeon <tgih.jun@samsung.com>
Tested-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/host/dw_mmc.c  | 74 ++++++++++++++++++++++++++++++++++++++++++++--
 drivers/mmc/host/dw_mmc.h  |  4 +++
 include/linux/mmc/dw_mmc.h |  1 +
 3 files changed, 76 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 50da6e330a15..acefdeb2465b 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -529,6 +529,47 @@ static void dw_mci_post_req(struct mmc_host *mmc,
 	data->host_cookie = 0;
 }
 
+static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
+{
+#ifdef CONFIG_MMC_DW_IDMAC
+	unsigned int blksz = data->blksz;
+	const u32 mszs[] = {1, 4, 8, 16, 32, 64, 128, 256};
+	u32 fifo_width = 1 << host->data_shift;
+	u32 blksz_depth = blksz / fifo_width, fifoth_val;
+	u32 msize = 0, rx_wmark = 1, tx_wmark, tx_wmark_invers;
+	int idx = (sizeof(mszs) / sizeof(mszs[0])) - 1;
+
+	tx_wmark = (host->fifo_depth) / 2;
+	tx_wmark_invers = host->fifo_depth - tx_wmark;
+
+	/*
+	 * MSIZE is '1',
+	 * if blksz is not a multiple of the FIFO width
+	 */
+	if (blksz % fifo_width) {
+		msize = 0;
+		rx_wmark = 1;
+		goto done;
+	}
+
+	do {
+		if (!((blksz_depth % mszs[idx]) ||
+		     (tx_wmark_invers % mszs[idx]))) {
+			msize = idx;
+			rx_wmark = mszs[idx] - 1;
+			break;
+		}
+	} while (--idx > 0);
+	/*
+	 * If idx is '0', it won't be tried
+	 * Thus, initial values are uesed
+	 */
+done:
+	fifoth_val = SDMMC_SET_FIFOTH(msize, rx_wmark, tx_wmark);
+	mci_writel(host, FIFOTH, fifoth_val);
+#endif
+}
+
 static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 {
 	int sg_len;
@@ -553,6 +594,14 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 		 (unsigned long)host->sg_cpu, (unsigned long)host->sg_dma,
 		 sg_len);
 
+	/*
+	 * Decide the MSIZE and RX/TX Watermark.
+	 * If current block size is same with previous size,
+	 * no need to update fifoth.
+	 */
+	if (host->prev_blksz != data->blksz)
+		dw_mci_adjust_fifoth(host, data);
+
 	/* Enable the DMA interface */
 	temp = mci_readl(host, CTRL);
 	temp |= SDMMC_CTRL_DMA_ENABLE;
@@ -603,6 +652,21 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 		temp = mci_readl(host, CTRL);
 		temp &= ~SDMMC_CTRL_DMA_ENABLE;
 		mci_writel(host, CTRL, temp);
+
+		/*
+		 * Use the initial fifoth_val for PIO mode.
+		 * If next issued data may be transfered by DMA mode,
+		 * prev_blksz should be invalidated.
+		 */
+		mci_writel(host, FIFOTH, host->fifoth_val);
+		host->prev_blksz = 0;
+	} else {
+		/*
+		 * Keep the current block size.
+		 * It will be used to decide whether to update
+		 * fifoth register next time.
+		 */
+		host->prev_blksz = data->blksz;
 	}
 }
 
@@ -2368,8 +2432,8 @@ int dw_mci_probe(struct dw_mci *host)
 		fifo_size = host->pdata->fifo_depth;
 	}
 	host->fifo_depth = fifo_size;
-	host->fifoth_val = ((0x2 << 28) | ((fifo_size/2 - 1) << 16) |
-			((fifo_size/2) << 0));
+	host->fifoth_val =
+		SDMMC_SET_FIFOTH(0x2, fifo_size / 2 - 1, fifo_size / 2);
 	mci_writel(host, FIFOTH, host->fifoth_val);
 
 	/* disable clock to CIU */
@@ -2552,8 +2616,12 @@ int dw_mci_resume(struct dw_mci *host)
 	if (host->use_dma && host->dma_ops->init)
 		host->dma_ops->init(host);
 
-	/* Restore the old value at FIFOTH register */
+	/*
+	 * Restore the initial value at FIFOTH register
+	 * And Invalidate the prev_blksz with zero
+	 */
 	mci_writel(host, FIFOTH, host->fifoth_val);
+	host->prev_blksz = 0;
 
 	/* Put in max timeout */
 	mci_writel(host, TMOUT, 0xFFFFFFFF);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index b281fdc6835f..a0f2f8d35f5d 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -128,6 +128,10 @@
 #define SDMMC_CMD_INDX(n)		((n) & 0x1F)
 /* Status register defines */
 #define SDMMC_GET_FCNT(x)		(((x)>>17) & 0x1FFF)
+/* FIFOTH register defines */
+#define SDMMC_SET_FIFOTH(m, r, t)	(((m) & 0x7) << 28 | \
+					 ((r) & 0xFFF) << 16 | \
+					 ((t) & 0xFFF))
 /* Internal DMAC interrupt defines */
 #define SDMMC_IDMAC_INT_AI		BIT(9)
 #define SDMMC_IDMAC_INT_NI		BIT(8)
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 198f0fa44e9f..4ec9dcc9460e 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -129,6 +129,7 @@ struct dw_mci {
 	struct mmc_request	*mrq;
 	struct mmc_command	*cmd;
 	struct mmc_data		*data;
+	unsigned int		prev_blksz;
 	struct workqueue_struct	*card_workqueue;
 
 	/* DMA interface members*/
-- 
cgit 


From f1d2736c815629f3b43d8eebf73a81b581438e65 Mon Sep 17 00:00:00 2001
From: Seungwon Jeon <tgih.jun@samsung.com>
Date: Sat, 31 Aug 2013 00:13:55 +0900
Subject: mmc: dw_mmc: control card read threshold

Card Read Threshold should be ensured that the card clock does not stop
in the middle of a block of data being transferred from the card to the
Host. Specially, clock stop is allowed in fast transfer such as HS200
or SDR104 mode. And so, it should be enabled.

Signed-off-by: Seungwon Jeon <tgih.jun@samsung.com>
Tested-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/host/dw_mmc.c  | 38 ++++++++++++++++++++++++++++++++++++--
 drivers/mmc/host/dw_mmc.h  |  3 +++
 include/linux/mmc/dw_mmc.h |  1 +
 3 files changed, 40 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index acefdeb2465b..8eb37983a72a 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -570,6 +570,37 @@ done:
 #endif
 }
 
+static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
+{
+	unsigned int blksz = data->blksz;
+	u32 blksz_depth, fifo_depth;
+	u16 thld_size;
+
+	WARN_ON(!(data->flags & MMC_DATA_READ));
+
+	if (host->timing != MMC_TIMING_MMC_HS200 &&
+	    host->timing != MMC_TIMING_UHS_SDR104)
+		goto disable;
+
+	blksz_depth = blksz / (1 << host->data_shift);
+	fifo_depth = host->fifo_depth;
+
+	if (blksz_depth > fifo_depth)
+		goto disable;
+
+	/*
+	 * If (blksz_depth) >= (fifo_depth >> 1), should be 'thld_size <= blksz'
+	 * If (blksz_depth) <  (fifo_depth >> 1), should be thld_size = blksz
+	 * Currently just choose blksz.
+	 */
+	thld_size = blksz;
+	mci_writel(host, CDTHRCTL, SDMMC_SET_RD_THLD(thld_size, 1));
+	return;
+
+disable:
+	mci_writel(host, CDTHRCTL, SDMMC_SET_RD_THLD(0, 0));
+}
+
 static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 {
 	int sg_len;
@@ -627,10 +658,12 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 	host->sg = NULL;
 	host->data = data;
 
-	if (data->flags & MMC_DATA_READ)
+	if (data->flags & MMC_DATA_READ) {
 		host->dir_status = DW_MCI_RECV_STATUS;
-	else
+		dw_mci_ctrl_rd_thld(host, data);
+	} else {
 		host->dir_status = DW_MCI_SEND_STATUS;
+	}
 
 	if (dw_mci_submit_data_dma(host, data)) {
 		int flags = SG_MITER_ATOMIC;
@@ -877,6 +910,7 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		regs &= ~((0x1 << slot->id) << 16);
 
 	mci_writel(slot->host, UHS_REG, regs);
+	slot->host->timing = ios->timing;
 
 	/*
 	 * Use mirror of ios->clock to prevent race with mmc
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index a0f2f8d35f5d..6bf24ab917e6 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -53,6 +53,7 @@
 #define SDMMC_IDINTEN		0x090
 #define SDMMC_DSCADDR		0x094
 #define SDMMC_BUFADDR		0x098
+#define SDMMC_CDTHRCTL		0x100
 #define SDMMC_DATA(x)		(x)
 
 /*
@@ -146,6 +147,8 @@
 #define SDMMC_IDMAC_SWRESET		BIT(0)
 /* Version ID register define */
 #define SDMMC_GET_VERID(x)		((x) & 0xFFFF)
+/* Card read threshold */
+#define SDMMC_SET_RD_THLD(v, x)		(((v) & 0x1FFF) << 16 | (x))
 
 /* Register access macros */
 #define mci_readl(dev, reg)			\
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 4ec9dcc9460e..a829f7ee28c8 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -130,6 +130,7 @@ struct dw_mci {
 	struct mmc_command	*cmd;
 	struct mmc_data		*data;
 	unsigned int		prev_blksz;
+	unsigned char		timing;
 	struct workqueue_struct	*card_workqueue;
 
 	/* DMA interface members*/
-- 
cgit 


From 90c2143a8f6d0cd1dbae1ea32fcd1befb81e4b0d Mon Sep 17 00:00:00 2001
From: Seungwon Jeon <tgih.jun@samsung.com>
Date: Sat, 31 Aug 2013 00:14:05 +0900
Subject: mmc: dw_mmc: guarantee stop-abort cmd in data errors

In error cases, DTO interrupt may or may not be generated depending
on remained data. Stop/Abort command ensures DTO generation for that
situation. Currently if 'stop' field of data is empty, there is no
stop/abort command. So, it could hang waiting DTO. This change
reinforces these cases.

Signed-off-by: Seungwon Jeon <tgih.jun@samsung.com>
Tested-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/host/dw_mmc.c  | 84 +++++++++++++++++++++++++++++++++++-----------
 include/linux/mmc/dw_mmc.h |  2 ++
 2 files changed, 66 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 649127e71894..b4328ad59cf0 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -29,6 +29,7 @@
 #include <linux/irq.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
+#include <linux/mmc/sdio.h>
 #include <linux/mmc/dw_mmc.h>
 #include <linux/bitops.h>
 #include <linux/regulator/consumer.h>
@@ -246,10 +247,15 @@ static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 
 	cmdr = cmd->opcode;
 
-	if (cmdr == MMC_STOP_TRANSMISSION)
+	if (cmd->opcode == MMC_STOP_TRANSMISSION ||
+	    cmd->opcode == MMC_GO_IDLE_STATE ||
+	    cmd->opcode == MMC_GO_INACTIVE_STATE ||
+	    (cmd->opcode == SD_IO_RW_DIRECT &&
+	     ((cmd->arg >> 9) & 0x1FFFF) == SDIO_CCCR_ABORT))
 		cmdr |= SDMMC_CMD_STOP;
 	else
-		cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
+		if (cmd->opcode != MMC_SEND_STATUS && cmd->data)
+			cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
 
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		/* We expect a response, so set this bit */
@@ -276,6 +282,40 @@ static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 	return cmdr;
 }
 
+static u32 dw_mci_prep_stop_abort(struct dw_mci *host, struct mmc_command *cmd)
+{
+	struct mmc_command *stop;
+	u32 cmdr;
+
+	if (!cmd->data)
+		return 0;
+
+	stop = &host->stop_abort;
+	cmdr = cmd->opcode;
+	memset(stop, 0, sizeof(struct mmc_command));
+
+	if (cmdr == MMC_READ_SINGLE_BLOCK ||
+	    cmdr == MMC_READ_MULTIPLE_BLOCK ||
+	    cmdr == MMC_WRITE_BLOCK ||
+	    cmdr == MMC_WRITE_MULTIPLE_BLOCK) {
+		stop->opcode = MMC_STOP_TRANSMISSION;
+		stop->arg = 0;
+		stop->flags = MMC_RSP_R1B | MMC_CMD_AC;
+	} else if (cmdr == SD_IO_RW_EXTENDED) {
+		stop->opcode = SD_IO_RW_DIRECT;
+		stop->arg |= (1 << 31) | (0 << 28) | (SDIO_CCCR_ABORT << 9) |
+			     ((cmd->arg >> 28) & 0x7);
+		stop->flags = MMC_RSP_SPI_R5 | MMC_RSP_R5 | MMC_CMD_AC;
+	} else {
+		return 0;
+	}
+
+	cmdr = stop->opcode | SDMMC_CMD_STOP |
+		SDMMC_CMD_RESP_CRC | SDMMC_CMD_RESP_EXP;
+
+	return cmdr;
+}
+
 static void dw_mci_start_command(struct dw_mci *host,
 				 struct mmc_command *cmd, u32 cmd_flags)
 {
@@ -290,9 +330,10 @@ static void dw_mci_start_command(struct dw_mci *host,
 	mci_writel(host, CMD, cmd_flags | SDMMC_CMD_START);
 }
 
-static void send_stop_cmd(struct dw_mci *host, struct mmc_data *data)
+static inline void send_stop_abort(struct dw_mci *host, struct mmc_data *data)
 {
-	dw_mci_start_command(host, data->stop, host->stop_cmdr);
+	struct mmc_command *stop = data->stop ? data->stop : &host->stop_abort;
+	dw_mci_start_command(host, stop, host->stop_cmdr);
 }
 
 /* DMA interface functions */
@@ -828,6 +869,8 @@ static void __dw_mci_start_request(struct dw_mci *host,
 
 	if (mrq->stop)
 		host->stop_cmdr = dw_mci_prepare_command(slot->mmc, mrq->stop);
+	else
+		host->stop_cmdr = dw_mci_prep_stop_abort(host, cmd);
 }
 
 static void dw_mci_start_request(struct dw_mci *host,
@@ -1190,13 +1233,9 @@ static void dw_mci_tasklet_func(unsigned long priv)
 
 			if (cmd->data && cmd->error) {
 				dw_mci_stop_dma(host);
-				if (data->stop) {
-					send_stop_cmd(host, data);
-					state = STATE_SENDING_STOP;
-					break;
-				} else {
-					host->data = NULL;
-				}
+				send_stop_abort(host, data);
+				state = STATE_SENDING_STOP;
+				break;
 			}
 
 			if (!host->mrq->data || cmd->error) {
@@ -1211,8 +1250,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			if (test_and_clear_bit(EVENT_DATA_ERROR,
 					       &host->pending_events)) {
 				dw_mci_stop_dma(host);
-				if (data->stop)
-					send_stop_cmd(host, data);
+				send_stop_abort(host, data);
 				state = STATE_DATA_ERROR;
 				break;
 			}
@@ -1272,7 +1310,7 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				data->error = 0;
 			}
 
-			if (!data->stop) {
+			if (!data->stop && !data->error) {
 				dw_mci_request_end(host, host->mrq);
 				goto unlock;
 			}
@@ -1284,8 +1322,10 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			}
 
 			prev_state = state = STATE_SENDING_STOP;
-			if (!data->error)
-				send_stop_cmd(host, data);
+			if (data->stop && !data->error) {
+				/* stop command for open-ended transfer*/
+				send_stop_abort(host, data);
+			}
 			/* fall through */
 
 		case STATE_SENDING_STOP:
@@ -1304,7 +1344,12 @@ static void dw_mci_tasklet_func(unsigned long priv)
 
 			host->cmd = NULL;
 			host->data = NULL;
-			dw_mci_command_complete(host, host->mrq->stop);
+
+			if (host->mrq->stop)
+				dw_mci_command_complete(host, host->mrq->stop);
+			else
+				host->cmd_status = 0;
+
 			dw_mci_request_end(host, host->mrq);
 			goto unlock;
 
@@ -1888,11 +1933,10 @@ static void dw_mci_work_routine_card(struct work_struct *work)
 					case STATE_DATA_ERROR:
 						if (mrq->data->error == -EINPROGRESS)
 							mrq->data->error = -ENOMEDIUM;
-						if (!mrq->stop)
-							break;
 						/* fall through */
 					case STATE_SENDING_STOP:
-						mrq->stop->error = -ENOMEDIUM;
+						if (mrq->stop)
+							mrq->stop->error = -ENOMEDIUM;
 						break;
 					}
 
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index a829f7ee28c8..6ce7d2cd3c7a 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -15,6 +15,7 @@
 #define LINUX_MMC_DW_MMC_H
 
 #include <linux/scatterlist.h>
+#include <linux/mmc/core.h>
 
 #define MAX_MCI_SLOTS	2
 
@@ -129,6 +130,7 @@ struct dw_mci {
 	struct mmc_request	*mrq;
 	struct mmc_command	*cmd;
 	struct mmc_data		*data;
+	struct mmc_command	stop_abort;
 	unsigned int		prev_blksz;
 	unsigned char		timing;
 	struct workqueue_struct	*card_workqueue;
-- 
cgit 


From 71ef1ea418ee45a4f939d53a02410627b394c336 Mon Sep 17 00:00:00 2001
From: Jackey Shen <jackey.shen@amd.com>
Date: Fri, 17 May 2013 17:17:43 +0800
Subject: mmc: core: clean up duplicate macros

Clean up the duplicate macros:
mmc_sd_card_uhs -> mmc_card_uhs
mmc_sd_card_set_uhs -> mmc_card_set_uhs

Signed-off-by: Jackey Shen <jackey.shen@amd.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/bus.c            | 2 +-
 drivers/mmc/host/rtsx_pci_sdmmc.c | 2 +-
 include/linux/mmc/card.h          | 2 --
 3 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 704bf66f5873..cdca8a70da38 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -340,7 +340,7 @@ int mmc_add_card(struct mmc_card *card)
 		break;
 	}
 
-	if (mmc_sd_card_uhs(card) &&
+	if (mmc_card_uhs(card) &&
 		(card->sd_bus_speed < ARRAY_SIZE(uhs_speeds)))
 		uhs_bus_speed_mode = uhs_speeds[card->sd_bus_speed];
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 375a880e0c5f..e2ab12473f97 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -364,7 +364,7 @@ static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_card *card = mmc->card;
 	struct mmc_data *data = mrq->data;
-	int uhs = mmc_sd_card_uhs(card);
+	int uhs = mmc_card_uhs(card);
 	int read = (data->flags & MMC_DATA_READ) ? 1 : 0;
 	u8 cfg2, trans_mode;
 	int err;
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 842de3e21e70..f42cdbd8ac21 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -420,7 +420,6 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 #define mmc_card_blockaddr(c)	((c)->state & MMC_STATE_BLOCKADDR)
 #define mmc_card_ddr_mode(c)	((c)->state & MMC_STATE_HIGHSPEED_DDR)
 #define mmc_card_uhs(c)		((c)->state & MMC_STATE_ULTRAHIGHSPEED)
-#define mmc_sd_card_uhs(c)	((c)->state & MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
 #define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
 #define mmc_card_doing_bkops(c)	((c)->state & MMC_STATE_DOING_BKOPS)
@@ -432,7 +431,6 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 #define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR)
 #define mmc_card_set_ddr_mode(c) ((c)->state |= MMC_STATE_HIGHSPEED_DDR)
 #define mmc_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED)
-#define mmc_sd_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC)
 #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
 #define mmc_card_set_doing_bkops(c)	((c)->state |= MMC_STATE_DOING_BKOPS)
-- 
cgit 


From 28061758dc83df445a05af347b5ce55ccd968c03 Mon Sep 17 00:00:00 2001
From: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
Date: Tue, 13 Aug 2013 13:43:26 +0100
Subject: ARM/ARM64: arch_timer: add macros for bits in control register

Add macros to describe the bitfields in the ARM architected timer
control register to make code easy to understand.

Reviewed-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
---
 arch/arm/include/asm/arch_timer.h    |  9 +++++++--
 arch/arm64/include/asm/arch_timer.h  | 12 ++++++++----
 include/clocksource/arm_arch_timer.h |  8 ++++++++
 3 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 5665134bfa3e..d57e04de8e8c 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -93,8 +93,13 @@ static inline void arch_counter_set_user_access(void)
 
 	asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
 
-	/* disable user access to everything */
-	cntkctl &= ~((3 << 8) | (7 << 0));
+	/* Disable user access to both physical/virtual counters/timers */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_VCT_ACCESS_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
 
 	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
 }
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index c9f1d2816c2b..2b9722f42729 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -96,12 +96,16 @@ static inline void arch_counter_set_user_access(void)
 {
 	u32 cntkctl;
 
-	/* Disable user access to the timers and the physical counter. */
 	asm volatile("mrs	%0, cntkctl_el1" : "=r" (cntkctl));
-	cntkctl &= ~((3 << 8) | (1 << 0));
 
-	/* Enable user access to the virtual counter and frequency. */
-	cntkctl |= (1 << 1);
+	/* Disable user access to the timers and the physical counter */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+
+	/* Enable user access to the virtual counter */
+	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 93b7f96f9c59..8707dae4cee2 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -33,6 +33,14 @@ enum arch_timer_reg {
 #define ARCH_TIMER_MEM_PHYS_ACCESS	2
 #define ARCH_TIMER_MEM_VIRT_ACCESS	3
 
+#define ARCH_TIMER_USR_PCT_ACCESS_EN	(1 << 0) /* physical counter */
+#define ARCH_TIMER_USR_VCT_ACCESS_EN	(1 << 1) /* virtual counter */
+#define ARCH_TIMER_VIRT_EVT_EN		(1 << 2)
+#define ARCH_TIMER_EVT_TRIGGER_SHIFT	(4)
+#define ARCH_TIMER_EVT_TRIGGER_MASK	(0xF << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+#define ARCH_TIMER_USR_VT_ACCESS_EN	(1 << 8) /* virtual timer registers */
+#define ARCH_TIMER_USR_PT_ACCESS_EN	(1 << 9) /* physical timer registers */
+
 #ifdef CONFIG_ARM_ARCH_TIMER
 
 extern u32 arch_timer_get_rate(void);
-- 
cgit 


From 037f637767a82907efedda78d3ff405c34020075 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Fri, 23 Aug 2013 15:32:29 +0100
Subject: drivers: clocksource: add support for ARM architected timer event
 stream

The ARM architected timer can generate events (used for waking up
CPUs executing the wfe instruction) at a frequency represented as a
power-of-2 divisor of the clock rate.

An event stream might be used:
- To implement wfe-based timeouts for userspace locking implementations.
- To impose a timeout on a wfe for safeguarding against any programming
  error in case an expected event is not generated.

This patch computes the event stream frequency aiming for a period
of 100us between events. It uses ARM/ARM64 specific backends to configure
and enable the event stream.

Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Will Deacon <will.deacon@arm.com>
[sudeep: moving ARM/ARM64 changes into separate patches
         and adding Kconfig option]
Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
---
 drivers/clocksource/Kconfig          | 15 +++++++++++++++
 drivers/clocksource/arm_arch_timer.c | 15 +++++++++++++++
 include/clocksource/arm_arch_timer.h |  2 ++
 3 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 41c69469ce20..559d80335446 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -74,6 +74,21 @@ config ARM_ARCH_TIMER
 	bool
 	select CLKSRC_OF if OF
 
+config ARM_ARCH_TIMER_EVTSTREAM
+	bool "Support for ARM architected timer event stream generation"
+	default y if ARM_ARCH_TIMER
+	help
+	  This option enables support for event stream generation based on
+	  the ARM architected timer. It is used for waking up CPUs executing
+	  the wfe instruction at a frequency represented as a power-of-2
+	  divisor of the clock rate.
+	  The main use of the event stream is wfe-based timeouts of userspace
+	  locking implementations. It might also be useful for imposing timeout
+	  on wfe to safeguard against any programming errors in case an expected
+	  event is not generated.
+	  This must be disabled for hardware validation purposes to detect any
+	  hardware anomalies of missing events.
+
 config ARM_GLOBAL_TIMER
 	bool
 	select CLKSRC_OF if OF
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index fbd9ccd5e114..105f8ffa66a8 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -294,6 +294,19 @@ static void __arch_timer_setup(unsigned type,
 	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
 }
 
+static void arch_timer_configure_evtstream(void)
+{
+	int evt_stream_div, pos;
+
+	/* Find the closest power of two to the divisor */
+	evt_stream_div = arch_timer_rate / ARCH_TIMER_EVT_STREAM_FREQ;
+	pos = fls(evt_stream_div);
+	if (pos > 1 && !(evt_stream_div & (1 << (pos - 2))))
+		pos--;
+	/* enable event stream */
+	arch_timer_evtstrm_enable(min(pos, 15));
+}
+
 static int arch_timer_setup(struct clock_event_device *clk)
 {
 	__arch_timer_setup(ARCH_CP15_TIMER, clk);
@@ -307,6 +320,8 @@ static int arch_timer_setup(struct clock_event_device *clk)
 	}
 
 	arch_counter_set_user_access();
+	if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
+		arch_timer_configure_evtstream();
 
 	return 0;
 }
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 8707dae4cee2..6d26b40cbf5d 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -41,6 +41,8 @@ enum arch_timer_reg {
 #define ARCH_TIMER_USR_VT_ACCESS_EN	(1 << 8) /* virtual timer registers */
 #define ARCH_TIMER_USR_PT_ACCESS_EN	(1 << 9) /* physical timer registers */
 
+#define ARCH_TIMER_EVT_STREAM_FREQ	10000	/* 100us */
+
 #ifdef CONFIG_ARM_ARCH_TIMER
 
 extern u32 arch_timer_get_rate(void);
-- 
cgit 


From b0f4fe1edf6abbc81500d661f730cebd653a838c Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 6 Jun 2013 11:57:27 +0100
Subject: mfd: dbx500-prcmu: Correctly reorder PRCMU clock identifiers

... as stipulated by the Hardware Specification document.

Acked-by: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/mfd/dbx500-prcmu.h | 135 ++++++++++++++++++++-------------------
 1 file changed, 71 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index ca0790fba2f5..87667d48602b 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -97,70 +97,77 @@ enum prcmu_wakeup_index {
 /*
  * Clock identifiers.
  */
-enum prcmu_clock {
-	PRCMU_SGACLK,
-	PRCMU_UARTCLK,
-	PRCMU_MSP02CLK,
-	PRCMU_MSP1CLK,
-	PRCMU_I2CCLK,
-	PRCMU_SDMMCCLK,
-	PRCMU_SPARE1CLK,
-	PRCMU_SLIMCLK,
-	PRCMU_PER1CLK,
-	PRCMU_PER2CLK,
-	PRCMU_PER3CLK,
-	PRCMU_PER5CLK,
-	PRCMU_PER6CLK,
-	PRCMU_PER7CLK,
-	PRCMU_LCDCLK,
-	PRCMU_BMLCLK,
-	PRCMU_HSITXCLK,
-	PRCMU_HSIRXCLK,
-	PRCMU_HDMICLK,
-	PRCMU_APEATCLK,
-	PRCMU_APETRACECLK,
-	PRCMU_MCDECLK,
-	PRCMU_IPI2CCLK,
-	PRCMU_DSIALTCLK,
-	PRCMU_DMACLK,
-	PRCMU_B2R2CLK,
-	PRCMU_TVCLK,
-	PRCMU_SSPCLK,
-	PRCMU_RNGCLK,
-	PRCMU_UICCCLK,
-	PRCMU_PWMCLK,
-	PRCMU_IRDACLK,
-	PRCMU_IRRCCLK,
-	PRCMU_SIACLK,
-	PRCMU_SVACLK,
-	PRCMU_ACLK,
-	PRCMU_HVACLK, /* Ux540 only */
-	PRCMU_G1CLK, /* Ux540 only */
-	PRCMU_SDMMCHCLK,
-	PRCMU_CAMCLK,
-	PRCMU_BML8580CLK,
-	PRCMU_NUM_REG_CLOCKS,
-	PRCMU_SYSCLK = PRCMU_NUM_REG_CLOCKS,
-	PRCMU_CDCLK,
-	PRCMU_TIMCLK,
-	PRCMU_PLLSOC0,
-	PRCMU_PLLSOC1,
-	PRCMU_ARMSS,
-	PRCMU_PLLDDR,
-	PRCMU_PLLDSI,
-	PRCMU_DSI0CLK,
-	PRCMU_DSI1CLK,
-	PRCMU_DSI0ESCCLK,
-	PRCMU_DSI1ESCCLK,
-	PRCMU_DSI2ESCCLK,
-	/* LCD DSI PLL - Ux540 only */
-	PRCMU_PLLDSI_LCD,
-	PRCMU_DSI0CLK_LCD,
-	PRCMU_DSI1CLK_LCD,
-	PRCMU_DSI0ESCCLK_LCD,
-	PRCMU_DSI1ESCCLK_LCD,
-	PRCMU_DSI2ESCCLK_LCD,
-};
+#define ARMCLK			0
+#define PRCMU_ACLK		1
+#define PRCMU_SVAMMCSPCLK 	2
+#define PRCMU_SDMMCHCLK 	2  /* DBx540 only. */
+#define PRCMU_SIACLK 		3
+#define PRCMU_SIAMMDSPCLK 	3  /* DBx540 only. */
+#define PRCMU_SGACLK 		4
+#define PRCMU_UARTCLK 		5
+#define PRCMU_MSP02CLK 		6
+#define PRCMU_MSP1CLK 		7
+#define PRCMU_I2CCLK 		8
+#define PRCMU_SDMMCCLK 		9
+#define PRCMU_SLIMCLK 		10
+#define PRCMU_CAMCLK 		10 /* DBx540 only. */
+#define PRCMU_PER1CLK 		11
+#define PRCMU_PER2CLK 		12
+#define PRCMU_PER3CLK 		13
+#define PRCMU_PER5CLK 		14
+#define PRCMU_PER6CLK 		15
+#define PRCMU_PER7CLK 		16
+#define PRCMU_LCDCLK 		17
+#define PRCMU_BMLCLK 		18
+#define PRCMU_HSITXCLK 		19
+#define PRCMU_HSIRXCLK 		20
+#define PRCMU_HDMICLK		21
+#define PRCMU_APEATCLK 		22
+#define PRCMU_APETRACECLK 	23
+#define PRCMU_MCDECLK  	 	24
+#define PRCMU_IPI2CCLK  	25
+#define PRCMU_DSIALTCLK  	26
+#define PRCMU_DMACLK  	 	27
+#define PRCMU_B2R2CLK  	 	28
+#define PRCMU_TVCLK  	 	29
+#define SPARE_UNIPROCLK  	30
+#define PRCMU_SSPCLK  	 	31
+#define PRCMU_RNGCLK  	 	32
+#define PRCMU_UICCCLK  	 	33
+#define PRCMU_G1CLK             34 /* DBx540 only. */
+#define PRCMU_HVACLK            35 /* DBx540 only. */
+#define PRCMU_SPARE1CLK	 	36
+#define PRCMU_SPARE2CLK	 	37
+
+#define PRCMU_NUM_REG_CLOCKS  	38
+
+#define PRCMU_RTCCLK  	 	PRCMU_NUM_REG_CLOCKS
+#define PRCMU_SYSCLK  	 	39
+#define PRCMU_CDCLK  	 	40
+#define PRCMU_TIMCLK  	 	41
+#define PRCMU_PLLSOC0  	 	42
+#define PRCMU_PLLSOC1  	 	43
+#define PRCMU_ARMSS  	 	44
+#define PRCMU_PLLDDR  	 	45
+#define PRCMU_BML8580CLK        46
+
+/* DSI Clocks */
+#define PRCMU_PLLDSI  	 	47
+#define PRCMU_DSI0CLK 	  	48
+#define PRCMU_DSI1CLK  	 	49
+#define PRCMU_DSI0ESCCLK  	50
+#define PRCMU_DSI1ESCCLK  	51
+#define PRCMU_DSI2ESCCLK  	52
+
+/* LCD DSI PLL - Ux540 only */
+#define PRCMU_PLLDSI_LCD        53
+#define PRCMU_DSI0CLK_LCD       54
+#define PRCMU_DSI1CLK_LCD       55
+#define PRCMU_DSI0ESCCLK_LCD    56
+#define PRCMU_DSI1ESCCLK_LCD    57
+#define PRCMU_DSI2ESCCLK_LCD    58
+
+#define PRCMU_NUM_CLKS  	59
 
 /**
  * enum prcmu_wdog_id - PRCMU watchdog IDs
-- 
cgit 


From 67f13daadccebf95c04f73db7b78cead844540bd Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Thu, 6 Jun 2013 11:50:47 +0100
Subject: mfd: dbx500-prcmu: Move PRCMU numerical clock identifiers into DT
 include file

These are required to request DBx500 PRCMU clocks from Device Tree. The
numbers used are taken directly from the Hardware Specification document.
We're moving them from the DBx500 PRCMU include file into the DT include
directory and referencing them from the former via a #include.

Acked-by: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/dt-bindings/mfd/dbx500-prcmu.h | 84 ++++++++++++++++++++++++++++++++++
 include/linux/mfd/dbx500-prcmu.h       | 77 +------------------------------
 2 files changed, 86 insertions(+), 75 deletions(-)
 create mode 100644 include/dt-bindings/mfd/dbx500-prcmu.h

(limited to 'include')

diff --git a/include/dt-bindings/mfd/dbx500-prcmu.h b/include/dt-bindings/mfd/dbx500-prcmu.h
new file mode 100644
index 000000000000..b7ee8c909908
--- /dev/null
+++ b/include/dt-bindings/mfd/dbx500-prcmu.h
@@ -0,0 +1,84 @@
+/*
+ * This header provides constants for the PRCMU bindings.
+ *
+ */
+
+#ifndef _DT_BINDINGS_MFD_PRCMU_H
+#define _DT_BINDINGS_MFD_PRCMU_H
+
+/*
+ * Clock identifiers.
+ */
+#define ARMCLK			0
+#define PRCMU_ACLK		1
+#define PRCMU_SVAMMCSPCLK 	2
+#define PRCMU_SDMMCHCLK 	2  /* DBx540 only. */
+#define PRCMU_SIACLK 		3
+#define PRCMU_SIAMMDSPCLK 	3  /* DBx540 only. */
+#define PRCMU_SGACLK 		4
+#define PRCMU_UARTCLK 		5
+#define PRCMU_MSP02CLK 		6
+#define PRCMU_MSP1CLK 		7
+#define PRCMU_I2CCLK 		8
+#define PRCMU_SDMMCCLK 		9
+#define PRCMU_SLIMCLK 		10
+#define PRCMU_CAMCLK 		10 /* DBx540 only. */
+#define PRCMU_PER1CLK 		11
+#define PRCMU_PER2CLK 		12
+#define PRCMU_PER3CLK 		13
+#define PRCMU_PER5CLK 		14
+#define PRCMU_PER6CLK 		15
+#define PRCMU_PER7CLK 		16
+#define PRCMU_LCDCLK 		17
+#define PRCMU_BMLCLK 		18
+#define PRCMU_HSITXCLK 		19
+#define PRCMU_HSIRXCLK 		20
+#define PRCMU_HDMICLK		21
+#define PRCMU_APEATCLK 		22
+#define PRCMU_APETRACECLK 	23
+#define PRCMU_MCDECLK  	 	24
+#define PRCMU_IPI2CCLK  	25
+#define PRCMU_DSIALTCLK  	26
+#define PRCMU_DMACLK  	 	27
+#define PRCMU_B2R2CLK  	 	28
+#define PRCMU_TVCLK  	 	29
+#define SPARE_UNIPROCLK  	30
+#define PRCMU_SSPCLK  	 	31
+#define PRCMU_RNGCLK  	 	32
+#define PRCMU_UICCCLK  	 	33
+#define PRCMU_G1CLK             34 /* DBx540 only. */
+#define PRCMU_HVACLK            35 /* DBx540 only. */
+#define PRCMU_SPARE1CLK	 	36
+#define PRCMU_SPARE2CLK	 	37
+
+#define PRCMU_NUM_REG_CLOCKS  	38
+
+#define PRCMU_RTCCLK  	 	PRCMU_NUM_REG_CLOCKS
+#define PRCMU_SYSCLK  	 	39
+#define PRCMU_CDCLK  	 	40
+#define PRCMU_TIMCLK  	 	41
+#define PRCMU_PLLSOC0  	 	42
+#define PRCMU_PLLSOC1  	 	43
+#define PRCMU_ARMSS  	 	44
+#define PRCMU_PLLDDR  	 	45
+#define PRCMU_BML8580CLK        46
+
+/* DSI Clocks */
+#define PRCMU_PLLDSI  	 	47
+#define PRCMU_DSI0CLK 	  	48
+#define PRCMU_DSI1CLK  	 	49
+#define PRCMU_DSI0ESCCLK  	50
+#define PRCMU_DSI1ESCCLK  	51
+#define PRCMU_DSI2ESCCLK  	52
+
+/* LCD DSI PLL - Ux540 only */
+#define PRCMU_PLLDSI_LCD        53
+#define PRCMU_DSI0CLK_LCD       54
+#define PRCMU_DSI1CLK_LCD       55
+#define PRCMU_DSI0ESCCLK_LCD    56
+#define PRCMU_DSI1ESCCLK_LCD    57
+#define PRCMU_DSI2ESCCLK_LCD    58
+
+#define PRCMU_NUM_CLKS  	59
+
+#endif
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index 87667d48602b..060e11256fbc 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -12,6 +12,8 @@
 #include <linux/notifier.h>
 #include <linux/err.h>
 
+#include <dt-bindings/mfd/dbx500-prcmu.h> /* For clock identifiers */
+
 /* Offset for the firmware version within the TCPM */
 #define DB8500_PRCMU_FW_VERSION_OFFSET 0xA4
 #define DBX540_PRCMU_FW_VERSION_OFFSET 0xA8
@@ -94,81 +96,6 @@ enum prcmu_wakeup_index {
 #define PRCMU_CLKSRC_ARMCLKFIX		0x46
 #define PRCMU_CLKSRC_HDMICLK		0x47
 
-/*
- * Clock identifiers.
- */
-#define ARMCLK			0
-#define PRCMU_ACLK		1
-#define PRCMU_SVAMMCSPCLK 	2
-#define PRCMU_SDMMCHCLK 	2  /* DBx540 only. */
-#define PRCMU_SIACLK 		3
-#define PRCMU_SIAMMDSPCLK 	3  /* DBx540 only. */
-#define PRCMU_SGACLK 		4
-#define PRCMU_UARTCLK 		5
-#define PRCMU_MSP02CLK 		6
-#define PRCMU_MSP1CLK 		7
-#define PRCMU_I2CCLK 		8
-#define PRCMU_SDMMCCLK 		9
-#define PRCMU_SLIMCLK 		10
-#define PRCMU_CAMCLK 		10 /* DBx540 only. */
-#define PRCMU_PER1CLK 		11
-#define PRCMU_PER2CLK 		12
-#define PRCMU_PER3CLK 		13
-#define PRCMU_PER5CLK 		14
-#define PRCMU_PER6CLK 		15
-#define PRCMU_PER7CLK 		16
-#define PRCMU_LCDCLK 		17
-#define PRCMU_BMLCLK 		18
-#define PRCMU_HSITXCLK 		19
-#define PRCMU_HSIRXCLK 		20
-#define PRCMU_HDMICLK		21
-#define PRCMU_APEATCLK 		22
-#define PRCMU_APETRACECLK 	23
-#define PRCMU_MCDECLK  	 	24
-#define PRCMU_IPI2CCLK  	25
-#define PRCMU_DSIALTCLK  	26
-#define PRCMU_DMACLK  	 	27
-#define PRCMU_B2R2CLK  	 	28
-#define PRCMU_TVCLK  	 	29
-#define SPARE_UNIPROCLK  	30
-#define PRCMU_SSPCLK  	 	31
-#define PRCMU_RNGCLK  	 	32
-#define PRCMU_UICCCLK  	 	33
-#define PRCMU_G1CLK             34 /* DBx540 only. */
-#define PRCMU_HVACLK            35 /* DBx540 only. */
-#define PRCMU_SPARE1CLK	 	36
-#define PRCMU_SPARE2CLK	 	37
-
-#define PRCMU_NUM_REG_CLOCKS  	38
-
-#define PRCMU_RTCCLK  	 	PRCMU_NUM_REG_CLOCKS
-#define PRCMU_SYSCLK  	 	39
-#define PRCMU_CDCLK  	 	40
-#define PRCMU_TIMCLK  	 	41
-#define PRCMU_PLLSOC0  	 	42
-#define PRCMU_PLLSOC1  	 	43
-#define PRCMU_ARMSS  	 	44
-#define PRCMU_PLLDDR  	 	45
-#define PRCMU_BML8580CLK        46
-
-/* DSI Clocks */
-#define PRCMU_PLLDSI  	 	47
-#define PRCMU_DSI0CLK 	  	48
-#define PRCMU_DSI1CLK  	 	49
-#define PRCMU_DSI0ESCCLK  	50
-#define PRCMU_DSI1ESCCLK  	51
-#define PRCMU_DSI2ESCCLK  	52
-
-/* LCD DSI PLL - Ux540 only */
-#define PRCMU_PLLDSI_LCD        53
-#define PRCMU_DSI0CLK_LCD       54
-#define PRCMU_DSI1CLK_LCD       55
-#define PRCMU_DSI0ESCCLK_LCD    56
-#define PRCMU_DSI1ESCCLK_LCD    57
-#define PRCMU_DSI2ESCCLK_LCD    58
-
-#define PRCMU_NUM_CLKS  	59
-
 /**
  * enum prcmu_wdog_id - PRCMU watchdog IDs
  * @PRCMU_WDOG_ALL: use all timers
-- 
cgit 


From 58092dc4dfde55d5824211e5aa1be47212a57f1f Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Mon, 19 Aug 2013 12:23:05 +0100
Subject: mfd: dbx500: Remove any mention of the BML8580CLK

The platform which it pertains to is no longer supported and is actually
causing some confusion in the new common clock implementation. A recent
patch removed its use in the clock driver, let's take out the definitions
too.

Acked-by: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/mfd/db8500-prcmu.c             |  1 -
 drivers/mfd/dbx500-prcmu-regs.h        |  1 -
 include/dt-bindings/mfd/dbx500-prcmu.h | 27 +++++++++++++--------------
 3 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index 53f371dcbb6e..b9ce60c301de 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -480,7 +480,6 @@ static struct clk_mgt clk_mgt[PRCMU_NUM_REG_CLOCKS] = {
 	CLK_MGT_ENTRY(PER6CLK, PLL_DIV, true),
 	CLK_MGT_ENTRY(PER7CLK, PLL_DIV, true),
 	CLK_MGT_ENTRY(LCDCLK, PLL_FIX, true),
-	CLK_MGT_ENTRY(BML8580CLK, PLL_DIV, true),
 	CLK_MGT_ENTRY(BMLCLK, PLL_DIV, true),
 	CLK_MGT_ENTRY(HSITXCLK, PLL_DIV, true),
 	CLK_MGT_ENTRY(HSIRXCLK, PLL_DIV, true),
diff --git a/drivers/mfd/dbx500-prcmu-regs.h b/drivers/mfd/dbx500-prcmu-regs.h
index 4f6f0fa5d3b7..7cc32a8ff01c 100644
--- a/drivers/mfd/dbx500-prcmu-regs.h
+++ b/drivers/mfd/dbx500-prcmu-regs.h
@@ -32,7 +32,6 @@
 #define PRCM_PER7CLK_MGT	(0x040)
 #define PRCM_LCDCLK_MGT		(0x044)
 #define PRCM_BMLCLK_MGT		(0x04C)
-#define PRCM_BML8580CLK_MGT	(0x108)
 #define PRCM_HSITXCLK_MGT	(0x050)
 #define PRCM_HSIRXCLK_MGT	(0x054)
 #define PRCM_HDMICLK_MGT	(0x058)
diff --git a/include/dt-bindings/mfd/dbx500-prcmu.h b/include/dt-bindings/mfd/dbx500-prcmu.h
index b7ee8c909908..552a2d174f01 100644
--- a/include/dt-bindings/mfd/dbx500-prcmu.h
+++ b/include/dt-bindings/mfd/dbx500-prcmu.h
@@ -61,24 +61,23 @@
 #define PRCMU_PLLSOC1  	 	43
 #define PRCMU_ARMSS  	 	44
 #define PRCMU_PLLDDR  	 	45
-#define PRCMU_BML8580CLK        46
 
 /* DSI Clocks */
-#define PRCMU_PLLDSI  	 	47
-#define PRCMU_DSI0CLK 	  	48
-#define PRCMU_DSI1CLK  	 	49
-#define PRCMU_DSI0ESCCLK  	50
-#define PRCMU_DSI1ESCCLK  	51
-#define PRCMU_DSI2ESCCLK  	52
+#define PRCMU_PLLDSI  	 	46
+#define PRCMU_DSI0CLK 	  	47
+#define PRCMU_DSI1CLK  	 	48
+#define PRCMU_DSI0ESCCLK  	49
+#define PRCMU_DSI1ESCCLK  	50
+#define PRCMU_DSI2ESCCLK  	51
 
 /* LCD DSI PLL - Ux540 only */
-#define PRCMU_PLLDSI_LCD        53
-#define PRCMU_DSI0CLK_LCD       54
-#define PRCMU_DSI1CLK_LCD       55
-#define PRCMU_DSI0ESCCLK_LCD    56
-#define PRCMU_DSI1ESCCLK_LCD    57
-#define PRCMU_DSI2ESCCLK_LCD    58
+#define PRCMU_PLLDSI_LCD        52
+#define PRCMU_DSI0CLK_LCD       53
+#define PRCMU_DSI1CLK_LCD       54
+#define PRCMU_DSI0ESCCLK_LCD    55
+#define PRCMU_DSI1ESCCLK_LCD    56
+#define PRCMU_DSI2ESCCLK_LCD    57
 
-#define PRCMU_NUM_CLKS  	59
+#define PRCMU_NUM_CLKS  	58
 
 #endif
-- 
cgit 


From 82b0f4b7c576d22c764239662cedc63c21f02d8d Mon Sep 17 00:00:00 2001
From: Lee Jones <lee.jones@linaro.org>
Date: Tue, 17 Sep 2013 10:11:53 +0100
Subject: clk: ux500: Copy u8500_clk_init() ready for DT enablement

Here we're using the old clock initialisation function as a template.
It's necessary to remove all of the clk_register_clkdev() calls as
they don't make sense when booting with Device Tree.

Cc: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/clk/ux500/Makefile              |   1 +
 drivers/clk/ux500/u8500_of_clk.c        | 381 ++++++++++++++++++++++++++++++++
 include/linux/platform_data/clk-ux500.h |   3 +
 3 files changed, 385 insertions(+)
 create mode 100644 drivers/clk/ux500/u8500_of_clk.c

(limited to 'include')

diff --git a/drivers/clk/ux500/Makefile b/drivers/clk/ux500/Makefile
index c6a806ed0e8c..521483f0ba33 100644
--- a/drivers/clk/ux500/Makefile
+++ b/drivers/clk/ux500/Makefile
@@ -8,6 +8,7 @@ obj-y += clk-prcmu.o
 obj-y += clk-sysctrl.o
 
 # Clock definitions
+obj-y += u8500_of_clk.o
 obj-y += u8500_clk.o
 obj-y += u9540_clk.o
 obj-y += u8540_clk.o
diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c
new file mode 100644
index 000000000000..ceebce6a624f
--- /dev/null
+++ b/drivers/clk/ux500/u8500_of_clk.c
@@ -0,0 +1,381 @@
+/*
+ * Clock definitions for u8500 platform.
+ *
+ * Copyright (C) 2012 ST-Ericsson SA
+ * Author: Ulf Hansson <ulf.hansson@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/mfd/dbx500-prcmu.h>
+#include <linux/platform_data/clk-ux500.h>
+#include "clk.h"
+
+void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
+		       u32 clkrst5_base, u32 clkrst6_base)
+{
+	struct prcmu_fw_version *fw_version;
+	const char *sgaclk_parent = NULL;
+	struct clk *clk;
+
+	/* Clock sources */
+	clk = clk_reg_prcmu_gate("soc0_pll", NULL, PRCMU_PLLSOC0,
+				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
+
+	clk = clk_reg_prcmu_gate("soc1_pll", NULL, PRCMU_PLLSOC1,
+				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
+
+	clk = clk_reg_prcmu_gate("ddr_pll", NULL, PRCMU_PLLDDR,
+				CLK_IS_ROOT|CLK_IGNORE_UNUSED);
+
+	/* FIXME: Add sys, ulp and int clocks here. */
+
+	clk = clk_register_fixed_rate(NULL, "rtc32k", "NULL",
+				CLK_IS_ROOT|CLK_IGNORE_UNUSED,
+				32768);
+
+	/* PRCMU clocks */
+	fw_version = prcmu_get_fw_version();
+	if (fw_version != NULL) {
+		switch (fw_version->project) {
+		case PRCMU_FW_PROJECT_U8500_C2:
+		case PRCMU_FW_PROJECT_U8520:
+		case PRCMU_FW_PROJECT_U8420:
+			sgaclk_parent = "soc0_pll";
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (sgaclk_parent)
+		clk = clk_reg_prcmu_gate("sgclk", sgaclk_parent,
+					PRCMU_SGACLK, 0);
+	else
+		clk = clk_reg_prcmu_gate("sgclk", NULL,
+					PRCMU_SGACLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("uartclk", NULL, PRCMU_UARTCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("msp02clk", NULL, PRCMU_MSP02CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("msp1clk", NULL, PRCMU_MSP1CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("i2cclk", NULL, PRCMU_I2CCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("slimclk", NULL, PRCMU_SLIMCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per1clk", NULL, PRCMU_PER1CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per2clk", NULL, PRCMU_PER2CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per3clk", NULL, PRCMU_PER3CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per5clk", NULL, PRCMU_PER5CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per6clk", NULL, PRCMU_PER6CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("per7clk", NULL, PRCMU_PER7CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_scalable("lcdclk", NULL, PRCMU_LCDCLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_opp_gate("bmlclk", NULL, PRCMU_BMLCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_scalable("hsitxclk", NULL, PRCMU_HSITXCLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("hsirxclk", NULL, PRCMU_HSIRXCLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("hdmiclk", NULL, PRCMU_HDMICLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_gate("apeatclk", NULL, PRCMU_APEATCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("apetraceclk", NULL, PRCMU_APETRACECLK,
+				CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("mcdeclk", NULL, PRCMU_MCDECLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_opp_gate("ipi2cclk", NULL, PRCMU_IPI2CCLK,
+				CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("dsialtclk", NULL, PRCMU_DSIALTCLK,
+				CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("dmaclk", NULL, PRCMU_DMACLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("b2r2clk", NULL, PRCMU_B2R2CLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_scalable("tvclk", NULL, PRCMU_TVCLK, 0,
+				CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_gate("sspclk", NULL, PRCMU_SSPCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("rngclk", NULL, PRCMU_RNGCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("uiccclk", NULL, PRCMU_UICCCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_gate("timclk", NULL, PRCMU_TIMCLK, CLK_IS_ROOT);
+
+	clk = clk_reg_prcmu_opp_volt_scalable("sdmmcclk", NULL, PRCMU_SDMMCCLK,
+					100000000,
+					CLK_IS_ROOT|CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("dsi_pll", "hdmiclk",
+				PRCMU_PLLDSI, 0, CLK_SET_RATE_GATE);
+
+
+	clk = clk_reg_prcmu_scalable("dsi0clk", "dsi_pll",
+				PRCMU_DSI0CLK, 0, CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("dsi1clk", "dsi_pll",
+				PRCMU_DSI1CLK, 0, CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("dsi0escclk", "tvclk",
+				PRCMU_DSI0ESCCLK, 0, CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("dsi1escclk", "tvclk",
+				PRCMU_DSI1ESCCLK, 0, CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable("dsi2escclk", "tvclk",
+				PRCMU_DSI2ESCCLK, 0, CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcmu_scalable_rate("armss", NULL,
+				PRCMU_ARMSS, 0, CLK_IS_ROOT|CLK_IGNORE_UNUSED);
+
+	clk = clk_register_fixed_factor(NULL, "smp_twd", "armss",
+				CLK_IGNORE_UNUSED, 1, 2);
+
+	/*
+	 * FIXME: Add special handled PRCMU clocks here:
+	 * 1. clkout0yuv, use PRCMU as parent + need regulator + pinctrl.
+	 * 2. ab9540_clkout1yuv, see clkout0yuv
+	 */
+
+	/* PRCC P-clocks */
+	clk = clk_reg_prcc_pclk("p1_pclk0", "per1clk", clkrst1_base,
+				BIT(0), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk1", "per1clk", clkrst1_base,
+				BIT(1), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk2", "per1clk", clkrst1_base,
+				BIT(2), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk3", "per1clk", clkrst1_base,
+				BIT(3), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk4", "per1clk", clkrst1_base,
+				BIT(4), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk5", "per1clk", clkrst1_base,
+				BIT(5), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk6", "per1clk", clkrst1_base,
+				BIT(6), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk7", "per1clk", clkrst1_base,
+				BIT(7), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk8", "per1clk", clkrst1_base,
+				BIT(8), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk9", "per1clk", clkrst1_base,
+				BIT(9), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk10", "per1clk", clkrst1_base,
+				BIT(10), 0);
+
+	clk = clk_reg_prcc_pclk("p1_pclk11", "per1clk", clkrst1_base,
+				BIT(11), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk0", "per2clk", clkrst2_base,
+				BIT(0), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk1", "per2clk", clkrst2_base,
+				BIT(1), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk2", "per2clk", clkrst2_base,
+				BIT(2), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk3", "per2clk", clkrst2_base,
+				BIT(3), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk4", "per2clk", clkrst2_base,
+				BIT(4), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk5", "per2clk", clkrst2_base,
+				BIT(5), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk6", "per2clk", clkrst2_base,
+				BIT(6), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk7", "per2clk", clkrst2_base,
+				BIT(7), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk8", "per2clk", clkrst2_base,
+				BIT(8), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk9", "per2clk", clkrst2_base,
+				BIT(9), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk10", "per2clk", clkrst2_base,
+				BIT(10), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk11", "per2clk", clkrst2_base,
+				BIT(11), 0);
+
+	clk = clk_reg_prcc_pclk("p2_pclk12", "per2clk", clkrst2_base,
+				BIT(12), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk0", "per3clk", clkrst3_base,
+				BIT(0), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk1", "per3clk", clkrst3_base,
+				BIT(1), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk2", "per3clk", clkrst3_base,
+				BIT(2), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk3", "per3clk", clkrst3_base,
+				BIT(3), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk4", "per3clk", clkrst3_base,
+				BIT(4), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk5", "per3clk", clkrst3_base,
+				BIT(5), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk6", "per3clk", clkrst3_base,
+				BIT(6), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk7", "per3clk", clkrst3_base,
+				BIT(7), 0);
+
+	clk = clk_reg_prcc_pclk("p3_pclk8", "per3clk", clkrst3_base,
+				BIT(8), 0);
+
+	clk = clk_reg_prcc_pclk("p5_pclk0", "per5clk", clkrst5_base,
+				BIT(0), 0);
+
+	clk = clk_reg_prcc_pclk("p5_pclk1", "per5clk", clkrst5_base,
+				BIT(1), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk0", "per6clk", clkrst6_base,
+				BIT(0), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk1", "per6clk", clkrst6_base,
+				BIT(1), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk2", "per6clk", clkrst6_base,
+				BIT(2), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk3", "per6clk", clkrst6_base,
+				BIT(3), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk4", "per6clk", clkrst6_base,
+				BIT(4), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk5", "per6clk", clkrst6_base,
+				BIT(5), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk6", "per6clk", clkrst6_base,
+				BIT(6), 0);
+
+	clk = clk_reg_prcc_pclk("p6_pclk7", "per6clk", clkrst6_base,
+				BIT(7), 0);
+
+	/* PRCC K-clocks
+	 *
+	 * FIXME: Some drivers requires PERPIH[n| to be automatically enabled
+	 * by enabling just the K-clock, even if it is not a valid parent to
+	 * the K-clock. Until drivers get fixed we might need some kind of
+	 * "parent muxed join".
+	 */
+
+	/* Periph1 */
+	clk = clk_reg_prcc_kclk("p1_uart0_kclk", "uartclk",
+			clkrst1_base, BIT(0), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_uart1_kclk", "uartclk",
+			clkrst1_base, BIT(1), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_i2c1_kclk", "i2cclk",
+			clkrst1_base, BIT(2), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_msp0_kclk", "msp02clk",
+			clkrst1_base, BIT(3), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_msp1_kclk", "msp1clk",
+			clkrst1_base, BIT(4), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_sdi0_kclk", "sdmmcclk",
+			clkrst1_base, BIT(5), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_i2c2_kclk", "i2cclk",
+			clkrst1_base, BIT(6), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_slimbus0_kclk", "slimclk",
+			clkrst1_base, BIT(8), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_i2c4_kclk", "i2cclk",
+			clkrst1_base, BIT(9), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p1_msp3_kclk", "msp1clk",
+			clkrst1_base, BIT(10), CLK_SET_RATE_GATE);
+
+	/* Periph2 */
+	clk = clk_reg_prcc_kclk("p2_i2c3_kclk", "i2cclk",
+			clkrst2_base, BIT(0), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p2_sdi4_kclk", "sdmmcclk",
+			clkrst2_base, BIT(2), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p2_msp2_kclk", "msp02clk",
+			clkrst2_base, BIT(3), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p2_sdi1_kclk", "sdmmcclk",
+			clkrst2_base, BIT(4), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p2_sdi3_kclk", "sdmmcclk",
+			clkrst2_base, BIT(5), CLK_SET_RATE_GATE);
+
+	/* Note that rate is received from parent. */
+	clk = clk_reg_prcc_kclk("p2_ssirx_kclk", "hsirxclk",
+			clkrst2_base, BIT(6),
+			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
+	clk = clk_reg_prcc_kclk("p2_ssitx_kclk", "hsitxclk",
+			clkrst2_base, BIT(7),
+			CLK_SET_RATE_GATE|CLK_SET_RATE_PARENT);
+
+	/* Periph3 */
+	clk = clk_reg_prcc_kclk("p3_ssp0_kclk", "sspclk",
+			clkrst3_base, BIT(1), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_ssp1_kclk", "sspclk",
+			clkrst3_base, BIT(2), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_i2c0_kclk", "i2cclk",
+			clkrst3_base, BIT(3), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_sdi2_kclk", "sdmmcclk",
+			clkrst3_base, BIT(4), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_ske_kclk", "rtc32k",
+			clkrst3_base, BIT(5), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_uart2_kclk", "uartclk",
+			clkrst3_base, BIT(6), CLK_SET_RATE_GATE);
+
+	clk = clk_reg_prcc_kclk("p3_sdi5_kclk", "sdmmcclk",
+			clkrst3_base, BIT(7), CLK_SET_RATE_GATE);
+
+	/* Periph6 */
+	clk = clk_reg_prcc_kclk("p3_rng_kclk", "rngclk",
+			clkrst6_base, BIT(0), CLK_SET_RATE_GATE);
+}
diff --git a/include/linux/platform_data/clk-ux500.h b/include/linux/platform_data/clk-ux500.h
index 9d98f3aaa16c..97baf831e071 100644
--- a/include/linux/platform_data/clk-ux500.h
+++ b/include/linux/platform_data/clk-ux500.h
@@ -10,6 +10,9 @@
 #ifndef __CLK_UX500_H
 #define __CLK_UX500_H
 
+void u8500_of_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
+		       u32 clkrst5_base, u32 clkrst6_base);
+
 void u8500_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
 		    u32 clkrst5_base, u32 clkrst6_base);
 void u9540_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base,
-- 
cgit 


From 819585bc4811bc54e316dfe521ce163816fa0ad1 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ricardo.ribalda@gmail.com>
Date: Wed, 28 Aug 2013 04:39:29 -0300
Subject: [media] videobuf2: Fix vb2_write prototype
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct v4_file_operations defines the data param as
const char __user *data but on vb2 is defined as
char __user *data.
This patch fixes the warnings produced by this. ie:
drivers/qtec/qtec_xform.c:817:2: warning: initialization from
incompatible pointer type [enabled by default]
drivers/qtec/qtec_xform.c:817:2: warning: (near initialization for
		‘qtec_xform_v4l_fops.write’) [enabled by default]

Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/v4l2-core/videobuf2-core.c | 7 ++++---
 include/media/videobuf2-core.h           | 4 ++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 594c75eab5a5..67ddadd5ea38 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -2467,10 +2467,11 @@ size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
 }
 EXPORT_SYMBOL_GPL(vb2_read);
 
-size_t vb2_write(struct vb2_queue *q, char __user *data, size_t count,
+size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
 		loff_t *ppos, int nonblocking)
 {
-	return __vb2_perform_fileio(q, data, count, ppos, nonblocking, 0);
+	return __vb2_perform_fileio(q, (char __user *) data, count,
+							ppos, nonblocking, 0);
 }
 EXPORT_SYMBOL_GPL(vb2_write);
 
@@ -2631,7 +2632,7 @@ int vb2_fop_release(struct file *file)
 }
 EXPORT_SYMBOL_GPL(vb2_fop_release);
 
-ssize_t vb2_fop_write(struct file *file, char __user *buf,
+ssize_t vb2_fop_write(struct file *file, const char __user *buf,
 		size_t count, loff_t *ppos)
 {
 	struct video_device *vdev = video_devdata(file);
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 6781258d0b67..bd8218b15009 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -391,7 +391,7 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q,
 unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait);
 size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count,
 		loff_t *ppos, int nonblock);
-size_t vb2_write(struct vb2_queue *q, char __user *data, size_t count,
+size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count,
 		loff_t *ppos, int nonblock);
 
 /**
@@ -491,7 +491,7 @@ int vb2_ioctl_expbuf(struct file *file, void *priv,
 
 int vb2_fop_mmap(struct file *file, struct vm_area_struct *vma);
 int vb2_fop_release(struct file *file);
-ssize_t vb2_fop_write(struct file *file, char __user *buf,
+ssize_t vb2_fop_write(struct file *file, const char __user *buf,
 		size_t count, loff_t *ppos);
 ssize_t vb2_fop_read(struct file *file, char __user *buf,
 		size_t count, loff_t *ppos);
-- 
cgit 


From 223012475968fb8dac866bff5b278e9311a36894 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ricardo.ribalda@gmail.com>
Date: Fri, 2 Aug 2013 10:20:00 -0300
Subject: [media] videobuf2-dma-sg: Replace vb2_dma_sg_desc with sg_table

Replace the private struct vb2_dma_sg_desc with the struct sg_table so
we can benefit from all the helping functions in lib/scatterlist.c for
things like allocating the sg or compacting the descriptor.
marvel-ccic and solo6x10 drivers, that use this API have been updated.

Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Andre Heider <a.heider@gmail.com>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
[s.nawrocki@samsung.com: minor corrections of the changelog]
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>

Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/marvell-ccic/mcam-core.c    |  14 +--
 drivers/media/v4l2-core/videobuf2-dma-sg.c         | 103 +++++++++------------
 drivers/staging/media/solo6x10/solo6x10-v4l2-enc.c |  20 ++--
 include/media/videobuf2-dma-sg.h                   |  10 +-
 4 files changed, 63 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index 5184887b155c..32fab30a9105 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -1221,16 +1221,16 @@ static int mcam_vb_sg_buf_prepare(struct vb2_buffer *vb)
 {
 	struct mcam_vb_buffer *mvb = vb_to_mvb(vb);
 	struct mcam_camera *cam = vb2_get_drv_priv(vb->vb2_queue);
-	struct vb2_dma_sg_desc *sgd = vb2_dma_sg_plane_desc(vb, 0);
+	struct sg_table *sg_table = vb2_dma_sg_plane_desc(vb, 0);
 	struct mcam_dma_desc *desc = mvb->dma_desc;
 	struct scatterlist *sg;
 	int i;
 
-	mvb->dma_desc_nent = dma_map_sg(cam->dev, sgd->sglist, sgd->num_pages,
-			DMA_FROM_DEVICE);
+	mvb->dma_desc_nent = dma_map_sg(cam->dev, sg_table->sgl,
+			sg_table->nents, DMA_FROM_DEVICE);
 	if (mvb->dma_desc_nent <= 0)
 		return -EIO;  /* Not sure what's right here */
-	for_each_sg(sgd->sglist, sg, mvb->dma_desc_nent, i) {
+	for_each_sg(sg_table->sgl, sg, mvb->dma_desc_nent, i) {
 		desc->dma_addr = sg_dma_address(sg);
 		desc->segment_len = sg_dma_len(sg);
 		desc++;
@@ -1241,9 +1241,11 @@ static int mcam_vb_sg_buf_prepare(struct vb2_buffer *vb)
 static int mcam_vb_sg_buf_finish(struct vb2_buffer *vb)
 {
 	struct mcam_camera *cam = vb2_get_drv_priv(vb->vb2_queue);
-	struct vb2_dma_sg_desc *sgd = vb2_dma_sg_plane_desc(vb, 0);
+	struct sg_table *sg_table = vb2_dma_sg_plane_desc(vb, 0);
 
-	dma_unmap_sg(cam->dev, sgd->sglist, sgd->num_pages, DMA_FROM_DEVICE);
+	if (sg_table)
+		dma_unmap_sg(cam->dev, sg_table->sgl,
+				sg_table->nents, DMA_FROM_DEVICE);
 	return 0;
 }
 
diff --git a/drivers/media/v4l2-core/videobuf2-dma-sg.c b/drivers/media/v4l2-core/videobuf2-dma-sg.c
index 4999c4886898..2f860543912c 100644
--- a/drivers/media/v4l2-core/videobuf2-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf2-dma-sg.c
@@ -35,7 +35,9 @@ struct vb2_dma_sg_buf {
 	struct page			**pages;
 	int				write;
 	int				offset;
-	struct vb2_dma_sg_desc		sg_desc;
+	struct sg_table			sg_table;
+	size_t				size;
+	unsigned int			num_pages;
 	atomic_t			refcount;
 	struct vb2_vmarea_handler	handler;
 };
@@ -46,7 +48,7 @@ static int vb2_dma_sg_alloc_compacted(struct vb2_dma_sg_buf *buf,
 		gfp_t gfp_flags)
 {
 	unsigned int last_page = 0;
-	int size = buf->sg_desc.size;
+	int size = buf->size;
 
 	while (size > 0) {
 		struct page *pages;
@@ -74,12 +76,8 @@ static int vb2_dma_sg_alloc_compacted(struct vb2_dma_sg_buf *buf,
 		}
 
 		split_page(pages, order);
-		for (i = 0; i < (1 << order); i++) {
-			buf->pages[last_page] = &pages[i];
-			sg_set_page(&buf->sg_desc.sglist[last_page],
-					buf->pages[last_page], PAGE_SIZE, 0);
-			last_page++;
-		}
+		for (i = 0; i < (1 << order); i++)
+			buf->pages[last_page++] = &pages[i];
 
 		size -= PAGE_SIZE << order;
 	}
@@ -91,6 +89,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 {
 	struct vb2_dma_sg_buf *buf;
 	int ret;
+	int num_pages;
 
 	buf = kzalloc(sizeof *buf, GFP_KERNEL);
 	if (!buf)
@@ -99,17 +98,11 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 	buf->vaddr = NULL;
 	buf->write = 0;
 	buf->offset = 0;
-	buf->sg_desc.size = size;
+	buf->size = size;
 	/* size is already page aligned */
-	buf->sg_desc.num_pages = size >> PAGE_SHIFT;
-
-	buf->sg_desc.sglist = vzalloc(buf->sg_desc.num_pages *
-				      sizeof(*buf->sg_desc.sglist));
-	if (!buf->sg_desc.sglist)
-		goto fail_sglist_alloc;
-	sg_init_table(buf->sg_desc.sglist, buf->sg_desc.num_pages);
+	buf->num_pages = size >> PAGE_SHIFT;
 
-	buf->pages = kzalloc(buf->sg_desc.num_pages * sizeof(struct page *),
+	buf->pages = kzalloc(buf->num_pages * sizeof(struct page *),
 			     GFP_KERNEL);
 	if (!buf->pages)
 		goto fail_pages_array_alloc;
@@ -118,6 +111,11 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 	if (ret)
 		goto fail_pages_alloc;
 
+	ret = sg_alloc_table_from_pages(&buf->sg_table, buf->pages,
+			buf->num_pages, 0, size, gfp_flags);
+	if (ret)
+		goto fail_table_alloc;
+
 	buf->handler.refcount = &buf->refcount;
 	buf->handler.put = vb2_dma_sg_put;
 	buf->handler.arg = buf;
@@ -125,16 +123,16 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size, gfp_t gfp_fla
 	atomic_inc(&buf->refcount);
 
 	dprintk(1, "%s: Allocated buffer of %d pages\n",
-		__func__, buf->sg_desc.num_pages);
+		__func__, buf->num_pages);
 	return buf;
 
+fail_table_alloc:
+	num_pages = buf->num_pages;
+	while (num_pages--)
+		__free_page(buf->pages[num_pages]);
 fail_pages_alloc:
 	kfree(buf->pages);
-
 fail_pages_array_alloc:
-	vfree(buf->sg_desc.sglist);
-
-fail_sglist_alloc:
 	kfree(buf);
 	return NULL;
 }
@@ -142,14 +140,14 @@ fail_sglist_alloc:
 static void vb2_dma_sg_put(void *buf_priv)
 {
 	struct vb2_dma_sg_buf *buf = buf_priv;
-	int i = buf->sg_desc.num_pages;
+	int i = buf->num_pages;
 
 	if (atomic_dec_and_test(&buf->refcount)) {
 		dprintk(1, "%s: Freeing buffer of %d pages\n", __func__,
-			buf->sg_desc.num_pages);
+			buf->num_pages);
 		if (buf->vaddr)
-			vm_unmap_ram(buf->vaddr, buf->sg_desc.num_pages);
-		vfree(buf->sg_desc.sglist);
+			vm_unmap_ram(buf->vaddr, buf->num_pages);
+		sg_free_table(&buf->sg_table);
 		while (--i >= 0)
 			__free_page(buf->pages[i]);
 		kfree(buf->pages);
@@ -162,7 +160,7 @@ static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
 {
 	struct vb2_dma_sg_buf *buf;
 	unsigned long first, last;
-	int num_pages_from_user, i;
+	int num_pages_from_user;
 
 	buf = kzalloc(sizeof *buf, GFP_KERNEL);
 	if (!buf)
@@ -171,56 +169,41 @@ static void *vb2_dma_sg_get_userptr(void *alloc_ctx, unsigned long vaddr,
 	buf->vaddr = NULL;
 	buf->write = write;
 	buf->offset = vaddr & ~PAGE_MASK;
-	buf->sg_desc.size = size;
+	buf->size = size;
 
 	first = (vaddr           & PAGE_MASK) >> PAGE_SHIFT;
 	last  = ((vaddr + size - 1) & PAGE_MASK) >> PAGE_SHIFT;
-	buf->sg_desc.num_pages = last - first + 1;
-
-	buf->sg_desc.sglist = vzalloc(
-		buf->sg_desc.num_pages * sizeof(*buf->sg_desc.sglist));
-	if (!buf->sg_desc.sglist)
-		goto userptr_fail_sglist_alloc;
+	buf->num_pages = last - first + 1;
 
-	sg_init_table(buf->sg_desc.sglist, buf->sg_desc.num_pages);
-
-	buf->pages = kzalloc(buf->sg_desc.num_pages * sizeof(struct page *),
+	buf->pages = kzalloc(buf->num_pages * sizeof(struct page *),
 			     GFP_KERNEL);
 	if (!buf->pages)
-		goto userptr_fail_pages_array_alloc;
+		return NULL;
 
 	num_pages_from_user = get_user_pages(current, current->mm,
 					     vaddr & PAGE_MASK,
-					     buf->sg_desc.num_pages,
+					     buf->num_pages,
 					     write,
 					     1, /* force */
 					     buf->pages,
 					     NULL);
 
-	if (num_pages_from_user != buf->sg_desc.num_pages)
+	if (num_pages_from_user != buf->num_pages)
 		goto userptr_fail_get_user_pages;
 
-	sg_set_page(&buf->sg_desc.sglist[0], buf->pages[0],
-		    PAGE_SIZE - buf->offset, buf->offset);
-	size -= PAGE_SIZE - buf->offset;
-	for (i = 1; i < buf->sg_desc.num_pages; ++i) {
-		sg_set_page(&buf->sg_desc.sglist[i], buf->pages[i],
-			    min_t(size_t, PAGE_SIZE, size), 0);
-		size -= min_t(size_t, PAGE_SIZE, size);
-	}
+	if (sg_alloc_table_from_pages(&buf->sg_table, buf->pages,
+			buf->num_pages, buf->offset, size, 0))
+		goto userptr_fail_alloc_table_from_pages;
+
 	return buf;
 
+userptr_fail_alloc_table_from_pages:
 userptr_fail_get_user_pages:
 	dprintk(1, "get_user_pages requested/got: %d/%d]\n",
-	       num_pages_from_user, buf->sg_desc.num_pages);
+	       num_pages_from_user, buf->num_pages);
 	while (--num_pages_from_user >= 0)
 		put_page(buf->pages[num_pages_from_user]);
 	kfree(buf->pages);
-
-userptr_fail_pages_array_alloc:
-	vfree(buf->sg_desc.sglist);
-
-userptr_fail_sglist_alloc:
 	kfree(buf);
 	return NULL;
 }
@@ -232,18 +215,18 @@ userptr_fail_sglist_alloc:
 static void vb2_dma_sg_put_userptr(void *buf_priv)
 {
 	struct vb2_dma_sg_buf *buf = buf_priv;
-	int i = buf->sg_desc.num_pages;
+	int i = buf->num_pages;
 
 	dprintk(1, "%s: Releasing userspace buffer of %d pages\n",
-	       __func__, buf->sg_desc.num_pages);
+	       __func__, buf->num_pages);
 	if (buf->vaddr)
-		vm_unmap_ram(buf->vaddr, buf->sg_desc.num_pages);
+		vm_unmap_ram(buf->vaddr, buf->num_pages);
+	sg_free_table(&buf->sg_table);
 	while (--i >= 0) {
 		if (buf->write)
 			set_page_dirty_lock(buf->pages[i]);
 		put_page(buf->pages[i]);
 	}
-	vfree(buf->sg_desc.sglist);
 	kfree(buf->pages);
 	kfree(buf);
 }
@@ -256,7 +239,7 @@ static void *vb2_dma_sg_vaddr(void *buf_priv)
 
 	if (!buf->vaddr)
 		buf->vaddr = vm_map_ram(buf->pages,
-					buf->sg_desc.num_pages,
+					buf->num_pages,
 					-1,
 					PAGE_KERNEL);
 
@@ -312,7 +295,7 @@ static void *vb2_dma_sg_cookie(void *buf_priv)
 {
 	struct vb2_dma_sg_buf *buf = buf_priv;
 
-	return &buf->sg_desc;
+	return &buf->sg_table;
 }
 
 const struct vb2_mem_ops vb2_dma_sg_memops = {
diff --git a/drivers/staging/media/solo6x10/solo6x10-v4l2-enc.c b/drivers/staging/media/solo6x10/solo6x10-v4l2-enc.c
index a4c589604b02..9a6d5c0b1339 100644
--- a/drivers/staging/media/solo6x10/solo6x10-v4l2-enc.c
+++ b/drivers/staging/media/solo6x10/solo6x10-v4l2-enc.c
@@ -346,7 +346,7 @@ static int enc_get_mpeg_dma(struct solo_dev *solo_dev, dma_addr_t dma,
 /* Build a descriptor queue out of an SG list and send it to the P2M for
  * processing. */
 static int solo_send_desc(struct solo_enc_dev *solo_enc, int skip,
-			  struct vb2_dma_sg_desc *vbuf, int off, int size,
+			  struct sg_table *vbuf, int off, int size,
 			  unsigned int base, unsigned int base_size)
 {
 	struct solo_dev *solo_dev = solo_enc->solo_dev;
@@ -359,7 +359,7 @@ static int solo_send_desc(struct solo_enc_dev *solo_enc, int skip,
 
 	solo_enc->desc_count = 1;
 
-	for_each_sg(vbuf->sglist, sg, vbuf->num_pages, i) {
+	for_each_sg(vbuf->sgl, sg, vbuf->nents, i) {
 		struct solo_p2m_desc *desc;
 		dma_addr_t dma;
 		int len;
@@ -434,7 +434,7 @@ static int solo_fill_jpeg(struct solo_enc_dev *solo_enc,
 		struct vb2_buffer *vb, struct vop_header *vh)
 {
 	struct solo_dev *solo_dev = solo_enc->solo_dev;
-	struct vb2_dma_sg_desc *vbuf = vb2_dma_sg_plane_desc(vb, 0);
+	struct sg_table *vbuf = vb2_dma_sg_plane_desc(vb, 0);
 	int frame_size;
 	int ret;
 
@@ -443,7 +443,7 @@ static int solo_fill_jpeg(struct solo_enc_dev *solo_enc,
 	if (vb2_plane_size(vb, 0) < vh->jpeg_size + solo_enc->jpeg_len)
 		return -EIO;
 
-	sg_copy_from_buffer(vbuf->sglist, vbuf->num_pages,
+	sg_copy_from_buffer(vbuf->sgl, vbuf->nents,
 			solo_enc->jpeg_header,
 			solo_enc->jpeg_len);
 
@@ -451,12 +451,12 @@ static int solo_fill_jpeg(struct solo_enc_dev *solo_enc,
 		& ~(DMA_ALIGN - 1);
 	vb2_set_plane_payload(vb, 0, vh->jpeg_size + solo_enc->jpeg_len);
 
-	dma_map_sg(&solo_dev->pdev->dev, vbuf->sglist, vbuf->num_pages,
+	dma_map_sg(&solo_dev->pdev->dev, vbuf->sgl, vbuf->nents,
 			DMA_FROM_DEVICE);
 	ret = solo_send_desc(solo_enc, solo_enc->jpeg_len, vbuf, vh->jpeg_off,
 			frame_size, SOLO_JPEG_EXT_ADDR(solo_dev),
 			SOLO_JPEG_EXT_SIZE(solo_dev));
-	dma_unmap_sg(&solo_dev->pdev->dev, vbuf->sglist, vbuf->num_pages,
+	dma_unmap_sg(&solo_dev->pdev->dev, vbuf->sgl, vbuf->nents,
 			DMA_FROM_DEVICE);
 	return ret;
 }
@@ -465,7 +465,7 @@ static int solo_fill_mpeg(struct solo_enc_dev *solo_enc,
 		struct vb2_buffer *vb, struct vop_header *vh)
 {
 	struct solo_dev *solo_dev = solo_enc->solo_dev;
-	struct vb2_dma_sg_desc *vbuf = vb2_dma_sg_plane_desc(vb, 0);
+	struct sg_table *vbuf = vb2_dma_sg_plane_desc(vb, 0);
 	int frame_off, frame_size;
 	int skip = 0;
 	int ret;
@@ -475,7 +475,7 @@ static int solo_fill_mpeg(struct solo_enc_dev *solo_enc,
 
 	/* If this is a key frame, add extra header */
 	if (!vh->vop_type) {
-		sg_copy_from_buffer(vbuf->sglist, vbuf->num_pages,
+		sg_copy_from_buffer(vbuf->sgl, vbuf->nents,
 				solo_enc->vop,
 				solo_enc->vop_len);
 
@@ -494,12 +494,12 @@ static int solo_fill_mpeg(struct solo_enc_dev *solo_enc,
 	frame_size = (vh->mpeg_size + skip + (DMA_ALIGN - 1))
 		& ~(DMA_ALIGN - 1);
 
-	dma_map_sg(&solo_dev->pdev->dev, vbuf->sglist, vbuf->num_pages,
+	dma_map_sg(&solo_dev->pdev->dev, vbuf->sgl, vbuf->nents,
 			DMA_FROM_DEVICE);
 	ret = solo_send_desc(solo_enc, skip, vbuf, frame_off, frame_size,
 			SOLO_MP4E_EXT_ADDR(solo_dev),
 			SOLO_MP4E_EXT_SIZE(solo_dev));
-	dma_unmap_sg(&solo_dev->pdev->dev, vbuf->sglist, vbuf->num_pages,
+	dma_unmap_sg(&solo_dev->pdev->dev, vbuf->sgl, vbuf->nents,
 			DMA_FROM_DEVICE);
 	return ret;
 }
diff --git a/include/media/videobuf2-dma-sg.h b/include/media/videobuf2-dma-sg.h
index 0038526b8ef7..7b89852779af 100644
--- a/include/media/videobuf2-dma-sg.h
+++ b/include/media/videobuf2-dma-sg.h
@@ -15,16 +15,10 @@
 
 #include <media/videobuf2-core.h>
 
-struct vb2_dma_sg_desc {
-	unsigned long		size;
-	unsigned int		num_pages;
-	struct scatterlist	*sglist;
-};
-
-static inline struct vb2_dma_sg_desc *vb2_dma_sg_plane_desc(
+static inline struct sg_table *vb2_dma_sg_plane_desc(
 		struct vb2_buffer *vb, unsigned int plane_no)
 {
-	return (struct vb2_dma_sg_desc *)vb2_plane_cookie(vb, plane_no);
+	return (struct sg_table *)vb2_plane_cookie(vb, plane_no);
 }
 
 extern const struct vb2_mem_ops vb2_dma_sg_memops;
-- 
cgit 


From c7c71066c27f2bafb2ce3b10c407c0285f56acfa Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 21 Aug 2013 22:07:20 +0200
Subject: mac80211: add ieee80211_iterate_active_interfaces_rtnl()

If it is needed to disconnect multiple virtual interfaces after
(WoWLAN-) suspend, the most obvious approach would be to iterate
all interfaces by calling ieee80211_iterate_active_interfaces()
and then call ieee80211_resume_disconnect() for each one. This
is what the iwlmvm driver does.

Unfortunately, this causes a locking dependency from mac80211's
iflist_mtx to the key_mtx. This is problematic as the former is
intentionally never held while calling any driver operation to
allow drivers to iterate with their own locks held. The key_mtx
is held while installing a key into the driver though, so this
new lock dependency means drivers implementing the logic above
can no longer hold their own lock while iterating.

To fix this, add a new ieee80211_iterate_active_interfaces_rtnl()
function that iterates while the RTNL is already held. This is
true during suspend/resume, so that then the locking dependency
isn't introduced.

While at it, also refactor the various interface iterators and
keep only a single implementation called by the various cases.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 19 ++++++++++++++
 net/mac80211/util.c    | 71 ++++++++++++++++++++++++--------------------------
 2 files changed, 53 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index cc6035f1a2f1..3411c59b636b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3919,6 +3919,25 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw,
 						    struct ieee80211_vif *vif),
 						void *data);
 
+/**
+ * ieee80211_iterate_active_interfaces_rtnl - iterate active interfaces
+ *
+ * This function iterates over the interfaces associated with a given
+ * hardware that are currently active and calls the callback for them.
+ * This version can only be used while holding the RTNL.
+ *
+ * @hw: the hardware struct of which the interfaces should be iterated over
+ * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags
+ * @iterator: the iterator function to call, cannot sleep
+ * @data: first argument of the iterator function
+ */
+void ieee80211_iterate_active_interfaces_rtnl(struct ieee80211_hw *hw,
+					      u32 iter_flags,
+					      void (*iterator)(void *data,
+						u8 *mac,
+						struct ieee80211_vif *vif),
+					      void *data);
+
 /**
  * ieee80211_queue_work - add work onto the mac80211 workqueue
  *
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index e1b34a18b243..75a16853fb45 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -567,18 +567,15 @@ void ieee80211_flush_queues(struct ieee80211_local *local,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH);
 }
 
-void ieee80211_iterate_active_interfaces(
-	struct ieee80211_hw *hw, u32 iter_flags,
-	void (*iterator)(void *data, u8 *mac,
-			 struct ieee80211_vif *vif),
-	void *data)
+static void __iterate_active_interfaces(struct ieee80211_local *local,
+					u32 iter_flags,
+					void (*iterator)(void *data, u8 *mac,
+						struct ieee80211_vif *vif),
+					void *data)
 {
-	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_sub_if_data *sdata;
 
-	mutex_lock(&local->iflist_mtx);
-
-	list_for_each_entry(sdata, &local->interfaces, list) {
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		switch (sdata->vif.type) {
 		case NL80211_IFTYPE_MONITOR:
 			if (!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))
@@ -597,13 +594,25 @@ void ieee80211_iterate_active_interfaces(
 				 &sdata->vif);
 	}
 
-	sdata = rcu_dereference_protected(local->monitor_sdata,
-					  lockdep_is_held(&local->iflist_mtx));
+	sdata = rcu_dereference_check(local->monitor_sdata,
+				      lockdep_is_held(&local->iflist_mtx) ||
+				      lockdep_rtnl_is_held());
 	if (sdata &&
 	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL ||
 	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 		iterator(data, sdata->vif.addr, &sdata->vif);
+}
 
+void ieee80211_iterate_active_interfaces(
+	struct ieee80211_hw *hw, u32 iter_flags,
+	void (*iterator)(void *data, u8 *mac,
+			 struct ieee80211_vif *vif),
+	void *data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	mutex_lock(&local->iflist_mtx);
+	__iterate_active_interfaces(local, iter_flags, iterator, data);
 	mutex_unlock(&local->iflist_mtx);
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces);
@@ -615,38 +624,26 @@ void ieee80211_iterate_active_interfaces_atomic(
 	void *data)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_sub_if_data *sdata;
 
 	rcu_read_lock();
+	__iterate_active_interfaces(local, iter_flags, iterator, data);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic);
 
-	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
-		switch (sdata->vif.type) {
-		case NL80211_IFTYPE_MONITOR:
-			if (!(sdata->u.mntr_flags & MONITOR_FLAG_ACTIVE))
-				continue;
-			break;
-		case NL80211_IFTYPE_AP_VLAN:
-			continue;
-		default:
-			break;
-		}
-		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
-		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
-			continue;
-		if (ieee80211_sdata_running(sdata))
-			iterator(data, sdata->vif.addr,
-				 &sdata->vif);
-	}
+void ieee80211_iterate_active_interfaces_rtnl(
+	struct ieee80211_hw *hw, u32 iter_flags,
+	void (*iterator)(void *data, u8 *mac,
+			 struct ieee80211_vif *vif),
+	void *data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
 
-	sdata = rcu_dereference(local->monitor_sdata);
-	if (sdata &&
-	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL ||
-	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
-		iterator(data, sdata->vif.addr, &sdata->vif);
+	ASSERT_RTNL();
 
-	rcu_read_unlock();
+	__iterate_active_interfaces(local, iter_flags, iterator, data);
 }
-EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic);
+EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_rtnl);
 
 /*
  * Nothing should have been stuffed into the workqueue during
-- 
cgit 


From 774f073461dbee0decee7524d9b930a98a3dc30c Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <simon.wunderlich@s2003.tu-chemnitz.de>
Date: Wed, 28 Aug 2013 13:41:28 +0200
Subject: cfg80211: export cfg80211_chandef_dfs_required

It will be used later by the IBSS CSA implementation of mac80211.

Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 9 +++++++++
 net/wireless/chan.c    | 1 +
 net/wireless/core.h    | 9 ---------
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cb710913d5c8..45f6bf591104 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -436,6 +436,15 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 			     const struct cfg80211_chan_def *chandef,
 			     u32 prohibited_flags);
 
+/**
+ * cfg80211_chandef_dfs_required - checks if radar detection is required
+ * @wiphy: the wiphy to validate against
+ * @chandef: the channel definition to check
+ * Return: 1 if radar detection is required, 0 if it is not, < 0 on error
+ */
+int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
+				  const struct cfg80211_chan_def *chandef);
+
 /**
  * ieee80211_chandef_rate_flags - returns rate flags for a channel
  *
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 50f6195c8b70..16f3c3a7b2c1 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -328,6 +328,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 	return cfg80211_get_chans_dfs_required(wiphy, chandef->center_freq2,
 					       width);
 }
+EXPORT_SYMBOL(cfg80211_chandef_dfs_required);
 
 static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy,
 					u32 center_freq, u32 bandwidth,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 9ad43c619c54..b43efac4efca 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -382,15 +382,6 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 enum cfg80211_chan_mode chanmode,
 				 u8 radar_detect);
 
-/**
- * cfg80211_chandef_dfs_required - checks if radar detection is required
- * @wiphy: the wiphy to validate against
- * @chandef: the channel definition to check
- * Return: 1 if radar detection is required, 0 if it is not, < 0 on error
- */
-int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
-				  const struct cfg80211_chan_def *c);
-
 void cfg80211_set_dfs_state(struct wiphy *wiphy,
 			    const struct cfg80211_chan_def *chandef,
 			    enum nl80211_dfs_state dfs_state);
-- 
cgit 


From ad93220de7da1f5bd8f9e4be1f1eeefba5eed0ad Mon Sep 17 00:00:00 2001
From: Dong Aisheng <b29396@freescale.com>
Date: Fri, 13 Sep 2013 19:11:35 +0800
Subject: mmc: sdhci-esdhc-imx: change pinctrl state according to uhs mode

Without proper pinctrl state, the card may not be able to work
on high speed stablely. e.g. SDR104.

This patch add pinctrl state switch code according to different
uhs mode include 100mhz sate, 200mhz sate and normal state
(50Mhz and below).

Signed-off-by: Dong Aisheng <b29396@freescale.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/host/sdhci-esdhc-imx.c          | 96 ++++++++++++++++++++++++++++-
 include/linux/platform_data/mmc-esdhc-imx.h |  4 ++
 2 files changed, 99 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index f906c206901d..ed00d6ddd5fd 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -53,6 +53,10 @@
 
 #define ESDHC_TUNING_BLOCK_PATTERN_LEN	64
 
+/* pinctrl state */
+#define ESDHC_PINCTRL_STATE_100MHZ	"state_100mhz"
+#define ESDHC_PINCTRL_STATE_200MHZ	"state_200mhz"
+
 /*
  * Our interpretation of the SDHCI_HOST_CONTROL register
  */
@@ -94,6 +98,9 @@ struct pltfm_imx_data {
 	u32 scratchpad;
 	enum imx_esdhc_type devtype;
 	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_default;
+	struct pinctrl_state *pins_100mhz;
+	struct pinctrl_state *pins_200mhz;
 	struct esdhc_platform_data boarddata;
 	struct clk *clk_ipg;
 	struct clk *clk_ahb;
@@ -693,6 +700,62 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	return ret;
 }
 
+static int esdhc_change_pinstate(struct sdhci_host *host,
+						unsigned int uhs)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+	struct pinctrl_state *pinctrl;
+
+	dev_dbg(mmc_dev(host->mmc), "change pinctrl state for uhs %d\n", uhs);
+
+	if (IS_ERR(imx_data->pinctrl) ||
+		IS_ERR(imx_data->pins_default) ||
+		IS_ERR(imx_data->pins_100mhz) ||
+		IS_ERR(imx_data->pins_200mhz))
+		return -EINVAL;
+
+	switch (uhs) {
+	case MMC_TIMING_UHS_SDR50:
+		pinctrl = imx_data->pins_100mhz;
+		break;
+	case MMC_TIMING_UHS_SDR104:
+		pinctrl = imx_data->pins_200mhz;
+		break;
+	default:
+		/* back to default state for other legacy timing */
+		pinctrl = imx_data->pins_default;
+	}
+
+	return pinctrl_select_state(imx_data->pinctrl, pinctrl);
+}
+
+static int esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+
+	switch (uhs) {
+	case MMC_TIMING_UHS_SDR12:
+		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR12;
+		break;
+	case MMC_TIMING_UHS_SDR25:
+		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR25;
+		break;
+	case MMC_TIMING_UHS_SDR50:
+		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR50;
+		break;
+	case MMC_TIMING_UHS_SDR104:
+		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR104;
+		break;
+	case MMC_TIMING_UHS_DDR50:
+		imx_data->uhs_mode = SDHCI_CTRL_UHS_DDR50;
+		break;
+	}
+
+	return esdhc_change_pinstate(host, uhs);
+}
+
 static const struct sdhci_ops sdhci_esdhc_ops = {
 	.read_l = esdhc_readl_le,
 	.read_w = esdhc_readw_le,
@@ -704,6 +767,7 @@ static const struct sdhci_ops sdhci_esdhc_ops = {
 	.get_min_clock = esdhc_pltfm_get_min_clock,
 	.get_ro = esdhc_pltfm_get_ro,
 	.platform_bus_width = esdhc_pltfm_bus_width,
+	.set_uhs_signaling = esdhc_set_uhs_signaling,
 	.platform_execute_tuning = esdhc_executing_tuning,
 };
 
@@ -746,6 +810,11 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 
 	of_property_read_u32(np, "max-frequency", &boarddata->f_max);
 
+	if (of_find_property(np, "no-1-8-v", NULL))
+		boarddata->support_vsel = false;
+	else
+		boarddata->support_vsel = true;
+
 	return 0;
 }
 #else
@@ -808,12 +877,20 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	clk_prepare_enable(imx_data->clk_ipg);
 	clk_prepare_enable(imx_data->clk_ahb);
 
-	imx_data->pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
+	imx_data->pinctrl = devm_pinctrl_get(&pdev->dev);
 	if (IS_ERR(imx_data->pinctrl)) {
 		err = PTR_ERR(imx_data->pinctrl);
 		goto disable_clk;
 	}
 
+	imx_data->pins_default = pinctrl_lookup_state(imx_data->pinctrl,
+						PINCTRL_STATE_DEFAULT);
+	if (IS_ERR(imx_data->pins_default)) {
+		err = PTR_ERR(imx_data->pins_default);
+		dev_err(mmc_dev(host->mmc), "could not get default state\n");
+		goto disable_clk;
+	}
+
 	host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
 
 	if (is_imx25_esdhc(imx_data) || is_imx35_esdhc(imx_data))
@@ -890,6 +967,23 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		break;
 	}
 
+	/* sdr50 and sdr104 needs work on 1.8v signal voltage */
+	if ((boarddata->support_vsel) && is_imx6q_usdhc(imx_data)) {
+		imx_data->pins_100mhz = pinctrl_lookup_state(imx_data->pinctrl,
+						ESDHC_PINCTRL_STATE_100MHZ);
+		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
+						ESDHC_PINCTRL_STATE_200MHZ);
+		if (IS_ERR(imx_data->pins_100mhz) ||
+				IS_ERR(imx_data->pins_200mhz)) {
+			dev_warn(mmc_dev(host->mmc),
+				"could not get ultra high speed state, work on normal mode\n");
+			/* fall back to not support uhs by specify no 1.8v quirk */
+			host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+		}
+	} else {
+		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+	}
+
 	err = sdhci_add_host(host);
 	if (err)
 		goto disable_clk;
diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h
index d44912d81578..a0f5a8f9b3bc 100644
--- a/include/linux/platform_data/mmc-esdhc-imx.h
+++ b/include/linux/platform_data/mmc-esdhc-imx.h
@@ -10,6 +10,8 @@
 #ifndef __ASM_ARCH_IMX_ESDHC_H
 #define __ASM_ARCH_IMX_ESDHC_H
 
+#include <linux/types.h>
+
 enum wp_types {
 	ESDHC_WP_NONE,		/* no WP, neither controller nor gpio */
 	ESDHC_WP_CONTROLLER,	/* mmc controller internal WP */
@@ -32,6 +34,7 @@ enum cd_types {
  * @cd_gpio:	gpio for card_detect interrupt
  * @wp_type:	type of write_protect method (see wp_types enum above)
  * @cd_type:	type of card_detect method (see cd_types enum above)
+ * @support_vsel:  indicate it supports 1.8v switching
  */
 
 struct esdhc_platform_data {
@@ -41,5 +44,6 @@ struct esdhc_platform_data {
 	enum cd_types cd_type;
 	int max_bus_width;
 	unsigned int f_max;
+	bool support_vsel;
 };
 #endif /* __ASM_ARCH_IMX_ESDHC_H */
-- 
cgit 


From 03f3a9107f5e848a42f25e3ab133db9f3b6546c7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:49 -0700
Subject: hv: use dev_groups for device attributes

This patch is the first in a series that moves the hv bus code to use the
dev_groups field instead of dev_attrs, as dev_attrs is going away in future
kernel releases.

It moves the id sysfs file to the dev_groups structure, and creates the needed
show/store functions, instead of relying on one "universal" function for this.
By doing this, it removes the need for this to be in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  1 -
 drivers/hv/vmbus_drv.c | 23 ++++++++++++++++++-----
 include/linux/hyperv.h |  1 -
 3 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 6de6c98ce6eb..b58a1785d038 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -69,7 +69,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_group = (u8)channel->offermsg.monitorid / 32;
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
-	debuginfo->relid = channel->offermsg.child_relid;
 	debuginfo->state = channel->state;
 	memcpy(&debuginfo->interfacetype,
 	       &channel->offermsg.offer.if_type, sizeof(uuid_le));
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index f9fe46f52cfa..5c21b22860af 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,7 +47,6 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	u32 chn_id;
 	u32 chn_state;
 	uuid_le chn_type;
 	uuid_le chn_instance;
@@ -83,7 +82,6 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	info->chn_id = debug_info.relid;
 	info->chn_state = debug_info.state;
 	memcpy(&info->chn_type, &debug_info.interfacetype,
 	       sizeof(uuid_le));
@@ -156,8 +154,6 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 		ret = sprintf(buf, "vmbus:%s\n", alias_name);
 	} else if (!strcmp(dev_attr->attr.name, "state")) {
 		ret = sprintf(buf, "%d\n", device_info->chn_state);
-	} else if (!strcmp(dev_attr->attr.name, "id")) {
-		ret = sprintf(buf, "%d\n", device_info->chn_id);
 	} else if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
 		ret = sprintf(buf, "%d\n", device_info->outbound.int_mask);
 	} else if (!strcmp(dev_attr->attr.name, "out_read_index")) {
@@ -204,9 +200,25 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	return ret;
 }
 
+static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
+		       char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid);
+}
+static DEVICE_ATTR_RO(id);
+
+static struct attribute *vmbus_attrs[] = {
+	&dev_attr_id.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(vmbus);
+
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(state, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(class_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(device_id, S_IRUGO, vmbus_show_device_attr, NULL),
@@ -384,6 +396,7 @@ static struct bus_type  hv_bus = {
 	.probe =		vmbus_probe,
 	.uevent =		vmbus_uevent,
 	.dev_attrs =	vmbus_device_attrs,
+	.dev_groups =		vmbus_groups,
 };
 
 static const char *driver_name = "hyperv";
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index a3b8b2e2d244..45e9b65e6ab6 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,7 +900,6 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	u32 relid;
 	enum vmbus_channel_state state;
 	uuid_le interfacetype;
 	uuid_le interface_instance;
-- 
cgit 


From a8fb5f3d582d3b4997d9449ceb82a0223d169486 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:50 -0700
Subject: hv: move "state" bus attribute to dev_groups

This moves the "state" bus attribute to the dev_groups structure,
removing the need for it to be in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  1 -
 drivers/hv/vmbus_drv.c | 17 ++++++++++++-----
 include/linux/hyperv.h |  1 -
 3 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index b58a1785d038..64f19f226c4e 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -69,7 +69,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_group = (u8)channel->offermsg.monitorid / 32;
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
-	debuginfo->state = channel->state;
 	memcpy(&debuginfo->interfacetype,
 	       &channel->offermsg.offer.if_type, sizeof(uuid_le));
 	memcpy(&debuginfo->interface_instance,
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 5c21b22860af..1e5bc9c49c63 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,7 +47,6 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	u32 chn_state;
 	uuid_le chn_type;
 	uuid_le chn_instance;
 
@@ -82,7 +81,6 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	info->chn_state = debug_info.state;
 	memcpy(&info->chn_type, &debug_info.interfacetype,
 	       sizeof(uuid_le));
 	memcpy(&info->chn_instance, &debug_info.interface_instance,
@@ -152,8 +150,6 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	} else if (!strcmp(dev_attr->attr.name, "modalias")) {
 		print_alias_name(hv_dev, alias_name);
 		ret = sprintf(buf, "vmbus:%s\n", alias_name);
-	} else if (!strcmp(dev_attr->attr.name, "state")) {
-		ret = sprintf(buf, "%d\n", device_info->chn_state);
 	} else if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
 		ret = sprintf(buf, "%d\n", device_info->outbound.int_mask);
 	} else if (!strcmp(dev_attr->attr.name, "out_read_index")) {
@@ -211,15 +207,26 @@ static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
 }
 static DEVICE_ATTR_RO(id);
 
+static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr,
+			  char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n", hv_dev->channel->state);
+}
+static DEVICE_ATTR_RO(state);
+
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
+	&dev_attr_state.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(state, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(class_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(device_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(monitor_id, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 45e9b65e6ab6..b350a8cfcff6 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,7 +900,6 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	enum vmbus_channel_state state;
 	uuid_le interfacetype;
 	uuid_le interface_instance;
 	u32 monitorid;
-- 
cgit 


From 5ffd00e241ea30fdd907d56419170a1e1338664c Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:51 -0700
Subject: hv: move "monitor_id" bus attribute to dev_groups

This moves the "state" bus attribute to the dev_groups structure,
removing the need for it to be in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  2 --
 drivers/hv/vmbus_drv.c | 18 ++++++++++++------
 include/linux/hyperv.h |  1 -
 3 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 64f19f226c4e..f26a5d252547 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -77,8 +77,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 
 	monitorpage = (struct hv_monitor_page *)vmbus_connection.monitor_pages;
 
-	debuginfo->monitorid = channel->offermsg.monitorid;
-
 	debuginfo->servermonitor_pending =
 			monitorpage->trigger_group[monitor_group].pending;
 	debuginfo->servermonitor_latency =
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 1e5bc9c49c63..2114ecb83c93 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -50,7 +50,6 @@ struct hv_device_info {
 	uuid_le chn_type;
 	uuid_le chn_instance;
 
-	u32 monitor_id;
 	u32 server_monitor_pending;
 	u32 server_monitor_latency;
 	u32 server_monitor_conn_id;
@@ -86,8 +85,6 @@ static void get_channel_info(struct hv_device *device,
 	memcpy(&info->chn_instance, &debug_info.interface_instance,
 	       sizeof(uuid_le));
 
-	info->monitor_id = debug_info.monitorid;
-
 	info->server_monitor_pending = debug_info.servermonitor_pending;
 	info->server_monitor_latency = debug_info.servermonitor_latency;
 	info->server_monitor_conn_id = debug_info.servermonitor_connectionid;
@@ -174,8 +171,6 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	} else if (!strcmp(dev_attr->attr.name, "in_write_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->inbound.bytes_avail_towrite);
-	} else if (!strcmp(dev_attr->attr.name, "monitor_id")) {
-		ret = sprintf(buf, "%d\n", device_info->monitor_id);
 	} else if (!strcmp(dev_attr->attr.name, "server_monitor_pending")) {
 		ret = sprintf(buf, "%d\n", device_info->server_monitor_pending);
 	} else if (!strcmp(dev_attr->attr.name, "server_monitor_latency")) {
@@ -218,9 +213,21 @@ static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr,
 }
 static DEVICE_ATTR_RO(state);
 
+static ssize_t monitor_id_show(struct device *dev,
+			       struct device_attribute *dev_attr, char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid);
+}
+static DEVICE_ATTR_RO(monitor_id);
+
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
 	&dev_attr_state.attr,
+	&dev_attr_monitor_id.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(vmbus);
@@ -229,7 +236,6 @@ ATTRIBUTE_GROUPS(vmbus);
 static struct device_attribute vmbus_device_attrs[] = {
 	__ATTR(class_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(device_id, S_IRUGO, vmbus_show_device_attr, NULL),
-	__ATTR(monitor_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(modalias, S_IRUGO, vmbus_show_device_attr, NULL),
 
 	__ATTR(server_monitor_pending, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index b350a8cfcff6..888a8e533d61 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -902,7 +902,6 @@ enum vmbus_channel_state {
 struct vmbus_channel_debug_info {
 	uuid_le interfacetype;
 	uuid_le interface_instance;
-	u32 monitorid;
 	u32 servermonitor_pending;
 	u32 servermonitor_latency;
 	u32 servermonitor_connectionid;
-- 
cgit 


From 68234c049cc1637a8898ebb3743c8587560929b7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:53 -0700
Subject: hv: move "class_id" bus attribute to dev_groups

This moves the "class_id" bus attribute to the dev_groups structure,
removing the need for it to be in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  2 --
 drivers/hv/vmbus_drv.c | 22 +++++++++++++++-------
 include/linux/hyperv.h |  1 -
 3 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index f26a5d252547..df9499c1ef32 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -69,8 +69,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_group = (u8)channel->offermsg.monitorid / 32;
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
-	memcpy(&debuginfo->interfacetype,
-	       &channel->offermsg.offer.if_type, sizeof(uuid_le));
 	memcpy(&debuginfo->interface_instance,
 	       &channel->offermsg.offer.if_instance,
 	       sizeof(uuid_le));
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index e3f4370036ab..48258ae3467d 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,7 +47,6 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	uuid_le chn_type;
 	uuid_le chn_instance;
 
 	u32 server_monitor_pending;
@@ -80,8 +79,6 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	memcpy(&info->chn_type, &debug_info.interfacetype,
-	       sizeof(uuid_le));
 	memcpy(&info->chn_instance, &debug_info.interface_instance,
 	       sizeof(uuid_le));
 
@@ -139,9 +136,7 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 
 	get_channel_info(hv_dev, device_info);
 
-	if (!strcmp(dev_attr->attr.name, "class_id")) {
-		ret = sprintf(buf, "{%pUl}\n", device_info->chn_type.b);
-	} else if (!strcmp(dev_attr->attr.name, "device_id")) {
+	if (!strcmp(dev_attr->attr.name, "device_id")) {
 		ret = sprintf(buf, "{%pUl}\n", device_info->chn_instance.b);
 	} else if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
 		ret = sprintf(buf, "%d\n", device_info->outbound.int_mask);
@@ -220,6 +215,18 @@ static ssize_t monitor_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(monitor_id);
 
+static ssize_t class_id_show(struct device *dev,
+			       struct device_attribute *dev_attr, char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "{%pUl}\n",
+		       hv_dev->channel->offermsg.offer.if_type.b);
+}
+static DEVICE_ATTR_RO(class_id);
+
 static ssize_t modalias_show(struct device *dev,
 			     struct device_attribute *dev_attr, char *buf)
 {
@@ -231,10 +238,12 @@ static ssize_t modalias_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(modalias);
 
+
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
 	&dev_attr_state.attr,
 	&dev_attr_monitor_id.attr,
+	&dev_attr_class_id.attr,
 	&dev_attr_modalias.attr,
 	NULL,
 };
@@ -242,7 +251,6 @@ ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(class_id, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(device_id, S_IRUGO, vmbus_show_device_attr, NULL),
 
 	__ATTR(server_monitor_pending, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 888a8e533d61..8ccf6f686272 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,7 +900,6 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	uuid_le interfacetype;
 	uuid_le interface_instance;
 	u32 servermonitor_pending;
 	u32 servermonitor_latency;
-- 
cgit 


From 7c55e1d0e64cf5acd8cf4a25927e2c7c322063aa Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:54 -0700
Subject: hv: move "device_id" bus attribute to dev_groups

This moves the "device_id" bus attribute to the dev_groups structure,
removing the need for it to be in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  4 ----
 drivers/hv/vmbus_drv.c | 24 ++++++++++++++----------
 include/linux/hyperv.h |  1 -
 3 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index df9499c1ef32..dde30b48c56c 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -69,10 +69,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_group = (u8)channel->offermsg.monitorid / 32;
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
-	memcpy(&debuginfo->interface_instance,
-	       &channel->offermsg.offer.if_instance,
-	       sizeof(uuid_le));
-
 	monitorpage = (struct hv_monitor_page *)vmbus_connection.monitor_pages;
 
 	debuginfo->servermonitor_pending =
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 48258ae3467d..944dc4b0b54d 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,8 +47,6 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	uuid_le chn_instance;
-
 	u32 server_monitor_pending;
 	u32 server_monitor_latency;
 	u32 server_monitor_conn_id;
@@ -79,9 +77,6 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	memcpy(&info->chn_instance, &debug_info.interface_instance,
-	       sizeof(uuid_le));
-
 	info->server_monitor_pending = debug_info.servermonitor_pending;
 	info->server_monitor_latency = debug_info.servermonitor_latency;
 	info->server_monitor_conn_id = debug_info.servermonitor_connectionid;
@@ -136,9 +131,7 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 
 	get_channel_info(hv_dev, device_info);
 
-	if (!strcmp(dev_attr->attr.name, "device_id")) {
-		ret = sprintf(buf, "{%pUl}\n", device_info->chn_instance.b);
-	} else if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
+	if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
 		ret = sprintf(buf, "%d\n", device_info->outbound.int_mask);
 	} else if (!strcmp(dev_attr->attr.name, "out_read_index")) {
 		ret = sprintf(buf, "%d\n", device_info->outbound.read_idx);
@@ -227,6 +220,18 @@ static ssize_t class_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(class_id);
 
+static ssize_t device_id_show(struct device *dev,
+			      struct device_attribute *dev_attr, char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "{%pUl}\n",
+		       hv_dev->channel->offermsg.offer.if_instance.b);
+}
+static DEVICE_ATTR_RO(device_id);
+
 static ssize_t modalias_show(struct device *dev,
 			     struct device_attribute *dev_attr, char *buf)
 {
@@ -244,6 +249,7 @@ static struct attribute *vmbus_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_monitor_id.attr,
 	&dev_attr_class_id.attr,
+	&dev_attr_device_id.attr,
 	&dev_attr_modalias.attr,
 	NULL,
 };
@@ -251,8 +257,6 @@ ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(device_id, S_IRUGO, vmbus_show_device_attr, NULL),
-
 	__ATTR(server_monitor_pending, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(server_monitor_latency, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(server_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 8ccf6f686272..687c01b85037 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,7 +900,6 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	uuid_le interface_instance;
 	u32 servermonitor_pending;
 	u32 servermonitor_latency;
 	u32 servermonitor_connectionid;
-- 
cgit 


From 76c52bbe5e5ffc6812dcd49729c09f5a207b4a9a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:56 -0700
Subject: hv: move "client/server_monitor_pending" bus attributes to dev_groups

This moves the "client_monitor_pending" and "server_monitor_pending" bus
attributes to the dev_groups structure, removing the need for it to be
in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  4 ----
 drivers/hv/vmbus_drv.c | 56 +++++++++++++++++++++++++++++++++++++++++---------
 include/linux/hyperv.h |  2 --
 3 files changed, 46 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 04bf06560085..d600360ee788 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -70,8 +70,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
 	monitorpage = vmbus_connection.monitor_pages[0];
-	debuginfo->servermonitor_pending =
-			monitorpage->trigger_group[monitor_group].pending;
 	debuginfo->servermonitor_latency =
 			monitorpage->latency[monitor_group][monitor_offset];
 	debuginfo->servermonitor_connectionid =
@@ -79,8 +77,6 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 					[monitor_offset].connectionid.u.id;
 
 	monitorpage = vmbus_connection.monitor_pages[1];
-	debuginfo->clientmonitor_pending =
-			monitorpage->trigger_group[monitor_group].pending;
 	debuginfo->clientmonitor_latency =
 			monitorpage->latency[monitor_group][monitor_offset];
 	debuginfo->clientmonitor_connectionid =
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 944dc4b0b54d..5a44957b7064 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,10 +47,8 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	u32 server_monitor_pending;
 	u32 server_monitor_latency;
 	u32 server_monitor_conn_id;
-	u32 client_monitor_pending;
 	u32 client_monitor_latency;
 	u32 client_monitor_conn_id;
 
@@ -77,11 +75,9 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	info->server_monitor_pending = debug_info.servermonitor_pending;
 	info->server_monitor_latency = debug_info.servermonitor_latency;
 	info->server_monitor_conn_id = debug_info.servermonitor_connectionid;
 
-	info->client_monitor_pending = debug_info.clientmonitor_pending;
 	info->client_monitor_latency = debug_info.clientmonitor_latency;
 	info->client_monitor_conn_id = debug_info.clientmonitor_connectionid;
 
@@ -155,15 +151,11 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	} else if (!strcmp(dev_attr->attr.name, "in_write_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->inbound.bytes_avail_towrite);
-	} else if (!strcmp(dev_attr->attr.name, "server_monitor_pending")) {
-		ret = sprintf(buf, "%d\n", device_info->server_monitor_pending);
 	} else if (!strcmp(dev_attr->attr.name, "server_monitor_latency")) {
 		ret = sprintf(buf, "%d\n", device_info->server_monitor_latency);
 	} else if (!strcmp(dev_attr->attr.name, "server_monitor_conn_id")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->server_monitor_conn_id);
-	} else if (!strcmp(dev_attr->attr.name, "client_monitor_pending")) {
-		ret = sprintf(buf, "%d\n", device_info->client_monitor_pending);
 	} else if (!strcmp(dev_attr->attr.name, "client_monitor_latency")) {
 		ret = sprintf(buf, "%d\n", device_info->client_monitor_latency);
 	} else if (!strcmp(dev_attr->attr.name, "client_monitor_conn_id")) {
@@ -175,6 +167,23 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	return ret;
 }
 
+static u8 channel_monitor_group(struct vmbus_channel *channel)
+{
+	return (u8)channel->offermsg.monitorid / 32;
+}
+
+static u8 channel_monitor_offset(struct vmbus_channel *channel)
+{
+	return (u8)channel->offermsg.monitorid % 32;
+}
+
+static u32 channel_pending(struct vmbus_channel *channel,
+			   struct hv_monitor_page *monitor_page)
+{
+	u8 monitor_group = channel_monitor_group(channel);
+	return monitor_page->trigger_group[monitor_group].pending;
+}
+
 static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
 		       char *buf)
 {
@@ -243,6 +252,33 @@ static ssize_t modalias_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t server_monitor_pending_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_pending(hv_dev->channel,
+				       vmbus_connection.monitor_pages[1]));
+}
+static DEVICE_ATTR_RO(server_monitor_pending);
+
+static ssize_t client_monitor_pending_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_pending(hv_dev->channel,
+				       vmbus_connection.monitor_pages[1]));
+}
+static DEVICE_ATTR_RO(client_monitor_pending);
 
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
@@ -251,17 +287,17 @@ static struct attribute *vmbus_attrs[] = {
 	&dev_attr_class_id.attr,
 	&dev_attr_device_id.attr,
 	&dev_attr_modalias.attr,
+	&dev_attr_server_monitor_pending.attr,
+	&dev_attr_client_monitor_pending.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(server_monitor_pending, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(server_monitor_latency, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(server_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
 
-	__ATTR(client_monitor_pending, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(client_monitor_latency, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(client_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 687c01b85037..f0a7d27ffb21 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,10 +900,8 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	u32 servermonitor_pending;
 	u32 servermonitor_latency;
 	u32 servermonitor_connectionid;
-	u32 clientmonitor_pending;
 	u32 clientmonitor_latency;
 	u32 clientmonitor_connectionid;
 
-- 
cgit 


From 1cee272b0249c5007391da6cf42903b8f30dbc5a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:57 -0700
Subject: hv: move "client/server_monitor_latency" bus attributes to dev_groups

This moves the "client_monitor_latency" and "server_monitor_latency" bus
attributes to the dev_groups structure, removing the need for it to be
in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   |  4 ----
 drivers/hv/vmbus_drv.c | 48 ++++++++++++++++++++++++++++++++++++++----------
 include/linux/hyperv.h |  2 --
 3 files changed, 38 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index d600360ee788..ff61464f57ca 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -70,15 +70,11 @@ void vmbus_get_debug_info(struct vmbus_channel *channel,
 	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
 
 	monitorpage = vmbus_connection.monitor_pages[0];
-	debuginfo->servermonitor_latency =
-			monitorpage->latency[monitor_group][monitor_offset];
 	debuginfo->servermonitor_connectionid =
 			monitorpage->parameter[monitor_group]
 					[monitor_offset].connectionid.u.id;
 
 	monitorpage = vmbus_connection.monitor_pages[1];
-	debuginfo->clientmonitor_latency =
-			monitorpage->latency[monitor_group][monitor_offset];
 	debuginfo->clientmonitor_connectionid =
 			monitorpage->parameter[monitor_group]
 					[monitor_offset].connectionid.u.id;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 5a44957b7064..461b989835b6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,9 +47,7 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	u32 server_monitor_latency;
 	u32 server_monitor_conn_id;
-	u32 client_monitor_latency;
 	u32 client_monitor_conn_id;
 
 	struct hv_dev_port_info inbound;
@@ -75,10 +73,8 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	info->server_monitor_latency = debug_info.servermonitor_latency;
 	info->server_monitor_conn_id = debug_info.servermonitor_connectionid;
 
-	info->client_monitor_latency = debug_info.clientmonitor_latency;
 	info->client_monitor_conn_id = debug_info.clientmonitor_connectionid;
 
 	info->inbound.int_mask = debug_info.inbound.current_interrupt_mask;
@@ -151,13 +147,9 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	} else if (!strcmp(dev_attr->attr.name, "in_write_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->inbound.bytes_avail_towrite);
-	} else if (!strcmp(dev_attr->attr.name, "server_monitor_latency")) {
-		ret = sprintf(buf, "%d\n", device_info->server_monitor_latency);
 	} else if (!strcmp(dev_attr->attr.name, "server_monitor_conn_id")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->server_monitor_conn_id);
-	} else if (!strcmp(dev_attr->attr.name, "client_monitor_latency")) {
-		ret = sprintf(buf, "%d\n", device_info->client_monitor_latency);
 	} else if (!strcmp(dev_attr->attr.name, "client_monitor_conn_id")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->client_monitor_conn_id);
@@ -184,6 +176,14 @@ static u32 channel_pending(struct vmbus_channel *channel,
 	return monitor_page->trigger_group[monitor_group].pending;
 }
 
+static u32 channel_latency(struct vmbus_channel *channel,
+			   struct hv_monitor_page *monitor_page)
+{
+	u8 monitor_group = channel_monitor_group(channel);
+	u8 monitor_offset = channel_monitor_offset(channel);
+	return monitor_page->latency[monitor_group][monitor_offset];
+}
+
 static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
 		       char *buf)
 {
@@ -280,6 +280,34 @@ static ssize_t client_monitor_pending_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(client_monitor_pending);
 
+static ssize_t server_monitor_latency_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_latency(hv_dev->channel,
+				       vmbus_connection.monitor_pages[0]));
+}
+static DEVICE_ATTR_RO(server_monitor_latency);
+
+static ssize_t client_monitor_latency_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_latency(hv_dev->channel,
+				       vmbus_connection.monitor_pages[1]));
+}
+static DEVICE_ATTR_RO(client_monitor_latency);
+
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
 	&dev_attr_state.attr,
@@ -289,16 +317,16 @@ static struct attribute *vmbus_attrs[] = {
 	&dev_attr_modalias.attr,
 	&dev_attr_server_monitor_pending.attr,
 	&dev_attr_client_monitor_pending.attr,
+	&dev_attr_server_monitor_latency.attr,
+	&dev_attr_client_monitor_latency.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(server_monitor_latency, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(server_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
 
-	__ATTR(client_monitor_latency, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(client_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
 
 	__ATTR(out_intr_mask, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index f0a7d27ffb21..ec1e5033bb99 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,9 +900,7 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	u32 servermonitor_latency;
 	u32 servermonitor_connectionid;
-	u32 clientmonitor_latency;
 	u32 clientmonitor_connectionid;
 
 	struct hv_ring_buffer_debug_info inbound;
-- 
cgit 


From 4947c7453b184bc33a0056cf95af61c3cad11ef6 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:58 -0700
Subject: hv: move "client/server_monitor_conn_id" bus attributes to dev_groups

This moves the "client_monitor_conn_id" and "server_monitor_conn_id" bus
attributes to the dev_groups structure, removing the need for it to be
in a temporary structure.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   | 14 -------------
 drivers/hv/vmbus_drv.c | 55 ++++++++++++++++++++++++++++++++++----------------
 include/linux/hyperv.h |  3 ---
 3 files changed, 38 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index ff61464f57ca..75c26da3e011 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -65,20 +65,6 @@ static void vmbus_setevent(struct vmbus_channel *channel)
 void vmbus_get_debug_info(struct vmbus_channel *channel,
 			      struct vmbus_channel_debug_info *debuginfo)
 {
-	struct hv_monitor_page *monitorpage;
-	u8 monitor_group = (u8)channel->offermsg.monitorid / 32;
-	u8 monitor_offset = (u8)channel->offermsg.monitorid % 32;
-
-	monitorpage = vmbus_connection.monitor_pages[0];
-	debuginfo->servermonitor_connectionid =
-			monitorpage->parameter[monitor_group]
-					[monitor_offset].connectionid.u.id;
-
-	monitorpage = vmbus_connection.monitor_pages[1];
-	debuginfo->clientmonitor_connectionid =
-			monitorpage->parameter[monitor_group]
-					[monitor_offset].connectionid.u.id;
-
 	hv_ringbuffer_get_debuginfo(&channel->inbound, &debuginfo->inbound);
 	hv_ringbuffer_get_debuginfo(&channel->outbound, &debuginfo->outbound);
 }
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 461b989835b6..73cb456e256b 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,9 +47,6 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	u32 server_monitor_conn_id;
-	u32 client_monitor_conn_id;
-
 	struct hv_dev_port_info inbound;
 	struct hv_dev_port_info outbound;
 };
@@ -73,10 +70,6 @@ static void get_channel_info(struct hv_device *device,
 
 	vmbus_get_debug_info(device->channel, &debug_info);
 
-	info->server_monitor_conn_id = debug_info.servermonitor_connectionid;
-
-	info->client_monitor_conn_id = debug_info.clientmonitor_connectionid;
-
 	info->inbound.int_mask = debug_info.inbound.current_interrupt_mask;
 	info->inbound.read_idx = debug_info.inbound.current_read_index;
 	info->inbound.write_idx = debug_info.inbound.current_write_index;
@@ -147,12 +140,6 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	} else if (!strcmp(dev_attr->attr.name, "in_write_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->inbound.bytes_avail_towrite);
-	} else if (!strcmp(dev_attr->attr.name, "server_monitor_conn_id")) {
-		ret = sprintf(buf, "%d\n",
-			       device_info->server_monitor_conn_id);
-	} else if (!strcmp(dev_attr->attr.name, "client_monitor_conn_id")) {
-		ret = sprintf(buf, "%d\n",
-			       device_info->client_monitor_conn_id);
 	}
 
 	kfree(device_info);
@@ -184,6 +171,14 @@ static u32 channel_latency(struct vmbus_channel *channel,
 	return monitor_page->latency[monitor_group][monitor_offset];
 }
 
+static u32 channel_conn_id(struct vmbus_channel *channel,
+			   struct hv_monitor_page *monitor_page)
+{
+	u8 monitor_group = channel_monitor_group(channel);
+	u8 monitor_offset = channel_monitor_offset(channel);
+	return monitor_page->parameter[monitor_group][monitor_offset].connectionid.u.id;
+}
+
 static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr,
 		       char *buf)
 {
@@ -308,6 +303,34 @@ static ssize_t client_monitor_latency_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(client_monitor_latency);
 
+static ssize_t server_monitor_conn_id_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_conn_id(hv_dev->channel,
+				       vmbus_connection.monitor_pages[0]));
+}
+static DEVICE_ATTR_RO(server_monitor_conn_id);
+
+static ssize_t client_monitor_conn_id_show(struct device *dev,
+					   struct device_attribute *dev_attr,
+					   char *buf)
+{
+	struct hv_device *hv_dev = device_to_hv_device(dev);
+
+	if (!hv_dev->channel)
+		return -ENODEV;
+	return sprintf(buf, "%d\n",
+		       channel_conn_id(hv_dev->channel,
+				       vmbus_connection.monitor_pages[1]));
+}
+static DEVICE_ATTR_RO(client_monitor_conn_id);
+
 static struct attribute *vmbus_attrs[] = {
 	&dev_attr_id.attr,
 	&dev_attr_state.attr,
@@ -319,16 +342,14 @@ static struct attribute *vmbus_attrs[] = {
 	&dev_attr_client_monitor_pending.attr,
 	&dev_attr_server_monitor_latency.attr,
 	&dev_attr_client_monitor_latency.attr,
+	&dev_attr_server_monitor_conn_id.attr,
+	&dev_attr_client_monitor_conn_id.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(vmbus);
 
 /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */
 static struct device_attribute vmbus_device_attrs[] = {
-	__ATTR(server_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
-
-	__ATTR(client_monitor_conn_id, S_IRUGO, vmbus_show_device_attr, NULL),
-
 	__ATTR(out_intr_mask, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(out_read_index, S_IRUGO, vmbus_show_device_attr, NULL),
 	__ATTR(out_write_index, S_IRUGO, vmbus_show_device_attr, NULL),
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index ec1e5033bb99..332e80ce9b8a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -900,9 +900,6 @@ enum vmbus_channel_state {
 };
 
 struct vmbus_channel_debug_info {
-	u32 servermonitor_connectionid;
-	u32 clientmonitor_connectionid;
-
 	struct hv_ring_buffer_debug_info inbound;
 	struct hv_ring_buffer_debug_info outbound;
 };
-- 
cgit 


From 2c9be3eacc39948af2341595322c014833699ac5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:32:59 -0700
Subject: hv: delete vmbus_get_debug_info()

It's only used once, only contains 2 function calls, so just make those
calls directly, deleting the function, and the now unneeded structure
entirely.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c   | 10 ----------
 drivers/hv/vmbus_drv.c | 35 ++++++++++++++++-------------------
 include/linux/hyperv.h |  8 --------
 3 files changed, 16 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 75c26da3e011..94d54591b226 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -59,16 +59,6 @@ static void vmbus_setevent(struct vmbus_channel *channel)
 	}
 }
 
-/*
- * vmbus_get_debug_info -Retrieve various channel debug info
- */
-void vmbus_get_debug_info(struct vmbus_channel *channel,
-			      struct vmbus_channel_debug_info *debuginfo)
-{
-	hv_ringbuffer_get_debuginfo(&channel->inbound, &debuginfo->inbound);
-	hv_ringbuffer_get_debuginfo(&channel->outbound, &debuginfo->outbound);
-}
-
 /*
  * vmbus_open - Open the specified channel.
  */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 73cb456e256b..62d9311b0541 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -63,29 +63,26 @@ static int vmbus_exists(void)
 static void get_channel_info(struct hv_device *device,
 			     struct hv_device_info *info)
 {
-	struct vmbus_channel_debug_info debug_info;
+	struct hv_ring_buffer_debug_info inbound;
+	struct hv_ring_buffer_debug_info outbound;
 
 	if (!device->channel)
 		return;
 
-	vmbus_get_debug_info(device->channel, &debug_info);
-
-	info->inbound.int_mask = debug_info.inbound.current_interrupt_mask;
-	info->inbound.read_idx = debug_info.inbound.current_read_index;
-	info->inbound.write_idx = debug_info.inbound.current_write_index;
-	info->inbound.bytes_avail_toread =
-		debug_info.inbound.bytes_avail_toread;
-	info->inbound.bytes_avail_towrite =
-		debug_info.inbound.bytes_avail_towrite;
-
-	info->outbound.int_mask =
-		debug_info.outbound.current_interrupt_mask;
-	info->outbound.read_idx = debug_info.outbound.current_read_index;
-	info->outbound.write_idx = debug_info.outbound.current_write_index;
-	info->outbound.bytes_avail_toread =
-		debug_info.outbound.bytes_avail_toread;
-	info->outbound.bytes_avail_towrite =
-		debug_info.outbound.bytes_avail_towrite;
+	hv_ringbuffer_get_debuginfo(&device->channel->inbound, &inbound);
+	hv_ringbuffer_get_debuginfo(&device->channel->outbound, &outbound);
+
+	info->inbound.int_mask = inbound.current_interrupt_mask;
+	info->inbound.read_idx = inbound.current_read_index;
+	info->inbound.write_idx = inbound.current_write_index;
+	info->inbound.bytes_avail_toread = inbound.bytes_avail_toread;
+	info->inbound.bytes_avail_towrite = inbound.bytes_avail_towrite;
+
+	info->outbound.int_mask = outbound.current_interrupt_mask;
+	info->outbound.read_idx = outbound.current_read_index;
+	info->outbound.write_idx = outbound.current_write_index;
+	info->outbound.bytes_avail_toread = outbound.bytes_avail_toread;
+	info->outbound.bytes_avail_towrite = outbound.bytes_avail_towrite;
 }
 
 #define VMBUS_ALIAS_LEN ((sizeof((struct hv_vmbus_device_id *)0)->guid) * 2)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 332e80ce9b8a..c0e8faf40b35 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -899,11 +899,6 @@ enum vmbus_channel_state {
 	CHANNEL_OPENED_STATE,
 };
 
-struct vmbus_channel_debug_info {
-	struct hv_ring_buffer_debug_info inbound;
-	struct hv_ring_buffer_debug_info outbound;
-};
-
 /*
  * Represents each channel msg on the vmbus connection This is a
  * variable-size data structure depending on the msg type itself
@@ -1169,9 +1164,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel,
 				     u64 *requestid);
 
 
-extern void vmbus_get_debug_info(struct vmbus_channel *channel,
-				     struct vmbus_channel_debug_info *debug);
-
 extern void vmbus_ontimer(unsigned long data);
 
 struct hv_dev_port_info {
-- 
cgit 


From 1fdde16d1f93376ad2a2df769f756572c2e84cbd Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 13 Sep 2013 11:33:00 -0700
Subject: hv: delete struct hv_dev_port_info

It's no longer needed, and the struct hv_ring_buffer_debug_info
structure shouldn't be "global" so move it to the local .h file instead.

Tested-by: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/hyperv_vmbus.h |  7 +++++++
 drivers/hv/vmbus_drv.c    | 35 ++++++++++-------------------------
 include/linux/hyperv.h    | 17 -----------------
 3 files changed, 17 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index d58c22ffb29a..e05517616a06 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -514,6 +514,13 @@ struct hv_context {
 
 extern struct hv_context hv_context;
 
+struct hv_ring_buffer_debug_info {
+	u32 current_interrupt_mask;
+	u32 current_read_index;
+	u32 current_write_index;
+	u32 bytes_avail_toread;
+	u32 bytes_avail_towrite;
+};
 
 /* Hv Interface */
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 62d9311b0541..cf3220e8a3a6 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -47,8 +47,8 @@ static struct completion probe_event;
 static int irq;
 
 struct hv_device_info {
-	struct hv_dev_port_info inbound;
-	struct hv_dev_port_info outbound;
+	struct hv_ring_buffer_debug_info inbound;
+	struct hv_ring_buffer_debug_info outbound;
 };
 
 static int vmbus_exists(void)
@@ -63,26 +63,11 @@ static int vmbus_exists(void)
 static void get_channel_info(struct hv_device *device,
 			     struct hv_device_info *info)
 {
-	struct hv_ring_buffer_debug_info inbound;
-	struct hv_ring_buffer_debug_info outbound;
-
 	if (!device->channel)
 		return;
 
-	hv_ringbuffer_get_debuginfo(&device->channel->inbound, &inbound);
-	hv_ringbuffer_get_debuginfo(&device->channel->outbound, &outbound);
-
-	info->inbound.int_mask = inbound.current_interrupt_mask;
-	info->inbound.read_idx = inbound.current_read_index;
-	info->inbound.write_idx = inbound.current_write_index;
-	info->inbound.bytes_avail_toread = inbound.bytes_avail_toread;
-	info->inbound.bytes_avail_towrite = inbound.bytes_avail_towrite;
-
-	info->outbound.int_mask = outbound.current_interrupt_mask;
-	info->outbound.read_idx = outbound.current_read_index;
-	info->outbound.write_idx = outbound.current_write_index;
-	info->outbound.bytes_avail_toread = outbound.bytes_avail_toread;
-	info->outbound.bytes_avail_towrite = outbound.bytes_avail_towrite;
+	hv_ringbuffer_get_debuginfo(&device->channel->inbound, &info->inbound);
+	hv_ringbuffer_get_debuginfo(&device->channel->outbound, &info->outbound);
 }
 
 #define VMBUS_ALIAS_LEN ((sizeof((struct hv_vmbus_device_id *)0)->guid) * 2)
@@ -114,11 +99,11 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 	get_channel_info(hv_dev, device_info);
 
 	if (!strcmp(dev_attr->attr.name, "out_intr_mask")) {
-		ret = sprintf(buf, "%d\n", device_info->outbound.int_mask);
+		ret = sprintf(buf, "%d\n", device_info->outbound.current_interrupt_mask);
 	} else if (!strcmp(dev_attr->attr.name, "out_read_index")) {
-		ret = sprintf(buf, "%d\n", device_info->outbound.read_idx);
+		ret = sprintf(buf, "%d\n", device_info->outbound.current_read_index);
 	} else if (!strcmp(dev_attr->attr.name, "out_write_index")) {
-		ret = sprintf(buf, "%d\n", device_info->outbound.write_idx);
+		ret = sprintf(buf, "%d\n", device_info->outbound.current_write_index);
 	} else if (!strcmp(dev_attr->attr.name, "out_read_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->outbound.bytes_avail_toread);
@@ -126,11 +111,11 @@ static ssize_t vmbus_show_device_attr(struct device *dev,
 		ret = sprintf(buf, "%d\n",
 			       device_info->outbound.bytes_avail_towrite);
 	} else if (!strcmp(dev_attr->attr.name, "in_intr_mask")) {
-		ret = sprintf(buf, "%d\n", device_info->inbound.int_mask);
+		ret = sprintf(buf, "%d\n", device_info->inbound.current_interrupt_mask);
 	} else if (!strcmp(dev_attr->attr.name, "in_read_index")) {
-		ret = sprintf(buf, "%d\n", device_info->inbound.read_idx);
+		ret = sprintf(buf, "%d\n", device_info->inbound.current_read_index);
 	} else if (!strcmp(dev_attr->attr.name, "in_write_index")) {
-		ret = sprintf(buf, "%d\n", device_info->inbound.write_idx);
+		ret = sprintf(buf, "%d\n", device_info->inbound.current_write_index);
 	} else if (!strcmp(dev_attr->attr.name, "in_read_bytes_avail")) {
 		ret = sprintf(buf, "%d\n",
 			       device_info->inbound.bytes_avail_toread);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c0e8faf40b35..c68ecfe29441 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -429,15 +429,6 @@ struct hv_ring_buffer_info {
 	u32 ring_data_startoffset;
 };
 
-struct hv_ring_buffer_debug_info {
-	u32 current_interrupt_mask;
-	u32 current_read_index;
-	u32 current_write_index;
-	u32 bytes_avail_toread;
-	u32 bytes_avail_towrite;
-};
-
-
 /*
  *
  * hv_get_ringbuffer_availbytes()
@@ -1166,14 +1157,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel,
 
 extern void vmbus_ontimer(unsigned long data);
 
-struct hv_dev_port_info {
-	u32 int_mask;
-	u32 read_idx;
-	u32 write_idx;
-	u32 bytes_avail_toread;
-	u32 bytes_avail_towrite;
-};
-
 /* Base driver object */
 struct hv_driver {
 	const char *name;
-- 
cgit 


From 2f268f129c2d1a05d297fe3ee34d393f862d2b22 Mon Sep 17 00:00:00 2001
From: Veaceslav Falico <vfalico@redhat.com>
Date: Wed, 25 Sep 2013 09:20:07 +0200
Subject: net: add adj_list to save only neighbours

Currently, we distinguish neighbours (first-level linked devices) from
non-neighbours by the neighbour bool in the netdev_adjacent. This could be
quite time-consuming in case we would like to traverse *only* through
neighbours - cause we'd have to traverse through all devices and check for
this flag, and in a (quite common) scenario where we have lots of vlans on
top of bridge, which is on top of a bond - the bonding would have to go
through all those vlans to get its upper neighbour linked devices.

This situation is really unpleasant, cause there are already a lot of cases
when a device with slaves needs to go through them in hot path.

To fix this, introduce a new upper/lower device lists structure -
adj_list, which contains only the neighbours. It works always in
pair with the all_adj_list structure (renamed from upper/lower_dev_list),
i.e. both of them contain the same links, only that all_adj_list contains
also non-neighbour device links. It's really a small change visible,
currently, only for __netdev_adjacent_dev_insert/remove(), and doesn't
change the main linked logic at all.

Also, add some comments a fix a name collision in
netdev_for_each_upper_dev_rcu() and rework the naming by the following
rules:

netdev_(all_)(upper|lower)_*

If "all_" is present, then we work with the whole list of upper/lower
devices, otherwise - only with direct neighbours. Uninline functions - to
get better stack traces.

CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
CC: Cong Wang <amwang@redhat.com>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_alb.c  |   2 +-
 drivers/net/bonding/bond_main.c |  10 +-
 include/linux/netdevice.h       |  28 ++++--
 net/core/dev.c                  | 203 ++++++++++++++++++++--------------------
 4 files changed, 129 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index f428ef574372..8524e33e6754 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1019,7 +1019,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[])
 
 	/* loop through vlans and send one packet for each */
 	rcu_read_lock();
-	netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 		if (upper->priv_flags & IFF_802_1Q_VLAN)
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_id(upper));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 55bbb8b8200c..91c4ab8913b1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2267,7 +2267,7 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
 		return true;
 
 	rcu_read_lock();
-	netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 		if (ip == bond_confirm_addr(upper, 0, ip)) {
 			ret = true;
 			break;
@@ -2342,10 +2342,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		 *
 		 * TODO: QinQ?
 		 */
-		netdev_for_each_upper_dev_rcu(bond->dev, vlan_upper, vlan_iter) {
+		netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper,
+						  vlan_iter) {
 			if (!is_vlan_dev(vlan_upper))
 				continue;
-			netdev_for_each_upper_dev_rcu(vlan_upper, upper, iter) {
+			netdev_for_each_all_upper_dev_rcu(vlan_upper, upper,
+							  iter) {
 				if (upper == rt->dst.dev) {
 					vlan_id = vlan_dev_vlan_id(vlan_upper);
 					rcu_read_unlock();
@@ -2358,7 +2360,7 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 		 * our upper vlans, then just search for any dev that
 		 * matches, and in case it's a vlan - save the id
 		 */
-		netdev_for_each_upper_dev_rcu(bond->dev, upper, iter) {
+		netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 			if (upper == rt->dst.dev) {
 				/* if it's a vlan - get its VID */
 				if (is_vlan_dev(upper))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3de49aca4519..514045c704a8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1143,8 +1143,18 @@ struct net_device {
 	struct list_head	dev_list;
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
-	struct list_head	upper_dev_list; /* List of upper devices */
-	struct list_head	lower_dev_list;
+
+	/* directly linked devices, like slaves for bonding */
+	struct {
+		struct list_head upper;
+		struct list_head lower;
+	} adj_list;
+
+	/* all linked devices, *including* neighbours */
+	struct {
+		struct list_head upper;
+		struct list_head lower;
+	} all_adj_list;
 
 
 	/* currently active device features */
@@ -2813,15 +2823,15 @@ extern int		bpf_jit_enable;
 extern bool netdev_has_upper_dev(struct net_device *dev,
 				 struct net_device *upper_dev);
 extern bool netdev_has_any_upper_dev(struct net_device *dev);
-extern struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
-							struct list_head **iter);
+extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
+							    struct list_head **iter);
 
 /* iterate through upper list, must be called under RCU read lock */
-#define netdev_for_each_upper_dev_rcu(dev, upper, iter) \
-	for (iter = &(dev)->upper_dev_list, \
-	     upper = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
-	     upper; \
-	     upper = netdev_upper_get_next_dev_rcu(dev, &(iter)))
+#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
+	for (iter = &(dev)->all_adj_list.upper, \
+	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
+	     updev; \
+	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
 extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 9be79377a0f3..9a395e03da74 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4373,9 +4373,6 @@ struct netdev_adjacent {
 	/* upper master flag, there can only be one master device per list */
 	bool master;
 
-	/* indicates that this dev is our first-level lower/upper device */
-	bool neighbour;
-
 	/* counter for the number of times this device was added to us */
 	u16 ref_nr;
 
@@ -4385,29 +4382,17 @@ struct netdev_adjacent {
 
 static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
 						 struct net_device *adj_dev,
-						 struct list_head *dev_list)
+						 struct list_head *adj_list)
 {
 	struct netdev_adjacent *adj;
 
-	list_for_each_entry(adj, dev_list, list) {
+	list_for_each_entry(adj, adj_list, list) {
 		if (adj->dev == adj_dev)
 			return adj;
 	}
 	return NULL;
 }
 
-static inline struct netdev_adjacent *__netdev_find_upper(struct net_device *dev,
-							  struct net_device *udev)
-{
-	return __netdev_find_adj(dev, udev, &dev->upper_dev_list);
-}
-
-static inline struct netdev_adjacent *__netdev_find_lower(struct net_device *dev,
-							  struct net_device *ldev)
-{
-	return __netdev_find_adj(dev, ldev, &dev->lower_dev_list);
-}
-
 /**
  * netdev_has_upper_dev - Check if device is linked to an upper device
  * @dev: device
@@ -4422,7 +4407,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
 {
 	ASSERT_RTNL();
 
-	return __netdev_find_upper(dev, upper_dev);
+	return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper);
 }
 EXPORT_SYMBOL(netdev_has_upper_dev);
 
@@ -4437,7 +4422,7 @@ bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
-	return !list_empty(&dev->upper_dev_list);
+	return !list_empty(&dev->all_adj_list.upper);
 }
 EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
@@ -4454,10 +4439,10 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	if (list_empty(&dev->upper_dev_list))
+	if (list_empty(&dev->adj_list.upper))
 		return NULL;
 
-	upper = list_first_entry(&dev->upper_dev_list,
+	upper = list_first_entry(&dev->adj_list.upper,
 				 struct netdev_adjacent, list);
 	if (likely(upper->master))
 		return upper->dev;
@@ -4465,15 +4450,15 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
 
-/* netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+/* netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position
  *
  * Gets the next device from the dev's upper list, starting from iter
  * position. The caller must hold RCU read lock.
  */
-struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
-						 struct list_head **iter)
+struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
+						     struct list_head **iter)
 {
 	struct netdev_adjacent *upper;
 
@@ -4481,14 +4466,14 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
 
 	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
 
-	if (&upper->list == &dev->upper_dev_list)
+	if (&upper->list == &dev->all_adj_list.upper)
 		return NULL;
 
 	*iter = &upper->list;
 
 	return upper->dev;
 }
-EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
 
 /**
  * netdev_master_upper_dev_get_rcu - Get master upper device
@@ -4501,7 +4486,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
 {
 	struct netdev_adjacent *upper;
 
-	upper = list_first_or_null_rcu(&dev->upper_dev_list,
+	upper = list_first_or_null_rcu(&dev->adj_list.upper,
 				       struct netdev_adjacent, list);
 	if (upper && likely(upper->master))
 		return upper->dev;
@@ -4512,14 +4497,13 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
 					struct list_head *dev_list,
-					bool neighbour, bool master)
+					bool master)
 {
 	struct netdev_adjacent *adj;
 
 	adj = __netdev_find_adj(dev, adj_dev, dev_list);
 
 	if (adj) {
-		BUG_ON(neighbour);
 		adj->ref_nr++;
 		return 0;
 	}
@@ -4530,13 +4514,11 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 
 	adj->dev = adj_dev;
 	adj->master = master;
-	adj->neighbour = neighbour;
 	adj->ref_nr = 1;
-
 	dev_hold(adj_dev);
-	pr_debug("dev_hold for %s, because of %s link added from %s to %s\n",
-		 adj_dev->name, dev_list == &dev->upper_dev_list ?
-		 "upper" : "lower", dev->name, adj_dev->name);
+
+	pr_debug("dev_hold for %s, because of link added from %s to %s\n",
+		 adj_dev->name, dev->name, adj_dev->name);
 
 	/* Ensure that master link is always the first item in list. */
 	if (master)
@@ -4547,22 +4529,6 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	return 0;
 }
 
-static inline int __netdev_upper_dev_insert(struct net_device *dev,
-					    struct net_device *udev,
-					    bool master, bool neighbour)
-{
-	return __netdev_adjacent_dev_insert(dev, udev, &dev->upper_dev_list,
-					    neighbour, master);
-}
-
-static inline int __netdev_lower_dev_insert(struct net_device *dev,
-					    struct net_device *ldev,
-					    bool neighbour)
-{
-	return __netdev_adjacent_dev_insert(dev, ldev, &dev->lower_dev_list,
-					    neighbour, false);
-}
-
 void __netdev_adjacent_dev_remove(struct net_device *dev,
 				  struct net_device *adj_dev,
 				  struct list_head *dev_list)
@@ -4571,73 +4537,102 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
 
 	adj = __netdev_find_adj(dev, adj_dev, dev_list);
 
-	if (!adj)
+	if (!adj) {
+		pr_err("tried to remove device %s from %s\n",
+		       dev->name, adj_dev->name);
 		BUG();
+	}
 
 	if (adj->ref_nr > 1) {
+		pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name,
+			 adj->ref_nr-1);
 		adj->ref_nr--;
 		return;
 	}
 
 	list_del_rcu(&adj->list);
-	pr_debug("dev_put for %s, because of %s link removed from %s to %s\n",
-		 adj_dev->name, dev_list == &dev->upper_dev_list ?
-		 "upper" : "lower", dev->name, adj_dev->name);
+	pr_debug("dev_put for %s, because link removed from %s to %s\n",
+		 adj_dev->name, dev->name, adj_dev->name);
 	dev_put(adj_dev);
 	kfree_rcu(adj, rcu);
 }
 
-static inline void __netdev_upper_dev_remove(struct net_device *dev,
-					     struct net_device *udev)
-{
-	return __netdev_adjacent_dev_remove(dev, udev, &dev->upper_dev_list);
-}
-
-static inline void __netdev_lower_dev_remove(struct net_device *dev,
-					     struct net_device *ldev)
-{
-	return __netdev_adjacent_dev_remove(dev, ldev, &dev->lower_dev_list);
-}
-
-int __netdev_adjacent_dev_insert_link(struct net_device *dev,
-				      struct net_device *upper_dev,
-				      bool master, bool neighbour)
+int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+				     struct net_device *upper_dev,
+				     struct list_head *up_list,
+				     struct list_head *down_list,
+				     bool master)
 {
 	int ret;
 
-	ret = __netdev_upper_dev_insert(dev, upper_dev, master, neighbour);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_lower_dev_insert(upper_dev, dev, neighbour);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, false);
 	if (ret) {
-		__netdev_upper_dev_remove(dev, upper_dev);
+		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
 		return ret;
 	}
 
 	return 0;
 }
 
-static inline int __netdev_adjacent_dev_link(struct net_device *dev,
-					     struct net_device *udev)
+int __netdev_adjacent_dev_link(struct net_device *dev,
+			       struct net_device *upper_dev)
 {
-	return __netdev_adjacent_dev_insert_link(dev, udev, false, false);
+	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+						&dev->all_adj_list.upper,
+						&upper_dev->all_adj_list.lower,
+						false);
 }
 
-static inline int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
-						       struct net_device *udev,
-						       bool master)
+void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+					struct net_device *upper_dev,
+					struct list_head *up_list,
+					struct list_head *down_list)
 {
-	return __netdev_adjacent_dev_insert_link(dev, udev, master, true);
+	__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
+	__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
 }
 
 void __netdev_adjacent_dev_unlink(struct net_device *dev,
 				  struct net_device *upper_dev)
 {
-	__netdev_upper_dev_remove(dev, upper_dev);
-	__netdev_lower_dev_remove(upper_dev, dev);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+					   &dev->all_adj_list.upper,
+					   &upper_dev->all_adj_list.lower);
+}
+
+int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+					 struct net_device *upper_dev,
+					 bool master)
+{
+	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
+
+	if (ret)
+		return ret;
+
+	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
+					       &dev->adj_list.upper,
+					       &upper_dev->adj_list.lower,
+					       master);
+	if (ret) {
+		__netdev_adjacent_dev_unlink(dev, upper_dev);
+		return ret;
+	}
+
+	return 0;
 }
 
+void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+					    struct net_device *upper_dev)
+{
+	__netdev_adjacent_dev_unlink(dev, upper_dev);
+	__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
+					   &dev->adj_list.upper,
+					   &upper_dev->adj_list.lower);
+}
 
 static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master)
@@ -4651,10 +4646,10 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		return -EBUSY;
 
 	/* To prevent loops, check if dev is not upper device to upper_dev. */
-	if (__netdev_find_upper(upper_dev, dev))
+	if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
 		return -EBUSY;
 
-	if (__netdev_find_upper(dev, upper_dev))
+	if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper))
 		return -EEXIST;
 
 	if (master && netdev_master_upper_dev_get(dev))
@@ -4665,12 +4660,14 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		return ret;
 
 	/* Now that we linked these devs, make all the upper_dev's
-	 * upper_dev_list visible to every dev's lower_dev_list and vice
+	 * all_adj_list.upper visible to every dev's all_adj_list.lower an
 	 * versa, and don't forget the devices itself. All of these
 	 * links are non-neighbours.
 	 */
-	list_for_each_entry(i, &dev->lower_dev_list, list) {
-		list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
+			pr_debug("Interlinking %s with %s, non-neighbour\n",
+				 i->dev->name, j->dev->name);
 			ret = __netdev_adjacent_dev_link(i->dev, j->dev);
 			if (ret)
 				goto rollback_mesh;
@@ -4678,14 +4675,18 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	}
 
 	/* add dev to every upper_dev's upper device */
-	list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
+		pr_debug("linking %s's upper device %s with %s\n",
+			 upper_dev->name, i->dev->name, dev->name);
 		ret = __netdev_adjacent_dev_link(dev, i->dev);
 		if (ret)
 			goto rollback_upper_mesh;
 	}
 
 	/* add upper_dev to every dev's lower device */
-	list_for_each_entry(i, &dev->lower_dev_list, list) {
+	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+		pr_debug("linking %s's lower device %s with %s\n", dev->name,
+			 i->dev->name, upper_dev->name);
 		ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
 		if (ret)
 			goto rollback_lower_mesh;
@@ -4696,7 +4697,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 
 rollback_lower_mesh:
 	to_i = i;
-	list_for_each_entry(i, &dev->lower_dev_list, list) {
+	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
 		if (i == to_i)
 			break;
 		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
@@ -4706,7 +4707,7 @@ rollback_lower_mesh:
 
 rollback_upper_mesh:
 	to_i = i;
-	list_for_each_entry(i, &upper_dev->upper_dev_list, list) {
+	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
 		if (i == to_i)
 			break;
 		__netdev_adjacent_dev_unlink(dev, i->dev);
@@ -4717,8 +4718,8 @@ rollback_upper_mesh:
 rollback_mesh:
 	to_i = i;
 	to_j = j;
-	list_for_each_entry(i, &dev->lower_dev_list, list) {
-		list_for_each_entry(j, &upper_dev->upper_dev_list, list) {
+	list_for_each_entry(i, &dev->all_adj_list.lower, list) {
+		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
 			if (i == to_i && j == to_j)
 				break;
 			__netdev_adjacent_dev_unlink(i->dev, j->dev);
@@ -4727,7 +4728,7 @@ rollback_mesh:
 			break;
 	}
 
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
+	__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
 
 	return ret;
 }
@@ -4781,23 +4782,23 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 	struct netdev_adjacent *i, *j;
 	ASSERT_RTNL();
 
-	__netdev_adjacent_dev_unlink(dev, upper_dev);
+	__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
 
 	/* Here is the tricky part. We must remove all dev's lower
 	 * devices from all upper_dev's upper devices and vice
 	 * versa, to maintain the graph relationship.
 	 */
-	list_for_each_entry(i, &dev->lower_dev_list, list)
-		list_for_each_entry(j, &upper_dev->upper_dev_list, list)
+	list_for_each_entry(i, &dev->all_adj_list.lower, list)
+		list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
 			__netdev_adjacent_dev_unlink(i->dev, j->dev);
 
 	/* remove also the devices itself from lower/upper device
 	 * list
 	 */
-	list_for_each_entry(i, &dev->lower_dev_list, list)
+	list_for_each_entry(i, &dev->all_adj_list.lower, list)
 		__netdev_adjacent_dev_unlink(i->dev, upper_dev);
 
-	list_for_each_entry(i, &upper_dev->upper_dev_list, list)
+	list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
 		__netdev_adjacent_dev_unlink(dev, i->dev);
 
 	call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
@@ -6059,8 +6060,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
 	INIT_LIST_HEAD(&dev->link_watch_list);
-	INIT_LIST_HEAD(&dev->upper_dev_list);
-	INIT_LIST_HEAD(&dev->lower_dev_list);
+	INIT_LIST_HEAD(&dev->adj_list.upper);
+	INIT_LIST_HEAD(&dev->adj_list.lower);
+	INIT_LIST_HEAD(&dev->all_adj_list.upper);
+	INIT_LIST_HEAD(&dev->all_adj_list.lower);
 	dev->priv_flags = IFF_XMIT_DST_RELEASE;
 	setup(dev);
 
-- 
cgit 


From 402dae9614557296e84543008a8e582c28fb1db3 Mon Sep 17 00:00:00 2001
From: Veaceslav Falico <vfalico@redhat.com>
Date: Wed, 25 Sep 2013 09:20:09 +0200
Subject: net: add netdev_adjacent->private and allow to use it

Currently, even though we can access any linked device, we can't attach
anything to it, which is vital to properly manage them.

To fix this, add a new void *private to netdev_adjacent and functions
setting/getting it (per link), so that we can save, per example, bonding's
slave structures there, per slave device.

netdev_master_upper_dev_link_private(dev, upper_dev, private) links dev to
upper dev and populates the neighbour link only with private.

netdev_lower_dev_get_private{,_rcu}() returns the private, if found.

CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  7 +++++
 net/core/dev.c            | 68 +++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 64 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 514045c704a8..75d5beac463b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2839,8 +2839,15 @@ extern int netdev_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev);
 extern int netdev_master_upper_dev_link(struct net_device *dev,
 					struct net_device *upper_dev);
+extern int netdev_master_upper_dev_link_private(struct net_device *dev,
+						struct net_device *upper_dev,
+						void *private);
 extern void netdev_upper_dev_unlink(struct net_device *dev,
 				    struct net_device *upper_dev);
+extern void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+					      struct net_device *lower_dev);
+extern void *netdev_lower_dev_get_private(struct net_device *dev,
+					  struct net_device *lower_dev);
 extern int skb_checksum_help(struct sk_buff *skb);
 extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 	netdev_features_t features, bool tx_path);
diff --git a/net/core/dev.c b/net/core/dev.c
index 9290f09cdf26..c69ab74fb201 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4376,6 +4376,9 @@ struct netdev_adjacent {
 	/* counter for the number of times this device was added to us */
 	u16 ref_nr;
 
+	/* private field for the users */
+	void *private;
+
 	struct list_head list;
 	struct rcu_head rcu;
 };
@@ -4510,7 +4513,7 @@ EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
 static int __netdev_adjacent_dev_insert(struct net_device *dev,
 					struct net_device *adj_dev,
 					struct list_head *dev_list,
-					bool master)
+					void *private, bool master)
 {
 	struct netdev_adjacent *adj;
 
@@ -4528,6 +4531,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj->dev = adj_dev;
 	adj->master = master;
 	adj->ref_nr = 1;
+	adj->private = private;
 	dev_hold(adj_dev);
 
 	pr_debug("dev_hold for %s, because of link added from %s to %s\n",
@@ -4574,15 +4578,17 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev,
 				     struct net_device *upper_dev,
 				     struct list_head *up_list,
 				     struct list_head *down_list,
-				     bool master)
+				     void *private, bool master)
 {
 	int ret;
 
-	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, master);
+	ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private,
+					   master);
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, false);
+	ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private,
+					   false);
 	if (ret) {
 		__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
 		return ret;
@@ -4597,7 +4603,7 @@ int __netdev_adjacent_dev_link(struct net_device *dev,
 	return __netdev_adjacent_dev_link_lists(dev, upper_dev,
 						&dev->all_adj_list.upper,
 						&upper_dev->all_adj_list.lower,
-						false);
+						NULL, false);
 }
 
 void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
@@ -4619,7 +4625,7 @@ void __netdev_adjacent_dev_unlink(struct net_device *dev,
 
 int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 					 struct net_device *upper_dev,
-					 bool master)
+					 void *private, bool master)
 {
 	int ret = __netdev_adjacent_dev_link(dev, upper_dev);
 
@@ -4629,7 +4635,7 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
 	ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
 					       &dev->adj_list.upper,
 					       &upper_dev->adj_list.lower,
-					       master);
+					       private, master);
 	if (ret) {
 		__netdev_adjacent_dev_unlink(dev, upper_dev);
 		return ret;
@@ -4648,7 +4654,8 @@ void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 }
 
 static int __netdev_upper_dev_link(struct net_device *dev,
-				   struct net_device *upper_dev, bool master)
+				   struct net_device *upper_dev, bool master,
+				   void *private)
 {
 	struct netdev_adjacent *i, *j, *to_i, *to_j;
 	int ret = 0;
@@ -4668,7 +4675,8 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (master && netdev_master_upper_dev_get(dev))
 		return -EBUSY;
 
-	ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, master);
+	ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
+						   master);
 	if (ret)
 		return ret;
 
@@ -4759,7 +4767,7 @@ rollback_mesh:
 int netdev_upper_dev_link(struct net_device *dev,
 			  struct net_device *upper_dev)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, false);
+	return __netdev_upper_dev_link(dev, upper_dev, false, NULL);
 }
 EXPORT_SYMBOL(netdev_upper_dev_link);
 
@@ -4777,10 +4785,18 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
 int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, true);
+	return __netdev_upper_dev_link(dev, upper_dev, true, NULL);
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_link);
 
+int netdev_master_upper_dev_link_private(struct net_device *dev,
+					 struct net_device *upper_dev,
+					 void *private)
+{
+	return __netdev_upper_dev_link(dev, upper_dev, true, private);
+}
+EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
+
 /**
  * netdev_upper_dev_unlink - Removes a link to upper device
  * @dev: device
@@ -4818,6 +4834,36 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
+void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+				       struct net_device *lower_dev)
+{
+	struct netdev_adjacent *lower;
+
+	if (!lower_dev)
+		return NULL;
+	lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
+	if (!lower)
+		return NULL;
+
+	return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
+
+void *netdev_lower_dev_get_private(struct net_device *dev,
+				   struct net_device *lower_dev)
+{
+	struct netdev_adjacent *lower;
+
+	if (!lower_dev)
+		return NULL;
+	lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower);
+	if (!lower)
+		return NULL;
+
+	return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_dev_get_private);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-- 
cgit 


From 31088a113c2a948856ed2047d8c21c217b13e85d Mon Sep 17 00:00:00 2001
From: Veaceslav Falico <vfalico@redhat.com>
Date: Wed, 25 Sep 2013 09:20:12 +0200
Subject: net: add for_each iterators through neighbour lower link's private

Add a possibility to iterate through netdev_adjacent's private, currently
only for lower neighbours.

Add both RCU and RTNL/other locking variants of iterators, and make the
non-rcu variant to be safe from removal.

CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 17 ++++++++++++++
 net/core/dev.c            | 60 ++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 75d5beac463b..168974e40cf5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2833,6 +2833,23 @@ extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *d
 	     updev; \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
+extern void *netdev_lower_get_next_private(struct net_device *dev,
+					   struct list_head **iter);
+extern void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+					       struct list_head **iter);
+
+#define netdev_for_each_lower_private(dev, priv, iter) \
+	for (iter = (dev)->adj_list.lower.next, \
+	     priv = netdev_lower_get_next_private(dev, &(iter)); \
+	     priv; \
+	     priv = netdev_lower_get_next_private(dev, &(iter)))
+
+#define netdev_for_each_lower_private_rcu(dev, priv, iter) \
+	for (iter = &(dev)->adj_list.lower, \
+	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \
+	     priv; \
+	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
+
 extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 extern int netdev_upper_dev_link(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index c69ab74fb201..0aa844aae40b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4466,7 +4466,8 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
 
-/* netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
+/**
+ * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position
  *
@@ -4491,6 +4492,63 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
 
+/**
+ * netdev_lower_get_next_private - Get the next ->private from the
+ *				   lower neighbour list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold either hold the
+ * RTNL lock or its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next_private(struct net_device *dev,
+				    struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry(*iter, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	if (iter)
+		*iter = lower->list.next;
+
+	return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private);
+
+/**
+ * netdev_lower_get_next_private_rcu - Get the next ->private from the
+ *				       lower neighbour list, RCU
+ *				       variant
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent->private from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+					struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	if (iter)
+		*iter = &lower->list;
+
+	return lower->private;
+}
+EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
+
 /**
  * netdev_master_upper_dev_get_rcu - Get master upper device
  * @dev: device
-- 
cgit 


From b6ccba4c681fdaf0070e580bf951badf7edc860b Mon Sep 17 00:00:00 2001
From: Veaceslav Falico <vfalico@redhat.com>
Date: Wed, 25 Sep 2013 09:20:23 +0200
Subject: net: add a possibility to get private from netdev_adjacent->list

It will be useful to get first/last element.

CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 168974e40cf5..b4cfb63f264e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2850,6 +2850,7 @@ extern void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 	     priv; \
 	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
 
+extern void *netdev_adjacent_get_private(struct list_head *adj_list);
 extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 extern int netdev_upper_dev_link(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 0aa844aae40b..acc11810805f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4466,6 +4466,16 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
 
+void *netdev_adjacent_get_private(struct list_head *adj_list)
+{
+	struct netdev_adjacent *adj;
+
+	adj = list_entry(adj_list, struct netdev_adjacent, list);
+
+	return adj->private;
+}
+EXPORT_SYMBOL(netdev_adjacent_get_private);
+
 /**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
-- 
cgit 


From 3a6a9201897c6482573ad07ee880574147761006 Mon Sep 17 00:00:00 2001
From: Sudeep Dutt <sudeep.dutt@intel.com>
Date: Thu, 5 Sep 2013 16:41:55 -0700
Subject: Intel MIC Host Driver, card OS state management.

This patch enables the following features:
a) Boots and shuts down the card via sysfs entries.
b) Allocates and maps a device page for communication with the
   card driver and updates the device page address via scratchpad
   registers.
c) Provides sysfs entries for shutdown status, kernel command line,
   ramdisk and log buffer information.

Co-author: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Caz Yokoyama <Caz.Yokoyama@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Harshavardhan R Kharche <harshavardhan.r.kharche@intel.com>
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Acked-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Reviewed-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-mic.txt | 113 ++++++++
 drivers/misc/mic/common/mic_device.h          |   7 +
 drivers/misc/mic/host/Makefile                |   2 +
 drivers/misc/mic/host/mic_boot.c              | 184 +++++++++++++
 drivers/misc/mic/host/mic_debugfs.c           | 355 +++++++++++++++++++++++++
 drivers/misc/mic/host/mic_device.h            |  60 +++++
 drivers/misc/mic/host/mic_main.c              | 129 ++++++++-
 drivers/misc/mic/host/mic_sysfs.c             | 369 ++++++++++++++++++++++++++
 drivers/misc/mic/host/mic_x100.c              | 251 ++++++++++++++++++
 drivers/misc/mic/host/mic_x100.h              |  12 +
 include/uapi/linux/Kbuild                     |   1 +
 include/uapi/linux/mic_common.h               |  74 ++++++
 12 files changed, 1553 insertions(+), 4 deletions(-)
 create mode 100644 drivers/misc/mic/host/mic_boot.c
 create mode 100644 drivers/misc/mic/host/mic_debugfs.c
 create mode 100644 include/uapi/linux/mic_common.h

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-mic.txt b/Documentation/ABI/testing/sysfs-class-mic.txt
index 09eb3c6d0237..82cdad3b614a 100644
--- a/Documentation/ABI/testing/sysfs-class-mic.txt
+++ b/Documentation/ABI/testing/sysfs-class-mic.txt
@@ -32,3 +32,116 @@ Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		Provides information about the silicon stepping for an Intel
 		MIC device. For example - "A0" or "B0"
+
+What:		/sys/class/mic/mic(x)/state
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		When read, this entry provides the current state of an Intel
+		MIC device in the context of the card OS. Possible values that
+		will be read are:
+		"offline" - The MIC device is ready to boot the card OS.
+		"online" - The MIC device has initiated booting a card OS.
+		"shutting_down" - The card OS is shutting down.
+		"reset_failed" - The MIC device has failed to reset.
+
+		When written, this sysfs entry triggers different state change
+		operations depending upon the current state of the card OS.
+		Acceptable values are:
+		"boot" - Boot the card OS image specified by the combination
+			 of firmware, ramdisk, cmdline and bootmode
+			sysfs entries.
+		"reset" - Initiates device reset.
+		"shutdown" - Initiates card OS shutdown.
+
+What:		/sys/class/mic/mic(x)/shutdown_status
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		An Intel MIC device runs a Linux OS during its operation. This
+		OS can shutdown because of various reasons. When read, this
+		entry provides the status on why the card OS was shutdown.
+		Possible values are:
+		"nop" -  shutdown status is not applicable, when the card OS is
+			"online"
+		"crashed" - Shutdown because of a HW or SW crash.
+		"halted" - Shutdown because of a halt command.
+		"poweroff" - Shutdown because of a poweroff command.
+		"restart" - Shutdown because of a restart command.
+
+What:		/sys/class/mic/mic(x)/cmdline
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		An Intel MIC device runs a Linux OS during its operation. Before
+		booting this card OS, it is possible to pass kernel command line
+		options to configure various features in it, similar to
+		self-bootable machines. When read, this entry provides
+		information about the current kernel command line options set to
+		boot the card OS. This entry can be written to change the
+		existing kernel command line options. Typically, the user would
+		want to read the current command line options, append new ones
+		or modify existing ones and then write the whole kernel command
+		line back to this entry.
+
+What:		/sys/class/mic/mic(x)/firmware
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		When read, this sysfs entry provides the path name under
+		/lib/firmware/ where the firmware image to be booted on the
+		card can be found. The entry can be written to change the
+		firmware image location under /lib/firmware/.
+
+What:		/sys/class/mic/mic(x)/ramdisk
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		When read, this sysfs entry provides the path name under
+		/lib/firmware/ where the ramdisk image to be used during card
+		OS boot can be found. The entry can be written to change
+		the ramdisk image location under /lib/firmware/.
+
+What:		/sys/class/mic/mic(x)/bootmode
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		When read, this sysfs entry provides the current bootmode for
+		the card. This sysfs entry can be written with the following
+		valid strings:
+		a) linux - Boot a Linux image.
+		b) elf - Boot an elf image for flash updates.
+
+What:		/sys/class/mic/mic(x)/log_buf_addr
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		An Intel MIC device runs a Linux OS during its operation. For
+		debugging purpose and early kernel boot messages, the user can
+		access the card OS log buffer via debugfs. When read, this entry
+		provides the kernel virtual address of the buffer where the card
+		OS log buffer can be read. This entry is written by the host
+		configuration daemon to set the log buffer address. The correct
+		log buffer address to be written can be found in the System.map
+		file of the card OS.
+
+What:		/sys/class/mic/mic(x)/log_buf_len
+Date:		August 2013
+KernelVersion:	3.11
+Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
+Description:
+		An Intel MIC device runs a Linux OS during its operation. For
+		debugging purpose and early kernel boot messages, the user can
+		access the card OS log buffer via debugfs. When read, this entry
+		provides the kernel virtual address where the card OS log buffer
+		length can be read. This entry is written by host configuration
+		daemon to set the log buffer length address. The correct log
+		buffer length address to be written can be found in the
+		System.map file of the card OS.
diff --git a/drivers/misc/mic/common/mic_device.h b/drivers/misc/mic/common/mic_device.h
index f02262e1c9d3..6440e9d58d3a 100644
--- a/drivers/misc/mic/common/mic_device.h
+++ b/drivers/misc/mic/common/mic_device.h
@@ -34,4 +34,11 @@ struct mic_mw {
 	resource_size_t len;
 };
 
+/*
+ * Scratch pad register offsets used by the host to communicate
+ * device page DMA address to the card.
+ */
+#define MIC_DPLO_SPAD 14
+#define MIC_DPHI_SPAD 15
+
 #endif
diff --git a/drivers/misc/mic/host/Makefile b/drivers/misc/mic/host/Makefile
index 6ff5550f10ac..a375dd32c3e2 100644
--- a/drivers/misc/mic/host/Makefile
+++ b/drivers/misc/mic/host/Makefile
@@ -8,3 +8,5 @@ mic_host-objs += mic_x100.o
 mic_host-objs += mic_sysfs.o
 mic_host-objs += mic_smpt.o
 mic_host-objs += mic_intr.o
+mic_host-objs += mic_boot.o
+mic_host-objs += mic_debugfs.o
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
new file mode 100644
index 000000000000..936fc58084f3
--- /dev/null
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -0,0 +1,184 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/interrupt.h>
+
+#include <linux/mic_common.h>
+#include "../common/mic_device.h"
+#include "mic_device.h"
+#include "mic_smpt.h"
+
+/**
+ * mic_reset - Reset the MIC device.
+ * @mdev: pointer to mic_device instance
+ */
+static void mic_reset(struct mic_device *mdev)
+{
+	int i;
+
+#define MIC_RESET_TO (45)
+
+	mdev->ops->reset_fw_ready(mdev);
+	mdev->ops->reset(mdev);
+
+	for (i = 0; i < MIC_RESET_TO; i++) {
+		if (mdev->ops->is_fw_ready(mdev))
+			return;
+		/*
+		 * Resets typically take 10s of seconds to complete.
+		 * Since an MMIO read is required to check if the
+		 * firmware is ready or not, a 1 second delay works nicely.
+		 */
+		msleep(1000);
+	}
+	mic_set_state(mdev, MIC_RESET_FAILED);
+}
+
+/* Initialize the MIC bootparams */
+void mic_bootparam_init(struct mic_device *mdev)
+{
+	struct mic_bootparam *bootparam = mdev->dp;
+
+	bootparam->magic = MIC_MAGIC;
+	bootparam->c2h_shutdown_db = mdev->shutdown_db;
+	bootparam->h2c_shutdown_db = -1;
+	bootparam->h2c_config_db = -1;
+	bootparam->shutdown_status = 0;
+	bootparam->shutdown_card = 0;
+}
+
+/**
+ * mic_start - Start the MIC.
+ * @mdev: pointer to mic_device instance
+ * @buf: buffer containing boot string including firmware/ramdisk path.
+ *
+ * This function prepares an MIC for boot and initiates boot.
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+int mic_start(struct mic_device *mdev, const char *buf)
+{
+	int rc;
+	mutex_lock(&mdev->mic_mutex);
+retry:
+	if (MIC_OFFLINE != mdev->state) {
+		rc = -EINVAL;
+		goto unlock_ret;
+	}
+	if (!mdev->ops->is_fw_ready(mdev)) {
+		mic_reset(mdev);
+		/*
+		 * The state will either be MIC_OFFLINE if the reset succeeded
+		 * or MIC_RESET_FAILED if the firmware reset failed.
+		 */
+		goto retry;
+	}
+	rc = mdev->ops->load_mic_fw(mdev, buf);
+	if (rc)
+		goto unlock_ret;
+	mic_smpt_restore(mdev);
+	mic_intr_restore(mdev);
+	mdev->intr_ops->enable_interrupts(mdev);
+	mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
+	mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
+	mdev->ops->send_firmware_intr(mdev);
+	mic_set_state(mdev, MIC_ONLINE);
+unlock_ret:
+	mutex_unlock(&mdev->mic_mutex);
+	return rc;
+}
+
+/**
+ * mic_stop - Prepare the MIC for reset and trigger reset.
+ * @mdev: pointer to mic_device instance
+ * @force: force a MIC to reset even if it is already offline.
+ *
+ * RETURNS: None.
+ */
+void mic_stop(struct mic_device *mdev, bool force)
+{
+	mutex_lock(&mdev->mic_mutex);
+	if (MIC_OFFLINE != mdev->state || force) {
+		mic_bootparam_init(mdev);
+		mic_reset(mdev);
+		if (MIC_RESET_FAILED == mdev->state)
+			goto unlock;
+		mic_set_shutdown_status(mdev, MIC_NOP);
+		mic_set_state(mdev, MIC_OFFLINE);
+	}
+unlock:
+	mutex_unlock(&mdev->mic_mutex);
+}
+
+/**
+ * mic_shutdown - Initiate MIC shutdown.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: None.
+ */
+void mic_shutdown(struct mic_device *mdev)
+{
+	struct mic_bootparam *bootparam = mdev->dp;
+	s8 db = bootparam->h2c_shutdown_db;
+
+	mutex_lock(&mdev->mic_mutex);
+	if (MIC_ONLINE == mdev->state && db != -1) {
+		bootparam->shutdown_card = 1;
+		mdev->ops->send_intr(mdev, db);
+		mic_set_state(mdev, MIC_SHUTTING_DOWN);
+	}
+	mutex_unlock(&mdev->mic_mutex);
+}
+
+/**
+ * mic_shutdown_work - Handle shutdown interrupt from MIC.
+ * @work: The work structure.
+ *
+ * This work is scheduled whenever the host has received a shutdown
+ * interrupt from the MIC.
+ */
+void mic_shutdown_work(struct work_struct *work)
+{
+	struct mic_device *mdev = container_of(work, struct mic_device,
+			shutdown_work);
+	struct mic_bootparam *bootparam = mdev->dp;
+
+	mutex_lock(&mdev->mic_mutex);
+	mic_set_shutdown_status(mdev, bootparam->shutdown_status);
+	bootparam->shutdown_status = 0;
+	if (MIC_SHUTTING_DOWN != mdev->state)
+		mic_set_state(mdev, MIC_SHUTTING_DOWN);
+	mutex_unlock(&mdev->mic_mutex);
+}
+
+/**
+ * mic_reset_trigger_work - Trigger MIC reset.
+ * @work: The work structure.
+ *
+ * This work is scheduled whenever the host wants to reset the MIC.
+ */
+void mic_reset_trigger_work(struct work_struct *work)
+{
+	struct mic_device *mdev = container_of(work, struct mic_device,
+			reset_trigger_work);
+
+	mic_stop(mdev, false);
+}
diff --git a/drivers/misc/mic/host/mic_debugfs.c b/drivers/misc/mic/host/mic_debugfs.c
new file mode 100644
index 000000000000..78541d42aaf9
--- /dev/null
+++ b/drivers/misc/mic/host/mic_debugfs.c
@@ -0,0 +1,355 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+
+#include <linux/mic_common.h>
+#include "../common/mic_device.h"
+#include "mic_device.h"
+#include "mic_smpt.h"
+
+/* Debugfs parent dir */
+static struct dentry *mic_dbg;
+
+/**
+ * mic_log_buf_show - Display MIC kernel log buffer.
+ *
+ * log_buf addr/len is read from System.map by user space
+ * and populated in sysfs entries.
+ */
+static int mic_log_buf_show(struct seq_file *s, void *unused)
+{
+	void __iomem *log_buf_va;
+	int __iomem *log_buf_len_va;
+	struct mic_device *mdev = s->private;
+	void *kva;
+	int size;
+	unsigned long aper_offset;
+
+	if (!mdev || !mdev->log_buf_addr || !mdev->log_buf_len)
+		goto done;
+	/*
+	 * Card kernel will never be relocated and any kernel text/data mapping
+	 * can be translated to phys address by subtracting __START_KERNEL_map.
+	 */
+	aper_offset = (unsigned long)mdev->log_buf_len - __START_KERNEL_map;
+	log_buf_len_va = mdev->aper.va + aper_offset;
+	aper_offset = (unsigned long)mdev->log_buf_addr - __START_KERNEL_map;
+	log_buf_va = mdev->aper.va + aper_offset;
+	size = ioread32(log_buf_len_va);
+
+	kva = kmalloc(size, GFP_KERNEL);
+	if (!kva)
+		goto done;
+	mutex_lock(&mdev->mic_mutex);
+	memcpy_fromio(kva, log_buf_va, size);
+	switch (mdev->state) {
+	case MIC_ONLINE:
+		/* Fall through */
+	case MIC_SHUTTING_DOWN:
+		seq_write(s, kva, size);
+		break;
+	default:
+		break;
+	}
+	mutex_unlock(&mdev->mic_mutex);
+	kfree(kva);
+done:
+	return 0;
+}
+
+static int mic_log_buf_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_log_buf_show, inode->i_private);
+}
+
+static int mic_log_buf_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations log_buf_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_log_buf_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_log_buf_release
+};
+
+static int mic_smpt_show(struct seq_file *s, void *pos)
+{
+	int i;
+	struct mic_device *mdev = s->private;
+	unsigned long flags;
+
+	seq_printf(s, "MIC %-2d |%-10s| %-14s %-10s\n",
+		mdev->id, "SMPT entry", "SW DMA addr", "RefCount");
+	seq_puts(s, "====================================================\n");
+
+	if (mdev->smpt) {
+		struct mic_smpt_info *smpt_info = mdev->smpt;
+		spin_lock_irqsave(&smpt_info->smpt_lock, flags);
+		for (i = 0; i < smpt_info->info.num_reg; i++) {
+			seq_printf(s, "%9s|%-10d| %-#14llx %-10lld\n",
+				" ",  i, smpt_info->entry[i].dma_addr,
+				smpt_info->entry[i].ref_count);
+		}
+		spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
+	}
+	seq_puts(s, "====================================================\n");
+	return 0;
+}
+
+static int mic_smpt_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_smpt_show, inode->i_private);
+}
+
+static int mic_smpt_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations smpt_file_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_smpt_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_smpt_debug_release
+};
+
+static int mic_soft_reset_show(struct seq_file *s, void *pos)
+{
+	struct mic_device *mdev = s->private;
+
+	mic_stop(mdev, true);
+	return 0;
+}
+
+static int mic_soft_reset_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_soft_reset_show, inode->i_private);
+}
+
+static int mic_soft_reset_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations soft_reset_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_soft_reset_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_soft_reset_debug_release
+};
+
+static int mic_post_code_show(struct seq_file *s, void *pos)
+{
+	struct mic_device *mdev = s->private;
+	u32 reg = mdev->ops->get_postcode(mdev);
+
+	seq_printf(s, "%c%c", reg & 0xff, (reg >> 8) & 0xff);
+	return 0;
+}
+
+static int mic_post_code_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_post_code_show, inode->i_private);
+}
+
+static int mic_post_code_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations post_code_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_post_code_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_post_code_debug_release
+};
+
+static int mic_dp_show(struct seq_file *s, void *pos)
+{
+	struct mic_device *mdev = s->private;
+	struct mic_bootparam *bootparam = mdev->dp;
+
+	seq_printf(s, "Bootparam: magic 0x%x\n",
+		bootparam->magic);
+	seq_printf(s, "Bootparam: h2c_shutdown_db %d\n",
+		bootparam->h2c_shutdown_db);
+	seq_printf(s, "Bootparam: h2c_config_db %d\n",
+		bootparam->h2c_config_db);
+	seq_printf(s, "Bootparam: c2h_shutdown_db %d\n",
+		bootparam->c2h_shutdown_db);
+	seq_printf(s, "Bootparam: shutdown_status %d\n",
+		bootparam->shutdown_status);
+	seq_printf(s, "Bootparam: shutdown_card %d\n",
+		bootparam->shutdown_card);
+
+	return 0;
+}
+
+static int mic_dp_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_dp_show, inode->i_private);
+}
+
+static int mic_dp_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations dp_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_dp_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_dp_debug_release
+};
+
+static int mic_msi_irq_info_show(struct seq_file *s, void *pos)
+{
+	struct mic_device *mdev  = s->private;
+	int reg;
+	int i, j;
+	u16 entry;
+	u16 vector;
+	struct pci_dev *pdev = container_of(mdev->sdev->parent,
+		struct pci_dev, dev);
+
+	if (pci_dev_msi_enabled(pdev)) {
+		for (i = 0; i < mdev->irq_info.num_vectors; i++) {
+			if (pdev->msix_enabled) {
+				entry = mdev->irq_info.msix_entries[i].entry;
+				vector = mdev->irq_info.msix_entries[i].vector;
+			} else {
+				entry = 0;
+				vector = pdev->irq;
+			}
+
+			reg = mdev->intr_ops->read_msi_to_src_map(mdev, entry);
+
+			seq_printf(s, "%s %-10d %s %-10d MXAR[%d]: %08X\n",
+				"IRQ:", vector, "Entry:", entry, i, reg);
+
+			seq_printf(s, "%-10s", "offset:");
+			for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
+				seq_printf(s, "%4d ", j);
+			seq_puts(s, "\n");
+
+
+			seq_printf(s, "%-10s", "count:");
+			for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
+				seq_printf(s, "%4d ",
+				(mdev->irq_info.mic_msi_map[i] & BIT(j)) ?
+					1 : 0);
+			seq_puts(s, "\n\n");
+		}
+	} else {
+		seq_puts(s, "MSI/MSIx interrupts not enabled\n");
+	}
+
+	return 0;
+
+}
+
+static int mic_msi_irq_info_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_msi_irq_info_show, inode->i_private);
+}
+
+static int
+mic_msi_irq_info_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations msi_irq_info_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_msi_irq_info_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_msi_irq_info_debug_release
+};
+
+/**
+ * mic_create_debug_dir - Initialize MIC debugfs entries.
+ */
+void mic_create_debug_dir(struct mic_device *mdev)
+{
+	if (!mic_dbg)
+		return;
+
+	mdev->dbg_dir = debugfs_create_dir(dev_name(mdev->sdev), mic_dbg);
+	if (!mdev->dbg_dir)
+		return;
+
+	debugfs_create_file("log_buf", 0444, mdev->dbg_dir,
+		mdev, &log_buf_ops);
+
+	debugfs_create_file("smpt", 0444, mdev->dbg_dir,
+		mdev, &smpt_file_ops);
+
+	debugfs_create_file("soft_reset", 0444, mdev->dbg_dir,
+		mdev, &soft_reset_ops);
+
+	debugfs_create_file("post_code", 0444, mdev->dbg_dir,
+		mdev, &post_code_ops);
+
+	debugfs_create_file("dp", 0444, mdev->dbg_dir,
+		mdev, &dp_ops);
+
+	debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir,
+		mdev, &msi_irq_info_ops);
+}
+
+/**
+ * mic_delete_debug_dir - Uninitialize MIC debugfs entries.
+ */
+void mic_delete_debug_dir(struct mic_device *mdev)
+{
+	if (!mdev->dbg_dir)
+		return;
+
+	debugfs_remove_recursive(mdev->dbg_dir);
+}
+
+/**
+ * mic_init_debugfs - Initialize global debugfs entry.
+ */
+void __init mic_init_debugfs(void)
+{
+	mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
+	if (!mic_dbg)
+		pr_err("can't create debugfs dir\n");
+}
+
+/**
+ * mic_exit_debugfs - Uninitialize global debugfs entry
+ */
+void mic_exit_debugfs(void)
+{
+	debugfs_remove(mic_dbg);
+}
diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h
index dd34b6532a01..50b8b88d70d3 100644
--- a/drivers/misc/mic/host/mic_device.h
+++ b/drivers/misc/mic/host/mic_device.h
@@ -63,6 +63,23 @@ enum mic_stepping {
  * @smpt: MIC SMPT information.
  * @intr_info: H/W specific interrupt information.
  * @irq_info: The OS specific irq information
+ * @dbg_dir: debugfs directory of this MIC device.
+ * @cmdline: Kernel command line.
+ * @firmware: Firmware file name.
+ * @ramdisk: Ramdisk file name.
+ * @bootmode: Boot mode i.e. "linux" or "elf" for flash updates.
+ * @bootaddr: MIC boot address.
+ * @reset_trigger_work: Work for triggering reset requests.
+ * @shutdown_work: Work for handling shutdown interrupts.
+ * @state: MIC state.
+ * @shutdown_status: MIC status reported by card for shutdown/crashes.
+ * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes.
+ * @log_buf_addr: Log buffer address for MIC.
+ * @log_buf_len: Log buffer length address for MIC.
+ * @dp: virtio device page
+ * @dp_dma_addr: virtio device page DMA address.
+ * @shutdown_db: shutdown doorbell.
+ * @shutdown_cookie: shutdown cookie.
  */
 struct mic_device {
 	struct mic_mw mmio;
@@ -79,6 +96,23 @@ struct mic_device {
 	struct mic_smpt_info *smpt;
 	struct mic_intr_info *intr_info;
 	struct mic_irq_info irq_info;
+	struct dentry *dbg_dir;
+	char *cmdline;
+	char *firmware;
+	char *ramdisk;
+	char *bootmode;
+	u32 bootaddr;
+	struct work_struct reset_trigger_work;
+	struct work_struct shutdown_work;
+	u8 state;
+	u8 shutdown_status;
+	struct sysfs_dirent *state_sysfs;
+	void *log_buf_addr;
+	int *log_buf_len;
+	void *dp;
+	dma_addr_t dp_dma_addr;
+	int shutdown_db;
+	struct mic_irq *shutdown_cookie;
 };
 
 /**
@@ -90,6 +124,13 @@ struct mic_device {
  * @send_intr: Send an interrupt for a particular doorbell on the card.
  * @ack_interrupt: Hardware specific operations to ack the h/w on
  * receipt of an interrupt.
+ * @reset: Reset the remote processor.
+ * @reset_fw_ready: Reset firmware ready field.
+ * @is_fw_ready: Check if firmware is ready for OS download.
+ * @send_firmware_intr: Send an interrupt to the card firmware.
+ * @load_mic_fw: Load firmware segments required to boot the card
+ * into card memory. This includes the kernel, command line, ramdisk etc.
+ * @get_postcode: Get post code status from firmware.
  */
 struct mic_hw_ops {
 	u8 aper_bar;
@@ -98,6 +139,12 @@ struct mic_hw_ops {
 	void (*write_spad)(struct mic_device *mdev, unsigned int idx, u32 val);
 	void (*send_intr)(struct mic_device *mdev, int doorbell);
 	u32 (*ack_interrupt)(struct mic_device *mdev);
+	void (*reset)(struct mic_device *mdev);
+	void (*reset_fw_ready)(struct mic_device *mdev);
+	bool (*is_fw_ready)(struct mic_device *mdev);
+	void (*send_firmware_intr)(struct mic_device *mdev);
+	int (*load_mic_fw)(struct mic_device *mdev, const char *buf);
+	u32 (*get_postcode)(struct mic_device *mdev);
 };
 
 /**
@@ -127,4 +174,17 @@ mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
 }
 
 void mic_sysfs_init(struct mic_device *mdev);
+int mic_start(struct mic_device *mdev, const char *buf);
+void mic_stop(struct mic_device *mdev, bool force);
+void mic_shutdown(struct mic_device *mdev);
+void mic_reset_delayed_work(struct work_struct *work);
+void mic_reset_trigger_work(struct work_struct *work);
+void mic_shutdown_work(struct work_struct *work);
+void mic_bootparam_init(struct mic_device *mdev);
+void mic_set_state(struct mic_device *mdev, u8 state);
+void mic_set_shutdown_status(struct mic_device *mdev, u8 status);
+void mic_create_debug_dir(struct mic_device *dev);
+void mic_delete_debug_dir(struct mic_device *dev);
+void __init mic_init_debugfs(void);
+void mic_exit_debugfs(void);
 #endif
diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c
index 332a15e4215b..998a20ab7e96 100644
--- a/drivers/misc/mic/host/mic_main.c
+++ b/drivers/misc/mic/host/mic_main.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
+#include <linux/mic_common.h>
 #include "../common/mic_device.h"
 #include "mic_device.h"
 #include "mic_x100.h"
@@ -63,6 +64,60 @@ static struct class *g_mic_class;
 /* Base device node number for MIC devices */
 static dev_t g_mic_devno;
 
+/* Initialize the device page */
+static int mic_dp_init(struct mic_device *mdev)
+{
+	mdev->dp = kzalloc(MIC_DP_SIZE, GFP_KERNEL);
+	if (!mdev->dp) {
+		dev_err(mdev->sdev->parent, "%s %d err %d\n",
+			__func__, __LINE__, -ENOMEM);
+		return -ENOMEM;
+	}
+
+	mdev->dp_dma_addr = mic_map_single(mdev,
+		mdev->dp, MIC_DP_SIZE);
+	if (mic_map_error(mdev->dp_dma_addr)) {
+		kfree(mdev->dp);
+		dev_err(mdev->sdev->parent, "%s %d err %d\n",
+			__func__, __LINE__, -ENOMEM);
+		return -ENOMEM;
+	}
+	mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
+	mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
+	return 0;
+}
+
+/* Uninitialize the device page */
+static void mic_dp_uninit(struct mic_device *mdev)
+{
+	mic_unmap_single(mdev, mdev->dp_dma_addr, MIC_DP_SIZE);
+	kfree(mdev->dp);
+}
+
+/**
+ * mic_shutdown_db - Shutdown doorbell interrupt handler.
+ */
+static irqreturn_t mic_shutdown_db(int irq, void *data)
+{
+	struct mic_device *mdev = data;
+	struct mic_bootparam *bootparam = mdev->dp;
+
+	mdev->ops->ack_interrupt(mdev);
+
+	switch (bootparam->shutdown_status) {
+	case MIC_HALTED:
+	case MIC_POWER_OFF:
+	case MIC_RESTART:
+		/* Fall through */
+	case MIC_CRASHED:
+		schedule_work(&mdev->shutdown_work);
+		break;
+	default:
+		break;
+	};
+	return IRQ_HANDLED;
+}
+
 /**
  * mic_ops_init: Initialize HW specific operation tables.
  *
@@ -136,6 +191,26 @@ mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
 	mic_sysfs_init(mdev);
 	mutex_init(&mdev->mic_mutex);
 	mdev->irq_info.next_avail_src = 0;
+	INIT_WORK(&mdev->reset_trigger_work, mic_reset_trigger_work);
+	INIT_WORK(&mdev->shutdown_work, mic_shutdown_work);
+}
+
+/**
+ * mic_device_uninit - Frees resources allocated during mic_device_init(..)
+ *
+ * @mdev: pointer to mic_device instance
+ *
+ * returns none
+ */
+static void mic_device_uninit(struct mic_device *mdev)
+{
+	/* The cmdline sysfs entry might have allocated cmdline */
+	kfree(mdev->cmdline);
+	kfree(mdev->firmware);
+	kfree(mdev->ramdisk);
+	kfree(mdev->bootmode);
+	flush_work(&mdev->reset_trigger_work);
+	flush_work(&mdev->shutdown_work);
 }
 
 /**
@@ -170,7 +245,7 @@ static int mic_probe(struct pci_dev *pdev,
 	rc = pci_enable_device(pdev);
 	if (rc) {
 		dev_err(&pdev->dev, "failed to enable pci device.\n");
-		goto ida_remove;
+		goto uninit_device;
 	}
 
 	pci_set_master(pdev);
@@ -228,7 +303,40 @@ static int mic_probe(struct pci_dev *pdev,
 			"device_create_with_groups failed rc %d\n", rc);
 		goto smpt_uninit;
 	}
+	mdev->state_sysfs = sysfs_get_dirent(mdev->sdev->kobj.sd,
+		NULL, "state");
+	if (!mdev->state_sysfs) {
+		rc = -ENODEV;
+		dev_err(&pdev->dev, "sysfs_get_dirent failed rc %d\n", rc);
+		goto destroy_device;
+	}
+
+	rc = mic_dp_init(mdev);
+	if (rc) {
+		dev_err(&pdev->dev, "mic_dp_init failed rc %d\n", rc);
+		goto sysfs_put;
+	}
+	mutex_lock(&mdev->mic_mutex);
+
+	mdev->shutdown_db = mic_next_db(mdev);
+	mdev->shutdown_cookie = mic_request_irq(mdev, mic_shutdown_db,
+		"shutdown-interrupt", mdev, mdev->shutdown_db, MIC_INTR_DB);
+	if (IS_ERR(mdev->shutdown_cookie)) {
+		rc = PTR_ERR(mdev->shutdown_cookie);
+		mutex_unlock(&mdev->mic_mutex);
+		goto dp_uninit;
+	}
+	mutex_unlock(&mdev->mic_mutex);
+	mic_bootparam_init(mdev);
+
+	mic_create_debug_dir(mdev);
 	return 0;
+dp_uninit:
+	mic_dp_uninit(mdev);
+sysfs_put:
+	sysfs_put(mdev->state_sysfs);
+destroy_device:
+	device_destroy(g_mic_class, MKDEV(MAJOR(g_mic_devno), mdev->id));
 smpt_uninit:
 	mic_smpt_uninit(mdev);
 free_interrupts:
@@ -241,7 +349,8 @@ release_regions:
 	pci_release_regions(pdev);
 disable_device:
 	pci_disable_device(pdev);
-ida_remove:
+uninit_device:
+	mic_device_uninit(mdev);
 	ida_simple_remove(&g_mic_ida, mdev->id);
 ida_fail:
 	kfree(mdev);
@@ -265,11 +374,20 @@ static void mic_remove(struct pci_dev *pdev)
 	if (!mdev)
 		return;
 
+	mic_stop(mdev, false);
+	mic_delete_debug_dir(mdev);
+	mutex_lock(&mdev->mic_mutex);
+	mic_free_irq(mdev, mdev->shutdown_cookie, mdev);
+	mutex_unlock(&mdev->mic_mutex);
+	flush_work(&mdev->shutdown_work);
+	mic_dp_uninit(mdev);
+	sysfs_put(mdev->state_sysfs);
 	device_destroy(g_mic_class, MKDEV(MAJOR(g_mic_devno), mdev->id));
 	mic_smpt_uninit(mdev);
 	mic_free_interrupts(mdev, pdev);
 	iounmap(mdev->mmio.va);
 	iounmap(mdev->aper.va);
+	mic_device_uninit(mdev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	ida_simple_remove(&g_mic_ida, mdev->id);
@@ -300,14 +418,16 @@ static int __init mic_init(void)
 		goto cleanup_chrdev;
 	}
 
+	mic_init_debugfs();
 	ida_init(&g_mic_ida);
 	ret = pci_register_driver(&mic_driver);
 	if (ret) {
 		pr_err("pci_register_driver failed ret %d\n", ret);
-		goto class_destroy;
+		goto cleanup_debugfs;
 	}
 	return ret;
-class_destroy:
+cleanup_debugfs:
+	mic_exit_debugfs();
 	class_destroy(g_mic_class);
 cleanup_chrdev:
 	unregister_chrdev_region(g_mic_devno, MIC_MAX_NUM_DEVS);
@@ -319,6 +439,7 @@ static void __exit mic_exit(void)
 {
 	pci_unregister_driver(&mic_driver);
 	ida_destroy(&g_mic_ida);
+	mic_exit_debugfs();
 	class_destroy(g_mic_class);
 	unregister_chrdev_region(g_mic_devno, MIC_MAX_NUM_DEVS);
 }
diff --git a/drivers/misc/mic/host/mic_sysfs.c b/drivers/misc/mic/host/mic_sysfs.c
index 972c18255263..aaf849945111 100644
--- a/drivers/misc/mic/host/mic_sysfs.c
+++ b/drivers/misc/mic/host/mic_sysfs.c
@@ -20,9 +20,50 @@
  */
 #include <linux/pci.h>
 
+#include <linux/mic_common.h>
 #include "../common/mic_device.h"
 #include "mic_device.h"
 
+/*
+ * A state-to-string lookup table, for exposing a human readable state
+ * via sysfs. Always keep in sync with enum mic_states
+ */
+static const char * const mic_state_string[] = {
+	[MIC_OFFLINE] = "offline",
+	[MIC_ONLINE] = "online",
+	[MIC_SHUTTING_DOWN] = "shutting_down",
+	[MIC_RESET_FAILED] = "reset_failed",
+};
+
+/*
+ * A shutdown-status-to-string lookup table, for exposing a human
+ * readable state via sysfs. Always keep in sync with enum mic_shutdown_status
+ */
+static const char * const mic_shutdown_status_string[] = {
+	[MIC_NOP] = "nop",
+	[MIC_CRASHED] = "crashed",
+	[MIC_HALTED] = "halted",
+	[MIC_POWER_OFF] = "poweroff",
+	[MIC_RESTART] = "restart",
+};
+
+void mic_set_shutdown_status(struct mic_device *mdev, u8 shutdown_status)
+{
+	dev_dbg(mdev->sdev->parent, "Shutdown Status %s -> %s\n",
+		mic_shutdown_status_string[mdev->shutdown_status],
+		mic_shutdown_status_string[shutdown_status]);
+	mdev->shutdown_status = shutdown_status;
+}
+
+void mic_set_state(struct mic_device *mdev, u8 state)
+{
+	dev_dbg(mdev->sdev->parent, "State %s -> %s\n",
+		mic_state_string[mdev->state],
+		mic_state_string[state]);
+	mdev->state = state;
+	sysfs_notify_dirent(mdev->state_sysfs);
+}
+
 static ssize_t
 mic_show_family(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -75,9 +116,337 @@ mic_show_stepping(struct device *dev, struct device_attribute *attr, char *buf)
 }
 static DEVICE_ATTR(stepping, S_IRUGO, mic_show_stepping, NULL);
 
+static ssize_t
+mic_show_state(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev || mdev->state >= MIC_LAST)
+		return -EINVAL;
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n",
+		mic_state_string[mdev->state]);
+}
+
+static ssize_t
+mic_store_state(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	int rc = 0;
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	if (!mdev)
+		return -EINVAL;
+	if (sysfs_streq(buf, "boot")) {
+		rc = mic_start(mdev, buf);
+		if (rc) {
+			dev_err(mdev->sdev->parent,
+				"mic_boot failed rc %d\n", rc);
+			count = rc;
+		}
+		goto done;
+	}
+
+	if (sysfs_streq(buf, "reset")) {
+		schedule_work(&mdev->reset_trigger_work);
+		goto done;
+	}
+
+	if (sysfs_streq(buf, "shutdown")) {
+		mic_shutdown(mdev);
+		goto done;
+	}
+
+	count = -EINVAL;
+done:
+	return count;
+}
+static DEVICE_ATTR(state, S_IRUGO|S_IWUSR, mic_show_state, mic_store_state);
+
+static ssize_t mic_show_shutdown_status(struct device *dev,
+	struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev || mdev->shutdown_status >= MIC_STATUS_LAST)
+		return -EINVAL;
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n",
+		mic_shutdown_status_string[mdev->shutdown_status]);
+}
+static DEVICE_ATTR(shutdown_status, S_IRUGO|S_IWUSR,
+	mic_show_shutdown_status, NULL);
+
+static ssize_t
+mic_show_cmdline(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	char *cmdline;
+
+	if (!mdev)
+		return -EINVAL;
+
+	cmdline = mdev->cmdline;
+
+	if (cmdline)
+		return scnprintf(buf, PAGE_SIZE, "%s\n", cmdline);
+	return 0;
+}
+
+static ssize_t
+mic_store_cmdline(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	mutex_lock(&mdev->mic_mutex);
+	kfree(mdev->cmdline);
+
+	mdev->cmdline = kmalloc(count + 1, GFP_KERNEL);
+	if (!mdev->cmdline) {
+		count = -ENOMEM;
+		goto unlock;
+	}
+
+	strncpy(mdev->cmdline, buf, count);
+
+	if (mdev->cmdline[count - 1] == '\n')
+		mdev->cmdline[count - 1] = '\0';
+	else
+		mdev->cmdline[count] = '\0';
+unlock:
+	mutex_unlock(&mdev->mic_mutex);
+	return count;
+}
+static DEVICE_ATTR(cmdline, S_IRUGO | S_IWUSR,
+	mic_show_cmdline, mic_store_cmdline);
+
+static ssize_t
+mic_show_firmware(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	char *firmware;
+
+	if (!mdev)
+		return -EINVAL;
+
+	firmware = mdev->firmware;
+
+	if (firmware)
+		return scnprintf(buf, PAGE_SIZE, "%s\n", firmware);
+	return 0;
+}
+
+static ssize_t
+mic_store_firmware(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	mutex_lock(&mdev->mic_mutex);
+	kfree(mdev->firmware);
+
+	mdev->firmware = kmalloc(count + 1, GFP_KERNEL);
+	if (!mdev->firmware) {
+		count = -ENOMEM;
+		goto unlock;
+	}
+	strncpy(mdev->firmware, buf, count);
+
+	if (mdev->firmware[count - 1] == '\n')
+		mdev->firmware[count - 1] = '\0';
+	else
+		mdev->firmware[count] = '\0';
+unlock:
+	mutex_unlock(&mdev->mic_mutex);
+	return count;
+}
+static DEVICE_ATTR(firmware, S_IRUGO | S_IWUSR,
+	mic_show_firmware, mic_store_firmware);
+
+static ssize_t
+mic_show_ramdisk(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	char *ramdisk;
+
+	if (!mdev)
+		return -EINVAL;
+
+	ramdisk = mdev->ramdisk;
+
+	if (ramdisk)
+		return scnprintf(buf, PAGE_SIZE, "%s\n", ramdisk);
+	return 0;
+}
+
+static ssize_t
+mic_store_ramdisk(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	mutex_lock(&mdev->mic_mutex);
+	kfree(mdev->ramdisk);
+
+	mdev->ramdisk = kmalloc(count + 1, GFP_KERNEL);
+	if (!mdev->ramdisk) {
+		count = -ENOMEM;
+		goto unlock;
+	}
+
+	strncpy(mdev->ramdisk, buf, count);
+
+	if (mdev->ramdisk[count - 1] == '\n')
+		mdev->ramdisk[count - 1] = '\0';
+	else
+		mdev->ramdisk[count] = '\0';
+unlock:
+	mutex_unlock(&mdev->mic_mutex);
+	return count;
+}
+static DEVICE_ATTR(ramdisk, S_IRUGO | S_IWUSR,
+	mic_show_ramdisk, mic_store_ramdisk);
+
+static ssize_t
+mic_show_bootmode(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	char *bootmode;
+
+	if (!mdev)
+		return -EINVAL;
+
+	bootmode = mdev->bootmode;
+
+	if (bootmode)
+		return scnprintf(buf, PAGE_SIZE, "%s\n", bootmode);
+	return 0;
+}
+
+static ssize_t
+mic_store_bootmode(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	if (!sysfs_streq(buf, "linux") && !sysfs_streq(buf, "elf"))
+		return -EINVAL;
+
+	mutex_lock(&mdev->mic_mutex);
+	kfree(mdev->bootmode);
+
+	mdev->bootmode = kmalloc(count + 1, GFP_KERNEL);
+	if (!mdev->bootmode) {
+		count = -ENOMEM;
+		goto unlock;
+	}
+
+	strncpy(mdev->bootmode, buf, count);
+
+	if (mdev->bootmode[count - 1] == '\n')
+		mdev->bootmode[count - 1] = '\0';
+	else
+		mdev->bootmode[count] = '\0';
+unlock:
+	mutex_unlock(&mdev->mic_mutex);
+	return count;
+}
+static DEVICE_ATTR(bootmode, S_IRUGO | S_IWUSR,
+	mic_show_bootmode, mic_store_bootmode);
+
+static ssize_t
+mic_show_log_buf_addr(struct device *dev, struct device_attribute *attr,
+	char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	return scnprintf(buf, PAGE_SIZE, "%p\n", mdev->log_buf_addr);
+}
+
+static ssize_t
+mic_store_log_buf_addr(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	int ret;
+	unsigned long addr;
+
+	if (!mdev)
+		return -EINVAL;
+
+	ret = kstrtoul(buf, 16, &addr);
+	if (ret)
+		goto exit;
+
+	mdev->log_buf_addr = (void *)addr;
+	ret = count;
+exit:
+	return ret;
+}
+static DEVICE_ATTR(log_buf_addr, S_IRUGO | S_IWUSR,
+	mic_show_log_buf_addr, mic_store_log_buf_addr);
+
+static ssize_t
+mic_show_log_buf_len(struct device *dev, struct device_attribute *attr,
+	char *buf)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+
+	if (!mdev)
+		return -EINVAL;
+
+	return scnprintf(buf, PAGE_SIZE, "%p\n", mdev->log_buf_len);
+}
+
+static ssize_t
+mic_store_log_buf_len(struct device *dev, struct device_attribute *attr,
+	const char *buf, size_t count)
+{
+	struct mic_device *mdev = dev_get_drvdata(dev->parent);
+	int ret;
+	unsigned long addr;
+
+	if (!mdev)
+		return -EINVAL;
+
+	ret = kstrtoul(buf, 16, &addr);
+	if (ret)
+		goto exit;
+
+	mdev->log_buf_len = (int *)addr;
+	ret = count;
+exit:
+	return ret;
+}
+static DEVICE_ATTR(log_buf_len, S_IRUGO | S_IWUSR,
+	mic_show_log_buf_len, mic_store_log_buf_len);
+
 static struct attribute *mic_default_attrs[] = {
 	&dev_attr_family.attr,
 	&dev_attr_stepping.attr,
+	&dev_attr_state.attr,
+	&dev_attr_shutdown_status.attr,
+	&dev_attr_cmdline.attr,
+	&dev_attr_firmware.attr,
+	&dev_attr_ramdisk.attr,
+	&dev_attr_bootmode.attr,
+	&dev_attr_log_buf_addr.attr,
+	&dev_attr_log_buf_len.attr,
 
 	NULL
 };
diff --git a/drivers/misc/mic/host/mic_x100.c b/drivers/misc/mic/host/mic_x100.c
index b63731691c73..a12ae5c8844d 100644
--- a/drivers/misc/mic/host/mic_x100.c
+++ b/drivers/misc/mic/host/mic_x100.c
@@ -20,6 +20,9 @@
  */
 #include <linux/fs.h>
 #include <linux/pci.h>
+#include <linux/sched.h>
+#include <linux/firmware.h>
+#include <linux/delay.h>
 
 #include "../common/mic_device.h"
 #include "mic_device.h"
@@ -256,6 +259,248 @@ mic_x100_program_msi_to_src_map(struct mic_device *mdev,
 	mic_mmio_write(mw, reg, mxar);
 }
 
+/*
+ * mic_x100_reset_fw_ready - Reset Firmware ready status field.
+ * @mdev: pointer to mic_device instance
+ */
+static void mic_x100_reset_fw_ready(struct mic_device *mdev)
+{
+	mdev->ops->write_spad(mdev, MIC_X100_DOWNLOAD_INFO, 0);
+}
+
+/*
+ * mic_x100_is_fw_ready - Check if firmware is ready.
+ * @mdev: pointer to mic_device instance
+ */
+static bool mic_x100_is_fw_ready(struct mic_device *mdev)
+{
+	u32 scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
+	return MIC_X100_SPAD2_DOWNLOAD_STATUS(scratch2) ? true : false;
+}
+
+/**
+ * mic_x100_get_apic_id - Get bootstrap APIC ID.
+ * @mdev: pointer to mic_device instance
+ */
+static u32 mic_x100_get_apic_id(struct mic_device *mdev)
+{
+	u32 scratch2 = 0;
+
+	scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
+	return MIC_X100_SPAD2_APIC_ID(scratch2);
+}
+
+/**
+ * mic_x100_send_firmware_intr - Send an interrupt to the firmware on MIC.
+ * @mdev: pointer to mic_device instance
+ */
+static void mic_x100_send_firmware_intr(struct mic_device *mdev)
+{
+	u32 apicicr_low;
+	u64 apic_icr_offset = MIC_X100_SBOX_APICICR7;
+	int vector = MIC_X100_BSP_INTERRUPT_VECTOR;
+	struct mic_mw *mw = &mdev->mmio;
+
+	/*
+	 * For MIC we need to make sure we "hit"
+	 * the send_icr bit (13).
+	 */
+	apicicr_low = (vector | (1 << 13));
+
+	mic_mmio_write(mw, mic_x100_get_apic_id(mdev),
+		MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset + 4);
+
+	/* Ensure that the interrupt is ordered w.r.t. previous stores. */
+	wmb();
+	mic_mmio_write(mw, apicicr_low,
+		MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
+}
+
+/**
+ * mic_x100_hw_reset - Reset the MIC device.
+ * @mdev: pointer to mic_device instance
+ */
+static void mic_x100_hw_reset(struct mic_device *mdev)
+{
+	u32 reset_reg;
+	u32 rgcr = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_RGCR;
+	struct mic_mw *mw = &mdev->mmio;
+
+	/* Ensure that the reset is ordered w.r.t. previous loads and stores */
+	mb();
+	/* Trigger reset */
+	reset_reg = mic_mmio_read(mw, rgcr);
+	reset_reg |= 0x1;
+	mic_mmio_write(mw, reset_reg, rgcr);
+	/*
+	 * It seems we really want to delay at least 1 second
+	 * after touching reset to prevent a lot of problems.
+	 */
+	msleep(1000);
+}
+
+/**
+ * mic_x100_load_command_line - Load command line to MIC.
+ * @mdev: pointer to mic_device instance
+ * @fw: the firmware image
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+static int
+mic_x100_load_command_line(struct mic_device *mdev, const struct firmware *fw)
+{
+	u32 len = 0;
+	u32 boot_mem;
+	char *buf;
+	void __iomem *cmd_line_va = mdev->aper.va + mdev->bootaddr + fw->size;
+#define CMDLINE_SIZE 2048
+
+	boot_mem = mdev->aper.len >> 20;
+	buf = kzalloc(CMDLINE_SIZE, GFP_KERNEL);
+	if (!buf) {
+		dev_err(mdev->sdev->parent,
+			"%s %d allocation failed\n", __func__, __LINE__);
+		return -ENOMEM;
+	}
+	len += snprintf(buf, CMDLINE_SIZE - len,
+		" mem=%dM", boot_mem);
+	if (mdev->cmdline)
+		snprintf(buf + len, CMDLINE_SIZE - len,
+				" %s", mdev->cmdline);
+	memcpy_toio(cmd_line_va, buf, strlen(buf) + 1);
+	kfree(buf);
+	return 0;
+}
+
+/**
+ * mic_x100_load_ramdisk - Load ramdisk to MIC.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+static int
+mic_x100_load_ramdisk(struct mic_device *mdev)
+{
+	const struct firmware *fw;
+	int rc;
+	struct boot_params __iomem *bp = mdev->aper.va + mdev->bootaddr;
+
+	rc = request_firmware(&fw,
+			mdev->ramdisk, mdev->sdev->parent);
+	if (rc < 0) {
+		dev_err(mdev->sdev->parent,
+			"ramdisk request_firmware failed: %d %s\n",
+			rc, mdev->ramdisk);
+		goto error;
+	}
+	/*
+	 * Typically the bootaddr for card OS is 64M
+	 * so copy over the ramdisk @ 128M.
+	 */
+	memcpy_toio(mdev->aper.va + (mdev->bootaddr << 1),
+		fw->data, fw->size);
+	iowrite32(cpu_to_le32(mdev->bootaddr << 1), &bp->hdr.ramdisk_image);
+	iowrite32(cpu_to_le32(fw->size), &bp->hdr.ramdisk_size);
+	release_firmware(fw);
+error:
+	return rc;
+}
+
+/**
+ * mic_x100_get_boot_addr - Get MIC boot address.
+ * @mdev: pointer to mic_device instance
+ *
+ * This function is called during firmware load to determine
+ * the address at which the OS should be downloaded in card
+ * memory i.e. GDDR.
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+static int
+mic_x100_get_boot_addr(struct mic_device *mdev)
+{
+	u32 scratch2, boot_addr;
+	int rc = 0;
+
+	scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
+	boot_addr = MIC_X100_SPAD2_DOWNLOAD_ADDR(scratch2);
+	dev_dbg(mdev->sdev->parent, "%s %d boot_addr 0x%x\n",
+		__func__, __LINE__, boot_addr);
+	if (boot_addr > (1 << 31)) {
+		dev_err(mdev->sdev->parent,
+			"incorrect bootaddr 0x%x\n",
+			boot_addr);
+		rc = -EINVAL;
+		goto error;
+	}
+	mdev->bootaddr = boot_addr;
+error:
+	return rc;
+}
+
+/**
+ * mic_x100_load_firmware - Load firmware to MIC.
+ * @mdev: pointer to mic_device instance
+ * @buf: buffer containing boot string including firmware/ramdisk path.
+ *
+ * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
+ */
+static int
+mic_x100_load_firmware(struct mic_device *mdev, const char *buf)
+{
+	int rc;
+	const struct firmware *fw;
+
+	rc = mic_x100_get_boot_addr(mdev);
+	if (rc)
+		goto error;
+	/* load OS */
+	rc = request_firmware(&fw, mdev->firmware, mdev->sdev->parent);
+	if (rc < 0) {
+		dev_err(mdev->sdev->parent,
+			"ramdisk request_firmware failed: %d %s\n",
+			rc, mdev->firmware);
+		goto error;
+	}
+	if (mdev->bootaddr > mdev->aper.len - fw->size) {
+		rc = -EINVAL;
+		dev_err(mdev->sdev->parent, "%s %d rc %d bootaddr 0x%x\n",
+			__func__, __LINE__, rc, mdev->bootaddr);
+		release_firmware(fw);
+		goto error;
+	}
+	memcpy_toio(mdev->aper.va + mdev->bootaddr, fw->data, fw->size);
+	mdev->ops->write_spad(mdev, MIC_X100_FW_SIZE, fw->size);
+	if (!strcmp(mdev->bootmode, "elf"))
+		goto done;
+	/* load command line */
+	rc = mic_x100_load_command_line(mdev, fw);
+	if (rc) {
+		dev_err(mdev->sdev->parent, "%s %d rc %d\n",
+			__func__, __LINE__, rc);
+		goto error;
+	}
+	release_firmware(fw);
+	/* load ramdisk */
+	if (mdev->ramdisk)
+		rc = mic_x100_load_ramdisk(mdev);
+error:
+	dev_dbg(mdev->sdev->parent, "%s %d rc %d\n",
+			__func__, __LINE__, rc);
+done:
+	return rc;
+}
+
+/**
+ * mic_x100_get_postcode - Get postcode status from firmware.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: postcode.
+ */
+static u32 mic_x100_get_postcode(struct mic_device *mdev)
+{
+	return mic_mmio_read(&mdev->mmio, MIC_X100_POSTCODE);
+}
+
 /**
  * mic_x100_smpt_set - Update an SMPT entry with a DMA address.
  * @mdev: pointer to mic_device instance
@@ -311,6 +556,12 @@ struct mic_hw_ops mic_x100_ops = {
 	.write_spad = mic_x100_write_spad,
 	.send_intr = mic_x100_send_intr,
 	.ack_interrupt = mic_x100_ack_interrupt,
+	.reset = mic_x100_hw_reset,
+	.reset_fw_ready = mic_x100_reset_fw_ready,
+	.is_fw_ready = mic_x100_is_fw_ready,
+	.send_firmware_intr = mic_x100_send_firmware_intr,
+	.load_mic_fw = mic_x100_load_firmware,
+	.get_postcode = mic_x100_get_postcode,
 };
 
 struct mic_hw_intr_ops mic_x100_intr_ops = {
diff --git a/drivers/misc/mic/host/mic_x100.h b/drivers/misc/mic/host/mic_x100.h
index 642cae9a0041..8b7daa182e54 100644
--- a/drivers/misc/mic/host/mic_x100.h
+++ b/drivers/misc/mic/host/mic_x100.h
@@ -69,6 +69,15 @@
 #define MIC_X100_NUM_SBOX_IRQ 8
 #define MIC_X100_NUM_RDMASR_IRQ 8
 #define MIC_X100_RDMASR_IRQ_BASE 17
+#define MIC_X100_SPAD2_DOWNLOAD_STATUS(x) ((x) & 0x1)
+#define MIC_X100_SPAD2_APIC_ID(x)	(((x) >> 1) & 0x1ff)
+#define MIC_X100_SPAD2_DOWNLOAD_ADDR(x) ((x) & 0xfffff000)
+#define MIC_X100_SBOX_APICICR7 0x0000AA08
+#define MIC_X100_SBOX_RGCR 0x00004010
+#define MIC_X100_SBOX_SDBIC0 0x0000CC90
+#define MIC_X100_DOWNLOAD_INFO 2
+#define MIC_X100_FW_SIZE 5
+#define MIC_X100_POSTCODE 0x242c
 
 static const u16 mic_x100_intr_init[] = {
 		MIC_X100_DOORBELL_IDX_START,
@@ -79,6 +88,9 @@ static const u16 mic_x100_intr_init[] = {
 		MIC_X100_NUM_ERR,
 };
 
+/* Host->Card(bootstrap) Interrupt Vector */
+#define MIC_X100_BSP_INTERRUPT_VECTOR 229
+
 extern struct mic_hw_ops mic_x100_ops;
 extern struct mic_smpt_ops mic_x100_smpt_ops;
 extern struct mic_hw_intr_ops mic_x100_intr_ops;
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 115add2515aa..d37263fbdca7 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -241,6 +241,7 @@ header-y += media.h
 header-y += mei.h
 header-y += mempolicy.h
 header-y += meye.h
+header-y += mic_common.h
 header-y += mii.h
 header-y += minix_fs.h
 header-y += mman.h
diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h
new file mode 100644
index 000000000000..a9091e529183
--- /dev/null
+++ b/include/uapi/linux/mic_common.h
@@ -0,0 +1,74 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC driver.
+ *
+ */
+#ifndef __MIC_COMMON_H_
+#define __MIC_COMMON_H_
+
+#include <linux/types.h>
+
+/**
+ * struct mic_bootparam: Virtio device independent information in device page
+ *
+ * @magic: A magic value used by the card to ensure it can see the host
+ * @c2h_shutdown_db: Card to Host shutdown doorbell set by host
+ * @h2c_shutdown_db: Host to Card shutdown doorbell set by card
+ * @h2c_config_db: Host to Card Virtio config doorbell set by card
+ * @shutdown_status: Card shutdown status set by card
+ * @shutdown_card: Set to 1 by the host when a card shutdown is initiated
+ */
+struct mic_bootparam {
+	__u32 magic;
+	__s8 c2h_shutdown_db;
+	__s8 h2c_shutdown_db;
+	__s8 h2c_config_db;
+	__u8 shutdown_status;
+	__u8 shutdown_card;
+} __aligned(8);
+
+/* Device page size */
+#define MIC_DP_SIZE 4096
+
+#define MIC_MAGIC 0xc0ffee00
+
+/**
+ * enum mic_states - MIC states.
+ */
+enum mic_states {
+	MIC_OFFLINE = 0,
+	MIC_ONLINE,
+	MIC_SHUTTING_DOWN,
+	MIC_RESET_FAILED,
+	MIC_LAST
+};
+
+/**
+ * enum mic_status - MIC status reported by card after
+ * a host or card initiated shutdown or a card crash.
+ */
+enum mic_status {
+	MIC_NOP = 0,
+	MIC_CRASHED,
+	MIC_HALTED,
+	MIC_POWER_OFF,
+	MIC_RESTART,
+	MIC_STATUS_LAST
+};
+
+#endif
-- 
cgit 


From f69bcbf3b4c4b333dcd7a48eaf868bf0c88edab5 Mon Sep 17 00:00:00 2001
From: Ashutosh Dixit <ashutosh.dixit@intel.com>
Date: Thu, 5 Sep 2013 16:42:18 -0700
Subject: Intel MIC Host Driver Changes for Virtio Devices.

This patch introduces the host "Virtio over PCIe" interface for
Intel MIC. It allows creating user space backends on the host and instantiating
virtio devices for them on the Intel MIC card. It uses the existing VRINGH
infrastructure in the kernel to access virtio rings from the host. A character
device per MIC is exposed with IOCTL, mmap and poll callbacks. This allows the
user space backend to:
(a) add/remove a virtio device via a device page.
(b) map (R/O) virtio rings and device page to user space.
(c) poll for availability of data.
(d) copy a descriptor or entire descriptor chain to/from the card.
(e) modify virtio configuration.
(f) handle virtio device reset.
The buffers are copied over using CPU copies for this initial patch
and host initiated MIC DMA support is planned for future patches.
The avail and desc virtio rings are in host memory and the used ring
is in card memory to maximize writes across PCIe for performance.

Co-author: Sudeep Dutt <sudeep.dutt@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Caz Yokoyama <Caz.Yokoyama@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Harshavardhan R Kharche <harshavardhan.r.kharche@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Acked-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Reviewed-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mic/Kconfig             |   1 +
 drivers/misc/mic/common/mic_device.h |   7 +
 drivers/misc/mic/host/Makefile       |   2 +
 drivers/misc/mic/host/mic_boot.c     |   3 +-
 drivers/misc/mic/host/mic_debugfs.c  | 140 +++++++
 drivers/misc/mic/host/mic_device.h   |   5 +
 drivers/misc/mic/host/mic_fops.c     | 221 +++++++++++
 drivers/misc/mic/host/mic_fops.h     |  32 ++
 drivers/misc/mic/host/mic_main.c     |  26 ++
 drivers/misc/mic/host/mic_virtio.c   | 703 +++++++++++++++++++++++++++++++++++
 drivers/misc/mic/host/mic_virtio.h   | 138 +++++++
 include/uapi/linux/Kbuild            |   1 +
 include/uapi/linux/mic_common.h      | 166 ++++++++-
 include/uapi/linux/mic_ioctl.h       |  74 ++++
 14 files changed, 1517 insertions(+), 2 deletions(-)
 create mode 100644 drivers/misc/mic/host/mic_fops.c
 create mode 100644 drivers/misc/mic/host/mic_fops.h
 create mode 100644 drivers/misc/mic/host/mic_virtio.c
 create mode 100644 drivers/misc/mic/host/mic_virtio.h
 create mode 100644 include/uapi/linux/mic_ioctl.h

(limited to 'include')

diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 279a2e649059..01f1a4a84c63 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -3,6 +3,7 @@ comment "Intel MIC Host Driver"
 config INTEL_MIC_HOST
 	tristate "Intel MIC Host Driver"
 	depends on 64BIT && PCI
+	select VHOST_RING
 	default N
 	help
 	  This enables Host Driver support for the Intel Many Integrated
diff --git a/drivers/misc/mic/common/mic_device.h b/drivers/misc/mic/common/mic_device.h
index 6440e9d58d3a..01eb74faae6b 100644
--- a/drivers/misc/mic/common/mic_device.h
+++ b/drivers/misc/mic/common/mic_device.h
@@ -41,4 +41,11 @@ struct mic_mw {
 #define MIC_DPLO_SPAD 14
 #define MIC_DPHI_SPAD 15
 
+/*
+ * These values are supposed to be in the config_change field of the
+ * device page when the host sends a config change interrupt to the card.
+ */
+#define MIC_VIRTIO_PARAM_DEV_REMOVE 0x1
+#define MIC_VIRTIO_PARAM_CONFIG_CHANGED 0x2
+
 #endif
diff --git a/drivers/misc/mic/host/Makefile b/drivers/misc/mic/host/Makefile
index a375dd32c3e2..c2197f999394 100644
--- a/drivers/misc/mic/host/Makefile
+++ b/drivers/misc/mic/host/Makefile
@@ -10,3 +10,5 @@ mic_host-objs += mic_smpt.o
 mic_host-objs += mic_intr.o
 mic_host-objs += mic_boot.o
 mic_host-objs += mic_debugfs.o
+mic_host-objs += mic_fops.o
+mic_host-objs += mic_virtio.o
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
index 936fc58084f3..fd9ff6d3784e 100644
--- a/drivers/misc/mic/host/mic_boot.c
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -20,12 +20,12 @@
  */
 #include <linux/delay.h>
 #include <linux/firmware.h>
-#include <linux/interrupt.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_device.h"
 #include "mic_device.h"
 #include "mic_smpt.h"
+#include "mic_virtio.h"
 
 /**
  * mic_reset - Reset the MIC device.
@@ -117,6 +117,7 @@ void mic_stop(struct mic_device *mdev, bool force)
 {
 	mutex_lock(&mdev->mic_mutex);
 	if (MIC_OFFLINE != mdev->state || force) {
+		mic_virtio_reset_devices(mdev);
 		mic_bootparam_init(mdev);
 		mic_reset(mdev);
 		if (MIC_RESET_FAILED == mdev->state)
diff --git a/drivers/misc/mic/host/mic_debugfs.c b/drivers/misc/mic/host/mic_debugfs.c
index 78541d42aaf9..e22fb7bbbb98 100644
--- a/drivers/misc/mic/host/mic_debugfs.c
+++ b/drivers/misc/mic/host/mic_debugfs.c
@@ -26,6 +26,7 @@
 #include "../common/mic_device.h"
 #include "mic_device.h"
 #include "mic_smpt.h"
+#include "mic_virtio.h"
 
 /* Debugfs parent dir */
 static struct dentry *mic_dbg;
@@ -193,7 +194,13 @@ static const struct file_operations post_code_ops = {
 static int mic_dp_show(struct seq_file *s, void *pos)
 {
 	struct mic_device *mdev = s->private;
+	struct mic_device_desc *d;
+	struct mic_device_ctrl *dc;
+	struct mic_vqconfig *vqconfig;
+	__u32 *features;
+	__u8 *config;
 	struct mic_bootparam *bootparam = mdev->dp;
+	int i, j;
 
 	seq_printf(s, "Bootparam: magic 0x%x\n",
 		bootparam->magic);
@@ -208,6 +215,53 @@ static int mic_dp_show(struct seq_file *s, void *pos)
 	seq_printf(s, "Bootparam: shutdown_card %d\n",
 		bootparam->shutdown_card);
 
+	for (i = sizeof(*bootparam); i < MIC_DP_SIZE;
+	     i += mic_total_desc_size(d)) {
+		d = mdev->dp + i;
+		dc = (void *)d + mic_aligned_desc_size(d);
+
+		/* end of list */
+		if (d->type == 0)
+			break;
+
+		if (d->type == -1)
+			continue;
+
+		seq_printf(s, "Type %d ", d->type);
+		seq_printf(s, "Num VQ %d ", d->num_vq);
+		seq_printf(s, "Feature Len %d\n", d->feature_len);
+		seq_printf(s, "Config Len %d ", d->config_len);
+		seq_printf(s, "Shutdown Status %d\n", d->status);
+
+		for (j = 0; j < d->num_vq; j++) {
+			vqconfig = mic_vq_config(d) + j;
+			seq_printf(s, "vqconfig[%d]: ", j);
+			seq_printf(s, "address 0x%llx ", vqconfig->address);
+			seq_printf(s, "num %d ", vqconfig->num);
+			seq_printf(s, "used address 0x%llx\n",
+				vqconfig->used_address);
+		}
+
+		features = (__u32 *) mic_vq_features(d);
+		seq_printf(s, "Features: Host 0x%x ", features[0]);
+		seq_printf(s, "Guest 0x%x\n", features[1]);
+
+		config = mic_vq_configspace(d);
+		for (j = 0; j < d->config_len; j++)
+			seq_printf(s, "config[%d]=%d\n", j, config[j]);
+
+		seq_puts(s, "Device control:\n");
+		seq_printf(s, "Config Change %d ", dc->config_change);
+		seq_printf(s, "Vdev reset %d\n", dc->vdev_reset);
+		seq_printf(s, "Guest Ack %d ", dc->guest_ack);
+		seq_printf(s, "Host ack %d\n", dc->host_ack);
+		seq_printf(s, "Used address updated %d ",
+			dc->used_address_updated);
+		seq_printf(s, "Vdev 0x%llx\n", dc->vdev);
+		seq_printf(s, "c2h doorbell %d ", dc->c2h_vdev_db);
+		seq_printf(s, "h2c doorbell %d\n", dc->h2c_vdev_db);
+	}
+
 	return 0;
 }
 
@@ -229,6 +283,89 @@ static const struct file_operations dp_ops = {
 	.release = mic_dp_debug_release
 };
 
+static int mic_vdev_info_show(struct seq_file *s, void *unused)
+{
+	struct mic_device *mdev = s->private;
+	struct list_head *pos, *tmp;
+	struct mic_vdev *mvdev;
+	int i, j;
+
+	mutex_lock(&mdev->mic_mutex);
+	list_for_each_safe(pos, tmp, &mdev->vdev_list) {
+		mvdev = list_entry(pos, struct mic_vdev, list);
+		seq_printf(s, "VDEV type %d state %s in %ld out %ld\n",
+			mvdev->virtio_id,
+			mic_vdevup(mvdev) ? "UP" : "DOWN",
+			mvdev->in_bytes,
+			mvdev->out_bytes);
+		for (i = 0; i < MIC_MAX_VRINGS; i++) {
+			struct vring_desc *desc;
+			struct vring_avail *avail;
+			struct vring_used *used;
+			struct mic_vringh *mvr = &mvdev->mvr[i];
+			struct vringh *vrh = &mvr->vrh;
+			int num = vrh->vring.num;
+			if (!num)
+				continue;
+			desc = vrh->vring.desc;
+			seq_printf(s, "vring i %d avail_idx %d",
+				i, mvr->vring.info->avail_idx & (num - 1));
+			seq_printf(s, " vring i %d avail_idx %d\n",
+				i, mvr->vring.info->avail_idx);
+			seq_printf(s, "vrh i %d weak_barriers %d",
+				i, vrh->weak_barriers);
+			seq_printf(s, " last_avail_idx %d last_used_idx %d",
+				vrh->last_avail_idx, vrh->last_used_idx);
+			seq_printf(s, " completed %d\n", vrh->completed);
+			for (j = 0; j < num; j++) {
+				seq_printf(s, "desc[%d] addr 0x%llx len %d",
+					j, desc->addr, desc->len);
+				seq_printf(s, " flags 0x%x next %d\n",
+					desc->flags,
+					desc->next);
+				desc++;
+			}
+			avail = vrh->vring.avail;
+			seq_printf(s, "avail flags 0x%x idx %d\n",
+				avail->flags, avail->idx & (num - 1));
+			seq_printf(s, "avail flags 0x%x idx %d\n",
+				avail->flags, avail->idx);
+			for (j = 0; j < num; j++)
+				seq_printf(s, "avail ring[%d] %d\n",
+					j, avail->ring[j]);
+			used = vrh->vring.used;
+			seq_printf(s, "used flags 0x%x idx %d\n",
+				used->flags, used->idx & (num - 1));
+			seq_printf(s, "used flags 0x%x idx %d\n",
+				used->flags, used->idx);
+			for (j = 0; j < num; j++)
+				seq_printf(s, "used ring[%d] id %d len %d\n",
+					j, used->ring[j].id, used->ring[j].len);
+		}
+	}
+	mutex_unlock(&mdev->mic_mutex);
+
+	return 0;
+}
+
+static int mic_vdev_info_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mic_vdev_info_show, inode->i_private);
+}
+
+static int mic_vdev_info_debug_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static const struct file_operations vdev_info_ops = {
+	.owner   = THIS_MODULE,
+	.open    = mic_vdev_info_debug_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = mic_vdev_info_debug_release
+};
+
 static int mic_msi_irq_info_show(struct seq_file *s, void *pos)
 {
 	struct mic_device *mdev  = s->private;
@@ -321,6 +458,9 @@ void mic_create_debug_dir(struct mic_device *mdev)
 	debugfs_create_file("dp", 0444, mdev->dbg_dir,
 		mdev, &dp_ops);
 
+	debugfs_create_file("vdev_info", 0444, mdev->dbg_dir,
+		mdev, &vdev_info_ops);
+
 	debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir,
 		mdev, &msi_irq_info_ops);
 }
diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h
index 50b8b88d70d3..dcba2a59e77f 100644
--- a/drivers/misc/mic/host/mic_device.h
+++ b/drivers/misc/mic/host/mic_device.h
@@ -21,6 +21,7 @@
 #ifndef _MIC_DEVICE_H_
 #define _MIC_DEVICE_H_
 
+#include <linux/cdev.h>
 #include <linux/idr.h>
 
 #include "mic_intr.h"
@@ -80,6 +81,8 @@ enum mic_stepping {
  * @dp_dma_addr: virtio device page DMA address.
  * @shutdown_db: shutdown doorbell.
  * @shutdown_cookie: shutdown cookie.
+ * @cdev: Character device for MIC.
+ * @vdev_list: list of virtio devices.
  */
 struct mic_device {
 	struct mic_mw mmio;
@@ -113,6 +116,8 @@ struct mic_device {
 	dma_addr_t dp_dma_addr;
 	int shutdown_db;
 	struct mic_irq *shutdown_cookie;
+	struct cdev cdev;
+	struct list_head vdev_list;
 };
 
 /**
diff --git a/drivers/misc/mic/host/mic_fops.c b/drivers/misc/mic/host/mic_fops.c
new file mode 100644
index 000000000000..661469ad339d
--- /dev/null
+++ b/drivers/misc/mic/host/mic_fops.c
@@ -0,0 +1,221 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#include <linux/poll.h>
+
+#include <linux/mic_common.h>
+#include "../common/mic_device.h"
+#include "mic_device.h"
+#include "mic_fops.h"
+#include "mic_virtio.h"
+
+int mic_open(struct inode *inode, struct file *f)
+{
+	struct mic_vdev *mvdev;
+	struct mic_device *mdev = container_of(inode->i_cdev,
+		struct mic_device, cdev);
+
+	mvdev = kzalloc(sizeof(*mvdev), GFP_KERNEL);
+	if (!mvdev)
+		return -ENOMEM;
+
+	init_waitqueue_head(&mvdev->waitq);
+	INIT_LIST_HEAD(&mvdev->list);
+	mvdev->mdev = mdev;
+	mvdev->virtio_id = -1;
+
+	f->private_data = mvdev;
+	return 0;
+}
+
+int mic_release(struct inode *inode, struct file *f)
+{
+	struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data;
+
+	if (-1 != mvdev->virtio_id)
+		mic_virtio_del_device(mvdev);
+	f->private_data = NULL;
+	kfree(mvdev);
+	return 0;
+}
+
+long mic_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
+{
+	struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data;
+	void __user *argp = (void __user *)arg;
+	int ret;
+
+	switch (cmd) {
+	case MIC_VIRTIO_ADD_DEVICE:
+	{
+		ret = mic_virtio_add_device(mvdev, argp);
+		if (ret < 0) {
+			dev_err(mic_dev(mvdev),
+				"%s %d errno ret %d\n",
+				__func__, __LINE__, ret);
+			return ret;
+		}
+		break;
+	}
+	case MIC_VIRTIO_COPY_DESC:
+	{
+		struct mic_copy_desc copy;
+
+		ret = mic_vdev_inited(mvdev);
+		if (ret)
+			return ret;
+
+		if (copy_from_user(&copy, argp, sizeof(copy)))
+			return -EFAULT;
+
+		dev_dbg(mic_dev(mvdev),
+			"%s %d === iovcnt 0x%x vr_idx 0x%x update_used %d\n",
+			__func__, __LINE__, copy.iovcnt, copy.vr_idx,
+			copy.update_used);
+
+		ret = mic_virtio_copy_desc(mvdev, &copy);
+		if (ret < 0) {
+			dev_err(mic_dev(mvdev),
+				"%s %d errno ret %d\n",
+				__func__, __LINE__, ret);
+			return ret;
+		}
+		if (copy_to_user(
+			&((struct mic_copy_desc __user *)argp)->out_len,
+			&copy.out_len, sizeof(copy.out_len))) {
+			dev_err(mic_dev(mvdev), "%s %d errno ret %d\n",
+				__func__, __LINE__, -EFAULT);
+			return -EFAULT;
+		}
+		break;
+	}
+	case MIC_VIRTIO_CONFIG_CHANGE:
+	{
+		ret = mic_vdev_inited(mvdev);
+		if (ret)
+			return ret;
+
+		ret = mic_virtio_config_change(mvdev, argp);
+		if (ret < 0) {
+			dev_err(mic_dev(mvdev),
+				"%s %d errno ret %d\n",
+				__func__, __LINE__, ret);
+			return ret;
+		}
+		break;
+	}
+	default:
+		return -ENOIOCTLCMD;
+	};
+	return 0;
+}
+
+/*
+ * We return POLLIN | POLLOUT from poll when new buffers are enqueued, and
+ * not when previously enqueued buffers may be available. This means that
+ * in the card->host (TX) path, when userspace is unblocked by poll it
+ * must drain all available descriptors or it can stall.
+ */
+unsigned int mic_poll(struct file *f, poll_table *wait)
+{
+	struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data;
+	int mask = 0;
+
+	poll_wait(f, &mvdev->waitq, wait);
+
+	if (mic_vdev_inited(mvdev))
+		mask = POLLERR;
+	else if (mvdev->poll_wake) {
+		mvdev->poll_wake = 0;
+		mask = POLLIN | POLLOUT;
+	}
+
+	return mask;
+}
+
+static inline int
+mic_query_offset(struct mic_vdev *mvdev, unsigned long offset,
+	unsigned long *size, unsigned long *pa)
+{
+	struct mic_device *mdev = mvdev->mdev;
+	unsigned long start = MIC_DP_SIZE;
+	int i;
+
+	/*
+	 * MMAP interface is as follows:
+	 * offset				region
+	 * 0x0					virtio device_page
+	 * 0x1000				first vring
+	 * 0x1000 + size of 1st vring		second vring
+	 * ....
+	 */
+	if (!offset) {
+		*pa = virt_to_phys(mdev->dp);
+		*size = MIC_DP_SIZE;
+		return 0;
+	}
+
+	for (i = 0; i < mvdev->dd->num_vq; i++) {
+		struct mic_vringh *mvr = &mvdev->mvr[i];
+		if (offset == start) {
+			*pa = virt_to_phys(mvr->vring.va);
+			*size = mvr->vring.len;
+			return 0;
+		}
+		start += mvr->vring.len;
+	}
+	return -1;
+}
+
+/*
+ * Maps the device page and virtio rings to user space for readonly access.
+ */
+int
+mic_mmap(struct file *f, struct vm_area_struct *vma)
+{
+	struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data;
+	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
+	unsigned long pa, size = vma->vm_end - vma->vm_start, size_rem = size;
+	int i, err;
+
+	err = mic_vdev_inited(mvdev);
+	if (err)
+		return err;
+
+	if (vma->vm_flags & VM_WRITE)
+		return -EACCES;
+
+	while (size_rem) {
+		i = mic_query_offset(mvdev, offset, &size, &pa);
+		if (i < 0)
+			return -EINVAL;
+		err = remap_pfn_range(vma, vma->vm_start + offset,
+			pa >> PAGE_SHIFT, size, vma->vm_page_prot);
+		if (err)
+			return err;
+		dev_dbg(mic_dev(mvdev),
+			"%s %d type %d size 0x%lx off 0x%lx pa 0x%lx vma 0x%lx\n",
+			__func__, __LINE__, mvdev->virtio_id, size, offset,
+			pa, vma->vm_start + offset);
+		size_rem -= size;
+		offset += size;
+	}
+	return 0;
+}
diff --git a/drivers/misc/mic/host/mic_fops.h b/drivers/misc/mic/host/mic_fops.h
new file mode 100644
index 000000000000..dc3893dff667
--- /dev/null
+++ b/drivers/misc/mic/host/mic_fops.h
@@ -0,0 +1,32 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#ifndef _MIC_FOPS_H_
+#define _MIC_FOPS_H_
+
+int mic_open(struct inode *inode, struct file *filp);
+int mic_release(struct inode *inode, struct file *filp);
+ssize_t mic_read(struct file *filp, char __user *buf,
+			size_t count, loff_t *pos);
+long mic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+int mic_mmap(struct file *f, struct vm_area_struct *vma);
+unsigned int mic_poll(struct file *f, poll_table *wait);
+
+#endif
diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c
index 998a20ab7e96..a8965d496e84 100644
--- a/drivers/misc/mic/host/mic_main.c
+++ b/drivers/misc/mic/host/mic_main.c
@@ -25,12 +25,15 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/poll.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_device.h"
 #include "mic_device.h"
 #include "mic_x100.h"
 #include "mic_smpt.h"
+#include "mic_fops.h"
+#include "mic_virtio.h"
 
 static const char mic_driver_name[] = "mic";
 
@@ -64,6 +67,15 @@ static struct class *g_mic_class;
 /* Base device node number for MIC devices */
 static dev_t g_mic_devno;
 
+static const struct file_operations mic_fops = {
+	.open = mic_open,
+	.release = mic_release,
+	.unlocked_ioctl = mic_ioctl,
+	.poll = mic_poll,
+	.mmap = mic_mmap,
+	.owner = THIS_MODULE,
+};
+
 /* Initialize the device page */
 static int mic_dp_init(struct mic_device *mdev)
 {
@@ -193,6 +205,7 @@ mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
 	mdev->irq_info.next_avail_src = 0;
 	INIT_WORK(&mdev->reset_trigger_work, mic_reset_trigger_work);
 	INIT_WORK(&mdev->shutdown_work, mic_shutdown_work);
+	INIT_LIST_HEAD(&mdev->vdev_list);
 }
 
 /**
@@ -330,7 +343,19 @@ static int mic_probe(struct pci_dev *pdev,
 	mic_bootparam_init(mdev);
 
 	mic_create_debug_dir(mdev);
+	cdev_init(&mdev->cdev, &mic_fops);
+	mdev->cdev.owner = THIS_MODULE;
+	rc = cdev_add(&mdev->cdev, MKDEV(MAJOR(g_mic_devno), mdev->id), 1);
+	if (rc) {
+		dev_err(&pdev->dev, "cdev_add err id %d rc %d\n", mdev->id, rc);
+		goto cleanup_debug_dir;
+	}
 	return 0;
+cleanup_debug_dir:
+	mic_delete_debug_dir(mdev);
+	mutex_lock(&mdev->mic_mutex);
+	mic_free_irq(mdev, mdev->shutdown_cookie, mdev);
+	mutex_unlock(&mdev->mic_mutex);
 dp_uninit:
 	mic_dp_uninit(mdev);
 sysfs_put:
@@ -375,6 +400,7 @@ static void mic_remove(struct pci_dev *pdev)
 		return;
 
 	mic_stop(mdev, false);
+	cdev_del(&mdev->cdev);
 	mic_delete_debug_dir(mdev);
 	mutex_lock(&mdev->mic_mutex);
 	mic_free_irq(mdev, mdev->shutdown_cookie, mdev);
diff --git a/drivers/misc/mic/host/mic_virtio.c b/drivers/misc/mic/host/mic_virtio.c
new file mode 100644
index 000000000000..be2a1f06c4ca
--- /dev/null
+++ b/drivers/misc/mic/host/mic_virtio.c
@@ -0,0 +1,703 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#include <linux/pci.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include <linux/mic_common.h>
+#include "../common/mic_device.h"
+#include "mic_device.h"
+#include "mic_smpt.h"
+#include "mic_virtio.h"
+
+/*
+ * Initiates the copies across the PCIe bus from card memory to
+ * a user space buffer.
+ */
+static int mic_virtio_copy_to_user(struct mic_vdev *mvdev,
+		void __user *ubuf, size_t len, u64 addr)
+{
+	int err;
+	void __iomem *dbuf = mvdev->mdev->aper.va + addr;
+	/*
+	 * We are copying from IO below an should ideally use something
+	 * like copy_to_user_fromio(..) if it existed.
+	 */
+	if (copy_to_user(ubuf, dbuf, len)) {
+		err = -EFAULT;
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, err);
+		goto err;
+	}
+	mvdev->in_bytes += len;
+	err = 0;
+err:
+	return err;
+}
+
+/*
+ * Initiates copies across the PCIe bus from a user space
+ * buffer to card memory.
+ */
+static int mic_virtio_copy_from_user(struct mic_vdev *mvdev,
+		void __user *ubuf, size_t len, u64 addr)
+{
+	int err;
+	void __iomem *dbuf = mvdev->mdev->aper.va + addr;
+	/*
+	 * We are copying to IO below and should ideally use something
+	 * like copy_from_user_toio(..) if it existed.
+	 */
+	if (copy_from_user(dbuf, ubuf, len)) {
+		err = -EFAULT;
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, err);
+		goto err;
+	}
+	mvdev->out_bytes += len;
+	err = 0;
+err:
+	return err;
+}
+
+#define MIC_VRINGH_READ true
+
+/* The function to call to notify the card about added buffers */
+static void mic_notify(struct vringh *vrh)
+{
+	struct mic_vringh *mvrh = container_of(vrh, struct mic_vringh, vrh);
+	struct mic_vdev *mvdev = mvrh->mvdev;
+	s8 db = mvdev->dc->h2c_vdev_db;
+
+	if (db != -1)
+		mvdev->mdev->ops->send_intr(mvdev->mdev, db);
+}
+
+/* Determine the total number of bytes consumed in a VRINGH KIOV */
+static inline u32 mic_vringh_iov_consumed(struct vringh_kiov *iov)
+{
+	int i;
+	u32 total = iov->consumed;
+
+	for (i = 0; i < iov->i; i++)
+		total += iov->iov[i].iov_len;
+	return total;
+}
+
+/*
+ * Traverse the VRINGH KIOV and issue the APIs to trigger the copies.
+ * This API is heavily based on the vringh_iov_xfer(..) implementation
+ * in vringh.c. The reason we cannot reuse vringh_iov_pull_kern(..)
+ * and vringh_iov_push_kern(..) directly is because there is no
+ * way to override the VRINGH xfer(..) routines as of v3.10.
+ */
+static int mic_vringh_copy(struct mic_vdev *mvdev, struct vringh_kiov *iov,
+	void __user *ubuf, size_t len, bool read, size_t *out_len)
+{
+	int ret = 0;
+	size_t partlen, tot_len = 0;
+
+	while (len && iov->i < iov->used) {
+		partlen = min(iov->iov[iov->i].iov_len, len);
+		if (read)
+			ret = mic_virtio_copy_to_user(mvdev,
+				ubuf, partlen,
+				(u64)iov->iov[iov->i].iov_base);
+		else
+			ret = mic_virtio_copy_from_user(mvdev,
+				ubuf, partlen,
+				(u64)iov->iov[iov->i].iov_base);
+		if (ret) {
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+				__func__, __LINE__, ret);
+			break;
+		}
+		len -= partlen;
+		ubuf += partlen;
+		tot_len += partlen;
+		iov->consumed += partlen;
+		iov->iov[iov->i].iov_len -= partlen;
+		iov->iov[iov->i].iov_base += partlen;
+		if (!iov->iov[iov->i].iov_len) {
+			/* Fix up old iov element then increment. */
+			iov->iov[iov->i].iov_len = iov->consumed;
+			iov->iov[iov->i].iov_base -= iov->consumed;
+
+			iov->consumed = 0;
+			iov->i++;
+		}
+	}
+	*out_len = tot_len;
+	return ret;
+}
+
+/*
+ * Use the standard VRINGH infrastructure in the kernel to fetch new
+ * descriptors, initiate the copies and update the used ring.
+ */
+static int _mic_virtio_copy(struct mic_vdev *mvdev,
+	struct mic_copy_desc *copy)
+{
+	int ret = 0, iovcnt = copy->iovcnt;
+	struct iovec iov;
+	struct iovec __user *u_iov = copy->iov;
+	void __user *ubuf = NULL;
+	struct mic_vringh *mvr = &mvdev->mvr[copy->vr_idx];
+	struct vringh_kiov *riov = &mvr->riov;
+	struct vringh_kiov *wiov = &mvr->wiov;
+	struct vringh *vrh = &mvr->vrh;
+	u16 *head = &mvr->head;
+	struct mic_vring *vr = &mvr->vring;
+	size_t len = 0, out_len;
+
+	copy->out_len = 0;
+	/* Fetch a new IOVEC if all previous elements have been processed */
+	if (riov->i == riov->used && wiov->i == wiov->used) {
+		ret = vringh_getdesc_kern(vrh, riov, wiov,
+				head, GFP_KERNEL);
+		/* Check if there are available descriptors */
+		if (ret <= 0)
+			return ret;
+	}
+	while (iovcnt) {
+		if (!len) {
+			/* Copy over a new iovec from user space. */
+			ret = copy_from_user(&iov, u_iov, sizeof(*u_iov));
+			if (ret) {
+				ret = -EINVAL;
+				dev_err(mic_dev(mvdev), "%s %d err %d\n",
+					__func__, __LINE__, ret);
+				break;
+			}
+			len = iov.iov_len;
+			ubuf = iov.iov_base;
+		}
+		/* Issue all the read descriptors first */
+		ret = mic_vringh_copy(mvdev, riov, ubuf, len,
+			MIC_VRINGH_READ, &out_len);
+		if (ret) {
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+					__func__, __LINE__, ret);
+			break;
+		}
+		len -= out_len;
+		ubuf += out_len;
+		copy->out_len += out_len;
+		/* Issue the write descriptors next */
+		ret = mic_vringh_copy(mvdev, wiov, ubuf, len,
+			!MIC_VRINGH_READ, &out_len);
+		if (ret) {
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+					__func__, __LINE__, ret);
+			break;
+		}
+		len -= out_len;
+		ubuf += out_len;
+		copy->out_len += out_len;
+		if (!len) {
+			/* One user space iovec is now completed */
+			iovcnt--;
+			u_iov++;
+		}
+		/* Exit loop if all elements in KIOVs have been processed. */
+		if (riov->i == riov->used && wiov->i == wiov->used)
+			break;
+	}
+	/*
+	 * Update the used ring if a descriptor was available and some data was
+	 * copied in/out and the user asked for a used ring update.
+	 */
+	if (*head != USHRT_MAX && copy->out_len &&
+		copy->update_used) {
+		u32 total = 0;
+
+		/* Determine the total data consumed */
+		total += mic_vringh_iov_consumed(riov);
+		total += mic_vringh_iov_consumed(wiov);
+		vringh_complete_kern(vrh, *head, total);
+		*head = USHRT_MAX;
+		if (vringh_need_notify_kern(vrh) > 0)
+			vringh_notify(vrh);
+		vringh_kiov_cleanup(riov);
+		vringh_kiov_cleanup(wiov);
+		/* Update avail idx for user space */
+		vr->info->avail_idx = vrh->last_avail_idx;
+	}
+	return ret;
+}
+
+static inline int mic_verify_copy_args(struct mic_vdev *mvdev,
+		struct mic_copy_desc *copy)
+{
+	if (copy->vr_idx >= mvdev->dd->num_vq) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -EINVAL);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Copy a specified number of virtio descriptors in a chain */
+int mic_virtio_copy_desc(struct mic_vdev *mvdev,
+		struct mic_copy_desc *copy)
+{
+	int err;
+	struct mic_vringh *mvr = &mvdev->mvr[copy->vr_idx];
+
+	err = mic_verify_copy_args(mvdev, copy);
+	if (err)
+		return err;
+
+	mutex_lock(&mvr->vr_mutex);
+	if (!mic_vdevup(mvdev)) {
+		err = -ENODEV;
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, err);
+		goto err;
+	}
+	err = _mic_virtio_copy(mvdev, copy);
+	if (err) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, err);
+	}
+err:
+	mutex_unlock(&mvr->vr_mutex);
+	return err;
+}
+
+static void mic_virtio_init_post(struct mic_vdev *mvdev)
+{
+	struct mic_vqconfig *vqconfig = mic_vq_config(mvdev->dd);
+	int i;
+
+	for (i = 0; i < mvdev->dd->num_vq; i++) {
+		if (!le64_to_cpu(vqconfig[i].used_address)) {
+			dev_warn(mic_dev(mvdev), "used_address zero??\n");
+			continue;
+		}
+		mvdev->mvr[i].vrh.vring.used =
+			mvdev->mdev->aper.va +
+			le64_to_cpu(vqconfig[i].used_address);
+	}
+
+	mvdev->dc->used_address_updated = 0;
+
+	dev_dbg(mic_dev(mvdev), "%s: device type %d LINKUP\n",
+		__func__, mvdev->virtio_id);
+}
+
+static inline void mic_virtio_device_reset(struct mic_vdev *mvdev)
+{
+	int i;
+
+	dev_dbg(mic_dev(mvdev), "%s: status %d device type %d RESET\n",
+		__func__, mvdev->dd->status, mvdev->virtio_id);
+
+	for (i = 0; i < mvdev->dd->num_vq; i++)
+		/*
+		 * Avoid lockdep false positive. The + 1 is for the mic
+		 * mutex which is held in the reset devices code path.
+		 */
+		mutex_lock_nested(&mvdev->mvr[i].vr_mutex, i + 1);
+
+	/* 0 status means "reset" */
+	mvdev->dd->status = 0;
+	mvdev->dc->vdev_reset = 0;
+	mvdev->dc->host_ack = 1;
+
+	for (i = 0; i < mvdev->dd->num_vq; i++) {
+		struct vringh *vrh = &mvdev->mvr[i].vrh;
+		mvdev->mvr[i].vring.info->avail_idx = 0;
+		vrh->completed = 0;
+		vrh->last_avail_idx = 0;
+		vrh->last_used_idx = 0;
+	}
+
+	for (i = 0; i < mvdev->dd->num_vq; i++)
+		mutex_unlock(&mvdev->mvr[i].vr_mutex);
+}
+
+void mic_virtio_reset_devices(struct mic_device *mdev)
+{
+	struct list_head *pos, *tmp;
+	struct mic_vdev *mvdev;
+
+	dev_dbg(mdev->sdev->parent, "%s\n",  __func__);
+
+	list_for_each_safe(pos, tmp, &mdev->vdev_list) {
+		mvdev = list_entry(pos, struct mic_vdev, list);
+		mic_virtio_device_reset(mvdev);
+		mvdev->poll_wake = 1;
+		wake_up(&mvdev->waitq);
+	}
+}
+
+void mic_bh_handler(struct work_struct *work)
+{
+	struct mic_vdev *mvdev = container_of(work, struct mic_vdev,
+			virtio_bh_work);
+
+	if (mvdev->dc->used_address_updated)
+		mic_virtio_init_post(mvdev);
+
+	if (mvdev->dc->vdev_reset)
+		mic_virtio_device_reset(mvdev);
+
+	mvdev->poll_wake = 1;
+	wake_up(&mvdev->waitq);
+}
+
+static irqreturn_t mic_virtio_intr_handler(int irq, void *data)
+{
+
+	struct mic_vdev *mvdev = data;
+	struct mic_device *mdev = mvdev->mdev;
+
+	mdev->ops->ack_interrupt(mdev);
+	schedule_work(&mvdev->virtio_bh_work);
+	return IRQ_HANDLED;
+}
+
+int mic_virtio_config_change(struct mic_vdev *mvdev,
+			void __user *argp)
+{
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
+	int ret = 0, retry = 100, i;
+	struct mic_bootparam *bootparam = mvdev->mdev->dp;
+	s8 db = bootparam->h2c_config_db;
+
+	mutex_lock(&mvdev->mdev->mic_mutex);
+	for (i = 0; i < mvdev->dd->num_vq; i++)
+		mutex_lock_nested(&mvdev->mvr[i].vr_mutex, i + 1);
+
+	if (db == -1 || mvdev->dd->type == -1) {
+		ret = -EIO;
+		goto exit;
+	}
+
+	if (copy_from_user(mic_vq_configspace(mvdev->dd),
+				argp, mvdev->dd->config_len)) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -EFAULT);
+		ret = -EFAULT;
+		goto exit;
+	}
+	mvdev->dc->config_change = MIC_VIRTIO_PARAM_CONFIG_CHANGED;
+	mvdev->mdev->ops->send_intr(mvdev->mdev, db);
+
+	for (i = retry; i--;) {
+		ret = wait_event_timeout(wake,
+			mvdev->dc->guest_ack, msecs_to_jiffies(100));
+		if (ret)
+			break;
+	}
+
+	dev_dbg(mic_dev(mvdev),
+		"%s %d retry: %d\n", __func__, __LINE__, retry);
+	mvdev->dc->config_change = 0;
+	mvdev->dc->guest_ack = 0;
+exit:
+	for (i = 0; i < mvdev->dd->num_vq; i++)
+		mutex_unlock(&mvdev->mvr[i].vr_mutex);
+	mutex_unlock(&mvdev->mdev->mic_mutex);
+	return ret;
+}
+
+static int mic_copy_dp_entry(struct mic_vdev *mvdev,
+					void __user *argp,
+					__u8 *type,
+					struct mic_device_desc **devpage)
+{
+	struct mic_device *mdev = mvdev->mdev;
+	struct mic_device_desc dd, *dd_config, *devp;
+	struct mic_vqconfig *vqconfig;
+	int ret = 0, i;
+	bool slot_found = false;
+
+	if (copy_from_user(&dd, argp, sizeof(dd))) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -EFAULT);
+		return -EFAULT;
+	}
+
+	if (mic_aligned_desc_size(&dd) > MIC_MAX_DESC_BLK_SIZE
+		|| dd.num_vq > MIC_MAX_VRINGS) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -EINVAL);
+		return -EINVAL;
+	}
+
+	dd_config = kmalloc(mic_desc_size(&dd), GFP_KERNEL);
+	if (dd_config == NULL) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -ENOMEM);
+		return -ENOMEM;
+	}
+	if (copy_from_user(dd_config, argp, mic_desc_size(&dd))) {
+		ret = -EFAULT;
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, ret);
+		goto exit;
+	}
+
+	vqconfig = mic_vq_config(dd_config);
+	for (i = 0; i < dd.num_vq; i++) {
+		if (le16_to_cpu(vqconfig[i].num) > MIC_MAX_VRING_ENTRIES) {
+			ret =  -EINVAL;
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+				__func__, __LINE__, ret);
+			goto exit;
+		}
+	}
+
+	/* Find the first free device page entry */
+	for (i = mic_aligned_size(struct mic_bootparam);
+		i < MIC_DP_SIZE - mic_total_desc_size(dd_config);
+		i += mic_total_desc_size(devp)) {
+		devp = mdev->dp + i;
+		if (devp->type == 0 || devp->type == -1) {
+			slot_found = true;
+			break;
+		}
+	}
+	if (!slot_found) {
+		ret =  -EINVAL;
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, ret);
+		goto exit;
+	}
+	/*
+	 * Save off the type before doing the memcpy. Type will be set in the
+	 * end after completing all initialization for the new device.
+	 */
+	*type = dd_config->type;
+	dd_config->type = 0;
+	memcpy(devp, dd_config, mic_desc_size(dd_config));
+
+	*devpage = devp;
+exit:
+	kfree(dd_config);
+	return ret;
+}
+
+static void mic_init_device_ctrl(struct mic_vdev *mvdev,
+				struct mic_device_desc *devpage)
+{
+	struct mic_device_ctrl *dc;
+
+	dc = mvdev->dc = (void *)devpage + mic_aligned_desc_size(devpage);
+
+	dc->config_change = 0;
+	dc->guest_ack = 0;
+	dc->vdev_reset = 0;
+	dc->host_ack = 0;
+	dc->used_address_updated = 0;
+	dc->c2h_vdev_db = -1;
+	dc->h2c_vdev_db = -1;
+}
+
+int mic_virtio_add_device(struct mic_vdev *mvdev,
+			void __user *argp)
+{
+	struct mic_device *mdev = mvdev->mdev;
+	struct mic_device_desc *dd;
+	struct mic_vqconfig *vqconfig;
+	int vr_size, i, j, ret;
+	u8 type;
+	s8 db;
+	char irqname[10];
+	struct mic_bootparam *bootparam = mdev->dp;
+	u16 num;
+
+	mutex_lock(&mdev->mic_mutex);
+
+	ret = mic_copy_dp_entry(mvdev, argp, &type, &dd);
+	if (ret) {
+		mutex_unlock(&mdev->mic_mutex);
+		return ret;
+	}
+
+	mic_init_device_ctrl(mvdev, dd);
+
+	mvdev->dd = dd;
+	mvdev->virtio_id = type;
+	vqconfig = mic_vq_config(dd);
+	INIT_WORK(&mvdev->virtio_bh_work, mic_bh_handler);
+
+	for (i = 0; i < dd->num_vq; i++) {
+		struct mic_vringh *mvr = &mvdev->mvr[i];
+		struct mic_vring *vr = &mvdev->mvr[i].vring;
+		num = le16_to_cpu(vqconfig[i].num);
+		mutex_init(&mvr->vr_mutex);
+		vr_size = PAGE_ALIGN(vring_size(num, MIC_VIRTIO_RING_ALIGN) +
+			sizeof(struct _mic_vring_info));
+		vr->va = (void *)
+			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+			get_order(vr_size));
+		if (!vr->va) {
+			ret = -ENOMEM;
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+				__func__, __LINE__, ret);
+			goto err;
+		}
+		vr->len = vr_size;
+		vr->info = vr->va + vring_size(num, MIC_VIRTIO_RING_ALIGN);
+		vr->info->magic = MIC_MAGIC + mvdev->virtio_id + i;
+		vqconfig[i].address = mic_map_single(mdev,
+			vr->va, vr_size);
+		if (mic_map_error(vqconfig[i].address)) {
+			free_pages((unsigned long)vr->va,
+				get_order(vr_size));
+			ret = -ENOMEM;
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+				__func__, __LINE__, ret);
+			goto err;
+		}
+		vqconfig[i].address = cpu_to_le64(vqconfig[i].address);
+
+		vring_init(&vr->vr, num,
+			vr->va, MIC_VIRTIO_RING_ALIGN);
+		ret = vringh_init_kern(&mvr->vrh,
+			*(u32 *)mic_vq_features(mvdev->dd), num, false,
+			vr->vr.desc, vr->vr.avail, vr->vr.used);
+		if (ret) {
+			dev_err(mic_dev(mvdev), "%s %d err %d\n",
+				__func__, __LINE__, ret);
+			goto err;
+		}
+		vringh_kiov_init(&mvr->riov, NULL, 0);
+		vringh_kiov_init(&mvr->wiov, NULL, 0);
+		mvr->head = USHRT_MAX;
+		mvr->mvdev = mvdev;
+		mvr->vrh.notify = mic_notify;
+		dev_dbg(mdev->sdev->parent,
+			"%s %d index %d va %p info %p vr_size 0x%x\n",
+			__func__, __LINE__, i, vr->va, vr->info, vr_size);
+	}
+
+	snprintf(irqname, sizeof(irqname),
+		"mic%dvirtio%d", mdev->id, mvdev->virtio_id);
+	mvdev->virtio_db = mic_next_db(mdev);
+	mvdev->virtio_cookie = mic_request_irq(mdev, mic_virtio_intr_handler,
+			irqname, mvdev, mvdev->virtio_db, MIC_INTR_DB);
+	if (IS_ERR(mvdev->virtio_cookie)) {
+		ret = PTR_ERR(mvdev->virtio_cookie);
+		dev_dbg(mdev->sdev->parent, "request irq failed\n");
+		goto err;
+	}
+
+	mvdev->dc->c2h_vdev_db = mvdev->virtio_db;
+
+	list_add_tail(&mvdev->list, &mdev->vdev_list);
+	/*
+	 * Order the type update with previous stores. This write barrier
+	 * is paired with the corresponding read barrier before the uncached
+	 * system memory read of the type, on the card while scanning the
+	 * device page.
+	 */
+	smp_wmb();
+	dd->type = type;
+
+	dev_dbg(mdev->sdev->parent, "Added virtio device id %d\n", dd->type);
+
+	db = bootparam->h2c_config_db;
+	if (db != -1)
+		mdev->ops->send_intr(mdev, db);
+	mutex_unlock(&mdev->mic_mutex);
+	return 0;
+err:
+	vqconfig = mic_vq_config(dd);
+	for (j = 0; j < i; j++) {
+		struct mic_vringh *mvr = &mvdev->mvr[j];
+		mic_unmap_single(mdev, le64_to_cpu(vqconfig[j].address),
+				mvr->vring.len);
+		free_pages((unsigned long)mvr->vring.va,
+			get_order(mvr->vring.len));
+	}
+	mutex_unlock(&mdev->mic_mutex);
+	return ret;
+}
+
+void mic_virtio_del_device(struct mic_vdev *mvdev)
+{
+	struct list_head *pos, *tmp;
+	struct mic_vdev *tmp_mvdev;
+	struct mic_device *mdev = mvdev->mdev;
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
+	int i, ret, retry = 100;
+	struct mic_vqconfig *vqconfig;
+	struct mic_bootparam *bootparam = mdev->dp;
+	s8 db;
+
+	mutex_lock(&mdev->mic_mutex);
+	db = bootparam->h2c_config_db;
+	if (db == -1)
+		goto skip_hot_remove;
+	dev_dbg(mdev->sdev->parent,
+		"Requesting hot remove id %d\n", mvdev->virtio_id);
+	mvdev->dc->config_change = MIC_VIRTIO_PARAM_DEV_REMOVE;
+	mdev->ops->send_intr(mdev, db);
+	for (i = retry; i--;) {
+		ret = wait_event_timeout(wake,
+			mvdev->dc->guest_ack, msecs_to_jiffies(100));
+		if (ret)
+			break;
+	}
+	dev_dbg(mdev->sdev->parent,
+		"Device id %d config_change %d guest_ack %d\n",
+		mvdev->virtio_id, mvdev->dc->config_change,
+		mvdev->dc->guest_ack);
+	mvdev->dc->config_change = 0;
+	mvdev->dc->guest_ack = 0;
+skip_hot_remove:
+	mic_free_irq(mdev, mvdev->virtio_cookie, mvdev);
+	flush_work(&mvdev->virtio_bh_work);
+	vqconfig = mic_vq_config(mvdev->dd);
+	for (i = 0; i < mvdev->dd->num_vq; i++) {
+		struct mic_vringh *mvr = &mvdev->mvr[i];
+		vringh_kiov_cleanup(&mvr->riov);
+		vringh_kiov_cleanup(&mvr->wiov);
+		mic_unmap_single(mdev, le64_to_cpu(vqconfig[i].address),
+				mvr->vring.len);
+		free_pages((unsigned long)mvr->vring.va,
+			get_order(mvr->vring.len));
+	}
+
+	list_for_each_safe(pos, tmp, &mdev->vdev_list) {
+		tmp_mvdev = list_entry(pos, struct mic_vdev, list);
+		if (tmp_mvdev == mvdev) {
+			list_del(pos);
+			dev_dbg(mdev->sdev->parent,
+				"Removing virtio device id %d\n",
+				mvdev->virtio_id);
+			break;
+		}
+	}
+	/*
+	 * Order the type update with previous stores. This write barrier
+	 * is paired with the corresponding read barrier before the uncached
+	 * system memory read of the type, on the card while scanning the
+	 * device page.
+	 */
+	smp_wmb();
+	mvdev->dd->type = -1;
+	mutex_unlock(&mdev->mic_mutex);
+}
diff --git a/drivers/misc/mic/host/mic_virtio.h b/drivers/misc/mic/host/mic_virtio.h
new file mode 100644
index 000000000000..184f3c84805b
--- /dev/null
+++ b/drivers/misc/mic/host/mic_virtio.h
@@ -0,0 +1,138 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#ifndef MIC_VIRTIO_H
+#define MIC_VIRTIO_H
+
+#include <linux/virtio_config.h>
+#include <linux/mic_ioctl.h>
+
+/*
+ * Note on endianness.
+ * 1. Host can be both BE or LE
+ * 2. Guest/card is LE. Host uses le_to_cpu to access desc/avail
+ *    rings and ioreadXX/iowriteXX to access used ring.
+ * 3. Device page exposed by host to guest contains LE values. Guest
+ *    accesses these using ioreadXX/iowriteXX etc. This way in general we
+ *    obey the virtio spec according to which guest works with native
+ *    endianness and host is aware of guest endianness and does all
+ *    required endianness conversion.
+ * 4. Data provided from user space to guest (in ADD_DEVICE and
+ *    CONFIG_CHANGE ioctl's) is not interpreted by the driver and should be
+ *    in guest endianness.
+ */
+
+/**
+ * struct mic_vringh - Virtio ring host information.
+ *
+ * @vring: The MIC vring used for setting up user space mappings.
+ * @vrh: The host VRINGH used for accessing the card vrings.
+ * @riov: The VRINGH read kernel IOV.
+ * @wiov: The VRINGH write kernel IOV.
+ * @head: The VRINGH head index address passed to vringh_getdesc_kern(..).
+ * @vr_mutex: Mutex for synchronizing access to the VRING.
+ * @mvdev: Back pointer to MIC virtio device for vringh_notify(..).
+ */
+struct mic_vringh {
+	struct mic_vring vring;
+	struct vringh vrh;
+	struct vringh_kiov riov;
+	struct vringh_kiov wiov;
+	u16 head;
+	struct mutex vr_mutex;
+	struct mic_vdev *mvdev;
+};
+
+/**
+ * struct mic_vdev - Host information for a card Virtio device.
+ *
+ * @virtio_id - Virtio device id.
+ * @waitq - Waitqueue to allow ring3 apps to poll.
+ * @mdev - Back pointer to host MIC device.
+ * @poll_wake - Used for waking up threads blocked in poll.
+ * @out_bytes - Debug stats for number of bytes copied from host to card.
+ * @in_bytes - Debug stats for number of bytes copied from card to host.
+ * @mvr - Store per VRING data structures.
+ * @virtio_bh_work - Work struct used to schedule virtio bottom half handling.
+ * @dd - Virtio device descriptor.
+ * @dc - Virtio device control fields.
+ * @list - List of Virtio devices.
+ * @virtio_db - The doorbell used by the card to interrupt the host.
+ * @virtio_cookie - The cookie returned while requesting interrupts.
+ */
+struct mic_vdev {
+	int virtio_id;
+	wait_queue_head_t waitq;
+	struct mic_device *mdev;
+	int poll_wake;
+	unsigned long out_bytes;
+	unsigned long in_bytes;
+	struct mic_vringh mvr[MIC_MAX_VRINGS];
+	struct work_struct virtio_bh_work;
+	struct mic_device_desc *dd;
+	struct mic_device_ctrl *dc;
+	struct list_head list;
+	int virtio_db;
+	struct mic_irq *virtio_cookie;
+};
+
+void mic_virtio_uninit(struct mic_device *mdev);
+int mic_virtio_add_device(struct mic_vdev *mvdev,
+			void __user *argp);
+void mic_virtio_del_device(struct mic_vdev *mvdev);
+int mic_virtio_config_change(struct mic_vdev *mvdev,
+			void __user *argp);
+int mic_virtio_copy_desc(struct mic_vdev *mvdev,
+	struct mic_copy_desc *request);
+void mic_virtio_reset_devices(struct mic_device *mdev);
+void mic_bh_handler(struct work_struct *work);
+
+/* Helper API to obtain the MIC PCIe device */
+static inline struct device *mic_dev(struct mic_vdev *mvdev)
+{
+	return mvdev->mdev->sdev->parent;
+}
+
+/* Helper API to check if a virtio device is initialized */
+static inline int mic_vdev_inited(struct mic_vdev *mvdev)
+{
+	/* Device has not been created yet */
+	if (!mvdev->dd || !mvdev->dd->type) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -EINVAL);
+		return -EINVAL;
+	}
+
+	/* Device has been removed/deleted */
+	if (mvdev->dd->type == -1) {
+		dev_err(mic_dev(mvdev), "%s %d err %d\n",
+			__func__, __LINE__, -ENODEV);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/* Helper API to check if a virtio device is running */
+static inline bool mic_vdevup(struct mic_vdev *mvdev)
+{
+	return !!mvdev->dd->status;
+}
+#endif
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index d37263fbdca7..33d2b8fe166d 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -242,6 +242,7 @@ header-y += mei.h
 header-y += mempolicy.h
 header-y += meye.h
 header-y += mic_common.h
+header-y += mic_ioctl.h
 header-y += mii.h
 header-y += minix_fs.h
 header-y += mman.h
diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h
index a9091e529183..364ac751bd04 100644
--- a/include/uapi/linux/mic_common.h
+++ b/include/uapi/linux/mic_common.h
@@ -21,7 +21,60 @@
 #ifndef __MIC_COMMON_H_
 #define __MIC_COMMON_H_
 
-#include <linux/types.h>
+#include <linux/virtio_ring.h>
+
+#ifndef __KERNEL__
+#define ALIGN(a, x)	(((a) + (x) - 1) & ~((x) - 1))
+#define __aligned(x)	__attribute__ ((aligned(x)))
+#endif
+
+#define mic_aligned_size(x) ALIGN(sizeof(x), 8)
+
+/**
+ * struct mic_device_desc: Virtio device information shared between the
+ * virtio driver and userspace backend
+ *
+ * @type: Device type: console/network/disk etc.  Type 0/-1 terminates.
+ * @num_vq: Number of virtqueues.
+ * @feature_len: Number of bytes of feature bits.  Multiply by 2: one for
+   host features and one for guest acknowledgements.
+ * @config_len: Number of bytes of the config array after virtqueues.
+ * @status: A status byte, written by the Guest.
+ * @config: Start of the following variable length config.
+ */
+struct mic_device_desc {
+	__s8 type;
+	__u8 num_vq;
+	__u8 feature_len;
+	__u8 config_len;
+	__u8 status;
+	__u64 config[0];
+} __aligned(8);
+
+/**
+ * struct mic_device_ctrl: Per virtio device information in the device page
+ * used internally by the host and card side drivers.
+ *
+ * @vdev: Used for storing MIC vdev information by the guest.
+ * @config_change: Set to 1 by host when a config change is requested.
+ * @vdev_reset: Set to 1 by guest to indicate virtio device has been reset.
+ * @guest_ack: Set to 1 by guest to ack a command.
+ * @host_ack: Set to 1 by host to ack a command.
+ * @used_address_updated: Set to 1 by guest when the used address should be
+ * updated.
+ * @c2h_vdev_db: The doorbell number to be used by guest. Set by host.
+ * @h2c_vdev_db: The doorbell number to be used by host. Set by guest.
+ */
+struct mic_device_ctrl {
+	__u64 vdev;
+	__u8 config_change;
+	__u8 vdev_reset;
+	__u8 guest_ack;
+	__u8 host_ack;
+	__u8 used_address_updated;
+	__s8 c2h_vdev_db;
+	__s8 h2c_vdev_db;
+} __aligned(8);
 
 /**
  * struct mic_bootparam: Virtio device independent information in device page
@@ -42,6 +95,117 @@ struct mic_bootparam {
 	__u8 shutdown_card;
 } __aligned(8);
 
+/**
+ * struct mic_device_page: High level representation of the device page
+ *
+ * @bootparam: The bootparam structure is used for sharing information and
+ * status updates between MIC host and card drivers.
+ * @desc: Array of MIC virtio device descriptors.
+ */
+struct mic_device_page {
+	struct mic_bootparam bootparam;
+	struct mic_device_desc desc[0];
+};
+/**
+ * struct mic_vqconfig: This is how we expect the device configuration field
+ * for a virtqueue to be laid out in config space.
+ *
+ * @address: Guest/MIC physical address of the virtio ring
+ * (avail and desc rings)
+ * @used_address: Guest/MIC physical address of the used ring
+ * @num: The number of entries in the virtio_ring
+ */
+struct mic_vqconfig {
+	__u64 address;
+	__u64 used_address;
+	__u16 num;
+} __aligned(8);
+
+/*
+ * The alignment to use between consumer and producer parts of vring.
+ * This is pagesize for historical reasons.
+ */
+#define MIC_VIRTIO_RING_ALIGN		4096
+
+#define MIC_MAX_VRINGS			4
+#define MIC_VRING_ENTRIES		128
+
+/*
+ * Max vring entries (power of 2) to ensure desc and avail rings
+ * fit in a single page
+ */
+#define MIC_MAX_VRING_ENTRIES		128
+
+/**
+ * Max size of the desc block in bytes: includes:
+ *	- struct mic_device_desc
+ *	- struct mic_vqconfig (num_vq of these)
+ *	- host and guest features
+ *	- virtio device config space
+ */
+#define MIC_MAX_DESC_BLK_SIZE		256
+
+/**
+ * struct _mic_vring_info - Host vring info exposed to userspace backend
+ * for the avail index and magic for the card.
+ *
+ * @avail_idx: host avail idx
+ * @magic: A magic debug cookie.
+ */
+struct _mic_vring_info {
+	__u16 avail_idx;
+	int magic;
+};
+
+/**
+ * struct mic_vring - Vring information.
+ *
+ * @vr: The virtio ring.
+ * @info: Host vring information exposed to the userspace backend for the
+ * avail index and magic for the card.
+ * @va: The va for the buffer allocated for vr and info.
+ * @len: The length of the buffer required for allocating vr and info.
+ */
+struct mic_vring {
+	struct vring vr;
+	struct _mic_vring_info *info;
+	void *va;
+	int len;
+};
+
+#define mic_aligned_desc_size(d) ALIGN(mic_desc_size(d), 8)
+
+#ifndef INTEL_MIC_CARD
+static inline unsigned mic_desc_size(const struct mic_device_desc *desc)
+{
+	return mic_aligned_size(*desc)
+		+ desc->num_vq * mic_aligned_size(struct mic_vqconfig)
+		+ desc->feature_len * 2
+		+ desc->config_len;
+}
+
+static inline struct mic_vqconfig *
+mic_vq_config(const struct mic_device_desc *desc)
+{
+	return (struct mic_vqconfig *)(desc + 1);
+}
+
+static inline __u8 *mic_vq_features(const struct mic_device_desc *desc)
+{
+	return (__u8 *)(mic_vq_config(desc) + desc->num_vq);
+}
+
+static inline __u8 *mic_vq_configspace(const struct mic_device_desc *desc)
+{
+	return mic_vq_features(desc) + desc->feature_len * 2;
+}
+static inline unsigned mic_total_desc_size(struct mic_device_desc *desc)
+{
+	return mic_aligned_desc_size(desc) +
+		mic_aligned_size(struct mic_device_ctrl);
+}
+#endif
+
 /* Device page size */
 #define MIC_DP_SIZE 4096
 
diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
new file mode 100644
index 000000000000..0e6cbf3e5292
--- /dev/null
+++ b/include/uapi/linux/mic_ioctl.h
@@ -0,0 +1,74 @@
+/*
+ * Intel MIC Platform Software Stack (MPSS)
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Intel MIC Host driver.
+ *
+ */
+#ifndef _MIC_IOCTL_H_
+#define _MIC_IOCTL_H_
+
+/*
+ * mic_copy - MIC virtio descriptor copy.
+ *
+ * @iov: An array of IOVEC structures containing user space buffers.
+ * @iovcnt: Number of IOVEC structures in iov.
+ * @vr_idx: The vring index.
+ * @update_used: A non zero value results in used index being updated.
+ * @out_len: The aggregate of the total length written to or read from
+ *	the virtio device.
+ */
+struct mic_copy_desc {
+#ifdef __KERNEL__
+	struct iovec __user *iov;
+#else
+	struct iovec *iov;
+#endif
+	int iovcnt;
+	__u8 vr_idx;
+	__u8 update_used;
+	__u32 out_len;
+};
+
+/*
+ * Add a new virtio device
+ * The (struct mic_device_desc *) pointer points to a device page entry
+ *	for the virtio device consisting of:
+ *	- struct mic_device_desc
+ *	- struct mic_vqconfig (num_vq of these)
+ *	- host and guest features
+ *	- virtio device config space
+ * The total size referenced by the pointer should equal the size returned
+ * by desc_size() in mic_common.h
+ */
+#define MIC_VIRTIO_ADD_DEVICE _IOWR('s', 1, struct mic_device_desc *)
+
+/*
+ * Copy the number of entries in the iovec and update the used index
+ * if requested by the user.
+ */
+#define MIC_VIRTIO_COPY_DESC	_IOWR('s', 2, struct mic_copy_desc *)
+
+/*
+ * Notify virtio device of a config change
+ * The (__u8 *) pointer points to config space values for the device
+ * as they should be written into the device page. The total size
+ * referenced by the pointer should equal the config_len field of struct
+ * mic_device_desc.
+ */
+#define MIC_VIRTIO_CONFIG_CHANGE _IOWR('s', 5, __u8 *)
+
+#endif
-- 
cgit 


From a0f4ecf3494c9869d20f606e7e2b2f50f0e67a7f Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 26 Sep 2013 14:48:15 -0700
Subject: netfilter: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
---
 include/linux/netfilter.h                        |  10 +-
 include/linux/netfilter/nf_conntrack_common.h    |   2 +-
 include/linux/netfilter/nf_conntrack_h323.h      |  14 +--
 include/linux/netfilter/nf_conntrack_proto_gre.h |   4 +-
 include/linux/netfilter/nf_conntrack_sip.h       |  57 +++++-----
 include/linux/netfilter/nfnetlink.h              |  28 ++---
 include/linux/netfilter/nfnetlink_acct.h         |   6 +-
 include/linux/netfilter/x_tables.h               | 128 +++++++++++------------
 include/linux/netfilter_bridge.h                 |   4 +-
 include/linux/netfilter_ipv4.h                   |   6 +-
 include/linux/netfilter_ipv6.h                   |  10 +-
 11 files changed, 133 insertions(+), 136 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 708fe72ab913..61223c52414f 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -35,7 +35,7 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1,
 	result->all[3] = a1->all[3] & mask->all[3];
 }
 
-extern int netfilter_init(void);
+int netfilter_init(void);
 
 /* Largest hook number + 1 */
 #define NF_MAX_HOOKS 8
@@ -208,7 +208,7 @@ int compat_nf_getsockopt(struct sock *sk, u_int8_t pf, int optval,
 /* Call this before modifying an existing packet: ensures it is
    modifiable and linear to the point you care about (writable_len).
    Returns true or false. */
-extern int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
+int skb_make_writable(struct sk_buff *skb, unsigned int writable_len);
 
 struct flowi;
 struct nf_queue_entry;
@@ -269,8 +269,8 @@ nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
 	return csum;
 }
 
-extern int nf_register_afinfo(const struct nf_afinfo *afinfo);
-extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo);
+int nf_register_afinfo(const struct nf_afinfo *afinfo);
+void nf_unregister_afinfo(const struct nf_afinfo *afinfo);
 
 #include <net/flow.h>
 extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
@@ -315,7 +315,7 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu;
-extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
+void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
 extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 
 struct nf_conn;
diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 127d0b90604f..275505792664 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -23,6 +23,6 @@ struct ip_conntrack_stat {
 };
 
 /* call to create an explicit dependency on nf_conntrack. */
-extern void need_conntrack(void);
+void need_conntrack(void);
 
 #endif /* _NF_CONNTRACK_COMMON_H */
diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h
index f381020eee92..858d9b214053 100644
--- a/include/linux/netfilter/nf_conntrack_h323.h
+++ b/include/linux/netfilter/nf_conntrack_h323.h
@@ -29,13 +29,13 @@ struct nf_ct_h323_master {
 
 struct nf_conn;
 
-extern int get_h225_addr(struct nf_conn *ct, unsigned char *data,
-			 TransportAddress *taddr,
-			 union nf_inet_addr *addr, __be16 *port);
-extern void nf_conntrack_h245_expect(struct nf_conn *new,
-				     struct nf_conntrack_expect *this);
-extern void nf_conntrack_q931_expect(struct nf_conn *new,
-				     struct nf_conntrack_expect *this);
+int get_h225_addr(struct nf_conn *ct, unsigned char *data,
+		  TransportAddress *taddr, union nf_inet_addr *addr,
+		  __be16 *port);
+void nf_conntrack_h245_expect(struct nf_conn *new,
+			      struct nf_conntrack_expect *this);
+void nf_conntrack_q931_expect(struct nf_conn *new,
+			      struct nf_conntrack_expect *this);
 extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff,
 				  unsigned char **data, int dataoff,
 				  H245_TransportAddress *taddr,
diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index 6a0664c0c451..ec2ffaf418c8 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -87,8 +87,8 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 /* delete keymap entries */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct);
 
-extern void nf_ct_gre_keymap_flush(struct net *net);
-extern void nf_nat_need_gre(void);
+void nf_ct_gre_keymap_flush(struct net *net);
+void nf_nat_need_gre(void);
 
 #endif /* __KERNEL__ */
 #endif /* _CONNTRACK_PROTO_GRE_H */
diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h
index ba7f571a2b1c..5cac0207b95d 100644
--- a/include/linux/netfilter/nf_conntrack_sip.h
+++ b/include/linux/netfilter/nf_conntrack_sip.h
@@ -157,35 +157,34 @@ extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb,
 					     unsigned int medialen,
 					     union nf_inet_addr *rtp_addr);
 
-extern int ct_sip_parse_request(const struct nf_conn *ct,
-				const char *dptr, unsigned int datalen,
-				unsigned int *matchoff, unsigned int *matchlen,
-				union nf_inet_addr *addr, __be16 *port);
-extern int ct_sip_get_header(const struct nf_conn *ct, const char *dptr,
-			     unsigned int dataoff, unsigned int datalen,
-			     enum sip_header_types type,
-			     unsigned int *matchoff, unsigned int *matchlen);
-extern int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr,
-				   unsigned int *dataoff, unsigned int datalen,
-				   enum sip_header_types type, int *in_header,
-				   unsigned int *matchoff, unsigned int *matchlen,
-				   union nf_inet_addr *addr, __be16 *port);
-extern int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr,
-				      unsigned int dataoff, unsigned int datalen,
-				      const char *name,
-				      unsigned int *matchoff, unsigned int *matchlen,
-				      union nf_inet_addr *addr, bool delim);
-extern int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr,
-					unsigned int off, unsigned int datalen,
-					const char *name,
-					unsigned int *matchoff, unsigned int *matchen,
-					unsigned int *val);
-
-extern int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr,
-				 unsigned int dataoff, unsigned int datalen,
-				 enum sdp_header_types type,
-				 enum sdp_header_types term,
-				 unsigned int *matchoff, unsigned int *matchlen);
+int ct_sip_parse_request(const struct nf_conn *ct, const char *dptr,
+			 unsigned int datalen, unsigned int *matchoff,
+			 unsigned int *matchlen, union nf_inet_addr *addr,
+			 __be16 *port);
+int ct_sip_get_header(const struct nf_conn *ct, const char *dptr,
+		      unsigned int dataoff, unsigned int datalen,
+		      enum sip_header_types type, unsigned int *matchoff,
+		      unsigned int *matchlen);
+int ct_sip_parse_header_uri(const struct nf_conn *ct, const char *dptr,
+			    unsigned int *dataoff, unsigned int datalen,
+			    enum sip_header_types type, int *in_header,
+			    unsigned int *matchoff, unsigned int *matchlen,
+			    union nf_inet_addr *addr, __be16 *port);
+int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr,
+			       unsigned int dataoff, unsigned int datalen,
+			       const char *name, unsigned int *matchoff,
+			       unsigned int *matchlen, union nf_inet_addr *addr,
+			       bool delim);
+int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr,
+				 unsigned int off, unsigned int datalen,
+				 const char *name, unsigned int *matchoff,
+				 unsigned int *matchen, unsigned int *val);
+
+int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr,
+			  unsigned int dataoff, unsigned int datalen,
+			  enum sdp_header_types type,
+			  enum sdp_header_types term,
+			  unsigned int *matchoff, unsigned int *matchlen);
 
 #endif /* __KERNEL__ */
 #endif /* __NF_CONNTRACK_SIP_H__ */
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index cadb7402d7a7..4f68cd7141d2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -25,20 +25,20 @@ struct nfnetlink_subsystem {
 	const struct nfnl_callback *cb;	/* callback for individual types */
 };
 
-extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
-extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
-
-extern int nfnetlink_has_listeners(struct net *net, unsigned int group);
-extern struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
-					   u32 dst_portid, gfp_t gfp_mask);
-extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
-			  unsigned int group, int echo, gfp_t flags);
-extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
-extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net,
-			     u32 portid, int flags);
-
-extern void nfnl_lock(__u8 subsys_id);
-extern void nfnl_unlock(__u8 subsys_id);
+int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
+int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
+
+int nfnetlink_has_listeners(struct net *net, unsigned int group);
+struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
+				    u32 dst_portid, gfp_t gfp_mask);
+int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
+		   unsigned int group, int echo, gfp_t flags);
+int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
+int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
+		      int flags);
+
+void nfnl_lock(__u8 subsys_id);
+void nfnl_unlock(__u8 subsys_id);
 
 #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \
 	MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys))
diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h
index bb4bbc9b7a18..b2e85e59f760 100644
--- a/include/linux/netfilter/nfnetlink_acct.h
+++ b/include/linux/netfilter/nfnetlink_acct.h
@@ -6,8 +6,8 @@
 
 struct nf_acct;
 
-extern struct nf_acct *nfnl_acct_find_get(const char *filter_name);
-extern void nfnl_acct_put(struct nf_acct *acct);
-extern void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
+struct nf_acct *nfnl_acct_find_get(const char *filter_name);
+void nfnl_acct_put(struct nf_acct *acct);
+void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
 
 #endif /* _NFNL_ACCT_H */
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index dd49566315c6..a3e215bb0241 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -229,50 +229,48 @@ struct xt_table_info {
 
 #define XT_TABLE_INFO_SZ (offsetof(struct xt_table_info, entries) \
 			  + nr_cpu_ids * sizeof(char *))
-extern int xt_register_target(struct xt_target *target);
-extern void xt_unregister_target(struct xt_target *target);
-extern int xt_register_targets(struct xt_target *target, unsigned int n);
-extern void xt_unregister_targets(struct xt_target *target, unsigned int n);
-
-extern int xt_register_match(struct xt_match *target);
-extern void xt_unregister_match(struct xt_match *target);
-extern int xt_register_matches(struct xt_match *match, unsigned int n);
-extern void xt_unregister_matches(struct xt_match *match, unsigned int n);
-
-extern int xt_check_match(struct xt_mtchk_param *,
-			  unsigned int size, u_int8_t proto, bool inv_proto);
-extern int xt_check_target(struct xt_tgchk_param *,
-			   unsigned int size, u_int8_t proto, bool inv_proto);
-
-extern struct xt_table *xt_register_table(struct net *net,
-					  const struct xt_table *table,
-					  struct xt_table_info *bootstrap,
-					  struct xt_table_info *newinfo);
-extern void *xt_unregister_table(struct xt_table *table);
-
-extern struct xt_table_info *xt_replace_table(struct xt_table *table,
-					      unsigned int num_counters,
-					      struct xt_table_info *newinfo,
-					      int *error);
-
-extern struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
-extern struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
-extern struct xt_match *xt_request_find_match(u8 af, const char *name,
-					      u8 revision);
-extern struct xt_target *xt_request_find_target(u8 af, const char *name,
-						u8 revision);
-extern int xt_find_revision(u8 af, const char *name, u8 revision,
-			    int target, int *err);
-
-extern struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
-					   const char *name);
-extern void xt_table_unlock(struct xt_table *t);
-
-extern int xt_proto_init(struct net *net, u_int8_t af);
-extern void xt_proto_fini(struct net *net, u_int8_t af);
-
-extern struct xt_table_info *xt_alloc_table_info(unsigned int size);
-extern void xt_free_table_info(struct xt_table_info *info);
+int xt_register_target(struct xt_target *target);
+void xt_unregister_target(struct xt_target *target);
+int xt_register_targets(struct xt_target *target, unsigned int n);
+void xt_unregister_targets(struct xt_target *target, unsigned int n);
+
+int xt_register_match(struct xt_match *target);
+void xt_unregister_match(struct xt_match *target);
+int xt_register_matches(struct xt_match *match, unsigned int n);
+void xt_unregister_matches(struct xt_match *match, unsigned int n);
+
+int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
+		   bool inv_proto);
+int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
+		    bool inv_proto);
+
+struct xt_table *xt_register_table(struct net *net,
+				   const struct xt_table *table,
+				   struct xt_table_info *bootstrap,
+				   struct xt_table_info *newinfo);
+void *xt_unregister_table(struct xt_table *table);
+
+struct xt_table_info *xt_replace_table(struct xt_table *table,
+				       unsigned int num_counters,
+				       struct xt_table_info *newinfo,
+				       int *error);
+
+struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
+struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
+struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision);
+struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision);
+int xt_find_revision(u8 af, const char *name, u8 revision, int target,
+		     int *err);
+
+struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
+				    const char *name);
+void xt_table_unlock(struct xt_table *t);
+
+int xt_proto_init(struct net *net, u_int8_t af);
+void xt_proto_fini(struct net *net, u_int8_t af);
+
+struct xt_table_info *xt_alloc_table_info(unsigned int size);
+void xt_free_table_info(struct xt_table_info *info);
 
 /**
  * xt_recseq - recursive seqcount for netfilter use
@@ -353,8 +351,8 @@ static inline unsigned long ifname_compare_aligned(const char *_a,
 	return ret;
 }
 
-extern struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
-extern void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
+struct nf_hook_ops *xt_hook_link(const struct xt_table *, nf_hookfn *);
+void xt_hook_unlink(const struct xt_table *, struct nf_hook_ops *);
 
 #ifdef CONFIG_COMPAT
 #include <net/compat.h>
@@ -414,25 +412,25 @@ struct _compat_xt_align {
 
 #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align))
 
-extern void xt_compat_lock(u_int8_t af);
-extern void xt_compat_unlock(u_int8_t af);
-
-extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
-extern void xt_compat_flush_offsets(u_int8_t af);
-extern void xt_compat_init_offsets(u_int8_t af, unsigned int number);
-extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
-
-extern int xt_compat_match_offset(const struct xt_match *match);
-extern int xt_compat_match_from_user(struct xt_entry_match *m,
-				     void **dstptr, unsigned int *size);
-extern int xt_compat_match_to_user(const struct xt_entry_match *m,
-				   void __user **dstptr, unsigned int *size);
-
-extern int xt_compat_target_offset(const struct xt_target *target);
-extern void xt_compat_target_from_user(struct xt_entry_target *t,
-				       void **dstptr, unsigned int *size);
-extern int xt_compat_target_to_user(const struct xt_entry_target *t,
-				    void __user **dstptr, unsigned int *size);
+void xt_compat_lock(u_int8_t af);
+void xt_compat_unlock(u_int8_t af);
+
+int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta);
+void xt_compat_flush_offsets(u_int8_t af);
+void xt_compat_init_offsets(u_int8_t af, unsigned int number);
+int xt_compat_calc_jump(u_int8_t af, unsigned int offset);
+
+int xt_compat_match_offset(const struct xt_match *match);
+int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
+			      unsigned int *size);
+int xt_compat_match_to_user(const struct xt_entry_match *m,
+			    void __user **dstptr, unsigned int *size);
+
+int xt_compat_target_offset(const struct xt_target *target);
+void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
+				unsigned int *size);
+int xt_compat_target_to_user(const struct xt_entry_target *t,
+			     void __user **dstptr, unsigned int *size);
 
 #endif /* CONFIG_COMPAT */
 #endif /* _X_TABLES_H */
diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index dfb4d9e52bcb..8ab1c278b66d 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -25,7 +25,7 @@ enum nf_br_hook_priorities {
 #define BRNF_PPPoE			0x20
 
 /* Only used in br_forward.c */
-extern int nf_bridge_copy_header(struct sk_buff *skb);
+int nf_bridge_copy_header(struct sk_buff *skb);
 static inline int nf_bridge_maybe_copy_header(struct sk_buff *skb)
 {
 	if (skb->nf_bridge &&
@@ -53,7 +53,7 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 	return 0;
 }
 
-extern int br_handle_frame_finish(struct sk_buff *skb);
+int br_handle_frame_finish(struct sk_buff *skb);
 /* Only used in br_device.c */
 static inline int br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 {
diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index dfaf116b3e81..6e4591bb54d4 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -6,7 +6,7 @@
 
 #include <uapi/linux/netfilter_ipv4.h>
 
-extern int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type);
-extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
-				   unsigned int dataoff, u_int8_t protocol);
+int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type);
+__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
+		       unsigned int dataoff, u_int8_t protocol);
 #endif /*__LINUX_IP_NETFILTER_H*/
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 2d4df6ce043e..64dad1cc1a4b 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -11,12 +11,12 @@
 
 
 #ifdef CONFIG_NETFILTER
-extern int ip6_route_me_harder(struct sk_buff *skb);
-extern __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
-				    unsigned int dataoff, u_int8_t protocol);
+int ip6_route_me_harder(struct sk_buff *skb);
+__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
+			unsigned int dataoff, u_int8_t protocol);
 
-extern int ipv6_netfilter_init(void);
-extern void ipv6_netfilter_fini(void);
+int ipv6_netfilter_init(void);
+void ipv6_netfilter_fini(void);
 
 /*
  * Hook functions for ipv6 to allow xt_* modules to be built-in even
-- 
cgit 


From 58292cbe6669d74498a5f08db13e57cb3bcfb81d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 11 Sep 2013 22:29:04 -0400
Subject: sysfs: make attr namespace interface less convoluted

sysfs ns (namespace) implementation became more convoluted than
necessary while trying to hide ns information from visible interface.
The relatively recent attr ns support is a good example.

* attr ns tag is determined by sysfs_ops->namespace() callback while
  dir tag is determined by kobj_type->namespace().  The placement is
  arbitrary.

* Instead of performing operations with explicit ns tag, the namespace
  callback is routed through sysfs_attr_ns(), sysfs_ops->namespace(),
  class_attr_namespace(), class_attr->namespace().  It's not simpler
  in any sense.  The only thing this convolution does is traversing
  the whole stack backwards.

The namespace callbacks are unncessary because the operations involved
are inherently synchronous.  The information can be provided in in
straight-forward top-down direction and reversing that direction is
unnecessary and against basic design principles.

This backward interface is unnecessarily convoluted and hinders
properly separating out sysfs from driver model / kobject for proper
layering.  This patch updates attr ns support such that

* sysfs_ops->namespace() and class_attr->namespace() are dropped.

* sysfs_{create|remove}_file_ns(), which take explicit @ns param, are
  added and sysfs_{create|remove}_file() are now simple wrappers
  around the ns aware functions.

* ns handling is dropped from sysfs_chmod_file().  Nobody uses it at
  this point.  sysfs_chmod_file_ns() can be added later if necessary.

* Explicit @ns is propagated through class_{create|remove}_file_ns()
  and netdev_class_{create|remove}_file_ns().

* driver/net/bonding which is currently the only user of attr
  namespace is updated to use netdev_class_{create|remove}_file_ns()
  with @bh->net as the ns tag instead of using the namespace callback.

This patch should be an equivalent conversion without any functional
difference.  It makes the code easier to follow, reduces lines of code
a bit and helps proper separation and layering.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kay Sievers <kay@vrfy.org>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/class.c             | 29 ++++--------
 drivers/net/bonding/bond_sysfs.c | 14 ++----
 fs/sysfs/file.c                  | 95 ++++++++++------------------------------
 fs/sysfs/group.c                 |  7 +--
 fs/sysfs/sysfs.h                 |  5 ++-
 include/linux/device.h           | 24 +++++++---
 include/linux/netdevice.h        | 16 ++++++-
 include/linux/sysfs.h            | 31 +++++++++----
 net/core/net-sysfs.c             | 14 +++---
 9 files changed, 106 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/drivers/base/class.c b/drivers/base/class.c
index 8b7818b80056..f96f70419a78 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -47,18 +47,6 @@ static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr,
 	return ret;
 }
 
-static const void *class_attr_namespace(struct kobject *kobj,
-					const struct attribute *attr)
-{
-	struct class_attribute *class_attr = to_class_attr(attr);
-	struct subsys_private *cp = to_subsys_private(kobj);
-	const void *ns = NULL;
-
-	if (class_attr->namespace)
-		ns = class_attr->namespace(cp->class, class_attr);
-	return ns;
-}
-
 static void class_release(struct kobject *kobj)
 {
 	struct subsys_private *cp = to_subsys_private(kobj);
@@ -86,7 +74,6 @@ static const struct kobj_ns_type_operations *class_child_ns_type(struct kobject
 static const struct sysfs_ops class_sysfs_ops = {
 	.show	   = class_attr_show,
 	.store	   = class_attr_store,
-	.namespace = class_attr_namespace,
 };
 
 static struct kobj_type class_ktype = {
@@ -99,21 +86,23 @@ static struct kobj_type class_ktype = {
 static struct kset *class_kset;
 
 
-int class_create_file(struct class *cls, const struct class_attribute *attr)
+int class_create_file_ns(struct class *cls, const struct class_attribute *attr,
+			 const void *ns)
 {
 	int error;
 	if (cls)
-		error = sysfs_create_file(&cls->p->subsys.kobj,
-					  &attr->attr);
+		error = sysfs_create_file_ns(&cls->p->subsys.kobj,
+					     &attr->attr, ns);
 	else
 		error = -EINVAL;
 	return error;
 }
 
-void class_remove_file(struct class *cls, const struct class_attribute *attr)
+void class_remove_file_ns(struct class *cls, const struct class_attribute *attr,
+			  const void *ns)
 {
 	if (cls)
-		sysfs_remove_file(&cls->p->subsys.kobj, &attr->attr);
+		sysfs_remove_file_ns(&cls->p->subsys.kobj, &attr->attr, ns);
 }
 
 static struct class *class_get(struct class *cls)
@@ -600,8 +589,8 @@ int __init classes_init(void)
 	return 0;
 }
 
-EXPORT_SYMBOL_GPL(class_create_file);
-EXPORT_SYMBOL_GPL(class_remove_file);
+EXPORT_SYMBOL_GPL(class_create_file_ns);
+EXPORT_SYMBOL_GPL(class_remove_file_ns);
 EXPORT_SYMBOL_GPL(class_unregister);
 EXPORT_SYMBOL_GPL(class_destroy);
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index c29b836749b6..ec9b6460a38d 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -149,14 +149,6 @@ err_no_cmd:
 	return -EPERM;
 }
 
-static const void *bonding_namespace(struct class *cls,
-				     const struct class_attribute *attr)
-{
-	const struct bond_net *bn =
-		container_of(attr, struct bond_net, class_attr_bonding_masters);
-	return bn->net;
-}
-
 /* class attribute for bond_masters file.  This ends up in /sys/class/net */
 static const struct class_attribute class_attr_bonding_masters = {
 	.attr = {
@@ -165,7 +157,6 @@ static const struct class_attribute class_attr_bonding_masters = {
 	},
 	.show = bonding_show_bonds,
 	.store = bonding_store_bonds,
-	.namespace = bonding_namespace,
 };
 
 int bond_create_slave_symlinks(struct net_device *master,
@@ -1787,7 +1778,8 @@ int bond_create_sysfs(struct bond_net *bn)
 	bn->class_attr_bonding_masters = class_attr_bonding_masters;
 	sysfs_attr_init(&bn->class_attr_bonding_masters.attr);
 
-	ret = netdev_class_create_file(&bn->class_attr_bonding_masters);
+	ret = netdev_class_create_file_ns(&bn->class_attr_bonding_masters,
+					  bn->net);
 	/*
 	 * Permit multiple loads of the module by ignoring failures to
 	 * create the bonding_masters sysfs file.  Bonding devices
@@ -1817,7 +1809,7 @@ int bond_create_sysfs(struct bond_net *bn)
  */
 void bond_destroy_sysfs(struct bond_net *bn)
 {
-	netdev_class_remove_file(&bn->class_attr_bonding_masters);
+	netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net);
 }
 
 /*
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 15ef5eb13663..e784340f1599 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -485,58 +485,15 @@ const struct file_operations sysfs_file_operations = {
 	.poll		= sysfs_poll,
 };
 
-static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr,
-			 const void **pns)
-{
-	struct sysfs_dirent *dir_sd = kobj->sd;
-	const struct sysfs_ops *ops;
-	const void *ns = NULL;
-	int err;
-
-	if (!dir_sd) {
-		WARN(1, KERN_ERR "sysfs: kobject %s without dirent\n",
-			kobject_name(kobj));
-		return -ENOENT;
-	}
-
-	err = 0;
-	if (!sysfs_ns_type(dir_sd))
-		goto out;
-
-	err = -EINVAL;
-	if (!kobj->ktype)
-		goto out;
-	ops = kobj->ktype->sysfs_ops;
-	if (!ops)
-		goto out;
-	if (!ops->namespace)
-		goto out;
-
-	err = 0;
-	ns = ops->namespace(kobj, attr);
-out:
-	if (err) {
-		WARN(1, KERN_ERR
-		     "missing sysfs namespace attribute operation for kobject: %s\n",
-		     kobject_name(kobj));
-	}
-	*pns = ns;
-	return err;
-}
-
-int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
-			const struct attribute *attr, int type, umode_t amode)
+int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
+			   const struct attribute *attr, int type,
+			   umode_t amode, const void *ns)
 {
 	umode_t mode = (amode & S_IALLUGO) | S_IFREG;
 	struct sysfs_addrm_cxt acxt;
 	struct sysfs_dirent *sd;
-	const void *ns;
 	int rc;
 
-	rc = sysfs_attr_ns(dir_sd->s_dir.kobj, attr, &ns);
-	if (rc)
-		return rc;
-
 	sd = sysfs_new_dirent(attr->name, mode, type);
 	if (!sd)
 		return -ENOMEM;
@@ -559,23 +516,25 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
 int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
 		   int type)
 {
-	return sysfs_add_file_mode(dir_sd, attr, type, attr->mode);
+	return sysfs_add_file_mode_ns(dir_sd, attr, type, attr->mode, NULL);
 }
 
-
 /**
- *	sysfs_create_file - create an attribute file for an object.
- *	@kobj:	object we're creating for.
- *	@attr:	attribute descriptor.
+ * sysfs_create_file_ns - create an attribute file for an object with custom ns
+ * @kobj: object we're creating for
+ * @attr: attribute descriptor
+ * @ns: namespace the new file should belong to
  */
-int sysfs_create_file(struct kobject *kobj, const struct attribute *attr)
+int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
+			 const void *ns)
 {
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR);
+	return sysfs_add_file_mode_ns(kobj->sd, attr, SYSFS_KOBJ_ATTR,
+				      attr->mode, ns);
 
 }
-EXPORT_SYMBOL_GPL(sysfs_create_file);
+EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
 
 int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
 {
@@ -630,17 +589,12 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 {
 	struct sysfs_dirent *sd;
 	struct iattr newattrs;
-	const void *ns;
 	int rc;
 
-	rc = sysfs_attr_ns(kobj, attr, &ns);
-	if (rc)
-		return rc;
-
 	mutex_lock(&sysfs_mutex);
 
 	rc = -ENOENT;
-	sd = sysfs_find_dirent(kobj->sd, ns, attr->name);
+	sd = sysfs_find_dirent(kobj->sd, NULL, attr->name);
 	if (!sd)
 		goto out;
 
@@ -655,22 +609,21 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 EXPORT_SYMBOL_GPL(sysfs_chmod_file);
 
 /**
- *	sysfs_remove_file - remove an object attribute.
- *	@kobj:	object we're acting for.
- *	@attr:	attribute descriptor.
+ * sysfs_remove_file_ns - remove an object attribute with a custom ns tag
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ * @ns: namespace tag of the file to remove
  *
- *	Hash the attribute name and kill the victim.
+ * Hash the attribute name and namespace tag and kill the victim.
  */
-void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr)
+void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
+			  const void *ns)
 {
-	const void *ns;
-
-	if (sysfs_attr_ns(kobj, attr, &ns))
-		return;
+	struct sysfs_dirent *dir_sd = kobj->sd;
 
-	sysfs_hash_and_remove(kobj->sd, ns, attr->name);
+	sysfs_hash_and_remove(dir_sd, ns, attr->name);
 }
-EXPORT_SYMBOL_GPL(sysfs_remove_file);
+EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
 {
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 5f92cd2f61c1..25c78f23dae8 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -56,9 +56,10 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
 				if (!mode)
 					continue;
 			}
-			error = sysfs_add_file_mode(dir_sd, *attr,
-						    SYSFS_KOBJ_ATTR,
-						    (*attr)->mode | mode);
+			error = sysfs_add_file_mode_ns(dir_sd, *attr,
+						       SYSFS_KOBJ_ATTR,
+						       (*attr)->mode | mode,
+						       NULL);
 			if (unlikely(error))
 				break;
 		}
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index b6deca3e301d..a96da2559db2 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -230,8 +230,9 @@ extern const struct file_operations sysfs_file_operations;
 int sysfs_add_file(struct sysfs_dirent *dir_sd,
 		   const struct attribute *attr, int type);
 
-int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
-			const struct attribute *attr, int type, umode_t amode);
+int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
+			   const struct attribute *attr, int type,
+			   umode_t amode, const void *ns);
 /*
  * bin.c
  */
diff --git a/include/linux/device.h b/include/linux/device.h
index 2a9d6ed59579..ce690ea34547 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -427,8 +427,6 @@ struct class_attribute {
 			char *buf);
 	ssize_t (*store)(struct class *class, struct class_attribute *attr,
 			const char *buf, size_t count);
-	const void *(*namespace)(struct class *class,
-				 const struct class_attribute *attr);
 };
 
 #define CLASS_ATTR(_name, _mode, _show, _store) \
@@ -438,10 +436,24 @@ struct class_attribute {
 #define CLASS_ATTR_RO(_name) \
 	struct class_attribute class_attr_##_name = __ATTR_RO(_name)
 
-extern int __must_check class_create_file(struct class *class,
-					  const struct class_attribute *attr);
-extern void class_remove_file(struct class *class,
-			      const struct class_attribute *attr);
+extern int __must_check class_create_file_ns(struct class *class,
+					     const struct class_attribute *attr,
+					     const void *ns);
+extern void class_remove_file_ns(struct class *class,
+				 const struct class_attribute *attr,
+				 const void *ns);
+
+static inline int __must_check class_create_file(struct class *class,
+					const struct class_attribute *attr)
+{
+	return class_create_file_ns(class, attr, NULL);
+}
+
+static inline void class_remove_file(struct class *class,
+				     const struct class_attribute *attr)
+{
+	return class_remove_file_ns(class, attr, NULL);
+}
 
 /* Simple class attribute that is just a static string */
 struct class_attribute_string {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3de49aca4519..42421ed49a47 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2873,8 +2873,20 @@ extern int __init dev_proc_init(void);
 #define dev_proc_init() 0
 #endif
 
-extern int netdev_class_create_file(struct class_attribute *class_attr);
-extern void netdev_class_remove_file(struct class_attribute *class_attr);
+extern int netdev_class_create_file_ns(struct class_attribute *class_attr,
+				       const void *ns);
+extern void netdev_class_remove_file_ns(struct class_attribute *class_attr,
+					const void *ns);
+
+static inline int netdev_class_create_file(struct class_attribute *class_attr)
+{
+	return netdev_class_create_file_ns(class_attr, NULL);
+}
+
+static inline void netdev_class_remove_file(struct class_attribute *class_attr)
+{
+	netdev_class_remove_file_ns(class_attr, NULL);
+}
 
 extern struct kobj_ns_type_operations net_ns_type_operations;
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 11baec7c9b26..82f7fac78e77 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -173,7 +173,6 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size)
 struct sysfs_ops {
 	ssize_t	(*show)(struct kobject *, struct attribute *, char *);
 	ssize_t	(*store)(struct kobject *, struct attribute *, const char *, size_t);
-	const void *(*namespace)(struct kobject *, const struct attribute *);
 };
 
 struct sysfs_dirent;
@@ -189,13 +188,15 @@ int __must_check sysfs_rename_dir(struct kobject *kobj, const char *new_name);
 int __must_check sysfs_move_dir(struct kobject *kobj,
 				struct kobject *new_parent_kobj);
 
-int __must_check sysfs_create_file(struct kobject *kobj,
-				   const struct attribute *attr);
+int __must_check sysfs_create_file_ns(struct kobject *kobj,
+				      const struct attribute *attr,
+				      const void *ns);
 int __must_check sysfs_create_files(struct kobject *kobj,
 				   const struct attribute **attr);
 int __must_check sysfs_chmod_file(struct kobject *kobj,
 				  const struct attribute *attr, umode_t mode);
-void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr);
+void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
+			  const void *ns);
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr);
 
 int __must_check sysfs_create_bin_file(struct kobject *kobj,
@@ -277,8 +278,9 @@ static inline int sysfs_move_dir(struct kobject *kobj,
 	return 0;
 }
 
-static inline int sysfs_create_file(struct kobject *kobj,
-				    const struct attribute *attr)
+static inline int sysfs_create_file_ns(struct kobject *kobj,
+				       const struct attribute *attr,
+				       const void *ns)
 {
 	return 0;
 }
@@ -295,8 +297,9 @@ static inline int sysfs_chmod_file(struct kobject *kobj,
 	return 0;
 }
 
-static inline void sysfs_remove_file(struct kobject *kobj,
-				     const struct attribute *attr)
+static inline void sysfs_remove_file_ns(struct kobject *kobj,
+					const struct attribute *attr,
+					const void *ns)
 {
 }
 
@@ -435,4 +438,16 @@ static inline int __must_check sysfs_init(void)
 
 #endif /* CONFIG_SYSFS */
 
+static inline int __must_check sysfs_create_file(struct kobject *kobj,
+						 const struct attribute *attr)
+{
+	return sysfs_create_file_ns(kobj, attr, NULL);
+}
+
+static inline void sysfs_remove_file(struct kobject *kobj,
+				     const struct attribute *attr)
+{
+	return sysfs_remove_file_ns(kobj, attr, NULL);
+}
+
 #endif /* _SYSFS_H_ */
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d954b56b4e47..325dee863e46 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1344,17 +1344,19 @@ int netdev_register_kobject(struct net_device *net)
 	return error;
 }
 
-int netdev_class_create_file(struct class_attribute *class_attr)
+int netdev_class_create_file_ns(struct class_attribute *class_attr,
+				const void *ns)
 {
-	return class_create_file(&net_class, class_attr);
+	return class_create_file_ns(&net_class, class_attr, ns);
 }
-EXPORT_SYMBOL(netdev_class_create_file);
+EXPORT_SYMBOL(netdev_class_create_file_ns);
 
-void netdev_class_remove_file(struct class_attribute *class_attr)
+void netdev_class_remove_file_ns(struct class_attribute *class_attr,
+				 const void *ns)
 {
-	class_remove_file(&net_class, class_attr);
+	class_remove_file_ns(&net_class, class_attr, ns);
 }
-EXPORT_SYMBOL(netdev_class_remove_file);
+EXPORT_SYMBOL(netdev_class_remove_file_ns);
 
 int netdev_kobject_init(void)
 {
-- 
cgit 


From 7965bd4d71ef7cf1db00afb9e406ddfc13443c13 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 26 Sep 2013 14:48:15 -0700
Subject: net.h/skbuff.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
---
 include/linux/net.h    |  82 ++++++++--------
 include/linux/skbuff.h | 250 ++++++++++++++++++++++---------------------------
 2 files changed, 148 insertions(+), 184 deletions(-)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index 4f27575ce1d6..ca9ec8540905 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -195,27 +195,23 @@ enum {
 	SOCK_WAKE_URG,
 };
 
-extern int	     sock_wake_async(struct socket *sk, int how, int band);
-extern int	     sock_register(const struct net_proto_family *fam);
-extern void	     sock_unregister(int family);
-extern int	     __sock_create(struct net *net, int family, int type, int proto,
-				 struct socket **res, int kern);
-extern int	     sock_create(int family, int type, int proto,
-				 struct socket **res);
-extern int	     sock_create_kern(int family, int type, int proto,
-				      struct socket **res);
-extern int	     sock_create_lite(int family, int type, int proto,
-				      struct socket **res); 
-extern void	     sock_release(struct socket *sock);
-extern int   	     sock_sendmsg(struct socket *sock, struct msghdr *msg,
-				  size_t len);
-extern int	     sock_recvmsg(struct socket *sock, struct msghdr *msg,
-				  size_t size, int flags);
-extern struct file  *sock_alloc_file(struct socket *sock, int flags, const char *dname);
-extern struct socket *sockfd_lookup(int fd, int *err);
-extern struct socket *sock_from_file(struct file *file, int *err);
+int sock_wake_async(struct socket *sk, int how, int band);
+int sock_register(const struct net_proto_family *fam);
+void sock_unregister(int family);
+int __sock_create(struct net *net, int family, int type, int proto,
+		  struct socket **res, int kern);
+int sock_create(int family, int type, int proto, struct socket **res);
+int sock_create_kern(int family, int type, int proto, struct socket **res);
+int sock_create_lite(int family, int type, int proto, struct socket **res);
+void sock_release(struct socket *sock);
+int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len);
+int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+		 int flags);
+struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname);
+struct socket *sockfd_lookup(int fd, int *err);
+struct socket *sock_from_file(struct file *file, int *err);
 #define		     sockfd_put(sock) fput(sock->file)
-extern int	     net_ratelimit(void);
+int net_ratelimit(void);
 
 #define net_ratelimited_function(function, ...)			\
 do {								\
@@ -243,32 +239,28 @@ do {								\
 #define net_random()		prandom_u32()
 #define net_srandom(seed)	prandom_seed((__force u32)(seed))
 
-extern int   	     kernel_sendmsg(struct socket *sock, struct msghdr *msg,
-				    struct kvec *vec, size_t num, size_t len);
-extern int   	     kernel_recvmsg(struct socket *sock, struct msghdr *msg,
-				    struct kvec *vec, size_t num,
-				    size_t len, int flags);
+int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
+		   size_t num, size_t len);
+int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
+		   size_t num, size_t len, int flags);
 
-extern int kernel_bind(struct socket *sock, struct sockaddr *addr,
-		       int addrlen);
-extern int kernel_listen(struct socket *sock, int backlog);
-extern int kernel_accept(struct socket *sock, struct socket **newsock,
-			 int flags);
-extern int kernel_connect(struct socket *sock, struct sockaddr *addr,
-			  int addrlen, int flags);
-extern int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
-			      int *addrlen);
-extern int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
-			      int *addrlen);
-extern int kernel_getsockopt(struct socket *sock, int level, int optname,
-			     char *optval, int *optlen);
-extern int kernel_setsockopt(struct socket *sock, int level, int optname,
-			     char *optval, unsigned int optlen);
-extern int kernel_sendpage(struct socket *sock, struct page *page, int offset,
-			   size_t size, int flags);
-extern int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
-extern int kernel_sock_shutdown(struct socket *sock,
-				enum sock_shutdown_cmd how);
+int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen);
+int kernel_listen(struct socket *sock, int backlog);
+int kernel_accept(struct socket *sock, struct socket **newsock, int flags);
+int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
+		   int flags);
+int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
+		       int *addrlen);
+int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
+		       int *addrlen);
+int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval,
+		      int *optlen);
+int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval,
+		      unsigned int optlen);
+int kernel_sendpage(struct socket *sock, struct page *page, int offset,
+		    size_t size, int flags);
+int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
+int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
 
 #define MODULE_ALIAS_NETPROTO(proto) \
 	MODULE_ALIAS("net-pf-" __stringify(proto))
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2ddb48d9312c..6d56840e561e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -585,8 +585,8 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst)
 	skb->_skb_refdst = (unsigned long)dst;
 }
 
-extern void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
-				bool force);
+void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst,
+			 bool force);
 
 /**
  * skb_dst_set_noref - sets skb dst, hopefully, without taking reference
@@ -634,20 +634,20 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
 	return (struct rtable *)skb_dst(skb);
 }
 
-extern void kfree_skb(struct sk_buff *skb);
-extern void kfree_skb_list(struct sk_buff *segs);
-extern void skb_tx_error(struct sk_buff *skb);
-extern void consume_skb(struct sk_buff *skb);
-extern void	       __kfree_skb(struct sk_buff *skb);
+void kfree_skb(struct sk_buff *skb);
+void kfree_skb_list(struct sk_buff *segs);
+void skb_tx_error(struct sk_buff *skb);
+void consume_skb(struct sk_buff *skb);
+void  __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
 
-extern void kfree_skb_partial(struct sk_buff *skb, bool head_stolen);
-extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
-			     bool *fragstolen, int *delta_truesize);
+void kfree_skb_partial(struct sk_buff *skb, bool head_stolen);
+bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
+		      bool *fragstolen, int *delta_truesize);
 
-extern struct sk_buff *__alloc_skb(unsigned int size,
-				   gfp_t priority, int flags, int node);
-extern struct sk_buff *build_skb(void *data, unsigned int frag_size);
+struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
+			    int node);
+struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
 {
@@ -660,41 +660,33 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 	return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
 }
 
-extern struct sk_buff *__alloc_skb_head(gfp_t priority, int node);
+struct sk_buff *__alloc_skb_head(gfp_t priority, int node);
 static inline struct sk_buff *alloc_skb_head(gfp_t priority)
 {
 	return __alloc_skb_head(priority, -1);
 }
 
-extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
-extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
-extern struct sk_buff *skb_clone(struct sk_buff *skb,
-				 gfp_t priority);
-extern struct sk_buff *skb_copy(const struct sk_buff *skb,
-				gfp_t priority);
-extern struct sk_buff *__pskb_copy(struct sk_buff *skb,
-				 int headroom, gfp_t gfp_mask);
-
-extern int	       pskb_expand_head(struct sk_buff *skb,
-					int nhead, int ntail,
-					gfp_t gfp_mask);
-extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
-					    unsigned int headroom);
-extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
-				       int newheadroom, int newtailroom,
-				       gfp_t priority);
-extern int	       skb_to_sgvec(struct sk_buff *skb,
-				    struct scatterlist *sg, int offset,
-				    int len);
-extern int	       skb_cow_data(struct sk_buff *skb, int tailbits,
-				    struct sk_buff **trailer);
-extern int	       skb_pad(struct sk_buff *skb, int pad);
+struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
+int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
+struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
+struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority);
+struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask);
+
+int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask);
+struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
+				     unsigned int headroom);
+struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom,
+				int newtailroom, gfp_t priority);
+int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset,
+		 int len);
+int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer);
+int skb_pad(struct sk_buff *skb, int pad);
 #define dev_kfree_skb(a)	consume_skb(a)
 
-extern int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
-			int getfrag(void *from, char *to, int offset,
-			int len,int odd, struct sk_buff *skb),
-			void *from, int length);
+int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
+			    int getfrag(void *from, char *to, int offset,
+					int len, int odd, struct sk_buff *skb),
+			    void *from, int length);
 
 struct skb_seq_state {
 	__u32		lower_offset;
@@ -706,18 +698,17 @@ struct skb_seq_state {
 	__u8		*frag_data;
 };
 
-extern void	      skb_prepare_seq_read(struct sk_buff *skb,
-					   unsigned int from, unsigned int to,
-					   struct skb_seq_state *st);
-extern unsigned int   skb_seq_read(unsigned int consumed, const u8 **data,
-				   struct skb_seq_state *st);
-extern void	      skb_abort_seq_read(struct skb_seq_state *st);
+void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
+			  unsigned int to, struct skb_seq_state *st);
+unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
+			  struct skb_seq_state *st);
+void skb_abort_seq_read(struct skb_seq_state *st);
 
-extern unsigned int   skb_find_text(struct sk_buff *skb, unsigned int from,
-				    unsigned int to, struct ts_config *config,
-				    struct ts_state *state);
+unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
+			   unsigned int to, struct ts_config *config,
+			   struct ts_state *state);
 
-extern void __skb_get_rxhash(struct sk_buff *skb);
+void __skb_get_rxhash(struct sk_buff *skb);
 static inline __u32 skb_get_rxhash(struct sk_buff *skb)
 {
 	if (!skb->l4_rxhash)
@@ -1095,7 +1086,8 @@ static inline void skb_queue_head_init_class(struct sk_buff_head *list,
  *	The "__skb_xxxx()" functions are the non-atomic ones that
  *	can only be called with interrupts disabled.
  */
-extern void        skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list);
+void skb_insert(struct sk_buff *old, struct sk_buff *newsk,
+		struct sk_buff_head *list);
 static inline void __skb_insert(struct sk_buff *newsk,
 				struct sk_buff *prev, struct sk_buff *next,
 				struct sk_buff_head *list)
@@ -1201,8 +1193,8 @@ static inline void __skb_queue_after(struct sk_buff_head *list,
 	__skb_insert(newsk, prev, prev->next, list);
 }
 
-extern void skb_append(struct sk_buff *old, struct sk_buff *newsk,
-		       struct sk_buff_head *list);
+void skb_append(struct sk_buff *old, struct sk_buff *newsk,
+		struct sk_buff_head *list);
 
 static inline void __skb_queue_before(struct sk_buff_head *list,
 				      struct sk_buff *next,
@@ -1221,7 +1213,7 @@ static inline void __skb_queue_before(struct sk_buff_head *list,
  *
  *	A buffer cannot be placed on two lists at the same time.
  */
-extern void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
+void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk);
 static inline void __skb_queue_head(struct sk_buff_head *list,
 				    struct sk_buff *newsk)
 {
@@ -1238,7 +1230,7 @@ static inline void __skb_queue_head(struct sk_buff_head *list,
  *
  *	A buffer cannot be placed on two lists at the same time.
  */
-extern void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk);
+void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk);
 static inline void __skb_queue_tail(struct sk_buff_head *list,
 				   struct sk_buff *newsk)
 {
@@ -1249,7 +1241,7 @@ static inline void __skb_queue_tail(struct sk_buff_head *list,
  * remove sk_buff from list. _Must_ be called atomically, and with
  * the list known..
  */
-extern void	   skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
+void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list);
 static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 {
 	struct sk_buff *next, *prev;
@@ -1270,7 +1262,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
  *	so must be used with appropriate locks held only. The head item is
  *	returned or %NULL if the list is empty.
  */
-extern struct sk_buff *skb_dequeue(struct sk_buff_head *list);
+struct sk_buff *skb_dequeue(struct sk_buff_head *list);
 static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
 {
 	struct sk_buff *skb = skb_peek(list);
@@ -1287,7 +1279,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list)
  *	so must be used with appropriate locks held only. The tail item is
  *	returned or %NULL if the list is empty.
  */
-extern struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list);
+struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list);
 static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list)
 {
 	struct sk_buff *skb = skb_peek_tail(list);
@@ -1373,8 +1365,8 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
-extern void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page,
-			    int off, int size, unsigned int truesize);
+void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
+		     int size, unsigned int truesize);
 
 #define SKB_PAGE_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->nr_frags)
 #define SKB_FRAG_ASSERT(skb) 	BUG_ON(skb_has_frag_list(skb))
@@ -1418,7 +1410,7 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
 /*
  *	Add data to an sk_buff
  */
-extern unsigned char *skb_put(struct sk_buff *skb, unsigned int len);
+unsigned char *skb_put(struct sk_buff *skb, unsigned int len);
 static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
 {
 	unsigned char *tmp = skb_tail_pointer(skb);
@@ -1428,7 +1420,7 @@ static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
 	return tmp;
 }
 
-extern unsigned char *skb_push(struct sk_buff *skb, unsigned int len);
+unsigned char *skb_push(struct sk_buff *skb, unsigned int len);
 static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
 {
 	skb->data -= len;
@@ -1436,7 +1428,7 @@ static inline unsigned char *__skb_push(struct sk_buff *skb, unsigned int len)
 	return skb->data;
 }
 
-extern unsigned char *skb_pull(struct sk_buff *skb, unsigned int len);
+unsigned char *skb_pull(struct sk_buff *skb, unsigned int len);
 static inline unsigned char *__skb_pull(struct sk_buff *skb, unsigned int len)
 {
 	skb->len -= len;
@@ -1449,7 +1441,7 @@ static inline unsigned char *skb_pull_inline(struct sk_buff *skb, unsigned int l
 	return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
 }
 
-extern unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta);
+unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta);
 
 static inline unsigned char *__pskb_pull(struct sk_buff *skb, unsigned int len)
 {
@@ -1753,7 +1745,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 #define NET_SKB_PAD	max(32, L1_CACHE_BYTES)
 #endif
 
-extern int ___pskb_trim(struct sk_buff *skb, unsigned int len);
+int ___pskb_trim(struct sk_buff *skb, unsigned int len);
 
 static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
 {
@@ -1765,7 +1757,7 @@ static inline void __skb_trim(struct sk_buff *skb, unsigned int len)
 	skb_set_tail_pointer(skb, len);
 }
 
-extern void skb_trim(struct sk_buff *skb, unsigned int len);
+void skb_trim(struct sk_buff *skb, unsigned int len);
 
 static inline int __pskb_trim(struct sk_buff *skb, unsigned int len)
 {
@@ -1838,7 +1830,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask)
  *	the list and one reference dropped. This function does not take the
  *	list lock and the caller must hold the relevant locks to use it.
  */
-extern void skb_queue_purge(struct sk_buff_head *list);
+void skb_queue_purge(struct sk_buff_head *list);
 static inline void __skb_queue_purge(struct sk_buff_head *list)
 {
 	struct sk_buff *skb;
@@ -1850,11 +1842,10 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
 #define NETDEV_FRAG_PAGE_MAX_SIZE  (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER)
 #define NETDEV_PAGECNT_MAX_BIAS	   NETDEV_FRAG_PAGE_MAX_SIZE
 
-extern void *netdev_alloc_frag(unsigned int fragsz);
+void *netdev_alloc_frag(unsigned int fragsz);
 
-extern struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
-					  unsigned int length,
-					  gfp_t gfp_mask);
+struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length,
+				   gfp_t gfp_mask);
 
 /**
  *	netdev_alloc_skb - allocate an skbuff for rx on a specific device
@@ -2342,60 +2333,42 @@ static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag)
 #define skb_walk_frags(skb, iter)	\
 	for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next)
 
-extern struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
-					   int *peeked, int *off, int *err);
-extern struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
-					 int noblock, int *err);
-extern unsigned int    datagram_poll(struct file *file, struct socket *sock,
-				     struct poll_table_struct *wait);
-extern int	       skb_copy_datagram_iovec(const struct sk_buff *from,
-					       int offset, struct iovec *to,
-					       int size);
-extern int	       skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
-							int hlen,
-							struct iovec *iov);
-extern int	       skb_copy_datagram_from_iovec(struct sk_buff *skb,
-						    int offset,
-						    const struct iovec *from,
-						    int from_offset,
-						    int len);
-extern int	       zerocopy_sg_from_iovec(struct sk_buff *skb,
-					      const struct iovec *frm,
-					      int offset,
-					      size_t count);
-extern int	       skb_copy_datagram_const_iovec(const struct sk_buff *from,
-						     int offset,
-						     const struct iovec *to,
-						     int to_offset,
-						     int size);
-extern void	       skb_free_datagram(struct sock *sk, struct sk_buff *skb);
-extern void	       skb_free_datagram_locked(struct sock *sk,
-						struct sk_buff *skb);
-extern int	       skb_kill_datagram(struct sock *sk, struct sk_buff *skb,
-					 unsigned int flags);
-extern __wsum	       skb_checksum(const struct sk_buff *skb, int offset,
-				    int len, __wsum csum);
-extern int	       skb_copy_bits(const struct sk_buff *skb, int offset,
-				     void *to, int len);
-extern int	       skb_store_bits(struct sk_buff *skb, int offset,
-				      const void *from, int len);
-extern __wsum	       skb_copy_and_csum_bits(const struct sk_buff *skb,
-					      int offset, u8 *to, int len,
-					      __wsum csum);
-extern int             skb_splice_bits(struct sk_buff *skb,
-						unsigned int offset,
-						struct pipe_inode_info *pipe,
-						unsigned int len,
-						unsigned int flags);
-extern void	       skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
-extern void	       skb_split(struct sk_buff *skb,
-				 struct sk_buff *skb1, const u32 len);
-extern int	       skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
-				 int shiftlen);
-extern void	       skb_scrub_packet(struct sk_buff *skb, bool xnet);
-
-extern struct sk_buff *skb_segment(struct sk_buff *skb,
-				   netdev_features_t features);
+struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+				    int *peeked, int *off, int *err);
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
+				  int *err);
+unsigned int datagram_poll(struct file *file, struct socket *sock,
+			   struct poll_table_struct *wait);
+int skb_copy_datagram_iovec(const struct sk_buff *from, int offset,
+			    struct iovec *to, int size);
+int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen,
+				     struct iovec *iov);
+int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
+				 const struct iovec *from, int from_offset,
+				 int len);
+int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *frm,
+			   int offset, size_t count);
+int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset,
+				  const struct iovec *to, int to_offset,
+				  int size);
+void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
+void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
+int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
+__wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
+		    __wsum csum);
+int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len);
+int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len);
+__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to,
+			      int len, __wsum csum);
+int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
+		    struct pipe_inode_info *pipe, unsigned int len,
+		    unsigned int flags);
+void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
+void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
+int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
+void skb_scrub_packet(struct sk_buff *skb, bool xnet);
+
+struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
@@ -2440,7 +2413,7 @@ static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb,
 	memcpy(skb->data + offset, from, len);
 }
 
-extern void skb_init(void);
+void skb_init(void);
 
 static inline ktime_t skb_get_ktime(const struct sk_buff *skb)
 {
@@ -2483,12 +2456,12 @@ static inline ktime_t net_invalid_timestamp(void)
 	return ktime_set(0, 0);
 }
 
-extern void skb_timestamping_init(void);
+void skb_timestamping_init(void);
 
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
 
-extern void skb_clone_tx_timestamp(struct sk_buff *skb);
-extern bool skb_defer_rx_timestamp(struct sk_buff *skb);
+void skb_clone_tx_timestamp(struct sk_buff *skb);
+bool skb_defer_rx_timestamp(struct sk_buff *skb);
 
 #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */
 
@@ -2529,8 +2502,8 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
  * generates a software time stamp (otherwise), then queues the clone
  * to the error queue of the socket.  Errors are silently ignored.
  */
-extern void skb_tstamp_tx(struct sk_buff *orig_skb,
-			struct skb_shared_hwtstamps *hwtstamps);
+void skb_tstamp_tx(struct sk_buff *orig_skb,
+		   struct skb_shared_hwtstamps *hwtstamps);
 
 static inline void sw_tx_timestamp(struct sk_buff *skb)
 {
@@ -2562,8 +2535,8 @@ static inline void skb_tx_timestamp(struct sk_buff *skb)
  */
 void skb_complete_wifi_ack(struct sk_buff *skb, bool acked);
 
-extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
-extern __sum16 __skb_checksum_complete(struct sk_buff *skb);
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
+__sum16 __skb_checksum_complete(struct sk_buff *skb);
 
 static inline int skb_csum_unnecessary(const struct sk_buff *skb)
 {
@@ -2593,7 +2566,7 @@ static inline __sum16 skb_checksum_complete(struct sk_buff *skb)
 }
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-extern void nf_conntrack_destroy(struct nf_conntrack *nfct);
+void nf_conntrack_destroy(struct nf_conntrack *nfct);
 static inline void nf_conntrack_put(struct nf_conntrack *nfct)
 {
 	if (nfct && atomic_dec_and_test(&nfct->use))
@@ -2732,9 +2705,8 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
 	return skb->queue_mapping != 0;
 }
 
-extern u16 __skb_tx_hash(const struct net_device *dev,
-			 const struct sk_buff *skb,
-			 unsigned int num_tx_queues);
+u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
+		  unsigned int num_tx_queues);
 
 #ifdef CONFIG_XFRM
 static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
@@ -2788,7 +2760,7 @@ static inline bool skb_is_gso_v6(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6;
 }
 
-extern void __skb_warn_lro_forwarding(const struct sk_buff *skb);
+void __skb_warn_lro_forwarding(const struct sk_buff *skb);
 
 static inline bool skb_warn_if_lro(const struct sk_buff *skb)
 {
-- 
cgit 


From f629d208d27a22f495b7734eede585b5d207e912 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 26 Sep 2013 14:48:15 -0700
Subject: [networking]device.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
---
 include/linux/etherdevice.h |  35 ++--
 include/linux/fcdevice.h    |   2 +-
 include/linux/fddidevice.h  |   7 +-
 include/linux/hippidevice.h |  10 +-
 include/linux/inetdevice.h  |  28 +--
 include/linux/netdevice.h   | 432 +++++++++++++++++++++-----------------------
 6 files changed, 248 insertions(+), 266 deletions(-)

(limited to 'include')

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index d8b512496e50..fc4a9aa7dd82 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -28,27 +28,24 @@
 #include <asm/unaligned.h>
 
 #ifdef __KERNEL__
-extern __be16		eth_type_trans(struct sk_buff *skb, struct net_device *dev);
+__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;
 
-extern int eth_header(struct sk_buff *skb, struct net_device *dev,
-		      unsigned short type,
-		      const void *daddr, const void *saddr, unsigned len);
-extern int eth_rebuild_header(struct sk_buff *skb);
-extern int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
-extern int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
-extern void eth_header_cache_update(struct hh_cache *hh,
-				    const struct net_device *dev,
-				    const unsigned char *haddr);
-extern int eth_prepare_mac_addr_change(struct net_device *dev, void *p);
-extern void eth_commit_mac_addr_change(struct net_device *dev, void *p);
-extern int eth_mac_addr(struct net_device *dev, void *p);
-extern int eth_change_mtu(struct net_device *dev, int new_mtu);
-extern int eth_validate_addr(struct net_device *dev);
-
-
-
-extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
+int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
+	       const void *daddr, const void *saddr, unsigned len);
+int eth_rebuild_header(struct sk_buff *skb);
+int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
+int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh,
+		     __be16 type);
+void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev,
+			     const unsigned char *haddr);
+int eth_prepare_mac_addr_change(struct net_device *dev, void *p);
+void eth_commit_mac_addr_change(struct net_device *dev, void *p);
+int eth_mac_addr(struct net_device *dev, void *p);
+int eth_change_mtu(struct net_device *dev, int new_mtu);
+int eth_validate_addr(struct net_device *dev);
+
+struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 					    unsigned int rxqs);
 #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
 #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
diff --git a/include/linux/fcdevice.h b/include/linux/fcdevice.h
index e460ef831984..5009fa16b5d8 100644
--- a/include/linux/fcdevice.h
+++ b/include/linux/fcdevice.h
@@ -27,7 +27,7 @@
 #include <linux/if_fc.h>
 
 #ifdef __KERNEL__
-extern struct net_device *alloc_fcdev(int sizeof_priv);
+struct net_device *alloc_fcdev(int sizeof_priv);
 #endif
 
 #endif	/* _LINUX_FCDEVICE_H */
diff --git a/include/linux/fddidevice.h b/include/linux/fddidevice.h
index 155bafd9e886..9a79f0106da1 100644
--- a/include/linux/fddidevice.h
+++ b/include/linux/fddidevice.h
@@ -25,10 +25,9 @@
 #include <linux/if_fddi.h>
 
 #ifdef __KERNEL__
-extern __be16	fddi_type_trans(struct sk_buff *skb,
-				struct net_device *dev);
-extern int fddi_change_mtu(struct net_device *dev, int new_mtu);
-extern struct net_device *alloc_fddidev(int sizeof_priv);
+__be16 fddi_type_trans(struct sk_buff *skb, struct net_device *dev);
+int fddi_change_mtu(struct net_device *dev, int new_mtu);
+struct net_device *alloc_fddidev(int sizeof_priv);
 #endif
 
 #endif	/* _LINUX_FDDIDEVICE_H */
diff --git a/include/linux/hippidevice.h b/include/linux/hippidevice.h
index f148e4908410..8ec23fb0b412 100644
--- a/include/linux/hippidevice.h
+++ b/include/linux/hippidevice.h
@@ -31,11 +31,11 @@ struct hippi_cb {
 	__u32	ifield;
 };
 
-extern __be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev);
-extern int hippi_change_mtu(struct net_device *dev, int new_mtu);
-extern int hippi_mac_addr(struct net_device *dev, void *p);
-extern int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p);
-extern struct net_device *alloc_hippi_dev(int sizeof_priv);
+__be16 hippi_type_trans(struct sk_buff *skb, struct net_device *dev);
+int hippi_change_mtu(struct net_device *dev, int new_mtu);
+int hippi_mac_addr(struct net_device *dev, void *p);
+int hippi_neigh_setup_dev(struct net_device *dev, struct neigh_parms *p);
+struct net_device *alloc_hippi_dev(int sizeof_priv);
 #endif
 
 #endif	/* _LINUX_HIPPIDEVICE_H */
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 79640e015a86..0d678aefe69d 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -147,25 +147,27 @@ struct in_ifaddr {
 	unsigned long		ifa_tstamp; /* updated timestamp */
 };
 
-extern int register_inetaddr_notifier(struct notifier_block *nb);
-extern int unregister_inetaddr_notifier(struct notifier_block *nb);
+int register_inetaddr_notifier(struct notifier_block *nb);
+int unregister_inetaddr_notifier(struct notifier_block *nb);
 
-extern void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
-					struct ipv4_devconf *devconf);
+void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
+				 struct ipv4_devconf *devconf);
 
-extern struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
+struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref);
 static inline struct net_device *ip_dev_find(struct net *net, __be32 addr)
 {
 	return __ip_dev_find(net, addr, true);
 }
 
-extern int		inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b);
-extern int		devinet_ioctl(struct net *net, unsigned int cmd, void __user *);
-extern void		devinet_init(void);
-extern struct in_device	*inetdev_by_index(struct net *, int);
-extern __be32		inet_select_addr(const struct net_device *dev, __be32 dst, int scope);
-extern __be32		inet_confirm_addr(struct in_device *in_dev, __be32 dst, __be32 local, int scope);
-extern struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask);
+int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b);
+int devinet_ioctl(struct net *net, unsigned int cmd, void __user *);
+void devinet_init(void);
+struct in_device *inetdev_by_index(struct net *, int);
+__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope);
+__be32 inet_confirm_addr(struct in_device *in_dev, __be32 dst, __be32 local,
+			 int scope);
+struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
+				    __be32 mask);
 
 static __inline__ int inet_ifa_match(__be32 addr, struct in_ifaddr *ifa)
 {
@@ -218,7 +220,7 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev)
 	return rtnl_dereference(dev->ip_ptr);
 }
 
-extern void in_dev_finish_destroy(struct in_device *idev);
+void in_dev_finish_destroy(struct in_device *idev);
 
 static inline void in_dev_put(struct in_device *idev)
 {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b4cfb63f264e..5f01af3927ca 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -60,8 +60,8 @@ struct wireless_dev;
 #define SET_ETHTOOL_OPS(netdev,ops) \
 	( (netdev)->ethtool_ops = (ops) )
 
-extern void netdev_set_default_ethtool_ops(struct net_device *dev,
-					   const struct ethtool_ops *ops);
+void netdev_set_default_ethtool_ops(struct net_device *dev,
+				    const struct ethtool_ops *ops);
 
 /* hardware address assignment types */
 #define NET_ADDR_PERM		0	/* address is permanent (default) */
@@ -298,7 +298,7 @@ struct netdev_boot_setup {
 };
 #define NETDEV_BOOT_SETUP_MAX 8
 
-extern int __init netdev_boot_setup(char *str);
+int __init netdev_boot_setup(char *str);
 
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
@@ -394,7 +394,7 @@ enum rx_handler_result {
 typedef enum rx_handler_result rx_handler_result_t;
 typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
 
-extern void __napi_schedule(struct napi_struct *n);
+void __napi_schedule(struct napi_struct *n);
 
 static inline bool napi_disable_pending(struct napi_struct *n)
 {
@@ -445,8 +445,8 @@ static inline bool napi_reschedule(struct napi_struct *napi)
  *
  * Mark NAPI processing as complete.
  */
-extern void __napi_complete(struct napi_struct *n);
-extern void napi_complete(struct napi_struct *n);
+void __napi_complete(struct napi_struct *n);
+void napi_complete(struct napi_struct *n);
 
 /**
  *	napi_by_id - lookup a NAPI by napi_id
@@ -455,7 +455,7 @@ extern void napi_complete(struct napi_struct *n);
  * lookup @napi_id in napi_hash table
  * must be called under rcu_read_lock()
  */
-extern struct napi_struct *napi_by_id(unsigned int napi_id);
+struct napi_struct *napi_by_id(unsigned int napi_id);
 
 /**
  *	napi_hash_add - add a NAPI to global hashtable
@@ -463,7 +463,7 @@ extern struct napi_struct *napi_by_id(unsigned int napi_id);
  *
  * generate a new napi_id and store a @napi under it in napi_hash
  */
-extern void napi_hash_add(struct napi_struct *napi);
+void napi_hash_add(struct napi_struct *napi);
 
 /**
  *	napi_hash_del - remove a NAPI from global table
@@ -472,7 +472,7 @@ extern void napi_hash_add(struct napi_struct *napi);
  * Warning: caller must observe rcu grace period
  * before freeing memory containing @napi
  */
-extern void napi_hash_del(struct napi_struct *napi);
+void napi_hash_del(struct napi_struct *napi);
 
 /**
  *	napi_disable - prevent NAPI from scheduling
@@ -664,8 +664,8 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
 extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
 
 #ifdef CONFIG_RFS_ACCEL
-extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
-				u32 flow_id, u16 filter_id);
+bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
+			 u16 filter_id);
 #endif
 
 /* This structure contains an instance of an RX queue. */
@@ -1497,9 +1497,9 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
-extern struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-					   struct sk_buff *skb);
-extern u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
+struct netdev_queue *netdev_pick_tx(struct net_device *dev,
+				    struct sk_buff *skb);
+u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
  * Net namespace inlines
@@ -1683,8 +1683,8 @@ struct packet_offload {
 #define NETDEV_CHANGEUPPER	0x0015
 #define NETDEV_RESEND_IGMP	0x0016
 
-extern int register_netdevice_notifier(struct notifier_block *nb);
-extern int unregister_netdevice_notifier(struct notifier_block *nb);
+int register_netdevice_notifier(struct notifier_block *nb);
+int unregister_netdevice_notifier(struct notifier_block *nb);
 
 struct netdev_notifier_info {
 	struct net_device *dev;
@@ -1707,9 +1707,9 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info)
 	return info->dev;
 }
 
-extern int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
-					 struct netdev_notifier_info *info);
-extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
+int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
+				  struct netdev_notifier_info *info);
+int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 
 
 extern rwlock_t				dev_base_lock;		/* Device list lock */
@@ -1764,54 +1764,52 @@ static inline struct net_device *first_net_device_rcu(struct net *net)
 	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
 }
 
-extern int 			netdev_boot_setup_check(struct net_device *dev);
-extern unsigned long		netdev_boot_base(const char *prefix, int unit);
-extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
-					      const char *hwaddr);
-extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
-extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
-extern void		dev_add_pack(struct packet_type *pt);
-extern void		dev_remove_pack(struct packet_type *pt);
-extern void		__dev_remove_pack(struct packet_type *pt);
-extern void		dev_add_offload(struct packet_offload *po);
-extern void		dev_remove_offload(struct packet_offload *po);
-extern void		__dev_remove_offload(struct packet_offload *po);
-
-extern struct net_device	*dev_get_by_flags_rcu(struct net *net, unsigned short flags,
-						      unsigned short mask);
-extern struct net_device	*dev_get_by_name(struct net *net, const char *name);
-extern struct net_device	*dev_get_by_name_rcu(struct net *net, const char *name);
-extern struct net_device	*__dev_get_by_name(struct net *net, const char *name);
-extern int		dev_alloc_name(struct net_device *dev, const char *name);
-extern int		dev_open(struct net_device *dev);
-extern int		dev_close(struct net_device *dev);
-extern void		dev_disable_lro(struct net_device *dev);
-extern int		dev_loopback_xmit(struct sk_buff *newskb);
-extern int		dev_queue_xmit(struct sk_buff *skb);
-extern int		register_netdevice(struct net_device *dev);
-extern void		unregister_netdevice_queue(struct net_device *dev,
-						   struct list_head *head);
-extern void		unregister_netdevice_many(struct list_head *head);
+int netdev_boot_setup_check(struct net_device *dev);
+unsigned long netdev_boot_base(const char *prefix, int unit);
+struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
+				       const char *hwaddr);
+struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
+struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type);
+void dev_add_pack(struct packet_type *pt);
+void dev_remove_pack(struct packet_type *pt);
+void __dev_remove_pack(struct packet_type *pt);
+void dev_add_offload(struct packet_offload *po);
+void dev_remove_offload(struct packet_offload *po);
+void __dev_remove_offload(struct packet_offload *po);
+
+struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
+					unsigned short mask);
+struct net_device *dev_get_by_name(struct net *net, const char *name);
+struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
+struct net_device *__dev_get_by_name(struct net *net, const char *name);
+int dev_alloc_name(struct net_device *dev, const char *name);
+int dev_open(struct net_device *dev);
+int dev_close(struct net_device *dev);
+void dev_disable_lro(struct net_device *dev);
+int dev_loopback_xmit(struct sk_buff *newskb);
+int dev_queue_xmit(struct sk_buff *skb);
+int register_netdevice(struct net_device *dev);
+void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
+void unregister_netdevice_many(struct list_head *head);
 static inline void unregister_netdevice(struct net_device *dev)
 {
 	unregister_netdevice_queue(dev, NULL);
 }
 
-extern int 		netdev_refcnt_read(const struct net_device *dev);
-extern void		free_netdev(struct net_device *dev);
-extern void		synchronize_net(void);
-extern int		init_dummy_netdev(struct net_device *dev);
+int netdev_refcnt_read(const struct net_device *dev);
+void free_netdev(struct net_device *dev);
+void synchronize_net(void);
+int init_dummy_netdev(struct net_device *dev);
 
-extern struct net_device	*dev_get_by_index(struct net *net, int ifindex);
-extern struct net_device	*__dev_get_by_index(struct net *net, int ifindex);
-extern struct net_device	*dev_get_by_index_rcu(struct net *net, int ifindex);
-extern int		netdev_get_name(struct net *net, char *name, int ifindex);
-extern int		dev_restart(struct net_device *dev);
+struct net_device *dev_get_by_index(struct net *net, int ifindex);
+struct net_device *__dev_get_by_index(struct net *net, int ifindex);
+struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
+int netdev_get_name(struct net *net, char *name, int ifindex);
+int dev_restart(struct net_device *dev);
 #ifdef CONFIG_NETPOLL_TRAP
-extern int		netpoll_trap(void);
+int netpoll_trap(void);
 #endif
-extern int	       skb_gro_receive(struct sk_buff **head,
-				       struct sk_buff *skb);
+int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
 
 static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
 {
@@ -1883,7 +1881,7 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 }
 
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
-extern int		register_gifconf(unsigned int family, gifconf_func_t * gifconf);
+int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
 {
 	return register_gifconf(family, NULL);
@@ -1954,7 +1952,7 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd,
 
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
-extern void __netif_schedule(struct Qdisc *q);
+void __netif_schedule(struct Qdisc *q);
 
 static inline void netif_schedule_queue(struct netdev_queue *txq)
 {
@@ -2274,8 +2272,8 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
 }
 
 #ifdef CONFIG_XPS
-extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask,
-			       u16 index);
+int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask,
+			u16 index);
 #else
 static inline int netif_set_xps_queue(struct net_device *dev,
 				      struct cpumask *mask,
@@ -2306,12 +2304,10 @@ static inline bool netif_is_multiqueue(const struct net_device *dev)
 	return dev->num_tx_queues > 1;
 }
 
-extern int netif_set_real_num_tx_queues(struct net_device *dev,
-					unsigned int txq);
+int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
 
 #ifdef CONFIG_RPS
-extern int netif_set_real_num_rx_queues(struct net_device *dev,
-					unsigned int rxq);
+int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
 #else
 static inline int netif_set_real_num_rx_queues(struct net_device *dev,
 						unsigned int rxq)
@@ -2338,28 +2334,27 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev,
 }
 
 #define DEFAULT_MAX_NUM_RSS_QUEUES	(8)
-extern int netif_get_num_default_rss_queues(void);
+int netif_get_num_default_rss_queues(void);
 
 /* Use this variant when it is known for sure that it
  * is executing from hardware interrupt context or with hardware interrupts
  * disabled.
  */
-extern void dev_kfree_skb_irq(struct sk_buff *skb);
+void dev_kfree_skb_irq(struct sk_buff *skb);
 
 /* Use this variant in places where it could be invoked
  * from either hardware interrupt or other context, with hardware interrupts
  * either disabled or enabled.
  */
-extern void dev_kfree_skb_any(struct sk_buff *skb);
+void dev_kfree_skb_any(struct sk_buff *skb);
 
-extern int		netif_rx(struct sk_buff *skb);
-extern int		netif_rx_ni(struct sk_buff *skb);
-extern int		netif_receive_skb(struct sk_buff *skb);
-extern gro_result_t	napi_gro_receive(struct napi_struct *napi,
-					 struct sk_buff *skb);
-extern void		napi_gro_flush(struct napi_struct *napi, bool flush_old);
-extern struct sk_buff *	napi_get_frags(struct napi_struct *napi);
-extern gro_result_t	napi_gro_frags(struct napi_struct *napi);
+int netif_rx(struct sk_buff *skb);
+int netif_rx_ni(struct sk_buff *skb);
+int netif_receive_skb(struct sk_buff *skb);
+gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
+void napi_gro_flush(struct napi_struct *napi, bool flush_old);
+struct sk_buff *napi_get_frags(struct napi_struct *napi);
+gro_result_t napi_gro_frags(struct napi_struct *napi);
 
 static inline void napi_free_frags(struct napi_struct *napi)
 {
@@ -2367,40 +2362,35 @@ static inline void napi_free_frags(struct napi_struct *napi)
 	napi->skb = NULL;
 }
 
-extern int netdev_rx_handler_register(struct net_device *dev,
-				      rx_handler_func_t *rx_handler,
-				      void *rx_handler_data);
-extern void netdev_rx_handler_unregister(struct net_device *dev);
-
-extern bool		dev_valid_name(const char *name);
-extern int		dev_ioctl(struct net *net, unsigned int cmd, void __user *);
-extern int		dev_ethtool(struct net *net, struct ifreq *);
-extern unsigned int	dev_get_flags(const struct net_device *);
-extern int		__dev_change_flags(struct net_device *, unsigned int flags);
-extern int		dev_change_flags(struct net_device *, unsigned int);
-extern void		__dev_notify_flags(struct net_device *, unsigned int old_flags);
-extern int		dev_change_name(struct net_device *, const char *);
-extern int		dev_set_alias(struct net_device *, const char *, size_t);
-extern int		dev_change_net_namespace(struct net_device *,
-						 struct net *, const char *);
-extern int		dev_set_mtu(struct net_device *, int);
-extern void		dev_set_group(struct net_device *, int);
-extern int		dev_set_mac_address(struct net_device *,
-					    struct sockaddr *);
-extern int		dev_change_carrier(struct net_device *,
-					   bool new_carrier);
-extern int		dev_get_phys_port_id(struct net_device *dev,
-					     struct netdev_phys_port_id *ppid);
-extern int		dev_hard_start_xmit(struct sk_buff *skb,
-					    struct net_device *dev,
-					    struct netdev_queue *txq);
-extern int		dev_forward_skb(struct net_device *dev,
-					struct sk_buff *skb);
+int netdev_rx_handler_register(struct net_device *dev,
+			       rx_handler_func_t *rx_handler,
+			       void *rx_handler_data);
+void netdev_rx_handler_unregister(struct net_device *dev);
+
+bool dev_valid_name(const char *name);
+int dev_ioctl(struct net *net, unsigned int cmd, void __user *);
+int dev_ethtool(struct net *net, struct ifreq *);
+unsigned int dev_get_flags(const struct net_device *);
+int __dev_change_flags(struct net_device *, unsigned int flags);
+int dev_change_flags(struct net_device *, unsigned int);
+void __dev_notify_flags(struct net_device *, unsigned int old_flags);
+int dev_change_name(struct net_device *, const char *);
+int dev_set_alias(struct net_device *, const char *, size_t);
+int dev_change_net_namespace(struct net_device *, struct net *, const char *);
+int dev_set_mtu(struct net_device *, int);
+void dev_set_group(struct net_device *, int);
+int dev_set_mac_address(struct net_device *, struct sockaddr *);
+int dev_change_carrier(struct net_device *, bool new_carrier);
+int dev_get_phys_port_id(struct net_device *dev,
+			 struct netdev_phys_port_id *ppid);
+int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
+			struct netdev_queue *txq);
+int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
 
 /* Called by rtnetlink.c:rtnl_unlock() */
-extern void netdev_run_todo(void);
+void netdev_run_todo(void);
 
 /**
  *	dev_put - release reference to device
@@ -2433,9 +2423,9 @@ static inline void dev_hold(struct net_device *dev)
  * kind of lower layer not just hardware media.
  */
 
-extern void linkwatch_init_dev(struct net_device *dev);
-extern void linkwatch_fire_event(struct net_device *dev);
-extern void linkwatch_forget_dev(struct net_device *dev);
+void linkwatch_init_dev(struct net_device *dev);
+void linkwatch_fire_event(struct net_device *dev);
+void linkwatch_forget_dev(struct net_device *dev);
 
 /**
  *	netif_carrier_ok - test if carrier present
@@ -2448,13 +2438,13 @@ static inline bool netif_carrier_ok(const struct net_device *dev)
 	return !test_bit(__LINK_STATE_NOCARRIER, &dev->state);
 }
 
-extern unsigned long dev_trans_start(struct net_device *dev);
+unsigned long dev_trans_start(struct net_device *dev);
 
-extern void __netdev_watchdog_up(struct net_device *dev);
+void __netdev_watchdog_up(struct net_device *dev);
 
-extern void netif_carrier_on(struct net_device *dev);
+void netif_carrier_on(struct net_device *dev);
 
-extern void netif_carrier_off(struct net_device *dev);
+void netif_carrier_off(struct net_device *dev);
 
 /**
  *	netif_dormant_on - mark device as dormant.
@@ -2522,9 +2512,9 @@ static inline bool netif_device_present(struct net_device *dev)
 	return test_bit(__LINK_STATE_PRESENT, &dev->state);
 }
 
-extern void netif_device_detach(struct net_device *dev);
+void netif_device_detach(struct net_device *dev);
 
-extern void netif_device_attach(struct net_device *dev);
+void netif_device_attach(struct net_device *dev);
 
 /*
  * Network interface message level settings
@@ -2733,98 +2723,93 @@ static inline void netif_addr_unlock_bh(struct net_device *dev)
 
 /* These functions live elsewhere (drivers/net/net_init.c, but related) */
 
-extern void		ether_setup(struct net_device *dev);
+void ether_setup(struct net_device *dev);
 
 /* Support for loadable net-drivers */
-extern struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
-				       void (*setup)(struct net_device *),
-				       unsigned int txqs, unsigned int rxqs);
+struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
+				    void (*setup)(struct net_device *),
+				    unsigned int txqs, unsigned int rxqs);
 #define alloc_netdev(sizeof_priv, name, setup) \
 	alloc_netdev_mqs(sizeof_priv, name, setup, 1, 1)
 
 #define alloc_netdev_mq(sizeof_priv, name, setup, count) \
 	alloc_netdev_mqs(sizeof_priv, name, setup, count, count)
 
-extern int		register_netdev(struct net_device *dev);
-extern void		unregister_netdev(struct net_device *dev);
+int register_netdev(struct net_device *dev);
+void unregister_netdev(struct net_device *dev);
 
 /* General hardware address lists handling functions */
-extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
-				  struct netdev_hw_addr_list *from_list,
-				  int addr_len, unsigned char addr_type);
-extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
-				   struct netdev_hw_addr_list *from_list,
-				   int addr_len, unsigned char addr_type);
-extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
-			  struct netdev_hw_addr_list *from_list,
-			  int addr_len);
-extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
-			     struct netdev_hw_addr_list *from_list,
-			     int addr_len);
-extern void __hw_addr_flush(struct netdev_hw_addr_list *list);
-extern void __hw_addr_init(struct netdev_hw_addr_list *list);
+int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
+			   struct netdev_hw_addr_list *from_list,
+			   int addr_len, unsigned char addr_type);
+void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
+			    struct netdev_hw_addr_list *from_list,
+			    int addr_len, unsigned char addr_type);
+int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
+		   struct netdev_hw_addr_list *from_list, int addr_len);
+void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
+		      struct netdev_hw_addr_list *from_list, int addr_len);
+void __hw_addr_flush(struct netdev_hw_addr_list *list);
+void __hw_addr_init(struct netdev_hw_addr_list *list);
 
 /* Functions used for device addresses handling */
-extern int dev_addr_add(struct net_device *dev, const unsigned char *addr,
-			unsigned char addr_type);
-extern int dev_addr_del(struct net_device *dev, const unsigned char *addr,
-			unsigned char addr_type);
-extern int dev_addr_add_multiple(struct net_device *to_dev,
-				 struct net_device *from_dev,
-				 unsigned char addr_type);
-extern int dev_addr_del_multiple(struct net_device *to_dev,
-				 struct net_device *from_dev,
-				 unsigned char addr_type);
-extern void dev_addr_flush(struct net_device *dev);
-extern int dev_addr_init(struct net_device *dev);
+int dev_addr_add(struct net_device *dev, const unsigned char *addr,
+		 unsigned char addr_type);
+int dev_addr_del(struct net_device *dev, const unsigned char *addr,
+		 unsigned char addr_type);
+int dev_addr_add_multiple(struct net_device *to_dev,
+			  struct net_device *from_dev, unsigned char addr_type);
+int dev_addr_del_multiple(struct net_device *to_dev,
+			  struct net_device *from_dev, unsigned char addr_type);
+void dev_addr_flush(struct net_device *dev);
+int dev_addr_init(struct net_device *dev);
 
 /* Functions used for unicast addresses handling */
-extern int dev_uc_add(struct net_device *dev, const unsigned char *addr);
-extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
-extern int dev_uc_del(struct net_device *dev, const unsigned char *addr);
-extern int dev_uc_sync(struct net_device *to, struct net_device *from);
-extern int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
-extern void dev_uc_unsync(struct net_device *to, struct net_device *from);
-extern void dev_uc_flush(struct net_device *dev);
-extern void dev_uc_init(struct net_device *dev);
+int dev_uc_add(struct net_device *dev, const unsigned char *addr);
+int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
+int dev_uc_del(struct net_device *dev, const unsigned char *addr);
+int dev_uc_sync(struct net_device *to, struct net_device *from);
+int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
+void dev_uc_unsync(struct net_device *to, struct net_device *from);
+void dev_uc_flush(struct net_device *dev);
+void dev_uc_init(struct net_device *dev);
 
 /* Functions used for multicast addresses handling */
-extern int dev_mc_add(struct net_device *dev, const unsigned char *addr);
-extern int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
-extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr);
-extern int dev_mc_del(struct net_device *dev, const unsigned char *addr);
-extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr);
-extern int dev_mc_sync(struct net_device *to, struct net_device *from);
-extern int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
-extern void dev_mc_unsync(struct net_device *to, struct net_device *from);
-extern void dev_mc_flush(struct net_device *dev);
-extern void dev_mc_init(struct net_device *dev);
+int dev_mc_add(struct net_device *dev, const unsigned char *addr);
+int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
+int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr);
+int dev_mc_del(struct net_device *dev, const unsigned char *addr);
+int dev_mc_del_global(struct net_device *dev, const unsigned char *addr);
+int dev_mc_sync(struct net_device *to, struct net_device *from);
+int dev_mc_sync_multiple(struct net_device *to, struct net_device *from);
+void dev_mc_unsync(struct net_device *to, struct net_device *from);
+void dev_mc_flush(struct net_device *dev);
+void dev_mc_init(struct net_device *dev);
 
 /* Functions used for secondary unicast and multicast support */
-extern void		dev_set_rx_mode(struct net_device *dev);
-extern void		__dev_set_rx_mode(struct net_device *dev);
-extern int		dev_set_promiscuity(struct net_device *dev, int inc);
-extern int		dev_set_allmulti(struct net_device *dev, int inc);
-extern void		netdev_state_change(struct net_device *dev);
-extern void		netdev_notify_peers(struct net_device *dev);
-extern void		netdev_features_change(struct net_device *dev);
+void dev_set_rx_mode(struct net_device *dev);
+void __dev_set_rx_mode(struct net_device *dev);
+int dev_set_promiscuity(struct net_device *dev, int inc);
+int dev_set_allmulti(struct net_device *dev, int inc);
+void netdev_state_change(struct net_device *dev);
+void netdev_notify_peers(struct net_device *dev);
+void netdev_features_change(struct net_device *dev);
 /* Load a device via the kmod */
-extern void		dev_load(struct net *net, const char *name);
-extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
-					       struct rtnl_link_stats64 *storage);
-extern void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
-				    const struct net_device_stats *netdev_stats);
+void dev_load(struct net *net, const char *name);
+struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
+					struct rtnl_link_stats64 *storage);
+void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
+			     const struct net_device_stats *netdev_stats);
 
 extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
 extern int		weight_p;
 extern int		bpf_jit_enable;
 
-extern bool netdev_has_upper_dev(struct net_device *dev,
-				 struct net_device *upper_dev);
-extern bool netdev_has_any_upper_dev(struct net_device *dev);
-extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
-							    struct list_head **iter);
+bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
+bool netdev_has_any_upper_dev(struct net_device *dev);
+struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
+						     struct list_head **iter);
 
 /* iterate through upper list, must be called under RCU read lock */
 #define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
@@ -2833,10 +2818,10 @@ extern struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *d
 	     updev; \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
-extern void *netdev_lower_get_next_private(struct net_device *dev,
-					   struct list_head **iter);
-extern void *netdev_lower_get_next_private_rcu(struct net_device *dev,
-					       struct list_head **iter);
+void *netdev_lower_get_next_private(struct net_device *dev,
+				    struct list_head **iter);
+void *netdev_lower_get_next_private_rcu(struct net_device *dev,
+					struct list_head **iter);
 
 #define netdev_for_each_lower_private(dev, priv, iter) \
 	for (iter = (dev)->adj_list.lower.next, \
@@ -2850,27 +2835,26 @@ extern void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 	     priv; \
 	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
 
-extern void *netdev_adjacent_get_private(struct list_head *adj_list);
-extern struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
-extern struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
-extern int netdev_upper_dev_link(struct net_device *dev,
+void *netdev_adjacent_get_private(struct list_head *adj_list);
+struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
+struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
+int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
+int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct net_device *upper_dev);
-extern int netdev_master_upper_dev_link(struct net_device *dev,
-					struct net_device *upper_dev);
-extern int netdev_master_upper_dev_link_private(struct net_device *dev,
-						struct net_device *upper_dev,
-						void *private);
-extern void netdev_upper_dev_unlink(struct net_device *dev,
-				    struct net_device *upper_dev);
-extern void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
-					      struct net_device *lower_dev);
-extern void *netdev_lower_dev_get_private(struct net_device *dev,
-					  struct net_device *lower_dev);
-extern int skb_checksum_help(struct sk_buff *skb);
-extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
-	netdev_features_t features, bool tx_path);
-extern struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
-					  netdev_features_t features);
+int netdev_master_upper_dev_link_private(struct net_device *dev,
+					 struct net_device *upper_dev,
+					 void *private);
+void netdev_upper_dev_unlink(struct net_device *dev,
+			     struct net_device *upper_dev);
+void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
+				       struct net_device *lower_dev);
+void *netdev_lower_dev_get_private(struct net_device *dev,
+				   struct net_device *lower_dev);
+int skb_checksum_help(struct sk_buff *skb);
+struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
+				  netdev_features_t features, bool tx_path);
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+				    netdev_features_t features);
 
 static inline
 struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
@@ -2892,30 +2876,30 @@ static inline bool can_checksum_protocol(netdev_features_t features,
 }
 
 #ifdef CONFIG_BUG
-extern void netdev_rx_csum_fault(struct net_device *dev);
+void netdev_rx_csum_fault(struct net_device *dev);
 #else
 static inline void netdev_rx_csum_fault(struct net_device *dev)
 {
 }
 #endif
 /* rx skb timestamps */
-extern void		net_enable_timestamp(void);
-extern void		net_disable_timestamp(void);
+void net_enable_timestamp(void);
+void net_disable_timestamp(void);
 
 #ifdef CONFIG_PROC_FS
-extern int __init dev_proc_init(void);
+int __init dev_proc_init(void);
 #else
 #define dev_proc_init() 0
 #endif
 
-extern int netdev_class_create_file(struct class_attribute *class_attr);
-extern void netdev_class_remove_file(struct class_attribute *class_attr);
+int netdev_class_create_file(struct class_attribute *class_attr);
+void netdev_class_remove_file(struct class_attribute *class_attr);
 
 extern struct kobj_ns_type_operations net_ns_type_operations;
 
-extern const char *netdev_drivername(const struct net_device *dev);
+const char *netdev_drivername(const struct net_device *dev);
 
-extern void linkwatch_run_queue(void);
+void linkwatch_run_queue(void);
 
 static inline netdev_features_t netdev_get_wanted_features(
 	struct net_device *dev)
@@ -3007,22 +2991,22 @@ static inline const char *netdev_name(const struct net_device *dev)
 	return dev->name;
 }
 
-extern __printf(3, 4)
+__printf(3, 4)
 int netdev_printk(const char *level, const struct net_device *dev,
 		  const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_emerg(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_alert(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_crit(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_err(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_warn(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_notice(const struct net_device *dev, const char *format, ...);
-extern __printf(2, 3)
+__printf(2, 3)
 int netdev_info(const struct net_device *dev, const char *format, ...);
 
 #define MODULE_ALIAS_NETDEV(device) \
-- 
cgit 


From e34ff4906199d2ebd248ae897ae34f52bea151c9 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 11 Sep 2013 22:29:05 -0400
Subject: sysfs: remove ktype->namespace() invocations in directory code

For some unrecognizable reason, namespace information is communicated
to sysfs through ktype->namespace() callback when there's *nothing*
which needs the use of a callback.  The whole sequence of operations
is completely synchronous and sysfs operations simply end up calling
back into the layer which just invoked it in order to find out the
namespace information, which is completely backwards, obfuscates
what's going on and unnecessarily tangles two separate layers.

This patch doesn't remove ktype->namespace() but shifts its handling
to kobject layer.  We probably want to get rid of the callback in the
long term.

This patch adds an explicit param to sysfs_{create|rename|move}_dir()
and renames them to sysfs_{create|rename|move}_dir_ns(), respectively.
ktype->namespace() invocations are moved to the calling sites of the
above functions.  A new helper kboject_namespace() is introduced which
directly tests kobj_ns_type_operations->type which should give the
same result as testing sysfs_fs_type(parent_sd) and returns @kobj's
namespace tag as necessary.  kobject_namespace() is extern as it will
be used from another file in the following patches.

This patch should be an equivalent conversion without any functional
difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/sysfs/dir.c          | 23 ++++++++---------------
 include/linux/kobject.h |  1 +
 include/linux/sysfs.h   | 20 ++++++++++++--------
 lib/kobject.c           | 28 ++++++++++++++++++++++++----
 4 files changed, 45 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 834c64cb7f88..878ac3afe1b8 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -730,14 +730,14 @@ static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
 }
 
 /**
- *	sysfs_create_dir - create a directory for an object.
- *	@kobj:		object we're creating directory for.
+ * sysfs_create_dir_ns - create a directory for an object with a namespace tag
+ * @kobj: object we're creating directory for
+ * @ns: the namespace tag to use
  */
-int sysfs_create_dir(struct kobject *kobj)
+int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	enum kobj_ns_type type;
 	struct sysfs_dirent *parent_sd, *sd;
-	const void *ns = NULL;
 	int error = 0;
 
 	BUG_ON(!kobj);
@@ -750,8 +750,6 @@ int sysfs_create_dir(struct kobject *kobj)
 	if (!parent_sd)
 		return -ENOENT;
 
-	if (sysfs_ns_type(parent_sd))
-		ns = kobj->ktype->namespace(kobj);
 	type = sysfs_read_ns_type(kobj);
 
 	error = create_dir(kobj, parent_sd, type, ns, kobject_name(kobj), &sd);
@@ -909,26 +907,21 @@ int sysfs_rename(struct sysfs_dirent *sd,
 	return error;
 }
 
-int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
+			const void *new_ns)
 {
 	struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
-	const void *new_ns = NULL;
-
-	if (sysfs_ns_type(parent_sd))
-		new_ns = kobj->ktype->namespace(kobj);
 
 	return sysfs_rename(kobj->sd, parent_sd, new_ns, new_name);
 }
 
-int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
+int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
+		      const void *new_ns)
 {
 	struct sysfs_dirent *sd = kobj->sd;
 	struct sysfs_dirent *new_parent_sd;
-	const void *new_ns = NULL;
 
 	BUG_ON(!sd->s_parent);
-	if (sysfs_ns_type(sd->s_parent))
-		new_ns = kobj->ktype->namespace(kobj);
 	new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
 		new_parent_kobj->sd : &sysfs_root;
 
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index de6dcbcc6ef7..e7ba650086ce 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -107,6 +107,7 @@ extern int __must_check kobject_move(struct kobject *, struct kobject *);
 extern struct kobject *kobject_get(struct kobject *kobj);
 extern void kobject_put(struct kobject *kobj);
 
+extern const void *kobject_namespace(struct kobject *kobj);
 extern char *kobject_get_path(struct kobject *kobj, gfp_t flag);
 
 struct kobj_type {
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 82f7fac78e77..7f56bad3be82 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -182,11 +182,13 @@ struct sysfs_dirent;
 int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
 			    void *data, struct module *owner);
 
-int __must_check sysfs_create_dir(struct kobject *kobj);
+int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
 void sysfs_remove_dir(struct kobject *kobj);
-int __must_check sysfs_rename_dir(struct kobject *kobj, const char *new_name);
-int __must_check sysfs_move_dir(struct kobject *kobj,
-				struct kobject *new_parent_kobj);
+int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
+				     const void *new_ns);
+int __must_check sysfs_move_dir_ns(struct kobject *kobj,
+				   struct kobject *new_parent_kobj,
+				   const void *new_ns);
 
 int __must_check sysfs_create_file_ns(struct kobject *kobj,
 				      const struct attribute *attr,
@@ -258,7 +260,7 @@ static inline int sysfs_schedule_callback(struct kobject *kobj,
 	return -ENOSYS;
 }
 
-static inline int sysfs_create_dir(struct kobject *kobj)
+static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	return 0;
 }
@@ -267,13 +269,15 @@ static inline void sysfs_remove_dir(struct kobject *kobj)
 {
 }
 
-static inline int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+static inline int sysfs_rename_dir_ns(struct kobject *kobj,
+				      const char *new_name, const void *new_ns)
 {
 	return 0;
 }
 
-static inline int sysfs_move_dir(struct kobject *kobj,
-				 struct kobject *new_parent_kobj)
+static inline int sysfs_move_dir_ns(struct kobject *kobj,
+				    struct kobject *new_parent_kobj,
+				    const void *new_ns)
 {
 	return 0;
 }
diff --git a/lib/kobject.c b/lib/kobject.c
index 962175134702..85fb3a161b21 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -18,6 +18,24 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 
+/**
+ * kobject_namespace - return @kobj's namespace tag
+ * @kobj: kobject in question
+ *
+ * Returns namespace tag of @kobj if its parent has namespace ops enabled
+ * and thus @kobj should have a namespace tag associated with it.  Returns
+ * %NULL otherwise.
+ */
+const void *kobject_namespace(struct kobject *kobj)
+{
+	const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj);
+
+	if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE)
+		return NULL;
+
+	return kobj->ktype->namespace(kobj);
+}
+
 /*
  * populate_dir - populate directory with attributes.
  * @kobj: object we're working on.
@@ -46,8 +64,9 @@ static int populate_dir(struct kobject *kobj)
 
 static int create_dir(struct kobject *kobj)
 {
-	int error = 0;
-	error = sysfs_create_dir(kobj);
+	int error;
+
+	error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj));
 	if (!error) {
 		error = populate_dir(kobj);
 		if (error)
@@ -428,7 +447,7 @@ int kobject_rename(struct kobject *kobj, const char *new_name)
 		goto out;
 	}
 
-	error = sysfs_rename_dir(kobj, new_name);
+	error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj));
 	if (error)
 		goto out;
 
@@ -472,6 +491,7 @@ int kobject_move(struct kobject *kobj, struct kobject *new_parent)
 		if (kobj->kset)
 			new_parent = kobject_get(&kobj->kset->kobj);
 	}
+
 	/* old object path */
 	devpath = kobject_get_path(kobj, GFP_KERNEL);
 	if (!devpath) {
@@ -486,7 +506,7 @@ int kobject_move(struct kobject *kobj, struct kobject *new_parent)
 	sprintf(devpath_string, "DEVPATH_OLD=%s", devpath);
 	envp[0] = devpath_string;
 	envp[1] = NULL;
-	error = sysfs_move_dir(kobj, new_parent);
+	error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj));
 	if (error)
 		goto out;
 	old_parent = kobj->parent;
-- 
cgit 


From 4b30ee58ee64c64f59fd876e4afa6ed82caef3a4 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 11 Sep 2013 22:29:06 -0400
Subject: sysfs: remove ktype->namespace() invocations in symlink code

There's no reason for sysfs to be calling ktype->namespace().  It is
backwards, obfuscates what's going on and unnecessarily tangles two
separate layers.

There are two places where symlink code calls ktype->namespace().

* sysfs_do_create_link_sd() calls it to find out the namespace tag of
  the target directory.  Unless symlinking races with cross-namespace
  renaming, this equals @target_sd->s_ns.

* sysfs_rename_link() uses it to find out the new namespace to rename
  to and the new namespace can be different from the existing one.
  The function is renamed to sysfs_rename_link_ns() with an explicit
  @ns argument and the ktype->namespace() invocation is shifted to the
  device layer.

While this patch replaces ktype->namespace() invocation with the
recorded result in @target_sd, this shouldn't result in any behvior
difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c   |  8 +++++---
 fs/sysfs/symlink.c    | 16 +++++++---------
 include/linux/sysfs.h | 16 ++++++++++++----
 3 files changed, 24 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index c7cfadcf6752..3335000be2dc 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1881,6 +1881,7 @@ EXPORT_SYMBOL_GPL(device_destroy);
  */
 int device_rename(struct device *dev, const char *new_name)
 {
+	struct kobject *kobj = &dev->kobj;
 	char *old_device_name = NULL;
 	int error;
 
@@ -1898,13 +1899,14 @@ int device_rename(struct device *dev, const char *new_name)
 	}
 
 	if (dev->class) {
-		error = sysfs_rename_link(&dev->class->p->subsys.kobj,
-			&dev->kobj, old_device_name, new_name);
+		error = sysfs_rename_link_ns(&dev->class->p->subsys.kobj,
+					     kobj, old_device_name,
+					     new_name, kobject_namespace(kobj));
 		if (error)
 			goto out;
 	}
 
-	error = kobject_rename(&dev->kobj, new_name);
+	error = kobject_rename(kobj, new_name);
 	if (error)
 		goto out;
 
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 2dd4507d9edd..12d58ada3e6d 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -52,7 +52,7 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
 
 	ns_type = sysfs_ns_type(parent_sd);
 	if (ns_type)
-		sd->s_ns = target->ktype->namespace(target);
+		sd->s_ns = target_sd->s_ns;
 	sd->s_symlink.target_sd = target_sd;
 	target_sd = NULL;	/* reference is now owned by the symlink */
 
@@ -181,19 +181,20 @@ void sysfs_remove_link(struct kobject *kobj, const char *name)
 EXPORT_SYMBOL_GPL(sysfs_remove_link);
 
 /**
- *	sysfs_rename_link - rename symlink in object's directory.
+ *	sysfs_rename_link_ns - rename symlink in object's directory.
  *	@kobj:	object we're acting for.
  *	@targ:	object we're pointing to.
  *	@old:	previous name of the symlink.
  *	@new:	new name of the symlink.
+ *	@new_ns: new namespace of the symlink.
  *
  *	A helper function for the common rename symlink idiom.
  */
-int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
-			const char *old, const char *new)
+int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
+			 const char *old, const char *new, const void *new_ns)
 {
 	struct sysfs_dirent *parent_sd, *sd = NULL;
-	const void *old_ns = NULL, *new_ns = NULL;
+	const void *old_ns = NULL;
 	int result;
 
 	if (!kobj)
@@ -215,16 +216,13 @@ int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
 	if (sd->s_symlink.target_sd->s_dir.kobj != targ)
 		goto out;
 
-	if (sysfs_ns_type(parent_sd))
-		new_ns = targ->ktype->namespace(targ);
-
 	result = sysfs_rename(sd, parent_sd, new_ns, new);
 
 out:
 	sysfs_put(sd);
 	return result;
 }
-EXPORT_SYMBOL_GPL(sysfs_rename_link);
+EXPORT_SYMBOL_GPL(sysfs_rename_link_ns);
 
 static int sysfs_get_target_path(struct sysfs_dirent *parent_sd,
 				 struct sysfs_dirent *target_sd, char *path)
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 7f56bad3be82..c792f73ac7fa 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -213,8 +213,9 @@ int __must_check sysfs_create_link_nowarn(struct kobject *kobj,
 					  const char *name);
 void sysfs_remove_link(struct kobject *kobj, const char *name);
 
-int sysfs_rename_link(struct kobject *kobj, struct kobject *target,
-			const char *old_name, const char *new_name);
+int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *target,
+			 const char *old_name, const char *new_name,
+			 const void *new_ns);
 
 void sysfs_delete_link(struct kobject *dir, struct kobject *targ,
 			const char *name);
@@ -340,8 +341,9 @@ static inline void sysfs_remove_link(struct kobject *kobj, const char *name)
 {
 }
 
-static inline int sysfs_rename_link(struct kobject *k, struct kobject *t,
-				    const char *old_name, const char *new_name)
+static inline int sysfs_rename_link_ns(struct kobject *k, struct kobject *t,
+				       const char *old_name,
+				       const char *new_name, const void *ns)
 {
 	return 0;
 }
@@ -454,4 +456,10 @@ static inline void sysfs_remove_file(struct kobject *kobj,
 	return sysfs_remove_file_ns(kobj, attr, NULL);
 }
 
+static inline int sysfs_rename_link(struct kobject *kobj, struct kobject *target,
+				    const char *old_name, const char *new_name)
+{
+	return sysfs_rename_link_ns(kobj, target, old_name, new_name, NULL);
+}
+
 #endif /* _SYSFS_H_ */
-- 
cgit 


From 388975cccaaf11abd47525f664c76891c440481a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 11 Sep 2013 23:19:13 -0400
Subject: sysfs: clean up sysfs_get_dirent()

The pre-existing sysfs interfaces which take explicit namespace
argument are weird in that they place the optional @ns in front of
@name which is contrary to the established convention.  For example,
we end up forcing vast majority of sysfs_get_dirent() users to do
sysfs_get_dirent(parent, NULL, name), which is silly and error-prone
especially as @ns and @name may be interchanged without causing
compilation warning.

This renames sysfs_get_dirent() to sysfs_get_dirent_ns() and swap the
positions of @name and @ns, and sysfs_get_dirent() is now a wrapper
around sysfs_get_dirent_ns().  This makes confusions a lot less
likely.

There are other interfaces which take @ns before @name.  They'll be
updated by following patches.

This patch doesn't introduce any functional changes.

v2: EXPORT_SYMBOL_GPL() wasn't updated leading to undefined symbol
    error on module builds.  Reported by build test robot.  Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kay Sievers <kay@vrfy.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpio/gpiolib.c |  2 +-
 drivers/md/bitmap.c    |  4 ++--
 drivers/md/md.c        |  2 +-
 drivers/md/md.h        |  2 +-
 fs/sysfs/dir.c         | 11 ++++++-----
 fs/sysfs/file.c        |  4 ++--
 fs/sysfs/group.c       | 10 +++++-----
 fs/sysfs/symlink.c     |  2 +-
 fs/sysfs/sysfs.h       |  3 ---
 include/linux/sysfs.h  | 19 ++++++++++++-------
 10 files changed, 31 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86ef3461ec06..a094356020a6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -408,7 +408,7 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 			IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING;
 
 	if (!value_sd) {
-		value_sd = sysfs_get_dirent(dev->kobj.sd, NULL, "value");
+		value_sd = sysfs_get_dirent(dev->kobj.sd, "value");
 		if (!value_sd) {
 			ret = -ENODEV;
 			goto err_out;
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index a7fd82133b12..12dc29ba7399 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1654,9 +1654,9 @@ int bitmap_create(struct mddev *mddev)
 	bitmap->mddev = mddev;
 
 	if (mddev->kobj.sd)
-		bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
+		bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap");
 	if (bm) {
-		bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear");
+		bitmap->sysfs_can_clear = sysfs_get_dirent(bm, "can_clear");
 		sysfs_put(bm);
 	} else
 		bitmap->sysfs_can_clear = NULL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index adf4d7e1d5e1..8a0d7625681c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3555,7 +3555,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			printk(KERN_WARNING
 			       "md: cannot register extra attributes for %s\n",
 			       mdname(mddev));
-		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
+		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
 	}		
 	if (mddev->pers->sync_request != NULL &&
 	    pers->sync_request == NULL) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 608050c43f17..b0051f2fbc0c 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -501,7 +501,7 @@ extern struct attribute_group md_bitmap_group;
 static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
 {
 	if (sd)
-		return sysfs_get_dirent(sd, NULL, name);
+		return sysfs_get_dirent(sd, name);
 	return sd;
 }
 static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 1dfb4aaf9446..fee19d16e4a2 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -630,9 +630,10 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
 }
 
 /**
- *	sysfs_get_dirent - find and get sysfs_dirent with the given name
+ *	sysfs_get_dirent_ns - find and get sysfs_dirent with the given name
  *	@parent_sd: sysfs_dirent to search under
  *	@name: name to look for
+ *	@ns: the namespace tag to use
  *
  *	Look for sysfs_dirent with name @name under @parent_sd and get
  *	it if found.
@@ -643,9 +644,9 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
  *	RETURNS:
  *	Pointer to sysfs_dirent if found, NULL if not.
  */
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name)
+struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
+					 const unsigned char *name,
+					 const void *ns)
 {
 	struct sysfs_dirent *sd;
 
@@ -656,7 +657,7 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
 
 	return sd;
 }
-EXPORT_SYMBOL_GPL(sysfs_get_dirent);
+EXPORT_SYMBOL_GPL(sysfs_get_dirent_ns);
 
 static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 	const void *ns, const char *name, struct sysfs_dirent **p_sd)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index e784340f1599..0f3214a70985 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -563,7 +563,7 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 	int error;
 
 	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, NULL, group);
+		dir_sd = sysfs_get_dirent(kobj->sd, group);
 	else
 		dir_sd = sysfs_get(kobj->sd);
 
@@ -645,7 +645,7 @@ void sysfs_remove_file_from_group(struct kobject *kobj,
 	struct sysfs_dirent *dir_sd;
 
 	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, NULL, group);
+		dir_sd = sysfs_get_dirent(kobj->sd, group);
 	else
 		dir_sd = sysfs_get(kobj->sd);
 	if (dir_sd) {
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 25c78f23dae8..21102158ca33 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -207,7 +207,7 @@ void sysfs_remove_group(struct kobject *kobj,
 	struct sysfs_dirent *sd;
 
 	if (grp->name) {
-		sd = sysfs_get_dirent(dir_sd, NULL, grp->name);
+		sd = sysfs_get_dirent(dir_sd, grp->name);
 		if (!sd) {
 			WARN(!sd, KERN_WARNING
 			     "sysfs group %p not found for kobject '%s'\n",
@@ -262,7 +262,7 @@ int sysfs_merge_group(struct kobject *kobj,
 	struct attribute *const *attr;
 	int i;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
 	if (!dir_sd)
 		return -ENOENT;
 
@@ -289,7 +289,7 @@ void sysfs_unmerge_group(struct kobject *kobj,
 	struct sysfs_dirent *dir_sd;
 	struct attribute *const *attr;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
 	if (dir_sd) {
 		for (attr = grp->attrs; *attr; ++attr)
 			sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
@@ -311,7 +311,7 @@ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
 	struct sysfs_dirent *dir_sd;
 	int error = 0;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
 	if (!dir_sd)
 		return -ENOENT;
 
@@ -333,7 +333,7 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
 {
 	struct sysfs_dirent *dir_sd;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
 	if (dir_sd) {
 		sysfs_hash_and_remove(dir_sd, NULL, link_name);
 		sysfs_put(dir_sd);
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 7d981ce2e87f..c96b31a16485 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -191,7 +191,7 @@ int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
 		old_ns = targ->sd->s_ns;
 
 	result = -ENOENT;
-	sd = sysfs_get_dirent(parent_sd, old_ns, old);
+	sd = sysfs_get_dirent_ns(parent_sd, old, old_ns);
 	if (!sd)
 		goto out;
 
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 7664d1b3d594..6faacafda777 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -164,9 +164,6 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
 struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
 				       const void *ns,
 				       const unsigned char *name);
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name);
 struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type);
 
 void release_sysfs_dirent(struct sysfs_dirent *sd);
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index c792f73ac7fa..6695040a0317 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -245,9 +245,9 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
 
 void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
 void sysfs_notify_dirent(struct sysfs_dirent *sd);
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name);
+struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
+					 const unsigned char *name,
+					 const void *ns);
 struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd);
 void sysfs_put(struct sysfs_dirent *sd);
 
@@ -422,10 +422,9 @@ static inline void sysfs_notify(struct kobject *kobj, const char *dir,
 static inline void sysfs_notify_dirent(struct sysfs_dirent *sd)
 {
 }
-static inline
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name)
+static inline struct sysfs_dirent *
+sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd, const unsigned char *name,
+		    const void *ns)
 {
 	return NULL;
 }
@@ -462,4 +461,10 @@ static inline int sysfs_rename_link(struct kobject *kobj, struct kobject *target
 	return sysfs_rename_link_ns(kobj, target, old_name, new_name, NULL);
 }
 
+static inline struct sysfs_dirent *
+sysfs_get_dirent(struct sysfs_dirent *parent_sd, const unsigned char *name)
+{
+	return sysfs_get_dirent_ns(parent_sd, name, NULL);
+}
+
 #endif /* _SYSFS_H_ */
-- 
cgit 


From eee031649707db3c9920d9498f8d03819b74fc23 Mon Sep 17 00:00:00 2001
From: Jeff Mahoney <jeffm@suse.com>
Date: Wed, 11 Sep 2013 13:00:30 -0400
Subject: kobject: introduce kobj_completion

A common way to handle kobject lifetimes in embedded in objects with
different lifetime rules is to pair the kobject with a struct completion.

This introduces a kobj_completion structure that can be used in place
of the pairing, along with several convenience functions for
initialization, release, and put-and-wait.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/kobj_completion.h | 18 +++++++++++++++
 lib/kobject.c                   | 50 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)
 create mode 100644 include/linux/kobj_completion.h

(limited to 'include')

diff --git a/include/linux/kobj_completion.h b/include/linux/kobj_completion.h
new file mode 100644
index 000000000000..a428f6436063
--- /dev/null
+++ b/include/linux/kobj_completion.h
@@ -0,0 +1,18 @@
+#ifndef _KOBJ_COMPLETION_H_
+#define _KOBJ_COMPLETION_H_
+
+#include <linux/kobject.h>
+#include <linux/completion.h>
+
+struct kobj_completion {
+	struct kobject kc_kobj;
+	struct completion kc_unregister;
+};
+
+#define kobj_to_kobj_completion(kobj) \
+	container_of(kobj, struct kobj_completion, kc_kobj)
+
+void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype);
+void kobj_completion_release(struct kobject *kobj);
+void kobj_completion_del_and_wait(struct kobj_completion *kc);
+#endif /* _KOBJ_COMPLETION_H_ */
diff --git a/lib/kobject.c b/lib/kobject.c
index e769ee3c2fb9..a5a9b13b0648 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/kobject.h>
+#include <linux/kobj_completion.h>
 #include <linux/string.h>
 #include <linux/export.h>
 #include <linux/stat.h>
@@ -749,6 +750,55 @@ const struct sysfs_ops kobj_sysfs_ops = {
 	.store	= kobj_attr_store,
 };
 
+/**
+ * kobj_completion_init - initialize a kobj_completion object.
+ * @kc: kobj_completion
+ * @ktype: type of kobject to initialize
+ *
+ * kobj_completion structures can be embedded within structures with different
+ * lifetime rules.  During the release of the enclosing object, we can
+ * wait on the release of the kobject so that we don't free it while it's
+ * still busy.
+ */
+void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype)
+{
+	init_completion(&kc->kc_unregister);
+	kobject_init(&kc->kc_kobj, ktype);
+}
+EXPORT_SYMBOL_GPL(kobj_completion_init);
+
+/**
+ * kobj_completion_release - release a kobj_completion object
+ * @kobj: kobject embedded in kobj_completion
+ *
+ * Used with kobject_release to notify waiters that the kobject has been
+ * released.
+ */
+void kobj_completion_release(struct kobject *kobj)
+{
+	struct kobj_completion *kc = kobj_to_kobj_completion(kobj);
+	complete(&kc->kc_unregister);
+}
+EXPORT_SYMBOL_GPL(kobj_completion_release);
+
+/**
+ * kobj_completion_del_and_wait - release the kobject and wait for it
+ * @kc: kobj_completion object to release
+ *
+ * Delete the kobject from sysfs and drop the reference count.  Then wait
+ * until any other outstanding references are also dropped.  This routine
+ * is only necessary once other references may have been taken on the
+ * kobject.  Typically this happens when the kobject has been published
+ * to sysfs via kobject_add.
+ */
+void kobj_completion_del_and_wait(struct kobj_completion *kc)
+{
+	kobject_del(&kc->kc_kobj);
+	kobject_put(&kc->kc_kobj);
+	wait_for_completion(&kc->kc_unregister);
+}
+EXPORT_SYMBOL_GPL(kobj_completion_del_and_wait);
+
 /**
  * kset_register - initialize and add a kset.
  * @k: kset.
-- 
cgit 


From 3f9120b0424f3e03c75518cb751f9e2bfa73c32a Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Mon, 23 Sep 2013 16:27:26 +0200
Subject: driver core: prevent deferred probe with platform_driver_probe

Prevent drivers relying on platform_driver_probe from requesting
deferred probing in order to avoid further futile probe attempts (either
the driver has been unregistered or its probe function has been set to
platform_drv_probe_fail when probing is retried).

Note that several platform drivers currently return subsystem errors
from probe and that these can include -EPROBE_DEFER (e.g. if a gpio
request fails).

Add a warning to platform_drv_probe that can be used to catch drivers
that inadvertently request probe deferral while using
platform_driver_probe.

Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/platform.c         | 17 +++++++++++++----
 include/linux/platform_device.h |  1 +
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 4f8bef3eb5a8..47051cd25113 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -488,6 +488,11 @@ static int platform_drv_probe(struct device *_dev)
 	if (ret && ACPI_HANDLE(_dev))
 		acpi_dev_pm_detach(_dev, true);
 
+	if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
+		dev_warn(_dev, "probe deferral not supported\n");
+		ret = -ENXIO;
+	}
+
 	return ret;
 }
 
@@ -553,8 +558,7 @@ EXPORT_SYMBOL_GPL(platform_driver_unregister);
 /**
  * platform_driver_probe - register driver for non-hotpluggable device
  * @drv: platform driver structure
- * @probe: the driver probe routine, probably from an __init section,
- *         must not return -EPROBE_DEFER.
+ * @probe: the driver probe routine, probably from an __init section
  *
  * Use this instead of platform_driver_register() when you know the device
  * is not hotpluggable and has already been registered, and you want to
@@ -565,8 +569,7 @@ EXPORT_SYMBOL_GPL(platform_driver_unregister);
  * into system-on-chip processors, where the controller devices have been
  * configured as part of board setup.
  *
- * This is incompatible with deferred probing so probe() must not
- * return -EPROBE_DEFER.
+ * Note that this is incompatible with deferred probing.
  *
  * Returns zero if the driver registered and bound to a device, else returns
  * a negative error code and with the driver not registered.
@@ -576,6 +579,12 @@ int __init_or_module platform_driver_probe(struct platform_driver *drv,
 {
 	int retval, code;
 
+	/*
+	 * Prevent driver from requesting probe deferral to avoid further
+	 * futile probe attempts.
+	 */
+	drv->prevent_deferred_probe = true;
+
 	/* make sure driver won't have bind/unbind attributes */
 	drv->driver.suppress_bind_attrs = true;
 
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index ce8e4ffd78c7..16f6654082dd 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -178,6 +178,7 @@ struct platform_driver {
 	int (*resume)(struct platform_device *);
 	struct device_driver driver;
 	const struct platform_device_id *id_table;
+	bool prevent_deferred_probe;
 };
 
 #define to_platform_driver(drv)	(container_of((drv), struct platform_driver, \
-- 
cgit 


From a75e1c73a46eed0332d036e371f714e76d167c07 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Sat, 31 Aug 2013 13:16:49 +0900
Subject: extcon: Fix indentation coding style to improve readability

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Myungjoo Ham <myungjoo.ham@samsung.com>
---
 drivers/extcon/extcon-adc-jack.c       | 20 +++++-----
 drivers/extcon/extcon-class.c          | 26 ++++++-------
 include/linux/extcon.h                 | 67 ++++++++++++++++++----------------
 include/linux/extcon/extcon-adc-jack.h | 42 ++++++++++-----------
 include/linux/extcon/extcon-gpio.h     | 16 ++++----
 5 files changed, 87 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index 5985807e52c9..5d16428afd53 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -27,16 +27,16 @@
 
 /**
  * struct adc_jack_data - internal data for adc_jack device driver
- * @edev        - extcon device.
- * @cable_names - list of supported cables.
- * @num_cables  - size of cable_names.
- * @adc_conditions       - list of adc value conditions.
- * @num_conditions       - size of adc_conditions.
- * @irq         - irq number of attach/detach event (0 if not exist).
- * @handling_delay      - interrupt handler will schedule extcon event
- *                      handling at handling_delay jiffies.
- * @handler     - extcon event handler called by interrupt handler.
- * @chan       - iio channel being queried.
+ * @edev:		extcon device.
+ * @cable_names:	list of supported cables.
+ * @num_cables:		size of cable_names.
+ * @adc_conditions:	list of adc value conditions.
+ * @num_conditions:	size of adc_conditions.
+ * @irq:		irq number of attach/detach event (0 if not exist).
+ * @handling_delay:	interrupt handler will schedule extcon event
+ *			handling at handling_delay jiffies.
+ * @handler:		extcon event handler called by interrupt handler.
+ * @chan:		iio channel being queried.
  */
 struct adc_jack_data {
 	struct extcon_dev edev;
diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c
index 148382faded9..a29720822847 100644
--- a/drivers/extcon/extcon-class.c
+++ b/drivers/extcon/extcon-class.c
@@ -74,7 +74,7 @@ static DEFINE_MUTEX(extcon_dev_list_lock);
 
 /**
  * check_mutually_exclusive - Check if new_state violates mutually_exclusive
- *			    condition.
+ *			      condition.
  * @edev:	the extcon device
  * @new_state:	new cable attach status for @edev
  *
@@ -189,7 +189,7 @@ static ssize_t cable_state_show(struct device *dev,
 
 /**
  * extcon_update_state() - Update the cable attach states of the extcon device
- *			only for the masked bits.
+ *			   only for the masked bits.
  * @edev:	the extcon device
  * @mask:	the bit mask to designate updated bits.
  * @state:	new cable attach status for @edev
@@ -227,7 +227,6 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state)
 		edev->state |= state & mask;
 
 		raw_notifier_call_chain(&edev->nh, old_state, edev);
-
 		/* This could be in interrupt handler */
 		prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 		if (prop_buf) {
@@ -339,8 +338,9 @@ EXPORT_SYMBOL_GPL(extcon_get_cable_state);
 
 /**
  * extcon_set_cable_state_() - Set the status of a specific cable.
- * @edev:	the extcon device that has the cable.
- * @index:	cable index that can be retrieved by extcon_find_cable_index().
+ * @edev:		the extcon device that has the cable.
+ * @index:		cable index that can be retrieved by
+ *			extcon_find_cable_index().
  * @cable_state:	the new cable status. The default semantics is
  *			true: attached / false: detached.
  */
@@ -359,8 +359,8 @@ EXPORT_SYMBOL_GPL(extcon_set_cable_state_);
 
 /**
  * extcon_set_cable_state() - Set the status of a specific cable.
- * @edev:	the extcon device that has the cable.
- * @cable_name:	cable name.
+ * @edev:		the extcon device that has the cable.
+ * @cable_name:		cable name.
  * @cable_state:	the new cable status. The default semantics is
  *			true: attached / false: detached.
  *
@@ -419,14 +419,14 @@ static int _call_per_cable(struct notifier_block *nb, unsigned long val,
 
 /**
  * extcon_register_interest() - Register a notifier for a state change of a
- *			      specific cable, not an entier set of cables of a
- *			      extcon device.
- * @obj:	an empty extcon_specific_cable_nb object to be returned.
+ *				specific cable, not an entier set of cables of a
+ *				extcon device.
+ * @obj:		an empty extcon_specific_cable_nb object to be returned.
  * @extcon_name:	the name of extcon device.
  *			if NULL, extcon_register_interest will register
  *			every cable with the target cable_name given.
  * @cable_name:		the target cable name.
- * @nb:		the notifier block to get notified.
+ * @nb:			the notifier block to get notified.
  *
  * Provide an empty extcon_specific_cable_nb. extcon_register_interest() sets
  * the struct for you.
@@ -487,7 +487,7 @@ EXPORT_SYMBOL_GPL(extcon_register_interest);
 
 /**
  * extcon_unregister_interest() - Unregister the notifier registered by
- *				extcon_register_interest().
+ *				  extcon_register_interest().
  * @obj:	the extcon_specific_cable_nb object returned by
  *		extcon_register_interest().
  */
@@ -502,7 +502,7 @@ EXPORT_SYMBOL_GPL(extcon_unregister_interest);
 
 /**
  * extcon_register_notifier() - Register a notifiee to get notified by
- *			      any attach status changes from the extcon.
+ *				any attach status changes from the extcon.
  * @edev:	the extcon device.
  * @nb:		a notifier block to be registered.
  *
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index fcb51c88319f..c2b652dde72c 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -51,10 +51,10 @@
 enum extcon_cable_name {
 	EXTCON_USB = 0,
 	EXTCON_USB_HOST,
-	EXTCON_TA, /* Travel Adaptor */
+	EXTCON_TA,			/* Travel Adaptor */
 	EXTCON_FAST_CHARGER,
 	EXTCON_SLOW_CHARGER,
-	EXTCON_CHARGE_DOWNSTREAM, /* Charging an external device */
+	EXTCON_CHARGE_DOWNSTREAM,	/* Charging an external device */
 	EXTCON_HDMI,
 	EXTCON_MHL,
 	EXTCON_DVI,
@@ -76,8 +76,8 @@ struct extcon_cable;
 
 /**
  * struct extcon_dev - An extcon device represents one external connector.
- * @name:	The name of this extcon device. Parent device name is used
- *		if NULL.
+ * @name:		The name of this extcon device. Parent device name is
+ *			used if NULL.
  * @supported_cable:	Array of supported cable names ending with NULL.
  *			If supported_cable is NULL, cable name related APIs
  *			are disabled.
@@ -89,21 +89,21 @@ struct extcon_cable;
  *			be attached simulataneously. {0x7, 0} is equivalent to
  *			{0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there
  *			can be no simultaneous connections.
- * @print_name:	An optional callback to override the method to print the
- *		name of the extcon device.
+ * @print_name:		An optional callback to override the method to print the
+ *			name of the extcon device.
  * @print_state:	An optional callback to override the method to print the
- *		status of the extcon device.
- * @dev:	Device of this extcon. Do not provide at register-time.
- * @state:	Attach/detach state of this extcon. Do not provide at
- *		register-time
- * @nh:	Notifier for the state change events from this extcon
- * @entry:	To support list of extcon devices so that users can search
- *		for extcon devices based on the extcon name.
+ *			status of the extcon device.
+ * @dev:		Device of this extcon. Do not provide at register-time.
+ * @state:		Attach/detach state of this extcon. Do not provide at
+ *			register-time.
+ * @nh:			Notifier for the state change events from this extcon
+ * @entry:		To support list of extcon devices so that users can search
+ *			for extcon devices based on the extcon name.
  * @lock:
  * @max_supported:	Internal value to store the number of cables.
  * @extcon_dev_type:	Device_type struct to provide attribute_groups
  *			customized for each extcon device.
- * @cables:	Sysfs subdirectories. Each represents one cable.
+ * @cables:		Sysfs subdirectories. Each represents one cable.
  *
  * In most cases, users only need to provide "User initializing data" of
  * this struct when registering an extcon. In some exceptional cases,
@@ -111,26 +111,27 @@ struct extcon_cable;
  * are overwritten by register function.
  */
 struct extcon_dev {
-	/* --- Optional user initializing data --- */
-	const char	*name;
+	/* Optional user initializing data */
+	const char *name;
 	const char **supported_cable;
-	const u32	*mutually_exclusive;
+	const u32 *mutually_exclusive;
 
-	/* --- Optional callbacks to override class functions --- */
+	/* Optional callbacks to override class functions */
 	ssize_t	(*print_name)(struct extcon_dev *edev, char *buf);
 	ssize_t	(*print_state)(struct extcon_dev *edev, char *buf);
 
-	/* --- Internal data. Please do not set. --- */
-	struct device	*dev;
-	u32		state;
+	/* Internal data. Please do not set. */
+	struct device *dev;
 	struct raw_notifier_head nh;
 	struct list_head entry;
-	spinlock_t lock; /* could be called by irq handler */
 	int max_supported;
+	spinlock_t lock;	/* could be called by irq handler */
+	u32 state;
 
 	/* /sys/class/extcon/.../cable.n/... */
 	struct device_type extcon_dev_type;
 	struct extcon_cable *cables;
+
 	/* /sys/class/extcon/.../mutually_exclusive/... */
 	struct attribute_group attr_g_muex;
 	struct attribute **attrs_muex;
@@ -138,13 +139,13 @@ struct extcon_dev {
 };
 
 /**
- * struct extcon_cable	- An internal data for each cable of extcon device.
- * @edev:	The extcon device
+ * struct extcon_cable - An internal data for each cable of extcon device.
+ * @edev:		The extcon device
  * @cable_index:	Index of this cable in the edev
- * @attr_g:	Attribute group for the cable
- * @attr_name:	"name" sysfs entry
- * @attr_state:	"state" sysfs entry
- * @attrs:	Array pointing to attr_name and attr_state for attr_g
+ * @attr_g:		Attribute group for the cable
+ * @attr_name:		"name" sysfs entry
+ * @attr_state:		"state" sysfs entry
+ * @attrs:		Array pointing to attr_name and attr_state for attr_g
  */
 struct extcon_cable {
 	struct extcon_dev *edev;
@@ -159,11 +160,13 @@ struct extcon_cable {
 
 /**
  * struct extcon_specific_cable_nb - An internal data for
- *				extcon_register_interest().
- * @internal_nb:	a notifier block bridging extcon notifier and cable notifier.
- * @user_nb:	user provided notifier block for events from a specific cable.
+ *				     extcon_register_interest().
+ * @internal_nb:	A notifier block bridging extcon notifier
+ *			and cable notifier.
+ * @user_nb:		user provided notifier block for events from
+ *			a specific cable.
  * @cable_index:	the target cable.
- * @edev:	the target extcon device.
+ * @edev:		the target extcon device.
  * @previous_value:	the saved previous event value.
  */
 struct extcon_specific_cable_nb {
diff --git a/include/linux/extcon/extcon-adc-jack.h b/include/linux/extcon/extcon-adc-jack.h
index 20e9eef25d4c..9ca958c4e94c 100644
--- a/include/linux/extcon/extcon-adc-jack.h
+++ b/include/linux/extcon/extcon-adc-jack.h
@@ -20,10 +20,10 @@
 
 /**
  * struct adc_jack_cond - condition to use an extcon state
- * @state      - the corresponding extcon state (if 0, this struct denotes
- *             the last adc_jack_cond element among the array)
- * @min_adc    - min adc value for this condition
- * @max_adc    - max adc value for this condition
+ * @state:		the corresponding extcon state (if 0, this struct
+ *			denotes the last adc_jack_cond element among the array)
+ * @min_adc:		min adc value for this condition
+ * @max_adc:		max adc value for this condition
  *
  * For example, if { .state = 0x3, .min_adc = 100, .max_adc = 200}, it means
  * that if ADC value is between (inclusive) 100 and 200, than the cable 0 and
@@ -33,34 +33,34 @@
  * because when no adc_jack_cond is met, state = 0 is automatically chosen.
  */
 struct adc_jack_cond {
-	u32 state; /* extcon state value. 0 if invalid */
+	u32 state;	/* extcon state value. 0 if invalid */
 	u32 min_adc;
 	u32 max_adc;
 };
 
 /**
  * struct adc_jack_pdata - platform data for adc jack device.
- * @name       - name of the extcon device. If null, "adc-jack" is used.
- * @consumer_channel - Unique name to identify the channel on the consumer
- *                   side. This typically describes the channels used within
- *                   the consumer. E.g. 'battery_voltage'
- * @cable_names        - array of cable names ending with null.
- * @adc_contitions     - array of struct adc_jack_cond conditions ending
- *                     with .state = 0 entry. This describes how to decode
- *                     adc values into extcon state.
- * @irq_flags  - irq flags used for the @irq
- * @handling_delay_ms  - in some devices, we need to read ADC value some
- *                     milli-seconds after the interrupt occurs. You may
- *                     describe such delays with @handling_delay_ms, which
- *                     is rounded-off by jiffies.
+ * @name:		name of the extcon device. If null, "adc-jack" is used.
+ * @consumer_channel:	Unique name to identify the channel on the consumer
+ *			side. This typically describes the channels used within
+ *			the consumer. E.g. 'battery_voltage'
+ * @cable_names:	array of cable names ending with null.
+ * @adc_contitions:	array of struct adc_jack_cond conditions ending
+ *			with .state = 0 entry. This describes how to decode
+ *			adc values into extcon state.
+ * @irq_flags:		irq flags used for the @irq
+ * @handling_delay_ms:	in some devices, we need to read ADC value some
+ *			milli-seconds after the interrupt occurs. You may
+ *			describe such delays with @handling_delay_ms, which
+ *			is rounded-off by jiffies.
  */
 struct adc_jack_pdata {
 	const char *name;
 	const char *consumer_channel;
-	/*
-	 * The last entry should be NULL
-	 */
+
+	/* The last entry should be NULL */
 	const char **cable_names;
+
 	/* The last entry's state should be 0 */
 	struct adc_jack_cond *adc_conditions;
 
diff --git a/include/linux/extcon/extcon-gpio.h b/include/linux/extcon/extcon-gpio.h
index 2d8307f7d67d..4ce1aa7d29bd 100644
--- a/include/linux/extcon/extcon-gpio.h
+++ b/include/linux/extcon/extcon-gpio.h
@@ -25,14 +25,14 @@
 
 /**
  * struct gpio_extcon_platform_data - A simple GPIO-controlled extcon device.
- * @name	The name of this GPIO extcon device.
- * @gpio	Corresponding GPIO.
- * @debounce	Debounce time for GPIO IRQ in ms.
- * @irq_flags	IRQ Flags (e.g., IRQF_TRIGGER_LOW).
- * @state_on	print_state is overriden with state_on if attached. If Null,
- *		default method of extcon class is used.
- * @state_off	print_state is overriden with state_on if detached. If Null,
- *		default method of extcon class is used.
+ * @name:		The name of this GPIO extcon device.
+ * @gpio:		Corresponding GPIO.
+ * @debounce:		Debounce time for GPIO IRQ in ms.
+ * @irq_flags:		IRQ Flags (e.g., IRQF_TRIGGER_LOW).
+ * @state_on:		print_state is overriden with state_on if attached.
+ *			If NULL, default method of extcon class is used.
+ * @state_off:		print_state is overriden with state_on if detached.
+ *			If NUll, default method of extcon class is used.
  *
  * Note that in order for state_on or state_off to be valid, both state_on
  * and state_off should be not NULL. If at least one of them is NULL,
-- 
cgit 


From 5bfbdc9caa7e16b2a77a62a9f9a63b5693e23716 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 12 Sep 2013 08:49:54 +0900
Subject: extcon: gpio: Add support for active-low presence to detect pins

This patch add 'gpio_active_low' field to 'struct gpio_extcon_data'
to check whether gpio active state is 1(high) or 0(low).

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-gpio.c       | 4 ++++
 include/linux/extcon/extcon-gpio.h | 4 ++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index cd7dbb60f60f..b02c670ef01d 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -34,6 +34,7 @@
 struct gpio_extcon_data {
 	struct extcon_dev edev;
 	unsigned gpio;
+	bool gpio_active_low;
 	const char *state_on;
 	const char *state_off;
 	int irq;
@@ -49,6 +50,8 @@ static void gpio_extcon_work(struct work_struct *work)
 			     work);
 
 	state = gpio_get_value(data->gpio);
+	if (data->gpio_active_low)
+		state = !state;
 	extcon_set_state(&data->edev, state);
 }
 
@@ -96,6 +99,7 @@ static int gpio_extcon_probe(struct platform_device *pdev)
 
 	extcon_data->edev.name = pdata->name;
 	extcon_data->gpio = pdata->gpio;
+	extcon_data->gpio_active_low = pdata->gpio_active_low;
 	extcon_data->state_on = pdata->state_on;
 	extcon_data->state_off = pdata->state_off;
 	if (pdata->state_on && pdata->state_off)
diff --git a/include/linux/extcon/extcon-gpio.h b/include/linux/extcon/extcon-gpio.h
index 4ce1aa7d29bd..4195810f87fe 100644
--- a/include/linux/extcon/extcon-gpio.h
+++ b/include/linux/extcon/extcon-gpio.h
@@ -27,6 +27,9 @@
  * struct gpio_extcon_platform_data - A simple GPIO-controlled extcon device.
  * @name:		The name of this GPIO extcon device.
  * @gpio:		Corresponding GPIO.
+ * @gpio_active_low:	Boolean describing whether gpio active state is 1 or 0
+ *			If true, low state of gpio means active.
+ *			If false, high state of gpio means active.
  * @debounce:		Debounce time for GPIO IRQ in ms.
  * @irq_flags:		IRQ Flags (e.g., IRQF_TRIGGER_LOW).
  * @state_on:		print_state is overriden with state_on if attached.
@@ -41,6 +44,7 @@
 struct gpio_extcon_platform_data {
 	const char *name;
 	unsigned gpio;
+	bool gpio_active_low;
 	unsigned long debounce;
 	unsigned long irq_flags;
 
-- 
cgit 


From dae616512476024aa61d2a598461ab6eff8c0709 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Fri, 27 Sep 2013 09:19:40 +0900
Subject: extcon: Change field type of 'dev' in extcon_dev structure

The extcon device must always need 'struct device' so this patch change
field type of 'dev' instead of allocating memory for 'struct device' on
extcon_dev_register() function.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Myungjoo Ham <cw00.choi@samsung.com>
---
 drivers/extcon/extcon-adc-jack.c |  2 +-
 drivers/extcon/extcon-class.c    | 52 ++++++++++++++++++----------------------
 include/linux/extcon.h           |  4 ++--
 3 files changed, 26 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index 5694c468b958..dcbade667d0c 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -64,7 +64,7 @@ static void adc_jack_handler(struct work_struct *work)
 
 	ret = iio_read_channel_raw(data->chan, &adc_val);
 	if (ret < 0) {
-		dev_err(data->edev.dev, "read channel() error: %d\n", ret);
+		dev_err(&data->edev.dev, "read channel() error: %d\n", ret);
 		return;
 	}
 
diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c
index 2f2d374ccd1d..2801c14d5232 100644
--- a/drivers/extcon/extcon-class.c
+++ b/drivers/extcon/extcon-class.c
@@ -162,7 +162,7 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 			return ret;
 	}
 
-	return sprintf(buf, "%s\n", dev_name(edev->dev));
+	return sprintf(buf, "%s\n", dev_name(&edev->dev));
 }
 static DEVICE_ATTR_RO(name);
 
@@ -230,7 +230,7 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state)
 		/* This could be in interrupt handler */
 		prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 		if (prop_buf) {
-			length = name_show(edev->dev, NULL, prop_buf);
+			length = name_show(&edev->dev, NULL, prop_buf);
 			if (length > 0) {
 				if (prop_buf[length - 1] == '\n')
 					prop_buf[length - 1] = 0;
@@ -238,7 +238,7 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state)
 					"NAME=%s", prop_buf);
 				envp[env_offset++] = name_buf;
 			}
-			length = state_show(edev->dev, NULL, prop_buf);
+			length = state_show(&edev->dev, NULL, prop_buf);
 			if (length > 0) {
 				if (prop_buf[length - 1] == '\n')
 					prop_buf[length - 1] = 0;
@@ -250,14 +250,14 @@ int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state)
 			/* Unlock early before uevent */
 			spin_unlock_irqrestore(&edev->lock, flags);
 
-			kobject_uevent_env(&edev->dev->kobj, KOBJ_CHANGE, envp);
+			kobject_uevent_env(&edev->dev.kobj, KOBJ_CHANGE, envp);
 			free_page((unsigned long)prop_buf);
 		} else {
 			/* Unlock early before uevent */
 			spin_unlock_irqrestore(&edev->lock, flags);
 
-			dev_err(edev->dev, "out of memory in extcon_set_state\n");
-			kobject_uevent(&edev->dev->kobj, KOBJ_CHANGE);
+			dev_err(&edev->dev, "out of memory in extcon_set_state\n");
+			kobject_uevent(&edev->dev.kobj, KOBJ_CHANGE);
 		}
 	} else {
 		/* No changes */
@@ -556,7 +556,6 @@ static int create_extcon_class(void)
 
 static void extcon_dev_release(struct device *dev)
 {
-	kfree(dev);
 }
 
 static const char *muex_name = "mutually_exclusive";
@@ -594,19 +593,16 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
 	}
 
 	if (index > SUPPORTED_CABLE_MAX) {
-		dev_err(edev->dev, "extcon: maximum number of supported cables exceeded.\n");
+		dev_err(&edev->dev, "extcon: maximum number of supported cables exceeded.\n");
 		return -EINVAL;
 	}
 
-	edev->dev = kzalloc(sizeof(struct device), GFP_KERNEL);
-	if (!edev->dev)
-		return -ENOMEM;
-	edev->dev->parent = dev;
-	edev->dev->class = extcon_class;
-	edev->dev->release = extcon_dev_release;
+	edev->dev.parent = dev;
+	edev->dev.class = extcon_class;
+	edev->dev.release = extcon_dev_release;
 
 	edev->name = edev->name ? edev->name : dev_name(dev);
-	dev_set_name(edev->dev, "%s", edev->name);
+	dev_set_name(&edev->dev, "%s", edev->name);
 
 	if (edev->max_supported) {
 		char buf[10];
@@ -714,7 +710,7 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
 			goto err_alloc_groups;
 		}
 
-		edev->extcon_dev_type.name = dev_name(edev->dev);
+		edev->extcon_dev_type.name = dev_name(&edev->dev);
 		edev->extcon_dev_type.release = dummy_sysfs_dev_release;
 
 		for (index = 0; index < edev->max_supported; index++)
@@ -724,25 +720,24 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
 			edev->extcon_dev_type.groups[index] =
 				&edev->attr_g_muex;
 
-		edev->dev->type = &edev->extcon_dev_type;
+		edev->dev.type = &edev->extcon_dev_type;
 	}
 
-	ret = device_register(edev->dev);
+	ret = device_register(&edev->dev);
 	if (ret) {
-		put_device(edev->dev);
+		put_device(&edev->dev);
 		goto err_dev;
 	}
 #if defined(CONFIG_ANDROID)
 	if (switch_class)
-		ret = class_compat_create_link(switch_class, edev->dev,
-					       NULL);
+		ret = class_compat_create_link(switch_class, &edev->dev, NULL);
 #endif /* CONFIG_ANDROID */
 
 	spin_lock_init(&edev->lock);
 
 	RAW_INIT_NOTIFIER_HEAD(&edev->nh);
 
-	dev_set_drvdata(edev->dev, edev);
+	dev_set_drvdata(&edev->dev, edev);
 	edev->state = 0;
 
 	mutex_lock(&extcon_dev_list_lock);
@@ -768,7 +763,6 @@ err_alloc_cables:
 	if (edev->max_supported)
 		kfree(edev->cables);
 err_sysfs_alloc:
-	kfree(edev->dev);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(extcon_dev_register);
@@ -788,9 +782,9 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 	list_del(&edev->entry);
 	mutex_unlock(&extcon_dev_list_lock);
 
-	if (IS_ERR_OR_NULL(get_device(edev->dev))) {
-		dev_err(edev->dev, "Failed to unregister extcon_dev (%s)\n",
-				dev_name(edev->dev));
+	if (IS_ERR_OR_NULL(get_device(&edev->dev))) {
+		dev_err(&edev->dev, "Failed to unregister extcon_dev (%s)\n",
+				dev_name(&edev->dev));
 		return;
 	}
 
@@ -812,10 +806,10 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 
 #if defined(CONFIG_ANDROID)
 	if (switch_class)
-		class_compat_remove_link(switch_class, edev->dev, NULL);
+		class_compat_remove_link(switch_class, &edev->dev, NULL);
 #endif
-	device_unregister(edev->dev);
-	put_device(edev->dev);
+	device_unregister(&edev->dev);
+	put_device(&edev->dev);
 }
 EXPORT_SYMBOL_GPL(extcon_dev_unregister);
 
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index c2b652dde72c..0269bafb0ee8 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -93,7 +93,7 @@ struct extcon_cable;
  *			name of the extcon device.
  * @print_state:	An optional callback to override the method to print the
  *			status of the extcon device.
- * @dev:		Device of this extcon. Do not provide at register-time.
+ * @dev:		Device of this extcon.
  * @state:		Attach/detach state of this extcon. Do not provide at
  *			register-time.
  * @nh:			Notifier for the state change events from this extcon
@@ -121,7 +121,7 @@ struct extcon_dev {
 	ssize_t	(*print_state)(struct extcon_dev *edev, char *buf);
 
 	/* Internal data. Please do not set. */
-	struct device *dev;
+	struct device dev;
 	struct raw_notifier_head nh;
 	struct list_head entry;
 	int max_supported;
-- 
cgit 


From 42d7d7539a7bcf1d493b989465283c464f4a0525 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Fri, 27 Sep 2013 09:20:26 +0900
Subject: extcon: Simplify extcon_dev_register() prototype by removing
 unnecessary parameter

This patch remove extcon_dev_register()'s second parameter which means
the pointer of parent device to simplify prototype of this function.
So, if extcon device has the parent device, it should set the pointer of
parent device to edev.dev.parent in extcon device driver instead of in
extcon_dev_register().

Cc: Graeme Gregory <gg@slimlogic.co.uk>
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Myungjoo Ham <myungjoo.ham@samsung.com>
---
 Documentation/extcon/porting-android-switch-class |  6 ++++--
 drivers/extcon/extcon-adc-jack.c                  |  3 ++-
 drivers/extcon/extcon-arizona.c                   |  3 ++-
 drivers/extcon/extcon-class.c                     | 11 +++++++----
 drivers/extcon/extcon-gpio.c                      |  3 ++-
 drivers/extcon/extcon-max77693.c                  |  3 ++-
 drivers/extcon/extcon-max8997.c                   |  3 ++-
 drivers/extcon/extcon-palmas.c                    |  3 ++-
 include/linux/extcon.h                            |  5 ++---
 9 files changed, 25 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/extcon/porting-android-switch-class b/Documentation/extcon/porting-android-switch-class
index eb0fa5f4fe88..5377f6317961 100644
--- a/Documentation/extcon/porting-android-switch-class
+++ b/Documentation/extcon/porting-android-switch-class
@@ -25,8 +25,10 @@ MyungJoo Ham <myungjoo.ham@samsung.com>
     @print_state: no change but type change (switch_dev->extcon_dev)
 
 - switch_dev_register(sdev, dev)
-	=> extcon_dev_register(edev, dev)
-	: no change but type change (sdev->edev)
+	=> extcon_dev_register(edev)
+	: type change (sdev->edev)
+	: remove second param('dev'). if edev has parent device, should store
+	  'dev' to 'edev.dev.parent' before registering extcon device
 - switch_dev_unregister(sdev)
 	=> extcon_dev_unregister(edev)
 	: no change but type change (sdev->edev)
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index dcbade667d0c..e23f1c2e5053 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -110,6 +110,7 @@ static int adc_jack_probe(struct platform_device *pdev)
 		goto out;
 	}
 
+	data->edev.dev.parent = &pdev->dev;
 	data->edev.supported_cable = pdata->cable_names;
 
 	/* Check the length of array and set num_cables */
@@ -148,7 +149,7 @@ static int adc_jack_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, data);
 
-	err = extcon_dev_register(&data->edev, &pdev->dev);
+	err = extcon_dev_register(&data->edev);
 	if (err)
 		goto out;
 
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index e54ce08f669c..ec9a14e05fdd 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -1130,9 +1130,10 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 	}
 
 	info->edev.name = "Headset Jack";
+	info->edev.dev.parent = arizona->dev;
 	info->edev.supported_cable = arizona_cable;
 
-	ret = extcon_dev_register(&info->edev, arizona->dev);
+	ret = extcon_dev_register(&info->edev);
 	if (ret < 0) {
 		dev_err(arizona->dev, "extcon_dev_register() failed: %d\n",
 			ret);
diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c
index 2801c14d5232..84902d3fee11 100644
--- a/drivers/extcon/extcon-class.c
+++ b/drivers/extcon/extcon-class.c
@@ -566,14 +566,13 @@ static void dummy_sysfs_dev_release(struct device *dev)
 /**
  * extcon_dev_register() - Register a new extcon device
  * @edev	: the new extcon device (should be allocated before calling)
- * @dev		: the parent device for this extcon device.
  *
  * Among the members of edev struct, please set the "user initializing data"
  * in any case and set the "optional callbacks" if required. However, please
  * do not set the values of "internal data", which are initialized by
  * this function.
  */
-int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
+int extcon_dev_register(struct extcon_dev *edev)
 {
 	int ret, index = 0;
 
@@ -597,11 +596,15 @@ int extcon_dev_register(struct extcon_dev *edev, struct device *dev)
 		return -EINVAL;
 	}
 
-	edev->dev.parent = dev;
 	edev->dev.class = extcon_class;
 	edev->dev.release = extcon_dev_release;
 
-	edev->name = edev->name ? edev->name : dev_name(dev);
+	edev->name = edev->name ? edev->name : dev_name(edev->dev.parent);
+	if (IS_ERR_OR_NULL(edev->name)) {
+		dev_err(&edev->dev,
+			"extcon device name is null\n");
+		return -EINVAL;
+	}
 	dev_set_name(&edev->dev, "%s", edev->name);
 
 	if (edev->max_supported) {
diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index b02c670ef01d..7e0dff58e494 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -98,6 +98,7 @@ static int gpio_extcon_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	extcon_data->edev.name = pdata->name;
+	extcon_data->edev.dev.parent = &pdev->dev;
 	extcon_data->gpio = pdata->gpio;
 	extcon_data->gpio_active_low = pdata->gpio_active_low;
 	extcon_data->state_on = pdata->state_on;
@@ -112,7 +113,7 @@ static int gpio_extcon_probe(struct platform_device *pdev)
 				msecs_to_jiffies(pdata->debounce);
 	}
 
-	ret = extcon_dev_register(&extcon_data->edev, &pdev->dev);
+	ret = extcon_dev_register(&extcon_data->edev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index 4849ea1e92f6..ab9bc24e1a52 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -1171,8 +1171,9 @@ static int max77693_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 	info->edev->name = DEV_NAME;
+	info->edev->dev.parent = &pdev->dev;
 	info->edev->supported_cable = max77693_extcon_cable;
-	ret = extcon_dev_register(info->edev, NULL);
+	ret = extcon_dev_register(info->edev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
 		goto err_irq;
diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index e55ec38b4148..0b1cbb5fdf9e 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -705,8 +705,9 @@ static int max8997_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 	info->edev->name = DEV_NAME;
+	info->edev->dev.parent = &pdev->dev;
 	info->edev->supported_cable = max8997_extcon_cable;
-	ret = extcon_dev_register(info->edev, NULL);
+	ret = extcon_dev_register(info->edev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
 		goto err_irq;
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 0c2fb68fb791..6c91976dd823 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -178,9 +178,10 @@ static int palmas_usb_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, palmas_usb);
 
 	palmas_usb->edev.supported_cable = palmas_extcon_cable;
+	palmas_usb->edev.dev.parent = palmas_usb->dev;
 	palmas_usb->edev.mutually_exclusive = mutually_exclusive;
 
-	status = extcon_dev_register(&palmas_usb->edev, palmas_usb->dev);
+	status = extcon_dev_register(&palmas_usb->edev);
 	if (status) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
 		return status;
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 0269bafb0ee8..21c59af1150b 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -183,7 +183,7 @@ struct extcon_specific_cable_nb {
  * Following APIs are for notifiers or configurations.
  * Notifiers are the external port and connection devices.
  */
-extern int extcon_dev_register(struct extcon_dev *edev, struct device *dev);
+extern int extcon_dev_register(struct extcon_dev *edev);
 extern void extcon_dev_unregister(struct extcon_dev *edev);
 extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name);
 
@@ -241,8 +241,7 @@ extern int extcon_register_notifier(struct extcon_dev *edev,
 extern int extcon_unregister_notifier(struct extcon_dev *edev,
 				      struct notifier_block *nb);
 #else /* CONFIG_EXTCON */
-static inline int extcon_dev_register(struct extcon_dev *edev,
-				      struct device *dev)
+static inline int extcon_dev_register(struct extcon_dev *edev)
 {
 	return 0;
 }
-- 
cgit 


From 8af2c2869fd129bce0d0dfd86c6364c1096f9eff Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Date: Thu, 28 Mar 2013 22:53:42 +0800
Subject: video: atmel_lcdfb: fix platform data struct

Today we mix pdata and drivers data in the struct atmel_lcdfb_info
Fix it and introduce a new struct atmel_lcdfb_pdata for platform data only

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 arch/arm/mach-at91/at91sam9261_devices.c    |   6 +-
 arch/arm/mach-at91/at91sam9263_devices.c    |   6 +-
 arch/arm/mach-at91/at91sam9g45_devices.c    |   6 +-
 arch/arm/mach-at91/at91sam9rl_devices.c     |   6 +-
 arch/arm/mach-at91/board-sam9261ek.c        |   6 +-
 arch/arm/mach-at91/board-sam9263ek.c        |   4 +-
 arch/arm/mach-at91/board-sam9m10g45ek.c     |   4 +-
 arch/arm/mach-at91/board-sam9rlek.c         |   4 +-
 arch/arm/mach-at91/board.h                  |   4 +-
 arch/avr32/boards/atngw100/evklcd10x.c      |   6 +-
 arch/avr32/boards/atngw100/mrmt.c           |   4 +-
 arch/avr32/boards/atstk1000/atstk1000.h     |   2 +-
 arch/avr32/boards/atstk1000/setup.c         |   2 +-
 arch/avr32/boards/favr-32/setup.c           |   2 +-
 arch/avr32/boards/hammerhead/setup.c        |   2 +-
 arch/avr32/boards/merisc/display.c          |   2 +-
 arch/avr32/boards/mimc200/setup.c           |   4 +-
 arch/avr32/mach-at32ap/at32ap700x.c         |   8 +--
 arch/avr32/mach-at32ap/include/mach/board.h |   4 +-
 drivers/video/atmel_lcdfb.c                 | 105 ++++++++++++++++++----------
 include/video/atmel_lcdc.h                  |  23 +-----
 21 files changed, 109 insertions(+), 101 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 629ea5fc95cf..b2a34740146a 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -465,7 +465,7 @@ void __init at91_add_device_spi(struct spi_board_info *devices, int nr_devices)
 
 #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
 static u64 lcdc_dmamask = DMA_BIT_MASK(32);
-static struct atmel_lcdfb_info lcdc_data;
+static struct atmel_lcdfb_pdata lcdc_data;
 
 static struct resource lcdc_resources[] = {
 	[0] = {
@@ -498,7 +498,7 @@ static struct platform_device at91_lcdc_device = {
 	.num_resources	= ARRAY_SIZE(lcdc_resources),
 };
 
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data)
 {
 	if (!data) {
 		return;
@@ -559,7 +559,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	platform_device_register(&at91_lcdc_device);
 }
 #else
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {}
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {}
 #endif
 
 
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index 858c8aac2daf..4aeadddbc181 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -832,7 +832,7 @@ void __init at91_add_device_can(struct at91_can_data *data) {}
 
 #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
 static u64 lcdc_dmamask = DMA_BIT_MASK(32);
-static struct atmel_lcdfb_info lcdc_data;
+static struct atmel_lcdfb_pdata lcdc_data;
 
 static struct resource lcdc_resources[] = {
 	[0] = {
@@ -859,7 +859,7 @@ static struct platform_device at91_lcdc_device = {
 	.num_resources	= ARRAY_SIZE(lcdc_resources),
 };
 
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data)
 {
 	if (!data)
 		return;
@@ -891,7 +891,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	platform_device_register(&at91_lcdc_device);
 }
 #else
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {}
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {}
 #endif
 
 
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index acb703e13331..cb36fa872d30 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -965,7 +965,7 @@ void __init at91_add_device_isi(struct isi_platform_data *data,
 
 #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
 static u64 lcdc_dmamask = DMA_BIT_MASK(32);
-static struct atmel_lcdfb_info lcdc_data;
+static struct atmel_lcdfb_pdata lcdc_data;
 
 static struct resource lcdc_resources[] = {
 	[0] = {
@@ -991,7 +991,7 @@ static struct platform_device at91_lcdc_device = {
 	.num_resources	= ARRAY_SIZE(lcdc_resources),
 };
 
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data)
 {
 	if (!data)
 		return;
@@ -1037,7 +1037,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	platform_device_register(&at91_lcdc_device);
 }
 #else
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {}
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {}
 #endif
 
 
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index 352468f265a9..a698bdab2cce 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -498,7 +498,7 @@ void __init at91_add_device_ac97(struct ac97c_platform_data *data) {}
 
 #if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
 static u64 lcdc_dmamask = DMA_BIT_MASK(32);
-static struct atmel_lcdfb_info lcdc_data;
+static struct atmel_lcdfb_pdata lcdc_data;
 
 static struct resource lcdc_resources[] = {
 	[0] = {
@@ -525,7 +525,7 @@ static struct platform_device at91_lcdc_device = {
 	.num_resources	= ARRAY_SIZE(lcdc_resources),
 };
 
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data)
 {
 	if (!data) {
 		return;
@@ -557,7 +557,7 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	platform_device_register(&at91_lcdc_device);
 }
 #else
-void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data) {}
+void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data) {}
 #endif
 
 
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index d3437624ca4e..4ab1ba7557e4 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -401,7 +401,7 @@ static void at91_lcdc_stn_power_control(int on)
 	}
 }
 
-static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = {
 	.default_bpp			= 1,
 	.default_dmacon			= ATMEL_LCDC_DMAEN,
 	.default_lcdcon2		= AT91SAM9261_DEFAULT_STN_LCDCON2,
@@ -453,7 +453,7 @@ static void at91_lcdc_tft_power_control(int on)
 		at91_set_gpio_value(AT91_PIN_PA12, 1);	/* power down */
 }
 
-static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = {
 	.lcdcon_is_backlight		= true,
 	.default_bpp			= 16,
 	.default_dmacon			= ATMEL_LCDC_DMAEN,
@@ -465,7 +465,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
 #endif
 
 #else
-static struct atmel_lcdfb_info __initdata ek_lcdc_data;
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data;
 #endif
 
 
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 3284df05df14..0fdae3f1541d 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -281,7 +281,7 @@ static void at91_lcdc_power_control(int on)
 }
 
 /* Driver datas */
-static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = {
 	.lcdcon_is_backlight		= true,
 	.default_bpp			= 16,
 	.default_dmacon			= ATMEL_LCDC_DMAEN,
@@ -292,7 +292,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
 };
 
 #else
-static struct atmel_lcdfb_info __initdata ek_lcdc_data;
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data;
 #endif
 
 
diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c
index 2a94896a1375..ef39078c8ce2 100644
--- a/arch/arm/mach-at91/board-sam9m10g45ek.c
+++ b/arch/arm/mach-at91/board-sam9m10g45ek.c
@@ -284,7 +284,7 @@ static struct fb_monspecs at91fb_default_monspecs = {
 					| ATMEL_LCDC_CLKMOD_ALWAYSACTIVE)
 
 /* Driver datas */
-static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = {
 	.lcdcon_is_backlight		= true,
 	.default_bpp			= 32,
 	.default_dmacon			= ATMEL_LCDC_DMAEN,
@@ -295,7 +295,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
 };
 
 #else
-static struct atmel_lcdfb_info __initdata ek_lcdc_data;
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data;
 #endif
 
 
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index aa265dcf2128..b77d7a9febd8 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -179,7 +179,7 @@ static void at91_lcdc_power_control(int on)
 }
 
 /* Driver datas */
-static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data = {
 	.lcdcon_is_backlight            = true,
 	.default_bpp			= 16,
 	.default_dmacon			= ATMEL_LCDC_DMAEN,
@@ -191,7 +191,7 @@ static struct atmel_lcdfb_info __initdata ek_lcdc_data = {
 };
 
 #else
-static struct atmel_lcdfb_info __initdata ek_lcdc_data;
+static struct atmel_lcdfb_pdata __initdata ek_lcdc_data;
 #endif
 
 
diff --git a/arch/arm/mach-at91/board.h b/arch/arm/mach-at91/board.h
index 4a234fb2ab3b..6c08b341167d 100644
--- a/arch/arm/mach-at91/board.h
+++ b/arch/arm/mach-at91/board.h
@@ -107,8 +107,8 @@ extern void __init at91_add_device_pwm(u32 mask);
 extern void __init at91_add_device_ssc(unsigned id, unsigned pins);
 
  /* LCD Controller */
-struct atmel_lcdfb_info;
-extern void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data);
+struct atmel_lcdfb_pdata;
+extern void __init at91_add_device_lcdc(struct atmel_lcdfb_pdata *data);
 
  /* AC97 */
 extern void __init at91_add_device_ac97(struct ac97c_platform_data *data);
diff --git a/arch/avr32/boards/atngw100/evklcd10x.c b/arch/avr32/boards/atngw100/evklcd10x.c
index 20388750d564..dc4280413e9d 100644
--- a/arch/avr32/boards/atngw100/evklcd10x.c
+++ b/arch/avr32/boards/atngw100/evklcd10x.c
@@ -58,7 +58,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
 	.dclkmax		= 28330000,
 };
 
-static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
 	.default_bpp		= 16,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
@@ -96,7 +96,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
 	.dclkmax		= 7000000,
 };
 
-static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
 	.default_bpp		= 16,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
@@ -134,7 +134,7 @@ static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
 	.dclkmax		= 6400000,
 };
 
-static struct atmel_lcdfb_info __initdata atevklcd10x_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
 	.default_bpp		= 16,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/atngw100/mrmt.c b/arch/avr32/boards/atngw100/mrmt.c
index 7de083d19b7e..1ba09e4c02b1 100644
--- a/arch/avr32/boards/atngw100/mrmt.c
+++ b/arch/avr32/boards/atngw100/mrmt.c
@@ -83,7 +83,7 @@ static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
 	.dclkmax		= 9260000,
 };
 
-static struct atmel_lcdfb_info __initdata rmt_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
 	.default_bpp		= 24,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
@@ -126,7 +126,7 @@ static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
 	.dclkmax		= 9260000,
 };
 
-static struct atmel_lcdfb_info __initdata rmt_lcdc_data = {
+static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
 	.default_bpp		= 24,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/atstk1000/atstk1000.h b/arch/avr32/boards/atstk1000/atstk1000.h
index 9392d3252865..653cc09e536c 100644
--- a/arch/avr32/boards/atstk1000/atstk1000.h
+++ b/arch/avr32/boards/atstk1000/atstk1000.h
@@ -10,7 +10,7 @@
 #ifndef __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
 #define __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
 
-extern struct atmel_lcdfb_info atstk1000_lcdc_data;
+extern struct atmel_lcdfb_pdata atstk1000_lcdc_data;
 
 void atstk1000_setup_j2_leds(void);
 
diff --git a/arch/avr32/boards/atstk1000/setup.c b/arch/avr32/boards/atstk1000/setup.c
index 2d6b560115d9..b6b88f5e0b43 100644
--- a/arch/avr32/boards/atstk1000/setup.c
+++ b/arch/avr32/boards/atstk1000/setup.c
@@ -55,7 +55,7 @@ static struct fb_monspecs __initdata atstk1000_default_monspecs = {
 	.dclkmax		= 30000000,
 };
 
-struct atmel_lcdfb_info __initdata atstk1000_lcdc_data = {
+struct atmel_lcdfb_pdata __initdata atstk1000_lcdc_data = {
 	.default_bpp		= 24,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/favr-32/setup.c b/arch/avr32/boards/favr-32/setup.c
index 27bd6fbe21cb..7b1f2cd85400 100644
--- a/arch/avr32/boards/favr-32/setup.c
+++ b/arch/avr32/boards/favr-32/setup.c
@@ -125,7 +125,7 @@ static struct fb_monspecs __initdata favr32_default_monspecs = {
 	.dclkmax		= 28000000,
 };
 
-struct atmel_lcdfb_info __initdata favr32_lcdc_data = {
+struct atmel_lcdfb_pdata __initdata favr32_lcdc_data = {
 	.default_bpp		= 16,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/hammerhead/setup.c b/arch/avr32/boards/hammerhead/setup.c
index 9d1efd1cd425..dc0e317f2ecd 100644
--- a/arch/avr32/boards/hammerhead/setup.c
+++ b/arch/avr32/boards/hammerhead/setup.c
@@ -77,7 +77,7 @@ static struct fb_monspecs __initdata hammerhead_hda350t_monspecs = {
 	.dclkmax		= 10000000,
 };
 
-struct atmel_lcdfb_info __initdata hammerhead_lcdc_data = {
+struct atmel_lcdfb_pdata __initdata hammerhead_lcdc_data = {
 	.default_bpp		= 24,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/merisc/display.c b/arch/avr32/boards/merisc/display.c
index 85a543cd4abc..e7683ee7ed40 100644
--- a/arch/avr32/boards/merisc/display.c
+++ b/arch/avr32/boards/merisc/display.c
@@ -45,7 +45,7 @@ static struct fb_monspecs merisc_fb_monspecs = {
 	.dclkmax	= 30000000,
 };
 
-struct atmel_lcdfb_info merisc_lcdc_data = {
+struct atmel_lcdfb_pdata merisc_lcdc_data = {
 	.default_bpp		= 24,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/boards/mimc200/setup.c b/arch/avr32/boards/mimc200/setup.c
index 05358aa5ef7d..1cb8e9cc5cfa 100644
--- a/arch/avr32/boards/mimc200/setup.c
+++ b/arch/avr32/boards/mimc200/setup.c
@@ -8,7 +8,7 @@
  * published by the Free Software Foundation.
  */
 
-extern struct atmel_lcdfb_info mimc200_lcdc_data;
+extern struct atmel_lcdfb_pdata mimc200_lcdc_data;
 
 #include <linux/clk.h>
 #include <linux/etherdevice.h>
@@ -71,7 +71,7 @@ static struct fb_monspecs __initdata mimc200_default_monspecs = {
 	.dclkmax		= 25200000,
 };
 
-struct atmel_lcdfb_info __initdata mimc200_lcdc_data = {
+struct atmel_lcdfb_pdata __initdata mimc200_lcdc_data = {
 	.default_bpp		= 16,
 	.default_dmacon		= ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
 	.default_lcdcon2	= (ATMEL_LCDC_DISTYPE_TFT
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index a68f3cf7c3c1..a1f4d1e91b52 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1439,7 +1439,7 @@ fail:
  *  LCDC
  * -------------------------------------------------------------------- */
 #if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
-static struct atmel_lcdfb_info atmel_lcdfb0_data;
+static struct atmel_lcdfb_pdata atmel_lcdfb0_data;
 static struct resource atmel_lcdfb0_resource[] = {
 	{
 		.start		= 0xff000000,
@@ -1467,12 +1467,12 @@ static struct clk atmel_lcdfb0_pixclk = {
 };
 
 struct platform_device *__init
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
+at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
 		     unsigned long fbmem_start, unsigned long fbmem_len,
 		     u64 pin_mask)
 {
 	struct platform_device *pdev;
-	struct atmel_lcdfb_info *info;
+	struct atmel_lcdfb_pdata *info;
 	struct fb_monspecs *monspecs;
 	struct fb_videomode *modedb;
 	unsigned int modedb_size;
@@ -1529,7 +1529,7 @@ at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
 	}
 
 	info = pdev->dev.platform_data;
-	memcpy(info, data, sizeof(struct atmel_lcdfb_info));
+	memcpy(info, data, sizeof(struct atmel_lcdfb_pdata));
 	info->default_monspecs = monspecs;
 
 	pdev->name = "at32ap-lcdfb";
diff --git a/arch/avr32/mach-at32ap/include/mach/board.h b/arch/avr32/mach-at32ap/include/mach/board.h
index d485b0391357..f1a316d52c73 100644
--- a/arch/avr32/mach-at32ap/include/mach/board.h
+++ b/arch/avr32/mach-at32ap/include/mach/board.h
@@ -44,9 +44,9 @@ struct platform_device *
 at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n);
 void at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n);
 
-struct atmel_lcdfb_info;
+struct atmel_lcdfb_pdata;
 struct platform_device *
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_info *data,
+at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
 		     unsigned long fbmem_start, unsigned long fbmem_len,
 		     u64 pin_mask);
 
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 3f7d6dc3408d..0d7214df1237 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -20,12 +20,44 @@
 #include <linux/gfp.h>
 #include <linux/module.h>
 #include <linux/platform_data/atmel.h>
+#include <video/of_display_timing.h>
 
 #include <mach/cpu.h>
 #include <asm/gpio.h>
 
 #include <video/atmel_lcdc.h>
 
+struct atmel_lcdfb_config {
+	bool have_alt_pixclock;
+	bool have_hozval;
+	bool have_intensity_bit;
+};
+
+ /* LCD Controller info data structure, stored in device platform_data */
+struct atmel_lcdfb_info {
+	spinlock_t		lock;
+	struct fb_info		*info;
+	void __iomem		*mmio;
+	int			irq_base;
+	struct work_struct	task;
+
+	unsigned int		smem_len;
+	struct platform_device	*pdev;
+	struct clk		*bus_clk;
+	struct clk		*lcdc_clk;
+
+	struct backlight_device	*backlight;
+	u8			bl_power;
+	u8			saved_lcdcon;
+
+	u32			pseudo_palette[16];
+	bool			have_intensity_bit;
+
+	struct atmel_lcdfb_pdata pdata;
+
+	struct atmel_lcdfb_config *config;
+};
+
 #define lcdc_readl(sinfo, reg)		__raw_readl((sinfo)->mmio+(reg))
 #define lcdc_writel(sinfo, reg, val)	__raw_writel((val), (sinfo)->mmio+(reg))
 
@@ -34,12 +66,6 @@
 #define ATMEL_LCDC_DMA_BURST_LEN	8	/* words */
 #define ATMEL_LCDC_FIFO_SIZE		512	/* words */
 
-struct atmel_lcdfb_config {
-	bool have_alt_pixclock;
-	bool have_hozval;
-	bool have_intensity_bit;
-};
-
 static struct atmel_lcdfb_config at91sam9261_config = {
 	.have_hozval		= true,
 	.have_intensity_bit	= true,
@@ -248,15 +274,17 @@ static void exit_backlight(struct atmel_lcdfb_info *sinfo)
 
 static void init_contrast(struct atmel_lcdfb_info *sinfo)
 {
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
+
 	/* contrast pwm can be 'inverted' */
-	if (sinfo->lcdcon_pol_negative)
+	if (pdata->lcdcon_pol_negative)
 			contrast_ctr &= ~(ATMEL_LCDC_POL_POSITIVE);
 
 	/* have some default contrast/backlight settings */
 	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, contrast_ctr);
 	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_VAL, ATMEL_LCDC_CVAL_DEFAULT);
 
-	if (sinfo->lcdcon_is_backlight)
+	if (pdata->lcdcon_is_backlight)
 		init_backlight(sinfo);
 }
 
@@ -299,9 +327,11 @@ static unsigned long compute_hozval(struct atmel_lcdfb_info *sinfo,
 
 static void atmel_lcdfb_stop_nowait(struct atmel_lcdfb_info *sinfo)
 {
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
+
 	/* Turn off the LCD controller and the DMA controller */
 	lcdc_writel(sinfo, ATMEL_LCDC_PWRCON,
-			sinfo->guard_time << ATMEL_LCDC_GUARDT_OFFSET);
+			pdata->guard_time << ATMEL_LCDC_GUARDT_OFFSET);
 
 	/* Wait for the LCDC core to become idle */
 	while (lcdc_readl(sinfo, ATMEL_LCDC_PWRCON) & ATMEL_LCDC_BUSY)
@@ -321,9 +351,11 @@ static void atmel_lcdfb_stop(struct atmel_lcdfb_info *sinfo)
 
 static void atmel_lcdfb_start(struct atmel_lcdfb_info *sinfo)
 {
-	lcdc_writel(sinfo, ATMEL_LCDC_DMACON, sinfo->default_dmacon);
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
+
+	lcdc_writel(sinfo, ATMEL_LCDC_DMACON, pdata->default_dmacon);
 	lcdc_writel(sinfo, ATMEL_LCDC_PWRCON,
-		(sinfo->guard_time << ATMEL_LCDC_GUARDT_OFFSET)
+		(pdata->guard_time << ATMEL_LCDC_GUARDT_OFFSET)
 		| ATMEL_LCDC_PWR);
 }
 
@@ -424,6 +456,7 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
 {
 	struct device *dev = info->device;
 	struct atmel_lcdfb_info *sinfo = info->par;
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 	unsigned long clk_value_khz;
 
 	clk_value_khz = clk_get_rate(sinfo->lcdc_clk) / 1000;
@@ -510,7 +543,7 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
 		else
 			var->green.length = 6;
 
-		if (sinfo->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
+		if (pdata->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
 			/* RGB:5X5 mode */
 			var->red.offset = var->green.length + 5;
 			var->blue.offset = 0;
@@ -527,7 +560,7 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
 		var->transp.length = 8;
 		/* fall through */
 	case 24:
-		if (sinfo->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
+		if (pdata->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
 			/* RGB:888 mode */
 			var->red.offset = 16;
 			var->blue.offset = 0;
@@ -576,6 +609,7 @@ static void atmel_lcdfb_reset(struct atmel_lcdfb_info *sinfo)
 static int atmel_lcdfb_set_par(struct fb_info *info)
 {
 	struct atmel_lcdfb_info *sinfo = info->par;
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 	unsigned long hozval_linesz;
 	unsigned long value;
 	unsigned long clk_value_khz;
@@ -637,7 +671,7 @@ static int atmel_lcdfb_set_par(struct fb_info *info)
 
 
 	/* Initialize control register 2 */
-	value = sinfo->default_lcdcon2;
+	value = pdata->default_lcdcon2;
 
 	if (!(info->var.sync & FB_SYNC_HOR_HIGH_ACT))
 		value |= ATMEL_LCDC_INVLINE_INVERTED;
@@ -741,6 +775,7 @@ static int atmel_lcdfb_setcolreg(unsigned int regno, unsigned int red,
 			     unsigned int transp, struct fb_info *info)
 {
 	struct atmel_lcdfb_info *sinfo = info->par;
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 	unsigned int val;
 	u32 *pal;
 	int ret = 1;
@@ -777,8 +812,7 @@ static int atmel_lcdfb_setcolreg(unsigned int regno, unsigned int red,
 				 */
 			} else {
 				/* new style BGR:565 / RGB:565 */
-				if (sinfo->lcd_wiring_mode ==
-				    ATMEL_LCDC_WIRING_RGB) {
+				if (pdata->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
 					val  = ((blue >> 11) & 0x001f);
 					val |= ((red  >>  0) & 0xf800);
 				} else {
@@ -918,7 +952,7 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct fb_info *info;
 	struct atmel_lcdfb_info *sinfo;
-	struct atmel_lcdfb_info *pdata_sinfo;
+	struct atmel_lcdfb_pdata *pdata;
 	struct fb_videomode fbmode;
 	struct resource *regs = NULL;
 	struct resource *map = NULL;
@@ -936,17 +970,8 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	sinfo = info->par;
 
 	if (dev_get_platdata(dev)) {
-		pdata_sinfo = dev_get_platdata(dev);
-		sinfo->default_bpp = pdata_sinfo->default_bpp;
-		sinfo->default_dmacon = pdata_sinfo->default_dmacon;
-		sinfo->default_lcdcon2 = pdata_sinfo->default_lcdcon2;
-		sinfo->default_monspecs = pdata_sinfo->default_monspecs;
-		sinfo->atmel_lcdfb_power_control = pdata_sinfo->atmel_lcdfb_power_control;
-		sinfo->guard_time = pdata_sinfo->guard_time;
-		sinfo->smem_len = pdata_sinfo->smem_len;
-		sinfo->lcdcon_is_backlight = pdata_sinfo->lcdcon_is_backlight;
-		sinfo->lcdcon_pol_negative = pdata_sinfo->lcdcon_pol_negative;
-		sinfo->lcd_wiring_mode = pdata_sinfo->lcd_wiring_mode;
+		pdata = dev_get_platdata(dev);
+		sinfo->pdata = *pdata;
 	} else {
 		dev_err(dev, "cannot get default configuration\n");
 		goto free_info;
@@ -962,7 +987,7 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	info->pseudo_palette = sinfo->pseudo_palette;
 	info->fbops = &atmel_lcdfb_ops;
 
-	memcpy(&info->monspecs, sinfo->default_monspecs, sizeof(info->monspecs));
+	memcpy(&info->monspecs, pdata->default_monspecs, sizeof(info->monspecs));
 	info->fix = atmel_lcdfb_fix;
 
 	/* Enable LCDC Clocks */
@@ -980,7 +1005,7 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 
 	ret = fb_find_mode(&info->var, info, NULL, info->monspecs.modedb,
 			info->monspecs.modedb_len, info->monspecs.modedb,
-			sinfo->default_bpp);
+			pdata->default_bpp);
 	if (!ret) {
 		dev_err(dev, "no suitable video mode found\n");
 		goto stop_clk;
@@ -1097,8 +1122,8 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	fb_add_videomode(&fbmode, &info->modelist);
 
 	/* Power up the LCDC screen */
-	if (sinfo->atmel_lcdfb_power_control)
-		sinfo->atmel_lcdfb_power_control(1);
+	if (pdata->atmel_lcdfb_power_control)
+		pdata->atmel_lcdfb_power_control(1);
 
 	dev_info(dev, "fb%d: Atmel LCDC at 0x%08lx (mapped at %p), irq %d\n",
 		       info->node, info->fix.mmio_start, sinfo->mmio, sinfo->irq_base);
@@ -1141,15 +1166,17 @@ static int __exit atmel_lcdfb_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct fb_info *info = dev_get_drvdata(dev);
 	struct atmel_lcdfb_info *sinfo;
+	struct atmel_lcdfb_pdata *pdata;
 
 	if (!info || !info->par)
 		return 0;
 	sinfo = info->par;
+	pdata = &sinfo->pdata;
 
 	cancel_work_sync(&sinfo->task);
 	exit_backlight(sinfo);
-	if (sinfo->atmel_lcdfb_power_control)
-		sinfo->atmel_lcdfb_power_control(0);
+	if (pdata->atmel_lcdfb_power_control)
+		pdata->atmel_lcdfb_power_control(0);
 	unregister_framebuffer(info);
 	atmel_lcdfb_stop_clock(sinfo);
 	clk_put(sinfo->lcdc_clk);
@@ -1176,6 +1203,7 @@ static int atmel_lcdfb_suspend(struct platform_device *pdev, pm_message_t mesg)
 {
 	struct fb_info *info = platform_get_drvdata(pdev);
 	struct atmel_lcdfb_info *sinfo = info->par;
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 
 	/*
 	 * We don't want to handle interrupts while the clock is
@@ -1185,8 +1213,8 @@ static int atmel_lcdfb_suspend(struct platform_device *pdev, pm_message_t mesg)
 
 	sinfo->saved_lcdcon = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_CTR);
 	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, 0);
-	if (sinfo->atmel_lcdfb_power_control)
-		sinfo->atmel_lcdfb_power_control(0);
+	if (pdata->atmel_lcdfb_power_control)
+		pdata->atmel_lcdfb_power_control(0);
 
 	atmel_lcdfb_stop(sinfo);
 	atmel_lcdfb_stop_clock(sinfo);
@@ -1198,11 +1226,12 @@ static int atmel_lcdfb_resume(struct platform_device *pdev)
 {
 	struct fb_info *info = platform_get_drvdata(pdev);
 	struct atmel_lcdfb_info *sinfo = info->par;
+	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 
 	atmel_lcdfb_start_clock(sinfo);
 	atmel_lcdfb_start(sinfo);
-	if (sinfo->atmel_lcdfb_power_control)
-		sinfo->atmel_lcdfb_power_control(1);
+	if (pdata->atmel_lcdfb_power_control)
+		pdata->atmel_lcdfb_power_control(1);
 	lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, sinfo->saved_lcdcon);
 
 	/* Enable FIFO & DMA errors */
diff --git a/include/video/atmel_lcdc.h b/include/video/atmel_lcdc.h
index 0f5a2fc69af9..f197c54712b0 100644
--- a/include/video/atmel_lcdc.h
+++ b/include/video/atmel_lcdc.h
@@ -31,39 +31,18 @@
 #define ATMEL_LCDC_WIRING_BGR	0
 #define ATMEL_LCDC_WIRING_RGB	1
 
-struct atmel_lcdfb_config;
 
  /* LCD Controller info data structure, stored in device platform_data */
-struct atmel_lcdfb_info {
-	spinlock_t		lock;
-	struct fb_info		*info;
-	void __iomem		*mmio;
-	int			irq_base;
-	struct work_struct	task;
-
+struct atmel_lcdfb_pdata {
 	unsigned int		guard_time;
-	unsigned int 		smem_len;
-	struct platform_device	*pdev;
-	struct clk		*bus_clk;
-	struct clk		*lcdc_clk;
-
-#ifdef CONFIG_BACKLIGHT_ATMEL_LCDC
-	struct backlight_device	*backlight;
-	u8			bl_power;
-#endif
 	bool			lcdcon_is_backlight;
 	bool			lcdcon_pol_negative;
-	u8			saved_lcdcon;
-
 	u8			default_bpp;
 	u8			lcd_wiring_mode;
 	unsigned int		default_lcdcon2;
 	unsigned int		default_dmacon;
 	void (*atmel_lcdfb_power_control)(int on);
 	struct fb_monspecs	*default_monspecs;
-	u32			pseudo_palette[16];
-
-	struct atmel_lcdfb_config *config;
 };
 
 #define ATMEL_LCDC_DMABADDR1	0x00
-- 
cgit 


From ce3b64f5f1ba9126c7f97115c15abe9c322d24e1 Mon Sep 17 00:00:00 2001
From: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Date: Fri, 29 Mar 2013 02:05:47 +0800
Subject: video: atmel_lcdfb: pass the pdata as params

so we can use have list gpio as example (probe via DT)

Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 arch/arm/mach-at91/board-sam9261ek.c   | 4 ++--
 arch/arm/mach-at91/board-sam9263ek.c   | 2 +-
 arch/arm/mach-at91/board-sam9rlek.c    | 2 +-
 arch/avr32/boards/atngw100/evklcd10x.c | 2 +-
 drivers/video/atmel_lcdfb.c            | 2 +-
 include/video/atmel_lcdc.h             | 4 +++-
 6 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index 4ab1ba7557e4..473546b9408b 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -389,7 +389,7 @@ static struct fb_monspecs at91fb_default_stn_monspecs = {
 					| ATMEL_LCDC_IFWIDTH_4 \
 					| ATMEL_LCDC_SCANMOD_SINGLE)
 
-static void at91_lcdc_stn_power_control(int on)
+static void at91_lcdc_stn_power_control(struct atmel_lcdfb_pdata *pdata, int on)
 {
 	/* backlight */
 	if (on) {	/* power up */
@@ -445,7 +445,7 @@ static struct fb_monspecs at91fb_default_tft_monspecs = {
 					| ATMEL_LCDC_DISTYPE_TFT    \
 					| ATMEL_LCDC_CLKMOD_ALWAYSACTIVE)
 
-static void at91_lcdc_tft_power_control(int on)
+static void at91_lcdc_tft_power_control(struct atmel_lcdfb_pdata *pdata, int on)
 {
 	if (on)
 		at91_set_gpio_value(AT91_PIN_PA12, 0);	/* power up */
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 0fdae3f1541d..8b4942cbb6d9 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -275,7 +275,7 @@ static struct fb_monspecs at91fb_default_monspecs = {
 					| ATMEL_LCDC_DISTYPE_TFT \
 					| ATMEL_LCDC_CLKMOD_ALWAYSACTIVE)
 
-static void at91_lcdc_power_control(int on)
+static void at91_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on)
 {
 	at91_set_gpio_value(AT91_PIN_PA30, on);
 }
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index b77d7a9febd8..604eecf6cd70 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -170,7 +170,7 @@ static struct fb_monspecs at91fb_default_monspecs = {
 					| ATMEL_LCDC_DISTYPE_TFT \
 					| ATMEL_LCDC_CLKMOD_ALWAYSACTIVE)
 
-static void at91_lcdc_power_control(int on)
+static void at91_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on)
 {
 	if (on)
 		at91_set_gpio_value(AT91_PIN_PC1, 0);	/* power up */
diff --git a/arch/avr32/boards/atngw100/evklcd10x.c b/arch/avr32/boards/atngw100/evklcd10x.c
index dc4280413e9d..64919b0da7aa 100644
--- a/arch/avr32/boards/atngw100/evklcd10x.c
+++ b/arch/avr32/boards/atngw100/evklcd10x.c
@@ -145,7 +145,7 @@ static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
 };
 #endif
 
-static void atevklcd10x_lcdc_power_control(int on)
+static void atevklcd10x_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on)
 {
 	gpio_set_value(GPIO_PIN_PB(15), on);
 }
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 3c7609c1c6fe..790a501538b0 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -293,7 +293,7 @@ static inline void atmel_lcdfb_power_control(struct atmel_lcdfb_info *sinfo, int
 	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 
 	if (pdata->atmel_lcdfb_power_control)
-		pdata->atmel_lcdfb_power_control(on);
+		pdata->atmel_lcdfb_power_control(pdata, on);
 }
 
 static struct fb_fix_screeninfo atmel_lcdfb_fix __initdata = {
diff --git a/include/video/atmel_lcdc.h b/include/video/atmel_lcdc.h
index f197c54712b0..c79f38131926 100644
--- a/include/video/atmel_lcdc.h
+++ b/include/video/atmel_lcdc.h
@@ -41,8 +41,10 @@ struct atmel_lcdfb_pdata {
 	u8			lcd_wiring_mode;
 	unsigned int		default_lcdcon2;
 	unsigned int		default_dmacon;
-	void (*atmel_lcdfb_power_control)(int on);
+	void (*atmel_lcdfb_power_control)(struct atmel_lcdfb_pdata *pdata, int on);
 	struct fb_monspecs	*default_monspecs;
+
+	struct list_head	pwr_gpios;
 };
 
 #define ATMEL_LCDC_DMABADDR1	0x00
-- 
cgit 


From 77966ad7b68112b1a536f994d78d88a9eaca25bc Mon Sep 17 00:00:00 2001
From: Boris BREZILLON <b.brezillon@overkiz.com>
Date: Fri, 13 Sep 2013 09:45:33 +0200
Subject: pinctrl: at91: fix typos

Fix AT91_PINCTRL_DEBOUNCE_VAL dt macro typo.
Fix at91_pinctrl_mux_ops callback typos.

Signed-off-by: Boris BREZILLON <b.brezillon@overkiz.com>
Acked-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-at91.c     | 6 +++---
 include/dt-bindings/pinctrl/at91.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index f350fd2e170e..fae1b4d1d692 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -144,11 +144,11 @@ struct at91_pinctrl_mux_ops {
 	void (*mux_C_periph)(void __iomem *pio, unsigned mask);
 	void (*mux_D_periph)(void __iomem *pio, unsigned mask);
 	bool (*get_deglitch)(void __iomem *pio, unsigned pin);
-	void (*set_deglitch)(void __iomem *pio, unsigned mask, bool in_on);
+	void (*set_deglitch)(void __iomem *pio, unsigned mask, bool is_on);
 	bool (*get_debounce)(void __iomem *pio, unsigned pin, u32 *div);
-	void (*set_debounce)(void __iomem *pio, unsigned mask, bool in_on, u32 div);
+	void (*set_debounce)(void __iomem *pio, unsigned mask, bool is_on, u32 div);
 	bool (*get_pulldown)(void __iomem *pio, unsigned pin);
-	void (*set_pulldown)(void __iomem *pio, unsigned mask, bool in_on);
+	void (*set_pulldown)(void __iomem *pio, unsigned mask, bool is_on);
 	bool (*get_schmitt_trig)(void __iomem *pio, unsigned pin);
 	void (*disable_schmitt_trig)(void __iomem *pio, unsigned mask);
 	/* irq */
diff --git a/include/dt-bindings/pinctrl/at91.h b/include/dt-bindings/pinctrl/at91.h
index d7988b4d8af9..0fee6ff77ffc 100644
--- a/include/dt-bindings/pinctrl/at91.h
+++ b/include/dt-bindings/pinctrl/at91.h
@@ -16,7 +16,7 @@
 #define AT91_PINCTRL_PULL_DOWN		(1 << 3)
 #define AT91_PINCTRL_DIS_SCHMIT		(1 << 4)
 #define AT91_PINCTRL_DEBOUNCE		(1 << 16)
-#define AT91_PINCTRL_DEBOUNCE_VA(x)	(x << 17)
+#define AT91_PINCTRL_DEBOUNCE_VAL(x)	(x << 17)
 
 #define AT91_PINCTRL_PULL_UP_DEGLITCH	(AT91_PINCTRL_PULL_UP | AT91_PINCTRL_DEGLITCH)
 
-- 
cgit 


From 8fb883f3e30065529e4f35d4b4f355193dcdb7a2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 21 Sep 2013 00:09:31 +0100
Subject: FS-Cache: Add use/unuse/wake cookie wrappers

Add wrapper functions for dealing with cookie->n_active:

 (*) __fscache_use_cookie() to increment it.

 (*) __fscache_unuse_cookie() to decrement and test against zero.

 (*) __fscache_wake_unused_cookie() to wake up anyone waiting for it to reach
     zero.

The second and third are split so that the third can be done after cookie->lock
has been released in case the waiter wakes up whilst we're still holding it and
tries to get it.

We will need to wake-on-zero once the cookie disablement patch is applied
because it will then be possible to see n_active become zero without the cookie
being relinquished.

Also move the cookie usement out of fscache_attr_changed_op() and into
fscache_attr_changed() and the operation struct so that cookie disablement
will be able to track it.

Whilst we're at it, only increment n_active if we're about to do
fscache_submit_op() so that we don't have to deal with undoing it if anything
earlier fails.  Possibly this should be moved into fscache_submit_op() which
could look at FSCACHE_OP_UNUSE_COOKIE.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/fscache/cookie.c           |  7 +++++--
 fs/fscache/page.c             | 42 +++++++++++++++++++++++++++++++-----------
 include/linux/fscache-cache.h | 19 +++++++++++++++++--
 3 files changed, 53 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index b2a86e324aac..d851aa555d28 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -568,6 +568,7 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 {
 	struct fscache_operation *op;
 	struct fscache_object *object;
+	bool wake_cookie = false;
 	int ret;
 
 	_enter("%p,", cookie);
@@ -600,7 +601,7 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 
 	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
 
-	atomic_inc(&cookie->n_active);
+	__fscache_use_cookie(cookie);
 	if (fscache_submit_op(object, op) < 0)
 		goto submit_failed;
 
@@ -622,9 +623,11 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 	return ret;
 
 submit_failed:
-	atomic_dec(&cookie->n_active);
+	wake_cookie = __fscache_unuse_cookie(cookie);
 inconsistent:
 	spin_unlock(&cookie->lock);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 	kfree(op);
 	_leave(" = -ESTALE");
 	return -ESTALE;
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 73899c1c3449..0fe42a6d0e9c 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -163,12 +163,10 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
 
 	fscache_stat(&fscache_n_attr_changed_calls);
 
-	if (fscache_object_is_active(object) &&
-	    fscache_use_cookie(object)) {
+	if (fscache_object_is_active(object)) {
 		fscache_stat(&fscache_n_cop_attr_changed);
 		ret = object->cache->ops->attr_changed(object);
 		fscache_stat_d(&fscache_n_cop_attr_changed);
-		fscache_unuse_cookie(object);
 		if (ret < 0)
 			fscache_abort_object(object);
 	}
@@ -184,6 +182,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 {
 	struct fscache_operation *op;
 	struct fscache_object *object;
+	bool wake_cookie;
 
 	_enter("%p", cookie);
 
@@ -199,7 +198,9 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 	}
 
 	fscache_operation_init(op, fscache_attr_changed_op, NULL);
-	op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
+	op->flags = FSCACHE_OP_ASYNC |
+		(1 << FSCACHE_OP_EXCLUSIVE) |
+		(1 << FSCACHE_OP_UNUSE_COOKIE);
 
 	spin_lock(&cookie->lock);
 
@@ -208,6 +209,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
 
+	__fscache_use_cookie(cookie);
 	if (fscache_submit_exclusive_op(object, op) < 0)
 		goto nobufs;
 	spin_unlock(&cookie->lock);
@@ -217,8 +219,11 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 	return 0;
 
 nobufs:
+	wake_cookie = __fscache_unuse_cookie(cookie);
 	spin_unlock(&cookie->lock);
 	kfree(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_attr_changed_nobufs);
 	_leave(" = %d", -ENOBUFS);
 	return -ENOBUFS;
@@ -263,7 +268,6 @@ static struct fscache_retrieval *fscache_alloc_retrieval(
 	}
 
 	fscache_operation_init(&op->op, NULL, fscache_release_retrieval_op);
-	atomic_inc(&cookie->n_active);
 	op->op.flags	= FSCACHE_OP_MYTHREAD |
 		(1UL << FSCACHE_OP_WAITING) |
 		(1UL << FSCACHE_OP_UNUSE_COOKIE);
@@ -384,6 +388,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 {
 	struct fscache_retrieval *op;
 	struct fscache_object *object;
+	bool wake_cookie = false;
 	int ret;
 
 	_enter("%p,%p,,,", cookie, page);
@@ -421,6 +426,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	ASSERT(test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags));
 
+	__fscache_use_cookie(cookie);
 	atomic_inc(&object->n_reads);
 	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
@@ -475,9 +481,11 @@ error:
 
 nobufs_unlock_dec:
 	atomic_dec(&object->n_reads);
+	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	atomic_dec(&cookie->n_active);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 	kfree(op);
 nobufs:
 	fscache_stat(&fscache_n_retrievals_nobufs);
@@ -514,6 +522,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 {
 	struct fscache_retrieval *op;
 	struct fscache_object *object;
+	bool wake_cookie = false;
 	int ret;
 
 	_enter("%p,,%d,,,", cookie, *nr_pages);
@@ -547,6 +556,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
 
+	__fscache_use_cookie(cookie);
 	atomic_inc(&object->n_reads);
 	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
@@ -601,10 +611,12 @@ error:
 
 nobufs_unlock_dec:
 	atomic_dec(&object->n_reads);
+	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	atomic_dec(&cookie->n_active);
 	kfree(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 nobufs:
 	fscache_stat(&fscache_n_retrievals_nobufs);
 	_leave(" = -ENOBUFS");
@@ -626,6 +638,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 {
 	struct fscache_retrieval *op;
 	struct fscache_object *object;
+	bool wake_cookie = false;
 	int ret;
 
 	_enter("%p,%p,,,", cookie, page);
@@ -658,8 +671,9 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
 
+	__fscache_use_cookie(cookie);
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_alloc_ops);
@@ -689,10 +703,13 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	atomic_dec(&cookie->n_active);
 	kfree(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 nobufs:
 	fscache_stat(&fscache_n_allocs_nobufs);
 	_leave(" = -ENOBUFS");
@@ -889,6 +906,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 {
 	struct fscache_storage *op;
 	struct fscache_object *object;
+	bool wake_cookie = false;
 	int ret;
 
 	_enter("%p,%x,", cookie, (u32) page->flags);
@@ -957,7 +975,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	op->op.debug_id	= atomic_inc_return(&fscache_op_debug_id);
 	op->store_limit = object->store_limit;
 
-	atomic_inc(&cookie->n_active);
+	__fscache_use_cookie(cookie);
 	if (fscache_submit_op(object, &op->op) < 0)
 		goto submit_failed;
 
@@ -984,10 +1002,10 @@ already_pending:
 	return 0;
 
 submit_failed:
-	atomic_dec(&cookie->n_active);
 	spin_lock(&cookie->stores_lock);
 	radix_tree_delete(&cookie->stores, page->index);
 	spin_unlock(&cookie->stores_lock);
+	wake_cookie = __fscache_unuse_cookie(cookie);
 	page_cache_release(page);
 	ret = -ENOBUFS;
 	goto nobufs;
@@ -999,6 +1017,8 @@ nobufs:
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
 	kfree(op);
+	if (wake_cookie)
+		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_stores_nobufs);
 	_leave(" = -ENOBUFS");
 	return -ENOBUFS;
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 7823e9ef995e..96a2b66f5968 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -511,6 +511,11 @@ static inline void fscache_end_io(struct fscache_retrieval *op,
 	op->end_io_func(page, op->context, error);
 }
 
+static inline void __fscache_use_cookie(struct fscache_cookie *cookie)
+{
+	atomic_inc(&cookie->n_active);
+}
+
 /**
  * fscache_use_cookie - Request usage of cookie attached to an object
  * @object: Object description
@@ -524,6 +529,16 @@ static inline bool fscache_use_cookie(struct fscache_object *object)
 	return atomic_inc_not_zero(&cookie->n_active) != 0;
 }
 
+static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie)
+{
+	return atomic_dec_and_test(&cookie->n_active);
+}
+
+static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie)
+{
+	wake_up_atomic_t(&cookie->n_active);
+}
+
 /**
  * fscache_unuse_cookie - Cease usage of cookie attached to an object
  * @object: Object description
@@ -534,8 +549,8 @@ static inline bool fscache_use_cookie(struct fscache_object *object)
 static inline void fscache_unuse_cookie(struct fscache_object *object)
 {
 	struct fscache_cookie *cookie = object->cookie;
-	if (atomic_dec_and_test(&cookie->n_active))
-		wake_up_atomic_t(&cookie->n_active);
+	if (__fscache_unuse_cookie(cookie))
+		__fscache_wake_unused_cookie(cookie);
 }
 
 /*
-- 
cgit 


From 94d30ae90a00cafe686c1057be57f4885f963abf Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 21 Sep 2013 00:09:31 +0100
Subject: FS-Cache: Provide the ability to enable/disable cookies

Provide the ability to enable and disable fscache cookies.  A disabled cookie
will reject or ignore further requests to:

	Acquire a child cookie
	Invalidate and update backing objects
	Check the consistency of a backing object
	Allocate storage for backing page
	Read backing pages
	Write to backing pages

but still allows:

	Checks/waits on the completion of already in-progress objects
	Uncaching of pages
	Relinquishment of cookies

Two new operations are provided:

 (1) Disable a cookie:

	void fscache_disable_cookie(struct fscache_cookie *cookie,
				    bool invalidate);

     If the cookie is not already disabled, this locks the cookie against other
     dis/enablement ops, marks the cookie as being disabled, discards or
     invalidates any backing objects and waits for cessation of activity on any
     associated object.

     This is a wrapper around a chunk split out of fscache_relinquish_cookie(),
     but it reinitialises the cookie such that it can be reenabled.

     All possible failures are handled internally.  The caller should consider
     calling fscache_uncache_all_inode_pages() afterwards to make sure all page
     markings are cleared up.

 (2) Enable a cookie:

	void fscache_enable_cookie(struct fscache_cookie *cookie,
				   bool (*can_enable)(void *data),
				   void *data)

     If the cookie is not already enabled, this locks the cookie against other
     dis/enablement ops, invokes can_enable() and, if the cookie is not an
     index cookie, will begin the procedure of acquiring backing objects.

     The optional can_enable() function is passed the data argument and returns
     a ruling as to whether or not enablement should actually be permitted to
     begin.

     All possible failures are handled internally.  The cookie will only be
     marked as enabled if provisional backing objects are allocated.

A later patch will introduce these to NFS.  Cookie enablement during nfs_open()
is then contingent on i_writecount <= 0.  can_enable() checks for a race
between open(O_RDONLY) and open(O_WRONLY/O_RDWR).  This simplifies NFS's cookie
handling and allows us to get rid of open(O_RDONLY) accidentally introducing
caching to an inode that's open for writing already.

One operation has its API modified:

 (3) Acquire a cookie.

	struct fscache_cookie *fscache_acquire_cookie(
		struct fscache_cookie *parent,
		const struct fscache_cookie_def *def,
		void *netfs_data,
		bool enable);

     This now has an additional argument that indicates whether the requested
     cookie should be enabled by default.  It doesn't need the can_enable()
     function because the caller must prevent multiple calls for the same netfs
     object and it doesn't need to take the enablement lock because no one else
     can get at the cookie before this returns.

Signed-off-by: David Howells <dhowells@redhat.com
---
 Documentation/filesystems/caching/netfs-api.txt |  73 ++++++++--
 fs/9p/cache.c                                   |   6 +-
 fs/afs/cell.c                                   |   2 +-
 fs/afs/inode.c                                  |   2 +-
 fs/afs/vlocation.c                              |   3 +-
 fs/afs/volume.c                                 |   2 +-
 fs/cachefiles/interface.c                       |   2 +-
 fs/ceph/cache.c                                 |   4 +-
 fs/cifs/fscache.c                               |   8 +-
 fs/fscache/cookie.c                             | 186 +++++++++++++++++-------
 fs/fscache/fsdef.c                              |   1 +
 fs/fscache/netfs.c                              |   1 +
 fs/fscache/object.c                             |   7 +-
 fs/fscache/page.c                               |  17 ++-
 fs/nfs/fscache.c                                |   8 +-
 include/linux/fscache-cache.h                   |  31 +---
 include/linux/fscache.h                         | 113 ++++++++++++--
 17 files changed, 334 insertions(+), 132 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 11a0a40ce445..aed6b94160b1 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -29,15 +29,16 @@ This document contains the following sections:
 	 (6) Index registration
 	 (7) Data file registration
 	 (8) Miscellaneous object registration
-	 (9) Setting the data file size
+ 	 (9) Setting the data file size
 	(10) Page alloc/read/write
 	(11) Page uncaching
 	(12) Index and data file consistency
-	(13) Miscellaneous cookie operations
-	(14) Cookie unregistration
-	(15) Index invalidation
-	(16) Data file invalidation
-	(17) FS-Cache specific page flags.
+	(13) Cookie enablement
+	(14) Miscellaneous cookie operations
+	(15) Cookie unregistration
+	(16) Index invalidation
+	(17) Data file invalidation
+	(18) FS-Cache specific page flags.
 
 
 =============================
@@ -334,7 +335,8 @@ the path to the file:
 	struct fscache_cookie *
 	fscache_acquire_cookie(struct fscache_cookie *parent,
 			       const struct fscache_object_def *def,
-			       void *netfs_data);
+			       void *netfs_data,
+			       bool enable);
 
 This function creates an index entry in the index represented by parent,
 filling in the index entry by calling the operations pointed to by def.
@@ -350,6 +352,10 @@ object needs to be created somewhere down the hierarchy.  Furthermore, an index
 may be created in several different caches independently at different times.
 This is all handled transparently, and the netfs doesn't see any of it.
 
+A cookie will be created in the disabled state if enabled is false.  A cookie
+must be enabled to do anything with it.  A disabled cookie can be enabled by
+calling fscache_enable_cookie() (see below).
+
 For example, with AFS, a cell would be added to the primary index.  This index
 entry would have a dependent inode containing a volume location index for the
 volume mappings within this cell:
@@ -357,7 +363,7 @@ volume mappings within this cell:
 	cell->cache =
 		fscache_acquire_cookie(afs_cache_netfs.primary_index,
 				       &afs_cell_cache_index_def,
-				       cell);
+				       cell, true);
 
 Then when a volume location was accessed, it would be entered into the cell's
 index and an inode would be allocated that acts as a volume type and hash chain
@@ -366,7 +372,7 @@ combination:
 	vlocation->cache =
 		fscache_acquire_cookie(cell->cache,
 				       &afs_vlocation_cache_index_def,
-				       vlocation);
+				       vlocation, true);
 
 And then a particular flavour of volume (R/O for example) could be added to
 that index, creating another index for vnodes (AFS inode equivalents):
@@ -374,7 +380,7 @@ that index, creating another index for vnodes (AFS inode equivalents):
 	volume->cache =
 		fscache_acquire_cookie(vlocation->cache,
 				       &afs_volume_cache_index_def,
-				       volume);
+				       volume, true);
 
 
 ======================
@@ -388,7 +394,7 @@ the object definition should be something other than index type.
 	vnode->cache =
 		fscache_acquire_cookie(volume->cache,
 				       &afs_vnode_cache_object_def,
-				       vnode);
+				       vnode, true);
 
 
 =================================
@@ -404,7 +410,7 @@ it would be some other type of object such as a data file.
 	xattr->cache =
 		fscache_acquire_cookie(vnode->cache,
 				       &afs_xattr_cache_object_def,
-				       xattr);
+				       xattr, true);
 
 Miscellaneous objects might be used to store extended attributes or directory
 entries for example.
@@ -733,6 +739,47 @@ Note that partial updates may happen automatically at other times, such as when
 data blocks are added to a data file object.
 
 
+=================
+COOKIE ENABLEMENT
+=================
+
+Cookies exist in one of two states: enabled and disabled.  If a cookie is
+disabled, it ignores all attempts to acquire child cookies; check, update or
+invalidate its state; allocate, read or write backing pages - though it is
+still possible to uncache pages and relinquish the cookie.
+
+The initial enablement state is set by fscache_acquire_cookie(), but the cookie
+can be enabled or disabled later.  To disable a cookie, call:
+    
+	void fscache_disable_cookie(struct fscache_cookie *cookie,
+    				    bool invalidate);
+    
+If the cookie is not already disabled, this locks the cookie against other
+enable and disable ops, marks the cookie as being disabled, discards or
+invalidates any backing objects and waits for cessation of activity on any
+associated object before unlocking the cookie.
+
+All possible failures are handled internally.  The caller should consider
+calling fscache_uncache_all_inode_pages() afterwards to make sure all page
+markings are cleared up.
+    
+Cookies can be enabled or reenabled with:
+    
+    	void fscache_enable_cookie(struct fscache_cookie *cookie,
+    				   bool (*can_enable)(void *data),
+    				   void *data)
+    
+If the cookie is not already enabled, this locks the cookie against other
+enable and disable ops, invokes can_enable() and, if the cookie is not an index
+cookie, will begin the procedure of acquiring backing objects.
+
+The optional can_enable() function is passed the data argument and returns a
+ruling as to whether or not enablement should actually be permitted to begin.
+
+All possible failures are handled internally.  The cookie will only be marked
+as enabled if provisional backing objects are allocated.
+
+
 ===============================
 MISCELLANEOUS COOKIE OPERATIONS
 ===============================
@@ -778,7 +825,7 @@ COOKIE UNREGISTRATION
 To get rid of a cookie, this function should be called.
 
 	void fscache_relinquish_cookie(struct fscache_cookie *cookie,
-				       int retire);
+				       bool retire);
 
 If retire is non-zero, then the object will be marked for recycling, and all
 copies of it will be removed from all active caches in which it is present.
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index a9ea73d6dcf3..2b7a032c37bc 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -90,7 +90,7 @@ void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses)
 
 	v9ses->fscache = fscache_acquire_cookie(v9fs_cache_netfs.primary_index,
 						&v9fs_cache_session_index_def,
-						v9ses);
+						v9ses, true);
 	p9_debug(P9_DEBUG_FSC, "session %p get cookie %p\n",
 		 v9ses, v9ses->fscache);
 }
@@ -204,7 +204,7 @@ void v9fs_cache_inode_get_cookie(struct inode *inode)
 	v9ses = v9fs_inode2v9ses(inode);
 	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
 						  &v9fs_cache_inode_index_def,
-						  v9inode);
+						  v9inode, true);
 
 	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
 		 inode, v9inode->fscache);
@@ -271,7 +271,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode)
 	v9ses = v9fs_inode2v9ses(inode);
 	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
 						  &v9fs_cache_inode_index_def,
-						  v9inode);
+						  v9inode, true);
 	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
 		 inode, old, v9inode->fscache);
 
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 3c090b7555ea..ca0a3cf93791 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -179,7 +179,7 @@ struct afs_cell *afs_cell_create(const char *name, unsigned namesz,
 	/* put it up for caching (this never returns an error) */
 	cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index,
 					     &afs_cell_cache_index_def,
-					     cell);
+					     cell, true);
 #endif
 
 	/* add to the cell lists */
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 789bc253b5f6..ce25d755b7aa 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -259,7 +259,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 #ifdef CONFIG_AFS_FSCACHE
 	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
 					      &afs_vnode_cache_index_def,
-					      vnode);
+					      vnode, true);
 #endif
 
 	ret = afs_inode_map_status(vnode, key);
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 57bcb1596530..b6df2e83809f 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -308,7 +308,8 @@ static int afs_vlocation_fill_in_record(struct afs_vlocation *vl,
 	/* see if we have an in-cache copy (will set vl->valid if there is) */
 #ifdef CONFIG_AFS_FSCACHE
 	vl->cache = fscache_acquire_cookie(vl->cell->cache,
-					   &afs_vlocation_cache_index_def, vl);
+					   &afs_vlocation_cache_index_def, vl,
+					   true);
 #endif
 
 	if (vl->valid) {
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 401eeb21869f..2b607257820c 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -131,7 +131,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 #ifdef CONFIG_AFS_FSCACHE
 	volume->cache = fscache_acquire_cookie(vlocation->cache,
 					       &afs_volume_cache_index_def,
-					       volume);
+					       volume, true);
 #endif
 	afs_get_vlocation(vlocation);
 	volume->vlocation = vlocation;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 43eb5592cdea..00baf1419989 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -270,7 +270,7 @@ static void cachefiles_drop_object(struct fscache_object *_object)
 #endif
 
 	/* delete retired objects */
-	if (test_bit(FSCACHE_COOKIE_RETIRED, &object->fscache.cookie->flags) &&
+	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->fscache.flags) &&
 	    _object != cache->cache.fsdef
 	    ) {
 		_debug("- retire object OBJ%x", object->fscache.debug_id);
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 6bfe65e0b038..7db2e6ca4b8f 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -68,7 +68,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
 {
 	fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
 					      &ceph_fscache_fsid_object_def,
-					      fsc);
+					      fsc, true);
 
 	if (fsc->fscache == NULL) {
 		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
@@ -204,7 +204,7 @@ void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
 
 	ci->fscache = fscache_acquire_cookie(fsc->fscache,
 					     &ceph_fscache_inode_object_def,
-					     ci);
+					     ci, true);
 done:
 	mutex_unlock(&inode->i_mutex);
 
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 2f4bc5a58054..fe2492d2a8fc 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -27,7 +27,7 @@ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server)
 {
 	server->fscache =
 		fscache_acquire_cookie(cifs_fscache_netfs.primary_index,
-				&cifs_fscache_server_index_def, server);
+				&cifs_fscache_server_index_def, server, true);
 	cifs_dbg(FYI, "%s: (0x%p/0x%p)\n",
 		 __func__, server, server->fscache);
 }
@@ -46,7 +46,7 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
 
 	tcon->fscache =
 		fscache_acquire_cookie(server->fscache,
-				&cifs_fscache_super_index_def, tcon);
+				&cifs_fscache_super_index_def, tcon, true);
 	cifs_dbg(FYI, "%s: (0x%p/0x%p)\n",
 		 __func__, server->fscache, tcon->fscache);
 }
@@ -69,7 +69,7 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode)
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) {
 		cifsi->fscache = fscache_acquire_cookie(tcon->fscache,
-				&cifs_fscache_inode_object_def, cifsi);
+				&cifs_fscache_inode_object_def, cifsi, true);
 		cifs_dbg(FYI, "%s: got FH cookie (0x%p/0x%p)\n",
 			 __func__, tcon->fscache, cifsi->fscache);
 	}
@@ -119,7 +119,7 @@ void cifs_fscache_reset_inode_cookie(struct inode *inode)
 		cifsi->fscache = fscache_acquire_cookie(
 					cifs_sb_master_tcon(cifs_sb)->fscache,
 					&cifs_fscache_inode_object_def,
-					cifsi);
+					cifsi, true);
 		cifs_dbg(FYI, "%s: new cookie 0x%p oldcookie 0x%p\n",
 			 __func__, cifsi->fscache, old);
 	}
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index d851aa555d28..29d7feb62cf7 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -58,15 +58,16 @@ void fscache_cookie_init_once(void *_cookie)
 struct fscache_cookie *__fscache_acquire_cookie(
 	struct fscache_cookie *parent,
 	const struct fscache_cookie_def *def,
-	void *netfs_data)
+	void *netfs_data,
+	bool enable)
 {
 	struct fscache_cookie *cookie;
 
 	BUG_ON(!def);
 
-	_enter("{%s},{%s},%p",
+	_enter("{%s},{%s},%p,%u",
 	       parent ? (char *) parent->def->name : "<no-parent>",
-	       def->name, netfs_data);
+	       def->name, netfs_data, enable);
 
 	fscache_stat(&fscache_n_acquires);
 
@@ -106,7 +107,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
 	cookie->def		= def;
 	cookie->parent		= parent;
 	cookie->netfs_data	= netfs_data;
-	cookie->flags		= 0;
+	cookie->flags		= (1 << FSCACHE_COOKIE_NO_DATA_YET);
 
 	/* radix tree insertion won't use the preallocation pool unless it's
 	 * told it may not wait */
@@ -124,16 +125,22 @@ struct fscache_cookie *__fscache_acquire_cookie(
 		break;
 	}
 
-	/* if the object is an index then we need do nothing more here - we
-	 * create indices on disk when we need them as an index may exist in
-	 * multiple caches */
-	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
-		if (fscache_acquire_non_index_cookie(cookie) < 0) {
-			atomic_dec(&parent->n_children);
-			__fscache_cookie_put(cookie);
-			fscache_stat(&fscache_n_acquires_nobufs);
-			_leave(" = NULL");
-			return NULL;
+	if (enable) {
+		/* if the object is an index then we need do nothing more here
+		 * - we create indices on disk when we need them as an index
+		 * may exist in multiple caches */
+		if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+			if (fscache_acquire_non_index_cookie(cookie) == 0) {
+				set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+			} else {
+				atomic_dec(&parent->n_children);
+				__fscache_cookie_put(cookie);
+				fscache_stat(&fscache_n_acquires_nobufs);
+				_leave(" = NULL");
+				return NULL;
+			}
+		} else {
+			set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
 		}
 	}
 
@@ -143,6 +150,39 @@ struct fscache_cookie *__fscache_acquire_cookie(
 }
 EXPORT_SYMBOL(__fscache_acquire_cookie);
 
+/*
+ * Enable a cookie to permit it to accept new operations.
+ */
+void __fscache_enable_cookie(struct fscache_cookie *cookie,
+			     bool (*can_enable)(void *data),
+			     void *data)
+{
+	_enter("%p", cookie);
+
+	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
+			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+
+	if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
+		goto out_unlock;
+
+	if (can_enable && !can_enable(data)) {
+		/* The netfs decided it didn't want to enable after all */
+	} else if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		/* Wait for outstanding disablement to complete */
+		__fscache_wait_on_invalidate(cookie);
+
+		if (fscache_acquire_non_index_cookie(cookie) == 0)
+			set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+	} else {
+		set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+	}
+
+out_unlock:
+	clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags);
+	wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK);
+}
+EXPORT_SYMBOL(__fscache_enable_cookie);
+
 /*
  * acquire a non-index cookie
  * - this must make sure the index chain is instantiated and instantiate the
@@ -157,7 +197,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
 
 	_enter("");
 
-	cookie->flags = 1 << FSCACHE_COOKIE_UNAVAILABLE;
+	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 
 	/* now we need to see whether the backing objects for this cookie yet
 	 * exist, if not there'll be nothing to search */
@@ -180,9 +220,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
 
 	_debug("cache %s", cache->tag->name);
 
-	cookie->flags =
-		(1 << FSCACHE_COOKIE_LOOKING_UP) |
-		(1 << FSCACHE_COOKIE_NO_DATA_YET);
+	set_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
 
 	/* ask the cache to allocate objects for this cookie and its parent
 	 * chain */
@@ -398,7 +436,8 @@ void __fscache_invalidate(struct fscache_cookie *cookie)
 	if (!hlist_empty(&cookie->backing_objects)) {
 		spin_lock(&cookie->lock);
 
-		if (!hlist_empty(&cookie->backing_objects) &&
+		if (fscache_cookie_enabled(cookie) &&
+		    !hlist_empty(&cookie->backing_objects) &&
 		    !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING,
 				      &cookie->flags)) {
 			object = hlist_entry(cookie->backing_objects.first,
@@ -452,10 +491,14 @@ void __fscache_update_cookie(struct fscache_cookie *cookie)
 
 	spin_lock(&cookie->lock);
 
-	/* update the index entry on disk in each cache backing this cookie */
-	hlist_for_each_entry(object,
-			     &cookie->backing_objects, cookie_link) {
-		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+	if (fscache_cookie_enabled(cookie)) {
+		/* update the index entry on disk in each cache backing this
+		 * cookie.
+		 */
+		hlist_for_each_entry(object,
+				     &cookie->backing_objects, cookie_link) {
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+		}
 	}
 
 	spin_unlock(&cookie->lock);
@@ -464,28 +507,14 @@ void __fscache_update_cookie(struct fscache_cookie *cookie)
 EXPORT_SYMBOL(__fscache_update_cookie);
 
 /*
- * release a cookie back to the cache
- * - the object will be marked as recyclable on disk if retire is true
- * - all dependents of this cookie must have already been unregistered
- *   (indices/files/pages)
+ * Disable a cookie to stop it from accepting new requests from the netfs.
  */
-void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 {
 	struct fscache_object *object;
+	bool awaken = false;
 
-	fscache_stat(&fscache_n_relinquishes);
-	if (retire)
-		fscache_stat(&fscache_n_relinquishes_retire);
-
-	if (!cookie) {
-		fscache_stat(&fscache_n_relinquishes_null);
-		_leave(" [no cookie]");
-		return;
-	}
-
-	_enter("%p{%s,%p,%d},%d",
-	       cookie, cookie->def->name, cookie->netfs_data,
-	       atomic_read(&cookie->n_active), retire);
+	_enter("%p,%u", cookie, invalidate);
 
 	ASSERTCMP(atomic_read(&cookie->n_active), >, 0);
 
@@ -495,24 +524,82 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 		BUG();
 	}
 
-	/* No further netfs-accessing operations on this cookie permitted */
-	set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags);
-	if (retire)
-		set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags);
+	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
+			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
+		goto out_unlock_enable;
+
+	/* If the cookie is being invalidated, wait for that to complete first
+	 * so that we can reuse the flag.
+	 */
+	__fscache_wait_on_invalidate(cookie);
+
+	/* Dispose of the backing objects */
+	set_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags);
 
 	spin_lock(&cookie->lock);
-	hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
-		fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
+	if (!hlist_empty(&cookie->backing_objects)) {
+		hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
+			if (invalidate)
+				set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
+		}
+	} else {
+		if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+			awaken = true;
 	}
 	spin_unlock(&cookie->lock);
+	if (awaken)
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
 
 	/* Wait for cessation of activity requiring access to the netfs (when
-	 * n_active reaches 0).
+	 * n_active reaches 0).  This makes sure outstanding reads and writes
+	 * have completed.
 	 */
 	if (!atomic_dec_and_test(&cookie->n_active))
 		wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
 				 TASK_UNINTERRUPTIBLE);
 
+	/* Reset the cookie state if it wasn't relinquished */
+	if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
+		atomic_inc(&cookie->n_active);
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+	}
+
+out_unlock_enable:
+	clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags);
+	wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_disable_cookie);
+
+/*
+ * release a cookie back to the cache
+ * - the object will be marked as recyclable on disk if retire is true
+ * - all dependents of this cookie must have already been unregistered
+ *   (indices/files/pages)
+ */
+void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire)
+{
+	fscache_stat(&fscache_n_relinquishes);
+	if (retire)
+		fscache_stat(&fscache_n_relinquishes_retire);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_relinquishes_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("%p{%s,%p,%d},%d",
+	       cookie, cookie->def->name, cookie->netfs_data,
+	       atomic_read(&cookie->n_active), retire);
+
+	/* No further netfs-accessing operations on this cookie permitted */
+	set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags);
+
+	__fscache_disable_cookie(cookie, retire);
+
 	/* Clear pointers back to the netfs */
 	cookie->netfs_data	= NULL;
 	cookie->def		= NULL;
@@ -592,7 +679,8 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto inconsistent;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c
index 10a2ade0bdf8..5a117df2a9ef 100644
--- a/fs/fscache/fsdef.c
+++ b/fs/fscache/fsdef.c
@@ -59,6 +59,7 @@ struct fscache_cookie fscache_fsdef_index = {
 	.lock		= __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock),
 	.backing_objects = HLIST_HEAD_INIT,
 	.def		= &fscache_fsdef_index_def,
+	.flags		= 1 << FSCACHE_COOKIE_ENABLED,
 };
 EXPORT_SYMBOL(fscache_fsdef_index);
 
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index b1bb6117473a..989f39401547 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -45,6 +45,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 	netfs->primary_index->def		= &fscache_fsdef_netfs_def;
 	netfs->primary_index->parent		= &fscache_fsdef_index;
 	netfs->primary_index->netfs_data	= netfs;
+	netfs->primary_index->flags		= 1 << FSCACHE_COOKIE_ENABLED;
 
 	atomic_inc(&netfs->primary_index->parent->usage);
 	atomic_inc(&netfs->primary_index->parent->n_children);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 86d75a60b20c..dcb821617774 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -495,6 +495,7 @@ void fscache_object_lookup_negative(struct fscache_object *object)
 		 * returning ENODATA.
 		 */
 		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+		clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 
 		_debug("wake up lookup %p", &cookie->flags);
 		clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
@@ -527,6 +528,7 @@ void fscache_obtained_object(struct fscache_object *object)
 
 		/* We do (presumably) have data */
 		clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+		clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 
 		/* Allow write requests to begin stacking up and read requests
 		 * to begin shovelling data.
@@ -679,7 +681,8 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob
 	 */
 	spin_lock(&cookie->lock);
 	hlist_del_init(&object->cookie_link);
-	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+	if (hlist_empty(&cookie->backing_objects) &&
+	    test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
 		awaken = true;
 	spin_unlock(&cookie->lock);
 
@@ -927,7 +930,7 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj
 	 */
 	if (!fscache_use_cookie(object)) {
 		ASSERT(object->cookie->stores.rnode == NULL);
-		set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags);
+		set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
 		_leave(" [no cookie]");
 		return transit_to(KILL_OBJECT);
 	}
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 0fe42a6d0e9c..7f5c658af755 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -204,7 +204,8 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
@@ -410,7 +411,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 		return -ERESTARTSYS;
 
 	op = fscache_alloc_retrieval(cookie, page->mapping,
-				     end_io_func,context);
+				     end_io_func, context);
 	if (!op) {
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
@@ -419,7 +420,8 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto nobufs_unlock;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
@@ -551,7 +553,8 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto nobufs_unlock;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
@@ -666,7 +669,8 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto nobufs_unlock;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
@@ -938,7 +942,8 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	ret = -ENOBUFS;
 	spin_lock(&cookie->lock);
 
-	if (hlist_empty(&cookie->backing_objects))
+	if (!fscache_cookie_enabled(cookie) ||
+	    hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 	object = hlist_entry(cookie->backing_objects.first,
 			     struct fscache_object, cookie_link);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 24d1d1c5fcaf..cd6e7efd4305 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -39,7 +39,7 @@ void nfs_fscache_get_client_cookie(struct nfs_client *clp)
 	/* create a cache index for looking up filehandles */
 	clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
 					      &nfs_fscache_server_index_def,
-					      clp);
+					      clp, true);
 	dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
 		 clp, clp->fscache);
 }
@@ -139,7 +139,7 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
 	/* create a cache index for looking up filehandles */
 	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
 					       &nfs_fscache_super_index_def,
-					       nfss);
+					       nfss, true);
 	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
 		 nfss, nfss->fscache);
 	return;
@@ -200,7 +200,7 @@ static void nfs_fscache_enable_inode_cookie(struct inode *inode)
 		nfsi->fscache = fscache_acquire_cookie(
 			NFS_SB(sb)->fscache,
 			&nfs_fscache_inode_object_def,
-			nfsi);
+			nfsi, true);
 
 		dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
 			 sb, nfsi, nfsi->fscache);
@@ -327,7 +327,7 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
 		nfsi->fscache = fscache_acquire_cookie(
 			nfss->nfs_client->fscache,
 			&nfs_fscache_inode_object_def,
-			nfsi);
+			nfsi, true);
 
 		dfprintk(FSCACHE,
 			 "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 96a2b66f5968..771484993ca7 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -308,36 +308,6 @@ struct fscache_cache_ops {
 	void (*dissociate_pages)(struct fscache_cache *cache);
 };
 
-/*
- * data file or index object cookie
- * - a file will only appear in one cache
- * - a request to cache a file may or may not be honoured, subject to
- *   constraints such as disk space
- * - indices are created on disk just-in-time
- */
-struct fscache_cookie {
-	atomic_t			usage;		/* number of users of this cookie */
-	atomic_t			n_children;	/* number of children of this cookie */
-	atomic_t			n_active;	/* number of active users of netfs ptrs */
-	spinlock_t			lock;
-	spinlock_t			stores_lock;	/* lock on page store tree */
-	struct hlist_head		backing_objects; /* object(s) backing this file/index */
-	const struct fscache_cookie_def	*def;		/* definition */
-	struct fscache_cookie		*parent;	/* parent of this entry */
-	void				*netfs_data;	/* back pointer to netfs */
-	struct radix_tree_root		stores;		/* pages to be stored on this cookie */
-#define FSCACHE_COOKIE_PENDING_TAG	0		/* pages tag: pending write to cache */
-#define FSCACHE_COOKIE_STORING_TAG	1		/* pages tag: writing to cache */
-
-	unsigned long			flags;
-#define FSCACHE_COOKIE_LOOKING_UP	0	/* T if non-index cookie being looked up still */
-#define FSCACHE_COOKIE_NO_DATA_YET	1	/* T if new object with no cached data yet */
-#define FSCACHE_COOKIE_UNAVAILABLE	2	/* T if cookie is unavailable (error, etc) */
-#define FSCACHE_COOKIE_INVALIDATING	3	/* T if cookie is being invalidated */
-#define FSCACHE_COOKIE_RELINQUISHED	4	/* T if cookie has been relinquished */
-#define FSCACHE_COOKIE_RETIRED		5	/* T if cookie was retired */
-};
-
 extern struct fscache_cookie fscache_fsdef_index;
 
 /*
@@ -400,6 +370,7 @@ struct fscache_object {
 #define FSCACHE_OBJECT_IS_LIVE		3	/* T if object is not withdrawn or relinquished */
 #define FSCACHE_OBJECT_IS_LOOKED_UP	4	/* T if object has been looked up */
 #define FSCACHE_OBJECT_IS_AVAILABLE	5	/* T if object has become active */
+#define FSCACHE_OBJECT_RETIRED		6	/* T if object was retired on relinquishment */
 
 	struct list_head	cache_link;	/* link in cache->object_list */
 	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 19b46458e4e8..115bb81912cc 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -166,6 +166,42 @@ struct fscache_netfs {
 	struct list_head		link;		/* internal link */
 };
 
+/*
+ * data file or index object cookie
+ * - a file will only appear in one cache
+ * - a request to cache a file may or may not be honoured, subject to
+ *   constraints such as disk space
+ * - indices are created on disk just-in-time
+ */
+struct fscache_cookie {
+	atomic_t			usage;		/* number of users of this cookie */
+	atomic_t			n_children;	/* number of children of this cookie */
+	atomic_t			n_active;	/* number of active users of netfs ptrs */
+	spinlock_t			lock;
+	spinlock_t			stores_lock;	/* lock on page store tree */
+	struct hlist_head		backing_objects; /* object(s) backing this file/index */
+	const struct fscache_cookie_def	*def;		/* definition */
+	struct fscache_cookie		*parent;	/* parent of this entry */
+	void				*netfs_data;	/* back pointer to netfs */
+	struct radix_tree_root		stores;		/* pages to be stored on this cookie */
+#define FSCACHE_COOKIE_PENDING_TAG	0		/* pages tag: pending write to cache */
+#define FSCACHE_COOKIE_STORING_TAG	1		/* pages tag: writing to cache */
+
+	unsigned long			flags;
+#define FSCACHE_COOKIE_LOOKING_UP	0	/* T if non-index cookie being looked up still */
+#define FSCACHE_COOKIE_NO_DATA_YET	1	/* T if new object with no cached data yet */
+#define FSCACHE_COOKIE_UNAVAILABLE	2	/* T if cookie is unavailable (error, etc) */
+#define FSCACHE_COOKIE_INVALIDATING	3	/* T if cookie is being invalidated */
+#define FSCACHE_COOKIE_RELINQUISHED	4	/* T if cookie has been relinquished */
+#define FSCACHE_COOKIE_ENABLED		5	/* T if cookie is enabled */
+#define FSCACHE_COOKIE_ENABLEMENT_LOCK	6	/* T if cookie is being en/disabled */
+};
+
+static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie)
+{
+	return test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags);
+}
+
 /*
  * slow-path functions for when there is actually caching available, and the
  * netfs does actually have a valid token
@@ -181,8 +217,8 @@ extern void __fscache_release_cache_tag(struct fscache_cache_tag *);
 extern struct fscache_cookie *__fscache_acquire_cookie(
 	struct fscache_cookie *,
 	const struct fscache_cookie_def *,
-	void *);
-extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+	void *, bool);
+extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool);
 extern int __fscache_check_consistency(struct fscache_cookie *);
 extern void __fscache_update_cookie(struct fscache_cookie *);
 extern int __fscache_attr_changed(struct fscache_cookie *);
@@ -211,6 +247,9 @@ extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *,
 					      struct inode *);
 extern void __fscache_readpages_cancel(struct fscache_cookie *cookie,
 				       struct list_head *pages);
+extern void __fscache_disable_cookie(struct fscache_cookie *, bool);
+extern void __fscache_enable_cookie(struct fscache_cookie *,
+				    bool (*)(void *), void *);
 
 /**
  * fscache_register_netfs - Register a filesystem as desiring caching services
@@ -289,6 +328,7 @@ void fscache_release_cache_tag(struct fscache_cache_tag *tag)
  * @def: A description of the cache object, including callback operations
  * @netfs_data: An arbitrary piece of data to be kept in the cookie to
  * represent the cache object to the netfs
+ * @enable: Whether or not to enable a data cookie immediately
  *
  * This function is used to inform FS-Cache about part of an index hierarchy
  * that can be used to locate files.  This is done by requesting a cookie for
@@ -301,10 +341,12 @@ static inline
 struct fscache_cookie *fscache_acquire_cookie(
 	struct fscache_cookie *parent,
 	const struct fscache_cookie_def *def,
-	void *netfs_data)
+	void *netfs_data,
+	bool enable)
 {
-	if (fscache_cookie_valid(parent))
-		return __fscache_acquire_cookie(parent, def, netfs_data);
+	if (fscache_cookie_valid(parent) && fscache_cookie_enabled(parent))
+		return __fscache_acquire_cookie(parent, def, netfs_data,
+						enable);
 	else
 		return NULL;
 }
@@ -322,7 +364,7 @@ struct fscache_cookie *fscache_acquire_cookie(
  * description.
  */
 static inline
-void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire)
 {
 	if (fscache_cookie_valid(cookie))
 		__fscache_relinquish_cookie(cookie, retire);
@@ -341,7 +383,7 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 static inline
 int fscache_check_consistency(struct fscache_cookie *cookie)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_check_consistency(cookie);
 	else
 		return 0;
@@ -360,7 +402,7 @@ int fscache_check_consistency(struct fscache_cookie *cookie)
 static inline
 void fscache_update_cookie(struct fscache_cookie *cookie)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		__fscache_update_cookie(cookie);
 }
 
@@ -407,7 +449,7 @@ void fscache_unpin_cookie(struct fscache_cookie *cookie)
 static inline
 int fscache_attr_changed(struct fscache_cookie *cookie)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_attr_changed(cookie);
 	else
 		return -ENOBUFS;
@@ -429,7 +471,7 @@ int fscache_attr_changed(struct fscache_cookie *cookie)
 static inline
 void fscache_invalidate(struct fscache_cookie *cookie)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		__fscache_invalidate(cookie);
 }
 
@@ -503,7 +545,7 @@ int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 			       void *context,
 			       gfp_t gfp)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_read_or_alloc_page(cookie, page, end_io_func,
 						    context, gfp);
 	else
@@ -554,7 +596,7 @@ int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 				void *context,
 				gfp_t gfp)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_read_or_alloc_pages(cookie, mapping, pages,
 						     nr_pages, end_io_func,
 						     context, gfp);
@@ -585,7 +627,7 @@ int fscache_alloc_page(struct fscache_cookie *cookie,
 		       struct page *page,
 		       gfp_t gfp)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_alloc_page(cookie, page, gfp);
 	else
 		return -ENOBUFS;
@@ -634,7 +676,7 @@ int fscache_write_page(struct fscache_cookie *cookie,
 		       struct page *page,
 		       gfp_t gfp)
 {
-	if (fscache_cookie_valid(cookie))
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
 		return __fscache_write_page(cookie, page, gfp);
 	else
 		return -ENOBUFS;
@@ -744,4 +786,47 @@ void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
 		__fscache_uncache_all_inode_pages(cookie, inode);
 }
 
+/**
+ * fscache_disable_cookie - Disable a cookie
+ * @cookie: The cookie representing the cache object
+ * @invalidate: Invalidate the backing object
+ *
+ * Disable a cookie from accepting further alloc, read, write, invalidate,
+ * update or acquire operations.  Outstanding operations can still be waited
+ * upon and pages can still be uncached and the cookie relinquished.
+ *
+ * This will not return until all outstanding operations have completed.
+ *
+ * If @invalidate is set, then the backing object will be invalidated and
+ * detached, otherwise it will just be detached.
+ */
+static inline
+void fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
+{
+	if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie))
+		__fscache_disable_cookie(cookie, invalidate);
+}
+
+/**
+ * fscache_enable_cookie - Reenable a cookie
+ * @cookie: The cookie representing the cache object
+ * @can_enable: A function to permit enablement once lock is held
+ * @data: Data for can_enable()
+ *
+ * Reenable a previously disabled cookie, allowing it to accept further alloc,
+ * read, write, invalidate, update or acquire operations.  An attempt will be
+ * made to immediately reattach the cookie to a backing object.
+ *
+ * The can_enable() function is called (if not NULL) once the enablement lock
+ * is held to rule on whether enablement is still permitted to go ahead.
+ */
+static inline
+void fscache_enable_cookie(struct fscache_cookie *cookie,
+			   bool (*can_enable)(void *data),
+			   void *data)
+{
+	if (fscache_cookie_valid(cookie) && !fscache_cookie_enabled(cookie))
+		__fscache_enable_cookie(cookie, can_enable, data);
+}
+
 #endif /* _LINUX_FSCACHE_H */
-- 
cgit 


From f1fe29b4a02d0805aa7d0ff6b73410a9f9316d69 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 27 Sep 2013 11:20:03 +0100
Subject: NFS: Use i_writecount to control whether to get an fscache cookie in
 nfs_open()

Use i_writecount to control whether to get an fscache cookie in nfs_open() as
NFS does not do write caching yet.  I *think* this is the cause of a problem
encountered by Mark Moseley whereby __fscache_uncache_page() gets a NULL
pointer dereference because cookie->def is NULL:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
IP: [<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160
PGD 0
Thread overran stack, or stack corrupted
Oops: 0000 [#1] SMP
Modules linked in: ...
CPU: 7 PID: 18993 Comm: php Not tainted 3.11.1 #1
Hardware name: Dell Inc. PowerEdge R420/072XWF, BIOS 1.3.5 08/21/2012
task: ffff8804203460c0 ti: ffff880420346640
RIP: 0010:[<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160
RSP: 0018:ffff8801053af878 EFLAGS: 00210286
RAX: 0000000000000000 RBX: ffff8800be2f8780 RCX: ffff88022ffae5e8
RDX: 0000000000004c66 RSI: ffffea00055ff440 RDI: ffff8800be2f8780
RBP: ffff8801053af898 R08: 0000000000000001 R09: 0000000000000003
R10: 0000000000000000 R11: 0000000000000000 R12: ffffea00055ff440
R13: 0000000000001000 R14: ffff8800c50be538 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ffff88042fc60000(0063) knlGS:00000000e439c700
CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033
CR2: 0000000000000010 CR3: 0000000001d8f000 CR4: 00000000000607f0
Stack:
...
Call Trace:
[<ffffffff81365a72>] __nfs_fscache_invalidate_page+0x42/0x70
[<ffffffff813553d5>] nfs_invalidate_page+0x75/0x90
[<ffffffff811b8f5e>] truncate_inode_page+0x8e/0x90
[<ffffffff811b90ad>] truncate_inode_pages_range.part.12+0x14d/0x620
[<ffffffff81d6387d>] ? __mutex_lock_slowpath+0x1fd/0x2e0
[<ffffffff811b95d3>] truncate_inode_pages_range+0x53/0x70
[<ffffffff811b969d>] truncate_inode_pages+0x2d/0x40
[<ffffffff811b96ff>] truncate_pagecache+0x4f/0x70
[<ffffffff81356840>] nfs_setattr_update_inode+0xa0/0x120
[<ffffffff81368de4>] nfs3_proc_setattr+0xc4/0xe0
[<ffffffff81357f78>] nfs_setattr+0xc8/0x150
[<ffffffff8122d95b>] notify_change+0x1cb/0x390
[<ffffffff8120a55b>] do_truncate+0x7b/0xc0
[<ffffffff8121f96c>] do_last+0xa4c/0xfd0
[<ffffffff8121ffbc>] path_openat+0xcc/0x670
[<ffffffff81220a0e>] do_filp_open+0x4e/0xb0
[<ffffffff8120ba1f>] do_sys_open+0x13f/0x2b0
[<ffffffff8126aaf6>] compat_SyS_open+0x36/0x50
[<ffffffff81d7204c>] sysenter_dispatch+0x7/0x24

The code at the instruction pointer was disassembled:

> (gdb) disas __fscache_uncache_page
> Dump of assembler code for function __fscache_uncache_page:
> ...
> 0xffffffff812a18ff <+31>: mov 0x48(%rbx),%rax
> 0xffffffff812a1903 <+35>: cmpb $0x0,0x10(%rax)
> 0xffffffff812a1907 <+39>: je 0xffffffff812a19cd <__fscache_uncache_page+237>

These instructions make up:

	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);

That cmpb is the faulting instruction (%rax is 0).  So cookie->def is NULL -
which presumably means that the cookie has already been at least partway
through __fscache_relinquish_cookie().

What I think may be happening is something like a three-way race on the same
file:

	PROCESS 1	PROCESS 2	PROCESS 3
	===============	===============	===============
	open(O_TRUNC|O_WRONLY)
			open(O_RDONLY)
					open(O_WRONLY)
	-->nfs_open()
	-->nfs_fscache_set_inode_cookie()
	nfs_fscache_inode_lock()
	nfs_fscache_disable_inode_cookie()
	__fscache_relinquish_cookie()
	nfs_inode->fscache = NULL
	<--nfs_fscache_set_inode_cookie()

			-->nfs_open()
			-->nfs_fscache_set_inode_cookie()
			nfs_fscache_inode_lock()
			nfs_fscache_enable_inode_cookie()
			__fscache_acquire_cookie()
			nfs_inode->fscache = cookie
			<--nfs_fscache_set_inode_cookie()
	<--nfs_open()
	-->nfs_setattr()
	...
	...
	-->nfs_invalidate_page()
	-->__nfs_fscache_invalidate_page()
	cookie = nfsi->fscache
					-->nfs_open()
					-->nfs_fscache_set_inode_cookie()
					nfs_fscache_inode_lock()
					nfs_fscache_disable_inode_cookie()
					-->__fscache_relinquish_cookie()
	-->__fscache_uncache_page(cookie)
	<crash>
					<--__fscache_relinquish_cookie()
					nfs_inode->fscache = NULL
					<--nfs_fscache_set_inode_cookie()

What is needed is something to prevent process #2 from reacquiring the cookie
- and I think checking i_writecount should do the trick.

It's also possible to have a two-way race on this if the file is opened
O_TRUNC|O_RDONLY instead.

Reported-by: Mark Moseley <moseleymark@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/nfs/dir.c           |   2 +-
 fs/nfs/fscache.c       | 198 ++++++++++++++-----------------------------------
 fs/nfs/fscache.h       |  18 ++---
 fs/nfs/inode.c         |   6 +-
 fs/nfs/nfs4file.c      |   2 +-
 include/linux/fs.h     |   5 ++
 include/linux/nfs_fs.h |   8 +-
 7 files changed, 79 insertions(+), 160 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 854a8f05a610..4c5edcc8b6e9 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1381,7 +1381,7 @@ static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, i
 
 static int do_open(struct inode *inode, struct file *filp)
 {
-	nfs_fscache_set_inode_cookie(inode, filp);
+	nfs_fscache_open_file(inode, filp);
 	return 0;
 }
 
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index cd6e7efd4305..3ef01f0ba0bc 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -178,163 +178,79 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
 /*
  * Initialise the per-inode cache cookie pointer for an NFS inode.
  */
-void nfs_fscache_init_inode_cookie(struct inode *inode)
+void nfs_fscache_init_inode(struct inode *inode)
 {
-	NFS_I(inode)->fscache = NULL;
-	if (S_ISREG(inode->i_mode))
-		set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
-}
-
-/*
- * Get the per-inode cache cookie for an NFS inode.
- */
-static void nfs_fscache_enable_inode_cookie(struct inode *inode)
-{
-	struct super_block *sb = inode->i_sb;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	if (nfsi->fscache || !NFS_FSCACHE(inode))
+	nfsi->fscache = NULL;
+	if (!S_ISREG(inode->i_mode))
 		return;
-
-	if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
-		nfsi->fscache = fscache_acquire_cookie(
-			NFS_SB(sb)->fscache,
-			&nfs_fscache_inode_object_def,
-			nfsi, true);
-
-		dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
-			 sb, nfsi, nfsi->fscache);
-	}
+	nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
+					       &nfs_fscache_inode_object_def,
+					       nfsi, false);
 }
 
 /*
  * Release a per-inode cookie.
  */
-void nfs_fscache_release_inode_cookie(struct inode *inode)
+void nfs_fscache_clear_inode(struct inode *inode)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
 
-	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
-		 nfsi, nfsi->fscache);
+	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
 
-	fscache_relinquish_cookie(nfsi->fscache, 0);
+	fscache_relinquish_cookie(cookie, false);
 	nfsi->fscache = NULL;
 }
 
-/*
- * Retire a per-inode cookie, destroying the data attached to it.
- */
-void nfs_fscache_zap_inode_cookie(struct inode *inode)
+static bool nfs_fscache_can_enable(void *data)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
+	struct inode *inode = data;
 
-	dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
-		 nfsi, nfsi->fscache);
-
-	fscache_relinquish_cookie(nfsi->fscache, 1);
-	nfsi->fscache = NULL;
+	return !inode_is_open_for_write(inode);
 }
 
 /*
- * Turn off the cache with regard to a per-inode cookie if opened for writing,
- * invalidating all the pages in the page cache relating to the associated
- * inode to clear the per-page caching.
- */
-static void nfs_fscache_disable_inode_cookie(struct inode *inode)
-{
-	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
-
-	if (NFS_I(inode)->fscache) {
-		dfprintk(FSCACHE,
-			 "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
-
-		/* Need to uncache any pages attached to this inode that
-		 * fscache knows about before turning off the cache.
-		 */
-		fscache_uncache_all_inode_pages(NFS_I(inode)->fscache, inode);
-		nfs_fscache_zap_inode_cookie(inode);
-	}
-}
-
-/*
- * wait_on_bit() sleep function for uninterruptible waiting
- */
-static int nfs_fscache_wait_bit(void *flags)
-{
-	schedule();
-	return 0;
-}
-
-/*
- * Lock against someone else trying to also acquire or relinquish a cookie
- */
-static inline void nfs_fscache_inode_lock(struct inode *inode)
-{
-	struct nfs_inode *nfsi = NFS_I(inode);
-
-	while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
-		wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
-			    nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
-}
-
-/*
- * Unlock cookie management lock
- */
-static inline void nfs_fscache_inode_unlock(struct inode *inode)
-{
-	struct nfs_inode *nfsi = NFS_I(inode);
-
-	smp_mb__before_clear_bit();
-	clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
-	smp_mb__after_clear_bit();
-	wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
-}
-
-/*
- * Decide if we should enable or disable local caching for this inode.
- * - For now, with NFS, only regular files that are open read-only will be able
- *   to use the cache.
- * - May be invoked multiple times in parallel by parallel nfs_open() functions.
- */
-void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
-{
-	if (NFS_FSCACHE(inode)) {
-		nfs_fscache_inode_lock(inode);
-		if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
-			nfs_fscache_disable_inode_cookie(inode);
-		else
-			nfs_fscache_enable_inode_cookie(inode);
-		nfs_fscache_inode_unlock(inode);
-	}
-}
-EXPORT_SYMBOL_GPL(nfs_fscache_set_inode_cookie);
-
-/*
- * Replace a per-inode cookie due to revalidation detecting a file having
- * changed on the server.
+ * Enable or disable caching for a file that is being opened as appropriate.
+ * The cookie is allocated when the inode is initialised, but is not enabled at
+ * that time.  Enablement is deferred to file-open time to avoid stat() and
+ * access() thrashing the cache.
+ *
+ * For now, with NFS, only regular files that are open read-only will be able
+ * to use the cache.
+ *
+ * We enable the cache for an inode if we open it read-only and it isn't
+ * currently open for writing.  We disable the cache if the inode is open
+ * write-only.
+ *
+ * The caller uses the file struct to pin i_writecount on the inode before
+ * calling us when a file is opened for writing, so we can make use of that.
+ *
+ * Note that this may be invoked multiple times in parallel by parallel
+ * nfs_open() functions.
  */
-void nfs_fscache_reset_inode_cookie(struct inode *inode)
+void nfs_fscache_open_file(struct inode *inode, struct file *filp)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct nfs_server *nfss = NFS_SERVER(inode);
-	NFS_IFDEBUG(struct fscache_cookie *old = nfsi->fscache);
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
 
-	nfs_fscache_inode_lock(inode);
-	if (nfsi->fscache) {
-		/* retire the current fscache cache and get a new one */
-		fscache_relinquish_cookie(nfsi->fscache, 1);
-
-		nfsi->fscache = fscache_acquire_cookie(
-			nfss->nfs_client->fscache,
-			&nfs_fscache_inode_object_def,
-			nfsi, true);
+	if (!fscache_cookie_valid(cookie))
+		return;
 
-		dfprintk(FSCACHE,
-			 "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
-			 nfss, nfsi, old, nfsi->fscache);
+	if (inode_is_open_for_write(inode)) {
+		dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
+		clear_bit(NFS_INO_FSCACHE, &nfsi->flags);
+		fscache_disable_cookie(cookie, true);
+		fscache_uncache_all_inode_pages(cookie, inode);
+	} else {
+		dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi);
+		fscache_enable_cookie(cookie, nfs_fscache_can_enable, inode);
+		if (fscache_cookie_enabled(cookie))
+			set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
 	}
-	nfs_fscache_inode_unlock(inode);
 }
+EXPORT_SYMBOL_GPL(nfs_fscache_open_file);
 
 /*
  * Release the caching state associated with a page, if the page isn't busy
@@ -344,12 +260,11 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
 int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
 	if (PageFsCache(page)) {
-		struct nfs_inode *nfsi = NFS_I(page->mapping->host);
-		struct fscache_cookie *cookie = nfsi->fscache;
+		struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host);
 
 		BUG_ON(!cookie);
 		dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
-			 cookie, page, nfsi);
+			 cookie, page, NFS_I(page->mapping->host));
 
 		if (!fscache_maybe_release_page(cookie, page, gfp))
 			return 0;
@@ -367,13 +282,12 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp)
  */
 void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
-	struct fscache_cookie *cookie = nfsi->fscache;
+	struct fscache_cookie *cookie = nfs_i_fscache(inode);
 
 	BUG_ON(!cookie);
 
 	dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
-		 cookie, page, nfsi);
+		 cookie, page, NFS_I(inode));
 
 	fscache_wait_on_page_write(cookie, page);
 
@@ -417,9 +331,9 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
 
 	dfprintk(FSCACHE,
 		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
-		 NFS_I(inode)->fscache, page, page->index, page->flags, inode);
+		 nfs_i_fscache(inode), page, page->index, page->flags, inode);
 
-	ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
+	ret = fscache_read_or_alloc_page(nfs_i_fscache(inode),
 					 page,
 					 nfs_readpage_from_fscache_complete,
 					 ctx,
@@ -459,9 +373,9 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 	int ret;
 
 	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
-		 NFS_I(inode)->fscache, npages, inode);
+		 nfs_i_fscache(inode), npages, inode);
 
-	ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
+	ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode),
 					  mapping, pages, nr_pages,
 					  nfs_readpage_from_fscache_complete,
 					  ctx,
@@ -506,15 +420,15 @@ void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
 
 	dfprintk(FSCACHE,
 		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
-		 NFS_I(inode)->fscache, page, page->index, page->flags, sync);
+		 nfs_i_fscache(inode), page, page->index, page->flags, sync);
 
-	ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
+	ret = fscache_write_page(nfs_i_fscache(inode), page, GFP_KERNEL);
 	dfprintk(FSCACHE,
 		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
 		 page, page->index, page->flags, ret);
 
 	if (ret != 0) {
-		fscache_uncache_page(NFS_I(inode)->fscache, page);
+		fscache_uncache_page(nfs_i_fscache(inode), page);
 		nfs_add_fscache_stats(inode,
 				      NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1);
 		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 4ecb76652eba..d7fe3e799f2f 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -76,11 +76,9 @@ extern void nfs_fscache_release_client_cookie(struct nfs_client *);
 extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int);
 extern void nfs_fscache_release_super_cookie(struct super_block *);
 
-extern void nfs_fscache_init_inode_cookie(struct inode *);
-extern void nfs_fscache_release_inode_cookie(struct inode *);
-extern void nfs_fscache_zap_inode_cookie(struct inode *);
-extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
-extern void nfs_fscache_reset_inode_cookie(struct inode *);
+extern void nfs_fscache_init_inode(struct inode *);
+extern void nfs_fscache_clear_inode(struct inode *);
+extern void nfs_fscache_open_file(struct inode *, struct file *);
 
 extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
 extern int nfs_fscache_release_page(struct page *, gfp_t);
@@ -187,12 +185,10 @@ static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
 
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
 
-static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
-static inline void nfs_fscache_release_inode_cookie(struct inode *inode) {}
-static inline void nfs_fscache_zap_inode_cookie(struct inode *inode) {}
-static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
-						struct file *filp) {}
-static inline void nfs_fscache_reset_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_init_inode(struct inode *inode) {}
+static inline void nfs_fscache_clear_inode(struct inode *inode) {}
+static inline void nfs_fscache_open_file(struct inode *inode,
+					 struct file *filp) {}
 
 static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index eda8879171c4..bb90bff0cb7a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -122,7 +122,7 @@ void nfs_clear_inode(struct inode *inode)
 	WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files));
 	nfs_zap_acl_cache(inode);
 	nfs_access_zap_cache(inode);
-	nfs_fscache_release_inode_cookie(inode);
+	nfs_fscache_clear_inode(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
@@ -459,7 +459,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		nfsi->attrtimeo_timestamp = now;
 		nfsi->access_cache = RB_ROOT;
 
-		nfs_fscache_init_inode_cookie(inode);
+		nfs_fscache_init_inode(inode);
 
 		unlock_new_inode(inode);
 	} else
@@ -854,7 +854,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 		return PTR_ERR(ctx);
 	nfs_file_set_open_context(filp, ctx);
 	put_nfs_open_context(ctx);
-	nfs_fscache_set_inode_cookie(inode, filp);
+	nfs_fscache_open_file(inode, filp);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e5b804dd944c..5b8a618a0f7a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -74,7 +74,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	nfs_file_set_open_context(filp, ctx);
-	nfs_fscache_set_inode_cookie(inode, filp);
+	nfs_fscache_open_file(inode, filp);
 	err = 0;
 
 out_put_ctx:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f40547ba191..955dff5da56a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2292,6 +2292,11 @@ static inline void allow_write_access(struct file *file)
 	if (file)
 		atomic_inc(&file_inode(file)->i_writecount);
 }
+static inline bool inode_is_open_for_write(const struct inode *inode)
+{
+	return atomic_read(&inode->i_writecount) > 0;
+}
+
 #ifdef CONFIG_IMA
 static inline void i_readcount_dec(struct inode *inode)
 {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 3ea4cde8701c..14a48207a304 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -269,9 +269,13 @@ static inline int NFS_STALE(const struct inode *inode)
 	return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
-static inline int NFS_FSCACHE(const struct inode *inode)
+static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode)
 {
-	return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+#ifdef CONFIG_NFS_FSCACHE
+	return NFS_I(inode)->fscache;
+#else
+	return NULL;
+#endif
 }
 
 static inline __u64 NFS_FILEID(const struct inode *inode)
-- 
cgit 


From 8d6a35fb13406f87d926fffeee0d70360ce3077d Mon Sep 17 00:00:00 2001
From: Sean Cross <xobs@kosagi.com>
Date: Thu, 26 Sep 2013 11:24:46 +0800
Subject: ARM: imx6q: Add PCIe bits to GPR syscon definition

PCIe requires additional bits be defined for GPR8 and GPR12.

Signed-off-by: Sean Cross <xobs@kosagi.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
index b6bdcd66c07d..e00e9f362fd5 100644
--- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
+++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
@@ -241,6 +241,12 @@
 
 #define IMX6Q_GPR5_L2_CLK_STOP			BIT(8)
 
+#define IMX6Q_GPR8_TX_SWING_LOW			(0x7f << 25)
+#define IMX6Q_GPR8_TX_SWING_FULL		(0x7f << 18)
+#define IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB		(0x3f << 12)
+#define IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB		(0x3f << 6)
+#define IMX6Q_GPR8_TX_DEEMPH_GEN1		(0x3f << 0)
+
 #define IMX6Q_GPR9_TZASC2_BYP			BIT(1)
 #define IMX6Q_GPR9_TZASC1_BYP			BIT(0)
 
@@ -273,7 +279,9 @@
 #define IMX6Q_GPR12_ARMP_AHB_CLK_EN		BIT(26)
 #define IMX6Q_GPR12_ARMP_ATB_CLK_EN		BIT(25)
 #define IMX6Q_GPR12_ARMP_APB_CLK_EN		BIT(24)
+#define IMX6Q_GPR12_DEVICE_TYPE			(0xf << 12)
 #define IMX6Q_GPR12_PCIE_CTL_2			BIT(10)
+#define IMX6Q_GPR12_LOS_LEVEL			(0x1f << 4)
 
 #define IMX6Q_GPR13_SDMA_STOP_REQ		BIT(30)
 #define IMX6Q_GPR13_CAN2_STOP_REQ		BIT(29)
-- 
cgit 


From 09a2c73ddfc7f173237fc7209a65b34dd5bcb5ed Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Thu, 12 Sep 2013 16:20:00 +0800
Subject: PCI: Remove unused PCI_MSIX_FLAGS_BIRMASK definition

PCI_MSIX_FLAGS_BIRMASK has been replaced by PCI_MSIX_TABLE_BIR for better
readability.  Now no one uses it, remove it.  No functional change.

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/uapi/linux/pci_regs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index baa7852468ef..f0509148111d 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -319,7 +319,6 @@
 #define PCI_MSIX_PBA		8	/* Pending Bit Array offset */
 #define  PCI_MSIX_PBA_BIR	0x00000007 /* BAR index */
 #define  PCI_MSIX_PBA_OFFSET	0xfffffff8 /* Offset into specified BAR */
-#define  PCI_MSIX_FLAGS_BIRMASK	(7 << 0)   /* deprecated */
 #define PCI_CAP_MSIX_SIZEOF	12	/* size of MSIX registers */
 
 /* MSI-X entry's format */
-- 
cgit 


From 8d2ca1d7b5c3e63b3a8a81ae99015b615c5f2bf7 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 21 Sep 2013 16:55:59 +0200
Subject: ipv6: avoid high order memory allocations for /proc/net/ipv6_route

Dumping routes on a system with lots rt6_infos in the fibs causes up to
11-order allocations in seq_file (which fail). While we could switch
there to vmalloc we could just implement the streaming interface for
/proc/net/ipv6_route. This patch switches /proc/net/ipv6_route from
single_open_net to seq_open_net.

loff_t *pos tracks dst entries.

Also kill never used struct rt6_proc_arg and now unused function
fib6_clean_all_ro.

Cc: Ben Greear <greearb@candelatech.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |   6 +-
 net/ipv6/ip6_fib.c    | 191 +++++++++++++++++++++++++++++++++++++++++++++-----
 net/ipv6/route.c      |  46 +-----------
 3 files changed, 175 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index eab88f0e2088..6738f3409a6f 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -280,10 +280,6 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
 			      const struct in6_addr *saddr, int src_len);
 
-void fib6_clean_all_ro(struct net *net,
-		       int (*func)(struct rt6_info *, void *arg),
-		       int prune, void *arg);
-
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    int prune, void *arg);
 
@@ -299,6 +295,8 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
+int ipv6_route_open(struct inode *inode, struct file *file);
+
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 int fib6_rules_init(void);
 void fib6_rules_cleanup(void);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5bec666aba61..05ffa54fcf21 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1529,25 +1529,6 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 	fib6_walk(&c.w);
 }
 
-void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
-		    int prune, void *arg)
-{
-	struct fib6_table *table;
-	struct hlist_head *head;
-	unsigned int h;
-
-	rcu_read_lock();
-	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			read_lock_bh(&table->tb6_lock);
-			fib6_clean_tree(net, &table->tb6_root,
-					func, prune, arg);
-			read_unlock_bh(&table->tb6_lock);
-		}
-	}
-	rcu_read_unlock();
-}
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    int prune, void *arg)
 {
@@ -1782,3 +1763,175 @@ void fib6_gc_cleanup(void)
 	unregister_pernet_subsys(&fib6_net_ops);
 	kmem_cache_destroy(fib6_node_kmem);
 }
+
+#ifdef CONFIG_PROC_FS
+
+struct ipv6_route_iter {
+	struct seq_net_private p;
+	struct fib6_walker_t w;
+	loff_t skip;
+	struct fib6_table *tbl;
+};
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	struct rt6_info *rt = v;
+	struct ipv6_route_iter *iter = seq->private;
+
+	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
+#else
+	seq_puts(seq, "00000000000000000000000000000000 00 ");
+#endif
+	if (rt->rt6i_flags & RTF_GATEWAY)
+		seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+	else
+		seq_puts(seq, "00000000000000000000000000000000");
+
+	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
+		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
+		   rt->dst.__use, rt->rt6i_flags,
+		   rt->dst.dev ? rt->dst.dev->name : "");
+	iter->w.leaf = NULL;
+	return 0;
+}
+
+static int ipv6_route_yield(struct fib6_walker_t *w)
+{
+	struct ipv6_route_iter *iter = w->args;
+
+	if (!iter->skip)
+		return 1;
+
+	do {
+		iter->w.leaf = iter->w.leaf->dst.rt6_next;
+		iter->skip--;
+		if (!iter->skip && iter->w.leaf)
+			return 1;
+	} while (iter->w.leaf);
+
+	return 0;
+}
+
+static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter)
+{
+	memset(&iter->w, 0, sizeof(iter->w));
+	iter->w.func = ipv6_route_yield;
+	iter->w.root = &iter->tbl->tb6_root;
+	iter->w.state = FWS_INIT;
+	iter->w.node = iter->w.root;
+	iter->w.args = iter;
+	INIT_LIST_HEAD(&iter->w.lh);
+	fib6_walker_link(&iter->w);
+}
+
+static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,
+						    struct net *net)
+{
+	unsigned int h;
+	struct hlist_node *node;
+
+	if (tbl) {
+		h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1;
+		node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist));
+	} else {
+		h = 0;
+		node = NULL;
+	}
+
+	while (!node && h < FIB6_TABLE_HASHSZ) {
+		node = rcu_dereference_bh(
+			hlist_first_rcu(&net->ipv6.fib_table_hash[h++]));
+	}
+	return hlist_entry_safe(node, struct fib6_table, tb6_hlist);
+}
+
+static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	int r;
+	struct rt6_info *n;
+	struct net *net = seq_file_net(seq);
+	struct ipv6_route_iter *iter = seq->private;
+
+	if (!v)
+		goto iter_table;
+
+	n = ((struct rt6_info *)v)->dst.rt6_next;
+	if (n) {
+		++*pos;
+		return n;
+	}
+
+iter_table:
+	read_lock(&iter->tbl->tb6_lock);
+	r = fib6_walk_continue(&iter->w);
+	read_unlock(&iter->tbl->tb6_lock);
+	if (r > 0) {
+		if (v)
+			++*pos;
+		return iter->w.leaf;
+	} else if (r < 0) {
+		fib6_walker_unlink(&iter->w);
+		return NULL;
+	}
+	fib6_walker_unlink(&iter->w);
+
+	iter->tbl = ipv6_route_seq_next_table(iter->tbl, net);
+	if (!iter->tbl)
+		return NULL;
+
+	ipv6_route_seq_setup_walk(iter);
+	goto iter_table;
+}
+
+static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU_BH)
+{
+	struct net *net = seq_file_net(seq);
+	struct ipv6_route_iter *iter = seq->private;
+
+	rcu_read_lock_bh();
+	iter->tbl = ipv6_route_seq_next_table(NULL, net);
+	iter->skip = *pos;
+
+	if (iter->tbl) {
+		ipv6_route_seq_setup_walk(iter);
+		return ipv6_route_seq_next(seq, NULL, pos);
+	} else {
+		return NULL;
+	}
+}
+
+static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
+{
+	struct fib6_walker_t *w = &iter->w;
+	return w->node && !(w->state == FWS_U && w->node == w->root);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU_BH)
+{
+	struct ipv6_route_iter *iter = seq->private;
+
+	if (ipv6_route_iter_active(iter))
+		fib6_walker_unlink(&iter->w);
+
+	rcu_read_unlock_bh();
+}
+
+static const struct seq_operations ipv6_route_seq_ops = {
+	.start	= ipv6_route_seq_start,
+	.next	= ipv6_route_seq_next,
+	.stop	= ipv6_route_seq_stop,
+	.show	= ipv6_route_seq_show
+};
+
+int ipv6_route_open(struct inode *inode, struct file *file)
+{
+	return seq_open_net(inode, file, &ipv6_route_seq_ops,
+			    sizeof(struct ipv6_route_iter));
+}
+
+#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c979dd96d82a..aa901bb60cf2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2800,56 +2800,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 
 #ifdef CONFIG_PROC_FS
 
-struct rt6_proc_arg
-{
-	char *buffer;
-	int offset;
-	int length;
-	int skip;
-	int len;
-};
-
-static int rt6_info_route(struct rt6_info *rt, void *p_arg)
-{
-	struct seq_file *m = p_arg;
-
-	seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
-
-#ifdef CONFIG_IPV6_SUBTREES
-	seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
-#else
-	seq_puts(m, "00000000000000000000000000000000 00 ");
-#endif
-	if (rt->rt6i_flags & RTF_GATEWAY) {
-		seq_printf(m, "%pi6", &rt->rt6i_gateway);
-	} else {
-		seq_puts(m, "00000000000000000000000000000000");
-	}
-	seq_printf(m, " %08x %08x %08x %08x %8s\n",
-		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
-		   rt->dst.__use, rt->rt6i_flags,
-		   rt->dst.dev ? rt->dst.dev->name : "");
-	return 0;
-}
-
-static int ipv6_route_show(struct seq_file *m, void *v)
-{
-	struct net *net = (struct net *)m->private;
-	fib6_clean_all_ro(net, rt6_info_route, 0, m);
-	return 0;
-}
-
-static int ipv6_route_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, ipv6_route_show);
-}
-
 static const struct file_operations ipv6_route_proc_fops = {
 	.owner		= THIS_MODULE,
 	.open		= ipv6_route_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= single_release_net,
+	.release	= seq_release_net,
 };
 
 static int rt6_stats_seq_show(struct seq_file *seq, void *v)
-- 
cgit 


From b019ba959fc4600a646bb9d732149b1b0056f88a Mon Sep 17 00:00:00 2001
From: Sudeep Dutt <sudeep.dutt@intel.com>
Date: Fri, 27 Sep 2013 09:50:06 -0700
Subject: misc: mic: fix a warning in the IOCTL header file.

The following warning from mic_ioctl.h is fixed via this patch:
found __[us]{8,16,32,64} type without #include <linux/types.h>

Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Harshavardhan R Kharche <harshavardhan.r.kharche@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/mic_ioctl.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h
index 0e6cbf3e5292..7fabba5059cf 100644
--- a/include/uapi/linux/mic_ioctl.h
+++ b/include/uapi/linux/mic_ioctl.h
@@ -21,6 +21,8 @@
 #ifndef _MIC_IOCTL_H_
 #define _MIC_IOCTL_H_
 
+#include <linux/types.h>
+
 /*
  * mic_copy - MIC virtio descriptor copy.
  *
-- 
cgit 


From ff764963479a1b18721ab96e531404c50fefe8b1 Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Fri, 27 Sep 2013 11:53:25 +0530
Subject: drivers: phy: add generic PHY framework

The PHY framework provides a set of APIs for the PHY drivers to
create/destroy a PHY and APIs for the PHY users to obtain a reference to the
PHY with or without using phandle. For dt-boot, the PHY drivers should
also register *PHY provider* with the framework.

PHY drivers should create the PHY by passing id and ops like init, exit,
power_on and power_off. This framework is also pm runtime enabled.

The documentation for the generic PHY framework is added in
Documentation/phy.txt and the documentation for dt binding can be found at
Documentation/devicetree/bindings/phy/phy-bindings.txt

Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Acked-by: Felipe Balbi <balbi@ti.com>
Tested-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/phy/phy-bindings.txt       |  66 ++
 Documentation/phy.txt                              | 166 +++++
 MAINTAINERS                                        |   8 +
 drivers/Kconfig                                    |   2 +
 drivers/Makefile                                   |   2 +
 drivers/phy/Kconfig                                |  18 +
 drivers/phy/Makefile                               |   5 +
 drivers/phy/phy-core.c                             | 698 +++++++++++++++++++++
 include/linux/phy/phy.h                            | 270 ++++++++
 9 files changed, 1235 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/phy/phy-bindings.txt
 create mode 100644 Documentation/phy.txt
 create mode 100644 drivers/phy/Kconfig
 create mode 100644 drivers/phy/Makefile
 create mode 100644 drivers/phy/phy-core.c
 create mode 100644 include/linux/phy/phy.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/phy/phy-bindings.txt b/Documentation/devicetree/bindings/phy/phy-bindings.txt
new file mode 100644
index 000000000000..8ae844fc0c60
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/phy-bindings.txt
@@ -0,0 +1,66 @@
+This document explains only the device tree data binding. For general
+information about PHY subsystem refer to Documentation/phy.txt
+
+PHY device node
+===============
+
+Required Properties:
+#phy-cells:	Number of cells in a PHY specifier;  The meaning of all those
+		cells is defined by the binding for the phy node. The PHY
+		provider can use the values in cells to find the appropriate
+		PHY.
+
+For example:
+
+phys: phy {
+    compatible = "xxx";
+    reg = <...>;
+    .
+    .
+    #phy-cells = <1>;
+    .
+    .
+};
+
+That node describes an IP block (PHY provider) that implements 2 different PHYs.
+In order to differentiate between these 2 PHYs, an additonal specifier should be
+given while trying to get a reference to it.
+
+PHY user node
+=============
+
+Required Properties:
+phys : the phandle for the PHY device (used by the PHY subsystem)
+phy-names : the names of the PHY corresponding to the PHYs present in the
+	    *phys* phandle
+
+Example 1:
+usb1: usb_otg_ss@xxx {
+    compatible = "xxx";
+    reg = <xxx>;
+    .
+    .
+    phys = <&usb2_phy>, <&usb3_phy>;
+    phy-names = "usb2phy", "usb3phy";
+    .
+    .
+};
+
+This node represents a controller that uses two PHYs, one for usb2 and one for
+usb3.
+
+Example 2:
+usb2: usb_otg_ss@xxx {
+    compatible = "xxx";
+    reg = <xxx>;
+    .
+    .
+    phys = <&phys 1>;
+    phy-names = "usbphy";
+    .
+    .
+};
+
+This node represents a controller that uses one of the PHYs of the PHY provider
+device defined previously. Note that the phy handle has an additional specifier
+"1" to differentiate between the two PHYs.
diff --git a/Documentation/phy.txt b/Documentation/phy.txt
new file mode 100644
index 000000000000..0103e4b15b0e
--- /dev/null
+++ b/Documentation/phy.txt
@@ -0,0 +1,166 @@
+			    PHY SUBSYSTEM
+		  Kishon Vijay Abraham I <kishon@ti.com>
+
+This document explains the Generic PHY Framework along with the APIs provided,
+and how-to-use.
+
+1. Introduction
+
+*PHY* is the abbreviation for physical layer. It is used to connect a device
+to the physical medium e.g., the USB controller has a PHY to provide functions
+such as serialization, de-serialization, encoding, decoding and is responsible
+for obtaining the required data transmission rate. Note that some USB
+controllers have PHY functionality embedded into it and others use an external
+PHY. Other peripherals that use PHY include Wireless LAN, Ethernet,
+SATA etc.
+
+The intention of creating this framework is to bring the PHY drivers spread
+all over the Linux kernel to drivers/phy to increase code re-use and for
+better code maintainability.
+
+This framework will be of use only to devices that use external PHY (PHY
+functionality is not embedded within the controller).
+
+2. Registering/Unregistering the PHY provider
+
+PHY provider refers to an entity that implements one or more PHY instances.
+For the simple case where the PHY provider implements only a single instance of
+the PHY, the framework provides its own implementation of of_xlate in
+of_phy_simple_xlate. If the PHY provider implements multiple instances, it
+should provide its own implementation of of_xlate. of_xlate is used only for
+dt boot case.
+
+#define of_phy_provider_register(dev, xlate)    \
+        __of_phy_provider_register((dev), THIS_MODULE, (xlate))
+
+#define devm_of_phy_provider_register(dev, xlate)       \
+        __devm_of_phy_provider_register((dev), THIS_MODULE, (xlate))
+
+of_phy_provider_register and devm_of_phy_provider_register macros can be used to
+register the phy_provider and it takes device and of_xlate as
+arguments. For the dt boot case, all PHY providers should use one of the above
+2 macros to register the PHY provider.
+
+void devm_of_phy_provider_unregister(struct device *dev,
+	struct phy_provider *phy_provider);
+void of_phy_provider_unregister(struct phy_provider *phy_provider);
+
+devm_of_phy_provider_unregister and of_phy_provider_unregister can be used to
+unregister the PHY.
+
+3. Creating the PHY
+
+The PHY driver should create the PHY in order for other peripheral controllers
+to make use of it. The PHY framework provides 2 APIs to create the PHY.
+
+struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
+        struct phy_init_data *init_data);
+struct phy *devm_phy_create(struct device *dev, const struct phy_ops *ops,
+	struct phy_init_data *init_data);
+
+The PHY drivers can use one of the above 2 APIs to create the PHY by passing
+the device pointer, phy ops and init_data.
+phy_ops is a set of function pointers for performing PHY operations such as
+init, exit, power_on and power_off. *init_data* is mandatory to get a reference
+to the PHY in the case of non-dt boot. See section *Board File Initialization*
+on how init_data should be used.
+
+Inorder to dereference the private data (in phy_ops), the phy provider driver
+can use phy_set_drvdata() after creating the PHY and use phy_get_drvdata() in
+phy_ops to get back the private data.
+
+4. Getting a reference to the PHY
+
+Before the controller can make use of the PHY, it has to get a reference to
+it. This framework provides the following APIs to get a reference to the PHY.
+
+struct phy *phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_get(struct device *dev, const char *string);
+
+phy_get and devm_phy_get can be used to get the PHY. In the case of dt boot,
+the string arguments should contain the phy name as given in the dt data and
+in the case of non-dt boot, it should contain the label of the PHY.
+The only difference between the two APIs is that devm_phy_get associates the
+device with the PHY using devres on successful PHY get. On driver detach,
+release function is invoked on the the devres data and devres data is freed.
+
+5. Releasing a reference to the PHY
+
+When the controller no longer needs the PHY, it has to release the reference
+to the PHY it has obtained using the APIs mentioned in the above section. The
+PHY framework provides 2 APIs to release a reference to the PHY.
+
+void phy_put(struct phy *phy);
+void devm_phy_put(struct device *dev, struct phy *phy);
+
+Both these APIs are used to release a reference to the PHY and devm_phy_put
+destroys the devres associated with this PHY.
+
+6. Destroying the PHY
+
+When the driver that created the PHY is unloaded, it should destroy the PHY it
+created using one of the following 2 APIs.
+
+void phy_destroy(struct phy *phy);
+void devm_phy_destroy(struct device *dev, struct phy *phy);
+
+Both these APIs destroy the PHY and devm_phy_destroy destroys the devres
+associated with this PHY.
+
+7. PM Runtime
+
+This subsystem is pm runtime enabled. So while creating the PHY,
+pm_runtime_enable of the phy device created by this subsystem is called and
+while destroying the PHY, pm_runtime_disable is called. Note that the phy
+device created by this subsystem will be a child of the device that calls
+phy_create (PHY provider device).
+
+So pm_runtime_get_sync of the phy_device created by this subsystem will invoke
+pm_runtime_get_sync of PHY provider device because of parent-child relationship.
+It should also be noted that phy_power_on and phy_power_off performs
+phy_pm_runtime_get_sync and phy_pm_runtime_put respectively.
+There are exported APIs like phy_pm_runtime_get, phy_pm_runtime_get_sync,
+phy_pm_runtime_put, phy_pm_runtime_put_sync, phy_pm_runtime_allow and
+phy_pm_runtime_forbid for performing PM operations.
+
+8. Board File Initialization
+
+Certain board file initialization is necessary in order to get a reference
+to the PHY in the case of non-dt boot.
+Say we have a single device that implements 3 PHYs that of USB, SATA and PCIe,
+then in the board file the following initialization should be done.
+
+struct phy_consumer consumers[] = {
+	PHY_CONSUMER("dwc3.0", "usb"),
+	PHY_CONSUMER("pcie.0", "pcie"),
+	PHY_CONSUMER("sata.0", "sata"),
+};
+PHY_CONSUMER takes 2 parameters, first is the device name of the controller
+(PHY consumer) and second is the port name.
+
+struct phy_init_data init_data = {
+	.consumers = consumers,
+	.num_consumers = ARRAY_SIZE(consumers),
+};
+
+static const struct platform_device pipe3_phy_dev = {
+	.name = "pipe3-phy",
+	.id = -1,
+	.dev = {
+		.platform_data = {
+			.init_data = &init_data,
+		},
+	},
+};
+
+then, while doing phy_create, the PHY driver should pass this init_data
+	phy_create(dev, ops, pdata->init_data);
+
+and the controller driver (phy consumer) should pass the port name along with
+the device to get a reference to the PHY
+	phy_get(dev, "pcie");
+
+9. DeviceTree Binding
+
+The documentation for PHY dt binding can be found @
+Documentation/devicetree/bindings/phy/phy-bindings.txt
diff --git a/MAINTAINERS b/MAINTAINERS
index e61c2e83fc2b..e0e6ae2b65e8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3654,6 +3654,14 @@ S:	Maintained
 F:	include/asm-generic/
 F:	include/uapi/asm-generic/
 
+GENERIC PHY FRAMEWORK
+M:	Kishon Vijay Abraham I <kishon@ti.com>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git
+S:	Supported
+F:	drivers/phy/
+F:	include/linux/phy/
+
 GENERIC UIO DRIVER FOR PCI DEVICES
 M:	"Michael S. Tsirkin" <mst@redhat.com>
 L:	kvm@vger.kernel.org
diff --git a/drivers/Kconfig b/drivers/Kconfig
index aa43b911ccef..8f451449abd3 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -166,4 +166,6 @@ source "drivers/reset/Kconfig"
 
 source "drivers/fmc/Kconfig"
 
+source "drivers/phy/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index ab93de8297f1..687da899cadb 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -8,6 +8,8 @@
 obj-y				+= irqchip/
 obj-y				+= bus/
 
+obj-$(CONFIG_GENERIC_PHY)	+= phy/
+
 # GPIO must come after pinctrl as gpios may need to mux pins etc
 obj-y				+= pinctrl/
 obj-y				+= gpio/
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
new file mode 100644
index 000000000000..349bef2e6e4e
--- /dev/null
+++ b/drivers/phy/Kconfig
@@ -0,0 +1,18 @@
+#
+# PHY
+#
+
+menu "PHY Subsystem"
+
+config GENERIC_PHY
+	tristate "PHY Core"
+	help
+	  Generic PHY support.
+
+	  This framework is designed to provide a generic interface for PHY
+	  devices present in the kernel. This layer will have the generic
+	  API by which phy drivers can create PHY using the phy framework and
+	  phy users can obtain reference to the PHY. All the users of this
+	  framework should select this config.
+
+endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
new file mode 100644
index 000000000000..9e9560fbb14d
--- /dev/null
+++ b/drivers/phy/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the phy drivers.
+#
+
+obj-$(CONFIG_GENERIC_PHY)	+= phy-core.o
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
new file mode 100644
index 000000000000..03cf8fb81554
--- /dev/null
+++ b/drivers/phy/phy-core.c
@@ -0,0 +1,698 @@
+/*
+ * phy-core.c  --  Generic Phy framework.
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/phy/phy.h>
+#include <linux/idr.h>
+#include <linux/pm_runtime.h>
+
+static struct class *phy_class;
+static DEFINE_MUTEX(phy_provider_mutex);
+static LIST_HEAD(phy_provider_list);
+static DEFINE_IDA(phy_ida);
+
+static void devm_phy_release(struct device *dev, void *res)
+{
+	struct phy *phy = *(struct phy **)res;
+
+	phy_put(phy);
+}
+
+static void devm_phy_provider_release(struct device *dev, void *res)
+{
+	struct phy_provider *phy_provider = *(struct phy_provider **)res;
+
+	of_phy_provider_unregister(phy_provider);
+}
+
+static void devm_phy_consume(struct device *dev, void *res)
+{
+	struct phy *phy = *(struct phy **)res;
+
+	phy_destroy(phy);
+}
+
+static int devm_phy_match(struct device *dev, void *res, void *match_data)
+{
+	return res == match_data;
+}
+
+static struct phy *phy_lookup(struct device *device, const char *port)
+{
+	unsigned int count;
+	struct phy *phy;
+	struct device *dev;
+	struct phy_consumer *consumers;
+	struct class_dev_iter iter;
+
+	class_dev_iter_init(&iter, phy_class, NULL, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		phy = to_phy(dev);
+		count = phy->init_data->num_consumers;
+		consumers = phy->init_data->consumers;
+		while (count--) {
+			if (!strcmp(consumers->dev_name, dev_name(device)) &&
+					!strcmp(consumers->port, port)) {
+				class_dev_iter_exit(&iter);
+				return phy;
+			}
+			consumers++;
+		}
+	}
+
+	class_dev_iter_exit(&iter);
+	return ERR_PTR(-ENODEV);
+}
+
+static struct phy_provider *of_phy_provider_lookup(struct device_node *node)
+{
+	struct phy_provider *phy_provider;
+
+	list_for_each_entry(phy_provider, &phy_provider_list, list) {
+		if (phy_provider->dev->of_node == node)
+			return phy_provider;
+	}
+
+	return ERR_PTR(-EPROBE_DEFER);
+}
+
+int phy_pm_runtime_get(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return -ENOTSUPP;
+
+	return pm_runtime_get(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_get);
+
+int phy_pm_runtime_get_sync(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return -ENOTSUPP;
+
+	return pm_runtime_get_sync(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_get_sync);
+
+int phy_pm_runtime_put(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return -ENOTSUPP;
+
+	return pm_runtime_put(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_put);
+
+int phy_pm_runtime_put_sync(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return -ENOTSUPP;
+
+	return pm_runtime_put_sync(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_put_sync);
+
+void phy_pm_runtime_allow(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return;
+
+	pm_runtime_allow(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_allow);
+
+void phy_pm_runtime_forbid(struct phy *phy)
+{
+	if (!pm_runtime_enabled(&phy->dev))
+		return;
+
+	pm_runtime_forbid(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_pm_runtime_forbid);
+
+int phy_init(struct phy *phy)
+{
+	int ret;
+
+	ret = phy_pm_runtime_get_sync(phy);
+	if (ret < 0 && ret != -ENOTSUPP)
+		return ret;
+
+	mutex_lock(&phy->mutex);
+	if (phy->init_count++ == 0 && phy->ops->init) {
+		ret = phy->ops->init(phy);
+		if (ret < 0) {
+			dev_err(&phy->dev, "phy init failed --> %d\n", ret);
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&phy->mutex);
+	phy_pm_runtime_put(phy);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_init);
+
+int phy_exit(struct phy *phy)
+{
+	int ret;
+
+	ret = phy_pm_runtime_get_sync(phy);
+	if (ret < 0 && ret != -ENOTSUPP)
+		return ret;
+
+	mutex_lock(&phy->mutex);
+	if (--phy->init_count == 0 && phy->ops->exit) {
+		ret = phy->ops->exit(phy);
+		if (ret < 0) {
+			dev_err(&phy->dev, "phy exit failed --> %d\n", ret);
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&phy->mutex);
+	phy_pm_runtime_put(phy);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_exit);
+
+int phy_power_on(struct phy *phy)
+{
+	int ret = -ENOTSUPP;
+
+	ret = phy_pm_runtime_get_sync(phy);
+	if (ret < 0 && ret != -ENOTSUPP)
+		return ret;
+
+	mutex_lock(&phy->mutex);
+	if (phy->power_count++ == 0 && phy->ops->power_on) {
+		ret = phy->ops->power_on(phy);
+		if (ret < 0) {
+			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&phy->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_power_on);
+
+int phy_power_off(struct phy *phy)
+{
+	int ret = -ENOTSUPP;
+
+	mutex_lock(&phy->mutex);
+	if (--phy->power_count == 0 && phy->ops->power_off) {
+		ret =  phy->ops->power_off(phy);
+		if (ret < 0) {
+			dev_err(&phy->dev, "phy poweroff failed --> %d\n", ret);
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&phy->mutex);
+	phy_pm_runtime_put(phy);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_power_off);
+
+/**
+ * of_phy_get() - lookup and obtain a reference to a phy by phandle
+ * @dev: device that requests this phy
+ * @index: the index of the phy
+ *
+ * Returns the phy associated with the given phandle value,
+ * after getting a refcount to it or -ENODEV if there is no such phy or
+ * -EPROBE_DEFER if there is a phandle to the phy, but the device is
+ * not yet loaded. This function uses of_xlate call back function provided
+ * while registering the phy_provider to find the phy instance.
+ */
+static struct phy *of_phy_get(struct device *dev, int index)
+{
+	int ret;
+	struct phy_provider *phy_provider;
+	struct phy *phy = NULL;
+	struct of_phandle_args args;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "phys", "#phy-cells",
+		index, &args);
+	if (ret) {
+		dev_dbg(dev, "failed to get phy in %s node\n",
+			dev->of_node->full_name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	mutex_lock(&phy_provider_mutex);
+	phy_provider = of_phy_provider_lookup(args.np);
+	if (IS_ERR(phy_provider) || !try_module_get(phy_provider->owner)) {
+		phy = ERR_PTR(-EPROBE_DEFER);
+		goto err0;
+	}
+
+	phy = phy_provider->of_xlate(phy_provider->dev, &args);
+	module_put(phy_provider->owner);
+
+err0:
+	mutex_unlock(&phy_provider_mutex);
+	of_node_put(args.np);
+
+	return phy;
+}
+
+/**
+ * phy_put() - release the PHY
+ * @phy: the phy returned by phy_get()
+ *
+ * Releases a refcount the caller received from phy_get().
+ */
+void phy_put(struct phy *phy)
+{
+	if (IS_ERR(phy))
+		return;
+
+	module_put(phy->ops->owner);
+	put_device(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_put);
+
+/**
+ * devm_phy_put() - release the PHY
+ * @dev: device that wants to release this phy
+ * @phy: the phy returned by devm_phy_get()
+ *
+ * destroys the devres associated with this phy and invokes phy_put
+ * to release the phy.
+ */
+void devm_phy_put(struct device *dev, struct phy *phy)
+{
+	int r;
+
+	r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy);
+	dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n");
+}
+EXPORT_SYMBOL_GPL(devm_phy_put);
+
+/**
+ * of_phy_simple_xlate() - returns the phy instance from phy provider
+ * @dev: the PHY provider device
+ * @args: of_phandle_args (not used here)
+ *
+ * Intended to be used by phy provider for the common case where #phy-cells is
+ * 0. For other cases where #phy-cells is greater than '0', the phy provider
+ * should provide a custom of_xlate function that reads the *args* and returns
+ * the appropriate phy.
+ */
+struct phy *of_phy_simple_xlate(struct device *dev, struct of_phandle_args
+	*args)
+{
+	struct phy *phy;
+	struct class_dev_iter iter;
+	struct device_node *node = dev->of_node;
+
+	class_dev_iter_init(&iter, phy_class, NULL, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		phy = to_phy(dev);
+		if (node != phy->dev.of_node)
+			continue;
+
+		class_dev_iter_exit(&iter);
+		return phy;
+	}
+
+	class_dev_iter_exit(&iter);
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(of_phy_simple_xlate);
+
+/**
+ * phy_get() - lookup and obtain a reference to a phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or the name of the controller
+ * port for non-dt case
+ *
+ * Returns the phy driver, after getting a refcount to it; or
+ * -ENODEV if there is no such phy.  The caller is responsible for
+ * calling phy_put() to release that count.
+ */
+struct phy *phy_get(struct device *dev, const char *string)
+{
+	int index = 0;
+	struct phy *phy = NULL;
+
+	if (string == NULL) {
+		dev_WARN(dev, "missing string\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (dev->of_node) {
+		index = of_property_match_string(dev->of_node, "phy-names",
+			string);
+		phy = of_phy_get(dev, index);
+		if (IS_ERR(phy)) {
+			dev_err(dev, "unable to find phy\n");
+			return phy;
+		}
+	} else {
+		phy = phy_lookup(dev, string);
+		if (IS_ERR(phy)) {
+			dev_err(dev, "unable to find phy\n");
+			return phy;
+		}
+	}
+
+	if (!try_module_get(phy->ops->owner))
+		return ERR_PTR(-EPROBE_DEFER);
+
+	get_device(&phy->dev);
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(phy_get);
+
+/**
+ * devm_phy_get() - lookup and obtain a reference to a phy.
+ * @dev: device that requests this phy
+ * @string: the phy name as given in the dt data or phy device name
+ * for non-dt case
+ *
+ * Gets the phy using phy_get(), and associates a device with it using
+ * devres. On driver detach, release function is invoked on the devres data,
+ * then, devres data is freed.
+ */
+struct phy *devm_phy_get(struct device *dev, const char *string)
+{
+	struct phy **ptr, *phy;
+
+	ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	phy = phy_get(dev, string);
+	if (!IS_ERR(phy)) {
+		*ptr = phy;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(devm_phy_get);
+
+/**
+ * phy_create() - create a new phy
+ * @dev: device that is creating the new phy
+ * @ops: function pointers for performing phy operations
+ * @init_data: contains the list of PHY consumers or NULL
+ *
+ * Called to create a phy using phy framework.
+ */
+struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
+	struct phy_init_data *init_data)
+{
+	int ret;
+	int id;
+	struct phy *phy;
+
+	if (!dev) {
+		dev_WARN(dev, "no device provided for PHY\n");
+		ret = -EINVAL;
+		goto err0;
+	}
+
+	phy = kzalloc(sizeof(*phy), GFP_KERNEL);
+	if (!phy) {
+		ret = -ENOMEM;
+		goto err0;
+	}
+
+	id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL);
+	if (id < 0) {
+		dev_err(dev, "unable to get id\n");
+		ret = id;
+		goto err0;
+	}
+
+	device_initialize(&phy->dev);
+	mutex_init(&phy->mutex);
+
+	phy->dev.class = phy_class;
+	phy->dev.parent = dev;
+	phy->dev.of_node = dev->of_node;
+	phy->id = id;
+	phy->ops = ops;
+	phy->init_data = init_data;
+
+	ret = dev_set_name(&phy->dev, "phy-%s.%d", dev_name(dev), id);
+	if (ret)
+		goto err1;
+
+	ret = device_add(&phy->dev);
+	if (ret)
+		goto err1;
+
+	if (pm_runtime_enabled(dev)) {
+		pm_runtime_enable(&phy->dev);
+		pm_runtime_no_callbacks(&phy->dev);
+	}
+
+	return phy;
+
+err1:
+	ida_remove(&phy_ida, phy->id);
+	put_device(&phy->dev);
+	kfree(phy);
+
+err0:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(phy_create);
+
+/**
+ * devm_phy_create() - create a new phy
+ * @dev: device that is creating the new phy
+ * @ops: function pointers for performing phy operations
+ * @init_data: contains the list of PHY consumers or NULL
+ *
+ * Creates a new PHY device adding it to the PHY class.
+ * While at that, it also associates the device with the phy using devres.
+ * On driver detach, release function is invoked on the devres data,
+ * then, devres data is freed.
+ */
+struct phy *devm_phy_create(struct device *dev, const struct phy_ops *ops,
+	struct phy_init_data *init_data)
+{
+	struct phy **ptr, *phy;
+
+	ptr = devres_alloc(devm_phy_consume, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	phy = phy_create(dev, ops, init_data);
+	if (!IS_ERR(phy)) {
+		*ptr = phy;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(devm_phy_create);
+
+/**
+ * phy_destroy() - destroy the phy
+ * @phy: the phy to be destroyed
+ *
+ * Called to destroy the phy.
+ */
+void phy_destroy(struct phy *phy)
+{
+	pm_runtime_disable(&phy->dev);
+	device_unregister(&phy->dev);
+}
+EXPORT_SYMBOL_GPL(phy_destroy);
+
+/**
+ * devm_phy_destroy() - destroy the PHY
+ * @dev: device that wants to release this phy
+ * @phy: the phy returned by devm_phy_get()
+ *
+ * destroys the devres associated with this phy and invokes phy_destroy
+ * to destroy the phy.
+ */
+void devm_phy_destroy(struct device *dev, struct phy *phy)
+{
+	int r;
+
+	r = devres_destroy(dev, devm_phy_consume, devm_phy_match, phy);
+	dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n");
+}
+EXPORT_SYMBOL_GPL(devm_phy_destroy);
+
+/**
+ * __of_phy_provider_register() - create/register phy provider with the framework
+ * @dev: struct device of the phy provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain phy instance from phy provider
+ *
+ * Creates struct phy_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the phy instance from
+ * phy provider.
+ */
+struct phy_provider *__of_phy_provider_register(struct device *dev,
+	struct module *owner, struct phy * (*of_xlate)(struct device *dev,
+	struct of_phandle_args *args))
+{
+	struct phy_provider *phy_provider;
+
+	phy_provider = kzalloc(sizeof(*phy_provider), GFP_KERNEL);
+	if (!phy_provider)
+		return ERR_PTR(-ENOMEM);
+
+	phy_provider->dev = dev;
+	phy_provider->owner = owner;
+	phy_provider->of_xlate = of_xlate;
+
+	mutex_lock(&phy_provider_mutex);
+	list_add_tail(&phy_provider->list, &phy_provider_list);
+	mutex_unlock(&phy_provider_mutex);
+
+	return phy_provider;
+}
+EXPORT_SYMBOL_GPL(__of_phy_provider_register);
+
+/**
+ * __devm_of_phy_provider_register() - create/register phy provider with the
+ * framework
+ * @dev: struct device of the phy provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain phy instance from phy provider
+ *
+ * Creates struct phy_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the phy instance from
+ * phy provider. While at that, it also associates the device with the
+ * phy provider using devres. On driver detach, release function is invoked
+ * on the devres data, then, devres data is freed.
+ */
+struct phy_provider *__devm_of_phy_provider_register(struct device *dev,
+	struct module *owner, struct phy * (*of_xlate)(struct device *dev,
+	struct of_phandle_args *args))
+{
+	struct phy_provider **ptr, *phy_provider;
+
+	ptr = devres_alloc(devm_phy_provider_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	phy_provider = __of_phy_provider_register(dev, owner, of_xlate);
+	if (!IS_ERR(phy_provider)) {
+		*ptr = phy_provider;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return phy_provider;
+}
+EXPORT_SYMBOL_GPL(__devm_of_phy_provider_register);
+
+/**
+ * of_phy_provider_unregister() - unregister phy provider from the framework
+ * @phy_provider: phy provider returned by of_phy_provider_register()
+ *
+ * Removes the phy_provider created using of_phy_provider_register().
+ */
+void of_phy_provider_unregister(struct phy_provider *phy_provider)
+{
+	if (IS_ERR(phy_provider))
+		return;
+
+	mutex_lock(&phy_provider_mutex);
+	list_del(&phy_provider->list);
+	kfree(phy_provider);
+	mutex_unlock(&phy_provider_mutex);
+}
+EXPORT_SYMBOL_GPL(of_phy_provider_unregister);
+
+/**
+ * devm_of_phy_provider_unregister() - remove phy provider from the framework
+ * @dev: struct device of the phy provider
+ *
+ * destroys the devres associated with this phy provider and invokes
+ * of_phy_provider_unregister to unregister the phy provider.
+ */
+void devm_of_phy_provider_unregister(struct device *dev,
+	struct phy_provider *phy_provider) {
+	int r;
+
+	r = devres_destroy(dev, devm_phy_provider_release, devm_phy_match,
+		phy_provider);
+	dev_WARN_ONCE(dev, r, "couldn't find PHY provider device resource\n");
+}
+EXPORT_SYMBOL_GPL(devm_of_phy_provider_unregister);
+
+/**
+ * phy_release() - release the phy
+ * @dev: the dev member within phy
+ *
+ * When the last reference to the device is removed, it is called
+ * from the embedded kobject as release method.
+ */
+static void phy_release(struct device *dev)
+{
+	struct phy *phy;
+
+	phy = to_phy(dev);
+	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
+	ida_remove(&phy_ida, phy->id);
+	kfree(phy);
+}
+
+static int __init phy_core_init(void)
+{
+	phy_class = class_create(THIS_MODULE, "phy");
+	if (IS_ERR(phy_class)) {
+		pr_err("failed to create phy class --> %ld\n",
+			PTR_ERR(phy_class));
+		return PTR_ERR(phy_class);
+	}
+
+	phy_class->dev_release = phy_release;
+
+	return 0;
+}
+module_init(phy_core_init);
+
+static void __exit phy_core_exit(void)
+{
+	class_destroy(phy_class);
+}
+module_exit(phy_core_exit);
+
+MODULE_DESCRIPTION("Generic PHY Framework");
+MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
new file mode 100644
index 000000000000..6d722695e027
--- /dev/null
+++ b/include/linux/phy/phy.h
@@ -0,0 +1,270 @@
+/*
+ * phy.h -- generic phy header file
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * Author: Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DRIVERS_PHY_H
+#define __DRIVERS_PHY_H
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/pm_runtime.h>
+
+struct phy;
+
+/**
+ * struct phy_ops - set of function pointers for performing phy operations
+ * @init: operation to be performed for initializing phy
+ * @exit: operation to be performed while exiting
+ * @power_on: powering on the phy
+ * @power_off: powering off the phy
+ * @owner: the module owner containing the ops
+ */
+struct phy_ops {
+	int	(*init)(struct phy *phy);
+	int	(*exit)(struct phy *phy);
+	int	(*power_on)(struct phy *phy);
+	int	(*power_off)(struct phy *phy);
+	struct module *owner;
+};
+
+/**
+ * struct phy - represents the phy device
+ * @dev: phy device
+ * @id: id of the phy device
+ * @ops: function pointers for performing phy operations
+ * @init_data: list of PHY consumers (non-dt only)
+ * @mutex: mutex to protect phy_ops
+ * @init_count: used to protect when the PHY is used by multiple consumers
+ * @power_count: used to protect when the PHY is used by multiple consumers
+ */
+struct phy {
+	struct device		dev;
+	int			id;
+	const struct phy_ops	*ops;
+	struct phy_init_data	*init_data;
+	struct mutex		mutex;
+	int			init_count;
+	int			power_count;
+};
+
+/**
+ * struct phy_provider - represents the phy provider
+ * @dev: phy provider device
+ * @owner: the module owner having of_xlate
+ * @of_xlate: function pointer to obtain phy instance from phy pointer
+ * @list: to maintain a linked list of PHY providers
+ */
+struct phy_provider {
+	struct device		*dev;
+	struct module		*owner;
+	struct list_head	list;
+	struct phy * (*of_xlate)(struct device *dev,
+		struct of_phandle_args *args);
+};
+
+/**
+ * struct phy_consumer - represents the phy consumer
+ * @dev_name: the device name of the controller that will use this PHY device
+ * @port: name given to the consumer port
+ */
+struct phy_consumer {
+	const char *dev_name;
+	const char *port;
+};
+
+/**
+ * struct phy_init_data - contains the list of PHY consumers
+ * @num_consumers: number of consumers for this PHY device
+ * @consumers: list of PHY consumers
+ */
+struct phy_init_data {
+	unsigned int num_consumers;
+	struct phy_consumer *consumers;
+};
+
+#define PHY_CONSUMER(_dev_name, _port)				\
+{								\
+	.dev_name	= _dev_name,				\
+	.port		= _port,				\
+}
+
+#define	to_phy(dev)	(container_of((dev), struct phy, dev))
+
+#define	of_phy_provider_register(dev, xlate)	\
+	__of_phy_provider_register((dev), THIS_MODULE, (xlate))
+
+#define	devm_of_phy_provider_register(dev, xlate)	\
+	__devm_of_phy_provider_register((dev), THIS_MODULE, (xlate))
+
+static inline void phy_set_drvdata(struct phy *phy, void *data)
+{
+	dev_set_drvdata(&phy->dev, data);
+}
+
+static inline void *phy_get_drvdata(struct phy *phy)
+{
+	return dev_get_drvdata(&phy->dev);
+}
+
+#if IS_ENABLED(CONFIG_GENERIC_PHY)
+int phy_pm_runtime_get(struct phy *phy);
+int phy_pm_runtime_get_sync(struct phy *phy);
+int phy_pm_runtime_put(struct phy *phy);
+int phy_pm_runtime_put_sync(struct phy *phy);
+void phy_pm_runtime_allow(struct phy *phy);
+void phy_pm_runtime_forbid(struct phy *phy);
+int phy_init(struct phy *phy);
+int phy_exit(struct phy *phy);
+int phy_power_on(struct phy *phy);
+int phy_power_off(struct phy *phy);
+struct phy *phy_get(struct device *dev, const char *string);
+struct phy *devm_phy_get(struct device *dev, const char *string);
+void phy_put(struct phy *phy);
+void devm_phy_put(struct device *dev, struct phy *phy);
+struct phy *of_phy_simple_xlate(struct device *dev,
+	struct of_phandle_args *args);
+struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
+	struct phy_init_data *init_data);
+struct phy *devm_phy_create(struct device *dev,
+	const struct phy_ops *ops, struct phy_init_data *init_data);
+void phy_destroy(struct phy *phy);
+void devm_phy_destroy(struct device *dev, struct phy *phy);
+struct phy_provider *__of_phy_provider_register(struct device *dev,
+	struct module *owner, struct phy * (*of_xlate)(struct device *dev,
+	struct of_phandle_args *args));
+struct phy_provider *__devm_of_phy_provider_register(struct device *dev,
+	struct module *owner, struct phy * (*of_xlate)(struct device *dev,
+	struct of_phandle_args *args));
+void of_phy_provider_unregister(struct phy_provider *phy_provider);
+void devm_of_phy_provider_unregister(struct device *dev,
+	struct phy_provider *phy_provider);
+#else
+static inline int phy_pm_runtime_get(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_pm_runtime_get_sync(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_pm_runtime_put(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_pm_runtime_put_sync(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline void phy_pm_runtime_allow(struct phy *phy)
+{
+	return;
+}
+
+static inline void phy_pm_runtime_forbid(struct phy *phy)
+{
+	return;
+}
+
+static inline int phy_init(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_exit(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_power_on(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline int phy_power_off(struct phy *phy)
+{
+	return -ENOSYS;
+}
+
+static inline struct phy *phy_get(struct device *dev, const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct phy *devm_phy_get(struct device *dev, const char *string)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void phy_put(struct phy *phy)
+{
+}
+
+static inline void devm_phy_put(struct device *dev, struct phy *phy)
+{
+}
+
+static inline struct phy *of_phy_simple_xlate(struct device *dev,
+	struct of_phandle_args *args)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct phy *phy_create(struct device *dev,
+	const struct phy_ops *ops, struct phy_init_data *init_data)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct phy *devm_phy_create(struct device *dev,
+	const struct phy_ops *ops, struct phy_init_data *init_data)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void phy_destroy(struct phy *phy)
+{
+}
+
+static inline void devm_phy_destroy(struct device *dev, struct phy *phy)
+{
+}
+
+static inline struct phy_provider *__of_phy_provider_register(
+	struct device *dev, struct module *owner, struct phy * (*of_xlate)(
+	struct device *dev, struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct phy_provider *__devm_of_phy_provider_register(struct device
+	*dev, struct module *owner, struct phy * (*of_xlate)(struct device *dev,
+	struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void of_phy_provider_unregister(struct phy_provider *phy_provider)
+{
+}
+
+static inline void devm_of_phy_provider_unregister(struct device *dev,
+	struct phy_provider *phy_provider)
+{
+}
+#endif
+
+#endif /* __DRIVERS_PHY_H */
-- 
cgit 


From 6747caa76cab1150c60a772cf64f8cd47fa19d39 Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Fri, 27 Sep 2013 11:53:27 +0530
Subject: usb: phy: twl4030: use the new generic PHY framework

Used the generic PHY framework API to create the PHY. For powering on
and powering off the PHY, power_on and power_off ops are used. Once the
MUSB OMAP glue is adapted to the new framework, the suspend and resume
ops of usb phy library will be removed. Also twl4030-usb driver is moved
to drivers/phy/.

However using the old usb phy library cannot be completely removed
because otg is intertwined with phy and moving to the new
framework completely will break otg. Once we have a separate otg state machine,
we can get rid of the usb phy library.

Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Acked-by: Felipe Balbi <balbi@ti.com>
Reviewed-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/phy/Kconfig               |  11 +
 drivers/phy/Makefile              |   1 +
 drivers/phy/phy-twl4030-usb.c     | 844 ++++++++++++++++++++++++++++++++++++++
 drivers/usb/phy/Kconfig           |  10 -
 drivers/usb/phy/Makefile          |   1 -
 drivers/usb/phy/phy-twl4030-usb.c | 794 -----------------------------------
 include/linux/i2c/twl.h           |   2 +
 7 files changed, 858 insertions(+), 805 deletions(-)
 create mode 100644 drivers/phy/phy-twl4030-usb.c
 delete mode 100644 drivers/usb/phy/phy-twl4030-usb.c

(limited to 'include')

diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 38c3477ead4c..ac239aca77ec 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -27,4 +27,15 @@ config OMAP_USB2
 	  The USB OTG controller communicates with the comparator using this
 	  driver.
 
+config TWL4030_USB
+	tristate "TWL4030 USB Transceiver Driver"
+	depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS
+	select GENERIC_PHY
+	select USB_PHY
+	help
+	  Enable this to support the USB OTG transceiver on TWL4030
+	  family chips (including the TWL5030 and TPS659x0 devices).
+	  This transceiver supports high and full speed devices plus,
+	  in host mode, low speed.
+
 endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index ed5b088abaee..0dd8a9834548 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -4,3 +4,4 @@
 
 obj-$(CONFIG_GENERIC_PHY)	+= phy-core.o
 obj-$(CONFIG_OMAP_USB2)		+= phy-omap-usb2.o
+obj-$(CONFIG_TWL4030_USB)	+= phy-twl4030-usb.o
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
new file mode 100644
index 000000000000..d02913f9a6b1
--- /dev/null
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -0,0 +1,844 @@
+/*
+ * twl4030_usb - TWL4030 USB transceiver, talking to OMAP OTG controller
+ *
+ * Copyright (C) 2004-2007 Texas Instruments
+ * Copyright (C) 2008 Nokia Corporation
+ * Contact: Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Current status:
+ *	- HS USB ULPI mode works.
+ *	- 3-pin mode support may be added in future.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/usb/otg.h>
+#include <linux/phy/phy.h>
+#include <linux/usb/musb-omap.h>
+#include <linux/usb/ulpi.h>
+#include <linux/i2c/twl.h>
+#include <linux/regulator/consumer.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+/* Register defines */
+
+#define MCPC_CTRL			0x30
+#define MCPC_CTRL_RTSOL			(1 << 7)
+#define MCPC_CTRL_EXTSWR		(1 << 6)
+#define MCPC_CTRL_EXTSWC		(1 << 5)
+#define MCPC_CTRL_VOICESW		(1 << 4)
+#define MCPC_CTRL_OUT64K		(1 << 3)
+#define MCPC_CTRL_RTSCTSSW		(1 << 2)
+#define MCPC_CTRL_HS_UART		(1 << 0)
+
+#define MCPC_IO_CTRL			0x33
+#define MCPC_IO_CTRL_MICBIASEN		(1 << 5)
+#define MCPC_IO_CTRL_CTS_NPU		(1 << 4)
+#define MCPC_IO_CTRL_RXD_PU		(1 << 3)
+#define MCPC_IO_CTRL_TXDTYP		(1 << 2)
+#define MCPC_IO_CTRL_CTSTYP		(1 << 1)
+#define MCPC_IO_CTRL_RTSTYP		(1 << 0)
+
+#define MCPC_CTRL2			0x36
+#define MCPC_CTRL2_MCPC_CK_EN		(1 << 0)
+
+#define OTHER_FUNC_CTRL			0x80
+#define OTHER_FUNC_CTRL_BDIS_ACON_EN	(1 << 4)
+#define OTHER_FUNC_CTRL_FIVEWIRE_MODE	(1 << 2)
+
+#define OTHER_IFC_CTRL			0x83
+#define OTHER_IFC_CTRL_OE_INT_EN	(1 << 6)
+#define OTHER_IFC_CTRL_CEA2011_MODE	(1 << 5)
+#define OTHER_IFC_CTRL_FSLSSERIALMODE_4PIN	(1 << 4)
+#define OTHER_IFC_CTRL_HIZ_ULPI_60MHZ_OUT	(1 << 3)
+#define OTHER_IFC_CTRL_HIZ_ULPI		(1 << 2)
+#define OTHER_IFC_CTRL_ALT_INT_REROUTE	(1 << 0)
+
+#define OTHER_INT_EN_RISE		0x86
+#define OTHER_INT_EN_FALL		0x89
+#define OTHER_INT_STS			0x8C
+#define OTHER_INT_LATCH			0x8D
+#define OTHER_INT_VB_SESS_VLD		(1 << 7)
+#define OTHER_INT_DM_HI			(1 << 6) /* not valid for "latch" reg */
+#define OTHER_INT_DP_HI			(1 << 5) /* not valid for "latch" reg */
+#define OTHER_INT_BDIS_ACON		(1 << 3) /* not valid for "fall" regs */
+#define OTHER_INT_MANU			(1 << 1)
+#define OTHER_INT_ABNORMAL_STRESS	(1 << 0)
+
+#define ID_STATUS			0x96
+#define ID_RES_FLOAT			(1 << 4)
+#define ID_RES_440K			(1 << 3)
+#define ID_RES_200K			(1 << 2)
+#define ID_RES_102K			(1 << 1)
+#define ID_RES_GND			(1 << 0)
+
+#define POWER_CTRL			0xAC
+#define POWER_CTRL_OTG_ENAB		(1 << 5)
+
+#define OTHER_IFC_CTRL2			0xAF
+#define OTHER_IFC_CTRL2_ULPI_STP_LOW	(1 << 4)
+#define OTHER_IFC_CTRL2_ULPI_TXEN_POL	(1 << 3)
+#define OTHER_IFC_CTRL2_ULPI_4PIN_2430	(1 << 2)
+#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_MASK	(3 << 0) /* bits 0 and 1 */
+#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_INT1N	(0 << 0)
+#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_INT2N	(1 << 0)
+
+#define REG_CTRL_EN			0xB2
+#define REG_CTRL_ERROR			0xB5
+#define ULPI_I2C_CONFLICT_INTEN		(1 << 0)
+
+#define OTHER_FUNC_CTRL2		0xB8
+#define OTHER_FUNC_CTRL2_VBAT_TIMER_EN	(1 << 0)
+
+/* following registers do not have separate _clr and _set registers */
+#define VBUS_DEBOUNCE			0xC0
+#define ID_DEBOUNCE			0xC1
+#define VBAT_TIMER			0xD3
+#define PHY_PWR_CTRL			0xFD
+#define PHY_PWR_PHYPWD			(1 << 0)
+#define PHY_CLK_CTRL			0xFE
+#define PHY_CLK_CTRL_CLOCKGATING_EN	(1 << 2)
+#define PHY_CLK_CTRL_CLK32K_EN		(1 << 1)
+#define REQ_PHY_DPLL_CLK		(1 << 0)
+#define PHY_CLK_CTRL_STS		0xFF
+#define PHY_DPLL_CLK			(1 << 0)
+
+/* In module TWL_MODULE_PM_MASTER */
+#define STS_HW_CONDITIONS		0x0F
+
+/* In module TWL_MODULE_PM_RECEIVER */
+#define VUSB_DEDICATED1			0x7D
+#define VUSB_DEDICATED2			0x7E
+#define VUSB1V5_DEV_GRP			0x71
+#define VUSB1V5_TYPE			0x72
+#define VUSB1V5_REMAP			0x73
+#define VUSB1V8_DEV_GRP			0x74
+#define VUSB1V8_TYPE			0x75
+#define VUSB1V8_REMAP			0x76
+#define VUSB3V1_DEV_GRP			0x77
+#define VUSB3V1_TYPE			0x78
+#define VUSB3V1_REMAP			0x79
+
+/* In module TWL4030_MODULE_INTBR */
+#define PMBR1				0x0D
+#define GPIO_USB_4PIN_ULPI_2430C	(3 << 0)
+
+struct twl4030_usb {
+	struct usb_phy		phy;
+	struct device		*dev;
+
+	/* TWL4030 internal USB regulator supplies */
+	struct regulator	*usb1v5;
+	struct regulator	*usb1v8;
+	struct regulator	*usb3v1;
+
+	/* for vbus reporting with irqs disabled */
+	spinlock_t		lock;
+
+	/* pin configuration */
+	enum twl4030_usb_mode	usb_mode;
+
+	int			irq;
+	enum omap_musb_vbus_id_status linkstat;
+	bool			vbus_supplied;
+	u8			asleep;
+	bool			irq_enabled;
+
+	struct delayed_work	id_workaround_work;
+};
+
+/* internal define on top of container_of */
+#define phy_to_twl(x)		container_of((x), struct twl4030_usb, phy)
+
+/*-------------------------------------------------------------------------*/
+
+static int twl4030_i2c_write_u8_verify(struct twl4030_usb *twl,
+		u8 module, u8 data, u8 address)
+{
+	u8 check;
+
+	if ((twl_i2c_write_u8(module, data, address) >= 0) &&
+	    (twl_i2c_read_u8(module, &check, address) >= 0) &&
+						(check == data))
+		return 0;
+	dev_dbg(twl->dev, "Write%d[%d,0x%x] wrote %02x but read %02x\n",
+			1, module, address, check, data);
+
+	/* Failed once: Try again */
+	if ((twl_i2c_write_u8(module, data, address) >= 0) &&
+	    (twl_i2c_read_u8(module, &check, address) >= 0) &&
+						(check == data))
+		return 0;
+	dev_dbg(twl->dev, "Write%d[%d,0x%x] wrote %02x but read %02x\n",
+			2, module, address, check, data);
+
+	/* Failed again: Return error */
+	return -EBUSY;
+}
+
+#define twl4030_usb_write_verify(twl, address, data)	\
+	twl4030_i2c_write_u8_verify(twl, TWL_MODULE_USB, (data), (address))
+
+static inline int twl4030_usb_write(struct twl4030_usb *twl,
+		u8 address, u8 data)
+{
+	int ret = 0;
+
+	ret = twl_i2c_write_u8(TWL_MODULE_USB, data, address);
+	if (ret < 0)
+		dev_dbg(twl->dev,
+			"TWL4030:USB:Write[0x%x] Error %d\n", address, ret);
+	return ret;
+}
+
+static inline int twl4030_readb(struct twl4030_usb *twl, u8 module, u8 address)
+{
+	u8 data;
+	int ret = 0;
+
+	ret = twl_i2c_read_u8(module, &data, address);
+	if (ret >= 0)
+		ret = data;
+	else
+		dev_dbg(twl->dev,
+			"TWL4030:readb[0x%x,0x%x] Error %d\n",
+					module, address, ret);
+
+	return ret;
+}
+
+static inline int twl4030_usb_read(struct twl4030_usb *twl, u8 address)
+{
+	return twl4030_readb(twl, TWL_MODULE_USB, address);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static inline int
+twl4030_usb_set_bits(struct twl4030_usb *twl, u8 reg, u8 bits)
+{
+	return twl4030_usb_write(twl, ULPI_SET(reg), bits);
+}
+
+static inline int
+twl4030_usb_clear_bits(struct twl4030_usb *twl, u8 reg, u8 bits)
+{
+	return twl4030_usb_write(twl, ULPI_CLR(reg), bits);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static bool twl4030_is_driving_vbus(struct twl4030_usb *twl)
+{
+	int ret;
+
+	ret = twl4030_usb_read(twl, PHY_CLK_CTRL_STS);
+	if (ret < 0 || !(ret & PHY_DPLL_CLK))
+		/*
+		 * if clocks are off, registers are not updated,
+		 * but we can assume we don't drive VBUS in this case
+		 */
+		return false;
+
+	ret = twl4030_usb_read(twl, ULPI_OTG_CTRL);
+	if (ret < 0)
+		return false;
+
+	return (ret & (ULPI_OTG_DRVVBUS | ULPI_OTG_CHRGVBUS)) ? true : false;
+}
+
+static enum omap_musb_vbus_id_status
+	twl4030_usb_linkstat(struct twl4030_usb *twl)
+{
+	int	status;
+	enum omap_musb_vbus_id_status linkstat = OMAP_MUSB_UNKNOWN;
+
+	twl->vbus_supplied = false;
+
+	/*
+	 * For ID/VBUS sensing, see manual section 15.4.8 ...
+	 * except when using only battery backup power, two
+	 * comparators produce VBUS_PRES and ID_PRES signals,
+	 * which don't match docs elsewhere.  But ... BIT(7)
+	 * and BIT(2) of STS_HW_CONDITIONS, respectively, do
+	 * seem to match up.  If either is true the USB_PRES
+	 * signal is active, the OTG module is activated, and
+	 * its interrupt may be raised (may wake the system).
+	 */
+	status = twl4030_readb(twl, TWL_MODULE_PM_MASTER, STS_HW_CONDITIONS);
+	if (status < 0)
+		dev_err(twl->dev, "USB link status err %d\n", status);
+	else if (status & (BIT(7) | BIT(2))) {
+		if (status & BIT(7)) {
+			if (twl4030_is_driving_vbus(twl))
+				status &= ~BIT(7);
+			else
+				twl->vbus_supplied = true;
+		}
+
+		if (status & BIT(2))
+			linkstat = OMAP_MUSB_ID_GROUND;
+		else if (status & BIT(7))
+			linkstat = OMAP_MUSB_VBUS_VALID;
+		else
+			linkstat = OMAP_MUSB_VBUS_OFF;
+	} else {
+		if (twl->linkstat != OMAP_MUSB_UNKNOWN)
+			linkstat = OMAP_MUSB_VBUS_OFF;
+	}
+
+	dev_dbg(twl->dev, "HW_CONDITIONS 0x%02x/%d; link %d\n",
+			status, status, linkstat);
+
+	/* REVISIT this assumes host and peripheral controllers
+	 * are registered, and that both are active...
+	 */
+
+	return linkstat;
+}
+
+static void twl4030_usb_set_mode(struct twl4030_usb *twl, int mode)
+{
+	twl->usb_mode = mode;
+
+	switch (mode) {
+	case T2_USB_MODE_ULPI:
+		twl4030_usb_clear_bits(twl, ULPI_IFC_CTRL,
+					ULPI_IFC_CTRL_CARKITMODE);
+		twl4030_usb_set_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
+		twl4030_usb_clear_bits(twl, ULPI_FUNC_CTRL,
+					ULPI_FUNC_CTRL_XCVRSEL_MASK |
+					ULPI_FUNC_CTRL_OPMODE_MASK);
+		break;
+	case -1:
+		/* FIXME: power on defaults */
+		break;
+	default:
+		dev_err(twl->dev, "unsupported T2 transceiver mode %d\n",
+				mode);
+		break;
+	};
+}
+
+static void twl4030_i2c_access(struct twl4030_usb *twl, int on)
+{
+	unsigned long timeout;
+	int val = twl4030_usb_read(twl, PHY_CLK_CTRL);
+
+	if (val >= 0) {
+		if (on) {
+			/* enable DPLL to access PHY registers over I2C */
+			val |= REQ_PHY_DPLL_CLK;
+			WARN_ON(twl4030_usb_write_verify(twl, PHY_CLK_CTRL,
+						(u8)val) < 0);
+
+			timeout = jiffies + HZ;
+			while (!(twl4030_usb_read(twl, PHY_CLK_CTRL_STS) &
+							PHY_DPLL_CLK)
+				&& time_before(jiffies, timeout))
+					udelay(10);
+			if (!(twl4030_usb_read(twl, PHY_CLK_CTRL_STS) &
+							PHY_DPLL_CLK))
+				dev_err(twl->dev, "Timeout setting T2 HSUSB "
+						"PHY DPLL clock\n");
+		} else {
+			/* let ULPI control the DPLL clock */
+			val &= ~REQ_PHY_DPLL_CLK;
+			WARN_ON(twl4030_usb_write_verify(twl, PHY_CLK_CTRL,
+						(u8)val) < 0);
+		}
+	}
+}
+
+static void __twl4030_phy_power(struct twl4030_usb *twl, int on)
+{
+	u8 pwr = twl4030_usb_read(twl, PHY_PWR_CTRL);
+
+	if (on)
+		pwr &= ~PHY_PWR_PHYPWD;
+	else
+		pwr |= PHY_PWR_PHYPWD;
+
+	WARN_ON(twl4030_usb_write_verify(twl, PHY_PWR_CTRL, pwr) < 0);
+}
+
+static void twl4030_phy_power(struct twl4030_usb *twl, int on)
+{
+	int ret;
+
+	if (on) {
+		ret = regulator_enable(twl->usb3v1);
+		if (ret)
+			dev_err(twl->dev, "Failed to enable usb3v1\n");
+
+		ret = regulator_enable(twl->usb1v8);
+		if (ret)
+			dev_err(twl->dev, "Failed to enable usb1v8\n");
+
+		/*
+		 * Disabling usb3v1 regulator (= writing 0 to VUSB3V1_DEV_GRP
+		 * in twl4030) resets the VUSB_DEDICATED2 register. This reset
+		 * enables VUSB3V1_SLEEP bit that remaps usb3v1 ACTIVE state to
+		 * SLEEP. We work around this by clearing the bit after usv3v1
+		 * is re-activated. This ensures that VUSB3V1 is really active.
+		 */
+		twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);
+
+		ret = regulator_enable(twl->usb1v5);
+		if (ret)
+			dev_err(twl->dev, "Failed to enable usb1v5\n");
+
+		__twl4030_phy_power(twl, 1);
+		twl4030_usb_write(twl, PHY_CLK_CTRL,
+				  twl4030_usb_read(twl, PHY_CLK_CTRL) |
+					(PHY_CLK_CTRL_CLOCKGATING_EN |
+						PHY_CLK_CTRL_CLK32K_EN));
+	} else {
+		__twl4030_phy_power(twl, 0);
+		regulator_disable(twl->usb1v5);
+		regulator_disable(twl->usb1v8);
+		regulator_disable(twl->usb3v1);
+	}
+}
+
+static void twl4030_phy_suspend(struct twl4030_usb *twl, int controller_off)
+{
+	if (twl->asleep)
+		return;
+
+	twl4030_phy_power(twl, 0);
+	twl->asleep = 1;
+	dev_dbg(twl->dev, "%s\n", __func__);
+}
+
+static int twl4030_phy_power_off(struct phy *phy)
+{
+	struct twl4030_usb *twl = phy_get_drvdata(phy);
+
+	twl4030_phy_suspend(twl, 0);
+	return 0;
+}
+
+static void __twl4030_phy_resume(struct twl4030_usb *twl)
+{
+	twl4030_phy_power(twl, 1);
+	twl4030_i2c_access(twl, 1);
+	twl4030_usb_set_mode(twl, twl->usb_mode);
+	if (twl->usb_mode == T2_USB_MODE_ULPI)
+		twl4030_i2c_access(twl, 0);
+}
+
+static void twl4030_phy_resume(struct twl4030_usb *twl)
+{
+	if (!twl->asleep)
+		return;
+	__twl4030_phy_resume(twl);
+	twl->asleep = 0;
+	dev_dbg(twl->dev, "%s\n", __func__);
+
+	/*
+	 * XXX When VBUS gets driven after musb goes to A mode,
+	 * ID_PRES related interrupts no longer arrive, why?
+	 * Register itself is updated fine though, so we must poll.
+	 */
+	if (twl->linkstat == OMAP_MUSB_ID_GROUND) {
+		cancel_delayed_work(&twl->id_workaround_work);
+		schedule_delayed_work(&twl->id_workaround_work, HZ);
+	}
+}
+
+static int twl4030_phy_power_on(struct phy *phy)
+{
+	struct twl4030_usb *twl = phy_get_drvdata(phy);
+
+	twl4030_phy_resume(twl);
+	return 0;
+}
+
+static int twl4030_usb_ldo_init(struct twl4030_usb *twl)
+{
+	/* Enable writing to power configuration registers */
+	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, TWL4030_PM_MASTER_KEY_CFG1,
+			 TWL4030_PM_MASTER_PROTECT_KEY);
+
+	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, TWL4030_PM_MASTER_KEY_CFG2,
+			 TWL4030_PM_MASTER_PROTECT_KEY);
+
+	/* Keep VUSB3V1 LDO in sleep state until VBUS/ID change detected*/
+	/*twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);*/
+
+	/* input to VUSB3V1 LDO is from VBAT, not VBUS */
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0x14, VUSB_DEDICATED1);
+
+	/* Initialize 3.1V regulator */
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB3V1_DEV_GRP);
+
+	twl->usb3v1 = devm_regulator_get(twl->dev, "usb3v1");
+	if (IS_ERR(twl->usb3v1))
+		return -ENODEV;
+
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB3V1_TYPE);
+
+	/* Initialize 1.5V regulator */
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V5_DEV_GRP);
+
+	twl->usb1v5 = devm_regulator_get(twl->dev, "usb1v5");
+	if (IS_ERR(twl->usb1v5))
+		return -ENODEV;
+
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V5_TYPE);
+
+	/* Initialize 1.8V regulator */
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V8_DEV_GRP);
+
+	twl->usb1v8 = devm_regulator_get(twl->dev, "usb1v8");
+	if (IS_ERR(twl->usb1v8))
+		return -ENODEV;
+
+	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V8_TYPE);
+
+	/* disable access to power configuration registers */
+	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, 0,
+			 TWL4030_PM_MASTER_PROTECT_KEY);
+
+	return 0;
+}
+
+static ssize_t twl4030_usb_vbus_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct twl4030_usb *twl = dev_get_drvdata(dev);
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&twl->lock, flags);
+	ret = sprintf(buf, "%s\n",
+			twl->vbus_supplied ? "on" : "off");
+	spin_unlock_irqrestore(&twl->lock, flags);
+
+	return ret;
+}
+static DEVICE_ATTR(vbus, 0444, twl4030_usb_vbus_show, NULL);
+
+static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
+{
+	struct twl4030_usb *twl = _twl;
+	enum omap_musb_vbus_id_status status;
+	bool status_changed = false;
+
+	status = twl4030_usb_linkstat(twl);
+
+	spin_lock_irq(&twl->lock);
+	if (status >= 0 && status != twl->linkstat) {
+		twl->linkstat = status;
+		status_changed = true;
+	}
+	spin_unlock_irq(&twl->lock);
+
+	if (status_changed) {
+		/* FIXME add a set_power() method so that B-devices can
+		 * configure the charger appropriately.  It's not always
+		 * correct to consume VBUS power, and how much current to
+		 * consume is a function of the USB configuration chosen
+		 * by the host.
+		 *
+		 * REVISIT usb_gadget_vbus_connect(...) as needed, ditto
+		 * its disconnect() sibling, when changing to/from the
+		 * USB_LINK_VBUS state.  musb_hdrc won't care until it
+		 * starts to handle softconnect right.
+		 */
+		omap_musb_mailbox(status);
+	}
+	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
+
+	return IRQ_HANDLED;
+}
+
+static void twl4030_id_workaround_work(struct work_struct *work)
+{
+	struct twl4030_usb *twl = container_of(work, struct twl4030_usb,
+		id_workaround_work.work);
+	enum omap_musb_vbus_id_status status;
+	bool status_changed = false;
+
+	status = twl4030_usb_linkstat(twl);
+
+	spin_lock_irq(&twl->lock);
+	if (status >= 0 && status != twl->linkstat) {
+		twl->linkstat = status;
+		status_changed = true;
+	}
+	spin_unlock_irq(&twl->lock);
+
+	if (status_changed) {
+		dev_dbg(twl->dev, "handle missing status change to %d\n",
+				status);
+		omap_musb_mailbox(status);
+	}
+
+	/* don't schedule during sleep - irq works right then */
+	if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) {
+		cancel_delayed_work(&twl->id_workaround_work);
+		schedule_delayed_work(&twl->id_workaround_work, HZ);
+	}
+}
+
+static int twl4030_usb_phy_init(struct usb_phy *phy)
+{
+	struct twl4030_usb *twl = phy_to_twl(phy);
+	enum omap_musb_vbus_id_status status;
+
+	/*
+	 * Start in sleep state, we'll get called through set_suspend()
+	 * callback when musb is runtime resumed and it's time to start.
+	 */
+	__twl4030_phy_power(twl, 0);
+	twl->asleep = 1;
+
+	status = twl4030_usb_linkstat(twl);
+	twl->linkstat = status;
+
+	if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) {
+		omap_musb_mailbox(twl->linkstat);
+		twl4030_phy_resume(twl);
+	}
+
+	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
+	return 0;
+}
+
+static int twl4030_phy_init(struct phy *phy)
+{
+	struct twl4030_usb *twl = phy_get_drvdata(phy);
+
+	return twl4030_usb_phy_init(&twl->phy);
+}
+
+static int twl4030_set_suspend(struct usb_phy *x, int suspend)
+{
+	struct twl4030_usb *twl = phy_to_twl(x);
+
+	if (suspend)
+		twl4030_phy_suspend(twl, 1);
+	else
+		twl4030_phy_resume(twl);
+
+	return 0;
+}
+
+static int twl4030_set_peripheral(struct usb_otg *otg,
+					struct usb_gadget *gadget)
+{
+	if (!otg)
+		return -ENODEV;
+
+	otg->gadget = gadget;
+	if (!gadget)
+		otg->phy->state = OTG_STATE_UNDEFINED;
+
+	return 0;
+}
+
+static int twl4030_set_host(struct usb_otg *otg, struct usb_bus *host)
+{
+	if (!otg)
+		return -ENODEV;
+
+	otg->host = host;
+	if (!host)
+		otg->phy->state = OTG_STATE_UNDEFINED;
+
+	return 0;
+}
+
+static const struct phy_ops ops = {
+	.init		= twl4030_phy_init,
+	.power_on	= twl4030_phy_power_on,
+	.power_off	= twl4030_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static int twl4030_usb_probe(struct platform_device *pdev)
+{
+	struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev);
+	struct twl4030_usb	*twl;
+	struct phy		*phy;
+	int			status, err;
+	struct usb_otg		*otg;
+	struct device_node	*np = pdev->dev.of_node;
+	struct phy_provider	*phy_provider;
+	struct phy_init_data	*init_data = NULL;
+
+	twl = devm_kzalloc(&pdev->dev, sizeof *twl, GFP_KERNEL);
+	if (!twl)
+		return -ENOMEM;
+
+	if (np)
+		of_property_read_u32(np, "usb_mode",
+				(enum twl4030_usb_mode *)&twl->usb_mode);
+	else if (pdata) {
+		twl->usb_mode = pdata->usb_mode;
+		init_data = pdata->init_data;
+	} else {
+		dev_err(&pdev->dev, "twl4030 initialized without pdata\n");
+		return -EINVAL;
+	}
+
+	otg = devm_kzalloc(&pdev->dev, sizeof *otg, GFP_KERNEL);
+	if (!otg)
+		return -ENOMEM;
+
+	twl->dev		= &pdev->dev;
+	twl->irq		= platform_get_irq(pdev, 0);
+	twl->vbus_supplied	= false;
+	twl->asleep		= 1;
+	twl->linkstat		= OMAP_MUSB_UNKNOWN;
+
+	twl->phy.dev		= twl->dev;
+	twl->phy.label		= "twl4030";
+	twl->phy.otg		= otg;
+	twl->phy.type		= USB_PHY_TYPE_USB2;
+	twl->phy.set_suspend	= twl4030_set_suspend;
+	twl->phy.init		= twl4030_usb_phy_init;
+
+	otg->phy		= &twl->phy;
+	otg->set_host		= twl4030_set_host;
+	otg->set_peripheral	= twl4030_set_peripheral;
+
+	phy_provider = devm_of_phy_provider_register(twl->dev,
+		of_phy_simple_xlate);
+	if (IS_ERR(phy_provider))
+		return PTR_ERR(phy_provider);
+
+	phy = devm_phy_create(twl->dev, &ops, init_data);
+	if (IS_ERR(phy)) {
+		dev_dbg(&pdev->dev, "Failed to create PHY\n");
+		return PTR_ERR(phy);
+	}
+
+	phy_set_drvdata(phy, twl);
+
+	/* init spinlock for workqueue */
+	spin_lock_init(&twl->lock);
+
+	INIT_DELAYED_WORK(&twl->id_workaround_work, twl4030_id_workaround_work);
+
+	err = twl4030_usb_ldo_init(twl);
+	if (err) {
+		dev_err(&pdev->dev, "ldo init failed\n");
+		return err;
+	}
+	usb_add_phy_dev(&twl->phy);
+
+	platform_set_drvdata(pdev, twl);
+	if (device_create_file(&pdev->dev, &dev_attr_vbus))
+		dev_warn(&pdev->dev, "could not create sysfs file\n");
+
+	/* Our job is to use irqs and status from the power module
+	 * to keep the transceiver disabled when nothing's connected.
+	 *
+	 * FIXME we actually shouldn't start enabling it until the
+	 * USB controller drivers have said they're ready, by calling
+	 * set_host() and/or set_peripheral() ... OTG_capable boards
+	 * need both handles, otherwise just one suffices.
+	 */
+	twl->irq_enabled = true;
+	status = devm_request_threaded_irq(twl->dev, twl->irq, NULL,
+			twl4030_usb_irq, IRQF_TRIGGER_FALLING |
+			IRQF_TRIGGER_RISING | IRQF_ONESHOT, "twl4030_usb", twl);
+	if (status < 0) {
+		dev_dbg(&pdev->dev, "can't get IRQ %d, err %d\n",
+			twl->irq, status);
+		return status;
+	}
+
+	dev_info(&pdev->dev, "Initialized TWL4030 USB module\n");
+	return 0;
+}
+
+static int twl4030_usb_remove(struct platform_device *pdev)
+{
+	struct twl4030_usb *twl = platform_get_drvdata(pdev);
+	int val;
+
+	cancel_delayed_work(&twl->id_workaround_work);
+	device_remove_file(twl->dev, &dev_attr_vbus);
+
+	/* set transceiver mode to power on defaults */
+	twl4030_usb_set_mode(twl, -1);
+
+	/* autogate 60MHz ULPI clock,
+	 * clear dpll clock request for i2c access,
+	 * disable 32KHz
+	 */
+	val = twl4030_usb_read(twl, PHY_CLK_CTRL);
+	if (val >= 0) {
+		val |= PHY_CLK_CTRL_CLOCKGATING_EN;
+		val &= ~(PHY_CLK_CTRL_CLK32K_EN | REQ_PHY_DPLL_CLK);
+		twl4030_usb_write(twl, PHY_CLK_CTRL, (u8)val);
+	}
+
+	/* disable complete OTG block */
+	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
+
+	if (!twl->asleep)
+		twl4030_phy_power(twl, 0);
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id twl4030_usb_id_table[] = {
+	{ .compatible = "ti,twl4030-usb" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, twl4030_usb_id_table);
+#endif
+
+static struct platform_driver twl4030_usb_driver = {
+	.probe		= twl4030_usb_probe,
+	.remove		= twl4030_usb_remove,
+	.driver		= {
+		.name	= "twl4030_usb",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(twl4030_usb_id_table),
+	},
+};
+
+static int __init twl4030_usb_init(void)
+{
+	return platform_driver_register(&twl4030_usb_driver);
+}
+subsys_initcall(twl4030_usb_init);
+
+static void __exit twl4030_usb_exit(void)
+{
+	platform_driver_unregister(&twl4030_usb_driver);
+}
+module_exit(twl4030_usb_exit);
+
+MODULE_ALIAS("platform:twl4030_usb");
+MODULE_AUTHOR("Texas Instruments, Inc, Nokia Corporation");
+MODULE_DESCRIPTION("TWL4030 USB transceiver driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 2ce041109993..64b8bef1919e 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -113,16 +113,6 @@ config SAMSUNG_USB3PHY
 	  Enable this to support Samsung USB 3.0 (Super Speed) phy controller
 	  for samsung SoCs.
 
-config TWL4030_USB
-	tristate "TWL4030 USB Transceiver Driver"
-	depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS
-	select USB_PHY
-	help
-	  Enable this to support the USB OTG transceiver on TWL4030
-	  family chips (including the TWL5030 and TPS659x0 devices).
-	  This transceiver supports high and full speed devices plus,
-	  in host mode, low speed.
-
 config TWL6030_USB
 	tristate "TWL6030 USB Transceiver Driver"
 	depends on TWL4030_CORE && OMAP_USB2 && USB_MUSB_OMAP2PLUS
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index fa4db0e4bdb9..9c3736109c2c 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_OMAP_USB3)			+= phy-omap-usb3.o
 obj-$(CONFIG_SAMSUNG_USBPHY)		+= phy-samsung-usb.o
 obj-$(CONFIG_SAMSUNG_USB2PHY)		+= phy-samsung-usb2.o
 obj-$(CONFIG_SAMSUNG_USB3PHY)		+= phy-samsung-usb3.o
-obj-$(CONFIG_TWL4030_USB)		+= phy-twl4030-usb.o
 obj-$(CONFIG_TWL6030_USB)		+= phy-twl6030-usb.o
 obj-$(CONFIG_USB_EHCI_TEGRA)		+= phy-tegra-usb.o
 obj-$(CONFIG_USB_GPIO_VBUS)		+= phy-gpio-vbus-usb.o
diff --git a/drivers/usb/phy/phy-twl4030-usb.c b/drivers/usb/phy/phy-twl4030-usb.c
deleted file mode 100644
index 90730c8762b8..000000000000
--- a/drivers/usb/phy/phy-twl4030-usb.c
+++ /dev/null
@@ -1,794 +0,0 @@
-/*
- * twl4030_usb - TWL4030 USB transceiver, talking to OMAP OTG controller
- *
- * Copyright (C) 2004-2007 Texas Instruments
- * Copyright (C) 2008 Nokia Corporation
- * Contact: Felipe Balbi <felipe.balbi@nokia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Current status:
- *	- HS USB ULPI mode works.
- *	- 3-pin mode support may be added in future.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/usb/otg.h>
-#include <linux/usb/musb-omap.h>
-#include <linux/usb/ulpi.h>
-#include <linux/i2c/twl.h>
-#include <linux/regulator/consumer.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-
-/* Register defines */
-
-#define MCPC_CTRL			0x30
-#define MCPC_CTRL_RTSOL			(1 << 7)
-#define MCPC_CTRL_EXTSWR		(1 << 6)
-#define MCPC_CTRL_EXTSWC		(1 << 5)
-#define MCPC_CTRL_VOICESW		(1 << 4)
-#define MCPC_CTRL_OUT64K		(1 << 3)
-#define MCPC_CTRL_RTSCTSSW		(1 << 2)
-#define MCPC_CTRL_HS_UART		(1 << 0)
-
-#define MCPC_IO_CTRL			0x33
-#define MCPC_IO_CTRL_MICBIASEN		(1 << 5)
-#define MCPC_IO_CTRL_CTS_NPU		(1 << 4)
-#define MCPC_IO_CTRL_RXD_PU		(1 << 3)
-#define MCPC_IO_CTRL_TXDTYP		(1 << 2)
-#define MCPC_IO_CTRL_CTSTYP		(1 << 1)
-#define MCPC_IO_CTRL_RTSTYP		(1 << 0)
-
-#define MCPC_CTRL2			0x36
-#define MCPC_CTRL2_MCPC_CK_EN		(1 << 0)
-
-#define OTHER_FUNC_CTRL			0x80
-#define OTHER_FUNC_CTRL_BDIS_ACON_EN	(1 << 4)
-#define OTHER_FUNC_CTRL_FIVEWIRE_MODE	(1 << 2)
-
-#define OTHER_IFC_CTRL			0x83
-#define OTHER_IFC_CTRL_OE_INT_EN	(1 << 6)
-#define OTHER_IFC_CTRL_CEA2011_MODE	(1 << 5)
-#define OTHER_IFC_CTRL_FSLSSERIALMODE_4PIN	(1 << 4)
-#define OTHER_IFC_CTRL_HIZ_ULPI_60MHZ_OUT	(1 << 3)
-#define OTHER_IFC_CTRL_HIZ_ULPI		(1 << 2)
-#define OTHER_IFC_CTRL_ALT_INT_REROUTE	(1 << 0)
-
-#define OTHER_INT_EN_RISE		0x86
-#define OTHER_INT_EN_FALL		0x89
-#define OTHER_INT_STS			0x8C
-#define OTHER_INT_LATCH			0x8D
-#define OTHER_INT_VB_SESS_VLD		(1 << 7)
-#define OTHER_INT_DM_HI			(1 << 6) /* not valid for "latch" reg */
-#define OTHER_INT_DP_HI			(1 << 5) /* not valid for "latch" reg */
-#define OTHER_INT_BDIS_ACON		(1 << 3) /* not valid for "fall" regs */
-#define OTHER_INT_MANU			(1 << 1)
-#define OTHER_INT_ABNORMAL_STRESS	(1 << 0)
-
-#define ID_STATUS			0x96
-#define ID_RES_FLOAT			(1 << 4)
-#define ID_RES_440K			(1 << 3)
-#define ID_RES_200K			(1 << 2)
-#define ID_RES_102K			(1 << 1)
-#define ID_RES_GND			(1 << 0)
-
-#define POWER_CTRL			0xAC
-#define POWER_CTRL_OTG_ENAB		(1 << 5)
-
-#define OTHER_IFC_CTRL2			0xAF
-#define OTHER_IFC_CTRL2_ULPI_STP_LOW	(1 << 4)
-#define OTHER_IFC_CTRL2_ULPI_TXEN_POL	(1 << 3)
-#define OTHER_IFC_CTRL2_ULPI_4PIN_2430	(1 << 2)
-#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_MASK	(3 << 0) /* bits 0 and 1 */
-#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_INT1N	(0 << 0)
-#define OTHER_IFC_CTRL2_USB_INT_OUTSEL_INT2N	(1 << 0)
-
-#define REG_CTRL_EN			0xB2
-#define REG_CTRL_ERROR			0xB5
-#define ULPI_I2C_CONFLICT_INTEN		(1 << 0)
-
-#define OTHER_FUNC_CTRL2		0xB8
-#define OTHER_FUNC_CTRL2_VBAT_TIMER_EN	(1 << 0)
-
-/* following registers do not have separate _clr and _set registers */
-#define VBUS_DEBOUNCE			0xC0
-#define ID_DEBOUNCE			0xC1
-#define VBAT_TIMER			0xD3
-#define PHY_PWR_CTRL			0xFD
-#define PHY_PWR_PHYPWD			(1 << 0)
-#define PHY_CLK_CTRL			0xFE
-#define PHY_CLK_CTRL_CLOCKGATING_EN	(1 << 2)
-#define PHY_CLK_CTRL_CLK32K_EN		(1 << 1)
-#define REQ_PHY_DPLL_CLK		(1 << 0)
-#define PHY_CLK_CTRL_STS		0xFF
-#define PHY_DPLL_CLK			(1 << 0)
-
-/* In module TWL_MODULE_PM_MASTER */
-#define STS_HW_CONDITIONS		0x0F
-
-/* In module TWL_MODULE_PM_RECEIVER */
-#define VUSB_DEDICATED1			0x7D
-#define VUSB_DEDICATED2			0x7E
-#define VUSB1V5_DEV_GRP			0x71
-#define VUSB1V5_TYPE			0x72
-#define VUSB1V5_REMAP			0x73
-#define VUSB1V8_DEV_GRP			0x74
-#define VUSB1V8_TYPE			0x75
-#define VUSB1V8_REMAP			0x76
-#define VUSB3V1_DEV_GRP			0x77
-#define VUSB3V1_TYPE			0x78
-#define VUSB3V1_REMAP			0x79
-
-/* In module TWL4030_MODULE_INTBR */
-#define PMBR1				0x0D
-#define GPIO_USB_4PIN_ULPI_2430C	(3 << 0)
-
-struct twl4030_usb {
-	struct usb_phy		phy;
-	struct device		*dev;
-
-	/* TWL4030 internal USB regulator supplies */
-	struct regulator	*usb1v5;
-	struct regulator	*usb1v8;
-	struct regulator	*usb3v1;
-
-	/* for vbus reporting with irqs disabled */
-	spinlock_t		lock;
-
-	/* pin configuration */
-	enum twl4030_usb_mode	usb_mode;
-
-	int			irq;
-	enum omap_musb_vbus_id_status linkstat;
-	bool			vbus_supplied;
-	u8			asleep;
-	bool			irq_enabled;
-
-	struct delayed_work	id_workaround_work;
-};
-
-/* internal define on top of container_of */
-#define phy_to_twl(x)		container_of((x), struct twl4030_usb, phy)
-
-/*-------------------------------------------------------------------------*/
-
-static int twl4030_i2c_write_u8_verify(struct twl4030_usb *twl,
-		u8 module, u8 data, u8 address)
-{
-	u8 check;
-
-	if ((twl_i2c_write_u8(module, data, address) >= 0) &&
-	    (twl_i2c_read_u8(module, &check, address) >= 0) &&
-						(check == data))
-		return 0;
-	dev_dbg(twl->dev, "Write%d[%d,0x%x] wrote %02x but read %02x\n",
-			1, module, address, check, data);
-
-	/* Failed once: Try again */
-	if ((twl_i2c_write_u8(module, data, address) >= 0) &&
-	    (twl_i2c_read_u8(module, &check, address) >= 0) &&
-						(check == data))
-		return 0;
-	dev_dbg(twl->dev, "Write%d[%d,0x%x] wrote %02x but read %02x\n",
-			2, module, address, check, data);
-
-	/* Failed again: Return error */
-	return -EBUSY;
-}
-
-#define twl4030_usb_write_verify(twl, address, data)	\
-	twl4030_i2c_write_u8_verify(twl, TWL_MODULE_USB, (data), (address))
-
-static inline int twl4030_usb_write(struct twl4030_usb *twl,
-		u8 address, u8 data)
-{
-	int ret = 0;
-
-	ret = twl_i2c_write_u8(TWL_MODULE_USB, data, address);
-	if (ret < 0)
-		dev_dbg(twl->dev,
-			"TWL4030:USB:Write[0x%x] Error %d\n", address, ret);
-	return ret;
-}
-
-static inline int twl4030_readb(struct twl4030_usb *twl, u8 module, u8 address)
-{
-	u8 data;
-	int ret = 0;
-
-	ret = twl_i2c_read_u8(module, &data, address);
-	if (ret >= 0)
-		ret = data;
-	else
-		dev_dbg(twl->dev,
-			"TWL4030:readb[0x%x,0x%x] Error %d\n",
-					module, address, ret);
-
-	return ret;
-}
-
-static inline int twl4030_usb_read(struct twl4030_usb *twl, u8 address)
-{
-	return twl4030_readb(twl, TWL_MODULE_USB, address);
-}
-
-/*-------------------------------------------------------------------------*/
-
-static inline int
-twl4030_usb_set_bits(struct twl4030_usb *twl, u8 reg, u8 bits)
-{
-	return twl4030_usb_write(twl, ULPI_SET(reg), bits);
-}
-
-static inline int
-twl4030_usb_clear_bits(struct twl4030_usb *twl, u8 reg, u8 bits)
-{
-	return twl4030_usb_write(twl, ULPI_CLR(reg), bits);
-}
-
-/*-------------------------------------------------------------------------*/
-
-static bool twl4030_is_driving_vbus(struct twl4030_usb *twl)
-{
-	int ret;
-
-	ret = twl4030_usb_read(twl, PHY_CLK_CTRL_STS);
-	if (ret < 0 || !(ret & PHY_DPLL_CLK))
-		/*
-		 * if clocks are off, registers are not updated,
-		 * but we can assume we don't drive VBUS in this case
-		 */
-		return false;
-
-	ret = twl4030_usb_read(twl, ULPI_OTG_CTRL);
-	if (ret < 0)
-		return false;
-
-	return (ret & (ULPI_OTG_DRVVBUS | ULPI_OTG_CHRGVBUS)) ? true : false;
-}
-
-static enum omap_musb_vbus_id_status
-	twl4030_usb_linkstat(struct twl4030_usb *twl)
-{
-	int	status;
-	enum omap_musb_vbus_id_status linkstat = OMAP_MUSB_UNKNOWN;
-
-	twl->vbus_supplied = false;
-
-	/*
-	 * For ID/VBUS sensing, see manual section 15.4.8 ...
-	 * except when using only battery backup power, two
-	 * comparators produce VBUS_PRES and ID_PRES signals,
-	 * which don't match docs elsewhere.  But ... BIT(7)
-	 * and BIT(2) of STS_HW_CONDITIONS, respectively, do
-	 * seem to match up.  If either is true the USB_PRES
-	 * signal is active, the OTG module is activated, and
-	 * its interrupt may be raised (may wake the system).
-	 */
-	status = twl4030_readb(twl, TWL_MODULE_PM_MASTER, STS_HW_CONDITIONS);
-	if (status < 0)
-		dev_err(twl->dev, "USB link status err %d\n", status);
-	else if (status & (BIT(7) | BIT(2))) {
-		if (status & BIT(7)) {
-			if (twl4030_is_driving_vbus(twl))
-				status &= ~BIT(7);
-			else
-				twl->vbus_supplied = true;
-		}
-
-		if (status & BIT(2))
-			linkstat = OMAP_MUSB_ID_GROUND;
-		else if (status & BIT(7))
-			linkstat = OMAP_MUSB_VBUS_VALID;
-		else
-			linkstat = OMAP_MUSB_VBUS_OFF;
-	} else {
-		if (twl->linkstat != OMAP_MUSB_UNKNOWN)
-			linkstat = OMAP_MUSB_VBUS_OFF;
-	}
-
-	dev_dbg(twl->dev, "HW_CONDITIONS 0x%02x/%d; link %d\n",
-			status, status, linkstat);
-
-	/* REVISIT this assumes host and peripheral controllers
-	 * are registered, and that both are active...
-	 */
-
-	return linkstat;
-}
-
-static void twl4030_usb_set_mode(struct twl4030_usb *twl, int mode)
-{
-	twl->usb_mode = mode;
-
-	switch (mode) {
-	case T2_USB_MODE_ULPI:
-		twl4030_usb_clear_bits(twl, ULPI_IFC_CTRL,
-					ULPI_IFC_CTRL_CARKITMODE);
-		twl4030_usb_set_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
-		twl4030_usb_clear_bits(twl, ULPI_FUNC_CTRL,
-					ULPI_FUNC_CTRL_XCVRSEL_MASK |
-					ULPI_FUNC_CTRL_OPMODE_MASK);
-		break;
-	case -1:
-		/* FIXME: power on defaults */
-		break;
-	default:
-		dev_err(twl->dev, "unsupported T2 transceiver mode %d\n",
-				mode);
-		break;
-	};
-}
-
-static void twl4030_i2c_access(struct twl4030_usb *twl, int on)
-{
-	unsigned long timeout;
-	int val = twl4030_usb_read(twl, PHY_CLK_CTRL);
-
-	if (val >= 0) {
-		if (on) {
-			/* enable DPLL to access PHY registers over I2C */
-			val |= REQ_PHY_DPLL_CLK;
-			WARN_ON(twl4030_usb_write_verify(twl, PHY_CLK_CTRL,
-						(u8)val) < 0);
-
-			timeout = jiffies + HZ;
-			while (!(twl4030_usb_read(twl, PHY_CLK_CTRL_STS) &
-							PHY_DPLL_CLK)
-				&& time_before(jiffies, timeout))
-					udelay(10);
-			if (!(twl4030_usb_read(twl, PHY_CLK_CTRL_STS) &
-							PHY_DPLL_CLK))
-				dev_err(twl->dev, "Timeout setting T2 HSUSB "
-						"PHY DPLL clock\n");
-		} else {
-			/* let ULPI control the DPLL clock */
-			val &= ~REQ_PHY_DPLL_CLK;
-			WARN_ON(twl4030_usb_write_verify(twl, PHY_CLK_CTRL,
-						(u8)val) < 0);
-		}
-	}
-}
-
-static void __twl4030_phy_power(struct twl4030_usb *twl, int on)
-{
-	u8 pwr = twl4030_usb_read(twl, PHY_PWR_CTRL);
-
-	if (on)
-		pwr &= ~PHY_PWR_PHYPWD;
-	else
-		pwr |= PHY_PWR_PHYPWD;
-
-	WARN_ON(twl4030_usb_write_verify(twl, PHY_PWR_CTRL, pwr) < 0);
-}
-
-static void twl4030_phy_power(struct twl4030_usb *twl, int on)
-{
-	int ret;
-
-	if (on) {
-		ret = regulator_enable(twl->usb3v1);
-		if (ret)
-			dev_err(twl->dev, "Failed to enable usb3v1\n");
-
-		ret = regulator_enable(twl->usb1v8);
-		if (ret)
-			dev_err(twl->dev, "Failed to enable usb1v8\n");
-
-		/*
-		 * Disabling usb3v1 regulator (= writing 0 to VUSB3V1_DEV_GRP
-		 * in twl4030) resets the VUSB_DEDICATED2 register. This reset
-		 * enables VUSB3V1_SLEEP bit that remaps usb3v1 ACTIVE state to
-		 * SLEEP. We work around this by clearing the bit after usv3v1
-		 * is re-activated. This ensures that VUSB3V1 is really active.
-		 */
-		twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);
-
-		ret = regulator_enable(twl->usb1v5);
-		if (ret)
-			dev_err(twl->dev, "Failed to enable usb1v5\n");
-
-		__twl4030_phy_power(twl, 1);
-		twl4030_usb_write(twl, PHY_CLK_CTRL,
-				  twl4030_usb_read(twl, PHY_CLK_CTRL) |
-					(PHY_CLK_CTRL_CLOCKGATING_EN |
-						PHY_CLK_CTRL_CLK32K_EN));
-	} else {
-		__twl4030_phy_power(twl, 0);
-		regulator_disable(twl->usb1v5);
-		regulator_disable(twl->usb1v8);
-		regulator_disable(twl->usb3v1);
-	}
-}
-
-static void twl4030_phy_suspend(struct twl4030_usb *twl, int controller_off)
-{
-	if (twl->asleep)
-		return;
-
-	twl4030_phy_power(twl, 0);
-	twl->asleep = 1;
-	dev_dbg(twl->dev, "%s\n", __func__);
-}
-
-static void __twl4030_phy_resume(struct twl4030_usb *twl)
-{
-	twl4030_phy_power(twl, 1);
-	twl4030_i2c_access(twl, 1);
-	twl4030_usb_set_mode(twl, twl->usb_mode);
-	if (twl->usb_mode == T2_USB_MODE_ULPI)
-		twl4030_i2c_access(twl, 0);
-}
-
-static void twl4030_phy_resume(struct twl4030_usb *twl)
-{
-	if (!twl->asleep)
-		return;
-	__twl4030_phy_resume(twl);
-	twl->asleep = 0;
-	dev_dbg(twl->dev, "%s\n", __func__);
-
-	/*
-	 * XXX When VBUS gets driven after musb goes to A mode,
-	 * ID_PRES related interrupts no longer arrive, why?
-	 * Register itself is updated fine though, so we must poll.
-	 */
-	if (twl->linkstat == OMAP_MUSB_ID_GROUND) {
-		cancel_delayed_work(&twl->id_workaround_work);
-		schedule_delayed_work(&twl->id_workaround_work, HZ);
-	}
-}
-
-static int twl4030_usb_ldo_init(struct twl4030_usb *twl)
-{
-	/* Enable writing to power configuration registers */
-	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, TWL4030_PM_MASTER_KEY_CFG1,
-			 TWL4030_PM_MASTER_PROTECT_KEY);
-
-	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, TWL4030_PM_MASTER_KEY_CFG2,
-			 TWL4030_PM_MASTER_PROTECT_KEY);
-
-	/* Keep VUSB3V1 LDO in sleep state until VBUS/ID change detected*/
-	/*twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB_DEDICATED2);*/
-
-	/* input to VUSB3V1 LDO is from VBAT, not VBUS */
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0x14, VUSB_DEDICATED1);
-
-	/* Initialize 3.1V regulator */
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB3V1_DEV_GRP);
-
-	twl->usb3v1 = devm_regulator_get(twl->dev, "usb3v1");
-	if (IS_ERR(twl->usb3v1))
-		return -ENODEV;
-
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB3V1_TYPE);
-
-	/* Initialize 1.5V regulator */
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V5_DEV_GRP);
-
-	twl->usb1v5 = devm_regulator_get(twl->dev, "usb1v5");
-	if (IS_ERR(twl->usb1v5))
-		return -ENODEV;
-
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V5_TYPE);
-
-	/* Initialize 1.8V regulator */
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V8_DEV_GRP);
-
-	twl->usb1v8 = devm_regulator_get(twl->dev, "usb1v8");
-	if (IS_ERR(twl->usb1v8))
-		return -ENODEV;
-
-	twl_i2c_write_u8(TWL_MODULE_PM_RECEIVER, 0, VUSB1V8_TYPE);
-
-	/* disable access to power configuration registers */
-	twl_i2c_write_u8(TWL_MODULE_PM_MASTER, 0,
-			 TWL4030_PM_MASTER_PROTECT_KEY);
-
-	return 0;
-}
-
-static ssize_t twl4030_usb_vbus_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct twl4030_usb *twl = dev_get_drvdata(dev);
-	unsigned long flags;
-	int ret = -EINVAL;
-
-	spin_lock_irqsave(&twl->lock, flags);
-	ret = sprintf(buf, "%s\n",
-			twl->vbus_supplied ? "on" : "off");
-	spin_unlock_irqrestore(&twl->lock, flags);
-
-	return ret;
-}
-static DEVICE_ATTR(vbus, 0444, twl4030_usb_vbus_show, NULL);
-
-static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
-{
-	struct twl4030_usb *twl = _twl;
-	enum omap_musb_vbus_id_status status;
-	bool status_changed = false;
-
-	status = twl4030_usb_linkstat(twl);
-
-	spin_lock_irq(&twl->lock);
-	if (status >= 0 && status != twl->linkstat) {
-		twl->linkstat = status;
-		status_changed = true;
-	}
-	spin_unlock_irq(&twl->lock);
-
-	if (status_changed) {
-		/* FIXME add a set_power() method so that B-devices can
-		 * configure the charger appropriately.  It's not always
-		 * correct to consume VBUS power, and how much current to
-		 * consume is a function of the USB configuration chosen
-		 * by the host.
-		 *
-		 * REVISIT usb_gadget_vbus_connect(...) as needed, ditto
-		 * its disconnect() sibling, when changing to/from the
-		 * USB_LINK_VBUS state.  musb_hdrc won't care until it
-		 * starts to handle softconnect right.
-		 */
-		omap_musb_mailbox(status);
-	}
-	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
-
-	return IRQ_HANDLED;
-}
-
-static void twl4030_id_workaround_work(struct work_struct *work)
-{
-	struct twl4030_usb *twl = container_of(work, struct twl4030_usb,
-		id_workaround_work.work);
-	enum omap_musb_vbus_id_status status;
-	bool status_changed = false;
-
-	status = twl4030_usb_linkstat(twl);
-
-	spin_lock_irq(&twl->lock);
-	if (status >= 0 && status != twl->linkstat) {
-		twl->linkstat = status;
-		status_changed = true;
-	}
-	spin_unlock_irq(&twl->lock);
-
-	if (status_changed) {
-		dev_dbg(twl->dev, "handle missing status change to %d\n",
-				status);
-		omap_musb_mailbox(status);
-	}
-
-	/* don't schedule during sleep - irq works right then */
-	if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) {
-		cancel_delayed_work(&twl->id_workaround_work);
-		schedule_delayed_work(&twl->id_workaround_work, HZ);
-	}
-}
-
-static int twl4030_usb_phy_init(struct usb_phy *phy)
-{
-	struct twl4030_usb *twl = phy_to_twl(phy);
-	enum omap_musb_vbus_id_status status;
-
-	/*
-	 * Start in sleep state, we'll get called through set_suspend()
-	 * callback when musb is runtime resumed and it's time to start.
-	 */
-	__twl4030_phy_power(twl, 0);
-	twl->asleep = 1;
-
-	status = twl4030_usb_linkstat(twl);
-	twl->linkstat = status;
-
-	if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID)
-		omap_musb_mailbox(twl->linkstat);
-
-	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
-	return 0;
-}
-
-static int twl4030_set_suspend(struct usb_phy *x, int suspend)
-{
-	struct twl4030_usb *twl = phy_to_twl(x);
-
-	if (suspend)
-		twl4030_phy_suspend(twl, 1);
-	else
-		twl4030_phy_resume(twl);
-
-	return 0;
-}
-
-static int twl4030_set_peripheral(struct usb_otg *otg,
-					struct usb_gadget *gadget)
-{
-	if (!otg)
-		return -ENODEV;
-
-	otg->gadget = gadget;
-	if (!gadget)
-		otg->phy->state = OTG_STATE_UNDEFINED;
-
-	return 0;
-}
-
-static int twl4030_set_host(struct usb_otg *otg, struct usb_bus *host)
-{
-	if (!otg)
-		return -ENODEV;
-
-	otg->host = host;
-	if (!host)
-		otg->phy->state = OTG_STATE_UNDEFINED;
-
-	return 0;
-}
-
-static int twl4030_usb_probe(struct platform_device *pdev)
-{
-	struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev);
-	struct twl4030_usb	*twl;
-	int			status, err;
-	struct usb_otg		*otg;
-	struct device_node	*np = pdev->dev.of_node;
-
-	twl = devm_kzalloc(&pdev->dev, sizeof *twl, GFP_KERNEL);
-	if (!twl)
-		return -ENOMEM;
-
-	if (np)
-		of_property_read_u32(np, "usb_mode",
-				(enum twl4030_usb_mode *)&twl->usb_mode);
-	else if (pdata)
-		twl->usb_mode = pdata->usb_mode;
-	else {
-		dev_err(&pdev->dev, "twl4030 initialized without pdata\n");
-		return -EINVAL;
-	}
-
-	otg = devm_kzalloc(&pdev->dev, sizeof *otg, GFP_KERNEL);
-	if (!otg)
-		return -ENOMEM;
-
-	twl->dev		= &pdev->dev;
-	twl->irq		= platform_get_irq(pdev, 0);
-	twl->vbus_supplied	= false;
-	twl->asleep		= 1;
-	twl->linkstat		= OMAP_MUSB_UNKNOWN;
-
-	twl->phy.dev		= twl->dev;
-	twl->phy.label		= "twl4030";
-	twl->phy.otg		= otg;
-	twl->phy.type		= USB_PHY_TYPE_USB2;
-	twl->phy.set_suspend	= twl4030_set_suspend;
-	twl->phy.init		= twl4030_usb_phy_init;
-
-	otg->phy		= &twl->phy;
-	otg->set_host		= twl4030_set_host;
-	otg->set_peripheral	= twl4030_set_peripheral;
-
-	/* init spinlock for workqueue */
-	spin_lock_init(&twl->lock);
-
-	INIT_DELAYED_WORK(&twl->id_workaround_work, twl4030_id_workaround_work);
-
-	err = twl4030_usb_ldo_init(twl);
-	if (err) {
-		dev_err(&pdev->dev, "ldo init failed\n");
-		return err;
-	}
-	usb_add_phy_dev(&twl->phy);
-
-	platform_set_drvdata(pdev, twl);
-	if (device_create_file(&pdev->dev, &dev_attr_vbus))
-		dev_warn(&pdev->dev, "could not create sysfs file\n");
-
-	/* Our job is to use irqs and status from the power module
-	 * to keep the transceiver disabled when nothing's connected.
-	 *
-	 * FIXME we actually shouldn't start enabling it until the
-	 * USB controller drivers have said they're ready, by calling
-	 * set_host() and/or set_peripheral() ... OTG_capable boards
-	 * need both handles, otherwise just one suffices.
-	 */
-	twl->irq_enabled = true;
-	status = devm_request_threaded_irq(twl->dev, twl->irq, NULL,
-			twl4030_usb_irq, IRQF_TRIGGER_FALLING |
-			IRQF_TRIGGER_RISING | IRQF_ONESHOT, "twl4030_usb", twl);
-	if (status < 0) {
-		dev_dbg(&pdev->dev, "can't get IRQ %d, err %d\n",
-			twl->irq, status);
-		return status;
-	}
-
-	dev_info(&pdev->dev, "Initialized TWL4030 USB module\n");
-	return 0;
-}
-
-static int twl4030_usb_remove(struct platform_device *pdev)
-{
-	struct twl4030_usb *twl = platform_get_drvdata(pdev);
-	int val;
-
-	cancel_delayed_work(&twl->id_workaround_work);
-	device_remove_file(twl->dev, &dev_attr_vbus);
-
-	/* set transceiver mode to power on defaults */
-	twl4030_usb_set_mode(twl, -1);
-
-	/* autogate 60MHz ULPI clock,
-	 * clear dpll clock request for i2c access,
-	 * disable 32KHz
-	 */
-	val = twl4030_usb_read(twl, PHY_CLK_CTRL);
-	if (val >= 0) {
-		val |= PHY_CLK_CTRL_CLOCKGATING_EN;
-		val &= ~(PHY_CLK_CTRL_CLK32K_EN | REQ_PHY_DPLL_CLK);
-		twl4030_usb_write(twl, PHY_CLK_CTRL, (u8)val);
-	}
-
-	/* disable complete OTG block */
-	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
-
-	if (!twl->asleep)
-		twl4030_phy_power(twl, 0);
-
-	return 0;
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id twl4030_usb_id_table[] = {
-	{ .compatible = "ti,twl4030-usb" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, twl4030_usb_id_table);
-#endif
-
-static struct platform_driver twl4030_usb_driver = {
-	.probe		= twl4030_usb_probe,
-	.remove		= twl4030_usb_remove,
-	.driver		= {
-		.name	= "twl4030_usb",
-		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(twl4030_usb_id_table),
-	},
-};
-
-static int __init twl4030_usb_init(void)
-{
-	return platform_driver_register(&twl4030_usb_driver);
-}
-subsys_initcall(twl4030_usb_init);
-
-static void __exit twl4030_usb_exit(void)
-{
-	platform_driver_unregister(&twl4030_usb_driver);
-}
-module_exit(twl4030_usb_exit);
-
-MODULE_ALIAS("platform:twl4030_usb");
-MODULE_AUTHOR("Texas Instruments, Inc, Nokia Corporation");
-MODULE_DESCRIPTION("TWL4030 USB transceiver driver");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index 81cbbdb96aae..673a3ce67f31 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -26,6 +26,7 @@
 #define __TWL_H_
 
 #include <linux/types.h>
+#include <linux/phy/phy.h>
 #include <linux/input/matrix_keypad.h>
 
 /*
@@ -615,6 +616,7 @@ enum twl4030_usb_mode {
 struct twl4030_usb_data {
 	enum twl4030_usb_mode	usb_mode;
 	unsigned long		features;
+	struct phy_init_data	*init_data;
 
 	int		(*phy_init)(struct device *dev);
 	int		(*phy_exit)(struct device *dev);
-- 
cgit 


From 75f93fed50c2abadbab6ef546b265f51ca975b27 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 27 Sep 2013 17:30:03 +0200
Subject: sched: Revert need_resched() to look at TIF_NEED_RESCHED

Yuanhan reported a serious throughput regression in his pigz
benchmark. Using the ftrace patch I found that several idle
paths need more TLC before we can switch the generic
need_resched() over to preempt_need_resched.

The preemption paths benefit most from preempt_need_resched and
do indeed use it; all other need_resched() users don't really
care that much so reverting need_resched() back to
tif_need_resched() is the simple and safe solution.

Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: lkp@linux.intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20130927153003.GF15690@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/preempt.h | 8 --------
 include/asm-generic/preempt.h  | 8 --------
 include/linux/sched.h          | 5 +++++
 3 files changed, 5 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 1de41690ff99..8729723636fd 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -79,14 +79,6 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
 }
 
-/*
- * Returns true when we need to resched -- even if we can not.
- */
-static __always_inline bool need_resched(void)
-{
-	return unlikely(test_preempt_need_resched());
-}
-
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5dc14ed3791c..ddf2b420ac8f 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -84,14 +84,6 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 	return !--*preempt_count_ptr();
 }
 
-/*
- * Returns true when we need to resched -- even if we can not.
- */
-static __always_inline bool need_resched(void)
-{
-	return unlikely(test_preempt_need_resched());
-}
-
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b09798b672f3..2ac5285db434 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2577,6 +2577,11 @@ static inline bool __must_check current_clr_polling_and_test(void)
 }
 #endif
 
+static __always_inline bool need_resched(void)
+{
+	return unlikely(tif_need_resched());
+}
+
 /*
  * Thread group CPU time accounting.
  */
-- 
cgit 


From b4e46138f946442608647be58e78e3ad4d15534e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 27 Sep 2013 21:46:51 -0700
Subject: driver-core: remove struct bus_type.bus_attrs

Now that all in-kernel users of bus_type.bus_attrs have been converted
to use bus_groups instead, the bus_attrs field, and logic surrounding
it, can be removed.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c     | 42 ------------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 44 deletions(-)

(limited to 'include')

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 4c289ab91357..2cdf29464063 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -846,42 +846,6 @@ struct bus_type *find_bus(char *name)
 }
 #endif  /*  0  */
 
-
-/**
- * bus_add_attrs - Add default attributes for this bus.
- * @bus: Bus that has just been registered.
- */
-
-static int bus_add_attrs(struct bus_type *bus)
-{
-	int error = 0;
-	int i;
-
-	if (bus->bus_attrs) {
-		for (i = 0; bus->bus_attrs[i].attr.name; i++) {
-			error = bus_create_file(bus, &bus->bus_attrs[i]);
-			if (error)
-				goto err;
-		}
-	}
-done:
-	return error;
-err:
-	while (--i >= 0)
-		bus_remove_file(bus, &bus->bus_attrs[i]);
-	goto done;
-}
-
-static void bus_remove_attrs(struct bus_type *bus)
-{
-	int i;
-
-	if (bus->bus_attrs) {
-		for (i = 0; bus->bus_attrs[i].attr.name; i++)
-			bus_remove_file(bus, &bus->bus_attrs[i]);
-	}
-}
-
 static int bus_add_groups(struct bus_type *bus,
 			  const struct attribute_group **groups)
 {
@@ -983,9 +947,6 @@ int bus_register(struct bus_type *bus)
 	if (retval)
 		goto bus_probe_files_fail;
 
-	retval = bus_add_attrs(bus);
-	if (retval)
-		goto bus_attrs_fail;
 	retval = bus_add_groups(bus, bus->bus_groups);
 	if (retval)
 		goto bus_groups_fail;
@@ -994,8 +955,6 @@ int bus_register(struct bus_type *bus)
 	return 0;
 
 bus_groups_fail:
-	bus_remove_attrs(bus);
-bus_attrs_fail:
 	remove_probe_files(bus);
 bus_probe_files_fail:
 	kset_unregister(bus->p->drivers_kset);
@@ -1024,7 +983,6 @@ void bus_unregister(struct bus_type *bus)
 	pr_debug("bus: '%s': unregistering\n", bus->name);
 	if (bus->dev_root)
 		device_unregister(bus->dev_root);
-	bus_remove_attrs(bus);
 	bus_remove_groups(bus, bus->bus_groups);
 	remove_probe_files(bus);
 	kset_unregister(bus->p->drivers_kset);
diff --git a/include/linux/device.h b/include/linux/device.h
index ce690ea34547..89a852e0896d 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -63,7 +63,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @name:	The name of the bus.
  * @dev_name:	Used for subsystems to enumerate devices like ("foo%u", dev->id).
  * @dev_root:	Default device to use as the parent.
- * @bus_attrs:	Default attributes of the bus.
  * @dev_attrs:	Default attributes of the devices on the bus.
  * @drv_attrs:	Default attributes of the device drivers on the bus.
  * @bus_groups:	Default attributes of the bus.
@@ -106,7 +105,6 @@ struct bus_type {
 	const char		*name;
 	const char		*dev_name;
 	struct device		*dev_root;
-	struct bus_attribute	*bus_attrs;	/* use bus_groups instead */
 	struct device_attribute	*dev_attrs;	/* use dev_groups instead */
 	struct driver_attribute	*drv_attrs;	/* use drv_groups instead */
 	const struct attribute_group **bus_groups;
-- 
cgit 


From e18945b159a1cdbc031f1d3b0b7e515a33bdcbf7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 27 Sep 2013 21:47:21 -0700
Subject: driver-core: remove struct bus_type.drv_attrs

Now that all in-kernel users of bus_type.drv_attrs have been converted
to use drv_groups instead, the drv_attrs field, and logic surrounding
it, can be removed.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c     | 40 ++--------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 2 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 2cdf29464063..73f6c2925281 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -591,37 +591,6 @@ void bus_remove_device(struct device *dev)
 	bus_put(dev->bus);
 }
 
-static int driver_add_attrs(struct bus_type *bus, struct device_driver *drv)
-{
-	int error = 0;
-	int i;
-
-	if (bus->drv_attrs) {
-		for (i = 0; bus->drv_attrs[i].attr.name; i++) {
-			error = driver_create_file(drv, &bus->drv_attrs[i]);
-			if (error)
-				goto err;
-		}
-	}
-done:
-	return error;
-err:
-	while (--i >= 0)
-		driver_remove_file(drv, &bus->drv_attrs[i]);
-	goto done;
-}
-
-static void driver_remove_attrs(struct bus_type *bus,
-				struct device_driver *drv)
-{
-	int i;
-
-	if (bus->drv_attrs) {
-		for (i = 0; bus->drv_attrs[i].attr.name; i++)
-			driver_remove_file(drv, &bus->drv_attrs[i]);
-	}
-}
-
 static int __must_check add_bind_files(struct device_driver *drv)
 {
 	int ret;
@@ -720,16 +689,12 @@ int bus_add_driver(struct device_driver *drv)
 		printk(KERN_ERR "%s: uevent attr (%s) failed\n",
 			__func__, drv->name);
 	}
-	error = driver_add_attrs(bus, drv);
+	error = driver_add_groups(drv, bus->drv_groups);
 	if (error) {
 		/* How the hell do we get out of this pickle? Give up */
-		printk(KERN_ERR "%s: driver_add_attrs(%s) failed\n",
-			__func__, drv->name);
-	}
-	error = driver_add_groups(drv, bus->drv_groups);
-	if (error)
 		printk(KERN_ERR "%s: driver_create_groups(%s) failed\n",
 			__func__, drv->name);
+	}
 
 	if (!drv->suppress_bind_attrs) {
 		error = add_bind_files(drv);
@@ -766,7 +731,6 @@ void bus_remove_driver(struct device_driver *drv)
 
 	if (!drv->suppress_bind_attrs)
 		remove_bind_files(drv);
-	driver_remove_attrs(drv->bus, drv);
 	driver_remove_groups(drv, drv->bus->drv_groups);
 	driver_remove_file(drv, &driver_attr_uevent);
 	klist_remove(&drv->p->knode_bus);
diff --git a/include/linux/device.h b/include/linux/device.h
index 89a852e0896d..e7f5b8585380 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -64,7 +64,6 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @dev_name:	Used for subsystems to enumerate devices like ("foo%u", dev->id).
  * @dev_root:	Default device to use as the parent.
  * @dev_attrs:	Default attributes of the devices on the bus.
- * @drv_attrs:	Default attributes of the device drivers on the bus.
  * @bus_groups:	Default attributes of the bus.
  * @dev_groups:	Default attributes of the devices on the bus.
  * @drv_groups: Default attributes of the device drivers on the bus.
@@ -106,7 +105,6 @@ struct bus_type {
 	const char		*dev_name;
 	struct device		*dev_root;
 	struct device_attribute	*dev_attrs;	/* use dev_groups instead */
-	struct driver_attribute	*drv_attrs;	/* use drv_groups instead */
 	const struct attribute_group **bus_groups;
 	const struct attribute_group **dev_groups;
 	const struct attribute_group **drv_groups;
-- 
cgit 


From f02db315b8d888570cb0d4496cfbb7e4acb047cb Mon Sep 17 00:00:00 2001
From: Francesco Fusco <ffusco@redhat.com>
Date: Tue, 24 Sep 2013 15:43:08 +0200
Subject: ipv4: IP_TOS and IP_TTL can be specified as ancillary data

This patch enables the IP_TTL and IP_TOS values passed from userspace to
be stored in the ipcm_cookie struct. Three fields are added to the struct:

- the TTL, expressed as __u8.
  The allowed values are in the [1-255].
  A value of 0 means that the TTL is not specified.

- the TOS, expressed as __s16.
  The allowed values are in the range [0,255].
  A value of -1 means that the TOS is not specified.

- the priority, expressed as a char and computed when
  handling the ancillary data.

Signed-off-by: Francesco Fusco <ffusco@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       |  3 +++
 net/ipv4/ip_sockglue.c | 20 +++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index c1f192b8cd0e..0135f3823e66 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -56,6 +56,9 @@ struct ipcm_cookie {
 	int			oif;
 	struct ip_options_rcu	*opt;
 	__u8			tx_flags;
+	__u8			ttl;
+	__s16			tos;
+	char			priority;
 };
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f113d709..56e34457ac07 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(ip_cmsg_recv);
 
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
 {
-	int err;
+	int err, val;
 	struct cmsghdr *cmsg;
 
 	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
@@ -215,6 +215,24 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc)
 			ipc->addr = info->ipi_spec_dst.s_addr;
 			break;
 		}
+		case IP_TTL:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 1 || val > 255)
+				return -EINVAL;
+			ipc->ttl = val;
+			break;
+		case IP_TOS:
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
+				return -EINVAL;
+			val = *(int *)CMSG_DATA(cmsg);
+			if (val < 0 || val > 255)
+				return -EINVAL;
+			ipc->tos = val;
+			ipc->priority = rt_tos2priority(ipc->tos);
+			break;
+
 		default:
 			return -EINVAL;
 		}
-- 
cgit 


From aa6615814533c634190019ee3a5b10490026d545 Mon Sep 17 00:00:00 2001
From: Francesco Fusco <ffusco@redhat.com>
Date: Tue, 24 Sep 2013 15:43:09 +0200
Subject: ipv4: processing ancillary IP_TOS or IP_TTL

If IP_TOS or IP_TTL are specified as ancillary data, then sendmsg() sends out
packets with the specified TTL or TOS overriding the socket values specified
with the traditional setsockopt().

The struct inet_cork stores the values of TOS, TTL and priority that are
passed through the struct ipcm_cookie. If there are user-specified TOS
(tos != -1) or TTL (ttl != 0) in the struct ipcm_cookie, these values are
used to override the per-socket values. In case of TOS also the priority
is changed accordingly.

Two helper functions get_rttos and get_rtconn_flags are defined to take
into account the presence of a user specified TOS value when computing
RT_TOS and RT_CONN_FLAGS.

Signed-off-by: Francesco Fusco <ffusco@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  3 +++
 include/net/ip.h        | 11 +++++++++++
 include/net/route.h     |  1 +
 net/ipv4/icmp.c         |  5 +++++
 net/ipv4/ip_output.c    | 13 ++++++++++---
 net/ipv4/ping.c         |  4 +++-
 net/ipv4/raw.c          |  4 +++-
 net/ipv4/udp.c          |  4 +++-
 8 files changed, 39 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 636d203727a2..f3141773c14d 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -103,6 +103,9 @@ struct inet_cork {
 	int			length; /* Total length of all frames */
 	struct dst_entry	*dst;
 	u8			tx_flags;
+	__u8			ttl;
+	__s16			tos;
+	char			priority;
 };
 
 struct inet_cork_full {
diff --git a/include/net/ip.h b/include/net/ip.h
index 0135f3823e66..77b4f9b57c28 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -28,6 +28,7 @@
 #include <linux/skbuff.h>
 
 #include <net/inet_sock.h>
+#include <net/route.h>
 #include <net/snmp.h>
 #include <net/flow.h>
 
@@ -140,6 +141,16 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
 
+static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
+{
+	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
+}
+
+static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk)
+{
+	return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk);
+}
+
 /* datagram.c */
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
diff --git a/include/net/route.h b/include/net/route.h
index 6f572ca66d25..0ad8e0102386 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -39,6 +39,7 @@
 #define RTO_ONLINK	0x01
 
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
+#define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
 struct fib_nh;
 struct fib_info;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5f7d11a45871..5c0e8bc6e5ba 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -353,6 +353,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	saddr = fib_compute_spec_dst(skb);
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
+
 	if (icmp_param->replyopts.opt.opt.optlen) {
 		ipc.opt = &icmp_param->replyopts.opt;
 		if (ipc.opt->opt.srr)
@@ -608,6 +611,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param->replyopts.opt;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
 			       type, code, icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a04d872c54f9..7d8357bb2ba6 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1060,6 +1060,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			 rt->dst.dev->mtu : dst_mtu(&rt->dst);
 	cork->dst = &rt->dst;
 	cork->length = 0;
+	cork->ttl = ipc->ttl;
+	cork->tos = ipc->tos;
+	cork->priority = ipc->priority;
 	cork->tx_flags = ipc->tx_flags;
 
 	return 0;
@@ -1311,7 +1314,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	if (cork->flags & IPCORK_OPT)
 		opt = cork->opt;
 
-	if (rt->rt_type == RTN_MULTICAST)
+	if (cork->ttl != 0)
+		ttl = cork->ttl;
+	else if (rt->rt_type == RTN_MULTICAST)
 		ttl = inet->mc_ttl;
 	else
 		ttl = ip_select_ttl(inet, &rt->dst);
@@ -1319,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph = ip_hdr(skb);
 	iph->version = 4;
 	iph->ihl = 5;
-	iph->tos = inet->tos;
+	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;
 	iph->frag_off = df;
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
@@ -1331,7 +1336,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
 
-	skb->priority = sk->sk_priority;
+	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
 	skb->mark = sk->sk_mark;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
@@ -1481,6 +1486,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	ipc.addr = daddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index d7d9882d4cae..706d108e128c 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -713,6 +713,8 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ipc.opt = NULL;
 	ipc.oif = sk->sk_bound_dev_if;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	sock_tx_timestamp(sk, &ipc.tx_flags);
 
@@ -744,7 +746,7 @@ int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			return -EINVAL;
 		faddr = ipc.opt->opt.faddr;
 	}
-	tos = RT_TOS(inet->tos);
+	tos = get_rttos(&ipc, inet);
 	if (sock_flag(sk, SOCK_LOCALROUTE) ||
 	    (msg->msg_flags & MSG_DONTROUTE) ||
 	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bfec521c717f..a3fe534c968e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -517,6 +517,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 	ipc.oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
@@ -556,7 +558,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			daddr = ipc.opt->opt.faddr;
 		}
 	}
-	tos = RT_CONN_FLAGS(sk);
+	tos = get_rtconn_flags(&ipc, sk);
 	if (msg->msg_flags & MSG_DONTROUTE)
 		tos |= RTO_ONLINK;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 74d2c95db57f..22462d947750 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -855,6 +855,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
@@ -938,7 +940,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
-	tos = RT_TOS(inet->tos);
+	tos = get_rttos(&ipc, inet);
 	if (sock_flag(sk, SOCK_LOCALROUTE) ||
 	    (msg->msg_flags & MSG_DONTROUTE) ||
 	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
-- 
cgit 


From 62748f32d501f5d3712a7c372bbb92abc7c62bc7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 24 Sep 2013 08:20:52 -0700
Subject: net: introduce SO_MAX_PACING_RATE

As mentioned in commit afe4fd062416b ("pkt_sched: fq: Fair Queue packet
scheduler"), this patch adds a new socket option.

SO_MAX_PACING_RATE offers the application the ability to cap the
rate computed by transport layer. Value is in bytes per second.

u32 val = 1000000;
setsockopt(sockfd, SOL_SOCKET, SO_MAX_PACING_RATE, &val, sizeof(val));

To be effectively paced, a flow must use FQ packet scheduler.

Note that a packet scheduler takes into account the headers for its
computations. The effective payload rate depends on MSS and retransmits
if any.

I chose to make this pacing rate a SOL_SOCKET option instead of a
TCP one because this can be used by other protocols.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steinar H. Gunderson <sesse@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/socket.h   |  4 +++-
 arch/avr32/include/uapi/asm/socket.h   |  2 ++
 arch/cris/include/uapi/asm/socket.h    |  2 ++
 arch/frv/include/uapi/asm/socket.h     |  2 ++
 arch/h8300/include/uapi/asm/socket.h   |  2 ++
 arch/ia64/include/uapi/asm/socket.h    |  2 ++
 arch/m32r/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h    |  2 ++
 arch/mn10300/include/uapi/asm/socket.h |  2 ++
 arch/parisc/include/uapi/asm/socket.h  |  2 ++
 arch/powerpc/include/uapi/asm/socket.h |  2 ++
 arch/s390/include/uapi/asm/socket.h    |  2 ++
 arch/sparc/include/uapi/asm/socket.h   |  2 ++
 arch/xtensa/include/uapi/asm/socket.h  |  2 ++
 include/net/sock.h                     |  1 +
 include/uapi/asm-generic/socket.h      |  2 ++
 net/core/sock.c                        | 12 ++++++++++++
 net/ipv4/tcp_input.c                   |  2 +-
 18 files changed, 45 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 467de010ea7e..e3a1491d5073 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -81,6 +81,8 @@
 
 #define SO_SELECT_ERR_QUEUE	45
 
-#define SO_BUSY_POLL			46
+#define SO_BUSY_POLL		46
+
+#define SO_MAX_PACING_RATE	47
 
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 11c4259c62fb..439936421434 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -76,4 +76,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* __ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index eb723e51554e..13829aaaeec5 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -78,6 +78,8 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index f0cb1c341163..5d4299762426 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -76,5 +76,7 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h
index 9490758c5e2b..214ccaf3554a 100644
--- a/arch/h8300/include/uapi/asm/socket.h
+++ b/arch/h8300/include/uapi/asm/socket.h
@@ -76,4 +76,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 556d0701a155..c25302fb48d9 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 24be7c8da86a..52966650114f 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -76,4 +76,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 61c01f054d1b..0df9787cd84d 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -94,4 +94,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index e2a2b203eb00..71dedcae55a6 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -76,4 +76,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 71700e636a8e..7c614d01f1fa 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -75,6 +75,8 @@
 
 #define SO_BUSY_POLL		0x4027
 
+#define SO_MAX_PACING_RATE	0x4048
+
 /* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
  * have to define SOCK_NONBLOCK to a different value here.
  */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index a6d74467c9ed..fa698324a1fd 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -83,4 +83,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 92494494692e..c286c2e868f0 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -82,4 +82,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 4e1d66c3ce71..0f21e9a5ca18 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -72,6 +72,8 @@
 
 #define SO_BUSY_POLL		0x0030
 
+#define SO_MAX_PACING_RATE	0x0031
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index c114483010c1..7db5c22faa68 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 4625d2eff461..240aa3f08cd6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -363,6 +363,7 @@ struct sock {
 	int			sk_wmem_queued;
 	gfp_t			sk_allocation;
 	u32			sk_pacing_rate; /* bytes per second */
+	u32			sk_max_pacing_rate;
 	netdev_features_t	sk_route_caps;
 	netdev_features_t	sk_route_nocaps;
 	int			sk_gso_type;
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index f04b69b6abf2..38f14d0264c3 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -78,4 +78,6 @@
 
 #define SO_BUSY_POLL		46
 
+#define SO_MAX_PACING_RATE	47
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 5b6beba494a3..2bd9b3faa0d0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -914,6 +914,13 @@ set_rcvbuf:
 		}
 		break;
 #endif
+
+	case SO_MAX_PACING_RATE:
+		sk->sk_max_pacing_rate = val;
+		sk->sk_pacing_rate = min(sk->sk_pacing_rate,
+					 sk->sk_max_pacing_rate);
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1177,6 +1184,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 #endif
 
+	case SO_MAX_PACING_RATE:
+		v.val = sk->sk_max_pacing_rate;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -2319,6 +2330,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_ll_usec		=	sysctl_net_busy_read;
 #endif
 
+	sk->sk_max_pacing_rate = ~0U;
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5d083855c111..66aa816ad30b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -735,7 +735,7 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	if (tp->srtt > 8 + 2)
 		do_div(rate, tp->srtt);
 
-	sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+	sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate);
 }
 
 /* Calculate rto without backoff.  This is the second half of Van Jacobson's
-- 
cgit 


From 74227e65f9742f559f6e243ba2c9a983e1f1221d Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Tue, 17 Sep 2013 00:32:34 +0200
Subject: clk: nomadik: declare OF clock provider

Common clock framework allows to register clock providers to get called
on of_clk_init() by using CLK_OF_DECLARE. This converts nomadik clock
provider to make use of it and get rid of the mach specific clk init
call. As clocks require system reset controller base address to be
initialized each clock driver checks src_base and calls new
nomadik_src_init if required.

Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Mike Turquette <mturquette@linaro.org>
---
 arch/arm/mach-nomadik/cpu-8815.c          |  5 ++--
 drivers/clk/clk-nomadik.c                 | 45 +++++++++++--------------------
 include/linux/platform_data/clk-nomadik.h |  2 --
 3 files changed, 17 insertions(+), 35 deletions(-)
 delete mode 100644 include/linux/platform_data/clk-nomadik.h

(limited to 'include')

diff --git a/arch/arm/mach-nomadik/cpu-8815.c b/arch/arm/mach-nomadik/cpu-8815.c
index 0fcb14966d5a..2be38a00a3d9 100644
--- a/arch/arm/mach-nomadik/cpu-8815.c
+++ b/arch/arm/mach-nomadik/cpu-8815.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/irq.h>
 #include <linux/dma-mapping.h>
-#include <linux/platform_data/clk-nomadik.h>
+#include <linux/clk-provider.h>
 #include <linux/clocksource.h>
 #include <linux/of_irq.h>
 #include <linux/of_gpio.h>
@@ -115,8 +115,7 @@ static void cpu8815_restart(enum reboot_mode mode, const char *cmd)
 
 static void __init cpu8815_timer_init_of(void)
 {
-	/* We need this to be up now */
-	nomadik_clk_init();
+	of_clk_init(NULL);
 	clocksource_of_init();
 }
 
diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c
index 06b29c264dbe..ce2d6b32e3f5 100644
--- a/drivers/clk/clk-nomadik.c
+++ b/drivers/clk/clk-nomadik.c
@@ -512,6 +512,9 @@ static void __init of_nomadik_pll_setup(struct device_node *np)
 	const char *parent_name;
 	u32 pll_id;
 
+	if (!src_base)
+		nomadik_src_init();
+
 	if (of_property_read_u32(np, "pll-id", &pll_id)) {
 		pr_err("%s: PLL \"%s\" missing pll-id property\n",
 			__func__, clk_name);
@@ -522,6 +525,8 @@ static void __init of_nomadik_pll_setup(struct device_node *np)
 	if (!IS_ERR(clk))
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(nomadik_pll_clk,
+	"st,nomadik-pll-clock", of_nomadik_pll_setup);
 
 static void __init of_nomadik_hclk_setup(struct device_node *np)
 {
@@ -529,6 +534,9 @@ static void __init of_nomadik_hclk_setup(struct device_node *np)
 	const char *clk_name = np->name;
 	const char *parent_name;
 
+	if (!src_base)
+		nomadik_src_init();
+
 	parent_name = of_clk_get_parent_name(np, 0);
 	/*
 	 * The HCLK divides PLL1 with 1 (passthru), 2, 3 or 4.
@@ -541,6 +549,8 @@ static void __init of_nomadik_hclk_setup(struct device_node *np)
 	if (!IS_ERR(clk))
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(nomadik_hclk_clk,
+	"st,nomadik-hclk-clock", of_nomadik_hclk_setup);
 
 static void __init of_nomadik_src_clk_setup(struct device_node *np)
 {
@@ -549,6 +559,9 @@ static void __init of_nomadik_src_clk_setup(struct device_node *np)
 	const char *parent_name;
 	u32 clk_id;
 
+	if (!src_base)
+		nomadik_src_init();
+
 	if (of_property_read_u32(np, "clock-id", &clk_id)) {
 		pr_err("%s: SRC clock \"%s\" missing clock-id property\n",
 			__func__, clk_name);
@@ -559,33 +572,5 @@ static void __init of_nomadik_src_clk_setup(struct device_node *np)
 	if (!IS_ERR(clk))
 		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
-
-static const struct of_device_id nomadik_src_clk_match[] __initconst = {
-	{
-		.compatible = "fixed-clock",
-		.data = of_fixed_clk_setup,
-	},
-	{
-		.compatible = "fixed-factor-clock",
-		.data = of_fixed_factor_clk_setup,
-	},
-	{
-		.compatible = "st,nomadik-pll-clock",
-		.data = of_nomadik_pll_setup,
-	},
-	{
-		.compatible = "st,nomadik-hclk-clock",
-		.data = of_nomadik_hclk_setup,
-	},
-	{
-		.compatible = "st,nomadik-src-clock",
-		.data = of_nomadik_src_clk_setup,
-	},
-	{ /* sentinel */ }
-};
-
-void __init nomadik_clk_init(void)
-{
-	nomadik_src_init();
-	of_clk_init(nomadik_src_clk_match);
-}
+CLK_OF_DECLARE(nomadik_src_clk,
+	"st,nomadik-src-clock", of_nomadik_src_clk_setup);
diff --git a/include/linux/platform_data/clk-nomadik.h b/include/linux/platform_data/clk-nomadik.h
deleted file mode 100644
index 5713c87b2477..000000000000
--- a/include/linux/platform_data/clk-nomadik.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* Minimal platform data header */
-void nomadik_clk_init(void);
-- 
cgit 


From be0804513a506de96925f9ed1aa8dc1facd4c180 Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Fri, 6 Sep 2013 14:59:57 +0200
Subject: clk: sunxi: declare OF clock provider

Common clock framework allows to register clock providers to get called
on of_clk_init() by using CLK_OF_DECLARE. This converts sunxi clock
providers to make use of it and get rid of the mach specific clk init
call. As sunxi has a bunch of independent clk provider nodes, we hook
current clock init to board compatible to make it called once.

Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
---
 arch/arm/mach-sunxi/sunxi.c   |  4 +---
 drivers/clk/sunxi/clk-sunxi.c | 11 ++++++-----
 include/linux/clk/sunxi.h     | 22 ----------------------
 3 files changed, 7 insertions(+), 30 deletions(-)
 delete mode 100644 include/linux/clk/sunxi.h

(limited to 'include')

diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index e79fb3469341..e5a69756427b 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -20,8 +20,6 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 
-#include <linux/clk/sunxi.h>
-
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/system_misc.h>
@@ -118,7 +116,7 @@ static void sunxi_setup_restart(void)
 
 static void __init sunxi_timer_init(void)
 {
-	sunxi_init_clocks();
+	of_clk_init(NULL);
 	clocksource_of_init();
 }
 
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 34ee69f4d50c..9bbd03514540 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -16,7 +16,6 @@
 
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
-#include <linux/clk/sunxi.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
@@ -617,11 +616,8 @@ static void __init of_sunxi_table_clock_setup(const struct of_device_id *clk_mat
 	}
 }
 
-void __init sunxi_init_clocks(void)
+static void __init sunxi_init_clocks(struct device_node *np)
 {
-	/* Register all the simple and basic clocks on DT */
-	of_clk_init(NULL);
-
 	/* Register factor clocks */
 	of_sunxi_table_clock_setup(clk_factors_match, sunxi_factors_clk_setup);
 
@@ -634,3 +630,8 @@ void __init sunxi_init_clocks(void)
 	/* Register gate clocks */
 	of_sunxi_table_clock_setup(clk_gates_match, sunxi_gates_clk_setup);
 }
+CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sunxi_init_clocks);
+CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sunxi_init_clocks);
+CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sunxi_init_clocks);
+CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sunxi_init_clocks);
+CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sunxi_init_clocks);
diff --git a/include/linux/clk/sunxi.h b/include/linux/clk/sunxi.h
deleted file mode 100644
index e074fdd5a236..000000000000
--- a/include/linux/clk/sunxi.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright 2012 Maxime Ripard
- *
- * Maxime Ripard <maxime.ripard@free-electrons.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __LINUX_CLK_SUNXI_H_
-#define __LINUX_CLK_SUNXI_H_
-
-void __init sunxi_init_clocks(void);
-
-#endif
-- 
cgit 


From dd03ee9ae5bc080297175c921b1a693d0de1e8b0 Mon Sep 17 00:00:00 2001
From: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Date: Wed, 4 Sep 2013 13:16:01 +0200
Subject: ARM: mxs: remove custom .init_time hook

This patch converts clk-imx2[38] clocksource_of_init compatible init
associated with fsl,imx2[38]-clkctrl. With arch/arm calling
of_clk_init(NULL) from time_init(), we can now also remove custom
.init_time hooks.

Signed-off-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
---
 arch/arm/mach-mxs/mach-mxs.c | 13 -------------
 drivers/clk/mxs/clk-imx23.c  | 15 ++++++++-------
 drivers/clk/mxs/clk-imx28.c  | 16 ++++++++--------
 include/linux/clk/mxs.h      |  2 --
 4 files changed, 16 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 98f6e2adb53e..cc511a4890a3 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -13,8 +13,6 @@
 #include <linux/clk.h>
 #include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
-#include <linux/clocksource.h>
-#include <linux/clk-provider.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
@@ -490,16 +488,6 @@ static void mxs_restart(enum reboot_mode mode, const char *cmd)
 	soft_restart(0);
 }
 
-static void __init mxs_timer_init(void)
-{
-	if (of_machine_is_compatible("fsl,imx23"))
-		mx23_clocks_init();
-	else
-		mx28_clocks_init();
-	of_clk_init(NULL);
-	clocksource_of_init();
-}
-
 static const char *mxs_dt_compat[] __initdata = {
 	"fsl,imx28",
 	"fsl,imx23",
@@ -508,7 +496,6 @@ static const char *mxs_dt_compat[] __initdata = {
 
 DT_MACHINE_START(MXS, "Freescale MXS (Device Tree)")
 	.handle_irq	= icoll_handle_irq,
-	.init_time	= mxs_timer_init,
 	.init_machine	= mxs_machine_init,
 	.init_late      = mxs_pm_init,
 	.dt_compat	= mxs_dt_compat,
diff --git a/drivers/clk/mxs/clk-imx23.c b/drivers/clk/mxs/clk-imx23.c
index c396fe361589..9fc9359f5133 100644
--- a/drivers/clk/mxs/clk-imx23.c
+++ b/drivers/clk/mxs/clk-imx23.c
@@ -12,6 +12,7 @@
 #include <linux/clk.h>
 #include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
+#include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -100,16 +101,16 @@ static enum imx23_clk clks_init_on[] __initdata = {
 	cpu, hbus, xbus, emi, uart,
 };
 
-int __init mx23_clocks_init(void)
+static void __init mx23_clocks_init(struct device_node *np)
 {
-	struct device_node *np;
+	struct device_node *dcnp;
 	u32 i;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx23-digctl");
-	digctrl = of_iomap(np, 0);
+	dcnp = of_find_compatible_node(NULL, NULL, "fsl,imx23-digctl");
+	digctrl = of_iomap(dcnp, 0);
 	WARN_ON(!digctrl);
+	of_node_put(dcnp);
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx23-clkctrl");
 	clkctrl = of_iomap(np, 0);
 	WARN_ON(!clkctrl);
 
@@ -162,7 +163,7 @@ int __init mx23_clocks_init(void)
 		if (IS_ERR(clks[i])) {
 			pr_err("i.MX23 clk %d: register failed with %ld\n",
 				i, PTR_ERR(clks[i]));
-			return PTR_ERR(clks[i]);
+			return;
 		}
 
 	clk_data.clks = clks;
@@ -172,5 +173,5 @@ int __init mx23_clocks_init(void)
 	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
 		clk_prepare_enable(clks[clks_init_on[i]]);
 
-	return 0;
 }
+CLK_OF_DECLARE(imx23_clkctrl, "fsl,imx23-clkctrl", mx23_clocks_init);
diff --git a/drivers/clk/mxs/clk-imx28.c b/drivers/clk/mxs/clk-imx28.c
index 4faf0afc44cd..a6c35010e4e5 100644
--- a/drivers/clk/mxs/clk-imx28.c
+++ b/drivers/clk/mxs/clk-imx28.c
@@ -12,6 +12,7 @@
 #include <linux/clk.h>
 #include <linux/clk/mxs.h>
 #include <linux/clkdev.h>
+#include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -154,16 +155,16 @@ static enum imx28_clk clks_init_on[] __initdata = {
 	cpu, hbus, xbus, emi, uart,
 };
 
-int __init mx28_clocks_init(void)
+static void __init mx28_clocks_init(struct device_node *np)
 {
-	struct device_node *np;
+	struct device_node *dcnp;
 	u32 i;
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx28-digctl");
-	digctrl = of_iomap(np, 0);
+	dcnp = of_find_compatible_node(NULL, NULL, "fsl,imx28-digctl");
+	digctrl = of_iomap(dcnp, 0);
 	WARN_ON(!digctrl);
+	of_node_put(dcnp);
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,imx28-clkctrl");
 	clkctrl = of_iomap(np, 0);
 	WARN_ON(!clkctrl);
 
@@ -239,7 +240,7 @@ int __init mx28_clocks_init(void)
 		if (IS_ERR(clks[i])) {
 			pr_err("i.MX28 clk %d: register failed with %ld\n",
 				i, PTR_ERR(clks[i]));
-			return PTR_ERR(clks[i]);
+			return;
 		}
 
 	clk_data.clks = clks;
@@ -250,6 +251,5 @@ int __init mx28_clocks_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
 		clk_prepare_enable(clks[clks_init_on[i]]);
-
-	return 0;
 }
+CLK_OF_DECLARE(imx28_clkctrl, "fsl,imx28-clkctrl", mx28_clocks_init);
diff --git a/include/linux/clk/mxs.h b/include/linux/clk/mxs.h
index 90c30dc3efc7..5138a90e018c 100644
--- a/include/linux/clk/mxs.h
+++ b/include/linux/clk/mxs.h
@@ -9,8 +9,6 @@
 #ifndef __LINUX_CLK_MXS_H
 #define __LINUX_CLK_MXS_H
 
-int mx23_clocks_init(void);
-int mx28_clocks_init(void);
 int mxs_saif_clkmux_select(unsigned int clkmux);
 
 #endif
-- 
cgit 


From 25f73ed5c67d17ecf8cefd560f55211cce726086 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Fri, 27 Sep 2013 15:06:28 -0400
Subject: misc: (at24) move header to linux/platform_data/

This patch moves the at24.h header from include/linux/i2c to
include/linux/platform_data and updates existing support accordingly.

It also fixes the following checkpatch warning:

    WARNING: please, no space before tabs
    #436: FILE: include/linux/platform_data/at24.h:31:
    + * ^Iu8 *mac_addr = ethernet_pdata->mac_addr;$

Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 MAINTAINERS                                |  2 +-
 arch/arm/mach-at91/board-sam9260ek.c       |  2 +-
 arch/arm/mach-at91/board-sam9263ek.c       |  2 +-
 arch/arm/mach-davinci/board-da830-evm.c    |  2 +-
 arch/arm/mach-davinci/board-da850-evm.c    |  2 +-
 arch/arm/mach-davinci/board-dm365-evm.c    |  2 +-
 arch/arm/mach-davinci/board-dm644x-evm.c   |  2 +-
 arch/arm/mach-davinci/board-dm646x-evm.c   |  2 +-
 arch/arm/mach-davinci/board-mityomapl138.c |  2 +-
 arch/arm/mach-davinci/board-sffsdr.c       |  2 +-
 arch/arm/mach-imx/mach-pca100.c            |  2 +-
 arch/arm/mach-imx/mach-pcm037.c            |  2 +-
 arch/arm/mach-imx/mach-pcm038.c            |  2 +-
 arch/arm/mach-imx/mach-pcm043.c            |  2 +-
 arch/arm/mach-imx/mach-vpr200.c            |  2 +-
 arch/arm/mach-kirkwood/lacie_v2-common.c   |  2 +-
 arch/arm/mach-omap1/board-osk.c            |  2 +-
 arch/arm/mach-omap2/board-cm-t35.c         |  2 +-
 arch/arm/mach-omap2/board-h4.c             |  2 +-
 arch/arm/mach-omap2/board-omap3stalker.c   |  2 +-
 arch/arm/mach-pxa/stargate2.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-mini2440.c      |  2 +-
 drivers/misc/eeprom/at24.c                 |  2 +-
 include/linux/i2c/at24.h                   | 55 ------------------------------
 include/linux/platform_data/at24.h         | 55 ++++++++++++++++++++++++++++++
 25 files changed, 78 insertions(+), 78 deletions(-)
 delete mode 100644 include/linux/i2c/at24.h
 create mode 100644 include/linux/platform_data/at24.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 284969fa2896..b9d19a7f3144 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1396,7 +1396,7 @@ M:	Wolfram Sang <wsa@the-dreams.de>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/misc/eeprom/at24.c
-F:	include/linux/i2c/at24.h
+F:	include/linux/platform_data/at24.h
 
 ATA OVER ETHERNET (AOE) DRIVER
 M:	"Ed L. Cashin" <ecashin@coraid.com>
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index 0b153c87521d..f4f8735315da 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -28,7 +28,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/at73c213.h>
 #include <linux/clk.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 3284df05df14..947e134ac4c3 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -27,7 +27,7 @@
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/fb.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index c4bdc0a1c36e..66b5b3cb5376 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -17,7 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pcf857x.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/spi/spi.h>
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index dd1fb24521aa..f25a569b0009 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -18,7 +18,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/input.h>
 #include <linux/input/tps6507x-ts.h>
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 92b7f770615a..30ee81fac925 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -18,7 +18,7 @@
 #include <linux/i2c.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/leds.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 40bb9b5b87e8..f21fde9dce00 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -15,7 +15,7 @@
 #include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/i2c/pcf857x.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 2bc3651d56cc..db2df32da6a8 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -22,7 +22,7 @@
 #include <linux/gpio.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/i2c/pcf857x.h>
 
 #include <media/tvp514x.h>
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index cd0f58730c2b..7aa105b1fd0f 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -15,7 +15,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/regulator/machine.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/etherdevice.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c
index d84360148100..41c7c9615791 100644
--- a/arch/arm/mach-davinci/board-sffsdr.c
+++ b/arch/arm/mach-davinci/board-sffsdr.c
@@ -26,7 +26,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c
index 19bb6441a7d4..c5f95674e9b7 100644
--- a/arch/arm/mach-imx/mach-pca100.c
+++ b/arch/arm/mach-imx/mach-pca100.c
@@ -20,7 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/dma-mapping.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/eeprom.h>
diff --git a/arch/arm/mach-imx/mach-pcm037.c b/arch/arm/mach-imx/mach-pcm037.c
index bc0261e99d39..20cc53f4cee1 100644
--- a/arch/arm/mach-imx/mach-pcm037.c
+++ b/arch/arm/mach-imx/mach-pcm037.c
@@ -23,7 +23,7 @@
 #include <linux/smsc911x.h>
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/irq.h>
diff --git a/arch/arm/mach-imx/mach-pcm038.c b/arch/arm/mach-imx/mach-pcm038.c
index e805ac273e9c..592ddbe031ac 100644
--- a/arch/arm/mach-imx/mach-pcm038.c
+++ b/arch/arm/mach-imx/mach-pcm038.c
@@ -18,7 +18,7 @@
  */
 
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/io.h>
 #include <linux/mtd/plat-ram.h>
 #include <linux/mtd/physmap.h>
diff --git a/arch/arm/mach-imx/mach-pcm043.c b/arch/arm/mach-imx/mach-pcm043.c
index b726cb1c5fdd..ac504b67326b 100644
--- a/arch/arm/mach-imx/mach-pcm043.c
+++ b/arch/arm/mach-imx/mach-pcm043.c
@@ -24,7 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
 
diff --git a/arch/arm/mach-imx/mach-vpr200.c b/arch/arm/mach-imx/mach-vpr200.c
index 0910761e8280..8825d1217d18 100644
--- a/arch/arm/mach-imx/mach-vpr200.c
+++ b/arch/arm/mach-imx/mach-vpr200.c
@@ -29,7 +29,7 @@
 #include <asm/mach/time.h>
 
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/mfd/mc13xxx.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-kirkwood/lacie_v2-common.c b/arch/arm/mach-kirkwood/lacie_v2-common.c
index 489495976fcd..8e3e4331c380 100644
--- a/arch/arm/mach-kirkwood/lacie_v2-common.c
+++ b/arch/arm/mach-kirkwood/lacie_v2-common.c
@@ -12,7 +12,7 @@
 #include <linux/spi/flash.h>
 #include <linux/spi/spi.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/gpio.h>
 #include <asm/mach/time.h>
 #include <mach/kirkwood.h>
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index a7ce69286688..d68909b095f1 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -300,7 +300,7 @@ static struct omap_lcd_config osk_lcd_config __initdata = {
 #ifdef	CONFIG_OMAP_OSK_MISTRAL
 
 #include <linux/input.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index 33d159e2386e..8dd0ec858cf1 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -25,7 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/i2c/twl.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c
index 87e41a8b8d46..f7808349a734 100644
--- a/arch/arm/mach-omap2/board-h4.c
+++ b/arch/arm/mach-omap2/board-h4.c
@@ -20,7 +20,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/input.h>
 #include <linux/err.h>
 #include <linux/clk.h>
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index ba8342fef799..119efaf5808a 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -32,7 +32,7 @@
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/smsc911x.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/usb/phy.h>
 
 #include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c
index 62aea3e835f3..01de542432a6 100644
--- a/arch/arm/mach-pxa/stargate2.c
+++ b/arch/arm/mach-pxa/stargate2.c
@@ -27,7 +27,7 @@
 
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/i2c/pcf857x.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/smc91x.h>
 #include <linux/gpio.h>
 #include <linux/leds.h>
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index a83db46320bc..4a18d49a63e0 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -24,7 +24,7 @@
 #include <linux/io.h>
 #include <linux/serial_core.h>
 #include <linux/dm9000.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 #include <linux/platform_device.h>
 #include <linux/gpio_keys.h>
 #include <linux/i2c.h>
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 5d4fd69d04ca..4ef01ab67853 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -22,7 +22,7 @@
 #include <linux/jiffies.h>
 #include <linux/of.h>
 #include <linux/i2c.h>
-#include <linux/i2c/at24.h>
+#include <linux/platform_data/at24.h>
 
 /*
  * I2C EEPROMs from most vendors are inexpensive and mostly interchangeable.
diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h
deleted file mode 100644
index 285025a9cdc9..000000000000
--- a/include/linux/i2c/at24.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * at24.h - platform_data for the at24 (generic eeprom) driver
- * (C) Copyright 2008 by Pengutronix
- * (C) Copyright 2012 by Wolfram Sang
- * same license as the driver
- */
-
-#ifndef _LINUX_AT24_H
-#define _LINUX_AT24_H
-
-#include <linux/types.h>
-#include <linux/memory.h>
-
-/**
- * struct at24_platform_data - data to set up at24 (generic eeprom) driver
- * @byte_len: size of eeprom in byte
- * @page_size: number of byte which can be written in one go
- * @flags: tunable options, check AT24_FLAG_* defines
- * @setup: an optional callback invoked after eeprom is probed; enables kernel
-	code to access eeprom via memory_accessor, see example
- * @context: optional parameter passed to setup()
- *
- * If you set up a custom eeprom type, please double-check the parameters.
- * Especially page_size needs extra care, as you risk data loss if your value
- * is bigger than what the chip actually supports!
- *
- * An example in pseudo code for a setup() callback:
- *
- * void get_mac_addr(struct memory_accessor *mem_acc, void *context)
- * {
- * 	u8 *mac_addr = ethernet_pdata->mac_addr;
- *	off_t offset = context;
- *
- *	// Read MAC addr from EEPROM
- *	if (mem_acc->read(mem_acc, mac_addr, offset, ETH_ALEN) == ETH_ALEN)
- *		pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr);
- * }
- *
- * This function pointer and context can now be set up in at24_platform_data.
- */
-
-struct at24_platform_data {
-	u32		byte_len;		/* size (sum of all addr) */
-	u16		page_size;		/* for writes */
-	u8		flags;
-#define AT24_FLAG_ADDR16	0x80	/* address pointer is 16 bit */
-#define AT24_FLAG_READONLY	0x40	/* sysfs-entry will be read-only */
-#define AT24_FLAG_IRUGO		0x20	/* sysfs-entry will be world-readable */
-#define AT24_FLAG_TAKE8ADDR	0x10	/* take always 8 addresses (24c00) */
-
-	void		(*setup)(struct memory_accessor *, void *context);
-	void		*context;
-};
-
-#endif /* _LINUX_AT24_H */
diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h
new file mode 100644
index 000000000000..c42aa89d34ee
--- /dev/null
+++ b/include/linux/platform_data/at24.h
@@ -0,0 +1,55 @@
+/*
+ * at24.h - platform_data for the at24 (generic eeprom) driver
+ * (C) Copyright 2008 by Pengutronix
+ * (C) Copyright 2012 by Wolfram Sang
+ * same license as the driver
+ */
+
+#ifndef _LINUX_AT24_H
+#define _LINUX_AT24_H
+
+#include <linux/types.h>
+#include <linux/memory.h>
+
+/**
+ * struct at24_platform_data - data to set up at24 (generic eeprom) driver
+ * @byte_len: size of eeprom in byte
+ * @page_size: number of byte which can be written in one go
+ * @flags: tunable options, check AT24_FLAG_* defines
+ * @setup: an optional callback invoked after eeprom is probed; enables kernel
+	code to access eeprom via memory_accessor, see example
+ * @context: optional parameter passed to setup()
+ *
+ * If you set up a custom eeprom type, please double-check the parameters.
+ * Especially page_size needs extra care, as you risk data loss if your value
+ * is bigger than what the chip actually supports!
+ *
+ * An example in pseudo code for a setup() callback:
+ *
+ * void get_mac_addr(struct memory_accessor *mem_acc, void *context)
+ * {
+ *	u8 *mac_addr = ethernet_pdata->mac_addr;
+ *	off_t offset = context;
+ *
+ *	// Read MAC addr from EEPROM
+ *	if (mem_acc->read(mem_acc, mac_addr, offset, ETH_ALEN) == ETH_ALEN)
+ *		pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr);
+ * }
+ *
+ * This function pointer and context can now be set up in at24_platform_data.
+ */
+
+struct at24_platform_data {
+	u32		byte_len;		/* size (sum of all addr) */
+	u16		page_size;		/* for writes */
+	u8		flags;
+#define AT24_FLAG_ADDR16	0x80	/* address pointer is 16 bit */
+#define AT24_FLAG_READONLY	0x40	/* sysfs-entry will be read-only */
+#define AT24_FLAG_IRUGO		0x20	/* sysfs-entry will be world-readable */
+#define AT24_FLAG_TAKE8ADDR	0x10	/* take always 8 addresses (24c00) */
+
+	void		(*setup)(struct memory_accessor *, void *context);
+	void		*context;
+};
+
+#endif /* _LINUX_AT24_H */
-- 
cgit 


From 2f303b74a62fb74983c0a66e2df353be963c527c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 25 Sep 2013 13:53:07 +0200
Subject: KVM: Convert kvm_lock back to non-raw spinlock

In commit e935b8372cf8 ("KVM: Convert kvm_lock to raw_spinlock"),
the kvm_lock was made a raw lock.  However, the kvm mmu_shrink()
function tries to grab the (non-raw) mmu_lock within the scope of
the raw locked kvm_lock being held.  This leads to the following:

BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
in_atomic(): 1, irqs_disabled(): 0, pid: 55, name: kswapd0
Preemption disabled at:[<ffffffffa0376eac>] mmu_shrink+0x5c/0x1b0 [kvm]

Pid: 55, comm: kswapd0 Not tainted 3.4.34_preempt-rt
Call Trace:
 [<ffffffff8106f2ad>] __might_sleep+0xfd/0x160
 [<ffffffff817d8d64>] rt_spin_lock+0x24/0x50
 [<ffffffffa0376f3c>] mmu_shrink+0xec/0x1b0 [kvm]
 [<ffffffff8111455d>] shrink_slab+0x17d/0x3a0
 [<ffffffff81151f00>] ? mem_cgroup_iter+0x130/0x260
 [<ffffffff8111824a>] balance_pgdat+0x54a/0x730
 [<ffffffff8111fe47>] ? set_pgdat_percpu_threshold+0xa7/0xd0
 [<ffffffff811185bf>] kswapd+0x18f/0x490
 [<ffffffff81070961>] ? get_parent_ip+0x11/0x50
 [<ffffffff81061970>] ? __init_waitqueue_head+0x50/0x50
 [<ffffffff81118430>] ? balance_pgdat+0x730/0x730
 [<ffffffff81060d2b>] kthread+0xdb/0xe0
 [<ffffffff8106e122>] ? finish_task_switch+0x52/0x100
 [<ffffffff817e1e94>] kernel_thread_helper+0x4/0x10
 [<ffffffff81060c50>] ? __init_kthread_worker+0x

After the previous patch, kvm_lock need not be a raw spinlock anymore,
so change it back.

Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: kvm@vger.kernel.org
Cc: gleb@redhat.com
Cc: jan.kiszka@siemens.com
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/locking.txt |  2 +-
 arch/x86/kvm/mmu.c                    |  5 ++---
 arch/x86/kvm/x86.c                    |  8 ++++----
 include/linux/kvm_host.h              |  2 +-
 virt/kvm/kvm_main.c                   | 18 +++++++++---------
 5 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index ba9e1c2150c2..f8869410d40c 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -132,7 +132,7 @@ See the comments in spte_has_volatile_bits() and mmu_spte_update().
 ------------
 
 Name:		kvm_lock
-Type:		raw_spinlock
+Type:		spinlock_t
 Arch:		any
 Protects:	- vm_list
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index dce0df8150df..cf95cfe050a6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4428,7 +4428,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	int nr_to_scan = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
@@ -4478,9 +4478,8 @@ unlock:
 		break;
 	}
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return freed;
-
 }
 
 static unsigned long
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5ca72a5cdb6..187f824b1454 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5263,7 +5263,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
@@ -5273,7 +5273,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 				send_ipi = 1;
 		}
 	}
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -5426,12 +5426,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 749bdb12cd15..7c961e1e9270 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -142,7 +142,7 @@ struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
-extern raw_spinlock_t kvm_lock;
+extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_io_range {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index eb94343c2ed2..d469114aff09 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -70,7 +70,7 @@ MODULE_LICENSE("GPL");
  * 		kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_RAW_SPINLOCK(kvm_lock);
+DEFINE_SPINLOCK(kvm_lock);
 static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
@@ -491,9 +491,9 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (r)
 		goto out_err;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	return kvm;
 
@@ -582,9 +582,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	struct mm_struct *mm = kvm->mm;
 
 	kvm_arch_sync_events(kvm);
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kvm_io_bus_destroy(kvm->buses[i]);
@@ -3054,10 +3054,10 @@ static int vm_stat_get(void *_offset, u64 *val)
 	struct kvm *kvm;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		*val += *(u32 *)((void *)kvm + offset);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -3071,12 +3071,12 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	int i;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			*val += *(u32 *)((void *)vcpu + offset);
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
-- 
cgit 


From 6dedcca610c6d6189b4a54d32118d1654adb73d2 Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hp.com>
Date: Wed, 25 Sep 2013 15:08:27 -0600
Subject: hotplug, powerpc, x86: Remove cpu_hotplug_driver_lock()

cpu_hotplug_driver_lock() serializes CPU online/offline operations
when ARCH_CPU_PROBE_RELEASE is set.  This lock interface is no longer
necessary with the following reason:

 - lock_device_hotplug() now protects CPU online/offline operations,
   including the probe & release interfaces enabled by
   ARCH_CPU_PROBE_RELEASE.  The use of cpu_hotplug_driver_lock() is
   redundant.
 - cpu_hotplug_driver_lock() is only valid when ARCH_CPU_PROBE_RELEASE
   is defined, which is misleading and is only enabled on powerpc.

This patch removes the cpu_hotplug_driver_lock() interface.  As
a result, ARCH_CPU_PROBE_RELEASE only enables / disables the cpu
probe & release interface as intended.  There is no functional change
in this patch.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Reviewed-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/powerpc/kernel/smp.c              | 12 ----------
 arch/powerpc/platforms/pseries/dlpar.c | 43 +++++++++++++---------------------
 arch/x86/kernel/topology.c             |  2 --
 drivers/base/cpu.c                     | 15 +++---------
 include/linux/cpu.h                    | 13 ----------
 5 files changed, 19 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8e59abc237d7..930cd8af3503 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -844,18 +844,6 @@ void __cpu_die(unsigned int cpu)
 		smp_ops->cpu_die(cpu);
 }
 
-static DEFINE_MUTEX(powerpc_cpu_hotplug_driver_mutex);
-
-void cpu_hotplug_driver_lock()
-{
-	mutex_lock(&powerpc_cpu_hotplug_driver_mutex);
-}
-
-void cpu_hotplug_driver_unlock()
-{
-	mutex_unlock(&powerpc_cpu_hotplug_driver_mutex);
-}
-
 void cpu_die(void)
 {
 	if (ppc_md.cpu_die)
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 7cfdaae1721a..a8fe5aa3d34f 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -404,46 +404,38 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	unsigned long drc_index;
 	int rc;
 
-	cpu_hotplug_driver_lock();
 	rc = strict_strtoul(buf, 0, &drc_index);
-	if (rc) {
-		rc = -EINVAL;
-		goto out;
-	}
+	if (rc)
+		return -EINVAL;
 
 	parent = of_find_node_by_path("/cpus");
-	if (!parent) {
-		rc = -ENODEV;
-		goto out;
-	}
+	if (!parent)
+		return -ENODEV;
 
 	dn = dlpar_configure_connector(drc_index, parent);
-	if (!dn) {
-		rc = -EINVAL;
-		goto out;
-	}
+	if (!dn)
+		return -EINVAL;
 
 	of_node_put(parent);
 
 	rc = dlpar_acquire_drc(drc_index);
 	if (rc) {
 		dlpar_free_cc_nodes(dn);
-		rc = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	rc = dlpar_attach_node(dn);
 	if (rc) {
 		dlpar_release_drc(drc_index);
 		dlpar_free_cc_nodes(dn);
-		goto out;
+		return rc;
 	}
 
 	rc = dlpar_online_cpu(dn);
-out:
-	cpu_hotplug_driver_unlock();
+	if (rc)
+		return rc;
 
-	return rc ? rc : count;
+	return count;
 }
 
 static int dlpar_offline_cpu(struct device_node *dn)
@@ -516,30 +508,27 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 		return -EINVAL;
 	}
 
-	cpu_hotplug_driver_lock();
 	rc = dlpar_offline_cpu(dn);
 	if (rc) {
 		of_node_put(dn);
-		rc = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	rc = dlpar_release_drc(*drc_index);
 	if (rc) {
 		of_node_put(dn);
-		goto out;
+		return rc;
 	}
 
 	rc = dlpar_detach_node(dn);
 	if (rc) {
 		dlpar_acquire_drc(*drc_index);
-		goto out;
+		return rc;
 	}
 
 	of_node_put(dn);
-out:
-	cpu_hotplug_driver_unlock();
-	return rc ? rc : count;
+
+	return count;
 }
 
 static int __init pseries_dlpar_init(void)
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index a3f35ebb3b52..649b010da00b 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -66,7 +66,6 @@ int __ref _debug_hotplug_cpu(int cpu, int action)
 		return -EINVAL;
 
 	lock_device_hotplug();
-	cpu_hotplug_driver_lock();
 
 	switch (action) {
 	case 0:
@@ -91,7 +90,6 @@ int __ref _debug_hotplug_cpu(int cpu, int action)
 		ret = -EINVAL;
 	}
 
-	cpu_hotplug_driver_unlock();
 	unlock_device_hotplug();
 
 	return ret;
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 51f5d7fe2f0b..f48370dfc908 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -44,13 +44,11 @@ static int __ref cpu_subsys_online(struct device *dev)
 	struct cpu *cpu = container_of(dev, struct cpu, dev);
 	int cpuid = dev->id;
 	int from_nid, to_nid;
-	int ret = -ENODEV;
-
-	cpu_hotplug_driver_lock();
+	int ret;
 
 	from_nid = cpu_to_node(cpuid);
 	if (from_nid == NUMA_NO_NODE)
-		goto out;
+		return -ENODEV;
 
 	ret = cpu_up(cpuid);
 	/*
@@ -61,19 +59,12 @@ static int __ref cpu_subsys_online(struct device *dev)
 	if (from_nid != to_nid)
 		change_cpu_under_node(cpu, from_nid, to_nid);
 
- out:
-	cpu_hotplug_driver_unlock();
 	return ret;
 }
 
 static int cpu_subsys_offline(struct device *dev)
 {
-	int ret;
-
-	cpu_hotplug_driver_lock();
-	ret = cpu_down(dev->id);
-	cpu_hotplug_driver_unlock();
-	return ret;
+	return cpu_down(dev->id);
 }
 
 void unregister_cpu(struct cpu *cpu)
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 801ff9e73679..3434ef7de017 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -185,19 +185,6 @@ extern void cpu_hotplug_enable(void);
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
-#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
-extern void cpu_hotplug_driver_lock(void);
-extern void cpu_hotplug_driver_unlock(void);
-#else
-static inline void cpu_hotplug_driver_lock(void)
-{
-}
-
-static inline void cpu_hotplug_driver_unlock(void)
-{
-}
-#endif
-
 #else		/* CONFIG_HOTPLUG_CPU */
 
 static inline void cpu_hotplug_begin(void) {}
-- 
cgit 


From 27047a603645d0885bcd72d7a0b6cce6e3c94ca7 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 16 Sep 2013 18:56:03 +0530
Subject: cpufreq: Add new helper cpufreq_table_validate_and_show()

Almost every cpufreq driver is required to validate its frequency table with:
cpufreq_frequency_table_cpuinfo() and then expose it to cpufreq core with:
cpufreq_frequency_table_get_attr().

This patch creates another helper routine cpufreq_table_validate_and_show() that
will do both these steps in a single call and will return 0 for success, error
otherwise.

This also fixes potential bugs in cpufreq drivers where people have called
cpufreq_frequency_table_get_attr() before calling
cpufreq_frequency_table_cpuinfo(), as the later may fail.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/freq_table.c | 12 ++++++++++++
 include/linux/cpufreq.h      |  2 ++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index f111454a7aea..11f6fa92a58d 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -219,6 +219,18 @@ void cpufreq_frequency_table_put_attr(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
 
+int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
+				      struct cpufreq_frequency_table *table)
+{
+	int ret = cpufreq_frequency_table_cpuinfo(policy, table);
+
+	if (!ret)
+		cpufreq_frequency_table_get_attr(table, policy->cpu);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
+
 void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy)
 {
 	pr_debug("Updating show_table for new_cpu %u from last_cpu %u\n",
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fcabc42d66ab..6b199ed7aa58 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -410,5 +410,7 @@ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
+int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
+				      struct cpufreq_frequency_table *table);
 
 #endif /* _LINUX_CPUFREQ_H */
-- 
cgit 


From a528c219df2e865e178c538c7178961dfed5a13c Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 25 Sep 2013 12:02:44 +0200
Subject: dev: update __dev_notify_flags() to send rtnl msg

This patch only prepares the next one, there is no functional change.
Now, __dev_notify_flags() can also be used to notify flags changes via
rtnetlink.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 +++-
 net/core/dev.c            | 11 ++++++-----
 net/core/rtnetlink.c      |  3 +--
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b4cfb63f264e..f44f99a69977 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2378,7 +2378,9 @@ extern int		dev_ethtool(struct net *net, struct ifreq *);
 extern unsigned int	dev_get_flags(const struct net_device *);
 extern int		__dev_change_flags(struct net_device *, unsigned int flags);
 extern int		dev_change_flags(struct net_device *, unsigned int);
-extern void		__dev_notify_flags(struct net_device *, unsigned int old_flags);
+void			__dev_notify_flags(struct net_device *,
+					   unsigned int old_flags,
+					   unsigned int gchanges);
 extern int		dev_change_name(struct net_device *, const char *);
 extern int		dev_set_alias(struct net_device *, const char *, size_t);
 extern int		dev_change_net_namespace(struct net_device *,
diff --git a/net/core/dev.c b/net/core/dev.c
index 25ab6fe80da2..594a6b0ab3da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5235,10 +5235,14 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags)
 	return ret;
 }
 
-void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
+void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
+			unsigned int gchanges)
 {
 	unsigned int changes = dev->flags ^ old_flags;
 
+	if (gchanges)
+		rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges);
+
 	if (changes & IFF_UP) {
 		if (dev->flags & IFF_UP)
 			call_netdevice_notifiers(NETDEV_UP, dev);
@@ -5274,10 +5278,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags)
 		return ret;
 
 	changes = old_flags ^ dev->flags;
-	if (changes)
-		rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
-
-	__dev_notify_flags(dev, old_flags);
+	__dev_notify_flags(dev, old_flags, changes);
 	return ret;
 }
 EXPORT_SYMBOL(dev_change_flags);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2a0e21de3060..4aedf03da052 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1647,9 +1647,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 	}
 
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
 
-	__dev_notify_flags(dev, old_flags);
+	__dev_notify_flags(dev, old_flags, ~0U);
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
-- 
cgit 


From 35b8dcf8c3a0be1feb1c8b29b22e1685ba0c2e14 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 30 Apr 2013 23:02:43 +0200
Subject: netfilter: ipset: Rename simple macro names to avoid namespace
 issues.

Reported-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      |   3 +
 net/netfilter/ipset/ip_set_bitmap_gen.h     |  47 +++++----
 net/netfilter/ipset/ip_set_bitmap_ip.c      |  10 +-
 net/netfilter/ipset/ip_set_bitmap_ipmac.c   |  10 +-
 net/netfilter/ipset/ip_set_bitmap_port.c    |  10 +-
 net/netfilter/ipset/ip_set_hash_gen.h       | 147 +++++++++++++++-------------
 net/netfilter/ipset/ip_set_hash_ip.c        |  10 +-
 net/netfilter/ipset/ip_set_hash_ipport.c    |  12 +--
 net/netfilter/ipset/ip_set_hash_ipportip.c  |  12 +--
 net/netfilter/ipset/ip_set_hash_ipportnet.c |  16 +--
 net/netfilter/ipset/ip_set_hash_net.c       |  14 +--
 net/netfilter/ipset/ip_set_hash_netiface.c  |  14 +--
 net/netfilter/ipset/ip_set_hash_netport.c   |  16 +--
 net/netfilter/ipset/ip_set_list_set.c       |  10 +-
 14 files changed, 169 insertions(+), 162 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 9ac9fbde7b61..f900f33a5f3d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -398,4 +398,7 @@ bitmap_bytes(u32 a, u32 b)
 	{ .bytes = ULLONG_MAX, .packets = ULLONG_MAX,	\
 	  .timeout = (map)->timeout }
 
+#define IPSET_CONCAT(a, b)		a##b
+#define IPSET_TOKEN(a, b)		IPSET_CONCAT(a, b)
+
 #endif /*_IP_SET_H */
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index f6af97cf8d3e..d39905e7e881 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -8,31 +8,28 @@
 #ifndef __IP_SET_BITMAP_IP_GEN_H
 #define __IP_SET_BITMAP_IP_GEN_H
 
-#define CONCAT(a, b)		a##b
-#define TOKEN(a,b)		CONCAT(a, b)
-
-#define mtype_do_test		TOKEN(MTYPE, _do_test)
-#define mtype_gc_test		TOKEN(MTYPE, _gc_test)
-#define mtype_is_filled		TOKEN(MTYPE, _is_filled)
-#define mtype_do_add		TOKEN(MTYPE, _do_add)
-#define mtype_do_del		TOKEN(MTYPE, _do_del)
-#define mtype_do_list		TOKEN(MTYPE, _do_list)
-#define mtype_do_head		TOKEN(MTYPE, _do_head)
-#define mtype_adt_elem		TOKEN(MTYPE, _adt_elem)
-#define mtype_add_timeout	TOKEN(MTYPE, _add_timeout)
-#define mtype_gc_init		TOKEN(MTYPE, _gc_init)
-#define mtype_kadt		TOKEN(MTYPE, _kadt)
-#define mtype_uadt		TOKEN(MTYPE, _uadt)
-#define mtype_destroy		TOKEN(MTYPE, _destroy)
-#define mtype_flush		TOKEN(MTYPE, _flush)
-#define mtype_head		TOKEN(MTYPE, _head)
-#define mtype_same_set		TOKEN(MTYPE, _same_set)
-#define mtype_elem		TOKEN(MTYPE, _elem)
-#define mtype_test		TOKEN(MTYPE, _test)
-#define mtype_add		TOKEN(MTYPE, _add)
-#define mtype_del		TOKEN(MTYPE, _del)
-#define mtype_list		TOKEN(MTYPE, _list)
-#define mtype_gc		TOKEN(MTYPE, _gc)
+#define mtype_do_test		IPSET_TOKEN(MTYPE, _do_test)
+#define mtype_gc_test		IPSET_TOKEN(MTYPE, _gc_test)
+#define mtype_is_filled		IPSET_TOKEN(MTYPE, _is_filled)
+#define mtype_do_add		IPSET_TOKEN(MTYPE, _do_add)
+#define mtype_do_del		IPSET_TOKEN(MTYPE, _do_del)
+#define mtype_do_list		IPSET_TOKEN(MTYPE, _do_list)
+#define mtype_do_head		IPSET_TOKEN(MTYPE, _do_head)
+#define mtype_adt_elem		IPSET_TOKEN(MTYPE, _adt_elem)
+#define mtype_add_timeout	IPSET_TOKEN(MTYPE, _add_timeout)
+#define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_kadt		IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt		IPSET_TOKEN(MTYPE, _uadt)
+#define mtype_destroy		IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_flush		IPSET_TOKEN(MTYPE, _flush)
+#define mtype_head		IPSET_TOKEN(MTYPE, _head)
+#define mtype_same_set		IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_elem		IPSET_TOKEN(MTYPE, _elem)
+#define mtype_test		IPSET_TOKEN(MTYPE, _test)
+#define mtype_add		IPSET_TOKEN(MTYPE, _add)
+#define mtype_del		IPSET_TOKEN(MTYPE, _del)
+#define mtype_list		IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype			MTYPE
 
 #define ext_timeout(e, m)	\
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index f1a8128bef01..c2f89b1c1d92 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -25,12 +25,12 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_bitmap.h>
 
-#define REVISION_MIN	0
-#define REVISION_MAX	1	/* Counter support added */
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1	/* Counter support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_bitmap:ip");
 
 #define MTYPE		bitmap_ip
@@ -401,8 +401,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
 	.features	= IPSET_TYPE_IP,
 	.dimension	= IPSET_DIM_ONE,
 	.family		= NFPROTO_IPV4,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= bitmap_ip_create,
 	.create_policy	= {
 		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 3b30e0bef890..1d6551cc590e 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -25,12 +25,12 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_bitmap.h>
 
-#define REVISION_MIN	0
-#define REVISION_MAX	1	/* Counter support added */
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1	/* Counter support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip,mac", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_bitmap:ip,mac");
 
 #define MTYPE		bitmap_ipmac
@@ -460,8 +460,8 @@ static struct ip_set_type bitmap_ipmac_type = {
 	.features	= IPSET_TYPE_IP | IPSET_TYPE_MAC,
 	.dimension	= IPSET_DIM_TWO,
 	.family		= NFPROTO_IPV4,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= bitmap_ipmac_create,
 	.create_policy	= {
 		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 8207d1fda528..b22048965d2a 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -20,12 +20,12 @@
 #include <linux/netfilter/ipset/ip_set_bitmap.h>
 #include <linux/netfilter/ipset/ip_set_getport.h>
 
-#define REVISION_MIN	0
-#define REVISION_MAX	1	/* Counter support added */
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1	/* Counter support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_bitmap:port");
 
 #define MTYPE		bitmap_port
@@ -333,8 +333,8 @@ static struct ip_set_type bitmap_port_type = {
 	.features	= IPSET_TYPE_PORT,
 	.dimension	= IPSET_DIM_ONE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= bitmap_port_create,
 	.create_policy	= {
 		[IPSET_ATTR_PORT]	= { .type = NLA_U16 },
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 09a21dd5f120..68b9ccebabaa 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -17,9 +17,6 @@
 
 #define rcu_dereference_bh_nfnl(p)	rcu_dereference_bh_check(p, 1)
 
-#define CONCAT(a, b)		a##b
-#define TOKEN(a, b)		CONCAT(a, b)
-
 /* Hashing which uses arrays to resolve clashing. The hash table is resized
  * (doubled) when searching becomes too long.
  * Internally jhash is used with the assumption that the size of the
@@ -222,41 +219,41 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 
 #undef HKEY
 
-#define mtype_data_equal	TOKEN(MTYPE, _data_equal)
+#define mtype_data_equal	IPSET_TOKEN(MTYPE, _data_equal)
 #ifdef IP_SET_HASH_WITH_NETS
-#define mtype_do_data_match	TOKEN(MTYPE, _do_data_match)
+#define mtype_do_data_match	IPSET_TOKEN(MTYPE, _do_data_match)
 #else
 #define mtype_do_data_match(d)	1
 #endif
-#define mtype_data_set_flags	TOKEN(MTYPE, _data_set_flags)
-#define mtype_data_reset_flags	TOKEN(MTYPE, _data_reset_flags)
-#define mtype_data_netmask	TOKEN(MTYPE, _data_netmask)
-#define mtype_data_list		TOKEN(MTYPE, _data_list)
-#define mtype_data_next		TOKEN(MTYPE, _data_next)
-#define mtype_elem		TOKEN(MTYPE, _elem)
-#define mtype_add_cidr		TOKEN(MTYPE, _add_cidr)
-#define mtype_del_cidr		TOKEN(MTYPE, _del_cidr)
-#define mtype_ahash_memsize	TOKEN(MTYPE, _ahash_memsize)
-#define mtype_flush		TOKEN(MTYPE, _flush)
-#define mtype_destroy		TOKEN(MTYPE, _destroy)
-#define mtype_gc_init		TOKEN(MTYPE, _gc_init)
-#define mtype_same_set		TOKEN(MTYPE, _same_set)
-#define mtype_kadt		TOKEN(MTYPE, _kadt)
-#define mtype_uadt		TOKEN(MTYPE, _uadt)
+#define mtype_data_set_flags	IPSET_TOKEN(MTYPE, _data_set_flags)
+#define mtype_data_reset_flags	IPSET_TOKEN(MTYPE, _data_reset_flags)
+#define mtype_data_netmask	IPSET_TOKEN(MTYPE, _data_netmask)
+#define mtype_data_list		IPSET_TOKEN(MTYPE, _data_list)
+#define mtype_data_next		IPSET_TOKEN(MTYPE, _data_next)
+#define mtype_elem		IPSET_TOKEN(MTYPE, _elem)
+#define mtype_add_cidr		IPSET_TOKEN(MTYPE, _add_cidr)
+#define mtype_del_cidr		IPSET_TOKEN(MTYPE, _del_cidr)
+#define mtype_ahash_memsize	IPSET_TOKEN(MTYPE, _ahash_memsize)
+#define mtype_flush		IPSET_TOKEN(MTYPE, _flush)
+#define mtype_destroy		IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_same_set		IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_kadt		IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt		IPSET_TOKEN(MTYPE, _uadt)
 #define mtype			MTYPE
 
-#define mtype_elem		TOKEN(MTYPE, _elem)
-#define mtype_add		TOKEN(MTYPE, _add)
-#define mtype_del		TOKEN(MTYPE, _del)
-#define mtype_test_cidrs	TOKEN(MTYPE, _test_cidrs)
-#define mtype_test		TOKEN(MTYPE, _test)
-#define mtype_expire		TOKEN(MTYPE, _expire)
-#define mtype_resize		TOKEN(MTYPE, _resize)
-#define mtype_head		TOKEN(MTYPE, _head)
-#define mtype_list		TOKEN(MTYPE, _list)
-#define mtype_gc		TOKEN(MTYPE, _gc)
-#define mtype_variant		TOKEN(MTYPE, _variant)
-#define mtype_data_match	TOKEN(MTYPE, _data_match)
+#define mtype_elem		IPSET_TOKEN(MTYPE, _elem)
+#define mtype_add		IPSET_TOKEN(MTYPE, _add)
+#define mtype_del		IPSET_TOKEN(MTYPE, _del)
+#define mtype_test_cidrs	IPSET_TOKEN(MTYPE, _test_cidrs)
+#define mtype_test		IPSET_TOKEN(MTYPE, _test)
+#define mtype_expire		IPSET_TOKEN(MTYPE, _expire)
+#define mtype_resize		IPSET_TOKEN(MTYPE, _resize)
+#define mtype_head		IPSET_TOKEN(MTYPE, _head)
+#define mtype_list		IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
+#define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
+#define mtype_data_match	IPSET_TOKEN(MTYPE, _data_match)
 
 #ifndef HKEY_DATALEN
 #define HKEY_DATALEN		sizeof(struct mtype_elem)
@@ -941,13 +938,13 @@ nla_put_failure:
 }
 
 static int
-TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb,
-	      const struct xt_action_param *par,
-	      enum ipset_adt adt, struct ip_set_adt_opt *opt);
+IPSET_TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb,
+	    const struct xt_action_param *par,
+	    enum ipset_adt adt, struct ip_set_adt_opt *opt);
 
 static int
-TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[],
-	      enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
+IPSET_TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[],
+	    enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
 
 static const struct ip_set_type_variant mtype_variant = {
 	.kadt	= mtype_kadt,
@@ -967,7 +964,7 @@ static const struct ip_set_type_variant mtype_variant = {
 
 #ifdef IP_SET_EMIT_CREATE
 static int
-TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
+IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 {
 	u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
 	u32 cadt_flags = 0;
@@ -1045,9 +1042,9 @@ TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 
 	set->data = h;
 	if (set->family ==  NFPROTO_IPV4)
-		set->variant = &TOKEN(HTYPE, 4_variant);
+		set->variant = &IPSET_TOKEN(HTYPE, 4_variant);
 	else
-		set->variant = &TOKEN(HTYPE, 6_variant);
+		set->variant = &IPSET_TOKEN(HTYPE, 6_variant);
 
 	if (tb[IPSET_ATTR_CADT_FLAGS])
 		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -1058,64 +1055,74 @@ TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 				ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 			set->extensions |= IPSET_EXT_TIMEOUT;
 			if (set->family == NFPROTO_IPV4) {
-				h->dsize =
-					sizeof(struct TOKEN(HTYPE, 4ct_elem));
+				h->dsize = sizeof(struct
+					IPSET_TOKEN(HTYPE, 4ct_elem));
 				h->offset[IPSET_OFFSET_TIMEOUT] =
-					offsetof(struct TOKEN(HTYPE, 4ct_elem),
-						 timeout);
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 4ct_elem),
+						timeout);
 				h->offset[IPSET_OFFSET_COUNTER] =
-					offsetof(struct TOKEN(HTYPE, 4ct_elem),
-						 counter);
-				TOKEN(HTYPE, 4_gc_init)(set,
-					TOKEN(HTYPE, 4_gc));
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 4ct_elem),
+						counter);
+				IPSET_TOKEN(HTYPE, 4_gc_init)(set,
+					IPSET_TOKEN(HTYPE, 4_gc));
 			} else {
-				h->dsize =
-					sizeof(struct TOKEN(HTYPE, 6ct_elem));
+				h->dsize = sizeof(struct
+					IPSET_TOKEN(HTYPE, 6ct_elem));
 				h->offset[IPSET_OFFSET_TIMEOUT] =
-					offsetof(struct TOKEN(HTYPE, 6ct_elem),
-						 timeout);
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 6ct_elem),
+						timeout);
 				h->offset[IPSET_OFFSET_COUNTER] =
-					offsetof(struct TOKEN(HTYPE, 6ct_elem),
-						 counter);
-				TOKEN(HTYPE, 6_gc_init)(set,
-					TOKEN(HTYPE, 6_gc));
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 6ct_elem),
+						counter);
+				IPSET_TOKEN(HTYPE, 6_gc_init)(set,
+					IPSET_TOKEN(HTYPE, 6_gc));
 			}
 		} else {
 			if (set->family == NFPROTO_IPV4) {
 				h->dsize =
-					sizeof(struct TOKEN(HTYPE, 4c_elem));
+					sizeof(struct
+						IPSET_TOKEN(HTYPE, 4c_elem));
 				h->offset[IPSET_OFFSET_COUNTER] =
-					offsetof(struct TOKEN(HTYPE, 4c_elem),
-						 counter);
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 4c_elem),
+						counter);
 			} else {
 				h->dsize =
-					sizeof(struct TOKEN(HTYPE, 6c_elem));
+					sizeof(struct
+						IPSET_TOKEN(HTYPE, 6c_elem));
 				h->offset[IPSET_OFFSET_COUNTER] =
-					offsetof(struct TOKEN(HTYPE, 6c_elem),
-						 counter);
+					offsetof(struct
+						IPSET_TOKEN(HTYPE, 6c_elem),
+						counter);
 			}
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
 		h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		set->extensions |= IPSET_EXT_TIMEOUT;
 		if (set->family == NFPROTO_IPV4) {
-			h->dsize = sizeof(struct TOKEN(HTYPE, 4t_elem));
+			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4t_elem));
 			h->offset[IPSET_OFFSET_TIMEOUT] =
-				offsetof(struct TOKEN(HTYPE, 4t_elem),
+				offsetof(struct IPSET_TOKEN(HTYPE, 4t_elem),
 					 timeout);
-			TOKEN(HTYPE, 4_gc_init)(set, TOKEN(HTYPE, 4_gc));
+			IPSET_TOKEN(HTYPE, 4_gc_init)(set,
+				IPSET_TOKEN(HTYPE, 4_gc));
 		} else {
-			h->dsize = sizeof(struct TOKEN(HTYPE, 6t_elem));
+			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6t_elem));
 			h->offset[IPSET_OFFSET_TIMEOUT] =
-				offsetof(struct TOKEN(HTYPE, 6t_elem),
+				offsetof(struct IPSET_TOKEN(HTYPE, 6t_elem),
 					 timeout);
-			TOKEN(HTYPE, 6_gc_init)(set, TOKEN(HTYPE, 6_gc));
+			IPSET_TOKEN(HTYPE, 6_gc_init)(set,
+				IPSET_TOKEN(HTYPE, 6_gc));
 		}
 	} else {
 		if (set->family == NFPROTO_IPV4)
-			h->dsize = sizeof(struct TOKEN(HTYPE, 4_elem));
+			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4_elem));
 		else
-			h->dsize = sizeof(struct TOKEN(HTYPE, 6_elem));
+			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6_elem));
 	}
 
 	pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index c74e6e14cd93..de44fca687c3 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -23,12 +23,12 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-#define REVISION_MAX	1	/* Counters support */
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1	/* Counters support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:ip");
 
 /* Type specific function prefix */
@@ -304,8 +304,8 @@ static struct ip_set_type hash_ip_type __read_mostly = {
 	.features	= IPSET_TYPE_IP,
 	.dimension	= IPSET_DIM_ONE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_ip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 7a2d2bd98d04..b514ff4e83ae 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -24,13 +24,13 @@
 #include <linux/netfilter/ipset/ip_set_getport.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    SCTP and UDPLITE support added */
-#define REVISION_MAX	2 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    SCTP and UDPLITE support added */
+#define IPSET_TYPE_REV_MAX	2 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:ip,port");
 
 /* Type specific function prefix */
@@ -396,8 +396,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
 	.features	= IPSET_TYPE_IP | IPSET_TYPE_PORT,
 	.dimension	= IPSET_DIM_TWO,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_ipport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 34e8a1acce42..d05070d74604 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -24,13 +24,13 @@
 #include <linux/netfilter/ipset/ip_set_getport.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    SCTP and UDPLITE support added */
-#define REVISION_MAX	2 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    SCTP and UDPLITE support added */
+#define IPSET_TYPE_REV_MAX	2 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:ip,port,ip");
 
 /* Type specific function prefix */
@@ -414,8 +414,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
 	.features	= IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2,
 	.dimension	= IPSET_DIM_THREE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_ipportip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 9a80d8bc9f18..7d1dede4ab6d 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -24,15 +24,15 @@
 #include <linux/netfilter/ipset/ip_set_getport.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    SCTP and UDPLITE support added */
-/*			2    Range as input support for IPv4 added */
-/*			3    nomatch flag support added */
-#define REVISION_MAX	4 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    SCTP and UDPLITE support added */
+/*				2    Range as input support for IPv4 added */
+/*				3    nomatch flag support added */
+#define IPSET_TYPE_REV_MAX	4 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:ip,port,net");
 
 /* Type specific function prefix */
@@ -574,8 +574,8 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
 			  IPSET_TYPE_NOMATCH,
 	.dimension	= IPSET_DIM_THREE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_ipportnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 223e9f546d0f..9cb9ef43d941 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -22,14 +22,14 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    Range as input support for IPv4 added */
-/*			2    nomatch flag support added */
-#define REVISION_MAX	3 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    Range as input support for IPv4 added */
+/*				2    nomatch flag support added */
+#define IPSET_TYPE_REV_MAX	3 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:net");
 
 /* Type specific function prefix */
@@ -406,8 +406,8 @@ static struct ip_set_type hash_net_type __read_mostly = {
 	.features	= IPSET_TYPE_IP | IPSET_TYPE_NOMATCH,
 	.dimension	= IPSET_DIM_ONE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_net_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 7d798d5d5cd3..2310fc29e89e 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -23,14 +23,14 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    nomatch flag support added */
-/*			2    /0 support added */
-#define REVISION_MAX	3 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    nomatch flag support added */
+/*				2    /0 support added */
+#define IPSET_TYPE_REV_MAX	3 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,iface", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,iface", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:net,iface");
 
 /* Interface name rbtree */
@@ -645,8 +645,8 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
 			  IPSET_TYPE_NOMATCH,
 	.dimension	= IPSET_DIM_TWO,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_netiface_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 09d6690bee6f..1601d489fdbc 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -23,15 +23,15 @@
 #include <linux/netfilter/ipset/ip_set_getport.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
-#define REVISION_MIN	0
-/*			1    SCTP and UDPLITE support added */
-/*			2    Range as input support for IPv4 added */
-/*			3    nomatch flag support added */
-#define REVISION_MAX	4 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+/*				1    SCTP and UDPLITE support added */
+/*				2    Range as input support for IPv4 added */
+/*				3    nomatch flag support added */
+#define IPSET_TYPE_REV_MAX	4 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_hash:net,port");
 
 /* Type specific function prefix */
@@ -518,8 +518,8 @@ static struct ip_set_type hash_netport_type __read_mostly = {
 	.features	= IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH,
 	.dimension	= IPSET_DIM_TWO,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= hash_netport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 68299ee15847..a9e301f6e093 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -15,12 +15,12 @@
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_list.h>
 
-#define REVISION_MIN	0
-#define REVISION_MAX	1 /* Counters support added */
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	1 /* Counters support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("list:set", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("list:set", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
 MODULE_ALIAS("ip_set_list:set");
 
 /* Member elements  */
@@ -703,8 +703,8 @@ static struct ip_set_type list_set_type __read_mostly = {
 	.features	= IPSET_TYPE_NAME | IPSET_DUMP_LAST,
 	.dimension	= IPSET_DIM_ONE,
 	.family		= NFPROTO_UNSPEC,
-	.revision_min	= REVISION_MIN,
-	.revision_max	= REVISION_MAX,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
 	.create		= list_set_create,
 	.create_policy	= {
 		[IPSET_ATTR_SIZE]	= { .type = NLA_U32 },
-- 
cgit 


From b8cd97865c903e032db85e5a4f2783928c56f2bd Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Thu, 2 May 2013 10:52:27 +0200
Subject: netfilter: ipset: Use fix sized type for timeout in the extension
 part

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index f900f33a5f3d..69aa60487f05 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -67,7 +67,7 @@ enum ip_set_offset {
 #define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
 
 struct ip_set_ext {
-	unsigned long timeout;
+	u32 timeout;
 	u64 packets;
 	u64 bytes;
 };
-- 
cgit 


From 5e04c0c38c90f1f11a0e87800e4c22d4aba1d733 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 30 Sep 2013 07:57:18 +0200
Subject: netfilter: ipset: Introduce new operation to get both setname and
 family

ip[6]tables set match and SET target need to know the family of the set
in order to reject adding rules which refer to a set with a non-mathcing
family. Currently such rules are silently accepted and then ignored
instead of generating a clear error message to the user, which is not
helpful.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/uapi/linux/netfilter/ipset/ip_set.h |  8 ++++++++
 net/netfilter/ipset/ip_set_core.c           | 17 +++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 8024cdf13b70..2b61ac44dcc1 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -250,6 +250,14 @@ struct ip_set_req_get_set {
 #define IP_SET_OP_GET_BYINDEX	0x00000007	/* Get set name by index */
 /* Uses ip_set_req_get_set */
 
+#define IP_SET_OP_GET_FNAME	0x00000008	/* Get set index and family */
+struct ip_set_req_get_set_family {
+	unsigned int op;
+	unsigned int version;
+	unsigned int family;
+	union ip_set_name_index set;
+};
+
 #define IP_SET_OP_VERSION	0x00000100	/* Ask kernel version */
 struct ip_set_req_version {
 	unsigned int op;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index f2e30fb31e78..428c30a8586f 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1788,6 +1788,23 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
 		goto copy;
 	}
+	case IP_SET_OP_GET_FNAME: {
+		struct ip_set_req_get_set_family *req_get = data;
+		ip_set_id_t id;
+
+		if (*len != sizeof(struct ip_set_req_get_set_family)) {
+			ret = -EINVAL;
+			goto done;
+		}
+		req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
+		nfnl_lock(NFNL_SUBSYS_IPSET);
+		find_set_and_id(req_get->set.name, &id);
+		req_get->set.index = id;
+		if (id != IPSET_INVALID_ID)
+			req_get->family = nfnl_set(id)->family;
+		nfnl_unlock(NFNL_SUBSYS_IPSET);
+		goto copy;
+	}
 	case IP_SET_OP_GET_BYINDEX: {
 		struct ip_set_req_get_set *req_get = data;
 		struct ip_set *set;
-- 
cgit 


From a04d8b6bd9113f3e7f0c216dcaa3c1ad498f2a96 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 30 Sep 2013 09:05:54 +0200
Subject: netfilter: ipset: Prepare ipset to support multiple networks for hash
 types

In order to support hash:net,net, hash:net,port,net etc. types,
arrays are introduced for the book-keeping of existing cidr sizes
and network numbers in a set.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      |  2 +
 net/netfilter/ipset/ip_set_hash_gen.h       | 78 +++++++++++++++--------------
 net/netfilter/ipset/ip_set_hash_ipportnet.c |  4 +-
 net/netfilter/ipset/ip_set_hash_net.c       |  4 +-
 net/netfilter/ipset/ip_set_hash_netiface.c  |  4 +-
 net/netfilter/ipset/ip_set_hash_netport.c   |  4 +-
 6 files changed, 50 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 69aa60487f05..56012a3431b2 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -398,6 +398,8 @@ bitmap_bytes(u32 a, u32 b)
 	{ .bytes = ULLONG_MAX, .packets = ULLONG_MAX,	\
 	  .timeout = (map)->timeout }
 
+#define IP_SET_INIT_CIDR(a, b) ((a) ? (a) : (b))
+
 #define IPSET_CONCAT(a, b)		a##b
 #define IPSET_TOKEN(a, b)		IPSET_CONCAT(a, b)
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 68b9ccebabaa..a8332404d9b4 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -77,10 +77,14 @@ struct htable {
 
 #define hbucket(h, i)		(&((h)->bucket[i]))
 
+#ifndef IPSET_NET_COUNT
+#define IPSET_NET_COUNT		1
+#endif
+
 /* Book-keeping of the prefixes added to the set */
 struct net_prefixes {
-	u8 cidr;		/* the different cidr values in the set */
-	u32 nets;		/* number of elements per cidr */
+	u32 nets[IPSET_NET_COUNT]; /* number of elements per cidr */
+	u8 cidr[IPSET_NET_COUNT];  /* the different cidr values in the set */
 };
 
 /* Compute the hash table size */
@@ -165,13 +169,13 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #define SET_HOST_MASK(family)	(family == AF_INET ? 32 : 128)
 
 #ifdef IP_SET_HASH_WITH_MULTI
-#define NETS_LENGTH(family)	(SET_HOST_MASK(family) + 1)
+#define NLEN(family)		(SET_HOST_MASK(family) + 1)
 #else
-#define NETS_LENGTH(family)	SET_HOST_MASK(family)
+#define NLEN(family)		SET_HOST_MASK(family)
 #endif
 
 #else
-#define NETS_LENGTH(family)	0
+#define NLEN(family)		0
 #endif /* IP_SET_HASH_WITH_NETS */
 
 #define ext_timeout(e, h)	\
@@ -296,49 +300,49 @@ struct htype {
 /* Network cidr size book keeping when the hash stores different
  * sized networks */
 static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length)
+mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 {
 	int i, j;
 
 	/* Add in increasing prefix order, so larger cidr first */
-	for (i = 0, j = -1; i < nets_length && h->nets[i].nets; i++) {
+	for (i = 0, j = -1; i < nets_length && h->nets[i].nets[n]; i++) {
 		if (j != -1)
 			continue;
-		else if (h->nets[i].cidr < cidr)
+		else if (h->nets[i].cidr[n] < cidr)
 			j = i;
-		else if (h->nets[i].cidr == cidr) {
-			h->nets[i].nets++;
+		else if (h->nets[i].cidr[n] == cidr) {
+			h->nets[i].nets[n]++;
 			return;
 		}
 	}
 	if (j != -1) {
 		for (; i > j; i--) {
-			h->nets[i].cidr = h->nets[i - 1].cidr;
-			h->nets[i].nets = h->nets[i - 1].nets;
+			h->nets[i].cidr[n] = h->nets[i - 1].cidr[n];
+			h->nets[i].nets[n] = h->nets[i - 1].nets[n];
 		}
 	}
-	h->nets[i].cidr = cidr;
-	h->nets[i].nets = 1;
+	h->nets[i].cidr[n] = cidr;
+	h->nets[i].nets[n] = 1;
 }
 
 static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length)
+mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 {
 	u8 i, j, net_end = nets_length - 1;
 
 	for (i = 0; i < nets_length; i++) {
-	        if (h->nets[i].cidr != cidr)
+	        if (h->nets[i].cidr[n] != cidr)
 	                continue;
-                if (h->nets[i].nets > 1 || i == net_end ||
-                    h->nets[i + 1].nets == 0) {
-                        h->nets[i].nets--;
+                if (h->nets[i].nets[n] > 1 || i == net_end ||
+                    h->nets[i + 1].nets[n] == 0) {
+                        h->nets[i].nets[n]--;
                         return;
                 }
-                for (j = i; j < net_end && h->nets[j].nets; j++) {
-		        h->nets[j].cidr = h->nets[j + 1].cidr;
-		        h->nets[j].nets = h->nets[j + 1].nets;
+                for (j = i; j < net_end && h->nets[j].nets[n]; j++) {
+		        h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
+		        h->nets[j].nets[n] = h->nets[j + 1].nets[n];
                 }
-                h->nets[j].nets = 0;
+                h->nets[j].nets[n] = 0;
                 return;
 	}
 }
@@ -382,8 +386,7 @@ mtype_flush(struct ip_set *set)
 		}
 	}
 #ifdef IP_SET_HASH_WITH_NETS
-	memset(h->nets, 0, sizeof(struct net_prefixes)
-			   * NETS_LENGTH(set->family));
+	memset(h->nets, 0, sizeof(struct net_prefixes) * NLEN(set->family));
 #endif
 	h->elements = 0;
 }
@@ -459,7 +462,7 @@ mtype_expire(struct htype *h, u8 nets_length, size_t dsize)
 				pr_debug("expired %u/%u\n", i, j);
 #ifdef IP_SET_HASH_WITH_NETS
 				mtype_del_cidr(h, CIDR(data->cidr),
-					       nets_length);
+					       nets_length, 0);
 #endif
 				if (j != n->pos - 1)
 					/* Not last one */
@@ -494,7 +497,7 @@ mtype_gc(unsigned long ul_set)
 
 	pr_debug("called\n");
 	write_lock_bh(&set->lock);
-	mtype_expire(h, NETS_LENGTH(set->family), h->dsize);
+	mtype_expire(h, NLEN(set->family), h->dsize);
 	write_unlock_bh(&set->lock);
 
 	h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
@@ -523,8 +526,7 @@ mtype_resize(struct ip_set *set, bool retried)
 	if (SET_WITH_TIMEOUT(set) && !retried) {
 		i = h->elements;
 		write_lock_bh(&set->lock);
-		mtype_expire(set->data, NETS_LENGTH(set->family),
-			     h->dsize);
+		mtype_expire(set->data, NLEN(set->family), h->dsize);
 		write_unlock_bh(&set->lock);
 		if (h->elements < i)
 			return 0;
@@ -607,7 +609,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
 		/* FIXME: when set is full, we slow down here */
-		mtype_expire(h, NETS_LENGTH(set->family), h->dsize);
+		mtype_expire(h, NLEN(set->family), h->dsize);
 
 	if (h->elements >= h->maxelem) {
 		if (net_ratelimit())
@@ -645,8 +647,8 @@ reuse_slot:
 		/* Fill out reused slot */
 		data = ahash_data(n, j, h->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
-		mtype_del_cidr(h, CIDR(data->cidr), NETS_LENGTH(set->family));
-		mtype_add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+		mtype_del_cidr(h, CIDR(data->cidr), NLEN(set->family), 0);
+		mtype_add_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
 	} else {
 		/* Use/create a new slot */
@@ -659,7 +661,7 @@ reuse_slot:
 		}
 		data = ahash_data(n, n->pos++, h->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
-		mtype_add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+		mtype_add_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
 		h->elements++;
 	}
@@ -711,7 +713,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		n->pos--;
 		h->elements--;
 #ifdef IP_SET_HASH_WITH_NETS
-		mtype_del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family));
+		mtype_del_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
 		if (n->pos + AHASH_INIT_SIZE < n->size) {
 			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
@@ -760,11 +762,11 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 	struct mtype_elem *data;
 	int i, j = 0;
 	u32 key, multi = 0;
-	u8 nets_length = NETS_LENGTH(set->family);
+	u8 nets_length = NLEN(set->family);
 
 	pr_debug("test by nets\n");
-	for (; j < nets_length && h->nets[j].nets && !multi; j++) {
-		mtype_data_netmask(d, h->nets[j].cidr);
+	for (; j < nets_length && h->nets[j].nets[0] && !multi; j++) {
+		mtype_data_netmask(d, h->nets[j].cidr[0]);
 		key = HKEY(d, h->initval, t->htable_bits);
 		n = hbucket(t, key);
 		for (i = 0; i < n->pos; i++) {
@@ -839,7 +841,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	size_t memsize;
 
 	t = rcu_dereference_bh_nfnl(h->table);
-	memsize = mtype_ahash_memsize(h, t, NETS_LENGTH(set->family));
+	memsize = mtype_ahash_memsize(h, t, NLEN(set->family));
 
 	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index f111558c4597..6ce5a8e2c44e 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -170,7 +170,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_ipportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet4_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
@@ -454,7 +454,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_ipportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet6_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 0a64dad156d9..ec1c7dc10489 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -143,7 +143,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_net *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_net4_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
@@ -338,7 +338,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_net *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_net6_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 846371b08630..814b4e31a7f8 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -265,7 +265,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_netiface *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netiface4_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 		.elem = 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
@@ -534,7 +534,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_netiface *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netiface6_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 		.elem = 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index d98a685cd916..3bd923d3f179 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -162,7 +162,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_netport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport4_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
@@ -407,7 +407,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_netport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport6_elem e = {
-		.cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1,
+		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
 	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
 
-- 
cgit 


From f925f7056920213889c5e61445f9529f1a86ae41 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Fri, 6 Sep 2013 22:31:40 +0200
Subject: netfilter: ipset: Rename extension offset ids to extension ids

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h    | 16 ++++++++--------
 net/netfilter/ipset/ip_set_bitmap_gen.h   |  4 ++--
 net/netfilter/ipset/ip_set_bitmap_ip.c    | 10 +++++-----
 net/netfilter/ipset/ip_set_bitmap_ipmac.c | 10 +++++-----
 net/netfilter/ipset/ip_set_bitmap_port.c  | 10 +++++-----
 net/netfilter/ipset/ip_set_hash_gen.h     | 22 +++++++++++-----------
 net/netfilter/ipset/ip_set_list_set.c     | 14 +++++++-------
 7 files changed, 43 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 56012a3431b2..b4db7912bf0d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -56,20 +56,20 @@ enum ip_set_extension {
 	IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER),
 };
 
-/* Extension offsets */
-enum ip_set_offset {
-	IPSET_OFFSET_TIMEOUT = 0,
-	IPSET_OFFSET_COUNTER,
-	IPSET_OFFSET_MAX,
-};
-
 #define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
 #define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
 
+/* Extension id, in size order */
+enum ip_set_ext_id {
+	IPSET_EXT_ID_COUNTER = 0,
+	IPSET_EXT_ID_TIMEOUT,
+	IPSET_EXT_ID_MAX,
+};
+
 struct ip_set_ext {
-	u32 timeout;
 	u64 packets;
 	u64 bytes;
+	u32 timeout;
 };
 
 struct ip_set;
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index d39905e7e881..889a929b908f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -33,9 +33,9 @@
 #define mtype			MTYPE
 
 #define ext_timeout(e, m)	\
-	(unsigned long *)((e) + (m)->offset[IPSET_OFFSET_TIMEOUT])
+	(unsigned long *)((e) + (m)->offset[IPSET_EXT_ID_TIMEOUT])
 #define ext_counter(e, m)	\
-	(struct ip_set_counter *)((e) + (m)->offset[IPSET_OFFSET_COUNTER])
+	(struct ip_set_counter *)((e) + (m)->offset[IPSET_EXT_ID_COUNTER])
 #define get_ext(map, id)	((map)->extensions + (map)->dsize * (id))
 
 static void
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index ce99d2652d47..2ee210ef49a2 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -45,7 +45,7 @@ struct bitmap_ip {
 	u32 hosts;		/* number of hosts in a subnet */
 	size_t memsize;		/* members size */
 	size_t dsize;		/* extensions struct size */
-	size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	u8 netmask;		/* subnet netmask */
 	u32 timeout;		/* timeout parameter */
 	struct timer_list gc;	/* garbage collection */
@@ -342,9 +342,9 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
 			map->dsize = sizeof(struct bitmap_ipct_elem);
-			map->offset[IPSET_OFFSET_TIMEOUT] =
+			map->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_ipct_elem, timeout);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipct_elem, counter);
 
 			if (!init_map_ip(set, map, first_ip, last_ip,
@@ -360,7 +360,7 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			bitmap_ip_gc_init(set, bitmap_ip_gc);
 		} else {
 			map->dsize = sizeof(struct bitmap_ipc_elem);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipc_elem, counter);
 
 			if (!init_map_ip(set, map, first_ip, last_ip,
@@ -371,7 +371,7 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
 		map->dsize = sizeof(struct bitmap_ipt_elem);
-		map->offset[IPSET_OFFSET_TIMEOUT] =
+		map->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_ipt_elem, timeout);
 
 		if (!init_map_ip(set, map, first_ip, last_ip,
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 6d5bad93026b..e711875ea452 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -52,7 +52,7 @@ struct bitmap_ipmac {
 	struct timer_list gc;	/* garbage collector */
 	size_t memsize;		/* members size */
 	size_t dsize;		/* size of element */
-	size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 };
 
 /* ADT structure for generic function args */
@@ -405,9 +405,9 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
 			map->dsize = sizeof(struct bitmap_ipmacct_elem);
-			map->offset[IPSET_OFFSET_TIMEOUT] =
+			map->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_ipmacct_elem, timeout);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipmacct_elem, counter);
 
 			if (!init_map_ipmac(set, map, first_ip, last_ip,
@@ -421,7 +421,7 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 			bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
 		} else {
 			map->dsize = sizeof(struct bitmap_ipmacc_elem);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipmacc_elem, counter);
 
 			if (!init_map_ipmac(set, map, first_ip, last_ip,
@@ -432,7 +432,7 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
 		map->dsize = sizeof(struct bitmap_ipmact_elem);
-		map->offset[IPSET_OFFSET_TIMEOUT] =
+		map->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_ipmact_elem, timeout);
 
 		if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index b22048965d2a..bebc137a5737 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -39,7 +39,7 @@ struct bitmap_port {
 	u32 elements;		/* number of max elements in the set */
 	size_t memsize;		/* members size */
 	size_t dsize;		/* extensions struct size */
-	size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	u32 timeout;		/* timeout parameter */
 	struct timer_list gc;	/* garbage collection */
 };
@@ -282,9 +282,9 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
 			map->dsize = sizeof(struct bitmap_portct_elem);
-			map->offset[IPSET_OFFSET_TIMEOUT] =
+			map->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_portct_elem, timeout);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_portct_elem, counter);
 			if (!init_map_port(set, map, first_port, last_port)) {
 				kfree(map);
@@ -297,7 +297,7 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			bitmap_port_gc_init(set, bitmap_port_gc);
 		} else {
 			map->dsize = sizeof(struct bitmap_portc_elem);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_portc_elem, counter);
 			if (!init_map_port(set, map, first_port, last_port)) {
 				kfree(map);
@@ -306,7 +306,7 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
 		map->dsize = sizeof(struct bitmap_portt_elem);
-		map->offset[IPSET_OFFSET_TIMEOUT] =
+		map->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_portt_elem, timeout);
 		if (!init_map_port(set, map, first_port, last_port)) {
 			kfree(map);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index a8332404d9b4..e4db9250f337 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -179,9 +179,9 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #endif /* IP_SET_HASH_WITH_NETS */
 
 #define ext_timeout(e, h)	\
-(unsigned long *)(((void *)(e)) + (h)->offset[IPSET_OFFSET_TIMEOUT])
+(unsigned long *)(((void *)(e)) + (h)->offset[IPSET_EXT_ID_TIMEOUT])
 #define ext_counter(e, h)	\
-(struct ip_set_counter *)(((void *)(e)) + (h)->offset[IPSET_OFFSET_COUNTER])
+(struct ip_set_counter *)(((void *)(e)) + (h)->offset[IPSET_EXT_ID_COUNTER])
 
 #endif /* _IP_SET_HASH_GEN_H */
 
@@ -278,7 +278,7 @@ struct htype {
 	u32 initval;		/* random jhash init value */
 	u32 timeout;		/* timeout value, if enabled */
 	size_t dsize;		/* data struct size */
-	size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	struct timer_list gc;	/* garbage collection when timeout enabled */
 	struct mtype_elem next; /* temporary storage for uadd */
 #ifdef IP_SET_HASH_WITH_MULTI
@@ -1059,11 +1059,11 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			if (set->family == NFPROTO_IPV4) {
 				h->dsize = sizeof(struct
 					IPSET_TOKEN(HTYPE, 4ct_elem));
-				h->offset[IPSET_OFFSET_TIMEOUT] =
+				h->offset[IPSET_EXT_ID_TIMEOUT] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4ct_elem),
 						timeout);
-				h->offset[IPSET_OFFSET_COUNTER] =
+				h->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4ct_elem),
 						counter);
@@ -1072,11 +1072,11 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			} else {
 				h->dsize = sizeof(struct
 					IPSET_TOKEN(HTYPE, 6ct_elem));
-				h->offset[IPSET_OFFSET_TIMEOUT] =
+				h->offset[IPSET_EXT_ID_TIMEOUT] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6ct_elem),
 						timeout);
-				h->offset[IPSET_OFFSET_COUNTER] =
+				h->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6ct_elem),
 						counter);
@@ -1088,7 +1088,7 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 				h->dsize =
 					sizeof(struct
 						IPSET_TOKEN(HTYPE, 4c_elem));
-				h->offset[IPSET_OFFSET_COUNTER] =
+				h->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4c_elem),
 						counter);
@@ -1096,7 +1096,7 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 				h->dsize =
 					sizeof(struct
 						IPSET_TOKEN(HTYPE, 6c_elem));
-				h->offset[IPSET_OFFSET_COUNTER] =
+				h->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6c_elem),
 						counter);
@@ -1107,14 +1107,14 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		set->extensions |= IPSET_EXT_TIMEOUT;
 		if (set->family == NFPROTO_IPV4) {
 			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4t_elem));
-			h->offset[IPSET_OFFSET_TIMEOUT] =
+			h->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct IPSET_TOKEN(HTYPE, 4t_elem),
 					 timeout);
 			IPSET_TOKEN(HTYPE, 4_gc_init)(set,
 				IPSET_TOKEN(HTYPE, 4_gc));
 		} else {
 			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6t_elem));
-			h->offset[IPSET_OFFSET_TIMEOUT] =
+			h->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct IPSET_TOKEN(HTYPE, 6t_elem),
 					 timeout);
 			IPSET_TOKEN(HTYPE, 6_gc_init)(set,
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index a9e301f6e093..0ed19b5e675e 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -59,7 +59,7 @@ struct set_adt_elem {
 /* Type structure */
 struct list_set {
 	size_t dsize;		/* element size */
-	size_t offset[IPSET_OFFSET_MAX]; /* Offsets to extensions */
+	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	u32 size;		/* size of set list array */
 	u32 timeout;		/* timeout value */
 	struct timer_list gc;	/* garbage collection */
@@ -73,9 +73,9 @@ list_set_elem(const struct list_set *map, u32 id)
 }
 
 #define ext_timeout(e, m)	\
-(unsigned long *)((void *)(e) + (m)->offset[IPSET_OFFSET_TIMEOUT])
+(unsigned long *)((void *)(e) + (m)->offset[IPSET_EXT_ID_TIMEOUT])
 #define ext_counter(e, m)	\
-(struct ip_set_counter *)((void *)(e) + (m)->offset[IPSET_OFFSET_COUNTER])
+(struct ip_set_counter *)((void *)(e) + (m)->offset[IPSET_EXT_ID_COUNTER])
 
 static int
 list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
@@ -667,9 +667,9 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			if (!map)
 				return -ENOMEM;
 			set->extensions |= IPSET_EXT_TIMEOUT;
-			map->offset[IPSET_OFFSET_TIMEOUT] =
+			map->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct setct_elem, timeout);
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct setct_elem, counter);
 			list_set_gc_init(set, list_set_gc);
 		} else {
@@ -677,7 +677,7 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 					    sizeof(struct setc_elem), 0);
 			if (!map)
 				return -ENOMEM;
-			map->offset[IPSET_OFFSET_COUNTER] =
+			map->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct setc_elem, counter);
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
@@ -686,7 +686,7 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		if (!map)
 			return -ENOMEM;
 		set->extensions |= IPSET_EXT_TIMEOUT;
-		map->offset[IPSET_OFFSET_TIMEOUT] =
+		map->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct sett_elem, timeout);
 		list_set_gc_init(set, list_set_gc);
 	} else {
-- 
cgit 


From ca134ce86451f3f5ac45ffbf1494a1f42110bf93 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sat, 7 Sep 2013 00:10:07 +0200
Subject: netfilter: ipset: Move extension data to set structure

Default timeout and extension offsets are moved to struct set, because
all set types supports all extensions and it makes possible to generalize
extension support.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h         |  29 ++++--
 include/linux/netfilter/ipset/ip_set_timeout.h |   4 +-
 net/netfilter/ipset/ip_set_bitmap_gen.h        |  59 ++++++------
 net/netfilter/ipset/ip_set_bitmap_ip.c         |  45 +++++----
 net/netfilter/ipset/ip_set_bitmap_ipmac.c      |  64 ++++++-------
 net/netfilter/ipset/ip_set_bitmap_port.c       |  44 ++++-----
 net/netfilter/ipset/ip_set_hash_gen.h          | 127 ++++++++++++-------------
 net/netfilter/ipset/ip_set_hash_ip.c           |   8 +-
 net/netfilter/ipset/ip_set_hash_ipport.c       |  10 +-
 net/netfilter/ipset/ip_set_hash_ipportip.c     |  10 +-
 net/netfilter/ipset/ip_set_hash_ipportnet.c    |  14 +--
 net/netfilter/ipset/ip_set_hash_net.c          |   9 +-
 net/netfilter/ipset/ip_set_hash_netiface.c     |   8 +-
 net/netfilter/ipset/ip_set_hash_netport.c      |   8 +-
 net/netfilter/ipset/ip_set_list_set.c          | 116 ++++++++++------------
 15 files changed, 266 insertions(+), 289 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index b4db7912bf0d..992a2f58dbd3 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -72,6 +72,16 @@ struct ip_set_ext {
 	u32 timeout;
 };
 
+struct ip_set_counter {
+	atomic64_t bytes;
+	atomic64_t packets;
+};
+
+#define ext_timeout(e, s)	\
+(unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])
+#define ext_counter(e, s)	\
+(struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])
+
 struct ip_set;
 
 typedef int (*ipset_adtfn)(struct ip_set *set, void *value,
@@ -179,15 +189,16 @@ struct ip_set {
 	u8 revision;
 	/* Extensions */
 	u8 extensions;
+	/* Default timeout value, if enabled */
+	u32 timeout;
+	/* Element data size */
+	size_t dsize;
+	/* Offsets to extensions in elements */
+	size_t offset[IPSET_EXT_ID_MAX];
 	/* The type specific data */
 	void *data;
 };
 
-struct ip_set_counter {
-	atomic64_t bytes;
-	atomic64_t packets;
-};
-
 static inline void
 ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
 {
@@ -390,13 +401,13 @@ bitmap_bytes(u32 a, u32 b)
 
 #include <linux/netfilter/ipset/ip_set_timeout.h>
 
-#define IP_SET_INIT_KEXT(skb, opt, map)			\
+#define IP_SET_INIT_KEXT(skb, opt, set)			\
 	{ .bytes = (skb)->len, .packets = 1,		\
-	  .timeout = ip_set_adt_opt_timeout(opt, map) }
+	  .timeout = ip_set_adt_opt_timeout(opt, set) }
 
-#define IP_SET_INIT_UEXT(map)				\
+#define IP_SET_INIT_UEXT(set)				\
 	{ .bytes = ULLONG_MAX, .packets = ULLONG_MAX,	\
-	  .timeout = (map)->timeout }
+	  .timeout = (set)->timeout }
 
 #define IP_SET_INIT_CIDR(a, b) ((a) ? (a) : (b))
 
diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h
index 3aac04167ca7..83c2f9e0886c 100644
--- a/include/linux/netfilter/ipset/ip_set_timeout.h
+++ b/include/linux/netfilter/ipset/ip_set_timeout.h
@@ -23,8 +23,8 @@
 /* Set is defined with timeout support: timeout value may be 0 */
 #define IPSET_NO_TIMEOUT	UINT_MAX
 
-#define ip_set_adt_opt_timeout(opt, map)	\
-((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (map)->timeout)
+#define ip_set_adt_opt_timeout(opt, set)	\
+((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (set)->timeout)
 
 static inline unsigned int
 ip_set_timeout_uget(struct nlattr *tb)
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 889a929b908f..f32ddbca3923 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -32,11 +32,7 @@
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype			MTYPE
 
-#define ext_timeout(e, m)	\
-	(unsigned long *)((e) + (m)->offset[IPSET_EXT_ID_TIMEOUT])
-#define ext_counter(e, m)	\
-	(struct ip_set_counter *)((e) + (m)->offset[IPSET_EXT_ID_COUNTER])
-#define get_ext(map, id)	((map)->extensions + (map)->dsize * (id))
+#define get_ext(set, map, id)	((map)->extensions + (set)->dsize * (id))
 
 static void
 mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
@@ -46,7 +42,7 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 	init_timer(&map->gc);
 	map->gc.data = (unsigned long) set;
 	map->gc.function = gc;
-	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&map->gc);
 }
 
@@ -59,7 +55,7 @@ mtype_destroy(struct ip_set *set)
 		del_timer_sync(&map->gc);
 
 	ip_set_free(map->members);
-	if (map->dsize)
+	if (set->dsize)
 		ip_set_free(map->extensions);
 	kfree(map);
 
@@ -88,9 +84,9 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
 			  htonl(sizeof(*map) +
 				map->memsize +
-				map->dsize * map->elements)) ||
+				set->dsize * map->elements)) ||
 	    (SET_WITH_TIMEOUT(set) &&
-	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) ||
+	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(set->timeout))) ||
 	    (SET_WITH_COUNTER(set) &&
 	     nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
 			   htonl(IPSET_FLAG_WITH_COUNTERS))))
@@ -108,16 +104,16 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 {
 	struct mtype *map = set->data;
 	const struct mtype_adt_elem *e = value;
-	void *x = get_ext(map, e->id);
-	int ret = mtype_do_test(e, map);
+	void *x = get_ext(set, map, e->id);
+	int ret = mtype_do_test(e, map, set->dsize);
 
 	if (ret <= 0)
 		return ret;
 	if (SET_WITH_TIMEOUT(set) &&
-	    ip_set_timeout_expired(ext_timeout(x, map)))
+	    ip_set_timeout_expired(ext_timeout(x, set)))
 		return 0;
 	if (SET_WITH_COUNTER(set))
-		ip_set_update_counter(ext_counter(x, map), ext, mext, flags);
+		ip_set_update_counter(ext_counter(x, set), ext, mext, flags);
 	return 1;
 }
 
@@ -127,12 +123,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 {
 	struct mtype *map = set->data;
 	const struct mtype_adt_elem *e = value;
-	void *x = get_ext(map, e->id);
-	int ret = mtype_do_add(e, map, flags);
+	void *x = get_ext(set, map, e->id);
+	int ret = mtype_do_add(e, map, flags, set->dsize);
 
 	if (ret == IPSET_ADD_FAILED) {
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(x, map)))
+		    ip_set_timeout_expired(ext_timeout(x, set)))
 			ret = 0;
 		else if (!(flags & IPSET_FLAG_EXIST))
 			return -IPSET_ERR_EXIST;
@@ -140,13 +136,13 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	if (SET_WITH_TIMEOUT(set))
 #ifdef IP_SET_BITMAP_STORED_TIMEOUT
-		mtype_add_timeout(ext_timeout(x, map), e, ext, map, ret);
+		mtype_add_timeout(ext_timeout(x, set), e, ext, set, map, ret);
 #else
-		ip_set_timeout_set(ext_timeout(x, map), ext->timeout);
+		ip_set_timeout_set(ext_timeout(x, set), ext->timeout);
 #endif
 
 	if (SET_WITH_COUNTER(set))
-		ip_set_init_counter(ext_counter(x, map), ext);
+		ip_set_init_counter(ext_counter(x, set), ext);
 	return 0;
 }
 
@@ -156,11 +152,11 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 {
 	struct mtype *map = set->data;
 	const struct mtype_adt_elem *e = value;
-	const void *x = get_ext(map, e->id);
+	const void *x = get_ext(set, map, e->id);
 
 	if (mtype_do_del(e, map) ||
 	    (SET_WITH_TIMEOUT(set) &&
-	     ip_set_timeout_expired(ext_timeout(x, map))))
+	     ip_set_timeout_expired(ext_timeout(x, set))))
 		return -IPSET_ERR_EXIST;
 
 	return 0;
@@ -180,13 +176,13 @@ mtype_list(const struct ip_set *set,
 		return -EMSGSIZE;
 	for (; cb->args[2] < map->elements; cb->args[2]++) {
 		id = cb->args[2];
-		x = get_ext(map, id);
+		x = get_ext(set, map, id);
 		if (!test_bit(id, map->members) ||
 		    (SET_WITH_TIMEOUT(set) &&
 #ifdef IP_SET_BITMAP_STORED_TIMEOUT
 		     mtype_is_filled((const struct mtype_elem *) x) &&
 #endif
-		     ip_set_timeout_expired(ext_timeout(x, map))))
+		     ip_set_timeout_expired(ext_timeout(x, set))))
 			continue;
 		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 		if (!nested) {
@@ -196,23 +192,24 @@ mtype_list(const struct ip_set *set,
 			} else
 				goto nla_put_failure;
 		}
-		if (mtype_do_list(skb, map, id))
+		if (mtype_do_list(skb, map, id, set->dsize))
 			goto nla_put_failure;
 		if (SET_WITH_TIMEOUT(set)) {
 #ifdef IP_SET_BITMAP_STORED_TIMEOUT
 			if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
 					  htonl(ip_set_timeout_stored(map, id,
-							ext_timeout(x, map)))))
+							ext_timeout(x, set),
+							set->dsize))))
 				goto nla_put_failure;
 #else
 			if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
 					  htonl(ip_set_timeout_get(
-							ext_timeout(x, map)))))
+							ext_timeout(x, set)))))
 				goto nla_put_failure;
 #endif
 		}
 		if (SET_WITH_COUNTER(set) &&
-		    ip_set_put_counter(skb, ext_counter(x, map)))
+		    ip_set_put_counter(skb, ext_counter(x, set)))
 			goto nla_put_failure;
 		ipset_nest_end(skb, nested);
 	}
@@ -245,14 +242,14 @@ mtype_gc(unsigned long ul_set)
 	 * but adding/deleting new entries is locked out */
 	read_lock_bh(&set->lock);
 	for (id = 0; id < map->elements; id++)
-		if (mtype_gc_test(id, map)) {
-			x = get_ext(map, id);
-			if (ip_set_timeout_expired(ext_timeout(x, map)))
+		if (mtype_gc_test(id, map, set->dsize)) {
+			x = get_ext(set, map, id);
+			if (ip_set_timeout_expired(ext_timeout(x, set)))
 				clear_bit(id, map->members);
 		}
 	read_unlock_bh(&set->lock);
 
-	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&map->gc);
 }
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 2ee210ef49a2..363022edb8fb 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -44,10 +44,7 @@ struct bitmap_ip {
 	u32 elements;		/* number of max elements in the set */
 	u32 hosts;		/* number of hosts in a subnet */
 	size_t memsize;		/* members size */
-	size_t dsize;		/* extensions struct size */
-	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	u8 netmask;		/* subnet netmask */
-	u32 timeout;		/* timeout parameter */
 	struct timer_list gc;	/* garbage collection */
 };
 
@@ -65,20 +62,21 @@ ip_to_id(const struct bitmap_ip *m, u32 ip)
 /* Common functions */
 
 static inline int
-bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
+bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e,
+		  struct bitmap_ip *map, size_t dsize)
 {
 	return !!test_bit(e->id, map->members);
 }
 
 static inline int
-bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map)
+bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map, size_t dsize)
 {
 	return !!test_bit(id, map->members);
 }
 
 static inline int
 bitmap_ip_do_add(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map,
-		 u32 flags)
+		 u32 flags, size_t dsize)
 {
 	return !!test_and_set_bit(e->id, map->members);
 }
@@ -90,7 +88,8 @@ bitmap_ip_do_del(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
 }
 
 static inline int
-bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id)
+bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id,
+		  size_t dsize)
 {
 	return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
 			htonl(map->first_ip + id * map->hosts));
@@ -113,7 +112,7 @@ bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct bitmap_ip *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct bitmap_ip_adt_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	u32 ip;
 
 	ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
@@ -133,7 +132,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	u32 ip = 0, ip_to = 0;
 	struct bitmap_ip_adt_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	int ret = 0;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
@@ -200,7 +199,7 @@ bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
 	return x->first_ip == y->first_ip &&
 	       x->last_ip == y->last_ip &&
 	       x->netmask == y->netmask &&
-	       x->timeout == y->timeout &&
+	       a->timeout == b->timeout &&
 	       a->extensions == b->extensions;
 }
 
@@ -240,8 +239,8 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 	map->members = ip_set_alloc(map->memsize);
 	if (!map->members)
 		return false;
-	if (map->dsize) {
-		map->extensions = ip_set_alloc(map->dsize * elements);
+	if (set->dsize) {
+		map->extensions = ip_set_alloc(set->dsize * elements);
 		if (!map->extensions) {
 			kfree(map->members);
 			return false;
@@ -252,7 +251,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 	map->elements = elements;
 	map->hosts = hosts;
 	map->netmask = netmask;
-	map->timeout = IPSET_NO_TIMEOUT;
+	set->timeout = IPSET_NO_TIMEOUT;
 
 	set->data = map;
 	set->family = NFPROTO_IPV4;
@@ -341,10 +340,10 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
-			map->dsize = sizeof(struct bitmap_ipct_elem);
-			map->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->dsize = sizeof(struct bitmap_ipct_elem);
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_ipct_elem, timeout);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipct_elem, counter);
 
 			if (!init_map_ip(set, map, first_ip, last_ip,
@@ -353,14 +352,14 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 				return -ENOMEM;
 			}
 
-			map->timeout = ip_set_timeout_uget(
+			set->timeout = ip_set_timeout_uget(
 				tb[IPSET_ATTR_TIMEOUT]);
 			set->extensions |= IPSET_EXT_TIMEOUT;
 
 			bitmap_ip_gc_init(set, bitmap_ip_gc);
 		} else {
-			map->dsize = sizeof(struct bitmap_ipc_elem);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->dsize = sizeof(struct bitmap_ipc_elem);
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipc_elem, counter);
 
 			if (!init_map_ip(set, map, first_ip, last_ip,
@@ -370,8 +369,8 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			}
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		map->dsize = sizeof(struct bitmap_ipt_elem);
-		map->offset[IPSET_EXT_ID_TIMEOUT] =
+		set->dsize = sizeof(struct bitmap_ipt_elem);
+		set->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_ipt_elem, timeout);
 
 		if (!init_map_ip(set, map, first_ip, last_ip,
@@ -380,12 +379,12 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			return -ENOMEM;
 		}
 
-		map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		set->extensions |= IPSET_EXT_TIMEOUT;
 
 		bitmap_ip_gc_init(set, bitmap_ip_gc);
 	} else {
-		map->dsize = 0;
+		set->dsize = 0;
 		if (!init_map_ip(set, map, first_ip, last_ip,
 				 elements, hosts, netmask)) {
 			kfree(map);
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index e711875ea452..74576cb19264 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -48,11 +48,8 @@ struct bitmap_ipmac {
 	u32 first_ip;		/* host byte order, included in range */
 	u32 last_ip;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
-	u32 timeout;		/* timeout value */
-	struct timer_list gc;	/* garbage collector */
 	size_t memsize;		/* members size */
-	size_t dsize;		/* size of element */
-	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
+	struct timer_list gc;	/* garbage collector */
 };
 
 /* ADT structure for generic function args */
@@ -82,13 +79,13 @@ get_elem(void *extensions, u16 id, size_t dsize)
 
 static inline int
 bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
-		     const struct bitmap_ipmac *map)
+		     const struct bitmap_ipmac *map, size_t dsize)
 {
 	const struct bitmap_ipmac_elem *elem;
 
 	if (!test_bit(e->id, map->members))
 		return 0;
-	elem = get_elem(map->extensions, e->id, map->dsize);
+	elem = get_elem(map->extensions, e->id, dsize);
 	if (elem->filled == MAC_FILLED)
 		return e->ether == NULL ||
 		       ether_addr_equal(e->ether, elem->ether);
@@ -97,13 +94,13 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
 }
 
 static inline int
-bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map)
+bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize)
 {
 	const struct bitmap_ipmac_elem *elem;
 
 	if (!test_bit(id, map->members))
 		return 0;
-	elem = get_elem(map->extensions, id, map->dsize);
+	elem = get_elem(map->extensions, id, dsize);
 	/* Timer not started for the incomplete elements */
 	return elem->filled == MAC_FILLED;
 }
@@ -117,13 +114,13 @@ bitmap_ipmac_is_filled(const struct bitmap_ipmac_elem *elem)
 static inline int
 bitmap_ipmac_add_timeout(unsigned long *timeout,
 			 const struct bitmap_ipmac_adt_elem *e,
-			 const struct ip_set_ext *ext,
+			 const struct ip_set_ext *ext, struct ip_set *set,
 			 struct bitmap_ipmac *map, int mode)
 {
 	u32 t = ext->timeout;
 
 	if (mode == IPSET_ADD_START_STORED_TIMEOUT) {
-		if (t == map->timeout)
+		if (t == set->timeout)
 			/* Timeout was not specified, get stored one */
 			t = *timeout;
 		ip_set_timeout_set(timeout, t);
@@ -142,11 +139,11 @@ bitmap_ipmac_add_timeout(unsigned long *timeout,
 
 static inline int
 bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e,
-		    struct bitmap_ipmac *map, u32 flags)
+		    struct bitmap_ipmac *map, u32 flags, size_t dsize)
 {
 	struct bitmap_ipmac_elem *elem;
 
-	elem = get_elem(map->extensions, e->id, map->dsize);
+	elem = get_elem(map->extensions, e->id, dsize);
 	if (test_and_set_bit(e->id, map->members)) {
 		if (elem->filled == MAC_FILLED) {
 			if (e->ether && (flags & IPSET_FLAG_EXIST))
@@ -179,10 +176,11 @@ bitmap_ipmac_do_del(const struct bitmap_ipmac_adt_elem *e,
 }
 
 static inline unsigned long
-ip_set_timeout_stored(struct bitmap_ipmac *map, u32 id, unsigned long *timeout)
+ip_set_timeout_stored(struct bitmap_ipmac *map, u32 id, unsigned long *timeout,
+		      size_t dsize)
 {
 	const struct bitmap_ipmac_elem *elem =
-		get_elem(map->extensions, id, map->dsize);
+		get_elem(map->extensions, id, dsize);
 
 	return elem->filled == MAC_FILLED ? ip_set_timeout_get(timeout) :
 					    *timeout;
@@ -190,10 +188,10 @@ ip_set_timeout_stored(struct bitmap_ipmac *map, u32 id, unsigned long *timeout)
 
 static inline int
 bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
-		     u32 id)
+		     u32 id, size_t dsize)
 {
 	const struct bitmap_ipmac_elem *elem =
-		get_elem(map->extensions, id, map->dsize);
+		get_elem(map->extensions, id, dsize);
 
 	return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
 			       htonl(map->first_ip + id)) ||
@@ -216,7 +214,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct bitmap_ipmac *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct bitmap_ipmac_adt_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	u32 ip;
 
 	/* MAC can be src only */
@@ -245,7 +243,7 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct bitmap_ipmac *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct bitmap_ipmac_adt_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0;
 	int ret = 0;
 
@@ -285,7 +283,7 @@ bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b)
 
 	return x->first_ip == y->first_ip &&
 	       x->last_ip == y->last_ip &&
-	       x->timeout == y->timeout &&
+	       a->timeout == b->timeout &&
 	       a->extensions == b->extensions;
 }
 
@@ -330,11 +328,11 @@ static bool
 init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	       u32 first_ip, u32 last_ip, u32 elements)
 {
-	map->members = ip_set_alloc((last_ip - first_ip + 1) * map->dsize);
+	map->members = ip_set_alloc((last_ip - first_ip + 1) * set->dsize);
 	if (!map->members)
 		return false;
-	if (map->dsize) {
-		map->extensions = ip_set_alloc(map->dsize * elements);
+	if (set->dsize) {
+		map->extensions = ip_set_alloc(set->dsize * elements);
 		if (!map->extensions) {
 			kfree(map->members);
 			return false;
@@ -343,7 +341,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	map->first_ip = first_ip;
 	map->last_ip = last_ip;
 	map->elements = elements;
-	map->timeout = IPSET_NO_TIMEOUT;
+	set->timeout = IPSET_NO_TIMEOUT;
 
 	set->data = map;
 	set->family = NFPROTO_IPV4;
@@ -404,10 +402,10 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
-			map->dsize = sizeof(struct bitmap_ipmacct_elem);
-			map->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->dsize = sizeof(struct bitmap_ipmacct_elem);
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_ipmacct_elem, timeout);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipmacct_elem, counter);
 
 			if (!init_map_ipmac(set, map, first_ip, last_ip,
@@ -415,13 +413,13 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 				kfree(map);
 				return -ENOMEM;
 			}
-			map->timeout = ip_set_timeout_uget(
+			set->timeout = ip_set_timeout_uget(
 				tb[IPSET_ATTR_TIMEOUT]);
 			set->extensions |= IPSET_EXT_TIMEOUT;
 			bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
 		} else {
-			map->dsize = sizeof(struct bitmap_ipmacc_elem);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->dsize = sizeof(struct bitmap_ipmacc_elem);
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_ipmacc_elem, counter);
 
 			if (!init_map_ipmac(set, map, first_ip, last_ip,
@@ -431,19 +429,19 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 			}
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		map->dsize = sizeof(struct bitmap_ipmact_elem);
-		map->offset[IPSET_EXT_ID_TIMEOUT] =
+		set->dsize = sizeof(struct bitmap_ipmact_elem);
+		set->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_ipmact_elem, timeout);
 
 		if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
 			kfree(map);
 			return -ENOMEM;
 		}
-		map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		set->extensions |= IPSET_EXT_TIMEOUT;
 		bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
 	} else {
-		map->dsize = sizeof(struct bitmap_ipmac_elem);
+		set->dsize = sizeof(struct bitmap_ipmac_elem);
 
 		if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
 			kfree(map);
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index bebc137a5737..71da31935499 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -38,9 +38,6 @@ struct bitmap_port {
 	u16 last_port;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
 	size_t memsize;		/* members size */
-	size_t dsize;		/* extensions struct size */
-	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
-	u32 timeout;		/* timeout parameter */
 	struct timer_list gc;	/* garbage collection */
 };
 
@@ -59,20 +56,20 @@ port_to_id(const struct bitmap_port *m, u16 port)
 
 static inline int
 bitmap_port_do_test(const struct bitmap_port_adt_elem *e,
-		    const struct bitmap_port *map)
+		    const struct bitmap_port *map, size_t dsize)
 {
 	return !!test_bit(e->id, map->members);
 }
 
 static inline int
-bitmap_port_gc_test(u16 id, const struct bitmap_port *map)
+bitmap_port_gc_test(u16 id, const struct bitmap_port *map, size_t dsize)
 {
 	return !!test_bit(id, map->members);
 }
 
 static inline int
 bitmap_port_do_add(const struct bitmap_port_adt_elem *e,
-		   struct bitmap_port *map, u32 flags)
+		   struct bitmap_port *map, u32 flags, size_t dsize)
 {
 	return !!test_and_set_bit(e->id, map->members);
 }
@@ -85,7 +82,8 @@ bitmap_port_do_del(const struct bitmap_port_adt_elem *e,
 }
 
 static inline int
-bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id)
+bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id,
+		    size_t dsize)
 {
 	return nla_put_net16(skb, IPSET_ATTR_PORT,
 			     htons(map->first_port + id));
@@ -106,7 +104,7 @@ bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct bitmap_port *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct bitmap_port_adt_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	__be16 __port;
 	u16 port = 0;
 
@@ -131,7 +129,7 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct bitmap_port *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct bitmap_port_adt_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port;	/* wraparound */
 	u16 port_to;
 	int ret = 0;
@@ -191,7 +189,7 @@ bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
 
 	return x->first_port == y->first_port &&
 	       x->last_port == y->last_port &&
-	       x->timeout == y->timeout &&
+	       a->timeout == b->timeout &&
 	       a->extensions == b->extensions;
 }
 
@@ -230,8 +228,8 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
 	map->members = ip_set_alloc(map->memsize);
 	if (!map->members)
 		return false;
-	if (map->dsize) {
-		map->extensions = ip_set_alloc(map->dsize * map->elements);
+	if (set->dsize) {
+		map->extensions = ip_set_alloc(set->dsize * map->elements);
 		if (!map->extensions) {
 			kfree(map->members);
 			return false;
@@ -239,7 +237,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
 	}
 	map->first_port = first_port;
 	map->last_port = last_port;
-	map->timeout = IPSET_NO_TIMEOUT;
+	set->timeout = IPSET_NO_TIMEOUT;
 
 	set->data = map;
 	set->family = NFPROTO_UNSPEC;
@@ -281,23 +279,23 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
-			map->dsize = sizeof(struct bitmap_portct_elem);
-			map->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->dsize = sizeof(struct bitmap_portct_elem);
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct bitmap_portct_elem, timeout);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_portct_elem, counter);
 			if (!init_map_port(set, map, first_port, last_port)) {
 				kfree(map);
 				return -ENOMEM;
 			}
 
-			map->timeout =
+			set->timeout =
 				ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 			set->extensions |= IPSET_EXT_TIMEOUT;
 			bitmap_port_gc_init(set, bitmap_port_gc);
 		} else {
-			map->dsize = sizeof(struct bitmap_portc_elem);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->dsize = sizeof(struct bitmap_portc_elem);
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct bitmap_portc_elem, counter);
 			if (!init_map_port(set, map, first_port, last_port)) {
 				kfree(map);
@@ -305,19 +303,19 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			}
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		map->dsize = sizeof(struct bitmap_portt_elem);
-		map->offset[IPSET_EXT_ID_TIMEOUT] =
+		set->dsize = sizeof(struct bitmap_portt_elem);
+		set->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct bitmap_portt_elem, timeout);
 		if (!init_map_port(set, map, first_port, last_port)) {
 			kfree(map);
 			return -ENOMEM;
 		}
 
-		map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		set->extensions |= IPSET_EXT_TIMEOUT;
 		bitmap_port_gc_init(set, bitmap_port_gc);
 	} else {
-		map->dsize = 0;
+		set->dsize = 0;
 		if (!init_map_port(set, map, first_port, last_port)) {
 			kfree(map);
 			return -ENOMEM;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index e4db9250f337..0cb840e1f8ae 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -178,11 +178,6 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #define NLEN(family)		0
 #endif /* IP_SET_HASH_WITH_NETS */
 
-#define ext_timeout(e, h)	\
-(unsigned long *)(((void *)(e)) + (h)->offset[IPSET_EXT_ID_TIMEOUT])
-#define ext_counter(e, h)	\
-(struct ip_set_counter *)(((void *)(e)) + (h)->offset[IPSET_EXT_ID_COUNTER])
-
 #endif /* _IP_SET_HASH_GEN_H */
 
 /* Family dependent templates */
@@ -276,9 +271,6 @@ struct htype {
 	u32 maxelem;		/* max elements in the hash */
 	u32 elements;		/* current element (vs timeout) */
 	u32 initval;		/* random jhash init value */
-	u32 timeout;		/* timeout value, if enabled */
-	size_t dsize;		/* data struct size */
-	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	struct timer_list gc;	/* garbage collection when timeout enabled */
 	struct mtype_elem next; /* temporary storage for uadd */
 #ifdef IP_SET_HASH_WITH_MULTI
@@ -351,7 +343,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 /* Calculate the actual memory size of the set data */
 static size_t
 mtype_ahash_memsize(const struct htype *h, const struct htable *t,
-		    u8 nets_length)
+		    u8 nets_length, size_t dsize)
 {
 	u32 i;
 	size_t memsize = sizeof(*h)
@@ -362,7 +354,7 @@ mtype_ahash_memsize(const struct htype *h, const struct htable *t,
 			 + jhash_size(t->htable_bits) * sizeof(struct hbucket);
 
 	for (i = 0; i < jhash_size(t->htable_bits); i++)
-		memsize += t->bucket[i].size * h->dsize;
+		memsize += t->bucket[i].size * dsize;
 
 	return memsize;
 }
@@ -417,10 +409,10 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 	init_timer(&h->gc);
 	h->gc.data = (unsigned long) set;
 	h->gc.function = gc;
-	h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+	h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&h->gc);
 	pr_debug("gc initialized, run in every %u\n",
-		 IPSET_GC_PERIOD(h->timeout));
+		 IPSET_GC_PERIOD(set->timeout));
 }
 
 static bool
@@ -431,7 +423,7 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 
 	/* Resizing changes htable_bits, so we ignore it */
 	return x->maxelem == y->maxelem &&
-	       x->timeout == y->timeout &&
+	       a->timeout == b->timeout &&
 #ifdef IP_SET_HASH_WITH_NETMASK
 	       x->netmask == y->netmask &&
 #endif
@@ -444,7 +436,7 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 
 /* Delete expired elements from the hashtable */
 static void
-mtype_expire(struct htype *h, u8 nets_length, size_t dsize)
+mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
 {
 	struct htable *t;
 	struct hbucket *n;
@@ -458,7 +450,7 @@ mtype_expire(struct htype *h, u8 nets_length, size_t dsize)
 		n = hbucket(t, i);
 		for (j = 0; j < n->pos; j++) {
 			data = ahash_data(n, j, dsize);
-			if (ip_set_timeout_expired(ext_timeout(data, h))) {
+			if (ip_set_timeout_expired(ext_timeout(data, set))) {
 				pr_debug("expired %u/%u\n", i, j);
 #ifdef IP_SET_HASH_WITH_NETS
 				mtype_del_cidr(h, CIDR(data->cidr),
@@ -497,10 +489,10 @@ mtype_gc(unsigned long ul_set)
 
 	pr_debug("called\n");
 	write_lock_bh(&set->lock);
-	mtype_expire(h, NLEN(set->family), h->dsize);
+	mtype_expire(set, h, NLEN(set->family), set->dsize);
 	write_unlock_bh(&set->lock);
 
-	h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ;
+	h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&h->gc);
 }
 
@@ -526,7 +518,7 @@ mtype_resize(struct ip_set *set, bool retried)
 	if (SET_WITH_TIMEOUT(set) && !retried) {
 		i = h->elements;
 		write_lock_bh(&set->lock);
-		mtype_expire(set->data, NLEN(set->family), h->dsize);
+		mtype_expire(set, set->data, NLEN(set->family), set->dsize);
 		write_unlock_bh(&set->lock);
 		if (h->elements < i)
 			return 0;
@@ -553,13 +545,13 @@ retry:
 	for (i = 0; i < jhash_size(orig->htable_bits); i++) {
 		n = hbucket(orig, i);
 		for (j = 0; j < n->pos; j++) {
-			data = ahash_data(n, j, h->dsize);
+			data = ahash_data(n, j, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 			flags = 0;
 			mtype_data_reset_flags(data, &flags);
 #endif
 			m = hbucket(t, HKEY(data, h->initval, htable_bits));
-			ret = hbucket_elem_add(m, AHASH_MAX(h), h->dsize);
+			ret = hbucket_elem_add(m, AHASH_MAX(h), set->dsize);
 			if (ret < 0) {
 #ifdef IP_SET_HASH_WITH_NETS
 				mtype_data_reset_flags(data, &flags);
@@ -570,8 +562,8 @@ retry:
 					goto retry;
 				return ret;
 			}
-			d = ahash_data(m, m->pos++, h->dsize);
-			memcpy(d, data, h->dsize);
+			d = ahash_data(m, m->pos++, set->dsize);
+			memcpy(d, data, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 			mtype_data_reset_flags(d, &flags);
 #endif
@@ -609,7 +601,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
 		/* FIXME: when set is full, we slow down here */
-		mtype_expire(h, NLEN(set->family), h->dsize);
+		mtype_expire(set, h, NLEN(set->family), set->dsize);
 
 	if (h->elements >= h->maxelem) {
 		if (net_ratelimit())
@@ -623,11 +615,11 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	key = HKEY(value, h->initval, t->htable_bits);
 	n = hbucket(t, key);
 	for (i = 0; i < n->pos; i++) {
-		data = ahash_data(n, i, h->dsize);
+		data = ahash_data(n, i, set->dsize);
 		if (mtype_data_equal(data, d, &multi)) {
 			if (flag_exist ||
 			    (SET_WITH_TIMEOUT(set) &&
-			     ip_set_timeout_expired(ext_timeout(data, h)))) {
+			     ip_set_timeout_expired(ext_timeout(data, set)))) {
 				/* Just the extensions could be overwritten */
 				j = i;
 				goto reuse_slot;
@@ -638,14 +630,14 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		}
 		/* Reuse first timed out entry */
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(data, h)) &&
+		    ip_set_timeout_expired(ext_timeout(data, set)) &&
 		    j != AHASH_MAX(h) + 1)
 			j = i;
 	}
 reuse_slot:
 	if (j != AHASH_MAX(h) + 1) {
 		/* Fill out reused slot */
-		data = ahash_data(n, j, h->dsize);
+		data = ahash_data(n, j, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 		mtype_del_cidr(h, CIDR(data->cidr), NLEN(set->family), 0);
 		mtype_add_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
@@ -653,13 +645,13 @@ reuse_slot:
 	} else {
 		/* Use/create a new slot */
 		TUNE_AHASH_MAX(h, multi);
-		ret = hbucket_elem_add(n, AHASH_MAX(h), h->dsize);
+		ret = hbucket_elem_add(n, AHASH_MAX(h), set->dsize);
 		if (ret != 0) {
 			if (ret == -EAGAIN)
 				mtype_data_next(&h->next, d);
 			goto out;
 		}
-		data = ahash_data(n, n->pos++, h->dsize);
+		data = ahash_data(n, n->pos++, set->dsize);
 #ifdef IP_SET_HASH_WITH_NETS
 		mtype_add_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
@@ -670,9 +662,9 @@ reuse_slot:
 	mtype_data_set_flags(data, flags);
 #endif
 	if (SET_WITH_TIMEOUT(set))
-		ip_set_timeout_set(ext_timeout(data, h), ext->timeout);
+		ip_set_timeout_set(ext_timeout(data, set), ext->timeout);
 	if (SET_WITH_COUNTER(set))
-		ip_set_init_counter(ext_counter(data, h), ext);
+		ip_set_init_counter(ext_counter(data, set), ext);
 
 out:
 	rcu_read_unlock_bh();
@@ -699,16 +691,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	key = HKEY(value, h->initval, t->htable_bits);
 	n = hbucket(t, key);
 	for (i = 0; i < n->pos; i++) {
-		data = ahash_data(n, i, h->dsize);
+		data = ahash_data(n, i, set->dsize);
 		if (!mtype_data_equal(data, d, &multi))
 			continue;
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(data, h)))
+		    ip_set_timeout_expired(ext_timeout(data, set)))
 			goto out;
 		if (i != n->pos - 1)
 			/* Not last one */
-			memcpy(data, ahash_data(n, n->pos - 1, h->dsize),
-			       h->dsize);
+			memcpy(data, ahash_data(n, n->pos - 1, set->dsize),
+			       set->dsize);
 
 		n->pos--;
 		h->elements--;
@@ -717,14 +709,14 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 #endif
 		if (n->pos + AHASH_INIT_SIZE < n->size) {
 			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
-					    * h->dsize,
+					    * set->dsize,
 					    GFP_ATOMIC);
 			if (!tmp) {
 				ret = 0;
 				goto out;
 			}
 			n->size -= AHASH_INIT_SIZE;
-			memcpy(tmp, n->value, n->size * h->dsize);
+			memcpy(tmp, n->value, n->size * set->dsize);
 			kfree(n->value);
 			n->value = tmp;
 		}
@@ -742,8 +734,7 @@ mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
 		 struct ip_set_ext *mext, struct ip_set *set, u32 flags)
 {
 	if (SET_WITH_COUNTER(set))
-		ip_set_update_counter(ext_counter(data,
-						  (struct htype *)(set->data)),
+		ip_set_update_counter(ext_counter(data, set),
 				      ext, mext, flags);
 	return mtype_do_data_match(data);
 }
@@ -770,12 +761,12 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
 		key = HKEY(d, h->initval, t->htable_bits);
 		n = hbucket(t, key);
 		for (i = 0; i < n->pos; i++) {
-			data = ahash_data(n, i, h->dsize);
+			data = ahash_data(n, i, set->dsize);
 			if (!mtype_data_equal(data, d, &multi))
 				continue;
 			if (SET_WITH_TIMEOUT(set)) {
 				if (!ip_set_timeout_expired(
-							ext_timeout(data, h)))
+						ext_timeout(data, set)))
 					return mtype_data_match(data, ext,
 								mext, set,
 								flags);
@@ -818,10 +809,10 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	key = HKEY(d, h->initval, t->htable_bits);
 	n = hbucket(t, key);
 	for (i = 0; i < n->pos; i++) {
-		data = ahash_data(n, i, h->dsize);
+		data = ahash_data(n, i, set->dsize);
 		if (mtype_data_equal(data, d, &multi) &&
 		    !(SET_WITH_TIMEOUT(set) &&
-		      ip_set_timeout_expired(ext_timeout(data, h)))) {
+		      ip_set_timeout_expired(ext_timeout(data, set)))) {
 			ret = mtype_data_match(data, ext, mext, set, flags);
 			goto out;
 		}
@@ -841,7 +832,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	size_t memsize;
 
 	t = rcu_dereference_bh_nfnl(h->table);
-	memsize = mtype_ahash_memsize(h, t, NLEN(set->family));
+	memsize = mtype_ahash_memsize(h, t, NLEN(set->family), set->dsize);
 
 	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
@@ -858,7 +849,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
 	    ((set->extensions & IPSET_EXT_TIMEOUT) &&
-	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout))) ||
+	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(set->timeout))) ||
 	    ((set->extensions & IPSET_EXT_COUNTER) &&
 	     nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
 			   htonl(IPSET_FLAG_WITH_COUNTERS))))
@@ -894,9 +885,9 @@ mtype_list(const struct ip_set *set,
 		n = hbucket(t, cb->args[2]);
 		pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n);
 		for (i = 0; i < n->pos; i++) {
-			e = ahash_data(n, i, h->dsize);
+			e = ahash_data(n, i, set->dsize);
 			if (SET_WITH_TIMEOUT(set) &&
-			    ip_set_timeout_expired(ext_timeout(e, h)))
+			    ip_set_timeout_expired(ext_timeout(e, set)))
 				continue;
 			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
 				 cb->args[2], n, i, e);
@@ -913,10 +904,10 @@ mtype_list(const struct ip_set *set,
 			if (SET_WITH_TIMEOUT(set) &&
 			    nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
 					  htonl(ip_set_timeout_get(
-						ext_timeout(e, h)))))
+						ext_timeout(e, set)))))
 				goto nla_put_failure;
 			if (SET_WITH_COUNTER(set) &&
-			    ip_set_put_counter(skb, ext_counter(e, h)))
+			    ip_set_put_counter(skb, ext_counter(e, set)))
 				goto nla_put_failure;
 			ipset_nest_end(skb, nested);
 		}
@@ -1026,7 +1017,7 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	h->netmask = netmask;
 #endif
 	get_random_bytes(&h->initval, sizeof(h->initval));
-	h->timeout = IPSET_NO_TIMEOUT;
+	set->timeout = IPSET_NO_TIMEOUT;
 
 	hbits = htable_bits(hashsize);
 	hsize = htable_size(hbits);
@@ -1053,30 +1044,30 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
 		set->extensions |= IPSET_EXT_COUNTER;
 		if (tb[IPSET_ATTR_TIMEOUT]) {
-			h->timeout =
+			set->timeout =
 				ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 			set->extensions |= IPSET_EXT_TIMEOUT;
 			if (set->family == NFPROTO_IPV4) {
-				h->dsize = sizeof(struct
+				set->dsize = sizeof(struct
 					IPSET_TOKEN(HTYPE, 4ct_elem));
-				h->offset[IPSET_EXT_ID_TIMEOUT] =
+				set->offset[IPSET_EXT_ID_TIMEOUT] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4ct_elem),
 						timeout);
-				h->offset[IPSET_EXT_ID_COUNTER] =
+				set->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4ct_elem),
 						counter);
 				IPSET_TOKEN(HTYPE, 4_gc_init)(set,
 					IPSET_TOKEN(HTYPE, 4_gc));
 			} else {
-				h->dsize = sizeof(struct
+				set->dsize = sizeof(struct
 					IPSET_TOKEN(HTYPE, 6ct_elem));
-				h->offset[IPSET_EXT_ID_TIMEOUT] =
+				set->offset[IPSET_EXT_ID_TIMEOUT] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6ct_elem),
 						timeout);
-				h->offset[IPSET_EXT_ID_COUNTER] =
+				set->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6ct_elem),
 						counter);
@@ -1085,36 +1076,36 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			}
 		} else {
 			if (set->family == NFPROTO_IPV4) {
-				h->dsize =
+				set->dsize =
 					sizeof(struct
 						IPSET_TOKEN(HTYPE, 4c_elem));
-				h->offset[IPSET_EXT_ID_COUNTER] =
+				set->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 4c_elem),
 						counter);
 			} else {
-				h->dsize =
+				set->dsize =
 					sizeof(struct
 						IPSET_TOKEN(HTYPE, 6c_elem));
-				h->offset[IPSET_EXT_ID_COUNTER] =
+				set->offset[IPSET_EXT_ID_COUNTER] =
 					offsetof(struct
 						IPSET_TOKEN(HTYPE, 6c_elem),
 						counter);
 			}
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		set->extensions |= IPSET_EXT_TIMEOUT;
 		if (set->family == NFPROTO_IPV4) {
-			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4t_elem));
-			h->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4t_elem));
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct IPSET_TOKEN(HTYPE, 4t_elem),
 					 timeout);
 			IPSET_TOKEN(HTYPE, 4_gc_init)(set,
 				IPSET_TOKEN(HTYPE, 4_gc));
 		} else {
-			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6t_elem));
-			h->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6t_elem));
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct IPSET_TOKEN(HTYPE, 6t_elem),
 					 timeout);
 			IPSET_TOKEN(HTYPE, 6_gc_init)(set,
@@ -1122,9 +1113,9 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		}
 	} else {
 		if (set->family == NFPROTO_IPV4)
-			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4_elem));
+			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4_elem));
 		else
-			h->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6_elem));
+			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6_elem));
 	}
 
 	pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 260c9a80d8a5..bbde7c304622 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -99,7 +99,7 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_ip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ip4_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	__be32 ip;
 
 	ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip);
@@ -118,7 +118,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ip4_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, hosts;
 	int ret = 0;
 
@@ -253,7 +253,7 @@ hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	const struct hash_ip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ip6_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
 	hash_ip6_netmask(&e.ip, h->netmask);
@@ -270,7 +270,7 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ip6_elem e = {};
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 64caad35a391..dd175d6f3965 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -116,10 +116,9 @@ hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		  const struct xt_action_param *par,
 		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
 {
-	const struct hash_ipport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport4_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
 				 &e.port, &e.proto))
@@ -136,7 +135,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport4_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip, ip_to = 0, p = 0, port, port_to;
 	bool with_ports = false;
 	int ret;
@@ -306,10 +305,9 @@ hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb,
 		  const struct xt_action_param *par,
 		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
 {
-	const struct hash_ipport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport6_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
 				 &e.port, &e.proto))
@@ -326,7 +324,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport6_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
 	int ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 2873bbc20d7a..87a2cfab2568 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -120,10 +120,9 @@ hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		    const struct xt_action_param *par,
 		    enum ipset_adt adt, struct ip_set_adt_opt *opt)
 {
-	const struct hash_ipportip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip4_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
 				 &e.port, &e.proto))
@@ -141,7 +140,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipportip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip4_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip, ip_to = 0, p = 0, port, port_to;
 	bool with_ports = false;
 	int ret;
@@ -319,10 +318,9 @@ hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb,
 		    const struct xt_action_param *par,
 		    enum ipset_adt adt, struct ip_set_adt_opt *opt)
 {
-	const struct hash_ipportip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip6_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
 				 &e.port, &e.proto))
@@ -340,7 +338,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipportip *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip6_elem e = { };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
 	int ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 6ce5a8e2c44e..0b9a28d7c740 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -172,7 +172,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_ipportnet4_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (adt == IPSET_TEST)
 		e.cidr = HOST_MASK - 1;
@@ -195,7 +195,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, p = 0, port, port_to;
 	u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
 	bool with_ports = false;
@@ -306,9 +306,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 						       : port;
 		for (; p <= port_to; p++) {
 			e.port = htons(p);
-			ip2 = retried
-			      && ip == ntohl(h->next.ip)
-			      && p == ntohs(h->next.port)
+			ip2 = retried &&
+			      ip == ntohl(h->next.ip) &&
+			      p == ntohs(h->next.port)
 				? ntohl(h->next.ip2) : ip2_from;
 			while (!after(ip2, ip2_to)) {
 				e.ip2 = htonl(ip2);
@@ -456,7 +456,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_ipportnet6_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (adt == IPSET_TEST)
 		e.cidr = HOST_MASK - 1;
@@ -479,7 +479,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_ipportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet6_elem e = { .cidr = HOST_MASK - 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
 	u8 cidr;
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index ec1c7dc10489..1d4caa50dacb 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -145,7 +145,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_net4_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (e.cidr == 0)
 		return -EINVAL;
@@ -165,7 +165,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_net *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_net4_elem e = { .cidr = HOST_MASK };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, last;
 	int ret;
 
@@ -340,7 +340,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_net6_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (e.cidr == 0)
 		return -EINVAL;
@@ -357,10 +357,9 @@ static int
 hash_net6_uadt(struct ip_set *set, struct nlattr *tb[],
 	       enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_net *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_net6_elem e = { .cidr = HOST_MASK };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	int ret;
 
 	if (unlikely(!tb[IPSET_ATTR_IP] ||
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 814b4e31a7f8..2f0ffe35c408 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -268,7 +268,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 		.elem = 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	int ret;
 
 	if (e.cidr == 0)
@@ -319,7 +319,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_netiface *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, last;
 	char iface[IFNAMSIZ];
 	int ret;
@@ -537,7 +537,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
 		.elem = 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 	int ret;
 
 	if (e.cidr == 0)
@@ -584,7 +584,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
 	struct hash_netiface *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netiface6_elem e = { .cidr = HOST_MASK, .elem = 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	char iface[IFNAMSIZ];
 	int ret;
 
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 3bd923d3f179..cab236625f97 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -164,7 +164,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_netport4_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (adt == IPSET_TEST)
 		e.cidr = HOST_MASK - 1;
@@ -186,7 +186,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_netport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to, p = 0, ip = 0, ip_to = 0, last;
 	bool with_ports = false;
 	u8 cidr;
@@ -409,7 +409,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	struct hash_netport6_elem e = {
 		.cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
 	};
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, h);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	if (adt == IPSET_TEST)
 		e.cidr = HOST_MASK - 1;
@@ -431,7 +431,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct hash_netport *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport6_elem e = { .cidr = HOST_MASK  - 1 };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(h);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
 	u8 cidr;
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 0ed19b5e675e..f22d05d6e366 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -58,24 +58,13 @@ struct set_adt_elem {
 
 /* Type structure */
 struct list_set {
-	size_t dsize;		/* element size */
-	size_t offset[IPSET_EXT_ID_MAX]; /* Offsets to extensions */
 	u32 size;		/* size of set list array */
-	u32 timeout;		/* timeout value */
 	struct timer_list gc;	/* garbage collection */
 	struct set_elem members[0]; /* the set members */
 };
 
-static inline struct set_elem *
-list_set_elem(const struct list_set *map, u32 id)
-{
-	return (struct set_elem *)((void *)map->members + id * map->dsize);
-}
-
-#define ext_timeout(e, m)	\
-(unsigned long *)((void *)(e) + (m)->offset[IPSET_EXT_ID_TIMEOUT])
-#define ext_counter(e, m)	\
-(struct ip_set_counter *)((void *)(e) + (m)->offset[IPSET_EXT_ID_COUNTER])
+#define list_set_elem(set, map, id)	\
+	(struct set_elem *)((void *)(map)->members + (id) * (set)->dsize)
 
 static int
 list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
@@ -92,16 +81,16 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
 	if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
 		opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			return 0;
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(e, map)))
+		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		ret = ip_set_test(e->id, skb, par, opt);
 		if (ret > 0) {
 			if (SET_WITH_COUNTER(set))
-				ip_set_update_counter(ext_counter(e, map),
+				ip_set_update_counter(ext_counter(e, set),
 						      ext, &opt->ext,
 						      cmdflags);
 			return ret;
@@ -121,11 +110,11 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
 	int ret;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			return 0;
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(e, map)))
+		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		ret = ip_set_add(e->id, skb, par, opt);
 		if (ret == 0)
@@ -145,11 +134,11 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
 	int ret;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			return 0;
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(e, map)))
+		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		ret = ip_set_del(e->id, skb, par, opt);
 		if (ret == 0)
@@ -163,8 +152,7 @@ list_set_kadt(struct ip_set *set, const struct sk_buff *skb,
 	      const struct xt_action_param *par,
 	      enum ipset_adt adt, struct ip_set_adt_opt *opt)
 {
-	struct list_set *map = set->data;
-	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, map);
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
 
 	switch (adt) {
 	case IPSET_TEST:
@@ -188,10 +176,10 @@ id_eq(const struct ip_set *set, u32 i, ip_set_id_t id)
 	if (i >= map->size)
 		return 0;
 
-	e = list_set_elem(map, i);
+	e = list_set_elem(set, map, i);
 	return !!(e->id == id &&
 		 !(SET_WITH_TIMEOUT(set) &&
-		   ip_set_timeout_expired(ext_timeout(e, map))));
+		   ip_set_timeout_expired(ext_timeout(e, set))));
 }
 
 static int
@@ -199,28 +187,29 @@ list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
 	     const struct ip_set_ext *ext)
 {
 	struct list_set *map = set->data;
-	struct set_elem *e = list_set_elem(map, i);
+	struct set_elem *e = list_set_elem(set, map, i);
 
 	if (e->id != IPSET_INVALID_ID) {
 		if (i == map->size - 1)
 			/* Last element replaced: e.g. add new,before,last */
 			ip_set_put_byindex(e->id);
 		else {
-			struct set_elem *x = list_set_elem(map, map->size - 1);
+			struct set_elem *x = list_set_elem(set, map,
+							   map->size - 1);
 
 			/* Last element pushed off */
 			if (x->id != IPSET_INVALID_ID)
 				ip_set_put_byindex(x->id);
-			memmove(list_set_elem(map, i + 1), e,
-				map->dsize * (map->size - (i + 1)));
+			memmove(list_set_elem(set, map, i + 1), e,
+				set->dsize * (map->size - (i + 1)));
 		}
 	}
 
 	e->id = d->id;
 	if (SET_WITH_TIMEOUT(set))
-		ip_set_timeout_set(ext_timeout(e, map), ext->timeout);
+		ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
 	if (SET_WITH_COUNTER(set))
-		ip_set_init_counter(ext_counter(e, map), ext);
+		ip_set_init_counter(ext_counter(e, set), ext);
 	return 0;
 }
 
@@ -228,16 +217,16 @@ static int
 list_set_del(struct ip_set *set, u32 i)
 {
 	struct list_set *map = set->data;
-	struct set_elem *e = list_set_elem(map, i);
+	struct set_elem *e = list_set_elem(set, map, i);
 
 	ip_set_put_byindex(e->id);
 
 	if (i < map->size - 1)
-		memmove(e, list_set_elem(map, i + 1),
-			map->dsize * (map->size - (i + 1)));
+		memmove(e, list_set_elem(set, map, i + 1),
+			set->dsize * (map->size - (i + 1)));
 
 	/* Last element */
-	e = list_set_elem(map, map->size - 1);
+	e = list_set_elem(set, map, map->size - 1);
 	e->id = IPSET_INVALID_ID;
 	return 0;
 }
@@ -250,9 +239,9 @@ set_cleanup_entries(struct ip_set *set)
 	u32 i;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id != IPSET_INVALID_ID &&
-		    ip_set_timeout_expired(ext_timeout(e, map)))
+		    ip_set_timeout_expired(ext_timeout(e, set)))
 			list_set_del(set, i);
 	}
 }
@@ -268,11 +257,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	int ret;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			return 0;
 		else if (SET_WITH_TIMEOUT(set) &&
-			 ip_set_timeout_expired(ext_timeout(e, map)))
+			 ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		else if (e->id != d->id)
 			continue;
@@ -301,11 +290,11 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 
 	/* Check already added element */
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			goto insert;
 		else if (SET_WITH_TIMEOUT(set) &&
-			 ip_set_timeout_expired(ext_timeout(e, map)))
+			 ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		else if (e->id != d->id)
 			continue;
@@ -320,9 +309,9 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 			return -IPSET_ERR_EXIST;
 		/* Update extensions */
 		if (SET_WITH_TIMEOUT(set))
-			ip_set_timeout_set(ext_timeout(e, map), ext->timeout);
+			ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
 		if (SET_WITH_COUNTER(set))
-			ip_set_init_counter(ext_counter(e, map), ext);
+			ip_set_init_counter(ext_counter(e, set), ext);
 		/* Set is already added to the list */
 		ip_set_put_byindex(d->id);
 		return 0;
@@ -330,7 +319,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 insert:
 	ret = -IPSET_ERR_LIST_FULL;
 	for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			ret = d->before != 0 ? -IPSET_ERR_REF_EXIST
 				: list_set_add(set, i, d, ext);
@@ -355,12 +344,12 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	u32 i;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			return d->before != 0 ? -IPSET_ERR_REF_EXIST
 					      : -IPSET_ERR_EXIST;
 		else if (SET_WITH_TIMEOUT(set) &&
-			 ip_set_timeout_expired(ext_timeout(e, map)))
+			 ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		else if (e->id != d->id)
 			continue;
@@ -383,10 +372,9 @@ static int
 list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 	      enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	struct list_set *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct set_adt_elem e = { .refid = IPSET_INVALID_ID };
-	struct ip_set_ext ext = IP_SET_INIT_UEXT(map);
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	struct ip_set *s;
 	int ret = 0;
 
@@ -454,7 +442,7 @@ list_set_flush(struct ip_set *set)
 	u32 i;
 
 	for (i = 0; i < map->size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id != IPSET_INVALID_ID) {
 			ip_set_put_byindex(e->id);
 			e->id = IPSET_INVALID_ID;
@@ -486,13 +474,13 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) ||
 	    (SET_WITH_TIMEOUT(set) &&
-	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) ||
+	     nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(set->timeout))) ||
 	    (SET_WITH_COUNTER(set) &&
 	     nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS,
 			   htonl(IPSET_FLAG_WITH_COUNTERS))) ||
 	    nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
-			  htonl(sizeof(*map) + map->size * map->dsize)))
+			  htonl(sizeof(*map) + map->size * set->dsize)))
 		goto nla_put_failure;
 	ipset_nest_end(skb, nested);
 
@@ -515,11 +503,11 @@ list_set_list(const struct ip_set *set,
 		return -EMSGSIZE;
 	for (; cb->args[2] < map->size; cb->args[2]++) {
 		i = cb->args[2];
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			goto finish;
 		if (SET_WITH_TIMEOUT(set) &&
-		    ip_set_timeout_expired(ext_timeout(e, map)))
+		    ip_set_timeout_expired(ext_timeout(e, set)))
 			continue;
 		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 		if (!nested) {
@@ -535,10 +523,10 @@ list_set_list(const struct ip_set *set,
 		if (SET_WITH_TIMEOUT(set) &&
 		    nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
 				  htonl(ip_set_timeout_get(
-						ext_timeout(e, map)))))
+						ext_timeout(e, set)))))
 			goto nla_put_failure;
 		if (SET_WITH_COUNTER(set) &&
-		    ip_set_put_counter(skb, ext_counter(e, map)))
+		    ip_set_put_counter(skb, ext_counter(e, set)))
 			goto nla_put_failure;
 		ipset_nest_end(skb, nested);
 	}
@@ -565,7 +553,7 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
 	const struct list_set *y = b->data;
 
 	return x->size == y->size &&
-	       x->timeout == y->timeout &&
+	       a->timeout == b->timeout &&
 	       a->extensions == b->extensions;
 }
 
@@ -594,7 +582,7 @@ list_set_gc(unsigned long ul_set)
 	set_cleanup_entries(set);
 	write_unlock_bh(&set->lock);
 
-	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&map->gc);
 }
 
@@ -606,7 +594,7 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 	init_timer(&map->gc);
 	map->gc.data = (unsigned long) set;
 	map->gc.function = gc;
-	map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+	map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
 	add_timer(&map->gc);
 }
 
@@ -625,12 +613,12 @@ init_list_set(struct ip_set *set, u32 size, size_t dsize,
 		return NULL;
 
 	map->size = size;
-	map->dsize = dsize;
-	map->timeout = timeout;
+	set->dsize = dsize;
+	set->timeout = timeout;
 	set->data = map;
 
 	for (i = 0; i < size; i++) {
-		e = list_set_elem(map, i);
+		e = list_set_elem(set, map, i);
 		e->id = IPSET_INVALID_ID;
 	}
 
@@ -667,9 +655,9 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 			if (!map)
 				return -ENOMEM;
 			set->extensions |= IPSET_EXT_TIMEOUT;
-			map->offset[IPSET_EXT_ID_TIMEOUT] =
+			set->offset[IPSET_EXT_ID_TIMEOUT] =
 				offsetof(struct setct_elem, timeout);
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct setct_elem, counter);
 			list_set_gc_init(set, list_set_gc);
 		} else {
@@ -677,7 +665,7 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 					    sizeof(struct setc_elem), 0);
 			if (!map)
 				return -ENOMEM;
-			map->offset[IPSET_EXT_ID_COUNTER] =
+			set->offset[IPSET_EXT_ID_COUNTER] =
 				offsetof(struct setc_elem, counter);
 		}
 	} else if (tb[IPSET_ATTR_TIMEOUT]) {
@@ -686,7 +674,7 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 		if (!map)
 			return -ENOMEM;
 		set->extensions |= IPSET_EXT_TIMEOUT;
-		map->offset[IPSET_EXT_ID_TIMEOUT] =
+		set->offset[IPSET_EXT_ID_TIMEOUT] =
 			offsetof(struct sett_elem, timeout);
 		list_set_gc_init(set, list_set_gc);
 	} else {
-- 
cgit 


From 03c8b234e61a9a3aab8d970b3bf681934ecfe443 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Sat, 7 Sep 2013 00:43:52 +0200
Subject: netfilter: ipset: Generalize extensions support

Get rid of the structure based extensions and introduce a blob for
the extensions. Thus we can support more extension types easily.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      | 13 +++++
 net/netfilter/ipset/ip_set_bitmap_ip.c      | 81 +++----------------------
 net/netfilter/ipset/ip_set_bitmap_ipmac.c   | 91 +++--------------------------
 net/netfilter/ipset/ip_set_bitmap_port.c    | 71 ++--------------------
 net/netfilter/ipset/ip_set_core.c           | 46 +++++++++++++++
 net/netfilter/ipset/ip_set_hash_gen.h       | 86 ++++-----------------------
 net/netfilter/ipset/ip_set_hash_ip.c        | 36 +-----------
 net/netfilter/ipset/ip_set_hash_ipport.c    | 54 +----------------
 net/netfilter/ipset/ip_set_hash_ipportip.c  | 60 +------------------
 net/netfilter/ipset/ip_set_hash_ipportnet.c | 66 +--------------------
 net/netfilter/ipset/ip_set_hash_net.c       | 54 +----------------
 net/netfilter/ipset/ip_set_hash_netiface.c  | 68 +--------------------
 net/netfilter/ipset/ip_set_hash_netport.c   | 60 +------------------
 net/netfilter/ipset/ip_set_list_set.c       | 81 ++++---------------------
 14 files changed, 118 insertions(+), 749 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 992a2f58dbd3..66d6bd404d64 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -66,6 +66,17 @@ enum ip_set_ext_id {
 	IPSET_EXT_ID_MAX,
 };
 
+/* Extension type */
+struct ip_set_ext_type {
+	enum ip_set_extension type;
+	enum ipset_cadt_flags flag;
+	/* Size and minimal alignment */
+	u8 len;
+	u8 align;
+};
+
+extern const struct ip_set_ext_type ip_set_extensions[];
+
 struct ip_set_ext {
 	u64 packets;
 	u64 bytes;
@@ -283,6 +294,8 @@ extern void *ip_set_alloc(size_t size);
 extern void ip_set_free(void *members);
 extern int ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr);
 extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr);
+extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[],
+			      size_t len);
 extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 				 struct ip_set_ext *ext);
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 363022edb8fb..94d985457c51 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -208,25 +208,6 @@ bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
 struct bitmap_ip_elem {
 };
 
-/* Timeout variant */
-
-struct bitmap_ipt_elem {
-	unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_ipc_elem {
-	struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_ipct_elem {
-	unsigned long timeout;
-	struct ip_set_counter counter;
-};
-
 #include "ip_set_bitmap_gen.h"
 
 /* Create bitmap:ip type of sets */
@@ -263,7 +244,7 @@ static int
 bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 {
 	struct bitmap_ip *map;
-	u32 first_ip = 0, last_ip = 0, hosts, cadt_flags = 0;
+	u32 first_ip = 0, last_ip = 0, hosts;
 	u64 elements;
 	u8 netmask = 32;
 	int ret;
@@ -335,61 +316,15 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 
 	map->memsize = bitmap_bytes(0, elements - 1);
 	set->variant = &bitmap_ip;
-	if (tb[IPSET_ATTR_CADT_FLAGS])
-		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
-	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
-		set->extensions |= IPSET_EXT_COUNTER;
-		if (tb[IPSET_ATTR_TIMEOUT]) {
-			set->dsize = sizeof(struct bitmap_ipct_elem);
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct bitmap_ipct_elem, timeout);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_ipct_elem, counter);
-
-			if (!init_map_ip(set, map, first_ip, last_ip,
-					 elements, hosts, netmask)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-
-			set->timeout = ip_set_timeout_uget(
-				tb[IPSET_ATTR_TIMEOUT]);
-			set->extensions |= IPSET_EXT_TIMEOUT;
-
-			bitmap_ip_gc_init(set, bitmap_ip_gc);
-		} else {
-			set->dsize = sizeof(struct bitmap_ipc_elem);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_ipc_elem, counter);
-
-			if (!init_map_ip(set, map, first_ip, last_ip,
-					 elements, hosts, netmask)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-		}
-	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		set->dsize = sizeof(struct bitmap_ipt_elem);
-		set->offset[IPSET_EXT_ID_TIMEOUT] =
-			offsetof(struct bitmap_ipt_elem, timeout);
-
-		if (!init_map_ip(set, map, first_ip, last_ip,
-				 elements, hosts, netmask)) {
-			kfree(map);
-			return -ENOMEM;
-		}
-
+	set->dsize = ip_set_elem_len(set, tb, 0);
+	if (!init_map_ip(set, map, first_ip, last_ip,
+			 elements, hosts, netmask)) {
+		kfree(map);
+		return -ENOMEM;
+	}
+	if (tb[IPSET_ATTR_TIMEOUT]) {
 		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-		set->extensions |= IPSET_EXT_TIMEOUT;
-
 		bitmap_ip_gc_init(set, bitmap_ip_gc);
-	} else {
-		set->dsize = 0;
-		if (!init_map_ip(set, map, first_ip, last_ip,
-				 elements, hosts, netmask)) {
-			kfree(map);
-			return -ENOMEM;
-		}
 	}
 	return 0;
 }
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 74576cb19264..654a97bedfe9 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -289,37 +289,6 @@ bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b)
 
 /* Plain variant */
 
-/* Timeout variant */
-
-struct bitmap_ipmact_elem {
-	struct {
-		unsigned char ether[ETH_ALEN];
-		unsigned char filled;
-	} __attribute__ ((aligned));
-	unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_ipmacc_elem {
-	struct {
-		unsigned char ether[ETH_ALEN];
-		unsigned char filled;
-	} __attribute__ ((aligned));
-	struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_ipmacct_elem {
-	struct {
-		unsigned char ether[ETH_ALEN];
-		unsigned char filled;
-	} __attribute__ ((aligned));
-	unsigned long timeout;
-	struct ip_set_counter counter;
-};
-
 #include "ip_set_bitmap_gen.h"
 
 /* Create bitmap:ip,mac type of sets */
@@ -328,7 +297,7 @@ static bool
 init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	       u32 first_ip, u32 last_ip, u32 elements)
 {
-	map->members = ip_set_alloc((last_ip - first_ip + 1) * set->dsize);
+	map->members = ip_set_alloc(map->memsize);
 	if (!map->members)
 		return false;
 	if (set->dsize) {
@@ -353,7 +322,7 @@ static int
 bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 		    u32 flags)
 {
-	u32 first_ip = 0, last_ip = 0, cadt_flags = 0;
+	u32 first_ip = 0, last_ip = 0;
 	u64 elements;
 	struct bitmap_ipmac *map;
 	int ret;
@@ -397,57 +366,15 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
 
 	map->memsize = bitmap_bytes(0, elements - 1);
 	set->variant = &bitmap_ipmac;
-	if (tb[IPSET_ATTR_CADT_FLAGS])
-		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
-	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
-		set->extensions |= IPSET_EXT_COUNTER;
-		if (tb[IPSET_ATTR_TIMEOUT]) {
-			set->dsize = sizeof(struct bitmap_ipmacct_elem);
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct bitmap_ipmacct_elem, timeout);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_ipmacct_elem, counter);
-
-			if (!init_map_ipmac(set, map, first_ip, last_ip,
-					    elements)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-			set->timeout = ip_set_timeout_uget(
-				tb[IPSET_ATTR_TIMEOUT]);
-			set->extensions |= IPSET_EXT_TIMEOUT;
-			bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
-		} else {
-			set->dsize = sizeof(struct bitmap_ipmacc_elem);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_ipmacc_elem, counter);
-
-			if (!init_map_ipmac(set, map, first_ip, last_ip,
-					    elements)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-		}
-	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		set->dsize = sizeof(struct bitmap_ipmact_elem);
-		set->offset[IPSET_EXT_ID_TIMEOUT] =
-			offsetof(struct bitmap_ipmact_elem, timeout);
-
-		if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
-			kfree(map);
-			return -ENOMEM;
-		}
+	set->dsize = ip_set_elem_len(set, tb,
+				     sizeof(struct bitmap_ipmac_elem));
+	if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
+		kfree(map);
+		return -ENOMEM;
+	}
+	if (tb[IPSET_ATTR_TIMEOUT]) {
 		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-		set->extensions |= IPSET_EXT_TIMEOUT;
 		bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
-	} else {
-		set->dsize = sizeof(struct bitmap_ipmac_elem);
-
-		if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
-			kfree(map);
-			return -ENOMEM;
-		}
-		set->variant = &bitmap_ipmac;
 	}
 	return 0;
 }
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 71da31935499..1ef2f3186b80 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -198,25 +198,6 @@ bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
 struct bitmap_port_elem {
 };
 
-/* Timeout variant */
-
-struct bitmap_portt_elem {
-	unsigned long timeout;
-};
-
-/* Plain variant with counter */
-
-struct bitmap_portc_elem {
-	struct ip_set_counter counter;
-};
-
-/* Timeout variant with counter */
-
-struct bitmap_portct_elem {
-	unsigned long timeout;
-	struct ip_set_counter counter;
-};
-
 #include "ip_set_bitmap_gen.h"
 
 /* Create bitmap:ip type of sets */
@@ -250,7 +231,6 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 {
 	struct bitmap_port *map;
 	u16 first_port, last_port;
-	u32 cadt_flags = 0;
 
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
 		     !ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) ||
@@ -274,53 +254,14 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	map->elements = last_port - first_port + 1;
 	map->memsize = map->elements * sizeof(unsigned long);
 	set->variant = &bitmap_port;
-	if (tb[IPSET_ATTR_CADT_FLAGS])
-		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
-	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
-		set->extensions |= IPSET_EXT_COUNTER;
-		if (tb[IPSET_ATTR_TIMEOUT]) {
-			set->dsize = sizeof(struct bitmap_portct_elem);
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct bitmap_portct_elem, timeout);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_portct_elem, counter);
-			if (!init_map_port(set, map, first_port, last_port)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-
-			set->timeout =
-				ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-			set->extensions |= IPSET_EXT_TIMEOUT;
-			bitmap_port_gc_init(set, bitmap_port_gc);
-		} else {
-			set->dsize = sizeof(struct bitmap_portc_elem);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct bitmap_portc_elem, counter);
-			if (!init_map_port(set, map, first_port, last_port)) {
-				kfree(map);
-				return -ENOMEM;
-			}
-		}
-	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		set->dsize = sizeof(struct bitmap_portt_elem);
-		set->offset[IPSET_EXT_ID_TIMEOUT] =
-			offsetof(struct bitmap_portt_elem, timeout);
-		if (!init_map_port(set, map, first_port, last_port)) {
-			kfree(map);
-			return -ENOMEM;
-		}
-
+	set->dsize = ip_set_elem_len(set, tb, 0);
+	if (!init_map_port(set, map, first_port, last_port)) {
+		kfree(map);
+		return -ENOMEM;
+	}
+	if (tb[IPSET_ATTR_TIMEOUT]) {
 		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-		set->extensions |= IPSET_EXT_TIMEOUT;
 		bitmap_port_gc_init(set, bitmap_port_gc);
-	} else {
-		set->dsize = 0;
-		if (!init_map_port(set, map, first_port, last_port)) {
-			kfree(map);
-			return -ENOMEM;
-		}
-
 	}
 	return 0;
 }
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 428c30a8586f..f35afed3814f 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -315,6 +315,52 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
 }
 EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
 
+/* ipset data extension types, in size order */
+
+const struct ip_set_ext_type ip_set_extensions[] = {
+	[IPSET_EXT_ID_COUNTER] = {
+		.type	= IPSET_EXT_COUNTER,
+		.flag	= IPSET_FLAG_WITH_COUNTERS,
+		.len	= sizeof(struct ip_set_counter),
+		.align	= __alignof__(struct ip_set_counter),
+	},
+	[IPSET_EXT_ID_TIMEOUT] = {
+		.type	= IPSET_EXT_TIMEOUT,
+		.len	= sizeof(unsigned long),
+		.align	= __alignof__(unsigned long),
+	},
+};
+EXPORT_SYMBOL_GPL(ip_set_extensions);
+
+static inline bool
+add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[])
+{
+	return ip_set_extensions[id].flag ?
+		(flags & ip_set_extensions[id].flag) :
+		!!tb[IPSET_ATTR_TIMEOUT];
+}
+
+size_t
+ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len)
+{
+	enum ip_set_ext_id id;
+	size_t offset = 0;
+	u32 cadt_flags = 0;
+
+	if (tb[IPSET_ATTR_CADT_FLAGS])
+		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+	for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
+		if (!add_extension(id, cadt_flags, tb))
+			continue;
+		offset += ALIGN(len + offset, ip_set_extensions[id].align);
+		set->offset[id] = offset;
+		set->extensions |= ip_set_extensions[id].type;
+		offset += ip_set_extensions[id].len;
+	}
+	return len + offset;
+}
+EXPORT_SYMBOL_GPL(ip_set_elem_len);
+
 int
 ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 		      struct ip_set_ext *ext)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 0cb840e1f8ae..3999f1719f69 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -960,7 +960,6 @@ static int
 IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 {
 	u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
-	u32 cadt_flags = 0;
 	u8 hbits;
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;
@@ -1034,88 +1033,23 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	rcu_assign_pointer(h->table, t);
 
 	set->data = h;
-	if (set->family ==  NFPROTO_IPV4)
+	if (set->family ==  NFPROTO_IPV4) {
 		set->variant = &IPSET_TOKEN(HTYPE, 4_variant);
-	else
+		set->dsize = ip_set_elem_len(set, tb,
+				sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)));
+	} else {
 		set->variant = &IPSET_TOKEN(HTYPE, 6_variant);
-
-	if (tb[IPSET_ATTR_CADT_FLAGS])
-		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
-	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
-		set->extensions |= IPSET_EXT_COUNTER;
-		if (tb[IPSET_ATTR_TIMEOUT]) {
-			set->timeout =
-				ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-			set->extensions |= IPSET_EXT_TIMEOUT;
-			if (set->family == NFPROTO_IPV4) {
-				set->dsize = sizeof(struct
-					IPSET_TOKEN(HTYPE, 4ct_elem));
-				set->offset[IPSET_EXT_ID_TIMEOUT] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 4ct_elem),
-						timeout);
-				set->offset[IPSET_EXT_ID_COUNTER] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 4ct_elem),
-						counter);
-				IPSET_TOKEN(HTYPE, 4_gc_init)(set,
-					IPSET_TOKEN(HTYPE, 4_gc));
-			} else {
-				set->dsize = sizeof(struct
-					IPSET_TOKEN(HTYPE, 6ct_elem));
-				set->offset[IPSET_EXT_ID_TIMEOUT] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 6ct_elem),
-						timeout);
-				set->offset[IPSET_EXT_ID_COUNTER] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 6ct_elem),
-						counter);
-				IPSET_TOKEN(HTYPE, 6_gc_init)(set,
-					IPSET_TOKEN(HTYPE, 6_gc));
-			}
-		} else {
-			if (set->family == NFPROTO_IPV4) {
-				set->dsize =
-					sizeof(struct
-						IPSET_TOKEN(HTYPE, 4c_elem));
-				set->offset[IPSET_EXT_ID_COUNTER] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 4c_elem),
-						counter);
-			} else {
-				set->dsize =
-					sizeof(struct
-						IPSET_TOKEN(HTYPE, 6c_elem));
-				set->offset[IPSET_EXT_ID_COUNTER] =
-					offsetof(struct
-						IPSET_TOKEN(HTYPE, 6c_elem),
-						counter);
-			}
-		}
-	} else if (tb[IPSET_ATTR_TIMEOUT]) {
+		set->dsize = ip_set_elem_len(set, tb,
+				sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)));
+	}
+	if (tb[IPSET_ATTR_TIMEOUT]) {
 		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-		set->extensions |= IPSET_EXT_TIMEOUT;
-		if (set->family == NFPROTO_IPV4) {
-			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4t_elem));
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct IPSET_TOKEN(HTYPE, 4t_elem),
-					 timeout);
+		if (set->family == NFPROTO_IPV4)
 			IPSET_TOKEN(HTYPE, 4_gc_init)(set,
 				IPSET_TOKEN(HTYPE, 4_gc));
-		} else {
-			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6t_elem));
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct IPSET_TOKEN(HTYPE, 6t_elem),
-					 timeout);
+		else
 			IPSET_TOKEN(HTYPE, 6_gc_init)(set,
 				IPSET_TOKEN(HTYPE, 6_gc));
-		}
-	} else {
-		if (set->family == NFPROTO_IPV4)
-			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 4_elem));
-		else
-			set->dsize = sizeof(struct IPSET_TOKEN(HTYPE, 6_elem));
 	}
 
 	pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index bbde7c304622..a111ffe40b46 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -35,7 +35,7 @@ MODULE_ALIAS("ip_set_hash:ip");
 #define HTYPE		hash_ip
 #define IP_SET_HASH_WITH_NETMASK
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements */
 struct hash_ip4_elem {
@@ -43,22 +43,6 @@ struct hash_ip4_elem {
 	__be32 ip;
 };
 
-struct hash_ip4t_elem {
-	__be32 ip;
-	unsigned long timeout;
-};
-
-struct hash_ip4c_elem {
-	__be32 ip;
-	struct ip_set_counter counter;
-};
-
-struct hash_ip4ct_elem {
-	__be32 ip;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -178,29 +162,13 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 /* Member elements */
 struct hash_ip6_elem {
 	union nf_inet_addr ip;
 };
 
-struct hash_ip6t_elem {
-	union nf_inet_addr ip;
-	unsigned long timeout;
-};
-
-struct hash_ip6c_elem {
-	union nf_inet_addr ip;
-	struct ip_set_counter counter;
-};
-
-struct hash_ip6ct_elem {
-	union nf_inet_addr ip;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index dd175d6f3965..5dc735c4dac2 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -36,7 +36,7 @@ MODULE_ALIAS("ip_set_hash:ip,port");
 /* Type specific function prefix */
 #define HTYPE		hash_ipport
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements */
 struct hash_ipport4_elem {
@@ -46,31 +46,6 @@ struct hash_ipport4_elem {
 	u8 padding;
 };
 
-struct hash_ipport4t_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	unsigned long timeout;
-};
-
-struct hash_ipport4c_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipport4ct_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -221,7 +196,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_ipport6_elem {
 	union nf_inet_addr ip;
@@ -230,31 +205,6 @@ struct hash_ipport6_elem {
 	u8 padding;
 };
 
-struct hash_ipport6t_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	unsigned long timeout;
-};
-
-struct hash_ipport6c_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipport6ct_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 87a2cfab2568..8c43dc7811cb 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -36,7 +36,7 @@ MODULE_ALIAS("ip_set_hash:ip,port,ip");
 /* Type specific function prefix */
 #define HTYPE		hash_ipportip
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements  */
 struct hash_ipportip4_elem {
@@ -47,34 +47,6 @@ struct hash_ipportip4_elem {
 	u8 padding;
 };
 
-struct hash_ipportip4t_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	unsigned long timeout;
-};
-
-struct hash_ipportip4c_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipportip4ct_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 static inline bool
 hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1,
 			  const struct hash_ipportip4_elem *ip2,
@@ -230,7 +202,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_ipportip6_elem {
 	union nf_inet_addr ip;
@@ -240,34 +212,6 @@ struct hash_ipportip6_elem {
 	u8 padding;
 };
 
-struct hash_ipportip6t_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	unsigned long timeout;
-};
-
-struct hash_ipportip6c_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipportip6ct_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 proto;
-	u8 padding;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 0b9a28d7c740..34890452366c 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -46,7 +46,7 @@ MODULE_ALIAS("ip_set_hash:ip,port,net");
 #define IP_SET_HASH_WITH_PROTO
 #define IP_SET_HASH_WITH_NETS
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements */
 struct hash_ipportnet4_elem {
@@ -58,37 +58,6 @@ struct hash_ipportnet4_elem {
 	u8 proto;
 };
 
-struct hash_ipportnet4t_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	unsigned long timeout;
-};
-
-struct hash_ipportnet4c_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipportnet4ct_elem {
-	__be32 ip;
-	__be32 ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -328,7 +297,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_ipportnet6_elem {
 	union nf_inet_addr ip;
@@ -339,37 +308,6 @@ struct hash_ipportnet6_elem {
 	u8 proto;
 };
 
-struct hash_ipportnet6t_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	unsigned long timeout;
-};
-
-struct hash_ipportnet6c_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	struct ip_set_counter counter;
-};
-
-struct hash_ipportnet6ct_elem {
-	union nf_inet_addr ip;
-	union nf_inet_addr ip2;
-	__be16 port;
-	u8 cidr:7;
-	u8 nomatch:1;
-	u8 proto;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 1d4caa50dacb..d5598557f4a9 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -36,7 +36,7 @@ MODULE_ALIAS("ip_set_hash:net");
 #define HTYPE		hash_net
 #define IP_SET_HASH_WITH_NETS
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements  */
 struct hash_net4_elem {
@@ -46,31 +46,6 @@ struct hash_net4_elem {
 	u8 cidr;
 };
 
-struct hash_net4t_elem {
-	__be32 ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	unsigned long timeout;
-};
-
-struct hash_net4c_elem {
-	__be32 ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	struct ip_set_counter counter;
-};
-
-struct hash_net4ct_elem {
-	__be32 ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -228,7 +203,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_net6_elem {
 	union nf_inet_addr ip;
@@ -237,31 +212,6 @@ struct hash_net6_elem {
 	u8 cidr;
 };
 
-struct hash_net6t_elem {
-	union nf_inet_addr ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	unsigned long timeout;
-};
-
-struct hash_net6c_elem {
-	union nf_inet_addr ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	struct ip_set_counter counter;
-};
-
-struct hash_net6ct_elem {
-	union nf_inet_addr ip;
-	u16 padding0;
-	u8 nomatch;
-	u8 cidr;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 2f0ffe35c408..26703e9e5082 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -134,7 +134,7 @@ iface_add(struct rb_root *root, const char **iface)
 
 #define STREQ(a, b)	(strcmp(a, b) == 0)
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 struct hash_netiface4_elem_hashed {
 	__be32 ip;
@@ -144,7 +144,7 @@ struct hash_netiface4_elem_hashed {
 	u8 elem;
 };
 
-/* Member elements without timeout */
+/* Member elements */
 struct hash_netiface4_elem {
 	__be32 ip;
 	u8 physdev;
@@ -154,37 +154,6 @@ struct hash_netiface4_elem {
 	const char *iface;
 };
 
-struct hash_netiface4t_elem {
-	__be32 ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	unsigned long timeout;
-};
-
-struct hash_netiface4c_elem {
-	__be32 ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	struct ip_set_counter counter;
-};
-
-struct hash_netiface4ct_elem {
-	__be32 ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -399,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_netiface6_elem_hashed {
 	union nf_inet_addr ip;
@@ -418,37 +387,6 @@ struct hash_netiface6_elem {
 	const char *iface;
 };
 
-struct hash_netiface6t_elem {
-	union nf_inet_addr ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	unsigned long timeout;
-};
-
-struct hash_netiface6c_elem {
-	union nf_inet_addr ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	struct ip_set_counter counter;
-};
-
-struct hash_netiface6ct_elem {
-	union nf_inet_addr ip;
-	u8 physdev;
-	u8 cidr;
-	u8 nomatch;
-	u8 elem;
-	const char *iface;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index cab236625f97..45b6e91b0636 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -45,7 +45,7 @@ MODULE_ALIAS("ip_set_hash:net,port");
  */
 #define IP_SET_HASH_WITH_NETS_PACKED
 
-/* IPv4 variants */
+/* IPv4 variant */
 
 /* Member elements */
 struct hash_netport4_elem {
@@ -56,34 +56,6 @@ struct hash_netport4_elem {
 	u8 nomatch:1;
 };
 
-struct hash_netport4t_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	unsigned long timeout;
-};
-
-struct hash_netport4c_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	struct ip_set_counter counter;
-};
-
-struct hash_netport4ct_elem {
-	__be32 ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
@@ -287,7 +259,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	return ret;
 }
 
-/* IPv6 variants */
+/* IPv6 variant */
 
 struct hash_netport6_elem {
 	union nf_inet_addr ip;
@@ -297,34 +269,6 @@ struct hash_netport6_elem {
 	u8 nomatch:1;
 };
 
-struct hash_netport6t_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	unsigned long timeout;
-};
-
-struct hash_netport6c_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	struct ip_set_counter counter;
-};
-
-struct hash_netport6ct_elem {
-	union nf_inet_addr ip;
-	__be16 port;
-	u8 proto;
-	u8 cidr:7;
-	u8 nomatch:1;
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 /* Common functions */
 
 static inline bool
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index f22d05d6e366..7fd11c79aff4 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -28,28 +28,6 @@ struct set_elem {
 	ip_set_id_t id;
 };
 
-struct sett_elem {
-	struct {
-		ip_set_id_t id;
-	} __attribute__ ((aligned));
-	unsigned long timeout;
-};
-
-struct setc_elem {
-	struct {
-		ip_set_id_t id;
-	} __attribute__ ((aligned));
-	struct ip_set_counter counter;
-};
-
-struct setct_elem {
-	struct {
-		ip_set_id_t id;
-	} __attribute__ ((aligned));
-	struct ip_set_counter counter;
-	unsigned long timeout;
-};
-
 struct set_adt_elem {
 	ip_set_id_t id;
 	ip_set_id_t refid;
@@ -600,21 +578,18 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 
 /* Create list:set type of sets */
 
-static struct list_set *
-init_list_set(struct ip_set *set, u32 size, size_t dsize,
-	      unsigned long timeout)
+static bool
+init_list_set(struct ip_set *set, u32 size)
 {
 	struct list_set *map;
 	struct set_elem *e;
 	u32 i;
 
-	map = kzalloc(sizeof(*map) + size * dsize, GFP_KERNEL);
+	map = kzalloc(sizeof(*map) + size * set->dsize, GFP_KERNEL);
 	if (!map)
-		return NULL;
+		return false;
 
 	map->size = size;
-	set->dsize = dsize;
-	set->timeout = timeout;
 	set->data = map;
 
 	for (i = 0; i < size; i++) {
@@ -622,15 +597,13 @@ init_list_set(struct ip_set *set, u32 size, size_t dsize,
 		e->id = IPSET_INVALID_ID;
 	}
 
-	return map;
+	return true;
 }
 
 static int
 list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 {
-	struct list_set *map;
-	u32 size = IP_SET_LIST_DEFAULT_SIZE, cadt_flags = 0;
-	unsigned long timeout = 0;
+	u32 size = IP_SET_LIST_DEFAULT_SIZE;
 
 	if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
@@ -642,45 +615,13 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	if (size < IP_SET_LIST_MIN_SIZE)
 		size = IP_SET_LIST_MIN_SIZE;
 
-	if (tb[IPSET_ATTR_CADT_FLAGS])
-		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
-	if (tb[IPSET_ATTR_TIMEOUT])
-		timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 	set->variant = &set_variant;
-	if (cadt_flags & IPSET_FLAG_WITH_COUNTERS) {
-		set->extensions |= IPSET_EXT_COUNTER;
-		if (tb[IPSET_ATTR_TIMEOUT]) {
-			map = init_list_set(set, size,
-					sizeof(struct setct_elem), timeout);
-			if (!map)
-				return -ENOMEM;
-			set->extensions |= IPSET_EXT_TIMEOUT;
-			set->offset[IPSET_EXT_ID_TIMEOUT] =
-				offsetof(struct setct_elem, timeout);
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct setct_elem, counter);
-			list_set_gc_init(set, list_set_gc);
-		} else {
-			map = init_list_set(set, size,
-					    sizeof(struct setc_elem), 0);
-			if (!map)
-				return -ENOMEM;
-			set->offset[IPSET_EXT_ID_COUNTER] =
-				offsetof(struct setc_elem, counter);
-		}
-	} else if (tb[IPSET_ATTR_TIMEOUT]) {
-		map = init_list_set(set, size,
-				    sizeof(struct sett_elem), timeout);
-		if (!map)
-			return -ENOMEM;
-		set->extensions |= IPSET_EXT_TIMEOUT;
-		set->offset[IPSET_EXT_ID_TIMEOUT] =
-			offsetof(struct sett_elem, timeout);
+	set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem));
+	if (!init_list_set(set, size))
+		return -ENOMEM;
+	if (tb[IPSET_ATTR_TIMEOUT]) {
+		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
 		list_set_gc_init(set, list_set_gc);
-	} else {
-		map = init_list_set(set, size, sizeof(struct set_elem), 0);
-		if (!map)
-			return -ENOMEM;
 	}
 	return 0;
 }
-- 
cgit 


From 40cd63bf33b21ef4d43776b1d49c605f876fe32c Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Mon, 9 Sep 2013 14:44:29 +0200
Subject: netfilter: ipset: Support extensions which need a per data destroy
 function

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h  | 22 +++++++---
 net/netfilter/ipset/ip_set_bitmap_gen.h | 38 ++++++++++++++----
 net/netfilter/ipset/ip_set_hash_gen.h   | 71 +++++++++++++++++++++------------
 net/netfilter/ipset/ip_set_list_set.c   | 19 ++++++---
 4 files changed, 107 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 66d6bd404d64..6372ee224fe8 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -49,11 +49,13 @@ enum ip_set_feature {
 
 /* Set extensions */
 enum ip_set_extension {
-	IPSET_EXT_NONE = 0,
-	IPSET_EXT_BIT_TIMEOUT = 1,
+	IPSET_EXT_BIT_TIMEOUT = 0,
 	IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT),
-	IPSET_EXT_BIT_COUNTER = 2,
+	IPSET_EXT_BIT_COUNTER = 1,
 	IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER),
+	/* Mark set with an extension which needs to call destroy */
+	IPSET_EXT_BIT_DESTROY = 7,
+	IPSET_EXT_DESTROY = (1 << IPSET_EXT_BIT_DESTROY),
 };
 
 #define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
@@ -68,6 +70,8 @@ enum ip_set_ext_id {
 
 /* Extension type */
 struct ip_set_ext_type {
+	/* Destroy extension private data (can be NULL) */
+	void (*destroy)(void *ext);
 	enum ip_set_extension type;
 	enum ipset_cadt_flags flag;
 	/* Size and minimal alignment */
@@ -88,13 +92,21 @@ struct ip_set_counter {
 	atomic64_t packets;
 };
 
+struct ip_set;
+
+static inline void
+ip_set_ext_destroy(struct ip_set *set, void *data)
+{
+	/* Check that the extension is enabled for the set and
+	 * call it's destroy function for its extension part in data.
+	 */
+}
+
 #define ext_timeout(e, s)	\
 (unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])
 #define ext_counter(e, s)	\
 (struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])
 
-struct ip_set;
-
 typedef int (*ipset_adtfn)(struct ip_set *set, void *value,
 			   const struct ip_set_ext *ext,
 			   struct ip_set_ext *mext, u32 cmdflags);
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index f32ddbca3923..4515fe8b83dd 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -12,6 +12,7 @@
 #define mtype_gc_test		IPSET_TOKEN(MTYPE, _gc_test)
 #define mtype_is_filled		IPSET_TOKEN(MTYPE, _is_filled)
 #define mtype_do_add		IPSET_TOKEN(MTYPE, _do_add)
+#define mtype_ext_cleanup	IPSET_TOKEN(MTYPE, _ext_cleanup)
 #define mtype_do_del		IPSET_TOKEN(MTYPE, _do_del)
 #define mtype_do_list		IPSET_TOKEN(MTYPE, _do_list)
 #define mtype_do_head		IPSET_TOKEN(MTYPE, _do_head)
@@ -46,6 +47,17 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 	add_timer(&map->gc);
 }
 
+static void
+mtype_ext_cleanup(struct ip_set *set)
+{
+	struct mtype *map = set->data;
+	u32 id;
+
+	for (id = 0; id < map->elements; id++)
+		if (test_bit(id, map->members))
+			ip_set_ext_destroy(set, get_ext(set, map, id));
+}
+
 static void
 mtype_destroy(struct ip_set *set)
 {
@@ -55,8 +67,11 @@ mtype_destroy(struct ip_set *set)
 		del_timer_sync(&map->gc);
 
 	ip_set_free(map->members);
-	if (set->dsize)
+	if (set->dsize) {
+		if (set->extensions & IPSET_EXT_DESTROY)
+			mtype_ext_cleanup(set);
 		ip_set_free(map->extensions);
+	}
 	kfree(map);
 
 	set->data = NULL;
@@ -67,6 +82,8 @@ mtype_flush(struct ip_set *set)
 {
 	struct mtype *map = set->data;
 
+	if (set->extensions & IPSET_EXT_DESTROY)
+		mtype_ext_cleanup(set);
 	memset(map->members, 0, map->memsize);
 }
 
@@ -132,6 +149,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 			ret = 0;
 		else if (!(flags & IPSET_FLAG_EXIST))
 			return -IPSET_ERR_EXIST;
+		/* Element is re-added, cleanup extensions */
+		ip_set_ext_destroy(set, x);
 	}
 
 	if (SET_WITH_TIMEOUT(set))
@@ -152,11 +171,14 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 {
 	struct mtype *map = set->data;
 	const struct mtype_adt_elem *e = value;
-	const void *x = get_ext(set, map, e->id);
+	void *x = get_ext(set, map, e->id);
 
-	if (mtype_do_del(e, map) ||
-	    (SET_WITH_TIMEOUT(set) &&
-	     ip_set_timeout_expired(ext_timeout(x, set))))
+	if (mtype_do_del(e, map))
+		return -IPSET_ERR_EXIST;
+
+	ip_set_ext_destroy(set, x);
+	if (SET_WITH_TIMEOUT(set) &&
+	    ip_set_timeout_expired(ext_timeout(x, set)))
 		return -IPSET_ERR_EXIST;
 
 	return 0;
@@ -235,7 +257,7 @@ mtype_gc(unsigned long ul_set)
 {
 	struct ip_set *set = (struct ip_set *) ul_set;
 	struct mtype *map = set->data;
-	const void *x;
+	void *x;
 	u32 id;
 
 	/* We run parallel with other readers (test element)
@@ -244,8 +266,10 @@ mtype_gc(unsigned long ul_set)
 	for (id = 0; id < map->elements; id++)
 		if (mtype_gc_test(id, map, set->dsize)) {
 			x = get_ext(set, map, id);
-			if (ip_set_timeout_expired(ext_timeout(x, set)))
+			if (ip_set_timeout_expired(ext_timeout(x, set))) {
 				clear_bit(id, map->members);
+				ip_set_ext_destroy(set, x);
+			}
 		}
 	read_unlock_bh(&set->lock);
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 3999f1719f69..3c26e5b946f5 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -117,23 +117,6 @@ htable_bits(u32 hashsize)
 	return bits;
 }
 
-/* Destroy the hashtable part of the set */
-static void
-ahash_destroy(struct htable *t)
-{
-	struct hbucket *n;
-	u32 i;
-
-	for (i = 0; i < jhash_size(t->htable_bits); i++) {
-		n = hbucket(t, i);
-		if (n->size)
-			/* FIXME: use slab cache */
-			kfree(n->value);
-	}
-
-	ip_set_free(t);
-}
-
 static int
 hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 {
@@ -192,6 +175,8 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #undef mtype_data_next
 #undef mtype_elem
 
+#undef mtype_ahash_destroy
+#undef mtype_ext_cleanup
 #undef mtype_add_cidr
 #undef mtype_del_cidr
 #undef mtype_ahash_memsize
@@ -230,6 +215,8 @@ hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
 #define mtype_data_list		IPSET_TOKEN(MTYPE, _data_list)
 #define mtype_data_next		IPSET_TOKEN(MTYPE, _data_next)
 #define mtype_elem		IPSET_TOKEN(MTYPE, _elem)
+#define mtype_ahash_destroy	IPSET_TOKEN(MTYPE, _ahash_destroy)
+#define mtype_ext_cleanup	IPSET_TOKEN(MTYPE, _ext_cleanup)
 #define mtype_add_cidr		IPSET_TOKEN(MTYPE, _add_cidr)
 #define mtype_del_cidr		IPSET_TOKEN(MTYPE, _del_cidr)
 #define mtype_ahash_memsize	IPSET_TOKEN(MTYPE, _ahash_memsize)
@@ -359,6 +346,19 @@ mtype_ahash_memsize(const struct htype *h, const struct htable *t,
 	return memsize;
 }
 
+/* Get the ith element from the array block n */
+#define ahash_data(n, i, dsize)	\
+	((struct mtype_elem *)((n)->value + ((i) * (dsize))))
+
+static void
+mtype_ext_cleanup(struct ip_set *set, struct hbucket *n)
+{
+	int i;
+
+	for (i = 0; i < n->pos; i++)
+		ip_set_ext_destroy(set, ahash_data(n, i, set->dsize));
+}
+
 /* Flush a hash type of set: destroy all elements */
 static void
 mtype_flush(struct ip_set *set)
@@ -372,6 +372,8 @@ mtype_flush(struct ip_set *set)
 	for (i = 0; i < jhash_size(t->htable_bits); i++) {
 		n = hbucket(t, i);
 		if (n->size) {
+			if (set->extensions & IPSET_EXT_DESTROY)
+				mtype_ext_cleanup(set, n);
 			n->size = n->pos = 0;
 			/* FIXME: use slab cache */
 			kfree(n->value);
@@ -383,6 +385,26 @@ mtype_flush(struct ip_set *set)
 	h->elements = 0;
 }
 
+/* Destroy the hashtable part of the set */
+static void
+mtype_ahash_destroy(struct ip_set *set, struct htable *t)
+{
+	struct hbucket *n;
+	u32 i;
+
+	for (i = 0; i < jhash_size(t->htable_bits); i++) {
+		n = hbucket(t, i);
+		if (n->size) {
+			if (set->extensions & IPSET_EXT_DESTROY)
+				mtype_ext_cleanup(set, n);
+			/* FIXME: use slab cache */
+			kfree(n->value);
+		}
+	}
+
+	ip_set_free(t);
+}
+
 /* Destroy a hash type of set */
 static void
 mtype_destroy(struct ip_set *set)
@@ -392,7 +414,7 @@ mtype_destroy(struct ip_set *set)
 	if (set->extensions & IPSET_EXT_TIMEOUT)
 		del_timer_sync(&h->gc);
 
-	ahash_destroy(rcu_dereference_bh_nfnl(h->table));
+	mtype_ahash_destroy(set, rcu_dereference_bh_nfnl(h->table));
 #ifdef IP_SET_HASH_WITH_RBTREE
 	rbtree_destroy(&h->rbtree);
 #endif
@@ -430,10 +452,6 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
-/* Get the ith element from the array block n */
-#define ahash_data(n, i, dsize)	\
-	((struct mtype_elem *)((n)->value + ((i) * (dsize))))
-
 /* Delete expired elements from the hashtable */
 static void
 mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
@@ -456,6 +474,7 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
 				mtype_del_cidr(h, CIDR(data->cidr),
 					       nets_length, 0);
 #endif
+				ip_set_ext_destroy(set, data);
 				if (j != n->pos - 1)
 					/* Not last one */
 					memcpy(data,
@@ -557,7 +576,7 @@ retry:
 				mtype_data_reset_flags(data, &flags);
 #endif
 				read_unlock_bh(&set->lock);
-				ahash_destroy(t);
+				mtype_ahash_destroy(set, t);
 				if (ret == -EAGAIN)
 					goto retry;
 				return ret;
@@ -578,7 +597,7 @@ retry:
 
 	pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
 		 orig->htable_bits, orig, t->htable_bits, t);
-	ahash_destroy(orig);
+	mtype_ahash_destroy(set, orig);
 
 	return 0;
 }
@@ -642,6 +661,7 @@ reuse_slot:
 		mtype_del_cidr(h, CIDR(data->cidr), NLEN(set->family), 0);
 		mtype_add_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
+		ip_set_ext_destroy(set, data);
 	} else {
 		/* Use/create a new slot */
 		TUNE_AHASH_MAX(h, multi);
@@ -707,6 +727,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 #ifdef IP_SET_HASH_WITH_NETS
 		mtype_del_cidr(h, CIDR(d->cidr), NLEN(set->family), 0);
 #endif
+		ip_set_ext_destroy(set, data);
 		if (n->pos + AHASH_INIT_SIZE < n->size) {
 			void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
 					    * set->dsize,
@@ -1033,7 +1054,7 @@ IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
 	rcu_assign_pointer(h->table, t);
 
 	set->data = h;
-	if (set->family ==  NFPROTO_IPV4) {
+	if (set->family == NFPROTO_IPV4) {
 		set->variant = &IPSET_TOKEN(HTYPE, 4_variant);
 		set->dsize = ip_set_elem_len(set, tb,
 				sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)));
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 7fd11c79aff4..e44986af1fc2 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -168,16 +168,19 @@ list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
 	struct set_elem *e = list_set_elem(set, map, i);
 
 	if (e->id != IPSET_INVALID_ID) {
-		if (i == map->size - 1)
+		if (i == map->size - 1) {
 			/* Last element replaced: e.g. add new,before,last */
 			ip_set_put_byindex(e->id);
-		else {
+			ip_set_ext_destroy(set, e);
+		} else {
 			struct set_elem *x = list_set_elem(set, map,
 							   map->size - 1);
 
 			/* Last element pushed off */
-			if (x->id != IPSET_INVALID_ID)
+			if (x->id != IPSET_INVALID_ID) {
 				ip_set_put_byindex(x->id);
+				ip_set_ext_destroy(set, x);
+			}
 			memmove(list_set_elem(set, map, i + 1), e,
 				set->dsize * (map->size - (i + 1)));
 		}
@@ -198,6 +201,7 @@ list_set_del(struct ip_set *set, u32 i)
 	struct set_elem *e = list_set_elem(set, map, i);
 
 	ip_set_put_byindex(e->id);
+	ip_set_ext_destroy(set, e);
 
 	if (i < map->size - 1)
 		memmove(e, list_set_elem(set, map, i + 1),
@@ -266,14 +270,14 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	bool flag_exist = flags & IPSET_FLAG_EXIST;
 	u32 i, ret = 0;
 
+	if (SET_WITH_TIMEOUT(set))
+		set_cleanup_entries(set);
+
 	/* Check already added element */
 	for (i = 0; i < map->size; i++) {
 		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			goto insert;
-		else if (SET_WITH_TIMEOUT(set) &&
-			 ip_set_timeout_expired(ext_timeout(e, set)))
-			continue;
 		else if (e->id != d->id)
 			continue;
 
@@ -286,6 +290,8 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 			/* Can't re-add */
 			return -IPSET_ERR_EXIST;
 		/* Update extensions */
+		ip_set_ext_destroy(set, e);
+
 		if (SET_WITH_TIMEOUT(set))
 			ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
 		if (SET_WITH_COUNTER(set))
@@ -423,6 +429,7 @@ list_set_flush(struct ip_set *set)
 		e = list_set_elem(set, map, i);
 		if (e->id != IPSET_INVALID_ID) {
 			ip_set_put_byindex(e->id);
+			ip_set_ext_destroy(set, e);
 			e->id = IPSET_INVALID_ID;
 		}
 	}
-- 
cgit 


From 68b63f08d22f23161c43cd2417104aa213ff877f Mon Sep 17 00:00:00 2001
From: Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>
Date: Sun, 22 Sep 2013 20:56:30 +0200
Subject: netfilter: ipset: Support comments for ipset entries in the core.

This adds the core support for having comments on ipset entries.

The comments are stored as standard null-terminated strings in
dynamically allocated memory after being passed to the kernel. As a
result of this, code has been added to the generic destroy function to
iterate all extensions and call that extension's destroy task if the set
has that extension activated, and if such a task is defined.

Signed-off-by: Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h         | 51 +++++++++++++++++++----
 include/linux/netfilter/ipset/ip_set_comment.h | 57 ++++++++++++++++++++++++++
 include/uapi/linux/netfilter/ipset/ip_set.h    |  8 +++-
 net/netfilter/ipset/ip_set_core.c              | 14 +++++++
 4 files changed, 121 insertions(+), 9 deletions(-)
 create mode 100644 include/linux/netfilter/ipset/ip_set_comment.h

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 6372ee224fe8..407f84df6a47 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -53,6 +53,8 @@ enum ip_set_extension {
 	IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT),
 	IPSET_EXT_BIT_COUNTER = 1,
 	IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER),
+	IPSET_EXT_BIT_COMMENT = 2,
+	IPSET_EXT_COMMENT = (1 << IPSET_EXT_BIT_COMMENT),
 	/* Mark set with an extension which needs to call destroy */
 	IPSET_EXT_BIT_DESTROY = 7,
 	IPSET_EXT_DESTROY = (1 << IPSET_EXT_BIT_DESTROY),
@@ -60,11 +62,13 @@ enum ip_set_extension {
 
 #define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
 #define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
+#define SET_WITH_COMMENT(s)	((s)->extensions & IPSET_EXT_COMMENT)
 
 /* Extension id, in size order */
 enum ip_set_ext_id {
 	IPSET_EXT_ID_COUNTER = 0,
 	IPSET_EXT_ID_TIMEOUT,
+	IPSET_EXT_ID_COMMENT,
 	IPSET_EXT_ID_MAX,
 };
 
@@ -85,6 +89,7 @@ struct ip_set_ext {
 	u64 packets;
 	u64 bytes;
 	u32 timeout;
+	char *comment;
 };
 
 struct ip_set_counter {
@@ -92,20 +97,19 @@ struct ip_set_counter {
 	atomic64_t packets;
 };
 
-struct ip_set;
+struct ip_set_comment {
+	char *str;
+};
 
-static inline void
-ip_set_ext_destroy(struct ip_set *set, void *data)
-{
-	/* Check that the extension is enabled for the set and
-	 * call it's destroy function for its extension part in data.
-	 */
-}
+struct ip_set;
 
 #define ext_timeout(e, s)	\
 (unsigned long *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_TIMEOUT])
 #define ext_counter(e, s)	\
 (struct ip_set_counter *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COUNTER])
+#define ext_comment(e, s)	\
+(struct ip_set_comment *)(((void *)(e)) + (s)->offset[IPSET_EXT_ID_COMMENT])
+
 
 typedef int (*ipset_adtfn)(struct ip_set *set, void *value,
 			   const struct ip_set_ext *ext,
@@ -222,6 +226,36 @@ struct ip_set {
 	void *data;
 };
 
+static inline void
+ip_set_ext_destroy(struct ip_set *set, void *data)
+{
+	/* Check that the extension is enabled for the set and
+	 * call it's destroy function for its extension part in data.
+	 */
+	if (SET_WITH_COMMENT(set))
+		ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(
+			ext_comment(data, set));
+}
+
+static inline int
+ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
+{
+	u32 cadt_flags = 0;
+
+	if (SET_WITH_TIMEOUT(set))
+		if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
+					   htonl(set->timeout))))
+			return -EMSGSIZE;
+	if (SET_WITH_COUNTER(set))
+		cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
+	if (SET_WITH_COMMENT(set))
+		cadt_flags |= IPSET_FLAG_WITH_COMMENT;
+
+	if (!cadt_flags)
+		return 0;
+	return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags));
+}
+
 static inline void
 ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
 {
@@ -425,6 +459,7 @@ bitmap_bytes(u32 a, u32 b)
 }
 
 #include <linux/netfilter/ipset/ip_set_timeout.h>
+#include <linux/netfilter/ipset/ip_set_comment.h>
 
 #define IP_SET_INIT_KEXT(skb, opt, set)			\
 	{ .bytes = (skb)->len, .packets = 1,		\
diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h
new file mode 100644
index 000000000000..21217ea008d7
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_comment.h
@@ -0,0 +1,57 @@
+#ifndef _IP_SET_COMMENT_H
+#define _IP_SET_COMMENT_H
+
+/* Copyright (C) 2013 Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifdef __KERNEL__
+
+static inline char*
+ip_set_comment_uget(struct nlattr *tb)
+{
+	return nla_data(tb);
+}
+
+static inline void
+ip_set_init_comment(struct ip_set_comment *comment,
+		    const struct ip_set_ext *ext)
+{
+	size_t len = ext->comment ? strlen(ext->comment) : 0;
+
+	if (unlikely(comment->str)) {
+		kfree(comment->str);
+		comment->str = NULL;
+	}
+	if (!len)
+		return;
+	if (unlikely(len > IPSET_MAX_COMMENT_SIZE))
+		len = IPSET_MAX_COMMENT_SIZE;
+	comment->str = kzalloc(len + 1, GFP_ATOMIC);
+	if (unlikely(!comment->str))
+		return;
+	strlcpy(comment->str, ext->comment, len + 1);
+}
+
+static inline int
+ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment)
+{
+	if (!comment->str)
+		return 0;
+	return nla_put_string(skb, IPSET_ATTR_COMMENT, comment->str);
+}
+
+static inline void
+ip_set_comment_free(struct ip_set_comment *comment)
+{
+	if (unlikely(!comment->str))
+		return;
+	kfree(comment->str);
+	comment->str = NULL;
+}
+
+#endif
+#endif
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 2b61ac44dcc1..25d3b2f79c02 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -10,12 +10,14 @@
 #ifndef _UAPI_IP_SET_H
 #define _UAPI_IP_SET_H
 
-
 #include <linux/types.h>
 
 /* The protocol version */
 #define IPSET_PROTOCOL		6
 
+/* The maximum permissible comment length we will accept over netlink */
+#define IPSET_MAX_COMMENT_SIZE	255
+
 /* The max length of strings including NUL: set and type identifiers */
 #define IPSET_MAXNAMELEN	32
 
@@ -110,6 +112,7 @@ enum {
 	IPSET_ATTR_IFACE,
 	IPSET_ATTR_BYTES,
 	IPSET_ATTR_PACKETS,
+	IPSET_ATTR_COMMENT,
 	__IPSET_ATTR_ADT_MAX,
 };
 #define IPSET_ATTR_ADT_MAX	(__IPSET_ATTR_ADT_MAX - 1)
@@ -140,6 +143,7 @@ enum ipset_errno {
 	IPSET_ERR_IPADDR_IPV4,
 	IPSET_ERR_IPADDR_IPV6,
 	IPSET_ERR_COUNTER,
+	IPSET_ERR_COMMENT,
 
 	/* Type specific error codes */
 	IPSET_ERR_TYPE_SPECIFIC = 4352,
@@ -176,6 +180,8 @@ enum ipset_cadt_flags {
 	IPSET_FLAG_NOMATCH	= (1 << IPSET_FLAG_BIT_NOMATCH),
 	IPSET_FLAG_BIT_WITH_COUNTERS = 3,
 	IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS),
+	IPSET_FLAG_BIT_WITH_COMMENT = 4,
+	IPSET_FLAG_WITH_COMMENT = (1 << IPSET_FLAG_BIT_WITH_COMMENT),
 	IPSET_FLAG_CADT_MAX	= 15,
 };
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index f35afed3814f..3bf9a3d29dff 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -315,6 +315,7 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
 }
 EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
 
+typedef void (*destroyer)(void *);
 /* ipset data extension types, in size order */
 
 const struct ip_set_ext_type ip_set_extensions[] = {
@@ -329,6 +330,13 @@ const struct ip_set_ext_type ip_set_extensions[] = {
 		.len	= sizeof(unsigned long),
 		.align	= __alignof__(unsigned long),
 	},
+	[IPSET_EXT_ID_COMMENT] = {
+		.type	 = IPSET_EXT_COMMENT | IPSET_EXT_DESTROY,
+		.flag	 = IPSET_FLAG_WITH_COMMENT,
+		.len	 = sizeof(struct ip_set_comment),
+		.align	 = __alignof__(struct ip_set_comment),
+		.destroy = (destroyer) ip_set_comment_free,
+	},
 };
 EXPORT_SYMBOL_GPL(ip_set_extensions);
 
@@ -380,6 +388,12 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
 			ext->packets = be64_to_cpu(nla_get_be64(
 						   tb[IPSET_ATTR_PACKETS]));
 	}
+	if (tb[IPSET_ATTR_COMMENT]) {
+		if (!(set->extensions & IPSET_EXT_COMMENT))
+			return -IPSET_ERR_COMMENT;
+		ext->comment = ip_set_comment_uget(tb[IPSET_ATTR_COMMENT]);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_set_get_extensions);
-- 
cgit 


From 3fd986b3d99e3847f1cce6fc36043d0f16508e1d Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Wed, 25 Sep 2013 17:44:35 +0200
Subject: netfilter: ipset: Use a common function at listing the extensions

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h    | 21 +++++++++++++++++++++
 net/netfilter/ipset/ip_set_bitmap_gen.h   | 29 ++++++++++-------------------
 net/netfilter/ipset/ip_set_bitmap_ipmac.c | 11 -----------
 net/netfilter/ipset/ip_set_hash_gen.h     | 11 +----------
 net/netfilter/ipset/ip_set_list_set.c     | 11 +----------
 5 files changed, 33 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 407f84df6a47..da2a45acf74c 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -461,6 +461,27 @@ bitmap_bytes(u32 a, u32 b)
 #include <linux/netfilter/ipset/ip_set_timeout.h>
 #include <linux/netfilter/ipset/ip_set_comment.h>
 
+static inline int
+ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
+		      const void *e, bool active)
+{
+	if (SET_WITH_TIMEOUT(set)) {
+		unsigned long *timeout = ext_timeout(e, set);
+
+		if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
+			htonl(active ? ip_set_timeout_get(timeout)
+				: *timeout)))
+			return -EMSGSIZE;
+	}
+	if (SET_WITH_COUNTER(set) &&
+	    ip_set_put_counter(skb, ext_counter(e, set)))
+		return -EMSGSIZE;
+	if (SET_WITH_COMMENT(set) &&
+	    ip_set_put_comment(skb, ext_comment(e, set)))
+		return -EMSGSIZE;
+	return 0;
+}
+
 #define IP_SET_INIT_KEXT(skb, opt, set)			\
 	{ .bytes = (skb)->len, .packets = 1,		\
 	  .timeout = ip_set_adt_opt_timeout(opt, set) }
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 6167fc9d0efe..a13e15be7911 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -183,6 +183,14 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	return 0;
 }
 
+#ifndef IP_SET_BITMAP_STORED_TIMEOUT
+static inline bool
+mtype_is_filled(const struct mtype_elem *x)
+{
+	return true;
+}
+#endif
+
 static int
 mtype_list(const struct ip_set *set,
 	   struct sk_buff *skb, struct netlink_callback *cb)
@@ -215,25 +223,8 @@ mtype_list(const struct ip_set *set,
 		}
 		if (mtype_do_list(skb, map, id, set->dsize))
 			goto nla_put_failure;
-		if (SET_WITH_TIMEOUT(set)) {
-#ifdef IP_SET_BITMAP_STORED_TIMEOUT
-			if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
-					  htonl(ip_set_timeout_stored(map, id,
-							ext_timeout(x, set),
-							set->dsize))))
-				goto nla_put_failure;
-#else
-			if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
-					  htonl(ip_set_timeout_get(
-							ext_timeout(x, set)))))
-				goto nla_put_failure;
-#endif
-		}
-		if (SET_WITH_COUNTER(set) &&
-		    ip_set_put_counter(skb, ext_counter(x, set)))
-			goto nla_put_failure;
-		if (SET_WITH_COMMENT(set) &&
-		    ip_set_put_comment(skb, ext_comment(x, set)))
+		if (ip_set_put_extensions(skb, set, x,
+		    mtype_is_filled((const struct mtype_elem *) x)))
 			goto nla_put_failure;
 		ipset_nest_end(skb, nested);
 	}
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index fb4d163dea82..87a218f8ab5f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -176,17 +176,6 @@ bitmap_ipmac_do_del(const struct bitmap_ipmac_adt_elem *e,
 	return !test_and_clear_bit(e->id, map->members);
 }
 
-static inline unsigned long
-ip_set_timeout_stored(struct bitmap_ipmac *map, u32 id, unsigned long *timeout,
-		      size_t dsize)
-{
-	const struct bitmap_ipmac_elem *elem =
-		get_elem(map->extensions, id, dsize);
-
-	return elem->filled == MAC_FILLED ? ip_set_timeout_get(timeout) :
-					    *timeout;
-}
-
 static inline int
 bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
 		     u32 id, size_t dsize)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 1cffeb977605..b4add206c603 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -961,16 +961,7 @@ mtype_list(const struct ip_set *set,
 			}
 			if (mtype_data_list(skb, e))
 				goto nla_put_failure;
-			if (SET_WITH_TIMEOUT(set) &&
-			    nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
-					  htonl(ip_set_timeout_get(
-						ext_timeout(e, set)))))
-				goto nla_put_failure;
-			if (SET_WITH_COUNTER(set) &&
-			    ip_set_put_counter(skb, ext_counter(e, set)))
-				goto nla_put_failure;
-			if (SET_WITH_COMMENT(set) &&
-			    ip_set_put_comment(skb, ext_comment(e, set)))
+			if (ip_set_put_extensions(skb, set, e, true))
 				goto nla_put_failure;
 			ipset_nest_end(skb, nested);
 		}
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index e23f33c14435..ba4232e451f4 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -512,16 +512,7 @@ list_set_list(const struct ip_set *set,
 		if (nla_put_string(skb, IPSET_ATTR_NAME,
 				   ip_set_name_byindex(e->id)))
 			goto nla_put_failure;
-		if (SET_WITH_TIMEOUT(set) &&
-		    nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
-				  htonl(ip_set_timeout_get(
-						ext_timeout(e, set)))))
-			goto nla_put_failure;
-		if (SET_WITH_COUNTER(set) &&
-		    ip_set_put_counter(skb, ext_counter(e, set)))
-			goto nla_put_failure;
-		if (SET_WITH_COMMENT(set) &&
-		    ip_set_put_comment(skb, ext_comment(e, set)))
+		if (ip_set_put_extensions(skb, set, e, true))
 			goto nla_put_failure;
 		ipset_nest_end(skb, nested);
 	}
-- 
cgit 


From 1785e8f473082aa60d62c7165856cf6484077b99 Mon Sep 17 00:00:00 2001
From: Vitaly Lavrov <lve@guap.ru>
Date: Mon, 30 Sep 2013 17:07:02 +0200
Subject: netfiler: ipset: Add net namespace for ipset

This patch adds netns support for ipset.

Major changes were made in ip_set_core.c and ip_set.h.
Global variables are moved to per net namespace.
Added initialization code and the destruction of the network namespace ipset subsystem.
In the prototypes of public functions ip_set_* added parameter "struct net*".

The remaining corrections related to the change prototypes of public functions ip_set_*.

The patch for git://git.netfilter.org/ipset.git commit 6a4ec96c0b8caac5c35474e40e319704d92ca347

Signed-off-by: Vitaly Lavrov <lve@guap.ru>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h    |  16 +-
 net/netfilter/ipset/ip_set_bitmap_ip.c    |   3 +-
 net/netfilter/ipset/ip_set_bitmap_ipmac.c |   2 +-
 net/netfilter/ipset/ip_set_bitmap_port.c  |   3 +-
 net/netfilter/ipset/ip_set_core.c         | 288 +++++++++++++++++++-----------
 net/netfilter/ipset/ip_set_hash_gen.h     |   3 +-
 net/netfilter/ipset/ip_set_list_set.c     |  31 ++--
 net/netfilter/xt_set.c                    |  40 ++---
 net/sched/em_ipset.c                      |   7 +-
 9 files changed, 245 insertions(+), 148 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index da2a45acf74c..7967516adc0d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -184,7 +184,8 @@ struct ip_set_type {
 	u8 revision_min, revision_max;
 
 	/* Create set */
-	int (*create)(struct ip_set *set, struct nlattr *tb[], u32 flags);
+	int (*create)(struct net *net, struct ip_set *set,
+		      struct nlattr *tb[], u32 flags);
 
 	/* Attribute policies */
 	const struct nla_policy create_policy[IPSET_ATTR_CREATE_MAX + 1];
@@ -316,12 +317,13 @@ ip_set_init_counter(struct ip_set_counter *counter,
 }
 
 /* register and unregister set references */
-extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set);
-extern void ip_set_put_byindex(ip_set_id_t index);
-extern const char *ip_set_name_byindex(ip_set_id_t index);
-extern ip_set_id_t ip_set_nfnl_get(const char *name);
-extern ip_set_id_t ip_set_nfnl_get_byindex(ip_set_id_t index);
-extern void ip_set_nfnl_put(ip_set_id_t index);
+extern ip_set_id_t ip_set_get_byname(struct net *net,
+				     const char *name, struct ip_set **set);
+extern void ip_set_put_byindex(struct net *net, ip_set_id_t index);
+extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index);
+extern ip_set_id_t ip_set_nfnl_get(struct net *net, const char *name);
+extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index);
+extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index);
 
 /* API for iptables set match, and SET target */
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index faac124e2645..6f1f9f494808 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -242,7 +242,8 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 }
 
 static int
-bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+		 u32 flags)
 {
 	struct bitmap_ip *map;
 	u32 first_ip = 0, last_ip = 0, hosts;
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 87a218f8ab5f..740eabededd9 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -309,7 +309,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 }
 
 static int
-bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
+bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		    u32 flags)
 {
 	u32 first_ip = 0, last_ip = 0;
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 407a63caee6b..e7603c5b53d7 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -228,7 +228,8 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
 }
 
 static int
-bitmap_port_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+		   u32 flags)
 {
 	struct bitmap_port *map;
 	u16 first_port, last_port;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 3bf9a3d29dff..dc9284bdd2dd 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -17,6 +17,8 @@
 #include <linux/spinlock.h>
 #include <linux/rculist.h>
 #include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter/x_tables.h>
@@ -27,8 +29,17 @@ static LIST_HEAD(ip_set_type_list);		/* all registered set types */
 static DEFINE_MUTEX(ip_set_type_mutex);		/* protects ip_set_type_list */
 static DEFINE_RWLOCK(ip_set_ref_lock);		/* protects the set refs */
 
-static struct ip_set * __rcu *ip_set_list;	/* all individual sets */
-static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
+struct ip_set_net {
+	struct ip_set * __rcu *ip_set_list;	/* all individual sets */
+	ip_set_id_t	ip_set_max;	/* max number of sets */
+	int		is_deleted;	/* deleted by ip_set_net_exit */
+};
+static int ip_set_net_id __read_mostly;
+
+static inline struct ip_set_net *ip_set_pernet(struct net *net)
+{
+	return net_generic(net, ip_set_net_id);
+}
 
 #define IP_SET_INC	64
 #define STREQ(a, b)	(strncmp(a, b, IPSET_MAXNAMELEN) == 0)
@@ -45,8 +56,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 /* When the nfnl mutex is held: */
 #define nfnl_dereference(p)		\
 	rcu_dereference_protected(p, 1)
-#define nfnl_set(id)			\
-	nfnl_dereference(ip_set_list)[id]
+#define nfnl_set(inst, id)			\
+	nfnl_dereference((inst)->ip_set_list)[id]
 
 /*
  * The set types are implemented in modules and registered set types
@@ -434,13 +445,14 @@ __ip_set_put(struct ip_set *set)
  */
 
 static inline struct ip_set *
-ip_set_rcu_get(ip_set_id_t index)
+ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
 	struct ip_set *set;
+	struct ip_set_net *inst = ip_set_pernet(net);
 
 	rcu_read_lock();
 	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(ip_set_list)[index];
+	set = rcu_dereference(inst->ip_set_list)[index];
 	rcu_read_unlock();
 
 	return set;
@@ -450,7 +462,8 @@ int
 ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
 	    const struct xt_action_param *par, struct ip_set_adt_opt *opt)
 {
-	struct ip_set *set = ip_set_rcu_get(index);
+	struct ip_set *set = ip_set_rcu_get(
+			dev_net(par->in ? par->in : par->out), index);
 	int ret = 0;
 
 	BUG_ON(set == NULL);
@@ -488,7 +501,8 @@ int
 ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
 	   const struct xt_action_param *par, struct ip_set_adt_opt *opt)
 {
-	struct ip_set *set = ip_set_rcu_get(index);
+	struct ip_set *set = ip_set_rcu_get(
+			dev_net(par->in ? par->in : par->out), index);
 	int ret;
 
 	BUG_ON(set == NULL);
@@ -510,7 +524,8 @@ int
 ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
 	   const struct xt_action_param *par, struct ip_set_adt_opt *opt)
 {
-	struct ip_set *set = ip_set_rcu_get(index);
+	struct ip_set *set = ip_set_rcu_get(
+			dev_net(par->in ? par->in : par->out), index);
 	int ret = 0;
 
 	BUG_ON(set == NULL);
@@ -534,14 +549,15 @@ EXPORT_SYMBOL_GPL(ip_set_del);
  *
  */
 ip_set_id_t
-ip_set_get_byname(const char *name, struct ip_set **set)
+ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
 {
 	ip_set_id_t i, index = IPSET_INVALID_ID;
 	struct ip_set *s;
+	struct ip_set_net *inst = ip_set_pernet(net);
 
 	rcu_read_lock();
-	for (i = 0; i < ip_set_max; i++) {
-		s = rcu_dereference(ip_set_list)[i];
+	for (i = 0; i < inst->ip_set_max; i++) {
+		s = rcu_dereference(inst->ip_set_list)[i];
 		if (s != NULL && STREQ(s->name, name)) {
 			__ip_set_get(s);
 			index = i;
@@ -561,17 +577,26 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
  * to be valid, after calling this function.
  *
  */
-void
-ip_set_put_byindex(ip_set_id_t index)
+
+static inline void
+__ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index)
 {
 	struct ip_set *set;
 
 	rcu_read_lock();
-	set = rcu_dereference(ip_set_list)[index];
+	set = rcu_dereference(inst->ip_set_list)[index];
 	if (set != NULL)
 		__ip_set_put(set);
 	rcu_read_unlock();
 }
+
+void
+ip_set_put_byindex(struct net *net, ip_set_id_t index)
+{
+	struct ip_set_net *inst = ip_set_pernet(net);
+
+	__ip_set_put_byindex(inst, index);
+}
 EXPORT_SYMBOL_GPL(ip_set_put_byindex);
 
 /*
@@ -582,9 +607,9 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex);
  *
  */
 const char *
-ip_set_name_byindex(ip_set_id_t index)
+ip_set_name_byindex(struct net *net, ip_set_id_t index)
 {
-	const struct ip_set *set = ip_set_rcu_get(index);
+	const struct ip_set *set = ip_set_rcu_get(net, index);
 
 	BUG_ON(set == NULL);
 	BUG_ON(set->ref == 0);
@@ -606,14 +631,15 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex);
  * The nfnl mutex is used in the function.
  */
 ip_set_id_t
-ip_set_nfnl_get(const char *name)
+ip_set_nfnl_get(struct net *net, const char *name)
 {
 	ip_set_id_t i, index = IPSET_INVALID_ID;
 	struct ip_set *s;
+	struct ip_set_net *inst = ip_set_pernet(net);
 
 	nfnl_lock(NFNL_SUBSYS_IPSET);
-	for (i = 0; i < ip_set_max; i++) {
-		s = nfnl_set(i);
+	for (i = 0; i < inst->ip_set_max; i++) {
+		s = nfnl_set(inst, i);
 		if (s != NULL && STREQ(s->name, name)) {
 			__ip_set_get(s);
 			index = i;
@@ -633,15 +659,16 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get);
  * The nfnl mutex is used in the function.
  */
 ip_set_id_t
-ip_set_nfnl_get_byindex(ip_set_id_t index)
+ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index)
 {
 	struct ip_set *set;
+	struct ip_set_net *inst = ip_set_pernet(net);
 
-	if (index > ip_set_max)
+	if (index > inst->ip_set_max)
 		return IPSET_INVALID_ID;
 
 	nfnl_lock(NFNL_SUBSYS_IPSET);
-	set = nfnl_set(index);
+	set = nfnl_set(inst, index);
 	if (set)
 		__ip_set_get(set);
 	else
@@ -660,13 +687,17 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex);
  * The nfnl mutex is used in the function.
  */
 void
-ip_set_nfnl_put(ip_set_id_t index)
+ip_set_nfnl_put(struct net *net, ip_set_id_t index)
 {
 	struct ip_set *set;
+	struct ip_set_net *inst = ip_set_pernet(net);
+
 	nfnl_lock(NFNL_SUBSYS_IPSET);
-	set = nfnl_set(index);
-	if (set != NULL)
-		__ip_set_put(set);
+	if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */
+		set = nfnl_set(inst, index);
+		if (set != NULL)
+			__ip_set_put(set);
+	}
 	nfnl_unlock(NFNL_SUBSYS_IPSET);
 }
 EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
@@ -724,14 +755,14 @@ static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = {
 };
 
 static struct ip_set *
-find_set_and_id(const char *name, ip_set_id_t *id)
+find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id)
 {
 	struct ip_set *set = NULL;
 	ip_set_id_t i;
 
 	*id = IPSET_INVALID_ID;
-	for (i = 0; i < ip_set_max; i++) {
-		set = nfnl_set(i);
+	for (i = 0; i < inst->ip_set_max; i++) {
+		set = nfnl_set(inst, i);
 		if (set != NULL && STREQ(set->name, name)) {
 			*id = i;
 			break;
@@ -741,22 +772,23 @@ find_set_and_id(const char *name, ip_set_id_t *id)
 }
 
 static inline struct ip_set *
-find_set(const char *name)
+find_set(struct ip_set_net *inst, const char *name)
 {
 	ip_set_id_t id;
 
-	return find_set_and_id(name, &id);
+	return find_set_and_id(inst, name, &id);
 }
 
 static int
-find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set)
+find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index,
+	     struct ip_set **set)
 {
 	struct ip_set *s;
 	ip_set_id_t i;
 
 	*index = IPSET_INVALID_ID;
-	for (i = 0;  i < ip_set_max; i++) {
-		s = nfnl_set(i);
+	for (i = 0;  i < inst->ip_set_max; i++) {
+		s = nfnl_set(inst, i);
 		if (s == NULL) {
 			if (*index == IPSET_INVALID_ID)
 				*index = i;
@@ -785,6 +817,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 	      const struct nlmsghdr *nlh,
 	      const struct nlattr * const attr[])
 {
+	struct net *net = sock_net(ctnl);
+	struct ip_set_net *inst = ip_set_pernet(net);
 	struct ip_set *set, *clash = NULL;
 	ip_set_id_t index = IPSET_INVALID_ID;
 	struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {};
@@ -843,7 +877,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 		goto put_out;
 	}
 
-	ret = set->type->create(set, tb, flags);
+	ret = set->type->create(net, set, tb, flags);
 	if (ret != 0)
 		goto put_out;
 
@@ -854,7 +888,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 	 * by the nfnl mutex. Find the first free index in ip_set_list
 	 * and check clashing.
 	 */
-	ret = find_free_id(set->name, &index, &clash);
+	ret = find_free_id(inst, set->name, &index, &clash);
 	if (ret == -EEXIST) {
 		/* If this is the same set and requested, ignore error */
 		if ((flags & IPSET_FLAG_EXIST) &&
@@ -867,9 +901,9 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 		goto cleanup;
 	} else if (ret == -IPSET_ERR_MAX_SETS) {
 		struct ip_set **list, **tmp;
-		ip_set_id_t i = ip_set_max + IP_SET_INC;
+		ip_set_id_t i = inst->ip_set_max + IP_SET_INC;
 
-		if (i < ip_set_max || i == IPSET_INVALID_ID)
+		if (i < inst->ip_set_max || i == IPSET_INVALID_ID)
 			/* Wraparound */
 			goto cleanup;
 
@@ -877,14 +911,14 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 		if (!list)
 			goto cleanup;
 		/* nfnl mutex is held, both lists are valid */
-		tmp = nfnl_dereference(ip_set_list);
-		memcpy(list, tmp, sizeof(struct ip_set *) * ip_set_max);
-		rcu_assign_pointer(ip_set_list, list);
+		tmp = nfnl_dereference(inst->ip_set_list);
+		memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
+		rcu_assign_pointer(inst->ip_set_list, list);
 		/* Make sure all current packets have passed through */
 		synchronize_net();
 		/* Use new list */
-		index = ip_set_max;
-		ip_set_max = i;
+		index = inst->ip_set_max;
+		inst->ip_set_max = i;
 		kfree(tmp);
 		ret = 0;
 	} else if (ret)
@@ -894,7 +928,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
 	 * Finally! Add our shiny new set to the list, and be done.
 	 */
 	pr_debug("create: '%s' created with index %u!\n", set->name, index);
-	nfnl_set(index) = set;
+	nfnl_set(inst, index) = set;
 
 	return ret;
 
@@ -917,12 +951,12 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
 };
 
 static void
-ip_set_destroy_set(ip_set_id_t index)
+ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index)
 {
-	struct ip_set *set = nfnl_set(index);
+	struct ip_set *set = nfnl_set(inst, index);
 
 	pr_debug("set: %s\n",  set->name);
-	nfnl_set(index) = NULL;
+	nfnl_set(inst, index) = NULL;
 
 	/* Must call it without holding any lock */
 	set->variant->destroy(set);
@@ -935,6 +969,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 	       const struct nlmsghdr *nlh,
 	       const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *s;
 	ip_set_id_t i;
 	int ret = 0;
@@ -954,21 +989,22 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 	 */
 	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
-		for (i = 0; i < ip_set_max; i++) {
-			s = nfnl_set(i);
+		for (i = 0; i < inst->ip_set_max; i++) {
+			s = nfnl_set(inst, i);
 			if (s != NULL && s->ref) {
 				ret = -IPSET_ERR_BUSY;
 				goto out;
 			}
 		}
 		read_unlock_bh(&ip_set_ref_lock);
-		for (i = 0; i < ip_set_max; i++) {
-			s = nfnl_set(i);
+		for (i = 0; i < inst->ip_set_max; i++) {
+			s = nfnl_set(inst, i);
 			if (s != NULL)
-				ip_set_destroy_set(i);
+				ip_set_destroy_set(inst, i);
 		}
 	} else {
-		s = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &i);
+		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+				    &i);
 		if (s == NULL) {
 			ret = -ENOENT;
 			goto out;
@@ -978,7 +1014,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
 		}
 		read_unlock_bh(&ip_set_ref_lock);
 
-		ip_set_destroy_set(i);
+		ip_set_destroy_set(inst, i);
 	}
 	return 0;
 out:
@@ -1003,6 +1039,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh,
 	     const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *s;
 	ip_set_id_t i;
 
@@ -1010,13 +1047,13 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
 		return -IPSET_ERR_PROTOCOL;
 
 	if (!attr[IPSET_ATTR_SETNAME]) {
-		for (i = 0; i < ip_set_max; i++) {
-			s = nfnl_set(i);
+		for (i = 0; i < inst->ip_set_max; i++) {
+			s = nfnl_set(inst, i);
 			if (s != NULL)
 				ip_set_flush_set(s);
 		}
 	} else {
-		s = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+		s = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 		if (s == NULL)
 			return -ENOENT;
 
@@ -1042,6 +1079,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 	      const struct nlmsghdr *nlh,
 	      const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *set, *s;
 	const char *name2;
 	ip_set_id_t i;
@@ -1052,7 +1090,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 		     attr[IPSET_ATTR_SETNAME2] == NULL))
 		return -IPSET_ERR_PROTOCOL;
 
-	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
 
@@ -1063,8 +1101,8 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
 	}
 
 	name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
-	for (i = 0; i < ip_set_max; i++) {
-		s = nfnl_set(i);
+	for (i = 0; i < inst->ip_set_max; i++) {
+		s = nfnl_set(inst, i);
 		if (s != NULL && STREQ(s->name, name2)) {
 			ret = -IPSET_ERR_EXIST_SETNAME2;
 			goto out;
@@ -1091,6 +1129,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *from, *to;
 	ip_set_id_t from_id, to_id;
 	char from_name[IPSET_MAXNAMELEN];
@@ -1100,11 +1139,13 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 		     attr[IPSET_ATTR_SETNAME2] == NULL))
 		return -IPSET_ERR_PROTOCOL;
 
-	from = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &from_id);
+	from = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+			       &from_id);
 	if (from == NULL)
 		return -ENOENT;
 
-	to = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME2]), &to_id);
+	to = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME2]),
+			     &to_id);
 	if (to == NULL)
 		return -IPSET_ERR_EXIST_SETNAME2;
 
@@ -1121,8 +1162,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 
 	write_lock_bh(&ip_set_ref_lock);
 	swap(from->ref, to->ref);
-	nfnl_set(from_id) = to;
-	nfnl_set(to_id) = from;
+	nfnl_set(inst, from_id) = to;
+	nfnl_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
 	return 0;
@@ -1141,9 +1182,10 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 static int
 ip_set_dump_done(struct netlink_callback *cb)
 {
+	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 	if (cb->args[2]) {
-		pr_debug("release set %s\n", nfnl_set(cb->args[1])->name);
-		ip_set_put_byindex((ip_set_id_t) cb->args[1]);
+		pr_debug("release set %s\n", nfnl_set(inst, cb->args[1])->name);
+		__ip_set_put_byindex(inst, (ip_set_id_t) cb->args[1]);
 	}
 	return 0;
 }
@@ -1169,6 +1211,7 @@ dump_init(struct netlink_callback *cb)
 	struct nlattr *attr = (void *)nlh + min_len;
 	u32 dump_type;
 	ip_set_id_t index;
+	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
 	/* Second pass, so parser can't fail */
 	nla_parse(cda, IPSET_ATTR_CMD_MAX,
@@ -1182,7 +1225,7 @@ dump_init(struct netlink_callback *cb)
 	if (cda[IPSET_ATTR_SETNAME]) {
 		struct ip_set *set;
 
-		set = find_set_and_id(nla_data(cda[IPSET_ATTR_SETNAME]),
+		set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]),
 				      &index);
 		if (set == NULL)
 			return -ENOENT;
@@ -1210,6 +1253,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0;
 	u32 dump_type, dump_flags;
 	int ret = 0;
+	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
 	if (!cb->args[0]) {
 		ret = dump_init(cb);
@@ -1223,18 +1267,18 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 
-	if (cb->args[1] >= ip_set_max)
+	if (cb->args[1] >= inst->ip_set_max)
 		goto out;
 
 	dump_type = DUMP_TYPE(cb->args[0]);
 	dump_flags = DUMP_FLAGS(cb->args[0]);
-	max = dump_type == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+	max = dump_type == DUMP_ONE ? cb->args[1] + 1 : inst->ip_set_max;
 dump_last:
 	pr_debug("args[0]: %u %u args[1]: %ld\n",
 		 dump_type, dump_flags, cb->args[1]);
 	for (; cb->args[1] < max; cb->args[1]++) {
 		index = (ip_set_id_t) cb->args[1];
-		set = nfnl_set(index);
+		set = nfnl_set(inst, index);
 		if (set == NULL) {
 			if (dump_type == DUMP_ONE) {
 				ret = -ENOENT;
@@ -1312,8 +1356,8 @@ next_set:
 release_refcount:
 	/* If there was an error or set is done, release set */
 	if (ret || !cb->args[2]) {
-		pr_debug("release set %s\n", nfnl_set(index)->name);
-		ip_set_put_byindex(index);
+		pr_debug("release set %s\n", nfnl_set(inst, index)->name);
+		__ip_set_put_byindex(inst, index);
 		cb->args[2] = 0;
 	}
 out:
@@ -1331,6 +1375,8 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
+
 	if (unlikely(protocol_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
@@ -1338,6 +1384,7 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 		struct netlink_dump_control c = {
 			.dump = ip_set_dump_start,
 			.done = ip_set_dump_done,
+			.data = (void *)inst
 		};
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
@@ -1416,6 +1463,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *set;
 	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
 	const struct nlattr *nla;
@@ -1434,7 +1482,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
 		       attr[IPSET_ATTR_LINENO] == NULL))))
 		return -IPSET_ERR_PROTOCOL;
 
-	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
 
@@ -1470,6 +1518,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *set;
 	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
 	const struct nlattr *nla;
@@ -1488,7 +1537,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
 		       attr[IPSET_ATTR_LINENO] == NULL))))
 		return -IPSET_ERR_PROTOCOL;
 
-	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
 
@@ -1524,6 +1573,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh,
 	     const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	struct ip_set *set;
 	struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
 	int ret = 0;
@@ -1534,7 +1584,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
 		     !flag_nested(attr[IPSET_ATTR_DATA])))
 		return -IPSET_ERR_PROTOCOL;
 
-	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
 
@@ -1559,6 +1609,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
 	      const struct nlmsghdr *nlh,
 	      const struct nlattr * const attr[])
 {
+	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
 	const struct ip_set *set;
 	struct sk_buff *skb2;
 	struct nlmsghdr *nlh2;
@@ -1568,7 +1619,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
 		     attr[IPSET_ATTR_SETNAME] == NULL))
 		return -IPSET_ERR_PROTOCOL;
 
-	set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+	set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
 	if (set == NULL)
 		return -ENOENT;
 
@@ -1793,8 +1844,10 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 	unsigned int *op;
 	void *data;
 	int copylen = *len, ret = 0;
+	struct net *net = sock_net(sk);
+	struct ip_set_net *inst = ip_set_pernet(net);
 
-	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	if (optval != SO_IP_SET)
 		return -EBADF;
@@ -1843,7 +1896,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		}
 		req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
 		nfnl_lock(NFNL_SUBSYS_IPSET);
-		find_set_and_id(req_get->set.name, &id);
+		find_set_and_id(inst, req_get->set.name, &id);
 		req_get->set.index = id;
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
 		goto copy;
@@ -1858,10 +1911,10 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		}
 		req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
 		nfnl_lock(NFNL_SUBSYS_IPSET);
-		find_set_and_id(req_get->set.name, &id);
+		find_set_and_id(inst, req_get->set.name, &id);
 		req_get->set.index = id;
 		if (id != IPSET_INVALID_ID)
-			req_get->family = nfnl_set(id)->family;
+			req_get->family = nfnl_set(inst, id)->family;
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
 		goto copy;
 	}
@@ -1870,12 +1923,12 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		struct ip_set *set;
 
 		if (*len != sizeof(struct ip_set_req_get_set) ||
-		    req_get->set.index >= ip_set_max) {
+		    req_get->set.index >= inst->ip_set_max) {
 			ret = -EINVAL;
 			goto done;
 		}
 		nfnl_lock(NFNL_SUBSYS_IPSET);
-		set = nfnl_set(req_get->set.index);
+		set = nfnl_set(inst, req_get->set.index);
 		strncpy(req_get->set.name, set ? set->name : "",
 			IPSET_MAXNAMELEN);
 		nfnl_unlock(NFNL_SUBSYS_IPSET);
@@ -1904,49 +1957,82 @@ static struct nf_sockopt_ops so_set __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
-static int __init
-ip_set_init(void)
+static int __net_init
+ip_set_net_init(struct net *net)
 {
+	struct ip_set_net *inst = ip_set_pernet(net);
+
 	struct ip_set **list;
-	int ret;
 
-	if (max_sets)
-		ip_set_max = max_sets;
-	if (ip_set_max >= IPSET_INVALID_ID)
-		ip_set_max = IPSET_INVALID_ID - 1;
+	inst->ip_set_max = max_sets ? max_sets : CONFIG_IP_SET_MAX;
+	if (inst->ip_set_max >= IPSET_INVALID_ID)
+		inst->ip_set_max = IPSET_INVALID_ID - 1;
 
-	list = kzalloc(sizeof(struct ip_set *) * ip_set_max, GFP_KERNEL);
+	list = kzalloc(sizeof(struct ip_set *) * inst->ip_set_max, GFP_KERNEL);
 	if (!list)
 		return -ENOMEM;
+	inst->is_deleted = 0;
+	rcu_assign_pointer(inst->ip_set_list, list);
+	pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+	return 0;
+}
+
+static void __net_exit
+ip_set_net_exit(struct net *net)
+{
+	struct ip_set_net *inst = ip_set_pernet(net);
+
+	struct ip_set *set = NULL;
+	ip_set_id_t i;
+
+	inst->is_deleted = 1; /* flag for ip_set_nfnl_put */
+
+	for (i = 0; i < inst->ip_set_max; i++) {
+		set = nfnl_set(inst, i);
+		if (set != NULL)
+			ip_set_destroy_set(inst, i);
+	}
+	kfree(rcu_dereference_protected(inst->ip_set_list, 1));
+}
+
+static struct pernet_operations ip_set_net_ops = {
+	.init	= ip_set_net_init,
+	.exit   = ip_set_net_exit,
+	.id	= &ip_set_net_id,
+	.size	= sizeof(struct ip_set_net)
+};
+
 
-	rcu_assign_pointer(ip_set_list, list);
-	ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+static int __init
+ip_set_init(void)
+{
+	int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
 	if (ret != 0) {
 		pr_err("ip_set: cannot register with nfnetlink.\n");
-		kfree(list);
 		return ret;
 	}
 	ret = nf_register_sockopt(&so_set);
 	if (ret != 0) {
 		pr_err("SO_SET registry failed: %d\n", ret);
 		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-		kfree(list);
 		return ret;
 	}
-
-	pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+	ret = register_pernet_subsys(&ip_set_net_ops);
+	if (ret) {
+		pr_err("ip_set: cannot register pernet_subsys.\n");
+		nf_unregister_sockopt(&so_set);
+		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+		return ret;
+	}
 	return 0;
 }
 
 static void __exit
 ip_set_fini(void)
 {
-	struct ip_set **list = rcu_dereference_protected(ip_set_list, 1);
-
-	/* There can't be any existing set */
+	unregister_pernet_subsys(&ip_set_net_ops);
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-	kfree(list);
 	pr_debug("these are the famous last words\n");
 }
 
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index b4add206c603..6a80dbd30df7 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1011,7 +1011,8 @@ static const struct ip_set_type_variant mtype_variant = {
 
 #ifdef IP_SET_EMIT_CREATE
 static int
-IPSET_TOKEN(HTYPE, _create)(struct ip_set *set, struct nlattr *tb[], u32 flags)
+IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
+			    struct nlattr *tb[], u32 flags)
 {
 	u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
 	u8 hbits;
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index ba4232e451f4..ec6f6d15dded 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -39,6 +39,7 @@ struct set_adt_elem {
 struct list_set {
 	u32 size;		/* size of set list array */
 	struct timer_list gc;	/* garbage collection */
+	struct net *net;	/* namespace */
 	struct set_elem members[0]; /* the set members */
 };
 
@@ -171,7 +172,7 @@ list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
 	if (e->id != IPSET_INVALID_ID) {
 		if (i == map->size - 1) {
 			/* Last element replaced: e.g. add new,before,last */
-			ip_set_put_byindex(e->id);
+			ip_set_put_byindex(map->net, e->id);
 			ip_set_ext_destroy(set, e);
 		} else {
 			struct set_elem *x = list_set_elem(set, map,
@@ -179,7 +180,7 @@ list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
 
 			/* Last element pushed off */
 			if (x->id != IPSET_INVALID_ID) {
-				ip_set_put_byindex(x->id);
+				ip_set_put_byindex(map->net, x->id);
 				ip_set_ext_destroy(set, x);
 			}
 			memmove(list_set_elem(set, map, i + 1), e,
@@ -205,7 +206,7 @@ list_set_del(struct ip_set *set, u32 i)
 	struct list_set *map = set->data;
 	struct set_elem *e = list_set_elem(set, map, i);
 
-	ip_set_put_byindex(e->id);
+	ip_set_put_byindex(map->net, e->id);
 	ip_set_ext_destroy(set, e);
 
 	if (i < map->size - 1)
@@ -307,7 +308,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		if (SET_WITH_COMMENT(set))
 			ip_set_init_comment(ext_comment(e, set), ext);
 		/* Set is already added to the list */
-		ip_set_put_byindex(d->id);
+		ip_set_put_byindex(map->net, d->id);
 		return 0;
 	}
 insert:
@@ -366,6 +367,7 @@ static int
 list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 	      enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
+	struct list_set *map = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct set_adt_elem e = { .refid = IPSET_INVALID_ID };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -385,7 +387,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 	ret = ip_set_get_extensions(set, tb, &ext);
 	if (ret)
 		return ret;
-	e.id = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAME]), &s);
+	e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s);
 	if (e.id == IPSET_INVALID_ID)
 		return -IPSET_ERR_NAME;
 	/* "Loop detection" */
@@ -405,7 +407,8 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 	}
 
 	if (tb[IPSET_ATTR_NAMEREF]) {
-		e.refid = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAMEREF]),
+		e.refid = ip_set_get_byname(map->net,
+					    nla_data(tb[IPSET_ATTR_NAMEREF]),
 					    &s);
 		if (e.refid == IPSET_INVALID_ID) {
 			ret = -IPSET_ERR_NAMEREF;
@@ -421,9 +424,9 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 
 finish:
 	if (e.refid != IPSET_INVALID_ID)
-		ip_set_put_byindex(e.refid);
+		ip_set_put_byindex(map->net, e.refid);
 	if (adt != IPSET_ADD || ret)
-		ip_set_put_byindex(e.id);
+		ip_set_put_byindex(map->net, e.id);
 
 	return ip_set_eexist(ret, flags) ? 0 : ret;
 }
@@ -438,7 +441,7 @@ list_set_flush(struct ip_set *set)
 	for (i = 0; i < map->size; i++) {
 		e = list_set_elem(set, map, i);
 		if (e->id != IPSET_INVALID_ID) {
-			ip_set_put_byindex(e->id);
+			ip_set_put_byindex(map->net, e->id);
 			ip_set_ext_destroy(set, e);
 			e->id = IPSET_INVALID_ID;
 		}
@@ -510,7 +513,7 @@ list_set_list(const struct ip_set *set,
 				goto nla_put_failure;
 		}
 		if (nla_put_string(skb, IPSET_ATTR_NAME,
-				   ip_set_name_byindex(e->id)))
+				   ip_set_name_byindex(map->net, e->id)))
 			goto nla_put_failure;
 		if (ip_set_put_extensions(skb, set, e, true))
 			goto nla_put_failure;
@@ -587,7 +590,7 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
 /* Create list:set type of sets */
 
 static bool
-init_list_set(struct ip_set *set, u32 size)
+init_list_set(struct net *net, struct ip_set *set, u32 size)
 {
 	struct list_set *map;
 	struct set_elem *e;
@@ -598,6 +601,7 @@ init_list_set(struct ip_set *set, u32 size)
 		return false;
 
 	map->size = size;
+	map->net = net;
 	set->data = map;
 
 	for (i = 0; i < size; i++) {
@@ -609,7 +613,8 @@ init_list_set(struct ip_set *set, u32 size)
 }
 
 static int
-list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+		u32 flags)
 {
 	u32 size = IP_SET_LIST_DEFAULT_SIZE;
 
@@ -625,7 +630,7 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
 
 	set->variant = &set_variant;
 	set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem));
-	if (!init_list_set(set, size))
+	if (!init_list_set(net, set, size))
 		return -ENOMEM;
 	if (tb[IPSET_ATTR_TIMEOUT]) {
 		set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 2095488684ff..e7c4e0e01ff5 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -81,7 +81,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
 	struct xt_set_info_match_v0 *info = par->matchinfo;
 	ip_set_id_t index;
 
-	index = ip_set_nfnl_get_byindex(info->match_set.index);
+	index = ip_set_nfnl_get_byindex(par->net, info->match_set.index);
 
 	if (index == IPSET_INVALID_ID) {
 		pr_warning("Cannot find set indentified by id %u to match\n",
@@ -91,7 +91,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
 	if (info->match_set.u.flags[IPSET_DIM_MAX-1] != 0) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
-		ip_set_nfnl_put(info->match_set.index);
+		ip_set_nfnl_put(par->net, info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -106,7 +106,7 @@ set_match_v0_destroy(const struct xt_mtdtor_param *par)
 {
 	struct xt_set_info_match_v0 *info = par->matchinfo;
 
-	ip_set_nfnl_put(info->match_set.index);
+	ip_set_nfnl_put(par->net, info->match_set.index);
 }
 
 /* Revision 1 match */
@@ -131,7 +131,7 @@ set_match_v1_checkentry(const struct xt_mtchk_param *par)
 	struct xt_set_info_match_v1 *info = par->matchinfo;
 	ip_set_id_t index;
 
-	index = ip_set_nfnl_get_byindex(info->match_set.index);
+	index = ip_set_nfnl_get_byindex(par->net, info->match_set.index);
 
 	if (index == IPSET_INVALID_ID) {
 		pr_warning("Cannot find set indentified by id %u to match\n",
@@ -141,7 +141,7 @@ set_match_v1_checkentry(const struct xt_mtchk_param *par)
 	if (info->match_set.dim > IPSET_DIM_MAX) {
 		pr_warning("Protocol error: set match dimension "
 			   "is over the limit!\n");
-		ip_set_nfnl_put(info->match_set.index);
+		ip_set_nfnl_put(par->net, info->match_set.index);
 		return -ERANGE;
 	}
 
@@ -153,7 +153,7 @@ set_match_v1_destroy(const struct xt_mtdtor_param *par)
 {
 	struct xt_set_info_match_v1 *info = par->matchinfo;
 
-	ip_set_nfnl_put(info->match_set.index);
+	ip_set_nfnl_put(par->net, info->match_set.index);
 }
 
 /* Revision 3 match */
@@ -228,7 +228,7 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
 	ip_set_id_t index;
 
 	if (info->add_set.index != IPSET_INVALID_ID) {
-		index = ip_set_nfnl_get_byindex(info->add_set.index);
+		index = ip_set_nfnl_get_byindex(par->net, info->add_set.index);
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find add_set index %u as target\n",
 				   info->add_set.index);
@@ -237,12 +237,12 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
 	}
 
 	if (info->del_set.index != IPSET_INVALID_ID) {
-		index = ip_set_nfnl_get_byindex(info->del_set.index);
+		index = ip_set_nfnl_get_byindex(par->net, info->del_set.index);
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
 			if (info->add_set.index != IPSET_INVALID_ID)
-				ip_set_nfnl_put(info->add_set.index);
+				ip_set_nfnl_put(par->net, info->add_set.index);
 			return -ENOENT;
 		}
 	}
@@ -251,9 +251,9 @@ set_target_v0_checkentry(const struct xt_tgchk_param *par)
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
 		if (info->add_set.index != IPSET_INVALID_ID)
-			ip_set_nfnl_put(info->add_set.index);
+			ip_set_nfnl_put(par->net, info->add_set.index);
 		if (info->del_set.index != IPSET_INVALID_ID)
-			ip_set_nfnl_put(info->del_set.index);
+			ip_set_nfnl_put(par->net, info->del_set.index);
 		return -ERANGE;
 	}
 
@@ -270,9 +270,9 @@ set_target_v0_destroy(const struct xt_tgdtor_param *par)
 	const struct xt_set_info_target_v0 *info = par->targinfo;
 
 	if (info->add_set.index != IPSET_INVALID_ID)
-		ip_set_nfnl_put(info->add_set.index);
+		ip_set_nfnl_put(par->net, info->add_set.index);
 	if (info->del_set.index != IPSET_INVALID_ID)
-		ip_set_nfnl_put(info->del_set.index);
+		ip_set_nfnl_put(par->net, info->del_set.index);
 }
 
 /* Revision 1 target */
@@ -301,7 +301,7 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
 	ip_set_id_t index;
 
 	if (info->add_set.index != IPSET_INVALID_ID) {
-		index = ip_set_nfnl_get_byindex(info->add_set.index);
+		index = ip_set_nfnl_get_byindex(par->net, info->add_set.index);
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find add_set index %u as target\n",
 				   info->add_set.index);
@@ -310,12 +310,12 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
 	}
 
 	if (info->del_set.index != IPSET_INVALID_ID) {
-		index = ip_set_nfnl_get_byindex(info->del_set.index);
+		index = ip_set_nfnl_get_byindex(par->net, info->del_set.index);
 		if (index == IPSET_INVALID_ID) {
 			pr_warning("Cannot find del_set index %u as target\n",
 				   info->del_set.index);
 			if (info->add_set.index != IPSET_INVALID_ID)
-				ip_set_nfnl_put(info->add_set.index);
+				ip_set_nfnl_put(par->net, info->add_set.index);
 			return -ENOENT;
 		}
 	}
@@ -324,9 +324,9 @@ set_target_v1_checkentry(const struct xt_tgchk_param *par)
 		pr_warning("Protocol error: SET target dimension "
 			   "is over the limit!\n");
 		if (info->add_set.index != IPSET_INVALID_ID)
-			ip_set_nfnl_put(info->add_set.index);
+			ip_set_nfnl_put(par->net, info->add_set.index);
 		if (info->del_set.index != IPSET_INVALID_ID)
-			ip_set_nfnl_put(info->del_set.index);
+			ip_set_nfnl_put(par->net, info->del_set.index);
 		return -ERANGE;
 	}
 
@@ -339,9 +339,9 @@ set_target_v1_destroy(const struct xt_tgdtor_param *par)
 	const struct xt_set_info_target_v1 *info = par->targinfo;
 
 	if (info->add_set.index != IPSET_INVALID_ID)
-		ip_set_nfnl_put(info->add_set.index);
+		ip_set_nfnl_put(par->net, info->add_set.index);
 	if (info->del_set.index != IPSET_INVALID_ID)
-		ip_set_nfnl_put(info->del_set.index);
+		ip_set_nfnl_put(par->net, info->del_set.index);
 }
 
 /* Revision 2 target */
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 938b7cbf5627..1ac41d3de5c3 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -24,11 +24,12 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
 {
 	struct xt_set_info *set = data;
 	ip_set_id_t index;
+	struct net *net = qdisc_dev(tp->q)->nd_net;
 
 	if (data_len != sizeof(*set))
 		return -EINVAL;
 
-	index = ip_set_nfnl_get_byindex(set->index);
+	index = ip_set_nfnl_get_byindex(net, set->index);
 	if (index == IPSET_INVALID_ID)
 		return -ENOENT;
 
@@ -37,7 +38,7 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
 	if (em->data)
 		return 0;
 
-	ip_set_nfnl_put(index);
+	ip_set_nfnl_put(net, index);
 	return -ENOMEM;
 }
 
@@ -45,7 +46,7 @@ static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em)
 {
 	const struct xt_set_info *set = (const void *) em->data;
 	if (set) {
-		ip_set_nfnl_put(set->index);
+		ip_set_nfnl_put(qdisc_dev(p->q)->nd_net, set->index);
 		kfree((void *) em->data);
 	}
 }
-- 
cgit 


From 3d2e423e0f0f0a3de504a6acae858c651599ba25 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 27 Sep 2013 14:48:41 +0300
Subject: drm/dp: add defines for downstream port types

Detailed cap info at address 80h is not available with DPCD ver
1.0. Whether such devices exist in the wild I don't know, but there
should be no harm done in having the defines for downstream port 0 in
address 05h.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Todd Previte <tprevite@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drm_dp_helper.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index ae8dbfb1207c..83da4eb1575b 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -77,10 +77,10 @@
 #define DP_DOWNSTREAMPORT_PRESENT           0x005
 # define DP_DWN_STRM_PORT_PRESENT           (1 << 0)
 # define DP_DWN_STRM_PORT_TYPE_MASK         0x06
-/* 00b = DisplayPort */
-/* 01b = Analog */
-/* 10b = TMDS or HDMI */
-/* 11b = Other */
+# define DP_DWN_STRM_PORT_TYPE_DP           (0 << 1)
+# define DP_DWN_STRM_PORT_TYPE_ANALOG       (1 << 1)
+# define DP_DWN_STRM_PORT_TYPE_TMDS         (2 << 1)
+# define DP_DWN_STRM_PORT_TYPE_OTHER        (3 << 1)
 # define DP_FORMAT_CONVERSION               (1 << 3)
 # define DP_DETAILED_CAP_INFO_AVAILABLE	    (1 << 4) /* DPI */
 
-- 
cgit 


From 51f8da5916f85c18b696f74f97970e5a7330147e Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 27 Sep 2013 15:08:27 +0300
Subject: drm/edid: add drm_edid_duplicate

We have some code duplication related to EDID duplication. Add a helper.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_edid.c | 12 ++++++++++++
 include/drm/drm_crtc.h     |  1 +
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 1688ff500513..3140a30aa818 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -1264,6 +1264,18 @@ struct edid *drm_get_edid(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_get_edid);
 
+/**
+ * drm_edid_duplicate - duplicate an EDID and the extensions
+ * @edid: EDID to duplicate
+ *
+ * Return duplicate edid or NULL on allocation failure.
+ */
+struct edid *drm_edid_duplicate(const struct edid *edid)
+{
+	return kmemdup(edid, (edid->extensions + 1) * EDID_LENGTH, GFP_KERNEL);
+}
+EXPORT_SYMBOL(drm_edid_duplicate);
+
 /*** EDID parsing ***/
 
 /**
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 24f499569a2f..92e782060199 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -964,6 +964,7 @@ extern int drm_mode_group_init_legacy_group(struct drm_device *dev, struct drm_m
 extern bool drm_probe_ddc(struct i2c_adapter *adapter);
 extern struct edid *drm_get_edid(struct drm_connector *connector,
 				 struct i2c_adapter *adapter);
+extern struct edid *drm_edid_duplicate(const struct edid *edid);
 extern int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid);
 extern void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode);
 extern void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src);
-- 
cgit 


From 0bbf87d852d243680ed7074110ccc1dea003b61a Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 28 Sep 2013 14:10:59 -0700
Subject: net ipv4: Convert ipv4.ip_local_port_range to be per netns v3

- Move sysctl_local_ports from a global variable into struct netns_ipv4.
- Modify inet_get_local_port_range to take a struct net, and update all
  of the callers.
- Move the initialization of sysctl_local_ports into
   sysctl_net_ipv4.c:ipv4_sysctl_init_net from inet_connection_sock.c

v2:
- Ensure indentation used tabs
- Fixed ip.h so it applies cleanly to todays net-next

v3:
- Compile fixes of strange callers of inet_get_local_port_range.
  This patch now successfully passes an allmodconfig build.
  Removed manual inlining of inet_get_local_port_range in ipv4_local_port_range

Originally-by: Samya <samya@twitter.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/cma.c   |  2 +-
 drivers/net/vxlan.c             |  2 +-
 include/net/ip.h                |  6 +----
 include/net/netns/ipv4.h        |  6 +++++
 net/ipv4/inet_connection_sock.c | 20 +++++-----------
 net/ipv4/inet_hashtables.c      |  2 +-
 net/ipv4/ping.c                 |  4 ++--
 net/ipv4/sysctl_net_ipv4.c      | 52 +++++++++++++++++++++++++++--------------
 net/ipv4/udp.c                  |  2 +-
 net/openvswitch/vport-vxlan.c   |  2 +-
 net/sctp/socket.c               |  2 +-
 security/selinux/hooks.c        |  2 +-
 12 files changed, 56 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index dab4b41f1715..a082fd9e7ebe 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2294,7 +2294,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
 	int low, high, remaining;
 	unsigned int rover;
 
-	inet_get_local_port_range(&low, &high);
+	inet_get_local_port_range(&init_net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = net_random() % remaining + low;
 retry:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d1292fe746bc..c376be7b528a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2089,7 +2089,7 @@ static void vxlan_setup(struct net_device *dev)
 	vxlan->age_timer.function = vxlan_cleanup;
 	vxlan->age_timer.data = (unsigned long) vxlan;
 
-	inet_get_local_port_range(&low, &high);
+	inet_get_local_port_range(dev_net(dev), &low, &high);
 	vxlan->port_min = low;
 	vxlan->port_max = high;
 	vxlan->dst_port = htons(vxlan_port);
diff --git a/include/net/ip.h b/include/net/ip.h
index 77b4f9b57c28..16078f422397 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -217,11 +217,7 @@ static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ])
 	}
 }
 
-extern struct local_ports {
-	seqlock_t	lock;
-	int		range[2];
-} sysctl_local_ports;
-void inet_get_local_port_range(int *low, int *high);
+void inet_get_local_port_range(struct net *net, int *low, int *high);
 
 extern unsigned long *sysctl_local_reserved_ports;
 static inline int inet_is_reserved_local_port(int port)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index bf2ec2202c56..5dbd232e12ff 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -15,6 +15,10 @@ struct fib_rules_ops;
 struct hlist_head;
 struct fib_table;
 struct sock;
+struct local_ports {
+	seqlock_t	lock;
+	int		range[2];
+};
 
 struct netns_ipv4 {
 #ifdef CONFIG_SYSCTL
@@ -62,6 +66,8 @@ struct netns_ipv4 {
 	int sysctl_icmp_ratemask;
 	int sysctl_icmp_errors_use_inbound_ifaddr;
 
+	struct local_ports sysctl_local_ports;
+
 	int sysctl_tcp_ecn;
 
 	kgid_t sysctl_ping_group_range[2];
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6acb541c9091..7ac7aa11130e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,27 +29,19 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
-/*
- * This struct holds the first and last local port number.
- */
-struct local_ports sysctl_local_ports __read_mostly = {
-	.lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock),
-	.range = { 32768, 61000 },
-};
-
 unsigned long *sysctl_local_reserved_ports;
 EXPORT_SYMBOL(sysctl_local_reserved_ports);
 
-void inet_get_local_port_range(int *low, int *high)
+void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
-		*low = sysctl_local_ports.range[0];
-		*high = sysctl_local_ports.range[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+		*low = net->ipv4.sysctl_local_ports.range[0];
+		*high = net->ipv4.sysctl_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
@@ -116,7 +108,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 		int remaining, rover, low, high;
 
 again:
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 		smallest_rover = rover = net_random() % remaining + low;
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 7bd8983dbfcf..2779037bd113 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -494,7 +494,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		u32 offset = hint + port_offset;
 		struct inet_timewait_sock *tw = NULL;
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
 		local_bh_disable();
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 706d108e128c..a62610443152 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -237,11 +237,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 540279f4c531..c08f096d46b5 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -43,12 +43,12 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 
 /* Update system visible IP port range */
-static void set_local_port_range(int range[2])
+static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&sysctl_local_ports.lock);
-	sysctl_local_ports.range[0] = range[0];
-	sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+	net->ipv4.sysctl_local_ports.range[0] = range[0];
+	net->ipv4.sysctl_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -56,6 +56,8 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 void __user *buffer,
 				 size_t *lenp, loff_t *ppos)
 {
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -66,14 +68,15 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 		.extra2 = &ip_local_port_range_max,
 	};
 
-	inet_get_local_port_range(range, range + 1);
+	inet_get_local_port_range(net, &range[0], &range[1]);
+
 	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
 
 	if (write && ret == 0) {
 		if (range[1] < range[0])
 			ret = -EINVAL;
 		else
-			set_local_port_range(range);
+			set_local_port_range(net, range);
 	}
 
 	return ret;
@@ -83,23 +86,27 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high)
 {
 	kgid_t *data = table->data;
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
 static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high)
 {
 	kgid_t *data = table->data;
-	write_seqlock(&sysctl_local_ports.lock);
+	struct net *net =
+		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -474,13 +481,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
-	{
-		.procname	= "ip_local_port_range",
-		.data		= &sysctl_local_ports.range,
-		.maxlen		= sizeof(sysctl_local_ports.range),
-		.mode		= 0644,
-		.proc_handler	= ipv4_local_port_range,
-	},
 	{
 		.procname	= "ip_local_reserved_ports",
 		.data		= NULL, /* initialized in sysctl_ipv4_init */
@@ -853,6 +853,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "ip_local_port_range",
+		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
+		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.mode		= 0644,
+		.proc_handler	= ipv4_local_port_range,
+	},
 	{
 		.procname	= "tcp_mem",
 		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_mem),
@@ -888,6 +895,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			&net->ipv4.sysctl_ping_group_range;
 		table[7].data =
 			&net->ipv4.sysctl_tcp_ecn;
+		table[8].data =
+			&net->ipv4.sysctl_local_ports.range;
 
 		/* Don't export sysctls to unprivileged users */
 		if (net->user_ns != &init_user_ns)
@@ -901,6 +910,13 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
 	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
 
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
+	net->ipv4.sysctl_local_ports.range[0] =  32768;
+	net->ipv4.sysctl_local_ports.range[1] =  61000;
+
 	tcp_init_mem(net);
 
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 22462d947750..728ce9503a27 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -219,7 +219,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		unsigned short first, last;
 		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
 		rand = net_random();
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index a481c03e2861..56e22b74cf96 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -173,7 +173,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 
 	skb->local_df = 1;
 
-	inet_get_local_port_range(&port_min, &port_max);
+	inet_get_local_port_range(net, &port_min, &port_max);
 	src_port = vxlan_src_port(port_min, port_max, skb);
 
 	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 911b71b26b0e..72046b9729a8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5890,7 +5890,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		int low, high, remaining, index;
 		unsigned int rover;
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(sock_net(sk), &low, &high);
 		remaining = (high - low) + 1;
 		rover = net_random() % remaining + low;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a5091ec06aa6..568c7699abf1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3929,7 +3929,7 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 		if (snum) {
 			int low, high;
 
-			inet_get_local_port_range(&low, &high);
+			inet_get_local_port_range(sock_net(sk), &low, &high);
 
 			if (snum < max(PROT_SOCK, low) || snum > high) {
 				err = sel_netport_sid(sk->sk_protocol,
-- 
cgit 


From c3f40d7c04152c6f168db2f9b43438015cf092c4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Sep 2013 01:12:40 -0700
Subject: net: add missing sk_max_pacing_rate doc

Warning(include/net/sock.h:411): No description found for parameter
'sk_max_pacing_rate'

Lets please "make htmldocs" and kbuild bot.

Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 240aa3f08cd6..cf91c8edcfc4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -233,6 +233,7 @@ struct cg_proto;
   *	@sk_ll_usec: usecs to busypoll when there is no data
   *	@sk_allocation: allocation mode
   *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
+  *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
   *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
-- 
cgit 


From 36a8f39e05ccc308a5619a7edb5ad6e15ee82ff6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 29 Sep 2013 01:21:32 -0700
Subject: net: skb_is_gso_v6() requires skb_is_gso()

bnx2x makes a dangerous use of skb_is_gso_v6().

It should first make sure skb is a gso packet

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Eilon Greenstein <eilong@broadcom.com>
Acked-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 18 ++++++++++--------
 include/linux/skbuff.h                          |  1 +
 2 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 61726af1de6e..0c7fb1ed1261 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3256,14 +3256,16 @@ static u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb)
 	if (prot == IPPROTO_TCP)
 		rc |= XMIT_CSUM_TCP;
 
-	if (skb_is_gso_v6(skb)) {
-		rc |= (XMIT_GSO_V6 | XMIT_CSUM_TCP);
-		if (rc & XMIT_CSUM_ENC)
-			rc |= XMIT_GSO_ENC_V6;
-	} else if (skb_is_gso(skb)) {
-		rc |= (XMIT_GSO_V4 | XMIT_CSUM_TCP);
-		if (rc & XMIT_CSUM_ENC)
-			rc |= XMIT_GSO_ENC_V4;
+	if (skb_is_gso(skb)) {
+		if (skb_is_gso_v6(skb)) {
+			rc |= (XMIT_GSO_V6 | XMIT_CSUM_TCP);
+			if (rc & XMIT_CSUM_ENC)
+				rc |= XMIT_GSO_ENC_V6;
+		} else {
+			rc |= (XMIT_GSO_V4 | XMIT_CSUM_TCP);
+			if (rc & XMIT_CSUM_ENC)
+				rc |= XMIT_GSO_ENC_V4;
+		}
 	}
 
 	return rc;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6d56840e561e..d72d71efa7a3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2755,6 +2755,7 @@ static inline bool skb_is_gso(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_size;
 }
 
+/* Note: Should be called only if skb_is_gso(skb) is true */
 static inline bool skb_is_gso_v6(const struct sk_buff *skb)
 {
 	return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6;
-- 
cgit 


From 0aec288130713cf7bcf97c929ac5fab6a8e00e44 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 27 Sep 2013 19:01:01 +0300
Subject: drm/dp: constify DP DPCD helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

None of the DP DPCD helpers need to modify the DPCD.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_dp_helper.c | 16 ++++++++--------
 include/drm/drm_dp_helper.h     | 16 ++++++++--------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 89e196627160..9e978aae8972 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -228,12 +228,12 @@ i2c_dp_aux_add_bus(struct i2c_adapter *adapter)
 EXPORT_SYMBOL(i2c_dp_aux_add_bus);
 
 /* Helpers for DP link training */
-static u8 dp_link_status(u8 link_status[DP_LINK_STATUS_SIZE], int r)
+static u8 dp_link_status(const u8 link_status[DP_LINK_STATUS_SIZE], int r)
 {
 	return link_status[r - DP_LANE0_1_STATUS];
 }
 
-static u8 dp_get_lane_status(u8 link_status[DP_LINK_STATUS_SIZE],
+static u8 dp_get_lane_status(const u8 link_status[DP_LINK_STATUS_SIZE],
 			     int lane)
 {
 	int i = DP_LANE0_1_STATUS + (lane >> 1);
@@ -242,7 +242,7 @@ static u8 dp_get_lane_status(u8 link_status[DP_LINK_STATUS_SIZE],
 	return (l >> s) & 0xf;
 }
 
-bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
 			  int lane_count)
 {
 	u8 lane_align;
@@ -262,7 +262,7 @@ bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_channel_eq_ok);
 
-bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
 			      int lane_count)
 {
 	int lane;
@@ -277,7 +277,7 @@ bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_clock_recovery_ok);
 
-u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
+u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE],
 				     int lane)
 {
 	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
@@ -290,7 +290,7 @@ u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_get_adjust_request_voltage);
 
-u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
+u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE],
 					  int lane)
 {
 	int i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
@@ -303,7 +303,7 @@ u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_get_adjust_request_pre_emphasis);
 
-void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
+void drm_dp_link_train_clock_recovery_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
 	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
 		udelay(100);
 	else
@@ -311,7 +311,7 @@ void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
 }
 EXPORT_SYMBOL(drm_dp_link_train_clock_recovery_delay);
 
-void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
+void drm_dp_link_train_channel_eq_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) {
 	if (dpcd[DP_TRAINING_AUX_RD_INTERVAL] == 0)
 		udelay(400);
 	else
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 83da4eb1575b..110f4f1f51d7 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -333,20 +333,20 @@ i2c_dp_aux_add_bus(struct i2c_adapter *adapter);
 
 
 #define DP_LINK_STATUS_SIZE	   6
-bool drm_dp_channel_eq_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
 			  int lane_count);
-bool drm_dp_clock_recovery_ok(u8 link_status[DP_LINK_STATUS_SIZE],
+bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
 			      int lane_count);
-u8 drm_dp_get_adjust_request_voltage(u8 link_status[DP_LINK_STATUS_SIZE],
+u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE],
 				     int lane);
-u8 drm_dp_get_adjust_request_pre_emphasis(u8 link_status[DP_LINK_STATUS_SIZE],
+u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE],
 					  int lane);
 
 #define DP_RECEIVER_CAP_SIZE		0xf
 #define EDP_PSR_RECEIVER_CAP_SIZE	2
 
-void drm_dp_link_train_clock_recovery_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
-void drm_dp_link_train_channel_eq_delay(u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+void drm_dp_link_train_clock_recovery_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+void drm_dp_link_train_channel_eq_delay(const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 
 u8 drm_dp_link_rate_to_bw_code(int link_rate);
 int drm_dp_bw_code_to_link_rate(u8 link_bw);
@@ -379,13 +379,13 @@ struct edp_vsc_psr {
 #define EDP_VSC_PSR_CRC_VALUES_VALID	(1<<2)
 
 static inline int
-drm_dp_max_link_rate(u8 dpcd[DP_RECEIVER_CAP_SIZE])
+drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
 	return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]);
 }
 
 static inline u8
-drm_dp_max_lane_count(u8 dpcd[DP_RECEIVER_CAP_SIZE])
+drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
 	return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
 }
-- 
cgit 


From a99b57dbc09bfff57acd8a7c20f25dfa6cb892a5 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:19 +0100
Subject: drm: Move the GET_CAP macros next to the corresponding ioctl
 structure

It's a tiny bit more logical to find the different capabilities you can
use with the GET_CAP ioctl next to the structure rather than putting
them at the end of the file.

v2: Tab align the litterals (David Herrmann)
v3: Make it clearer that DRM_PRIME_CAP_EXPORT/IMPORT are flags of
    DRM_CAP_PRIME.
v4: Rebase on top of latest bits (DRM_CAP_ASYNC_PAGE_FLIP was
    introduced)

Reviewed-by: David Herrmann <dh.herrmann@gmail.com> (for v2)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/uapi/drm/drm.h | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index ece867889cc7..1e09e8f257ba 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -611,6 +611,16 @@ struct drm_gem_open {
 	__u64 size;
 };
 
+#define DRM_CAP_DUMB_BUFFER		0x1
+#define DRM_CAP_VBLANK_HIGH_CRTC	0x2
+#define DRM_CAP_DUMB_PREFERRED_DEPTH	0x3
+#define DRM_CAP_DUMB_PREFER_SHADOW	0x4
+#define DRM_CAP_PRIME			0x5
+#define  DRM_PRIME_CAP_IMPORT		0x1
+#define  DRM_PRIME_CAP_EXPORT		0x2
+#define DRM_CAP_TIMESTAMP_MONOTONIC	0x6
+#define DRM_CAP_ASYNC_PAGE_FLIP		0x7
+
 /** DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
 	__u64 capability;
@@ -774,17 +784,6 @@ struct drm_event_vblank {
 	__u32 reserved;
 };
 
-#define DRM_CAP_DUMB_BUFFER 0x1
-#define DRM_CAP_VBLANK_HIGH_CRTC 0x2
-#define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3
-#define DRM_CAP_DUMB_PREFER_SHADOW 0x4
-#define DRM_CAP_PRIME 0x5
-#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6
-#define DRM_CAP_ASYNC_PAGE_FLIP 0x7
-
-#define DRM_PRIME_CAP_IMPORT 0x1
-#define DRM_PRIME_CAP_EXPORT 0x2
-
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
-- 
cgit 


From 1c0814fed3a558146402713028cb7114734ec172 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:20 +0100
Subject: drm: Add a SET_CLIENT_CAP ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This ioctl can be used to turn some knobs in a DRM driver. The client
can ask the DRM core for an alternate view of the reality: it can be
useful to be able to instruct the core that the DRM client can handle
new functionnality that would otherwise break current ABI.

v2: Rename to ioctl from SET_CAP to SET_CLIENT_CAP (Chris Wilson)

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_drv.c   | 1 +
 drivers/gpu/drm/drm_ioctl.c | 9 +++++++++
 include/drm/drmP.h          | 2 ++
 include/uapi/drm/drm.h      | 7 +++++++
 4 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index e572dd20bdee..e79d8d9ca203 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -69,6 +69,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 07247e2855a2..15da4124ee12 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -302,6 +302,15 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 	return 0;
 }
 
+/**
+ * Set device/driver capabilities
+ */
+int
+drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
+{
+	return -EINVAL;
+}
+
 /**
  * Setversion ioctl.
  *
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index b46fb45f2cca..dbc86b06a724 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1303,6 +1303,8 @@ extern int drm_getstats(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 extern int drm_getcap(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
+extern int drm_setclientcap(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv);
 extern int drm_setversion(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv);
 extern int drm_noop(struct drm_device *dev, void *data,
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 1e09e8f257ba..526baed365ff 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -627,6 +627,12 @@ struct drm_get_cap {
 	__u64 value;
 };
 
+/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+struct drm_set_client_cap {
+	__u64 capability;
+	__u64 value;
+};
+
 #define DRM_CLOEXEC O_CLOEXEC
 struct drm_prime_handle {
 	__u32 handle;
@@ -659,6 +665,7 @@ struct drm_prime_handle {
 #define DRM_IOCTL_GEM_FLINK		DRM_IOWR(0x0a, struct drm_gem_flink)
 #define DRM_IOCTL_GEM_OPEN		DRM_IOWR(0x0b, struct drm_gem_open)
 #define DRM_IOCTL_GET_CAP		DRM_IOWR(0x0c, struct drm_get_cap)
+#define DRM_IOCTL_SET_CLIENT_CAP	DRM_IOW( 0x0d, struct drm_set_client_cap)
 
 #define DRM_IOCTL_SET_UNIQUE		DRM_IOW( 0x10, struct drm_unique)
 #define DRM_IOCTL_AUTH_MAGIC		DRM_IOW( 0x11, struct drm_auth)
-- 
cgit 


From 4aa17cf0d889cfc984b68a78ae02070cef21bb6b Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:21 +0100
Subject: drm: Add HDMI stereo 3D flags to struct drm_mode_modeinfo
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

HDMI 1.4a defines a few layouts that we'd like to expose. This commits
add new modeinfo flags that can be used to list the supported stereo
layouts (when querying the list of modes) and to set a given stereo 3D
mode (when setting a mode).

v2: Add a drm_mode_is_stereo() helper

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_crtc.h      | 14 ++++++++++++++
 include/uapi/drm/drm_mode.h | 36 ++++++++++++++++++++++--------------
 2 files changed, 36 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 24f499569a2f..825d6fad0981 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -180,6 +180,20 @@ struct drm_display_mode {
 	int hsync;		/* in kHz */
 };
 
+#define DRM_MODE_FLAG_3D_MASK	(DRM_MODE_FLAG_3D_FRAME_PACKING		| \
+				 DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	| \
+				 DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	| \
+				 DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	| \
+				 DRM_MODE_FLAG_3D_L_DEPTH		| \
+				 DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH | \
+				 DRM_MODE_FLAG_3D_TOP_AND_BOTTOM	| \
+				 DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF)
+
+static inline bool drm_mode_is_stereo(const struct drm_display_mode *mode)
+{
+	return mode->flags & DRM_MODE_FLAG_3D_MASK;
+}
+
 enum drm_connector_status {
 	connector_status_connected = 1,
 	connector_status_disconnected = 2,
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 113d32457fa4..bafe61252754 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -44,20 +44,28 @@
 
 /* Video mode flags */
 /* bit compatible with the xorg definitions. */
-#define DRM_MODE_FLAG_PHSYNC	(1<<0)
-#define DRM_MODE_FLAG_NHSYNC	(1<<1)
-#define DRM_MODE_FLAG_PVSYNC	(1<<2)
-#define DRM_MODE_FLAG_NVSYNC	(1<<3)
-#define DRM_MODE_FLAG_INTERLACE	(1<<4)
-#define DRM_MODE_FLAG_DBLSCAN	(1<<5)
-#define DRM_MODE_FLAG_CSYNC	(1<<6)
-#define DRM_MODE_FLAG_PCSYNC	(1<<7)
-#define DRM_MODE_FLAG_NCSYNC	(1<<8)
-#define DRM_MODE_FLAG_HSKEW	(1<<9) /* hskew provided */
-#define DRM_MODE_FLAG_BCAST	(1<<10)
-#define DRM_MODE_FLAG_PIXMUX	(1<<11)
-#define DRM_MODE_FLAG_DBLCLK	(1<<12)
-#define DRM_MODE_FLAG_CLKDIV2	(1<<13)
+#define DRM_MODE_FLAG_PHSYNC			(1<<0)
+#define DRM_MODE_FLAG_NHSYNC			(1<<1)
+#define DRM_MODE_FLAG_PVSYNC			(1<<2)
+#define DRM_MODE_FLAG_NVSYNC			(1<<3)
+#define DRM_MODE_FLAG_INTERLACE			(1<<4)
+#define DRM_MODE_FLAG_DBLSCAN			(1<<5)
+#define DRM_MODE_FLAG_CSYNC			(1<<6)
+#define DRM_MODE_FLAG_PCSYNC			(1<<7)
+#define DRM_MODE_FLAG_NCSYNC			(1<<8)
+#define DRM_MODE_FLAG_HSKEW			(1<<9) /* hskew provided */
+#define DRM_MODE_FLAG_BCAST			(1<<10)
+#define DRM_MODE_FLAG_PIXMUX			(1<<11)
+#define DRM_MODE_FLAG_DBLCLK			(1<<12)
+#define DRM_MODE_FLAG_CLKDIV2			(1<<13)
+#define DRM_MODE_FLAG_3D_FRAME_PACKING		(1<<14)
+#define DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	(1<<15)
+#define DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	(1<<16)
+#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	(1<<17)
+#define DRM_MODE_FLAG_3D_L_DEPTH		(1<<18)
+#define DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH	(1<<19)
+#define DRM_MODE_FLAG_3D_TOP_AND_BOTTOM		(1<<20)
+#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF	(1<<21)
 
 /* DPMS flags */
 /* bit compatible with the xorg definitions. */
-- 
cgit 


From 61d8e3282541139cf5bb31e4c42f952a6cc168f8 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:22 +0100
Subject: drm: Add a STEREO_3D capability to the SET_CLIENT_CAP ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This capability allows user space to control the delivery of modes with
the 3D flags set. This is to not play games with current user space
users not knowing anything about stereo 3D flags and that could try
to set a mode with one or several of those bits set.

So, the plan is to remove the stereo modes from the list of modes we
give to DRM clients by default, and let them through if we are being
told otherwise.

stereo_allowed is bound to the drm_file structure to make it a
per-client setting, not a global one.

v2: Replace clearing 3D flags by discarding the stereo modes now that
    they are regular modes.
v3: SET_CAP -> SET_CLIENT_CAP rename (Chris Wilson)

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c  | 19 ++++++++++++++++++-
 drivers/gpu/drm/drm_ioctl.c | 14 +++++++++++++-
 include/drm/drmP.h          |  3 +++
 include/uapi/drm/drm.h      |  9 +++++++++
 4 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index e79577cb4665..454ac8a6381c 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1581,6 +1581,19 @@ out:
 	return ret;
 }
 
+static bool drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
+					 const struct drm_file *file_priv)
+{
+	/*
+	 * If user-space hasn't configured the driver to expose the stereo 3D
+	 * modes, don't expose them.
+	 */
+	if (!file_priv->stereo_allowed && drm_mode_is_stereo(mode))
+		return false;
+
+	return true;
+}
+
 /**
  * drm_mode_getconnector - get connector configuration
  * @dev: drm device for the ioctl
@@ -1646,7 +1659,8 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 
 	/* delayed so we get modes regardless of pre-fill_modes state */
 	list_for_each_entry(mode, &connector->modes, head)
-		mode_count++;
+		if (drm_mode_expose_to_userspace(mode, file_priv))
+			mode_count++;
 
 	out_resp->connector_id = connector->base.id;
 	out_resp->connector_type = connector->connector_type;
@@ -1668,6 +1682,9 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 		copied = 0;
 		mode_ptr = (struct drm_mode_modeinfo __user *)(unsigned long)out_resp->modes_ptr;
 		list_for_each_entry(mode, &connector->modes, head) {
+			if (!drm_mode_expose_to_userspace(mode, file_priv))
+				continue;
+
 			drm_crtc_convert_to_umode(&u_mode, mode);
 			if (copy_to_user(mode_ptr + copied,
 					 &u_mode, sizeof(u_mode))) {
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 15da4124ee12..dffc836144cc 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -308,7 +308,19 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 int
 drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
-	return -EINVAL;
+	struct drm_set_client_cap *req = data;
+
+	switch (req->capability) {
+	case DRM_CLIENT_CAP_STEREO_3D:
+		if (req->value > 1)
+			return -EINVAL;
+		file_priv->stereo_allowed = req->value;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 /**
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index dbc86b06a724..c65f496ad6b6 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -433,6 +433,9 @@ struct drm_file {
 	struct drm_master *master; /* master this node is currently associated with
 				      N.B. not always minor->master */
 
+	/* true when the client has asked us to expose stereo 3D mode flags */
+	bool stereo_allowed;
+
 	/**
 	 * fbs - List of framebuffers associated with this file.
 	 *
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 526baed365ff..9b24d65fed72 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -627,6 +627,15 @@ struct drm_get_cap {
 	__u64 value;
 };
 
+/**
+ * DRM_CLIENT_CAP_STEREO_3D
+ *
+ * if set to 1, the DRM core will expose the stereo 3D capabilities of the
+ * monitor by advertising the supported 3D layouts in the flags of struct
+ * drm_mode_modeinfo.
+ */
+#define DRM_CLIENT_CAP_STEREO_3D	1
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
-- 
cgit 


From f2ecf2e3bc01868f244fc6ba9cf8fe5d8446db5b Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:27 +0100
Subject: drm: Make drm_match_cea_mode() return the underlying 2D VIC for 3d
 modes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When scanning out a stereo mode, the AVI infoframe vic field has to be
the underlyng 2D VIC. Before that commit, we weren't matching the CEA
mode because of the extra stereo flag and then were setting the VIC
field in the AVI infoframe to 0.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_edid.c  |  4 ++--
 drivers/gpu/drm/drm_modes.c | 18 ++++++++++++------
 include/drm/drm_crtc.h      |  2 +-
 3 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 0bae76d40f28..48f1746f67d8 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2404,7 +2404,7 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 
 		if ((KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock1) ||
 		     KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock2)) &&
-		    drm_mode_equal_no_clocks(to_match, cea_mode))
+		    drm_mode_equal_no_clocks_no_stereo(to_match, cea_mode))
 			return mode + 1;
 	}
 	return 0;
@@ -2453,7 +2453,7 @@ static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
 
 		if ((KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock1) ||
 		     KHZ2PICOS(to_match->clock) == KHZ2PICOS(clock2)) &&
-		    drm_mode_equal_no_clocks(to_match, hdmi_mode))
+		    drm_mode_equal_no_clocks_no_stereo(to_match, hdmi_mode))
 			return mode + 1;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index fc2adb62b757..c2cb2c80f945 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -830,12 +830,16 @@ bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_displ
 	} else if (mode1->clock != mode2->clock)
 		return false;
 
-	return drm_mode_equal_no_clocks(mode1, mode2);
+	if ((mode1->flags & DRM_MODE_FLAG_3D_MASK) !=
+	    (mode2->flags & DRM_MODE_FLAG_3D_MASK))
+		return false;
+
+	return drm_mode_equal_no_clocks_no_stereo(mode1, mode2);
 }
 EXPORT_SYMBOL(drm_mode_equal);
 
 /**
- * drm_mode_equal_no_clocks - test modes for equality
+ * drm_mode_equal_no_clocks_no_stereo - test modes for equality
  * @mode1: first mode
  * @mode2: second mode
  *
@@ -843,12 +847,13 @@ EXPORT_SYMBOL(drm_mode_equal);
  * None.
  *
  * Check to see if @mode1 and @mode2 are equivalent, but
- * don't check the pixel clocks.
+ * don't check the pixel clocks nor the stereo layout.
  *
  * RETURNS:
  * True if the modes are equal, false otherwise.
  */
-bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2)
+bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
+					const struct drm_display_mode *mode2)
 {
 	if (mode1->hdisplay == mode2->hdisplay &&
 	    mode1->hsync_start == mode2->hsync_start &&
@@ -860,12 +865,13 @@ bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1, const struct
 	    mode1->vsync_end == mode2->vsync_end &&
 	    mode1->vtotal == mode2->vtotal &&
 	    mode1->vscan == mode2->vscan &&
-	    mode1->flags == mode2->flags)
+	    (mode1->flags & ~DRM_MODE_FLAG_3D_MASK) ==
+	     (mode2->flags & ~DRM_MODE_FLAG_3D_MASK))
 		return true;
 
 	return false;
 }
-EXPORT_SYMBOL(drm_mode_equal_no_clocks);
+EXPORT_SYMBOL(drm_mode_equal_no_clocks_no_stereo);
 
 /**
  * drm_mode_validate_size - make sure modes adhere to size constraints
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 825d6fad0981..6b7f9c766b4e 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -989,7 +989,7 @@ extern void drm_mode_config_reset(struct drm_device *dev);
 extern void drm_mode_config_cleanup(struct drm_device *dev);
 extern void drm_mode_set_name(struct drm_display_mode *mode);
 extern bool drm_mode_equal(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
-extern bool drm_mode_equal_no_clocks(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
+extern bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1, const struct drm_display_mode *mode2);
 extern int drm_mode_width(const struct drm_display_mode *mode);
 extern int drm_mode_height(const struct drm_display_mode *mode);
 
-- 
cgit 


From 560a067a93520a18a1dd7cf07ebd759a45270855 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:29 +0100
Subject: drm: Make exposing stereo modes a per-connector opt-in
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just like with interlaced or double scan modes, make stereo modes a
per-connector opt-in to give a chance to driver authors to make it work
before enabling it.

Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc_helper.c | 8 +++++++-
 include/drm/drm_crtc.h            | 2 ++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index c722c3b5404d..4280e37f34c5 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -76,7 +76,8 @@ static void drm_mode_validate_flag(struct drm_connector *connector,
 {
 	struct drm_display_mode *mode;
 
-	if (flags == (DRM_MODE_FLAG_DBLSCAN | DRM_MODE_FLAG_INTERLACE))
+	if (flags == (DRM_MODE_FLAG_DBLSCAN | DRM_MODE_FLAG_INTERLACE |
+		      DRM_MODE_FLAG_3D_MASK))
 		return;
 
 	list_for_each_entry(mode, &connector->modes, head) {
@@ -86,6 +87,9 @@ static void drm_mode_validate_flag(struct drm_connector *connector,
 		if ((mode->flags & DRM_MODE_FLAG_DBLSCAN) &&
 				!(flags & DRM_MODE_FLAG_DBLSCAN))
 			mode->status = MODE_NO_DBLESCAN;
+		if ((mode->flags & DRM_MODE_FLAG_3D_MASK) &&
+				!(flags & DRM_MODE_FLAG_3D_MASK))
+			mode->status = MODE_NO_STEREO;
 	}
 
 	return;
@@ -175,6 +179,8 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 		mode_flags |= DRM_MODE_FLAG_INTERLACE;
 	if (connector->doublescan_allowed)
 		mode_flags |= DRM_MODE_FLAG_DBLSCAN;
+	if (connector->stereo_allowed)
+		mode_flags |= DRM_MODE_FLAG_3D_MASK;
 	drm_mode_validate_flag(connector, mode_flags);
 
 	list_for_each_entry(mode, &connector->modes, head) {
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 6b7f9c766b4e..1b69407f3f0f 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -108,6 +108,7 @@ enum drm_mode_status {
     MODE_ONE_HEIGHT,    /* only one height is supported */
     MODE_ONE_SIZE,      /* only one resolution is supported */
     MODE_NO_REDUCED,    /* monitor doesn't accept reduced blanking */
+    MODE_NO_STEREO,	/* stereo modes not supported */
     MODE_UNVERIFIED = -3, /* mode needs to reverified */
     MODE_BAD = -2,	/* unspecified reason */
     MODE_ERROR	= -1	/* error condition */
@@ -611,6 +612,7 @@ struct drm_connector {
 	int connector_type_id;
 	bool interlace_allowed;
 	bool doublescan_allowed;
+	bool stereo_allowed;
 	struct list_head modes; /* list of modes on this connector */
 
 	enum drm_connector_status status;
-- 
cgit 


From 99b314a0b37c1f637929db7f20d7e47eb2374c97 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:32 +0100
Subject: drm: Remove clock_index from struct drm_display_mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This field was only accessed by the nouveau driver, but never set. So
concluded we can rid of this one.

Acked-by: Ben Skeggs <bskeggs@redhat.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/nouveau/dispnv04/crtc.c | 2 --
 include/drm/drm_crtc.h                  | 1 -
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index d4fbf11360fe..0e3270c3ffd2 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -326,8 +326,6 @@ nv_crtc_mode_set_vga(struct drm_crtc *crtc, struct drm_display_mode *mode)
 			regp->MiscOutReg = 0x23;	/* +hsync +vsync */
 	}
 
-	regp->MiscOutReg |= (mode->clock_index & 0x03) << 2;
-
 	/*
 	 * Time Sequencer
 	 */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 1b69407f3f0f..011baaa159a2 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -156,7 +156,6 @@ struct drm_display_mode {
 	int height_mm;
 
 	/* Actual mode we give to hw */
-	int clock_index;
 	int synth_clock;
 	int crtc_hdisplay;
 	int crtc_hblank_start;
-- 
cgit 


From 65427b1e94eca5923e0f723d1dd000f47e6d1696 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:33 +0100
Subject: drm: Remove synth_clock from struct drm_display_mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This field is unused. Garbage collect it.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_crtc.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 011baaa159a2..8e9716e362e1 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -156,7 +156,6 @@ struct drm_display_mode {
 	int height_mm;
 
 	/* Actual mode we give to hw */
-	int synth_clock;
 	int crtc_hdisplay;
 	int crtc_hblank_start;
 	int crtc_hblank_end;
-- 
cgit 


From bde2dcf701db9fa6d010afa8e9254c3d7b0331fb Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:34 +0100
Subject: drm: Introduce a crtc_clock for struct drm_display_mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just like the various timings, make it possible to have a clock field
what we can tweak before giving it to hardware.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_modes.c | 1 +
 include/drm/drm_crtc.h      | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index c2cb2c80f945..ef26eb28364a 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -719,6 +719,7 @@ void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags)
 	if ((p == NULL) || ((p->type & DRM_MODE_TYPE_CRTC_C) == DRM_MODE_TYPE_BUILTIN))
 		return;
 
+	p->crtc_clock = p->clock;
 	p->crtc_hdisplay = p->hdisplay;
 	p->crtc_hsync_start = p->hsync_start;
 	p->crtc_hsync_end = p->hsync_end;
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 8e9716e362e1..73478bc8f9ee 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -156,6 +156,7 @@ struct drm_display_mode {
 	int height_mm;
 
 	/* Actual mode we give to hw */
+	int crtc_clock;		/* in KHz */
 	int crtc_hdisplay;
 	int crtc_hblank_start;
 	int crtc_hblank_end;
-- 
cgit 


From 448cce25f408be4c933f88ed8962455a0c16d0f8 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Wed, 25 Sep 2013 16:45:35 +0100
Subject: drm: Implement timings adjustments for frame packing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When using the frame packing and a single big framebuffer, some hardware
requires that we do everything like if we were scanning out the big
buffer itself. Let's instrument drm_mode_set_crtcinfo() to be able to do
this adjustement if the driver is asking for it.

v2: Use crtc_vtotal and multiply the clock by 2 instead of
    reconstructing it (Ville Syrjälä)

Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_modes.c | 22 +++++++++++++++++++++-
 include/drm/drm_crtc.h      |  3 ++-
 2 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ef26eb28364a..b0733153dfd2 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -707,12 +707,18 @@ EXPORT_SYMBOL(drm_mode_vrefresh);
 /**
  * drm_mode_set_crtcinfo - set CRTC modesetting parameters
  * @p: mode
- * @adjust_flags: unused? (FIXME)
+ * @adjust_flags: a combination of adjustment flags
  *
  * LOCKING:
  * None.
  *
  * Setup the CRTC modesetting parameters for @p, adjusting if necessary.
+ *
+ * - The CRTC_INTERLACE_HALVE_V flag can be used to halve vertical timings of
+ *   interlaced modes.
+ * - The CRTC_STEREO_DOUBLE flag can be used to compute the timings for
+ *   buffers containing two eyes (only adjust the timings when needed, eg. for
+ *   "frame packing" or "side by side full").
  */
 void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags)
 {
@@ -753,6 +759,20 @@ void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags)
 		p->crtc_vtotal *= p->vscan;
 	}
 
+	if (adjust_flags & CRTC_STEREO_DOUBLE) {
+		unsigned int layout = p->flags & DRM_MODE_FLAG_3D_MASK;
+
+		switch (layout) {
+		case DRM_MODE_FLAG_3D_FRAME_PACKING:
+			p->crtc_clock *= 2;
+			p->crtc_vdisplay += p->crtc_vtotal;
+			p->crtc_vsync_start += p->crtc_vtotal;
+			p->crtc_vsync_end += p->crtc_vtotal;
+			p->crtc_vtotal += p->crtc_vtotal;
+			break;
+		}
+	}
+
 	p->crtc_vblank_start = min(p->crtc_vsync_start, p->crtc_vdisplay);
 	p->crtc_vblank_end = max(p->crtc_vsync_end, p->crtc_vtotal);
 	p->crtc_hblank_start = min(p->crtc_hsync_start, p->crtc_hdisplay);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 73478bc8f9ee..b2d08ca68ee7 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -125,7 +125,8 @@ enum drm_mode_status {
 	.vscan = (vs), .flags = (f), \
 	.base.type = DRM_MODE_OBJECT_MODE
 
-#define CRTC_INTERLACE_HALVE_V 0x1 /* halve V values for interlacing */
+#define CRTC_INTERLACE_HALVE_V	(1 << 0) /* halve V values for interlacing */
+#define CRTC_STEREO_DOUBLE	(1 << 1) /* adjust timings for stereo modes */
 
 struct drm_display_mode {
 	/* Header */
-- 
cgit 


From f7e121b76469624459152542c1b809a1ebc835fe Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 27 Sep 2013 12:11:48 +0100
Subject: drm: Code stereo layouts as an enum rather than a bit field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows us to use fewer bits in the mode structure, leaving room for
future work while allowing more stereo layouts types than we could have
ever dreamt of.

I also exposed the previously private DRM_MODE_FLAG_3D_MASK to set in
stone that we are using 5 bits for the stereo layout enum, reserving 32
values.

Even with that reservation, we gain 3 bits from the previous encoding.

The code adding the mandatory stereo modes needeed to be adapted as it was
relying or being able to or stereo layouts together.

Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_edid.c  | 47 +++++++++++++++------------------------------
 include/drm/drm_crtc.h      |  9 ---------
 include/uapi/drm/drm_mode.h | 19 ++++++++++--------
 3 files changed, 26 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index c24af1d6cb47..7d1e8a90480a 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2562,16 +2562,16 @@ struct stereo_mandatory_mode {
 };
 
 static const struct stereo_mandatory_mode stereo_mandatory_modes[] = {
-	{ 1920, 1080, 24,
-	  DRM_MODE_FLAG_3D_TOP_AND_BOTTOM | DRM_MODE_FLAG_3D_FRAME_PACKING },
+	{ 1920, 1080, 24, DRM_MODE_FLAG_3D_TOP_AND_BOTTOM },
+	{ 1920, 1080, 24, DRM_MODE_FLAG_3D_FRAME_PACKING },
 	{ 1920, 1080, 50,
 	  DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF },
 	{ 1920, 1080, 60,
 	  DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF },
-	{ 1280, 720,  50,
-	  DRM_MODE_FLAG_3D_TOP_AND_BOTTOM | DRM_MODE_FLAG_3D_FRAME_PACKING },
-	{ 1280, 720,  60,
-	  DRM_MODE_FLAG_3D_TOP_AND_BOTTOM | DRM_MODE_FLAG_3D_FRAME_PACKING }
+	{ 1280, 720,  50, DRM_MODE_FLAG_3D_TOP_AND_BOTTOM },
+	{ 1280, 720,  50, DRM_MODE_FLAG_3D_FRAME_PACKING },
+	{ 1280, 720,  60, DRM_MODE_FLAG_3D_TOP_AND_BOTTOM },
+	{ 1280, 720,  60, DRM_MODE_FLAG_3D_FRAME_PACKING }
 };
 
 static bool
@@ -2586,50 +2586,33 @@ stereo_match_mandatory(const struct drm_display_mode *mode,
 	       drm_mode_vrefresh(mode) == stereo_mode->vrefresh;
 }
 
-static const struct stereo_mandatory_mode *
-hdmi_find_stereo_mandatory_mode(const struct drm_display_mode *mode)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(stereo_mandatory_modes); i++)
-		if (stereo_match_mandatory(mode, &stereo_mandatory_modes[i]))
-			return &stereo_mandatory_modes[i];
-
-	return NULL;
-}
-
 static int add_hdmi_mandatory_stereo_modes(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	const struct drm_display_mode *mode;
 	struct list_head stereo_modes;
-	int modes = 0;
+	int modes = 0, i;
 
 	INIT_LIST_HEAD(&stereo_modes);
 
 	list_for_each_entry(mode, &connector->probed_modes, head) {
-		const struct stereo_mandatory_mode *mandatory;
-		u32 stereo_layouts, layout;
-
-		mandatory = hdmi_find_stereo_mandatory_mode(mode);
-		if (!mandatory)
-			continue;
-
-		stereo_layouts = mandatory->flags & DRM_MODE_FLAG_3D_MASK;
-		do {
+		for (i = 0; i < ARRAY_SIZE(stereo_mandatory_modes); i++) {
+			const struct stereo_mandatory_mode *mandatory;
 			struct drm_display_mode *new_mode;
 
-			layout = 1 << (ffs(stereo_layouts) - 1);
-			stereo_layouts &= ~layout;
+			if (!stereo_match_mandatory(mode,
+						    &stereo_mandatory_modes[i]))
+				continue;
 
+			mandatory = &stereo_mandatory_modes[i];
 			new_mode = drm_mode_duplicate(dev, mode);
 			if (!new_mode)
 				continue;
 
-			new_mode->flags |= layout;
+			new_mode->flags |= mandatory->flags;
 			list_add_tail(&new_mode->head, &stereo_modes);
 			modes++;
-		} while (stereo_layouts);
+		}
 	}
 
 	list_splice_tail(&stereo_modes, &connector->probed_modes);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index b2d08ca68ee7..eb6b8dc971d9 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -181,15 +181,6 @@ struct drm_display_mode {
 	int hsync;		/* in kHz */
 };
 
-#define DRM_MODE_FLAG_3D_MASK	(DRM_MODE_FLAG_3D_FRAME_PACKING		| \
-				 DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	| \
-				 DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	| \
-				 DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	| \
-				 DRM_MODE_FLAG_3D_L_DEPTH		| \
-				 DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH | \
-				 DRM_MODE_FLAG_3D_TOP_AND_BOTTOM	| \
-				 DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF)
-
 static inline bool drm_mode_is_stereo(const struct drm_display_mode *mode)
 {
 	return mode->flags & DRM_MODE_FLAG_3D_MASK;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index bafe61252754..7980f8994070 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -58,14 +58,17 @@
 #define DRM_MODE_FLAG_PIXMUX			(1<<11)
 #define DRM_MODE_FLAG_DBLCLK			(1<<12)
 #define DRM_MODE_FLAG_CLKDIV2			(1<<13)
-#define DRM_MODE_FLAG_3D_FRAME_PACKING		(1<<14)
-#define DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	(1<<15)
-#define DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	(1<<16)
-#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	(1<<17)
-#define DRM_MODE_FLAG_3D_L_DEPTH		(1<<18)
-#define DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH	(1<<19)
-#define DRM_MODE_FLAG_3D_TOP_AND_BOTTOM		(1<<20)
-#define DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF	(1<<21)
+#define DRM_MODE_FLAG_3D_MASK			(0x1f<<14)
+#define  DRM_MODE_FLAG_3D_NONE			(0<<14)
+#define  DRM_MODE_FLAG_3D_FRAME_PACKING		(1<<14)
+#define  DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	(2<<14)
+#define  DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	(3<<14)
+#define  DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	(4<<14)
+#define  DRM_MODE_FLAG_3D_L_DEPTH		(5<<14)
+#define  DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH	(6<<14)
+#define  DRM_MODE_FLAG_3D_TOP_AND_BOTTOM	(7<<14)
+#define  DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF	(8<<14)
+
 
 /* DPMS flags */
 /* bit compatible with the xorg definitions. */
-- 
cgit 


From 5848ad409c1817f5b70507e6b4440fcbd002f6c5 Mon Sep 17 00:00:00 2001
From: Damien Lespiau <damien.lespiau@intel.com>
Date: Fri, 27 Sep 2013 12:11:50 +0100
Subject: drm: Reject stereo modes with an unknown layout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The kernel shouldn't accept invalid modes, just say No.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c  | 3 +++
 include/drm/drm_crtc.h      | 2 ++
 include/uapi/drm/drm_mode.h | 4 ++++
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 2ce80ed55b08..d7a8370e3cdc 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1319,6 +1319,9 @@ static int drm_crtc_convert_umode(struct drm_display_mode *out,
 	if (in->clock > INT_MAX || in->vrefresh > INT_MAX)
 		return -ERANGE;
 
+	if ((in->flags & DRM_MODE_FLAG_3D_MASK) > DRM_MODE_FLAG_3D_MAX)
+		return -EINVAL;
+
 	out->clock = in->clock;
 	out->hdisplay = in->hdisplay;
 	out->hsync_start = in->hsync_start;
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index eb6b8dc971d9..50cedadc9fcc 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -128,6 +128,8 @@ enum drm_mode_status {
 #define CRTC_INTERLACE_HALVE_V	(1 << 0) /* halve V values for interlacing */
 #define CRTC_STEREO_DOUBLE	(1 << 1) /* adjust timings for stereo modes */
 
+#define DRM_MODE_FLAG_3D_MAX	DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF
+
 struct drm_display_mode {
 	/* Header */
 	struct list_head head;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 7980f8994070..c2c4ace3db61 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -58,6 +58,10 @@
 #define DRM_MODE_FLAG_PIXMUX			(1<<11)
 #define DRM_MODE_FLAG_DBLCLK			(1<<12)
 #define DRM_MODE_FLAG_CLKDIV2			(1<<13)
+ /*
+  * When adding a new stereo mode don't forget to adjust DRM_MODE_FLAGS_3D_MAX
+  * (define not exposed to user space).
+  */
 #define DRM_MODE_FLAG_3D_MASK			(0x1f<<14)
 #define  DRM_MODE_FLAG_3D_NONE			(0<<14)
 #define  DRM_MODE_FLAG_3D_FRAME_PACKING		(1<<14)
-- 
cgit 


From 5eb7906b47dcd906b3ffd811e689e0de4a6b1b6a Mon Sep 17 00:00:00 2001
From: Eliad Peller <eliad@wizery.com>
Date: Thu, 29 Aug 2013 15:03:14 +0300
Subject: ieee80211: fix vht cap definitions

VHT_CAP_BEAMFORMER_ANTENNAS cap is actually defined in the draft as
VHT_CAP_BEAMFORMEE_STS_MAX, and its size is 3 bits long.

VHT_CAP_SOUNDING_DIMENSIONS is also 3 bits long.

Fix the definitions and change the cap masking accordingly.

Signed-off-by: Eliad Peller <eliad@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 ++--
 net/mac80211/vht.c        | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index a5b598a79bec..7c1e1ebc0e23 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1391,8 +1391,8 @@ struct ieee80211_vht_operation {
 #define IEEE80211_VHT_CAP_RXSTBC_MASK				0x00000700
 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE			0x00000800
 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE			0x00001000
-#define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX		0x00006000
-#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX		0x00030000
+#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MAX			0x0000e000
+#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX		0x00070000
 #define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE			0x00080000
 #define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE			0x00100000
 #define IEEE80211_VHT_CAP_VHT_TXOP_PS				0x00200000
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index 97c289414e32..de0112785aae 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -185,13 +185,13 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE) {
 		vht_cap->cap |= cap_info &
 				(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE |
-				 IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX |
 				 IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX);
 	}
 
 	if (own_cap.cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE)
 		vht_cap->cap |= cap_info &
-				IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE;
+				(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
+				 IEEE80211_VHT_CAP_BEAMFORMEE_STS_MAX);
 
 	if (own_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE)
 		vht_cap->cap |= cap_info &
-- 
cgit 


From 55fff50113daa178010a38e0dc27172f06d17b8e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 19 Aug 2013 18:48:41 +0200
Subject: mac80211: add explicit IBSS driver operations

This can be useful for drivers if they have any failure cases
when joining an IBSS. Also move setting the queue parameters
to before this new call, in case the new driver op needs them
already.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  7 +++++++
 net/mac80211/driver-ops.h | 27 +++++++++++++++++++++++++++
 net/mac80211/ibss.c       | 22 ++++++++++++++++++++--
 net/mac80211/trace.h      | 35 +++++++++++++++++++++++++++++++++++
 4 files changed, 89 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 3411c59b636b..8cff800f7046 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2666,6 +2666,10 @@ enum ieee80211_roc_type {
  *	zero using ieee80211_csa_is_complete() after the beacon has been
  *	transmitted and then call ieee80211_csa_finish().
  *
+ * @join_ibss: Join an IBSS (on an IBSS interface); this is called after all
+ *	information in bss_conf is set up and the beacon can be retrieved. A
+ *	channel context is bound before this is called.
+ * @leave_ibss: Leave the IBSS again.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -2857,6 +2861,9 @@ struct ieee80211_ops {
 	void (*channel_switch_beacon)(struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
 				      struct cfg80211_chan_def *chandef);
+
+	int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
+	void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 };
 
 /**
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index b3ea11f3d526..5d03c47c0a4c 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1085,4 +1085,31 @@ drv_channel_switch_beacon(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
+static inline int drv_join_ibss(struct ieee80211_local *local,
+				struct ieee80211_sub_if_data *sdata)
+{
+	int ret = 0;
+
+	might_sleep();
+	check_sdata_in_driver(sdata);
+
+	trace_drv_join_ibss(local, sdata, &sdata->vif.bss_conf);
+	if (local->ops->join_ibss)
+		ret = local->ops->join_ibss(&local->hw, &sdata->vif);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
+static inline void drv_leave_ibss(struct ieee80211_local *local,
+				  struct ieee80211_sub_if_data *sdata)
+{
+	might_sleep();
+	check_sdata_in_driver(sdata);
+
+	trace_drv_leave_ibss(local, sdata);
+	if (local->ops->leave_ibss)
+		local->ops->leave_ibss(&local->hw, &sdata->vif);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 5ea9b3ae303e..21a0b8835cb3 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -229,6 +229,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	struct beacon_data *presp;
 	enum nl80211_bss_scan_width scan_width;
 	bool have_higher_than_11mbit;
+	int err;
 
 	sdata_assert_lock(sdata);
 
@@ -247,6 +248,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		ieee80211_bss_info_change_notify(sdata,
 						 BSS_CHANGED_IBSS |
 						 BSS_CHANGED_BEACON_ENABLED);
+		drv_leave_ibss(local, sdata);
 	}
 
 	presp = rcu_dereference_protected(ifibss->presp,
@@ -329,11 +331,26 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	else
 		sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE;
 
+	ieee80211_set_wmm_default(sdata, true);
+
 	sdata->vif.bss_conf.ibss_joined = true;
 	sdata->vif.bss_conf.ibss_creator = creator;
-	ieee80211_bss_info_change_notify(sdata, bss_change);
 
-	ieee80211_set_wmm_default(sdata, true);
+	err = drv_join_ibss(local, sdata);
+	if (err) {
+		sdata->vif.bss_conf.ibss_joined = false;
+		sdata->vif.bss_conf.ibss_creator = false;
+		sdata->vif.bss_conf.enable_beacon = false;
+		sdata->vif.bss_conf.ssid_len = 0;
+		RCU_INIT_POINTER(ifibss->presp, NULL);
+		kfree_rcu(presp, rcu_head);
+		ieee80211_vif_release_channel(sdata);
+		sdata_info(sdata, "Failed to join IBSS, driver failure: %d\n",
+			   err);
+		return;
+	}
+
+	ieee80211_bss_info_change_notify(sdata, bss_change);
 
 	ifibss->state = IEEE80211_IBSS_MLME_JOINED;
 	mod_timer(&ifibss->timer,
@@ -761,6 +778,7 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata)
 	clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state);
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED |
 						BSS_CHANGED_IBSS);
+	drv_leave_ibss(local, sdata);
 	ieee80211_vif_release_channel(sdata);
 }
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 1aba645882bd..5d62c5804819 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -1475,6 +1475,41 @@ DEFINE_EVENT(local_sdata_evt, drv_ipv6_addr_change,
 );
 #endif
 
+TRACE_EVENT(drv_join_ibss,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_bss_conf *info),
+
+	TP_ARGS(local, sdata, info),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u8, dtimper)
+		__field(u16, bcnint)
+		__dynamic_array(u8, ssid, info->ssid_len);
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->dtimper = info->dtim_period;
+		__entry->bcnint = info->beacon_int;
+		memcpy(__get_dynamic_array(ssid), info->ssid, info->ssid_len);
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT,
+		LOCAL_PR_ARG, VIF_PR_ARG
+	)
+);
+
+DEFINE_EVENT(local_sdata_evt, drv_leave_ibss,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
-- 
cgit 


From 0cfcefef1945c6d3f24bce1c22937cfeae07eae8 Mon Sep 17 00:00:00 2001
From: Michal Kazior <michal.kazior@tieto.com>
Date: Mon, 23 Sep 2013 15:34:38 +0200
Subject: mac80211: support reporting A-MSDU subframes individually

Some devices may not be able to report A-MSDUs in
single buffers. Drivers for such devices were
forced to re-assemble A-MSDUs which would then
be eventually disassembled by mac80211. This could
lead to CPU cache thrashing and poor performance.

Since A-MSDU has a single sequence number all
subframes share it. This was in conflict with
retransmission/duplication recovery
(IEEE802.11-2012: 9.3.2.10).

Patch introduces a new flag that is meant to be
set for all individually reported A-MSDU subframes
except the last one. This ensures the
last_seq_ctrl is updated after the last subframe
is processed. If an A-MSDU is actually a duplicate
transmission all reported subframes will be
properly discarded.

Signed-off-by: Michal Kazior <michal.kazior@tieto.com>
[johannes: add braces that were missing even before]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 10 ++++++++++
 net/mac80211/rx.c      |  3 ++-
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8cff800f7046..da8011920b65 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -829,6 +829,15 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  * @RX_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3
  * @RX_FLAG_10MHZ: 10 MHz (half channel) was used
  * @RX_FLAG_5MHZ: 5 MHz (quarter channel) was used
+ * @RX_FLAG_AMSDU_MORE: Some drivers may prefer to report separate A-MSDU
+ *	subframes instead of a one huge frame for performance reasons.
+ *	All, but the last MSDU from an A-MSDU should have this flag set. E.g.
+ *	if an A-MSDU has 3 frames, the first 2 must have the flag set, while
+ *	the 3rd (last) one must not have this flag set. The flag is used to
+ *	deal with retransmission/duplication recovery properly since A-MSDU
+ *	subframes share the same sequence number. Reported subframes can be
+ *	either regular MSDU or singly A-MSDUs. Subframes must not be
+ *	interleaved with other frames.
  */
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
@@ -859,6 +868,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_STBC_MASK		= BIT(26) | BIT(27),
 	RX_FLAG_10MHZ			= BIT(28),
 	RX_FLAG_5MHZ			= BIT(29),
+	RX_FLAG_AMSDU_MORE		= BIT(30),
 };
 
 #define RX_FLAG_STBC_SHIFT		26
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 8e908e17e248..f0247a43a75c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -995,8 +995,9 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 				rx->sta->num_duplicates++;
 			}
 			return RX_DROP_UNUSABLE;
-		} else
+		} else if (!(status->flag & RX_FLAG_AMSDU_MORE)) {
 			rx->sta->last_seq_ctrl[rx->seqno_idx] = hdr->seq_ctrl;
+		}
 	}
 
 	if (unlikely(rx->skb->len < 16)) {
-- 
cgit 


From 180cf72f56fab2810e00497c087c7126bfe53c85 Mon Sep 17 00:00:00 2001
From: "holger@eitzenberger.org" <holger@eitzenberger.org>
Date: Mon, 30 Sep 2013 17:07:28 +0200
Subject: netfilter: nf_ct_sip: consolidate NAT hook functions

There are currently seven different NAT hooks used in both
nf_conntrack_sip and nf_nat_sip, each of the hooks is exported in
nf_conntrack_sip, then set from the nf_nat_sip NAT helper.

And because each of them is exported there is quite some overhead
introduced due of this.

By introducing nf_nat_sip_hooks I am able to reduce both text/data
somewhat.  For nf_conntrack_sip e. g. I get

        text             data              bss              dec
old    15243             5256               32            20531
new    15010             5192               32            20234

Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_conntrack_sip.h | 107 +++++++++++++-----------
 net/netfilter/nf_conntrack_sip.c           | 127 ++++++++---------------------
 net/netfilter/nf_nat_sip.c                 |  35 ++++----
 3 files changed, 107 insertions(+), 162 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h
index ba7f571a2b1c..4cb71551f611 100644
--- a/include/linux/netfilter/nf_conntrack_sip.h
+++ b/include/linux/netfilter/nf_conntrack_sip.h
@@ -107,55 +107,64 @@ enum sdp_header_types {
 	SDP_HDR_MEDIA,
 };
 
-extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb,
-				       unsigned int protoff,
-				       unsigned int dataoff,
-				       const char **dptr,
-				       unsigned int *datalen);
-extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb,
-					  unsigned int protoff, s16 off);
-extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb,
-					      unsigned int protoff,
-					      unsigned int dataoff,
-					      const char **dptr,
-					      unsigned int *datalen,
-					      struct nf_conntrack_expect *exp,
-					      unsigned int matchoff,
-					      unsigned int matchlen);
-extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb,
-					    unsigned int protoff,
-					    unsigned int dataoff,
-					    const char **dptr,
-					    unsigned int *datalen,
-					    unsigned int sdpoff,
-					    enum sdp_header_types type,
-					    enum sdp_header_types term,
-					    const union nf_inet_addr *addr);
-extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb,
-					    unsigned int protoff,
-					    unsigned int dataoff,
-					    const char **dptr,
-					    unsigned int *datalen,
-					    unsigned int matchoff,
-					    unsigned int matchlen,
-					    u_int16_t port);
-extern unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb,
-					       unsigned int protoff,
-					       unsigned int dataoff,
-					       const char **dptr,
-					       unsigned int *datalen,
-					       unsigned int sdpoff,
-					       const union nf_inet_addr *addr);
-extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb,
-					     unsigned int protoff,
-					     unsigned int dataoff,
-					     const char **dptr,
-					     unsigned int *datalen,
-					     struct nf_conntrack_expect *rtp_exp,
-					     struct nf_conntrack_expect *rtcp_exp,
-					     unsigned int mediaoff,
-					     unsigned int medialen,
-					     union nf_inet_addr *rtp_addr);
+struct nf_nat_sip_hooks {
+	unsigned int (*msg)(struct sk_buff *skb,
+			    unsigned int protoff,
+			    unsigned int dataoff,
+			    const char **dptr,
+			    unsigned int *datalen);
+
+	void (*seq_adjust)(struct sk_buff *skb,
+			   unsigned int protoff, s16 off);
+
+	unsigned int (*expect)(struct sk_buff *skb,
+			       unsigned int protoff,
+			       unsigned int dataoff,
+			       const char **dptr,
+			       unsigned int *datalen,
+			       struct nf_conntrack_expect *exp,
+			       unsigned int matchoff,
+			       unsigned int matchlen);
+
+	unsigned int (*sdp_addr)(struct sk_buff *skb,
+				 unsigned int protoff,
+				 unsigned int dataoff,
+				 const char **dptr,
+				 unsigned int *datalen,
+				 unsigned int sdpoff,
+				 enum sdp_header_types type,
+				 enum sdp_header_types term,
+				 const union nf_inet_addr *addr);
+
+	unsigned int (*sdp_port)(struct sk_buff *skb,
+				 unsigned int protoff,
+				 unsigned int dataoff,
+				 const char **dptr,
+				 unsigned int *datalen,
+				 unsigned int matchoff,
+				 unsigned int matchlen,
+				 u_int16_t port);
+
+	unsigned int (*sdp_session)(struct sk_buff *skb,
+				    unsigned int protoff,
+				    unsigned int dataoff,
+				    const char **dptr,
+				    unsigned int *datalen,
+				    unsigned int sdpoff,
+				    const union nf_inet_addr *addr);
+
+	unsigned int (*sdp_media)(struct sk_buff *skb,
+				  unsigned int protoff,
+				  unsigned int dataoff,
+				  const char **dptr,
+				  unsigned int *datalen,
+				  struct nf_conntrack_expect *rtp_exp,
+				  struct nf_conntrack_expect *rtcp_exp,
+				  unsigned int mediaoff,
+				  unsigned int medialen,
+				  union nf_inet_addr *rtp_addr);
+};
+extern const struct nf_nat_sip_hooks *nf_nat_sip_hooks;
 
 extern int ct_sip_parse_request(const struct nf_conn *ct,
 				const char *dptr, unsigned int datalen,
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 5ed8c441dffd..466410eaa482 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -52,66 +52,8 @@ module_param(sip_direct_media, int, 0600);
 MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling "
 				   "endpoints only (default 1)");
 
-unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int protoff,
-				unsigned int dataoff, const char **dptr,
-				unsigned int *datalen) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_hook);
-
-void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, unsigned int protoff,
-				   s16 off) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook);
-
-unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb,
-				       unsigned int protoff,
-				       unsigned int dataoff,
-				       const char **dptr,
-				       unsigned int *datalen,
-				       struct nf_conntrack_expect *exp,
-				       unsigned int matchoff,
-				       unsigned int matchlen) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sip_expect_hook);
-
-unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int protoff,
-				     unsigned int dataoff,
-				     const char **dptr,
-				     unsigned int *datalen,
-				     unsigned int sdpoff,
-				     enum sdp_header_types type,
-				     enum sdp_header_types term,
-				     const union nf_inet_addr *addr)
-				     __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_addr_hook);
-
-unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int protoff,
-				     unsigned int dataoff,
-				     const char **dptr,
-				     unsigned int *datalen,
-				     unsigned int matchoff,
-				     unsigned int matchlen,
-				     u_int16_t port) __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_port_hook);
-
-unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb,
-					unsigned int protoff,
-					unsigned int dataoff,
-					const char **dptr,
-					unsigned int *datalen,
-					unsigned int sdpoff,
-					const union nf_inet_addr *addr)
-					__read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_session_hook);
-
-unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int protoff,
-				      unsigned int dataoff,
-				      const char **dptr,
-				      unsigned int *datalen,
-				      struct nf_conntrack_expect *rtp_exp,
-				      struct nf_conntrack_expect *rtcp_exp,
-				      unsigned int mediaoff,
-				      unsigned int medialen,
-				      union nf_inet_addr *rtp_addr)
-				      __read_mostly;
-EXPORT_SYMBOL_GPL(nf_nat_sdp_media_hook);
+const struct nf_nat_sip_hooks *nf_nat_sip_hooks;
+EXPORT_SYMBOL_GPL(nf_nat_sip_hooks);
 
 static int string_len(const struct nf_conn *ct, const char *dptr,
 		      const char *limit, int *shift)
@@ -914,8 +856,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 	int direct_rtp = 0, skip_expect = 0, ret = NF_DROP;
 	u_int16_t base_port;
 	__be16 rtp_port, rtcp_port;
-	typeof(nf_nat_sdp_port_hook) nf_nat_sdp_port;
-	typeof(nf_nat_sdp_media_hook) nf_nat_sdp_media;
+	const struct nf_nat_sip_hooks *hooks;
 
 	saddr = NULL;
 	if (sip_direct_media) {
@@ -972,9 +913,9 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 	rtcp_port = htons(base_port + 1);
 
 	if (direct_rtp) {
-		nf_nat_sdp_port = rcu_dereference(nf_nat_sdp_port_hook);
-		if (nf_nat_sdp_port &&
-		    !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen,
+		hooks = rcu_dereference(nf_nat_sip_hooks);
+		if (hooks &&
+		    !hooks->sdp_port(skb, protoff, dataoff, dptr, datalen,
 				     mediaoff, medialen, ntohs(rtp_port)))
 			goto err1;
 	}
@@ -996,10 +937,10 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 	nf_ct_expect_init(rtcp_exp, class, nf_ct_l3num(ct), saddr, daddr,
 			  IPPROTO_UDP, NULL, &rtcp_port);
 
-	nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook);
-	if (nf_nat_sdp_media && ct->status & IPS_NAT_MASK && !direct_rtp)
-		ret = nf_nat_sdp_media(skb, protoff, dataoff, dptr, datalen,
-				       rtp_exp, rtcp_exp,
+	hooks = rcu_dereference(nf_nat_sip_hooks);
+	if (hooks && ct->status & IPS_NAT_MASK && !direct_rtp)
+		ret = hooks->sdp_media(skb, protoff, dataoff, dptr,
+				       datalen, rtp_exp, rtcp_exp,
 				       mediaoff, medialen, daddr);
 	else {
 		if (nf_ct_expect_related(rtp_exp) == 0) {
@@ -1053,13 +994,12 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 	unsigned int caddr_len, maddr_len;
 	unsigned int i;
 	union nf_inet_addr caddr, maddr, rtp_addr;
+	const struct nf_nat_sip_hooks *hooks;
 	unsigned int port;
 	const struct sdp_media_type *t;
 	int ret = NF_ACCEPT;
-	typeof(nf_nat_sdp_addr_hook) nf_nat_sdp_addr;
-	typeof(nf_nat_sdp_session_hook) nf_nat_sdp_session;
 
-	nf_nat_sdp_addr = rcu_dereference(nf_nat_sdp_addr_hook);
+	hooks = rcu_dereference(nf_nat_sip_hooks);
 
 	/* Find beginning of session description */
 	if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen,
@@ -1127,10 +1067,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 		}
 
 		/* Update media connection address if present */
-		if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) {
-			ret = nf_nat_sdp_addr(skb, protoff, dataoff,
+		if (maddr_len && hooks && ct->status & IPS_NAT_MASK) {
+			ret = hooks->sdp_addr(skb, protoff, dataoff,
 					      dptr, datalen, mediaoff,
-					      SDP_HDR_CONNECTION, SDP_HDR_MEDIA,
+					      SDP_HDR_CONNECTION,
+					      SDP_HDR_MEDIA,
 					      &rtp_addr);
 			if (ret != NF_ACCEPT) {
 				nf_ct_helper_log(skb, ct, "cannot mangle SDP");
@@ -1141,10 +1082,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 	}
 
 	/* Update session connection and owner addresses */
-	nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook);
-	if (nf_nat_sdp_session && ct->status & IPS_NAT_MASK)
-		ret = nf_nat_sdp_session(skb, protoff, dataoff,
-					 dptr, datalen, sdpoff, &rtp_addr);
+	hooks = rcu_dereference(nf_nat_sip_hooks);
+	if (hooks && ct->status & IPS_NAT_MASK)
+		ret = hooks->sdp_session(skb, protoff, dataoff,
+					 dptr, datalen, sdpoff,
+					 &rtp_addr);
 
 	return ret;
 }
@@ -1244,11 +1186,11 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 	unsigned int matchoff, matchlen;
 	struct nf_conntrack_expect *exp;
 	union nf_inet_addr *saddr, daddr;
+	const struct nf_nat_sip_hooks *hooks;
 	__be16 port;
 	u8 proto;
 	unsigned int expires = 0;
 	int ret;
-	typeof(nf_nat_sip_expect_hook) nf_nat_sip_expect;
 
 	/* Expected connections can not register again. */
 	if (ct->status & IPS_EXPECTED)
@@ -1311,10 +1253,10 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 	exp->helper = nfct_help(ct)->helper;
 	exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
 
-	nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook);
-	if (nf_nat_sip_expect && ct->status & IPS_NAT_MASK)
-		ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen,
-					exp, matchoff, matchlen);
+	hooks = rcu_dereference(nf_nat_sip_hooks);
+	if (hooks && ct->status & IPS_NAT_MASK)
+		ret = hooks->expect(skb, protoff, dataoff, dptr, datalen,
+				    exp, matchoff, matchlen);
 	else {
 		if (nf_ct_expect_related(exp) != 0) {
 			nf_ct_helper_log(skb, ct, "cannot add expectation");
@@ -1517,7 +1459,7 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct,
 			   unsigned int protoff, unsigned int dataoff,
 			   const char **dptr, unsigned int *datalen)
 {
-	typeof(nf_nat_sip_hook) nf_nat_sip;
+	const struct nf_nat_sip_hooks *hooks;
 	int ret;
 
 	if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0)
@@ -1526,9 +1468,9 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct,
 		ret = process_sip_response(skb, protoff, dataoff, dptr, datalen);
 
 	if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) {
-		nf_nat_sip = rcu_dereference(nf_nat_sip_hook);
-		if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff,
-					      dptr, datalen)) {
+		hooks = rcu_dereference(nf_nat_sip_hooks);
+		if (hooks && !hooks->msg(skb, protoff, dataoff,
+					 dptr, datalen)) {
 			nf_ct_helper_log(skb, ct, "cannot NAT SIP message");
 			ret = NF_DROP;
 		}
@@ -1548,7 +1490,6 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 	s16 diff, tdiff = 0;
 	int ret = NF_ACCEPT;
 	bool term;
-	typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust;
 
 	if (ctinfo != IP_CT_ESTABLISHED &&
 	    ctinfo != IP_CT_ESTABLISHED_REPLY)
@@ -1612,9 +1553,11 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 	}
 
 	if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) {
-		nf_nat_sip_seq_adjust = rcu_dereference(nf_nat_sip_seq_adjust_hook);
-		if (nf_nat_sip_seq_adjust)
-			nf_nat_sip_seq_adjust(skb, protoff, tdiff);
+		const struct nf_nat_sip_hooks *hooks;
+
+		hooks = rcu_dereference(nf_nat_sip_hooks);
+		if (hooks)
+			hooks->seq_adjust(skb, protoff, tdiff);
 	}
 
 	return ret;
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index f9790405b7ff..b4d691db955e 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -625,33 +625,26 @@ static struct nf_ct_helper_expectfn sip_nat = {
 
 static void __exit nf_nat_sip_fini(void)
 {
-	RCU_INIT_POINTER(nf_nat_sip_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL);
-	RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL);
+	RCU_INIT_POINTER(nf_nat_sip_hooks, NULL);
+
 	nf_ct_helper_expectfn_unregister(&sip_nat);
 	synchronize_rcu();
 }
 
+static const struct nf_nat_sip_hooks sip_hooks = {
+	.msg		= nf_nat_sip,
+	.seq_adjust	= nf_nat_sip_seq_adjust,
+	.expect		= nf_nat_sip_expect,
+	.sdp_addr	= nf_nat_sdp_addr,
+	.sdp_port	= nf_nat_sdp_port,
+	.sdp_session	= nf_nat_sdp_session,
+	.sdp_media	= nf_nat_sdp_media,
+};
+
 static int __init nf_nat_sip_init(void)
 {
-	BUG_ON(nf_nat_sip_hook != NULL);
-	BUG_ON(nf_nat_sip_seq_adjust_hook != NULL);
-	BUG_ON(nf_nat_sip_expect_hook != NULL);
-	BUG_ON(nf_nat_sdp_addr_hook != NULL);
-	BUG_ON(nf_nat_sdp_port_hook != NULL);
-	BUG_ON(nf_nat_sdp_session_hook != NULL);
-	BUG_ON(nf_nat_sdp_media_hook != NULL);
-	RCU_INIT_POINTER(nf_nat_sip_hook, nf_nat_sip);
-	RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, nf_nat_sip_seq_adjust);
-	RCU_INIT_POINTER(nf_nat_sip_expect_hook, nf_nat_sip_expect);
-	RCU_INIT_POINTER(nf_nat_sdp_addr_hook, nf_nat_sdp_addr);
-	RCU_INIT_POINTER(nf_nat_sdp_port_hook, nf_nat_sdp_port);
-	RCU_INIT_POINTER(nf_nat_sdp_session_hook, nf_nat_sdp_session);
-	RCU_INIT_POINTER(nf_nat_sdp_media_hook, nf_nat_sdp_media);
+	BUG_ON(nf_nat_sip_hooks != NULL);
+	RCU_INIT_POINTER(nf_nat_sip_hooks, &sip_hooks);
 	nf_ct_helper_expectfn_register(&sip_nat);
 	return 0;
 }
-- 
cgit 


From 7d65f4a6553203da6a22097821d151fbbe7e4956 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 5 Sep 2013 15:49:45 +0200
Subject: irq: Consolidate do_softirq() arch overriden implementations

All arch overriden implementations of do_softirq() share the following
common code: disable irqs (to avoid races with the pending check),
check if there are softirqs pending, then execute __do_softirq() on
a specific stack.

Consolidate the common parts such that archs only worry about the
stack switch.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@au1.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@au1.ibm.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: James E.J. Bottomley <jejb@parisc-linux.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 arch/metag/kernel/irq.c    | 52 ++++++++++++++++--------------------------
 arch/parisc/kernel/irq.c   | 17 ++------------
 arch/powerpc/kernel/irq.c  | 17 +-------------
 arch/s390/kernel/irq.c     | 52 +++++++++++++++++-------------------------
 arch/sh/kernel/irq.c       | 57 +++++++++++++++++-----------------------------
 arch/sparc/kernel/irq_64.c | 31 ++++++++-----------------
 arch/x86/kernel/entry_64.S |  4 ++--
 arch/x86/kernel/irq_32.c   | 30 +++++++-----------------
 arch/x86/kernel/irq_64.c   | 21 -----------------
 include/linux/interrupt.h  | 11 +++++++++
 kernel/softirq.c           |  8 +++----
 11 files changed, 98 insertions(+), 202 deletions(-)

(limited to 'include')

diff --git a/arch/metag/kernel/irq.c b/arch/metag/kernel/irq.c
index 2a2c9d55187e..3b4b7f6c0950 100644
--- a/arch/metag/kernel/irq.c
+++ b/arch/metag/kernel/irq.c
@@ -159,44 +159,30 @@ void irq_ctx_exit(int cpu)
 
 extern asmlinkage void __do_softirq(void);
 
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags;
 	struct thread_info *curctx;
 	union irq_ctx *irqctx;
 	u32 *isp;
 
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending()) {
-		curctx = current_thread_info();
-		irqctx = softirq_ctx[smp_processor_id()];
-		irqctx->tinfo.task = curctx->task;
-
-		/* build the stack frame on the softirq stack */
-		isp = (u32 *) ((char *)irqctx + sizeof(struct thread_info));
-
-		asm volatile (
-			"MOV   D0.5,%0\n"
-			"SWAP  A0StP,D0.5\n"
-			"CALLR D1RtP,___do_softirq\n"
-			"MOV   A0StP,D0.5\n"
-			:
-			: "r" (isp)
-			: "memory", "cc", "D1Ar1", "D0Ar2", "D1Ar3", "D0Ar4",
-			  "D1Ar5", "D0Ar6", "D0Re0", "D1Re0", "D0.4", "D1RtP",
-			  "D0.5"
-			);
-		/*
-		 * Shouldn't happen, we returned above if in_interrupt():
-		 */
-		WARN_ON_ONCE(softirq_count());
-	}
-
-	local_irq_restore(flags);
+	curctx = current_thread_info();
+	irqctx = softirq_ctx[smp_processor_id()];
+	irqctx->tinfo.task = curctx->task;
+
+	/* build the stack frame on the softirq stack */
+	isp = (u32 *) ((char *)irqctx + sizeof(struct thread_info));
+
+	asm volatile (
+		"MOV   D0.5,%0\n"
+		"SWAP  A0StP,D0.5\n"
+		"CALLR D1RtP,___do_softirq\n"
+		"MOV   A0StP,D0.5\n"
+		:
+		: "r" (isp)
+		: "memory", "cc", "D1Ar1", "D0Ar2", "D1Ar3", "D0Ar4",
+		  "D1Ar5", "D0Ar6", "D0Re0", "D1Re0", "D0.4", "D1RtP",
+		  "D0.5"
+		);
 }
 #endif
 
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 2e6443b1e922..ef5927685299 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -499,22 +499,9 @@ static void execute_on_irq_stack(void *func, unsigned long param1)
 	*irq_stack_in_use = 1;
 }
 
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	__u32 pending;
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	pending = local_softirq_pending();
-
-	if (pending)
-		execute_on_irq_stack(__do_softirq, 0);
-
-	local_irq_restore(flags);
+	execute_on_irq_stack(__do_softirq, 0);
 }
 #endif /* CONFIG_IRQSTACKS */
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 57d286a78f86..5c4adfc6a6d0 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -593,7 +593,7 @@ void irq_ctx_init(void)
 	}
 }
 
-static inline void do_softirq_onstack(void)
+void do_softirq_own_stack(void)
 {
 	struct thread_info *curtp, *irqtp;
 
@@ -611,21 +611,6 @@ static inline void do_softirq_onstack(void)
 		set_bits(irqtp->flags, &curtp->flags);
 }
 
-void do_softirq(void)
-{
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending())
-		do_softirq_onstack();
-
-	local_irq_restore(flags);
-}
-
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(virq);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 8ac2097f13d4..bb27a262c44a 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -157,39 +157,29 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 /*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags, old, new;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending()) {
-		/* Get current stack pointer. */
-		asm volatile("la %0,0(15)" : "=a" (old));
-		/* Check against async. stack address range. */
-		new = S390_lowcore.async_stack;
-		if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {
-			/* Need to switch to the async. stack. */
-			new -= STACK_FRAME_OVERHEAD;
-			((struct stack_frame *) new)->back_chain = old;
-
-			asm volatile("   la    15,0(%0)\n"
-				     "   basr  14,%2\n"
-				     "   la    15,0(%1)\n"
-				     : : "a" (new), "a" (old),
-				         "a" (__do_softirq)
-				     : "0", "1", "2", "3", "4", "5", "14",
-				       "cc", "memory" );
-		} else {
-			/* We are already on the async stack. */
-			__do_softirq();
-		}
+	unsigned long old, new;
+
+	/* Get current stack pointer. */
+	asm volatile("la %0,0(15)" : "=a" (old));
+	/* Check against async. stack address range. */
+	new = S390_lowcore.async_stack;
+	if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {
+		/* Need to switch to the async. stack. */
+		new -= STACK_FRAME_OVERHEAD;
+		((struct stack_frame *) new)->back_chain = old;
+		asm volatile("   la    15,0(%0)\n"
+			     "   basr  14,%2\n"
+			     "   la    15,0(%1)\n"
+			     : : "a" (new), "a" (old),
+			         "a" (__do_softirq)
+			     : "0", "1", "2", "3", "4", "5", "14",
+			       "cc", "memory" );
+	} else {
+		/* We are already on the async stack. */
+		__do_softirq();
 	}
-
-	local_irq_restore(flags);
 }
 
 /*
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 063af10ff3c1..0833736afa32 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -149,47 +149,32 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags;
 	struct thread_info *curctx;
 	union irq_ctx *irqctx;
 	u32 *isp;
 
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending()) {
-		curctx = current_thread_info();
-		irqctx = softirq_ctx[smp_processor_id()];
-		irqctx->tinfo.task = curctx->task;
-		irqctx->tinfo.previous_sp = current_stack_pointer;
-
-		/* build the stack frame on the softirq stack */
-		isp = (u32 *)((char *)irqctx + sizeof(*irqctx));
-
-		__asm__ __volatile__ (
-			"mov	r15, r9		\n"
-			"jsr	@%0		\n"
-			/* switch to the softirq stack */
-			" mov	%1, r15		\n"
-			/* restore the thread stack */
-			"mov	r9, r15		\n"
-			: /* no outputs */
-			: "r" (__do_softirq), "r" (isp)
-			: "memory", "r0", "r1", "r2", "r3", "r4",
-			  "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
-		);
-
-		/*
-		 * Shouldn't happen, we returned above if in_interrupt():
-		 */
-		WARN_ON_ONCE(softirq_count());
-	}
-
-	local_irq_restore(flags);
+	curctx = current_thread_info();
+	irqctx = softirq_ctx[smp_processor_id()];
+	irqctx->tinfo.task = curctx->task;
+	irqctx->tinfo.previous_sp = current_stack_pointer;
+
+	/* build the stack frame on the softirq stack */
+	isp = (u32 *)((char *)irqctx + sizeof(*irqctx));
+
+	__asm__ __volatile__ (
+		"mov	r15, r9		\n"
+		"jsr	@%0		\n"
+		/* switch to the softirq stack */
+		" mov	%1, r15		\n"
+		/* restore the thread stack */
+		"mov	r9, r15		\n"
+		: /* no outputs */
+		: "r" (__do_softirq), "r" (isp)
+		: "memory", "r0", "r1", "r2", "r3", "r4",
+		  "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
+	);
 }
 #else
 static inline void handle_one_irq(unsigned int irq)
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d4840cec2c55..666193f4e8bb 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -698,30 +698,19 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
+	void *orig_sp, *sp = softirq_stack[smp_processor_id()];
 
-	if (local_softirq_pending()) {
-		void *orig_sp, *sp = softirq_stack[smp_processor_id()];
-
-		sp += THREAD_SIZE - 192 - STACK_BIAS;
-
-		__asm__ __volatile__("mov %%sp, %0\n\t"
-				     "mov %1, %%sp"
-				     : "=&r" (orig_sp)
-				     : "r" (sp));
-		__do_softirq();
-		__asm__ __volatile__("mov %0, %%sp"
-				     : : "r" (orig_sp));
-	}
+	sp += THREAD_SIZE - 192 - STACK_BIAS;
 
-	local_irq_restore(flags);
+	__asm__ __volatile__("mov %%sp, %0\n\t"
+			     "mov %1, %%sp"
+			     : "=&r" (orig_sp)
+			     : "r" (sp));
+	__do_softirq();
+	__asm__ __volatile__("mov %0, %%sp"
+			     : : "r" (orig_sp));
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b077f4cc225a..083da7c2f40d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1342,7 +1342,7 @@ bad_gs:
 	.previous
 
 /* Call softirq on interrupt stack. Interrupts are off. */
-ENTRY(call_softirq)
+ENTRY(do_softirq_own_stack)
 	CFI_STARTPROC
 	pushq_cfi %rbp
 	CFI_REL_OFFSET rbp,0
@@ -1359,7 +1359,7 @@ ENTRY(call_softirq)
 	decl PER_CPU_VAR(irq_count)
 	ret
 	CFI_ENDPROC
-END(call_softirq)
+END(do_softirq_own_stack)
 
 #ifdef CONFIG_XEN
 zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 4186755f1d7c..8a5bb01dbc0e 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -149,35 +149,21 @@ void irq_ctx_init(int cpu)
 	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
 }
 
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
 {
-	unsigned long flags;
 	struct thread_info *curctx;
 	union irq_ctx *irqctx;
 	u32 *isp;
 
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	if (local_softirq_pending()) {
-		curctx = current_thread_info();
-		irqctx = __this_cpu_read(softirq_ctx);
-		irqctx->tinfo.task = curctx->task;
-		irqctx->tinfo.previous_esp = current_stack_pointer;
-
-		/* build the stack frame on the softirq stack */
-		isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+	curctx = current_thread_info();
+	irqctx = __this_cpu_read(softirq_ctx);
+	irqctx->tinfo.task = curctx->task;
+	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-		call_on_stack(__do_softirq, isp);
-		/*
-		 * Shouldn't happen, we returned above if in_interrupt():
-		 */
-		WARN_ON_ONCE(softirq_count());
-	}
+	/* build the stack frame on the softirq stack */
+	isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
 
-	local_irq_restore(flags);
+	call_on_stack(__do_softirq, isp);
 }
 
 bool handle_irq(unsigned irq, struct pt_regs *regs)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index d04d3ecded62..4d1c746892eb 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -87,24 +87,3 @@ bool handle_irq(unsigned irq, struct pt_regs *regs)
 	generic_handle_irq_desc(irq, desc);
 	return true;
 }
-
-
-extern void call_softirq(void);
-
-asmlinkage void do_softirq(void)
-{
-	__u32 pending;
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-	pending = local_softirq_pending();
-	/* Switch to interrupt stack */
-	if (pending) {
-		call_softirq();
-		WARN_ON_ONCE(softirq_count());
-	}
-	local_irq_restore(flags);
-}
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5e865b554940..c9e831dc80bc 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -19,6 +19,7 @@
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
+#include <asm/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -374,6 +375,16 @@ struct softirq_action
 
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
+
+#ifdef __ARCH_HAS_DO_SOFTIRQ
+void do_softirq_own_stack(void);
+#else
+static inline void do_softirq_own_stack(void)
+{
+	__do_softirq();
+}
+#endif
+
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d7d498d8cc4f..26ee72725d29 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -29,7 +29,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/irq.h>
 
-#include <asm/irq.h>
 /*
    - No shared variables, all the data are CPU local.
    - If a softirq needs serialization, let it serialize itself
@@ -283,7 +282,7 @@ restart:
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-#ifndef __ARCH_HAS_DO_SOFTIRQ
+
 
 asmlinkage void do_softirq(void)
 {
@@ -298,13 +297,12 @@ asmlinkage void do_softirq(void)
 	pending = local_softirq_pending();
 
 	if (pending)
-		__do_softirq();
+		do_softirq_own_stack();
 
+	WARN_ON_ONCE(softirq_count());
 	local_irq_restore(flags);
 }
 
-#endif
-
 /*
  * Enter an interrupt context.
  */
-- 
cgit 


From 91cb498e6a34b429a032f8cfbb57dde28cd20e0c Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 4 Sep 2013 20:57:48 +0200
Subject: netfilter: cttimeout: allow to set/get default protocol timeouts

Default timeouts are currently set via proc/sysctl interface, the
typical pattern is a file name like:

/proc/sys/net/netfilter/nf_conntrack_PROTOCOL_timeout_STATE

This results in one entry per default protocol state timeout.
This patch simplifies this by allowing to set default protocol
timeouts via cttimeout netlink interface.

This should allow us to get rid of the existing proc/sysctl code
in the midterm.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nfnetlink_cttimeout.h |   2 +
 net/netfilter/nfnetlink_cttimeout.c                | 161 ++++++++++++++++++++-
 2 files changed, 155 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
index a2810a7c5e30..1ab0b97b3a1e 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
@@ -6,6 +6,8 @@ enum ctnl_timeout_msg_types {
 	IPCTNL_MSG_TIMEOUT_NEW,
 	IPCTNL_MSG_TIMEOUT_GET,
 	IPCTNL_MSG_TIMEOUT_DELETE,
+	IPCTNL_MSG_TIMEOUT_DEFAULT_SET,
+	IPCTNL_MSG_TIMEOUT_DEFAULT_GET,
 
 	IPCTNL_MSG_TIMEOUT_MAX
 };
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 50580494148d..476accd17145 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -49,10 +49,8 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = {
 };
 
 static int
-ctnl_timeout_parse_policy(struct ctnl_timeout *timeout,
-			  struct nf_conntrack_l4proto *l4proto,
-			  struct net *net,
-			  const struct nlattr *attr)
+ctnl_timeout_parse_policy(void *timeouts, struct nf_conntrack_l4proto *l4proto,
+			  struct net *net, const struct nlattr *attr)
 {
 	int ret = 0;
 
@@ -64,8 +62,7 @@ ctnl_timeout_parse_policy(struct ctnl_timeout *timeout,
 		if (ret < 0)
 			return ret;
 
-		ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net,
-							  &timeout->data);
+		ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts);
 	}
 	return ret;
 }
@@ -123,7 +120,8 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
 				goto err_proto_put;
 			}
 
-			ret = ctnl_timeout_parse_policy(matching, l4proto, net,
+			ret = ctnl_timeout_parse_policy(&matching->data,
+							l4proto, net,
 							cda[CTA_TIMEOUT_DATA]);
 			return ret;
 		}
@@ -138,7 +136,7 @@ cttimeout_new_timeout(struct sock *ctnl, struct sk_buff *skb,
 		goto err_proto_put;
 	}
 
-	ret = ctnl_timeout_parse_policy(timeout, l4proto, net,
+	ret = ctnl_timeout_parse_policy(&timeout->data, l4proto, net,
 					cda[CTA_TIMEOUT_DATA]);
 	if (ret < 0)
 		goto err;
@@ -342,6 +340,147 @@ cttimeout_del_timeout(struct sock *ctnl, struct sk_buff *skb,
 	return ret;
 }
 
+static int
+cttimeout_default_set(struct sock *ctnl, struct sk_buff *skb,
+		      const struct nlmsghdr *nlh,
+		      const struct nlattr * const cda[])
+{
+	__u16 l3num;
+	__u8 l4num;
+	struct nf_conntrack_l4proto *l4proto;
+	struct net *net = sock_net(skb->sk);
+	unsigned int *timeouts;
+	int ret;
+
+	if (!cda[CTA_TIMEOUT_L3PROTO] ||
+	    !cda[CTA_TIMEOUT_L4PROTO] ||
+	    !cda[CTA_TIMEOUT_DATA])
+		return -EINVAL;
+
+	l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO]));
+	l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
+	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+	/* This protocol is not supported, skip. */
+	if (l4proto->l4proto != l4num) {
+		ret = -EOPNOTSUPP;
+		goto err;
+	}
+
+	timeouts = l4proto->get_timeouts(net);
+
+	ret = ctnl_timeout_parse_policy(timeouts, l4proto, net,
+					cda[CTA_TIMEOUT_DATA]);
+	if (ret < 0)
+		goto err;
+
+	nf_ct_l4proto_put(l4proto);
+	return 0;
+err:
+	nf_ct_l4proto_put(l4proto);
+	return ret;
+}
+
+static int
+cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
+			    u32 seq, u32 type, int event,
+			    struct nf_conntrack_l4proto *l4proto)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	unsigned int flags = portid ? NLM_F_MULTI : 0;
+
+	event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family = AF_UNSPEC;
+	nfmsg->version = NFNETLINK_V0;
+	nfmsg->res_id = 0;
+
+	if (nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(l4proto->l3proto)) ||
+	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto))
+		goto nla_put_failure;
+
+	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
+		struct nlattr *nest_parms;
+		unsigned int *timeouts = l4proto->get_timeouts(net);
+		int ret;
+
+		nest_parms = nla_nest_start(skb,
+					    CTA_TIMEOUT_DATA | NLA_F_NESTED);
+		if (!nest_parms)
+			goto nla_put_failure;
+
+		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts);
+		if (ret < 0)
+			goto nla_put_failure;
+
+		nla_nest_end(skb, nest_parms);
+	}
+
+	nlmsg_end(skb, nlh);
+	return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -1;
+}
+
+static int cttimeout_default_get(struct sock *ctnl, struct sk_buff *skb,
+				 const struct nlmsghdr *nlh,
+				 const struct nlattr * const cda[])
+{
+	__u16 l3num;
+	__u8 l4num;
+	struct nf_conntrack_l4proto *l4proto;
+	struct net *net = sock_net(skb->sk);
+	struct sk_buff *skb2;
+	int ret, err;
+
+	if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO])
+		return -EINVAL;
+
+	l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO]));
+	l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
+	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+	/* This protocol is not supported, skip. */
+	if (l4proto->l4proto != l4num) {
+		err = -EOPNOTSUPP;
+		goto err;
+	}
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	ret = cttimeout_default_fill_info(net, skb2, NETLINK_CB(skb).portid,
+					  nlh->nlmsg_seq,
+					  NFNL_MSG_TYPE(nlh->nlmsg_type),
+					  IPCTNL_MSG_TIMEOUT_DEFAULT_SET,
+					  l4proto);
+	if (ret <= 0) {
+		kfree_skb(skb2);
+		err = -ENOMEM;
+		goto err;
+	}
+	ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT);
+	if (ret > 0)
+		ret = 0;
+
+	/* this avoids a loop in nfnetlink. */
+	return ret == -EAGAIN ? -ENOBUFS : ret;
+err:
+	nf_ct_l4proto_put(l4proto);
+	return err;
+}
+
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 static struct ctnl_timeout *ctnl_timeout_find_get(const char *name)
 {
@@ -384,6 +523,12 @@ static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = {
 	[IPCTNL_MSG_TIMEOUT_DELETE]	= { .call = cttimeout_del_timeout,
 					    .attr_count = CTA_TIMEOUT_MAX,
 					    .policy = cttimeout_nla_policy },
+	[IPCTNL_MSG_TIMEOUT_DEFAULT_SET]= { .call = cttimeout_default_set,
+					    .attr_count = CTA_TIMEOUT_MAX,
+					    .policy = cttimeout_nla_policy },
+	[IPCTNL_MSG_TIMEOUT_DEFAULT_GET]= { .call = cttimeout_default_get,
+					    .attr_count = CTA_TIMEOUT_MAX,
+					    .policy = cttimeout_nla_policy },
 };
 
 static const struct nfnetlink_subsystem cttimeout_subsys = {
-- 
cgit 


From cb2ffb26e67ef89c44f46e971440cda2f83ae236 Mon Sep 17 00:00:00 2001
From: Tom Gundersen <teg@jklm.no>
Date: Mon, 9 Sep 2013 20:18:27 +0200
Subject: cuse: add fix minor number to /dev/cuse

This allows udev (or more recently systemd-tmpfiles) to create /dev/cuse on
boot, in the same way as /dev/fuse is currently created, and the corresponding
module to be loaded on first access.

The corresponding functionalty was introduced for fuse in commit 578454f.

Signed-off-by: Tom Gundersen <teg@jklm.no>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 Documentation/devices.txt  | 1 +
 fs/fuse/cuse.c             | 5 ++++-
 include/linux/miscdevice.h | 1 +
 3 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 23721d3be3e6..80b72419ffd8 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -414,6 +414,7 @@ Your cooperation is appreciated.
 		200 = /dev/net/tun	TAP/TUN network device
 		201 = /dev/button/gulpb	Transmeta GULP-B buttons
 		202 = /dev/emd/ctl	Enhanced Metadisk RAID (EMD) control
+		203 = /dev/cuse		Cuse (character device in user-space)
 		204 = /dev/video/em8300		EM8300 DVD decoder control
 		205 = /dev/video/em8300_mv	EM8300 DVD decoder video
 		206 = /dev/video/em8300_ma	EM8300 DVD decoder audio
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index adbfd66b380f..24da581cb52b 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -589,11 +589,14 @@ static struct attribute *cuse_class_dev_attrs[] = {
 ATTRIBUTE_GROUPS(cuse_class_dev);
 
 static struct miscdevice cuse_miscdev = {
-	.minor		= MISC_DYNAMIC_MINOR,
+	.minor		= CUSE_MINOR,
 	.name		= "cuse",
 	.fops		= &cuse_channel_fops,
 };
 
+MODULE_ALIAS_MISCDEV(CUSE_MINOR);
+MODULE_ALIAS("devname:cuse");
+
 static int __init cuse_init(void)
 {
 	int i, rc;
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 09c2300ddb37..c8cf093d8b71 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -31,6 +31,7 @@
 #define I2O_MINOR		166
 #define MICROCODE_MINOR		184
 #define TUN_MINOR		200
+#define CUSE_MINOR		203
 #define MWAVE_MINOR		219	/* ACP/Mwave Modem */
 #define MPT_MINOR		220
 #define MPT2SAS_MINOR		221
-- 
cgit 


From 1df3a401154add23826d714c808204633b3b1c31 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 18 Sep 2013 18:13:00 +0100
Subject: HID: Delay opening HID device

Don't call hid_open_device till there is actually an user. This saves
power by not opening underlying transport for HID. Also close device
if there are no active mfd client using HID sensor hub.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/hid/hid-sensor-hub.c   | 45 ++++++++++++++++++++++++++++++++----------
 include/linux/hid-sensor-hub.h | 18 +++++++++++++++++
 2 files changed, 53 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 10e1581022cf..88fc5aefcd96 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -465,6 +465,39 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 	return 1;
 }
 
+int sensor_hub_device_open(struct hid_sensor_hub_device *hsdev)
+{
+	int ret = 0;
+	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
+
+	mutex_lock(&data->mutex);
+	if (!hsdev->ref_cnt) {
+		ret = hid_hw_open(hsdev->hdev);
+		if (ret) {
+			hid_err(hsdev->hdev, "failed to open hid device\n");
+			mutex_unlock(&data->mutex);
+			return ret;
+		}
+	}
+	hsdev->ref_cnt++;
+	mutex_unlock(&data->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sensor_hub_device_open);
+
+void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev)
+{
+	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
+
+	mutex_lock(&data->mutex);
+	hsdev->ref_cnt--;
+	if (!hsdev->ref_cnt)
+		hid_hw_close(hsdev->hdev);
+	mutex_unlock(&data->mutex);
+}
+EXPORT_SYMBOL_GPL(sensor_hub_device_close);
+
 static int sensor_hub_probe(struct hid_device *hdev,
 				const struct hid_device_id *id)
 {
@@ -506,12 +539,6 @@ static int sensor_hub_probe(struct hid_device *hdev,
 		hid_err(hdev, "hw start failed\n");
 		return ret;
 	}
-	ret = hid_hw_open(hdev);
-	if (ret) {
-		hid_err(hdev, "failed to open input interrupt pipe\n");
-		goto err_stop_hw;
-	}
-
 	INIT_LIST_HEAD(&sd->dyn_callback_list);
 	sd->hid_sensor_client_cnt = 0;
 	report_enum = &hdev->report_enum[HID_INPUT_REPORT];
@@ -520,7 +547,7 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	if (dev_cnt > HID_MAX_PHY_DEVICES) {
 		hid_err(hdev, "Invalid Physical device count\n");
 		ret = -EINVAL;
-		goto err_close;
+		goto err_stop_hw;
 	}
 	sd->hid_sensor_hub_client_devs = kzalloc(dev_cnt *
 						sizeof(struct mfd_cell),
@@ -528,7 +555,7 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	if (sd->hid_sensor_hub_client_devs == NULL) {
 		hid_err(hdev, "Failed to allocate memory for mfd cells\n");
 			ret = -ENOMEM;
-			goto err_close;
+			goto err_stop_hw;
 	}
 	list_for_each_entry(report, &report_enum->report_list, list) {
 		hid_dbg(hdev, "Report id:%x\n", report->id);
@@ -565,8 +592,6 @@ err_free_names:
 	for (i = 0; i < sd->hid_sensor_client_cnt ; ++i)
 		kfree(sd->hid_sensor_hub_client_devs[i].name);
 	kfree(sd->hid_sensor_hub_client_devs);
-err_close:
-	hid_hw_close(hdev);
 err_stop_hw:
 	hid_hw_stop(hdev);
 
diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h
index 32ba45158d39..a265af294ea4 100644
--- a/include/linux/hid-sensor-hub.h
+++ b/include/linux/hid-sensor-hub.h
@@ -47,11 +47,13 @@ struct hid_sensor_hub_attribute_info {
  * @hdev:		Stores the hid instance.
  * @vendor_id:		Vendor id of hub device.
  * @product_id:		Product id of hub device.
+ * @ref_cnt:		Number of MFD clients have opened this device
  */
 struct hid_sensor_hub_device {
 	struct hid_device *hdev;
 	u32 vendor_id;
 	u32 product_id;
+	int ref_cnt;
 };
 
 /**
@@ -74,6 +76,22 @@ struct hid_sensor_hub_callbacks {
 			 void *priv);
 };
 
+/**
+* sensor_hub_device_open() - Open hub device
+* @hsdev:	Hub device instance.
+*
+* Used to open hid device for sensor hub.
+*/
+int sensor_hub_device_open(struct hid_sensor_hub_device *hsdev);
+
+/**
+* sensor_hub_device_clode() - Close hub device
+* @hsdev:	Hub device instance.
+*
+* Used to clode hid device for sensor hub.
+*/
+void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev);
+
 /* Registration functions */
 
 /**
-- 
cgit 


From 90051ea774613ffc6b8aad3dc665c8505d6205a8 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Wed, 25 Sep 2013 12:17:18 -0400
Subject: SUNRPC: Clean up - convert xprt_prepare_transmit to return a bool

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/sunrpc/xprt.h |  2 +-
 net/sunrpc/clnt.c           |  6 ++----
 net/sunrpc/xprt.c           | 15 +++++++++------
 3 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index cec7b9b5e1bf..8097b9df6773 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -288,7 +288,7 @@ int			xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 int			xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
-int			xprt_prepare_transmit(struct rpc_task *task);
+bool			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
 void			xprt_end_transmit(struct rpc_task *task);
 int			xprt_adjust_timeout(struct rpc_rqst *req);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 77479606a971..fa50e42aabd3 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1722,8 +1722,7 @@ call_transmit(struct rpc_task *task)
 	task->tk_action = call_status;
 	if (task->tk_status < 0)
 		return;
-	task->tk_status = xprt_prepare_transmit(task);
-	if (task->tk_status != 0)
+	if (!xprt_prepare_transmit(task))
 		return;
 	task->tk_action = call_transmit_status;
 	/* Encode here so that rpcsec_gss can use correct sequence number. */
@@ -1811,8 +1810,7 @@ call_bc_transmit(struct rpc_task *task)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 
-	task->tk_status = xprt_prepare_transmit(task);
-	if (task->tk_status == -EAGAIN) {
+	if (!xprt_prepare_transmit(task)) {
 		/*
 		 * Could not reserve the transport. Try again after the
 		 * transport is released.
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 8cc5c8bcad7f..2326af57b9b9 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -864,24 +864,27 @@ static inline int xprt_has_timer(struct rpc_xprt *xprt)
  * @task: RPC task about to send a request
  *
  */
-int xprt_prepare_transmit(struct rpc_task *task)
+bool xprt_prepare_transmit(struct rpc_task *task)
 {
 	struct rpc_rqst	*req = task->tk_rqstp;
 	struct rpc_xprt	*xprt = req->rq_xprt;
-	int err = 0;
+	bool ret = false;
 
 	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);
 
 	spin_lock_bh(&xprt->transport_lock);
 	if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) {
-		err = req->rq_reply_bytes_recvd;
+		task->tk_status = req->rq_reply_bytes_recvd;
 		goto out_unlock;
 	}
-	if (!xprt->ops->reserve_xprt(xprt, task))
-		err = -EAGAIN;
+	if (!xprt->ops->reserve_xprt(xprt, task)) {
+		task->tk_status = -EAGAIN;
+		goto out_unlock;
+	}
+	ret = true;
 out_unlock:
 	spin_unlock_bh(&xprt->transport_lock);
-	return err;
+	return ret;
 }
 
 void xprt_end_transmit(struct rpc_task *task)
-- 
cgit 


From 8a19a0b6cb2e2216afd68ef2047f30260cc8a220 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Tue, 24 Sep 2013 12:00:27 -0400
Subject: SUNRPC: Add RPC task and client level options to disable the resend
 timeout

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/sunrpc/clnt.h  |  2 ++
 include/linux/sunrpc/sched.h |  1 +
 net/sunrpc/clnt.c            |  5 ++++-
 net/sunrpc/xprt.c            | 15 ++++++++++++---
 4 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 6740801aa71a..943ee895f2d1 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -49,6 +49,7 @@ struct rpc_clnt {
 
 	unsigned int		cl_softrtry : 1,/* soft timeouts */
 				cl_discrtry : 1,/* disconnect before retry */
+				cl_noretranstimeo: 1,/* No retransmit timeouts */
 				cl_autobind : 1,/* use getport() */
 				cl_chatty   : 1;/* be verbose */
 
@@ -126,6 +127,7 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_QUIET		(1UL << 6)
 #define RPC_CLNT_CREATE_INFINITE_SLOTS	(1UL << 7)
 #define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT	(1UL << 8)
+#define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 096ee58be11a..3a847de83fab 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -122,6 +122,7 @@ struct rpc_task_setup {
 #define RPC_TASK_SENT		0x0800		/* message was sent */
 #define RPC_TASK_TIMEOUT	0x1000		/* fail with ETIMEDOUT on timeout */
 #define RPC_TASK_NOCONNECT	0x2000		/* return ENOTCONN if not connected */
+#define RPC_TASK_NO_RETRANS_TIMEOUT	0x4000		/* wait forever for a reply */
 
 #define RPC_IS_ASYNC(t)		((t)->tk_flags & RPC_TASK_ASYNC)
 #define RPC_IS_SWAPPER(t)	((t)->tk_flags & RPC_TASK_SWAPPER)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index fa50e42aabd3..b58525009e40 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -772,6 +772,8 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
 		atomic_inc(&clnt->cl_count);
 		if (clnt->cl_softrtry)
 			task->tk_flags |= RPC_TASK_SOFT;
+		if (clnt->cl_noretranstimeo)
+			task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
 		if (sk_memalloc_socks()) {
 			struct rpc_xprt *xprt;
 
@@ -1898,7 +1900,8 @@ call_status(struct rpc_task *task)
 		rpc_delay(task, 3*HZ);
 	case -ETIMEDOUT:
 		task->tk_action = call_timeout;
-		if (task->tk_client->cl_discrtry)
+		if (!(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT)
+		    && task->tk_client->cl_discrtry)
 			xprt_conditional_disconnect(req->rq_xprt,
 					req->rq_connect_cookie);
 		break;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2326af57b9b9..d166d9947e36 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -873,9 +873,18 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);
 
 	spin_lock_bh(&xprt->transport_lock);
-	if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) {
-		task->tk_status = req->rq_reply_bytes_recvd;
-		goto out_unlock;
+	if (!req->rq_bytes_sent) {
+		if (req->rq_reply_bytes_recvd) {
+			task->tk_status = req->rq_reply_bytes_recvd;
+			goto out_unlock;
+		}
+		if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT)
+		    && xprt_connected(xprt)
+		    && req->rq_connect_cookie == xprt->connect_cookie) {
+			xprt->ops->set_retrans_timeout(task);
+			rpc_sleep_on(&xprt->pending, task, xprt_timer);
+			goto out_unlock;
+		}
 	}
 	if (!xprt->ops->reserve_xprt(xprt, task)) {
 		task->tk_status = -EAGAIN;
-- 
cgit 


From 99875249bfbfb6d9a2aba020ce65da2862d0dafa Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Tue, 24 Sep 2013 12:06:07 -0400
Subject: NFSv4: Ensure that we disable the resend timeout for NFSv4

The spec states that the client should not resend requests because
the server will disconnect if it needs to drop an RPC request.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/client.c           | 2 ++
 fs/nfs/nfs4client.c       | 1 +
 include/linux/nfs_fs_sb.h | 1 +
 3 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2dceee4db076..af0325864df6 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -590,6 +590,8 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 
 	if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_DISCRTRY;
+	if (test_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags))
+		args.flags |= RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT;
 	if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 	if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index a860ab566d6e..511cdce6ecf2 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -368,6 +368,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	if (clp->cl_minorversion != 0)
 		__set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
 	if (error == -EINVAL)
 		error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b8cedced50c9..f9c0a6cb41e9 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -41,6 +41,7 @@ struct nfs_client {
 #define NFS_CS_DISCRTRY		1		/* - disconnect on RPC retry */
 #define NFS_CS_MIGRATION	2		/* - transparent state migr */
 #define NFS_CS_INFINITE_SLOTS	3		/* - don't limit TCP slots */
+#define NFS_CS_NO_RETRANS_TIMEOUT	4	/* - Disable retransmit timeouts */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
-- 
cgit 


From a59ac2f7447d8a4202f29ade1af785212d12b1d1 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 1 Oct 2013 22:59:21 -0700
Subject: Bluetooth: Replace BDADDR_LOCAL with BDADDR_NONE

The BDADDR_LOCAL is a relict from userspace and has never been used
within the kernel. So remove that constant and replace it with a new
BDADDR_NONE that is similar to HCI_DEV_NONE with all bits set.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index afbc711ba37a..5fd510675cfa 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -197,8 +197,8 @@ static inline bool bdaddr_type_is_le(__u8 type)
 	return false;
 }
 
-#define BDADDR_ANY   (&(bdaddr_t) {{0, 0, 0, 0, 0, 0} })
-#define BDADDR_LOCAL (&(bdaddr_t) {{0, 0, 0, 0xff, 0xff, 0xff} })
+#define BDADDR_ANY  (&(bdaddr_t) {{0, 0, 0, 0, 0, 0}})
+#define BDADDR_NONE (&(bdaddr_t) {{0xff, 0xff, 0xff, 0xff, 0xff, 0xff}})
 
 /* Copy, swap, convert BD Address */
 static inline int bacmp(const bdaddr_t *ba1, const bdaddr_t *ba2)
-- 
cgit 


From 848566b381e72b07e41beffde677955ae1498153 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 1 Oct 2013 22:59:22 -0700
Subject: Bluetooth: Provide high speed configuration option

Hiding the Bluetooth high speed support behind a module parameter is
not really useful. This can be enabled and disabled at runtime via
the management interface. This also has the advantage that this can
now be changed per controller and not just global.

This patch removes the module parameter and exposes the high speed
setting of the management interface to all controllers.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/hci_core.c      |  6 ------
 net/bluetooth/l2cap_core.c    | 35 +++++++++++++++++++----------------
 net/bluetooth/l2cap_sock.c    | 10 ----------
 net/bluetooth/mgmt.c          | 11 ++---------
 5 files changed, 22 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1a966afbbfa8..f141b5f6e4f1 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -564,6 +564,7 @@ struct l2cap_conn {
 
 	__u32			feat_mask;
 	__u8			fixed_chan_mask;
+	bool			hs_enabled;
 
 	__u8			info_state;
 	__u8			info_ident;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index dd2528c5b6bc..750c360f96db 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1222,12 +1222,6 @@ int hci_dev_open(__u16 dev)
 		ret = hdev->setup(hdev);
 
 	if (!ret) {
-		/* Treat all non BR/EDR controllers as raw devices if
-		 * enable_hs is not set.
-		 */
-		if (hdev->dev_type != HCI_BREDR && !enable_hs)
-			set_bit(HCI_RAW, &hdev->flags);
-
 		if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
 			set_bit(HCI_RAW, &hdev->flags);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index d1f1e78d1140..6d42498e862b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1016,13 +1016,12 @@ static bool __amp_capable(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
 
-	if (enable_hs &&
-	    hci_amp_capable() &&
+	if (conn->hs_enabled && hci_amp_capable() &&
 	    chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED &&
 	    conn->fixed_chan_mask & L2CAP_FC_A2MP)
 		return true;
-	else
-		return false;
+
+	return false;
 }
 
 static bool l2cap_check_efs(struct l2cap_chan *chan)
@@ -1638,6 +1637,10 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	conn->feat_mask = 0;
 
+	if (hcon->type == ACL_LINK)
+		conn->hs_enabled = test_bit(HCI_HS_ENABLED,
+					    &hcon->hdev->dev_flags);
+
 	spin_lock_init(&conn->lock);
 	mutex_init(&conn->chan_lock);
 
@@ -3084,14 +3087,14 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask)
 	}
 }
 
-static inline bool __l2cap_ews_supported(struct l2cap_chan *chan)
+static inline bool __l2cap_ews_supported(struct l2cap_conn *conn)
 {
-	return enable_hs && chan->conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
+	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_WINDOW;
 }
 
-static inline bool __l2cap_efs_supported(struct l2cap_chan *chan)
+static inline bool __l2cap_efs_supported(struct l2cap_conn *conn)
 {
-	return enable_hs && chan->conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
+	return conn->hs_enabled && conn->feat_mask & L2CAP_FEAT_EXT_FLOW;
 }
 
 static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
@@ -3135,7 +3138,7 @@ static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
 static inline void l2cap_txwin_setup(struct l2cap_chan *chan)
 {
 	if (chan->tx_win > L2CAP_DEFAULT_TX_WINDOW &&
-	    __l2cap_ews_supported(chan)) {
+	    __l2cap_ews_supported(chan->conn)) {
 		/* use extended control field */
 		set_bit(FLAG_EXT_CTRL, &chan->flags);
 		chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW;
@@ -3165,7 +3168,7 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data)
 		if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state))
 			break;
 
-		if (__l2cap_efs_supported(chan))
+		if (__l2cap_efs_supported(chan->conn))
 			set_bit(FLAG_EFS_ENABLE, &chan->flags);
 
 		/* fall through */
@@ -3317,7 +3320,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
 			break;
 
 		case L2CAP_CONF_EWS:
-			if (!enable_hs)
+			if (!chan->conn->hs_enabled)
 				return -ECONNREFUSED;
 
 			set_bit(FLAG_EXT_CTRL, &chan->flags);
@@ -3349,7 +3352,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data)
 		}
 
 		if (remote_efs) {
-			if (__l2cap_efs_supported(chan))
+			if (__l2cap_efs_supported(chan->conn))
 				set_bit(FLAG_EFS_ENABLE, &chan->flags);
 			else
 				return -ECONNREFUSED;
@@ -4303,7 +4306,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		if (!disable_ertm)
 			feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING
 				| L2CAP_FEAT_FCS;
-		if (enable_hs)
+		if (conn->hs_enabled)
 			feat_mask |= L2CAP_FEAT_EXT_FLOW
 				| L2CAP_FEAT_EXT_WINDOW;
 
@@ -4314,7 +4317,7 @@ static inline int l2cap_information_req(struct l2cap_conn *conn,
 		u8 buf[12];
 		struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf;
 
-		if (enable_hs)
+		if (conn->hs_enabled)
 			l2cap_fixed_chan[0] |= L2CAP_FC_A2MP;
 		else
 			l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP;
@@ -4411,7 +4414,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
 	if (cmd_len != sizeof(*req))
 		return -EPROTO;
 
-	if (!enable_hs)
+	if (!conn->hs_enabled)
 		return -EINVAL;
 
 	psm = le16_to_cpu(req->psm);
@@ -4838,7 +4841,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 
 	BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id);
 
-	if (!enable_hs)
+	if (!conn->hs_enabled)
 		return -EINVAL;
 
 	chan = l2cap_get_chan_by_dcid(conn, icid);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index c85537ca1a23..9119898ef040 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -445,11 +445,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_CHANNEL_POLICY:
-		if (!enable_hs) {
-			err = -ENOPROTOOPT;
-			break;
-		}
-
 		if (put_user(chan->chan_policy, (u32 __user *) optval))
 			err = -EFAULT;
 		break;
@@ -720,11 +715,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case BT_CHANNEL_POLICY:
-		if (!enable_hs) {
-			err = -ENOPROTOOPT;
-			break;
-		}
-
 		if (get_user(opt, (u32 __user *) optval)) {
 			err = -EFAULT;
 			break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1b5b10fab545..dd15491f2374 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -32,8 +32,6 @@
 #include <net/bluetooth/mgmt.h>
 #include <net/bluetooth/smp.h>
 
-bool enable_hs;
-
 #define MGMT_VERSION	1
 #define MGMT_REVISION	3
 
@@ -380,10 +378,8 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 		settings |= MGMT_SETTING_DISCOVERABLE;
 		settings |= MGMT_SETTING_BREDR;
 		settings |= MGMT_SETTING_LINK_SECURITY;
-	}
-
-	if (enable_hs)
 		settings |= MGMT_SETTING_HS;
+	}
 
 	if (lmp_le_capable(hdev)) {
 		settings |= MGMT_SETTING_LE;
@@ -1344,7 +1340,7 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!enable_hs)
+	if (!lmp_bredr_capable(hdev))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -4396,6 +4392,3 @@ int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 	return mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, hdev, &ev, sizeof(ev),
 			  cmd ? cmd->sk : NULL);
 }
-
-module_param(enable_hs, bool, 0644);
-MODULE_PARM_DESC(enable_hs, "Enable High Speed support");
-- 
cgit 


From 3713c0cfd06fa49729a12929a7ee8b7ad48f3c02 Mon Sep 17 00:00:00 2001
From: Soren Brinkmann <soren.brinkmann@xilinx.com>
Date: Wed, 18 Sep 2013 11:48:35 -0700
Subject: clockchips: Add FEAT_PERCPU clockevent flag

Add the flag CLOCK_EVT_FEAT_PERCPU which is supposed to be set for per
cpu clockevent devices.

Signed-off-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Michal Simek <michal.simek@xilinx.com>
---
 include/linux/clockchips.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 0857922e8ad0..493aa021c7a9 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -60,6 +60,7 @@ enum clock_event_mode {
  * Core shall set the interrupt affinity dynamically in broadcast mode
  */
 #define CLOCK_EVT_FEAT_DYNIRQ		0x000020
+#define CLOCK_EVT_FEAT_PERCPU		0x000040
 
 /**
  * struct clock_event_device - clock event device descriptor
-- 
cgit 


From 56f8790102f48a4959a729ecdccff332591014e1 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 2 Oct 2013 13:43:13 +0300
Subject: Bluetooth: Introduce a new HCI_BREDR_ENABLED flag

To allow treating dual-mode (BR/EDR/LE) controllers as single-mode ones
(LE-only) we want to introduce a new HCI_BREDR_ENABLED flag to track
whether BR/EDR is enabled or not (previously we simply looked at the
feature bit with lmp_bredr_enabled).

This patch add the new flag and updates the relevant places to test
against it instead of using lmp_bredr_enabled. The flag is by default
enabled when registering an adapter and only cleared if necessary once
the local features have been read during the HCI init procedure.

We cannot completely block BR/EDR usage in case user space uses raw HCI
sockets but the patch tries to block this in places where possible, such
as the various BR/EDR specific ioctls.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/hci_conn.c    |  3 +++
 net/bluetooth/hci_core.c    | 21 +++++++++++++++++++--
 net/bluetooth/mgmt.c        | 24 +++++++++++++-----------
 4 files changed, 36 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 7ede2666dc75..4fa08d7b997d 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -122,6 +122,7 @@ enum {
 	HCI_LINK_SECURITY,
 	HCI_PERIODIC_INQ,
 	HCI_FAST_CONNECTABLE,
+	HCI_BREDR_ENABLED,
 };
 
 /* A mask for the flags that are supposed to remain when a reset happens
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d2380e0c7df0..514148b7a66b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -581,6 +581,9 @@ static struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
 {
 	struct hci_conn *acl;
 
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+		return ERR_PTR(-ENOTSUPP);
+
 	acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
 	if (!acl) {
 		acl = hci_conn_add(hdev, ACL_LINK, dst);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 7cbdd33d9b38..14df032543b2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -519,6 +519,8 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 
 	if (lmp_bredr_capable(hdev))
 		bredr_setup(req);
+	else
+		clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
 
 	if (lmp_le_capable(hdev))
 		le_setup(req);
@@ -1034,6 +1036,11 @@ int hci_inquiry(void __user *arg)
 		goto done;
 	}
 
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+
 	hci_dev_lock(hdev);
 	if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX ||
 	    inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) {
@@ -1101,7 +1108,7 @@ static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
 	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
 		flags |= LE_AD_GENERAL;
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		flags |= LE_AD_NO_BREDR;
 
 	if (lmp_le_br_capable(hdev))
@@ -1493,6 +1500,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 		goto done;
 	}
 
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+		err = -EOPNOTSUPP;
+		goto done;
+	}
+
 	switch (cmd) {
 	case HCISETAUTH:
 		err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt,
@@ -2318,8 +2330,13 @@ int hci_register_dev(struct hci_dev *hdev)
 
 	set_bit(HCI_SETUP, &hdev->dev_flags);
 
-	if (hdev->dev_type != HCI_AMP)
+	if (hdev->dev_type != HCI_AMP) {
 		set_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+		/* Assume BR/EDR support until proven otherwise (such as
+		 * through reading supported features during init.
+		 */
+		set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+	}
 
 	write_lock(&hci_dev_list_lock);
 	list_add(&hdev->list, &hci_dev_list);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ad3862949a2c..e1c41b0b7a75 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -408,7 +408,7 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (test_bit(HCI_PAIRABLE, &hdev->dev_flags))
 		settings |= MGMT_SETTING_PAIRABLE;
 
-	if (lmp_bredr_capable(hdev))
+	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		settings |= MGMT_SETTING_BREDR;
 
 	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
@@ -929,7 +929,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_DISCOVERABLE,
 				 MGMT_STATUS_NOT_SUPPORTED);
 
@@ -1085,7 +1085,7 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_CONNECTABLE,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -1208,7 +1208,7 @@ static int set_link_security(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_LINK_SECURITY,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -1342,7 +1342,7 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -1409,7 +1409,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 				  MGMT_STATUS_INVALID_PARAMS);
 
 	/* LE-only devices do not allow toggling LE on/off */
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_LE,
 				  MGMT_STATUS_REJECTED);
 
@@ -1720,7 +1720,7 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev))
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_DEV_CLASS,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -2803,7 +2803,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_BREDR:
-		if (!lmp_bredr_capable(hdev)) {
+		if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
 			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
 					 MGMT_STATUS_NOT_SUPPORTED);
 			mgmt_pending_remove(cmd);
@@ -2835,7 +2835,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 		}
 
 		if (hdev->discovery.type == DISCOV_TYPE_INTERLEAVED &&
-		    !lmp_bredr_capable(hdev)) {
+		    !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
 			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
 					 MGMT_STATUS_NOT_SUPPORTED);
 			mgmt_pending_remove(cmd);
@@ -3282,7 +3282,8 @@ static int set_fast_connectable(struct sock *sk, struct hci_dev *hdev,
 
 	BT_DBG("%s", hdev->name);
 
-	if (!lmp_bredr_capable(hdev) || hdev->hci_ver < BLUETOOTH_VER_1_2)
+	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags) ||
+	    hdev->hci_ver < BLUETOOTH_VER_1_2)
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_FAST_CONNECTABLE,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -3646,7 +3647,8 @@ static int powered_update_hci(struct hci_dev *hdev)
 			    sizeof(link_sec), &link_sec);
 
 	if (lmp_bredr_capable(hdev)) {
-		set_bredr_scan(&req);
+		if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
+			set_bredr_scan(&req);
 		update_class(&req);
 		update_name(&req);
 		update_eir(&req);
-- 
cgit 


From 0663ca2a032eea12480a8f86fe08bef9d72f8faf Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 2 Oct 2013 13:43:14 +0300
Subject: Bluetooth: Add a new mgmt_set_bredr command

This patch introduces a new mgmt command for enabling/disabling BR/EDR
functionality. This can be convenient when one wants to make a dual-mode
controller behave like a single-mode one. The command is only available
for dual-mode controllers and requires that LE is enabled before using
it. The BR/EDR setting can be enabled at any point, however disabling it
requires the controller to be powered off (otherwise a "rejected"
response will be sent).

Disabling the BR/EDR setting will automatically disable all other BR/EDR
related settings.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h |   2 +
 net/bluetooth/hci_event.c    |   5 ++
 net/bluetooth/mgmt.c         | 120 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 421d7633a91f..7347df800a2e 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -354,6 +354,8 @@ struct mgmt_cp_set_device_id {
 
 #define MGMT_OP_SET_ADVERTISING		0x0029
 
+#define MGMT_OP_SET_BREDR		0x002A
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d171c04bddbd..4785ab0795f5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -297,6 +297,11 @@ static void hci_cc_write_scan_enable(struct hci_dev *hdev, struct sk_buff *skb)
 		goto done;
 	}
 
+	/* We need to ensure that we set this back on if someone changed
+	 * the scan mode through a raw HCI socket.
+	 */
+	set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
 	old_pscan = test_and_clear_bit(HCI_PSCAN, &hdev->flags);
 	old_iscan = test_and_clear_bit(HCI_ISCAN, &hdev->flags);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index e1c41b0b7a75..dcce0cf1d7cc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -75,6 +75,7 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_UNBLOCK_DEVICE,
 	MGMT_OP_SET_DEVICE_ID,
 	MGMT_OP_SET_ADVERTISING,
+	MGMT_OP_SET_BREDR,
 };
 
 static const u16 mgmt_events[] = {
@@ -3337,6 +3338,121 @@ unlock:
 	return err;
 }
 
+static void set_bredr_complete(struct hci_dev *hdev, u8 status)
+{
+	struct pending_cmd *cmd;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = mgmt_pending_find(MGMT_OP_SET_BREDR, hdev);
+	if (!cmd)
+		goto unlock;
+
+	if (status) {
+		u8 mgmt_err = mgmt_status(status);
+
+		/* We need to restore the flag if related HCI commands
+		 * failed.
+		 */
+		clear_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+		cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+	} else {
+		send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev);
+		new_settings(hdev, cmd->sk);
+	}
+
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
+{
+	struct mgmt_mode *cp = data;
+	struct pending_cmd *cmd;
+	struct hci_request req;
+	int err;
+
+	BT_DBG("request for %s", hdev->name);
+
+	if (!lmp_bredr_capable(hdev) || !lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				  MGMT_STATUS_REJECTED);
+
+	if (cp->val != 0x00 && cp->val != 0x01)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	if (cp->val == test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+		err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
+		goto unlock;
+	}
+
+	if (!hdev_is_powered(hdev)) {
+		if (!cp->val) {
+			clear_bit(HCI_CONNECTABLE, &hdev->dev_flags);
+			clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+			clear_bit(HCI_SSP_ENABLED, &hdev->dev_flags);
+			clear_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
+			clear_bit(HCI_FAST_CONNECTABLE, &hdev->dev_flags);
+			clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
+		}
+
+		change_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+		err = send_settings_rsp(sk, MGMT_OP_SET_BREDR, hdev);
+		if (err < 0)
+			goto unlock;
+
+		err = new_settings(hdev, sk);
+		goto unlock;
+	}
+
+	/* Reject disabling when powered on */
+	if (!cp->val) {
+		err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				 MGMT_STATUS_REJECTED);
+		goto unlock;
+	}
+
+	if (mgmt_pending_find(MGMT_OP_SET_BREDR, hdev)) {
+		err = cmd_status(sk, hdev->id, MGMT_OP_SET_BREDR,
+				 MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_BREDR, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	/* We need to flip the bit already here so that hci_update_ad
+	 * generates the correct flags.
+	 */
+	set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
+
+	hci_req_init(&req, hdev);
+	hci_update_ad(&req);
+	err = hci_req_run(&req, set_bredr_complete);
+	if (err < 0)
+		mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
 static bool ltk_is_valid(struct mgmt_ltk_info *key)
 {
 	if (key->authenticated != 0x00 && key->authenticated != 0x01)
@@ -3452,6 +3568,7 @@ static const struct mgmt_handler {
 	{ unblock_device,         false, MGMT_UNBLOCK_DEVICE_SIZE },
 	{ set_device_id,          false, MGMT_SET_DEVICE_ID_SIZE },
 	{ set_advertising,        false, MGMT_SETTING_SIZE },
+	{ set_bredr,              false, MGMT_SETTING_SIZE },
 };
 
 
@@ -3633,6 +3750,9 @@ static int powered_update_hci(struct hci_dev *hdev)
 		    cp.simul != lmp_host_le_br_capable(hdev))
 			hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED,
 				    sizeof(cp), &cp);
+
+		/* In case BR/EDR was toggled during the AUTO_OFF phase */
+		hci_update_ad(&req);
 	}
 
 	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
-- 
cgit 


From d13eafce2c892d57f1eb243e43dfe48b4626006d Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 2 Oct 2013 04:41:30 -0700
Subject: Bluetooth: Add management command for setting static address

On dual-mode BR/EDR/LE and LE only controllers it is possible
to configure a random address. There are two types or random
addresses, one is static and the other private. Since the
random private addresses require special privacy feature to
be supported, the configuration of these two are kept separate.

This command allows for setting the static random address. It is
only supported on controllers with LE support. The static random
address is suppose to be valid for the lifetime of the controller
or at least until the next power cycle. To ensure such behavior,
setting of the address is limited to when the controller is
powered off.

The special BDADDR_ANY address (00:00:00:00:00:00) can be used to
disable the static address. This is also the default value.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h      |  2 ++
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/mgmt.h     |  6 +++++
 net/bluetooth/mgmt.c             | 49 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4fa08d7b997d..d7fd825ed2ce 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -978,6 +978,8 @@ struct hci_rp_le_read_local_features {
 	__u8     features[8];
 } __packed;
 
+#define HCI_OP_LE_SET_RANDOM_ADDR	0x2005
+
 #define HCI_OP_LE_READ_ADV_TX_POWER	0x2007
 struct hci_rp_le_read_adv_tx_power {
 	__u8	status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 26cc9f7858cd..e09c30577b3a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -140,6 +140,7 @@ struct hci_dev {
 	__u8		bus;
 	__u8		dev_type;
 	bdaddr_t	bdaddr;
+	bdaddr_t	static_addr;
 	__u8		dev_name[HCI_MAX_NAME_LENGTH];
 	__u8		short_name[HCI_MAX_SHORT_NAME_LENGTH];
 	__u8		eir[HCI_MAX_EIR_LENGTH];
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 7347df800a2e..2ad433bb9a2e 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -356,6 +356,12 @@ struct mgmt_cp_set_device_id {
 
 #define MGMT_OP_SET_BREDR		0x002A
 
+#define MGMT_OP_SET_STATIC_ADDRESS	0x002B
+struct mgmt_cp_set_static_address {
+	bdaddr_t bdaddr;
+} __packed;
+#define MGMT_SET_STATIC_ADDRESS_SIZE	6
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 4ac31695946b..b87163238c10 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -76,6 +76,7 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_SET_DEVICE_ID,
 	MGMT_OP_SET_ADVERTISING,
 	MGMT_OP_SET_BREDR,
+	MGMT_OP_SET_STATIC_ADDRESS,
 };
 
 static const u16 mgmt_events[] = {
@@ -3247,6 +3248,46 @@ unlock:
 	return err;
 }
 
+static int set_static_address(struct sock *sk, struct hci_dev *hdev,
+			      void *data, u16 len)
+{
+	struct mgmt_cp_set_static_address *cp = data;
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	if (hdev_is_powered(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS,
+				  MGMT_STATUS_REJECTED);
+
+	if (bacmp(&cp->bdaddr, BDADDR_ANY)) {
+		if (!bacmp(&cp->bdaddr, BDADDR_NONE))
+			return cmd_status(sk, hdev->id,
+					  MGMT_OP_SET_STATIC_ADDRESS,
+					  MGMT_STATUS_INVALID_PARAMS);
+
+		/* Two most significant bits shall be set */
+		if ((cp->bdaddr.b[5] & 0xc0) != 0xc0)
+			return cmd_status(sk, hdev->id,
+					  MGMT_OP_SET_STATIC_ADDRESS,
+					  MGMT_STATUS_INVALID_PARAMS);
+	}
+
+	hci_dev_lock(hdev);
+
+	bacpy(&hdev->static_addr, &cp->bdaddr);
+
+	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_STATIC_ADDRESS, 0, NULL, 0);
+
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -3576,6 +3617,7 @@ static const struct mgmt_handler {
 	{ set_device_id,          false, MGMT_SET_DEVICE_ID_SIZE },
 	{ set_advertising,        false, MGMT_SETTING_SIZE },
 	{ set_bredr,              false, MGMT_SETTING_SIZE },
+	{ set_static_address,     false, MGMT_SET_STATIC_ADDRESS_SIZE },
 };
 
 
@@ -3762,6 +3804,13 @@ static int powered_update_hci(struct hci_dev *hdev)
 		hci_update_ad(&req);
 	}
 
+	if (lmp_le_capable(hdev)) {
+		/* Set random address to static address if configured */
+		if (bacmp(&hdev->static_addr, BDADDR_ANY))
+			hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
+				    &hdev->static_addr);
+	}
+
 	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
 		u8 adv = 0x01;
 
-- 
cgit 


From 7578d57520f51093f590d68e16965e2714e69747 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Sun, 1 Sep 2013 17:15:51 +0300
Subject: mac80211: implement STA CSA for drivers using channel contexts

Limit the current implementation to a single channel context used by
a single vif, thereby avoiding multi-vif/channel complexities.

Reuse the main function from AP CSA code, but move a portion out in
order to fit the STA scenario.

Add a new mac80211 HW flag so we don't break devices that don't support
channel switch with channel-contexts. The new behavior will be opt-in.

Signed-off-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  6 ++++++
 net/mac80211/cfg.c     |  5 +++++
 net/mac80211/chan.c    |  5 -----
 net/mac80211/mlme.c    | 57 +++++++++++++++++++++++++++++++++++++-------------
 4 files changed, 54 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index da8011920b65..f386c480e134 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1502,6 +1502,11 @@ struct ieee80211_tx_control {
  *
  * @IEEE80211_HW_TIMING_BEACON_ONLY: Use sync timing from beacon frames
  *	only, to allow getting TBTT of a DTIM beacon.
+ *
+ * @IEEE80211_HW_CHANCTX_STA_CSA: Support 802.11h based channel-switch (CSA)
+ *	for a single active channel while using channel contexts. When support
+ *	is not enabled the default action is to disconnect when getting the
+ *	CSA frame.
  */
 enum ieee80211_hw_flags {
 	IEEE80211_HW_HAS_RATE_CONTROL			= 1<<0,
@@ -1532,6 +1537,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF		= 1<<25,
 	IEEE80211_HW_TIMING_BEACON_ONLY			= 1<<26,
 	IEEE80211_HW_SUPPORTS_HT_CCK_RATES		= 1<<27,
+	IEEE80211_HW_CHANCTX_STA_CSA			= 1<<28,
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b455e7264f4f..ac28af74a414 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2871,6 +2871,11 @@ void ieee80211_csa_finalize_work(struct work_struct *work)
 	if (WARN_ON(err < 0))
 		return;
 
+	if (!local->use_chanctx) {
+		local->_oper_chandef = local->csa_chandef;
+		ieee80211_hw_config(local, 0);
+	}
+
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	switch (sdata->vif.type) {
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 3a4764b2869e..03ba6b5c5373 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -453,11 +453,6 @@ int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 	chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL;
 	drv_change_chanctx(local, ctx, chanctx_changed);
 
-	if (!local->use_chanctx) {
-		local->_oper_chandef = *chandef;
-		ieee80211_hw_config(local, 0);
-	}
-
 	ieee80211_recalc_chanctx_chantype(local, ctx);
 	ieee80211_recalc_smps_chanctx(local, ctx);
 	ieee80211_recalc_radar_chanctx(local, ctx);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 9fce0f49cd10..91cc8281e266 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -876,6 +876,8 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 		container_of(work, struct ieee80211_sub_if_data, u.mgd.chswitch_work);
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u32 changed = 0;
+	int ret;
 
 	if (!ieee80211_sdata_running(sdata))
 		return;
@@ -884,24 +886,39 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	if (!ifmgd->associated)
 		goto out;
 
-	local->_oper_chandef = local->csa_chandef;
+	ret = ieee80211_vif_change_channel(sdata, &local->csa_chandef,
+					   &changed);
+	if (ret) {
+		sdata_info(sdata,
+			   "vif channel switch failed, disconnecting\n");
+		ieee80211_queue_work(&sdata->local->hw,
+				     &ifmgd->csa_connection_drop_work);
+		goto out;
+	}
 
-	if (!local->ops->channel_switch) {
-		/* call "hw_config" only if doing sw channel switch */
-		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
-	} else {
-		/* update the device channel directly */
-		local->hw.conf.chandef = local->_oper_chandef;
+	if (!local->use_chanctx) {
+		local->_oper_chandef = local->csa_chandef;
+		/* Call "hw_config" only if doing sw channel switch.
+		 * Otherwise update the channel directly
+		 */
+		if (!local->ops->channel_switch)
+			ieee80211_hw_config(local, 0);
+		else
+			local->hw.conf.chandef = local->_oper_chandef;
 	}
 
 	/* XXX: shouldn't really modify cfg80211-owned data! */
-	ifmgd->associated->channel = local->_oper_chandef.chan;
+	ifmgd->associated->channel = local->csa_chandef.chan;
 
 	/* XXX: wait for a beacon first? */
 	ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
+
+	ieee80211_bss_info_change_notify(sdata, changed);
+
  out:
+	sdata->vif.csa_active = false;
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
 	sdata_unlock(sdata);
 }
@@ -983,17 +1000,28 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED;
+	sdata->vif.csa_active = true;
 
+	mutex_lock(&local->chanctx_mtx);
 	if (local->use_chanctx) {
-		sdata_info(sdata,
-			   "not handling channel switch with channel contexts\n");
-		ieee80211_queue_work(&local->hw,
-				     &ifmgd->csa_connection_drop_work);
-		return;
+		u32 num_chanctx = 0;
+		list_for_each_entry(chanctx, &local->chanctx_list, list)
+		       num_chanctx++;
+
+		if (num_chanctx > 1 ||
+		    !(local->hw.flags & IEEE80211_HW_CHANCTX_STA_CSA)) {
+			sdata_info(sdata,
+				   "not handling chan-switch with channel contexts\n");
+			ieee80211_queue_work(&local->hw,
+					     &ifmgd->csa_connection_drop_work);
+			mutex_unlock(&local->chanctx_mtx);
+			return;
+		}
 	}
 
-	mutex_lock(&local->chanctx_mtx);
 	if (WARN_ON(!rcu_access_pointer(sdata->vif.chanctx_conf))) {
+		ieee80211_queue_work(&local->hw,
+				     &ifmgd->csa_connection_drop_work);
 		mutex_unlock(&local->chanctx_mtx);
 		return;
 	}
@@ -1955,6 +1983,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
 			       true, frame_buf);
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
+	sdata->vif.csa_active = false;
 	ieee80211_wake_queues_by_reason(&sdata->local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
-- 
cgit 


From 2b2b614dd24e4e6474fcf2dcf69c95c908838959 Mon Sep 17 00:00:00 2001
From: Zoltan Kiss <zoltan.kiss@citrix.com>
Date: Wed, 4 Sep 2013 21:11:05 +0100
Subject: tracing/events: Add bounce tracing to swiotbl

Ftrace is currently not able to detect when SWIOTLB has to do double buffering.
Under Xen you can only see it indirectly in function_graph, when
xen_swiotlb_map_page() doesn't stop after range_straddles_page_boundary(), but
calls spinlock functions, memcpy() and xen_phys_to_bus() as well. This patch
introduces the swiotlb:swiotlb_bounced event, which also prints out the
following informations to help you find out why bouncing happened:

dev_name: 0000:08:00.0 dma_mask=ffffffffffffffff dev_addr=9149f000 size=32768
swiotlb_force=0

If you use Xen, and (dev_addr + size + 1) > dma_mask, the buffer is out of the
device's DMA range. If swiotlb_force == 1, you should really change the kernel
parameters. Otherwise, the buffer is not contiguous in mfn space.

Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
[v1: Don't print 'swiotlb_force=X', just print swiotlb_force if it is enabled]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/xen/swiotlb-xen.c      |  5 +++++
 include/trace/events/swiotlb.h | 46 ++++++++++++++++++++++++++++++++++++++++++
 lib/swiotlb.c                  |  4 ++++
 3 files changed, 55 insertions(+)
 create mode 100644 include/trace/events/swiotlb.h

(limited to 'include')

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1b2277c311d2..b31081007a81 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -42,6 +42,9 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/swiotlb.h>
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
@@ -358,6 +361,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
+	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+
 	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h
new file mode 100644
index 000000000000..7ea4c5e7c448
--- /dev/null
+++ b/include/trace/events/swiotlb.h
@@ -0,0 +1,46 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM swiotlb
+
+#if !defined(_TRACE_SWIOTLB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SWIOTLB_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(swiotlb_bounced,
+
+	TP_PROTO(struct device *dev,
+		 dma_addr_t dev_addr,
+		 size_t size,
+		 int swiotlb_force),
+
+	TP_ARGS(dev, dev_addr, size, swiotlb_force),
+
+	TP_STRUCT__entry(
+		__string(	dev_name,	dev_name(dev)	)
+		__field(	u64,	dma_mask		)
+		__field(	dma_addr_t,	dev_addr	)
+		__field(	size_t,	size			)
+		__field(	int,	swiotlb_force		)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(dev));
+		__entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0);
+		__entry->dev_addr = dev_addr;
+		__entry->size = size;
+		__entry->swiotlb_force = swiotlb_force;
+	),
+
+	TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx "
+		"size=%zu %s",
+		__get_str(dev_name),
+		__entry->dma_mask,
+		(unsigned long long)__entry->dev_addr,
+		__entry->size,
+		__entry->swiotlb_force ? "swiotlb_force" : "" )
+);
+
+#endif /*  _TRACE_SWIOTLB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 4e8686c7e5a4..f0d841907da6 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -38,6 +38,8 @@
 #include <linux/bootmem.h>
 #include <linux/iommu-helper.h>
 
+#include <trace/events/swiotlb.h>
+
 #define OFFSET(val,align) ((unsigned long)	\
 	                   ( (val) & ( (align) - 1)))
 
@@ -726,6 +728,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
 		return dev_addr;
 
+	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+
 	/* Oh well, have to allocate and map a bounce buffer. */
 	map = map_single(dev, phys, size, dir);
 	if (map == SWIOTLB_MAP_ERROR) {
-- 
cgit 


From d0bf75a51b172fdd9dd90bfa03c0f5de473b6c94 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:46 +0900
Subject: Bluetooth: Add the definition and structure for Set Reserved LT_ADDR

The Set_Reserved_LT_ADDR command allows the host to request that the
BR/EDR Controller reserve a specific LT_ADDR for Connectionless Slave
Broadcast.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 90

"7.3.86 Set Reserved LT_ADDR Command [New Section]
...
If the LT_ADDR indicated in the LT_ADDR parameter is already in use by the
BR/EDR Controller, it shall return the ACL Connection Already Exists (0x0B)
error code. If the LT_ADDR indicated in the LT_ADDR parameter is out of
range, the controller shall return the Invalid HCI Command Parameters (0x12)
error code. If the command succeeds, then the reserved LT_ADDR shall be
used when issuing subsequent Set Connectionless Slave Broadcast Data and
Set Connectionless Slave Broadcast commands.
To ensure that the reserved LT_ADDR is not already allocated, it is
recommended that this command be issued at some point after HCI_Reset is
issued but before page scanning is enabled or paging is initiated."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index d7fd825ed2ce..4d88809da3f6 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -839,6 +839,15 @@ struct hci_cp_write_le_host_supported {
 	__u8	simul;
 } __packed;
 
+#define HCI_OP_SET_RESERVED_LT_ADDR	0x0c74
+struct hci_cp_set_reserved_lt_addr {
+	__u8	lt_addr;
+} __packed;
+struct hci_rp_set_reserved_lt_addr {
+	__u8	status;
+	__u8	lt_addr;
+} __packed;
+
 #define HCI_OP_READ_SYNC_TRAIN_PARAMS	0x0c77
 
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
-- 
cgit 


From 6a20eaf40419481dd55031ffe7a856e7a304ca4d Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:47 +0900
Subject: Bluetooth: Add the definition and structure for Delete Reserved
 LT_ADDR

The Delete_Reserved_LT_ADDR command requests that the BR/EDR
Controller cancel the reservation for a specific LT_ADDR reserved for the
purposes of Connectionless Slave Broadcast.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 92

"7.3.87 Delete Reserved LT_ADDR Command [New Section]
...
If the LT_ADDR indicated in the LT_ADDR parameter is not reserved by the
BR/EDR Controller, it shall return the Unknown Connection Identifier (0x02)
error code.
If connectionless slave broadcast mode is still active, then the Controller
shall return the Command Disallowed (0x0C) error code."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4d88809da3f6..9b071f162dde 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -848,6 +848,15 @@ struct hci_rp_set_reserved_lt_addr {
 	__u8	lt_addr;
 } __packed;
 
+#define HCI_OP_DELETE_RESERVED_LT_ADDR	0x0c75
+struct hci_cp_delete_reserved_lt_addr {
+	__u8	lt_addr;
+} __packed;
+struct hci_rp_delete_reserved_lt_addr {
+	__u8	status;
+	__u8	lt_addr;
+} __packed;
+
 #define HCI_OP_READ_SYNC_TRAIN_PARAMS	0x0c77
 
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
-- 
cgit 


From 7d1dab49f645557bb0b9246f7ae87fafd2716e70 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:48 +0900
Subject: Bluetooth: Add the definition and structure for Set CSB Data

The Set_Connectionless_Slave_Broadcast_Data command provides the
ability for the Host to set Connectionless Slave Broadcast data in
the BR/EDR Controller.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 93

"7.3.88 Set Connectionless Slave Broadcast Data Command [New Section]
...
If connectionless slave broadcast mode is disabled, this data shall be
kept by the BR/EDR Controller and used once connectionless slave broadcast
mode is enabled. If connectionless slave broadcast mode is enabled,
and this command is successful, this data will be sent starting with
the next Connectionless Slave Broadcast instant.

The Data_Length field may be zero, in which case no data needs to be
provided.

The Host may fragment the data using the Fragment field in the command. If
the combined length of the fragments exceeds the capacity of the largest
allowed packet size specified in the Set Connectionless Slave Broadcast
command, all fragments associated with the data being assembled shall be
discarded and the Invalid HCI Command Parameters error (0x12) shall be
returned."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 9b071f162dde..d9e0a8467ddc 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -35,6 +35,8 @@
 
 #define HCI_MAX_AMP_ASSOC_SIZE	672
 
+#define HCI_MAX_CSB_DATA_SIZE	252
+
 /* HCI dev events */
 #define HCI_DEV_REG			1
 #define HCI_DEV_UNREG			2
@@ -857,6 +859,18 @@ struct hci_rp_delete_reserved_lt_addr {
 	__u8	lt_addr;
 } __packed;
 
+#define HCI_OP_SET_CSB_DATA		0x0c76
+struct hci_cp_set_csb_data {
+	__u8	lt_addr;
+	__u8	fragment;
+	__u8	data_length;
+	__u8	data[HCI_MAX_CSB_DATA_SIZE];
+} __packed;
+struct hci_rp_set_csb_data {
+	__u8	status;
+	__u8	lt_addr;
+} __packed;
+
 #define HCI_OP_READ_SYNC_TRAIN_PARAMS	0x0c77
 
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
-- 
cgit 


From a9b07a643f16332c4cc96259ef5cad2163f8e28a Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:49 +0900
Subject: Bluetooth: Add the structure for Write Sync Train Parameters

The Write_Synchronization_Train_Parameters command configures
the Synchronization Train functionality in the BR/EDR Controller.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 97

"7.3.90 Write Synchronization Train Parameters Command [New Section]
...
Note: The AFH_Channel_Map used in the Synchronization Train packets is
configured by the Set_AFH_Channel_Classification command and the local
channel classification in the BR/EDR Controller.

Interval_Min and Interval_Max specify the allowed range of
Sync_Train_Interval. Refer to [Vol. 2], Part B, section 2.7.2 for
a detailed description of Sync_Train_Interval. The BR/EDR Controller shall
select an interval from this range and return it in Sync_Train_Interval.
If the Controller is unable to select a value from this range, it shall
return the Invalid HCI Command Parameters (0x12) error code.

Once started (via the Start_Synchronization_Train Command) the
Synchronization Train will continue until synchronization_trainTO slots have
passed or Connectionless Slave Broadcast has been disabled."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index d9e0a8467ddc..cad6ca121461 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -873,6 +873,18 @@ struct hci_rp_set_csb_data {
 
 #define HCI_OP_READ_SYNC_TRAIN_PARAMS	0x0c77
 
+#define HCI_OP_WRITE_SYNC_TRAIN_PARAMS	0x0c78
+struct hci_cp_write_sync_train_params {
+	__le16	interval_min;
+	__le16	interval_max;
+	__le32	sync_train_tout;
+	__u8	service_data;
+} __packed;
+struct hci_rp_write_sync_train_params {
+	__u8	status;
+	__le16	sync_train_int;
+} __packed;
+
 #define HCI_OP_READ_LOCAL_VERSION	0x1001
 struct hci_rp_read_local_version {
 	__u8     status;
-- 
cgit 


From 8c9a041be2b8d534e770594a5e8d3251cc221bd1 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:50 +0900
Subject: Bluetooth: Add the definition and structure for Set CSB

he Set_Connectionless_Slave_Broadcast command controls the
Connectionless Slave Broadcast functionality in the BR/EDR
Controller.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 78

"7.1.49 Set Connectionless Slave Broadcast Command [New Section]
...
The LT_ADDR indicated in the Set_Connectionless_Slave_Broadcast shall be
pre-allocated using the HCI_Set_Reserved_LT_ADDR command. If the
LT_ADDR has not been reserved, the Unknown Connection Identifier (0x02)
error code shall be returned. If the controller is unable to reserve
sufficient bandwidth for the requested activity, the Connection Rejected
Due to Limited Resources (0x0D) error code shall be returned.

The LPO_Allowed parameter informs the BR/EDR Controller whether it is
allowed to sleep.

The Packet_Type parameter specifies which packet types are allowed. The
Host shall either enable BR packet types only, or shall enable EDR and DM1
packet types only.

The Interval_Min and Interval_Max parameters specify the range from which
the BR/EDR Controller must select the Connectionless Slave Broadcast
Interval. The selected Interval is returned."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index cad6ca121461..42d3832f0602 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -628,6 +628,22 @@ struct hci_rp_logical_link_cancel {
 	__u8     flow_spec_id;
 } __packed;
 
+#define HCI_OP_SET_CSB			0x0441
+struct hci_cp_set_csb {
+	__u8	enable;
+	__u8	lt_addr;
+	__u8	lpo_allowed;
+	__le16	packet_type;
+	__le16	interval_min;
+	__le16	interval_max;
+	__le16	csb_sv_tout;
+} __packed;
+struct hci_rp_set_csb {
+	__u8	status;
+	__u8	lt_addr;
+	__le16	interval;
+} __packed;
+
 #define HCI_OP_SNIFF_MODE		0x0803
 struct hci_cp_sniff_mode {
 	__le16   handle;
-- 
cgit 


From cefded981960d60f7d18f6596c020390b9764aa3 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:51 +0900
Subject: Bluetooth: Add the definition for Start Synchronization Train

The Start_Synchronization_Train command controls the Synchronization
Train functionality in the BR/EDR Controller.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 86

"7.1.51 Start Synchronization Train Command [New Section]
...
If connectionless slave broadcast mode is not enabled, the Command
Disallowed (0x0C) error code shall be returned. After receiving this
command and returning a Command Status event, the Baseband starts
attempting to send synchronization train packets containing information
related to the enabled Connectionless Slave Broadcast packet timing.

Note: The AFH_Channel_Map used in the synchronization train packets is
configured by the Set_AFH_Channel_Classification command and the local
channel classification in the BR/EDR Controller.

The synchronization train packets will be sent using the parameters
specified by the latest Write_Synchronization_Train_Parameters command.
The Synchronization Train will continue until synchronization_trainTO
slots (as specified in the last Write_Synchronization_Train command)
have passed or until the Host disables the Connectionless Slave Broadcast
logical transport."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 42d3832f0602..657d2b09e3fe 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -644,6 +644,8 @@ struct hci_rp_set_csb {
 	__le16	interval;
 } __packed;
 
+#define HCI_OP_START_SYNC_TRAIN		0x0443
+
 #define HCI_OP_SNIFF_MODE		0x0803
 struct hci_cp_sniff_mode {
 	__le16   handle;
-- 
cgit 


From 2b359445d5578f65cdd5301dfcbf9e0bdc358b20 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:52 +0900
Subject: Bluetooth: Add the definition and stcuture for Sync Train Complete

The Synchronization Train Complete event indicates that the Start
Synchronization Train command has completed.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 103

"7.7.67 Synchronization Train Complete Event [New Section]
...

Event Parameters:

Status 0x00       Start Synchronization Train command completed
                  successfully.
       0x01-0xFF  Start Synchronization Train command failed.
                  See Part D, Error Codes, for error codes and
                  descriptions."

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 657d2b09e3fe..03f2a9126a5d 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1505,6 +1505,11 @@ struct hci_ev_num_comp_blocks {
 	struct hci_comp_blocks_info handles[0];
 } __packed;
 
+#define HCI_EV_SYNC_TRAIN_COMPLETE	0x4F
+struct hci_ev_sync_train_complete {
+	__u8	status;
+} __packed;
+
 /* Low energy meta events */
 #define LE_CONN_ROLE_MASTER	0x00
 
-- 
cgit 


From 2ed01805ee439056f4e1fe182846c029e0a08e49 Mon Sep 17 00:00:00 2001
From: DoHyun Pyun <dh79.pyun@samsung.com>
Date: Wed, 2 Oct 2013 21:54:53 +0900
Subject: Bluetooth: Add the definition for Slave Page Response Timeout

The Slave Page Response Timeout event indicates to the Host that a
slave page response timeout has occurred in the BR/EDR Controller.

The Core Spec Addendum 4 adds this command in part B Connectionless
Slave Broadcast.

Bluetooth Core Specification Addendum 4 - Page 110

"7.7.72 Slave Page Response Timeout Event [New Section]
...
Note: this event will be generated if the slave BR/EDR Controller
responds to a page but does not receive the master FHS packet
(see Baseband, Section 8.3.3) within pagerespTO.

Event Parameters: NONE"

Signed-off-by: Dohyun Pyun <dh79.pyun@samsung.com>
Signed-off-by: C S Bhargava <cs.bhargava@samsung.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 03f2a9126a5d..b90eec5e9c06 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1510,6 +1510,8 @@ struct hci_ev_sync_train_complete {
 	__u8	status;
 } __packed;
 
+#define HCI_EV_SLAVE_PAGE_RESP_TIMEOUT	0x54
+
 /* Low energy meta events */
 #define LE_CONN_ROLE_MASTER	0x00
 
-- 
cgit 


From 42c4e0c77ac91505ab94284b14025e3a0865c0a5 Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@linaro.org>
Date: Mon, 30 Sep 2013 14:20:07 +0530
Subject: ARM/ARM64: KVM: Implement KVM_ARM_PREFERRED_TARGET ioctl

For implementing CPU=host, we need a mechanism for querying
preferred VCPU target type on underlying Host.

This patch implements KVM_ARM_PREFERRED_TARGET vm ioctl which
returns struct kvm_vcpu_init instance containing information
about preferred VCPU target type and target specific features
available for it.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 arch/arm/kvm/arm.c       | 13 +++++++++++++
 include/uapi/linux/kvm.h |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9c697db2787e..cc5adb9349ef 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -797,6 +797,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			return -EFAULT;
 		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
 	}
+	case KVM_ARM_PREFERRED_TARGET: {
+		int err;
+		struct kvm_vcpu_init init;
+
+		err = kvm_vcpu_preferred_target(&init);
+		if (err)
+			return err;
+
+		if (copy_to_user(argp, &init, sizeof(init)))
+			return -EFAULT;
+
+		return 0;
+	}
 	default:
 		return -EINVAL;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 99c25338ede8..e32e776f20c0 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1012,6 +1012,7 @@ struct kvm_s390_ucas_mapping {
 /* VM is being stopped by host */
 #define KVM_KVMCLOCK_CTRL	  _IO(KVMIO,   0xad)
 #define KVM_ARM_VCPU_INIT	  _IOW(KVMIO,  0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET  _IOR(KVMIO,  0xaf, struct kvm_vcpu_init)
 #define KVM_GET_REG_LIST	  _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
-- 
cgit 


From 4bcef89f0c6ca1eb4f1a789c2a226f4c02656a4b Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sat, 28 Sep 2013 23:15:27 +0200
Subject: ssb: provide phy address for Gigabit Ethernet driver

Add a function to provide the phy address which should be used to the
Gigabit Ethernet driver connected to ssb.

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Reviewed-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ssb/ssb_driver_gige.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h
index 86a12b0cb239..0688472500bb 100644
--- a/include/linux/ssb/ssb_driver_gige.h
+++ b/include/linux/ssb/ssb_driver_gige.h
@@ -108,6 +108,16 @@ static inline int ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr)
 	return 0;
 }
 
+/* Get the device phy address */
+static inline int ssb_gige_get_phyaddr(struct pci_dev *pdev)
+{
+	struct ssb_gige *dev = pdev_to_ssb_gige(pdev);
+	if (!dev)
+		return -ENODEV;
+
+	return dev->dev->bus->sprom.et0phyaddr;
+}
+
 extern int ssb_gige_pcibios_plat_dev_init(struct ssb_device *sdev,
 					  struct pci_dev *pdev);
 extern int ssb_gige_map_irq(struct ssb_device *sdev,
@@ -174,6 +184,10 @@ static inline int ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr)
 {
 	return -ENODEV;
 }
+static inline int ssb_gige_get_phyaddr(struct pci_dev *pdev)
+{
+	return -ENODEV;
+}
 
 #endif /* CONFIG_SSB_DRIVER_GIGE */
 #endif /* LINUX_SSB_DRIVER_GIGE_H_ */
-- 
cgit 


From 0b3d8e087bbee2a4e3f479d538a7edd3f1d2950c Mon Sep 17 00:00:00 2001
From: Denis Kirjanov <kda@linux-powerpc.org>
Date: Wed, 2 Oct 2013 05:58:32 +0400
Subject: include/linux/skbuff.h: move CONFIG_XFRM check inside the
 skb_sec_path()

And thus we have only one function definition

Signed-off-by: Denis Kirjanov <kda@linux-powerpc.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 71b1d9402fd3..1cd32f96055e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2708,17 +2708,14 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb)
 u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 		  unsigned int num_tx_queues);
 
-#ifdef CONFIG_XFRM
 static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
 {
+#ifdef CONFIG_XFRM
 	return skb->sp;
-}
 #else
-static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
-{
 	return NULL;
-}
 #endif
+}
 
 /* Keeps track of mac header offset relative to skb->head.
  * It is useful for TSO of Tunneling protocol. e.g. GRE.
-- 
cgit 


From 05071aa864e84000759191438a4a9ff7ba2c360e Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 27 Sep 2013 16:34:27 +0200
Subject: spi: Add a spi_w8r16be() helper

This patch adds a new spi_w8r16be() helper, which is similar to spi_w8r16()
except that it converts the read data word from big endian to native endianness
before returning it. The reason for introducing this new helper is that for SPI
slave devices it is quite common that the read 16 bit data word is in big
endian. So users of spi_w8r16() have to convert the result to native endianness
manually. A second reason is that in this case the endianness of the return
value of spi_w8r16() depends on its sign. If it is negative (i.e. a error code)
it is already in native endianness, if it is positive it is in big endian. The
sparse code checker doesn't like this kind of mixed endianness and special
annotations are necessary to keep it quiet (E.g. casting to be16 using __force).
Doing the conversion to native endianness in the helper function does not
require such annotations since we are not mixing different endiannesses in the
same variable.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/spi/spi.h | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'include')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 887116dbce2c..0e0aebdeb56b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -823,6 +823,33 @@ static inline ssize_t spi_w8r16(struct spi_device *spi, u8 cmd)
 	return (status < 0) ? status : result;
 }
 
+/**
+ * spi_w8r16be - SPI synchronous 8 bit write followed by 16 bit big-endian read
+ * @spi: device with which data will be exchanged
+ * @cmd: command to be written before data is read back
+ * Context: can sleep
+ *
+ * This returns the (unsigned) sixteen bit number returned by the device in cpu
+ * endianness, or else a negative error code. Callable only from contexts that
+ * can sleep.
+ *
+ * This function is similar to spi_w8r16, with the exception that it will
+ * convert the read 16 bit data word from big-endian to native endianness.
+ *
+ */
+static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd)
+
+{
+	ssize_t status;
+	__be16 result;
+
+	status = spi_write_then_read(spi, &cmd, 1, &result, 2);
+	if (status < 0)
+		return status;
+
+	return be16_to_cpu(result);
+}
+
 /*---------------------------------------------------------------------------*/
 
 /*
-- 
cgit 


From 8daaa5f8261bffd2f6217a960f9182d0503a5c44 Mon Sep 17 00:00:00 2001
From: Mike Travis <travis@sgi.com>
Date: Wed, 2 Oct 2013 10:14:18 -0500
Subject: kdb: Add support for external NMI handler to call KGDB/KDB

This patch adds a kgdb_nmicallin() interface that can be used by
external NMI handlers to call the KGDB/KDB handler.  The primary
need for this is for those types of NMI interrupts where all the
CPUs have already received the NMI signal.  Therefore no
send_IPI(NMI) is required, and in fact it will cause a 2nd
unhandled NMI to occur. This generates the "Dazed and Confuzed"
messages.

Since all the CPUs are getting the NMI at roughly the same time,
it's not guaranteed that the first CPU that hits the NMI handler
will manage to enter KGDB and set the dbg_master_lock before the
slaves start entering. The new argument "send_ready" was added
for KGDB to signal the NMI handler to release the slave CPUs for
entry into KGDB.

Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Jason Wessel <jason.wessel@windriver.com>
Reviewed-by: Dimitri Sivanich <sivanich@sgi.com>
Reviewed-by: Hedi Berriche <hedi@sgi.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Link: http://lkml.kernel.org/r/20131002151417.928886849@asylum.americas.sgi.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kdb.h             |  1 +
 include/linux/kgdb.h            |  1 +
 kernel/debug/debug_core.c       | 32 ++++++++++++++++++++++++++++++--
 kernel/debug/debug_core.h       |  3 +++
 kernel/debug/kdb/kdb_debugger.c |  5 ++++-
 kernel/debug/kdb/kdb_main.c     |  3 +++
 6 files changed, 42 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 7f6fe6e015bc..290db1269c4c 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -109,6 +109,7 @@ typedef enum {
 	KDB_REASON_RECURSE,	/* Recursive entry to kdb;
 				 * regs probably valid */
 	KDB_REASON_SSTEP,	/* Single Step trap. - regs valid */
+	KDB_REASON_SYSTEM_NMI,	/* In NMI due to SYSTEM cmd; regs valid */
 } kdb_reason_t;
 
 extern int kdb_trap_printk;
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index c6e091bf39a5..dfb4f2ffdaa2 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -310,6 +310,7 @@ extern int
 kgdb_handle_exception(int ex_vector, int signo, int err_code,
 		      struct pt_regs *regs);
 extern int kgdb_nmicallback(int cpu, void *regs);
+extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *snd_rdy);
 extern void gdbstub_exit(int status);
 
 extern int			kgdb_single_step;
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0506d447aed2..7d2f35e5df2f 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -575,8 +575,12 @@ return_normal:
 		raw_spin_lock(&dbg_slave_lock);
 
 #ifdef CONFIG_SMP
+	/* If send_ready set, slaves are already waiting */
+	if (ks->send_ready)
+		atomic_set(ks->send_ready, 1);
+
 	/* Signal the other CPUs to enter kgdb_wait() */
-	if ((!kgdb_single_step) && kgdb_do_roundup)
+	else if ((!kgdb_single_step) && kgdb_do_roundup)
 		kgdb_roundup_cpus(flags);
 #endif
 
@@ -678,11 +682,11 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
 	if (arch_kgdb_ops.enable_nmi)
 		arch_kgdb_ops.enable_nmi(0);
 
+	memset(ks, 0, sizeof(struct kgdb_state));
 	ks->cpu			= raw_smp_processor_id();
 	ks->ex_vector		= evector;
 	ks->signo		= signo;
 	ks->err_code		= ecode;
-	ks->kgdb_usethreadid	= 0;
 	ks->linux_regs		= regs;
 
 	if (kgdb_reenter_check(ks))
@@ -732,6 +736,30 @@ int kgdb_nmicallback(int cpu, void *regs)
 	return 1;
 }
 
+int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *send_ready)
+{
+#ifdef CONFIG_SMP
+	if (!kgdb_io_ready(0) || !send_ready)
+		return 1;
+
+	if (kgdb_info[cpu].enter_kgdb == 0) {
+		struct kgdb_state kgdb_var;
+		struct kgdb_state *ks = &kgdb_var;
+
+		memset(ks, 0, sizeof(struct kgdb_state));
+		ks->cpu			= cpu;
+		ks->ex_vector		= trapnr;
+		ks->signo		= SIGTRAP;
+		ks->err_code		= KGDB_KDB_REASON_SYSTEM_NMI;
+		ks->linux_regs		= regs;
+		ks->send_ready		= send_ready;
+		kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
+		return 0;
+	}
+#endif
+	return 1;
+}
+
 static void kgdb_console_write(struct console *co, const char *s,
    unsigned count)
 {
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index 2235967e78b0..572aa4f5677c 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -26,6 +26,7 @@ struct kgdb_state {
 	unsigned long		threadid;
 	long			kgdb_usethreadid;
 	struct pt_regs		*linux_regs;
+	atomic_t		*send_ready;
 };
 
 /* Exception state values */
@@ -74,11 +75,13 @@ extern int kdb_stub(struct kgdb_state *ks);
 extern int kdb_parse(const char *cmdstr);
 extern int kdb_common_init_state(struct kgdb_state *ks);
 extern int kdb_common_deinit_state(void);
+#define KGDB_KDB_REASON_SYSTEM_NMI KDB_REASON_SYSTEM_NMI
 #else /* ! CONFIG_KGDB_KDB */
 static inline int kdb_stub(struct kgdb_state *ks)
 {
 	return DBG_PASS_EVENT;
 }
+#define KGDB_KDB_REASON_SYSTEM_NMI 0
 #endif /* CONFIG_KGDB_KDB */
 
 #endif /* _DEBUG_CORE_H_ */
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 328d18ef31e4..8859ca34dcfe 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -69,7 +69,10 @@ int kdb_stub(struct kgdb_state *ks)
 	if (atomic_read(&kgdb_setting_breakpoint))
 		reason = KDB_REASON_KEYBOARD;
 
-	if (in_nmi())
+	if (ks->err_code == KDB_REASON_SYSTEM_NMI && ks->signo == SIGTRAP)
+		reason = KDB_REASON_SYSTEM_NMI;
+
+	else if (in_nmi())
 		reason = KDB_REASON_NMI;
 
 	for (i = 0, bp = kdb_breakpoints; i < KDB_MAXBPT; i++, bp++) {
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 00eb8f7fbf41..0b097c8a1e50 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1200,6 +1200,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 			   instruction_pointer(regs));
 		kdb_dumpregs(regs);
 		break;
+	case KDB_REASON_SYSTEM_NMI:
+		kdb_printf("due to System NonMaskable Interrupt\n");
+		break;
 	case KDB_REASON_NMI:
 		kdb_printf("due to NonMaskable Interrupt @ "
 			   kdb_machreg_fmt "\n",
-- 
cgit 


From 5080546682bae3d32734b18e281091684f0ebbe4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Oct 2013 04:29:50 -0700
Subject: inet: consolidate INET_TW_MATCH

TCP listener refactoring, part 2 :

We can use a generic lookup, sockets being in whatever state, if
we are sure all relevant fields are at the same place in all socket
types (ESTABLISH, TIME_WAIT, SYN_RECV)

This patch removes these macros :

 inet_addrpair, inet_addrpair, tw_addrpair, tw_portpair

And adds :

 sk_portpair, sk_addrpair, sk_daddr, sk_rcv_saddr

Then, INET_TW_MATCH() is really the same than INET_MATCH()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             |  4 ++--
 include/net/inet_hashtables.h    | 26 ++++++++------------------
 include/net/inet_sock.h          |  2 --
 include/net/inet_timewait_sock.h |  8 --------
 include/net/sock.h               |  4 ++++
 net/ipv4/inet_connection_sock.c  | 11 +++++------
 net/ipv6/udp.c                   |  6 ++----
 7 files changed, 21 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 28ea38439313..b7f1f3bb346d 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -370,7 +370,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 
 #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
-	((inet_sk(__sk)->inet_portpair == (__ports))		&&	\
+	(((__sk)->sk_portpair == (__ports))			&&	\
 	 ((__sk)->sk_family == AF_INET6)			&&	\
 	 ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))	&&	\
 	 ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&&	\
@@ -379,7 +379,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 	 net_eq(sock_net(__sk), (__net)))
 
 #define INET6_TW_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	   \
-	((inet_twsk(__sk)->tw_portpair == (__ports))			&& \
+	(((__sk)->sk_portpair == (__ports))				&& \
 	 ((__sk)->sk_family == AF_INET6)				&& \
 	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr))	&& \
 	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr)) && \
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 594dfeead70f..10d6838378c3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -302,35 +302,25 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 				   ((__force __u64)(__be32)(__saddr)));
 #endif /* __BIG_ENDIAN */
 #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)	\
-	((inet_sk(__sk)->inet_portpair == (__ports))		&&	\
-	 (inet_sk(__sk)->inet_addrpair == (__cookie))		&&	\
+	(((__sk)->sk_portpair == (__ports))			&&	\
+	 ((__sk)->sk_addrpair == (__cookie))			&&	\
 	 (!(__sk)->sk_bound_dev_if	||				\
 	   ((__sk)->sk_bound_dev_if == (__dif))) 		&& 	\
 	 net_eq(sock_net(__sk), (__net)))
-#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)\
-	((inet_twsk(__sk)->tw_portpair == (__ports))	&&		\
-	 (inet_twsk(__sk)->tw_addrpair == (__cookie))	&&		\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif)))	&&		\
-	 net_eq(sock_net(__sk), (__net)))
 #else /* 32-bit arch */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr)
 #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
-	((inet_sk(__sk)->inet_portpair == (__ports))	&&		\
-	 (inet_sk(__sk)->inet_daddr	== (__saddr))	&&		\
-	 (inet_sk(__sk)->inet_rcv_saddr	== (__daddr))	&&		\
-	 (!(__sk)->sk_bound_dev_if	||				\
-	   ((__sk)->sk_bound_dev_if == (__dif))) 	&&		\
-	 net_eq(sock_net(__sk), (__net)))
-#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
-	((inet_twsk(__sk)->tw_portpair == (__ports))	&&		\
-	 (inet_twsk(__sk)->tw_daddr	== (__saddr))	&&		\
-	 (inet_twsk(__sk)->tw_rcv_saddr	== (__daddr))	&&		\
+	(((__sk)->sk_portpair == (__ports))		&&		\
+	 ((__sk)->sk_daddr	== (__saddr))		&&		\
+	 ((__sk)->sk_rcv_saddr	== (__daddr))		&&		\
 	 (!(__sk)->sk_bound_dev_if	||				\
 	   ((__sk)->sk_bound_dev_if == (__dif))) 	&&		\
 	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
+#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)\
+	INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)
+
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index f3141773c14d..6d9a7e6eb5a4 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -146,10 +146,8 @@ struct inet_sock {
 	/* Socket demultiplex comparisons on incoming packets. */
 #define inet_daddr		sk.__sk_common.skc_daddr
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
-#define inet_addrpair		sk.__sk_common.skc_addrpair
 #define inet_dport		sk.__sk_common.skc_dport
 #define inet_num		sk.__sk_common.skc_num
-#define inet_portpair		sk.__sk_common.skc_portpair
 
 	__be32			inet_saddr;
 	__s16			uc_ttl;
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 828200ab1125..48fd3561722c 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -112,10 +112,8 @@ struct inet_timewait_sock {
 #define tw_net			__tw_common.skc_net
 #define tw_daddr        	__tw_common.skc_daddr
 #define tw_rcv_saddr    	__tw_common.skc_rcv_saddr
-#define tw_addrpair		__tw_common.skc_addrpair
 #define tw_dport		__tw_common.skc_dport
 #define tw_num			__tw_common.skc_num
-#define tw_portpair		__tw_common.skc_portpair
 
 	int			tw_timeout;
 	volatile unsigned char	tw_substate;
@@ -189,12 +187,6 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
 	return (struct inet_timewait_sock *)sk;
 }
 
-static inline __be32 sk_rcv_saddr(const struct sock *sk)
-{
-/* both inet_sk() and inet_twsk() store rcv_saddr in skc_rcv_saddr */
-	return sk->__sk_common.skc_rcv_saddr;
-}
-
 void inet_twsk_put(struct inet_timewait_sock *tw);
 
 int inet_twsk_unhash(struct inet_timewait_sock *tw);
diff --git a/include/net/sock.h b/include/net/sock.h
index f0a44cc1ff9d..e3bf213be625 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -300,6 +300,10 @@ struct sock {
 #define sk_dontcopy_begin	__sk_common.skc_dontcopy_begin
 #define sk_dontcopy_end		__sk_common.skc_dontcopy_end
 #define sk_hash			__sk_common.skc_hash
+#define sk_portpair		__sk_common.skc_portpair
+#define sk_addrpair		__sk_common.skc_addrpair
+#define sk_daddr		__sk_common.skc_daddr
+#define sk_rcv_saddr		__sk_common.skc_rcv_saddr
 #define sk_family		__sk_common.skc_family
 #define sk_state		__sk_common.skc_state
 #define sk_reuse		__sk_common.skc_reuse
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 7ac7aa11130e..56e82a4027b4 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -71,17 +71,16 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			    (!reuseport || !sk2->sk_reuseport ||
 			    (sk2->sk_state != TCP_TIME_WAIT &&
 			     !uid_eq(uid, sock_i_uid(sk2))))) {
-				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
-				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
-				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+
+				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
 					break;
 			}
 			if (!relax && reuse && sk2->sk_reuse &&
 			    sk2->sk_state != TCP_LISTEN) {
-				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 
-				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
-				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
+				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
 					break;
 			}
 		}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 72b7eaaf3ca0..8119791e8a95 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -57,8 +57,6 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
 	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
 	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
-	__be32 sk1_rcv_saddr = sk_rcv_saddr(sk);
-	__be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 	int sk_ipv6only = ipv6_only_sock(sk);
 	int sk2_ipv6only = inet_v6_ipv6only(sk2);
 	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
@@ -67,8 +65,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 	/* if both are mapped, treat as IPv4 */
 	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
 		return (!sk2_ipv6only &&
-			(!sk1_rcv_saddr || !sk2_rcv_saddr ||
-			  sk1_rcv_saddr == sk2_rcv_saddr));
+			(!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr ||
+			  sk->sk_rcv_saddr == sk2->sk_rcv_saddr));
 
 	if (addr_type2 == IPV6_ADDR_ANY &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
-- 
cgit 


From 357afe9c46c951c34769e39cabdf8d1637e2eecc Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@redhat.com>
Date: Wed, 2 Oct 2013 13:39:24 +0200
Subject: flow_dissector: factor out the ports extraction in skb_flow_get_ports

Factor out the code that extracts the ports from skb_flow_dissect and
add a new function skb_flow_get_ports which can be re-used.

Suggested-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_keys.h   |  1 +
 net/core/flow_dissector.c | 39 ++++++++++++++++++++++++++++-----------
 2 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index ac2439d02f54..7e64bd8bbda9 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -14,4 +14,5 @@ struct flow_keys {
 };
 
 bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto);
 #endif
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 8d7d0dd72db2..f8e25ac41c6c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -25,9 +25,35 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
 	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
 }
 
+/**
+ * skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: buffer to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ *
+ * The function will try to retrieve the ports at offset thoff + poff where poff
+ * is the protocol port offset returned from proto_ports_offset
+ */
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+{
+	int poff = proto_ports_offset(ip_proto);
+
+	if (poff >= 0) {
+		__be32 *ports, _ports;
+
+		ports = skb_header_pointer(skb, thoff + poff,
+					   sizeof(_ports), &_ports);
+		if (ports)
+			return *ports;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_flow_get_ports);
+
 bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
 {
-	int poff, nhoff = skb_network_offset(skb);
+	int nhoff = skb_network_offset(skb);
 	u8 ip_proto;
 	__be16 proto = skb->protocol;
 
@@ -150,16 +176,7 @@ ipv6:
 	}
 
 	flow->ip_proto = ip_proto;
-	poff = proto_ports_offset(ip_proto);
-	if (poff >= 0) {
-		__be32 *ports, _ports;
-
-		ports = skb_header_pointer(skb, nhoff + poff,
-					   sizeof(_ports), &_ports);
-		if (ports)
-			flow->ports = *ports;
-	}
-
+	flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
 	flow->thoff = (u16) nhoff;
 
 	return true;
-- 
cgit 


From 32819dc1834866cb9547cb75f81af9edd58d33cd Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@redhat.com>
Date: Wed, 2 Oct 2013 13:39:25 +0200
Subject: bonding: modify the old and add new xmit hash policies

This patch adds two new hash policy modes which use skb_flow_dissect:
3 - Encapsulated layer 2+3
4 - Encapsulated layer 3+4
There should be a good improvement for tunnel users in those modes.
It also changes the old hash functions to:
hash ^= (__force u32)flow.dst ^ (__force u32)flow.src;
hash ^= (hash >> 16);
hash ^= (hash >> 8);

Where hash will be initialized either to L2 hash, that is
SRCMAC[5] XOR DSTMAC[5], or to flow->ports which should be extracted
from the upper layer. Flow's dst and src are also extracted based on the
xmit policy either directly from the buffer or by using skb_flow_dissect,
but in both cases if the protocol is IPv6 then dst and src are obtained by
ipv6_addr_hash() on the real addresses. In case of a non-dissectable
packet, the algorithms fall back to L2 hashing.
The bond_set_mode_ops() function is now obsolete and thus deleted
because it was used only to set the proper hash policy. Also we trim a
pointer from struct bonding because we no longer need to keep the hash
function, now there's only a single hash function - bond_xmit_hash that
works based on bond->params.xmit_policy.

The hash function and skb_flow_dissect were suggested by Eric Dumazet.
The layer names were suggested by Andy Gospodarek, because I suck at
semantics.

Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_3ad.c   |   2 +-
 drivers/net/bonding/bond_main.c  | 197 ++++++++++++++-------------------------
 drivers/net/bonding/bond_sysfs.c |   2 -
 drivers/net/bonding/bonding.h    |   3 +-
 include/uapi/linux/if_bonding.h  |   2 +
 5 files changed, 72 insertions(+), 134 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index c62606a67f6a..ea3e64e22e22 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2403,7 +2403,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
-	slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg);
+	slave_agg_no = bond_xmit_hash(bond, skb, slaves_in_agg);
 	first_ok_slave = NULL;
 
 	bond_for_each_slave(bond, slave, iter) {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index fe8a94f9d7db..dfb4f6dd5de0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -78,6 +78,7 @@
 #include <net/netns/generic.h>
 #include <net/pkt_sched.h>
 #include <linux/rculist.h>
+#include <net/flow_keys.h>
 #include "bonding.h"
 #include "bond_3ad.h"
 #include "bond_alb.h"
@@ -159,7 +160,8 @@ MODULE_PARM_DESC(min_links, "Minimum number of available links before turning on
 module_param(xmit_hash_policy, charp, 0);
 MODULE_PARM_DESC(xmit_hash_policy, "balance-xor and 802.3ad hashing method; "
 				   "0 for layer 2 (default), 1 for layer 3+4, "
-				   "2 for layer 2+3");
+				   "2 for layer 2+3, 3 for encap layer 2+3, "
+				   "4 for encap layer 3+4");
 module_param(arp_interval, int, 0);
 MODULE_PARM_DESC(arp_interval, "arp interval in milliseconds");
 module_param_array(arp_ip_target, charp, NULL, 0);
@@ -217,6 +219,8 @@ const struct bond_parm_tbl xmit_hashtype_tbl[] = {
 {	"layer2",		BOND_XMIT_POLICY_LAYER2},
 {	"layer3+4",		BOND_XMIT_POLICY_LAYER34},
 {	"layer2+3",		BOND_XMIT_POLICY_LAYER23},
+{	"encap2+3",		BOND_XMIT_POLICY_ENCAP23},
+{	"encap3+4",		BOND_XMIT_POLICY_ENCAP34},
 {	NULL,			-1},
 };
 
@@ -3035,99 +3039,85 @@ static struct notifier_block bond_netdev_notifier = {
 
 /*---------------------------- Hashing Policies -----------------------------*/
 
-/*
- * Hash for the output device based upon layer 2 data
- */
-static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count)
+/* L2 hash helper */
+static inline u32 bond_eth_hash(struct sk_buff *skb)
 {
 	struct ethhdr *data = (struct ethhdr *)skb->data;
 
 	if (skb_headlen(skb) >= offsetof(struct ethhdr, h_proto))
-		return (data->h_dest[5] ^ data->h_source[5]) % count;
+		return data->h_dest[5] ^ data->h_source[5];
 
 	return 0;
 }
 
-/*
- * Hash for the output device based upon layer 2 and layer 3 data. If
- * the packet is not IP, fall back on bond_xmit_hash_policy_l2()
- */
-static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count)
+/* Extract the appropriate headers based on bond's xmit policy */
+static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
+			      struct flow_keys *fk)
 {
-	const struct ethhdr *data;
+	const struct ipv6hdr *iph6;
 	const struct iphdr *iph;
-	const struct ipv6hdr *ipv6h;
-	u32 v6hash;
-	const __be32 *s, *d;
+	int noff, proto = -1;
 
-	if (skb->protocol == htons(ETH_P_IP) &&
-	    pskb_network_may_pull(skb, sizeof(*iph))) {
+	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
+		return skb_flow_dissect(skb, fk);
+
+	fk->ports = 0;
+	noff = skb_network_offset(skb);
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (!pskb_may_pull(skb, noff + sizeof(*iph)))
+			return false;
 		iph = ip_hdr(skb);
-		data = (struct ethhdr *)skb->data;
-		return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^
-			(data->h_dest[5] ^ data->h_source[5])) % count;
-	} else if (skb->protocol == htons(ETH_P_IPV6) &&
-		   pskb_network_may_pull(skb, sizeof(*ipv6h))) {
-		ipv6h = ipv6_hdr(skb);
-		data = (struct ethhdr *)skb->data;
-		s = &ipv6h->saddr.s6_addr32[0];
-		d = &ipv6h->daddr.s6_addr32[0];
-		v6hash = (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
-		v6hash ^= (v6hash >> 24) ^ (v6hash >> 16) ^ (v6hash >> 8);
-		return (v6hash ^ data->h_dest[5] ^ data->h_source[5]) % count;
-	}
-
-	return bond_xmit_hash_policy_l2(skb, count);
+		fk->src = iph->saddr;
+		fk->dst = iph->daddr;
+		noff += iph->ihl << 2;
+		if (!ip_is_fragment(iph))
+			proto = iph->protocol;
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		if (!pskb_may_pull(skb, noff + sizeof(*iph6)))
+			return false;
+		iph6 = ipv6_hdr(skb);
+		fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
+		fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
+		noff += sizeof(*iph6);
+		proto = iph6->nexthdr;
+	} else {
+		return false;
+	}
+	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
+		fk->ports = skb_flow_get_ports(skb, noff, proto);
+
+	return true;
 }
 
-/*
- * Hash for the output device based upon layer 3 and layer 4 data. If
- * the packet is a frag or not TCP or UDP, just use layer 3 data.  If it is
- * altogether not IP, fall back on bond_xmit_hash_policy_l2()
+/**
+ * bond_xmit_hash - generate a hash value based on the xmit policy
+ * @bond: bonding device
+ * @skb: buffer to use for headers
+ * @count: modulo value
+ *
+ * This function will extract the necessary headers from the skb buffer and use
+ * them to generate a hash based on the xmit_policy set in the bonding device
+ * which will be reduced modulo count before returning.
  */
-static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count)
+int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count)
 {
-	u32 layer4_xor = 0;
-	const struct iphdr *iph;
-	const struct ipv6hdr *ipv6h;
-	const __be32 *s, *d;
-	const __be16 *l4 = NULL;
-	__be16 _l4[2];
-	int noff = skb_network_offset(skb);
-	int poff;
-
-	if (skb->protocol == htons(ETH_P_IP) &&
-	    pskb_may_pull(skb, noff + sizeof(*iph))) {
-		iph = ip_hdr(skb);
-		poff = proto_ports_offset(iph->protocol);
+	struct flow_keys flow;
+	u32 hash;
 
-		if (!ip_is_fragment(iph) && poff >= 0) {
-			l4 = skb_header_pointer(skb, noff + (iph->ihl << 2) + poff,
-						sizeof(_l4), &_l4);
-			if (l4)
-				layer4_xor = ntohs(l4[0] ^ l4[1]);
-		}
-		return (layer4_xor ^
-			((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count;
-	} else if (skb->protocol == htons(ETH_P_IPV6) &&
-		   pskb_may_pull(skb, noff + sizeof(*ipv6h))) {
-		ipv6h = ipv6_hdr(skb);
-		poff = proto_ports_offset(ipv6h->nexthdr);
-		if (poff >= 0) {
-			l4 = skb_header_pointer(skb, noff + sizeof(*ipv6h) + poff,
-						sizeof(_l4), &_l4);
-			if (l4)
-				layer4_xor = ntohs(l4[0] ^ l4[1]);
-		}
-		s = &ipv6h->saddr.s6_addr32[0];
-		d = &ipv6h->daddr.s6_addr32[0];
-		layer4_xor ^= (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]);
-		layer4_xor ^= (layer4_xor >> 24) ^ (layer4_xor >> 16) ^
-			       (layer4_xor >> 8);
-		return layer4_xor % count;
-	}
+	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
+	    !bond_flow_dissect(bond, skb, &flow))
+		return bond_eth_hash(skb) % count;
+
+	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
+	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
+		hash = bond_eth_hash(skb);
+	else
+		hash = (__force u32)flow.ports;
+	hash ^= (__force u32)flow.dst ^ (__force u32)flow.src;
+	hash ^= (hash >> 16);
+	hash ^= (hash >> 8);
 
-	return bond_xmit_hash_policy_l2(skb, count);
+	return hash % count;
 }
 
 /*-------------------------- Device entry points ----------------------------*/
@@ -3721,8 +3711,7 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d
 	return NETDEV_TX_OK;
 }
 
-/*
- * In bond_xmit_xor() , we determine the output device by using a pre-
+/* In bond_xmit_xor() , we determine the output device by using a pre-
  * determined xmit_hash_policy(), If the selected device is not enabled,
  * find the next active slave.
  */
@@ -3730,8 +3719,7 @@ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 
-	bond_xmit_slave_id(bond, skb,
-			   bond->xmit_hash_policy(skb, bond->slave_cnt));
+	bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt));
 
 	return NETDEV_TX_OK;
 }
@@ -3768,22 +3756,6 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
 
 /*------------------------- Device initialization ---------------------------*/
 
-static void bond_set_xmit_hash_policy(struct bonding *bond)
-{
-	switch (bond->params.xmit_policy) {
-	case BOND_XMIT_POLICY_LAYER23:
-		bond->xmit_hash_policy = bond_xmit_hash_policy_l23;
-		break;
-	case BOND_XMIT_POLICY_LAYER34:
-		bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
-		break;
-	case BOND_XMIT_POLICY_LAYER2:
-	default:
-		bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
-		break;
-	}
-}
-
 /*
  * Lookup the slave that corresponds to a qid
  */
@@ -3894,38 +3866,6 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
-/*
- * set bond mode specific net device operations
- */
-void bond_set_mode_ops(struct bonding *bond, int mode)
-{
-	struct net_device *bond_dev = bond->dev;
-
-	switch (mode) {
-	case BOND_MODE_ROUNDROBIN:
-		break;
-	case BOND_MODE_ACTIVEBACKUP:
-		break;
-	case BOND_MODE_XOR:
-		bond_set_xmit_hash_policy(bond);
-		break;
-	case BOND_MODE_BROADCAST:
-		break;
-	case BOND_MODE_8023AD:
-		bond_set_xmit_hash_policy(bond);
-		break;
-	case BOND_MODE_ALB:
-		/* FALLTHRU */
-	case BOND_MODE_TLB:
-		break;
-	default:
-		/* Should never happen, mode already checked */
-		pr_err("%s: Error: Unknown bonding mode %d\n",
-		       bond_dev->name, mode);
-		break;
-	}
-}
-
 static int bond_ethtool_get_settings(struct net_device *bond_dev,
 				     struct ethtool_cmd *ecmd)
 {
@@ -4027,7 +3967,6 @@ static void bond_setup(struct net_device *bond_dev)
 	ether_setup(bond_dev);
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
-	bond_set_mode_ops(bond, bond->params.mode);
 
 	bond_dev->destructor = bond_destructor;
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index e06c644470b1..e9249527e7e7 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -318,7 +318,6 @@ static ssize_t bonding_store_mode(struct device *d,
 	/* don't cache arp_validate between modes */
 	bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
 	bond->params.mode = new_value;
-	bond_set_mode_ops(bond, bond->params.mode);
 	pr_info("%s: setting mode to %s (%d).\n",
 		bond->dev->name, bond_mode_tbl[new_value].modename,
 		new_value);
@@ -358,7 +357,6 @@ static ssize_t bonding_store_xmit_hash(struct device *d,
 		ret = -EINVAL;
 	} else {
 		bond->params.xmit_policy = new_value;
-		bond_set_mode_ops(bond, bond->params.mode);
 		pr_info("%s: setting xmit hash policy to %s (%d).\n",
 			bond->dev->name,
 			xmit_hashtype_tbl[new_value].modename, new_value);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 9a26fbd82645..0bd04fbda8e9 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -217,7 +217,6 @@ struct bonding {
 	char     proc_file_name[IFNAMSIZ];
 #endif /* CONFIG_PROC_FS */
 	struct   list_head bond_list;
-	int      (*xmit_hash_policy)(struct sk_buff *, int);
 	u16      rr_tx_counter;
 	struct   ad_bond_info ad_info;
 	struct   alb_bond_info alb_info;
@@ -409,7 +408,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 void bond_mii_monitor(struct work_struct *);
 void bond_loadbalance_arp_mon(struct work_struct *);
 void bond_activebackup_arp_mon(struct work_struct *);
-void bond_set_mode_ops(struct bonding *bond, int mode);
+int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count);
 int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl);
 void bond_select_active_slave(struct bonding *bond);
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h
index a17edda8a781..9635a62f6f89 100644
--- a/include/uapi/linux/if_bonding.h
+++ b/include/uapi/linux/if_bonding.h
@@ -91,6 +91,8 @@
 #define BOND_XMIT_POLICY_LAYER2		0 /* layer 2 (MAC only), default */
 #define BOND_XMIT_POLICY_LAYER34	1 /* layer 3+4 (IP ^ (TCP || UDP)) */
 #define BOND_XMIT_POLICY_LAYER23	2 /* layer 2+3 (IP ^ MAC) */
+#define BOND_XMIT_POLICY_ENCAP23	3 /* encapsulated layer 2+3 */
+#define BOND_XMIT_POLICY_ENCAP34	4 /* encapsulated layer 3+4 */
 
 typedef struct ifbond {
 	__s32 bond_mode;
-- 
cgit 


From f9d32f25084ce7a27f966a0e71eae6ee0fe2f5ab Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 29 Sep 2013 10:51:01 +0200
Subject: media: core: Don't use i2c_client->driver

The 'driver' field of the i2c_client struct is redundant and is going to be
removed. The results of the expressions 'client->driver.driver->field' and
'client->dev.driver->field' are identical, so replace all occurrences of the
former with the later.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/media/v4l2-core/tuner-core.c  |  6 +++---
 drivers/media/v4l2-core/v4l2-common.c | 10 +++++-----
 include/media/v4l2-common.h           |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/tuner-core.c b/drivers/media/v4l2-core/tuner-core.c
index ddc9379eb276..4133af01774a 100644
--- a/drivers/media/v4l2-core/tuner-core.c
+++ b/drivers/media/v4l2-core/tuner-core.c
@@ -43,7 +43,7 @@
 
 #define UNSET (-1U)
 
-#define PREFIX (t->i2c->driver->driver.name)
+#define PREFIX (t->i2c->dev.driver->name)
 
 /*
  * Driver modprobe parameters
@@ -452,7 +452,7 @@ static void set_type(struct i2c_client *c, unsigned int type,
 	}
 
 	tuner_dbg("%s %s I2C addr 0x%02x with type %d used for 0x%02x\n",
-		  c->adapter->name, c->driver->driver.name, c->addr << 1, type,
+		  c->adapter->name, c->dev.driver->name, c->addr << 1, type,
 		  t->mode_mask);
 	return;
 
@@ -556,7 +556,7 @@ static void tuner_lookup(struct i2c_adapter *adap,
 		int mode_mask;
 
 		if (pos->i2c->adapter != adap ||
-		    strcmp(pos->i2c->driver->driver.name, "tuner"))
+		    strcmp(pos->i2c->dev.driver->name, "tuner"))
 			continue;
 
 		mode_mask = pos->mode_mask;
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 037d7a55aa8c..433d6d77942e 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -236,14 +236,14 @@ void v4l2_i2c_subdev_init(struct v4l2_subdev *sd, struct i2c_client *client,
 	v4l2_subdev_init(sd, ops);
 	sd->flags |= V4L2_SUBDEV_FL_IS_I2C;
 	/* the owner is the same as the i2c_client's driver owner */
-	sd->owner = client->driver->driver.owner;
+	sd->owner = client->dev.driver->owner;
 	sd->dev = &client->dev;
 	/* i2c_client and v4l2_subdev point to one another */
 	v4l2_set_subdevdata(sd, client);
 	i2c_set_clientdata(client, sd);
 	/* initialize name */
 	snprintf(sd->name, sizeof(sd->name), "%s %d-%04x",
-		client->driver->driver.name, i2c_adapter_id(client->adapter),
+		client->dev.driver->name, i2c_adapter_id(client->adapter),
 		client->addr);
 }
 EXPORT_SYMBOL_GPL(v4l2_i2c_subdev_init);
@@ -274,11 +274,11 @@ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev,
 	   loaded. This delay-load mechanism doesn't work if other drivers
 	   want to use the i2c device, so explicitly loading the module
 	   is the best alternative. */
-	if (client == NULL || client->driver == NULL)
+	if (client == NULL || client->dev.driver == NULL)
 		goto error;
 
 	/* Lock the module so we can safely get the v4l2_subdev pointer */
-	if (!try_module_get(client->driver->driver.owner))
+	if (!try_module_get(client->dev.driver->owner))
 		goto error;
 	sd = i2c_get_clientdata(client);
 
@@ -287,7 +287,7 @@ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev,
 	if (v4l2_device_register_subdev(v4l2_dev, sd))
 		sd = NULL;
 	/* Decrease the module use count to match the first try_module_get. */
-	module_put(client->driver->driver.owner);
+	module_put(client->dev.driver->owner);
 
 error:
 	/* If we have a client but no subdev, then something went wrong and
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 16550c439008..a707529841e2 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -35,7 +35,7 @@
 	printk(level "%s %d-%04x: " fmt, name, i2c_adapter_id(adapter), addr , ## arg)
 
 #define v4l_client_printk(level, client, fmt, arg...)			    \
-	v4l_printk(level, (client)->driver->driver.name, (client)->adapter, \
+	v4l_printk(level, (client)->dev.driver->name, (client)->adapter, \
 		   (client)->addr, fmt , ## arg)
 
 #define v4l_err(client, fmt, arg...) \
-- 
cgit 


From 0acc2b321342aa813fa9fc485afb09fbc811f594 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 29 Sep 2013 10:51:06 +0200
Subject: i2c: Remove redundant 'driver' field from the i2c_client struct

The 'driver' field of the i2c_client struct is redundant. The same data can be
accessed through to_i2c_driver(client->dev.driver). The generated code for both
approaches in more or less the same.

E.g. on ARM the expression client->driver->command(...) generates

		...
		ldr     r3, [r0, #28]
		ldr     r3, [r3, #32]
		blx     r3
		...

and the expression to_i2c_driver(client->dev.driver)->command(...) generates

		...
		ldr     r3, [r0, #160]
    	ldr     r3, [r3, #-4]
    	blx     r3
		...

Other architectures will generate similar code.

All users of the 'driver' field outside of the I2C core have already been
converted. So this only leaves the core itself. This patch converts the
remaining few users in the I2C core and then removes the 'driver' field from the
i2c_client struct.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-core.c  | 21 ++++++++++++---------
 drivers/i2c/i2c-smbus.c | 10 ++++++----
 include/linux/i2c.h     |  2 --
 3 files changed, 18 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 29d3f045a2bf..430c001b3f1e 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -248,17 +248,16 @@ static int i2c_device_probe(struct device *dev)
 	driver = to_i2c_driver(dev->driver);
 	if (!driver->probe || !driver->id_table)
 		return -ENODEV;
-	client->driver = driver;
+
 	if (!device_can_wakeup(&client->dev))
 		device_init_wakeup(&client->dev,
 					client->flags & I2C_CLIENT_WAKE);
 	dev_dbg(dev, "probe\n");
 
 	status = driver->probe(client, i2c_match_id(driver->id_table, client));
-	if (status) {
-		client->driver = NULL;
+	if (status)
 		i2c_set_clientdata(client, NULL);
-	}
+
 	return status;
 }
 
@@ -279,10 +278,9 @@ static int i2c_device_remove(struct device *dev)
 		dev->driver = NULL;
 		status = 0;
 	}
-	if (status == 0) {
-		client->driver = NULL;
+	if (status == 0)
 		i2c_set_clientdata(client, NULL);
-	}
+
 	return status;
 }
 
@@ -1606,9 +1604,14 @@ static int i2c_cmd(struct device *dev, void *_arg)
 {
 	struct i2c_client	*client = i2c_verify_client(dev);
 	struct i2c_cmd_arg	*arg = _arg;
+	struct i2c_driver	*driver;
+
+	if (!client || !client->dev.driver)
+		return 0;
 
-	if (client && client->driver && client->driver->command)
-		client->driver->command(client, arg->cmd, arg->arg);
+	driver = to_i2c_driver(client->dev.driver);
+	if (driver->command)
+		driver->command(client, arg->cmd, arg->arg);
 	return 0;
 }
 
diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index 44d4c6071c15..c99b22987366 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -46,6 +46,7 @@ static int smbus_do_alert(struct device *dev, void *addrp)
 {
 	struct i2c_client *client = i2c_verify_client(dev);
 	struct alert_data *data = addrp;
+	struct i2c_driver *driver;
 
 	if (!client || client->addr != data->addr)
 		return 0;
@@ -54,12 +55,13 @@ static int smbus_do_alert(struct device *dev, void *addrp)
 
 	/*
 	 * Drivers should either disable alerts, or provide at least
-	 * a minimal handler.  Lock so client->driver won't change.
+	 * a minimal handler.  Lock so the driver won't change.
 	 */
 	device_lock(dev);
-	if (client->driver) {
-		if (client->driver->alert)
-			client->driver->alert(client, data->flag);
+	if (client->dev.driver) {
+		driver = to_i2c_driver(client->dev.driver);
+		if (driver->alert)
+			driver->alert(client, data->flag);
 		else
 			dev_warn(&client->dev, "no driver alert()!\n");
 	} else
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 2ab11dc38077..eff50e062be8 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -205,7 +205,6 @@ struct i2c_driver {
  * @name: Indicates the type of the device, usually a chip name that's
  *	generic enough to hide second-sourcing and compatible revisions.
  * @adapter: manages the bus segment hosting this I2C device
- * @driver: device's driver, hence pointer to access routines
  * @dev: Driver model device node for the slave.
  * @irq: indicates the IRQ generated by this device (if any)
  * @detected: member of an i2c_driver.clients list or i2c-core's
@@ -222,7 +221,6 @@ struct i2c_client {
 					/* _LOWER_ 7 bits		*/
 	char name[I2C_NAME_SIZE];
 	struct i2c_adapter *adapter;	/* the adapter we sit on	*/
-	struct i2c_driver *driver;	/* and our access routines	*/
 	struct device dev;		/* the device structure		*/
 	int irq;			/* irq issued by device		*/
 	struct list_head detected;
-- 
cgit 


From 96f817fedec48b59c9e8b22141cec4e56ad47913 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Oct 2013 14:27:25 -0700
Subject: tcp: shrink tcp6_timewait_sock by one cache line

While working on tcp listener refactoring, I found that it
would really make things easier if sock_common could include
the IPv6 addresses needed in the lookups, instead of doing
very complex games to get their values (depending on sock
being SYN_RECV, ESTABLISHED, TIME_WAIT)

For this to happen, I need to be sure that tcp6_timewait_sock
and tcp_timewait_sock consume same number of cache lines.

This is possible if we only use 32bits for tw_ttd, as we remove
one 32bit hole in inet_timewait_sock

inet_tw_time_stamp() is defined and used, even if its current
implementation looks like tcp_time_stamp : We might need finer
resolution for tcp_time_stamp in the future.

Before patch : sizeof(struct tcp6_timewait_sock) = 0xc8

After patch : sizeof(struct tcp6_timewait_sock) = 0xc0

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h | 7 ++++++-
 net/ipv4/inet_diag.c             | 6 +++---
 net/ipv4/inet_timewait_sock.c    | 4 ++--
 net/ipv6/tcp_ipv6.c              | 2 +-
 4 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 48fd3561722c..f528d1b0ac95 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -58,6 +58,11 @@ struct inet_hashinfo;
 # define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG)
 #endif
 
+static inline u32 inet_tw_time_stamp(void)
+{
+	return jiffies;
+}
+
 /* TIME_WAIT reaping mechanism. */
 #define INET_TWDR_TWKILL_SLOTS	8 /* Please keep this a power of 2. */
 
@@ -130,7 +135,7 @@ struct inet_timewait_sock {
 				tw_tos		: 8,
 				tw_ipv6_offset  : 16;
 	kmemcheck_bitfield_end(flags);
-	unsigned long		tw_ttd;
+	u32			tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
 	struct hlist_node	tw_death_node;
 };
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5f648751fce2..22000279efc8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -222,7 +222,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 			       u32 portid, u32 seq, u16 nlmsg_flags,
 			       const struct nlmsghdr *unlh)
 {
-	long tmo;
+	s32 tmo;
 	struct inet_diag_msg *r;
 	struct nlmsghdr *nlh;
 
@@ -234,7 +234,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r = nlmsg_data(nlh);
 	BUG_ON(tw->tw_state != TCP_TIME_WAIT);
 
-	tmo = tw->tw_ttd - jiffies;
+	tmo = tw->tw_ttd - inet_tw_time_stamp();
 	if (tmo < 0)
 		tmo = 0;
 
@@ -248,7 +248,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->id.idiag_dst[0]    = tw->tw_daddr;
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
-	r->idiag_expires      = DIV_ROUND_UP(tmo * 1000, HZ);
+	r->idiag_expires      = jiffies_to_msecs(tmo);
 	r->idiag_rqueue	      = 0;
 	r->idiag_wqueue	      = 0;
 	r->idiag_uid	      = 0;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1f27c9f4afd0..9bcd8f7234ec 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -387,11 +387,11 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw,
 			if (slot >= INET_TWDR_TWKILL_SLOTS)
 				slot = INET_TWDR_TWKILL_SLOTS - 1;
 		}
-		tw->tw_ttd = jiffies + timeo;
+		tw->tw_ttd = inet_tw_time_stamp() + timeo;
 		slot = (twdr->slot + slot) & (INET_TWDR_TWKILL_SLOTS - 1);
 		list = &twdr->cells[slot];
 	} else {
-		tw->tw_ttd = jiffies + (slot << INET_TWDR_RECYCLE_TICK);
+		tw->tw_ttd = inet_tw_time_stamp() + (slot << INET_TWDR_RECYCLE_TICK);
 
 		if (twdr->twcal_hand < 0) {
 			twdr->twcal_hand = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5c71501fc917..dde8bad04481 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1811,7 +1811,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 	const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest = &tw6->tw_v6_daddr;
 	src  = &tw6->tw_v6_rcv_saddr;
-- 
cgit 


From 4ae1a5bd3fabd7f7f3575309c7a0d676fecf6303 Mon Sep 17 00:00:00 2001
From: Thomas Pugliese <thomas.pugliese@gmail.com>
Date: Tue, 1 Oct 2013 14:04:35 -0500
Subject: usb: wusbcore: Add isoc transfer type enum and packet definitions

This patch adds transfer type enum and packet definitions for
WA_XFER_ISO_PACKET_INFO and WA_XFER_ISO_PACKET_STATUS packets.

It also changes instances of __attribute__((packed)) to __packed to make
checkpatch.pl happy.

Signed-off-by: Thomas Pugliese <thomas.pugliese@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/wusb-wa.h | 45 +++++++++++++++++++++++++++++++++------------
 1 file changed, 33 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h
index 4ff744e2b678..9ae7e299bf77 100644
--- a/include/linux/usb/wusb-wa.h
+++ b/include/linux/usb/wusb-wa.h
@@ -142,7 +142,7 @@ enum wa_notif_type {
 struct wa_notif_hdr {
 	u8 bLength;
 	u8 bNotifyType;			/* enum wa_notif_type */
-} __attribute__((packed));
+} __packed;
 
 /**
  * HWA DN Received notification [(WUSB] section 8.5.4.2)
@@ -158,7 +158,7 @@ struct hwa_notif_dn {
 	u8 bSourceDeviceAddr;		/* from errata 2005/07 */
 	u8 bmAttributes;
 	struct wusb_dn_hdr dndata[];
-} __attribute__((packed));
+} __packed;
 
 /* [WUSB] section 8.3.3 */
 enum wa_xfer_type {
@@ -167,6 +167,8 @@ enum wa_xfer_type {
 	WA_XFER_TYPE_ISO = 0x82,
 	WA_XFER_RESULT = 0x83,
 	WA_XFER_ABORT = 0x84,
+	WA_XFER_ISO_PACKET_INFO = 0xA0,
+	WA_XFER_ISO_PACKET_STATUS = 0xA1,
 };
 
 /* [WUSB] section 8.3.3 */
@@ -177,28 +179,47 @@ struct wa_xfer_hdr {
 	__le32 dwTransferID;		/* Host-assigned ID */
 	__le32 dwTransferLength;	/* Length of data to xfer */
 	u8 bTransferSegment;
-} __attribute__((packed));
+} __packed;
 
 struct wa_xfer_ctl {
 	struct wa_xfer_hdr hdr;
 	u8 bmAttribute;
 	__le16 wReserved;
 	struct usb_ctrlrequest baSetupData;
-} __attribute__((packed));
+} __packed;
 
 struct wa_xfer_bi {
 	struct wa_xfer_hdr hdr;
 	u8 bReserved;
 	__le16 wReserved;
-} __attribute__((packed));
+} __packed;
 
+/* [WUSB] section 8.5.5 */
 struct wa_xfer_hwaiso {
 	struct wa_xfer_hdr hdr;
 	u8 bReserved;
 	__le16 wPresentationTime;
 	__le32 dwNumOfPackets;
-	/* FIXME: u8 pktdata[]? */
-} __attribute__((packed));
+} __packed;
+
+struct wa_xfer_packet_info_hwaiso {
+	__le16 wLength;
+	u8 bPacketType;
+	u8 bReserved;
+	__le16 PacketLength[0];
+} __packed;
+
+struct wa_xfer_packet_status_len_hwaiso {
+	__le16 PacketLength;
+	__le16 PacketStatus;
+} __packed;
+
+struct wa_xfer_packet_status_hwaiso {
+	__le16 wLength;
+	u8 bPacketType;
+	u8 bReserved;
+	struct wa_xfer_packet_status_len_hwaiso PacketStatus[0];
+} __packed;
 
 /* [WUSB] section 8.3.3.5 */
 struct wa_xfer_abort {
@@ -206,7 +227,7 @@ struct wa_xfer_abort {
 	u8 bRequestType;
 	__le16 wRPipe;			/* RPipe index */
 	__le32 dwTransferID;		/* Host-assigned ID */
-} __attribute__((packed));
+} __packed;
 
 /**
  * WA Transfer Complete notification ([WUSB] section 8.3.3.3)
@@ -216,7 +237,7 @@ struct wa_notif_xfer {
 	struct wa_notif_hdr hdr;
 	u8 bEndpoint;
 	u8 Reserved;
-} __attribute__((packed));
+} __packed;
 
 /** Transfer result basic codes [WUSB] table 8-15 */
 enum {
@@ -243,7 +264,7 @@ struct wa_xfer_result {
 	u8     bTransferSegment;
 	u8     bTransferStatus;
 	__le32 dwNumOfPackets;
-} __attribute__((packed));
+} __packed;
 
 /**
  * Wire Adapter Class Descriptor ([WUSB] section 8.5.2.7).
@@ -267,7 +288,7 @@ struct usb_wa_descriptor {
 	u8	bPwrOn2PwrGood;
 	u8	bNumMMCIEs;
 	u8	DeviceRemovable;	/* FIXME: in DWA this is up to 16 bytes */
-} __attribute__((packed));
+} __packed;
 
 /**
  * HWA Device Information Buffer (WUSB1.0[T8.54])
@@ -277,6 +298,6 @@ struct hwa_dev_info {
 	u8	bDeviceAddress;
 	__le16	wPHYRates;
 	u8	bmDeviceAttribute;
-} __attribute__((packed));
+} __packed;
 
 #endif /* #ifndef __LINUX_USB_WUSB_WA_H */
-- 
cgit 


From 4fd06af96b9397fc54eb6b1a013a60c34693eef0 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 3 Oct 2013 18:12:30 +0300
Subject: usb: phy: omap-control: Get rid of platform data

omap-control device is present from OMAP4 onwards which
support device tree boots only. So get rid of platform data.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-omap-control.c   | 12 +++---------
 include/linux/usb/omap_control_usb.h |  4 ----
 2 files changed, 3 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/phy/phy-omap-control.c b/drivers/usb/phy/phy-omap-control.c
index a4dda8e12562..977259252a8e 100644
--- a/drivers/usb/phy/phy-omap-control.c
+++ b/drivers/usb/phy/phy-omap-control.c
@@ -197,8 +197,6 @@ static int omap_control_usb_probe(struct platform_device *pdev)
 {
 	struct resource	*res;
 	struct device_node *np = pdev->dev.of_node;
-	struct omap_control_usb_platform_data *pdata =
-			dev_get_platdata(&pdev->dev);
 
 	control_usb = devm_kzalloc(&pdev->dev, sizeof(*control_usb),
 		GFP_KERNEL);
@@ -207,14 +205,10 @@ static int omap_control_usb_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	if (np) {
+	if (np)
 		of_property_read_u32(np, "ti,type", &control_usb->type);
-	} else if (pdata) {
-		control_usb->type = pdata->type;
-	} else {
-		dev_err(&pdev->dev, "no pdata present\n");
-		return -EINVAL;
-	}
+	else
+		return -EINVAL;	/* We only support DT boot */
 
 	control_usb->dev	= &pdev->dev;
 
diff --git a/include/linux/usb/omap_control_usb.h b/include/linux/usb/omap_control_usb.h
index 27b5b8c931b0..e2416b45169b 100644
--- a/include/linux/usb/omap_control_usb.h
+++ b/include/linux/usb/omap_control_usb.h
@@ -31,10 +31,6 @@ struct omap_control_usb {
 	u32 type;
 };
 
-struct omap_control_usb_platform_data {
-	u8 type;
-};
-
 enum omap_control_usb_mode {
 	USB_MODE_UNDEFINED = 0,
 	USB_MODE_HOST,
-- 
cgit 


From 6cb9310a3290beb8c0d31703a2e76b90a10b4ca0 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 3 Oct 2013 18:12:31 +0300
Subject: usb: phy: omap: Add new device types and remove
 omap_control_usb3_phy_power()

Add support for new device types and in the process rid of "ti,type"
device tree property. The correct type of device will be determined
from the compatible string instead.

Introduce a compatible string for each device type. At the moment
we support 4 types OTGHS, USB2, PIPE3 (e.g. USB3) and DRA7USB2.

Update DT binding information to reflect these changes.

Also get rid of omap_control_usb3_phy_power(). Just one function
i.e. omap_control_usb_phy_power() will now take care of all PHY types.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/omap-usb.txt |  30 ++--
 drivers/usb/phy/phy-omap-control.c                 | 173 ++++++++++++---------
 drivers/usb/phy/phy-omap-usb3.c                    |   6 +-
 include/linux/usb/omap_control_usb.h               |  24 +--
 4 files changed, 130 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/usb/omap-usb.txt b/Documentation/devicetree/bindings/usb/omap-usb.txt
index 661cb06a9063..9add35c37ebc 100644
--- a/Documentation/devicetree/bindings/usb/omap-usb.txt
+++ b/Documentation/devicetree/bindings/usb/omap-usb.txt
@@ -83,22 +83,22 @@ omap_dwc3 {
 OMAP CONTROL USB
 
 Required properties:
- - compatible: Should be "ti,omap-control-usb"
+ - compatible: Should be one of
+ "ti,control-phy-otghs" - if it has otghs_control mailbox register as on OMAP4.
+ "ti,control-phy-usb2" - if it has Power down bit in control_dev_conf register
+			e.g. USB2_PHY on OMAP5.
+ "ti,control-phy-pipe3" - if it has DPLL and individual Rx & Tx power control
+			e.g. USB3 PHY and SATA PHY on OMAP5.
+ "ti,control-phy-dra7usb2" - if it has power down register like USB2 PHY on
+			DRA7 platform.
  - reg : Address and length of the register set for the device. It contains
-   the address of "control_dev_conf" and "otghs_control" or "phy_power_usb"
-   depending upon omap4 or omap5.
- - reg-names: The names of the register addresses corresponding to the registers
-   filled in "reg".
- - ti,type: This is used to differentiate whether the control module has
-   usb mailbox or usb3 phy power. omap4 has usb mailbox in control module to
-   notify events to the musb core and omap5 has usb3 phy power register to
-   power on usb3 phy. Should be "1" if it has mailbox and "2" if it has usb3
-   phy power.
+   the address of "otghs_control" for control-phy-otghs or "power" register
+   for other types.
+ - reg-names: should be "otghs_control" control-phy-otghs and "power" for
+   other types.
 
 omap_control_usb: omap-control-usb@4a002300 {
-	compatible = "ti,omap-control-usb";
-	reg = <0x4a002300 0x4>,
-	      <0x4a00233c 0x4>;
-	reg-names = "control_dev_conf", "otghs_control";
-	ti,type = <1>;
+	compatible = "ti,control-phy-otghs";
+	reg = <0x4a00233c 0x4>;
+	reg-names = "otghs_control";
 };
diff --git a/drivers/usb/phy/phy-omap-control.c b/drivers/usb/phy/phy-omap-control.c
index 977259252a8e..1c8a7c5ccb9b 100644
--- a/drivers/usb/phy/phy-omap-control.c
+++ b/drivers/usb/phy/phy-omap-control.c
@@ -20,6 +20,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/clk.h>
@@ -46,61 +47,70 @@ struct device *omap_get_control_dev(void)
 EXPORT_SYMBOL_GPL(omap_get_control_dev);
 
 /**
- * omap_control_usb3_phy_power - power on/off the serializer using control
- *	module
+ * omap_control_usb_phy_power - power on/off the phy using control module reg
  * @dev: the control module device
- * @on: 0 to off and 1 to on based on powering on or off the PHY
- *
- * usb3 PHY driver should call this API to power on or off the PHY.
+ * @on: 0 or 1, based on powering on or off the PHY
  */
-void omap_control_usb3_phy_power(struct device *dev, bool on)
+void omap_control_usb_phy_power(struct device *dev, int on)
 {
 	u32 val;
 	unsigned long rate;
-	struct omap_control_usb	*control_usb = dev_get_drvdata(dev);
+	struct omap_control_usb	*control_usb;
 
-	if (control_usb->type != OMAP_CTRL_DEV_TYPE2)
+	if (IS_ERR(dev) || !dev) {
+		pr_err("%s: invalid device\n", __func__);
 		return;
+	}
 
-	rate = clk_get_rate(control_usb->sys_clk);
-	rate = rate/1000000;
-
-	val = readl(control_usb->phy_power);
-
-	if (on) {
-		val &= ~(OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK |
-			OMAP_CTRL_USB_PWRCTL_CLK_FREQ_MASK);
-		val |= OMAP_CTRL_USB3_PHY_TX_RX_POWERON <<
-			OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
-		val |= rate << OMAP_CTRL_USB_PWRCTL_CLK_FREQ_SHIFT;
-	} else {
-		val &= ~OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK;
-		val |= OMAP_CTRL_USB3_PHY_TX_RX_POWEROFF <<
-			OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
+	control_usb = dev_get_drvdata(dev);
+	if (!control_usb) {
+		dev_err(dev, "%s: invalid control usb device\n", __func__);
+		return;
 	}
 
-	writel(val, control_usb->phy_power);
-}
-EXPORT_SYMBOL_GPL(omap_control_usb3_phy_power);
+	if (control_usb->type == OMAP_CTRL_TYPE_OTGHS)
+		return;
 
-/**
- * omap_control_usb_phy_power - power on/off the phy using control module reg
- * @dev: the control module device
- * @on: 0 or 1, based on powering on or off the PHY
- */
-void omap_control_usb_phy_power(struct device *dev, int on)
-{
-	u32 val;
-	struct omap_control_usb	*control_usb = dev_get_drvdata(dev);
+	val = readl(control_usb->power);
+
+	switch (control_usb->type) {
+	case OMAP_CTRL_TYPE_USB2:
+		if (on)
+			val &= ~OMAP_CTRL_DEV_PHY_PD;
+		else
+			val |= OMAP_CTRL_DEV_PHY_PD;
+		break;
 
-	val = readl(control_usb->dev_conf);
+	case OMAP_CTRL_TYPE_PIPE3:
+		rate = clk_get_rate(control_usb->sys_clk);
+		rate = rate/1000000;
+
+		if (on) {
+			val &= ~(OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK |
+					OMAP_CTRL_USB_PWRCTL_CLK_FREQ_MASK);
+			val |= OMAP_CTRL_USB3_PHY_TX_RX_POWERON <<
+				OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
+			val |= rate << OMAP_CTRL_USB_PWRCTL_CLK_FREQ_SHIFT;
+		} else {
+			val &= ~OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK;
+			val |= OMAP_CTRL_USB3_PHY_TX_RX_POWEROFF <<
+				OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
+		}
+		break;
 
-	if (on)
-		val &= ~OMAP_CTRL_DEV_PHY_PD;
-	else
-		val |= OMAP_CTRL_DEV_PHY_PD;
+	case OMAP_CTRL_TYPE_DRA7USB2:
+		if (on)
+			val &= ~OMAP_CTRL_USB2_PHY_PD;
+		else
+			val |= OMAP_CTRL_USB2_PHY_PD;
+		break;
+	default:
+		dev_err(dev, "%s: type %d not recognized\n",
+					__func__, control_usb->type);
+		break;
+	}
 
-	writel(val, control_usb->dev_conf);
+	writel(val, control_usb->power);
 }
 EXPORT_SYMBOL_GPL(omap_control_usb_phy_power);
 
@@ -172,7 +182,7 @@ void omap_control_usb_set_mode(struct device *dev,
 {
 	struct omap_control_usb	*ctrl_usb;
 
-	if (IS_ERR(dev) || control_usb->type != OMAP_CTRL_DEV_TYPE1)
+	if (IS_ERR(dev) || control_usb->type != OMAP_CTRL_TYPE_OTGHS)
 		return;
 
 	ctrl_usb = dev_get_drvdata(dev);
@@ -193,10 +203,45 @@ void omap_control_usb_set_mode(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(omap_control_usb_set_mode);
 
+#ifdef CONFIG_OF
+
+static const enum omap_control_usb_type otghs_data = OMAP_CTRL_TYPE_OTGHS;
+static const enum omap_control_usb_type usb2_data = OMAP_CTRL_TYPE_USB2;
+static const enum omap_control_usb_type pipe3_data = OMAP_CTRL_TYPE_PIPE3;
+static const enum omap_control_usb_type dra7usb2_data = OMAP_CTRL_TYPE_DRA7USB2;
+
+static const struct of_device_id omap_control_usb_id_table[] = {
+	{
+		.compatible = "ti,control-phy-otghs",
+		.data = &otghs_data,
+	},
+	{
+		.compatible = "ti,control-phy-usb2",
+		.data = &usb2_data,
+	},
+	{
+		.compatible = "ti,control-phy-pipe3",
+		.data = &pipe3_data,
+	},
+	{
+		.compatible = "ti,control-phy-dra7usb2",
+		.data = &dra7usb2_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, omap_control_usb_id_table);
+#endif
+
+
 static int omap_control_usb_probe(struct platform_device *pdev)
 {
 	struct resource	*res;
-	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *of_id;
+
+	of_id = of_match_device(of_match_ptr(omap_control_usb_id_table),
+								&pdev->dev);
+	if (!of_id)
+		return -EINVAL;
 
 	control_usb = devm_kzalloc(&pdev->dev, sizeof(*control_usb),
 		GFP_KERNEL);
@@ -205,36 +250,27 @@ static int omap_control_usb_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	if (np)
-		of_property_read_u32(np, "ti,type", &control_usb->type);
-	else
-		return -EINVAL;	/* We only support DT boot */
-
-	control_usb->dev	= &pdev->dev;
+	control_usb->dev = &pdev->dev;
+	control_usb->type = *(enum omap_control_usb_type *)of_id->data;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-		"control_dev_conf");
-	control_usb->dev_conf = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(control_usb->dev_conf))
-		return PTR_ERR(control_usb->dev_conf);
-
-	if (control_usb->type == OMAP_CTRL_DEV_TYPE1) {
+	if (control_usb->type == OMAP_CTRL_TYPE_OTGHS) {
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 			"otghs_control");
 		control_usb->otghs_control = devm_ioremap_resource(
 			&pdev->dev, res);
 		if (IS_ERR(control_usb->otghs_control))
 			return PTR_ERR(control_usb->otghs_control);
-	}
-
-	if (control_usb->type == OMAP_CTRL_DEV_TYPE2) {
+	} else {
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"phy_power_usb");
-		control_usb->phy_power = devm_ioremap_resource(
-			&pdev->dev, res);
-		if (IS_ERR(control_usb->phy_power))
-			return PTR_ERR(control_usb->phy_power);
+				"power");
+		control_usb->power = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(control_usb->power)) {
+			dev_err(&pdev->dev, "Couldn't get power register\n");
+			return PTR_ERR(control_usb->power);
+		}
+	}
 
+	if (control_usb->type == OMAP_CTRL_TYPE_PIPE3) {
 		control_usb->sys_clk = devm_clk_get(control_usb->dev,
 			"sys_clkin");
 		if (IS_ERR(control_usb->sys_clk)) {
@@ -243,20 +279,11 @@ static int omap_control_usb_probe(struct platform_device *pdev)
 		}
 	}
 
-
 	dev_set_drvdata(control_usb->dev, control_usb);
 
 	return 0;
 }
 
-#ifdef CONFIG_OF
-static const struct of_device_id omap_control_usb_id_table[] = {
-	{ .compatible = "ti,omap-control-usb" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, omap_control_usb_id_table);
-#endif
-
 static struct platform_driver omap_control_usb_driver = {
 	.probe		= omap_control_usb_probe,
 	.driver		= {
diff --git a/drivers/usb/phy/phy-omap-usb3.c b/drivers/usb/phy/phy-omap-usb3.c
index 4e8a0405f956..0824be42cd18 100644
--- a/drivers/usb/phy/phy-omap-usb3.c
+++ b/drivers/usb/phy/phy-omap-usb3.c
@@ -100,7 +100,7 @@ static int omap_usb3_suspend(struct usb_phy *x, int suspend)
 			udelay(1);
 		} while (--timeout);
 
-		omap_control_usb3_phy_power(phy->control_dev, 0);
+		omap_control_usb_phy_power(phy->control_dev, 0);
 
 		phy->is_suspended	= 1;
 	} else if (!suspend && phy->is_suspended) {
@@ -189,7 +189,7 @@ static int omap_usb3_init(struct usb_phy *x)
 	if (ret)
 		return ret;
 
-	omap_control_usb3_phy_power(phy->control_dev, 1);
+	omap_control_usb_phy_power(phy->control_dev, 1);
 
 	return 0;
 }
@@ -245,7 +245,7 @@ static int omap_usb3_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	omap_control_usb3_phy_power(phy->control_dev, 0);
+	omap_control_usb_phy_power(phy->control_dev, 0);
 	usb_add_phy_dev(&phy->phy);
 
 	platform_set_drvdata(pdev, phy);
diff --git a/include/linux/usb/omap_control_usb.h b/include/linux/usb/omap_control_usb.h
index e2416b45169b..61b889a9c67b 100644
--- a/include/linux/usb/omap_control_usb.h
+++ b/include/linux/usb/omap_control_usb.h
@@ -19,16 +19,23 @@
 #ifndef __OMAP_CONTROL_USB_H__
 #define __OMAP_CONTROL_USB_H__
 
+enum omap_control_usb_type {
+	OMAP_CTRL_TYPE_OTGHS = 1,	/* Mailbox OTGHS_CONTROL */
+	OMAP_CTRL_TYPE_USB2,	/* USB2_PHY, power down in CONTROL_DEV_CONF */
+	OMAP_CTRL_TYPE_PIPE3,	/* PIPE3 PHY, DPLL & seperate Rx/Tx power */
+	OMAP_CTRL_TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */
+};
+
 struct omap_control_usb {
 	struct device *dev;
 
-	u32 __iomem *dev_conf;
 	u32 __iomem *otghs_control;
-	u32 __iomem *phy_power;
+	u32 __iomem *power;
+	u32 __iomem *power_aux;
 
 	struct clk *sys_clk;
 
-	u32 type;
+	enum omap_control_usb_type type;
 };
 
 enum omap_control_usb_mode {
@@ -38,10 +45,6 @@ enum omap_control_usb_mode {
 	USB_MODE_DISCONNECT,
 };
 
-/* To differentiate ctrl module IP having either mailbox or USB3 PHY power */
-#define	OMAP_CTRL_DEV_TYPE1		0x1
-#define	OMAP_CTRL_DEV_TYPE2		0x2
-
 #define	OMAP_CTRL_DEV_PHY_PD		BIT(0)
 
 #define	OMAP_CTRL_DEV_AVALID		BIT(0)
@@ -59,10 +62,11 @@ enum omap_control_usb_mode {
 #define	OMAP_CTRL_USB3_PHY_TX_RX_POWERON	0x3
 #define	OMAP_CTRL_USB3_PHY_TX_RX_POWEROFF	0x0
 
+#define OMAP_CTRL_USB2_PHY_PD		BIT(28)
+
 #if IS_ENABLED(CONFIG_OMAP_CONTROL_USB)
 extern struct device *omap_get_control_dev(void);
 extern void omap_control_usb_phy_power(struct device *dev, int on);
-extern void omap_control_usb3_phy_power(struct device *dev, bool on);
 extern void omap_control_usb_set_mode(struct device *dev,
 	enum omap_control_usb_mode mode);
 #else
@@ -75,10 +79,6 @@ static inline void omap_control_usb_phy_power(struct device *dev, int on)
 {
 }
 
-static inline void omap_control_usb3_phy_power(struct device *dev, int on)
-{
-}
-
 static inline void omap_control_usb_set_mode(struct device *dev,
 	enum omap_control_usb_mode mode)
 {
-- 
cgit 


From 8934d3e4d0e7aed1bd067529c667984d7929d92d Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 3 Oct 2013 18:12:34 +0300
Subject: usb: musb: omap2430: Don't use omap_get_control_dev()

omap_get_control_dev() is being deprecated as it doesn't support
multiple instances. As control device is present only from OMAP4
onwards which supports DT only, we use phandles to get the
reference to the control device.

Also get rid of "ti,has-mailbox" property as it is redundant and
we can determine that from whether "ctrl-module" property is present
or not. Get rid of has_mailbox from musb_hdrc_platform_data as well.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/omap-usb.txt |  4 ----
 drivers/usb/musb/omap2430.c                        | 25 ++++++++++++----------
 include/linux/usb/musb.h                           |  2 --
 3 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/usb/omap-usb.txt b/Documentation/devicetree/bindings/usb/omap-usb.txt
index 9add35c37ebc..090e5e22bd2b 100644
--- a/Documentation/devicetree/bindings/usb/omap-usb.txt
+++ b/Documentation/devicetree/bindings/usb/omap-usb.txt
@@ -3,9 +3,6 @@ OMAP GLUE AND OTHER OMAP SPECIFIC COMPONENTS
 OMAP MUSB GLUE
  - compatible : Should be "ti,omap4-musb" or "ti,omap3-musb"
  - ti,hwmods : must be "usb_otg_hs"
- - ti,has-mailbox : to specify that omap uses an external mailbox
-   (in control module) to communicate with the musb core during device connect
-   and disconnect.
  - multipoint : Should be "1" indicating the musb controller supports
    multipoint. This is a MUSB configuration-specific setting.
  - num-eps : Specifies the number of endpoints. This is also a
@@ -31,7 +28,6 @@ SOC specific device node entry
 usb_otg_hs: usb_otg_hs@4a0ab000 {
 	compatible = "ti,omap4-musb";
 	ti,hwmods = "usb_otg_hs";
-	ti,has-mailbox;
 	multipoint = <1>;
 	num-eps = <16>;
 	ram-bits = <12>;
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index d0fc4d9c7b80..9eab645fed8b 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -38,6 +38,7 @@
 #include <linux/delay.h>
 #include <linux/usb/musb-omap.h>
 #include <linux/usb/omap_control_usb.h>
+#include <linux/of_platform.h>
 
 #include "musb_core.h"
 #include "omap2430.h"
@@ -524,8 +525,12 @@ static int omap2430_probe(struct platform_device *pdev)
 	glue->dev			= &pdev->dev;
 	glue->musb			= musb;
 	glue->status			= OMAP_MUSB_UNKNOWN;
+	glue->control_otghs = ERR_PTR(-ENODEV);
 
 	if (np) {
+		struct device_node *control_node;
+		struct platform_device *control_pdev;
+
 		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 		if (!pdata) {
 			dev_err(&pdev->dev,
@@ -554,22 +559,20 @@ static int omap2430_probe(struct platform_device *pdev)
 		of_property_read_u32(np, "ram-bits", (u32 *)&config->ram_bits);
 		of_property_read_u32(np, "power", (u32 *)&pdata->power);
 		config->multipoint = of_property_read_bool(np, "multipoint");
-		pdata->has_mailbox = of_property_read_bool(np,
-		    "ti,has-mailbox");
 
 		pdata->board_data	= data;
 		pdata->config		= config;
-	}
 
-	if (pdata->has_mailbox) {
-		glue->control_otghs = omap_get_control_dev();
-		if (IS_ERR(glue->control_otghs)) {
-			dev_vdbg(&pdev->dev, "Failed to get control device\n");
-			ret = PTR_ERR(glue->control_otghs);
-			goto err2;
+		control_node = of_parse_phandle(np, "ctrl-module", 0);
+		if (control_node) {
+			control_pdev = of_find_device_by_node(control_node);
+			if (!control_pdev) {
+				dev_err(&pdev->dev, "Failed to get control device\n");
+				ret = -EINVAL;
+				goto err2;
+			}
+			glue->control_otghs = &control_pdev->dev;
 		}
-	} else {
-		glue->control_otghs = ERR_PTR(-ENODEV);
 	}
 	pdata->platform_ops		= &omap2430_ops;
 
diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h
index 053c26841cc3..eb505250940a 100644
--- a/include/linux/usb/musb.h
+++ b/include/linux/usb/musb.h
@@ -99,8 +99,6 @@ struct musb_hdrc_platform_data {
 	/* MUSB_HOST, MUSB_PERIPHERAL, or MUSB_OTG */
 	u8		mode;
 
-	u8		has_mailbox:1;
-
 	/* for clk_get() */
 	const char	*clock;
 
-- 
cgit 


From 0bb85dc2d3f7117b6686661aba4a88dedead0c8a Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Thu, 3 Oct 2013 18:12:35 +0300
Subject: usb: phy: omap: get rid of omap_get_control_dev()

This function was preventing us from supporting multiple
instances. Get rid of it. Since we support DT boots only,
users can get the control device phandle from the DT node.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-omap-control.c   | 31 ++++++++++---------------------
 include/linux/usb/omap_control_usb.h |  5 -----
 2 files changed, 10 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/phy/phy-omap-control.c b/drivers/usb/phy/phy-omap-control.c
index 1c8a7c5ccb9b..09c5ace1edd8 100644
--- a/drivers/usb/phy/phy-omap-control.c
+++ b/drivers/usb/phy/phy-omap-control.c
@@ -26,26 +26,6 @@
 #include <linux/clk.h>
 #include <linux/usb/omap_control_usb.h>
 
-static struct omap_control_usb *control_usb;
-
-/**
- * omap_get_control_dev - returns the device pointer for this control device
- *
- * This API should be called to get the device pointer for this control
- * module device. This device pointer should be used for called other
- * exported API's in this driver.
- *
- * To be used by PHY driver and glue driver.
- */
-struct device *omap_get_control_dev(void)
-{
-	if (!control_usb)
-		return ERR_PTR(-ENODEV);
-
-	return control_usb->dev;
-}
-EXPORT_SYMBOL_GPL(omap_get_control_dev);
-
 /**
  * omap_control_usb_phy_power - power on/off the phy using control module reg
  * @dev: the control module device
@@ -182,11 +162,19 @@ void omap_control_usb_set_mode(struct device *dev,
 {
 	struct omap_control_usb	*ctrl_usb;
 
-	if (IS_ERR(dev) || control_usb->type != OMAP_CTRL_TYPE_OTGHS)
+	if (IS_ERR(dev) || !dev)
 		return;
 
 	ctrl_usb = dev_get_drvdata(dev);
 
+	if (!ctrl_usb) {
+		dev_err(dev, "Invalid control usb device\n");
+		return;
+	}
+
+	if (ctrl_usb->type != OMAP_CTRL_TYPE_OTGHS)
+		return;
+
 	switch (mode) {
 	case USB_MODE_HOST:
 		omap_control_usb_host_mode(ctrl_usb);
@@ -237,6 +225,7 @@ static int omap_control_usb_probe(struct platform_device *pdev)
 {
 	struct resource	*res;
 	const struct of_device_id *of_id;
+	struct omap_control_usb *control_usb;
 
 	of_id = of_match_device(of_match_ptr(omap_control_usb_id_table),
 								&pdev->dev);
diff --git a/include/linux/usb/omap_control_usb.h b/include/linux/usb/omap_control_usb.h
index 61b889a9c67b..596b01918813 100644
--- a/include/linux/usb/omap_control_usb.h
+++ b/include/linux/usb/omap_control_usb.h
@@ -65,15 +65,10 @@ enum omap_control_usb_mode {
 #define OMAP_CTRL_USB2_PHY_PD		BIT(28)
 
 #if IS_ENABLED(CONFIG_OMAP_CONTROL_USB)
-extern struct device *omap_get_control_dev(void);
 extern void omap_control_usb_phy_power(struct device *dev, int on);
 extern void omap_control_usb_set_mode(struct device *dev,
 	enum omap_control_usb_mode mode);
 #else
-static inline struct device *omap_get_control_dev(void)
-{
-	return ERR_PTR(-ENODEV);
-}
 
 static inline void omap_control_usb_phy_power(struct device *dev, int on)
 {
-- 
cgit 


From 5b8802143a4a3e38906879e78f2c1415c5b3db73 Mon Sep 17 00:00:00 2001
From: Weijie Yang <weijie.yang@samsung.com>
Date: Fri, 27 Sep 2013 17:09:07 +0800
Subject: fs/debugfs: add declaration for no CONFIG_DEBUG_FS

Two function declarations are absence if not define CONFIG_DEBUG_FS
in include/linux/debugfs.h

Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/debugfs.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 263489d0788d..4d0b4d1aa132 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -206,6 +206,12 @@ static inline struct dentry *debugfs_create_size_t(const char *name, umode_t mod
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode,
+				     struct dentry *parent, atomic_t *value)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode,
 						 struct dentry *parent,
 						 u32 *value)
@@ -227,6 +233,12 @@ static inline struct dentry *debugfs_create_regset32(const char *name,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline int debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs,
+			 int nregs, void __iomem *base, char *prefix)
+{
+	return 0;
+}
+
 static inline bool debugfs_initialized(void)
 {
 	return false;
-- 
cgit 


From fdfbbd07e91f8fe387140776f3fd94605f0c89e5 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Fri, 20 Sep 2013 07:40:39 -0700
Subject: perf: Add generic transaction flags

Add a generic qualifier for transaction events, as a new sample
type that returns a flag word. This is particularly useful
for qualifying aborts: to distinguish aborts which happen
due to asynchronous events (like conflicts caused by another
CPU) versus instructions that lead to an abort.

The tuning strategies are very different for those cases,
so it's important to distinguish them easily and early.

Since it's inconvenient and inflexible to filter for this
in the kernel we report all the events out and allow
some post processing in user space.

The flags are based on the Intel TSX events, but should be fairly
generic and mostly applicable to other HTM architectures too. In addition
to various flag words there's also reserved space to report an
program supplied abort code. For TSX this is used to distinguish specific
classes of aborts, like a lock busy abort when doing lock elision.

Flags:

Elision and generic transactions 		   (ELISION vs TRANSACTION)
(HLE vs RTM on TSX; IBM etc.  would likely only use TRANSACTION)
Aborts caused by current thread vs aborts caused by others (SYNC vs ASYNC)
Retryable transaction				   (RETRY)
Conflicts with other threads			   (CONFLICT)
Transaction write capacity overflow		   (CAPACITY WRITE)
Transaction read capacity overflow		   (CAPACITY READ)

Transactions implicitely aborted can also return an abort code.
This can be used to signal specific events to the profiler. A common
case is abort on lock busy in a RTM eliding library (code 0xff)
To handle this case we include the TSX abort code

Common example aborts in TSX would be:

- Data conflict with another thread on memory read.
                                      Flags: TRANSACTION|ASYNC|CONFLICT
- executing a WRMSR in a transaction. Flags: TRANSACTION|SYNC
- HLE transaction in user space is too large
                                      Flags: ELISION|SYNC|CAPACITY-WRITE

The only flag that is somewhat TSX specific is ELISION.

This adds the perf core glue needed for reporting the new flag word out.

v2: Add MEM/MISC
v3: Move transaction to the end
v4: Separate capacity-read/write and remove misc
v5: Remove _SAMPLE. Move abort flags to 32bit. Rename
    transaction to txn
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1379688044-14173-2-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h      |  5 +++++
 include/uapi/linux/perf_event.h | 25 ++++++++++++++++++++++++-
 kernel/events/core.c            |  6 ++++++
 3 files changed, 35 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8ba627c1d60..2e069d1288df 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -584,6 +584,10 @@ struct perf_sample_data {
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
 	u64				weight;
+	/*
+	 * Transaction flags for abort events:
+	 */
+	u64				txn;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -599,6 +603,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = 0;
+	data->txn = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 009a655a5d35..da48837d617d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -136,8 +136,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 
-	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 18,		/* non-ABI */
 };
 
 /*
@@ -180,6 +181,28 @@ enum perf_sample_regs_abi {
 	PERF_SAMPLE_REGS_ABI_64		= 2,
 };
 
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+	PERF_TXN_ELISION        = (1 << 0), /* From elision */
+	PERF_TXN_TRANSACTION    = (1 << 1), /* From transaction */
+	PERF_TXN_SYNC           = (1 << 2), /* Instruction is related */
+	PERF_TXN_ASYNC          = (1 << 3), /* Instruction not related */
+	PERF_TXN_RETRY          = (1 << 4), /* Retry possible */
+	PERF_TXN_CONFLICT       = (1 << 5), /* Conflict abort */
+	PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+	PERF_TXN_CAPACITY_READ  = (1 << 7), /* Capacity read abort */
+
+	PERF_TXN_MAX	        = (1 << 8), /* non-ABI */
+
+	/* bits 32..63 are reserved for the abort code */
+
+	PERF_TXN_ABORT_MASK  = (0xffffffffULL << 32),
+	PERF_TXN_ABORT_SHIFT = 32,
+};
+
 /*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b25d65ce7106..c716385f6483 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1201,6 +1201,9 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_DATA_SRC)
 		size += sizeof(data->data_src.val);
 
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		size += sizeof(data->txn);
+
 	event->header_size = size;
 }
 
@@ -4572,6 +4575,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_DATA_SRC)
 		perf_output_put(handle, data->data_src.val);
 
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		perf_output_put(handle, data->txn);
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
-- 
cgit 


From 2f2a2b60adf368bacd6acd2116c01e32caf936c4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:18 +0200
Subject: sched/wait: Make the signal_pending() checks consistent

There's two patterns to check signals in the __wait_event*() macros:

  if (!signal_pending(current)) {
	schedule();
	continue;
  }
  ret = -ERESTARTSYS;
  break;

And the more natural:

  if (signal_pending(current)) {
	ret = -ERESTARTSYS;
	break;
  }
  schedule();

Change them all into the latter form.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092527.956416254@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/tty.h  | 13 ++++++-------
 include/linux/wait.h | 35 ++++++++++++++++-------------------
 2 files changed, 22 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 64f864651d86..050372979076 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -686,14 +686,13 @@ do {									\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
 		if (condition)						\
 			break;						\
-		if (!signal_pending(current)) {				\
-			tty_unlock(tty);					\
-			schedule();					\
-			tty_lock(tty);					\
-			continue;					\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
 		}							\
-		ret = -ERESTARTSYS;					\
-		break;							\
+		tty_unlock(tty);					\
+		schedule();						\
+		tty_lock(tty);						\
 	}								\
 	finish_wait(&wq, &__wait);					\
 } while (0)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index a67fc1635592..ccf0c529fd37 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -261,12 +261,11 @@ do {									\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
 		if (condition)						\
 			break;						\
-		if (!signal_pending(current)) {				\
-			schedule();					\
-			continue;					\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
 		}							\
-		ret = -ERESTARTSYS;					\
-		break;							\
+		schedule();						\
 	}								\
 	finish_wait(&wq, &__wait);					\
 } while (0)
@@ -302,14 +301,13 @@ do {									\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
 		if (condition)						\
 			break;						\
-		if (!signal_pending(current)) {				\
-			ret = schedule_timeout(ret);			\
-			if (!ret)					\
-				break;					\
-			continue;					\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
 		}							\
-		ret = -ERESTARTSYS;					\
-		break;							\
+		ret = schedule_timeout(ret);				\
+		if (!ret)						\
+			break;						\
 	}								\
 	if (!ret && (condition))					\
 		ret = 1;						\
@@ -439,14 +437,13 @@ do {									\
 			finish_wait(&wq, &__wait);			\
 			break;						\
 		}							\
-		if (!signal_pending(current)) {				\
-			schedule();					\
-			continue;					\
-		}							\
-		ret = -ERESTARTSYS;					\
-		abort_exclusive_wait(&wq, &__wait, 			\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			abort_exclusive_wait(&wq, &__wait, 		\
 				TASK_INTERRUPTIBLE, NULL);		\
-		break;							\
+			break;						\
+		}							\
+		schedule();						\
 	}								\
 } while (0)
 
-- 
cgit 


From 2953ef246b058989657e1e77b36b67566ac06f7b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:19 +0200
Subject: sched/wait: Change timeout logic

Commit 4c663cf ("wait: fix false timeouts when using
wait_event_timeout()") introduced an additional condition check after
a timeout but there's a few issues;

 - it forgot one site
 - it put the check after the main loop; not at the actual timeout
   check.

Cure both; by wrapping the condition (as suggested by Oleg), this
avoids double evaluation of 'condition' which could be quite big.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.028892896@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ccf0c529fd37..b2afd665e4ea 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -179,6 +179,14 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_interruptible_sync_poll(x, m)				\
 	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
 
+#define ___wait_cond_timeout(condition, ret)				\
+({									\
+ 	bool __cond = (condition);					\
+ 	if (__cond && !ret)						\
+ 		ret = 1;						\
+ 	__cond || !ret;							\
+})
+
 #define __wait_event(wq, condition) 					\
 do {									\
 	DEFINE_WAIT(__wait);						\
@@ -217,14 +225,10 @@ do {									\
 									\
 	for (;;) {							\
 		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
-		if (condition)						\
+		if (___wait_cond_timeout(condition, ret))		\
 			break;						\
 		ret = schedule_timeout(ret);				\
-		if (!ret)						\
-			break;						\
 	}								\
-	if (!ret && (condition))					\
-		ret = 1;						\
 	finish_wait(&wq, &__wait);					\
 } while (0)
 
@@ -299,18 +303,14 @@ do {									\
 									\
 	for (;;) {							\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
+		if (___wait_cond_timeout(condition, ret))		\
 			break;						\
 		if (signal_pending(current)) {				\
 			ret = -ERESTARTSYS;				\
 			break;						\
 		}							\
 		ret = schedule_timeout(ret);				\
-		if (!ret)						\
-			break;						\
 	}								\
-	if (!ret && (condition))					\
-		ret = 1;						\
 	finish_wait(&wq, &__wait);					\
 } while (0)
 
@@ -815,7 +815,7 @@ do {									\
 									\
 	for (;;) {							\
 		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
+		if (___wait_cond_timeout(condition, ret))		\
 			break;						\
 		if (signal_pending(current)) {				\
 			ret = -ERESTARTSYS;				\
@@ -824,8 +824,6 @@ do {									\
 		spin_unlock_irq(&lock);					\
 		ret = schedule_timeout(ret);				\
 		spin_lock_irq(&lock);					\
-		if (!ret)						\
-			break;						\
 	}								\
 	finish_wait(&wq, &__wait);					\
 } while (0)
-- 
cgit 


From bb632bc44970f75b66df102e831a4fc0692e9159 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:20 +0200
Subject: sched/wait: Change the wait_exclusive control flow

Purely a preparatory patch; it changes the control flow to match what
will soon be generated by generic code so that that patch can be a
unity transform.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.107994763@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index b2afd665e4ea..7d7819dafcc5 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -428,23 +428,24 @@ do {									\
 
 #define __wait_event_interruptible_exclusive(wq, condition, ret)	\
 do {									\
+	__label__ __out;						\
 	DEFINE_WAIT(__wait);						\
 									\
 	for (;;) {							\
 		prepare_to_wait_exclusive(&wq, &__wait,			\
 					TASK_INTERRUPTIBLE);		\
-		if (condition) {					\
-			finish_wait(&wq, &__wait);			\
+		if (condition)						\
 			break;						\
-		}							\
 		if (signal_pending(current)) {				\
 			ret = -ERESTARTSYS;				\
 			abort_exclusive_wait(&wq, &__wait, 		\
 				TASK_INTERRUPTIBLE, NULL);		\
-			break;						\
+			goto __out;					\
 		}							\
 		schedule();						\
 	}								\
+	finish_wait(&wq, &__wait);					\
+__out:	;								\
 } while (0)
 
 #define wait_event_interruptible_exclusive(wq, condition)		\
-- 
cgit 


From 41a1431b178c3b731d6dfc40b987528b333dd93e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:21 +0200
Subject: sched/wait: Introduce ___wait_event()

There's far too much duplication in the __wait_event macros; in order
to fix this introduce ___wait_event() a macro with the capability to
replace most other macros.

With the previous patches changing the various __wait_event*()
implementations to be more uniform; we can now collapse the lot
without also changing generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.181897111@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 7d7819dafcc5..29d0249e03ab 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -187,6 +187,42 @@ wait_queue_head_t *bit_waitqueue(void *, int);
  	__cond || !ret;							\
 })
 
+#define ___wait_signal_pending(state)					\
+	((state == TASK_INTERRUPTIBLE && signal_pending(current)) ||	\
+	 (state == TASK_KILLABLE && fatal_signal_pending(current)))
+
+#define ___wait_nop_ret		int ret __always_unused
+
+#define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
+do {									\
+	__label__ __out;						\
+	DEFINE_WAIT(__wait);						\
+									\
+	for (;;) {							\
+		if (exclusive)						\
+			prepare_to_wait_exclusive(&wq, &__wait, state); \
+		else							\
+			prepare_to_wait(&wq, &__wait, state);		\
+									\
+		if (condition)						\
+			break;						\
+									\
+		if (___wait_signal_pending(state)) {			\
+			ret = -ERESTARTSYS;				\
+			if (exclusive) {				\
+				abort_exclusive_wait(&wq, &__wait, 	\
+						     state, NULL); 	\
+				goto __out;				\
+			}						\
+			break;						\
+		}							\
+									\
+		cmd;							\
+	}								\
+	finish_wait(&wq, &__wait);					\
+__out:	;								\
+} while (0)
+
 #define __wait_event(wq, condition) 					\
 do {									\
 	DEFINE_WAIT(__wait);						\
-- 
cgit 


From 854267f4384243b19c03a2942e84f06f2beb0952 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:22 +0200
Subject: sched/wait: Collapse __wait_event()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.254863348@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 29d0249e03ab..68e3a628e157 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -224,17 +224,8 @@ __out:	;								\
 } while (0)
 
 #define __wait_event(wq, condition) 					\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		schedule();						\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,		\
+		      ___wait_nop_ret, schedule())
 
 /**
  * wait_event - sleep until a condition gets true
-- 
cgit 


From ddc1994b8217527e1818f690f17597fc9cedf81b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:23 +0200
Subject: sched/wait: Collapse __wait_event_timeout()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.325264677@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 68e3a628e157..546b94efc82e 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -247,17 +247,9 @@ do {									\
 } while (0)
 
 #define __wait_event_timeout(wq, condition, ret)			\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
-		if (___wait_cond_timeout(condition, ret))		\
-			break;						\
-		ret = schedule_timeout(ret);				\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, ___wait_cond_timeout(condition, ret), 	\
+		      TASK_UNINTERRUPTIBLE, 0, ret,			\
+		      ret = schedule_timeout(ret))
 
 /**
  * wait_event_timeout - sleep until a condition gets true or a timeout elapses
-- 
cgit 


From f13f4c41c9cf9cd61c896e46e4e7ba2687e2af9c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:24 +0200
Subject: sched/wait: Collapse __wait_event_interruptible()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.396949919@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 546b94efc82e..39e4bbd2c735 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -277,21 +277,8 @@ do {									\
 })
 
 #define __wait_event_interruptible(wq, condition, ret)			\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
-		schedule();						\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	\
+		      schedule())
 
 /**
  * wait_event_interruptible - sleep until a condition gets true
-- 
cgit 


From c2ebb1fb4eddf3d1d66fe31d1e89e83ee211b81c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:25 +0200
Subject: sched/wait: Collapse __wait_event_interruptible_timeout()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.469616907@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 39e4bbd2c735..a79fb15c1dd4 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -304,21 +304,9 @@ do {									\
 })
 
 #define __wait_event_interruptible_timeout(wq, condition, ret)		\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (___wait_cond_timeout(condition, ret))		\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
-		ret = schedule_timeout(ret);				\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, ___wait_cond_timeout(condition, ret),		\
+		      TASK_INTERRUPTIBLE, 0, ret,			\
+		      ret = schedule_timeout(ret))
 
 /**
  * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
-- 
cgit 


From 48c2521717b39cb6904941ec2847d9775669207a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:26 +0200
Subject: sched/wait: Collapse __wait_event_interruptible_exclusive()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.541716442@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index a79fb15c1dd4..c4ab172daac0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -421,26 +421,8 @@ do {									\
 })
 
 #define __wait_event_interruptible_exclusive(wq, condition, ret)	\
-do {									\
-	__label__ __out;						\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait_exclusive(&wq, &__wait,			\
-					TASK_INTERRUPTIBLE);		\
-		if (condition)						\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			abort_exclusive_wait(&wq, &__wait, 		\
-				TASK_INTERRUPTIBLE, NULL);		\
-			goto __out;					\
-		}							\
-		schedule();						\
-	}								\
-	finish_wait(&wq, &__wait);					\
-__out:	;								\
-} while (0)
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, ret,	\
+		      schedule())
 
 #define wait_event_interruptible_exclusive(wq, condition)		\
 ({									\
-- 
cgit 


From 13cb5042a4b80396f77cf5d599d2c002c57b89dc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:27 +0200
Subject: sched/wait: Collapse __wait_event_lock_irq()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.612813379@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index c4ab172daac0..d64918e09e3c 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -624,20 +624,12 @@ do {									\
 
 
 #define __wait_event_lock_irq(wq, condition, lock, cmd)			\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		spin_unlock_irq(&lock);					\
-		cmd;							\
-		schedule();						\
-		spin_lock_irq(&lock);					\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,		\
+		      ___wait_nop_ret,					\
+		      spin_unlock_irq(&lock);				\
+		      cmd;						\
+		      schedule();					\
+		      spin_lock_irq(&lock))
 
 /**
  * wait_event_lock_irq_cmd - sleep until a condition gets true. The
-- 
cgit 


From 8fbd88fa1717601ef91ced49a32f24786b167065 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:28 +0200
Subject: sched/wait: Collapse __wait_event_interruptible_lock_irq()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.686006009@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 26 ++++++--------------------
 1 file changed, 6 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index d64918e09e3c..a577a85004ae 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -689,26 +689,12 @@ do {									\
 } while (0)
 
 
-#define __wait_event_interruptible_lock_irq(wq, condition,		\
-					    lock, ret, cmd)		\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
-		spin_unlock_irq(&lock);					\
-		cmd;							\
-		schedule();						\
-		spin_lock_irq(&lock);					\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+#define __wait_event_interruptible_lock_irq(wq, condition, lock, ret, cmd) \
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	   \
+		      spin_unlock_irq(&lock);				   \
+		      cmd;						   \
+		      schedule();					   \
+		      spin_lock_irq(&lock))
 
 /**
  * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true.
-- 
cgit 


From a1dc6852ac5eecdcd3122ae01703183a3e88e979 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:29 +0200
Subject: sched/wait: Collapse __wait_event_interruptible_lock_irq_timeout()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.759956109@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index a577a85004ae..5d5408b08ba5 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -763,25 +763,12 @@ do {									\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
-						    lock, ret)		\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (___wait_cond_timeout(condition, ret))		\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
-		spin_unlock_irq(&lock);					\
-		ret = schedule_timeout(ret);				\
-		spin_lock_irq(&lock);					\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+#define __wait_event_interruptible_lock_irq_timeout(wq, condition, lock, ret) \
+	___wait_event(wq, ___wait_cond_timeout(condition, ret),		      \
+		      TASK_INTERRUPTIBLE, 0, ret,	      		      \
+		      spin_unlock_irq(&lock);				      \
+		      ret = schedule_timeout(ret);			      \
+		      spin_lock_irq(&lock));
 
 /**
  * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses.
-- 
cgit 


From 0d1e1c8a430450a3ce61a842cec64f9e2a9f3b05 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:30 +0200
Subject: sched/wait: Collapse __wait_event_interruptible_tty()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.831085521@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/tty.h | 21 ++++-----------------
 1 file changed, 4 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 050372979076..6e803291028f 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -679,23 +679,10 @@ static inline void tty_wait_until_sent_from_close(struct tty_struct *tty,
 })
 
 #define __wait_event_interruptible_tty(tty, wq, condition, ret)		\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE);	\
-		if (condition)						\
-			break;						\
-		if (signal_pending(current)) {				\
-			ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
-		tty_unlock(tty);					\
-		schedule();						\
-		tty_lock(tty);						\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	\
+			tty_unlock(tty);				\
+			schedule();					\
+			tty_lock(tty))
 
 #ifdef CONFIG_PROC_FS
 extern void proc_tty_register_driver(struct tty_driver *);
-- 
cgit 


From cf7361fd961b6f0510572af6cf8ca3ffba07018b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:31 +0200
Subject: sched/wait: Collapse __wait_event_killable()

Reduce macro complexity by using the new ___wait_event() helper.
No change in behaviour, identical generated code.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.898691966@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 5d5408b08ba5..ec3683ee0fc2 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -582,22 +582,7 @@ do {									\
 
 
 #define __wait_event_killable(wq, condition, ret)			\
-do {									\
-	DEFINE_WAIT(__wait);						\
-									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, TASK_KILLABLE);		\
-		if (condition)						\
-			break;						\
-		if (!fatal_signal_pending(current)) {			\
-			schedule();					\
-			continue;					\
-		}							\
-		ret = -ERESTARTSYS;					\
-		break;							\
-	}								\
-	finish_wait(&wq, &__wait);					\
-} while (0)
+	___wait_event(wq, condition, TASK_KILLABLE, 0, ret, schedule())
 
 /**
  * wait_event_killable - sleep until a condition gets true
-- 
cgit 


From ebdc195f2ec68576876216081035293e37318e86 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:32 +0200
Subject: sched/wait: Collapse __wait_event_hrtimeout()

While not a whole-sale replacement like the others we can still reduce
the size of __wait_event_hrtimeout() considerably by noting that the
actual core of __wait_event_hrtimeout() is identical to what
___wait_event() generates.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092528.972793648@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ec3683ee0fc2..c065e8af9749 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -337,7 +337,6 @@ do {									\
 #define __wait_event_hrtimeout(wq, condition, timeout, state)		\
 ({									\
 	int __ret = 0;							\
-	DEFINE_WAIT(__wait);						\
 	struct hrtimer_sleeper __t;					\
 									\
 	hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC,		\
@@ -348,25 +347,15 @@ do {									\
 				       current->timer_slack_ns,		\
 				       HRTIMER_MODE_REL);		\
 									\
-	for (;;) {							\
-		prepare_to_wait(&wq, &__wait, state);			\
-		if (condition)						\
-			break;						\
-		if (state == TASK_INTERRUPTIBLE &&			\
-		    signal_pending(current)) {				\
-			__ret = -ERESTARTSYS;				\
-			break;						\
-		}							\
+	___wait_event(wq, condition, state, 0, __ret,			\
 		if (!__t.task) {					\
 			__ret = -ETIME;					\
 			break;						\
 		}							\
-		schedule();						\
-	}								\
+		schedule());						\
 									\
 	hrtimer_cancel(&__t.timer);					\
 	destroy_hrtimer_on_stack(&__t.timer);				\
-	finish_wait(&wq, &__wait);					\
 	__ret;								\
 })
 
-- 
cgit 


From 35a2af94c7ce7130ca292c68b1d27fcfdb648f6b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Oct 2013 11:22:33 +0200
Subject: sched/wait: Make the __wait_event*() interface more friendly

Change all __wait_event*() implementations to match the corresponding
wait_event*() signature for convenience.

In particular this does away with the weird 'ret' logic. Since there
are __wait_event*() users this requires we update them too.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131002092529.042563462@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/kernel/rtlx.c         |  19 ++++---
 include/linux/tty.h             |  10 ++--
 include/linux/wait.h            | 113 +++++++++++++++++++---------------------
 net/irda/af_irda.c              |   5 +-
 net/netfilter/ipvs/ip_vs_sync.c |   7 +--
 5 files changed, 73 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index d763f11e35e2..2c12ea1668d1 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -172,8 +172,9 @@ int rtlx_open(int index, int can_sleep)
 	if (rtlx == NULL) {
 		if( (p = vpe_get_shared(tclimit)) == NULL) {
 		    if (can_sleep) {
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
-				(p = vpe_get_shared(tclimit)), ret);
+			ret = __wait_event_interruptible(
+					channel_wqs[index].lx_queue,
+					(p = vpe_get_shared(tclimit)));
 			if (ret)
 				goto out_fail;
 		    } else {
@@ -263,11 +264,10 @@ unsigned int rtlx_read_poll(int index, int can_sleep)
 	/* data available to read? */
 	if (chan->lx_read == chan->lx_write) {
 		if (can_sleep) {
-			int ret = 0;
-
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
+			int ret = __wait_event_interruptible(
+				channel_wqs[index].lx_queue,
 				(chan->lx_read != chan->lx_write) ||
-				sp_stopping, ret);
+				sp_stopping);
 			if (ret)
 				return ret;
 
@@ -440,14 +440,13 @@ static ssize_t file_write(struct file *file, const char __user * buffer,
 
 	/* any space left... */
 	if (!rtlx_write_poll(minor)) {
-		int ret = 0;
+		int ret;
 
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 
-		__wait_event_interruptible(channel_wqs[minor].rt_queue,
-					   rtlx_write_poll(minor),
-					   ret);
+		ret = __wait_event_interruptible(channel_wqs[minor].rt_queue,
+					   rtlx_write_poll(minor));
 		if (ret)
 			return ret;
 	}
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 6e803291028f..633cac77f9f9 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -672,14 +672,14 @@ static inline void tty_wait_until_sent_from_close(struct tty_struct *tty,
 #define wait_event_interruptible_tty(tty, wq, condition)		\
 ({									\
 	int __ret = 0;							\
-	if (!(condition)) {						\
-		__wait_event_interruptible_tty(tty, wq, condition, __ret);	\
-	}								\
+	if (!(condition))						\
+		__ret = __wait_event_interruptible_tty(tty, wq,		\
+						       condition);	\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_tty(tty, wq, condition, ret)		\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	\
+#define __wait_event_interruptible_tty(tty, wq, condition)		\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 			tty_unlock(tty);				\
 			schedule();					\
 			tty_lock(tty))
diff --git a/include/linux/wait.h b/include/linux/wait.h
index c065e8af9749..bd4bd7b479b6 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -179,24 +179,23 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_interruptible_sync_poll(x, m)				\
 	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
 
-#define ___wait_cond_timeout(condition, ret)				\
+#define ___wait_cond_timeout(condition)					\
 ({									\
  	bool __cond = (condition);					\
- 	if (__cond && !ret)						\
- 		ret = 1;						\
- 	__cond || !ret;							\
+ 	if (__cond && !__ret)						\
+ 		__ret = 1;						\
+ 	__cond || !__ret;						\
 })
 
 #define ___wait_signal_pending(state)					\
 	((state == TASK_INTERRUPTIBLE && signal_pending(current)) ||	\
 	 (state == TASK_KILLABLE && fatal_signal_pending(current)))
 
-#define ___wait_nop_ret		int ret __always_unused
-
 #define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
-do {									\
+({									\
 	__label__ __out;						\
 	DEFINE_WAIT(__wait);						\
+	long __ret = ret;						\
 									\
 	for (;;) {							\
 		if (exclusive)						\
@@ -208,7 +207,7 @@ do {									\
 			break;						\
 									\
 		if (___wait_signal_pending(state)) {			\
-			ret = -ERESTARTSYS;				\
+			__ret = -ERESTARTSYS;				\
 			if (exclusive) {				\
 				abort_exclusive_wait(&wq, &__wait, 	\
 						     state, NULL); 	\
@@ -220,12 +219,12 @@ do {									\
 		cmd;							\
 	}								\
 	finish_wait(&wq, &__wait);					\
-__out:	;								\
-} while (0)
+__out:	__ret;								\
+})
 
 #define __wait_event(wq, condition) 					\
-	___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,		\
-		      ___wait_nop_ret, schedule())
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    schedule())
 
 /**
  * wait_event - sleep until a condition gets true
@@ -246,10 +245,10 @@ do {									\
 	__wait_event(wq, condition);					\
 } while (0)
 
-#define __wait_event_timeout(wq, condition, ret)			\
-	___wait_event(wq, ___wait_cond_timeout(condition, ret), 	\
-		      TASK_UNINTERRUPTIBLE, 0, ret,			\
-		      ret = schedule_timeout(ret))
+#define __wait_event_timeout(wq, condition, timeout)			\
+	___wait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
+		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_timeout - sleep until a condition gets true or a timeout elapses
@@ -272,12 +271,12 @@ do {									\
 ({									\
 	long __ret = timeout;						\
 	if (!(condition)) 						\
-		__wait_event_timeout(wq, condition, __ret);		\
+		__ret = __wait_event_timeout(wq, condition, timeout);	\
 	__ret;								\
 })
 
-#define __wait_event_interruptible(wq, condition, ret)			\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	\
+#define __wait_event_interruptible(wq, condition)			\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 		      schedule())
 
 /**
@@ -299,14 +298,14 @@ do {									\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
-		__wait_event_interruptible(wq, condition, __ret);	\
+		__ret = __wait_event_interruptible(wq, condition);	\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_timeout(wq, condition, ret)		\
-	___wait_event(wq, ___wait_cond_timeout(condition, ret),		\
-		      TASK_INTERRUPTIBLE, 0, ret,			\
-		      ret = schedule_timeout(ret))
+#define __wait_event_interruptible_timeout(wq, condition, timeout)	\
+	___wait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, 0, timeout,			\
+		      __ret = schedule_timeout(__ret))
 
 /**
  * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses
@@ -330,7 +329,8 @@ do {									\
 ({									\
 	long __ret = timeout;						\
 	if (!(condition))						\
-		__wait_event_interruptible_timeout(wq, condition, __ret); \
+		__ret = __wait_event_interruptible_timeout(wq, 		\
+						condition, timeout);	\
 	__ret;								\
 })
 
@@ -347,7 +347,7 @@ do {									\
 				       current->timer_slack_ns,		\
 				       HRTIMER_MODE_REL);		\
 									\
-	___wait_event(wq, condition, state, 0, __ret,			\
+	__ret = ___wait_event(wq, condition, state, 0, 0,		\
 		if (!__t.task) {					\
 			__ret = -ETIME;					\
 			break;						\
@@ -409,15 +409,15 @@ do {									\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_exclusive(wq, condition, ret)	\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, ret,	\
+#define __wait_event_interruptible_exclusive(wq, condition)		\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
 		      schedule())
 
 #define wait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
-		__wait_event_interruptible_exclusive(wq, condition, __ret);\
+		__ret = __wait_event_interruptible_exclusive(wq, condition);\
 	__ret;								\
 })
 
@@ -570,8 +570,8 @@ do {									\
 
 
 
-#define __wait_event_killable(wq, condition, ret)			\
-	___wait_event(wq, condition, TASK_KILLABLE, 0, ret, schedule())
+#define __wait_event_killable(wq, condition)				\
+	___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
 
 /**
  * wait_event_killable - sleep until a condition gets true
@@ -592,18 +592,17 @@ do {									\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
-		__wait_event_killable(wq, condition, __ret);		\
+		__ret = __wait_event_killable(wq, condition);		\
 	__ret;								\
 })
 
 
 #define __wait_event_lock_irq(wq, condition, lock, cmd)			\
-	___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,		\
-		      ___wait_nop_ret,					\
-		      spin_unlock_irq(&lock);				\
-		      cmd;						\
-		      schedule();					\
-		      spin_lock_irq(&lock))
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    spin_unlock_irq(&lock);			\
+			    cmd;					\
+			    schedule();					\
+			    spin_lock_irq(&lock))
 
 /**
  * wait_event_lock_irq_cmd - sleep until a condition gets true. The
@@ -663,11 +662,11 @@ do {									\
 } while (0)
 
 
-#define __wait_event_interruptible_lock_irq(wq, condition, lock, ret, cmd) \
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, ret,	   \
-		      spin_unlock_irq(&lock);				   \
-		      cmd;						   \
-		      schedule();					   \
+#define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd)	\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,	   	\
+		      spin_unlock_irq(&lock);				\
+		      cmd;						\
+		      schedule();					\
 		      spin_lock_irq(&lock))
 
 /**
@@ -698,10 +697,9 @@ do {									\
 #define wait_event_interruptible_lock_irq_cmd(wq, condition, lock, cmd)	\
 ({									\
 	int __ret = 0;							\
-									\
 	if (!(condition))						\
-		__wait_event_interruptible_lock_irq(wq, condition,	\
-						    lock, __ret, cmd);	\
+		__ret = __wait_event_interruptible_lock_irq(wq, 	\
+						condition, lock, cmd);	\
 	__ret;								\
 })
 
@@ -730,18 +728,18 @@ do {									\
 #define wait_event_interruptible_lock_irq(wq, condition, lock)		\
 ({									\
 	int __ret = 0;							\
-									\
 	if (!(condition))						\
-		__wait_event_interruptible_lock_irq(wq, condition,	\
-						    lock, __ret, );	\
+		__ret = __wait_event_interruptible_lock_irq(wq,		\
+						condition, lock,)	\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_lock_irq_timeout(wq, condition, lock, ret) \
-	___wait_event(wq, ___wait_cond_timeout(condition, ret),		      \
-		      TASK_INTERRUPTIBLE, 0, ret,	      		      \
-		      spin_unlock_irq(&lock);				      \
-		      ret = schedule_timeout(ret);			      \
+#define __wait_event_interruptible_lock_irq_timeout(wq, condition, 	\
+						    lock, timeout) 	\
+	___wait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, 0, ret,	      		\
+		      spin_unlock_irq(&lock);				\
+		      __ret = schedule_timeout(__ret);			\
 		      spin_lock_irq(&lock));
 
 /**
@@ -771,11 +769,10 @@ do {									\
 #define wait_event_interruptible_lock_irq_timeout(wq, condition, lock,	\
 						  timeout)		\
 ({									\
-	int __ret = timeout;						\
-									\
+	long __ret = timeout;						\
 	if (!(condition))						\
-		__wait_event_interruptible_lock_irq_timeout(		\
-					wq, condition, lock, __ret);	\
+		__ret = __wait_event_interruptible_lock_irq_timeout(	\
+					wq, condition, lock, timeout);	\
 	__ret;								\
 })
 
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0578d4fa00a9..0f676908d15b 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -2563,9 +2563,8 @@ bed:
 				  jiffies + msecs_to_jiffies(val));
 
 			/* Wait for IR-LMP to call us back */
-			__wait_event_interruptible(self->query_wait,
-			      (self->cachedaddr != 0 || self->errno == -ETIME),
-						   err);
+			err = __wait_event_interruptible(self->query_wait,
+			      (self->cachedaddr != 0 || self->errno == -ETIME));
 
 			/* If watchdog is still activated, kill it! */
 			del_timer(&(self->watchdog));
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f4484719f3e6..f63c2388f38d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1637,12 +1637,9 @@ static int sync_thread_master(void *data)
 			continue;
 		}
 		while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) {
-			int ret = 0;
-
-			__wait_event_interruptible(*sk_sleep(sk),
+			int ret = __wait_event_interruptible(*sk_sleep(sk),
 						   sock_writeable(sk) ||
-						   kthread_should_stop(),
-						   ret);
+						   kthread_should_stop());
 			if (unlikely(kthread_should_stop()))
 				goto done;
 		}
-- 
cgit 


From fb869b6e91a3ac235f237f73305ecf34cdc4969b Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 4 Oct 2013 10:24:49 +0200
Subject: sched/wait: Clean up wait.h details a bit

Since we are changing wait.h profoundly, use the opportunity to:

 - add a sentence to explain what this file is about
 - remove whitespace noise
 - prettify weird looking line break fixup attempts
 - standardize type definition and initialization sequences
 - use consistent style details

No code is changed.

Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-O8dIie5swnctqpupakatvqyq@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 124 +++++++++++++++++++++++++--------------------------
 1 file changed, 60 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index bd4bd7b479b6..a2726c7dd244 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -1,7 +1,8 @@
 #ifndef _LINUX_WAIT_H
 #define _LINUX_WAIT_H
-
-
+/*
+ * Linux wait queue related types and methods
+ */
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
@@ -13,27 +14,27 @@ typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, v
 int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
 
 struct __wait_queue {
-	unsigned int flags;
+	unsigned int		flags;
 #define WQ_FLAG_EXCLUSIVE	0x01
-	void *private;
-	wait_queue_func_t func;
-	struct list_head task_list;
+	void			*private;
+	wait_queue_func_t	func;
+	struct list_head	task_list;
 };
 
 struct wait_bit_key {
-	void *flags;
-	int bit_nr;
-#define WAIT_ATOMIC_T_BIT_NR -1
+	void			*flags;
+	int			bit_nr;
+#define WAIT_ATOMIC_T_BIT_NR	-1
 };
 
 struct wait_bit_queue {
-	struct wait_bit_key key;
-	wait_queue_t wait;
+	struct wait_bit_key	key;
+	wait_queue_t		wait;
 };
 
 struct __wait_queue_head {
-	spinlock_t lock;
-	struct list_head task_list;
+	spinlock_t		lock;
+	struct list_head	task_list;
 };
 typedef struct __wait_queue_head wait_queue_head_t;
 
@@ -84,17 +85,17 @@ extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct
 
 static inline void init_waitqueue_entry(wait_queue_t *q, struct task_struct *p)
 {
-	q->flags = 0;
-	q->private = p;
-	q->func = default_wake_function;
+	q->flags	= 0;
+	q->private	= p;
+	q->func		= default_wake_function;
 }
 
-static inline void init_waitqueue_func_entry(wait_queue_t *q,
-					wait_queue_func_t func)
+static inline void
+init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func)
 {
-	q->flags = 0;
-	q->private = NULL;
-	q->func = func;
+	q->flags	= 0;
+	q->private	= NULL;
+	q->func		= func;
 }
 
 static inline int waitqueue_active(wait_queue_head_t *q)
@@ -114,8 +115,8 @@ static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
 /*
  * Used for wake-one threads:
  */
-static inline void __add_wait_queue_exclusive(wait_queue_head_t *q,
-					      wait_queue_t *wait)
+static inline void
+__add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	wait->flags |= WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue(q, wait);
@@ -127,23 +128,22 @@ static inline void __add_wait_queue_tail(wait_queue_head_t *head,
 	list_add_tail(&new->task_list, &head->task_list);
 }
 
-static inline void __add_wait_queue_tail_exclusive(wait_queue_head_t *q,
-					      wait_queue_t *wait)
+static inline void
+__add_wait_queue_tail_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
 {
 	wait->flags |= WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue_tail(q, wait);
 }
 
-static inline void __remove_wait_queue(wait_queue_head_t *head,
-							wait_queue_t *old)
+static inline void
+__remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 {
 	list_del(&old->task_list);
 }
 
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			void *key);
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
@@ -170,21 +170,21 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 /*
  * Wakeup macros to be used to report events to the targets.
  */
-#define wake_up_poll(x, m)				\
+#define wake_up_poll(x, m)						\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
-#define wake_up_locked_poll(x, m)				\
+#define wake_up_locked_poll(x, m)					\
 	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
-#define wake_up_interruptible_poll(x, m)			\
+#define wake_up_interruptible_poll(x, m)				\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)				\
 	__wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, (void *) (m))
 
 #define ___wait_cond_timeout(condition)					\
 ({									\
- 	bool __cond = (condition);					\
- 	if (__cond && !__ret)						\
- 		__ret = 1;						\
- 	__cond || !__ret;						\
+	bool __cond = (condition);					\
+	if (__cond && !__ret)						\
+		__ret = 1;						\
+	__cond || !__ret;						\
 })
 
 #define ___wait_signal_pending(state)					\
@@ -209,8 +209,8 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 		if (___wait_signal_pending(state)) {			\
 			__ret = -ERESTARTSYS;				\
 			if (exclusive) {				\
-				abort_exclusive_wait(&wq, &__wait, 	\
-						     state, NULL); 	\
+				abort_exclusive_wait(&wq, &__wait,	\
+						     state, NULL);	\
 				goto __out;				\
 			}						\
 			break;						\
@@ -222,7 +222,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 __out:	__ret;								\
 })
 
-#define __wait_event(wq, condition) 					\
+#define __wait_event(wq, condition)					\
 	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    schedule())
 
@@ -238,9 +238,9 @@ __out:	__ret;								\
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  */
-#define wait_event(wq, condition) 					\
+#define wait_event(wq, condition)					\
 do {									\
-	if (condition)	 						\
+	if (condition)							\
 		break;							\
 	__wait_event(wq, condition);					\
 } while (0)
@@ -270,7 +270,7 @@ do {									\
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
 	long __ret = timeout;						\
-	if (!(condition)) 						\
+	if (!(condition))						\
 		__ret = __wait_event_timeout(wq, condition, timeout);	\
 	__ret;								\
 })
@@ -329,7 +329,7 @@ do {									\
 ({									\
 	long __ret = timeout;						\
 	if (!(condition))						\
-		__ret = __wait_event_interruptible_timeout(wq, 		\
+		__ret = __wait_event_interruptible_timeout(wq,		\
 						condition, timeout);	\
 	__ret;								\
 })
@@ -569,7 +569,6 @@ do {									\
 	 ? 0 : __wait_event_interruptible_locked(wq, condition, 1, 1))
 
 
-
 #define __wait_event_killable(wq, condition)				\
 	___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule())
 
@@ -663,7 +662,7 @@ do {									\
 
 
 #define __wait_event_interruptible_lock_irq(wq, condition, lock, cmd)	\
-	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,	   	\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 		      spin_unlock_irq(&lock);				\
 		      cmd;						\
 		      schedule();					\
@@ -698,7 +697,7 @@ do {									\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
-		__ret = __wait_event_interruptible_lock_irq(wq, 	\
+		__ret = __wait_event_interruptible_lock_irq(wq,		\
 						condition, lock, cmd);	\
 	__ret;								\
 })
@@ -734,18 +733,18 @@ do {									\
 	__ret;								\
 })
 
-#define __wait_event_interruptible_lock_irq_timeout(wq, condition, 	\
-						    lock, timeout) 	\
+#define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
+						    lock, timeout)	\
 	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, ret,	      		\
+		      TASK_INTERRUPTIBLE, 0, ret,			\
 		      spin_unlock_irq(&lock);				\
 		      __ret = schedule_timeout(__ret);			\
 		      spin_lock_irq(&lock));
 
 /**
- * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses.
- *		The condition is checked under the lock. This is expected
- *		to be called with the lock taken.
+ * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets
+ *		true or a timeout elapses. The condition is checked under
+ *		the lock. This is expected to be called with the lock taken.
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @lock: a locked spinlock_t, which will be released before schedule()
@@ -783,11 +782,9 @@ do {									\
  * We plan to remove these interfaces.
  */
 extern void sleep_on(wait_queue_head_t *q);
-extern long sleep_on_timeout(wait_queue_head_t *q,
-				      signed long timeout);
+extern long sleep_on_timeout(wait_queue_head_t *q, signed long timeout);
 extern void interruptible_sleep_on(wait_queue_head_t *q);
-extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
-					   signed long timeout);
+extern long interruptible_sleep_on_timeout(wait_queue_head_t *q, signed long timeout);
 
 /*
  * Waitqueues which are removed from the waitqueue_head at wakeup time
@@ -795,8 +792,7 @@ extern long interruptible_sleep_on_timeout(wait_queue_head_t *q,
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
-void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
-			unsigned int mode, void *key);
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
@@ -842,8 +838,8 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
  * One uses wait_on_bit() where one is waiting for the bit to clear,
  * but has no intention of setting it.
  */
-static inline int wait_on_bit(void *word, int bit,
-				int (*action)(void *), unsigned mode)
+static inline int
+wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
 {
 	if (!test_bit(bit, word))
 		return 0;
@@ -866,8 +862,8 @@ static inline int wait_on_bit(void *word, int bit,
  * One uses wait_on_bit_lock() where one is waiting for the bit to
  * clear with the intention of setting it, and when done, clearing it.
  */
-static inline int wait_on_bit_lock(void *word, int bit,
-				int (*action)(void *), unsigned mode)
+static inline int
+wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode)
 {
 	if (!test_and_set_bit(bit, word))
 		return 0;
@@ -891,5 +887,5 @@ int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
 		return 0;
 	return out_of_line_wait_on_atomic_t(val, action, mode);
 }
-	
-#endif
+
+#endif /* _LINUX_WAIT_H */
-- 
cgit 


From 8e933359ee2c3a861d5022b83110ce88ba3a2dda Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Tue, 24 Sep 2013 11:53:47 +0300
Subject: usb: phy: generic: Add gpio_reset to platform data

The GPIO number of the RESET line can be passed to the
driver using the gpio_reset member.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/usb_phy_gen_xceiv.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h
index f9a7e7bc925b..42f3b71a9775 100644
--- a/include/linux/usb/usb_phy_gen_xceiv.h
+++ b/include/linux/usb/usb_phy_gen_xceiv.h
@@ -9,7 +9,8 @@ struct usb_phy_gen_xceiv_platform_data {
 
 	/* if set fails with -EPROBE_DEFER if can't get regulator */
 	unsigned int needs_vcc:1;
-	unsigned int needs_reset:1;
+	unsigned int needs_reset:1;	/* deprecated */
+	int gpio_reset;
 };
 
 #if IS_ENABLED(CONFIG_NOP_USB_XCEIV)
-- 
cgit 


From f3d3444a4d7f76e79841c59c78105a45295cc4b0 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Sat, 5 Oct 2013 12:01:04 +0200
Subject: Bluetooth: Rename HCI_LE_PERIPHERAL to HCI_ADVERTISING

This flag is used to indicate whether we want to have advertising
enabled or not, so give it a more suitable name.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  2 +-
 net/bluetooth/hci_conn.c    |  2 +-
 net/bluetooth/hci_core.c    |  2 +-
 net/bluetooth/hci_event.c   |  6 +++---
 net/bluetooth/mgmt.c        | 18 +++++++++---------
 5 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index b90eec5e9c06..e8bba05686d1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -118,7 +118,7 @@ enum {
 	HCI_SSP_ENABLED,
 	HCI_HS_ENABLED,
 	HCI_LE_ENABLED,
-	HCI_LE_PERIPHERAL,
+	HCI_ADVERTISING,
 	HCI_CONNECTABLE,
 	HCI_DISCOVERABLE,
 	HCI_LINK_SECURITY,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 08e601c68314..8b0d08fb6158 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -546,7 +546,7 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 {
 	struct hci_conn *conn;
 
-	if (test_bit(HCI_LE_PERIPHERAL, &hdev->flags))
+	if (test_bit(HCI_ADVERTISING, &hdev->flags))
 		return ERR_PTR(-ENOTSUPP);
 
 	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 82dbdc6a7e9e..aa63ebb114d4 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1105,7 +1105,7 @@ static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
 	u8 ad_len = 0, flags = 0;
 	size_t name_len;
 
-	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 		flags |= LE_AD_GENERAL;
 
 	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4785ab0795f5..e1ad858b1fb6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -918,9 +918,9 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 
 	if (!status) {
 		if (*sent)
-			set_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+			set_bit(HCI_ADVERTISING, &hdev->dev_flags);
 		else
-			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
 	}
 
 	if (!test_bit(HCI_INIT, &hdev->flags)) {
@@ -1005,7 +1005,7 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 		} else {
 			hdev->features[1][0] &= ~LMP_HOST_LE;
 			clear_bit(HCI_LE_ENABLED, &hdev->dev_flags);
-			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
 		}
 
 		if (sent->simul)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 16125ff918f1..7e43d376e2e6 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -425,7 +425,7 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (test_bit(HCI_HS_ENABLED, &hdev->dev_flags))
 		settings |= MGMT_SETTING_HS;
 
-	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags))
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 		settings |= MGMT_SETTING_ADVERTISING;
 
 	return settings;
@@ -1463,8 +1463,8 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 			changed = true;
 		}
 
-		if (!val && test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
-			clear_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+		if (!val && test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
 			changed = true;
 		}
 
@@ -1500,7 +1500,7 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	hci_req_init(&req, hdev);
 
-	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags) && !val)
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) && !val)
 		hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(val), &val);
 
 	hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
@@ -2888,7 +2888,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 			goto failed;
 		}
 
-		if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
 			err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY,
 					 MGMT_STATUS_REJECTED);
 			mgmt_pending_remove(cmd);
@@ -3236,13 +3236,13 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data, u1
 	hci_dev_lock(hdev);
 
 	val = !!cp->val;
-	enabled = test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+	enabled = test_bit(HCI_ADVERTISING, &hdev->dev_flags);
 
 	if (!hdev_is_powered(hdev) || val == enabled) {
 		bool changed = false;
 
-		if (val != test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
-			change_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags);
+		if (val != test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+			change_bit(HCI_ADVERTISING, &hdev->dev_flags);
 			changed = true;
 		}
 
@@ -3851,7 +3851,7 @@ static int powered_update_hci(struct hci_dev *hdev)
 				    &hdev->static_addr);
 	}
 
-	if (test_bit(HCI_LE_PERIPHERAL, &hdev->dev_flags)) {
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
 		u8 adv = 0x01;
 
 		hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(adv), &adv);
-- 
cgit 


From d2f5a196d7b401b79e2321b24cc0ac8636ffbc17 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Sat, 5 Oct 2013 12:01:05 +0200
Subject: Bluetooth: Add public mgmt function to send New Settings event

A function is needed so that the HCI event processing can ask the mgmt
code to emit a new settings event. This is necessary e.g. when the event
processing does updates to mgmt related states without any dependency of
actual mgmt commands.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/mgmt.c             | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e09c30577b3a..079c5c55c829 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1123,6 +1123,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 int mgmt_index_added(struct hci_dev *hdev);
 int mgmt_index_removed(struct hci_dev *hdev);
+int mgmt_new_settings(struct hci_dev *hdev);
 int mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7e43d376e2e6..6e808d1d78f3 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -890,6 +890,11 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip)
 	return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip);
 }
 
+int mgmt_new_settings(struct hci_dev *hdev)
+{
+	return new_settings(hdev, NULL);
+}
+
 struct cmd_lookup {
 	struct sock *sk;
 	struct hci_dev *hdev;
-- 
cgit 


From e4a49a6015efa6bd35f107640a497380d5e4ed48 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Oct 2013 13:35:35 +0300
Subject: usb: remove intel_mid_otg.h

It's not used anymore.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/intel_mid_otg.h | 180 --------------------------------------
 1 file changed, 180 deletions(-)
 delete mode 100644 include/linux/usb/intel_mid_otg.h

(limited to 'include')

diff --git a/include/linux/usb/intel_mid_otg.h b/include/linux/usb/intel_mid_otg.h
deleted file mode 100644
index 756cf5543ffd..000000000000
--- a/include/linux/usb/intel_mid_otg.h
+++ /dev/null
@@ -1,180 +0,0 @@
-/*
- * Intel MID (Langwell/Penwell) USB OTG Transceiver driver
- * Copyright (C) 2008 - 2010, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
- */
-
-#ifndef __INTEL_MID_OTG_H
-#define __INTEL_MID_OTG_H
-
-#include <linux/pm.h>
-#include <linux/usb/otg.h>
-#include <linux/notifier.h>
-
-struct intel_mid_otg_xceiv;
-
-/* This is a common data structure for Intel MID platform to
- * save values of the OTG state machine */
-struct otg_hsm {
-	/* Input */
-	int a_bus_resume;
-	int a_bus_suspend;
-	int a_conn;
-	int a_sess_vld;
-	int a_srp_det;
-	int a_vbus_vld;
-	int b_bus_resume;
-	int b_bus_suspend;
-	int b_conn;
-	int b_se0_srp;
-	int b_ssend_srp;
-	int b_sess_end;
-	int b_sess_vld;
-	int id;
-/* id values */
-#define ID_B		0x05
-#define ID_A		0x04
-#define ID_ACA_C	0x03
-#define ID_ACA_B	0x02
-#define ID_ACA_A	0x01
-	int power_up;
-	int adp_change;
-	int test_device;
-
-	/* Internal variables */
-	int a_set_b_hnp_en;
-	int b_srp_done;
-	int b_hnp_enable;
-	int hnp_poll_enable;
-
-	/* Timeout indicator for timers */
-	int a_wait_vrise_tmout;
-	int a_wait_bcon_tmout;
-	int a_aidl_bdis_tmout;
-	int a_bidl_adis_tmout;
-	int a_bidl_adis_tmr;
-	int a_wait_vfall_tmout;
-	int b_ase0_brst_tmout;
-	int b_bus_suspend_tmout;
-	int b_srp_init_tmout;
-	int b_srp_fail_tmout;
-	int b_srp_fail_tmr;
-	int b_adp_sense_tmout;
-
-	/* Informative variables */
-	int a_bus_drop;
-	int a_bus_req;
-	int a_clr_err;
-	int b_bus_req;
-	int a_suspend_req;
-	int b_bus_suspend_vld;
-
-	/* Output */
-	int drv_vbus;
-	int loc_conn;
-	int loc_sof;
-
-	/* Others */
-	int vbus_srp_up;
-};
-
-/* must provide ULPI access function to read/write registers implemented in
- * ULPI address space */
-struct iotg_ulpi_access_ops {
-	int	(*read)(struct intel_mid_otg_xceiv *iotg, u8 reg, u8 *val);
-	int	(*write)(struct intel_mid_otg_xceiv *iotg, u8 reg, u8 val);
-};
-
-#define OTG_A_DEVICE	0x0
-#define OTG_B_DEVICE	0x1
-
-/*
- * the Intel MID (Langwell/Penwell) otg transceiver driver needs to interact
- * with device and host drivers to implement the USB OTG related feature. More
- * function members are added based on usb_phy data structure for this
- * purpose.
- */
-struct intel_mid_otg_xceiv {
-	struct usb_phy		otg;
-	struct otg_hsm		hsm;
-
-	/* base address */
-	void __iomem		*base;
-
-	/* ops to access ulpi */
-	struct iotg_ulpi_access_ops	ulpi_ops;
-
-	/* atomic notifier for interrupt context */
-	struct atomic_notifier_head	iotg_notifier;
-
-	/* start/stop USB Host function */
-	int	(*start_host)(struct intel_mid_otg_xceiv *iotg);
-	int	(*stop_host)(struct intel_mid_otg_xceiv *iotg);
-
-	/* start/stop USB Peripheral function */
-	int	(*start_peripheral)(struct intel_mid_otg_xceiv *iotg);
-	int	(*stop_peripheral)(struct intel_mid_otg_xceiv *iotg);
-
-	/* start/stop ADP sense/probe function */
-	int	(*set_adp_probe)(struct intel_mid_otg_xceiv *iotg,
-					bool enabled, int dev);
-	int	(*set_adp_sense)(struct intel_mid_otg_xceiv *iotg,
-					bool enabled);
-
-#ifdef CONFIG_PM
-	/* suspend/resume USB host function */
-	int	(*suspend_host)(struct intel_mid_otg_xceiv *iotg,
-					pm_message_t message);
-	int	(*resume_host)(struct intel_mid_otg_xceiv *iotg);
-
-	int	(*suspend_peripheral)(struct intel_mid_otg_xceiv *iotg,
-					pm_message_t message);
-	int	(*resume_peripheral)(struct intel_mid_otg_xceiv *iotg);
-#endif
-
-};
-static inline
-struct intel_mid_otg_xceiv *otg_to_mid_xceiv(struct usb_phy *otg)
-{
-	return container_of(otg, struct intel_mid_otg_xceiv, otg);
-}
-
-#define MID_OTG_NOTIFY_CONNECT		0x0001
-#define MID_OTG_NOTIFY_DISCONN		0x0002
-#define MID_OTG_NOTIFY_HSUSPEND		0x0003
-#define MID_OTG_NOTIFY_HRESUME		0x0004
-#define MID_OTG_NOTIFY_CSUSPEND		0x0005
-#define MID_OTG_NOTIFY_CRESUME		0x0006
-#define MID_OTG_NOTIFY_HOSTADD		0x0007
-#define MID_OTG_NOTIFY_HOSTREMOVE	0x0008
-#define MID_OTG_NOTIFY_CLIENTADD	0x0009
-#define MID_OTG_NOTIFY_CLIENTREMOVE	0x000a
-
-static inline int
-intel_mid_otg_register_notifier(struct intel_mid_otg_xceiv *iotg,
-				struct notifier_block *nb)
-{
-	return atomic_notifier_chain_register(&iotg->iotg_notifier, nb);
-}
-
-static inline void
-intel_mid_otg_unregister_notifier(struct intel_mid_otg_xceiv *iotg,
-				struct notifier_block *nb)
-{
-	atomic_notifier_chain_unregister(&iotg->iotg_notifier, nb);
-}
-
-#endif /* __INTEL_MID_OTG_H */
-- 
cgit 


From af190494f9b2e1fb6e1c039e9626c3c334717da1 Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 3 Oct 2013 18:06:23 -0700
Subject: misc: mic: Enable OSPM suspend and resume support.

This patch enables support for OSPM suspend and resume in the MIC
driver. During a host suspend event, the driver performs an
orderly shutdown of the cards if they are online. Upon resume, any
cards that were previously online before suspend are rebooted.
The driver performs an orderly shutdown of the card primarily to
ensure that applications in the card are terminated and mounted
devices are safely un-mounted before the card is powered down in
the event of an OSPM suspend.

The driver makes use of the MIC daemon to accomplish OSPM suspend
and resume. The driver registers a PM notifier per MIC device.
The devices get notified synchronously during PM_SUSPEND_PREPARE and
PM_POST_SUSPEND phases.

During the PM_SUSPEND_PREPARE phase, the driver performs one of the
following three tasks.
1) If the card is 'offline', the driver sets the card to a
   'suspended' state and returns.
2) If the card is 'online', the driver initiates card shutdown by
   setting the card state to suspending. This notifies the MIC
   daemon which invokes shutdown and sets card state to 'suspended'.
   The driver returns after the shutdown is complete.
3) If the card is already being shutdown, possibly by a host user
   space application, the driver sets the card state to 'suspended'
   and returns after the shutdown is complete.

During the PM_POST_SUSPEND phase, the driver simply notifies the
daemon and returns. The daemon boots those cards that were previously
online during the suspend phase.

Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
Signed-off-by: Harshavardhan R Kharche <harshavardhan.r.kharche@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-class-mic.txt |  60 +++++++------
 Documentation/mic/mic_overview.txt            |   4 +-
 Documentation/mic/mpssd/mpssd.c               |  27 +++++-
 Documentation/mic/mpssd/mpssd.h               |   1 +
 drivers/misc/mic/host/mic_boot.c              | 120 +++++++++++++++++++++++++-
 drivers/misc/mic/host/mic_device.h            |   8 ++
 drivers/misc/mic/host/mic_main.c              |  63 +++++++++++++-
 drivers/misc/mic/host/mic_sysfs.c             |   7 ++
 include/uapi/linux/mic_common.h               |   2 +
 9 files changed, 257 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-class-mic.txt b/Documentation/ABI/testing/sysfs-class-mic.txt
index 82cdad3b614a..13f48afc534f 100644
--- a/Documentation/ABI/testing/sysfs-class-mic.txt
+++ b/Documentation/ABI/testing/sysfs-class-mic.txt
@@ -1,6 +1,6 @@
 What:		/sys/class/mic/
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		The mic class directory belongs to Intel MIC devices and
@@ -9,8 +9,8 @@ Description:
 		Integrated Core (MIC) architecture that runs a Linux OS.
 
 What:		/sys/class/mic/mic(x)
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		The directories /sys/class/mic/mic0, /sys/class/mic/mic1 etc.,
@@ -18,33 +18,41 @@ Description:
 		information specific to that MIC device.
 
 What:		/sys/class/mic/mic(x)/family
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		Provides information about the Coprocessor family for an Intel
 		MIC device. For example - "x100"
 
 What:		/sys/class/mic/mic(x)/stepping
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		Provides information about the silicon stepping for an Intel
 		MIC device. For example - "A0" or "B0"
 
 What:		/sys/class/mic/mic(x)/state
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		When read, this entry provides the current state of an Intel
 		MIC device in the context of the card OS. Possible values that
 		will be read are:
-		"offline" - The MIC device is ready to boot the card OS.
+		"offline" - The MIC device is ready to boot the card OS. On
+		reading this entry after an OSPM resume, a "boot" has to be
+		written to this entry if the card was previously shutdown
+		during OSPM suspend.
 		"online" - The MIC device has initiated booting a card OS.
 		"shutting_down" - The card OS is shutting down.
 		"reset_failed" - The MIC device has failed to reset.
+		"suspending" - The MIC device is currently being prepared for
+		suspend. On reading this entry, a "suspend" has to be written
+		to the state sysfs entry to ensure the card is shutdown during
+		OSPM suspend.
+		"suspended" - The MIC device has been suspended.
 
 		When written, this sysfs entry triggers different state change
 		operations depending upon the current state of the card OS.
@@ -54,10 +62,12 @@ Description:
 			sysfs entries.
 		"reset" - Initiates device reset.
 		"shutdown" - Initiates card OS shutdown.
+		"suspend" - Initiates card OS shutdown and also marks the card
+		as suspended.
 
 What:		/sys/class/mic/mic(x)/shutdown_status
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		An Intel MIC device runs a Linux OS during its operation. This
@@ -72,8 +82,8 @@ Description:
 		"restart" - Shutdown because of a restart command.
 
 What:		/sys/class/mic/mic(x)/cmdline
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		An Intel MIC device runs a Linux OS during its operation. Before
@@ -88,8 +98,8 @@ Description:
 		line back to this entry.
 
 What:		/sys/class/mic/mic(x)/firmware
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		When read, this sysfs entry provides the path name under
@@ -98,8 +108,8 @@ Description:
 		firmware image location under /lib/firmware/.
 
 What:		/sys/class/mic/mic(x)/ramdisk
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		When read, this sysfs entry provides the path name under
@@ -108,8 +118,8 @@ Description:
 		the ramdisk image location under /lib/firmware/.
 
 What:		/sys/class/mic/mic(x)/bootmode
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		When read, this sysfs entry provides the current bootmode for
@@ -119,8 +129,8 @@ Description:
 		b) elf - Boot an elf image for flash updates.
 
 What:		/sys/class/mic/mic(x)/log_buf_addr
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		An Intel MIC device runs a Linux OS during its operation. For
@@ -133,8 +143,8 @@ Description:
 		file of the card OS.
 
 What:		/sys/class/mic/mic(x)/log_buf_len
-Date:		August 2013
-KernelVersion:	3.11
+Date:		October 2013
+KernelVersion:	3.13
 Contact:	Sudeep Dutt <sudeep.dutt@intel.com>
 Description:
 		An Intel MIC device runs a Linux OS during its operation. For
diff --git a/Documentation/mic/mic_overview.txt b/Documentation/mic/mic_overview.txt
index c4424ed1b746..b41929224804 100644
--- a/Documentation/mic/mic_overview.txt
+++ b/Documentation/mic/mic_overview.txt
@@ -4,7 +4,9 @@ that runs a Linux OS. It is a PCIe endpoint in a platform and therefore
 implements the three required standard address spaces i.e. configuration,
 memory and I/O. The host OS loads a device driver as is typical for
 PCIe devices. The card itself runs a bootstrap after reset that
-transfers control to the card OS downloaded from the host driver.
+transfers control to the card OS downloaded from the host driver. The
+host driver supports OSPM suspend and resume operations. It shuts down
+the card during suspend and reboots the card OS during resume.
 The card OS as shipped by Intel is a Linux kernel with modifications
 for the X100 devices.
 
diff --git a/Documentation/mic/mpssd/mpssd.c b/Documentation/mic/mpssd/mpssd.c
index 82c6bc2e3cb6..0c980ad40b17 100644
--- a/Documentation/mic/mpssd/mpssd.c
+++ b/Documentation/mic/mpssd/mpssd.c
@@ -1295,7 +1295,13 @@ reset(struct mic_info *mic)
 			goto retry;
 		mpsslog("%s: %s %d state %s\n",
 			mic->name, __func__, __LINE__, state);
-		if ((!strcmp(state, "offline"))) {
+
+		/*
+		 * If the shutdown was initiated by OSPM, the state stays
+		 * in "suspended" which is also a valid condition for reset.
+		 */
+		if ((!strcmp(state, "offline")) ||
+		    (!strcmp(state, "suspended"))) {
 			free(state);
 			break;
 		}
@@ -1334,6 +1340,10 @@ static int get_mic_state(struct mic_info *mic, char *state)
 		return MIC_SHUTTING_DOWN;
 	if (!strcmp(state, "reset_failed"))
 		return MIC_RESET_FAILED;
+	if (!strcmp(state, "suspending"))
+		return MIC_SUSPENDING;
+	if (!strcmp(state, "suspended"))
+		return MIC_SUSPENDED;
 	mpsslog("%s: BUG invalid state %s\n", mic->name, state);
 	/* Invalid state */
 	assert(0);
@@ -1418,6 +1428,17 @@ retry:
 		case MIC_SHUTTING_DOWN:
 			mic_handle_shutdown(mic);
 			goto close_error;
+		case MIC_SUSPENDING:
+			mic->boot_on_resume = 1;
+			setsysfs(mic->name, "state", "suspend");
+			mic_handle_shutdown(mic);
+			goto close_error;
+		case MIC_OFFLINE:
+			if (mic->boot_on_resume) {
+				setsysfs(mic->name, "state", "boot");
+				mic->boot_on_resume = 0;
+			}
+			break;
 		default:
 			break;
 		}
@@ -1621,11 +1642,9 @@ init_mic_list(void)
 
 	while ((file = readdir(dp)) != NULL) {
 		if (!strncmp(file->d_name, "mic", 3)) {
-			mic->next = malloc(sizeof(struct mic_info));
+			mic->next = calloc(1, sizeof(struct mic_info));
 			if (mic->next) {
 				mic = mic->next;
-				mic->next = NULL;
-				memset(mic, 0, sizeof(struct mic_info));
 				mic->id = atoi(&file->d_name[3]);
 				mic->name = malloc(strlen(file->d_name) + 16);
 				if (mic->name)
diff --git a/Documentation/mic/mpssd/mpssd.h b/Documentation/mic/mpssd/mpssd.h
index ccd589ff9146..f5f18b15d9a0 100644
--- a/Documentation/mic/mpssd/mpssd.h
+++ b/Documentation/mic/mpssd/mpssd.h
@@ -91,6 +91,7 @@ struct mic_info {
 	struct mic_net_info	mic_net;
 	struct mic_virtblk_info	mic_virtblk;
 	int		restart;
+	int		boot_on_resume;
 	struct mic_info *next;
 };
 
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
index 60c54d5c43c2..d56b8bf4eaf6 100644
--- a/drivers/misc/mic/host/mic_boot.c
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -37,12 +37,13 @@ static void mic_reset(struct mic_device *mdev)
 
 #define MIC_RESET_TO (45)
 
+	INIT_COMPLETION(mdev->reset_wait);
 	mdev->ops->reset_fw_ready(mdev);
 	mdev->ops->reset(mdev);
 
 	for (i = 0; i < MIC_RESET_TO; i++) {
 		if (mdev->ops->is_fw_ready(mdev))
-			return;
+			goto done;
 		/*
 		 * Resets typically take 10s of seconds to complete.
 		 * Since an MMIO read is required to check if the
@@ -51,6 +52,8 @@ static void mic_reset(struct mic_device *mdev)
 		msleep(1000);
 	}
 	mic_set_state(mdev, MIC_RESET_FAILED);
+done:
+	complete_all(&mdev->reset_wait);
 }
 
 /* Initialize the MIC bootparams */
@@ -123,7 +126,8 @@ void mic_stop(struct mic_device *mdev, bool force)
 		if (MIC_RESET_FAILED == mdev->state)
 			goto unlock;
 		mic_set_shutdown_status(mdev, MIC_NOP);
-		mic_set_state(mdev, MIC_OFFLINE);
+		if (MIC_SUSPENDED != mdev->state)
+			mic_set_state(mdev, MIC_OFFLINE);
 	}
 unlock:
 	mutex_unlock(&mdev->mic_mutex);
@@ -165,7 +169,14 @@ void mic_shutdown_work(struct work_struct *work)
 	mutex_lock(&mdev->mic_mutex);
 	mic_set_shutdown_status(mdev, bootparam->shutdown_status);
 	bootparam->shutdown_status = 0;
-	if (MIC_SHUTTING_DOWN != mdev->state)
+
+	/*
+	 * if state is MIC_SUSPENDED, OSPM suspend is in progress. We do not
+	 * change the state here so as to prevent users from booting the card
+	 * during and after the suspend operation.
+	 */
+	if (MIC_SHUTTING_DOWN != mdev->state &&
+	    MIC_SUSPENDED != mdev->state)
 		mic_set_state(mdev, MIC_SHUTTING_DOWN);
 	mutex_unlock(&mdev->mic_mutex);
 }
@@ -183,3 +194,106 @@ void mic_reset_trigger_work(struct work_struct *work)
 
 	mic_stop(mdev, false);
 }
+
+/**
+ * mic_complete_resume - Complete MIC Resume after an OSPM suspend/hibernate
+ * event.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: None.
+ */
+void mic_complete_resume(struct mic_device *mdev)
+{
+	if (mdev->state != MIC_SUSPENDED) {
+		dev_warn(mdev->sdev->parent, "state %d should be %d\n",
+			 mdev->state, MIC_SUSPENDED);
+		return;
+	}
+
+	/* Make sure firmware is ready */
+	if (!mdev->ops->is_fw_ready(mdev))
+		mic_stop(mdev, true);
+
+	mutex_lock(&mdev->mic_mutex);
+	mic_set_state(mdev, MIC_OFFLINE);
+	mutex_unlock(&mdev->mic_mutex);
+}
+
+/**
+ * mic_prepare_suspend - Handle suspend notification for the MIC device.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: None.
+ */
+void mic_prepare_suspend(struct mic_device *mdev)
+{
+	int rc;
+
+#define MIC_SUSPEND_TIMEOUT (60 * HZ)
+
+	mutex_lock(&mdev->mic_mutex);
+	switch (mdev->state) {
+	case MIC_OFFLINE:
+		/*
+		 * Card is already offline. Set state to MIC_SUSPENDED
+		 * to prevent users from booting the card.
+		 */
+		mic_set_state(mdev, MIC_SUSPENDED);
+		mutex_unlock(&mdev->mic_mutex);
+		break;
+	case MIC_ONLINE:
+		/*
+		 * Card is online. Set state to MIC_SUSPENDING and notify
+		 * MIC user space daemon which will issue card
+		 * shutdown and reset.
+		 */
+		mic_set_state(mdev, MIC_SUSPENDING);
+		mutex_unlock(&mdev->mic_mutex);
+		rc = wait_for_completion_timeout(&mdev->reset_wait,
+						MIC_SUSPEND_TIMEOUT);
+		/* Force reset the card if the shutdown completion timed out */
+		if (!rc) {
+			mutex_lock(&mdev->mic_mutex);
+			mic_set_state(mdev, MIC_SUSPENDED);
+			mutex_unlock(&mdev->mic_mutex);
+			mic_stop(mdev, true);
+		}
+		break;
+	case MIC_SHUTTING_DOWN:
+		/*
+		 * Card is shutting down. Set state to MIC_SUSPENDED
+		 * to prevent further boot of the card.
+		 */
+		mic_set_state(mdev, MIC_SUSPENDED);
+		mutex_unlock(&mdev->mic_mutex);
+		rc = wait_for_completion_timeout(&mdev->reset_wait,
+						MIC_SUSPEND_TIMEOUT);
+		/* Force reset the card if the shutdown completion timed out */
+		if (!rc)
+			mic_stop(mdev, true);
+		break;
+	default:
+		mutex_unlock(&mdev->mic_mutex);
+		break;
+	}
+}
+
+/**
+ * mic_suspend - Initiate MIC suspend. Suspend merely issues card shutdown.
+ * @mdev: pointer to mic_device instance
+ *
+ * RETURNS: None.
+ */
+void mic_suspend(struct mic_device *mdev)
+{
+	struct mic_bootparam *bootparam = mdev->dp;
+	s8 db = bootparam->h2c_shutdown_db;
+
+	mutex_lock(&mdev->mic_mutex);
+	if (MIC_SUSPENDING == mdev->state && db != -1) {
+		bootparam->shutdown_card = 1;
+		mdev->ops->send_intr(mdev, db);
+		mic_set_state(mdev, MIC_SUSPENDED);
+	}
+	mutex_unlock(&mdev->mic_mutex);
+}
diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h
index dcba2a59e77f..3574cc375bb9 100644
--- a/drivers/misc/mic/host/mic_device.h
+++ b/drivers/misc/mic/host/mic_device.h
@@ -23,6 +23,7 @@
 
 #include <linux/cdev.h>
 #include <linux/idr.h>
+#include <linux/notifier.h>
 
 #include "mic_intr.h"
 
@@ -75,6 +76,7 @@ enum mic_stepping {
  * @state: MIC state.
  * @shutdown_status: MIC status reported by card for shutdown/crashes.
  * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes.
+ * @reset_wait: Waitqueue for sleeping while reset completes.
  * @log_buf_addr: Log buffer address for MIC.
  * @log_buf_len: Log buffer length address for MIC.
  * @dp: virtio device page
@@ -83,6 +85,7 @@ enum mic_stepping {
  * @shutdown_cookie: shutdown cookie.
  * @cdev: Character device for MIC.
  * @vdev_list: list of virtio devices.
+ * @pm_notifier: Handles PM notifications from the OS.
  */
 struct mic_device {
 	struct mic_mw mmio;
@@ -110,6 +113,7 @@ struct mic_device {
 	u8 state;
 	u8 shutdown_status;
 	struct sysfs_dirent *state_sysfs;
+	struct completion reset_wait;
 	void *log_buf_addr;
 	int *log_buf_len;
 	void *dp;
@@ -118,6 +122,7 @@ struct mic_device {
 	struct mic_irq *shutdown_cookie;
 	struct cdev cdev;
 	struct list_head vdev_list;
+	struct notifier_block pm_notifier;
 };
 
 /**
@@ -192,4 +197,7 @@ void mic_create_debug_dir(struct mic_device *dev);
 void mic_delete_debug_dir(struct mic_device *dev);
 void __init mic_init_debugfs(void);
 void mic_exit_debugfs(void);
+void mic_prepare_suspend(struct mic_device *mdev);
+void mic_complete_resume(struct mic_device *mdev);
+void mic_suspend(struct mic_device *mdev);
 #endif
diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c
index ca06aa9b7114..b3520859abd3 100644
--- a/drivers/misc/mic/host/mic_main.c
+++ b/drivers/misc/mic/host/mic_main.c
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/poll.h>
+#include <linux/suspend.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_dev.h"
@@ -186,6 +187,43 @@ static enum mic_hw_family mic_get_family(struct pci_dev *pdev)
 	return family;
 }
 
+/**
+* mic_pm_notifier: Notifier callback function that handles
+* PM notifications.
+*
+* @notifier_block: The notifier structure.
+* @pm_event: The event for which the driver was notified.
+* @unused: Meaningless. Always NULL.
+*
+* returns NOTIFY_DONE
+*/
+static int mic_pm_notifier(struct notifier_block *notifier,
+		unsigned long pm_event, void *unused)
+{
+	struct mic_device *mdev = container_of(notifier,
+		struct mic_device, pm_notifier);
+
+	switch (pm_event) {
+	case PM_HIBERNATION_PREPARE:
+		/* Fall through */
+	case PM_SUSPEND_PREPARE:
+		mic_prepare_suspend(mdev);
+		break;
+	case PM_POST_HIBERNATION:
+		/* Fall through */
+	case PM_POST_SUSPEND:
+		/* Fall through */
+	case PM_POST_RESTORE:
+		mic_complete_resume(mdev);
+		break;
+	case PM_RESTORE_PREPARE:
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
 /**
  * mic_device_init - Allocates and initializes the MIC device structure
  *
@@ -194,9 +232,11 @@ static enum mic_hw_family mic_get_family(struct pci_dev *pdev)
  *
  * returns none.
  */
-static void
+static int
 mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
 {
+	int rc;
+
 	mdev->family = mic_get_family(pdev);
 	mdev->stepping = pdev->revision;
 	mic_ops_init(mdev);
@@ -205,7 +245,20 @@ mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
 	mdev->irq_info.next_avail_src = 0;
 	INIT_WORK(&mdev->reset_trigger_work, mic_reset_trigger_work);
 	INIT_WORK(&mdev->shutdown_work, mic_shutdown_work);
+	init_completion(&mdev->reset_wait);
 	INIT_LIST_HEAD(&mdev->vdev_list);
+	mdev->pm_notifier.notifier_call = mic_pm_notifier;
+	rc = register_pm_notifier(&mdev->pm_notifier);
+	if (rc) {
+		dev_err(&pdev->dev, "register_pm_notifier failed rc %d\n",
+			rc);
+		goto register_pm_notifier_fail;
+	}
+	return 0;
+register_pm_notifier_fail:
+	flush_work(&mdev->shutdown_work);
+	flush_work(&mdev->reset_trigger_work);
+	return rc;
 }
 
 /**
@@ -224,6 +277,7 @@ static void mic_device_uninit(struct mic_device *mdev)
 	kfree(mdev->bootmode);
 	flush_work(&mdev->reset_trigger_work);
 	flush_work(&mdev->shutdown_work);
+	unregister_pm_notifier(&mdev->pm_notifier);
 }
 
 /**
@@ -253,7 +307,11 @@ static int mic_probe(struct pci_dev *pdev,
 		goto ida_fail;
 	}
 
-	mic_device_init(mdev, pdev);
+	rc = mic_device_init(mdev, pdev);
+	if (rc) {
+		dev_err(&pdev->dev, "mic_device_init failed rc %d\n", rc);
+		goto device_init_fail;
+	}
 
 	rc = pci_enable_device(pdev);
 	if (rc) {
@@ -376,6 +434,7 @@ disable_device:
 	pci_disable_device(pdev);
 uninit_device:
 	mic_device_uninit(mdev);
+device_init_fail:
 	ida_simple_remove(&g_mic_ida, mdev->id);
 ida_fail:
 	kfree(mdev);
diff --git a/drivers/misc/mic/host/mic_sysfs.c b/drivers/misc/mic/host/mic_sysfs.c
index 75746adfb155..6dd864e4a617 100644
--- a/drivers/misc/mic/host/mic_sysfs.c
+++ b/drivers/misc/mic/host/mic_sysfs.c
@@ -33,6 +33,8 @@ static const char * const mic_state_string[] = {
 	[MIC_ONLINE] = "online",
 	[MIC_SHUTTING_DOWN] = "shutting_down",
 	[MIC_RESET_FAILED] = "reset_failed",
+	[MIC_SUSPENDING] = "suspending",
+	[MIC_SUSPENDED] = "suspended",
 };
 
 /*
@@ -156,6 +158,11 @@ state_store(struct device *dev, struct device_attribute *attr,
 		goto done;
 	}
 
+	if (sysfs_streq(buf, "suspend")) {
+		mic_suspend(mdev);
+		goto done;
+	}
+
 	count = -EINVAL;
 done:
 	return count;
diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h
index 364ac751bd04..17e7d95e4f53 100644
--- a/include/uapi/linux/mic_common.h
+++ b/include/uapi/linux/mic_common.h
@@ -219,6 +219,8 @@ enum mic_states {
 	MIC_ONLINE,
 	MIC_SHUTTING_DOWN,
 	MIC_RESET_FAILED,
+	MIC_SUSPENDING,
+	MIC_SUSPENDED,
 	MIC_LAST
 };
 
-- 
cgit 


From bcc8edb52f05c1a9e75118d6b3bc04996a750593 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Sat, 5 Oct 2013 18:25:02 -0700
Subject: driver core: remove dev_attrs from struct class

Now that all in-kernel users of the dev_attrs field are converted to use
dev_groups, we can safely remove dev_attrs from struct class.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 38 +-------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 1 insertion(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 319c2c594ac6..f67e86687ae2 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -455,35 +455,6 @@ static ssize_t online_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(online);
 
-static int device_add_attributes(struct device *dev,
-				 struct device_attribute *attrs)
-{
-	int error = 0;
-	int i;
-
-	if (attrs) {
-		for (i = 0; attrs[i].attr.name; i++) {
-			error = device_create_file(dev, &attrs[i]);
-			if (error)
-				break;
-		}
-		if (error)
-			while (--i >= 0)
-				device_remove_file(dev, &attrs[i]);
-	}
-	return error;
-}
-
-static void device_remove_attributes(struct device *dev,
-				     struct device_attribute *attrs)
-{
-	int i;
-
-	if (attrs)
-		for (i = 0; attrs[i].attr.name; i++)
-			device_remove_file(dev, &attrs[i]);
-}
-
 static int device_add_bin_attributes(struct device *dev,
 				     struct bin_attribute *attrs)
 {
@@ -534,12 +505,9 @@ static int device_add_attrs(struct device *dev)
 		error = device_add_groups(dev, class->dev_groups);
 		if (error)
 			return error;
-		error = device_add_attributes(dev, class->dev_attrs);
-		if (error)
-			goto err_remove_class_groups;
 		error = device_add_bin_attributes(dev, class->dev_bin_attrs);
 		if (error)
-			goto err_remove_class_attrs;
+			goto err_remove_class_groups;
 	}
 
 	if (type) {
@@ -566,9 +534,6 @@ static int device_add_attrs(struct device *dev)
  err_remove_class_bin_attrs:
 	if (class)
 		device_remove_bin_attributes(dev, class->dev_bin_attrs);
- err_remove_class_attrs:
-	if (class)
-		device_remove_attributes(dev, class->dev_attrs);
  err_remove_class_groups:
 	if (class)
 		device_remove_groups(dev, class->dev_groups);
@@ -588,7 +553,6 @@ static void device_remove_attrs(struct device *dev)
 		device_remove_groups(dev, type->groups);
 
 	if (class) {
-		device_remove_attributes(dev, class->dev_attrs);
 		device_remove_bin_attributes(dev, class->dev_bin_attrs);
 		device_remove_groups(dev, class->dev_groups);
 	}
diff --git a/include/linux/device.h b/include/linux/device.h
index e7f5b8585380..9ffe8561df75 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -325,7 +325,6 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @owner:	The module owner.
  * @class_attrs: Default attributes of this class.
  * @dev_groups:	Default attributes of the devices that belong to the class.
- * @dev_attrs:	Default attributes of the devices belong to the class.
  * @dev_bin_attrs: Default binary attributes of the devices belong to the class.
  * @dev_kobj:	The kobject that represents this class and links it into the hierarchy.
  * @dev_uevent:	Called when a device is added, removed from this class, or a
@@ -354,7 +353,6 @@ struct class {
 	struct module		*owner;
 
 	struct class_attribute		*class_attrs;
-	struct device_attribute		*dev_attrs;	/* use dev_groups instead */
 	const struct attribute_group	**dev_groups;
 	struct bin_attribute		*dev_bin_attrs;
 	struct kobject			*dev_kobj;
-- 
cgit 


From a6b01deda1e79259d2fe98fe68d41e4b7bad2783 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Sat, 5 Oct 2013 18:19:30 -0700
Subject: driver core: remove dev_bin_attrs from struct class

No in-kernel code is now using this, they have all be converted over to
using the bin_attrs support in attribute groups, so this field, and the
code in the driver core that was creating/remove the binary files can be
removed.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 41 ++---------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 2 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index f67e86687ae2..bf35c557707f 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -455,35 +455,6 @@ static ssize_t online_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(online);
 
-static int device_add_bin_attributes(struct device *dev,
-				     struct bin_attribute *attrs)
-{
-	int error = 0;
-	int i;
-
-	if (attrs) {
-		for (i = 0; attrs[i].attr.name; i++) {
-			error = device_create_bin_file(dev, &attrs[i]);
-			if (error)
-				break;
-		}
-		if (error)
-			while (--i >= 0)
-				device_remove_bin_file(dev, &attrs[i]);
-	}
-	return error;
-}
-
-static void device_remove_bin_attributes(struct device *dev,
-					 struct bin_attribute *attrs)
-{
-	int i;
-
-	if (attrs)
-		for (i = 0; attrs[i].attr.name; i++)
-			device_remove_bin_file(dev, &attrs[i]);
-}
-
 int device_add_groups(struct device *dev, const struct attribute_group **groups)
 {
 	return sysfs_create_groups(&dev->kobj, groups);
@@ -505,15 +476,12 @@ static int device_add_attrs(struct device *dev)
 		error = device_add_groups(dev, class->dev_groups);
 		if (error)
 			return error;
-		error = device_add_bin_attributes(dev, class->dev_bin_attrs);
-		if (error)
-			goto err_remove_class_groups;
 	}
 
 	if (type) {
 		error = device_add_groups(dev, type->groups);
 		if (error)
-			goto err_remove_class_bin_attrs;
+			goto err_remove_class_groups;
 	}
 
 	error = device_add_groups(dev, dev->groups);
@@ -531,9 +499,6 @@ static int device_add_attrs(struct device *dev)
  err_remove_type_groups:
 	if (type)
 		device_remove_groups(dev, type->groups);
- err_remove_class_bin_attrs:
-	if (class)
-		device_remove_bin_attributes(dev, class->dev_bin_attrs);
  err_remove_class_groups:
 	if (class)
 		device_remove_groups(dev, class->dev_groups);
@@ -552,10 +517,8 @@ static void device_remove_attrs(struct device *dev)
 	if (type)
 		device_remove_groups(dev, type->groups);
 
-	if (class) {
-		device_remove_bin_attributes(dev, class->dev_bin_attrs);
+	if (class)
 		device_remove_groups(dev, class->dev_groups);
-	}
 }
 
 static ssize_t dev_show(struct device *dev, struct device_attribute *attr,
diff --git a/include/linux/device.h b/include/linux/device.h
index 9ffe8561df75..94638efa0bf8 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -325,7 +325,6 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @owner:	The module owner.
  * @class_attrs: Default attributes of this class.
  * @dev_groups:	Default attributes of the devices that belong to the class.
- * @dev_bin_attrs: Default binary attributes of the devices belong to the class.
  * @dev_kobj:	The kobject that represents this class and links it into the hierarchy.
  * @dev_uevent:	Called when a device is added, removed from this class, or a
  *		few other things that generate uevents to add the environment
@@ -354,7 +353,6 @@ struct class {
 
 	struct class_attribute		*class_attrs;
 	const struct attribute_group	**dev_groups;
-	struct bin_attribute		*dev_bin_attrs;
 	struct kobject			*dev_kobj;
 
 	int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env);
-- 
cgit 


From f822c411b26ce0353c8b97877e53a12e4f895ca1 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:41 -0700
Subject: Bluetooth: Remove useless external function to count controllers

The list of controllers can be counted ahead of time and inline
inside the AMP discover handling. There is no need to export such
a function at all.

In addition just count the AMP controller and only allocated space
for a single mandatory BR/EDR controller. No need to allocate more
space than needed.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 13 -------------
 net/bluetooth/a2mp.c             | 10 +++++++++-
 2 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 079c5c55c829..db650baf8177 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -704,19 +704,6 @@ static inline void hci_set_drvdata(struct hci_dev *hdev, void *data)
 	dev_set_drvdata(&hdev->dev, data);
 }
 
-/* hci_dev_list shall be locked */
-static inline uint8_t __hci_num_ctrl(void)
-{
-	uint8_t count = 0;
-	struct list_head *p;
-
-	list_for_each(p, &hci_dev_list) {
-		count++;
-	}
-
-	return count;
-}
-
 struct hci_dev *hci_dev_get(int index);
 struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src);
 
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index eb0f05e09cd5..a6e45e177b3d 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -129,6 +129,7 @@ static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	struct a2mp_discov_rsp *rsp;
 	u16 ext_feat;
 	u8 num_ctrl;
+	struct hci_dev *hdev;
 
 	if (len < sizeof(*req))
 		return -EINVAL;
@@ -152,7 +153,14 @@ static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	read_lock(&hci_dev_list_lock);
 
-	num_ctrl = __hci_num_ctrl();
+	/* at minimum the BR/EDR needs to be listed */
+	num_ctrl = 1;
+
+	list_for_each_entry(hdev, &hci_dev_list, list) {
+		if (hdev->dev_type == HCI_AMP)
+			num_ctrl++;
+	}
+
 	len = num_ctrl * sizeof(struct a2mp_cl) + sizeof(*rsp);
 	rsp = kmalloc(len, GFP_ATOMIC);
 	if (!rsp) {
-- 
cgit 


From 7c13823d5b6b7cf06adeb5d56d2435fc0d97383f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:42 -0700
Subject: Bluetooth: Add constants for AMP controller type

Add the constants for BR/EDR and 802.11 AMP controller types.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e8bba05686d1..8e3076ebb8ad 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -66,6 +66,10 @@
 /* First BR/EDR Controller shall have ID = 0 */
 #define HCI_BREDR_ID	0
 
+/* AMP controller types */
+#define AMP_TYPE_BREDR	0x00
+#define AMP_TYPE_80211	0x01
+
 /* AMP controller status */
 #define AMP_CTRL_POWERED_DOWN			0x00
 #define AMP_CTRL_BLUETOOTH_ONLY			0x01
-- 
cgit 


From ece6912648da3fcf257a40774e3aad531c3e5fac Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:43 -0700
Subject: Bluetooth: Separate AMP controller type from HCI device type

There are two defined HCI device types. One is for BR/EDR controllers
and the other is for AMP controllers. The HCI device type is not the
same as the AMP controller type. It just happens that currently the
defined types match, but that is not guaranteed.

Split the usage of AMP controller type into its own domain so that
it is possible to separate between BR/EDR controllers, 802.11 AMP
controllers and any other AMP technology that might be defined in
the future.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/a2mp.c             | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index db650baf8177..4cb355b023a4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -803,7 +803,7 @@ static inline bool hci_amp_capable(void)
 
 	read_lock(&hci_dev_list_lock);
 	list_for_each_entry(hdev, &hci_dev_list, list)
-		if (hdev->amp_type == HCI_AMP &&
+		if (hdev->amp_type != AMP_TYPE_BREDR &&
 		    test_bit(HCI_UP, &hdev->flags))
 			ret = true;
 	read_unlock(&hci_dev_list_lock);
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index a6e45e177b3d..b2ef3d392a0e 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -78,7 +78,7 @@ u8 __next_ident(struct amp_mgr *mgr)
 static inline void __a2mp_cl_bredr(struct a2mp_cl *cl)
 {
 	cl->id = 0;
-	cl->type = 0;
+	cl->type = AMP_TYPE_BREDR;
 	cl->status = 1;
 }
 
@@ -352,7 +352,7 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC);
 
 	hdev = hci_dev_get(req->id);
-	if (!hdev || hdev->amp_type == HCI_BREDR || tmp) {
+	if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) {
 		struct a2mp_amp_assoc_rsp rsp;
 		rsp.id = req->id;
 
@@ -459,7 +459,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	rsp.remote_id = req->local_id;
 
 	hdev = hci_dev_get(req->remote_id);
-	if (!hdev || hdev->amp_type != HCI_AMP) {
+	if (!hdev || hdev->amp_type == AMP_TYPE_BREDR) {
 		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 		goto send_rsp;
 	}
@@ -879,7 +879,7 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 	rsp.id = hdev->id;
 	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
-	if (hdev->amp_type != HCI_BREDR) {
+	if (hdev->amp_type != AMP_TYPE_BREDR) {
 		rsp.status = 0;
 		rsp.total_bw = cpu_to_le32(hdev->amp_total_bw);
 		rsp.max_bw = cpu_to_le32(hdev->amp_max_bw);
-- 
cgit 


From 6ed971ca4f6bd96e26b3166cb5a94f7f8158fe77 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:44 -0700
Subject: Bluetooth: Use explicit AMP controller id value for BR/EDR

The special AMP controller id 0 is reserved for the BR/EDR controller
that has the main link. It is a fixed value and so use a constant for
this throughout the code to make it more visible when the handling is
for the BR/EDR channel or when it is for the AMP channel.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  2 +-
 net/bluetooth/a2mp.c        |  4 ++--
 net/bluetooth/l2cap_core.c  | 28 ++++++++++++++--------------
 3 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8e3076ebb8ad..393eabc0d21f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -64,7 +64,7 @@
 #define HCI_AMP		0x01
 
 /* First BR/EDR Controller shall have ID = 0 */
-#define HCI_BREDR_ID	0
+#define AMP_ID_BREDR	0x00
 
 /* AMP controller types */
 #define AMP_TYPE_BREDR	0x00
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index b2ef3d392a0e..6d62d3140cf8 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -77,7 +77,7 @@ u8 __next_ident(struct amp_mgr *mgr)
 
 static inline void __a2mp_cl_bredr(struct a2mp_cl *cl)
 {
-	cl->id = 0;
+	cl->id = AMP_ID_BREDR;
 	cl->type = AMP_TYPE_BREDR;
 	cl->status = 1;
 }
@@ -216,7 +216,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 		BT_DBG("Remote AMP id %d type %d status %d", cl->id, cl->type,
 		       cl->status);
 
-		if (cl->id != HCI_BREDR_ID && cl->type == HCI_AMP) {
+		if (cl->id != AMP_ID_BREDR && cl->type == HCI_AMP) {
 			struct a2mp_info_req req;
 
 			found = true;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 02dba4e6df96..b0208e20390c 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3046,8 +3046,8 @@ int l2cap_ertm_init(struct l2cap_chan *chan)
 
 	skb_queue_head_init(&chan->tx_q);
 
-	chan->local_amp_id = 0;
-	chan->move_id = 0;
+	chan->local_amp_id = AMP_ID_BREDR;
+	chan->move_id = AMP_ID_BREDR;
 	chan->move_state = L2CAP_MOVE_STABLE;
 	chan->move_role = L2CAP_MOVE_ROLE_NONE;
 
@@ -3100,7 +3100,7 @@ static inline bool __l2cap_efs_supported(struct l2cap_conn *conn)
 static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan,
 				      struct l2cap_conf_rfc *rfc)
 {
-	if (chan->local_amp_id && chan->hs_hcon) {
+	if (chan->local_amp_id != AMP_ID_BREDR && chan->hs_hcon) {
 		u64 ertm_to = chan->hs_hcon->hdev->amp_be_flush_to;
 
 		/* Class 1 devices have must have ERTM timeouts
@@ -3791,12 +3791,12 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 				 * The connection will succeed after the
 				 * physical link is up.
 				 */
-				if (amp_id) {
-					__l2cap_state_change(chan, BT_CONNECT2);
-					result = L2CAP_CR_PEND;
-				} else {
+				if (amp_id == AMP_ID_BREDR) {
 					__l2cap_state_change(chan, BT_CONFIG);
 					result = L2CAP_CR_SUCCESS;
+				} else {
+					__l2cap_state_change(chan, BT_CONNECT2);
+					result = L2CAP_CR_PEND;
 				}
 				status = L2CAP_CS_NO_INFO;
 			}
@@ -4423,7 +4423,7 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn,
 	BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id);
 
 	/* For controller id 0 make BR/EDR connection */
-	if (req->amp_id == HCI_BREDR_ID) {
+	if (req->amp_id == AMP_ID_BREDR) {
 		l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP,
 			      req->amp_id);
 		return 0;
@@ -4658,7 +4658,7 @@ void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
 
 	if (chan->state != BT_CONNECTED) {
 		/* Ignore logical link if channel is on BR/EDR */
-		if (chan->local_amp_id)
+		if (chan->local_amp_id != AMP_ID_BREDR)
 			l2cap_logical_finish_create(chan, hchan);
 	} else {
 		l2cap_logical_finish_move(chan, hchan);
@@ -4669,7 +4669,7 @@ void l2cap_move_start(struct l2cap_chan *chan)
 {
 	BT_DBG("chan %p", chan);
 
-	if (chan->local_amp_id == HCI_BREDR_ID) {
+	if (chan->local_amp_id == AMP_ID_BREDR) {
 		if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED)
 			return;
 		chan->move_role = L2CAP_MOVE_ROLE_INITIATOR;
@@ -4868,7 +4868,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 		goto send_move_response;
 	}
 
-	if (req->dest_amp_id) {
+	if (req->dest_amp_id != AMP_ID_BREDR) {
 		struct hci_dev *hdev;
 		hdev = hci_dev_get(req->dest_amp_id);
 		if (!hdev || hdev->dev_type != HCI_AMP ||
@@ -4898,7 +4898,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
 	chan->move_id = req->dest_amp_id;
 	icid = chan->dcid;
 
-	if (!req->dest_amp_id) {
+	if (req->dest_amp_id == AMP_ID_BREDR) {
 		/* Moving to BR/EDR */
 		if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) {
 			chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY;
@@ -5090,7 +5090,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn,
 	if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM) {
 		if (result == L2CAP_MC_CONFIRMED) {
 			chan->local_amp_id = chan->move_id;
-			if (!chan->local_amp_id)
+			if (chan->local_amp_id == AMP_ID_BREDR)
 				__release_logical_link(chan);
 		} else {
 			chan->move_id = chan->local_amp_id;
@@ -5130,7 +5130,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
 	if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM_RSP) {
 		chan->local_amp_id = chan->move_id;
 
-		if (!chan->local_amp_id && chan->hs_hchan)
+		if (chan->local_amp_id == AMP_ID_BREDR && chan->hs_hchan)
 			__release_logical_link(chan);
 
 		l2cap_move_done(chan);
-- 
cgit 


From 536619e86d9398a20063f7c3d15deb9dcc234097 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:45 -0700
Subject: Bluetooth: Rename AMP status constants and use them

The AMP controller status constants need to be actually used to avoid
crypted hardcoded numbers.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 14 +++++++-------
 net/bluetooth/a2mp.c        |  2 +-
 net/bluetooth/hci_core.c    |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 393eabc0d21f..9f8d1c1f0414 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -71,13 +71,13 @@
 #define AMP_TYPE_80211	0x01
 
 /* AMP controller status */
-#define AMP_CTRL_POWERED_DOWN			0x00
-#define AMP_CTRL_BLUETOOTH_ONLY			0x01
-#define AMP_CTRL_NO_CAPACITY			0x02
-#define AMP_CTRL_LOW_CAPACITY			0x03
-#define AMP_CTRL_MEDIUM_CAPACITY		0x04
-#define AMP_CTRL_HIGH_CAPACITY			0x05
-#define AMP_CTRL_FULL_CAPACITY			0x06
+#define AMP_STATUS_POWERED_DOWN			0x00
+#define AMP_STATUS_BLUETOOTH_ONLY		0x01
+#define AMP_STATUS_NO_CAPACITY			0x02
+#define AMP_STATUS_LOW_CAPACITY			0x03
+#define AMP_STATUS_MEDIUM_CAPACITY		0x04
+#define AMP_STATUS_HIGH_CAPACITY		0x05
+#define AMP_STATUS_FULL_CAPACITY		0x06
 
 /* HCI device quirks */
 enum {
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 6d62d3140cf8..6dfef731825f 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -79,7 +79,7 @@ static inline void __a2mp_cl_bredr(struct a2mp_cl *cl)
 {
 	cl->id = AMP_ID_BREDR;
 	cl->type = AMP_TYPE_BREDR;
-	cl->status = 1;
+	cl->status = AMP_STATUS_BLUETOOTH_ONLY;
 }
 
 /* hci_dev_list shall be locked */
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index aa63ebb114d4..0d5fe0843f5e 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1381,7 +1381,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 	}
 
 	/* Controller radio is available but is currently powered down */
-	hdev->amp_status = 0;
+	hdev->amp_status = AMP_STATUS_POWERED_DOWN;
 
 	memset(hdev->eir, 0, sizeof(hdev->eir));
 	memset(hdev->dev_class, 0, sizeof(hdev->dev_class));
-- 
cgit 


From 80d58d0b5b18b68addad61e228ced167f8b80dd3 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 5 Oct 2013 11:47:48 -0700
Subject: Bluetooth: Move hci_amp_capable() function into L2CAP core

The hci_amp_capable() function has only a single user inside the L2CAP
core. Instead of exporting the function, place it next to its user.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 16 ----------------
 net/bluetooth/l2cap_core.c       | 16 ++++++++++++++++
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4cb355b023a4..82c397451261 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -795,22 +795,6 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_host_le_capable(dev)   (!!((dev)->features[1][0] & LMP_HOST_LE))
 #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR))
 
-/* returns true if at least one AMP active */
-static inline bool hci_amp_capable(void)
-{
-	struct hci_dev *hdev;
-	bool ret = false;
-
-	read_lock(&hci_dev_list_lock);
-	list_for_each_entry(hdev, &hci_dev_list, list)
-		if (hdev->amp_type != AMP_TYPE_BREDR &&
-		    test_bit(HCI_UP, &hdev->flags))
-			ret = true;
-	read_unlock(&hci_dev_list_lock);
-
-	return ret;
-}
-
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b0208e20390c..2efdb17d87a3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1012,6 +1012,22 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan)
 	return !test_bit(CONF_CONNECT_PEND, &chan->conf_state);
 }
 
+/* returns true if at least one AMP active */
+static inline bool hci_amp_capable(void)
+{
+	struct hci_dev *hdev;
+	bool ret = false;
+
+	read_lock(&hci_dev_list_lock);
+	list_for_each_entry(hdev, &hci_dev_list, list)
+		if (hdev->amp_type != AMP_TYPE_BREDR &&
+		    test_bit(HCI_UP, &hdev->flags))
+			ret = true;
+	read_unlock(&hci_dev_list_lock);
+
+	return ret;
+}
+
 static bool __amp_capable(struct l2cap_chan *chan)
 {
 	struct l2cap_conn *conn = chan->conn;
-- 
cgit 


From 1e191893f38e89796d948af0516b7e29594dab99 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 02:34:38 -0700
Subject: Bluetooth: Add HCI structure for LE advertising parameters command

Add the basic HCI structure for building the LE advertising parameters
command.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 9f8d1c1f0414..9b0e3f9aa1c3 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1046,6 +1046,18 @@ struct hci_rp_le_read_local_features {
 
 #define HCI_OP_LE_SET_RANDOM_ADDR	0x2005
 
+#define HCI_OP_LE_SET_ADV_PARAM		0x2006
+struct hci_cp_le_set_adv_param {
+	__le16   min_interval;
+	__le16   max_interval;
+	__u8     type;
+	__u8     own_address_type;
+	__u8     direct_addr_type;
+	bdaddr_t direct_addr;
+	__u8     channel_map;
+	__u8     filter_policy;
+} __packed;
+
 #define HCI_OP_LE_READ_ADV_TX_POWER	0x2007
 struct hci_rp_le_read_adv_tx_power {
 	__u8	status;
-- 
cgit 


From c2f5ebd2148860537762c8d0d687efed73c2c2d0 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 03:03:46 -0700
Subject: Bluetooth: Add constants for LE advertising types

Add constants for ADV_IND, ADV_DIRECT_IND, ADV_SCAN_IND and
ADV_NONCONN_IND advertising types.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 9b0e3f9aa1c3..3616ea794eb1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1046,6 +1046,11 @@ struct hci_rp_le_read_local_features {
 
 #define HCI_OP_LE_SET_RANDOM_ADDR	0x2005
 
+#define LE_ADV_IND			0x00
+#define LE_ADV_DIRECT_IND		0x01
+#define LE_ADV_SCAN_IND			0x02
+#define LE_ADV_NONCONN_IND		0x03
+
 #define HCI_OP_LE_SET_ADV_PARAM		0x2006
 struct hci_cp_le_set_adv_param {
 	__le16   min_interval;
-- 
cgit 


From 5976e60811723220678ebdb2ea06fbb52fe900bd Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 04:08:14 -0700
Subject: Bluetooth: Use helper function for re-enabling advertising

When the all LE connections have been disconneted, then it is up to
the host to re-enable advertising at that point. To ensure that the
correct advertising parameters are used, force the usage of the
common helper to enable advertising.

The change just moves the manual enabling of advertising from the
event handler into the management core so that the helper can
be actually shared.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_event.c        | 36 +-----------------------------------
 net/bluetooth/mgmt.c             | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 82c397451261..869f6ad602d1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1151,6 +1151,7 @@ int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 bool mgmt_valid_hdev(struct hci_dev *hdev);
 int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent);
+void mgmt_reenable_advertising(struct hci_dev *hdev);
 
 /* HCI info for socket */
 #define hci_pi(sk) ((struct hci_pinfo *) sk)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6eaef6ed9522..224210ce82fc 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1796,40 +1796,6 @@ static u8 hci_to_mgmt_reason(u8 err)
 	}
 }
 
-static void adv_enable_complete(struct hci_dev *hdev, u8 status)
-{
-	BT_DBG("%s status %u", hdev->name, status);
-
-	/* Clear the advertising mgmt setting if we failed to re-enable it */
-	if (status) {
-		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
-		mgmt_new_settings(hdev);
-	}
-}
-
-static void reenable_advertising(struct hci_dev *hdev)
-{
-	struct hci_request req;
-	u8 enable = 0x01;
-
-	if (hdev->conn_hash.le_num)
-		return;
-
-	if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags))
-		return;
-
-	hci_req_init(&req, hdev);
-	hci_req_add(&req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
-
-	/* If this fails we have no option but to let user space know
-	 * that we've disabled advertising.
-	 */
-	if (hci_req_run(&req, adv_enable_complete) < 0) {
-		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
-		mgmt_new_settings(hdev);
-	}
-}
-
 static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_disconn_complete *ev = (void *) skb->data;
@@ -1878,7 +1844,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		 * is timed out due to Directed Advertising."
 		 */
 		if (type == LE_LINK)
-			reenable_advertising(hdev);
+			mgmt_reenable_advertising(hdev);
 	}
 
 unlock:
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index b78a0eefe03e..381faf600195 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4660,3 +4660,36 @@ int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 	return mgmt_event(MGMT_EV_DEVICE_UNBLOCKED, hdev, &ev, sizeof(ev),
 			  cmd ? cmd->sk : NULL);
 }
+
+static void adv_enable_complete(struct hci_dev *hdev, u8 status)
+{
+	BT_DBG("%s status %u", hdev->name, status);
+
+	/* Clear the advertising mgmt setting if we failed to re-enable it */
+	if (status) {
+		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+		mgmt_new_settings(hdev);
+	}
+}
+
+void mgmt_reenable_advertising(struct hci_dev *hdev)
+{
+	struct hci_request req;
+
+	if (hdev->conn_hash.le_num)
+		return;
+
+	if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+		return;
+
+	hci_req_init(&req, hdev);
+	enable_advertising(&req);
+
+	/* If this fails we have no option but to let user space know
+	 * that we've disabled advertising.
+	 */
+	if (hci_req_run(&req, adv_enable_complete) < 0) {
+		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+		mgmt_new_settings(hdev);
+	}
+}
-- 
cgit 


From a6d811ed28f7c49e869b4076a00969c4028cda0d Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 04:11:12 -0700
Subject: Bluetooth: Remove no longer needed mgmt_new_settings() function

The mgmt_new_settings() function was only needed to handle the
error case when re-enabling advertising failed. Since that is
now handled internally inside the management core, this function
is not needed anymore. So just remove it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 -
 net/bluetooth/mgmt.c             | 9 ++-------
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 869f6ad602d1..30e0fbb92b0a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1094,7 +1094,6 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 int mgmt_index_added(struct hci_dev *hdev);
 int mgmt_index_removed(struct hci_dev *hdev);
-int mgmt_new_settings(struct hci_dev *hdev);
 int mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 381faf600195..dd48e2a88c50 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -890,11 +890,6 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip)
 	return mgmt_event(MGMT_EV_NEW_SETTINGS, hdev, &ev, sizeof(ev), skip);
 }
 
-int mgmt_new_settings(struct hci_dev *hdev)
-{
-	return new_settings(hdev, NULL);
-}
-
 struct cmd_lookup {
 	struct sock *sk;
 	struct hci_dev *hdev;
@@ -4668,7 +4663,7 @@ static void adv_enable_complete(struct hci_dev *hdev, u8 status)
 	/* Clear the advertising mgmt setting if we failed to re-enable it */
 	if (status) {
 		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
-		mgmt_new_settings(hdev);
+		new_settings(hdev, NULL);
 	}
 }
 
@@ -4690,6 +4685,6 @@ void mgmt_reenable_advertising(struct hci_dev *hdev)
 	 */
 	if (hci_req_run(&req, adv_enable_complete) < 0) {
 		clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
-		mgmt_new_settings(hdev);
+		new_settings(hdev, NULL);
 	}
 }
-- 
cgit 


From 1514b8928e5d8273920b26276cd9617b6dbc7760 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 08:25:01 -0700
Subject: Bluetooth: Remove mgmt_valid_hdev() helper function

The helper function mgmt_valid_hdev() is more obfuscating the code
then it makes it easier to read. So intead of this helper, use the
direct check for BR/EDR device type.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_core.c         |  4 ++--
 net/bluetooth/mgmt.c             | 24 ++++++++----------------
 3 files changed, 10 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 30e0fbb92b0a..d80d4311ccb0 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1148,7 +1148,6 @@ int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 int mgmt_discovering(struct hci_dev *hdev, u8 discovering);
 int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
-bool mgmt_valid_hdev(struct hci_dev *hdev);
 int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent);
 void mgmt_reenable_advertising(struct hci_dev *hdev);
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index bf3c5b0c22b9..d9626aad7ade 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1254,7 +1254,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 		hci_notify(hdev, HCI_DEV_UP);
 		if (!test_bit(HCI_SETUP, &hdev->dev_flags) &&
 		    !test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) &&
-		    mgmt_valid_hdev(hdev)) {
+		    hdev->dev_type == HCI_BREDR) {
 			hci_dev_lock(hdev);
 			mgmt_powered(hdev, 1);
 			hci_dev_unlock(hdev);
@@ -1394,7 +1394,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 	hdev->dev_flags &= ~HCI_PERSISTENT_MASK;
 
 	if (!test_and_clear_bit(HCI_AUTO_OFF, &hdev->dev_flags) &&
-	    mgmt_valid_hdev(hdev)) {
+	    hdev->dev_type == HCI_BREDR) {
 		hci_dev_lock(hdev);
 		mgmt_powered(hdev, 0);
 		hci_dev_unlock(hdev);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index dd48e2a88c50..9702079833fc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -182,11 +182,6 @@ static u8 mgmt_status_table[] = {
 	MGMT_STATUS_CONNECT_FAILED,	/* MAC Connection Failed */
 };
 
-bool mgmt_valid_hdev(struct hci_dev *hdev)
-{
-	return hdev->dev_type == HCI_BREDR;
-}
-
 static u8 mgmt_status(u8 hci_status)
 {
 	if (hci_status < ARRAY_SIZE(mgmt_status_table))
@@ -322,10 +317,8 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	count = 0;
 	list_for_each_entry(d, &hci_dev_list, list) {
-		if (!mgmt_valid_hdev(d))
-			continue;
-
-		count++;
+		if (d->dev_type == HCI_BREDR)
+			count++;
 	}
 
 	rp_len = sizeof(*rp) + (2 * count);
@@ -343,11 +336,10 @@ static int read_index_list(struct sock *sk, struct hci_dev *hdev, void *data,
 		if (test_bit(HCI_USER_CHANNEL, &d->dev_flags))
 			continue;
 
-		if (!mgmt_valid_hdev(d))
-			continue;
-
-		rp->index[count++] = cpu_to_le16(d->id);
-		BT_DBG("Added hci%u", d->id);
+		if (d->dev_type == HCI_BREDR) {
+			rp->index[count++] = cpu_to_le16(d->id);
+			BT_DBG("Added hci%u", d->id);
+		}
 	}
 
 	rp->num_controllers = cpu_to_le16(count);
@@ -3790,7 +3782,7 @@ done:
 
 int mgmt_index_added(struct hci_dev *hdev)
 {
-	if (!mgmt_valid_hdev(hdev))
+	if (hdev->dev_type != HCI_BREDR)
 		return -ENOTSUPP;
 
 	return mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL);
@@ -3800,7 +3792,7 @@ int mgmt_index_removed(struct hci_dev *hdev)
 {
 	u8 status = MGMT_STATUS_INVALID_INDEX;
 
-	if (!mgmt_valid_hdev(hdev))
+	if (hdev->dev_type != HCI_BREDR)
 		return -ENOTSUPP;
 
 	mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status);
-- 
cgit 


From bf6b56db0acbe844c96fe36ab65eb7a53c6d8654 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:45 -0700
Subject: Bluetooth: Make mgmt_index_added() and mgmt_index_removed() return
 void

The return value from mgmt_index_added() and mgmt_index_removed()
functions is never used. So do not pretend that returning an error
would actually be handled and just make both functions return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d80d4311ccb0..1e6f584d5149 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1092,8 +1092,8 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
 #define DISCOV_BREDR_INQUIRY_LEN	0x08
 
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
-int mgmt_index_added(struct hci_dev *hdev);
-int mgmt_index_removed(struct hci_dev *hdev);
+void mgmt_index_added(struct hci_dev *hdev);
+void mgmt_index_removed(struct hci_dev *hdev);
 int mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3f628fd71b4e..811c41192ec7 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3782,24 +3782,24 @@ done:
 	return err;
 }
 
-int mgmt_index_added(struct hci_dev *hdev)
+void mgmt_index_added(struct hci_dev *hdev)
 {
 	if (hdev->dev_type != HCI_BREDR)
-		return -ENOTSUPP;
+		return;
 
-	return mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL);
+	mgmt_event(MGMT_EV_INDEX_ADDED, hdev, NULL, 0, NULL);
 }
 
-int mgmt_index_removed(struct hci_dev *hdev)
+void mgmt_index_removed(struct hci_dev *hdev)
 {
 	u8 status = MGMT_STATUS_INVALID_INDEX;
 
 	if (hdev->dev_type != HCI_BREDR)
-		return -ENOTSUPP;
+		return;
 
 	mgmt_pending_foreach(0, hdev, cmd_status_rsp, &status);
 
-	return mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL);
+	mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL);
 }
 
 static void set_bredr_scan(struct hci_request *req)
-- 
cgit 


From 3eec705e42d19b3d3e367fcb88693c24175bdbc6 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:46 -0700
Subject: Bluetooth: Make mgmt_set_powered_failed() return void

The return value of mgmt_set_powered_failed() function is never used
and so make the function just return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/mgmt.c             | 8 +++-----
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 1e6f584d5149..62e2fc1bc7cc 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1094,7 +1094,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 void mgmt_index_added(struct hci_dev *hdev);
 void mgmt_index_removed(struct hci_dev *hdev);
-int mgmt_set_powered_failed(struct hci_dev *hdev, int err);
+void mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
 int mgmt_connectable(struct hci_dev *hdev, u8 connectable);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 811c41192ec7..5da7464e57a5 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3934,25 +3934,23 @@ new_settings:
 	return err;
 }
 
-int mgmt_set_powered_failed(struct hci_dev *hdev, int err)
+void mgmt_set_powered_failed(struct hci_dev *hdev, int err)
 {
 	struct pending_cmd *cmd;
 	u8 status;
 
 	cmd = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev);
 	if (!cmd)
-		return -ENOENT;
+		return;
 
 	if (err == -ERFKILL)
 		status = MGMT_STATUS_RFKILLED;
 	else
 		status = MGMT_STATUS_FAILED;
 
-	err = cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status);
+	cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_POWERED, status);
 
 	mgmt_pending_remove(cmd);
-
-	return err;
 }
 
 int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
-- 
cgit 


From 7892924c7d5d74be8ad52316000a78fe96379044 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:47 -0700
Subject: Bluetooth: Make mgmt_disconnect_failed() return void

The return value of mgmt_disconnect_failed() function is not used
so change it to just return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 13 +++++--------
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 62e2fc1bc7cc..429969fdb9f3 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1106,8 +1106,8 @@ int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			  u8 *dev_class);
 int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 link_type, u8 addr_type, u8 reason);
-int mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			   u8 link_type, u8 addr_type, u8 status);
+void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			    u8 link_type, u8 addr_type, u8 status);
 int mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			u8 addr_type, u8 status);
 int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5da7464e57a5..a35f28e9172e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4143,29 +4143,26 @@ int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	return err;
 }
 
-int mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			   u8 link_type, u8 addr_type, u8 status)
+void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			    u8 link_type, u8 addr_type, u8 status)
 {
 	struct mgmt_rp_disconnect rp;
 	struct pending_cmd *cmd;
-	int err;
 
 	mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
 			     hdev);
 
 	cmd = mgmt_pending_find(MGMT_OP_DISCONNECT, hdev);
 	if (!cmd)
-		return -ENOENT;
+		return;
 
 	bacpy(&rp.addr.bdaddr, bdaddr);
 	rp.addr.type = link_to_bdaddr(link_type, addr_type);
 
-	err = cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT,
-			   mgmt_status(status), &rp, sizeof(rp));
+	cmd_complete(cmd->sk, cmd->index, MGMT_OP_DISCONNECT,
+		     mgmt_status(status), &rp, sizeof(rp));
 
 	mgmt_pending_remove(cmd);
-
-	return err;
 }
 
 int mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-- 
cgit 


From 445608d078bf7f7fe975792a940ffac83f495fa9 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:48 -0700
Subject: Bluetooth: Make mgmt_connect_failed() return void

The return value of mgmt_connect_failed() function is not used
so change it to just return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/mgmt.c             | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 429969fdb9f3..d982458a96e3 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1108,8 +1108,8 @@ int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 link_type, u8 addr_type, u8 reason);
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 link_type, u8 addr_type, u8 status);
-int mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			u8 addr_type, u8 status);
+void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+			 u8 addr_type, u8 status);
 int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
 int mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				 u8 status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a35f28e9172e..bd32c430cdfe 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4165,8 +4165,8 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	mgmt_pending_remove(cmd);
 }
 
-int mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			u8 addr_type, u8 status)
+void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+			 u8 addr_type, u8 status)
 {
 	struct mgmt_ev_connect_failed ev;
 
@@ -4174,7 +4174,7 @@ int mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.status = mgmt_status(status);
 
-	return mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL);
+	mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
-- 
cgit 


From ecd90ae7f600270d68b471f87c66d5b41ce5a974 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:49 -0700
Subject: Bluetooth: Make mgmt_device_connected() return void

The return value of mgmt_device_connected() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  6 +++---
 net/bluetooth/mgmt.c             | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d982458a96e3..48569442ec17 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1101,9 +1101,9 @@ int mgmt_connectable(struct hci_dev *hdev, u8 connectable);
 int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
 int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 		      bool persistent);
-int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			  u8 addr_type, u32 flags, u8 *name, u8 name_len,
-			  u8 *dev_class);
+void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
+			   u8 *dev_class);
 int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 link_type, u8 addr_type, u8 reason);
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index bd32c430cdfe..9029e67b3341 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4056,9 +4056,9 @@ int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
 			  NULL);
 }
 
-int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			  u8 addr_type, u32 flags, u8 *name, u8 name_len,
-			  u8 *dev_class)
+void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
+			   u8 *dev_class)
 {
 	char buf[512];
 	struct mgmt_ev_device_connected *ev = (void *) buf;
@@ -4079,8 +4079,8 @@ int mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	ev->eir_len = cpu_to_le16(eir_len);
 
-	return mgmt_event(MGMT_EV_DEVICE_CONNECTED, hdev, buf,
-			  sizeof(*ev) + eir_len, NULL);
+	mgmt_event(MGMT_EV_DEVICE_CONNECTED, hdev, buf,
+		    sizeof(*ev) + eir_len, NULL);
 }
 
 static void disconnect_rsp(struct pending_cmd *cmd, void *data)
-- 
cgit 


From 9b80ec5e8e66ada404ad65ce61a1de70fee0fbbd Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:50 -0700
Subject: Bluetooth: Make mgmt_device_disconnected() return void

The return value of mgmt_device_disconnected() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 10 +++-------
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 48569442ec17..2b0bc31ec785 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1104,8 +1104,8 @@ int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
 			   u8 *dev_class);
-int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			     u8 link_type, u8 addr_type, u8 reason);
+void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			      u8 link_type, u8 addr_type, u8 reason);
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 link_type, u8 addr_type, u8 status);
 void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9029e67b3341..b9cd5829672e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4118,12 +4118,11 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data)
 	mgmt_pending_remove(cmd);
 }
 
-int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
-			     u8 link_type, u8 addr_type, u8 reason)
+void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
+			      u8 link_type, u8 addr_type, u8 reason)
 {
 	struct mgmt_ev_device_disconnected ev;
 	struct sock *sk = NULL;
-	int err;
 
 	mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk);
 
@@ -4131,16 +4130,13 @@ int mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.reason = reason;
 
-	err = mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev),
-			 sk);
+	mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev), sk);
 
 	if (sk)
 		sock_put(sk);
 
 	mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
 			     hdev);
-
-	return err;
 }
 
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
-- 
cgit 


From 901801b9a420e58969e039731dd007ae104842d3 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:51 -0700
Subject: Bluetooth: Make mgmt_device_found() return void

The return value of mgmt_device_found() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  6 +++---
 net/bluetooth/mgmt.c             | 12 ++++++------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2b0bc31ec785..5b738a2d1786 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1140,9 +1140,9 @@ int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
 int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 					    u8 *randomizer, u8 status);
-int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		      u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
-		      u8 ssp, u8 *eir, u16 eir_len);
+void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
+		       u8 ssp, u8 *eir, u16 eir_len);
 int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		     u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 int mgmt_discovering(struct hci_dev *hdev, u8 discovering);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index b9cd5829672e..abf500b3b265 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4524,20 +4524,20 @@ int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 	return err;
 }
 
-int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		      u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
-		      ssp, u8 *eir, u16 eir_len)
+void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
+		       ssp, u8 *eir, u16 eir_len)
 {
 	char buf[512];
 	struct mgmt_ev_device_found *ev = (void *) buf;
 	size_t ev_size;
 
 	if (!hci_discovery_active(hdev))
-		return -EPERM;
+		return;
 
 	/* Leave 5 bytes for a potential CoD field */
 	if (sizeof(*ev) + eir_len + 5 > sizeof(buf))
-		return -EINVAL;
+		return;
 
 	memset(buf, 0, sizeof(buf));
 
@@ -4559,7 +4559,7 @@ int mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	ev->eir_len = cpu_to_le16(eir_len);
 	ev_size = sizeof(*ev) + eir_len;
 
-	return mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL);
+	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL);
 }
 
 int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-- 
cgit 


From 9cf12aee8bf5eb219c79089fb4556ad1d2066585 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:52 -0700
Subject: Bluetooth: Make mgmt_remote_name() return void

The return value of mgmt_remote_name() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/mgmt.c             | 7 +++----
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5b738a2d1786..960c64b92415 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1143,8 +1143,8 @@ int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
 		       u8 ssp, u8 *eir, u16 eir_len);
-int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		     u8 addr_type, s8 rssi, u8 *name, u8 name_len);
+void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 int mgmt_discovering(struct hci_dev *hdev, u8 discovering);
 int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index abf500b3b265..4a4545e1e44d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4562,8 +4562,8 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL);
 }
 
-int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		     u8 addr_type, s8 rssi, u8 *name, u8 name_len)
+void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		      u8 addr_type, s8 rssi, u8 *name, u8 name_len)
 {
 	struct mgmt_ev_device_found *ev;
 	char buf[sizeof(*ev) + HCI_MAX_NAME_LENGTH + 2];
@@ -4582,8 +4582,7 @@ int mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	ev->eir_len = cpu_to_le16(eir_len);
 
-	return mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev,
-			  sizeof(*ev) + eir_len, NULL);
+	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, sizeof(*ev) + eir_len, NULL);
 }
 
 int mgmt_discovering(struct hci_dev *hdev, u8 discovering)
-- 
cgit 


From 2f1e063bc035dbbdb9174cc5f55f073a28780aa8 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 6 Oct 2013 23:55:53 -0700
Subject: Bluetooth: Make mgmt_discovering() return void

The return value of mgmt_discovering() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/mgmt.c             | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 960c64b92415..c06552769644 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1145,7 +1145,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 ssp, u8 *eir, u16 eir_len);
 void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
-int mgmt_discovering(struct hci_dev *hdev, u8 discovering);
+void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
 int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 4a4545e1e44d..4070bb05d304 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4585,7 +4585,7 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, sizeof(*ev) + eir_len, NULL);
 }
 
-int mgmt_discovering(struct hci_dev *hdev, u8 discovering)
+void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 {
 	struct mgmt_ev_discovering ev;
 	struct pending_cmd *cmd;
@@ -4609,7 +4609,7 @@ int mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	ev.type = hdev->discovery.type;
 	ev.discovering = discovering;
 
-	return mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
+	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
-- 
cgit 


From 7528ca1c5a3821951695e0e55daf192097a9925a Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 7 Oct 2013 03:55:52 -0700
Subject: Bluetooth: Read location data on AMP controller init

When initializing an AMP controller, read its current known location
data so that it can be analyzed later on.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 2 ++
 net/bluetooth/hci_core.c    | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 3616ea794eb1..c8a91cb20173 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -851,6 +851,8 @@ struct hci_rp_read_inq_rsp_tx_power {
 
 #define HCI_OP_SET_EVENT_MASK_PAGE_2	0x0c63
 
+#define HCI_OP_READ_LOCATION_DATA	0x0c64
+
 #define HCI_OP_READ_FLOW_CONTROL_MODE	0x0c66
 struct hci_rp_read_flow_control_mode {
 	__u8     status;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 99f83abbcaa6..967739c0285b 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -318,6 +318,9 @@ static void amp_init(struct hci_request *req)
 
 	/* Read Data Blk size */
 	hci_req_add(req, HCI_OP_READ_DATA_BLOCK_SIZE, 0, NULL);
+
+	/* Read Location Data */
+	hci_req_add(req, HCI_OP_READ_LOCATION_DATA, 0, NULL);
 }
 
 static void hci_init1_req(struct hci_request *req, unsigned long opt)
-- 
cgit 


From 56ec1978ff07380bbdc0a942c8779ec9fd9e02ee Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Mon, 7 Oct 2013 19:33:53 +0100
Subject: spi: Provide trace points for message processing

Provide tracepoints for the lifecycle of a message from submission to
completion and for the active time for masters to help with performance
analysis of SPI I/O.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c          | 16 +++++++-
 include/trace/events/spi.h | 94 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 109 insertions(+), 1 deletion(-)
 create mode 100644 include/trace/events/spi.h

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 9e039c60c068..8bef0c9a7233 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -39,6 +39,9 @@
 #include <linux/ioport.h>
 #include <linux/acpi.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/spi.h>
+
 static void spidev_release(struct device *dev)
 {
 	struct spi_device	*spi = to_spi_device(dev);
@@ -557,6 +560,7 @@ static void spi_pump_messages(struct kthread_work *work)
 			pm_runtime_mark_last_busy(master->dev.parent);
 			pm_runtime_put_autosuspend(master->dev.parent);
 		}
+		trace_spi_master_idle(master);
 		return;
 	}
 
@@ -585,6 +589,9 @@ static void spi_pump_messages(struct kthread_work *work)
 		}
 	}
 
+	if (!was_busy)
+		trace_spi_master_busy(master);
+
 	if (!was_busy && master->prepare_transfer_hardware) {
 		ret = master->prepare_transfer_hardware(master);
 		if (ret) {
@@ -597,6 +604,8 @@ static void spi_pump_messages(struct kthread_work *work)
 		}
 	}
 
+	trace_spi_message_start(master->cur_msg);
+
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
@@ -689,6 +698,8 @@ void spi_finalize_current_message(struct spi_master *master)
 	mesg->state = NULL;
 	if (mesg->complete)
 		mesg->complete(mesg->context);
+
+	trace_spi_message_done(mesg);
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_message);
 
@@ -1421,6 +1432,10 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
 	struct spi_master *master = spi->master;
 	struct spi_transfer *xfer;
 
+	message->spi = spi;
+
+	trace_spi_message_submit(message);
+
 	if (list_empty(&message->transfers))
 		return -EINVAL;
 	if (!message->complete)
@@ -1520,7 +1535,6 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
 		}
 	}
 
-	message->spi = spi;
 	message->status = -EINPROGRESS;
 	return master->transfer(spi, message);
 }
diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h
new file mode 100644
index 000000000000..a7b09072ce56
--- /dev/null
+++ b/include/trace/events/spi.h
@@ -0,0 +1,94 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM spi
+
+#if !defined(_TRACE_SPI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SPI_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(spi_master,
+
+	TP_PROTO(struct spi_master *master),
+
+	TP_ARGS(master),
+
+	TP_STRUCT__entry(
+		__field(        int,           bus_num             )
+	),
+
+	TP_fast_assign(
+		__entry->bus_num = master->bus_num;
+	),
+
+	TP_printk("spi%d", (int)__entry->bus_num)
+
+);
+
+DEFINE_EVENT(spi_master, spi_master_idle,
+
+	TP_PROTO(struct spi_master *master),
+
+	TP_ARGS(master)
+
+);
+
+DEFINE_EVENT(spi_master, spi_master_busy,
+
+	TP_PROTO(struct spi_master *master),
+
+	TP_ARGS(master)
+
+);
+
+DECLARE_EVENT_CLASS(spi_message,
+
+	TP_PROTO(struct spi_message *msg),
+
+	TP_ARGS(msg),
+
+	TP_STRUCT__entry(
+		__field(        int,            bus_num         )
+		__field(        int,            chip_select     )
+		__field(        struct spi_message *,   msg     )
+	),
+
+	TP_fast_assign(
+		__entry->bus_num = msg->spi->master->bus_num;
+		__entry->chip_select = msg->spi->chip_select;
+		__entry->msg = msg;
+	),
+
+        TP_printk("spi%d.%d %p", (int)__entry->bus_num,
+		  (int)__entry->chip_select,
+		  (struct spi_message *)__entry->msg)
+);
+
+DEFINE_EVENT(spi_message, spi_message_submit,
+
+	TP_PROTO(struct spi_message *msg),
+
+	TP_ARGS(msg)
+
+);
+
+DEFINE_EVENT(spi_message, spi_message_start,
+
+	TP_PROTO(struct spi_message *msg),
+
+	TP_ARGS(msg)
+
+);
+
+DEFINE_EVENT(spi_message, spi_message_done,
+
+	TP_PROTO(struct spi_message *msg),
+
+	TP_ARGS(msg)
+
+);
+
+#endif /* _TRACE_POWER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit 


From 5cde282938915f36a2e6769b51c24c4159654859 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 5 Oct 2013 19:26:05 -0700
Subject: net: Separate the close_list and the unreg_list v2

Separate the unreg_list and the close_list in dev_close_many preventing
dev_close_many from permuting the unreg_list.  The permutations of the
unreg_list have resulted in cases where the loopback device is accessed
it has been freed in code such as dst_ifdown.  Resulting in subtle memory
corruption.

This is the second bug from sharing the storage between the close_list
and the unreg_list.  The issues that crop up with sharing are
apparently too subtle to show up in normal testing or usage, so let's
forget about being clever and use two separate lists.

v2: Make all callers pass in a close_list to dev_close_many

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 25 ++++++++++++++-----------
 net/sched/sch_generic.c   |  6 +++---
 3 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f5cd464271bf..6d77e0f3cc10 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1143,6 +1143,7 @@ struct net_device {
 	struct list_head	dev_list;
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
+	struct list_head	close_list;
 
 	/* directly linked devices, like slaves for bonding */
 	struct {
diff --git a/net/core/dev.c b/net/core/dev.c
index c25db20a4246..fa0b2b06c1a6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1307,7 +1307,7 @@ static int __dev_close_many(struct list_head *head)
 	ASSERT_RTNL();
 	might_sleep();
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry(dev, head, close_list) {
 		call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
 
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1323,7 +1323,7 @@ static int __dev_close_many(struct list_head *head)
 
 	dev_deactivate_many(head);
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry(dev, head, close_list) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 
 		/*
@@ -1351,7 +1351,7 @@ static int __dev_close(struct net_device *dev)
 	/* Temporarily disable netpoll until the interface is down */
 	netpoll_rx_disable(dev);
 
-	list_add(&dev->unreg_list, &single);
+	list_add(&dev->close_list, &single);
 	retval = __dev_close_many(&single);
 	list_del(&single);
 
@@ -1362,21 +1362,20 @@ static int __dev_close(struct net_device *dev)
 static int dev_close_many(struct list_head *head)
 {
 	struct net_device *dev, *tmp;
-	LIST_HEAD(tmp_list);
 
-	list_for_each_entry_safe(dev, tmp, head, unreg_list)
+	/* Remove the devices that don't need to be closed */
+	list_for_each_entry_safe(dev, tmp, head, close_list)
 		if (!(dev->flags & IFF_UP))
-			list_move(&dev->unreg_list, &tmp_list);
+			list_del_init(&dev->close_list);
 
 	__dev_close_many(head);
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry_safe(dev, tmp, head, close_list) {
 		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
 		call_netdevice_notifiers(NETDEV_DOWN, dev);
+		list_del_init(&dev->close_list);
 	}
 
-	/* rollback_registered_many needs the complete original list */
-	list_splice(&tmp_list, head);
 	return 0;
 }
 
@@ -1397,7 +1396,7 @@ int dev_close(struct net_device *dev)
 		/* Block netpoll rx while the interface is going down */
 		netpoll_rx_disable(dev);
 
-		list_add(&dev->unreg_list, &single);
+		list_add(&dev->close_list, &single);
 		dev_close_many(&single);
 		list_del(&single);
 
@@ -5439,6 +5438,7 @@ static void net_set_todo(struct net_device *dev)
 static void rollback_registered_many(struct list_head *head)
 {
 	struct net_device *dev, *tmp;
+	LIST_HEAD(close_head);
 
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();
@@ -5461,7 +5461,9 @@ static void rollback_registered_many(struct list_head *head)
 	}
 
 	/* If device is running, close it first. */
-	dev_close_many(head);
+	list_for_each_entry(dev, head, unreg_list)
+		list_add_tail(&dev->close_list, &close_head);
+	dev_close_many(&close_head);
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
@@ -6257,6 +6259,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
+	INIT_LIST_HEAD(&dev->close_list);
 	INIT_LIST_HEAD(&dev->link_watch_list);
 	INIT_LIST_HEAD(&dev->adj_list.upper);
 	INIT_LIST_HEAD(&dev->adj_list.lower);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e7121d29c4bd..7fc899a943a8 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -829,7 +829,7 @@ void dev_deactivate_many(struct list_head *head)
 	struct net_device *dev;
 	bool sync_needed = false;
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry(dev, head, close_list) {
 		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
 					 &noop_qdisc);
 		if (dev_ingress_queue(dev))
@@ -848,7 +848,7 @@ void dev_deactivate_many(struct list_head *head)
 		synchronize_net();
 
 	/* Wait for outstanding qdisc_run calls. */
-	list_for_each_entry(dev, head, unreg_list)
+	list_for_each_entry(dev, head, close_list)
 		while (some_qdisc_is_busy(dev))
 			yield();
 }
@@ -857,7 +857,7 @@ void dev_deactivate(struct net_device *dev)
 {
 	LIST_HEAD(single);
 
-	list_add(&dev->unreg_list, &single);
+	list_add(&dev->close_list, &single);
 	dev_deactivate_many(&single);
 	list_del(&single);
 }
-- 
cgit 


From ddeccb8d6b5bbe2c1e3a29f8c74b52f170c2207d Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Tue, 8 Oct 2013 06:42:10 +0900
Subject: dmaengine: add driver for Samsung s3c24xx SoCs

This adds a new driver to support the s3c24xx dma using the dmaengine
and makes the old one in mach-s3c24xx obsolete in the long run.

Conceptually the s3c24xx-dma feels like a distant relative of the pl08x
with numerous virtual channels being mapped to a lot less physical ones.
The driver therefore borrows a lot from the amba-pl08x driver in this
regard. Functionality-wise the driver gains a memcpy ability in addition
to the slave_sg one.

The driver supports both the method for requesting the peripheral used
by SoCs before the S3C2443 and the different method for S3C2443 and later.

On earlier SoCs the hardware channels usable for specific peripherals is
constrainted while on later SoCs all channels can be used for any peripheral.

Tested on a s3c2416-based board, memcpy using the dmatest module and
slave_sg partially using the spi-s3c64xx driver.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
---
 drivers/dma/Kconfig                       |   12 +
 drivers/dma/Makefile                      |    1 +
 drivers/dma/s3c24xx-dma.c                 | 1340 +++++++++++++++++++++++++++++
 include/linux/platform_data/dma-s3c24xx.h |   43 +
 4 files changed, 1396 insertions(+)
 create mode 100644 drivers/dma/s3c24xx-dma.c
 create mode 100644 include/linux/platform_data/dma-s3c24xx.h

(limited to 'include')

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 526ec77c7ba0..d639115aa875 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -154,6 +154,18 @@ config TEGRA20_APB_DMA
 	  This DMA controller transfers data from memory to peripheral fifo
 	  or vice versa. It does not support memory to memory data transfer.
 
+config S3C24XX_DMAC
+	tristate "Samsung S3C24XX DMA support"
+	depends on ARCH_S3C24XX && !S3C24XX_DMA
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Samsung S3C24XX DMA controller driver. The
+	  DMA controller is having multiple DMA channels which can be
+	  configured for different peripherals like audio, UART, SPI.
+	  The DMA controller can transfer data from memory to peripheral,
+	  periphal to memory, periphal to periphal and memory to memory.
+
 source "drivers/dma/sh/Kconfig"
 
 config COH901318
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index db89035b3626..0ce2da97e429 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
+obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
 obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
new file mode 100644
index 000000000000..56c92538bc4c
--- /dev/null
+++ b/drivers/dma/s3c24xx-dma.c
@@ -0,0 +1,1340 @@
+/*
+ * S3C24XX DMA handling
+ *
+ * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
+ *
+ * based on amba-pl08x.c
+ *
+ * Copyright (c) 2006 ARM Ltd.
+ * Copyright (c) 2010 ST-Ericsson SA
+ *
+ * Author: Peter Pearse <peter.pearse@arm.com>
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * The DMA controllers in S3C24XX SoCs have a varying number of DMA signals
+ * that can be routed to any of the 4 to 8 hardware-channels.
+ *
+ * Therefore on these DMA controllers the number of channels
+ * and the number of incoming DMA signals are two totally different things.
+ * It is usually not possible to theoretically handle all physical signals,
+ * so a multiplexing scheme with possible denial of use is necessary.
+ *
+ * Open items:
+ * - bursts
+ */
+
+#include <linux/platform_device.h>
+#include <linux/types.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/platform_data/dma-s3c24xx.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+#define MAX_DMA_CHANNELS	8
+
+#define S3C24XX_DISRC			0x00
+#define S3C24XX_DISRCC			0x04
+#define S3C24XX_DISRCC_INC_INCREMENT	0
+#define S3C24XX_DISRCC_INC_FIXED	BIT(0)
+#define S3C24XX_DISRCC_LOC_AHB		0
+#define S3C24XX_DISRCC_LOC_APB		BIT(1)
+
+#define S3C24XX_DIDST			0x08
+#define S3C24XX_DIDSTC			0x0c
+#define S3C24XX_DIDSTC_INC_INCREMENT	0
+#define S3C24XX_DIDSTC_INC_FIXED	BIT(0)
+#define S3C24XX_DIDSTC_LOC_AHB		0
+#define S3C24XX_DIDSTC_LOC_APB		BIT(1)
+#define S3C24XX_DIDSTC_INT_TC0		0
+#define S3C24XX_DIDSTC_INT_RELOAD	BIT(2)
+
+#define S3C24XX_DCON			0x10
+
+#define S3C24XX_DCON_TC_MASK		0xfffff
+#define S3C24XX_DCON_DSZ_BYTE		(0 << 20)
+#define S3C24XX_DCON_DSZ_HALFWORD	(1 << 20)
+#define S3C24XX_DCON_DSZ_WORD		(2 << 20)
+#define S3C24XX_DCON_DSZ_MASK		(3 << 20)
+#define S3C24XX_DCON_DSZ_SHIFT		20
+#define S3C24XX_DCON_AUTORELOAD		0
+#define S3C24XX_DCON_NORELOAD		BIT(22)
+#define S3C24XX_DCON_HWTRIG		BIT(23)
+#define S3C24XX_DCON_HWSRC_SHIFT	24
+#define S3C24XX_DCON_SERV_SINGLE	0
+#define S3C24XX_DCON_SERV_WHOLE		BIT(27)
+#define S3C24XX_DCON_TSZ_UNIT		0
+#define S3C24XX_DCON_TSZ_BURST4		BIT(28)
+#define S3C24XX_DCON_INT		BIT(29)
+#define S3C24XX_DCON_SYNC_PCLK		0
+#define S3C24XX_DCON_SYNC_HCLK		BIT(30)
+#define S3C24XX_DCON_DEMAND		0
+#define S3C24XX_DCON_HANDSHAKE		BIT(31)
+
+#define S3C24XX_DSTAT			0x14
+#define S3C24XX_DSTAT_STAT_BUSY		BIT(20)
+#define S3C24XX_DSTAT_CURRTC_MASK	0xfffff
+
+#define S3C24XX_DMASKTRIG		0x20
+#define S3C24XX_DMASKTRIG_SWTRIG	BIT(0)
+#define S3C24XX_DMASKTRIG_ON		BIT(1)
+#define S3C24XX_DMASKTRIG_STOP		BIT(2)
+
+#define S3C24XX_DMAREQSEL		0x24
+#define S3C24XX_DMAREQSEL_HW		BIT(0)
+
+/*
+ * S3C2410, S3C2440 and S3C2442 SoCs cannot select any physical channel
+ * for a DMA source. Instead only specific channels are valid.
+ * All of these SoCs have 4 physical channels and the number of request
+ * source bits is 3. Additionally we also need 1 bit to mark the channel
+ * as valid.
+ * Therefore we separate the chansel element of the channel data into 4
+ * parts of 4 bits each, to hold the information if the channel is valid
+ * and the hw request source to use.
+ *
+ * Example:
+ * SDI is valid on channels 0, 2 and 3 - with varying hw request sources.
+ * For it the chansel field would look like
+ *
+ * ((BIT(3) | 1) << 3 * 4) | // channel 3, with request source 1
+ * ((BIT(3) | 2) << 2 * 4) | // channel 2, with request source 2
+ * ((BIT(3) | 2) << 0 * 4)   // channel 0, with request source 2
+ */
+#define S3C24XX_CHANSEL_WIDTH		4
+#define S3C24XX_CHANSEL_VALID		BIT(3)
+#define S3C24XX_CHANSEL_REQ_MASK	7
+
+/*
+ * struct soc_data - vendor-specific config parameters for individual SoCs
+ * @stride: spacing between the registers of each channel
+ * @has_reqsel: does the controller use the newer requestselection mechanism
+ * @has_clocks: are controllable dma-clocks present
+ */
+struct soc_data {
+	int stride;
+	bool has_reqsel;
+	bool has_clocks;
+};
+
+/*
+ * enum s3c24xx_dma_chan_state - holds the virtual channel states
+ * @S3C24XX_DMA_CHAN_IDLE: the channel is idle
+ * @S3C24XX_DMA_CHAN_RUNNING: the channel has allocated a physical transport
+ * channel and is running a transfer on it
+ * @S3C24XX_DMA_CHAN_WAITING: the channel is waiting for a physical transport
+ * channel to become available (only pertains to memcpy channels)
+ */
+enum s3c24xx_dma_chan_state {
+	S3C24XX_DMA_CHAN_IDLE,
+	S3C24XX_DMA_CHAN_RUNNING,
+	S3C24XX_DMA_CHAN_WAITING,
+};
+
+/*
+ * struct s3c24xx_sg - structure containing data per sg
+ * @src_addr: src address of sg
+ * @dst_addr: dst address of sg
+ * @len: transfer len in bytes
+ * @node: node for txd's dsg_list
+ */
+struct s3c24xx_sg {
+	dma_addr_t src_addr;
+	dma_addr_t dst_addr;
+	size_t len;
+	struct list_head node;
+};
+
+/*
+ * struct s3c24xx_txd - wrapper for struct dma_async_tx_descriptor
+ * @vd: virtual DMA descriptor
+ * @dsg_list: list of children sg's
+ * @at: sg currently being transfered
+ * @width: transfer width
+ * @disrcc: value for source control register
+ * @didstc: value for destination control register
+ * @dcon: base value for dcon register
+ */
+struct s3c24xx_txd {
+	struct virt_dma_desc vd;
+	struct list_head dsg_list;
+	struct list_head *at;
+	u8 width;
+	u32 disrcc;
+	u32 didstc;
+	u32 dcon;
+};
+
+struct s3c24xx_dma_chan;
+
+/*
+ * struct s3c24xx_dma_phy - holder for the physical channels
+ * @id: physical index to this channel
+ * @valid: does the channel have all required elements
+ * @base: virtual memory base (remapped) for the this channel
+ * @irq: interrupt for this channel
+ * @clk: clock for this channel
+ * @lock: a lock to use when altering an instance of this struct
+ * @serving: virtual channel currently being served by this physicalchannel
+ * @host: a pointer to the host (internal use)
+ */
+struct s3c24xx_dma_phy {
+	unsigned int			id;
+	bool				valid;
+	void __iomem			*base;
+	unsigned int			irq;
+	struct clk			*clk;
+	spinlock_t			lock;
+	struct s3c24xx_dma_chan		*serving;
+	struct s3c24xx_dma_engine	*host;
+};
+
+/*
+ * struct s3c24xx_dma_chan - this structure wraps a DMA ENGINE channel
+ * @id: the id of the channel
+ * @name: name of the channel
+ * @vc: wrappped virtual channel
+ * @phy: the physical channel utilized by this channel, if there is one
+ * @runtime_addr: address for RX/TX according to the runtime config
+ * @at: active transaction on this channel
+ * @lock: a lock for this channel data
+ * @host: a pointer to the host (internal use)
+ * @state: whether the channel is idle, running etc
+ * @slave: whether this channel is a device (slave) or for memcpy
+ */
+struct s3c24xx_dma_chan {
+	int id;
+	const char *name;
+	struct virt_dma_chan vc;
+	struct s3c24xx_dma_phy *phy;
+	struct dma_slave_config cfg;
+	struct s3c24xx_txd *at;
+	struct s3c24xx_dma_engine *host;
+	enum s3c24xx_dma_chan_state state;
+	bool slave;
+};
+
+/*
+ * struct s3c24xx_dma_engine - the local state holder for the S3C24XX
+ * @pdev: the corresponding platform device
+ * @pdata: platform data passed in from the platform/machine
+ * @base: virtual memory base (remapped)
+ * @slave: slave engine for this instance
+ * @memcpy: memcpy engine for this instance
+ * @phy_chans: array of data for the physical channels
+ */
+struct s3c24xx_dma_engine {
+	struct platform_device			*pdev;
+	const struct s3c24xx_dma_platdata	*pdata;
+	struct soc_data				*sdata;
+	void __iomem				*base;
+	struct dma_device			slave;
+	struct dma_device			memcpy;
+	struct s3c24xx_dma_phy			*phy_chans;
+};
+
+/*
+ * Physical channel handling
+ */
+
+/*
+ * Check whether a certain channel is busy or not.
+ */
+static int s3c24xx_dma_phy_busy(struct s3c24xx_dma_phy *phy)
+{
+	unsigned int val = readl(phy->base + S3C24XX_DSTAT);
+	return val & S3C24XX_DSTAT_STAT_BUSY;
+}
+
+static bool s3c24xx_dma_phy_valid(struct s3c24xx_dma_chan *s3cchan,
+				  struct s3c24xx_dma_phy *phy)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
+	int phyvalid;
+
+	/* every phy is valid for memcopy channels */
+	if (!s3cchan->slave)
+		return true;
+
+	/* On newer variants all phys can be used for all virtual channels */
+	if (s3cdma->sdata->has_reqsel)
+		return true;
+
+	phyvalid = (cdata->chansel >> (phy->id * S3C24XX_CHANSEL_WIDTH));
+	return (phyvalid & S3C24XX_CHANSEL_VALID) ? true : false;
+}
+
+/*
+ * Allocate a physical channel for a virtual channel
+ *
+ * Try to locate a physical channel to be used for this transfer. If all
+ * are taken return NULL and the requester will have to cope by using
+ * some fallback PIO mode or retrying later.
+ */
+static
+struct s3c24xx_dma_phy *s3c24xx_dma_get_phy(struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_dma_channel *cdata;
+	struct s3c24xx_dma_phy *phy = NULL;
+	unsigned long flags;
+	int i;
+	int ret;
+
+	if (s3cchan->slave)
+		cdata = &pdata->channels[s3cchan->id];
+
+	for (i = 0; i < s3cdma->pdata->num_phy_channels; i++) {
+		phy = &s3cdma->phy_chans[i];
+
+		if (!phy->valid)
+			continue;
+
+		if (!s3c24xx_dma_phy_valid(s3cchan, phy))
+			continue;
+
+		spin_lock_irqsave(&phy->lock, flags);
+
+		if (!phy->serving) {
+			phy->serving = s3cchan;
+			spin_unlock_irqrestore(&phy->lock, flags);
+			break;
+		}
+
+		spin_unlock_irqrestore(&phy->lock, flags);
+	}
+
+	/* No physical channel available, cope with it */
+	if (i == s3cdma->pdata->num_phy_channels) {
+		dev_warn(&s3cdma->pdev->dev, "no phy channel available\n");
+		return NULL;
+	}
+
+	/* start the phy clock */
+	if (s3cdma->sdata->has_clocks) {
+		ret = clk_enable(phy->clk);
+		if (ret) {
+			dev_err(&s3cdma->pdev->dev, "could not enable clock for channel %d, err %d\n",
+				phy->id, ret);
+			phy->serving = NULL;
+			return NULL;
+		}
+	}
+
+	return phy;
+}
+
+/*
+ * Mark the physical channel as free.
+ *
+ * This drops the link between the physical and virtual channel.
+ */
+static inline void s3c24xx_dma_put_phy(struct s3c24xx_dma_phy *phy)
+{
+	struct s3c24xx_dma_engine *s3cdma = phy->host;
+
+	if (s3cdma->sdata->has_clocks)
+		clk_disable(phy->clk);
+
+	phy->serving = NULL;
+}
+
+/*
+ * Stops the channel by writing the stop bit.
+ * This should not be used for an on-going transfer, but as a method of
+ * shutting down a channel (eg, when it's no longer used) or terminating a
+ * transfer.
+ */
+static void s3c24xx_dma_terminate_phy(struct s3c24xx_dma_phy *phy)
+{
+	writel(S3C24XX_DMASKTRIG_STOP, phy->base + S3C24XX_DMASKTRIG);
+}
+
+/*
+ * Virtual channel handling
+ */
+
+static inline
+struct s3c24xx_dma_chan *to_s3c24xx_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct s3c24xx_dma_chan, vc.chan);
+}
+
+static u32 s3c24xx_dma_getbytes_chan(struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_phy *phy = s3cchan->phy;
+	struct s3c24xx_txd *txd = s3cchan->at;
+	u32 tc = readl(phy->base + S3C24XX_DSTAT) & S3C24XX_DSTAT_CURRTC_MASK;
+
+	return tc * txd->width;
+}
+
+static int s3c24xx_dma_set_runtime_config(struct s3c24xx_dma_chan *s3cchan,
+				  struct dma_slave_config *config)
+{
+	if (!s3cchan->slave)
+		return -EINVAL;
+
+	/* Reject definitely invalid configurations */
+	if (config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	s3cchan->cfg = *config;
+
+	return 0;
+}
+
+/*
+ * Transfer handling
+ */
+
+static inline
+struct s3c24xx_txd *to_s3c24xx_txd(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct s3c24xx_txd, vd.tx);
+}
+
+static struct s3c24xx_txd *s3c24xx_dma_get_txd(void)
+{
+	struct s3c24xx_txd *txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
+
+	if (txd) {
+		INIT_LIST_HEAD(&txd->dsg_list);
+		txd->dcon = S3C24XX_DCON_INT | S3C24XX_DCON_NORELOAD;
+	}
+
+	return txd;
+}
+
+static void s3c24xx_dma_free_txd(struct s3c24xx_txd *txd)
+{
+	struct s3c24xx_sg *dsg, *_dsg;
+
+	list_for_each_entry_safe(dsg, _dsg, &txd->dsg_list, node) {
+		list_del(&dsg->node);
+		kfree(dsg);
+	}
+
+	kfree(txd);
+}
+
+static void s3c24xx_dma_start_next_sg(struct s3c24xx_dma_chan *s3cchan,
+				       struct s3c24xx_txd *txd)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	struct s3c24xx_dma_phy *phy = s3cchan->phy;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_sg *dsg = list_entry(txd->at, struct s3c24xx_sg, node);
+	u32 dcon = txd->dcon;
+	u32 val;
+
+	/* transfer-size and -count from len and width */
+	switch (txd->width) {
+	case 1:
+		dcon |= S3C24XX_DCON_DSZ_BYTE | dsg->len;
+		break;
+	case 2:
+		dcon |= S3C24XX_DCON_DSZ_HALFWORD | (dsg->len / 2);
+		break;
+	case 4:
+		dcon |= S3C24XX_DCON_DSZ_WORD | (dsg->len / 4);
+		break;
+	}
+
+	if (s3cchan->slave) {
+		struct s3c24xx_dma_channel *cdata =
+					&pdata->channels[s3cchan->id];
+
+		if (s3cdma->sdata->has_reqsel) {
+			writel_relaxed((cdata->chansel << 1) |
+							S3C24XX_DMAREQSEL_HW,
+					phy->base + S3C24XX_DMAREQSEL);
+		} else {
+			int csel = cdata->chansel >> (phy->id *
+							S3C24XX_CHANSEL_WIDTH);
+
+			csel &= S3C24XX_CHANSEL_REQ_MASK;
+			dcon |= csel << S3C24XX_DCON_HWSRC_SHIFT;
+			dcon |= S3C24XX_DCON_HWTRIG;
+		}
+	} else {
+		if (s3cdma->sdata->has_reqsel)
+			writel_relaxed(0, phy->base + S3C24XX_DMAREQSEL);
+	}
+
+	writel_relaxed(dsg->src_addr, phy->base + S3C24XX_DISRC);
+	writel_relaxed(txd->disrcc, phy->base + S3C24XX_DISRCC);
+	writel_relaxed(dsg->dst_addr, phy->base + S3C24XX_DIDST);
+	writel_relaxed(txd->didstc, phy->base + S3C24XX_DIDSTC);
+	writel_relaxed(dcon, phy->base + S3C24XX_DCON);
+
+	val = readl_relaxed(phy->base + S3C24XX_DMASKTRIG);
+	val &= ~S3C24XX_DMASKTRIG_STOP;
+	val |= S3C24XX_DMASKTRIG_ON;
+
+	/* trigger the dma operation for memcpy transfers */
+	if (!s3cchan->slave)
+		val |= S3C24XX_DMASKTRIG_SWTRIG;
+
+	writel(val, phy->base + S3C24XX_DMASKTRIG);
+}
+
+/*
+ * Set the initial DMA register values and start first sg.
+ */
+static void s3c24xx_dma_start_next_txd(struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_phy *phy = s3cchan->phy;
+	struct virt_dma_desc *vd = vchan_next_desc(&s3cchan->vc);
+	struct s3c24xx_txd *txd = to_s3c24xx_txd(&vd->tx);
+
+	list_del(&txd->vd.node);
+
+	s3cchan->at = txd;
+
+	/* Wait for channel inactive */
+	while (s3c24xx_dma_phy_busy(phy))
+		cpu_relax();
+
+	/* point to the first element of the sg list */
+	txd->at = txd->dsg_list.next;
+	s3c24xx_dma_start_next_sg(s3cchan, txd);
+}
+
+static void s3c24xx_dma_free_txd_list(struct s3c24xx_dma_engine *s3cdma,
+				struct s3c24xx_dma_chan *s3cchan)
+{
+	LIST_HEAD(head);
+
+	vchan_get_all_descriptors(&s3cchan->vc, &head);
+	vchan_dma_desc_free_list(&s3cchan->vc, &head);
+}
+
+/*
+ * Try to allocate a physical channel.  When successful, assign it to
+ * this virtual channel, and initiate the next descriptor.  The
+ * virtual channel lock must be held at this point.
+ */
+static void s3c24xx_dma_phy_alloc_and_start(struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	struct s3c24xx_dma_phy *phy;
+
+	phy = s3c24xx_dma_get_phy(s3cchan);
+	if (!phy) {
+		dev_dbg(&s3cdma->pdev->dev, "no physical channel available for xfer on %s\n",
+			s3cchan->name);
+		s3cchan->state = S3C24XX_DMA_CHAN_WAITING;
+		return;
+	}
+
+	dev_dbg(&s3cdma->pdev->dev, "allocated physical channel %d for xfer on %s\n",
+		phy->id, s3cchan->name);
+
+	s3cchan->phy = phy;
+	s3cchan->state = S3C24XX_DMA_CHAN_RUNNING;
+
+	s3c24xx_dma_start_next_txd(s3cchan);
+}
+
+static void s3c24xx_dma_phy_reassign_start(struct s3c24xx_dma_phy *phy,
+	struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+
+	dev_dbg(&s3cdma->pdev->dev, "reassigned physical channel %d for xfer on %s\n",
+		phy->id, s3cchan->name);
+
+	/*
+	 * We do this without taking the lock; we're really only concerned
+	 * about whether this pointer is NULL or not, and we're guaranteed
+	 * that this will only be called when it _already_ is non-NULL.
+	 */
+	phy->serving = s3cchan;
+	s3cchan->phy = phy;
+	s3cchan->state = S3C24XX_DMA_CHAN_RUNNING;
+	s3c24xx_dma_start_next_txd(s3cchan);
+}
+
+/*
+ * Free a physical DMA channel, potentially reallocating it to another
+ * virtual channel if we have any pending.
+ */
+static void s3c24xx_dma_phy_free(struct s3c24xx_dma_chan *s3cchan)
+{
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	struct s3c24xx_dma_chan *p, *next;
+
+retry:
+	next = NULL;
+
+	/* Find a waiting virtual channel for the next transfer. */
+	list_for_each_entry(p, &s3cdma->memcpy.channels, vc.chan.device_node)
+		if (p->state == S3C24XX_DMA_CHAN_WAITING) {
+			next = p;
+			break;
+		}
+
+	if (!next) {
+		list_for_each_entry(p, &s3cdma->slave.channels,
+				    vc.chan.device_node)
+			if (p->state == S3C24XX_DMA_CHAN_WAITING &&
+				      s3c24xx_dma_phy_valid(p, s3cchan->phy)) {
+				next = p;
+				break;
+			}
+	}
+
+	/* Ensure that the physical channel is stopped */
+	s3c24xx_dma_terminate_phy(s3cchan->phy);
+
+	if (next) {
+		bool success;
+
+		/*
+		 * Eww.  We know this isn't going to deadlock
+		 * but lockdep probably doesn't.
+		 */
+		spin_lock(&next->vc.lock);
+		/* Re-check the state now that we have the lock */
+		success = next->state == S3C24XX_DMA_CHAN_WAITING;
+		if (success)
+			s3c24xx_dma_phy_reassign_start(s3cchan->phy, next);
+		spin_unlock(&next->vc.lock);
+
+		/* If the state changed, try to find another channel */
+		if (!success)
+			goto retry;
+	} else {
+		/* No more jobs, so free up the physical channel */
+		s3c24xx_dma_put_phy(s3cchan->phy);
+	}
+
+	s3cchan->phy = NULL;
+	s3cchan->state = S3C24XX_DMA_CHAN_IDLE;
+}
+
+static void s3c24xx_dma_unmap_buffers(struct s3c24xx_txd *txd)
+{
+	struct device *dev = txd->vd.tx.chan->device->dev;
+	struct s3c24xx_sg *dsg;
+
+	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		if (txd->vd.tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_single(dev, dsg->src_addr, dsg->len,
+						DMA_TO_DEVICE);
+		else {
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_page(dev, dsg->src_addr, dsg->len,
+						DMA_TO_DEVICE);
+		}
+	}
+
+	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+		if (txd->vd.tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_single(dev, dsg->dst_addr, dsg->len,
+						DMA_FROM_DEVICE);
+		else
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_page(dev, dsg->dst_addr, dsg->len,
+						DMA_FROM_DEVICE);
+	}
+}
+
+static void s3c24xx_dma_desc_free(struct virt_dma_desc *vd)
+{
+	struct s3c24xx_txd *txd = to_s3c24xx_txd(&vd->tx);
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(vd->tx.chan);
+
+	if (!s3cchan->slave)
+		s3c24xx_dma_unmap_buffers(txd);
+
+	s3c24xx_dma_free_txd(txd);
+}
+
+static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
+{
+	struct s3c24xx_dma_phy *phy = data;
+	struct s3c24xx_dma_chan *s3cchan = phy->serving;
+	struct s3c24xx_txd *txd;
+
+	dev_dbg(&phy->host->pdev->dev, "interrupt on channel %d\n", phy->id);
+
+	/*
+	 * Interrupts happen to notify the completion of a transfer and the
+	 * channel should have moved into its stop state already on its own.
+	 * Therefore interrupts on channels not bound to a virtual channel
+	 * should never happen. Nevertheless send a terminate command to the
+	 * channel if the unlikely case happens.
+	 */
+	if (unlikely(!s3cchan)) {
+		dev_err(&phy->host->pdev->dev, "interrupt on unused channel %d\n",
+			phy->id);
+
+		s3c24xx_dma_terminate_phy(phy);
+
+		return IRQ_HANDLED;
+	}
+
+	spin_lock(&s3cchan->vc.lock);
+	txd = s3cchan->at;
+	if (txd) {
+		/* when more sg's are in this txd, start the next one */
+		if (!list_is_last(txd->at, &txd->dsg_list)) {
+			txd->at = txd->at->next;
+			s3c24xx_dma_start_next_sg(s3cchan, txd);
+		} else {
+			s3cchan->at = NULL;
+			vchan_cookie_complete(&txd->vd);
+
+			/*
+			 * And start the next descriptor (if any),
+			 * otherwise free this channel.
+			 */
+			if (vchan_next_desc(&s3cchan->vc))
+				s3c24xx_dma_start_next_txd(s3cchan);
+			else
+				s3c24xx_dma_phy_free(s3cchan);
+		}
+	}
+	spin_unlock(&s3cchan->vc.lock);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * The DMA ENGINE API
+ */
+
+static int s3c24xx_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+			 unsigned long arg)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&s3cchan->vc.lock, flags);
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		ret = s3c24xx_dma_set_runtime_config(s3cchan,
+					      (struct dma_slave_config *)arg);
+		break;
+	case DMA_TERMINATE_ALL:
+		if (!s3cchan->phy && !s3cchan->at) {
+			dev_err(&s3cdma->pdev->dev, "trying to terminate already stopped channel %d\n",
+				s3cchan->id);
+			ret = -EINVAL;
+			break;
+		}
+
+		s3cchan->state = S3C24XX_DMA_CHAN_IDLE;
+
+		 /* Mark physical channel as free */
+		if (s3cchan->phy)
+			s3c24xx_dma_phy_free(s3cchan);
+
+		/* Dequeue current job */
+		if (s3cchan->at) {
+			s3c24xx_dma_desc_free(&s3cchan->at->vd);
+			s3cchan->at = NULL;
+		}
+
+		/* Dequeue jobs not yet fired as well */
+		s3c24xx_dma_free_txd_list(s3cdma, s3cchan);
+		break;
+	default:
+		/* Unknown command */
+		ret = -ENXIO;
+		break;
+	}
+
+	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+
+	return ret;
+}
+
+static int s3c24xx_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	return 0;
+}
+
+static void s3c24xx_dma_free_chan_resources(struct dma_chan *chan)
+{
+	/* Ensure all queued descriptors are freed */
+	vchan_free_chan_resources(to_virt_chan(chan));
+}
+
+static enum dma_status s3c24xx_dma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_txd *txd;
+	struct s3c24xx_sg *dsg;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	enum dma_status ret;
+	size_t bytes = 0;
+
+	spin_lock_irqsave(&s3cchan->vc.lock, flags);
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_SUCCESS) {
+		spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+		return ret;
+	}
+
+	/*
+	 * There's no point calculating the residue if there's
+	 * no txstate to store the value.
+	 */
+	if (!txstate) {
+		spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+		return ret;
+	}
+
+	vd = vchan_find_desc(&s3cchan->vc, cookie);
+	if (vd) {
+		/* On the issued list, so hasn't been processed yet */
+		txd = to_s3c24xx_txd(&vd->tx);
+
+		list_for_each_entry(dsg, &txd->dsg_list, node)
+			bytes += dsg->len;
+	} else {
+		/*
+		 * Currently running, so sum over the pending sg's and
+		 * the currently active one.
+		 */
+		txd = s3cchan->at;
+
+		dsg = list_entry(txd->at, struct s3c24xx_sg, node);
+		list_for_each_entry_from(dsg, &txd->dsg_list, node)
+			bytes += dsg->len;
+
+		bytes += s3c24xx_dma_getbytes_chan(s3cchan);
+	}
+	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+
+	/*
+	 * This cookie not complete yet
+	 * Get number of bytes left in the active transactions and queue
+	 */
+	dma_set_residue(txstate, bytes);
+
+	/* Whether waiting or running, we're in progress */
+	return ret;
+}
+
+/*
+ * Initialize a descriptor to be used by memcpy submit
+ */
+static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy(
+		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	struct s3c24xx_txd *txd;
+	struct s3c24xx_sg *dsg;
+	int src_mod, dest_mod;
+
+	dev_dbg(&s3cdma->pdev->dev, "prepare memcpy of %d bytes from %s\n",
+			len, s3cchan->name);
+
+	if ((len & S3C24XX_DCON_TC_MASK) != len) {
+		dev_err(&s3cdma->pdev->dev, "memcpy size %d to large\n", len);
+		return NULL;
+	}
+
+	txd = s3c24xx_dma_get_txd();
+	if (!txd)
+		return NULL;
+
+	dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
+	if (!dsg) {
+		s3c24xx_dma_free_txd(txd);
+		return NULL;
+	}
+	list_add_tail(&dsg->node, &txd->dsg_list);
+
+	dsg->src_addr = src;
+	dsg->dst_addr = dest;
+	dsg->len = len;
+
+	/*
+	 * Determine a suitable transfer width.
+	 * The DMA controller cannot fetch/store information which is not
+	 * naturally aligned on the bus, i.e., a 4 byte fetch must start at
+	 * an address divisible by 4 - more generally addr % width must be 0.
+	 */
+	src_mod = src % 4;
+	dest_mod = dest % 4;
+	switch (len % 4) {
+	case 0:
+		txd->width = (src_mod == 0 && dest_mod == 0) ? 4 : 1;
+		break;
+	case 2:
+		txd->width = ((src_mod == 2 || src_mod == 0) &&
+			      (dest_mod == 2 || dest_mod == 0)) ? 2 : 1;
+		break;
+	default:
+		txd->width = 1;
+		break;
+	}
+
+	txd->disrcc = S3C24XX_DISRCC_LOC_AHB | S3C24XX_DISRCC_INC_INCREMENT;
+	txd->didstc = S3C24XX_DIDSTC_LOC_AHB | S3C24XX_DIDSTC_INC_INCREMENT;
+	txd->dcon |= S3C24XX_DCON_DEMAND | S3C24XX_DCON_SYNC_HCLK |
+		     S3C24XX_DCON_SERV_WHOLE;
+
+	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
+	struct s3c24xx_txd *txd;
+	struct s3c24xx_sg *dsg;
+	struct scatterlist *sg;
+	dma_addr_t slave_addr;
+	u32 hwcfg = 0;
+	int tmp;
+
+	dev_dbg(&s3cdma->pdev->dev, "prepare transaction of %d bytes from %s\n",
+			sg_dma_len(sgl), s3cchan->name);
+
+	txd = s3c24xx_dma_get_txd();
+	if (!txd)
+		return NULL;
+
+	if (cdata->handshake)
+		txd->dcon |= S3C24XX_DCON_HANDSHAKE;
+
+	switch (cdata->bus) {
+	case S3C24XX_DMA_APB:
+		txd->dcon |= S3C24XX_DCON_SYNC_PCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_APB;
+		break;
+	case S3C24XX_DMA_AHB:
+		txd->dcon |= S3C24XX_DCON_SYNC_HCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_AHB;
+		break;
+	}
+
+	/*
+	 * Always assume our peripheral desintation is a fixed
+	 * address in memory.
+	 */
+	hwcfg |= S3C24XX_DISRCC_INC_FIXED;
+
+	/*
+	 * Individual dma operations are requested by the slave,
+	 * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE).
+	 */
+	txd->dcon |= S3C24XX_DCON_SERV_SINGLE;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		txd->disrcc = S3C24XX_DISRCC_LOC_AHB |
+			      S3C24XX_DISRCC_INC_INCREMENT;
+		txd->didstc = hwcfg;
+		slave_addr = s3cchan->cfg.dst_addr;
+		txd->width = s3cchan->cfg.dst_addr_width;
+	} else if (direction == DMA_DEV_TO_MEM) {
+		txd->disrcc = hwcfg;
+		txd->didstc = S3C24XX_DIDSTC_LOC_AHB |
+			      S3C24XX_DIDSTC_INC_INCREMENT;
+		slave_addr = s3cchan->cfg.src_addr;
+		txd->width = s3cchan->cfg.src_addr_width;
+	} else {
+		s3c24xx_dma_free_txd(txd);
+		dev_err(&s3cdma->pdev->dev,
+			"direction %d unsupported\n", direction);
+		return NULL;
+	}
+
+	for_each_sg(sgl, sg, sg_len, tmp) {
+		dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
+		if (!dsg) {
+			s3c24xx_dma_free_txd(txd);
+			return NULL;
+		}
+		list_add_tail(&dsg->node, &txd->dsg_list);
+
+		dsg->len = sg_dma_len(sg);
+		if (direction == DMA_MEM_TO_DEV) {
+			dsg->src_addr = sg_dma_address(sg);
+			dsg->dst_addr = slave_addr;
+		} else { /* DMA_DEV_TO_MEM */
+			dsg->src_addr = slave_addr;
+			dsg->dst_addr = sg_dma_address(sg);
+		}
+		break;
+	}
+
+	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
+}
+
+/*
+ * Slave transactions callback to the slave device to allow
+ * synchronization of slave DMA signals with the DMAC enable
+ */
+static void s3c24xx_dma_issue_pending(struct dma_chan *chan)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&s3cchan->vc.lock, flags);
+	if (vchan_issue_pending(&s3cchan->vc)) {
+		if (!s3cchan->phy && s3cchan->state != S3C24XX_DMA_CHAN_WAITING)
+			s3c24xx_dma_phy_alloc_and_start(s3cchan);
+	}
+	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+}
+
+/*
+ * Bringup and teardown
+ */
+
+/*
+ * Initialise the DMAC memcpy/slave channels.
+ * Make a local wrapper to hold required data
+ */
+static int s3c24xx_dma_init_virtual_channels(struct s3c24xx_dma_engine *s3cdma,
+		struct dma_device *dmadev, unsigned int channels, bool slave)
+{
+	struct s3c24xx_dma_chan *chan;
+	int i;
+
+	INIT_LIST_HEAD(&dmadev->channels);
+
+	/*
+	 * Register as many many memcpy as we have physical channels,
+	 * we won't always be able to use all but the code will have
+	 * to cope with that situation.
+	 */
+	for (i = 0; i < channels; i++) {
+		chan = devm_kzalloc(dmadev->dev, sizeof(*chan), GFP_KERNEL);
+		if (!chan) {
+			dev_err(dmadev->dev,
+				"%s no memory for channel\n", __func__);
+			return -ENOMEM;
+		}
+
+		chan->id = i;
+		chan->host = s3cdma;
+		chan->state = S3C24XX_DMA_CHAN_IDLE;
+
+		if (slave) {
+			chan->slave = true;
+			chan->name = kasprintf(GFP_KERNEL, "slave%d", i);
+			if (!chan->name)
+				return -ENOMEM;
+		} else {
+			chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i);
+			if (!chan->name)
+				return -ENOMEM;
+		}
+		dev_dbg(dmadev->dev,
+			 "initialize virtual channel \"%s\"\n",
+			 chan->name);
+
+		chan->vc.desc_free = s3c24xx_dma_desc_free;
+		vchan_init(&chan->vc, dmadev);
+	}
+	dev_info(dmadev->dev, "initialized %d virtual %s channels\n",
+		 i, slave ? "slave" : "memcpy");
+	return i;
+}
+
+static void s3c24xx_dma_free_virtual_channels(struct dma_device *dmadev)
+{
+	struct s3c24xx_dma_chan *chan = NULL;
+	struct s3c24xx_dma_chan *next;
+
+	list_for_each_entry_safe(chan,
+				 next, &dmadev->channels, vc.chan.device_node)
+		list_del(&chan->vc.chan.device_node);
+}
+
+/* s3c2412 and s3c2413 have a 0x40 stride and dmareqsel mechanism */
+static struct soc_data soc_s3c2412 = {
+	.stride = 0x40,
+	.has_reqsel = true,
+	.has_clocks = true,
+};
+
+/* s3c2443 and following have a 0x100 stride and dmareqsel mechanism */
+static struct soc_data soc_s3c2443 = {
+	.stride = 0x100,
+	.has_reqsel = true,
+	.has_clocks = true,
+};
+
+static struct platform_device_id s3c24xx_dma_driver_ids[] = {
+	{
+		.name		= "s3c2412-dma",
+		.driver_data	= (kernel_ulong_t)&soc_s3c2412,
+	}, {
+		.name		= "s3c2443-dma",
+		.driver_data	= (kernel_ulong_t)&soc_s3c2443,
+	},
+	{ },
+};
+
+static struct soc_data *s3c24xx_dma_get_soc_data(struct platform_device *pdev)
+{
+	return (struct soc_data *)
+			 platform_get_device_id(pdev)->driver_data;
+}
+
+static int s3c24xx_dma_probe(struct platform_device *pdev)
+{
+	const struct s3c24xx_dma_platdata *pdata = dev_get_platdata(&pdev->dev);
+	struct s3c24xx_dma_engine *s3cdma;
+	struct soc_data *sdata;
+	struct resource *res;
+	int ret;
+	int i;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "platform data missing\n");
+		return -ENODEV;
+	}
+
+	/* Basic sanity check */
+	if (pdata->num_phy_channels > MAX_DMA_CHANNELS) {
+		dev_err(&pdev->dev, "to many dma channels %d, max %d\n",
+			pdata->num_phy_channels, MAX_DMA_CHANNELS);
+		return -EINVAL;
+	}
+
+	sdata = s3c24xx_dma_get_soc_data(pdev);
+	if (!sdata)
+		return -EINVAL;
+
+	s3cdma = devm_kzalloc(&pdev->dev, sizeof(*s3cdma), GFP_KERNEL);
+	if (!s3cdma)
+		return -ENOMEM;
+
+	s3cdma->pdev = pdev;
+	s3cdma->pdata = pdata;
+	s3cdma->sdata = sdata;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	s3cdma->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(s3cdma->base))
+		return PTR_ERR(s3cdma->base);
+
+	s3cdma->phy_chans = devm_kzalloc(&pdev->dev,
+					      sizeof(struct s3c24xx_dma_phy) *
+							pdata->num_phy_channels,
+					      GFP_KERNEL);
+	if (!s3cdma->phy_chans)
+		return -ENOMEM;
+
+	/* aquire irqs and clocks for all physical channels */
+	for (i = 0; i < pdata->num_phy_channels; i++) {
+		struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
+		char clk_name[6];
+
+		phy->id = i;
+		phy->base = s3cdma->base + (i * sdata->stride);
+		phy->host = s3cdma;
+
+		phy->irq = platform_get_irq(pdev, i);
+		if (phy->irq < 0) {
+			dev_err(&pdev->dev, "failed to get irq %d, err %d\n",
+				i, phy->irq);
+			continue;
+		}
+
+		ret = devm_request_irq(&pdev->dev, phy->irq, s3c24xx_dma_irq,
+				       0, pdev->name, phy);
+		if (ret) {
+			dev_err(&pdev->dev, "Unable to request irq for channel %d, error %d\n",
+				i, ret);
+			continue;
+		}
+
+		if (sdata->has_clocks) {
+			sprintf(clk_name, "dma.%d", i);
+			phy->clk = devm_clk_get(&pdev->dev, clk_name);
+			if (IS_ERR(phy->clk) && sdata->has_clocks) {
+				dev_err(&pdev->dev, "unable to aquire clock for channel %d, error %lu",
+					i, PTR_ERR(phy->clk));
+				continue;
+			}
+
+			ret = clk_prepare(phy->clk);
+			if (ret) {
+				dev_err(&pdev->dev, "clock for phy %d failed, error %d\n",
+					i, ret);
+				continue;
+			}
+		}
+
+		spin_lock_init(&phy->lock);
+		phy->valid = true;
+
+		dev_dbg(&pdev->dev, "physical channel %d is %s\n",
+			i, s3c24xx_dma_phy_busy(phy) ? "BUSY" : "FREE");
+	}
+
+	/* Initialize memcpy engine */
+	dma_cap_set(DMA_MEMCPY, s3cdma->memcpy.cap_mask);
+	dma_cap_set(DMA_PRIVATE, s3cdma->memcpy.cap_mask);
+	s3cdma->memcpy.dev = &pdev->dev;
+	s3cdma->memcpy.device_alloc_chan_resources =
+					s3c24xx_dma_alloc_chan_resources;
+	s3cdma->memcpy.device_free_chan_resources =
+					s3c24xx_dma_free_chan_resources;
+	s3cdma->memcpy.device_prep_dma_memcpy = s3c24xx_dma_prep_memcpy;
+	s3cdma->memcpy.device_tx_status = s3c24xx_dma_tx_status;
+	s3cdma->memcpy.device_issue_pending = s3c24xx_dma_issue_pending;
+	s3cdma->memcpy.device_control = s3c24xx_dma_control;
+
+	/* Initialize slave engine for SoC internal dedicated peripherals */
+	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
+	dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask);
+	s3cdma->slave.dev = &pdev->dev;
+	s3cdma->slave.device_alloc_chan_resources =
+					s3c24xx_dma_alloc_chan_resources;
+	s3cdma->slave.device_free_chan_resources =
+					s3c24xx_dma_free_chan_resources;
+	s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status;
+	s3cdma->slave.device_issue_pending = s3c24xx_dma_issue_pending;
+	s3cdma->slave.device_prep_slave_sg = s3c24xx_dma_prep_slave_sg;
+	s3cdma->slave.device_control = s3c24xx_dma_control;
+
+	/* Register as many memcpy channels as there are physical channels */
+	ret = s3c24xx_dma_init_virtual_channels(s3cdma, &s3cdma->memcpy,
+						pdata->num_phy_channels, false);
+	if (ret <= 0) {
+		dev_warn(&pdev->dev,
+			 "%s failed to enumerate memcpy channels - %d\n",
+			 __func__, ret);
+		goto err_memcpy;
+	}
+
+	/* Register slave channels */
+	ret = s3c24xx_dma_init_virtual_channels(s3cdma, &s3cdma->slave,
+				pdata->num_channels, true);
+	if (ret <= 0) {
+		dev_warn(&pdev->dev,
+			"%s failed to enumerate slave channels - %d\n",
+				__func__, ret);
+		goto err_slave;
+	}
+
+	ret = dma_async_device_register(&s3cdma->memcpy);
+	if (ret) {
+		dev_warn(&pdev->dev,
+			"%s failed to register memcpy as an async device - %d\n",
+			__func__, ret);
+		goto err_memcpy_reg;
+	}
+
+	ret = dma_async_device_register(&s3cdma->slave);
+	if (ret) {
+		dev_warn(&pdev->dev,
+			"%s failed to register slave as an async device - %d\n",
+			__func__, ret);
+		goto err_slave_reg;
+	}
+
+	platform_set_drvdata(pdev, s3cdma);
+	dev_info(&pdev->dev, "Loaded dma driver with %d physical channels\n",
+		 pdata->num_phy_channels);
+
+	return 0;
+
+err_slave_reg:
+	dma_async_device_unregister(&s3cdma->memcpy);
+err_memcpy_reg:
+	s3c24xx_dma_free_virtual_channels(&s3cdma->slave);
+err_slave:
+	s3c24xx_dma_free_virtual_channels(&s3cdma->memcpy);
+err_memcpy:
+	if (sdata->has_clocks)
+		for (i = 0; i < pdata->num_phy_channels; i++) {
+			struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
+			if (phy->valid)
+				clk_unprepare(phy->clk);
+		}
+
+	return ret;
+}
+
+static int s3c24xx_dma_remove(struct platform_device *pdev)
+{
+	const struct s3c24xx_dma_platdata *pdata = dev_get_platdata(&pdev->dev);
+	struct s3c24xx_dma_engine *s3cdma = platform_get_drvdata(pdev);
+	struct soc_data *sdata = s3c24xx_dma_get_soc_data(pdev);
+	int i;
+
+	dma_async_device_unregister(&s3cdma->slave);
+	dma_async_device_unregister(&s3cdma->memcpy);
+
+	s3c24xx_dma_free_virtual_channels(&s3cdma->slave);
+	s3c24xx_dma_free_virtual_channels(&s3cdma->memcpy);
+
+	if (sdata->has_clocks)
+		for (i = 0; i < pdata->num_phy_channels; i++) {
+			struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
+			if (phy->valid)
+				clk_unprepare(phy->clk);
+		}
+
+	return 0;
+}
+
+static struct platform_driver s3c24xx_dma_driver = {
+	.driver		= {
+		.name	= "s3c24xx-dma",
+		.owner	= THIS_MODULE,
+	},
+	.id_table	= s3c24xx_dma_driver_ids,
+	.probe		= s3c24xx_dma_probe,
+	.remove		= s3c24xx_dma_remove,
+};
+
+module_platform_driver(s3c24xx_dma_driver);
+
+bool s3c24xx_dma_filter(struct dma_chan *chan, void *param)
+{
+	struct s3c24xx_dma_chan *s3cchan;
+
+	if (chan->device->dev->driver != &s3c24xx_dma_driver.driver)
+		return false;
+
+	s3cchan = to_s3c24xx_dma_chan(chan);
+
+	return s3cchan->id == (int)param;
+}
+EXPORT_SYMBOL(s3c24xx_dma_filter);
+
+MODULE_DESCRIPTION("S3C24XX DMA Driver");
+MODULE_AUTHOR("Heiko Stuebner");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/platform_data/dma-s3c24xx.h b/include/linux/platform_data/dma-s3c24xx.h
new file mode 100644
index 000000000000..5a0cfffe3bbb
--- /dev/null
+++ b/include/linux/platform_data/dma-s3c24xx.h
@@ -0,0 +1,43 @@
+/*
+ * S3C24XX DMA handling
+ *
+ * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+enum s3c24xx_dma_bus {
+	S3C24XX_DMA_APB,
+	S3C24XX_DMA_AHB,
+};
+
+/**
+ * @bus: on which bus does the peripheral reside - AHB or APB.
+ * @handshake: is a handshake with the peripheral necessary
+ * @chansel: channel selection information, depending on variant; reqsel for
+ *	     s3c2443 and later and channel-selection map for earlier SoCs
+ *	     see CHANSEL doc in s3c2443-dma.c
+ */
+struct s3c24xx_dma_channel {
+	enum s3c24xx_dma_bus bus;
+	bool handshake;
+	u16 chansel;
+};
+
+/**
+ * struct s3c24xx_dma_platdata - platform specific settings
+ * @num_phy_channels: number of physical channels
+ * @channels: array of virtual channel descriptions
+ * @num_channels: number of virtual channels
+ */
+struct s3c24xx_dma_platdata {
+	int num_phy_channels;
+	struct s3c24xx_dma_channel *channels;
+	int num_channels;
+};
+
+struct dma_chan;
+bool s3c24xx_dma_filter(struct dma_chan *chan, void *param);
-- 
cgit 


From f61027426a5bc7093aa8359a411b053a35bb4b68 Mon Sep 17 00:00:00 2001
From: Mike Turquette <mturquette@linaro.org>
Date: Mon, 7 Oct 2013 23:12:13 -0700
Subject: clk: of: helper for determining number of parent clocks

Walks the "clocks" array of parent clock phandles and returns the
number.

Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c            | 6 ++++++
 include/linux/clk-provider.h | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 32e2fed6d143..2cf2ea6b77a1 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2202,6 +2202,12 @@ struct clk *of_clk_get_from_provider(struct of_phandle_args *clkspec)
 	return clk;
 }
 
+int of_clk_get_parent_count(struct device_node *np)
+{
+	return of_count_phandle_with_args(np, "clocks", "#clock-cells");
+}
+EXPORT_SYMBOL_GPL(of_clk_get_parent_count);
+
 const char *of_clk_get_parent_name(struct device_node *np, int index)
 {
 	struct of_phandle_args clkspec;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 73bdb69f0c08..7e59253b8603 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -472,6 +472,7 @@ void of_clk_del_provider(struct device_node *np);
 struct clk *of_clk_src_simple_get(struct of_phandle_args *clkspec,
 				  void *data);
 struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data);
+int of_clk_get_parent_count(struct device_node *np);
 const char *of_clk_get_parent_name(struct device_node *np, int index);
 
 void of_clk_init(const struct of_device_id *matches);
-- 
cgit 


From fe1811438a2a229e93beaefa69481d72652795e5 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
Date: Mon, 7 Oct 2013 16:27:55 -0700
Subject: cfg80211: fix nl80211.h documentation for DFS enum states

The names are prefixed incorrectly on the documentation.

Signed-off-by: Luis R. Rodriguez <mcgrof@do-not-panic.com>
[also remove spurious blank line]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index fde2c021b26d..a58ea652cc24 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3860,13 +3860,12 @@ enum nl80211_radar_event {
  *
  * Channel states used by the DFS code.
  *
- * @IEEE80211_DFS_USABLE: The channel can be used, but channel availability
+ * @NL80211_DFS_USABLE: The channel can be used, but channel availability
  *	check (CAC) must be performed before using it for AP or IBSS.
- * @IEEE80211_DFS_UNAVAILABLE: A radar has been detected on this channel, it
+ * @NL80211_DFS_UNAVAILABLE: A radar has been detected on this channel, it
  *	is therefore marked as not available.
- * @IEEE80211_DFS_AVAILABLE: The channel has been CAC checked and is available.
+ * @NL80211_DFS_AVAILABLE: The channel has been CAC checked and is available.
  */
-
 enum nl80211_dfs_state {
 	NL80211_DFS_USABLE,
 	NL80211_DFS_UNAVAILABLE,
-- 
cgit 


From 6e58b8f1daaf1af340fb9309907e5ffa473c7aff Mon Sep 17 00:00:00 2001
From: R Sricharan <r.sricharan@ti.com>
Date: Wed, 14 Aug 2013 19:08:20 +0530
Subject: ARM: dts: DRA7: Add the dts files for dra7 SoC and dra7-evm board

Add minimal device tree source needed for DRA7 based SoCs.
Also add a board dts file for the dra7-evm (based on dra752)
which contains 1.5G of memory with 1G interleaved and 512MB
non-interleaved. Also added in the board file are pin configuration
details for i2c, mcspi and uart devices on board.

Signed-off-by: R Sricharan <r.sricharan@ti.com>
Signed-off-by: Rajendra Nayak <rnayak@ti.com>
Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Benoit Cousson <bcousson@baylibre.com>
---
 arch/arm/boot/dts/Makefile        |   3 +-
 arch/arm/boot/dts/dra7-evm.dts    | 140 ++++++++++
 arch/arm/boot/dts/dra7.dtsi       | 575 ++++++++++++++++++++++++++++++++++++++
 include/dt-bindings/pinctrl/dra.h |  50 ++++
 4 files changed, 767 insertions(+), 1 deletion(-)
 create mode 100644 arch/arm/boot/dts/dra7-evm.dts
 create mode 100644 arch/arm/boot/dts/dra7.dtsi
 create mode 100644 include/dt-bindings/pinctrl/dra.h

(limited to 'include')

diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index a7cae5371489..b057b0e12d7c 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -189,7 +189,8 @@ dtb-$(CONFIG_ARCH_OMAP2PLUS) += omap2420-h4.dtb \
 	am335x-boneblack.dtb \
 	am3517-evm.dtb \
 	am3517_mt_ventoux.dtb \
-	am43x-epos-evm.dtb
+	am43x-epos-evm.dtb \
+	dra7-evm.dtb
 dtb-$(CONFIG_ARCH_ORION5X) += orion5x-lacie-ethernet-disk-mini-v2.dtb
 dtb-$(CONFIG_ARCH_PRIMA2) += prima2-evb.dtb
 dtb-$(CONFIG_ARCH_U8500) += ste-snowball.dtb \
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
new file mode 100644
index 000000000000..ca5dab2214d5
--- /dev/null
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -0,0 +1,140 @@
+/*
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/dts-v1/;
+
+#include "dra7.dtsi"
+
+/ {
+	model = "TI DRA7";
+	compatible = "ti,dra7-evm", "ti,dra752", "ti,dra7";
+
+	memory {
+		device_type = "memory";
+		reg = <0x80000000 0x60000000>; /* 1536 MB */
+	};
+};
+
+&dra7_pmx_core {
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			0x400 (PIN_INPUT | MUX_MODE0) /* i2c1_sda */
+			0x404 (PIN_INPUT | MUX_MODE0) /* i2c1_scl */
+		>;
+	};
+
+	i2c2_pins: pinmux_i2c2_pins {
+		pinctrl-single,pins = <
+			0x408 (PIN_INPUT | MUX_MODE0) /* i2c2_sda */
+			0x40c (PIN_INPUT | MUX_MODE0) /* i2c2_scl */
+		>;
+	};
+
+	i2c3_pins: pinmux_i2c3_pins {
+		pinctrl-single,pins = <
+			0x410 (PIN_INPUT | MUX_MODE0) /* i2c3_sda */
+			0x414 (PIN_INPUT | MUX_MODE0) /* i2c3_scl */
+		>;
+	};
+
+	mcspi1_pins: pinmux_mcspi1_pins {
+		pinctrl-single,pins = <
+			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */
+			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */
+			0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */
+			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
+			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */
+			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */
+			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */
+		>;
+	};
+
+	mcspi2_pins: pinmux_mcspi2_pins {
+		pinctrl-single,pins = <
+			0x3c0 (PIN_INPUT | MUX_MODE0) /* spi2_sclk */
+			0x3c4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_d1 */
+			0x3c8 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_d1 */
+			0x3cc (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
+		>;
+	};
+
+	uart1_pins: pinmux_uart1_pins {
+		pinctrl-single,pins = <
+			0x3e0 (PIN_INPUT_SLEW | MUX_MODE0) /* uart1_rxd */
+			0x3e4 (PIN_INPUT_SLEW | MUX_MODE0) /* uart1_txd */
+			0x3e8 (PIN_INPUT | MUX_MODE3) /* uart1_ctsn */
+			0x3ec (PIN_INPUT | MUX_MODE3) /* uart1_rtsn */
+		>;
+	};
+
+	uart2_pins: pinmux_uart2_pins {
+		pinctrl-single,pins = <
+			0x3f0 (PIN_INPUT | MUX_MODE0) /* uart2_rxd */
+			0x3f4 (PIN_INPUT | MUX_MODE0) /* uart2_txd */
+			0x3f8 (PIN_INPUT | MUX_MODE0) /* uart2_ctsn */
+			0x3fc (PIN_INPUT | MUX_MODE0) /* uart2_rtsn */
+		>;
+	};
+
+	uart3_pins: pinmux_uart3_pins {
+		pinctrl-single,pins = <
+			0x248 (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_rxd */
+			0x24c (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_txd */
+		>;
+	};
+};
+
+&i2c1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
+	clock-frequency = <400000>;
+};
+
+&i2c2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c2_pins>;
+	clock-frequency = <400000>;
+};
+
+&i2c3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c3_pins>;
+	clock-frequency = <3400000>;
+};
+
+&mcspi1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcspi1_pins>;
+};
+
+&mcspi2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcspi2_pins>;
+};
+
+&uart1 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart1_pins>;
+};
+
+&uart2 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart2_pins>;
+};
+
+&uart3 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart3_pins>;
+};
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
new file mode 100644
index 000000000000..c01ef769761f
--- /dev/null
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -0,0 +1,575 @@
+/*
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ * Based on "omap4.dtsi"
+ */
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/pinctrl/dra.h>
+
+#include "skeleton.dtsi"
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	compatible = "ti,dra7xx";
+	interrupt-parent = <&gic>;
+
+	aliases {
+		serial0 = &uart1;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+		serial5 = &uart6;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	gic: interrupt-controller@48211000 {
+		compatible = "arm,cortex-a15-gic";
+		interrupt-controller;
+		#interrupt-cells = <3>;
+		reg = <0x48211000 0x1000>,
+		      <0x48212000 0x1000>,
+		      <0x48214000 0x2000>,
+		      <0x48216000 0x2000>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	/*
+	 * The soc node represents the soc top level view. It is uses for IPs
+	 * that are not memory mapped in the MPU view or for the MPU itself.
+	 */
+	soc {
+		compatible = "ti,omap-infra";
+		mpu {
+			compatible = "ti,omap5-mpu";
+			ti,hwmods = "mpu";
+		};
+	};
+
+	/*
+	 * XXX: Use a flat representation of the SOC interconnect.
+	 * The real OMAP interconnect network is quite complex.
+	 * Since that will not bring real advantage to represent that in DT for
+	 * the moment, just use a fake OCP bus entry to represent the whole bus
+	 * hierarchy.
+	 */
+	ocp {
+		compatible = "ti,omap4-l3-noc", "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+		ti,hwmods = "l3_main_1", "l3_main_2";
+		reg = <0x44000000 0x2000>,
+		      <0x44800000 0x3000>;
+		interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+
+		counter32k: counter@4ae04000 {
+			compatible = "ti,omap-counter32k";
+			reg = <0x4ae04000 0x40>;
+			ti,hwmods = "counter_32k";
+		};
+
+		dra7_pmx_core: pinmux@4a003400 {
+			compatible = "pinctrl-single";
+			reg = <0x4a003400 0x0464>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			pinctrl-single,register-width = <32>;
+			pinctrl-single,function-mask = <0x3fffffff>;
+		};
+
+		sdma: dma-controller@4a056000 {
+			compatible = "ti,omap4430-sdma";
+			reg = <0x4a056000 0x1000>;
+			interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+			#dma-cells = <1>;
+			#dma-channels = <32>;
+			#dma-requests = <127>;
+		};
+
+		gpio1: gpio@4ae10000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x4ae10000 0x200>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio1";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio2: gpio@48055000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x48055000 0x200>;
+			interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio2";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio3: gpio@48057000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x48057000 0x200>;
+			interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio3";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio4: gpio@48059000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x48059000 0x200>;
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio4";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio5: gpio@4805b000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x4805b000 0x200>;
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio5";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio6: gpio@4805d000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x4805d000 0x200>;
+			interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio6";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio7: gpio@48051000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x48051000 0x200>;
+			interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio7";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		gpio8: gpio@48053000 {
+			compatible = "ti,omap4-gpio";
+			reg = <0x48053000 0x200>;
+			interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "gpio8";
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <1>;
+		};
+
+		uart1: serial@4806a000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x4806a000 0x100>;
+			interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart1";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart2: serial@4806c000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x4806c000 0x100>;
+			interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart2";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart3: serial@48020000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48020000 0x100>;
+			interrupts = <GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart3";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart4: serial@4806e000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x4806e000 0x100>;
+			interrupts = <GIC_SPI 70 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart4";
+			clock-frequency = <48000000>;
+                        status = "disabled";
+		};
+
+		uart5: serial@48066000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48066000 0x100>;
+			interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart5";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart6: serial@48068000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48068000 0x100>;
+			interrupts = <GIC_SPI 106 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "uart6";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart7: serial@48420000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48420000 0x100>;
+			ti,hwmods = "uart7";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart8: serial@48422000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48422000 0x100>;
+			ti,hwmods = "uart8";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart9: serial@48424000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x48424000 0x100>;
+			ti,hwmods = "uart9";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		uart10: serial@4ae2b000 {
+			compatible = "ti,omap4-uart";
+			reg = <0x4ae2b000 0x100>;
+			ti,hwmods = "uart10";
+			clock-frequency = <48000000>;
+			status = "disabled";
+		};
+
+		timer1: timer@4ae18000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x4ae18000 0x80>;
+			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer1";
+			ti,timer-alwon;
+		};
+
+		timer2: timer@48032000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48032000 0x80>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer2";
+		};
+
+		timer3: timer@48034000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48034000 0x80>;
+			interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer3";
+		};
+
+		timer4: timer@48036000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48036000 0x80>;
+			interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer4";
+		};
+
+		timer5: timer@48820000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48820000 0x80>;
+			interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer5";
+			ti,timer-dsp;
+		};
+
+		timer6: timer@48822000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48822000 0x80>;
+			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer6";
+			ti,timer-dsp;
+			ti,timer-pwm;
+		};
+
+		timer7: timer@48824000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48824000 0x80>;
+			interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer7";
+			ti,timer-dsp;
+		};
+
+		timer8: timer@48826000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48826000 0x80>;
+			interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer8";
+			ti,timer-dsp;
+			ti,timer-pwm;
+		};
+
+		timer9: timer@4803e000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x4803e000 0x80>;
+			interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer9";
+		};
+
+		timer10: timer@48086000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48086000 0x80>;
+			interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer10";
+		};
+
+		timer11: timer@48088000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48088000 0x80>;
+			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "timer11";
+			ti,timer-pwm;
+		};
+
+		timer13: timer@48828000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x48828000 0x80>;
+			ti,hwmods = "timer13";
+			status = "disabled";
+		};
+
+		timer14: timer@4882a000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x4882a000 0x80>;
+			ti,hwmods = "timer14";
+			status = "disabled";
+		};
+
+		timer15: timer@4882c000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x4882c000 0x80>;
+			ti,hwmods = "timer15";
+			status = "disabled";
+		};
+
+		timer16: timer@4882e000 {
+			compatible = "ti,omap5430-timer";
+			reg = <0x4882e000 0x80>;
+			ti,hwmods = "timer16";
+			status = "disabled";
+		};
+
+		wdt2: wdt@4ae14000 {
+			compatible = "ti,omap4-wdt";
+			reg = <0x4ae14000 0x80>;
+			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "wd_timer2";
+		};
+
+		i2c1: i2c@48070000 {
+			compatible = "ti,omap4-i2c";
+			reg = <0x48070000 0x100>;
+			interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "i2c1";
+			status = "disabled";
+		};
+
+		i2c2: i2c@48072000 {
+			compatible = "ti,omap4-i2c";
+			reg = <0x48072000 0x100>;
+			interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "i2c2";
+			status = "disabled";
+		};
+
+		i2c3: i2c@48060000 {
+			compatible = "ti,omap4-i2c";
+			reg = <0x48060000 0x100>;
+			interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "i2c3";
+			status = "disabled";
+		};
+
+		i2c4: i2c@4807a000 {
+			compatible = "ti,omap4-i2c";
+			reg = <0x4807a000 0x100>;
+			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "i2c4";
+			status = "disabled";
+		};
+
+		i2c5: i2c@4807c000 {
+			compatible = "ti,omap4-i2c";
+			reg = <0x4807c000 0x100>;
+			interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "i2c5";
+			status = "disabled";
+		};
+
+		mmc1: mmc@4809c000 {
+			compatible = "ti,omap4-hsmmc";
+			reg = <0x4809c000 0x400>;
+			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "mmc1";
+			ti,dual-volt;
+			ti,needs-special-reset;
+			dmas = <&sdma 61>, <&sdma 62>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
+		mmc2: mmc@480b4000 {
+			compatible = "ti,omap4-hsmmc";
+			reg = <0x480b4000 0x400>;
+			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "mmc2";
+			ti,needs-special-reset;
+			dmas = <&sdma 47>, <&sdma 48>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
+		mmc3: mmc@480ad000 {
+			compatible = "ti,omap4-hsmmc";
+			reg = <0x480ad000 0x400>;
+			interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "mmc3";
+			ti,needs-special-reset;
+			dmas = <&sdma 77>, <&sdma 78>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
+		mmc4: mmc@480d1000 {
+			compatible = "ti,omap4-hsmmc";
+			reg = <0x480d1000 0x400>;
+			interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "mmc4";
+			ti,needs-special-reset;
+			dmas = <&sdma 57>, <&sdma 58>;
+			dma-names = "tx", "rx";
+			status = "disabled";
+		};
+
+		mcspi1: spi@48098000 {
+			compatible = "ti,omap4-mcspi";
+			reg = <0x48098000 0x200>;
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "mcspi1";
+			ti,spi-num-cs = <4>;
+			dmas = <&sdma 35>,
+			       <&sdma 36>,
+			       <&sdma 37>,
+			       <&sdma 38>,
+			       <&sdma 39>,
+			       <&sdma 40>,
+			       <&sdma 41>,
+			       <&sdma 42>;
+			dma-names = "tx0", "rx0", "tx1", "rx1",
+				    "tx2", "rx2", "tx3", "rx3";
+			status = "disabled";
+		};
+
+		mcspi2: spi@4809a000 {
+			compatible = "ti,omap4-mcspi";
+			reg = <0x4809a000 0x200>;
+			interrupts = <GIC_SPI 66 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "mcspi2";
+			ti,spi-num-cs = <2>;
+			dmas = <&sdma 43>,
+			       <&sdma 44>,
+			       <&sdma 45>,
+			       <&sdma 46>;
+			dma-names = "tx0", "rx0", "tx1", "rx1";
+			status = "disabled";
+		};
+
+		mcspi3: spi@480b8000 {
+			compatible = "ti,omap4-mcspi";
+			reg = <0x480b8000 0x200>;
+			interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "mcspi3";
+			ti,spi-num-cs = <2>;
+			dmas = <&sdma 15>, <&sdma 16>;
+			dma-names = "tx0", "rx0";
+			status = "disabled";
+		};
+
+		mcspi4: spi@480ba000 {
+			compatible = "ti,omap4-mcspi";
+			reg = <0x480ba000 0x200>;
+			interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			ti,hwmods = "mcspi4";
+			ti,spi-num-cs = <1>;
+			dmas = <&sdma 70>, <&sdma 71>;
+			dma-names = "tx0", "rx0";
+			status = "disabled";
+		};
+	};
+};
diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h
new file mode 100644
index 000000000000..002a2855c046
--- /dev/null
+++ b/include/dt-bindings/pinctrl/dra.h
@@ -0,0 +1,50 @@
+/*
+ * This header provides constants for DRA pinctrl bindings.
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com/
+ * Author: Rajendra Nayak <rnayak@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _DT_BINDINGS_PINCTRL_DRA_H
+#define _DT_BINDINGS_PINCTRL_DRA_H
+
+/* DRA7 mux mode options for each pin. See TRM for options */
+#define MUX_MODE0	0x0
+#define MUX_MODE1	0x1
+#define MUX_MODE2	0x2
+#define MUX_MODE3	0x3
+#define MUX_MODE4	0x4
+#define MUX_MODE5	0x5
+#define MUX_MODE6	0x6
+#define MUX_MODE7	0x7
+#define MUX_MODE8	0x8
+#define MUX_MODE9	0x9
+#define MUX_MODE10	0xa
+#define MUX_MODE11	0xb
+#define MUX_MODE12	0xc
+#define MUX_MODE13	0xd
+#define MUX_MODE14	0xe
+#define MUX_MODE15	0xf
+
+#define PULL_ENA		(1 << 16)
+#define PULL_UP			(1 << 17)
+#define INPUT_EN		(1 << 18)
+#define SLEWCONTROL		(1 << 19)
+#define WAKEUP_EN		(1 << 24)
+#define WAKEUP_EVENT		(1 << 25)
+
+/* Active pin states */
+#define PIN_OUTPUT		0
+#define PIN_OUTPUT_PULLUP	(PIN_OUTPUT | PULL_ENA | PULL_UP)
+#define PIN_OUTPUT_PULLDOWN	(PIN_OUTPUT | PULL_ENA)
+#define PIN_INPUT		INPUT_EN
+#define PIN_INPUT_SLEW		(INPUT_EN | SLEWCONTROL)
+#define PIN_INPUT_PULLUP	(PULL_ENA | INPUT_EN | PULL_UP)
+#define PIN_INPUT_PULLDOWN	(PULL_ENA | INPUT_EN)
+
+#endif
+
-- 
cgit 


From 31a2c46cd94c6463b2b57b476e5a0fd154fee439 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Mon, 7 Oct 2013 23:36:56 +0100
Subject: spi/trace: Trace length of SPI messages on completion

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/trace/events/spi.h | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h
index a7b09072ce56..5e77e21f885a 100644
--- a/include/trace/events/spi.h
+++ b/include/trace/events/spi.h
@@ -80,12 +80,32 @@ DEFINE_EVENT(spi_message, spi_message_start,
 
 );
 
-DEFINE_EVENT(spi_message, spi_message_done,
+TRACE_EVENT(spi_message_done,
 
 	TP_PROTO(struct spi_message *msg),
 
-	TP_ARGS(msg)
+	TP_ARGS(msg),
+
+	TP_STRUCT__entry(
+		__field(        int,            bus_num         )
+		__field(        int,            chip_select     )
+		__field(        struct spi_message *,   msg     )
+		__field(        unsigned,       frame           )
+		__field(        unsigned,       actual          )
+	),
 
+	TP_fast_assign(
+		__entry->bus_num = msg->spi->master->bus_num;
+		__entry->chip_select = msg->spi->chip_select;
+		__entry->msg = msg;
+		__entry->frame = msg->frame_length;
+		__entry->actual = msg->actual_length;
+	),
+
+        TP_printk("spi%d.%d %p len=%u/%u", (int)__entry->bus_num,
+		  (int)__entry->chip_select,
+		  (struct spi_message *)__entry->msg,
+                  (unsigned)__entry->actual, (unsigned)__entry->frame)
 );
 
 #endif /* _TRACE_POWER_H */
-- 
cgit 


From 421b3885bf6d56391297844f43fb7154a6396e12 Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Mon, 7 Oct 2013 11:01:39 -0500
Subject: udp: ipv4: Add udp early demux

The removal of the routing cache introduced a performance regression for
some UDP workloads since a dst lookup must be done for each packet.
This change caches the dst per socket in a similar manner to what we do
for TCP by implementing early_demux.

For UDP multicast we can only cache the dst if there is only one
receiving socket on the host.  Since caching only works when there is
one receiving socket we do the multicast socket lookup using RCU.

For UDP unicast we only demux sockets with an exact match in order to
not break forwarding setups.  Additionally since the hash chains may be
long we only check the first socket to see if it is a match and not
waste extra time searching the whole chain when we might not find an
exact match.

Benchmark results from a netperf UDP_RR test:
Before 87961.22 transactions/s
After  89789.68 transactions/s

Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.97us RTT
After  12.63us RTT

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |   2 +-
 include/net/udp.h  |   1 +
 net/ipv4/af_inet.c |   1 +
 net/ipv4/udp.c     | 202 ++++++++++++++++++++++++++++++++++++++++++++++++-----
 4 files changed, 187 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index e3bf213be625..79532540201b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -218,7 +218,7 @@ struct cg_proto;
   *	@sk_lock:	synchronizer
   *	@sk_rcvbuf: size of receive buffer in bytes
   *	@sk_wq: sock wait queue and async head
-  *	@sk_rx_dst: receive input route used by early tcp demux
+  *	@sk_rx_dst: receive input route used by early demux
   *	@sk_dst_cache: destination cache
   *	@sk_dst_lock: destination cache lock
   *	@sk_policy: flow policy
diff --git a/include/net/udp.h b/include/net/udp.h
index 510b8cb4d1a7..fe4ba9f32429 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -175,6 +175,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		     unsigned int hash2_nulladdr);
 
 /* net/ipv4/udp.c */
+void udp_v4_early_demux(struct sk_buff *skb);
 int udp_get_port(struct sock *sk, unsigned short snum,
 		 int (*saddr_cmp)(const struct sock *,
 				  const struct sock *));
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cfeb85cff4f0..35913fb77dc8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1546,6 +1546,7 @@ static const struct net_protocol tcp_protocol = {
 };
 
 static const struct net_protocol udp_protocol = {
+	.early_demux =	udp_v4_early_demux,
 	.handler =	udp_rcv,
 	.err_handler =	udp_err,
 	.no_policy =	1,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5950e12bd3ab..262ea3929da6 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -103,6 +103,7 @@
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
 #include <net/icmp.h>
+#include <net/inet_hashtables.h>
 #include <net/route.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
@@ -565,6 +566,26 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 }
 EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 
+static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
+				       __be16 loc_port, __be32 loc_addr,
+				       __be16 rmt_port, __be32 rmt_addr,
+				       int dif, unsigned short hnum)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
+	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
+	    ipv6_only_sock(sk) ||
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+		return false;
+	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+		return false;
+	return true;
+}
+
 static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
 					     __be16 loc_port, __be32 loc_addr,
 					     __be16 rmt_port, __be32 rmt_addr,
@@ -575,20 +596,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
 	unsigned short hnum = ntohs(loc_port);
 
 	sk_nulls_for_each_from(s, node) {
-		struct inet_sock *inet = inet_sk(s);
-
-		if (!net_eq(sock_net(s), net) ||
-		    udp_sk(s)->udp_port_hash != hnum ||
-		    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
-		    (inet->inet_dport != rmt_port && inet->inet_dport) ||
-		    (inet->inet_rcv_saddr &&
-		     inet->inet_rcv_saddr != loc_addr) ||
-		    ipv6_only_sock(s) ||
-		    (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
-			continue;
-		if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
-			continue;
-		goto found;
+		if (__udp_is_mcast_sock(net, s,
+					loc_port, loc_addr,
+					rmt_port, rmt_addr,
+					dif, hnum))
+			goto found;
 	}
 	s = NULL;
 found:
@@ -1581,6 +1593,14 @@ static void flush_stack(struct sock **stack, unsigned int count,
 		kfree_skb(skb1);
 }
 
+static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	dst_hold(dst);
+	sk->sk_rx_dst = dst;
+}
+
 /*
  *	Multicasts and broadcasts go to each listener.
  *
@@ -1709,11 +1729,28 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
-		return __udp4_lib_mcast_deliver(net, skb, uh,
-				saddr, daddr, udptable);
+	if (skb->sk) {
+		int ret;
+		sk = skb->sk;
 
-	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+		if (unlikely(sk->sk_rx_dst == NULL))
+			udp_sk_rx_dst_set(sk, skb);
+
+		ret = udp_queue_rcv_skb(sk, skb);
+
+		/* a return value > 0 means to resubmit the input, but
+		 * it wants the return to be -protocol, or 0
+		 */
+		if (ret > 0)
+			return -ret;
+		return 0;
+	} else {
+		if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+			return __udp4_lib_mcast_deliver(net, skb, uh,
+					saddr, daddr, udptable);
+
+		sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+	}
 
 	if (sk != NULL) {
 		int ret;
@@ -1771,6 +1808,135 @@ drop:
 	return 0;
 }
 
+/* We can only early demux multicast if there is a single matching socket.
+ * If more than one socket found returns NULL
+ */
+static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
+						  __be16 loc_port, __be32 loc_addr,
+						  __be16 rmt_port, __be32 rmt_addr,
+						  int dif)
+{
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
+	struct udp_hslot *hslot = &udp_table.hash[slot];
+
+	rcu_read_lock();
+begin:
+	count = 0;
+	result = NULL;
+	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+		if (__udp_is_mcast_sock(net, sk,
+					loc_port, loc_addr,
+					rmt_port, rmt_addr,
+					dif, hnum)) {
+			result = sk;
+			++count;
+		}
+	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot)
+		goto begin;
+
+	if (result) {
+		if (count != 1 ||
+		    unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+			result = NULL;
+		else if (unlikely(!__udp_is_mcast_sock(net, sk,
+						       loc_port, loc_addr,
+						       rmt_port, rmt_addr,
+						       dif, hnum))) {
+			sock_put(result);
+			result = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return result;
+}
+
+/* For unicast we should only early demux connected sockets or we can
+ * break forwarding setups.  The chains here can be long so only check
+ * if the first socket is an exact match and if not move on.
+ */
+static struct sock *__udp4_lib_demux_lookup(struct net *net,
+					    __be16 loc_port, __be32 loc_addr,
+					    __be16 rmt_port, __be32 rmt_addr,
+					    int dif)
+{
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
+	unsigned int slot2 = hash2 & udp_table.mask;
+	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
+	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr)
+	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+
+	rcu_read_lock();
+	result = NULL;
+	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+		if (INET_MATCH(sk, net, acookie,
+			       rmt_addr, loc_addr, ports, dif))
+			result = sk;
+		/* Only check first socket in chain */
+		break;
+	}
+
+	if (result) {
+		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+			result = NULL;
+		else if (unlikely(!INET_MATCH(sk, net, acookie,
+					      rmt_addr, loc_addr,
+					      ports, dif))) {
+			sock_put(result);
+			result = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return result;
+}
+
+void udp_v4_early_demux(struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	const struct udphdr *uh = udp_hdr(skb);
+	struct sock *sk;
+	struct dst_entry *dst;
+	struct net *net = dev_net(skb->dev);
+	int dif = skb->dev->ifindex;
+
+	/* validate the packet */
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
+		return;
+
+	if (skb->pkt_type == PACKET_BROADCAST ||
+	    skb->pkt_type == PACKET_MULTICAST)
+		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
+						   uh->source, iph->saddr, dif);
+	else if (skb->pkt_type == PACKET_HOST)
+		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
+					     uh->source, iph->saddr, dif);
+	else
+		return;
+
+	if (!sk)
+		return;
+
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+	dst = sk->sk_rx_dst;
+
+	if (dst)
+		dst = dst_check(dst, 0);
+	if (dst)
+		skb_dst_set_noref(skb, dst);
+}
+
 int udp_rcv(struct sk_buff *skb)
 {
 	return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
-- 
cgit 


From fbf8866d65d5de84f75563eb0edd7fc27dbe9a90 Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@rgmadvisors.com>
Date: Mon, 7 Oct 2013 11:01:40 -0500
Subject: net: ipv4 only populate IP_PKTINFO when needed

The since the removal of the routing cache computing
fib_compute_spec_dst() does a fib_table lookup for each UDP multicast
packet received.  This has introduced a performance regression for some
UDP workloads.

This change skips populating the packet info for sockets that do not have
IP_PKTINFO set.

Benchmark results from a netperf UDP_RR test:
Before 89789.68 transactions/s
After  90587.62 transactions/s

Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.63us RTT
After  12.48us RTT

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       | 2 +-
 net/ipv4/ip_sockglue.c | 5 +++--
 net/ipv4/raw.c         | 2 +-
 net/ipv4/udp.c         | 2 +-
 4 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 16078f422397..b39ebe5339ac 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -459,7 +459,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
 void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 56e34457ac07..0626f2cb192e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1052,11 +1052,12 @@ e_inval:
  * destination in skb->cb[] before dst drop.
  * This way, receiver doesnt make cache line misses to read rtable.
  */
-void ipv4_pktinfo_prepare(struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
 
-	if (skb_rtable(skb)) {
+	if ((inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) &&
+	    skb_rtable(skb)) {
 		pktinfo->ipi_ifindex = inet_iif(skb);
 		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
 	} else {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b2fa14c1a6f1..41e1d2845c8f 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -299,7 +299,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	/* Charge it to the socket. */
 
-	ipv4_pktinfo_prepare(skb);
+	ipv4_pktinfo_prepare(sk, skb);
 	if (sock_queue_rcv_skb(sk, skb) < 0) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 262ea3929da6..4226c53daaed 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1544,7 +1544,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	rc = 0;
 
-	ipv4_pktinfo_prepare(skb);
+	ipv4_pktinfo_prepare(sk, skb);
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk))
 		rc = __udp_queue_rcv_skb(sk, skb);
-- 
cgit 


From 05dbc7b59481ca891bbcfe6799a562d48159fbf7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Oct 2013 00:22:02 -0700
Subject: tcp/dccp: remove twchain

TCP listener refactoring, part 3 :

Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.

Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.

As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.

If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.

[ INET_TW_MATCH() is no longer needed ]

I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()

This way, SYN_RECV pseudo sockets will be supported the same.

A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].

Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()

Before patch :

dmesg | grep "TCP established"

TCP established hash table entries: 524288 (order: 11, 8388608 bytes)

After patch :

TCP established hash table entries: 524288 (order: 10, 4194304 bytes)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h    |  9 +----
 include/net/inet_timewait_sock.h | 13 +------
 include/net/sock.h               |  8 +++-
 include/net/tcp.h                |  1 -
 net/dccp/proto.c                 |  4 +-
 net/ipv4/inet_diag.c             | 48 +++++++----------------
 net/ipv4/inet_hashtables.c       | 83 ++++++++++++++--------------------------
 net/ipv4/inet_timewait_sock.c    | 55 +++++++++++++-------------
 net/ipv4/tcp.c                   |  5 +--
 net/ipv4/tcp_ipv4.c              | 83 +++++++---------------------------------
 net/ipv6/inet6_hashtables.c      | 75 +++++++++++++++---------------------
 net/ipv6/tcp_ipv6.c              |  9 +++--
 12 files changed, 132 insertions(+), 261 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 10d6838378c3..1bdb47715def 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -37,12 +37,11 @@
 #include <asm/byteorder.h>
 
 /* This is for all connections with a full identity, no wildcards.
- * One chain is dedicated to TIME_WAIT sockets.
- * I'll experiment with dynamic table growth later.
+ * The 'e' prefix stands for Establish, but we really put all sockets
+ * but LISTEN ones.
  */
 struct inet_ehash_bucket {
 	struct hlist_nulls_head chain;
-	struct hlist_nulls_head twchain;
 };
 
 /* There are a few simple rules, which allow for local port reuse by
@@ -123,7 +122,6 @@ struct inet_hashinfo {
 	 *
 	 *          TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
 	 *
-	 * TIME_WAIT sockets use a separate chain (twchain).
 	 */
 	struct inet_ehash_bucket	*ehash;
 	spinlock_t			*ehash_locks;
@@ -318,9 +316,6 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	 net_eq(sock_net(__sk), (__net)))
 #endif /* 64-bit arch */
 
-#define INET_TW_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)\
-	INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)
-
 /*
  * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index f528d1b0ac95..de9e3ab7d43d 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -141,18 +141,6 @@ struct inet_timewait_sock {
 };
 #define tw_tclass tw_tos
 
-static inline void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
-				      struct hlist_nulls_head *list)
-{
-	hlist_nulls_add_head_rcu(&tw->tw_node, list);
-}
-
-static inline void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
-					   struct hlist_head *list)
-{
-	hlist_add_head(&tw->tw_bind_node, list);
-}
-
 static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw)
 {
 	return !hlist_unhashed(&tw->tw_death_node);
@@ -192,6 +180,7 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
 	return (struct inet_timewait_sock *)sk;
 }
 
+void inet_twsk_free(struct inet_timewait_sock *tw);
 void inet_twsk_put(struct inet_timewait_sock *tw);
 
 int inet_twsk_unhash(struct inet_timewait_sock *tw);
diff --git a/include/net/sock.h b/include/net/sock.h
index 7cf8d2331afb..3f3e48c4704d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -156,7 +156,7 @@ typedef __u64 __bitwise __addrpair;
  */
 struct sock_common {
 	/* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned
-	 * address on 64bit arches : cf INET_MATCH() and INET_TW_MATCH()
+	 * address on 64bit arches : cf INET_MATCH()
 	 */
 	union {
 		__addrpair	skc_addrpair;
@@ -301,6 +301,8 @@ struct sock {
 #define sk_dontcopy_end		__sk_common.skc_dontcopy_end
 #define sk_hash			__sk_common.skc_hash
 #define sk_portpair		__sk_common.skc_portpair
+#define sk_num			__sk_common.skc_num
+#define sk_dport		__sk_common.skc_dport
 #define sk_addrpair		__sk_common.skc_addrpair
 #define sk_daddr		__sk_common.skc_daddr
 #define sk_rcv_saddr		__sk_common.skc_rcv_saddr
@@ -1653,6 +1655,10 @@ static inline void sock_put(struct sock *sk)
 	if (atomic_dec_and_test(&sk->sk_refcnt))
 		sk_free(sk);
 }
+/* Generic version of sock_put(), dealing with all sockets
+ * (TCP_TIMEWAIT, ESTABLISHED...)
+ */
+void sock_gen_put(struct sock *sk);
 
 int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested);
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index de870ee5582d..39bbfa1602b2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1519,7 +1519,6 @@ enum tcp_seq_states {
 	TCP_SEQ_STATE_LISTENING,
 	TCP_SEQ_STATE_OPENREQ,
 	TCP_SEQ_STATE_ESTABLISHED,
-	TCP_SEQ_STATE_TIME_WAIT,
 };
 
 int tcp_seq_open(struct inode *inode, struct file *file);
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index ba64750f0387..eb892b4f4814 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1158,10 +1158,8 @@ static int __init dccp_init(void)
 		goto out_free_bind_bucket_cachep;
 	}
 
-	for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) {
+	for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
 		INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
-		INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i);
-	}
 
 	if (inet_ehash_locks_alloc(&dccp_hashinfo))
 			goto out_free_dccp_ehash;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 22000279efc8..8e1e40653357 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -635,12 +635,14 @@ static int inet_csk_diag_dump(struct sock *sk,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
-static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
+static int inet_twsk_diag_dump(struct sock *sk,
 			       struct sk_buff *skb,
 			       struct netlink_callback *cb,
 			       struct inet_diag_req_v2 *r,
 			       const struct nlattr *bc)
 {
+	struct inet_timewait_sock *tw = inet_twsk(sk);
+
 	if (bc != NULL) {
 		struct inet_diag_entry entry;
 
@@ -911,8 +913,7 @@ skip_listen_ht:
 
 		num = 0;
 
-		if (hlist_nulls_empty(&head->chain) &&
-			hlist_nulls_empty(&head->twchain))
+		if (hlist_nulls_empty(&head->chain))
 			continue;
 
 		if (i > s_i)
@@ -920,7 +921,7 @@ skip_listen_ht:
 
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &head->chain) {
-			struct inet_sock *inet = inet_sk(sk);
+			int res;
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
@@ -929,15 +930,19 @@ skip_listen_ht:
 			if (!(r->idiag_states & (1 << sk->sk_state)))
 				goto next_normal;
 			if (r->sdiag_family != AF_UNSPEC &&
-					sk->sk_family != r->sdiag_family)
+			    sk->sk_family != r->sdiag_family)
 				goto next_normal;
-			if (r->id.idiag_sport != inet->inet_sport &&
+			if (r->id.idiag_sport != htons(sk->sk_num) &&
 			    r->id.idiag_sport)
 				goto next_normal;
-			if (r->id.idiag_dport != inet->inet_dport &&
+			if (r->id.idiag_dport != sk->sk_dport &&
 			    r->id.idiag_dport)
 				goto next_normal;
-			if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
+			if (sk->sk_state == TCP_TIME_WAIT)
+				res = inet_twsk_diag_dump(sk, skb, cb, r, bc);
+			else
+				res = inet_csk_diag_dump(sk, skb, cb, r, bc);
+			if (res < 0) {
 				spin_unlock_bh(lock);
 				goto done;
 			}
@@ -945,33 +950,6 @@ next_normal:
 			++num;
 		}
 
-		if (r->idiag_states & TCPF_TIME_WAIT) {
-			struct inet_timewait_sock *tw;
-
-			inet_twsk_for_each(tw, node,
-				    &head->twchain) {
-				if (!net_eq(twsk_net(tw), net))
-					continue;
-
-				if (num < s_num)
-					goto next_dying;
-				if (r->sdiag_family != AF_UNSPEC &&
-						tw->tw_family != r->sdiag_family)
-					goto next_dying;
-				if (r->id.idiag_sport != tw->tw_sport &&
-				    r->id.idiag_sport)
-					goto next_dying;
-				if (r->id.idiag_dport != tw->tw_dport &&
-				    r->id.idiag_dport)
-					goto next_dying;
-				if (inet_twsk_diag_dump(tw, skb, cb, r, bc) < 0) {
-					spin_unlock_bh(lock);
-					goto done;
-				}
-next_dying:
-				++num;
-			}
-		}
 		spin_unlock_bh(lock);
 	}
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ae199596b9b0..a4b66bbe4f21 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -230,6 +230,19 @@ begin:
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_listener);
 
+/* All sockets share common refcount, but have different destructors */
+void sock_gen_put(struct sock *sk)
+{
+	if (!atomic_dec_and_test(&sk->sk_refcnt))
+		return;
+
+	if (sk->sk_state == TCP_TIME_WAIT)
+		inet_twsk_free(inet_twsk(sk));
+	else
+		sk_free(sk);
+}
+EXPORT_SYMBOL_GPL(sock_gen_put);
+
 struct sock *__inet_lookup_established(struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
@@ -255,13 +268,13 @@ begin:
 		if (likely(INET_MATCH(sk, net, acookie,
 				      saddr, daddr, ports, dif))) {
 			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
-				goto begintw;
+				goto out;
 			if (unlikely(!INET_MATCH(sk, net, acookie,
 						 saddr, daddr, ports, dif))) {
-				sock_put(sk);
+				sock_gen_put(sk);
 				goto begin;
 			}
-			goto out;
+			goto found;
 		}
 	}
 	/*
@@ -271,37 +284,9 @@ begin:
 	 */
 	if (get_nulls_value(node) != slot)
 		goto begin;
-
-begintw:
-	/* Must check for a TIME_WAIT'er before going to listener hash. */
-	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
-		if (sk->sk_hash != hash)
-			continue;
-		if (likely(INET_TW_MATCH(sk, net, acookie,
-					 saddr, daddr, ports,
-					 dif))) {
-			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
-				sk = NULL;
-				goto out;
-			}
-			if (unlikely(!INET_TW_MATCH(sk, net, acookie,
-						    saddr, daddr, ports,
-						    dif))) {
-				inet_twsk_put(inet_twsk(sk));
-				goto begintw;
-			}
-			goto out;
-		}
-	}
-	/*
-	 * if the nulls value we got at the end of this lookup is
-	 * not the expected one, we must restart lookup.
-	 * We probably met an item that was moved to another chain.
-	 */
-	if (get_nulls_value(node) != slot)
-		goto begintw;
-	sk = NULL;
 out:
+	sk = NULL;
+found:
 	rcu_read_unlock();
 	return sk;
 }
@@ -326,39 +311,29 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
 	struct sock *sk2;
 	const struct hlist_nulls_node *node;
-	struct inet_timewait_sock *tw;
+	struct inet_timewait_sock *tw = NULL;
 	int twrefcnt = 0;
 
 	spin_lock(lock);
 
-	/* Check TIME-WAIT sockets first. */
-	sk_nulls_for_each(sk2, node, &head->twchain) {
-		if (sk2->sk_hash != hash)
-			continue;
-
-		if (likely(INET_TW_MATCH(sk2, net, acookie,
-					 saddr, daddr, ports, dif))) {
-			tw = inet_twsk(sk2);
-			if (twsk_unique(sk, sk2, twp))
-				goto unique;
-			else
-				goto not_unique;
-		}
-	}
-	tw = NULL;
-
-	/* And established part... */
 	sk_nulls_for_each(sk2, node, &head->chain) {
 		if (sk2->sk_hash != hash)
 			continue;
+
 		if (likely(INET_MATCH(sk2, net, acookie,
-				      saddr, daddr, ports, dif)))
+					 saddr, daddr, ports, dif))) {
+			if (sk2->sk_state == TCP_TIME_WAIT) {
+				tw = inet_twsk(sk2);
+				if (twsk_unique(sk, sk2, twp))
+					break;
+			}
 			goto not_unique;
+		}
 	}
 
-unique:
 	/* Must record num and sport now. Otherwise we will see
-	 * in hash table socket with a funny identity. */
+	 * in hash table socket with a funny identity.
+	 */
 	inet->inet_num = lport;
 	inet->inet_sport = htons(lport);
 	sk->sk_hash = hash;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 9bcd8f7234ec..6d592f8555fb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -87,19 +87,11 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
 	refcnt += inet_twsk_bind_unhash(tw, hashinfo);
 	spin_unlock(&bhead->lock);
 
-#ifdef SOCK_REFCNT_DEBUG
-	if (atomic_read(&tw->tw_refcnt) != 1) {
-		pr_debug("%s timewait_sock %p refcnt=%d\n",
-			 tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt));
-	}
-#endif
-	while (refcnt) {
-		inet_twsk_put(tw);
-		refcnt--;
-	}
+	BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt));
+	atomic_sub(refcnt, &tw->tw_refcnt);
 }
 
-static noinline void inet_twsk_free(struct inet_timewait_sock *tw)
+void inet_twsk_free(struct inet_timewait_sock *tw)
 {
 	struct module *owner = tw->tw_prot->owner;
 	twsk_destructor((struct sock *)tw);
@@ -118,6 +110,18 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(inet_twsk_put);
 
+static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+				   struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_head_rcu(&tw->tw_node, list);
+}
+
+static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
+				    struct hlist_head *list)
+{
+	hlist_add_head(&tw->tw_bind_node, list);
+}
+
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -146,26 +150,21 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 	spin_lock(lock);
 
 	/*
-	 * Step 2: Hash TW into TIMEWAIT chain.
-	 * Should be done before removing sk from established chain
-	 * because readers are lockless and search established first.
+	 * Step 2: Hash TW into tcp ehash chain.
+	 * Notes :
+	 * - tw_refcnt is set to 3 because :
+	 * - We have one reference from bhash chain.
+	 * - We have one reference from ehash chain.
+	 * We can use atomic_set() because prior spin_lock()/spin_unlock()
+	 * committed into memory all tw fields.
 	 */
-	inet_twsk_add_node_rcu(tw, &ehead->twchain);
+	atomic_set(&tw->tw_refcnt, 1 + 1 + 1);
+	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
-	/* Step 3: Remove SK from established hash. */
+	/* Step 3: Remove SK from hash chain */
 	if (__sk_nulls_del_node_init_rcu(sk))
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 
-	/*
-	 * Notes :
-	 * - We initially set tw_refcnt to 0 in inet_twsk_alloc()
-	 * - We add one reference for the bhash link
-	 * - We add one reference for the ehash link
-	 * - We want this refcnt update done before allowing other
-	 *   threads to find this tw in ehash chain.
-	 */
-	atomic_add(1 + 1 + 1, &tw->tw_refcnt);
-
 	spin_unlock(lock);
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
@@ -490,7 +489,9 @@ void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 restart_rcu:
 		rcu_read_lock();
 restart:
-		sk_nulls_for_each_rcu(sk, node, &head->twchain) {
+		sk_nulls_for_each_rcu(sk, node, &head->chain) {
+			if (sk->sk_state != TCP_TIME_WAIT)
+				continue;
 			tw = inet_twsk(sk);
 			if ((tw->tw_family != family) ||
 				atomic_read(&twsk_net(tw)->count))
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6e5617b9f9db..be4b161802e8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3137,10 +3137,9 @@ void __init tcp_init(void)
 					&tcp_hashinfo.ehash_mask,
 					0,
 					thash_entries ? 0 : 512 * 1024);
-	for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) {
+	for (i = 0; i <= tcp_hashinfo.ehash_mask; i++)
 		INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
-		INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i);
-	}
+
 	if (inet_ehash_locks_alloc(&tcp_hashinfo))
 		panic("TCP: failed to alloc ehash_locks");
 	tcp_hashinfo.bhash =
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5d6b1a609da8..e4695dde1af6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2194,18 +2194,6 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
 
-static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
-{
-	return hlist_nulls_empty(head) ? NULL :
-		list_entry(head->first, struct inet_timewait_sock, tw_node);
-}
-
-static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
-{
-	return !is_a_nulls(tw->tw_node.next) ?
-		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
-}
-
 /*
  * Get next listener socket follow cur.  If cur is NULL, get first socket
  * starting from bucket given in st->bucket; when st->bucket is zero the
@@ -2309,10 +2297,9 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 	return rc;
 }
 
-static inline bool empty_bucket(struct tcp_iter_state *st)
+static inline bool empty_bucket(const struct tcp_iter_state *st)
 {
-	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
-		hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain);
 }
 
 /*
@@ -2329,7 +2316,6 @@ static void *established_get_first(struct seq_file *seq)
 	for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
-		struct inet_timewait_sock *tw;
 		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
 
 		/* Lockless fast path for the common case of empty buckets */
@@ -2345,18 +2331,7 @@ static void *established_get_first(struct seq_file *seq)
 			rc = sk;
 			goto out;
 		}
-		st->state = TCP_SEQ_STATE_TIME_WAIT;
-		inet_twsk_for_each(tw, node,
-				   &tcp_hashinfo.ehash[st->bucket].twchain) {
-			if (tw->tw_family != st->family ||
-			    !net_eq(twsk_net(tw), net)) {
-				continue;
-			}
-			rc = tw;
-			goto out;
-		}
 		spin_unlock_bh(lock);
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
 	}
 out:
 	return rc;
@@ -2365,7 +2340,6 @@ out:
 static void *established_get_next(struct seq_file *seq, void *cur)
 {
 	struct sock *sk = cur;
-	struct inet_timewait_sock *tw;
 	struct hlist_nulls_node *node;
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
@@ -2373,45 +2347,16 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 	++st->offset;
 
-	if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
-		tw = cur;
-		tw = tw_next(tw);
-get_tw:
-		while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
-			tw = tw_next(tw);
-		}
-		if (tw) {
-			cur = tw;
-			goto out;
-		}
-		spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
-
-		/* Look for next non empty bucket */
-		st->offset = 0;
-		while (++st->bucket <= tcp_hashinfo.ehash_mask &&
-				empty_bucket(st))
-			;
-		if (st->bucket > tcp_hashinfo.ehash_mask)
-			return NULL;
-
-		spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
-	} else
-		sk = sk_nulls_next(sk);
+	sk = sk_nulls_next(sk);
 
 	sk_nulls_for_each_from(sk, node) {
 		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
-			goto found;
+			return sk;
 	}
 
-	st->state = TCP_SEQ_STATE_TIME_WAIT;
-	tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
-	goto get_tw;
-found:
-	cur = sk;
-out:
-	return cur;
+	spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+	++st->bucket;
+	return established_get_first(seq);
 }
 
 static void *established_get_idx(struct seq_file *seq, loff_t pos)
@@ -2464,10 +2409,9 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 		if (rc)
 			break;
 		st->bucket = 0;
+		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		/* Fallthrough */
 	case TCP_SEQ_STATE_ESTABLISHED:
-	case TCP_SEQ_STATE_TIME_WAIT:
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		if (st->bucket > tcp_hashinfo.ehash_mask)
 			break;
 		rc = established_get_first(seq);
@@ -2524,7 +2468,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		}
 		break;
 	case TCP_SEQ_STATE_ESTABLISHED:
-	case TCP_SEQ_STATE_TIME_WAIT:
 		rc = established_get_next(seq, v);
 		break;
 	}
@@ -2548,7 +2491,6 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 		if (v != SEQ_START_TOKEN)
 			spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
 		break;
-	case TCP_SEQ_STATE_TIME_WAIT:
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
 			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
@@ -2707,6 +2649,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 static int tcp4_seq_show(struct seq_file *seq, void *v)
 {
 	struct tcp_iter_state *st;
+	struct sock *sk = v;
 	int len;
 
 	if (v == SEQ_START_TOKEN) {
@@ -2721,14 +2664,14 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
 	case TCP_SEQ_STATE_ESTABLISHED:
-		get_tcp4_sock(v, seq, st->num, &len);
+		if (sk->sk_state == TCP_TIME_WAIT)
+			get_timewait4_sock(v, seq, st->num, &len);
+		else
+			get_tcp4_sock(v, seq, st->num, &len);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
 		get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
 		break;
-	case TCP_SEQ_STATE_TIME_WAIT:
-		get_timewait4_sock(v, seq, st->num, &len);
-		break;
 	}
 	seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
 out:
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 066640e0ba8e..46440777e1c5 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -89,43 +89,36 @@ begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (likely(INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
-			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
-				goto begintw;
+		if (sk->sk_state == TCP_TIME_WAIT) {
+			if (!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))
+				continue;
+		} else {
+			if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+				continue;
+		}
+		if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
+			goto out;
+
+		if (sk->sk_state == TCP_TIME_WAIT) {
+			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
+						     ports, dif))) {
+				sock_gen_put(sk);
+				goto begin;
+			}
+		} else {
 			if (unlikely(!INET6_MATCH(sk, net, saddr, daddr,
 						  ports, dif))) {
 				sock_put(sk);
 				goto begin;
 			}
-		goto out;
+		goto found;
 		}
 	}
 	if (get_nulls_value(node) != slot)
 		goto begin;
-
-begintw:
-	/* Must check for a TIME_WAIT'er before going to listener hash. */
-	sk_nulls_for_each_rcu(sk, node, &head->twchain) {
-		if (sk->sk_hash != hash)
-			continue;
-		if (likely(INET6_TW_MATCH(sk, net, saddr, daddr,
-					  ports, dif))) {
-			if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
-				sk = NULL;
-				goto out;
-			}
-			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
-						     ports, dif))) {
-				inet_twsk_put(inet_twsk(sk));
-				goto begintw;
-			}
-			goto out;
-		}
-	}
-	if (get_nulls_value(node) != slot)
-		goto begintw;
-	sk = NULL;
 out:
+	sk = NULL;
+found:
 	rcu_read_unlock();
 	return sk;
 }
@@ -248,31 +241,25 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
 	struct sock *sk2;
 	const struct hlist_nulls_node *node;
-	struct inet_timewait_sock *tw;
+	struct inet_timewait_sock *tw = NULL;
 	int twrefcnt = 0;
 
 	spin_lock(lock);
 
-	/* Check TIME-WAIT sockets first. */
-	sk_nulls_for_each(sk2, node, &head->twchain) {
+	sk_nulls_for_each(sk2, node, &head->chain) {
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
-					  ports, dif))) {
-			tw = inet_twsk(sk2);
-			if (twsk_unique(sk, sk2, twp))
-				goto unique;
-			else
-				goto not_unique;
+		if (sk2->sk_state == TCP_TIME_WAIT) {
+			if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
+						  ports, dif))) {
+				tw = inet_twsk(sk2);
+				if (twsk_unique(sk, sk2, twp))
+					goto unique;
+				else
+					goto not_unique;
+			}
 		}
-	}
-	tw = NULL;
-
-	/* And established part... */
-	sk_nulls_for_each(sk2, node, &head->chain) {
-		if (sk2->sk_hash != hash)
-			continue;
 		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif)))
 			goto not_unique;
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index dde8bad04481..528e61afaf5e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1834,6 +1834,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 static int tcp6_seq_show(struct seq_file *seq, void *v)
 {
 	struct tcp_iter_state *st;
+	struct sock *sk = v;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -1849,14 +1850,14 @@ static int tcp6_seq_show(struct seq_file *seq, void *v)
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
 	case TCP_SEQ_STATE_ESTABLISHED:
-		get_tcp6_sock(seq, v, st->num);
+		if (sk->sk_state == TCP_TIME_WAIT)
+			get_timewait6_sock(seq, v, st->num);
+		else
+			get_tcp6_sock(seq, v, st->num);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
 		get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
 		break;
-	case TCP_SEQ_STATE_TIME_WAIT:
-		get_timewait6_sock(seq, v, st->num);
-		break;
 	}
 out:
 	return 0;
-- 
cgit 


From efe4208f47f907b86f528788da711e8ab9dea44d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Oct 2013 15:42:29 -0700
Subject: ipv6: make lookups simpler and faster

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h                           | 46 +++-----------------
 include/net/inet6_hashtables.h                 |  5 +--
 include/net/inet_timewait_sock.h               |  4 +-
 include/net/ip.h                               |  2 +-
 include/net/ip6_checksum.h                     |  2 +-
 include/net/sock.h                             |  9 ++++
 net/dccp/ipv6.c                                | 24 +++++------
 net/dccp/ipv6.h                                |  1 -
 net/dccp/minisocks.c                           |  7 +---
 net/ipv4/inet_diag.c                           | 35 +++++++---------
 net/ipv4/ping.c                                | 15 ++++---
 net/ipv4/tcp_metrics.c                         | 10 ++---
 net/ipv4/tcp_minisocks.c                       |  7 +---
 net/ipv4/tcp_probe.c                           | 29 +++++--------
 net/ipv4/tcp_timer.c                           |  3 +-
 net/ipv6/af_inet6.c                            | 10 ++---
 net/ipv6/datagram.c                            | 25 ++++++-----
 net/ipv6/inet6_connection_sock.c               |  7 ++--
 net/ipv6/inet6_hashtables.c                    | 58 +++++++++-----------------
 net/ipv6/ipv6_sockglue.c                       |  7 ++--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c |  4 +-
 net/ipv6/ping.c                                |  2 +-
 net/ipv6/raw.c                                 | 17 ++++----
 net/ipv6/tcp_ipv6.c                            | 44 ++++++++++---------
 net/ipv6/udp.c                                 | 48 ++++++++++-----------
 net/l2tp/l2tp_core.c                           | 10 ++---
 net/l2tp/l2tp_debugfs.c                        |  5 ++-
 net/l2tp/l2tp_ip6.c                            | 16 +++----
 net/l2tp/l2tp_netlink.c                        |  4 +-
 net/l2tp/l2tp_ppp.c                            | 12 +++---
 net/netfilter/xt_TPROXY.c                      |  2 +-
 net/netfilter/xt_socket.c                      |  2 +-
 net/sctp/ipv6.c                                | 22 +++++-----
 net/sunrpc/svcsock.c                           |  2 +-
 security/lsm_audit.c                           |  5 +--
 35 files changed, 213 insertions(+), 288 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index b7f1f3bb346d..35f6c1b562c4 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -141,8 +141,6 @@ struct ipv6_fl_socklist;
  */
 struct ipv6_pinfo {
 	struct in6_addr 	saddr;
-	struct in6_addr 	rcv_saddr;
-	struct in6_addr		daddr;
 	struct in6_pktinfo	sticky_pktinfo;
 	const struct in6_addr		*daddr_cache;
 #ifdef CONFIG_IPV6_SUBTREES
@@ -256,22 +254,10 @@ struct tcp6_sock {
 
 extern int inet6_sk_rebuild_header(struct sock *sk);
 
-struct inet6_timewait_sock {
-	struct in6_addr tw_v6_daddr;
-	struct in6_addr	tw_v6_rcv_saddr;
-};
-
 struct tcp6_timewait_sock {
 	struct tcp_timewait_sock   tcp6tw_tcp;
-	struct inet6_timewait_sock tcp6tw_inet6;
 };
 
-static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk)
-{
-	return (struct inet6_timewait_sock *)(((u8 *)sk) +
-					      inet_twsk(sk)->tw_ipv6_offset);
-}
-
 #if IS_ENABLED(CONFIG_IPV6)
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
@@ -321,21 +307,11 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 #define __ipv6_only_sock(sk)	(inet6_sk(sk)->ipv6only)
 #define ipv6_only_sock(sk)	((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk))
 
-static inline u16 inet6_tw_offset(const struct proto *prot)
-{
-	return prot->twsk_prot->twsk_obj_size -
-			sizeof(struct inet6_timewait_sock);
-}
-
-static inline struct in6_addr *__inet6_rcv_saddr(const struct sock *sk)
+static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
 {
-	return likely(sk->sk_state != TCP_TIME_WAIT) ?
-		&inet6_sk(sk)->rcv_saddr : &inet6_twsk(sk)->tw_v6_rcv_saddr;
-}
-
-static inline struct in6_addr *inet6_rcv_saddr(const struct sock *sk)
-{
-	return sk->sk_family == AF_INET6 ? __inet6_rcv_saddr(sk) : NULL;
+	if (sk->sk_family == AF_INET6)
+		return &sk->sk_v6_rcv_saddr;
+	return NULL;
 }
 
 static inline int inet_v6_ipv6only(const struct sock *sk)
@@ -363,7 +339,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 	return NULL;
 }
 
-#define __inet6_rcv_saddr(__sk)	NULL
 #define inet6_rcv_saddr(__sk)	NULL
 #define tcp_twsk_ipv6only(__sk)		0
 #define inet_v6_ipv6only(__sk)		0
@@ -372,19 +347,10 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	\
 	(((__sk)->sk_portpair == (__ports))			&&	\
 	 ((__sk)->sk_family == AF_INET6)			&&	\
-	 ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr))	&&	\
-	 ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr))	&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr))		&&	\
+	 ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr))	&&	\
 	 (!(__sk)->sk_bound_dev_if	||				\
 	   ((__sk)->sk_bound_dev_if == (__dif))) 		&&	\
 	 net_eq(sock_net(__sk), (__net)))
 
-#define INET6_TW_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif)	   \
-	(((__sk)->sk_portpair == (__ports))				&& \
-	 ((__sk)->sk_family == AF_INET6)				&& \
-	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr))	&& \
-	 ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr)) && \
-	 (!(__sk)->sk_bound_dev_if	||				   \
-	  ((__sk)->sk_bound_dev_if == (__dif)))				&& \
-	 net_eq(sock_net(__sk), (__net)))
-
 #endif /* _IPV6_H */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index f52fa88feb64..a105d1a2fc00 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -43,9 +43,8 @@ static inline unsigned int inet6_ehashfn(struct net *net,
 static inline int inet6_sk_ehashfn(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct in6_addr *laddr = &np->rcv_saddr;
-	const struct in6_addr *faddr = &np->daddr;
+	const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *faddr = &sk->sk_v6_daddr;
 	const __u16 lport = inet->inet_num;
 	const __be16 fport = inet->inet_dport;
 	struct net *net = sock_net(sk);
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index de9e3ab7d43d..b647c6270eb7 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -116,7 +116,9 @@ struct inet_timewait_sock {
 #define tw_prot			__tw_common.skc_prot
 #define tw_net			__tw_common.skc_net
 #define tw_daddr        	__tw_common.skc_daddr
+#define tw_v6_daddr		__tw_common.skc_v6_daddr
 #define tw_rcv_saddr    	__tw_common.skc_rcv_saddr
+#define tw_v6_rcv_saddr    	__tw_common.skc_v6_rcv_saddr
 #define tw_dport		__tw_common.skc_dport
 #define tw_num			__tw_common.skc_num
 
@@ -133,7 +135,7 @@ struct inet_timewait_sock {
 				tw_transparent  : 1,
 				tw_pad		: 6,	/* 6 bits hole */
 				tw_tos		: 8,
-				tw_ipv6_offset  : 16;
+				tw_pad2		: 16 /* 16 bits hole */
 	kmemcheck_bitfield_end(flags);
 	u32			tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
diff --git a/include/net/ip.h b/include/net/ip.h
index b39ebe5339ac..217bc5bfc6c6 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -374,7 +374,7 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		memset(&np->saddr, 0, sizeof(np->saddr));
-		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
 	}
 #endif
 }
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 7686e3f5033d..1944406949ba 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -70,7 +70,7 @@ static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 
-	__tcp_v6_send_check(skb, &np->saddr, &np->daddr);
+	__tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
 }
 
 int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto);
diff --git a/include/net/sock.h b/include/net/sock.h
index 3f3e48c4704d..7e50df5c71d4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -191,6 +191,12 @@ struct sock_common {
 #ifdef CONFIG_NET_NS
 	struct net	 	*skc_net;
 #endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr		skc_v6_daddr;
+	struct in6_addr		skc_v6_rcv_saddr;
+#endif
+
 	/*
 	 * fields between dontcopy_begin/dontcopy_end
 	 * are not copied in sock_copy()
@@ -314,6 +320,9 @@ struct sock {
 #define sk_bind_node		__sk_common.skc_bind_node
 #define sk_prot			__sk_common.skc_prot
 #define sk_net			__sk_common.skc_net
+#define sk_v6_daddr		__sk_common.skc_v6_daddr
+#define sk_v6_rcv_saddr	__sk_common.skc_v6_rcv_saddr
+
 	socket_lock_t		sk_lock;
 	struct sk_buff_head	sk_receive_queue;
 	/*
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6cf9f7782ad4..7f075b83128a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -67,7 +67,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 	struct dccp_hdr *dh = dccp_hdr(skb);
 
 	dccp_csum_outgoing(skb);
-	dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr);
+	dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr);
 }
 
 static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
@@ -467,11 +467,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
+		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		newnp->rcv_saddr = newnp->saddr;
+		newsk->sk_v6_rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
@@ -538,9 +538,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newnp->daddr = ireq6->rmt_addr;
+	newsk->sk_v6_daddr = ireq6->rmt_addr;
 	newnp->saddr = ireq6->loc_addr;
-	newnp->rcv_saddr = ireq6->loc_addr;
+	newsk->sk_v6_rcv_saddr = ireq6->loc_addr;
 	newsk->sk_bound_dev_if = ireq6->iif;
 
 	/* Now IPv6 options...
@@ -885,7 +885,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			return -EINVAL;
 	}
 
-	np->daddr = usin->sin6_addr;
+	sk->sk_v6_daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -915,16 +915,16 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			goto failure;
 		}
 		ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
-		ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr);
+		ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr);
 
 		return err;
 	}
 
-	if (!ipv6_addr_any(&np->rcv_saddr))
-		saddr = &np->rcv_saddr;
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		saddr = &sk->sk_v6_rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.fl6_dport = usin->sin6_port;
@@ -941,7 +941,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		np->rcv_saddr = *saddr;
+		sk->sk_v6_rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
@@ -963,7 +963,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		goto late_failure;
 
 	dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
-						      np->daddr.s6_addr32,
+						      sk->sk_v6_daddr.s6_addr32,
 						      inet->inet_sport,
 						      inet->inet_dport);
 	err = dccp_connect(sk);
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
index 6eef81fdbe56..6604fc3fe953 100644
--- a/net/dccp/ipv6.h
+++ b/net/dccp/ipv6.h
@@ -30,7 +30,6 @@ struct dccp6_request_sock {
 
 struct dccp6_timewait_sock {
 	struct inet_timewait_sock   inet;
-	struct inet6_timewait_sock  tw6;
 };
 
 #endif /* _DCCP_IPV6_H */
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 662071b249cc..32e80d96d4c0 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -56,12 +56,9 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			const struct ipv6_pinfo *np = inet6_sk(sk);
-			struct inet6_timewait_sock *tw6;
 
-			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
-			tw6 = inet6_twsk((struct sock *)tw);
-			tw6->tw_v6_daddr = np->daddr;
-			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8e1e40653357..ecc179d676e4 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -121,13 +121,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		const struct ipv6_pinfo *np = inet6_sk(sk);
 
-		*(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = np->daddr;
+		*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
 
 		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
-			if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0)
+			if (nla_put_u8(skb, INET_DIAG_TCLASS,
+				       inet6_sk(sk)->tclass) < 0)
 				goto errout;
 	}
 #endif
@@ -255,11 +255,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_inode	      = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tw->tw_family == AF_INET6) {
-		const struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-
-		*(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
+		*(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr;
 	}
 #endif
 
@@ -273,10 +270,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
-		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
-					   skb, r, portid, seq, nlmsg_flags,
-					   unlh);
-	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh);
+		return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, seq,
+					   nlmsg_flags, unlh);
+
+	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
+				  nlmsg_flags, unlh);
 }
 
 int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
@@ -489,10 +487,9 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry.family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (entry.family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 
-		entry.saddr = np->rcv_saddr.s6_addr32;
-		entry.daddr = np->daddr.s6_addr32;
+		entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32;
+		entry.daddr = sk->sk_v6_daddr.s6_addr32;
 	} else
 #endif
 	{
@@ -649,10 +646,8 @@ static int inet_twsk_diag_dump(struct sock *sk,
 		entry.family = tw->tw_family;
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
-			struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-			entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
-			entry.daddr = tw6->tw_v6_daddr.s6_addr32;
+			entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32;
+			entry.daddr = tw->tw_v6_daddr.s6_addr32;
 		} else
 #endif
 		{
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a62610443152..ccefc07beacd 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -202,15 +202,14 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 #if IS_ENABLED(CONFIG_IPV6)
 		} else if (skb->protocol == htons(ETH_P_IPV6) &&
 			   sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
 			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
 				 (int) isk->inet_num,
-				 &inet6_sk(sk)->rcv_saddr,
+				 &sk->sk_v6_rcv_saddr,
 				 sk->sk_bound_dev_if);
 
-			if (!ipv6_addr_any(&np->rcv_saddr) &&
-			    !ipv6_addr_equal(&np->rcv_saddr,
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
 					     &ipv6_hdr(skb)->daddr))
 				continue;
 #endif
@@ -362,7 +361,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
 	} else if (saddr->sa_family == AF_INET6) {
 		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		np->rcv_saddr = np->saddr = addr->sin6_addr;
+		sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
 #endif
 	}
 }
@@ -376,7 +375,7 @@ static void ping_clear_saddr(struct sock *sk, int dif)
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (sk->sk_family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
 		memset(&np->saddr, 0, sizeof(np->saddr));
 #endif
 	}
@@ -418,7 +417,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	err = 0;
 	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
 	    (sk->sk_family == AF_INET6 &&
-	     !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
+	     !ipv6_addr_any(&sk->sk_v6_rcv_saddr)))
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
 
 	if (snum)
@@ -429,7 +428,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
-		memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
 #endif
 
 	sk_dst_reset(sk);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 52f3c6b971d2..27535fd5ea10 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -240,7 +240,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 
 static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
 {
-	struct inet6_timewait_sock *tw6;
 	struct tcp_metrics_block *tm;
 	struct inetpeer_addr addr;
 	unsigned int hash;
@@ -253,9 +252,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		tw6 = inet6_twsk((struct sock *)tw);
-		*(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr;
-		hash = ipv6_addr_hash(&tw6->tw_v6_daddr);
+		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
+		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		break;
 	default:
 		return NULL;
@@ -289,8 +287,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr;
-		hash = ipv6_addr_hash(&inet6_sk(sk)->daddr);
+		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
+		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		break;
 	default:
 		return NULL;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 58a3e69aef64..97b684159861 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -293,12 +293,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
-			struct inet6_timewait_sock *tw6;
 
-			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
-			tw6 = inet6_twsk((struct sock *)tw);
-			tw6->tw_v6_daddr = np->daddr;
-			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
 			tw->tw_ipv6only = np->ipv6only;
 		}
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 611beab38a00..8b97d71e193b 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -101,22 +101,6 @@ static inline int tcp_probe_avail(void)
 		si4.sin_addr.s_addr = inet->inet_##mem##addr;	\
 	} while (0)						\
 
-#if IS_ENABLED(CONFIG_IPV6)
-#define tcp_probe_copy_fl_to_si6(inet, si6, mem)		\
-	do {							\
-		struct ipv6_pinfo *pi6 = inet->pinet6;		\
-		si6.sin6_family = AF_INET6;			\
-		si6.sin6_port = inet->inet_##mem##port;		\
-		si6.sin6_addr = pi6->mem##addr;			\
-		si6.sin6_flowinfo = 0; /* No need here. */	\
-		si6.sin6_scope_id = 0;	/* No need here. */	\
-	} while (0)
-#else
-#define tcp_probe_copy_fl_to_si6(fl, si6, mem)			\
-	do {							\
-		memset(&si6, 0, sizeof(si6));			\
-	} while (0)
-#endif
 
 /*
  * Hook inserted to be called before each receive packet.
@@ -147,8 +131,17 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 				tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d);
 				break;
 			case AF_INET6:
-				tcp_probe_copy_fl_to_si6(inet, p->src.v6, s);
-				tcp_probe_copy_fl_to_si6(inet, p->dst.v6, d);
+				memset(&p->src.v6, 0, sizeof(p->src.v6));
+				memset(&p->dst.v6, 0, sizeof(p->dst.v6));
+#if IS_ENABLED(CONFIG_IPV6)
+				p->src.v6.sin6_family = AF_INET6;
+				p->src.v6.sin6_port = inet->inet_sport;
+				p->src.v6.sin6_addr = inet6_sk(sk)->saddr;
+
+				p->dst.v6.sin6_family = AF_INET6;
+				p->dst.v6.sin6_port = inet->inet_dport;
+				p->dst.v6.sin6_addr = sk->sk_v6_daddr;
+#endif
 				break;
 			default:
 				BUG();
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4b85e6f636c9..af07b5b23ebf 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -374,9 +374,8 @@ void tcp_retransmit_timer(struct sock *sk)
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &np->daddr,
+				       &sk->sk_v6_daddr,
 				       ntohs(inet->inet_dport), inet->inet_num,
 				       tp->snd_una, tp->snd_nxt);
 		}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4966b124dc2e..a2cb07cd3850 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -364,7 +364,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	inet->inet_rcv_saddr = v4addr;
 	inet->inet_saddr = v4addr;
 
-	np->rcv_saddr = addr->sin6_addr;
+	sk->sk_v6_rcv_saddr = addr->sin6_addr;
 
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
@@ -461,14 +461,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		    peer == 1)
 			return -ENOTCONN;
 		sin->sin6_port = inet->inet_dport;
-		sin->sin6_addr = np->daddr;
+		sin->sin6_addr = sk->sk_v6_daddr;
 		if (np->sndflow)
 			sin->sin6_flowinfo = np->flow_label;
 	} else {
-		if (ipv6_addr_any(&np->rcv_saddr))
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			sin->sin6_addr = np->saddr;
 		else
-			sin->sin6_addr = np->rcv_saddr;
+			sin->sin6_addr = sk->sk_v6_rcv_saddr;
 
 		sin->sin6_port = inet->inet_sport;
 	}
@@ -655,7 +655,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = sk->sk_protocol;
-		fl6.daddr = np->daddr;
+		fl6.daddr = sk->sk_v6_daddr;
 		fl6.saddr = np->saddr;
 		fl6.flowlabel = np->flow_label;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 48b6bd2a9a14..a454b0ff57c7 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -107,16 +107,16 @@ ipv4_connected:
 		if (err)
 			goto out;
 
-		ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr);
+		ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr);
 
 		if (ipv6_addr_any(&np->saddr) ||
 		    ipv6_mapped_addr_any(&np->saddr))
 			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 
-		if (ipv6_addr_any(&np->rcv_saddr) ||
-		    ipv6_mapped_addr_any(&np->rcv_saddr)) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
+		    ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) {
 			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &np->rcv_saddr);
+					       &sk->sk_v6_rcv_saddr);
 			if (sk->sk_prot->rehash)
 				sk->sk_prot->rehash(sk);
 		}
@@ -145,7 +145,7 @@ ipv4_connected:
 		}
 	}
 
-	np->daddr = *daddr;
+	sk->sk_v6_daddr = *daddr;
 	np->flow_label = fl6.flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
@@ -156,7 +156,7 @@ ipv4_connected:
 	 */
 
 	fl6.flowi6_proto = sk->sk_protocol;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
@@ -183,16 +183,16 @@ ipv4_connected:
 	if (ipv6_addr_any(&np->saddr))
 		np->saddr = fl6.saddr;
 
-	if (ipv6_addr_any(&np->rcv_saddr)) {
-		np->rcv_saddr = fl6.saddr;
+	if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+		sk->sk_v6_rcv_saddr = fl6.saddr;
 		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 		if (sk->sk_prot->rehash)
 			sk->sk_prot->rehash(sk);
 	}
 
 	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
-		      &np->daddr : NULL,
+		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+		      &sk->sk_v6_daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
 		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 		      &np->saddr :
@@ -883,11 +883,10 @@ EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 			     __u16 srcp, __u16 destp, int bucket)
 {
-	struct ipv6_pinfo *np = inet6_sk(sp);
 	const struct in6_addr *dest, *src;
 
-	dest  = &np->daddr;
-	src   = &np->rcv_saddr;
+	dest  = &sp->sk_v6_daddr;
+	src   = &sp->sk_v6_rcv_saddr;
 	seq_printf(seq,
 		   "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
 		   "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e4311cbc8b4e..b7400b480e74 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -165,11 +165,10 @@ EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
 
 void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
 {
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
 
 	sin6->sin6_family = AF_INET6;
-	sin6->sin6_addr = np->daddr;
+	sin6->sin6_addr = sk->sk_v6_daddr;
 	sin6->sin6_port	= inet_sk(sk)->inet_dport;
 	/* We do not store received flowlabel for TCP */
 	sin6->sin6_flowinfo = 0;
@@ -203,7 +202,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = sk->sk_protocol;
-	fl6->daddr = np->daddr;
+	fl6->daddr = sk->sk_v6_daddr;
 	fl6->saddr = np->saddr;
 	fl6->flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
@@ -245,7 +244,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	skb_dst_set_noref(skb, dst);
 
 	/* Restore final destination back after routing done */
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 
 	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
 	rcu_read_unlock();
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 46440777e1c5..842d833dfc18 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -89,30 +89,16 @@ begin:
 	sk_nulls_for_each_rcu(sk, node, &head->chain) {
 		if (sk->sk_hash != hash)
 			continue;
-		if (sk->sk_state == TCP_TIME_WAIT) {
-			if (!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))
-				continue;
-		} else {
-			if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
-				continue;
-		}
+		if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+			continue;
 		if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
 			goto out;
 
-		if (sk->sk_state == TCP_TIME_WAIT) {
-			if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
-						     ports, dif))) {
-				sock_gen_put(sk);
-				goto begin;
-			}
-		} else {
-			if (unlikely(!INET6_MATCH(sk, net, saddr, daddr,
-						  ports, dif))) {
-				sock_put(sk);
-				goto begin;
-			}
-		goto found;
+		if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
+			sock_gen_put(sk);
+			goto begin;
 		}
+		goto found;
 	}
 	if (get_nulls_value(node) != slot)
 		goto begin;
@@ -133,11 +119,10 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
 	    sk->sk_family == PF_INET6) {
-		const struct ipv6_pinfo *np = inet6_sk(sk);
 
 		score = 1;
-		if (!ipv6_addr_any(&np->rcv_saddr)) {
-			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 				return -1;
 			score++;
 		}
@@ -229,9 +214,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	const struct in6_addr *daddr = &np->rcv_saddr;
-	const struct in6_addr *saddr = &np->daddr;
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
 	const int dif = sk->sk_bound_dev_if;
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct net *net = sock_net(sk);
@@ -250,23 +234,19 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 		if (sk2->sk_hash != hash)
 			continue;
 
-		if (sk2->sk_state == TCP_TIME_WAIT) {
-			if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr,
-						  ports, dif))) {
+		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) {
+			if (sk2->sk_state == TCP_TIME_WAIT) {
 				tw = inet_twsk(sk2);
 				if (twsk_unique(sk, sk2, twp))
-					goto unique;
-				else
-					goto not_unique;
+					break;
 			}
-		}
-		if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif)))
 			goto not_unique;
+		}
 	}
 
-unique:
 	/* Must record num and sport now. Otherwise we will see
-	 * in hash table socket with a funny identity. */
+	 * in hash table socket with a funny identity.
+	 */
 	inet->inet_num = lport;
 	inet->inet_sport = htons(lport);
 	sk->sk_hash = hash;
@@ -299,9 +279,9 @@ not_unique:
 static inline u32 inet6_sk_port_offset(const struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct ipv6_pinfo *np = inet6_sk(sk);
-	return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32,
-					  np->daddr.s6_addr32,
+
+	return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32,
+					  sk->sk_v6_daddr.s6_addr32,
 					  inet->inet_dport);
 }
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d1e2e8ef29c5..4919a8e6063e 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -174,7 +174,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 			}
 
 			if (ipv6_only_sock(sk) ||
-			    !ipv6_addr_v4mapped(&np->daddr)) {
+			    !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
 				retv = -EADDRNOTAVAIL;
 				break;
 			}
@@ -1011,7 +1011,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxhlim) {
@@ -1026,7 +1026,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
+				src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr :
+								     np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index d6e4dd8b58df..54b75ead5a69 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -297,9 +297,9 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
 	struct nf_conn *ct;
 
-	tuple.src.u3.in6 = inet6->rcv_saddr;
+	tuple.src.u3.in6 = sk->sk_v6_rcv_saddr;
 	tuple.src.u.tcp.port = inet->inet_sport;
-	tuple.dst.u3.in6 = inet6->daddr;
+	tuple.dst.u3.in6 = sk->sk_v6_daddr;
 	tuple.dst.u.tcp.port = inet->inet_dport;
 	tuple.dst.protonum = sk->sk_protocol;
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 18f19df4189f..8815e31a87fe 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -116,7 +116,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	} else {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 	}
 
 	if (!iif)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a4ed2416399e..3c00842b0079 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -77,20 +77,19 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
 
 	sk_for_each_from(sk)
 		if (inet_sk(sk)->inet_num == num) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
 
-			if (!ipv6_addr_any(&np->daddr) &&
-			    !ipv6_addr_equal(&np->daddr, rmt_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&np->rcv_saddr)) {
-				if (ipv6_addr_equal(&np->rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+				if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					goto found;
 				if (is_multicast &&
 				    inet6_mc_check(sk, loc_addr, rmt_addr))
@@ -302,7 +301,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 
 	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
-	np->rcv_saddr = addr->sin6_addr;
+	sk->sk_v6_rcv_saddr = addr->sin6_addr;
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
 		np->saddr = addr->sin6_addr;
 	err = 0;
@@ -804,8 +803,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
@@ -816,7 +815,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 			return -EDESTADDRREQ;
 
 		proto = inet->inet_num;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 528e61afaf5e..541dfc40c7b3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -192,13 +192,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	}
 
 	if (tp->rx_opt.ts_recent_stamp &&
-	    !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
+	    !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
 		tp->rx_opt.ts_recent = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		tp->write_seq = 0;
 	}
 
-	np->daddr = usin->sin6_addr;
+	sk->sk_v6_daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -237,17 +237,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		} else {
 			ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
 			ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
-					       &np->rcv_saddr);
+					       &sk->sk_v6_rcv_saddr);
 		}
 
 		return err;
 	}
 
-	if (!ipv6_addr_any(&np->rcv_saddr))
-		saddr = &np->rcv_saddr;
+	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		saddr = &sk->sk_v6_rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.daddr = np->daddr;
+	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
@@ -266,7 +266,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		np->rcv_saddr = *saddr;
+		sk->sk_v6_rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
@@ -279,7 +279,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	rt = (struct rt6_info *) dst;
 	if (tcp_death_row.sysctl_tw_recycle &&
 	    !tp->rx_opt.ts_recent_stamp &&
-	    ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr))
+	    ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr))
 		tcp_fetch_timewait_stamp(sk, dst);
 
 	icsk->icsk_ext_hdr_len = 0;
@@ -298,7 +298,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
-							     np->daddr.s6_addr32,
+							     sk->sk_v6_daddr.s6_addr32,
 							     inet->inet_sport,
 							     inet->inet_dport);
 
@@ -515,7 +515,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
 static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
 						struct sock *addr_sk)
 {
-	return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr);
+	return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr);
 }
 
 static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
@@ -621,7 +621,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 
 	if (sk) {
 		saddr = &inet6_sk(sk)->saddr;
-		daddr = &inet6_sk(sk)->daddr;
+		daddr = &sk->sk_v6_daddr;
 	} else if (req) {
 		saddr = &inet6_rsk(req)->loc_addr;
 		daddr = &inet6_rsk(req)->rmt_addr;
@@ -1116,11 +1116,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
+		ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr);
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		newnp->rcv_saddr = newnp->saddr;
+		newsk->sk_v6_rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
 		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -1185,9 +1185,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newnp->daddr = treq->rmt_addr;
+	newsk->sk_v6_daddr = treq->rmt_addr;
 	newnp->saddr = treq->loc_addr;
-	newnp->rcv_saddr = treq->loc_addr;
+	newsk->sk_v6_rcv_saddr = treq->loc_addr;
 	newsk->sk_bound_dev_if = treq->iif;
 
 	/* Now IPv6 options...
@@ -1244,13 +1244,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Copy over the MD5 key from the original socket */
-	if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != NULL) {
+	if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) {
 		/* We're using one, so create a matching key
 		 * on the newsk structure. If we fail to get
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr,
+		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
 			       AF_INET6, key->key, key->keylen,
 			       sk_gfp_atomic(sk, GFP_ATOMIC));
 	}
@@ -1758,10 +1758,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct inet_sock *inet = inet_sk(sp);
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
-	const struct ipv6_pinfo *np = inet6_sk(sp);
 
-	dest  = &np->daddr;
-	src   = &np->rcv_saddr;
+	dest  = &sp->sk_v6_daddr;
+	src   = &sp->sk_v6_rcv_saddr;
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
@@ -1810,11 +1809,10 @@ static void get_timewait6_sock(struct seq_file *seq,
 {
 	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
-	const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
 	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
-	dest = &tw6->tw_v6_daddr;
-	src  = &tw6->tw_v6_rcv_saddr;
+	dest = &tw->tw_v6_daddr;
+	src  = &tw->tw_v6_rcv_saddr;
 	destp = ntohs(tw->tw_dport);
 	srcp  = ntohs(tw->tw_sport);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 37532478e3ba..b496de19a341 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -55,11 +55,10 @@
 
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
-	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
 	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
 	int sk_ipv6only = ipv6_only_sock(sk);
 	int sk2_ipv6only = inet_v6_ipv6only(sk2);
-	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
+	int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
 	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
 
 	/* if both are mapped, treat as IPv4 */
@@ -77,7 +76,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 		return 1;
 
 	if (sk2_rcv_saddr6 &&
-	    ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
+	    ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6))
 		return 1;
 
 	return 0;
@@ -105,7 +104,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
 	unsigned int hash2_nulladdr =
 		udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
 	unsigned int hash2_partial =
-		udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0);
+		udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
 
 	/* precompute partial secondary hash */
 	udp_sk(sk)->udp_portaddr_hash = hash2_partial;
@@ -115,7 +114,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
 static void udp_v6_rehash(struct sock *sk)
 {
 	u16 new_hash = udp6_portaddr_hash(sock_net(sk),
-					  &inet6_sk(sk)->rcv_saddr,
+					  &sk->sk_v6_rcv_saddr,
 					  inet_sk(sk)->inet_num);
 
 	udp_lib_rehash(sk, new_hash);
@@ -131,7 +130,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
 			sk->sk_family == PF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct inet_sock *inet = inet_sk(sk);
 
 		score = 0;
@@ -140,13 +138,13 @@ static inline int compute_score(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->rcv_saddr)) {
-			if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->daddr)) {
-			if (!ipv6_addr_equal(&np->daddr, saddr))
+		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
 				return -1;
 			score++;
 		}
@@ -169,10 +167,9 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 
 	if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
 			sk->sk_family == PF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 		struct inet_sock *inet = inet_sk(sk);
 
-		if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 			return -1;
 		score = 0;
 		if (inet->inet_dport) {
@@ -180,8 +177,8 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 				return -1;
 			score++;
 		}
-		if (!ipv6_addr_any(&np->daddr)) {
-			if (!ipv6_addr_equal(&np->daddr, saddr))
+		if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
+			if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
 				return -1;
 			score++;
 		}
@@ -549,7 +546,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
-	if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) {
+	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 	}
@@ -690,20 +687,19 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 
 		if (udp_sk(s)->udp_port_hash == num &&
 		    s->sk_family == PF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(s);
 			if (inet->inet_dport) {
 				if (inet->inet_dport != rmt_port)
 					continue;
 			}
-			if (!ipv6_addr_any(&np->daddr) &&
-			    !ipv6_addr_equal(&np->daddr, rmt_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&np->rcv_saddr)) {
-				if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
 			if (!inet6_mc_check(s, loc_addr, rmt_addr))
@@ -1063,7 +1059,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	} else if (!up->pending) {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 	} else
 		daddr = NULL;
 
@@ -1133,8 +1129,8 @@ do_udp_sendmsg:
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    sin6->sin6_scope_id &&
@@ -1145,7 +1141,7 @@ do_udp_sendmsg:
 			return -EDESTADDRREQ;
 
 		fl6.fl6_dport = inet->inet_dport;
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 		connected = 1;
 	}
@@ -1261,8 +1257,8 @@ do_append_data:
 	if (dst) {
 		if (connected) {
 			ip6_dst_store(sk, dst,
-				      ipv6_addr_equal(&fl6.daddr, &np->daddr) ?
-				      &np->daddr : NULL,
+				      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+				      &sk->sk_v6_daddr : NULL,
 #ifdef CONFIG_IPV6_SUBTREES
 				      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
 				      &np->saddr :
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index b076e8309bc2..9af77d9c0ec9 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1181,7 +1181,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
 	    !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
 		__wsum csum = skb_checksum(skb, 0, udp_len, 0);
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		uh->check = csum_ipv6_magic(&np->saddr, &np->daddr, udp_len,
+		uh->check = csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len,
 					    IPPROTO_UDP, csum);
 		if (uh->check == 0)
 			uh->check = CSUM_MANGLED_0;
@@ -1189,7 +1189,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_ipv6_magic(&np->saddr, &np->daddr,
+		uh->check = ~csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr,
 					     udp_len, IPPROTO_UDP, 0);
 	}
 }
@@ -1713,13 +1713,13 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
 		if (ipv6_addr_v4mapped(&np->saddr) &&
-		    ipv6_addr_v4mapped(&np->daddr)) {
+		    ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
 			struct inet_sock *inet = inet_sk(sk);
 
 			tunnel->v4mapped = true;
 			inet->inet_saddr = np->saddr.s6_addr32[3];
-			inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
-			inet->inet_daddr = np->daddr.s6_addr32[3];
+			inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3];
+			inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3];
 		} else {
 			tunnel->v4mapped = false;
 		}
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 072d7202e182..2d6760a2ae34 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -127,9 +127,10 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
 
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tunnel->sock->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
+			const struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
+
 			seq_printf(m, " from %pI6c to %pI6c\n",
-				&np->saddr, &np->daddr);
+				&np->saddr, &tunnel->sock->sk_v6_daddr);
 		} else
 #endif
 		seq_printf(m, " from %pI4 to %pI4\n",
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b8a6039314e8..cfd65304be60 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -63,7 +63,7 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net,
 	struct sock *sk;
 
 	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
-		struct in6_addr *addr = inet6_rcv_saddr(sk);
+		const struct in6_addr *addr = inet6_rcv_saddr(sk);
 		struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
 
 		if (l2tp == NULL)
@@ -331,7 +331,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rcu_read_unlock();
 
 	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
-	np->rcv_saddr = addr->l2tp_addr;
+	sk->sk_v6_rcv_saddr = addr->l2tp_addr;
 	np->saddr = addr->l2tp_addr;
 
 	l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
@@ -421,14 +421,14 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
 		if (!lsk->peer_conn_id)
 			return -ENOTCONN;
 		lsa->l2tp_conn_id = lsk->peer_conn_id;
-		lsa->l2tp_addr = np->daddr;
+		lsa->l2tp_addr = sk->sk_v6_daddr;
 		if (np->sndflow)
 			lsa->l2tp_flowinfo = np->flow_label;
 	} else {
-		if (ipv6_addr_any(&np->rcv_saddr))
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			lsa->l2tp_addr = np->saddr;
 		else
-			lsa->l2tp_addr = np->rcv_saddr;
+			lsa->l2tp_addr = sk->sk_v6_rcv_saddr;
 
 		lsa->l2tp_conn_id = lsk->conn_id;
 	}
@@ -537,8 +537,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		 * sk->sk_dst_cache.
 		 */
 		if (sk->sk_state == TCP_ESTABLISHED &&
-		    ipv6_addr_equal(daddr, &np->daddr))
-			daddr = &np->daddr;
+		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+			daddr = &sk->sk_v6_daddr;
 
 		if (addr_len >= sizeof(struct sockaddr_in6) &&
 		    lsa->l2tp_scope_id &&
@@ -548,7 +548,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 
-		daddr = &np->daddr;
+		daddr = &sk->sk_v6_daddr;
 		fl6.flowlabel = np->flow_label;
 	}
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 0825ff26e113..be446d517bc9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -306,8 +306,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 		if (np) {
 			if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr),
 				    &np->saddr) ||
-			    nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(np->daddr),
-				    &np->daddr))
+			    nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(sk->sk_v6_daddr),
+				    &sk->sk_v6_daddr))
 				goto nla_put_failure;
 		} else
 #endif
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5ebee2ded9e9..f0a7adaef2ea 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -906,8 +906,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if ((tunnel->version == 2) &&
 		   (tunnel->sock->sk_family == AF_INET6)) {
-		struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
 		struct sockaddr_pppol2tpin6 sp;
+
 		len = sizeof(sp);
 		memset(&sp, 0, len);
 		sp.sa_family	= AF_PPPOX;
@@ -920,13 +920,13 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 		sp.pppol2tp.d_session = session->peer_session_id;
 		sp.pppol2tp.addr.sin6_family = AF_INET6;
 		sp.pppol2tp.addr.sin6_port = inet->inet_dport;
-		memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr,
-		       sizeof(np->daddr));
+		memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr,
+		       sizeof(tunnel->sock->sk_v6_daddr));
 		memcpy(uaddr, &sp, len);
 	} else if ((tunnel->version == 3) &&
 		   (tunnel->sock->sk_family == AF_INET6)) {
-		struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
 		struct sockaddr_pppol2tpv3in6 sp;
+
 		len = sizeof(sp);
 		memset(&sp, 0, len);
 		sp.sa_family	= AF_PPPOX;
@@ -939,8 +939,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 		sp.pppol2tp.d_session = session->peer_session_id;
 		sp.pppol2tp.addr.sin6_family = AF_INET6;
 		sp.pppol2tp.addr.sin6_port = inet->inet_dport;
-		memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr,
-		       sizeof(np->daddr));
+		memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr,
+		       sizeof(tunnel->sock->sk_v6_daddr));
 		memcpy(uaddr, &sp, len);
 #endif
 	} else if (tunnel->version == 3) {
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 5d8a3a3cd5a7..ef8a926752a9 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -200,7 +200,7 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
 				     in->ifindex);
 		if (sk) {
 			int connected = (sk->sk_state == TCP_ESTABLISHED);
-			int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr);
+			int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);
 
 			/* NOTE: we return listeners even if bound to
 			 * 0.0.0.0, those are filtered out in
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 06df2b9110f5..3dd0e374bc2b 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -370,7 +370,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 		 */
 		wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) &&
 			    sk->sk_state != TCP_TIME_WAIT &&
-			    ipv6_addr_any(&inet6_sk(sk)->rcv_saddr));
+			    ipv6_addr_any(&sk->sk_v6_rcv_saddr));
 
 		/* Ignore non-transparent sockets,
 		   if XT_SOCKET_TRANSPARENT is used */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e7b2d4fe2b6a..f6334aa19151 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -426,20 +426,20 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
 {
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = 0;
-	addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr;
+	addr->v6.sin6_addr = sk->sk_v6_rcv_saddr;
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
 static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
 {
 	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
-		inet6_sk(sk)->rcv_saddr.s6_addr32[0] = 0;
-		inet6_sk(sk)->rcv_saddr.s6_addr32[1] = 0;
-		inet6_sk(sk)->rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
-		inet6_sk(sk)->rcv_saddr.s6_addr32[3] =
+		sk->sk_v6_rcv_saddr.s6_addr32[0] = 0;
+		sk->sk_v6_rcv_saddr.s6_addr32[1] = 0;
+		sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff);
+		sk->sk_v6_rcv_saddr.s6_addr32[3] =
 			addr->v4.sin_addr.s_addr;
 	} else {
-		inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr;
+		sk->sk_v6_rcv_saddr = addr->v6.sin6_addr;
 	}
 }
 
@@ -447,12 +447,12 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
 static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
 {
 	if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) {
-		inet6_sk(sk)->daddr.s6_addr32[0] = 0;
-		inet6_sk(sk)->daddr.s6_addr32[1] = 0;
-		inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff);
-		inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
+		sk->sk_v6_daddr.s6_addr32[0] = 0;
+		sk->sk_v6_daddr.s6_addr32[1] = 0;
+		sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff);
+		sk->sk_v6_daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	} else {
-		inet6_sk(sk)->daddr = addr->v6.sin6_addr;
+		sk->sk_v6_daddr = addr->v6.sin6_addr;
 	}
 }
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 9c9caaa5e0d3..0045c7cf1e9e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -294,7 +294,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 	case PF_INET6:
 		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
 				proto_name,
-				&inet6_sk(sk)->rcv_saddr,
+				&sk->sk_v6_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
 	default:
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 8d8d97dbb389..80554fcf9fcc 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -304,12 +304,11 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 			}
 			case AF_INET6: {
 				struct inet_sock *inet = inet_sk(sk);
-				struct ipv6_pinfo *inet6 = inet6_sk(sk);
 
-				print_ipv6_addr(ab, &inet6->rcv_saddr,
+				print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr,
 						inet->inet_sport,
 						"laddr", "lport");
-				print_ipv6_addr(ab, &inet6->daddr,
+				print_ipv6_addr(ab, &sk->sk_v6_daddr,
 						inet->inet_dport,
 						"faddr", "fport");
 				break;
-- 
cgit 


From 16eb5f4379b2097438a224381be3b4d9e56ac979 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 2 Oct 2013 10:15:18 +0200
Subject: drm: kill ->gem_init_object() and friends

All drivers embed gem-objects into their own buffer objects. There is no
reason to keep drm_gem_object_alloc(), gem->driver_private and
->gem_init_object() anymore.

New drivers are highly encouraged to do the same. There is no benefit in
allocating gem-objects separately.

Cc: Dave Airlie <airlied@gmail.com>
Cc: Alex Deucher <alexdeucher@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Inki Dae <inki.dae@samsung.com>
Cc: Ben Skeggs <skeggsb@gmail.com>
Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/ast/ast_drv.c           |  1 -
 drivers/gpu/drm/ast/ast_drv.h           |  1 -
 drivers/gpu/drm/ast/ast_main.c          |  6 ------
 drivers/gpu/drm/cirrus/cirrus_drv.c     |  1 -
 drivers/gpu/drm/cirrus/cirrus_drv.h     |  1 -
 drivers/gpu/drm/cirrus/cirrus_main.c    |  6 ------
 drivers/gpu/drm/drm_gem.c               | 29 -----------------------------
 drivers/gpu/drm/exynos/exynos_drm_drv.c |  1 -
 drivers/gpu/drm/exynos/exynos_drm_gem.c |  5 -----
 drivers/gpu/drm/exynos/exynos_drm_gem.h |  3 ---
 drivers/gpu/drm/gma500/gem.c            |  5 -----
 drivers/gpu/drm/gma500/psb_drv.c        |  1 -
 drivers/gpu/drm/gma500/psb_drv.h        |  1 -
 drivers/gpu/drm/i915/i915_drv.c         |  1 -
 drivers/gpu/drm/i915/i915_drv.h         |  1 -
 drivers/gpu/drm/i915/i915_gem.c         |  7 -------
 drivers/gpu/drm/mgag200/mgag200_drv.c   |  1 -
 drivers/gpu/drm/mgag200/mgag200_drv.h   |  1 -
 drivers/gpu/drm/mgag200/mgag200_main.c  |  6 ------
 drivers/gpu/drm/nouveau/nouveau_drm.c   |  1 -
 drivers/gpu/drm/nouveau/nouveau_gem.c   |  6 ------
 drivers/gpu/drm/nouveau/nouveau_gem.h   |  1 -
 drivers/gpu/drm/omapdrm/omap_drv.c      |  1 -
 drivers/gpu/drm/omapdrm/omap_drv.h      |  1 -
 drivers/gpu/drm/omapdrm/omap_gem.c      |  5 -----
 drivers/gpu/drm/qxl/qxl_drv.c           |  1 -
 drivers/gpu/drm/qxl/qxl_drv.h           |  1 -
 drivers/gpu/drm/qxl/qxl_gem.c           |  6 ------
 drivers/gpu/drm/radeon/radeon_drv.c     |  2 --
 drivers/gpu/drm/radeon/radeon_gem.c     |  7 -------
 drivers/gpu/drm/udl/udl_drv.c           |  1 -
 drivers/gpu/drm/udl/udl_drv.h           |  1 -
 drivers/gpu/drm/udl/udl_gem.c           |  7 -------
 include/drm/drmP.h                      |  5 -----
 34 files changed, 124 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index 32e270dc714e..5137f15dba19 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -211,7 +211,6 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 
-	.gem_init_object = ast_gem_init_object,
 	.gem_free_object = ast_gem_free_object,
 	.dumb_create = ast_dumb_create,
 	.dumb_map_offset = ast_dumb_mmap_offset,
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 8492b68e873c..9833a1b1acc1 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -323,7 +323,6 @@ extern int ast_dumb_create(struct drm_file *file,
 			   struct drm_device *dev,
 			   struct drm_mode_create_dumb *args);
 
-extern int ast_gem_init_object(struct drm_gem_object *obj);
 extern void ast_gem_free_object(struct drm_gem_object *obj);
 extern int ast_dumb_mmap_offset(struct drm_file *file,
 				struct drm_device *dev,
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 7f6152d374ca..af0b868a9dfd 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -449,12 +449,6 @@ int ast_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int ast_gem_init_object(struct drm_gem_object *obj)
-{
-	BUG();
-	return 0;
-}
-
 void ast_bo_unref(struct ast_bo **bo)
 {
 	struct ttm_buffer_object *tbo;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 138364d91782..953fc8aea69c 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -97,7 +97,6 @@ static struct drm_driver driver = {
 	.major = DRIVER_MAJOR,
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
-	.gem_init_object = cirrus_gem_init_object,
 	.gem_free_object = cirrus_gem_free_object,
 	.dumb_create = cirrus_dumb_create,
 	.dumb_map_offset = cirrus_dumb_mmap_offset,
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 9b0bb9184afd..b6aded73838b 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -191,7 +191,6 @@ int cirrus_device_init(struct cirrus_device *cdev,
 		      struct pci_dev *pdev,
 		      uint32_t flags);
 void cirrus_device_fini(struct cirrus_device *cdev);
-int cirrus_gem_init_object(struct drm_gem_object *obj);
 void cirrus_gem_free_object(struct drm_gem_object *obj);
 int cirrus_dumb_mmap_offset(struct drm_file *file,
 			    struct drm_device *dev,
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index f130a533a512..78e76f24343d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -255,12 +255,6 @@ int cirrus_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int cirrus_gem_init_object(struct drm_gem_object *obj)
-{
-	BUG();
-	return 0;
-}
-
 void cirrus_bo_unref(struct cirrus_bo **bo)
 {
 	struct ttm_buffer_object *tbo;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 49293bdc972a..4761adedad2a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -160,35 +160,6 @@ void drm_gem_private_object_init(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_gem_private_object_init);
 
-/**
- * Allocate a GEM object of the specified size with shmfs backing store
- */
-struct drm_gem_object *
-drm_gem_object_alloc(struct drm_device *dev, size_t size)
-{
-	struct drm_gem_object *obj;
-
-	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
-	if (!obj)
-		goto free;
-
-	if (drm_gem_object_init(dev, obj, size) != 0)
-		goto free;
-
-	if (dev->driver->gem_init_object != NULL &&
-	    dev->driver->gem_init_object(obj) != 0) {
-		goto fput;
-	}
-	return obj;
-fput:
-	/* Object_init mangles the global counters - readjust them. */
-	fput(obj->filp);
-free:
-	kfree(obj);
-	return NULL;
-}
-EXPORT_SYMBOL(drm_gem_object_alloc);
-
 static void
 drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
 {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index bb82ef78ca85..3a1e6d9b25f7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -264,7 +264,6 @@ static struct drm_driver exynos_drm_driver = {
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= exynos_drm_crtc_enable_vblank,
 	.disable_vblank		= exynos_drm_crtc_disable_vblank,
-	.gem_init_object	= exynos_drm_gem_init_object,
 	.gem_free_object	= exynos_drm_gem_free_object,
 	.gem_vm_ops		= &exynos_drm_gem_vm_ops,
 	.dumb_create		= exynos_drm_gem_dumb_create,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 49f9cd232757..1ade191d84f4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -630,11 +630,6 @@ void exynos_gem_unmap_sgt_from_dma(struct drm_device *drm_dev,
 	dma_unmap_sg(drm_dev->dev, sgt->sgl, sgt->nents, dir);
 }
 
-int exynos_drm_gem_init_object(struct drm_gem_object *obj)
-{
-	return 0;
-}
-
 void exynos_drm_gem_free_object(struct drm_gem_object *obj)
 {
 	struct exynos_drm_gem_obj *exynos_gem_obj;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 09555afdfe9c..702ec3abe85c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -135,9 +135,6 @@ unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
 						unsigned int gem_handle,
 						struct drm_file *file_priv);
 
-/* initialize gem object. */
-int exynos_drm_gem_init_object(struct drm_gem_object *obj);
-
 /* free gem object. */
 void exynos_drm_gem_free_object(struct drm_gem_object *gem_obj);
 
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index 10ae8c52d06f..e2db48a81ed0 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -29,11 +29,6 @@
 #include <drm/drm_vma_manager.h>
 #include "psb_drv.h"
 
-int psb_gem_init_object(struct drm_gem_object *obj)
-{
-	return -EINVAL;
-}
-
 void psb_gem_free_object(struct drm_gem_object *obj)
 {
 	struct gtt_range *gtt = container_of(obj, struct gtt_range, gem);
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index fcb4e9ff1f20..30dceb43690b 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -646,7 +646,6 @@ static struct drm_driver driver = {
 	.preclose = psb_driver_preclose,
 	.postclose = psb_driver_close,
 
-	.gem_init_object = psb_gem_init_object,
 	.gem_free_object = psb_gem_free_object,
 	.gem_vm_ops = &psb_gem_vm_ops,
 	.dumb_create = psb_gem_dumb_create,
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 4535ac7708f8..6856bce58445 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -837,7 +837,6 @@ extern const struct drm_connector_helper_funcs
 extern const struct drm_connector_funcs psb_intel_lvds_connector_funcs;
 
 /* gem.c */
-extern int psb_gem_init_object(struct drm_gem_object *obj);
 extern void psb_gem_free_object(struct drm_gem_object *obj);
 extern int psb_gem_get_aperture(struct drm_device *dev, void *data,
 			struct drm_file *file);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6f385e1e9ed6..5f424899009b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -938,7 +938,6 @@ static struct drm_driver driver = {
 	.debugfs_init = i915_debugfs_init,
 	.debugfs_cleanup = i915_debugfs_cleanup,
 #endif
-	.gem_init_object = i915_gem_init_object,
 	.gem_free_object = i915_gem_free_object,
 	.gem_vm_ops = &i915_gem_vm_ops,
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8c52cbdb76f3..923d9d0eecf5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1848,7 +1848,6 @@ int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 void i915_gem_load(struct drm_device *dev);
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
-int i915_gem_init_object(struct drm_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			 const struct drm_i915_gem_object_ops *ops);
 struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 36c4ad9c752e..cf57276ce9aa 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4107,13 +4107,6 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	return obj;
 }
 
-int i915_gem_init_object(struct drm_gem_object *obj)
-{
-	BUG();
-
-	return 0;
-}
-
 void i915_gem_free_object(struct drm_gem_object *gem_obj)
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index fcce7b2f8011..f15ea3c4a90a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -99,7 +99,6 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 
-	.gem_init_object = mgag200_gem_init_object,
 	.gem_free_object = mgag200_gem_free_object,
 	.dumb_create = mgag200_dumb_create,
 	.dumb_map_offset = mgag200_dumb_mmap_offset,
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index baaae19332e2..cf11ee68a6d9 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -260,7 +260,6 @@ int mgag200_driver_unload(struct drm_device *dev);
 int mgag200_gem_create(struct drm_device *dev,
 		   u32 size, bool iskernel,
 		       struct drm_gem_object **obj);
-int mgag200_gem_init_object(struct drm_gem_object *obj);
 int mgag200_dumb_create(struct drm_file *file,
 			struct drm_device *dev,
 			struct drm_mode_create_dumb *args);
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 0f8b861b10b3..b1120cb1db6d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -310,12 +310,6 @@ int mgag200_dumb_create(struct drm_file *file,
 	return 0;
 }
 
-int mgag200_gem_init_object(struct drm_gem_object *obj)
-{
-	BUG();
-	return 0;
-}
-
 void mgag200_bo_unref(struct mgag200_bo **bo)
 {
 	struct ttm_buffer_object *tbo;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index e893c5362402..428d818be775 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -834,7 +834,6 @@ driver = {
 	.gem_prime_vmap = nouveau_gem_prime_vmap,
 	.gem_prime_vunmap = nouveau_gem_prime_vunmap,
 
-	.gem_init_object = nouveau_gem_object_new,
 	.gem_free_object = nouveau_gem_object_del,
 	.gem_open_object = nouveau_gem_object_open,
 	.gem_close_object = nouveau_gem_object_close,
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 6618318abf50..418a6177a653 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -34,12 +34,6 @@
 #include "nouveau_ttm.h"
 #include "nouveau_gem.h"
 
-int
-nouveau_gem_object_new(struct drm_gem_object *gem)
-{
-	return 0;
-}
-
 void
 nouveau_gem_object_del(struct drm_gem_object *gem)
 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h
index b535895df1a6..7caca057bc38 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.h
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.h
@@ -19,7 +19,6 @@ nouveau_gem_object(struct drm_gem_object *gem)
 extern int nouveau_gem_new(struct drm_device *, int size, int align,
 			   uint32_t domain, uint32_t tile_mode,
 			   uint32_t tile_flags, struct nouveau_bo **);
-extern int nouveau_gem_object_new(struct drm_gem_object *);
 extern void nouveau_gem_object_del(struct drm_gem_object *);
 extern int nouveau_gem_object_open(struct drm_gem_object *, struct drm_file *);
 extern void nouveau_gem_object_close(struct drm_gem_object *,
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 2603d909f49c..e7fa3cd96743 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -620,7 +620,6 @@ static struct drm_driver omap_drm_driver = {
 		.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 		.gem_prime_export = omap_gem_prime_export,
 		.gem_prime_import = omap_gem_prime_import,
-		.gem_init_object = omap_gem_init_object,
 		.gem_free_object = omap_gem_free_object,
 		.gem_vm_ops = &omap_gem_vm_ops,
 		.dumb_create = omap_gem_dumb_create,
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 30b95b736658..07847693cf49 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -220,7 +220,6 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 int omap_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		union omap_gem_size gsize, uint32_t flags, uint32_t *handle);
 void omap_gem_free_object(struct drm_gem_object *obj);
-int omap_gem_init_object(struct drm_gem_object *obj);
 void *omap_gem_vaddr(struct drm_gem_object *obj);
 int omap_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 		uint32_t handle, uint64_t *offset);
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 533f6ebec531..5aec3e81fe24 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1274,11 +1274,6 @@ unlock:
 	return ret;
 }
 
-int omap_gem_init_object(struct drm_gem_object *obj)
-{
-	return -EINVAL;          /* unused */
-}
-
 /* don't call directly.. called from GEM core when it is time to actually
  * free the object..
  */
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 514118ae72d4..fee8748bdca5 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -225,7 +225,6 @@ static struct drm_driver qxl_driver = {
 	.debugfs_init = qxl_debugfs_init,
 	.debugfs_cleanup = qxl_debugfs_takedown,
 #endif
-	.gem_init_object = qxl_gem_object_init,
 	.gem_free_object = qxl_gem_object_free,
 	.gem_open_object = qxl_gem_object_open,
 	.gem_close_object = qxl_gem_object_close,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index f7c9adde46a0..41d22ed26060 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -412,7 +412,6 @@ int qxl_gem_object_create_with_handle(struct qxl_device *qdev,
 				      struct qxl_surface *surf,
 				      struct qxl_bo **qobj,
 				      uint32_t *handle);
-int qxl_gem_object_init(struct drm_gem_object *obj);
 void qxl_gem_object_free(struct drm_gem_object *gobj);
 int qxl_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_priv);
 void qxl_gem_object_close(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/qxl/qxl_gem.c b/drivers/gpu/drm/qxl/qxl_gem.c
index 1648e4125af7..b96f0c9d89b2 100644
--- a/drivers/gpu/drm/qxl/qxl_gem.c
+++ b/drivers/gpu/drm/qxl/qxl_gem.c
@@ -28,12 +28,6 @@
 #include "qxl_drv.h"
 #include "qxl_object.h"
 
-int qxl_gem_object_init(struct drm_gem_object *obj)
-{
-	/* we do nothings here */
-	return 0;
-}
-
 void qxl_gem_object_free(struct drm_gem_object *gobj)
 {
 	struct qxl_bo *qobj = gem_to_qxl_bo(gobj);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index cdd12dcd988b..22f685827b7e 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -100,7 +100,6 @@ void radeon_driver_irq_preinstall_kms(struct drm_device *dev);
 int radeon_driver_irq_postinstall_kms(struct drm_device *dev);
 void radeon_driver_irq_uninstall_kms(struct drm_device *dev);
 irqreturn_t radeon_driver_irq_handler_kms(DRM_IRQ_ARGS);
-int radeon_gem_object_init(struct drm_gem_object *obj);
 void radeon_gem_object_free(struct drm_gem_object *obj);
 int radeon_gem_object_open(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
@@ -408,7 +407,6 @@ static struct drm_driver kms_driver = {
 	.irq_uninstall = radeon_driver_irq_uninstall_kms,
 	.irq_handler = radeon_driver_irq_handler_kms,
 	.ioctls = radeon_ioctls_kms,
-	.gem_init_object = radeon_gem_object_init,
 	.gem_free_object = radeon_gem_object_free,
 	.gem_open_object = radeon_gem_object_open,
 	.gem_close_object = radeon_gem_object_close,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index dce99c8a5835..805c5e566b9a 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -29,13 +29,6 @@
 #include <drm/radeon_drm.h>
 #include "radeon.h"
 
-int radeon_gem_object_init(struct drm_gem_object *obj)
-{
-	BUG();
-
-	return 0;
-}
-
 void radeon_gem_object_free(struct drm_gem_object *gobj)
 {
 	struct radeon_bo *robj = gem_to_radeon_bo(gobj);
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 7650dc0d78ce..3ddd6cd98ac1 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -77,7 +77,6 @@ static struct drm_driver driver = {
 	.unload = udl_driver_unload,
 
 	/* gem hooks */
-	.gem_init_object = udl_gem_init_object,
 	.gem_free_object = udl_gem_free_object,
 	.gem_vm_ops = &udl_gem_vm_ops,
 
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 56aec9409fa3..1fbf7b357f16 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -115,7 +115,6 @@ int udl_dumb_create(struct drm_file *file_priv,
 int udl_gem_mmap(struct drm_file *file_priv, struct drm_device *dev,
 		 uint32_t handle, uint64_t *offset);
 
-int udl_gem_init_object(struct drm_gem_object *obj);
 void udl_gem_free_object(struct drm_gem_object *gem_obj);
 struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev,
 					    size_t size);
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 8bf646183bac..24ffbe990736 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -107,13 +107,6 @@ int udl_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 }
 
-int udl_gem_init_object(struct drm_gem_object *obj)
-{
-	BUG();
-
-	return 0;
-}
-
 static int udl_gem_get_pages(struct udl_gem_object *obj, gfp_t gfpmask)
 {
 	struct page **pages;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index b46fb45f2cca..69dd5fd5b215 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -667,8 +667,6 @@ struct drm_gem_object {
 	uint32_t pending_read_domains;
 	uint32_t pending_write_domain;
 
-	void *driver_private;
-
 	/**
 	 * dma_buf - dma buf associated with this GEM object
 	 *
@@ -922,7 +920,6 @@ struct drm_driver {
 	 *
 	 * Returns 0 on success.
 	 */
-	int (*gem_init_object) (struct drm_gem_object *obj);
 	void (*gem_free_object) (struct drm_gem_object *obj);
 	int (*gem_open_object) (struct drm_gem_object *, struct drm_file *);
 	void (*gem_close_object) (struct drm_gem_object *, struct drm_file *);
@@ -1556,8 +1553,6 @@ int drm_gem_init(struct drm_device *dev);
 void drm_gem_destroy(struct drm_device *dev);
 void drm_gem_object_release(struct drm_gem_object *obj);
 void drm_gem_object_free(struct kref *kref);
-struct drm_gem_object *drm_gem_object_alloc(struct drm_device *dev,
-					    size_t size);
 int drm_gem_object_init(struct drm_device *dev,
 			struct drm_gem_object *obj, size_t size);
 void drm_gem_private_object_init(struct drm_device *dev,
-- 
cgit 


From 1bb72532ac260a2d3982b40bdd4c936d779d0d16 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 2 Oct 2013 11:23:34 +0200
Subject: drm: add drm_dev_alloc() helper

Instead of managing device allocation+initialization in each bus-driver,
we should do that in a central place. drm_fill_in_dev() already does most
of it, but also requires the global drm lock for partial AGP device
registration.

Split both apart so we have a clean device initialization/allocation
phase, and a registration phase.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_pci.c      |   4 +-
 drivers/gpu/drm/drm_platform.c |   3 +-
 drivers/gpu/drm/drm_stub.c     | 121 +++++++++++++++++++++++++----------------
 drivers/gpu/drm/drm_usb.c      |   7 +--
 include/drm/drmP.h             |   2 +
 5 files changed, 80 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 1f96cee6eee8..d2758be37a93 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -322,7 +322,7 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 
 	DRM_DEBUG("\n");
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	dev = drm_dev_alloc(driver, &pdev->dev);
 	if (!dev)
 		return -ENOMEM;
 
@@ -331,8 +331,6 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 		goto err_g1;
 
 	dev->pdev = pdev;
-	dev->dev = &pdev->dev;
-
 	dev->pci_device = pdev->device;
 	dev->pci_vendor = pdev->vendor;
 
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index f7a18c6ba4c4..fb2721738a8a 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -47,12 +47,11 @@ static int drm_get_platform_dev(struct platform_device *platdev,
 
 	DRM_DEBUG("\n");
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	dev = drm_dev_alloc(driver, &platdev->dev);
 	if (!dev)
 		return -ENOMEM;
 
 	dev->platformdev = platdev;
-	dev->dev = &platdev->dev;
 
 	mutex_lock(&drm_global_mutex);
 
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 39d864576be4..64bd52f13199 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -260,60 +260,15 @@ int drm_fill_in_dev(struct drm_device *dev,
 {
 	int retcode;
 
-	INIT_LIST_HEAD(&dev->filelist);
-	INIT_LIST_HEAD(&dev->ctxlist);
-	INIT_LIST_HEAD(&dev->vmalist);
-	INIT_LIST_HEAD(&dev->maplist);
-	INIT_LIST_HEAD(&dev->vblank_event_list);
-
-	spin_lock_init(&dev->count_lock);
-	spin_lock_init(&dev->event_lock);
-	mutex_init(&dev->struct_mutex);
-	mutex_init(&dev->ctxlist_mutex);
-
-	if (drm_ht_create(&dev->map_hash, 12)) {
-		return -ENOMEM;
-	}
-
-	/* the DRM has 6 basic counters */
-	dev->counters = 6;
-	dev->types[0] = _DRM_STAT_LOCK;
-	dev->types[1] = _DRM_STAT_OPENS;
-	dev->types[2] = _DRM_STAT_CLOSES;
-	dev->types[3] = _DRM_STAT_IOCTLS;
-	dev->types[4] = _DRM_STAT_LOCKS;
-	dev->types[5] = _DRM_STAT_UNLOCKS;
-
-	dev->driver = driver;
-
 	if (dev->driver->bus->agp_init) {
 		retcode = dev->driver->bus->agp_init(dev);
-		if (retcode)
-			goto error_out_unreg;
-	}
-
-
-
-	retcode = drm_ctxbitmap_init(dev);
-	if (retcode) {
-		DRM_ERROR("Cannot allocate memory for context bitmap.\n");
-		goto error_out_unreg;
-	}
-
-	if (driver->driver_features & DRIVER_GEM) {
-		retcode = drm_gem_init(dev);
 		if (retcode) {
-			DRM_ERROR("Cannot initialize graphics execution "
-				  "manager (GEM)\n");
-			goto error_out_unreg;
+			drm_lastclose(dev);
+			return retcode;
 		}
 	}
 
 	return 0;
-
-      error_out_unreg:
-	drm_lastclose(dev);
-	return retcode;
 }
 EXPORT_SYMBOL(drm_fill_in_dev);
 
@@ -490,3 +445,75 @@ void drm_unplug_dev(struct drm_device *dev)
 	mutex_unlock(&drm_global_mutex);
 }
 EXPORT_SYMBOL(drm_unplug_dev);
+
+/**
+ * drm_dev_alloc - Allocate new drm device
+ * @driver: DRM driver to allocate device for
+ * @parent: Parent device object
+ *
+ * Allocate and initialize a new DRM device. No device registration is done.
+ *
+ * RETURNS:
+ * Pointer to new DRM device, or NULL if out of memory.
+ */
+struct drm_device *drm_dev_alloc(struct drm_driver *driver,
+				 struct device *parent)
+{
+	struct drm_device *dev;
+	int ret;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	dev->dev = parent;
+	dev->driver = driver;
+
+	INIT_LIST_HEAD(&dev->filelist);
+	INIT_LIST_HEAD(&dev->ctxlist);
+	INIT_LIST_HEAD(&dev->vmalist);
+	INIT_LIST_HEAD(&dev->maplist);
+	INIT_LIST_HEAD(&dev->vblank_event_list);
+
+	spin_lock_init(&dev->count_lock);
+	spin_lock_init(&dev->event_lock);
+	mutex_init(&dev->struct_mutex);
+	mutex_init(&dev->ctxlist_mutex);
+
+	/* the DRM has 6 basic counters */
+	dev->counters = 6;
+	dev->types[0] = _DRM_STAT_LOCK;
+	dev->types[1] = _DRM_STAT_OPENS;
+	dev->types[2] = _DRM_STAT_CLOSES;
+	dev->types[3] = _DRM_STAT_IOCTLS;
+	dev->types[4] = _DRM_STAT_LOCKS;
+	dev->types[5] = _DRM_STAT_UNLOCKS;
+
+	if (drm_ht_create(&dev->map_hash, 12))
+		goto err_free;
+
+	ret = drm_ctxbitmap_init(dev);
+	if (ret) {
+		DRM_ERROR("Cannot allocate memory for context bitmap.\n");
+		goto err_ht;
+	}
+
+	if (driver->driver_features & DRIVER_GEM) {
+		ret = drm_gem_init(dev);
+		if (ret) {
+			DRM_ERROR("Cannot initialize graphics execution manager (GEM)\n");
+			goto err_ctxbitmap;
+		}
+	}
+
+	return dev;
+
+err_ctxbitmap:
+	drm_ctxbitmap_cleanup(dev);
+err_ht:
+	drm_ht_remove(&dev->map_hash);
+err_free:
+	kfree(dev);
+	return NULL;
+}
+EXPORT_SYMBOL(drm_dev_alloc);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index 87664723b9ce..34ad8edfe806 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -7,18 +7,15 @@ int drm_get_usb_dev(struct usb_interface *interface,
 		    struct drm_driver *driver)
 {
 	struct drm_device *dev;
-	struct usb_device *usbdev;
 	int ret;
 
 	DRM_DEBUG("\n");
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	dev = drm_dev_alloc(driver, &interface->dev);
 	if (!dev)
 		return -ENOMEM;
 
-	usbdev = interface_to_usbdev(interface);
-	dev->usbdev = usbdev;
-	dev->dev = &interface->dev;
+	dev->usbdev = interface_to_usbdev(interface);
 
 	mutex_lock(&drm_global_mutex);
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 69dd5fd5b215..ea545b5ad467 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1643,6 +1643,8 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map)
 extern int drm_fill_in_dev(struct drm_device *dev,
 			   const struct pci_device_id *ent,
 			   struct drm_driver *driver);
+struct drm_device *drm_dev_alloc(struct drm_driver *driver,
+				 struct device *parent);
 int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type);
 /*@}*/
 
-- 
cgit 


From c22f0ace1926da399d9a16dfaf09174c1b03594c Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 2 Oct 2013 11:23:35 +0200
Subject: drm: merge device setup into drm_dev_register()

All bus drivers do device setup themselves. This requires us to adjust all
of them if we introduce new core features. Thus, merge all these into a
uniform drm_dev_register() helper.

Note that this removes the drm_lastclose() error path for AGP as it is
horribly broken. Moreover, no bus driver called this in any other error
path either. Instead, we use the recently introduced AGP cleanup helpers.

We also keep a DRIVER_MODESET condition around pci_set_drvdata() to keep
semantics.

[airlied: keep passing flags through so drivers don't oops on load]

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_pci.c      |  56 +++--------------------
 drivers/gpu/drm/drm_platform.c |  54 ++--------------------
 drivers/gpu/drm/drm_stub.c     | 101 +++++++++++++++++++++++++++++++++--------
 drivers/gpu/drm/drm_usb.c      |  48 ++------------------
 include/drm/drmP.h             |   4 +-
 5 files changed, 96 insertions(+), 167 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index d2758be37a93..743589dc47ce 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -328,7 +328,7 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 
 	ret = pci_enable_device(pdev);
 	if (ret)
-		goto err_g1;
+		goto err_free;
 
 	dev->pdev = pdev;
 	dev->pci_device = pdev->device;
@@ -338,65 +338,23 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 	dev->hose = pdev->sysdata;
 #endif
 
-	mutex_lock(&drm_global_mutex);
-
-	if ((ret = drm_fill_in_dev(dev, ent, driver))) {
-		printk(KERN_ERR "DRM: Fill_in_dev failed.\n");
-		goto err_g2;
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		pci_set_drvdata(pdev, dev);
-		ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL);
-		if (ret)
-			goto err_g2;
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
-		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
-		if (ret)
-			goto err_g21;
-	}
 
-	if ((ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY)))
-		goto err_g3;
-
-	if (dev->driver->load) {
-		ret = dev->driver->load(dev, ent->driver_data);
-		if (ret)
-			goto err_g4;
-	}
-
-	/* setup the grouping for the legacy output */
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		ret = drm_mode_group_init_legacy_group(dev,
-						&dev->primary->mode_group);
-		if (ret)
-			goto err_g4;
-	}
-
-	list_add_tail(&dev->driver_item, &driver->device_list);
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_pci;
 
 	DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n",
 		 driver->name, driver->major, driver->minor, driver->patchlevel,
 		 driver->date, pci_name(pdev), dev->primary->index);
 
-	mutex_unlock(&drm_global_mutex);
 	return 0;
 
-err_g4:
-	drm_put_minor(&dev->primary);
-err_g3:
-	if (dev->render)
-		drm_put_minor(&dev->render);
-err_g21:
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_put_minor(&dev->control);
-err_g2:
+err_pci:
 	pci_disable_device(pdev);
-err_g1:
+err_free:
 	kfree(dev);
-	mutex_unlock(&drm_global_mutex);
 	return ret;
 }
 EXPORT_SYMBOL(drm_get_pci_dev);
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index fb2721738a8a..a0f91f85651f 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -53,48 +53,9 @@ static int drm_get_platform_dev(struct platform_device *platdev,
 
 	dev->platformdev = platdev;
 
-	mutex_lock(&drm_global_mutex);
-
-	ret = drm_fill_in_dev(dev, NULL, driver);
-
-	if (ret) {
-		printk(KERN_ERR "DRM: Fill_in_dev failed.\n");
-		goto err_g1;
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL);
-		if (ret)
-			goto err_g1;
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
-		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
-		if (ret)
-			goto err_g11;
-	}
-
-	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
+	ret = drm_dev_register(dev, 0);
 	if (ret)
-		goto err_g2;
-
-	if (dev->driver->load) {
-		ret = dev->driver->load(dev, 0);
-		if (ret)
-			goto err_g3;
-	}
-
-	/* setup the grouping for the legacy output */
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		ret = drm_mode_group_init_legacy_group(dev,
-				&dev->primary->mode_group);
-		if (ret)
-			goto err_g3;
-	}
-
-	list_add_tail(&dev->driver_item, &driver->device_list);
-
-	mutex_unlock(&drm_global_mutex);
+		goto err_free;
 
 	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
 		 driver->name, driver->major, driver->minor, driver->patchlevel,
@@ -102,17 +63,8 @@ static int drm_get_platform_dev(struct platform_device *platdev,
 
 	return 0;
 
-err_g3:
-	drm_put_minor(&dev->primary);
-err_g2:
-	if (dev->render)
-		drm_put_minor(&dev->render);
-err_g11:
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_put_minor(&dev->control);
-err_g1:
+err_free:
 	kfree(dev);
-	mutex_unlock(&drm_global_mutex);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 64bd52f13199..432994aafc3b 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -254,25 +254,6 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-int drm_fill_in_dev(struct drm_device *dev,
-			   const struct pci_device_id *ent,
-			   struct drm_driver *driver)
-{
-	int retcode;
-
-	if (dev->driver->bus->agp_init) {
-		retcode = dev->driver->bus->agp_init(dev);
-		if (retcode) {
-			drm_lastclose(dev);
-			return retcode;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(drm_fill_in_dev);
-
-
 /**
  * Get a secondary minor number.
  *
@@ -452,6 +433,8 @@ EXPORT_SYMBOL(drm_unplug_dev);
  * @parent: Parent device object
  *
  * Allocate and initialize a new DRM device. No device registration is done.
+ * Call drm_dev_register() to advertice the device to user space and register it
+ * with other core subsystems.
  *
  * RETURNS:
  * Pointer to new DRM device, or NULL if out of memory.
@@ -517,3 +500,83 @@ err_free:
 	return NULL;
 }
 EXPORT_SYMBOL(drm_dev_alloc);
+
+/**
+ * drm_dev_register - Register DRM device
+ * @dev: Device to register
+ *
+ * Register the DRM device @dev with the system, advertise device to user-space
+ * and start normal device operation. @dev must be allocated via drm_dev_alloc()
+ * previously.
+ *
+ * Never call this twice on any device!
+ *
+ * RETURNS:
+ * 0 on success, negative error code on failure.
+ */
+int drm_dev_register(struct drm_device *dev, unsigned long flags)
+{
+	int ret;
+
+	mutex_lock(&drm_global_mutex);
+
+	if (dev->driver->bus->agp_init) {
+		ret = dev->driver->bus->agp_init(dev);
+		if (ret)
+			goto out_unlock;
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL);
+		if (ret)
+			goto err_agp;
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
+		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
+		if (ret)
+			goto err_control_node;
+	}
+
+	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
+	if (ret)
+		goto err_render_node;
+
+	if (dev->driver->load) {
+		ret = dev->driver->load(dev, flags);
+		if (ret)
+			goto err_primary_node;
+	}
+
+	/* setup grouping for legacy outputs */
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		ret = drm_mode_group_init_legacy_group(dev,
+				&dev->primary->mode_group);
+		if (ret)
+			goto err_unload;
+	}
+
+	list_add_tail(&dev->driver_item, &dev->driver->device_list);
+
+	ret = 0;
+	goto out_unlock;
+
+err_unload:
+	if (dev->driver->unload)
+		dev->driver->unload(dev);
+err_primary_node:
+	drm_put_minor(&dev->primary);
+err_render_node:
+	if (dev->render)
+		drm_put_minor(&dev->render);
+err_control_node:
+	if (dev->control)
+		drm_put_minor(&dev->control);
+err_agp:
+	if (dev->driver->bus->agp_destroy)
+		dev->driver->bus->agp_destroy(dev);
+out_unlock:
+	mutex_unlock(&drm_global_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(drm_dev_register);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index 34ad8edfe806..5ef353f77b5a 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -16,45 +16,11 @@ int drm_get_usb_dev(struct usb_interface *interface,
 		return -ENOMEM;
 
 	dev->usbdev = interface_to_usbdev(interface);
-
-	mutex_lock(&drm_global_mutex);
-
-	ret = drm_fill_in_dev(dev, NULL, driver);
-	if (ret) {
-		printk(KERN_ERR "DRM: Fill_in_dev failed.\n");
-		goto err_g1;
-	}
-
 	usb_set_intfdata(interface, dev);
-	ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL);
-	if (ret)
-		goto err_g1;
-
-	if (drm_core_check_feature(dev, DRIVER_RENDER) && drm_rnodes) {
-		ret = drm_get_minor(dev, &dev->render, DRM_MINOR_RENDER);
-		if (ret)
-			goto err_g11;
-	}
 
-	ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY);
+	ret = drm_dev_register(dev, 0);
 	if (ret)
-		goto err_g2;
-
-	if (dev->driver->load) {
-		ret = dev->driver->load(dev, 0);
-		if (ret)
-			goto err_g3;
-	}
-
-	/* setup the grouping for the legacy output */
-	ret = drm_mode_group_init_legacy_group(dev,
-					       &dev->primary->mode_group);
-	if (ret)
-		goto err_g3;
-
-	list_add_tail(&dev->driver_item, &driver->device_list);
-
-	mutex_unlock(&drm_global_mutex);
+		goto err_free;
 
 	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
 		 driver->name, driver->major, driver->minor, driver->patchlevel,
@@ -62,16 +28,8 @@ int drm_get_usb_dev(struct usb_interface *interface,
 
 	return 0;
 
-err_g3:
-	drm_put_minor(&dev->primary);
-err_g2:
-	if (dev->render)
-		drm_put_minor(&dev->render);
-err_g11:
-	drm_put_minor(&dev->control);
-err_g1:
+err_free:
 	kfree(dev);
-	mutex_unlock(&drm_global_mutex);
 	return ret;
 
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index ea545b5ad467..1973f7966511 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1640,11 +1640,9 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map)
 
 #include <drm/drm_mem_util.h>
 
-extern int drm_fill_in_dev(struct drm_device *dev,
-			   const struct pci_device_id *ent,
-			   struct drm_driver *driver);
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
+int drm_dev_register(struct drm_device *dev, unsigned long flags);
 int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type);
 /*@}*/
 
-- 
cgit 


From 0dc8fe5985e01f238e7dc64ff1733cc0291811e8 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 2 Oct 2013 11:23:37 +0200
Subject: drm: introduce drm_dev_free() to fix error paths

The error paths in DRM bus drivers currently leak memory as they don't
correctly revert drm_dev_alloc(). Introduce drm_dev_free() to free DRM
devices which haven't been registered, yet.

We must be careful not to introduce any side-effects with cleanups done in
drm_dev_free(). drm_ht_remove(), drm_ctxbitmap_cleanup() and
drm_gem_destroy() are all fine in that regard.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_pci.c      |  2 +-
 drivers/gpu/drm/drm_platform.c |  2 +-
 drivers/gpu/drm/drm_stub.c     | 35 +++++++++++++++++++++++++----------
 drivers/gpu/drm/drm_usb.c      |  2 +-
 include/drm/drmP.h             |  1 +
 5 files changed, 29 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 743589dc47ce..cabe2bd702ae 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -354,7 +354,7 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	kfree(dev);
+	drm_dev_free(dev);
 	return ret;
 }
 EXPORT_SYMBOL(drm_get_pci_dev);
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index a0f91f85651f..fc24fee8ec83 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -64,7 +64,7 @@ static int drm_get_platform_dev(struct platform_device *platdev,
 	return 0;
 
 err_free:
-	kfree(dev);
+	drm_dev_free(dev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 432994aafc3b..3b5b07482de8 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -363,7 +363,6 @@ static void drm_unplug_minor(struct drm_minor *minor)
  */
 void drm_put_dev(struct drm_device *dev)
 {
-	struct drm_driver *driver;
 	struct drm_map_list *r_list, *list_temp;
 
 	DRM_DEBUG("\n");
@@ -372,7 +371,6 @@ void drm_put_dev(struct drm_device *dev)
 		DRM_ERROR("cleanup called no dev\n");
 		return;
 	}
-	driver = dev->driver;
 
 	drm_lastclose(dev);
 
@@ -386,9 +384,6 @@ void drm_put_dev(struct drm_device *dev)
 
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
 		drm_rmmap(dev, r_list->map);
-	drm_ht_remove(&dev->map_hash);
-
-	drm_ctxbitmap_cleanup(dev);
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_put_minor(&dev->control);
@@ -396,14 +391,11 @@ void drm_put_dev(struct drm_device *dev)
 	if (dev->render)
 		drm_put_minor(&dev->render);
 
-	if (driver->driver_features & DRIVER_GEM)
-		drm_gem_destroy(dev);
-
 	drm_put_minor(&dev->primary);
 
 	list_del(&dev->driver_item);
-	kfree(dev->devname);
-	kfree(dev);
+
+	drm_dev_free(dev);
 }
 EXPORT_SYMBOL(drm_put_dev);
 
@@ -501,6 +493,29 @@ err_free:
 }
 EXPORT_SYMBOL(drm_dev_alloc);
 
+/**
+ * drm_dev_free - Free DRM device
+ * @dev: DRM device to free
+ *
+ * Free a DRM device that has previously been allocated via drm_dev_alloc().
+ * You must not use kfree() instead or you will leak memory.
+ *
+ * This must not be called once the device got registered. Use drm_put_dev()
+ * instead, which then calls drm_dev_free().
+ */
+void drm_dev_free(struct drm_device *dev)
+{
+	if (dev->driver->driver_features & DRIVER_GEM)
+		drm_gem_destroy(dev);
+
+	drm_ctxbitmap_cleanup(dev);
+	drm_ht_remove(&dev->map_hash);
+
+	kfree(dev->devname);
+	kfree(dev);
+}
+EXPORT_SYMBOL(drm_dev_free);
+
 /**
  * drm_dev_register - Register DRM device
  * @dev: Device to register
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index 5ef353f77b5a..b179b70e7853 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -29,7 +29,7 @@ int drm_get_usb_dev(struct usb_interface *interface,
 	return 0;
 
 err_free:
-	kfree(dev);
+	drm_dev_free(dev);
 	return ret;
 
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 1973f7966511..537833c9ab83 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1642,6 +1642,7 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map)
 
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
+void drm_dev_free(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
 int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type);
 /*@}*/
-- 
cgit 


From c3a49737ef7db0bdd4fcf6cf0b7140a883e32b2a Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Wed, 2 Oct 2013 11:23:38 +0200
Subject: drm: move device unregistration into drm_dev_unregister()

Analog to drm_dev_register(), we now provide drm_dev_unregister() which
does the reverse. drm_dev_put() is still in place and combines the calls
to drm_dev_unregister() and drm_dev_free() so buses don't have to change.

*_get() and *_put() are used for reference-counting in the kernel.
However, drm_dev_put() definitely does not do any kind of ref-counting.
Hence, use the more appropriate *_register(), *_unregister(), *_alloc()
and *_free() names.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_stub.c | 61 +++++++++++++++++++++++++++-------------------
 include/drm/drmP.h         |  1 +
 2 files changed, 37 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 3b5b07482de8..2badef766d20 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -363,8 +363,6 @@ static void drm_unplug_minor(struct drm_minor *minor)
  */
 void drm_put_dev(struct drm_device *dev)
 {
-	struct drm_map_list *r_list, *list_temp;
-
 	DRM_DEBUG("\n");
 
 	if (!dev) {
@@ -372,29 +370,7 @@ void drm_put_dev(struct drm_device *dev)
 		return;
 	}
 
-	drm_lastclose(dev);
-
-	if (dev->driver->unload)
-		dev->driver->unload(dev);
-
-	if (dev->driver->bus->agp_destroy)
-		dev->driver->bus->agp_destroy(dev);
-
-	drm_vblank_cleanup(dev);
-
-	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
-		drm_rmmap(dev, r_list->map);
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_put_minor(&dev->control);
-
-	if (dev->render)
-		drm_put_minor(&dev->render);
-
-	drm_put_minor(&dev->primary);
-
-	list_del(&dev->driver_item);
-
+	drm_dev_unregister(dev);
 	drm_dev_free(dev);
 }
 EXPORT_SYMBOL(drm_put_dev);
@@ -595,3 +571,38 @@ out_unlock:
 	return ret;
 }
 EXPORT_SYMBOL(drm_dev_register);
+
+/**
+ * drm_dev_unregister - Unregister DRM device
+ * @dev: Device to unregister
+ *
+ * Unregister the DRM device from the system. This does the reverse of
+ * drm_dev_register() but does not deallocate the device. The caller must call
+ * drm_dev_free() to free all resources.
+ */
+void drm_dev_unregister(struct drm_device *dev)
+{
+	struct drm_map_list *r_list, *list_temp;
+
+	drm_lastclose(dev);
+
+	if (dev->driver->unload)
+		dev->driver->unload(dev);
+
+	if (dev->driver->bus->agp_destroy)
+		dev->driver->bus->agp_destroy(dev);
+
+	drm_vblank_cleanup(dev);
+
+	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
+		drm_rmmap(dev, r_list->map);
+
+	if (dev->control)
+		drm_put_minor(&dev->control);
+	if (dev->render)
+		drm_put_minor(&dev->render);
+	drm_put_minor(&dev->primary);
+
+	list_del(&dev->driver_item);
+}
+EXPORT_SYMBOL(drm_dev_unregister);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 537833c9ab83..2b9b033efea4 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1644,6 +1644,7 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
 void drm_dev_free(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
+void drm_dev_unregister(struct drm_device *dev);
 int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type);
 /*@}*/
 
-- 
cgit 


From ba0bf1200ec75722c558c56f58c596ff42a3b494 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:33 +0300
Subject: drm: Make vblank_disable_allowed bool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vblank_disable_allowed is only ever 0 or 1, so make it a bool.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c                | 5 +++--
 drivers/gpu/drm/exynos/exynos_drm_fimd.c | 4 ++--
 drivers/gpu/drm/exynos/exynos_drm_vidi.c | 4 ++--
 drivers/gpu/drm/gma500/psb_drv.c         | 2 +-
 drivers/gpu/drm/i915/i915_dma.c          | 2 +-
 drivers/staging/imx-drm/imx-drm-core.c   | 4 ++--
 include/drm/drmP.h                       | 2 +-
 7 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index f92da0a32f0d..81b4c84449a4 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -271,7 +271,8 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 		atomic_set(&dev->vblank_refcount[i], 0);
 	}
 
-	dev->vblank_disable_allowed = 0;
+	dev->vblank_disable_allowed = false;
+
 	return 0;
 
 err:
@@ -1085,7 +1086,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, int crtc)
 
 	if (dev->vblank_inmodeset[crtc]) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
-		dev->vblank_disable_allowed = 1;
+		dev->vblank_disable_allowed = true;
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
 		if (dev->vblank_inmodeset[crtc] & 0x2)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 868a14d52995..1648b40700e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -725,11 +725,11 @@ static int fimd_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 	drm_dev->irq_enabled = 1;
 
 	/*
-	 * with vblank_disable_allowed = 1, vblank interrupt will be disabled
+	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
 	 * by drm timer once a current process gives up ownership of
 	 * vblank event.(after drm_vblank_put function is called)
 	 */
-	drm_dev->vblank_disable_allowed = 1;
+	drm_dev->vblank_disable_allowed = true;
 
 	/* attach this sub driver to iommu mapping if supported. */
 	if (is_drm_iommu_supported(drm_dev))
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 26e089f4ff1c..347aa40a94f5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -392,11 +392,11 @@ static int vidi_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 	drm_dev->irq_enabled = 1;
 
 	/*
-	 * with vblank_disable_allowed = 1, vblank interrupt will be disabled
+	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
 	 * by drm timer once a current process gives up ownership of
 	 * vblank event.(after drm_vblank_put function is called)
 	 */
-	drm_dev->vblank_disable_allowed = 1;
+	drm_dev->vblank_disable_allowed = true;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 30dceb43690b..dd607f820a26 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -359,7 +359,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	drm_irq_install(dev);
 
-	dev->vblank_disable_allowed = 1;
+	dev->vblank_disable_allowed = true;
 
 	dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 512645fdaff5..93cbacba26a2 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1330,7 +1330,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
-	dev->vblank_disable_allowed = 1;
+	dev->vblank_disable_allowed = true;
 	if (INTEL_INFO(dev)->num_pipes == 0)
 		return 0;
 
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index a2e52a0c53c9..52c29b3afa28 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -423,11 +423,11 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 		goto err_init;
 
 	/*
-	 * with vblank_disable_allowed = 1, vblank interrupt will be disabled
+	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
 	 * by drm timer once a current process gives up ownership of
 	 * vblank event.(after drm_vblank_put function is called)
 	 */
-	imxdrm->drm->vblank_disable_allowed = 1;
+	imxdrm->drm->vblank_disable_allowed = true;
 
 	if (!imx_drm_device_get())
 		ret = -EINVAL;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2b9b033efea4..06cb8f785d0e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1151,7 +1151,7 @@ struct drm_device {
 	 * Once the modeset ioctl *has* been called though, we can safely
 	 * disable them when unused.
 	 */
-	int vblank_disable_allowed;
+	bool vblank_disable_allowed;
 
 	wait_queue_head_t *vbl_queue;   /**< VBLANK wait queue */
 	atomic_t *_vblank_count;        /**< number of VBLANK interrupts (driver must alloc the right number of counters) */
-- 
cgit 


From 54edf9aec79779f85d49674580b7ccab4d6f3c4a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:34 +0300
Subject: drm: Make vblank_inmodeset unsigned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vblank_inmodeset is a bitmask, with only two bits mind you, but better
make it unsigned anyway.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 06cb8f785d0e..e73809b380f8 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1163,7 +1163,7 @@ struct drm_device {
 					/* for wraparound handling */
 	int *vblank_enabled;            /* so we don't call enable more than
 					   once per disable */
-	int *vblank_inmodeset;          /* Display driver is setting mode */
+	unsigned int *vblank_inmodeset; /* Display driver is setting mode */
 	u32 *last_vblank_wait;		/* Last vblank seqno waited per CRTC */
 	struct timer_list vblank_disable_timer;
 
-- 
cgit 


From bf507d90cf0eecf5495f66f21dbb66e35e9131ae Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:35 +0300
Subject: drm: Make vblank_enabled bool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

vblank_enabled is only ever 0 or 1, so make it a bool.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c          | 8 ++++----
 drivers/gpu/drm/omapdrm/omap_irq.c | 2 +-
 include/drm/drmP.h                 | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 81b4c84449a4..49680a8ab96a 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -115,7 +115,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
 
 	dev->driver->disable_vblank(dev, crtc);
-	dev->vblank_enabled[crtc] = 0;
+	dev->vblank_enabled[crtc] = false;
 
 	/* No further vblank irq's will be processed after
 	 * this point. Get current hardware vblank count and
@@ -235,7 +235,7 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 	if (!dev->vblank_refcount)
 		goto err;
 
-	dev->vblank_enabled = kcalloc(num_crtcs, sizeof(int), GFP_KERNEL);
+	dev->vblank_enabled = kcalloc(num_crtcs, sizeof(bool), GFP_KERNEL);
 	if (!dev->vblank_enabled)
 		goto err;
 
@@ -412,7 +412,7 @@ int drm_irq_uninstall(struct drm_device *dev)
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		for (i = 0; i < dev->num_crtcs; i++) {
 			DRM_WAKEUP(&dev->vbl_queue[i]);
-			dev->vblank_enabled[i] = 0;
+			dev->vblank_enabled[i] = false;
 			dev->last_vblank[i] =
 				dev->driver->get_vblank_counter(dev, i);
 		}
@@ -973,7 +973,7 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 			if (ret)
 				atomic_dec(&dev->vblank_refcount[crtc]);
 			else {
-				dev->vblank_enabled[crtc] = 1;
+				dev->vblank_enabled[crtc] = true;
 				drm_update_vblank_count(dev, crtc);
 			}
 		}
diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c
index 9263db117ff8..3cbe92c72fd5 100644
--- a/drivers/gpu/drm/omapdrm/omap_irq.c
+++ b/drivers/gpu/drm/omapdrm/omap_irq.c
@@ -308,7 +308,7 @@ int omap_drm_irq_uninstall(struct drm_device *dev)
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		for (i = 0; i < dev->num_crtcs; i++) {
 			DRM_WAKEUP(&dev->vbl_queue[i]);
-			dev->vblank_enabled[i] = 0;
+			dev->vblank_enabled[i] = false;
 			dev->last_vblank[i] =
 				dev->driver->get_vblank_counter(dev, i);
 		}
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index e73809b380f8..2d390abbf550 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1161,7 +1161,7 @@ struct drm_device {
 	atomic_t *vblank_refcount;      /* number of users of vblank interruptsper crtc */
 	u32 *last_vblank;               /* protected by dev->vbl_lock, used */
 					/* for wraparound handling */
-	int *vblank_enabled;            /* so we don't call enable more than
+	bool *vblank_enabled;           /* so we don't call enable more than
 					   once per disable */
 	unsigned int *vblank_inmodeset; /* Display driver is setting mode */
 	u32 *last_vblank_wait;		/* Last vblank seqno waited per CRTC */
-- 
cgit 


From 5380e9293b865d88de04de6e5324726d8c5b53c9 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:36 +0300
Subject: drm: Collect per-crtc vblank stuff to a struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drm_vblank_init() is too ugly. Make it a bit easier on the eye by
collecting all the per-crtc vblank counters, timestamps etc. to
a structure and just allocate an array of those.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_info.c         |   6 +-
 drivers/gpu/drm/drm_irq.c          | 138 +++++++++++++------------------------
 drivers/gpu/drm/gma500/psb_irq.c   |  22 +++---
 drivers/gpu/drm/i915/intel_pm.c    |   2 +-
 drivers/gpu/drm/omapdrm/omap_irq.c |   6 +-
 include/drm/drmP.h                 |  26 ++++---
 6 files changed, 81 insertions(+), 119 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 53298320080b..7d5a152eeb02 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -163,13 +163,13 @@ int drm_vblank_info(struct seq_file *m, void *data)
 	mutex_lock(&dev->struct_mutex);
 	for (crtc = 0; crtc < dev->num_crtcs; crtc++) {
 		seq_printf(m, "CRTC %d enable:     %d\n",
-			   crtc, atomic_read(&dev->vblank_refcount[crtc]));
+			   crtc, atomic_read(&dev->vblank[crtc].refcount));
 		seq_printf(m, "CRTC %d counter:    %d\n",
 			   crtc, drm_vblank_count(dev, crtc));
 		seq_printf(m, "CRTC %d last wait:  %d\n",
-			   crtc, dev->last_vblank_wait[crtc]);
+			   crtc, dev->vblank[crtc].last_wait);
 		seq_printf(m, "CRTC %d in modeset: %d\n",
-			   crtc, dev->vblank_inmodeset[crtc]);
+			   crtc, dev->vblank[crtc].inmodeset);
 	}
 	mutex_unlock(&dev->struct_mutex);
 	return 0;
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 49680a8ab96a..dea859f20035 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -43,9 +43,8 @@
 #include <linux/export.h>
 
 /* Access macro for slots in vblank timestamp ringbuffer. */
-#define vblanktimestamp(dev, crtc, count) ( \
-	(dev)->_vblank_time[(crtc) * DRM_VBLANKTIME_RBSIZE + \
-	((count) % DRM_VBLANKTIME_RBSIZE)])
+#define vblanktimestamp(dev, crtc, count) \
+	((dev)->vblank[crtc].time[(count) % DRM_VBLANKTIME_RBSIZE])
 
 /* Retry timestamp calculation up to 3 times to satisfy
  * drm_timestamp_precision before giving up.
@@ -89,8 +88,7 @@ int drm_irq_by_busid(struct drm_device *dev, void *data,
  */
 static void clear_vblank_timestamps(struct drm_device *dev, int crtc)
 {
-	memset(&dev->_vblank_time[crtc * DRM_VBLANKTIME_RBSIZE], 0,
-		DRM_VBLANKTIME_RBSIZE * sizeof(struct timeval));
+	memset(dev->vblank[crtc].time, 0, sizeof(dev->vblank[crtc].time));
 }
 
 /*
@@ -115,7 +113,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
 
 	dev->driver->disable_vblank(dev, crtc);
-	dev->vblank_enabled[crtc] = false;
+	dev->vblank[crtc].enabled = false;
 
 	/* No further vblank irq's will be processed after
 	 * this point. Get current hardware vblank count and
@@ -130,9 +128,9 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * delayed gpu counter increment.
 	 */
 	do {
-		dev->last_vblank[crtc] = dev->driver->get_vblank_counter(dev, crtc);
+		dev->vblank[crtc].last = dev->driver->get_vblank_counter(dev, crtc);
 		vblrc = drm_get_last_vbltimestamp(dev, crtc, &tvblank, 0);
-	} while (dev->last_vblank[crtc] != dev->driver->get_vblank_counter(dev, crtc) && (--count) && vblrc);
+	} while (dev->vblank[crtc].last != dev->driver->get_vblank_counter(dev, crtc) && (--count) && vblrc);
 
 	if (!count)
 		vblrc = 0;
@@ -140,7 +138,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	/* Compute time difference to stored timestamp of last vblank
 	 * as updated by last invocation of drm_handle_vblank() in vblank irq.
 	 */
-	vblcount = atomic_read(&dev->_vblank_count[crtc]);
+	vblcount = atomic_read(&dev->vblank[crtc].count);
 	diff_ns = timeval_to_ns(&tvblank) -
 		  timeval_to_ns(&vblanktimestamp(dev, crtc, vblcount));
 
@@ -157,7 +155,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * hope for the best.
 	 */
 	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
-		atomic_inc(&dev->_vblank_count[crtc]);
+		atomic_inc(&dev->vblank[crtc].count);
 		smp_mb__after_atomic_inc();
 	}
 
@@ -178,8 +176,8 @@ static void vblank_disable_fn(unsigned long arg)
 
 	for (i = 0; i < dev->num_crtcs; i++) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
-		if (atomic_read(&dev->vblank_refcount[i]) == 0 &&
-		    dev->vblank_enabled[i]) {
+		if (atomic_read(&dev->vblank[i].refcount) == 0 &&
+		    dev->vblank[i].enabled) {
 			DRM_DEBUG("disabling vblank on crtc %d\n", i);
 			vblank_disable_and_save(dev, i);
 		}
@@ -197,14 +195,7 @@ void drm_vblank_cleanup(struct drm_device *dev)
 
 	vblank_disable_fn((unsigned long)dev);
 
-	kfree(dev->vbl_queue);
-	kfree(dev->_vblank_count);
-	kfree(dev->vblank_refcount);
-	kfree(dev->vblank_enabled);
-	kfree(dev->last_vblank);
-	kfree(dev->last_vblank_wait);
-	kfree(dev->vblank_inmodeset);
-	kfree(dev->_vblank_time);
+	kfree(dev->vblank);
 
 	dev->num_crtcs = 0;
 }
@@ -221,40 +212,12 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 
 	dev->num_crtcs = num_crtcs;
 
-	dev->vbl_queue = kmalloc(sizeof(wait_queue_head_t) * num_crtcs,
-				 GFP_KERNEL);
-	if (!dev->vbl_queue)
+	dev->vblank = kcalloc(num_crtcs, sizeof(*dev->vblank), GFP_KERNEL);
+	if (!dev->vblank)
 		goto err;
 
-	dev->_vblank_count = kmalloc(sizeof(atomic_t) * num_crtcs, GFP_KERNEL);
-	if (!dev->_vblank_count)
-		goto err;
-
-	dev->vblank_refcount = kmalloc(sizeof(atomic_t) * num_crtcs,
-				       GFP_KERNEL);
-	if (!dev->vblank_refcount)
-		goto err;
-
-	dev->vblank_enabled = kcalloc(num_crtcs, sizeof(bool), GFP_KERNEL);
-	if (!dev->vblank_enabled)
-		goto err;
-
-	dev->last_vblank = kcalloc(num_crtcs, sizeof(u32), GFP_KERNEL);
-	if (!dev->last_vblank)
-		goto err;
-
-	dev->last_vblank_wait = kcalloc(num_crtcs, sizeof(u32), GFP_KERNEL);
-	if (!dev->last_vblank_wait)
-		goto err;
-
-	dev->vblank_inmodeset = kcalloc(num_crtcs, sizeof(int), GFP_KERNEL);
-	if (!dev->vblank_inmodeset)
-		goto err;
-
-	dev->_vblank_time = kcalloc(num_crtcs * DRM_VBLANKTIME_RBSIZE,
-				    sizeof(struct timeval), GFP_KERNEL);
-	if (!dev->_vblank_time)
-		goto err;
+	for (i = 0; i < num_crtcs; i++)
+		init_waitqueue_head(&dev->vblank[i].queue);
 
 	DRM_INFO("Supports vblank timestamp caching Rev 1 (10.10.2010).\n");
 
@@ -264,13 +227,6 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 	else
 		DRM_INFO("No driver support for vblank timestamp query.\n");
 
-	/* Zero per-crtc vblank stuff */
-	for (i = 0; i < num_crtcs; i++) {
-		init_waitqueue_head(&dev->vbl_queue[i]);
-		atomic_set(&dev->_vblank_count[i], 0);
-		atomic_set(&dev->vblank_refcount[i], 0);
-	}
-
 	dev->vblank_disable_allowed = false;
 
 	return 0;
@@ -411,9 +367,9 @@ int drm_irq_uninstall(struct drm_device *dev)
 	if (dev->num_crtcs) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		for (i = 0; i < dev->num_crtcs; i++) {
-			DRM_WAKEUP(&dev->vbl_queue[i]);
-			dev->vblank_enabled[i] = false;
-			dev->last_vblank[i] =
+			DRM_WAKEUP(&dev->vblank[i].queue);
+			dev->vblank[i].enabled = false;
+			dev->vblank[i].last =
 				dev->driver->get_vblank_counter(dev, i);
 		}
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
@@ -796,7 +752,7 @@ EXPORT_SYMBOL(drm_get_last_vbltimestamp);
  */
 u32 drm_vblank_count(struct drm_device *dev, int crtc)
 {
-	return atomic_read(&dev->_vblank_count[crtc]);
+	return atomic_read(&dev->vblank[crtc].count);
 }
 EXPORT_SYMBOL(drm_vblank_count);
 
@@ -825,10 +781,10 @@ u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 	 * a seqlock.
 	 */
 	do {
-		cur_vblank = atomic_read(&dev->_vblank_count[crtc]);
+		cur_vblank = atomic_read(&dev->vblank[crtc].count);
 		*vblanktime = vblanktimestamp(dev, crtc, cur_vblank);
 		smp_rmb();
-	} while (cur_vblank != atomic_read(&dev->_vblank_count[crtc]));
+	} while (cur_vblank != atomic_read(&dev->vblank[crtc].count));
 
 	return cur_vblank;
 }
@@ -915,12 +871,12 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 	} while (cur_vblank != dev->driver->get_vblank_counter(dev, crtc));
 
 	/* Deal with counter wrap */
-	diff = cur_vblank - dev->last_vblank[crtc];
-	if (cur_vblank < dev->last_vblank[crtc]) {
+	diff = cur_vblank - dev->vblank[crtc].last;
+	if (cur_vblank < dev->vblank[crtc].last) {
 		diff += dev->max_vblank_count;
 
 		DRM_DEBUG("last_vblank[%d]=0x%x, cur_vblank=0x%x => diff=0x%x\n",
-			  crtc, dev->last_vblank[crtc], cur_vblank, diff);
+			  crtc, dev->vblank[crtc].last, cur_vblank, diff);
 	}
 
 	DRM_DEBUG("enabling vblank interrupts on crtc %d, missed %d\n",
@@ -931,12 +887,12 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 	 * reinitialize delayed at next vblank interrupt in that case.
 	 */
 	if (rc) {
-		tslot = atomic_read(&dev->_vblank_count[crtc]) + diff;
+		tslot = atomic_read(&dev->vblank[crtc].count) + diff;
 		vblanktimestamp(dev, crtc, tslot) = t_vblank;
 	}
 
 	smp_mb__before_atomic_inc();
-	atomic_add(diff, &dev->_vblank_count[crtc]);
+	atomic_add(diff, &dev->vblank[crtc].count);
 	smp_mb__after_atomic_inc();
 }
 
@@ -958,9 +914,9 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	/* Going from 0->1 means we have to enable interrupts again */
-	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
+	if (atomic_add_return(1, &dev->vblank[crtc].refcount) == 1) {
 		spin_lock_irqsave(&dev->vblank_time_lock, irqflags2);
-		if (!dev->vblank_enabled[crtc]) {
+		if (!dev->vblank[crtc].enabled) {
 			/* Enable vblank irqs under vblank_time_lock protection.
 			 * All vblank count & timestamp updates are held off
 			 * until we are done reinitializing master counter and
@@ -971,16 +927,16 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 			DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n",
 				  crtc, ret);
 			if (ret)
-				atomic_dec(&dev->vblank_refcount[crtc]);
+				atomic_dec(&dev->vblank[crtc].refcount);
 			else {
-				dev->vblank_enabled[crtc] = true;
+				dev->vblank[crtc].enabled = true;
 				drm_update_vblank_count(dev, crtc);
 			}
 		}
 		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2);
 	} else {
-		if (!dev->vblank_enabled[crtc]) {
-			atomic_dec(&dev->vblank_refcount[crtc]);
+		if (!dev->vblank[crtc].enabled) {
+			atomic_dec(&dev->vblank[crtc].refcount);
 			ret = -EINVAL;
 		}
 	}
@@ -1000,10 +956,10 @@ EXPORT_SYMBOL(drm_vblank_get);
  */
 void drm_vblank_put(struct drm_device *dev, int crtc)
 {
-	BUG_ON(atomic_read(&dev->vblank_refcount[crtc]) == 0);
+	BUG_ON(atomic_read(&dev->vblank[crtc].refcount) == 0);
 
 	/* Last user schedules interrupt disable */
-	if (atomic_dec_and_test(&dev->vblank_refcount[crtc]) &&
+	if (atomic_dec_and_test(&dev->vblank[crtc].refcount) &&
 	    (drm_vblank_offdelay > 0))
 		mod_timer(&dev->vblank_disable_timer,
 			  jiffies + ((drm_vblank_offdelay * DRM_HZ)/1000));
@@ -1026,7 +982,7 @@ void drm_vblank_off(struct drm_device *dev, int crtc)
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	vblank_disable_and_save(dev, crtc);
-	DRM_WAKEUP(&dev->vbl_queue[crtc]);
+	DRM_WAKEUP(&dev->vblank[crtc].queue);
 
 	/* Send any queued vblank events, lest the natives grow disquiet */
 	seq = drm_vblank_count_and_time(dev, crtc, &now);
@@ -1068,10 +1024,10 @@ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc)
 	 * to avoid corrupting the count if multiple, mismatch calls occur),
 	 * so that interrupts remain enabled in the interim.
 	 */
-	if (!dev->vblank_inmodeset[crtc]) {
-		dev->vblank_inmodeset[crtc] = 0x1;
+	if (!dev->vblank[crtc].inmodeset) {
+		dev->vblank[crtc].inmodeset = 0x1;
 		if (drm_vblank_get(dev, crtc) == 0)
-			dev->vblank_inmodeset[crtc] |= 0x2;
+			dev->vblank[crtc].inmodeset |= 0x2;
 	}
 }
 EXPORT_SYMBOL(drm_vblank_pre_modeset);
@@ -1084,15 +1040,15 @@ void drm_vblank_post_modeset(struct drm_device *dev, int crtc)
 	if (!dev->num_crtcs)
 		return;
 
-	if (dev->vblank_inmodeset[crtc]) {
+	if (dev->vblank[crtc].inmodeset) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		dev->vblank_disable_allowed = true;
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
-		if (dev->vblank_inmodeset[crtc] & 0x2)
+		if (dev->vblank[crtc].inmodeset & 0x2)
 			drm_vblank_put(dev, crtc);
 
-		dev->vblank_inmodeset[crtc] = 0;
+		dev->vblank[crtc].inmodeset = 0;
 	}
 }
 EXPORT_SYMBOL(drm_vblank_post_modeset);
@@ -1289,8 +1245,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 
 	DRM_DEBUG("waiting on vblank count %d, crtc %d\n",
 		  vblwait->request.sequence, crtc);
-	dev->last_vblank_wait[crtc] = vblwait->request.sequence;
-	DRM_WAIT_ON(ret, dev->vbl_queue[crtc], 3 * DRM_HZ,
+	dev->vblank[crtc].last_wait = vblwait->request.sequence;
+	DRM_WAIT_ON(ret, dev->vblank[crtc].queue, 3 * DRM_HZ,
 		    (((drm_vblank_count(dev, crtc) -
 		       vblwait->request.sequence) <= (1 << 23)) ||
 		     !dev->irq_enabled));
@@ -1368,7 +1324,7 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
 
 	/* Vblank irq handling disabled. Nothing to do. */
-	if (!dev->vblank_enabled[crtc]) {
+	if (!dev->vblank[crtc].enabled) {
 		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
 		return false;
 	}
@@ -1378,7 +1334,7 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	 */
 
 	/* Get current timestamp and count. */
-	vblcount = atomic_read(&dev->_vblank_count[crtc]);
+	vblcount = atomic_read(&dev->vblank[crtc].count);
 	drm_get_last_vbltimestamp(dev, crtc, &tvblank, DRM_CALLED_FROM_VBLIRQ);
 
 	/* Compute time difference to timestamp of last vblank */
@@ -1402,14 +1358,14 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 		 * the timestamp computed above.
 		 */
 		smp_mb__before_atomic_inc();
-		atomic_inc(&dev->_vblank_count[crtc]);
+		atomic_inc(&dev->vblank[crtc].count);
 		smp_mb__after_atomic_inc();
 	} else {
 		DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
 			  crtc, (int) diff_ns);
 	}
 
-	DRM_WAKEUP(&dev->vbl_queue[crtc]);
+	DRM_WAKEUP(&dev->vblank[crtc].queue);
 	drm_handle_vblank_events(dev, crtc);
 
 	spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index 029eccf30137..ba4830342d34 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -271,15 +271,15 @@ void psb_irq_preinstall(struct drm_device *dev)
 
 	if (gma_power_is_on(dev))
 		PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
-	if (dev->vblank_enabled[0])
+	if (dev->vblank[0].enabled)
 		dev_priv->vdc_irq_mask |= _PSB_VSYNC_PIPEA_FLAG;
-	if (dev->vblank_enabled[1])
+	if (dev->vblank[1].enabled)
 		dev_priv->vdc_irq_mask |= _PSB_VSYNC_PIPEB_FLAG;
 
 	/* FIXME: Handle Medfield irq mask
-	if (dev->vblank_enabled[1])
+	if (dev->vblank[1].enabled)
 		dev_priv->vdc_irq_mask |= _MDFLD_PIPEB_EVENT_FLAG;
-	if (dev->vblank_enabled[2])
+	if (dev->vblank[2].enabled)
 		dev_priv->vdc_irq_mask |= _MDFLD_PIPEC_EVENT_FLAG;
 	*/
 
@@ -305,17 +305,17 @@ int psb_irq_postinstall(struct drm_device *dev)
 	PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank_enabled[0])
+	if (dev->vblank[0].enabled)
 		psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
 	else
 		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
 
-	if (dev->vblank_enabled[1])
+	if (dev->vblank[1].enabled)
 		psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
 	else
 		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
 
-	if (dev->vblank_enabled[2])
+	if (dev->vblank[2].enabled)
 		psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
 	else
 		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
@@ -339,13 +339,13 @@ void psb_irq_uninstall(struct drm_device *dev)
 
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank_enabled[0])
+	if (dev->vblank[0].enabled)
 		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
 
-	if (dev->vblank_enabled[1])
+	if (dev->vblank[1].enabled)
 		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
 
-	if (dev->vblank_enabled[2])
+	if (dev->vblank[2].enabled)
 		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
 
 	dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
@@ -456,7 +456,7 @@ static int psb_vblank_do_wait(struct drm_device *dev,
 {
 	unsigned int cur_vblank;
 	int ret = 0;
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
+	DRM_WAIT_ON(ret, dev->vblank.queue, 3 * DRM_HZ,
 		    (((cur_vblank = atomic_read(counter))
 		      - *sequence) <= (1 << 23)));
 	*sequence = cur_vblank;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4692f8cb7724..3907c60a72de 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5340,7 +5340,7 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable)
 			spin_lock_irqsave(&dev->vbl_lock, irqflags);
 			for_each_pipe(p)
 				if (p != PIPE_A)
-					dev->last_vblank[p] = 0;
+					dev->vblank[p].last = 0;
 			spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 		}
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c
index 3cbe92c72fd5..261b227e4692 100644
--- a/drivers/gpu/drm/omapdrm/omap_irq.c
+++ b/drivers/gpu/drm/omapdrm/omap_irq.c
@@ -307,9 +307,9 @@ int omap_drm_irq_uninstall(struct drm_device *dev)
 	if (dev->num_crtcs) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		for (i = 0; i < dev->num_crtcs; i++) {
-			DRM_WAKEUP(&dev->vbl_queue[i]);
-			dev->vblank_enabled[i] = false;
-			dev->last_vblank[i] =
+			DRM_WAKEUP(&dev->vblank[i].queue);
+			dev->vblank[i].enabled = false;
+			dev->vblank[i].last =
 				dev->driver->get_vblank_counter(dev, i);
 		}
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2d390abbf550..7198febd9d8e 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1078,6 +1078,19 @@ struct drm_pending_vblank_event {
 	struct drm_event_vblank event;
 };
 
+struct drm_vblank_crtc {
+	wait_queue_head_t queue;	/**< VBLANK wait queue */
+	struct timeval time[DRM_VBLANKTIME_RBSIZE];	/**< timestamp of current count */
+	atomic_t count;			/**< number of VBLANK interrupts */
+	atomic_t refcount;		/* number of users of vblank interruptsper crtc */
+	u32 last;			/* protected by dev->vbl_lock, used */
+					/* for wraparound handling */
+	u32 last_wait;			/* Last vblank seqno waited per CRTC */
+	unsigned int inmodeset;		/* Display driver is setting mode */
+	bool enabled;			/* so we don't call enable more than
+					   once per disable */
+};
+
 /**
  * DRM device structure. This structure represent a complete card that
  * may contain multiple heads.
@@ -1153,18 +1166,11 @@ struct drm_device {
 	 */
 	bool vblank_disable_allowed;
 
-	wait_queue_head_t *vbl_queue;   /**< VBLANK wait queue */
-	atomic_t *_vblank_count;        /**< number of VBLANK interrupts (driver must alloc the right number of counters) */
-	struct timeval *_vblank_time;   /**< timestamp of current vblank_count (drivers must alloc right number of fields) */
+	/* array of size num_crtcs */
+	struct drm_vblank_crtc *vblank;
+
 	spinlock_t vblank_time_lock;    /**< Protects vblank count and time updates during vblank enable/disable */
 	spinlock_t vbl_lock;
-	atomic_t *vblank_refcount;      /* number of users of vblank interruptsper crtc */
-	u32 *last_vblank;               /* protected by dev->vbl_lock, used */
-					/* for wraparound handling */
-	bool *vblank_enabled;           /* so we don't call enable more than
-					   once per disable */
-	unsigned int *vblank_inmodeset; /* Display driver is setting mode */
-	u32 *last_vblank_wait;		/* Last vblank seqno waited per CRTC */
 	struct timer_list vblank_disable_timer;
 
 	u32 max_vblank_count;           /**< size of vblank counter register */
-- 
cgit 


From 4423843cde65232c1d553df220e1d133f4a0fa2b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:37 +0300
Subject: drm: Make irq_enabled bool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

irq_enabled is only ever 0 or 1, so make it a bool.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c                | 11 ++++++-----
 drivers/gpu/drm/exynos/exynos_drm_fimd.c |  4 ++--
 drivers/gpu/drm/exynos/exynos_drm_vidi.c |  4 ++--
 drivers/gpu/drm/mga/mga_irq.c            |  2 +-
 drivers/gpu/drm/omapdrm/omap_irq.c       | 11 ++++++-----
 drivers/gpu/host1x/drm/drm.c             |  2 +-
 drivers/staging/imx-drm/imx-drm-core.c   |  4 ++--
 include/drm/drmP.h                       |  2 +-
 8 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index dea859f20035..f9af048828ea 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -293,7 +293,7 @@ int drm_irq_install(struct drm_device *dev)
 		mutex_unlock(&dev->struct_mutex);
 		return -EBUSY;
 	}
-	dev->irq_enabled = 1;
+	dev->irq_enabled = true;
 	mutex_unlock(&dev->struct_mutex);
 
 	DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev));
@@ -316,7 +316,7 @@ int drm_irq_install(struct drm_device *dev)
 
 	if (ret < 0) {
 		mutex_lock(&dev->struct_mutex);
-		dev->irq_enabled = 0;
+		dev->irq_enabled = false;
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
 	}
@@ -330,7 +330,7 @@ int drm_irq_install(struct drm_device *dev)
 
 	if (ret < 0) {
 		mutex_lock(&dev->struct_mutex);
-		dev->irq_enabled = 0;
+		dev->irq_enabled = false;
 		mutex_unlock(&dev->struct_mutex);
 		if (!drm_core_check_feature(dev, DRIVER_MODESET))
 			vga_client_register(dev->pdev, NULL, NULL, NULL);
@@ -351,14 +351,15 @@ EXPORT_SYMBOL(drm_irq_install);
 int drm_irq_uninstall(struct drm_device *dev)
 {
 	unsigned long irqflags;
-	int irq_enabled, i;
+	bool irq_enabled;
+	int i;
 
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
 		return -EINVAL;
 
 	mutex_lock(&dev->struct_mutex);
 	irq_enabled = dev->irq_enabled;
-	dev->irq_enabled = 0;
+	dev->irq_enabled = false;
 	mutex_unlock(&dev->struct_mutex);
 
 	/*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 1648b40700e8..23da72b5eae9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -716,13 +716,13 @@ static int fimd_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 {
 	/*
 	 * enable drm irq mode.
-	 * - with irq_enabled = 1, we can use the vblank feature.
+	 * - with irq_enabled = true, we can use the vblank feature.
 	 *
 	 * P.S. note that we wouldn't use drm irq handler but
 	 *	just specific driver own one instead because
 	 *	drm framework supports only one irq handler.
 	 */
-	drm_dev->irq_enabled = 1;
+	drm_dev->irq_enabled = true;
 
 	/*
 	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 347aa40a94f5..ddaaedde173d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -383,13 +383,13 @@ static int vidi_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 {
 	/*
 	 * enable drm irq mode.
-	 * - with irq_enabled = 1, we can use the vblank feature.
+	 * - with irq_enabled = true, we can use the vblank feature.
 	 *
 	 * P.S. note that we wouldn't use drm irq handler but
 	 *	just specific driver own one instead because
 	 *	drm framework supports only one irq handler.
 	 */
-	drm_dev->irq_enabled = 1;
+	drm_dev->irq_enabled = true;
 
 	/*
 	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
diff --git a/drivers/gpu/drm/mga/mga_irq.c b/drivers/gpu/drm/mga/mga_irq.c
index 598c281def0a..2b0ceb8dc11b 100644
--- a/drivers/gpu/drm/mga/mga_irq.c
+++ b/drivers/gpu/drm/mga/mga_irq.c
@@ -169,5 +169,5 @@ void mga_driver_irq_uninstall(struct drm_device *dev)
 	/* Disable *all* interrupts */
 	MGA_WRITE(MGA_IEN, 0);
 
-	dev->irq_enabled = 0;
+	dev->irq_enabled = false;
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c
index 261b227e4692..cb858600185f 100644
--- a/drivers/gpu/drm/omapdrm/omap_irq.c
+++ b/drivers/gpu/drm/omapdrm/omap_irq.c
@@ -261,7 +261,7 @@ int omap_drm_irq_install(struct drm_device *dev)
 		mutex_unlock(&dev->struct_mutex);
 		return -EBUSY;
 	}
-	dev->irq_enabled = 1;
+	dev->irq_enabled = true;
 	mutex_unlock(&dev->struct_mutex);
 
 	/* Before installing handler */
@@ -272,7 +272,7 @@ int omap_drm_irq_install(struct drm_device *dev)
 
 	if (ret < 0) {
 		mutex_lock(&dev->struct_mutex);
-		dev->irq_enabled = 0;
+		dev->irq_enabled = false;
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
 	}
@@ -283,7 +283,7 @@ int omap_drm_irq_install(struct drm_device *dev)
 
 	if (ret < 0) {
 		mutex_lock(&dev->struct_mutex);
-		dev->irq_enabled = 0;
+		dev->irq_enabled = false;
 		mutex_unlock(&dev->struct_mutex);
 		dispc_free_irq(dev);
 	}
@@ -294,11 +294,12 @@ int omap_drm_irq_install(struct drm_device *dev)
 int omap_drm_irq_uninstall(struct drm_device *dev)
 {
 	unsigned long irqflags;
-	int irq_enabled, i;
+	bool irq_enabled;
+	int i;
 
 	mutex_lock(&dev->struct_mutex);
 	irq_enabled = dev->irq_enabled;
-	dev->irq_enabled = 0;
+	dev->irq_enabled = false;
 	mutex_unlock(&dev->struct_mutex);
 
 	/*
diff --git a/drivers/gpu/host1x/drm/drm.c b/drivers/gpu/host1x/drm/drm.c
index 8c61ceeaa12d..df7d90a3a4fa 100644
--- a/drivers/gpu/host1x/drm/drm.c
+++ b/drivers/gpu/host1x/drm/drm.c
@@ -264,7 +264,7 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 	 * core, so we need to set this manually in order to allow the
 	 * DRM_IOCTL_WAIT_VBLANK to operate correctly.
 	 */
-	drm->irq_enabled = 1;
+	drm->irq_enabled = true;
 
 	err = drm_vblank_init(drm, drm->mode_config.num_crtc);
 	if (err < 0)
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 52c29b3afa28..c1014eb2907d 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -396,14 +396,14 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 
 	/*
 	 * enable drm irq mode.
-	 * - with irq_enabled = 1, we can use the vblank feature.
+	 * - with irq_enabled = true, we can use the vblank feature.
 	 *
 	 * P.S. note that we wouldn't use drm irq handler but
 	 *      just specific driver own one instead because
 	 *      drm framework supports only one irq handler and
 	 *      drivers can well take care of their interrupts
 	 */
-	drm->irq_enabled = 1;
+	drm->irq_enabled = true;
 
 	drm_mode_config_init(drm);
 	imx_drm_mode_config_init(drm);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 7198febd9d8e..713d7c699bcd 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1149,7 +1149,7 @@ struct drm_device {
 
 	/** \name Context support */
 	/*@{ */
-	int irq_enabled;		/**< True if irq handler is enabled */
+	bool irq_enabled;		/**< True if irq handler is enabled */
 	__volatile__ long context_flag;	/**< Context swapping flag */
 	int last_context;		/**< Last current context */
 	/*@} */
-- 
cgit 


From 6b8837df7a39d88f6a48a892312b08bbefba2540 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:38 +0300
Subject: drm: Kill unused stuff from struct drm_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'map_count' and 'work' are never used. Kill them both.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 713d7c699bcd..5b99c0e072ef 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1127,7 +1127,6 @@ struct drm_device {
 	/** \name Memory management */
 	/*@{ */
 	struct list_head maplist;	/**< Linked list of regions */
-	int map_count;			/**< Number of mappable regions */
 	struct drm_open_hash map_hash;	/**< User token hash table for maps */
 
 	/** \name Context handle management */
@@ -1154,7 +1153,6 @@ struct drm_device {
 	int last_context;		/**< Last current context */
 	/*@} */
 
-	struct work_struct work;
 	/** \name VBLANK IRQ support */
 	/*@{ */
 
-- 
cgit 


From fc6ff1935b550bdf525e0caa5ef0894010375414 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:39 +0300
Subject: drm: Kill ctx_count from struct drm_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only user of ctx_count is the via driver, and we can replace that
use with list_is_singular().

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_context.c | 2 --
 drivers/gpu/drm/drm_fops.c    | 1 -
 drivers/gpu/drm/via/via_mm.c  | 2 +-
 include/drm/drmP.h            | 1 -
 4 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c
index 224ff965bcf7..a4b017b6849e 100644
--- a/drivers/gpu/drm/drm_context.c
+++ b/drivers/gpu/drm/drm_context.c
@@ -334,7 +334,6 @@ int drm_addctx(struct drm_device *dev, void *data,
 
 	mutex_lock(&dev->ctxlist_mutex);
 	list_add(&ctx_entry->head, &dev->ctxlist);
-	++dev->ctx_count;
 	mutex_unlock(&dev->ctxlist_mutex);
 
 	return 0;
@@ -432,7 +431,6 @@ int drm_rmctx(struct drm_device *dev, void *data,
 			if (pos->handle == ctx->handle) {
 				list_del(&pos->head);
 				kfree(pos);
-				--dev->ctx_count;
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 8bc94eaaf9f5..621b45e08bd1 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -524,7 +524,6 @@ int drm_release(struct inode *inode, struct file *filp)
 
 				list_del(&pos->head);
 				kfree(pos);
-				--dev->ctx_count;
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index 7e3ad87c366c..927889105483 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -79,7 +79,7 @@ int via_final_context(struct drm_device *dev, int context)
 
 	/* Linux specific until context tracking code gets ported to BSD */
 	/* Last context, perform cleanup */
-	if (dev->ctx_count == 1 && dev->dev_private) {
+	if (list_is_singular(&dev->ctxlist) && dev->dev_private) {
 		DRM_DEBUG("Last Context\n");
 		drm_irq_uninstall(dev);
 		via_cleanup_futex(dev_priv);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 5b99c0e072ef..e26b80236719 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1132,7 +1132,6 @@ struct drm_device {
 	/** \name Context handle management */
 	/*@{ */
 	struct list_head ctxlist;	/**< Linked list of context handles */
-	int ctx_count;			/**< Number of context handles */
 	struct mutex ctxlist_mutex;	/**< For ctxlist */
 
 	struct idr ctx_idr;
-- 
cgit 


From ffbab09bf939975b62ec233c426bf7df0dd4cea8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:40 +0300
Subject: drm: Remove pci_vendor and pci_device from struct drm_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can get the PCI vendor and device IDs via dev->pdev. So we can drop
the duplicated information.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_pci.c                   |  3 ---
 drivers/gpu/drm/gma500/psb_drv.h            |  8 +++----
 drivers/gpu/drm/i915/i915_dma.c             |  2 +-
 drivers/gpu/drm/i915/i915_drv.h             | 36 ++++++++++++++---------------
 drivers/gpu/drm/i915/i915_gpu_error.c       |  2 +-
 drivers/gpu/drm/i915/intel_tv.c             |  2 +-
 drivers/gpu/drm/nouveau/dispnv04/arb.c      |  8 +++----
 drivers/gpu/drm/nouveau/dispnv04/dfp.c      |  4 ++--
 drivers/gpu/drm/nouveau/dispnv04/disp.h     |  6 ++---
 drivers/gpu/drm/nouveau/dispnv04/hw.c       |  4 ++--
 drivers/gpu/drm/nouveau/nouveau_abi16.c     |  4 ++--
 drivers/gpu/drm/nouveau/nouveau_bios.c      |  4 ++--
 drivers/gpu/drm/nouveau/nouveau_connector.c |  4 ++--
 drivers/gpu/drm/radeon/radeon_bios.c        |  6 ++---
 drivers/gpu/drm/radeon/radeon_kms.c         |  2 +-
 include/drm/drmP.h                          |  2 --
 16 files changed, 46 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index cabe2bd702ae..f00d7a9671ea 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -331,9 +331,6 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 		goto err_free;
 
 	dev->pdev = pdev;
-	dev->pci_device = pdev->device;
-	dev->pci_vendor = pdev->vendor;
-
 #ifdef __alpha__
 	dev->hose = pdev->sysdata;
 #endif
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 6856bce58445..0bab46bd73d2 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -44,10 +44,10 @@ enum {
 	CHIP_MFLD_0130 = 3,		/* Medfield */
 };
 
-#define IS_PSB(dev) (((dev)->pci_device & 0xfffe) == 0x8108)
-#define IS_MRST(dev) (((dev)->pci_device & 0xfffc) == 0x4100)
-#define IS_MFLD(dev) (((dev)->pci_device & 0xfff8) == 0x0130)
-#define IS_CDV(dev) (((dev)->pci_device & 0xfff0) == 0x0be0)
+#define IS_PSB(dev) (((dev)->pdev->device & 0xfffe) == 0x8108)
+#define IS_MRST(dev) (((dev)->pdev->device & 0xfffc) == 0x4100)
+#define IS_MFLD(dev) (((dev)->pdev->device & 0xfff8) == 0x0130)
+#define IS_CDV(dev) (((dev)->pdev->device & 0xfff0) == 0x0be0)
 
 /*
  * Driver definitions
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 93cbacba26a2..d8478f7cdbf0 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -931,7 +931,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		value = READ_BREADCRUMB(dev_priv);
 		break;
 	case I915_PARAM_CHIPSET_ID:
-		value = dev->pci_device;
+		value = dev->pdev->device;
 		break;
 	case I915_PARAM_HAS_GEM:
 		value = 1;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 923d9d0eecf5..a404e7dc065a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1590,39 +1590,39 @@ struct drm_i915_file_private {
 
 #define INTEL_INFO(dev)	(to_i915(dev)->info)
 
-#define IS_I830(dev)		((dev)->pci_device == 0x3577)
-#define IS_845G(dev)		((dev)->pci_device == 0x2562)
+#define IS_I830(dev)		((dev)->pdev->device == 0x3577)
+#define IS_845G(dev)		((dev)->pdev->device == 0x2562)
 #define IS_I85X(dev)		(INTEL_INFO(dev)->is_i85x)
-#define IS_I865G(dev)		((dev)->pci_device == 0x2572)
+#define IS_I865G(dev)		((dev)->pdev->device == 0x2572)
 #define IS_I915G(dev)		(INTEL_INFO(dev)->is_i915g)
-#define IS_I915GM(dev)		((dev)->pci_device == 0x2592)
-#define IS_I945G(dev)		((dev)->pci_device == 0x2772)
+#define IS_I915GM(dev)		((dev)->pdev->device == 0x2592)
+#define IS_I945G(dev)		((dev)->pdev->device == 0x2772)
 #define IS_I945GM(dev)		(INTEL_INFO(dev)->is_i945gm)
 #define IS_BROADWATER(dev)	(INTEL_INFO(dev)->is_broadwater)
 #define IS_CRESTLINE(dev)	(INTEL_INFO(dev)->is_crestline)
-#define IS_GM45(dev)		((dev)->pci_device == 0x2A42)
+#define IS_GM45(dev)		((dev)->pdev->device == 0x2A42)
 #define IS_G4X(dev)		(INTEL_INFO(dev)->is_g4x)
-#define IS_PINEVIEW_G(dev)	((dev)->pci_device == 0xa001)
-#define IS_PINEVIEW_M(dev)	((dev)->pci_device == 0xa011)
+#define IS_PINEVIEW_G(dev)	((dev)->pdev->device == 0xa001)
+#define IS_PINEVIEW_M(dev)	((dev)->pdev->device == 0xa011)
 #define IS_PINEVIEW(dev)	(INTEL_INFO(dev)->is_pineview)
 #define IS_G33(dev)		(INTEL_INFO(dev)->is_g33)
-#define IS_IRONLAKE_M(dev)	((dev)->pci_device == 0x0046)
+#define IS_IRONLAKE_M(dev)	((dev)->pdev->device == 0x0046)
 #define IS_IVYBRIDGE(dev)	(INTEL_INFO(dev)->is_ivybridge)
-#define IS_IVB_GT1(dev)		((dev)->pci_device == 0x0156 || \
-				 (dev)->pci_device == 0x0152 ||	\
-				 (dev)->pci_device == 0x015a)
-#define IS_SNB_GT1(dev)		((dev)->pci_device == 0x0102 || \
-				 (dev)->pci_device == 0x0106 ||	\
-				 (dev)->pci_device == 0x010A)
+#define IS_IVB_GT1(dev)		((dev)->pdev->device == 0x0156 || \
+				 (dev)->pdev->device == 0x0152 || \
+				 (dev)->pdev->device == 0x015a)
+#define IS_SNB_GT1(dev)		((dev)->pdev->device == 0x0102 || \
+				 (dev)->pdev->device == 0x0106 || \
+				 (dev)->pdev->device == 0x010A)
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
-				 ((dev)->pci_device & 0xFF00) == 0x0C00)
+				 ((dev)->pdev->device & 0xFF00) == 0x0C00)
 #define IS_ULT(dev)		(IS_HASWELL(dev) && \
-				 ((dev)->pci_device & 0xFF00) == 0x0A00)
+				 ((dev)->pdev->device & 0xFF00) == 0x0A00)
 #define IS_HSW_GT3(dev)		(IS_HASWELL(dev) && \
-				 ((dev)->pci_device & 0x00F0) == 0x0020)
+				 ((dev)->pdev->device & 0x00F0) == 0x0020)
 #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 7bea61325741..3858825e0978 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -304,7 +304,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
 	err_printf(m, "Kernel: " UTS_RELEASE "\n");
-	err_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
+	err_printf(m, "PCI ID: 0x%04x\n", dev->pdev->device);
 	err_printf(m, "EIR: 0x%08x\n", error->eir);
 	err_printf(m, "IER: 0x%08x\n", error->ier);
 	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index dd6f84bf6c22..fa602d3b1cb7 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1044,7 +1044,7 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		tv_mode->dda3_inc << TV_SCDDA3_INC_SHIFT;
 
 	/* Enable two fixes for the chips that need them. */
-	if (dev->pci_device < 0x2772)
+	if (dev->pdev->device < 0x2772)
 		tv_ctl |= TV_ENC_C0_FIX | TV_ENC_SDP_FIX;
 
 	I915_WRITE(TV_H_CTL_1, hctl1);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/arb.c b/drivers/gpu/drm/nouveau/dispnv04/arb.c
index 2e70462883e8..2a15b98b4d2b 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/arb.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/arb.c
@@ -210,8 +210,8 @@ nv04_update_arb(struct drm_device *dev, int VClk, int bpp,
 	sim_data.nvclk_khz = NVClk;
 	sim_data.bpp = bpp;
 	sim_data.two_heads = nv_two_heads(dev);
-	if ((dev->pci_device & 0xffff) == 0x01a0 /*CHIPSET_NFORCE*/ ||
-	    (dev->pci_device & 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) {
+	if ((dev->pdev->device & 0xffff) == 0x01a0 /*CHIPSET_NFORCE*/ ||
+	    (dev->pdev->device & 0xffff) == 0x01f0 /*CHIPSET_NFORCE2*/) {
 		uint32_t type;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 1), 0x7c, &type);
@@ -256,8 +256,8 @@ nouveau_calc_arb(struct drm_device *dev, int vclk, int bpp, int *burst, int *lwm
 
 	if (nv_device(drm->device)->card_type < NV_20)
 		nv04_update_arb(dev, vclk, bpp, burst, lwm);
-	else if ((dev->pci_device & 0xfff0) == 0x0240 /*CHIPSET_C51*/ ||
-		 (dev->pci_device & 0xfff0) == 0x03d0 /*CHIPSET_C512*/) {
+	else if ((dev->pdev->device & 0xfff0) == 0x0240 /*CHIPSET_C51*/ ||
+		 (dev->pdev->device & 0xfff0) == 0x03d0 /*CHIPSET_C512*/) {
 		*burst = 128;
 		*lwm = 0x0480;
 	} else
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index 93dd23ff0093..59d1c040b84f 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -490,8 +490,8 @@ static void nv04_dfp_update_backlight(struct drm_encoder *encoder, int mode)
 	/* BIOS scripts usually take care of the backlight, thanks
 	 * Apple for your consistency.
 	 */
-	if (dev->pci_device == 0x0174 || dev->pci_device == 0x0179 ||
-	    dev->pci_device == 0x0189 || dev->pci_device == 0x0329) {
+	if (dev->pdev->device == 0x0174 || dev->pdev->device == 0x0179 ||
+	    dev->pdev->device == 0x0189 || dev->pdev->device == 0x0329) {
 		if (mode == DRM_MODE_DPMS_ON) {
 			nv_mask(device, NV_PBUS_DEBUG_DUALHEAD_CTL, 0, 1 << 31);
 			nv_mask(device, NV_PCRTC_GPIO_EXT, 3, 1);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.h b/drivers/gpu/drm/nouveau/dispnv04/disp.h
index 9928187f0a7d..2cf65e0b517e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.h
@@ -127,7 +127,7 @@ static inline bool
 nv_two_heads(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	const int impl = dev->pci_device & 0x0ff0;
+	const int impl = dev->pdev->device & 0x0ff0;
 
 	if (nv_device(drm->device)->card_type >= NV_10 && impl != 0x0100 &&
 	    impl != 0x0150 && impl != 0x01a0 && impl != 0x0200)
@@ -139,14 +139,14 @@ nv_two_heads(struct drm_device *dev)
 static inline bool
 nv_gf4_disp_arch(struct drm_device *dev)
 {
-	return nv_two_heads(dev) && (dev->pci_device & 0x0ff0) != 0x0110;
+	return nv_two_heads(dev) && (dev->pdev->device & 0x0ff0) != 0x0110;
 }
 
 static inline bool
 nv_two_reg_pll(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	const int impl = dev->pci_device & 0x0ff0;
+	const int impl = dev->pdev->device & 0x0ff0;
 
 	if (impl == 0x0310 || impl == 0x0340 || nv_device(drm->device)->card_type >= NV_40)
 		return true;
diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c
index 973056b86207..f8dee834527f 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/hw.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c
@@ -220,7 +220,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 	int ret;
 
 	if (plltype == PLL_MEMORY &&
-	    (dev->pci_device & 0x0ff0) == CHIPSET_NFORCE) {
+	    (dev->pdev->device & 0x0ff0) == CHIPSET_NFORCE) {
 		uint32_t mpllP;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
@@ -230,7 +230,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		return 400000 / mpllP;
 	} else
 	if (plltype == PLL_MEMORY &&
-	    (dev->pci_device & 0xff0) == CHIPSET_NFORCE2) {
+	    (dev->pdev->device & 0xff0) == CHIPSET_NFORCE2) {
 		uint32_t clock;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 3897549aabba..72055a35f845 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -178,10 +178,10 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS)
 		getparam->value = device->chipset;
 		break;
 	case NOUVEAU_GETPARAM_PCI_VENDOR:
-		getparam->value = dev->pci_vendor;
+		getparam->value = dev->pdev->vendor;
 		break;
 	case NOUVEAU_GETPARAM_PCI_DEVICE:
-		getparam->value = dev->pci_device;
+		getparam->value = dev->pdev->device;
 		break;
 	case NOUVEAU_GETPARAM_BUS_TYPE:
 		if (drm_pci_device_is_agp(dev))
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 3e7287675ecf..4c3feaaa1037 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -127,8 +127,8 @@ static int call_lvds_manufacturer_script(struct drm_device *dev, struct dcb_outp
 #ifdef __powerpc__
 	/* Powerbook specific quirks */
 	if (script == LVDS_RESET &&
-	    (dev->pci_device == 0x0179 || dev->pci_device == 0x0189 ||
-	     dev->pci_device == 0x0329))
+	    (dev->pdev->device == 0x0179 || dev->pdev->device == 0x0189 ||
+	     dev->pdev->device == 0x0329))
 		nv_write_tmds(dev, dcbent->or, 0, 0x02, 0x72);
 #endif
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index c5b36f9e9a10..2136d0038252 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -215,8 +215,8 @@ nouveau_connector_set_encoder(struct drm_connector *connector,
 		connector->doublescan_allowed = true;
 		if (nv_device(drm->device)->card_type == NV_20 ||
 		   (nv_device(drm->device)->card_type == NV_10 &&
-		    (dev->pci_device & 0x0ff0) != 0x0100 &&
-		    (dev->pci_device & 0x0ff0) != 0x0150))
+		    (dev->pdev->device & 0x0ff0) != 0x0100 &&
+		    (dev->pdev->device & 0x0ff0) != 0x0150))
 			/* HW is broken */
 			connector->interlace_allowed = false;
 		else
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 061b227dae0c..c155d6f3fa68 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -499,7 +499,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 	crtc_ext_cntl = RREG32(RADEON_CRTC_EXT_CNTL);
 	fp2_gen_cntl = 0;
 
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL);
 	}
 
@@ -536,7 +536,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 		(RADEON_CRTC_SYNC_TRISTAT |
 		 RADEON_CRTC_DISPLAY_DIS)));
 
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		WREG32(RADEON_FP2_GEN_CNTL, (fp2_gen_cntl & ~RADEON_FP2_ON));
 	}
 
@@ -554,7 +554,7 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev)
 		WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl);
 	}
 	WREG32(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl);
-	if (rdev->ddev->pci_device == PCI_DEVICE_ID_ATI_RADEON_QY) {
+	if (rdev->ddev->pdev->device == PCI_DEVICE_ID_ATI_RADEON_QY) {
 		WREG32(RADEON_FP2_GEN_CNTL, fp2_gen_cntl);
 	}
 	return r;
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 61580ddc4eb2..d6b36766e8c9 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -191,7 +191,7 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	switch (info->request) {
 	case RADEON_INFO_DEVICE_ID:
-		*value = dev->pci_device;
+		*value = dev->pdev->device;
 		break;
 	case RADEON_INFO_NUM_GB_PIPES:
 		*value = rdev->num_gb_pipes;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index e26b80236719..a5d8024ad56d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1184,8 +1184,6 @@ struct drm_device {
 
 	struct device *dev;             /**< Device structure */
 	struct pci_dev *pdev;		/**< PCI device structure */
-	int pci_vendor;			/**< PCI vendor id */
-	int pci_device;			/**< PCI device id */
 #ifdef __alpha__
 	struct pci_controller *hose;
 #endif
-- 
cgit 


From 0111be42186fc5461b9e9d579014c70869ab3152 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Oct 2013 14:53:41 +0300
Subject: drm: Kill drm perf counter leftovers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The user of these counters was killed in

 commit d79cdc8312689b39c6d83718c1c196af4b3cd18c
 Author: Daniel Vetter <daniel.vetter@ffwll.ch>
 Date:   Thu Aug 8 15:41:32 2013 +0200

    drm: no-op out GET_STATS ioctl

so clean up the leftovers as well.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_drv.c       |  1 -
 drivers/gpu/drm/drm_fops.c      |  7 -------
 drivers/gpu/drm/drm_lock.c      |  3 ---
 drivers/gpu/drm/drm_stub.c      |  9 ---------
 drivers/gpu/drm/i810/i810_dma.c | 11 -----------
 drivers/gpu/drm/i915/i915_dma.c |  7 -------
 drivers/gpu/drm/mga/mga_dma.c   |  5 -----
 include/drm/drmP.h              |  7 -------
 8 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 34d372ed904c..6495bdfd35dc 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -315,7 +315,6 @@ long drm_ioctl(struct file *filp,
 		return -ENODEV;
 
 	atomic_inc(&dev->ioctl_count);
-	atomic_inc(&dev->counts[_DRM_STAT_IOCTLS]);
 	++file_priv->ioctl_count;
 
 	if ((nr >= DRM_CORE_IOCTL_COUNT) &&
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 621b45e08bd1..d0e27667a4eb 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -113,7 +113,6 @@ int drm_open(struct inode *inode, struct file *filp)
 	retcode = drm_open_helper(inode, filp, dev);
 	if (retcode)
 		goto err_undo;
-	atomic_inc(&dev->counts[_DRM_STAT_OPENS]);
 	if (need_setup) {
 		retcode = drm_setup(dev);
 		if (retcode)
@@ -392,17 +391,12 @@ static void drm_events_release(struct drm_file *file_priv)
  */
 static void drm_legacy_dev_reinit(struct drm_device *dev)
 {
-	int i;
-
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return;
 
 	atomic_set(&dev->ioctl_count, 0);
 	atomic_set(&dev->vma_count, 0);
 
-	for (i = 0; i < ARRAY_SIZE(dev->counts); i++)
-		atomic_set(&dev->counts[i], 0);
-
 	dev->sigdata.lock = NULL;
 
 	dev->context_flag = 0;
@@ -585,7 +579,6 @@ int drm_release(struct inode *inode, struct file *filp)
 	 * End inline drm_release
 	 */
 
-	atomic_inc(&dev->counts[_DRM_STAT_CLOSES]);
 	if (!--dev->open_count) {
 		if (atomic_read(&dev->ioctl_count)) {
 			DRM_ERROR("Device busy: %d\n",
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index d752c96d6090..f6452682141b 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -86,7 +86,6 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		if (drm_lock_take(&master->lock, lock->context)) {
 			master->lock.file_priv = file_priv;
 			master->lock.lock_time = jiffies;
-			atomic_inc(&dev->counts[_DRM_STAT_LOCKS]);
 			break;	/* Got lock */
 		}
 
@@ -157,8 +156,6 @@ int drm_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		return -EINVAL;
 	}
 
-	atomic_inc(&dev->counts[_DRM_STAT_UNLOCKS]);
-
 	if (drm_lock_free(&master->lock, lock->context)) {
 		/* FIXME: Should really bail out here. */
 	}
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 2badef766d20..26055abf94ee 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -431,15 +431,6 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->ctxlist_mutex);
 
-	/* the DRM has 6 basic counters */
-	dev->counters = 6;
-	dev->types[0] = _DRM_STAT_LOCK;
-	dev->types[1] = _DRM_STAT_OPENS;
-	dev->types[2] = _DRM_STAT_CLOSES;
-	dev->types[3] = _DRM_STAT_IOCTLS;
-	dev->types[4] = _DRM_STAT_LOCKS;
-	dev->types[5] = _DRM_STAT_UNLOCKS;
-
 	if (drm_ht_create(&dev->map_hash, 12))
 		goto err_free;
 
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index ab1892eb1074..249fdff305c6 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -944,8 +944,6 @@ static int i810_dma_vertex(struct drm_device *dev, void *data,
 				 dma->buflist[vertex->idx],
 				 vertex->discard, vertex->used);
 
-	atomic_add(vertex->used, &dev->counts[_DRM_STAT_SECONDARY]);
-	atomic_inc(&dev->counts[_DRM_STAT_DMA]);
 	sarea_priv->last_enqueue = dev_priv->counter - 1;
 	sarea_priv->last_dispatch = (int)hw_status[5];
 
@@ -1105,8 +1103,6 @@ static int i810_dma_mc(struct drm_device *dev, void *data,
 	i810_dma_dispatch_mc(dev, dma->buflist[mc->idx], mc->used,
 			     mc->last_render);
 
-	atomic_add(mc->used, &dev->counts[_DRM_STAT_SECONDARY]);
-	atomic_inc(&dev->counts[_DRM_STAT_DMA]);
 	sarea_priv->last_enqueue = dev_priv->counter - 1;
 	sarea_priv->last_dispatch = (int)hw_status[5];
 
@@ -1197,13 +1193,6 @@ static int i810_flip_bufs(struct drm_device *dev, void *data,
 
 int i810_driver_load(struct drm_device *dev, unsigned long flags)
 {
-	/* i810 has 4 more counters */
-	dev->counters += 4;
-	dev->types[6] = _DRM_STAT_IRQ;
-	dev->types[7] = _DRM_STAT_PRIMARY;
-	dev->types[8] = _DRM_STAT_SECONDARY;
-	dev->types[9] = _DRM_STAT_DMA;
-
 	pci_set_master(dev->pdev);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index d8478f7cdbf0..637b695eafbd 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1473,13 +1473,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (info->gen >= 6 && !drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
-	/* i915 has 4 more counters */
-	dev->counters += 4;
-	dev->types[6] = _DRM_STAT_IRQ;
-	dev->types[7] = _DRM_STAT_PRIMARY;
-	dev->types[8] = _DRM_STAT_SECONDARY;
-	dev->types[9] = _DRM_STAT_DMA;
-
 	dev_priv = kzalloc(sizeof(drm_i915_private_t), GFP_KERNEL);
 	if (dev_priv == NULL)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c
index cc3166dd445a..087db33f6cff 100644
--- a/drivers/gpu/drm/mga/mga_dma.c
+++ b/drivers/gpu/drm/mga/mga_dma.c
@@ -406,11 +406,6 @@ int mga_driver_load(struct drm_device *dev, unsigned long flags)
 	dev_priv->mmio_base = pci_resource_start(dev->pdev, 1);
 	dev_priv->mmio_size = pci_resource_len(dev->pdev, 1);
 
-	dev->counters += 3;
-	dev->types[6] = _DRM_STAT_IRQ;
-	dev->types[7] = _DRM_STAT_PRIMARY;
-	dev->types[8] = _DRM_STAT_SECONDARY;
-
 	ret = drm_vblank_init(dev, 1);
 
 	if (ret) {
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a5d8024ad56d..9ba6a38f54be 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1115,13 +1115,6 @@ struct drm_device {
 	atomic_t buf_alloc;		/**< Buffer allocation in progress */
 	/*@} */
 
-	/** \name Performance counters */
-	/*@{ */
-	unsigned long counters;
-	enum drm_stat_type types[15];
-	atomic_t counts[15];
-	/*@} */
-
 	struct list_head filelist;
 
 	/** \name Memory management */
-- 
cgit 


From 789fd03331aa1ec45cb58168e2d82525c97c7351 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
Date: Fri, 4 Oct 2013 18:07:24 -0700
Subject: cfg80211: rename regulatory_hint_11d() to
 regulatory_hint_country_ie()

It is incorrect to refer to this as 11d as 802.11d was just a
proposed amendment, 802.11d was merged to the standard so
use proper terminology.

Signed-off-by: Luis R. Rodriguez <mcgrof@do-not-panic.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 2 +-
 net/wireless/reg.c           | 4 ++--
 net/wireless/reg.h           | 4 ++--
 net/wireless/sme.c           | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a58ea652cc24..8c0417c222c6 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -988,7 +988,7 @@ enum nl80211_commands {
  * 	to query the CRDA to retrieve one regulatory domain. This attribute can
  * 	also be used by userspace to query the kernel for the currently set
  * 	regulatory domain. We chose an alpha2 as that is also used by the
- * 	IEEE-802.11d country information element to identify a country.
+ * 	IEEE-802.11 country information element to identify a country.
  * 	Users can also simply ask the wireless core to set regulatory domain
  * 	to a specific alpha2.
  * @NL80211_ATTR_REG_RULES: a nested array of regulatory domain regulatory
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d62cb1e91475..8fbe664fdcf8 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1699,8 +1699,8 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 }
 EXPORT_SYMBOL(regulatory_hint);
 
-void regulatory_hint_11d(struct wiphy *wiphy, enum ieee80211_band band,
-			 const u8 *country_ie, u8 country_ie_len)
+void regulatory_hint_country_ie(struct wiphy *wiphy, enum ieee80211_band band,
+				const u8 *country_ie, u8 country_ie_len)
 {
 	char alpha2[2];
 	enum environment_cap env = ENVIRON_ANY;
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index af2d5f8a5d82..9677e3c13da9 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -58,7 +58,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
 				 gfp_t gfp);
 
 /**
- * regulatory_hint_11d - hints a country IE as a regulatory domain
+ * regulatory_hint_country_ie - hints a country IE as a regulatory domain
  * @wiphy: the wireless device giving the hint (used only for reporting
  *	conflicts)
  * @band: the band on which the country IE was received on. This determines
@@ -78,7 +78,7 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy,
  * not observed. For this reason if a triplet is seen with channel
  * information for a band the BSS is not present in it will be ignored.
  */
-void regulatory_hint_11d(struct wiphy *wiphy,
+void regulatory_hint_country_ie(struct wiphy *wiphy,
 			 enum ieee80211_band band,
 			 const u8 *country_ie,
 			 u8 country_ie_len);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 20e86a95dc4e..65f800890d70 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -682,8 +682,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 	 * - country_ie + 2, the start of the country ie data, and
 	 * - and country_ie[1] which is the IE length
 	 */
-	regulatory_hint_11d(wdev->wiphy, bss->channel->band,
-			    country_ie + 2, country_ie[1]);
+	regulatory_hint_country_ie(wdev->wiphy, bss->channel->band,
+				   country_ie + 2, country_ie[1]);
 	kfree(country_ie);
 }
 
-- 
cgit 


From 58704e6a5478a96ca0e549ce6605332aab815eea Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 4 Oct 2013 15:08:08 +0300
Subject: drm/dp: add helper for checking DP_ENHANCED_FRAME_CAP in DPCD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drm_dp_helper.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 110f4f1f51d7..a92c3754e3bb 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -390,4 +390,11 @@ drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 	return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
 }
 
+static inline bool
+drm_dp_enhanced_frame_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	return dpcd[DP_DPCD_REV] >= 0x11 &&
+		(dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP);
+}
+
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit 


From b726b7dfb400c937546fa91cf8523dcb1aa2fc6e Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:28:53 +0100
Subject: Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled
 on a new node"

PTE scanning and NUMA hinting fault handling is expensive so commit
5bca2303 ("mm: sched: numa: Delay PTE scanning until a task is scheduled
on a new node") deferred the PTE scan until a task had been scheduled on
another node. The problem is that in the purely shared memory case that
this may never happen and no NUMA hinting fault information will be
captured. We are not ruling out the possibility that something better
can be done here but for now, this patch needs to be reverted and depend
entirely on the scan_delay to avoid punishing short-lived processes.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-16-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm_types.h | 10 ----------
 kernel/fork.c            |  3 ---
 kernel/sched/fair.c      | 18 ------------------
 kernel/sched/features.h  |  4 +---
 4 files changed, 1 insertion(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d9851eeb6e1d..b7adf1d4310c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -428,20 +428,10 @@ struct mm_struct {
 
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
-
-	/*
-	 * The first node a task was scheduled on. If a task runs on
-	 * a different node than Make PTE Scan Go Now.
-	 */
-	int first_nid;
 #endif
 	struct uprobes_state uprobes_state;
 };
 
-/* first nid will either be a valid NID or one of these values */
-#define NUMA_PTE_SCAN_INIT	-1
-#define NUMA_PTE_SCAN_ACTIVE	-2
-
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/kernel/fork.c b/kernel/fork.c
index 086fe73ad6bd..7192d91b5415 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -816,9 +816,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
-#endif
-#ifdef CONFIG_NUMA_BALANCING
-	mm->first_nid = NUMA_PTE_SCAN_INIT;
 #endif
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 464207fc9eef..49b11faa2961 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -900,24 +900,6 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
-	/*
-	 * We do not care about task placement until a task runs on a node
-	 * other than the first one used by the address space. This is
-	 * largely because migrations are driven by what CPU the task
-	 * is running on. If it's never scheduled on another node, it'll
-	 * not migrate so why bother trapping the fault.
-	 */
-	if (mm->first_nid == NUMA_PTE_SCAN_INIT)
-		mm->first_nid = numa_node_id();
-	if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) {
-		/* Are we running on a new node yet? */
-		if (numa_node_id() == mm->first_nid &&
-		    !sched_feat_numa(NUMA_FORCE))
-			return;
-
-		mm->first_nid = NUMA_PTE_SCAN_ACTIVE;
-	}
-
 	/*
 	 * Reset the scan period if enough time has gone by. Objective is that
 	 * scanning will be reduced if pages are properly placed. As tasks
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 99399f8e4799..cba5c616a157 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -63,10 +63,8 @@ SCHED_FEAT(LB_MIN, false)
 /*
  * Apply the automatic NUMA scheduling policy. Enabled automatically
  * at runtime if running on a NUMA machine. Can be controlled via
- * numa_balancing=. Allow PTE scanning to be forced on UMA machines
- * for debugging the core machinery.
+ * numa_balancing=
  */
 #ifdef CONFIG_NUMA_BALANCING
 SCHED_FEAT(NUMA,	false)
-SCHED_FEAT(NUMA_FORCE,	false)
 #endif
-- 
cgit 


From 598f0ec0bc996e90a806ee9564af919ea5aad401 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:28:55 +0100
Subject: sched/numa: Set the scan rate proportional to the memory usage of the
 task being scanned

The NUMA PTE scan rate is controlled with a combination of the
numa_balancing_scan_period_min, numa_balancing_scan_period_max and
numa_balancing_scan_size. This scan rate is independent of the size
of the task and as an aside it is further complicated by the fact that
numa_balancing_scan_size controls how many pages are marked pte_numa and
not how much virtual memory is scanned.

In combination, it is almost impossible to meaningfully tune the min and
max scan periods and reasoning about performance is complex when the time
to complete a full scan is is partially a function of the tasks memory
size. This patch alters the semantic of the min and max tunables to be
about tuning the length time it takes to complete a scan of a tasks occupied
virtual address space. Conceptually this is a lot easier to understand. There
is a "sanity" check to ensure the scan rate is never extremely fast based on
the amount of virtual memory that should be scanned in a second. The default
of 2.5G seems arbitrary but it is to have the maximum scan rate after the
patch roughly match the maximum scan rate before the patch was applied.

On a similar note, numa_scan_period is in milliseconds and not
jiffies. Properly placed pages slow the scanning rate but adding 10 jiffies
to numa_scan_period means that the rate scanning slows depends on HZ which
is confusing. Get rid of the jiffies_to_msec conversion and treat it as ms.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-18-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/sysctl/kernel.txt | 11 +++---
 include/linux/sched.h           |  1 +
 kernel/sched/fair.c             | 88 +++++++++++++++++++++++++++++++++++------
 3 files changed, 83 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 1428c6659254..8cd7e5fc79da 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -403,15 +403,16 @@ workload pattern changes and minimises performance impact due to remote
 memory accesses. These sysctls control the thresholds for scan delays and
 the number of pages scanned.
 
-numa_balancing_scan_period_min_ms is the minimum delay in milliseconds
-between scans. It effectively controls the maximum scanning rate for
-each task.
+numa_balancing_scan_period_min_ms is the minimum time in milliseconds to
+scan a tasks virtual memory. It effectively controls the maximum scanning
+rate for each task.
 
 numa_balancing_scan_delay_ms is the starting "scan delay" used for a task
 when it initially forks.
 
-numa_balancing_scan_period_max_ms is the maximum delay between scans. It
-effectively controls the minimum scanning rate for each task.
+numa_balancing_scan_period_max_ms is the maximum time in milliseconds to
+scan a tasks virtual memory. It effectively controls the minimum scanning
+rate for each task.
 
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2ac5285db434..fdcb4c855072 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1339,6 +1339,7 @@ struct task_struct {
 	int numa_scan_seq;
 	int numa_migrate_seq;
 	unsigned int numa_scan_period;
+	unsigned int numa_scan_period_max;
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
 #endif /* CONFIG_NUMA_BALANCING */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0966f0c16f1b..e08d757720de 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -818,11 +818,13 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #ifdef CONFIG_NUMA_BALANCING
 /*
- * numa task sample period in ms
+ * Approximate time to scan a full NUMA task in ms. The task scan period is
+ * calculated based on the tasks virtual memory size and
+ * numa_balancing_scan_size.
  */
-unsigned int sysctl_numa_balancing_scan_period_min = 100;
-unsigned int sysctl_numa_balancing_scan_period_max = 100*50;
-unsigned int sysctl_numa_balancing_scan_period_reset = 100*600;
+unsigned int sysctl_numa_balancing_scan_period_min = 1000;
+unsigned int sysctl_numa_balancing_scan_period_max = 60000;
+unsigned int sysctl_numa_balancing_scan_period_reset = 60000;
 
 /* Portion of address space to scan in MB */
 unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -830,6 +832,51 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
+static unsigned int task_nr_scan_windows(struct task_struct *p)
+{
+	unsigned long rss = 0;
+	unsigned long nr_scan_pages;
+
+	/*
+	 * Calculations based on RSS as non-present and empty pages are skipped
+	 * by the PTE scanner and NUMA hinting faults should be trapped based
+	 * on resident pages
+	 */
+	nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT);
+	rss = get_mm_rss(p->mm);
+	if (!rss)
+		rss = nr_scan_pages;
+
+	rss = round_up(rss, nr_scan_pages);
+	return rss / nr_scan_pages;
+}
+
+/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */
+#define MAX_SCAN_WINDOW 2560
+
+static unsigned int task_scan_min(struct task_struct *p)
+{
+	unsigned int scan, floor;
+	unsigned int windows = 1;
+
+	if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
+		windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+	floor = 1000 / windows;
+
+	scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
+	return max_t(unsigned int, floor, scan);
+}
+
+static unsigned int task_scan_max(struct task_struct *p)
+{
+	unsigned int smin = task_scan_min(p);
+	unsigned int smax;
+
+	/* Watch for min being lower than max due to floor calculations */
+	smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
+	return max(smin, smax);
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq;
@@ -840,6 +887,7 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
+	p->numa_scan_period_max = task_scan_max(p);
 
 	/* FIXME: Scheduling placement policy hints go here */
 }
@@ -860,9 +908,14 @@ void task_numa_fault(int node, int pages, bool migrated)
 	 * If pages are properly placed (did not migrate) then scan slower.
 	 * This is reset periodically in case of phase changes
 	 */
-        if (!migrated)
-		p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max,
-			p->numa_scan_period + jiffies_to_msecs(10));
+	if (!migrated) {
+		/* Initialise if necessary */
+		if (!p->numa_scan_period_max)
+			p->numa_scan_period_max = task_scan_max(p);
+
+		p->numa_scan_period = min(p->numa_scan_period_max,
+			p->numa_scan_period + 10);
+	}
 
 	task_numa_placement(p);
 }
@@ -884,6 +937,7 @@ void task_numa_work(struct callback_head *work)
 	struct mm_struct *mm = p->mm;
 	struct vm_area_struct *vma;
 	unsigned long start, end;
+	unsigned long nr_pte_updates = 0;
 	long pages;
 
 	WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
@@ -915,7 +969,7 @@ void task_numa_work(struct callback_head *work)
 	 */
 	migrate = mm->numa_next_reset;
 	if (time_after(now, migrate)) {
-		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+		p->numa_scan_period = task_scan_min(p);
 		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
 		xchg(&mm->numa_next_reset, next_scan);
 	}
@@ -927,8 +981,10 @@ void task_numa_work(struct callback_head *work)
 	if (time_before(now, migrate))
 		return;
 
-	if (p->numa_scan_period == 0)
-		p->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+	if (p->numa_scan_period == 0) {
+		p->numa_scan_period_max = task_scan_max(p);
+		p->numa_scan_period = task_scan_min(p);
+	}
 
 	next_scan = now + msecs_to_jiffies(p->numa_scan_period);
 	if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
@@ -965,7 +1021,15 @@ void task_numa_work(struct callback_head *work)
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
 			end = min(end, vma->vm_end);
-			pages -= change_prot_numa(vma, start, end);
+			nr_pte_updates += change_prot_numa(vma, start, end);
+
+			/*
+			 * Scan sysctl_numa_balancing_scan_size but ensure that
+			 * at least one PTE is updated so that unused virtual
+			 * address space is quickly skipped.
+			 */
+			if (nr_pte_updates)
+				pages -= (end - start) >> PAGE_SHIFT;
 
 			start = end;
 			if (pages <= 0)
@@ -1012,7 +1076,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 
 	if (now - curr->node_stamp > period) {
 		if (!curr->node_stamp)
-			curr->numa_scan_period = sysctl_numa_balancing_scan_period_min;
+			curr->numa_scan_period = task_scan_min(curr);
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan)) {
-- 
cgit 


From f809ca9a554dda49fb264c79e31c722e0b063ff8 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:28:57 +0100
Subject: sched/numa: Track NUMA hinting faults on per-node basis

This patch tracks what nodes numa hinting faults were incurred on.
This information is later used to schedule a task on the node storing
the pages most frequently faulted by the task.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-20-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  2 ++
 kernel/sched/core.c   |  3 +++
 kernel/sched/fair.c   | 11 ++++++++++-
 kernel/sched/sched.h  | 12 ++++++++++++
 4 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fdcb4c855072..a810e95bca2b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1342,6 +1342,8 @@ struct task_struct {
 	unsigned int numa_scan_period_max;
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
+
+	unsigned long *numa_faults;
 #endif /* CONFIG_NUMA_BALANCING */
 
 	struct rcu_head rcu;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index aee7e4dcbbf3..6808d35fd7ed 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1634,6 +1634,7 @@ static void __sched_fork(struct task_struct *p)
 	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
+	p->numa_faults = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
@@ -1892,6 +1893,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (mm)
 		mmdrop(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
+		task_numa_free(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c6c330245f7f..0bb3e0aa110b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -902,7 +902,14 @@ void task_numa_fault(int node, int pages, bool migrated)
 	if (!numabalancing_enabled)
 		return;
 
-	/* FIXME: Allocate task-specific structure for placement policy here */
+	/* Allocate buffer to track faults on a per-node basis */
+	if (unlikely(!p->numa_faults)) {
+		int size = sizeof(*p->numa_faults) * nr_node_ids;
+
+		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults)
+			return;
+	}
 
 	/*
 	 * If pages are properly placed (did not migrate) then scan slower.
@@ -918,6 +925,8 @@ void task_numa_fault(int node, int pages, bool migrated)
 	}
 
 	task_numa_placement(p);
+
+	p->numa_faults[node] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e82484db7699..199099c7aa22 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
 #include <linux/tick.h>
+#include <linux/slab.h>
 
 #include "cpupri.h"
 #include "cpuacct.h"
@@ -555,6 +556,17 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline void task_numa_free(struct task_struct *p)
+{
+	kfree(p->numa_faults);
+}
+#else /* CONFIG_NUMA_BALANCING */
+static inline void task_numa_free(struct task_struct *p)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #ifdef CONFIG_SMP
 
 #define rcu_dereference_check_sched_domain(p) \
-- 
cgit 


From 688b7585d16ab57a17aa4422a3b290b3a55fa679 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:28:58 +0100
Subject: sched/numa: Select a preferred node with the most numa hinting faults

This patch selects a preferred node for a task to run on based on the
NUMA hinting faults. This information is later used to migrate tasks
towards the node during balancing.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-21-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/core.c   |  1 +
 kernel/sched/fair.c   | 17 +++++++++++++++--
 3 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a810e95bca2b..b1fc75e7187b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1344,6 +1344,7 @@ struct task_struct {
 	struct callback_head numa_work;
 
 	unsigned long *numa_faults;
+	int numa_preferred_nid;
 #endif /* CONFIG_NUMA_BALANCING */
 
 	struct rcu_head rcu;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6808d35fd7ed..d15cd70f85b5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1633,6 +1633,7 @@ static void __sched_fork(struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
+	p->numa_preferred_nid = -1;
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0bb3e0aa110b..9efd34f63e81 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -879,7 +879,8 @@ static unsigned int task_scan_max(struct task_struct *p)
 
 static void task_numa_placement(struct task_struct *p)
 {
-	int seq;
+	int seq, nid, max_nid = -1;
+	unsigned long max_faults = 0;
 
 	if (!p->mm)	/* for example, ksmd faulting in a user's mm */
 		return;
@@ -889,7 +890,19 @@ static void task_numa_placement(struct task_struct *p)
 	p->numa_scan_seq = seq;
 	p->numa_scan_period_max = task_scan_max(p);
 
-	/* FIXME: Scheduling placement policy hints go here */
+	/* Find the node with the highest number of faults */
+	for_each_online_node(nid) {
+		unsigned long faults = p->numa_faults[nid];
+		p->numa_faults[nid] >>= 1;
+		if (faults > max_faults) {
+			max_faults = faults;
+			max_nid = nid;
+		}
+	}
+
+	/* Update the tasks preferred node if necessary */
+	if (max_faults && max_nid != p->numa_preferred_nid)
+		p->numa_preferred_nid = max_nid;
 }
 
 /*
-- 
cgit 


From 745d61476ddb737aad3495fa6d9a8f8c2ee59f86 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:28:59 +0100
Subject: sched/numa: Update NUMA hinting faults once per scan

NUMA hinting fault counts and placement decisions are both recorded in the
same array which distorts the samples in an unpredictable fashion. The values
linearly accumulate during the scan and then decay creating a sawtooth-like
pattern in the per-node counts. It also means that placement decisions are
time sensitive. At best it means that it is very difficult to state that
the buffer holds a decaying average of past faulting behaviour. At worst,
it can confuse the load balancer if it sees one node with an artifically high
count due to very recent faulting activity and may create a bouncing effect.

This patch adds a second array. numa_faults stores the historical data
which is used for placement decisions. numa_faults_buffer holds the
fault activity during the current scan window. When the scan completes,
numa_faults decays and the values from numa_faults_buffer are copied
across.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-22-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 13 +++++++++++++
 kernel/sched/core.c   |  1 +
 kernel/sched/fair.c   | 16 +++++++++++++---
 3 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b1fc75e7187b..a463bc3ad437 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1343,7 +1343,20 @@ struct task_struct {
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
 
+	/*
+	 * Exponential decaying average of faults on a per-node basis.
+	 * Scheduling placement decisions are made based on the these counts.
+	 * The values remain static for the duration of a PTE scan
+	 */
 	unsigned long *numa_faults;
+
+	/*
+	 * numa_faults_buffer records faults per node during the current
+	 * scan window. When the scan completes, the counts in numa_faults
+	 * decay and these values are copied.
+	 */
+	unsigned long *numa_faults_buffer;
+
 	int numa_preferred_nid;
 #endif /* CONFIG_NUMA_BALANCING */
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d15cd70f85b5..064a0af44540 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1636,6 +1636,7 @@ static void __sched_fork(struct task_struct *p)
 	p->numa_preferred_nid = -1;
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
+	p->numa_faults_buffer = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9efd34f63e81..3abc651bc38a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -892,8 +892,14 @@ static void task_numa_placement(struct task_struct *p)
 
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
-		unsigned long faults = p->numa_faults[nid];
+		unsigned long faults;
+
+		/* Decay existing window and copy faults since last scan */
 		p->numa_faults[nid] >>= 1;
+		p->numa_faults[nid] += p->numa_faults_buffer[nid];
+		p->numa_faults_buffer[nid] = 0;
+
+		faults = p->numa_faults[nid];
 		if (faults > max_faults) {
 			max_faults = faults;
 			max_nid = nid;
@@ -919,9 +925,13 @@ void task_numa_fault(int node, int pages, bool migrated)
 	if (unlikely(!p->numa_faults)) {
 		int size = sizeof(*p->numa_faults) * nr_node_ids;
 
-		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		/* numa_faults and numa_faults_buffer share the allocation */
+		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
 		if (!p->numa_faults)
 			return;
+
+		BUG_ON(p->numa_faults_buffer);
+		p->numa_faults_buffer = p->numa_faults + nr_node_ids;
 	}
 
 	/*
@@ -939,7 +949,7 @@ void task_numa_fault(int node, int pages, bool migrated)
 
 	task_numa_placement(p);
 
-	p->numa_faults[node] += pages;
+	p->numa_faults_buffer[node] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
-- 
cgit 


From 3a7053b3224f4a8b0e8184166190076593621617 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:00 +0100
Subject: sched/numa: Favour moving tasks towards the preferred node

This patch favours moving tasks towards NUMA node that recorded a higher
number of NUMA faults during active load balancing.  Ideally this is
self-reinforcing as the longer the task runs on that node, the more faults
it should incur causing task_numa_placement to keep the task running on that
node. In reality a big weakness is that the nodes CPUs can be overloaded
and it would be more efficient to queue tasks on an idle node and migrate
to the new node. This would require additional smarts in the balancer so
for now the balancer will simply prefer to place the task on the preferred
node for a PTE scans which is controlled by the numa_balancing_settle_count
sysctl. Once the settle_count number of scans has complete the schedule
is free to place the task on an alternative node if the load is imbalanced.

[srikar@linux.vnet.ibm.com: Fixed statistics]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
[ Tunable and use higher faults instead of preferred. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-23-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/sysctl/kernel.txt |  8 +++++-
 include/linux/sched.h           |  1 +
 kernel/sched/core.c             |  3 +-
 kernel/sched/fair.c             | 63 ++++++++++++++++++++++++++++++++++++++---
 kernel/sched/features.h         |  7 +++++
 kernel/sysctl.c                 |  7 +++++
 6 files changed, 83 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 8cd7e5fc79da..d48bca45b6f2 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -375,7 +375,8 @@ feature should be disabled. Otherwise, if the system overhead from the
 feature is too high then the rate the kernel samples for NUMA hinting
 faults may be controlled by the numa_balancing_scan_period_min_ms,
 numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset,
-numa_balancing_scan_period_max_ms and numa_balancing_scan_size_mb sysctls.
+numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb and
+numa_balancing_settle_count sysctls.
 
 ==============================================================
 
@@ -420,6 +421,11 @@ scanned for a given scan.
 numa_balancing_scan_period_reset is a blunt instrument that controls how
 often a tasks scan delay is reset to detect sudden changes in task behaviour.
 
+numa_balancing_settle_count is how many scan periods must complete before
+the schedule balancer stops pushing the task towards a preferred node. This
+gives the scheduler a chance to place the task on an alternative node if the
+preferred node is overloaded.
+
 ==============================================================
 
 osrelease, ostype & version:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a463bc3ad437..aecdc5a18773 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -777,6 +777,7 @@ enum cpu_idle_type {
 #define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 #define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
+#define SD_NUMA			0x4000	/* cross-node balancing */
 
 extern int __weak arch_sd_sibiling_asym_packing(void);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 064a0af44540..b7e6b6f9c5f6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1631,7 +1631,7 @@ static void __sched_fork(struct task_struct *p)
 
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0;
+	p->numa_migrate_seq = 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_preferred_nid = -1;
 	p->numa_work.next = &p->numa_work;
@@ -5656,6 +5656,7 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 1*SD_SERIALIZE
 					| 0*SD_PREFER_SIBLING
+					| 1*SD_NUMA
 					| sd_local_flags(level)
 					,
 		.last_balance		= jiffies,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3abc651bc38a..6ffddca687fe 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -877,6 +877,15 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
+/*
+ * Once a preferred node is selected the scheduler balancer will prefer moving
+ * a task to that node for sysctl_numa_balancing_settle_count number of PTE
+ * scans. This will give the process the chance to accumulate more faults on
+ * the preferred node but still allow the scheduler to move the task again if
+ * the nodes CPUs are overloaded.
+ */
+unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3;
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1;
@@ -888,6 +897,7 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
+	p->numa_migrate_seq++;
 	p->numa_scan_period_max = task_scan_max(p);
 
 	/* Find the node with the highest number of faults */
@@ -907,8 +917,10 @@ static void task_numa_placement(struct task_struct *p)
 	}
 
 	/* Update the tasks preferred node if necessary */
-	if (max_faults && max_nid != p->numa_preferred_nid)
+	if (max_faults && max_nid != p->numa_preferred_nid) {
 		p->numa_preferred_nid = max_nid;
+		p->numa_migrate_seq = 0;
+	}
 }
 
 /*
@@ -4071,6 +4083,38 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	return delta < (s64)sysctl_sched_migration_cost;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Returns true if the destination node has incurred more faults */
+static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
+{
+	int src_nid, dst_nid;
+
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
+	    !(env->sd->flags & SD_NUMA)) {
+		return false;
+	}
+
+	src_nid = cpu_to_node(env->src_cpu);
+	dst_nid = cpu_to_node(env->dst_cpu);
+
+	if (src_nid == dst_nid ||
+	    p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
+		return false;
+
+	if (dst_nid == p->numa_preferred_nid ||
+	    p->numa_faults[dst_nid] > p->numa_faults[src_nid])
+		return true;
+
+	return false;
+}
+#else
+static inline bool migrate_improves_locality(struct task_struct *p,
+					     struct lb_env *env)
+{
+	return false;
+}
+#endif
+
 /*
  * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
  */
@@ -4128,11 +4172,22 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 
 	/*
 	 * Aggressive migration if:
-	 * 1) task is cache cold, or
-	 * 2) too many balance attempts have failed.
+	 * 1) destination numa is preferred
+	 * 2) task is cache cold, or
+	 * 3) too many balance attempts have failed.
 	 */
-
 	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
+
+	if (migrate_improves_locality(p, env)) {
+#ifdef CONFIG_SCHEDSTATS
+		if (tsk_cache_hot) {
+			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+			schedstat_inc(p, se.statistics.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
+
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index cba5c616a157..d9278ce2c4b4 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -67,4 +67,11 @@ SCHED_FEAT(LB_MIN, false)
  */
 #ifdef CONFIG_NUMA_BALANCING
 SCHED_FEAT(NUMA,	false)
+
+/*
+ * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a
+ * higher number of hinting faults are recorded during active load
+ * balancing.
+ */
+SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
 #endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2f06f3c6a3f..42f616a74f40 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -391,6 +391,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname       = "numa_balancing_settle_count",
+		.data           = &sysctl_numa_balancing_settle_count,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
-- 
cgit 


From ac8e895bd260cb8bb19ade6a3abd44e7abe9a01d Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:03 +0100
Subject: sched/numa: Add infrastructure for split shared/private accounting of
 NUMA hinting faults

Ideally it would be possible to distinguish between NUMA hinting faults
that are private to a task and those that are shared.  This patch prepares
infrastructure for separately accounting shared and private faults by
allocating the necessary buffers and passing in relevant information. For
now, all faults are treated as private and detection will be introduced
later.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-26-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  5 +++--
 kernel/sched/fair.c   | 46 +++++++++++++++++++++++++++++++++++-----------
 mm/huge_memory.c      |  5 +++--
 mm/memory.c           |  8 ++++++--
 4 files changed, 47 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index aecdc5a18773..d946195eec10 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1445,10 +1445,11 @@ struct task_struct {
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
 #ifdef CONFIG_NUMA_BALANCING
-extern void task_numa_fault(int node, int pages, bool migrated);
+extern void task_numa_fault(int last_node, int node, int pages, bool migrated);
 extern void set_numabalancing_state(bool enabled);
 #else
-static inline void task_numa_fault(int node, int pages, bool migrated)
+static inline void task_numa_fault(int last_node, int node, int pages,
+				   bool migrated)
 {
 }
 static inline void set_numabalancing_state(bool enabled)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8b15e9e1d1b8..89eeb89fd99a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -886,6 +886,20 @@ static unsigned int task_scan_max(struct task_struct *p)
  */
 unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3;
 
+static inline int task_faults_idx(int nid, int priv)
+{
+	return 2 * nid + priv;
+}
+
+static inline unsigned long task_faults(struct task_struct *p, int nid)
+{
+	if (!p->numa_faults)
+		return 0;
+
+	return p->numa_faults[task_faults_idx(nid, 0)] +
+		p->numa_faults[task_faults_idx(nid, 1)];
+}
+
 static unsigned long weighted_cpuload(const int cpu);
 
 
@@ -928,13 +942,19 @@ static void task_numa_placement(struct task_struct *p)
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
 		unsigned long faults;
+		int priv, i;
 
-		/* Decay existing window and copy faults since last scan */
-		p->numa_faults[nid] >>= 1;
-		p->numa_faults[nid] += p->numa_faults_buffer[nid];
-		p->numa_faults_buffer[nid] = 0;
+		for (priv = 0; priv < 2; priv++) {
+			i = task_faults_idx(nid, priv);
 
-		faults = p->numa_faults[nid];
+			/* Decay existing window, copy faults since last scan */
+			p->numa_faults[i] >>= 1;
+			p->numa_faults[i] += p->numa_faults_buffer[i];
+			p->numa_faults_buffer[i] = 0;
+		}
+
+		/* Find maximum private faults */
+		faults = p->numa_faults[task_faults_idx(nid, 1)];
 		if (faults > max_faults) {
 			max_faults = faults;
 			max_nid = nid;
@@ -970,16 +990,20 @@ static void task_numa_placement(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int node, int pages, bool migrated)
+void task_numa_fault(int last_nid, int node, int pages, bool migrated)
 {
 	struct task_struct *p = current;
+	int priv;
 
 	if (!numabalancing_enabled)
 		return;
 
+	/* For now, do not attempt to detect private/shared accesses */
+	priv = 1;
+
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
-		int size = sizeof(*p->numa_faults) * nr_node_ids;
+		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
 
 		/* numa_faults and numa_faults_buffer share the allocation */
 		p->numa_faults = kzalloc(size * 2, GFP_KERNEL|__GFP_NOWARN);
@@ -987,7 +1011,7 @@ void task_numa_fault(int node, int pages, bool migrated)
 			return;
 
 		BUG_ON(p->numa_faults_buffer);
-		p->numa_faults_buffer = p->numa_faults + nr_node_ids;
+		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
 	}
 
 	/*
@@ -1005,7 +1029,7 @@ void task_numa_fault(int node, int pages, bool migrated)
 
 	task_numa_placement(p);
 
-	p->numa_faults_buffer[node] += pages;
+	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
@@ -4146,7 +4170,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 		return false;
 
 	if (dst_nid == p->numa_preferred_nid ||
-	    p->numa_faults[dst_nid] > p->numa_faults[src_nid])
+	    task_faults(p, dst_nid) > task_faults(p, src_nid))
 		return true;
 
 	return false;
@@ -4170,7 +4194,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	    p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
 		return false;
 
-	if (p->numa_faults[dst_nid] < p->numa_faults[src_nid])
+	if (task_faults(p, dst_nid) < task_faults(p, src_nid))
 		return true;
 
 	return false;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8677dbf31c2e..914216733e0a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1282,7 +1282,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int page_nid = -1, this_nid = numa_node_id();
-	int target_nid;
+	int target_nid, last_nid = -1;
 	bool page_locked;
 	bool migrated = false;
 
@@ -1293,6 +1293,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
+	last_nid = page_nid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
@@ -1361,7 +1362,7 @@ out:
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(last_nid, page_nid, HPAGE_PMD_NR, migrated);
 
 	return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index ed51f15136ee..24bc9b848af6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3536,6 +3536,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	int page_nid = -1;
+	int last_nid;
 	int target_nid;
 	bool migrated = false;
 
@@ -3566,6 +3567,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
+	last_nid = page_nid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
@@ -3581,7 +3583,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 out:
 	if (page_nid != -1)
-		task_numa_fault(page_nid, 1, migrated);
+		task_numa_fault(last_nid, page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3596,6 +3598,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
+	int last_nid;
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3643,6 +3646,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
+		last_nid = page_nid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
@@ -3655,7 +3659,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		if (page_nid != -1)
-			task_numa_fault(page_nid, 1, migrated);
+			task_numa_fault(last_nid, page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
-- 
cgit 


From 1bc115d87dffd1c43bdc3c9c9d1e3a51c195d18e Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:05 +0100
Subject: mm: numa: Scan pages with elevated page_mapcount

Currently automatic NUMA balancing is unable to distinguish between false
shared versus private pages except by ignoring pages with an elevated
page_mapcount entirely. This avoids shared pages bouncing between the
nodes whose task is using them but that is ignored quite a lot of data.

This patch kicks away the training wheels in preparation for adding support
for identifying shared/private pages is now in place. The ordering is so
that the impact of the shared/private detection can be easily measured. Note
that the patch does not migrate shared, file-backed within vmas marked
VM_EXEC as these are generally shared library pages. Migrating such pages
is not beneficial as there is an expectation they are read-shared between
caches and iTLB and iCache pressure is generally low.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-28-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/migrate.h |  7 ++++---
 mm/huge_memory.c        | 12 +++++-------
 mm/memory.c             |  7 ++-----
 mm/migrate.c            | 17 ++++++-----------
 mm/mprotect.c           |  4 +---
 5 files changed, 18 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 8d3c57fdf221..f5096b58b20d 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -90,11 +90,12 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
-extern int migrate_misplaced_page(struct page *page, int node);
-extern int migrate_misplaced_page(struct page *page, int node);
+extern int migrate_misplaced_page(struct page *page,
+				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
 #else
-static inline int migrate_misplaced_page(struct page *page, int node)
+static inline int migrate_misplaced_page(struct page *page,
+					 struct vm_area_struct *vma, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 914216733e0a..2a28c2c6c165 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1484,14 +1484,12 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			struct page *page = pmd_page(*pmd);
 
 			/*
-			 * Only check non-shared pages. Do not trap faults
-			 * against the zero page. The read-only data is likely
-			 * to be read-cached on the local CPU cache and it is
-			 * less useful to know about local vs remote hits on
-			 * the zero page.
+			 * Do not trap faults against the zero page. The
+			 * read-only data is likely to be read-cached on the
+			 * local CPU cache and it is less useful to know about
+			 * local vs remote hits on the zero page.
 			 */
-			if (page_mapcount(page) == 1 &&
-			    !is_huge_zero_page(page) &&
+			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
 				entry = pmdp_get_and_clear(mm, addr, pmd);
 				entry = pmd_mknuma(entry);
diff --git a/mm/memory.c b/mm/memory.c
index 24bc9b848af6..3e3b4b8b6c41 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3577,7 +3577,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	/* Migrate to the requested node */
-	migrated = migrate_misplaced_page(page, target_nid);
+	migrated = migrate_misplaced_page(page, vma, target_nid);
 	if (migrated)
 		page_nid = target_nid;
 
@@ -3642,16 +3642,13 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page = vm_normal_page(vma, addr, pteval);
 		if (unlikely(!page))
 			continue;
-		/* only check non-shared pages */
-		if (unlikely(page_mapcount(page) != 1))
-			continue;
 
 		last_nid = page_nid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
 		if (target_nid != -1) {
-			migrated = migrate_misplaced_page(page, target_nid);
+			migrated = migrate_misplaced_page(page, vma, target_nid);
 			if (migrated)
 				page_nid = target_nid;
 		} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index 7bd90d3b16bb..fcba2f46bb80 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1599,7 +1599,8 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
  * node. Caller is expected to have an elevated reference count on
  * the page that will be dropped by this function before returning.
  */
-int migrate_misplaced_page(struct page *page, int node)
+int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
+			   int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated;
@@ -1607,10 +1608,11 @@ int migrate_misplaced_page(struct page *page, int node)
 	LIST_HEAD(migratepages);
 
 	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
+	 * Don't migrate file pages that are mapped in multiple processes
+	 * with execute permissions as they are probably shared libraries.
 	 */
-	if (page_mapcount(page) != 1)
+	if (page_mapcount(page) != 1 && page_is_file_cache(page) &&
+	    (vma->vm_flags & VM_EXEC))
 		goto out;
 
 	/*
@@ -1660,13 +1662,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
 
-	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
-	 */
-	if (page_mapcount(page) != 1)
-		goto out_dropref;
-
 	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
 	 * Optimal placement is no good if the memory bus is saturated and
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2da33dca6134..41e02923fcd9 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -69,9 +69,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 					if (last_nid != this_nid)
 						all_same_node = false;
 
-					/* only check non-shared pages */
-					if (!pte_numa(oldpte) &&
-					    page_mapcount(page) == 1) {
+					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
 						updated = true;
 					}
-- 
cgit 


From b795854b1fa70f6aee923ae5df74ff7afeaddcaa Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:07 +0100
Subject: sched/numa: Set preferred NUMA node based on number of private faults

Ideally it would be possible to distinguish between NUMA hinting faults that
are private to a task and those that are shared. If treated identically
there is a risk that shared pages bounce between nodes depending on
the order they are referenced by tasks. Ultimately what is desirable is
that task private pages remain local to the task while shared pages are
interleaved between sharing tasks running on different nodes to give good
average performance. This is further complicated by THP as even
applications that partition their data may not be partitioning on a huge
page boundary.

To start with, this patch assumes that multi-threaded or multi-process
applications partition their data and that in general the private accesses
are more important for cpu->memory locality in the general case. Also,
no new infrastructure is required to treat private pages properly but
interleaving for shared pages requires additional infrastructure.

To detect private accesses the pid of the last accessing task is required
but the storage requirements are a high. This patch borrows heavily from
Ingo Molnar's patch "numa, mm, sched: Implement last-CPU+PID hash tracking"
to encode some bits from the last accessing task in the page flags as
well as the node information. Collisions will occur but it is better than
just depending on the node information. Node information is then used to
determine if a page needs to migrate. The PID information is used to detect
private/shared accesses. The preferred NUMA node is selected based on where
the maximum number of approximately private faults were measured. Shared
faults are not taken into consideration for a few reasons.

First, if there are many tasks sharing the page then they'll all move
towards the same node. The node will be compute overloaded and then
scheduled away later only to bounce back again. Alternatively the shared
tasks would just bounce around nodes because the fault information is
effectively noise. Either way accounting for shared faults the same as
private faults can result in lower performance overall.

The second reason is based on a hypothetical workload that has a small
number of very important, heavily accessed private pages but a large shared
array. The shared array would dominate the number of faults and be selected
as a preferred node even though it's the wrong decision.

The third reason is that multiple threads in a process will race each
other to fault the shared page making the fault information unreliable.

Signed-off-by: Mel Gorman <mgorman@suse.de>
[ Fix complication error when !NUMA_BALANCING. ]
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-30-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm.h                | 89 +++++++++++++++++++++++++++++----------
 include/linux/mm_types.h          |  4 +-
 include/linux/page-flags-layout.h | 28 +++++++-----
 kernel/sched/fair.c               | 12 ++++--
 mm/huge_memory.c                  |  8 ++--
 mm/memory.c                       | 16 +++----
 mm/mempolicy.c                    |  8 ++--
 mm/migrate.c                      |  4 +-
 mm/mm_init.c                      | 18 ++++----
 mm/mmzone.c                       | 14 +++---
 mm/mprotect.c                     | 26 ++++++++----
 mm/page_alloc.c                   |  4 +-
 12 files changed, 149 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b6e55ee8855..bb412ce2a8b5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -581,11 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
  * sets it, so none of the operations on it need to be atomic.
  */
 
-/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NIDPID] | ... | FLAGS | */
 #define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
 #define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
 #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
-#define LAST_NID_PGOFF		(ZONES_PGOFF - LAST_NID_WIDTH)
+#define LAST_NIDPID_PGOFF	(ZONES_PGOFF - LAST_NIDPID_WIDTH)
 
 /*
  * Define the bit shifts to access each section.  For non-existent
@@ -595,7 +595,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
 #define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
 #define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
-#define LAST_NID_PGSHIFT	(LAST_NID_PGOFF * (LAST_NID_WIDTH != 0))
+#define LAST_NIDPID_PGSHIFT	(LAST_NIDPID_PGOFF * (LAST_NIDPID_WIDTH != 0))
 
 /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
 #ifdef NODE_NOT_IN_PAGE_FLAGS
@@ -617,7 +617,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
-#define LAST_NID_MASK		((1UL << LAST_NID_WIDTH) - 1)
+#define LAST_NIDPID_MASK	((1UL << LAST_NIDPID_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
@@ -661,48 +661,93 @@ static inline int page_to_nid(const struct page *page)
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-static inline int page_nid_xchg_last(struct page *page, int nid)
+static inline int nid_pid_to_nidpid(int nid, int pid)
 {
-	return xchg(&page->_last_nid, nid);
+	return ((nid & LAST__NID_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK);
 }
 
-static inline int page_nid_last(struct page *page)
+static inline int nidpid_to_pid(int nidpid)
 {
-	return page->_last_nid;
+	return nidpid & LAST__PID_MASK;
 }
-static inline void page_nid_reset_last(struct page *page)
+
+static inline int nidpid_to_nid(int nidpid)
+{
+	return (nidpid >> LAST__PID_SHIFT) & LAST__NID_MASK;
+}
+
+static inline bool nidpid_pid_unset(int nidpid)
+{
+	return nidpid_to_pid(nidpid) == (-1 & LAST__PID_MASK);
+}
+
+static inline bool nidpid_nid_unset(int nidpid)
 {
-	page->_last_nid = -1;
+	return nidpid_to_nid(nidpid) == (-1 & LAST__NID_MASK);
+}
+
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
+static inline int page_nidpid_xchg_last(struct page *page, int nid)
+{
+	return xchg(&page->_last_nidpid, nid);
+}
+
+static inline int page_nidpid_last(struct page *page)
+{
+	return page->_last_nidpid;
+}
+static inline void page_nidpid_reset_last(struct page *page)
+{
+	page->_last_nidpid = -1;
 }
 #else
-static inline int page_nid_last(struct page *page)
+static inline int page_nidpid_last(struct page *page)
 {
-	return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+	return (page->flags >> LAST_NIDPID_PGSHIFT) & LAST_NIDPID_MASK;
 }
 
-extern int page_nid_xchg_last(struct page *page, int nid);
+extern int page_nidpid_xchg_last(struct page *page, int nidpid);
 
-static inline void page_nid_reset_last(struct page *page)
+static inline void page_nidpid_reset_last(struct page *page)
 {
-	int nid = (1 << LAST_NID_SHIFT) - 1;
+	int nidpid = (1 << LAST_NIDPID_SHIFT) - 1;
 
-	page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
-	page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+	page->flags &= ~(LAST_NIDPID_MASK << LAST_NIDPID_PGSHIFT);
+	page->flags |= (nidpid & LAST_NIDPID_MASK) << LAST_NIDPID_PGSHIFT;
 }
-#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */
+#endif /* LAST_NIDPID_NOT_IN_PAGE_FLAGS */
 #else
-static inline int page_nid_xchg_last(struct page *page, int nid)
+static inline int page_nidpid_xchg_last(struct page *page, int nidpid)
 {
 	return page_to_nid(page);
 }
 
-static inline int page_nid_last(struct page *page)
+static inline int page_nidpid_last(struct page *page)
 {
 	return page_to_nid(page);
 }
 
-static inline void page_nid_reset_last(struct page *page)
+static inline int nidpid_to_nid(int nidpid)
+{
+	return -1;
+}
+
+static inline int nidpid_to_pid(int nidpid)
+{
+	return -1;
+}
+
+static inline int nid_pid_to_nidpid(int nid, int pid)
+{
+	return -1;
+}
+
+static inline bool nidpid_pid_unset(int nidpid)
+{
+	return 1;
+}
+
+static inline void page_nidpid_reset_last(struct page *page)
 {
 }
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b7adf1d4310c..38a902a6d1e3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -174,8 +174,8 @@ struct page {
 	void *shadow;
 #endif
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-	int _last_nid;
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
+	int _last_nidpid;
 #endif
 }
 /*
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index 93506a114034..02bc9184f16b 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -38,10 +38,10 @@
  * The last is when there is insufficient space in page->flags and a separate
  * lookup is necessary.
  *
- * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |          ... | FLAGS |
- *         " plus space for last_nid: |       NODE     | ZONE | LAST_NID ... | FLAGS |
- * classic sparse with space for node:| SECTION | NODE | ZONE |          ... | FLAGS |
- *         " plus space for last_nid: | SECTION | NODE | ZONE | LAST_NID ... | FLAGS |
+ * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |             ... | FLAGS |
+ *      " plus space for last_nidpid: |       NODE     | ZONE | LAST_NIDPID ... | FLAGS |
+ * classic sparse with space for node:| SECTION | NODE | ZONE |             ... | FLAGS |
+ *      " plus space for last_nidpid: | SECTION | NODE | ZONE | LAST_NIDPID ... | FLAGS |
  * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
  */
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -62,15 +62,21 @@
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
-#define LAST_NID_SHIFT NODES_SHIFT
+#define LAST__PID_SHIFT 8
+#define LAST__PID_MASK  ((1 << LAST__PID_SHIFT)-1)
+
+#define LAST__NID_SHIFT NODES_SHIFT
+#define LAST__NID_MASK  ((1 << LAST__NID_SHIFT)-1)
+
+#define LAST_NIDPID_SHIFT (LAST__PID_SHIFT+LAST__NID_SHIFT)
 #else
-#define LAST_NID_SHIFT 0
+#define LAST_NIDPID_SHIFT 0
 #endif
 
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-#define LAST_NID_WIDTH LAST_NID_SHIFT
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NIDPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define LAST_NIDPID_WIDTH LAST_NIDPID_SHIFT
 #else
-#define LAST_NID_WIDTH 0
+#define LAST_NIDPID_WIDTH 0
 #endif
 
 /*
@@ -81,8 +87,8 @@
 #define NODE_NOT_IN_PAGE_FLAGS
 #endif
 
-#if defined(CONFIG_NUMA_BALANCING) && LAST_NID_WIDTH == 0
-#define LAST_NID_NOT_IN_PAGE_FLAGS
+#if defined(CONFIG_NUMA_BALANCING) && LAST_NIDPID_WIDTH == 0
+#define LAST_NIDPID_NOT_IN_PAGE_FLAGS
 #endif
 
 #endif /* _LINUX_PAGE_FLAGS_LAYOUT */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 862d20d02e5c..b1de7c55e9f7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -988,7 +988,7 @@ static void task_numa_placement(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_nid, int node, int pages, bool migrated)
+void task_numa_fault(int last_nidpid, int node, int pages, bool migrated)
 {
 	struct task_struct *p = current;
 	int priv;
@@ -1000,8 +1000,14 @@ void task_numa_fault(int last_nid, int node, int pages, bool migrated)
 	if (!p->mm)
 		return;
 
-	/* For now, do not attempt to detect private/shared accesses */
-	priv = 1;
+	/*
+	 * First accesses are treated as private, otherwise consider accesses
+	 * to be private if the accessing pid has not changed
+	 */
+	if (!nidpid_pid_unset(last_nidpid))
+		priv = ((p->pid & LAST__PID_MASK) == nidpid_to_pid(last_nidpid));
+	else
+		priv = 1;
 
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2a28c2c6c165..0baf0e4d5203 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1282,7 +1282,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int page_nid = -1, this_nid = numa_node_id();
-	int target_nid, last_nid = -1;
+	int target_nid, last_nidpid = -1;
 	bool page_locked;
 	bool migrated = false;
 
@@ -1293,7 +1293,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
-	last_nid = page_nid_last(page);
+	last_nidpid = page_nidpid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
@@ -1362,7 +1362,7 @@ out:
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(last_nid, page_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(last_nidpid, page_nid, HPAGE_PMD_NR, migrated);
 
 	return 0;
 }
@@ -1682,7 +1682,7 @@ static void __split_huge_page_refcount(struct page *page,
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_nid_xchg_last(page_tail, page_nid_last(page));
+		page_nidpid_xchg_last(page_tail, page_nidpid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
diff --git a/mm/memory.c b/mm/memory.c
index 3e3b4b8b6c41..cc7f20691c82 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,8 +69,8 @@
 
 #include "internal.h"
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nidpid.
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -3536,7 +3536,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	int page_nid = -1;
-	int last_nid;
+	int last_nidpid;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,7 +3567,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
-	last_nid = page_nid_last(page);
+	last_nidpid = page_nidpid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
@@ -3583,7 +3583,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 out:
 	if (page_nid != -1)
-		task_numa_fault(last_nid, page_nid, 1, migrated);
+		task_numa_fault(last_nidpid, page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3598,7 +3598,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int last_nid;
+	int last_nidpid;
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3643,7 +3643,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(!page))
 			continue;
 
-		last_nid = page_nid_last(page);
+		last_nidpid = page_nidpid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
@@ -3656,7 +3656,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		if (page_nid != -1)
-			task_numa_fault(last_nid, page_nid, 1, migrated);
+			task_numa_fault(last_nidpid, page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 04729647f359..aff1f1ed3dc5 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2348,9 +2348,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_nid;
+		int last_nidpid;
+		int this_nidpid;
 
 		polnid = numa_node_id();
+		this_nidpid = nid_pid_to_nidpid(polnid, current->pid);
 
 		/*
 		 * Multi-stage node selection is used in conjunction
@@ -2373,8 +2375,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * it less likely we act on an unlikely task<->page
 		 * relation.
 		 */
-		last_nid = page_nid_xchg_last(page, polnid);
-		if (last_nid != polnid)
+		last_nidpid = page_nidpid_xchg_last(page, this_nidpid);
+		if (!nidpid_pid_unset(last_nidpid) && nidpid_to_nid(last_nidpid) != polnid)
 			goto out;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index fcba2f46bb80..025d1e3d2ad2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1498,7 +1498,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_nid_xchg_last(newpage, page_nid_last(page));
+		page_nidpid_xchg_last(newpage, page_nidpid_last(page));
 
 	return newpage;
 }
@@ -1675,7 +1675,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	if (!new_page)
 		goto out_fail;
 
-	page_nid_xchg_last(new_page, page_nid_last(page));
+	page_nidpid_xchg_last(new_page, page_nidpid_last(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 633c08863fd8..467de579784b 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -71,26 +71,26 @@ void __init mminit_verify_pageflags_layout(void)
 	unsigned long or_mask, add_mask;
 
 	shift = 8 * sizeof(unsigned long);
-	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NID_SHIFT;
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NIDPID_SHIFT;
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-		"Section %d Node %d Zone %d Lastnid %d Flags %d\n",
+		"Section %d Node %d Zone %d Lastnidpid %d Flags %d\n",
 		SECTIONS_WIDTH,
 		NODES_WIDTH,
 		ZONES_WIDTH,
-		LAST_NID_WIDTH,
+		LAST_NIDPID_WIDTH,
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
-		"Section %d Node %d Zone %d Lastnid %d\n",
+		"Section %d Node %d Zone %d Lastnidpid %d\n",
 		SECTIONS_SHIFT,
 		NODES_SHIFT,
 		ZONES_SHIFT,
-		LAST_NID_SHIFT);
+		LAST_NIDPID_SHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
-		"Section %lu Node %lu Zone %lu Lastnid %lu\n",
+		"Section %lu Node %lu Zone %lu Lastnidpid %lu\n",
 		(unsigned long)SECTIONS_PGSHIFT,
 		(unsigned long)NODES_PGSHIFT,
 		(unsigned long)ZONES_PGSHIFT,
-		(unsigned long)LAST_NID_PGSHIFT);
+		(unsigned long)LAST_NIDPID_PGSHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
 		"Node/Zone ID: %lu -> %lu\n",
 		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
@@ -102,9 +102,9 @@ void __init mminit_verify_pageflags_layout(void)
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
 		"Node not in page flags");
 #endif
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
-		"Last nid not in page flags");
+		"Last nidpid not in page flags");
 #endif
 
 	if (SECTIONS_WIDTH) {
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 2ac0afbd68f3..25bb477deb26 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -97,20 +97,20 @@ void lruvec_init(struct lruvec *lruvec)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 }
 
-#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NID_NOT_IN_PAGE_FLAGS)
-int page_nid_xchg_last(struct page *page, int nid)
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NIDPID_NOT_IN_PAGE_FLAGS)
+int page_nidpid_xchg_last(struct page *page, int nidpid)
 {
 	unsigned long old_flags, flags;
-	int last_nid;
+	int last_nidpid;
 
 	do {
 		old_flags = flags = page->flags;
-		last_nid = page_nid_last(page);
+		last_nidpid = page_nidpid_last(page);
 
-		flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
-		flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+		flags &= ~(LAST_NIDPID_MASK << LAST_NIDPID_PGSHIFT);
+		flags |= (nidpid & LAST_NIDPID_MASK) << LAST_NIDPID_PGSHIFT;
 	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
 
-	return last_nid;
+	return last_nidpid;
 }
 #endif
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 41e02923fcd9..f0b087d1069c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,15 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+		int dirty_accountable, int prot_numa, bool *ret_all_same_nidpid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
-	bool all_same_node = true;
+	bool all_same_nidpid = true;
 	int last_nid = -1;
+	int last_pid = -1;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	arch_enter_lazy_mmu_mode();
@@ -63,11 +64,18 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
-					int this_nid = page_to_nid(page);
+					int nidpid = page_nidpid_last(page);
+					int this_nid = nidpid_to_nid(nidpid);
+					int this_pid = nidpid_to_pid(nidpid);
+
 					if (last_nid == -1)
 						last_nid = this_nid;
-					if (last_nid != this_nid)
-						all_same_node = false;
+					if (last_pid == -1)
+						last_pid = this_pid;
+					if (last_nid != this_nid ||
+					    last_pid != this_pid) {
+						all_same_nidpid = false;
+					}
 
 					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
@@ -107,7 +115,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_node = all_same_node;
+	*ret_all_same_nidpid = all_same_nidpid;
 	return pages;
 }
 
@@ -134,7 +142,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
-	bool all_same_node;
+	bool all_same_nidpid;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -158,7 +166,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		pages += change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa, &all_same_node);
+				 dirty_accountable, prot_numa, &all_same_nidpid);
 
 		/*
 		 * If we are changing protections for NUMA hinting faults then
@@ -166,7 +174,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		 * node. This allows a regular PMD to be handled as one fault
 		 * and effectively batches the taking of the PTL
 		 */
-		if (prot_numa && all_same_node)
+		if (prot_numa && all_same_nidpid)
 			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dd886fac451a..89bedd0e4cad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -626,7 +626,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
-	page_nid_reset_last(page);
+	page_nidpid_reset_last(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -4015,7 +4015,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
 		page_mapcount_reset(page);
-		page_nid_reset_last(page);
+		page_nidpid_reset_last(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for
-- 
cgit 


From fc3147245d193bd0f57307859c698fa28a20b0fe Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:09 +0100
Subject: mm: numa: Limit NUMA scanning to migrate-on-fault VMAs

There is a 90% regression observed with a large Oracle performance test
on a 4 node system. Profiles indicated that the overhead was due to
contention on sp_lock when looking up shared memory policies. These
policies do not have the appropriate flags to allow them to be
automatically balanced so trapping faults on them is pointless. This
patch skips VMAs that do not have MPOL_F_MOF set.

[riel@redhat.com: Initial patch]

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-and-tested-by: Joe Mario <jmario@redhat.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-32-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mempolicy.h |  1 +
 kernel/sched/fair.c       |  2 +-
 mm/mempolicy.c            | 24 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index da6716b9e3fe..ea4d2495c646 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -136,6 +136,7 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 
 struct mempolicy *get_vma_policy(struct task_struct *tsk,
 		struct vm_area_struct *vma, unsigned long addr);
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 61ec0d4765b9..d98175d5c2c6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1130,7 +1130,7 @@ void task_numa_work(struct callback_head *work)
 		vma = mm->mmap;
 	}
 	for (; vma; vma = vma->vm_next) {
-		if (!vma_migratable(vma))
+		if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
 			continue;
 
 		do {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 196d8da2b657..0e895a2eed5f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1679,6 +1679,30 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 	return pol;
 }
 
+bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+{
+	struct mempolicy *pol = get_task_policy(task);
+	if (vma) {
+		if (vma->vm_ops && vma->vm_ops->get_policy) {
+			bool ret = false;
+
+			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+			if (pol && (pol->flags & MPOL_F_MOF))
+				ret = true;
+			mpol_cond_put(pol);
+
+			return ret;
+		} else if (vma->vm_policy) {
+			pol = vma->vm_policy;
+		}
+	}
+
+	if (!pol)
+		return default_policy.flags & MPOL_F_MOF;
+
+	return pol->flags & MPOL_F_MOF;
+}
+
 static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone)
 {
 	enum zone_type dynamic_policy_zone = policy_zone;
-- 
cgit 


From 6b9a7460b6baf6c77fc3d23d927ddfc3f3f05bf3 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:11 +0100
Subject: sched/numa: Retry migration of tasks to CPU on a preferred node

When a preferred node is selected for a tasks there is an attempt to migrate
the task to a CPU there. This may fail in which case the task will only
migrate if the active load balancer takes action. This may never happen if
the conditions are not right. This patch will check at NUMA hinting fault
time if another attempt should be made to migrate the task. It will only
make an attempt once every five seconds.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-34-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/fair.c   | 30 +++++++++++++++++++++++-------
 2 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d946195eec10..14251a8ff2ea 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1341,6 +1341,7 @@ struct task_struct {
 	int numa_migrate_seq;
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
+	unsigned long numa_migrate_retry;
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 51a760081193..f84ac3fb581b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1011,6 +1011,23 @@ migrate:
 	return migrate_task_to(p, env.best_cpu);
 }
 
+/* Attempt to migrate a task to a CPU on the preferred node. */
+static void numa_migrate_preferred(struct task_struct *p)
+{
+	/* Success if task is already running on preferred CPU */
+	p->numa_migrate_retry = 0;
+	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+		return;
+
+	/* This task has no NUMA fault statistics yet */
+	if (unlikely(p->numa_preferred_nid == -1))
+		return;
+
+	/* Otherwise, try migrate to a CPU on the preferred node */
+	if (task_numa_migrate(p) != 0)
+		p->numa_migrate_retry = jiffies + HZ*5;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1;
@@ -1045,17 +1062,12 @@ static void task_numa_placement(struct task_struct *p)
 		}
 	}
 
-	/*
-	 * Record the preferred node as the node with the most faults,
-	 * requeue the task to be running on the idlest CPU on the
-	 * preferred node and reset the scanning rate to recheck
-	 * the working set placement.
-	 */
+	/* Preferred node as the node with the most faults */
 	if (max_faults && max_nid != p->numa_preferred_nid) {
 		/* Update the preferred nid and migrate task if possible */
 		p->numa_preferred_nid = max_nid;
 		p->numa_migrate_seq = 1;
-		task_numa_migrate(p);
+		numa_migrate_preferred(p);
 	}
 }
 
@@ -1111,6 +1123,10 @@ void task_numa_fault(int last_nidpid, int node, int pages, bool migrated)
 
 	task_numa_placement(p);
 
+	/* Retry task to preferred node migration if it previously failed */
+	if (p->numa_migrate_retry && time_after(jiffies, p->numa_migrate_retry))
+		numa_migrate_preferred(p);
+
 	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
 }
 
-- 
cgit 


From 1be0bd77c5dd7c903f46abf52f9a3650face3c1d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Oct 2013 11:29:15 +0100
Subject: stop_machine: Introduce stop_two_cpus()

Introduce stop_two_cpus() in order to allow controlled swapping of two
tasks. It repurposes the stop_machine() state machine but only stops
the two cpus which we can do with on-stack structures and avoid
machine wide synchronization issues.

The ordering of CPUs is important to avoid deadlocks. If unordered then
two cpus calling stop_two_cpus on each other simultaneously would attempt
to queue in the opposite order on each CPU causing an AB-BA style deadlock.
By always having the lowest number CPU doing the queueing of works, we can
guarantee that works are always queued in the same order, and deadlocks
are avoided.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
[ Implemented deadlock avoidance. ]
Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1381141781-10992-38-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/stop_machine.h |   1 +
 kernel/stop_machine.c        | 272 +++++++++++++++++++++++++++----------------
 2 files changed, 175 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 3b5e910d14ca..d2abbdb8c6aa 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -28,6 +28,7 @@ struct cpu_stop_work {
 };
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg);
 void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c09f2955ae30..32a6c44d8f78 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -115,6 +115,166 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 	return done.executed ? done.ret : -ENOENT;
 }
 
+/* This controls the threads on each CPU. */
+enum multi_stop_state {
+	/* Dummy starting state for thread. */
+	MULTI_STOP_NONE,
+	/* Awaiting everyone to be scheduled. */
+	MULTI_STOP_PREPARE,
+	/* Disable interrupts. */
+	MULTI_STOP_DISABLE_IRQ,
+	/* Run the function */
+	MULTI_STOP_RUN,
+	/* Exit */
+	MULTI_STOP_EXIT,
+};
+
+struct multi_stop_data {
+	int			(*fn)(void *);
+	void			*data;
+	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+	unsigned int		num_threads;
+	const struct cpumask	*active_cpus;
+
+	enum multi_stop_state	state;
+	atomic_t		thread_ack;
+};
+
+static void set_state(struct multi_stop_data *msdata,
+		      enum multi_stop_state newstate)
+{
+	/* Reset ack counter. */
+	atomic_set(&msdata->thread_ack, msdata->num_threads);
+	smp_wmb();
+	msdata->state = newstate;
+}
+
+/* Last one to ack a state moves to the next state. */
+static void ack_state(struct multi_stop_data *msdata)
+{
+	if (atomic_dec_and_test(&msdata->thread_ack))
+		set_state(msdata, msdata->state + 1);
+}
+
+/* This is the cpu_stop function which stops the CPU. */
+static int multi_cpu_stop(void *data)
+{
+	struct multi_stop_data *msdata = data;
+	enum multi_stop_state curstate = MULTI_STOP_NONE;
+	int cpu = smp_processor_id(), err = 0;
+	unsigned long flags;
+	bool is_active;
+
+	/*
+	 * When called from stop_machine_from_inactive_cpu(), irq might
+	 * already be disabled.  Save the state and restore it on exit.
+	 */
+	local_save_flags(flags);
+
+	if (!msdata->active_cpus)
+		is_active = cpu == cpumask_first(cpu_online_mask);
+	else
+		is_active = cpumask_test_cpu(cpu, msdata->active_cpus);
+
+	/* Simple state machine */
+	do {
+		/* Chill out and ensure we re-read multi_stop_state. */
+		cpu_relax();
+		if (msdata->state != curstate) {
+			curstate = msdata->state;
+			switch (curstate) {
+			case MULTI_STOP_DISABLE_IRQ:
+				local_irq_disable();
+				hard_irq_disable();
+				break;
+			case MULTI_STOP_RUN:
+				if (is_active)
+					err = msdata->fn(msdata->data);
+				break;
+			default:
+				break;
+			}
+			ack_state(msdata);
+		}
+	} while (curstate != MULTI_STOP_EXIT);
+
+	local_irq_restore(flags);
+	return err;
+}
+
+struct irq_cpu_stop_queue_work_info {
+	int cpu1;
+	int cpu2;
+	struct cpu_stop_work *work1;
+	struct cpu_stop_work *work2;
+};
+
+/*
+ * This function is always run with irqs and preemption disabled.
+ * This guarantees that both work1 and work2 get queued, before
+ * our local migrate thread gets the chance to preempt us.
+ */
+static void irq_cpu_stop_queue_work(void *arg)
+{
+	struct irq_cpu_stop_queue_work_info *info = arg;
+	cpu_stop_queue_work(info->cpu1, info->work1);
+	cpu_stop_queue_work(info->cpu2, info->work2);
+}
+
+/**
+ * stop_two_cpus - stops two cpus
+ * @cpu1: the cpu to stop
+ * @cpu2: the other cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Stops both the current and specified CPU and runs @fn on one of them.
+ *
+ * returns when both are completed.
+ */
+int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg)
+{
+	int call_cpu;
+	struct cpu_stop_done done;
+	struct cpu_stop_work work1, work2;
+	struct irq_cpu_stop_queue_work_info call_args;
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = arg,
+		.num_threads = 2,
+		.active_cpus = cpumask_of(cpu1),
+	};
+
+	work1 = work2 = (struct cpu_stop_work){
+		.fn = multi_cpu_stop,
+		.arg = &msdata,
+		.done = &done
+	};
+
+	call_args = (struct irq_cpu_stop_queue_work_info){
+		.cpu1 = cpu1,
+		.cpu2 = cpu2,
+		.work1 = &work1,
+		.work2 = &work2,
+	};
+
+	cpu_stop_init_done(&done, 2);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+
+	/*
+	 * Queuing needs to be done by the lowest numbered CPU, to ensure
+	 * that works are always queued in the same order on every CPU.
+	 * This prevents deadlocks.
+	 */
+	call_cpu = min(cpu1, cpu2);
+
+	smp_call_function_single(call_cpu, &irq_cpu_stop_queue_work,
+				 &call_args, 0);
+
+	wait_for_completion(&done.completion);
+	return done.executed ? done.ret : -ENOENT;
+}
+
 /**
  * stop_one_cpu_nowait - stop a cpu but don't wait for completion
  * @cpu: cpu to stop
@@ -359,98 +519,14 @@ early_initcall(cpu_stop_init);
 
 #ifdef CONFIG_STOP_MACHINE
 
-/* This controls the threads on each CPU. */
-enum stopmachine_state {
-	/* Dummy starting state for thread. */
-	STOPMACHINE_NONE,
-	/* Awaiting everyone to be scheduled. */
-	STOPMACHINE_PREPARE,
-	/* Disable interrupts. */
-	STOPMACHINE_DISABLE_IRQ,
-	/* Run the function */
-	STOPMACHINE_RUN,
-	/* Exit */
-	STOPMACHINE_EXIT,
-};
-
-struct stop_machine_data {
-	int			(*fn)(void *);
-	void			*data;
-	/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-	unsigned int		num_threads;
-	const struct cpumask	*active_cpus;
-
-	enum stopmachine_state	state;
-	atomic_t		thread_ack;
-};
-
-static void set_state(struct stop_machine_data *smdata,
-		      enum stopmachine_state newstate)
-{
-	/* Reset ack counter. */
-	atomic_set(&smdata->thread_ack, smdata->num_threads);
-	smp_wmb();
-	smdata->state = newstate;
-}
-
-/* Last one to ack a state moves to the next state. */
-static void ack_state(struct stop_machine_data *smdata)
-{
-	if (atomic_dec_and_test(&smdata->thread_ack))
-		set_state(smdata, smdata->state + 1);
-}
-
-/* This is the cpu_stop function which stops the CPU. */
-static int stop_machine_cpu_stop(void *data)
-{
-	struct stop_machine_data *smdata = data;
-	enum stopmachine_state curstate = STOPMACHINE_NONE;
-	int cpu = smp_processor_id(), err = 0;
-	unsigned long flags;
-	bool is_active;
-
-	/*
-	 * When called from stop_machine_from_inactive_cpu(), irq might
-	 * already be disabled.  Save the state and restore it on exit.
-	 */
-	local_save_flags(flags);
-
-	if (!smdata->active_cpus)
-		is_active = cpu == cpumask_first(cpu_online_mask);
-	else
-		is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
-
-	/* Simple state machine */
-	do {
-		/* Chill out and ensure we re-read stopmachine_state. */
-		cpu_relax();
-		if (smdata->state != curstate) {
-			curstate = smdata->state;
-			switch (curstate) {
-			case STOPMACHINE_DISABLE_IRQ:
-				local_irq_disable();
-				hard_irq_disable();
-				break;
-			case STOPMACHINE_RUN:
-				if (is_active)
-					err = smdata->fn(smdata->data);
-				break;
-			default:
-				break;
-			}
-			ack_state(smdata);
-		}
-	} while (curstate != STOPMACHINE_EXIT);
-
-	local_irq_restore(flags);
-	return err;
-}
-
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
-					    .num_threads = num_online_cpus(),
-					    .active_cpus = cpus };
+	struct multi_stop_data msdata = {
+		.fn = fn,
+		.data = data,
+		.num_threads = num_online_cpus(),
+		.active_cpus = cpus,
+	};
 
 	if (!stop_machine_initialized) {
 		/*
@@ -461,7 +537,7 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 		unsigned long flags;
 		int ret;
 
-		WARN_ON_ONCE(smdata.num_threads != 1);
+		WARN_ON_ONCE(msdata.num_threads != 1);
 
 		local_irq_save(flags);
 		hard_irq_disable();
@@ -472,8 +548,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 	}
 
 	/* Set the initial state and stop all online cpus. */
-	set_state(&smdata, STOPMACHINE_PREPARE);
-	return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
+	set_state(&msdata, MULTI_STOP_PREPARE);
+	return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata);
 }
 
 int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
@@ -513,25 +589,25 @@ EXPORT_SYMBOL_GPL(stop_machine);
 int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
 				  const struct cpumask *cpus)
 {
-	struct stop_machine_data smdata = { .fn = fn, .data = data,
+	struct multi_stop_data msdata = { .fn = fn, .data = data,
 					    .active_cpus = cpus };
 	struct cpu_stop_done done;
 	int ret;
 
 	/* Local CPU must be inactive and CPU hotplug in progress. */
 	BUG_ON(cpu_active(raw_smp_processor_id()));
-	smdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
+	msdata.num_threads = num_active_cpus() + 1;	/* +1 for local */
 
 	/* No proper task established and can't sleep - busy wait for lock. */
 	while (!mutex_trylock(&stop_cpus_mutex))
 		cpu_relax();
 
 	/* Schedule work on other CPUs and execute directly for local CPU */
-	set_state(&smdata, STOPMACHINE_PREPARE);
+	set_state(&msdata, MULTI_STOP_PREPARE);
 	cpu_stop_init_done(&done, num_active_cpus());
-	queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
+	queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata,
 			     &done);
-	ret = stop_machine_cpu_stop(&smdata);
+	ret = multi_cpu_stop(&msdata);
 
 	/* Busy wait for completion. */
 	while (!completion_done(&done.completion))
-- 
cgit 


From ac66f5477239ebd3c4e2cbf2f591ef387aa09884 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Oct 2013 11:29:16 +0100
Subject: sched/numa: Introduce migrate_swap()

Use the new stop_two_cpus() to implement migrate_swap(), a function that
flips two tasks between their respective cpus.

I'm fairly sure there's a less crude way than employing the stop_two_cpus()
method, but everything I tried either got horribly fragile and/or complex. So
keep it simple for now.

The notable detail is how we 'migrate' tasks that aren't runnable
anymore. We'll make it appear like we migrated them before they went to
sleep. The sole difference is the previous cpu in the wakeup path, so we
override this.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1381141781-10992-39-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h    |   2 +
 kernel/sched/core.c      | 106 ++++++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/fair.c      |   3 +-
 kernel/sched/idle_task.c |   2 +-
 kernel/sched/rt.c        |   5 +--
 kernel/sched/sched.h     |   4 +-
 kernel/sched/stop_task.c |   2 +-
 7 files changed, 110 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 14251a8ff2ea..b6619792bb13 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1043,6 +1043,8 @@ struct task_struct {
 	struct task_struct *last_wakee;
 	unsigned long wakee_flips;
 	unsigned long wakee_flip_decay_ts;
+
+	int wake_cpu;
 #endif
 	int on_rq;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9060a7f4e9ed..32a2b29c2610 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1013,6 +1013,102 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+static void __migrate_swap_task(struct task_struct *p, int cpu)
+{
+	if (p->on_rq) {
+		struct rq *src_rq, *dst_rq;
+
+		src_rq = task_rq(p);
+		dst_rq = cpu_rq(cpu);
+
+		deactivate_task(src_rq, p, 0);
+		set_task_cpu(p, cpu);
+		activate_task(dst_rq, p, 0);
+		check_preempt_curr(dst_rq, p, 0);
+	} else {
+		/*
+		 * Task isn't running anymore; make it appear like we migrated
+		 * it before it went to sleep. This means on wakeup we make the
+		 * previous cpu our targer instead of where it really is.
+		 */
+		p->wake_cpu = cpu;
+	}
+}
+
+struct migration_swap_arg {
+	struct task_struct *src_task, *dst_task;
+	int src_cpu, dst_cpu;
+};
+
+static int migrate_swap_stop(void *data)
+{
+	struct migration_swap_arg *arg = data;
+	struct rq *src_rq, *dst_rq;
+	int ret = -EAGAIN;
+
+	src_rq = cpu_rq(arg->src_cpu);
+	dst_rq = cpu_rq(arg->dst_cpu);
+
+	double_rq_lock(src_rq, dst_rq);
+	if (task_cpu(arg->dst_task) != arg->dst_cpu)
+		goto unlock;
+
+	if (task_cpu(arg->src_task) != arg->src_cpu)
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task)))
+		goto unlock;
+
+	if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task)))
+		goto unlock;
+
+	__migrate_swap_task(arg->src_task, arg->dst_cpu);
+	__migrate_swap_task(arg->dst_task, arg->src_cpu);
+
+	ret = 0;
+
+unlock:
+	double_rq_unlock(src_rq, dst_rq);
+
+	return ret;
+}
+
+/*
+ * Cross migrate two tasks
+ */
+int migrate_swap(struct task_struct *cur, struct task_struct *p)
+{
+	struct migration_swap_arg arg;
+	int ret = -EINVAL;
+
+	get_online_cpus();
+
+	arg = (struct migration_swap_arg){
+		.src_task = cur,
+		.src_cpu = task_cpu(cur),
+		.dst_task = p,
+		.dst_cpu = task_cpu(p),
+	};
+
+	if (arg.src_cpu == arg.dst_cpu)
+		goto out;
+
+	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task)))
+		goto out;
+
+	if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task)))
+		goto out;
+
+	ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg);
+
+out:
+	put_online_cpus();
+	return ret;
+}
+
 struct migration_arg {
 	struct task_struct *task;
 	int dest_cpu;
@@ -1232,9 +1328,9 @@ out:
  * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 {
-	int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+	cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
@@ -1518,7 +1614,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (p->sched_class->task_waking)
 		p->sched_class->task_waking(p);
 
-	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
@@ -1752,7 +1848,7 @@ void wake_up_new_task(struct task_struct *p)
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
 	 */
-	set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0));
+	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 
 	/* Initialize new task's runnable average */
@@ -2080,7 +2176,7 @@ void sched_exec(void)
 	int dest_cpu;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0);
+	dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
 	if (dest_cpu == smp_processor_id())
 		goto unlock;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fbc0c84a8a04..b1e5061287ab 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3706,11 +3706,10 @@ done:
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
 {
 	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
 	int cpu = smp_processor_id();
-	int prev_cpu = task_cpu(p);
 	int new_cpu = cpu;
 	int want_affine = 0;
 	int sync = wake_flags & WF_SYNC;
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index d8da01008d39..516c3d9ceea1 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -9,7 +9,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ceebfba0a1dd..e9304cdc26fe 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1169,13 +1169,10 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
 	struct rq *rq;
-	int cpu;
-
-	cpu = task_cpu(p);
 
 	if (p->nr_cpus_allowed == 1)
 		goto out;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 66458c902d84..4dc92d016aef 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -558,6 +558,7 @@ static inline u64 rq_clock_task(struct rq *rq)
 
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_task_to(struct task_struct *p, int cpu);
+extern int migrate_swap(struct task_struct *, struct task_struct *);
 static inline void task_numa_free(struct task_struct *p)
 {
 	kfree(p->numa_faults);
@@ -736,6 +737,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 	 */
 	smp_wmb();
 	task_thread_info(p)->cpu = cpu;
+	p->wake_cpu = cpu;
 #endif
 }
 
@@ -991,7 +993,7 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index e08fbeeb54b9..47197de8abd9 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct task_struct *p, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
-- 
cgit 


From 212e560112598cfa8a3061237dd9db5f2252e48c Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Mon, 19 Aug 2013 08:07:34 +0200
Subject: ipv6: Add a receive path hook for vti6 in xfrm6_mode_tunnel.

Add a receive path hook for the IPsec vritual tunnel interface.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h           |  2 ++
 net/ipv6/xfrm6_mode_tunnel.c | 69 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b8a9ed849801..6b82fdf4ba71 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1508,6 +1508,8 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
 void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
 int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
 int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
+int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler);
+int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler);
 int xfrm6_extract_header(struct sk_buff *skb);
 int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 4770d515c2c8..cb04f7a16b5e 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -18,6 +18,65 @@
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
+/* Informational hook. The decap is still done here. */
+static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly;
+static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex);
+
+int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler)
+{
+	struct xfrm_tunnel_notifier __rcu **pprev;
+	struct xfrm_tunnel_notifier *t;
+	int ret = -EEXIST;
+	int priority = handler->priority;
+
+	mutex_lock(&xfrm6_mode_tunnel_input_mutex);
+
+	for (pprev = &rcv_notify_handlers;
+	     (t = rcu_dereference_protected(*pprev,
+	     lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t->priority > priority)
+			break;
+		if (t->priority == priority)
+			goto err;
+
+	}
+
+	handler->next = *pprev;
+	rcu_assign_pointer(*pprev, handler);
+
+	ret = 0;
+
+err:
+	mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register);
+
+int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler)
+{
+	struct xfrm_tunnel_notifier __rcu **pprev;
+	struct xfrm_tunnel_notifier *t;
+	int ret = -ENOENT;
+
+	mutex_lock(&xfrm6_mode_tunnel_input_mutex);
+	for (pprev = &rcv_notify_handlers;
+	     (t = rcu_dereference_protected(*pprev,
+	     lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL;
+	     pprev = &t->next) {
+		if (t == handler) {
+			*pprev = handler->next;
+			ret = 0;
+			break;
+		}
+	}
+	mutex_unlock(&xfrm6_mode_tunnel_input_mutex);
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister);
+
 static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
 {
 	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
@@ -63,8 +122,15 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
+#define for_each_input_rcu(head, handler)	\
+	for (handler = rcu_dereference(head);	\
+	     handler != NULL;			\
+	     handler = rcu_dereference(handler->next))
+
+
 static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
+	struct xfrm_tunnel_notifier *handler;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
@@ -72,6 +138,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto out;
 
+	for_each_input_rcu(rcv_notify_handlers, handler)
+		handler->handler(skb);
+
 	err = skb_unclone(skb, GFP_ATOMIC);
 	if (err)
 		goto out;
-- 
cgit 


From 90572890d202527c366aa9489b32404e88a7c020 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Oct 2013 11:29:20 +0100
Subject: mm: numa: Change page last {nid,pid} into {cpu,pid}

Change the per page last fault tracking to use cpu,pid instead of
nid,pid. This will allow us to try and lookup the alternate task more
easily. Note that even though it is the cpu that is store in the page
flags that the mpol_misplaced decision is still based on the node.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-43-git-send-email-mgorman@suse.de
[ Fixed build failure on 32-bit systems. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm.h                | 90 ++++++++++++++++++++++-----------------
 include/linux/mm_types.h          |  4 +-
 include/linux/page-flags-layout.h | 22 +++++-----
 kernel/bounds.c                   |  4 ++
 kernel/sched/fair.c               |  6 +--
 mm/huge_memory.c                  |  8 ++--
 mm/memory.c                       | 16 +++----
 mm/mempolicy.c                    | 16 ++++---
 mm/migrate.c                      |  4 +-
 mm/mm_init.c                      | 18 ++++----
 mm/mmzone.c                       | 14 +++---
 mm/mprotect.c                     | 28 ++++++------
 mm/page_alloc.c                   |  4 +-
 13 files changed, 125 insertions(+), 109 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index bb412ce2a8b5..ce464cd4777e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -581,11 +581,11 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
  * sets it, so none of the operations on it need to be atomic.
  */
 
-/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NIDPID] | ... | FLAGS | */
+/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
 #define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
 #define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
 #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
-#define LAST_NIDPID_PGOFF	(ZONES_PGOFF - LAST_NIDPID_WIDTH)
+#define LAST_CPUPID_PGOFF	(ZONES_PGOFF - LAST_CPUPID_WIDTH)
 
 /*
  * Define the bit shifts to access each section.  For non-existent
@@ -595,7 +595,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
 #define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
 #define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
-#define LAST_NIDPID_PGSHIFT	(LAST_NIDPID_PGOFF * (LAST_NIDPID_WIDTH != 0))
+#define LAST_CPUPID_PGSHIFT	(LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))
 
 /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
 #ifdef NODE_NOT_IN_PAGE_FLAGS
@@ -617,7 +617,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
-#define LAST_NIDPID_MASK	((1UL << LAST_NIDPID_WIDTH) - 1)
+#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
@@ -661,96 +661,106 @@ static inline int page_to_nid(const struct page *page)
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
-static inline int nid_pid_to_nidpid(int nid, int pid)
+static inline int cpu_pid_to_cpupid(int cpu, int pid)
 {
-	return ((nid & LAST__NID_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK);
+	return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK);
 }
 
-static inline int nidpid_to_pid(int nidpid)
+static inline int cpupid_to_pid(int cpupid)
 {
-	return nidpid & LAST__PID_MASK;
+	return cpupid & LAST__PID_MASK;
 }
 
-static inline int nidpid_to_nid(int nidpid)
+static inline int cpupid_to_cpu(int cpupid)
 {
-	return (nidpid >> LAST__PID_SHIFT) & LAST__NID_MASK;
+	return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK;
 }
 
-static inline bool nidpid_pid_unset(int nidpid)
+static inline int cpupid_to_nid(int cpupid)
 {
-	return nidpid_to_pid(nidpid) == (-1 & LAST__PID_MASK);
+	return cpu_to_node(cpupid_to_cpu(cpupid));
 }
 
-static inline bool nidpid_nid_unset(int nidpid)
+static inline bool cpupid_pid_unset(int cpupid)
 {
-	return nidpid_to_nid(nidpid) == (-1 & LAST__NID_MASK);
+	return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK);
 }
 
-#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
-static inline int page_nidpid_xchg_last(struct page *page, int nid)
+static inline bool cpupid_cpu_unset(int cpupid)
 {
-	return xchg(&page->_last_nidpid, nid);
+	return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK);
 }
 
-static inline int page_nidpid_last(struct page *page)
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
-	return page->_last_nidpid;
+	return xchg(&page->_last_cpupid, cpupid);
 }
-static inline void page_nidpid_reset_last(struct page *page)
+
+static inline int page_cpupid_last(struct page *page)
+{
+	return page->_last_cpupid;
+}
+static inline void page_cpupid_reset_last(struct page *page)
 {
-	page->_last_nidpid = -1;
+	page->_last_cpupid = -1;
 }
 #else
-static inline int page_nidpid_last(struct page *page)
+static inline int page_cpupid_last(struct page *page)
 {
-	return (page->flags >> LAST_NIDPID_PGSHIFT) & LAST_NIDPID_MASK;
+	return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
 }
 
-extern int page_nidpid_xchg_last(struct page *page, int nidpid);
+extern int page_cpupid_xchg_last(struct page *page, int cpupid);
 
-static inline void page_nidpid_reset_last(struct page *page)
+static inline void page_cpupid_reset_last(struct page *page)
 {
-	int nidpid = (1 << LAST_NIDPID_SHIFT) - 1;
+	int cpupid = (1 << LAST_CPUPID_SHIFT) - 1;
 
-	page->flags &= ~(LAST_NIDPID_MASK << LAST_NIDPID_PGSHIFT);
-	page->flags |= (nidpid & LAST_NIDPID_MASK) << LAST_NIDPID_PGSHIFT;
+	page->flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
+	page->flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
 }
-#endif /* LAST_NIDPID_NOT_IN_PAGE_FLAGS */
-#else
-static inline int page_nidpid_xchg_last(struct page *page, int nidpid)
+#endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */
+#else /* !CONFIG_NUMA_BALANCING */
+static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
-	return page_to_nid(page);
+	return page_to_nid(page); /* XXX */
 }
 
-static inline int page_nidpid_last(struct page *page)
+static inline int page_cpupid_last(struct page *page)
 {
-	return page_to_nid(page);
+	return page_to_nid(page); /* XXX */
 }
 
-static inline int nidpid_to_nid(int nidpid)
+static inline int cpupid_to_nid(int cpupid)
 {
 	return -1;
 }
 
-static inline int nidpid_to_pid(int nidpid)
+static inline int cpupid_to_pid(int cpupid)
 {
 	return -1;
 }
 
-static inline int nid_pid_to_nidpid(int nid, int pid)
+static inline int cpupid_to_cpu(int cpupid)
 {
 	return -1;
 }
 
-static inline bool nidpid_pid_unset(int nidpid)
+static inline int cpu_pid_to_cpupid(int nid, int pid)
+{
+	return -1;
+}
+
+static inline bool cpupid_pid_unset(int cpupid)
 {
 	return 1;
 }
 
-static inline void page_nidpid_reset_last(struct page *page)
+static inline void page_cpupid_reset_last(struct page *page)
 {
 }
-#endif
+#endif /* CONFIG_NUMA_BALANCING */
 
 static inline struct zone *page_zone(const struct page *page)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 38a902a6d1e3..a30f9ca66557 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -174,8 +174,8 @@ struct page {
 	void *shadow;
 #endif
 
-#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
-	int _last_nidpid;
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	int _last_cpupid;
 #endif
 }
 /*
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index 02bc9184f16b..da523661500a 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -39,9 +39,9 @@
  * lookup is necessary.
  *
  * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE |             ... | FLAGS |
- *      " plus space for last_nidpid: |       NODE     | ZONE | LAST_NIDPID ... | FLAGS |
+ *      " plus space for last_cpupid: |       NODE     | ZONE | LAST_CPUPID ... | FLAGS |
  * classic sparse with space for node:| SECTION | NODE | ZONE |             ... | FLAGS |
- *      " plus space for last_nidpid: | SECTION | NODE | ZONE | LAST_NIDPID ... | FLAGS |
+ *      " plus space for last_cpupid: | SECTION | NODE | ZONE | LAST_CPUPID ... | FLAGS |
  * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
  */
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -65,18 +65,18 @@
 #define LAST__PID_SHIFT 8
 #define LAST__PID_MASK  ((1 << LAST__PID_SHIFT)-1)
 
-#define LAST__NID_SHIFT NODES_SHIFT
-#define LAST__NID_MASK  ((1 << LAST__NID_SHIFT)-1)
+#define LAST__CPU_SHIFT NR_CPUS_BITS
+#define LAST__CPU_MASK  ((1 << LAST__CPU_SHIFT)-1)
 
-#define LAST_NIDPID_SHIFT (LAST__PID_SHIFT+LAST__NID_SHIFT)
+#define LAST_CPUPID_SHIFT (LAST__PID_SHIFT+LAST__CPU_SHIFT)
 #else
-#define LAST_NIDPID_SHIFT 0
+#define LAST_CPUPID_SHIFT 0
 #endif
 
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NIDPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-#define LAST_NIDPID_WIDTH LAST_NIDPID_SHIFT
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
 #else
-#define LAST_NIDPID_WIDTH 0
+#define LAST_CPUPID_WIDTH 0
 #endif
 
 /*
@@ -87,8 +87,8 @@
 #define NODE_NOT_IN_PAGE_FLAGS
 #endif
 
-#if defined(CONFIG_NUMA_BALANCING) && LAST_NIDPID_WIDTH == 0
-#define LAST_NIDPID_NOT_IN_PAGE_FLAGS
+#if defined(CONFIG_NUMA_BALANCING) && LAST_CPUPID_WIDTH == 0
+#define LAST_CPUPID_NOT_IN_PAGE_FLAGS
 #endif
 
 #endif /* _LINUX_PAGE_FLAGS_LAYOUT */
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 0c9b862292b2..e8ca97b5c386 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -10,6 +10,7 @@
 #include <linux/mmzone.h>
 #include <linux/kbuild.h>
 #include <linux/page_cgroup.h>
+#include <linux/log2.h>
 
 void foo(void)
 {
@@ -17,5 +18,8 @@ void foo(void)
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 	DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
+#ifdef CONFIG_SMP
+	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+#endif
 	/* End of constants */
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa561c8dc899..dbe0f628efa3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1210,7 +1210,7 @@ static void task_numa_placement(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_nidpid, int node, int pages, bool migrated)
+void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 {
 	struct task_struct *p = current;
 	int priv;
@@ -1226,8 +1226,8 @@ void task_numa_fault(int last_nidpid, int node, int pages, bool migrated)
 	 * First accesses are treated as private, otherwise consider accesses
 	 * to be private if the accessing pid has not changed
 	 */
-	if (!nidpid_pid_unset(last_nidpid))
-		priv = ((p->pid & LAST__PID_MASK) == nidpid_to_pid(last_nidpid));
+	if (!cpupid_pid_unset(last_cpupid))
+		priv = ((p->pid & LAST__PID_MASK) == cpupid_to_pid(last_cpupid));
 	else
 		priv = 1;
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0baf0e4d5203..becf92ca54f3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1282,7 +1282,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int page_nid = -1, this_nid = numa_node_id();
-	int target_nid, last_nidpid = -1;
+	int target_nid, last_cpupid = -1;
 	bool page_locked;
 	bool migrated = false;
 
@@ -1293,7 +1293,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
-	last_nidpid = page_nidpid_last(page);
+	last_cpupid = page_cpupid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
@@ -1362,7 +1362,7 @@ out:
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(last_nidpid, page_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, migrated);
 
 	return 0;
 }
@@ -1682,7 +1682,7 @@ static void __split_huge_page_refcount(struct page *page,
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_nidpid_xchg_last(page_tail, page_nidpid_last(page));
+		page_cpupid_xchg_last(page_tail, page_cpupid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
diff --git a/mm/memory.c b/mm/memory.c
index cc7f20691c82..5162e6d0d652 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,8 +69,8 @@
 
 #include "internal.h"
 
-#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
-#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nidpid.
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -3536,7 +3536,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	int page_nid = -1;
-	int last_nidpid;
+	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,7 +3567,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
-	last_nidpid = page_nidpid_last(page);
+	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
@@ -3583,7 +3583,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 out:
 	if (page_nid != -1)
-		task_numa_fault(last_nidpid, page_nid, 1, migrated);
+		task_numa_fault(last_cpupid, page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3598,7 +3598,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int last_nidpid;
+	int last_cpupid;
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3643,7 +3643,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(!page))
 			continue;
 
-		last_nidpid = page_nidpid_last(page);
+		last_cpupid = page_cpupid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
@@ -3656,7 +3656,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		if (page_nid != -1)
-			task_numa_fault(last_nidpid, page_nid, 1, migrated);
+			task_numa_fault(last_cpupid, page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0e895a2eed5f..a5867ef24bda 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2324,6 +2324,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 	struct zone *zone;
 	int curnid = page_to_nid(page);
 	unsigned long pgoff;
+	int thiscpu = raw_smp_processor_id();
+	int thisnid = cpu_to_node(thiscpu);
 	int polnid = -1;
 	int ret = -1;
 
@@ -2372,11 +2374,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	/* Migrate the page towards the node whose CPU is referencing it */
 	if (pol->flags & MPOL_F_MORON) {
-		int last_nidpid;
-		int this_nidpid;
+		int last_cpupid;
+		int this_cpupid;
 
-		polnid = numa_node_id();
-		this_nidpid = nid_pid_to_nidpid(polnid, current->pid);
+		polnid = thisnid;
+		this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
 
 		/*
 		 * Multi-stage node selection is used in conjunction
@@ -2399,8 +2401,8 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * it less likely we act on an unlikely task<->page
 		 * relation.
 		 */
-		last_nidpid = page_nidpid_xchg_last(page, this_nidpid);
-		if (!nidpid_pid_unset(last_nidpid) && nidpid_to_nid(last_nidpid) != polnid)
+		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid)
 			goto out;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -2410,7 +2412,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * This way a short and temporary process migration will
 		 * not cause excessive memory migration.
 		 */
-		if (polnid != current->numa_preferred_nid &&
+		if (thisnid != current->numa_preferred_nid &&
 				!current->numa_migrate_seq)
 			goto out;
 #endif
diff --git a/mm/migrate.c b/mm/migrate.c
index 025d1e3d2ad2..ff537749d3b4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1498,7 +1498,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_nidpid_xchg_last(newpage, page_nidpid_last(page));
+		page_cpupid_xchg_last(newpage, page_cpupid_last(page));
 
 	return newpage;
 }
@@ -1675,7 +1675,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	if (!new_page)
 		goto out_fail;
 
-	page_nidpid_xchg_last(new_page, page_nidpid_last(page));
+	page_cpupid_xchg_last(new_page, page_cpupid_last(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 467de579784b..68562e92d50c 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -71,26 +71,26 @@ void __init mminit_verify_pageflags_layout(void)
 	unsigned long or_mask, add_mask;
 
 	shift = 8 * sizeof(unsigned long);
-	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_NIDPID_SHIFT;
+	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT;
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-		"Section %d Node %d Zone %d Lastnidpid %d Flags %d\n",
+		"Section %d Node %d Zone %d Lastcpupid %d Flags %d\n",
 		SECTIONS_WIDTH,
 		NODES_WIDTH,
 		ZONES_WIDTH,
-		LAST_NIDPID_WIDTH,
+		LAST_CPUPID_WIDTH,
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
-		"Section %d Node %d Zone %d Lastnidpid %d\n",
+		"Section %d Node %d Zone %d Lastcpupid %d\n",
 		SECTIONS_SHIFT,
 		NODES_SHIFT,
 		ZONES_SHIFT,
-		LAST_NIDPID_SHIFT);
+		LAST_CPUPID_SHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
-		"Section %lu Node %lu Zone %lu Lastnidpid %lu\n",
+		"Section %lu Node %lu Zone %lu Lastcpupid %lu\n",
 		(unsigned long)SECTIONS_PGSHIFT,
 		(unsigned long)NODES_PGSHIFT,
 		(unsigned long)ZONES_PGSHIFT,
-		(unsigned long)LAST_NIDPID_PGSHIFT);
+		(unsigned long)LAST_CPUPID_PGSHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
 		"Node/Zone ID: %lu -> %lu\n",
 		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
@@ -102,9 +102,9 @@ void __init mminit_verify_pageflags_layout(void)
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
 		"Node not in page flags");
 #endif
-#ifdef LAST_NIDPID_NOT_IN_PAGE_FLAGS
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
-		"Last nidpid not in page flags");
+		"Last cpupid not in page flags");
 #endif
 
 	if (SECTIONS_WIDTH) {
diff --git a/mm/mmzone.c b/mm/mmzone.c
index 25bb477deb26..bf34fb8556db 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -97,20 +97,20 @@ void lruvec_init(struct lruvec *lruvec)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
 }
 
-#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_NIDPID_NOT_IN_PAGE_FLAGS)
-int page_nidpid_xchg_last(struct page *page, int nidpid)
+#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
+int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
 	unsigned long old_flags, flags;
-	int last_nidpid;
+	int last_cpupid;
 
 	do {
 		old_flags = flags = page->flags;
-		last_nidpid = page_nidpid_last(page);
+		last_cpupid = page_cpupid_last(page);
 
-		flags &= ~(LAST_NIDPID_MASK << LAST_NIDPID_PGSHIFT);
-		flags |= (nidpid & LAST_NIDPID_MASK) << LAST_NIDPID_PGSHIFT;
+		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
+		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
 	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));
 
-	return last_nidpid;
+	return last_cpupid;
 }
 #endif
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 5aae39017d6d..9a74855f1241 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,14 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa, bool *ret_all_same_nidpid)
+		int dirty_accountable, int prot_numa, bool *ret_all_same_cpupid)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;
 	unsigned long pages = 0;
-	bool all_same_nidpid = true;
-	int last_nid = -1;
+	bool all_same_cpupid = true;
+	int last_cpu = -1;
 	int last_pid = -1;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -64,17 +64,17 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
-					int nidpid = page_nidpid_last(page);
-					int this_nid = nidpid_to_nid(nidpid);
-					int this_pid = nidpid_to_pid(nidpid);
+					int cpupid = page_cpupid_last(page);
+					int this_cpu = cpupid_to_cpu(cpupid);
+					int this_pid = cpupid_to_pid(cpupid);
 
-					if (last_nid == -1)
-						last_nid = this_nid;
+					if (last_cpu == -1)
+						last_cpu = this_cpu;
 					if (last_pid == -1)
 						last_pid = this_pid;
-					if (last_nid != this_nid ||
+					if (last_cpu != this_cpu ||
 					    last_pid != this_pid) {
-						all_same_nidpid = false;
+						all_same_cpupid = false;
 					}
 
 					if (!pte_numa(oldpte)) {
@@ -115,7 +115,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
 
-	*ret_all_same_nidpid = all_same_nidpid;
+	*ret_all_same_cpupid = all_same_cpupid;
 	return pages;
 }
 
@@ -142,7 +142,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
-	bool all_same_nidpid;
+	bool all_same_cpupid;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -168,7 +168,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		this_pages = change_pte_range(vma, pmd, addr, next, newprot,
-				 dirty_accountable, prot_numa, &all_same_nidpid);
+				 dirty_accountable, prot_numa, &all_same_cpupid);
 		pages += this_pages;
 
 		/*
@@ -177,7 +177,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		 * node. This allows a regular PMD to be handled as one fault
 		 * and effectively batches the taking of the PTL
 		 */
-		if (prot_numa && this_pages && all_same_nidpid)
+		if (prot_numa && this_pages && all_same_cpupid)
 			change_pmd_protnuma(vma->vm_mm, addr, pmd);
 	} while (pmd++, addr = next, addr != end);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89bedd0e4cad..73d812f16dde 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -626,7 +626,7 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 		return 1;
 	}
-	page_nidpid_reset_last(page);
+	page_cpupid_reset_last(page);
 	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
 		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	return 0;
@@ -4015,7 +4015,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		mminit_verify_page_links(page, zone, nid, pfn);
 		init_page_count(page);
 		page_mapcount_reset(page);
-		page_nidpid_reset_last(page);
+		page_cpupid_reset_last(page);
 		SetPageReserved(page);
 		/*
 		 * Mark the block movable so that blocks are reserved for
-- 
cgit 


From 8c8a743c5087bac9caac8155b8f3b367e75cdd0b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Oct 2013 11:29:21 +0100
Subject: sched/numa: Use {cpu, pid} to create task groups for shared faults

While parallel applications tend to align their data on the cache
boundary, they tend not to align on the page or THP boundary.
Consequently tasks that partition their data can still "false-share"
pages presenting a problem for optimal NUMA placement.

This patch uses NUMA hinting faults to chain tasks together into
numa_groups. As well as storing the NID a task was running on when
accessing a page a truncated representation of the faulting PID is
stored. If subsequent faults are from different PIDs it is reasonable
to assume that those two tasks share a page and are candidates for
being grouped together. Note that this patch makes no scheduling
decisions based on the grouping information.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-44-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/mm.h    |  11 ++++
 include/linux/sched.h |   3 +
 kernel/sched/core.c   |   3 +
 kernel/sched/fair.c   | 165 +++++++++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/sched.h  |   5 +-
 mm/memory.c           |   8 +++
 6 files changed, 182 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ce464cd4777e..81443d557a2e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -691,6 +691,12 @@ static inline bool cpupid_cpu_unset(int cpupid)
 	return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK);
 }
 
+static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
+{
+	return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid);
+}
+
+#define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid)
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
 {
@@ -760,6 +766,11 @@ static inline bool cpupid_pid_unset(int cpupid)
 static inline void page_cpupid_reset_last(struct page *page)
 {
 }
+
+static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
+{
+	return false;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline struct zone *page_zone(const struct page *page)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b6619792bb13..f587ded5c148 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1347,6 +1347,9 @@ struct task_struct {
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
 
+	struct list_head numa_entry;
+	struct numa_group *numa_group;
+
 	/*
 	 * Exponential decaying average of faults on a per-node basis.
 	 * Scheduling placement decisions are made based on the these counts.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1fe59da280e3..51092d5cc64c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1733,6 +1733,9 @@ static void __sched_fork(struct task_struct *p)
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
 	p->numa_faults_buffer = NULL;
+
+	INIT_LIST_HEAD(&p->numa_entry);
+	p->numa_group = NULL;
 #endif /* CONFIG_NUMA_BALANCING */
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dbe0f628efa3..85565053a6ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -888,6 +888,17 @@ static unsigned int task_scan_max(struct task_struct *p)
  */
 unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
 
+struct numa_group {
+	atomic_t refcount;
+
+	spinlock_t lock; /* nr_tasks, tasks */
+	int nr_tasks;
+	struct list_head task_list;
+
+	struct rcu_head rcu;
+	atomic_long_t faults[0];
+};
+
 static inline int task_faults_idx(int nid, int priv)
 {
 	return 2 * nid + priv;
@@ -1182,7 +1193,10 @@ static void task_numa_placement(struct task_struct *p)
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
+			long diff;
+
 			i = task_faults_idx(nid, priv);
+			diff = -p->numa_faults[i];
 
 			/* Decay existing window, copy faults since last scan */
 			p->numa_faults[i] >>= 1;
@@ -1190,6 +1204,11 @@ static void task_numa_placement(struct task_struct *p)
 			p->numa_faults_buffer[i] = 0;
 
 			faults += p->numa_faults[i];
+			diff += p->numa_faults[i];
+			if (p->numa_group) {
+				/* safe because we can only change our own group */
+				atomic_long_add(diff, &p->numa_group->faults[i]);
+			}
 		}
 
 		if (faults > max_faults) {
@@ -1207,6 +1226,131 @@ static void task_numa_placement(struct task_struct *p)
 	}
 }
 
+static inline int get_numa_group(struct numa_group *grp)
+{
+	return atomic_inc_not_zero(&grp->refcount);
+}
+
+static inline void put_numa_group(struct numa_group *grp)
+{
+	if (atomic_dec_and_test(&grp->refcount))
+		kfree_rcu(grp, rcu);
+}
+
+static void double_lock(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
+static void task_numa_group(struct task_struct *p, int cpupid)
+{
+	struct numa_group *grp, *my_grp;
+	struct task_struct *tsk;
+	bool join = false;
+	int cpu = cpupid_to_cpu(cpupid);
+	int i;
+
+	if (unlikely(!p->numa_group)) {
+		unsigned int size = sizeof(struct numa_group) +
+				    2*nr_node_ids*sizeof(atomic_long_t);
+
+		grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+		if (!grp)
+			return;
+
+		atomic_set(&grp->refcount, 1);
+		spin_lock_init(&grp->lock);
+		INIT_LIST_HEAD(&grp->task_list);
+
+		for (i = 0; i < 2*nr_node_ids; i++)
+			atomic_long_set(&grp->faults[i], p->numa_faults[i]);
+
+		list_add(&p->numa_entry, &grp->task_list);
+		grp->nr_tasks++;
+		rcu_assign_pointer(p->numa_group, grp);
+	}
+
+	rcu_read_lock();
+	tsk = ACCESS_ONCE(cpu_rq(cpu)->curr);
+
+	if (!cpupid_match_pid(tsk, cpupid))
+		goto unlock;
+
+	grp = rcu_dereference(tsk->numa_group);
+	if (!grp)
+		goto unlock;
+
+	my_grp = p->numa_group;
+	if (grp == my_grp)
+		goto unlock;
+
+	/*
+	 * Only join the other group if its bigger; if we're the bigger group,
+	 * the other task will join us.
+	 */
+	if (my_grp->nr_tasks > grp->nr_tasks)
+		goto unlock;
+
+	/*
+	 * Tie-break on the grp address.
+	 */
+	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
+		goto unlock;
+
+	if (!get_numa_group(grp))
+		goto unlock;
+
+	join = true;
+
+unlock:
+	rcu_read_unlock();
+
+	if (!join)
+		return;
+
+	for (i = 0; i < 2*nr_node_ids; i++) {
+		atomic_long_sub(p->numa_faults[i], &my_grp->faults[i]);
+		atomic_long_add(p->numa_faults[i], &grp->faults[i]);
+	}
+
+	double_lock(&my_grp->lock, &grp->lock);
+
+	list_move(&p->numa_entry, &grp->task_list);
+	my_grp->nr_tasks--;
+	grp->nr_tasks++;
+
+	spin_unlock(&my_grp->lock);
+	spin_unlock(&grp->lock);
+
+	rcu_assign_pointer(p->numa_group, grp);
+
+	put_numa_group(my_grp);
+}
+
+void task_numa_free(struct task_struct *p)
+{
+	struct numa_group *grp = p->numa_group;
+	int i;
+
+	if (grp) {
+		for (i = 0; i < 2*nr_node_ids; i++)
+			atomic_long_sub(p->numa_faults[i], &grp->faults[i]);
+
+		spin_lock(&grp->lock);
+		list_del(&p->numa_entry);
+		grp->nr_tasks--;
+		spin_unlock(&grp->lock);
+		rcu_assign_pointer(p->numa_group, NULL);
+		put_numa_group(grp);
+	}
+
+	kfree(p->numa_faults);
+}
+
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
@@ -1222,15 +1366,6 @@ void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 	if (!p->mm)
 		return;
 
-	/*
-	 * First accesses are treated as private, otherwise consider accesses
-	 * to be private if the accessing pid has not changed
-	 */
-	if (!cpupid_pid_unset(last_cpupid))
-		priv = ((p->pid & LAST__PID_MASK) == cpupid_to_pid(last_cpupid));
-	else
-		priv = 1;
-
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
 		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
@@ -1244,6 +1379,18 @@ void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
 	}
 
+	/*
+	 * First accesses are treated as private, otherwise consider accesses
+	 * to be private if the accessing pid has not changed
+	 */
+	if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) {
+		priv = 1;
+	} else {
+		priv = cpupid_match_pid(p, last_cpupid);
+		if (!priv)
+			task_numa_group(p, last_cpupid);
+	}
+
 	/*
 	 * If pages are properly placed (did not migrate) then scan slower.
 	 * This is reset periodically in case of phase changes
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 691e96964dcc..8037b10a256f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -559,10 +559,7 @@ static inline u64 rq_clock_task(struct rq *rq)
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
-static inline void task_numa_free(struct task_struct *p)
-{
-	kfree(p->numa_faults);
-}
+extern void task_numa_free(struct task_struct *p);
 #else /* CONFIG_NUMA_BALANCING */
 static inline void task_numa_free(struct task_struct *p)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 5162e6d0d652..c57efa25cdbb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2719,6 +2719,14 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		get_page(dirty_page);
 
 reuse:
+		/*
+		 * Clear the pages cpupid information as the existing
+		 * information potentially belongs to a now completely
+		 * unrelated process.
+		 */
+		if (old_page)
+			page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1);
+
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-- 
cgit 


From e29cf08b05dc0b8151d65704d96d525a9e179a6b Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:22 +0100
Subject: sched/numa: Report a NUMA task group ID

It is desirable to model from userspace how the scheduler groups tasks
over time. This patch adds an ID to the numa_group and reports it via
/proc/PID/status.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-45-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/proc/array.c       | 2 ++
 include/linux/sched.h | 5 +++++
 kernel/sched/fair.c   | 7 +++++++
 3 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index cbd0f1b324b9..1bd2077187fd 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -183,6 +183,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	seq_printf(m,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
+		"Ngid:\t%d\n"
 		"Pid:\t%d\n"
 		"PPid:\t%d\n"
 		"TracerPid:\t%d\n"
@@ -190,6 +191,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		"Gid:\t%d\t%d\t%d\t%d\n",
 		get_task_state(p),
 		task_tgid_nr_ns(p, ns),
+		task_numa_group_id(p),
 		pid_nr_ns(pid, ns),
 		ppid, tpid,
 		from_kuid_munged(user_ns, cred->uid),
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f587ded5c148..b0b343b1ba64 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1452,12 +1452,17 @@ struct task_struct {
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, bool migrated);
+extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   bool migrated)
 {
 }
+static inline pid_t task_numa_group_id(struct task_struct *p)
+{
+	return 0;
+}
 static inline void set_numabalancing_state(bool enabled)
 {
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 85565053a6ed..5bd309c035c7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -893,12 +893,18 @@ struct numa_group {
 
 	spinlock_t lock; /* nr_tasks, tasks */
 	int nr_tasks;
+	pid_t gid;
 	struct list_head task_list;
 
 	struct rcu_head rcu;
 	atomic_long_t faults[0];
 };
 
+pid_t task_numa_group_id(struct task_struct *p)
+{
+	return p->numa_group ? p->numa_group->gid : 0;
+}
+
 static inline int task_faults_idx(int nid, int priv)
 {
 	return 2 * nid + priv;
@@ -1265,6 +1271,7 @@ static void task_numa_group(struct task_struct *p, int cpupid)
 		atomic_set(&grp->refcount, 1);
 		spin_lock_init(&grp->lock);
 		INIT_LIST_HEAD(&grp->task_list);
+		grp->gid = p->pid;
 
 		for (i = 0; i < 2*nr_node_ids; i++)
 			atomic_long_set(&grp->faults[i], p->numa_faults[i]);
-- 
cgit 


From 6688cc05473b36a0a3d3971e1adf1712919b32eb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 7 Oct 2013 11:29:24 +0100
Subject: mm: numa: Do not group on RO pages

And here's a little something to make sure not the whole world ends up
in a single group.

As while we don't migrate shared executable pages, we do scan/fault on
them. And since everybody links to libc, everybody ends up in the same
group.

Suggested-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1381141781-10992-47-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  7 +++++--
 kernel/sched/fair.c   |  5 +++--
 mm/huge_memory.c      | 15 +++++++++++++--
 mm/memory.c           | 30 ++++++++++++++++++++++++++----
 4 files changed, 47 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b0b343b1ba64..ff543851a18a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1450,13 +1450,16 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#define TNF_MIGRATED	0x01
+#define TNF_NO_GROUP	0x02
+
 #ifdef CONFIG_NUMA_BALANCING
-extern void task_numa_fault(int last_node, int node, int pages, bool migrated);
+extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
-				   bool migrated)
+				   int flags)
 {
 }
 static inline pid_t task_numa_group_id(struct task_struct *p)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5bd309c035c7..35661b8afb4e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1361,9 +1361,10 @@ void task_numa_free(struct task_struct *p)
 /*
  * Got a PROT_NONE fault for a page on @node.
  */
-void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
+void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 {
 	struct task_struct *p = current;
+	bool migrated = flags & TNF_MIGRATED;
 	int priv;
 
 	if (!numabalancing_enabled)
@@ -1394,7 +1395,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, bool migrated)
 		priv = 1;
 	} else {
 		priv = cpupid_match_pid(p, last_cpupid);
-		if (!priv)
+		if (!priv && !(flags & TNF_NO_GROUP))
 			task_numa_group(p, last_cpupid);
 	}
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index becf92ca54f3..7ab4e32afe12 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1285,6 +1285,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int target_nid, last_cpupid = -1;
 	bool page_locked;
 	bool migrated = false;
+	int flags = 0;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1298,6 +1299,14 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Avoid grouping on DSO/COW pages in specific and RO pages
+	 * in general, RO pages shouldn't hurt as much anyway since
+	 * they can be in shared cache state.
+	 */
+	if (!pmd_write(pmd))
+		flags |= TNF_NO_GROUP;
+
 	/*
 	 * Acquire the page lock to serialise THP migrations but avoid dropping
 	 * page_table_lock if at all possible
@@ -1343,8 +1352,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (migrated)
+	if (migrated) {
+		flags |= TNF_MIGRATED;
 		page_nid = target_nid;
+	}
 
 	goto out;
 clear_pmdnuma:
@@ -1362,7 +1373,7 @@ out:
 		page_unlock_anon_vma_read(anon_vma);
 
 	if (page_nid != -1)
-		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags);
 
 	return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index c57efa25cdbb..eba846bcf124 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3547,6 +3547,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	int flags = 0;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3575,6 +3576,14 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
+	/*
+	 * Avoid grouping on DSO/COW pages in specific and RO pages
+	 * in general, RO pages shouldn't hurt as much anyway since
+	 * they can be in shared cache state.
+	 */
+	if (!pte_write(pte))
+		flags |= TNF_NO_GROUP;
+
 	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
@@ -3586,12 +3595,14 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, vma, target_nid);
-	if (migrated)
+	if (migrated) {
 		page_nid = target_nid;
+		flags |= TNF_MIGRATED;
+	}
 
 out:
 	if (page_nid != -1)
-		task_numa_fault(last_cpupid, page_nid, 1, migrated);
+		task_numa_fault(last_cpupid, page_nid, 1, flags);
 	return 0;
 }
 
@@ -3632,6 +3643,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		int page_nid = -1;
 		int target_nid;
 		bool migrated = false;
+		int flags = 0;
 
 		if (!pte_present(pteval))
 			continue;
@@ -3651,20 +3663,30 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(!page))
 			continue;
 
+		/*
+		 * Avoid grouping on DSO/COW pages in specific and RO pages
+		 * in general, RO pages shouldn't hurt as much anyway since
+		 * they can be in shared cache state.
+		 */
+		if (!pte_write(pteval))
+			flags |= TNF_NO_GROUP;
+
 		last_cpupid = page_cpupid_last(page);
 		page_nid = page_to_nid(page);
 		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 		pte_unmap_unlock(pte, ptl);
 		if (target_nid != -1) {
 			migrated = migrate_misplaced_page(page, vma, target_nid);
-			if (migrated)
+			if (migrated) {
 				page_nid = target_nid;
+				flags |= TNF_MIGRATED;
+			}
 		} else {
 			put_page(page);
 		}
 
 		if (page_nid != -1)
-			task_numa_fault(last_cpupid, page_nid, 1, migrated);
+			task_numa_fault(last_cpupid, page_nid, 1, flags);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
-- 
cgit 


From 5e1576ed0e54d419286a8096133029062b6ad456 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:26 +0100
Subject: sched/numa: Stay on the same node if CLONE_VM

A newly spawned thread inside a process should stay on the same
NUMA node as its parent. This prevents processes from being "torn"
across multiple NUMA nodes every time they spawn a new thread.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-49-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  2 +-
 kernel/fork.c         |  2 +-
 kernel/sched/core.c   | 14 +++++++++-----
 3 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ff543851a18a..8563e3dd5c0f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2021,7 +2021,7 @@ extern void wake_up_new_task(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(struct task_struct *p);
+extern void sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index 7192d91b5415..c93be06dee87 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1310,7 +1310,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(p);
+	sched_fork(clone_flags, p);
 
 	retval = perf_event_init_task(p);
 	if (retval)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51092d5cc64c..3e2c893df173 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1696,7 +1696,7 @@ int wake_up_state(struct task_struct *p, unsigned int state)
  *
  * __sched_fork() is basic setup used by init_idle() too:
  */
-static void __sched_fork(struct task_struct *p)
+static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	p->on_rq			= 0;
 
@@ -1725,11 +1725,15 @@ static void __sched_fork(struct task_struct *p)
 		p->mm->numa_scan_seq = 0;
 	}
 
+	if (clone_flags & CLONE_VM)
+		p->numa_preferred_nid = current->numa_preferred_nid;
+	else
+		p->numa_preferred_nid = -1;
+
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_migrate_seq = 1;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-	p->numa_preferred_nid = -1;
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
 	p->numa_faults_buffer = NULL;
@@ -1761,12 +1765,12 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(struct task_struct *p)
+void sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
 
-	__sched_fork(p);
+	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as running here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
@@ -4287,7 +4291,7 @@ void init_idle(struct task_struct *idle, int cpu)
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
 
-	__sched_fork(idle);
+	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
-- 
cgit 


From 83e1d2cd9eabec5164afea295ff06b941ae8e4a9 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:27 +0100
Subject: sched/numa: Use group fault statistics in numa placement

This patch uses the fraction of faults on a particular node for both task
and group, to figure out the best node to place a task.  If the task and
group statistics disagree on what the preferred node should be then a full
rescan will select the node with the best combined weight.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-50-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |   1 +
 kernel/sched/fair.c   | 124 +++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 108 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8563e3dd5c0f..724482200b83 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1356,6 +1356,7 @@ struct task_struct {
 	 * The values remain static for the duration of a PTE scan
 	 */
 	unsigned long *numa_faults;
+	unsigned long total_numa_faults;
 
 	/*
 	 * numa_faults_buffer records faults per node during the current
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 35661b8afb4e..4c40e13310e9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -897,6 +897,7 @@ struct numa_group {
 	struct list_head task_list;
 
 	struct rcu_head rcu;
+	atomic_long_t total_faults;
 	atomic_long_t faults[0];
 };
 
@@ -919,6 +920,51 @@ static inline unsigned long task_faults(struct task_struct *p, int nid)
 		p->numa_faults[task_faults_idx(nid, 1)];
 }
 
+static inline unsigned long group_faults(struct task_struct *p, int nid)
+{
+	if (!p->numa_group)
+		return 0;
+
+	return atomic_long_read(&p->numa_group->faults[2*nid]) +
+	       atomic_long_read(&p->numa_group->faults[2*nid+1]);
+}
+
+/*
+ * These return the fraction of accesses done by a particular task, or
+ * task group, on a particular numa node.  The group weight is given a
+ * larger multiplier, in order to group tasks together that are almost
+ * evenly spread out between numa nodes.
+ */
+static inline unsigned long task_weight(struct task_struct *p, int nid)
+{
+	unsigned long total_faults;
+
+	if (!p->numa_faults)
+		return 0;
+
+	total_faults = p->total_numa_faults;
+
+	if (!total_faults)
+		return 0;
+
+	return 1000 * task_faults(p, nid) / total_faults;
+}
+
+static inline unsigned long group_weight(struct task_struct *p, int nid)
+{
+	unsigned long total_faults;
+
+	if (!p->numa_group)
+		return 0;
+
+	total_faults = atomic_long_read(&p->numa_group->total_faults);
+
+	if (!total_faults)
+		return 0;
+
+	return 1200 * group_faults(p, nid) / total_faults;
+}
+
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1018,8 +1064,10 @@ static void task_numa_compare(struct task_numa_env *env, long imp)
 		if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur)))
 			goto unlock;
 
-		imp += task_faults(cur, env->src_nid) -
-		       task_faults(cur, env->dst_nid);
+		imp += task_weight(cur, env->src_nid) +
+		       group_weight(cur, env->src_nid) -
+		       task_weight(cur, env->dst_nid) -
+		       group_weight(cur, env->dst_nid);
 	}
 
 	if (imp < env->best_imp)
@@ -1098,7 +1146,7 @@ static int task_numa_migrate(struct task_struct *p)
 		.best_cpu = -1
 	};
 	struct sched_domain *sd;
-	unsigned long faults;
+	unsigned long weight;
 	int nid, ret;
 	long imp;
 
@@ -1115,10 +1163,10 @@ static int task_numa_migrate(struct task_struct *p)
 	env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2;
 	rcu_read_unlock();
 
-	faults = task_faults(p, env.src_nid);
+	weight = task_weight(p, env.src_nid) + group_weight(p, env.src_nid);
 	update_numa_stats(&env.src_stats, env.src_nid);
 	env.dst_nid = p->numa_preferred_nid;
-	imp = task_faults(env.p, env.dst_nid) - faults;
+	imp = task_weight(p, env.dst_nid) + group_weight(p, env.dst_nid) - weight;
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* If the preferred nid has capacity, try to use it. */
@@ -1131,8 +1179,8 @@ static int task_numa_migrate(struct task_struct *p)
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
 
-			/* Only consider nodes that recorded more faults */
-			imp = task_faults(env.p, nid) - faults;
+			/* Only consider nodes where both task and groups benefit */
+			imp = task_weight(p, nid) + group_weight(p, nid) - weight;
 			if (imp < 0)
 				continue;
 
@@ -1183,8 +1231,8 @@ static void numa_migrate_preferred(struct task_struct *p)
 
 static void task_numa_placement(struct task_struct *p)
 {
-	int seq, nid, max_nid = -1;
-	unsigned long max_faults = 0;
+	int seq, nid, max_nid = -1, max_group_nid = -1;
+	unsigned long max_faults = 0, max_group_faults = 0;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
 	if (p->numa_scan_seq == seq)
@@ -1195,7 +1243,7 @@ static void task_numa_placement(struct task_struct *p)
 
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
-		unsigned long faults = 0;
+		unsigned long faults = 0, group_faults = 0;
 		int priv, i;
 
 		for (priv = 0; priv < 2; priv++) {
@@ -1211,9 +1259,12 @@ static void task_numa_placement(struct task_struct *p)
 
 			faults += p->numa_faults[i];
 			diff += p->numa_faults[i];
+			p->total_numa_faults += diff;
 			if (p->numa_group) {
 				/* safe because we can only change our own group */
 				atomic_long_add(diff, &p->numa_group->faults[i]);
+				atomic_long_add(diff, &p->numa_group->total_faults);
+				group_faults += atomic_long_read(&p->numa_group->faults[i]);
 			}
 		}
 
@@ -1221,6 +1272,27 @@ static void task_numa_placement(struct task_struct *p)
 			max_faults = faults;
 			max_nid = nid;
 		}
+
+		if (group_faults > max_group_faults) {
+			max_group_faults = group_faults;
+			max_group_nid = nid;
+		}
+	}
+
+	/*
+	 * If the preferred task and group nids are different,
+	 * iterate over the nodes again to find the best place.
+	 */
+	if (p->numa_group && max_nid != max_group_nid) {
+		unsigned long weight, max_weight = 0;
+
+		for_each_online_node(nid) {
+			weight = task_weight(p, nid) + group_weight(p, nid);
+			if (weight > max_weight) {
+				max_weight = weight;
+				max_nid = nid;
+			}
+		}
 	}
 
 	/* Preferred node as the node with the most faults */
@@ -1276,6 +1348,8 @@ static void task_numa_group(struct task_struct *p, int cpupid)
 		for (i = 0; i < 2*nr_node_ids; i++)
 			atomic_long_set(&grp->faults[i], p->numa_faults[i]);
 
+		atomic_long_set(&grp->total_faults, p->total_numa_faults);
+
 		list_add(&p->numa_entry, &grp->task_list);
 		grp->nr_tasks++;
 		rcu_assign_pointer(p->numa_group, grp);
@@ -1323,6 +1397,8 @@ unlock:
 		atomic_long_sub(p->numa_faults[i], &my_grp->faults[i]);
 		atomic_long_add(p->numa_faults[i], &grp->faults[i]);
 	}
+	atomic_long_sub(p->total_numa_faults, &my_grp->total_faults);
+	atomic_long_add(p->total_numa_faults, &grp->total_faults);
 
 	double_lock(&my_grp->lock, &grp->lock);
 
@@ -1347,6 +1423,8 @@ void task_numa_free(struct task_struct *p)
 		for (i = 0; i < 2*nr_node_ids; i++)
 			atomic_long_sub(p->numa_faults[i], &grp->faults[i]);
 
+		atomic_long_sub(p->total_numa_faults, &grp->total_faults);
+
 		spin_lock(&grp->lock);
 		list_del(&p->numa_entry);
 		grp->nr_tasks--;
@@ -1385,6 +1463,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 
 		BUG_ON(p->numa_faults_buffer);
 		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
+		p->total_numa_faults = 0;
 	}
 
 	/*
@@ -4572,12 +4651,17 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 	src_nid = cpu_to_node(env->src_cpu);
 	dst_nid = cpu_to_node(env->dst_cpu);
 
-	if (src_nid == dst_nid ||
-	    p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
+	if (src_nid == dst_nid)
 		return false;
 
-	if (dst_nid == p->numa_preferred_nid ||
-	    task_faults(p, dst_nid) > task_faults(p, src_nid))
+	/* Always encourage migration to the preferred node. */
+	if (dst_nid == p->numa_preferred_nid)
+		return true;
+
+	/* After the task has settled, check if the new node is better. */
+	if (p->numa_migrate_seq >= sysctl_numa_balancing_settle_count &&
+			task_weight(p, dst_nid) + group_weight(p, dst_nid) >
+			task_weight(p, src_nid) + group_weight(p, src_nid))
 		return true;
 
 	return false;
@@ -4597,11 +4681,17 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	src_nid = cpu_to_node(env->src_cpu);
 	dst_nid = cpu_to_node(env->dst_cpu);
 
-	if (src_nid == dst_nid ||
-	    p->numa_migrate_seq >= sysctl_numa_balancing_settle_count)
+	if (src_nid == dst_nid)
 		return false;
 
-	if (task_faults(p, dst_nid) < task_faults(p, src_nid))
+	/* Migrating away from the preferred node is always bad. */
+	if (src_nid == p->numa_preferred_nid)
+		return true;
+
+	/* After the task has settled, check if the new node is worse. */
+	if (p->numa_migrate_seq >= sysctl_numa_balancing_settle_count &&
+			task_weight(p, dst_nid) + group_weight(p, dst_nid) <
+			task_weight(p, src_nid) + group_weight(p, src_nid))
 		return true;
 
 	return false;
-- 
cgit 


From 82727018b0d33d188e9916bcf76f18387484cb04 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:28 +0100
Subject: sched/numa: Call task_numa_free() from do_execve()

It is possible for a task in a numa group to call exec, and
have the new (unrelated) executable inherit the numa group
association from its former self.

This has the potential to break numa grouping, and is trivial
to fix.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-51-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/exec.c             | 1 +
 include/linux/sched.h | 4 ++++
 kernel/sched/fair.c   | 9 ++++++++-
 kernel/sched/sched.h  | 5 -----
 4 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index 8875dd10ae7a..2ea437e5acf4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1547,6 +1547,7 @@ static int do_execve_common(const char *filename,
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	acct_update_integrals(current);
+	task_numa_free(current);
 	free_bprm(bprm);
 	if (displaced)
 		put_files_struct(displaced);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 724482200b83..f6385107c352 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1458,6 +1458,7 @@ struct task_struct {
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
+extern void task_numa_free(struct task_struct *p);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
@@ -1470,6 +1471,9 @@ static inline pid_t task_numa_group_id(struct task_struct *p)
 static inline void set_numabalancing_state(bool enabled)
 {
 }
+static inline void task_numa_free(struct task_struct *p)
+{
+}
 #endif
 
 static inline struct pid *task_pid(struct task_struct *task)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4c40e13310e9..c4df2de6ca4a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1418,6 +1418,7 @@ void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
 	int i;
+	void *numa_faults = p->numa_faults;
 
 	if (grp) {
 		for (i = 0; i < 2*nr_node_ids; i++)
@@ -1433,7 +1434,9 @@ void task_numa_free(struct task_struct *p)
 		put_numa_group(grp);
 	}
 
-	kfree(p->numa_faults);
+	p->numa_faults = NULL;
+	p->numa_faults_buffer = NULL;
+	kfree(numa_faults);
 }
 
 /*
@@ -1452,6 +1455,10 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (!p->mm)
 		return;
 
+	/* Do not worry about placement if exiting */
+	if (p->state == TASK_DEAD)
+		return;
+
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults)) {
 		int size = sizeof(*p->numa_faults) * 2 * nr_node_ids;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8037b10a256f..eeb1923812a1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -559,11 +559,6 @@ static inline u64 rq_clock_task(struct rq *rq)
 #ifdef CONFIG_NUMA_BALANCING
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
-extern void task_numa_free(struct task_struct *p);
-#else /* CONFIG_NUMA_BALANCING */
-static inline void task_numa_free(struct task_struct *p)
-{
-}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_SMP
-- 
cgit 


From b32e86b4301e345611f0446265f782a229faadf6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Mon, 7 Oct 2013 11:29:30 +0100
Subject: sched/numa: Add debugging

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1381141781-10992-53-git-send-email-mgorman@suse.de
---
 include/linux/sched.h |  6 ++++++
 kernel/sched/debug.c  | 60 +++++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/fair.c   |  5 ++++-
 3 files changed, 68 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index f6385107c352..1127a46ac3d2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1366,6 +1366,7 @@ struct task_struct {
 	unsigned long *numa_faults_buffer;
 
 	int numa_preferred_nid;
+	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
 	struct rcu_head rcu;
@@ -2661,6 +2662,11 @@ static inline unsigned int task_cpu(const struct task_struct *p)
 	return task_thread_info(p)->cpu;
 }
 
+static inline int task_node(const struct task_struct *p)
+{
+	return cpu_to_node(task_cpu(p));
+}
+
 extern void set_task_cpu(struct task_struct *p, unsigned int cpu);
 
 #else
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 196559994f7c..e6ba5e31c7ca 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
+#include <linux/mempolicy.h>
 
 #include "sched.h"
 
@@ -137,6 +138,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+#endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
 #endif
@@ -159,7 +163,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_lock_irqsave(&tasklist_lock, flags);
 
 	do_each_thread(g, p) {
-		if (!p->on_rq || task_cpu(p) != rq_cpu)
+		if (task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);
@@ -345,7 +349,7 @@ static void sched_debug_header(struct seq_file *m)
 	cpu_clk = local_clock();
 	local_irq_restore(flags);
 
-	SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
@@ -488,6 +492,56 @@ static int __init init_sched_debug_procfs(void)
 
 __initcall(init_sched_debug_procfs);
 
+#define __P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+
+static void sched_show_numa(struct task_struct *p, struct seq_file *m)
+{
+#ifdef CONFIG_NUMA_BALANCING
+	struct mempolicy *pol;
+	int node, i;
+
+	if (p->mm)
+		P(mm->numa_scan_seq);
+
+	task_lock(p);
+	pol = p->mempolicy;
+	if (pol && !(pol->flags & MPOL_F_MORON))
+		pol = NULL;
+	mpol_get(pol);
+	task_unlock(p);
+
+	SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
+
+	for_each_online_node(node) {
+		for (i = 0; i < 2; i++) {
+			unsigned long nr_faults = -1;
+			int cpu_current, home_node;
+
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
+
+			cpu_current = !i ? (task_node(p) == node) :
+				(pol && node_isset(node, pol->v.nodes));
+
+			home_node = (p->numa_preferred_nid == node);
+
+			SEQ_printf(m, "numa_faults, %d, %d, %d, %d, %ld\n",
+				i, node, cpu_current, home_node, nr_faults);
+		}
+	}
+
+	mpol_put(pol);
+#endif
+}
+
 void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 {
 	unsigned long nr_switches;
@@ -591,6 +645,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		SEQ_printf(m, "%-45s:%21Ld\n",
 			   "clock-delta", (long long)(t1-t0));
 	}
+
+	sched_show_numa(p, m);
 }
 
 void proc_sched_set_task(struct task_struct *p)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 147349987bfe..2876a37cdfc4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1137,7 +1137,7 @@ static int task_numa_migrate(struct task_struct *p)
 		.p = p,
 
 		.src_cpu = task_cpu(p),
-		.src_nid = cpu_to_node(task_cpu(p)),
+		.src_nid = task_node(p),
 
 		.imbalance_pct = 112,
 
@@ -1515,6 +1515,9 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	if (p->numa_migrate_retry && time_after(jiffies, p->numa_migrate_retry))
 		numa_migrate_preferred(p);
 
+	if (migrated)
+		p->numa_pages_migrated += pages;
+
 	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
 }
 
-- 
cgit 


From dabe1d992414a6456e60e41f1d1ad8affc6d444d Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:34 +0100
Subject: sched/numa: Be more careful about joining numa groups

Due to the way the pid is truncated, and tasks are moved between
CPUs by the scheduler, it is possible for the current task_numa_fault
to group together tasks that do not actually share memory together.

This patch adds a few easy sanity checks to task_numa_fault, joining
tasks together if they share the same tsk->mm, or if the fault was on
a page with an elevated mapcount, in a shared VMA.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-57-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 +
 kernel/sched/fair.c   | 16 +++++++++++-----
 mm/memory.c           |  7 +++++++
 3 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1127a46ac3d2..59f953b2e413 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1454,6 +1454,7 @@ struct task_struct {
 
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
+#define TNF_SHARED	0x04
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5166b9b1af70..222c2d0b6ae2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1381,7 +1381,7 @@ static void double_lock(spinlock_t *l1, spinlock_t *l2)
 	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
 }
 
-static void task_numa_group(struct task_struct *p, int cpupid)
+static void task_numa_group(struct task_struct *p, int cpupid, int flags)
 {
 	struct numa_group *grp, *my_grp;
 	struct task_struct *tsk;
@@ -1439,10 +1439,16 @@ static void task_numa_group(struct task_struct *p, int cpupid)
 	if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp)
 		goto unlock;
 
-	if (!get_numa_group(grp))
-		goto unlock;
+	/* Always join threads in the same process. */
+	if (tsk->mm == current->mm)
+		join = true;
+
+	/* Simple filter to avoid false positives due to PID collisions */
+	if (flags & TNF_SHARED)
+		join = true;
 
-	join = true;
+	if (join && !get_numa_group(grp))
+		join = false;
 
 unlock:
 	rcu_read_unlock();
@@ -1539,7 +1545,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 	} else {
 		priv = cpupid_match_pid(p, last_cpupid);
 		if (!priv && !(flags & TNF_NO_GROUP))
-			task_numa_group(p, last_cpupid);
+			task_numa_group(p, last_cpupid, flags);
 	}
 
 	/*
diff --git a/mm/memory.c b/mm/memory.c
index 9898eeb9a21c..823720c43ea9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3584,6 +3584,13 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte_write(pte))
 		flags |= TNF_NO_GROUP;
 
+	/*
+	 * Flag if the page is shared between multiple address spaces. This
+	 * is later used when determining whether to group tasks together
+	 */
+	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+		flags |= TNF_SHARED;
+
 	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
 	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
-- 
cgit 


From 04bb2f9475054298f0c67a89ca92cade42d3fe5e Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:36 +0100
Subject: sched/numa: Adjust scan rate in task_numa_placement

Adjust numa_scan_period in task_numa_placement, depending on how much
useful work the numa code can do. The more local faults there are in a
given scan window the longer the period (and hence the slower the scan rate)
during the next window. If there are excessive shared faults then the scan
period will decrease with the amount of scaling depending on whether the
ratio of shared/private faults. If the preferred node changes then the
scan rate is reset to recheck if the task is properly placed.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-59-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |   9 ++++
 kernel/sched/fair.c   | 112 +++++++++++++++++++++++++++++++++++++++-----------
 mm/huge_memory.c      |   4 +-
 mm/memory.c           |   9 ++--
 4 files changed, 105 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 59f953b2e413..2292f6c1596f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1365,6 +1365,14 @@ struct task_struct {
 	 */
 	unsigned long *numa_faults_buffer;
 
+	/*
+	 * numa_faults_locality tracks if faults recorded during the last
+	 * scan window were remote/local. The task scan period is adapted
+	 * based on the locality of the faults with different weights
+	 * depending on whether they were shared or private faults
+	 */
+	unsigned long numa_faults_locality[2];
+
 	int numa_preferred_nid;
 	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
@@ -1455,6 +1463,7 @@ struct task_struct {
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
+#define TNF_FAULT_LOCAL	0x08
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d26a16e45437..66237ff8b01e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1241,6 +1241,12 @@ static int task_numa_migrate(struct task_struct *p)
 
 	sched_setnuma(p, env.dst_nid);
 
+	/*
+	 * Reset the scan period if the task is being rescheduled on an
+	 * alternative node to recheck if the tasks is now properly placed.
+	 */
+	p->numa_scan_period = task_scan_min(p);
+
 	if (env.best_task == NULL) {
 		int ret = migrate_task_to(p, env.best_cpu);
 		return ret;
@@ -1276,10 +1282,86 @@ static void numa_migrate_preferred(struct task_struct *p)
 		p->numa_migrate_retry = jiffies + HZ*5;
 }
 
+/*
+ * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
+ * increments. The more local the fault statistics are, the higher the scan
+ * period will be for the next scan window. If local/remote ratio is below
+ * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the
+ * scan period will decrease
+ */
+#define NUMA_PERIOD_SLOTS 10
+#define NUMA_PERIOD_THRESHOLD 3
+
+/*
+ * Increase the scan period (slow down scanning) if the majority of
+ * our memory is already on our local node, or if the majority of
+ * the page accesses are shared with other processes.
+ * Otherwise, decrease the scan period.
+ */
+static void update_task_scan_period(struct task_struct *p,
+			unsigned long shared, unsigned long private)
+{
+	unsigned int period_slot;
+	int ratio;
+	int diff;
+
+	unsigned long remote = p->numa_faults_locality[0];
+	unsigned long local = p->numa_faults_locality[1];
+
+	/*
+	 * If there were no record hinting faults then either the task is
+	 * completely idle or all activity is areas that are not of interest
+	 * to automatic numa balancing. Scan slower
+	 */
+	if (local + shared == 0) {
+		p->numa_scan_period = min(p->numa_scan_period_max,
+			p->numa_scan_period << 1);
+
+		p->mm->numa_next_scan = jiffies +
+			msecs_to_jiffies(p->numa_scan_period);
+
+		return;
+	}
+
+	/*
+	 * Prepare to scale scan period relative to the current period.
+	 *	 == NUMA_PERIOD_THRESHOLD scan period stays the same
+	 *       <  NUMA_PERIOD_THRESHOLD scan period decreases (scan faster)
+	 *	 >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower)
+	 */
+	period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS);
+	ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote);
+	if (ratio >= NUMA_PERIOD_THRESHOLD) {
+		int slot = ratio - NUMA_PERIOD_THRESHOLD;
+		if (!slot)
+			slot = 1;
+		diff = slot * period_slot;
+	} else {
+		diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot;
+
+		/*
+		 * Scale scan rate increases based on sharing. There is an
+		 * inverse relationship between the degree of sharing and
+		 * the adjustment made to the scanning period. Broadly
+		 * speaking the intent is that there is little point
+		 * scanning faster if shared accesses dominate as it may
+		 * simply bounce migrations uselessly
+		 */
+		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
+	}
+
+	p->numa_scan_period = clamp(p->numa_scan_period + diff,
+			task_scan_min(p), task_scan_max(p));
+	memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
 	unsigned long max_faults = 0, max_group_faults = 0;
+	unsigned long fault_types[2] = { 0, 0 };
 	spinlock_t *group_lock = NULL;
 
 	seq = ACCESS_ONCE(p->mm->numa_scan_seq);
@@ -1309,6 +1391,7 @@ static void task_numa_placement(struct task_struct *p)
 			/* Decay existing window, copy faults since last scan */
 			p->numa_faults[i] >>= 1;
 			p->numa_faults[i] += p->numa_faults_buffer[i];
+			fault_types[priv] += p->numa_faults_buffer[i];
 			p->numa_faults_buffer[i] = 0;
 
 			faults += p->numa_faults[i];
@@ -1333,6 +1416,8 @@ static void task_numa_placement(struct task_struct *p)
 		}
 	}
 
+	update_task_scan_period(p, fault_types[0], fault_types[1]);
+
 	if (p->numa_group) {
 		/*
 		 * If the preferred task and group nids are different,
@@ -1538,6 +1623,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 		BUG_ON(p->numa_faults_buffer);
 		p->numa_faults_buffer = p->numa_faults + (2 * nr_node_ids);
 		p->total_numa_faults = 0;
+		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
 
 	/*
@@ -1552,19 +1638,6 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 			task_numa_group(p, last_cpupid, flags, &priv);
 	}
 
-	/*
-	 * If pages are properly placed (did not migrate) then scan slower.
-	 * This is reset periodically in case of phase changes
-	 */
-	if (!migrated) {
-		/* Initialise if necessary */
-		if (!p->numa_scan_period_max)
-			p->numa_scan_period_max = task_scan_max(p);
-
-		p->numa_scan_period = min(p->numa_scan_period_max,
-			p->numa_scan_period + 10);
-	}
-
 	task_numa_placement(p);
 
 	/* Retry task to preferred node migration if it previously failed */
@@ -1575,6 +1648,7 @@ void task_numa_fault(int last_cpupid, int node, int pages, int flags)
 		p->numa_pages_migrated += pages;
 
 	p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+	p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages;
 }
 
 static void reset_ptenuma_scan(struct task_struct *p)
@@ -1701,18 +1775,6 @@ void task_numa_work(struct callback_head *work)
 	}
 
 out:
-	/*
-	 * If the whole process was scanned without updates then no NUMA
-	 * hinting faults are being recorded and scan rate should be lower.
-	 */
-	if (mm->numa_scan_offset == 0 && !nr_pte_updates) {
-		p->numa_scan_period = min(p->numa_scan_period_max,
-			p->numa_scan_period << 1);
-
-		next_scan = now + msecs_to_jiffies(p->numa_scan_period);
-		mm->numa_next_scan = next_scan;
-	}
-
 	/*
 	 * It is possible to reach the end of the VMA list but the last few
 	 * VMAs are not guaranteed to the vma_migratable. If they are not, we
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7ab4e32afe12..1be2a1f95b61 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1296,8 +1296,10 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page_nid = page_to_nid(page);
 	last_cpupid = page_cpupid_last(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (page_nid == this_nid)
+	if (page_nid == this_nid) {
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+		flags |= TNF_FAULT_LOCAL;
+	}
 
 	/*
 	 * Avoid grouping on DSO/COW pages in specific and RO pages
diff --git a/mm/memory.c b/mm/memory.c
index 823720c43ea9..1c7501f7fb1a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3527,13 +3527,16 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int page_nid)
+				unsigned long addr, int page_nid,
+				int *flags)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (page_nid == numa_node_id())
+	if (page_nid == numa_node_id()) {
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+		*flags |= TNF_FAULT_LOCAL;
+	}
 
 	return mpol_misplaced(page, vma, addr);
 }
@@ -3593,7 +3596,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	last_cpupid = page_cpupid_last(page);
 	page_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
 		put_page(page);
-- 
cgit 


From 930aa174fcc8b0efaad102fd80f677b92f35eaa2 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Mon, 7 Oct 2013 11:29:37 +0100
Subject: sched/numa: Remove the numa_balancing_scan_period_reset sysctl

With scan rate adaptions based on whether the workload has properly
converged or not there should be no need for the scan period reset
hammer. Get rid of it.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-60-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/sysctl/kernel.txt | 11 +++--------
 include/linux/mm_types.h        |  3 ---
 include/linux/sched/sysctl.h    |  1 -
 kernel/sched/core.c             |  1 -
 kernel/sched/fair.c             | 18 +-----------------
 kernel/sysctl.c                 |  7 -------
 6 files changed, 4 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index d48bca45b6f2..84f17800f8b5 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -374,15 +374,13 @@ guarantee. If the target workload is already bound to NUMA nodes then this
 feature should be disabled. Otherwise, if the system overhead from the
 feature is too high then the rate the kernel samples for NUMA hinting
 faults may be controlled by the numa_balancing_scan_period_min_ms,
-numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset,
-numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb and
-numa_balancing_settle_count sysctls.
+numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
+numa_balancing_scan_size_mb and numa_balancing_settle_count sysctls.
 
 ==============================================================
 
 numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms,
-numa_balancing_scan_period_max_ms, numa_balancing_scan_period_reset,
-numa_balancing_scan_size_mb
+numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb
 
 Automatic NUMA balancing scans tasks address space and unmaps pages to
 detect if pages are properly placed or if the data should be migrated to a
@@ -418,9 +416,6 @@ rate for each task.
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
 
-numa_balancing_scan_period_reset is a blunt instrument that controls how
-often a tasks scan delay is reset to detect sudden changes in task behaviour.
-
 numa_balancing_settle_count is how many scan periods must complete before
 the schedule balancer stops pushing the task towards a preferred node. This
 gives the scheduler a chance to place the task on an alternative node if the
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index a30f9ca66557..a3198e5aaf4e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -420,9 +420,6 @@ struct mm_struct {
 	 */
 	unsigned long numa_next_scan;
 
-	/* numa_next_reset is when the PTE scanner period will be reset */
-	unsigned long numa_next_reset;
-
 	/* Restart point for scanning and setting pte_numa */
 	unsigned long numa_scan_offset;
 
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index bf8086b2506e..10d16c4fbe89 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -47,7 +47,6 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
 extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_settle_count;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8cfd51f62241..89c5ae836f66 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1721,7 +1721,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #ifdef CONFIG_NUMA_BALANCING
 	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
 		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		p->mm->numa_next_reset = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
 		p->mm->numa_scan_seq = 0;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 66237ff8b01e..da6fa22be000 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -826,7 +826,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  */
 unsigned int sysctl_numa_balancing_scan_period_min = 1000;
 unsigned int sysctl_numa_balancing_scan_period_max = 60000;
-unsigned int sysctl_numa_balancing_scan_period_reset = 60000;
 
 /* Portion of address space to scan in MB */
 unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -1685,24 +1684,9 @@ void task_numa_work(struct callback_head *work)
 	if (p->flags & PF_EXITING)
 		return;
 
-	if (!mm->numa_next_reset || !mm->numa_next_scan) {
+	if (!mm->numa_next_scan) {
 		mm->numa_next_scan = now +
 			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		mm->numa_next_reset = now +
-			msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
-	}
-
-	/*
-	 * Reset the scan period if enough time has gone by. Objective is that
-	 * scanning will be reduced if pages are properly placed. As tasks
-	 * can enter different phases this needs to be re-examined. Lacking
-	 * proper tracking of reference behaviour, this blunt hammer is used.
-	 */
-	migrate = mm->numa_next_reset;
-	if (time_after(now, migrate)) {
-		p->numa_scan_period = task_scan_min(p);
-		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);
-		xchg(&mm->numa_next_reset, next_scan);
 	}
 
 	/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 42f616a74f40..e509b90a8002 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -370,13 +370,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "numa_balancing_scan_period_reset",
-		.data		= &sysctl_numa_balancing_scan_period_reset,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "numa_balancing_scan_period_max_ms",
 		.data		= &sysctl_numa_balancing_scan_period_max,
-- 
cgit 


From 1e3646ffc64b232cb14a5ef01d7b98997c1b73f9 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:38 +0100
Subject: mm: numa: Revert temporarily disabling of NUMA migration

With the scan rate code working (at least for multi-instance specjbb),
the large hammer that is "sched: Do not migrate memory immediately after
switching node" can be replaced with something smarter. Revert temporarily
migration disabling and all traces of numa_migrate_seq.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-61-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h |  1 -
 kernel/sched/core.c   |  2 --
 kernel/sched/fair.c   | 25 +------------------------
 mm/mempolicy.c        | 12 ------------
 4 files changed, 1 insertion(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2292f6c1596f..d24f70ffddee 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1340,7 +1340,6 @@ struct task_struct {
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	int numa_scan_seq;
-	int numa_migrate_seq;
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
 	unsigned long numa_migrate_retry;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89c5ae836f66..0c3feebcf112 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1731,7 +1731,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	p->node_stamp = 0ULL;
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_migrate_seq = 1;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
 	p->numa_faults = NULL;
@@ -4488,7 +4487,6 @@ void sched_setnuma(struct task_struct *p, int nid)
 		p->sched_class->put_prev_task(rq, p);
 
 	p->numa_preferred_nid = nid;
-	p->numa_migrate_seq = 1;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index da6fa22be000..8454c38b1b12 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1261,16 +1261,8 @@ static void numa_migrate_preferred(struct task_struct *p)
 {
 	/* Success if task is already running on preferred CPU */
 	p->numa_migrate_retry = 0;
-	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid) {
-		/*
-		 * If migration is temporarily disabled due to a task migration
-		 * then re-enable it now as the task is running on its
-		 * preferred node and memory should migrate locally
-		 */
-		if (!p->numa_migrate_seq)
-			p->numa_migrate_seq++;
+	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
 		return;
-	}
 
 	/* This task has no NUMA fault statistics yet */
 	if (unlikely(p->numa_preferred_nid == -1))
@@ -1367,7 +1359,6 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_scan_seq == seq)
 		return;
 	p->numa_scan_seq = seq;
-	p->numa_migrate_seq++;
 	p->numa_scan_period_max = task_scan_max(p);
 
 	/* If the task is part of a group prevent parallel updates to group stats */
@@ -4730,20 +4721,6 @@ static void move_task(struct task_struct *p, struct lb_env *env)
 	set_task_cpu(p, env->dst_cpu);
 	activate_task(env->dst_rq, p, 0);
 	check_preempt_curr(env->dst_rq, p, 0);
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->numa_preferred_nid != -1) {
-		int src_nid = cpu_to_node(env->src_cpu);
-		int dst_nid = cpu_to_node(env->dst_cpu);
-
-		/*
-		 * If the load balancer has moved the task then limit
-		 * migrations from taking place in the short term in
-		 * case this is a short-lived migration.
-		 */
-		if (src_nid != dst_nid && dst_nid != p->numa_preferred_nid)
-			p->numa_migrate_seq = 0;
-	}
-#endif
 }
 
 /*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index a5867ef24bda..2929c24c22b7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2404,18 +2404,6 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
 		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid)
 			goto out;
-
-#ifdef CONFIG_NUMA_BALANCING
-		/*
-		 * If the scheduler has just moved us away from our
-		 * preferred node, do not bother migrating pages yet.
-		 * This way a short and temporary process migration will
-		 * not cause excessive memory migration.
-		 */
-		if (thisnid != current->numa_preferred_nid &&
-				!current->numa_migrate_seq)
-			goto out;
-#endif
 	}
 
 	if (curnid != polnid)
-- 
cgit 


From de1c9ce6f07fec0381a39a9d0b379ea35aa1167f Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 7 Oct 2013 11:29:39 +0100
Subject: sched/numa: Skip some page migrations after a shared fault

Shared faults can lead to lots of unnecessary page migrations,
slowing down the system, and causing private faults to hit the
per-pgdat migration ratelimit.

This patch adds sysctl numa_balancing_migrate_deferred, which specifies
how many shared page migrations to skip unconditionally, after each page
migration that is skipped because it is a shared fault.

This reduces the number of page migrations back and forth in
shared fault situations. It also gives a strong preference to
the tasks that are already running where most of the memory is,
and to moving the other tasks to near the memory.

Testing this with a much higher scan rate than the default
still seems to result in fewer page migrations than before.

Memory seems to be somewhat better consolidated than previously,
with multi-instance specjbb runs on a 4 node system.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-62-git-send-email-mgorman@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/sysctl/kernel.txt | 10 ++++++++-
 include/linux/sched.h           |  5 ++++-
 kernel/sched/fair.c             |  8 +++++++
 kernel/sysctl.c                 |  7 ++++++
 mm/mempolicy.c                  | 48 ++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 75 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 84f17800f8b5..4273b2d71a27 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -375,7 +375,8 @@ feature should be disabled. Otherwise, if the system overhead from the
 feature is too high then the rate the kernel samples for NUMA hinting
 faults may be controlled by the numa_balancing_scan_period_min_ms,
 numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
-numa_balancing_scan_size_mb and numa_balancing_settle_count sysctls.
+numa_balancing_scan_size_mb, numa_balancing_settle_count sysctls and
+numa_balancing_migrate_deferred.
 
 ==============================================================
 
@@ -421,6 +422,13 @@ the schedule balancer stops pushing the task towards a preferred node. This
 gives the scheduler a chance to place the task on an alternative node if the
 preferred node is overloaded.
 
+numa_balancing_migrate_deferred is how many page migrations get skipped
+unconditionally, after a page migration is skipped because a page is shared
+with other tasks. This reduces page migration overhead, and determines
+how much stronger the "move task near its memory" policy scheduler becomes,
+versus the "move memory near its task" memory management policy, for workloads
+with shared memory.
+
 ==============================================================
 
 osrelease, ostype & version:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d24f70ffddee..833eed55cf43 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1342,6 +1342,8 @@ struct task_struct {
 	int numa_scan_seq;
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
+	int numa_preferred_nid;
+	int numa_migrate_deferred;
 	unsigned long numa_migrate_retry;
 	u64 node_stamp;			/* migration stamp  */
 	struct callback_head numa_work;
@@ -1372,7 +1374,6 @@ struct task_struct {
 	 */
 	unsigned long numa_faults_locality[2];
 
-	int numa_preferred_nid;
 	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
@@ -1469,6 +1470,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p);
+
+extern unsigned int sysctl_numa_balancing_migrate_deferred;
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8454c38b1b12..e7884dc3416d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -833,6 +833,14 @@ unsigned int sysctl_numa_balancing_scan_size = 256;
 /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */
 unsigned int sysctl_numa_balancing_scan_delay = 1000;
 
+/*
+ * After skipping a page migration on a shared page, skip N more numa page
+ * migrations unconditionally. This reduces the number of NUMA migrations
+ * in shared memory workloads, and has the effect of pulling tasks towards
+ * where their memory lives, over pulling the memory towards the task.
+ */
+unsigned int sysctl_numa_balancing_migrate_deferred = 16;
+
 static unsigned int task_nr_scan_windows(struct task_struct *p)
 {
 	unsigned long rss = 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e509b90a8002..a159e1fd2013 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -391,6 +391,13 @@ static struct ctl_table kern_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
+	{
+		.procname       = "numa_balancing_migrate_deferred",
+		.data           = &sysctl_numa_balancing_migrate_deferred,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_SCHED_DEBUG */
 	{
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2929c24c22b7..71cb253368cb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2301,6 +2301,35 @@ static void sp_free(struct sp_node *n)
 	kmem_cache_free(sn_cache, n);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+	/* Never defer a private fault */
+	if (cpupid_match_pid(p, last_cpupid))
+		return false;
+
+	if (p->numa_migrate_deferred) {
+		p->numa_migrate_deferred--;
+		return true;
+	}
+	return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+	p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
+}
+#else
+static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
+{
+	return false;
+}
+
+static inline void defer_numa_migrate(struct task_struct *p)
+{
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2402,7 +2431,24 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		 * relation.
 		 */
 		last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid)
+		if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
+
+			/* See sysctl_numa_balancing_migrate_deferred comment */
+			if (!cpupid_match_pid(current, last_cpupid))
+				defer_numa_migrate(current);
+
+			goto out;
+		}
+
+		/*
+		 * The quadratic filter above reduces extraneous migration
+		 * of shared pages somewhat. This code reduces it even more,
+		 * reducing the overhead of page migrations of shared pages.
+		 * This makes workloads with shared pages rely more on
+		 * "move task near its memory", and less on "move memory
+		 * towards its task", which is exactly what we want.
+		 */
+		if (numa_migrate_deferred(current, last_cpupid))
 			goto out;
 	}
 
-- 
cgit 


From a8bf7527a2e17ccf1366e67f6ac728327ca34c40 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Mon, 26 Aug 2013 11:22:45 -0500
Subject: of: create unflatten_and_copy_device_tree

Several architectures using DT support built-in dtb's in the init
section. These platforms need to copy the dtb from init since the
strings are referenced after unflattening. Every arch has their own
copying routine which do the same thing. Create a common function,
unflatten_and_copy_device_tree, to copy the dtb when unflattening the
dtb.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/fdt.c       | 24 ++++++++++++++++++++++++
 include/linux/of_fdt.h |  2 ++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 229dd9d69e18..51776166d2b0 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -802,6 +802,30 @@ void __init unflatten_device_tree(void)
 	of_alias_scan(early_init_dt_alloc_memory_arch);
 }
 
+/**
+ * unflatten_and_copy_device_tree - copy and create tree of device_nodes from flat blob
+ *
+ * Copies and unflattens the device-tree passed by the firmware, creating the
+ * tree of struct device_node. It also fills the "name" and "type"
+ * pointers of the nodes so the normal device-tree walking functions
+ * can be used. This should only be used when the FDT memory has not been
+ * reserved such is the case when the FDT is built-in to the kernel init
+ * section. If the FDT memory is reserved already then unflatten_device_tree
+ * should be used instead.
+ */
+void __init unflatten_and_copy_device_tree(void)
+{
+	int size = __be32_to_cpu(initial_boot_params->totalsize);
+	void *dt = early_init_dt_alloc_memory_arch(size,
+		__alignof__(struct boot_param_header));
+
+	if (dt) {
+		memcpy(dt, initial_boot_params, size);
+		initial_boot_params = dt;
+	}
+	unflatten_device_tree();
+}
+
 #endif /* CONFIG_OF_EARLY_FLATTREE */
 
 /* Feed entire flattened device tree into the random pool */
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index a478c62a2aab..58c28a8cc257 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -118,9 +118,11 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname,
 
 /* Other Prototypes */
 extern void unflatten_device_tree(void);
+extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 #else /* CONFIG_OF_FLATTREE */
 static inline void unflatten_device_tree(void) {}
+static inline void unflatten_and_copy_device_tree(void) {}
 #endif /* CONFIG_OF_FLATTREE */
 
 #endif /* __ASSEMBLY__ */
-- 
cgit 


From 0288ffcbfdf9b8656e7320c24caa1e4c1d498287 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Mon, 26 Aug 2013 09:47:40 -0500
Subject: of: Introduce common early_init_dt_scan

Most architectures scan the all the same items early in the FDT and none
are really architecture specific. Create a common early_init_dt_scan to
unify the early scan of root, memory, and chosen nodes in the flattened
DT.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/fdt.c       | 26 ++++++++++++++++++++++++++
 include/linux/of_fdt.h |  2 ++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 51776166d2b0..bfbfda543768 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -785,6 +785,32 @@ void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
 }
 #endif
 
+bool __init early_init_dt_scan(void *params)
+{
+	if (!params)
+		return false;
+
+	/* Setup flat device-tree pointer */
+	initial_boot_params = params;
+
+	/* check device tree validity */
+	if (be32_to_cpu(initial_boot_params->magic) != OF_DT_HEADER) {
+		initial_boot_params = NULL;
+		return false;
+	}
+
+	/* Retrieve various information from the /chosen node */
+	of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
+
+	/* Initialize {size,address}-cells info */
+	of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+	/* Setup memory, calling early_init_dt_add_memory_arch */
+	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
+
+	return true;
+}
+
 /**
  * unflatten_device_tree - create tree of device_nodes from flat blob
  *
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 58c28a8cc257..73e16511134e 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -116,6 +116,8 @@ extern void early_init_dt_setup_initrd_arch(u64 start, u64 end);
 extern int early_init_dt_scan_root(unsigned long node, const char *uname,
 				   int depth, void *data);
 
+extern bool early_init_dt_scan(void *params);
+
 /* Other Prototypes */
 extern void unflatten_device_tree(void);
 extern void unflatten_and_copy_device_tree(void);
-- 
cgit 


From 29eb45a9ab4839a1e9cef2bcf369b918c9c4fcad Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Fri, 30 Aug 2013 17:06:53 -0500
Subject: of: remove early_init_dt_setup_initrd_arch

All arches do essentially the same thing now for
early_init_dt_setup_initrd_arch, so it can now be removed.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Vineet Gupta <vgupta@synopsys.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Mark Salter <msalter@redhat.com>
Cc: Aurelien Jacquiot <a-jacquiot@ti.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Chris Zankel <chris@zankel.net>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 arch/arc/mm/init.c            |  7 -------
 arch/arm/mm/init.c            |  8 --------
 arch/c6x/kernel/devicetree.c  | 10 ----------
 arch/metag/mm/init.c          |  9 ---------
 arch/microblaze/kernel/prom.c |  9 ---------
 arch/mips/kernel/prom.c       | 10 ----------
 arch/openrisc/kernel/prom.c   |  9 ---------
 arch/powerpc/kernel/prom.c    |  9 ---------
 arch/x86/kernel/devicetree.c  |  9 ---------
 arch/xtensa/kernel/setup.c    | 15 ++++-----------
 drivers/of/fdt.c              |  9 ++++++---
 include/linux/of_fdt.h        | 10 ----------
 12 files changed, 10 insertions(+), 104 deletions(-)

(limited to 'include')

diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 81279ec73a6a..55e0a85bea78 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -125,10 +125,3 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 	free_reserved_area((void *)start, (void *)end, -1, "initrd");
 }
 #endif
-
-#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	pr_err("%s(%llx, %llx)\n", __func__, start, end);
-}
-#endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9eeb1cd1c401..9d0b91dccf37 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -77,14 +77,6 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
-#if defined(CONFIG_OF_FLATTREE) && defined(CONFIG_BLK_DEV_INITRD)
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-}
-#endif /* CONFIG_OF_FLATTREE */
-
 /*
  * This keeps memory configuration data used by a couple memory
  * initialization functions, as well as show_mem() for the skipping
diff --git a/arch/c6x/kernel/devicetree.c b/arch/c6x/kernel/devicetree.c
index d28a92fc0c52..fa3e5741514e 100644
--- a/arch/c6x/kernel/devicetree.c
+++ b/arch/c6x/kernel/devicetree.c
@@ -10,18 +10,8 @@
  *
  */
 #include <linux/init.h>
-#include <linux/initrd.h>
 #include <linux/memblock.h>
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
-
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	c6x_add_memory(base, size);
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index 123919534b80..249fff66add3 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -12,7 +12,6 @@
 #include <linux/percpu.h>
 #include <linux/memblock.h>
 #include <linux/initrd.h>
-#include <linux/of_fdt.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -405,11 +404,3 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 			   "initrd");
 }
 #endif
-
-#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	pr_err("%s(%llx, %llx)\n",
-	       __func__, start, end);
-}
-#endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 951e4d61ca2d..cab6dc356119 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -114,15 +114,6 @@ void __init early_init_devtree(void *params)
 	pr_debug(" <- early_init_devtree()\n");
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
-
 /*******
  *
  * New implementation of the OF "find" APIs, return a refcounted
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 67a4c53b2b54..0b2485f9a6c1 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -13,7 +13,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/bootmem.h>
-#include <linux/initrd.h>
 #include <linux/debugfs.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
@@ -48,15 +47,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
-
 int __init early_init_dt_scan_model(unsigned long node,	const char *uname,
 				    int depth, void *data)
 {
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 6dbcaa85421c..2aae474b44c3 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -52,12 +52,3 @@ void __init early_init_devtree(void *params)
 	early_init_dt_scan(params);
 	memblock_allow_resize();
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index b7634ce41dbc..a0894688daef 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -546,15 +546,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
-
 static void __init early_reserve_mem_dt(void)
 {
 	unsigned long i, len, dt_root;
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 0db805c4b9e8..0e1f95b06336 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -51,15 +51,6 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (unsigned long)__va(start);
-	initrd_end = (unsigned long)__va(end);
-	initrd_below_start_ok = 1;
-}
-#endif
-
 void __init add_dtb(u64 data)
 {
 	initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 65974a8f41a4..6e2b6638122d 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -61,8 +61,8 @@ extern struct rtc_ops no_rtc_ops;
 struct rtc_ops *rtc_ops;
 
 #ifdef CONFIG_BLK_DEV_INITRD
-extern void *initrd_start;
-extern void *initrd_end;
+extern unsigned long initrd_start;
+extern unsigned long initrd_end;
 int initrd_is_mapped = 0;
 extern int initrd_below_start_ok;
 #endif
@@ -149,8 +149,8 @@ static int __init parse_tag_initrd(const bp_tag_t* tag)
 {
 	meminfo_t* mi;
 	mi = (meminfo_t*)(tag->data);
-	initrd_start = __va(mi->start);
-	initrd_end = __va(mi->end);
+	initrd_start = (unsigned long)__va(mi->start);
+	initrd_end = (unsigned long)__va(mi->end);
 
 	return 0;
 }
@@ -167,13 +167,6 @@ static int __init parse_tag_fdt(const bp_tag_t *tag)
 
 __tagtable(BP_TAG_FDT, parse_tag_fdt);
 
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	initrd_start = (void *)__va(start);
-	initrd_end = (void *)__va(end);
-	initrd_below_start_ok = 1;
-}
-
 #endif /* CONFIG_OF */
 
 #endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 5bc55b6e2b41..5f4cc88cd89e 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -624,7 +624,7 @@ int __init of_scan_flat_dt_by_path(const char *path,
  * early_init_dt_check_for_initrd - Decode initrd location from flat tree
  * @node: reference to node containing initrd location ('chosen')
  */
-void __init early_init_dt_check_for_initrd(unsigned long node)
+static void __init early_init_dt_check_for_initrd(unsigned long node)
 {
 	u64 start, end;
 	unsigned long len;
@@ -642,12 +642,15 @@ void __init early_init_dt_check_for_initrd(unsigned long node)
 		return;
 	end = of_read_number(prop, len/4);
 
-	early_init_dt_setup_initrd_arch(start, end);
+	initrd_start = (unsigned long)__va(start);
+	initrd_end = (unsigned long)__va(end);
+	initrd_below_start_ok = 1;
+
 	pr_debug("initrd_start=0x%llx  initrd_end=0x%llx\n",
 		 (unsigned long long)start, (unsigned long long)end);
 }
 #else
-inline void early_init_dt_check_for_initrd(unsigned long node)
+static inline void early_init_dt_check_for_initrd(unsigned long node)
 {
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 73e16511134e..b365f5ac7b54 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -96,22 +96,12 @@ extern int of_scan_flat_dt_by_path(const char *path,
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
-extern void early_init_dt_check_for_initrd(unsigned long node);
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
 extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
 extern u64 dt_mem_next_cell(int s, __be32 **cellp);
 
-/*
- * If BLK_DEV_INITRD, the fdt early init code will call this function,
- * to be provided by the arch code. start and end are specified as
- * physical addresses.
- */
-#ifdef CONFIG_BLK_DEV_INITRD
-extern void early_init_dt_setup_initrd_arch(u64 start, u64 end);
-#endif
-
 /* Early flat tree scan hooks */
 extern int early_init_dt_scan_root(unsigned long node, const char *uname,
 				   int depth, void *data);
-- 
cgit 


From 69908907b02efee31377af0cefbcd5a3ba66334a Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Wed, 9 Oct 2013 16:56:32 +0000
Subject: xen: make xen_create_contiguous_region return the dma address

Modify xen_create_contiguous_region to return the dma address of the
newly contiguous buffer.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: David Vrabel <david.vrabel@citrix.com>


Changes in v4:
- use virt_to_machine instead of virt_to_bus.
---
 arch/x86/xen/mmu.c        | 4 +++-
 drivers/xen/swiotlb-xen.c | 6 +++---
 include/xen/xen-ops.h     | 3 ++-
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fdc3ba28ca38..6c34d7c03d5b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2329,7 +2329,8 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
 }
 
 int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
-				 unsigned int address_bits)
+				 unsigned int address_bits,
+				 dma_addr_t *dma_handle)
 {
 	unsigned long *in_frames = discontig_frames, out_frame;
 	unsigned long  flags;
@@ -2368,6 +2369,7 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 
 	spin_unlock_irqrestore(&xen_reservation_lock, flags);
 
+	*dma_handle = virt_to_machine(vstart).maddr;
 	return success ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 1b2277c311d2..b72f31c1e018 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -126,6 +126,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 {
 	int i, rc;
 	int dma_bits;
+	dma_addr_t dma_handle;
 
 	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
 
@@ -137,7 +138,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 			rc = xen_create_contiguous_region(
 				(unsigned long)buf + (i << IO_TLB_SHIFT),
 				get_order(slabs << IO_TLB_SHIFT),
-				dma_bits);
+				dma_bits, &dma_handle);
 		} while (rc && dma_bits++ < max_dma_bits);
 		if (rc)
 			return rc;
@@ -294,11 +295,10 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		*dma_handle = dev_addr;
 	else {
 		if (xen_create_contiguous_region(vstart, order,
-						 fls64(dma_mask)) != 0) {
+						 fls64(dma_mask), dma_handle) != 0) {
 			free_pages(vstart, order);
 			return NULL;
 		}
-		*dma_handle = virt_to_machine(ret).maddr;
 	}
 	memset(ret, 0, size);
 	return ret;
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index d6fe062cad6b..9ef704d3a9dd 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -20,7 +20,8 @@ int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
 int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
-				unsigned int address_bits);
+				unsigned int address_bits,
+				dma_addr_t *dma_handle);
 
 void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
 
-- 
cgit 


From eb1ddc00b81cb8cb23891b6c7c5fbfaea29f3c73 Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Wed, 9 Oct 2013 16:56:33 +0000
Subject: swiotlb-xen: introduce xen_swiotlb_set_dma_mask

Implement xen_swiotlb_set_dma_mask, use it for set_dma_mask on arm.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 arch/arm/xen/mm.c         |  1 +
 drivers/xen/swiotlb-xen.c | 12 ++++++++++++
 include/xen/swiotlb-xen.h |  2 ++
 3 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d56b8c6e4fbb..0d69b874d249 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -51,6 +51,7 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.map_page = xen_swiotlb_map_page,
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
+	.set_dma_mask = xen_swiotlb_set_dma_mask,
 };
 
 int __init xen_mm_init(void)
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f0fc1a4f565a..d8ef0bf577d2 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -608,3 +608,15 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 	return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);
+
+int
+xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
+{
+	if (!dev->dma_mask || !xen_swiotlb_dma_supported(dev, dma_mask))
+		return -EIO;
+
+	*dev->dma_mask = dma_mask;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index de8bcc641c49..7b644650d968 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -55,4 +55,6 @@ xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
 extern int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
+extern int
+xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
 #endif /* __LINUX_SWIOTLB_XEN_H */
-- 
cgit 


From c2bb06db59eaf92eb5ca9c6faed590597c6ceccb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2013 03:05:48 -0700
Subject: net: fix build errors if ipv6 is disabled

CONFIG_IPV6=n is still a valid choice ;)

It appears we can remove dead code.

Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_checksum.h | 2 ++
 net/ipv4/ping.c            | 8 +++++---
 net/ipv4/tcp_metrics.c     | 4 ++++
 net/sunrpc/svcsock.c       | 2 ++
 security/lsm_audit.c       | 2 ++
 5 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 1944406949ba..9e3c540c1b11 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -66,12 +66,14 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb,
 	}
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 
 	__tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr);
 }
+#endif
 
 int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto);
 #endif
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index ccefc07beacd..9afbdb19f4a2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -415,10 +415,12 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		 (int)sk->sk_bound_dev_if);
 
 	err = 0;
-	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
-	    (sk->sk_family == AF_INET6 &&
-	     !ipv6_addr_any(&sk->sk_v6_rcv_saddr)))
+	if (sk->sk_family == AF_INET && isk->inet_rcv_saddr)
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+#endif
 
 	if (snum)
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 27535fd5ea10..8fcc2cb9dba4 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -251,10 +251,12 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		addr.addr.a4 = tw->tw_daddr;
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
 		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		break;
+#endif
 	default:
 		return NULL;
 	}
@@ -286,10 +288,12 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		addr.addr.a4 = inet_sk(sk)->inet_daddr;
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
 		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		break;
+#endif
 	default:
 		return NULL;
 	}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0045c7cf1e9e..b6e59f0a9475 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -291,12 +291,14 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 				&inet_sk(sk)->inet_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
 		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
 				proto_name,
 				&sk->sk_v6_rcv_saddr,
 				inet_sk(sk)->inet_num);
 		break;
+#endif
 	default:
 		len = snprintf(buf, remaining, "*unknown-%d*\n",
 				sk->sk_family);
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 80554fcf9fcc..234bc2ab450c 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -302,6 +302,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 						"faddr", "fport");
 				break;
 			}
+#if IS_ENABLED(CONFIG_IPV6)
 			case AF_INET6: {
 				struct inet_sock *inet = inet_sk(sk);
 
@@ -313,6 +314,7 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 						"faddr", "fport");
 				break;
 			}
+#endif
 			case AF_UNIX:
 				u = unix_sk(sk);
 				if (u->path.dentry) {
-- 
cgit 


From b4042ceaabbd913bc5b397ddd1e396eeb312d72f Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Thu, 18 Jul 2013 16:21:19 -0700
Subject: sched_clock: Remove sched_clock_func() hook

Nobody is using sched_clock_func() anymore now that sched_clock
supports up to 64 bits. Remove the hook so that new code only
uses sched_clock_register().

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/sched_clock.h | 2 --
 kernel/time/sched_clock.c   | 9 +--------
 2 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index eca7abeb86fc..cddf0c2940b6 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -18,6 +18,4 @@ extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
 extern void sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate);
 
-extern unsigned long long (*sched_clock_func)(void);
-
 #endif
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index f388baeaf2b6..68b799375981 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -63,7 +63,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long notrace sched_clock_32(void)
+unsigned long long notrace sched_clock(void)
 {
 	u64 epoch_ns;
 	u64 epoch_cyc;
@@ -170,13 +170,6 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	sched_clock_register(read_sched_clock_32_wrapper, bits, rate);
 }
 
-unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
-
-unsigned long long notrace sched_clock(void)
-{
-	return sched_clock_func();
-}
-
 void __init sched_clock_postinit(void)
 {
 	/*
-- 
cgit 


From 6a903a2551ef778d60ce4341722d611144251398 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Tue, 27 Aug 2013 21:41:56 -0500
Subject: of: introduce common FDT machine related functions

Introduce common of_flat_dt_match_machine and
of_flat_dt_get_machine_name functions to unify architectures' handling
of machine level model and compatible properties.

Several architectures match the root compatible string with an arch
specific list of machine descriptors duplicating the same search
algorithm. Create a common implementation with a simple architecture
specific hook to iterate over each machine's match table.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/fdt.c       | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of_fdt.h |  5 +++++
 2 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 5f4cc88cd89e..5c479104fc67 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -619,6 +619,66 @@ int __init of_scan_flat_dt_by_path(const char *path,
 		return ret;
 }
 
+const char * __init of_flat_dt_get_machine_name(void)
+{
+	const char *name;
+	unsigned long dt_root = of_get_flat_dt_root();
+
+	name = of_get_flat_dt_prop(dt_root, "model", NULL);
+	if (!name)
+		name = of_get_flat_dt_prop(dt_root, "compatible", NULL);
+	return name;
+}
+
+/**
+ * of_flat_dt_match_machine - Iterate match tables to find matching machine.
+ *
+ * @default_match: A machine specific ptr to return in case of no match.
+ * @get_next_compat: callback function to return next compatible match table.
+ *
+ * Iterate through machine match tables to find the best match for the machine
+ * compatible string in the FDT.
+ */
+const void * __init of_flat_dt_match_machine(const void *default_match,
+		const void * (*get_next_compat)(const char * const**))
+{
+	const void *data = NULL;
+	const void *best_data = default_match;
+	const char *const *compat;
+	unsigned long dt_root;
+	unsigned int best_score = ~1, score = 0;
+
+	dt_root = of_get_flat_dt_root();
+	while ((data = get_next_compat(&compat))) {
+		score = of_flat_dt_match(dt_root, compat);
+		if (score > 0 && score < best_score) {
+			best_data = data;
+			best_score = score;
+		}
+	}
+	if (!best_data) {
+		const char *prop;
+		long size;
+
+		pr_err("\n unrecognized device tree list:\n[ ");
+
+		prop = of_get_flat_dt_prop(dt_root, "compatible", &size);
+		if (prop) {
+			while (size > 0) {
+				printk("'%s' ", prop);
+				size -= strlen(prop) + 1;
+				prop += strlen(prop) + 1;
+			}
+		}
+		printk("]\n\n");
+		return NULL;
+	}
+
+	pr_info("Machine model: %s\n", of_flat_dt_get_machine_name());
+
+	return best_data;
+}
+
 #ifdef CONFIG_BLK_DEV_INITRD
 /**
  * early_init_dt_check_for_initrd - Decode initrd location from flat tree
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index b365f5ac7b54..0beaee9dac1f 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -108,11 +108,16 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname,
 
 extern bool early_init_dt_scan(void *params);
 
+extern const char *of_flat_dt_get_machine_name(void);
+extern const void *of_flat_dt_match_machine(const void *default_match,
+		const void * (*get_next_compat)(const char * const**));
+
 /* Other Prototypes */
 extern void unflatten_device_tree(void);
 extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 #else /* CONFIG_OF_FLATTREE */
+static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
 static inline void unflatten_device_tree(void) {}
 static inline void unflatten_and_copy_device_tree(void) {}
 #endif /* CONFIG_OF_FLATTREE */
-- 
cgit 


From 25ff79443cbfa924b8df1d4a8a0fbff83816938a Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Sat, 7 Sep 2013 14:07:11 -0500
Subject: of: implement pci_address_to_pio as weak function

Implement pci_address_to_pio as weak function to remove the dependency on
asm/prom.h. This is in preparation to make prom.h optional.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Grant Likely <grant.likely@linaro.org>
---
 arch/microblaze/include/asm/prom.h |  9 ---------
 arch/mips/include/asm/prom.h       | 11 -----------
 arch/powerpc/include/asm/prom.h    |  5 -----
 arch/x86/include/asm/prom.h        |  3 ---
 arch/x86/kernel/devicetree.c       | 10 ----------
 drivers/of/address.c               |  8 ++++++++
 drivers/of/of_pci.c                |  1 -
 include/linux/of_address.h         |  5 +----
 8 files changed, 9 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h
index f05bedce70d0..0ebd924902df 100644
--- a/arch/microblaze/include/asm/prom.h
+++ b/arch/microblaze/include/asm/prom.h
@@ -26,13 +26,4 @@ enum early_consoles {
 
 extern int of_early_console(void *version);
 
-/*
- * OF address retreival & translation
- */
-
-#ifdef CONFIG_PCI
-extern unsigned long pci_address_to_pio(phys_addr_t address);
-#define pci_address_to_pio pci_address_to_pio
-#endif	/* CONFIG_PCI */
-
 #endif /* _ASM_MICROBLAZE_PROM_H */
diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h
index e3dbd0e0608e..ccd2b75f152c 100644
--- a/arch/mips/include/asm/prom.h
+++ b/arch/mips/include/asm/prom.h
@@ -19,17 +19,6 @@
 
 extern void device_tree_init(void);
 
-static inline unsigned long pci_address_to_pio(phys_addr_t address)
-{
-	/*
-	 * The ioport address can be directly used by inX() / outX()
-	 */
-	BUG_ON(address > IO_SPACE_LIMIT);
-
-	return (unsigned long) address;
-}
-#define pci_address_to_pio pci_address_to_pio
-
 struct boot_param_header;
 
 extern void __dt_setup_arch(struct boot_param_header *bph);
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 7d0c7f3a7171..bd215f74df0f 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -30,11 +30,6 @@
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
 
-#ifdef CONFIG_PCI
-extern unsigned long pci_address_to_pio(phys_addr_t address);
-#define pci_address_to_pio pci_address_to_pio
-#endif	/* CONFIG_PCI */
-
 /* Parse the ibm,dma-window property of an OF node into the busno, phys and
  * size parameters.
  */
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index bade6ac3b14f..8ef2ec70858f 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -39,9 +39,6 @@ static inline void x86_dtb_init(void) { }
 
 extern char cmd_line[COMMAND_LINE_SIZE];
 
-#define pci_address_to_pio pci_address_to_pio
-unsigned long pci_address_to_pio(phys_addr_t addr);
-
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 679d676a30d7..cffd07368547 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -27,16 +27,6 @@ char __initdata cmd_line[COMMAND_LINE_SIZE];
 
 int __initdata of_ioapic;
 
-unsigned long pci_address_to_pio(phys_addr_t address)
-{
-	/*
-	 * The ioport address can be directly used by inX / outX
-	 */
-	BUG_ON(address >= (1 << 16));
-	return (unsigned long)address;
-}
-EXPORT_SYMBOL_GPL(pci_address_to_pio);
-
 void __init early_init_dt_scan_chosen_arch(unsigned long node)
 {
 	BUG();
diff --git a/drivers/of/address.c b/drivers/of/address.c
index b55c21890760..556a7fb6ead3 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -626,6 +626,14 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size,
 }
 EXPORT_SYMBOL(of_get_address);
 
+unsigned long __weak pci_address_to_pio(phys_addr_t address)
+{
+	if (address > IO_SPACE_LIMIT)
+		return (unsigned long)-1;
+
+	return (unsigned long) address;
+}
+
 static int __of_address_to_resource(struct device_node *dev,
 		const __be32 *addrp, u64 size, unsigned int flags,
 		const char *name, struct resource *r)
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index e5ca00893c0c..848199633798 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -2,7 +2,6 @@
 #include <linux/export.h>
 #include <linux/of.h>
 #include <linux/of_pci.h>
-#include <asm/prom.h>
 
 static inline int __of_pci_pci_compare(struct device_node *node,
 				       unsigned int data)
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 4c2e6f26432c..f6fc6899ceae 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -52,10 +52,7 @@ extern void __iomem *of_iomap(struct device_node *device, int index);
 extern const __be32 *of_get_address(struct device_node *dev, int index,
 			   u64 *size, unsigned int *flags);
 
-#ifndef pci_address_to_pio
-static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; }
-#define pci_address_to_pio pci_address_to_pio
-#endif
+extern unsigned long pci_address_to_pio(phys_addr_t addr);
 
 extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 			struct device_node *node);
-- 
cgit 


From 0c3f061c195ceb891067b6de9e4ecc347c4dea31 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Tue, 17 Sep 2013 10:42:50 -0500
Subject: of: implement of_node_to_nid as a weak function

Implement of_node_to_nid as weak function to remove the dependency on
asm/prom.h. This is in preparation to make prom.h optional.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 arch/powerpc/include/asm/prom.h |  7 -------
 arch/sparc/include/asm/prom.h   |  4 ----
 drivers/of/base.c               |  7 +++++++
 include/linux/of.h              | 11 ++++-------
 4 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bd215f74df0f..6707c16d8fc5 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -42,13 +42,6 @@ extern void kdump_move_device_tree(void);
 /* cache lookup */
 struct device_node *of_find_next_cache_node(struct device_node *np);
 
-#ifdef CONFIG_NUMA
-extern int of_node_to_nid(struct device_node *device);
-#else
-static inline int of_node_to_nid(struct device_node *device) { return 0; }
-#endif
-#define of_node_to_nid of_node_to_nid
-
 extern void of_instantiate_rtc(void);
 
 extern int of_get_ibm_chip_id(struct device_node *np);
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index 67c62578d170..60c8d7bd4058 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -43,10 +43,6 @@ extern int of_getintprop_default(struct device_node *np,
 				 const char *name,
 				 int def);
 extern int of_find_in_proplist(const char *list, const char *match, int len);
-#ifdef CONFIG_NUMA
-extern int of_node_to_nid(struct device_node *dp);
-#define of_node_to_nid of_node_to_nid
-#endif
 
 extern void prom_build_devicetree(void);
 extern void of_populate_present_mask(void);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 865d3f66c86b..ced4c06d79b3 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -74,6 +74,13 @@ int of_n_size_cells(struct device_node *np)
 }
 EXPORT_SYMBOL(of_n_size_cells);
 
+#ifdef CONFIG_NUMA
+int __weak of_node_to_nid(struct device_node *np)
+{
+	return numa_node_id();
+}
+#endif
+
 #if defined(CONFIG_OF_DYNAMIC)
 /**
  *	of_node_get - Increment refcount of a node
diff --git a/include/linux/of.h b/include/linux/of.h
index f95aee391e30..4d294a0b8a57 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -534,13 +534,10 @@ static inline const char *of_prop_next_string(struct property *prop,
 #define of_match_node(_matches, _node)	NULL
 #endif /* CONFIG_OF */
 
-#ifndef of_node_to_nid
-static inline int of_node_to_nid(struct device_node *np)
-{
-	return numa_node_id();
-}
-
-#define of_node_to_nid of_node_to_nid
+#if defined(CONFIG_OF) && defined(CONFIG_NUMA)
+extern int of_node_to_nid(struct device_node *np);
+#else
+static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 
 /**
-- 
cgit 


From 4acf4b9cd4534aaa9102004937e1ba79da01d008 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Mon, 16 Sep 2013 21:03:24 -0500
Subject: of: move of_address_to_resource and of_iomap declarations from sparc

Move of_address_to_resource and of_iomap declarations to common code. These
only differ on sparc, but the declarations are the same and don't need to
be in arch header.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: sparclinux@vger.kernel.org
---
 arch/sparc/include/asm/prom.h |  8 --------
 include/linux/of_address.h    | 30 +++++++++++++++++-------------
 2 files changed, 17 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index 60c8d7bd4058..11ebd659e7b6 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -59,13 +59,5 @@ extern char *of_console_options;
 extern void irq_trans_init(struct device_node *dp);
 extern char *build_path_component(struct device_node *dp);
 
-/* SPARC has local implementations */
-extern int of_address_to_resource(struct device_node *dev, int index,
-				  struct resource *r);
-#define of_address_to_resource of_address_to_resource
-
-void __iomem *of_iomap(struct device_node *node, int index);
-#define of_iomap of_iomap
-
 #endif /* __KERNEL__ */
 #endif /* _SPARC_PROM_H */
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index f6fc6899ceae..e8a179773a1a 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -60,13 +60,6 @@ extern struct of_pci_range *of_pci_range_parser_one(
 					struct of_pci_range_parser *parser,
 					struct of_pci_range *range);
 #else /* CONFIG_OF_ADDRESS */
-#ifndef of_address_to_resource
-static inline int of_address_to_resource(struct device_node *dev, int index,
-					 struct resource *r)
-{
-	return -EINVAL;
-}
-#endif
 static inline struct device_node *of_find_matching_node_by_address(
 					struct device_node *from,
 					const struct of_device_id *matches,
@@ -74,12 +67,7 @@ static inline struct device_node *of_find_matching_node_by_address(
 {
 	return NULL;
 }
-#ifndef of_iomap
-static inline void __iomem *of_iomap(struct device_node *device, int index)
-{
-	return NULL;
-}
-#endif
+
 static inline const __be32 *of_get_address(struct device_node *dev, int index,
 					u64 *size, unsigned int *flags)
 {
@@ -100,6 +88,22 @@ static inline struct of_pci_range *of_pci_range_parser_one(
 }
 #endif /* CONFIG_OF_ADDRESS */
 
+#ifdef CONFIG_OF
+extern int of_address_to_resource(struct device_node *dev, int index,
+				  struct resource *r);
+void __iomem *of_iomap(struct device_node *node, int index);
+#else
+static inline int of_address_to_resource(struct device_node *dev, int index,
+					 struct resource *r)
+{
+	return -EINVAL;
+}
+
+static inline void __iomem *of_iomap(struct device_node *device, int index)
+{
+	return NULL;
+}
+#endif
 
 #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI)
 extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no,
-- 
cgit 


From d0dfa16a600190d142f7538e5909d13c35b60d98 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Mon, 16 Sep 2013 21:05:05 -0500
Subject: of: move of_translate_dma_address to of_address.h

of_translate_dma_address is implemented in common code, so move the
declaration there too.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
---
 arch/powerpc/include/asm/prom.h | 4 ----
 include/linux/of_address.h      | 4 ++++
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 43fe0023d722..b8774bdc69e0 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -24,10 +24,6 @@
  * OF address retreival & translation
  */
 
-/* Translate a DMA address from device space to CPU space */
-extern u64 of_translate_dma_address(struct device_node *dev,
-				    const __be32 *in_addr);
-
 /* Parse the ibm,dma-window property of an OF node into the busno, phys and
  * size parameters.
  */
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index e8a179773a1a..5f6ed6b182b8 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -34,6 +34,10 @@ static inline void of_pci_range_to_resource(struct of_pci_range *range,
 	res->name = np->full_name;
 }
 
+/* Translate a DMA address from device space to CPU space */
+extern u64 of_translate_dma_address(struct device_node *dev,
+				    const __be32 *in_addr);
+
 #ifdef CONFIG_OF_ADDRESS
 extern u64 of_translate_address(struct device_node *np, const __be32 *addr);
 extern bool of_can_translate_address(struct device_node *dev);
-- 
cgit 


From b5b4bb3f6a11f9c37b6d53138244f2ffe5bacd12 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Sat, 7 Sep 2013 14:08:20 -0500
Subject: of: only include prom.h on sparc

The dependency on prom.h by the core DT code is now removed and only
sparc needs to include prom.h for the core code.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 4d294a0b8a57..54017b83650b 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -136,7 +136,9 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size)
 	return of_read_number(cell, size);
 }
 
+#if defined(CONFIG_SPARC)
 #include <asm/prom.h>
+#endif
 
 /* Default #address and #size cells.  Allow arch asm/prom.h to override */
 #if !defined(OF_ROOT_NODE_ADDR_CELLS_DEFAULT)
-- 
cgit 


From 634fb979e8f3a70f04c1f2f519d0cd1142eb5c1a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2013 15:21:29 -0700
Subject: inet: includes a sock_common in request_sock

TCP listener refactoring, part 5 :

We want to be able to insert request sockets (SYN_RECV) into main
ehash table instead of the per listener hash table to allow RCU
lookups and remove listener lock contention.

This patch includes the needed struct sock_common in front
of struct request_sock

This means there is no more inet6_request_sock IPv6 specific
structure.

Following inet_request_sock fields were renamed as they became
macros to reference fields from struct sock_common.
Prefix ir_ was chosen to avoid name collisions.

loc_port   -> ir_loc_port
loc_addr   -> ir_loc_addr
rmt_addr   -> ir_rmt_addr
rmt_port   -> ir_rmt_port
iif        -> ir_iif

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h             | 26 ++---------------
 include/net/inet_sock.h          | 16 +++++-----
 include/net/request_sock.h       |  1 +
 include/net/tcp.h                |  4 +--
 net/dccp/ipv4.c                  | 18 ++++++------
 net/dccp/ipv6.c                  | 63 ++++++++++++++++++++--------------------
 net/dccp/ipv6.h                  |  1 -
 net/dccp/minisocks.c             |  4 +--
 net/dccp/output.c                |  4 +--
 net/ipv4/inet_connection_sock.c  | 23 ++++++++-------
 net/ipv4/inet_diag.c             | 22 +++++++-------
 net/ipv4/syncookies.c            | 12 ++++----
 net/ipv4/tcp_ipv4.c              | 38 ++++++++++++------------
 net/ipv4/tcp_metrics.c           |  8 +++--
 net/ipv4/tcp_output.c            |  4 +--
 net/ipv6/inet6_connection_sock.c | 26 ++++++++---------
 net/ipv6/syncookies.c            | 24 +++++++--------
 net/ipv6/tcp_ipv6.c              | 61 +++++++++++++++++++-------------------
 net/netlabel/netlabel_kapi.c     |  2 +-
 19 files changed, 169 insertions(+), 188 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 35f6c1b562c4..a80a63cfb70c 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -115,16 +115,8 @@ static inline int inet6_iif(const struct sk_buff *skb)
 	return IP6CB(skb)->iif;
 }
 
-struct inet6_request_sock {
-	struct in6_addr		loc_addr;
-	struct in6_addr		rmt_addr;
-	struct sk_buff		*pktopts;
-	int			iif;
-};
-
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
-	struct inet6_request_sock tcp6rsk_inet6;
 };
 
 struct ipv6_mc_socklist;
@@ -264,26 +256,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 	return inet_sk(__sk)->pinet6;
 }
 
-static inline struct inet6_request_sock *
-			inet6_rsk(const struct request_sock *rsk)
-{
-	return (struct inet6_request_sock *)(((u8 *)rsk) +
-					     inet_rsk(rsk)->inet6_rsk_offset);
-}
-
-static inline u32 inet6_rsk_offset(struct request_sock *rsk)
-{
-	return rsk->rsk_ops->obj_size - sizeof(struct inet6_request_sock);
-}
-
 static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *ops)
 {
 	struct request_sock *req = reqsk_alloc(ops);
 
-	if (req != NULL) {
-		inet_rsk(req)->inet6_rsk_offset = inet6_rsk_offset(req);
-		inet6_rsk(req)->pktopts = NULL;
-	}
+	if (req)
+		inet_rsk(req)->pktopts = NULL;
 
 	return req;
 }
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6d9a7e6eb5a4..f91204442efa 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -70,13 +70,14 @@ struct ip_options_data {
 
 struct inet_request_sock {
 	struct request_sock	req;
-#if IS_ENABLED(CONFIG_IPV6)
-	u16			inet6_rsk_offset;
-#endif
-	__be16			loc_port;
-	__be32			loc_addr;
-	__be32			rmt_addr;
-	__be16			rmt_port;
+#define ir_loc_addr		req.__req_common.skc_rcv_saddr
+#define ir_rmt_addr		req.__req_common.skc_daddr
+#define ir_loc_port		req.__req_common.skc_num
+#define ir_rmt_port		req.__req_common.skc_dport
+#define ir_v6_rmt_addr		req.__req_common.skc_v6_daddr
+#define ir_v6_loc_addr		req.__req_common.skc_v6_rcv_saddr
+#define ir_iif			req.__req_common.skc_bound_dev_if
+
 	kmemcheck_bitfield_begin(flags);
 	u16			snd_wscale : 4,
 				rcv_wscale : 4,
@@ -88,6 +89,7 @@ struct inet_request_sock {
 				no_srccheck: 1;
 	kmemcheck_bitfield_end(flags);
 	struct ip_options_rcu	*opt;
+	struct sk_buff		*pktopts;
 };
 
 static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 65c3e5164a5c..7f830ff67f08 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -48,6 +48,7 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
 /* struct request_sock - mini sock to represent a connection request
  */
 struct request_sock {
+	struct sock_common		__req_common;
 	struct request_sock		*dl_next;
 	u16				mss;
 	u8				num_retrans; /* number of retransmits */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 39bbfa1602b2..24a06161d174 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1109,8 +1109,8 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->wscale_ok = rx_opt->wscale_ok;
 	ireq->acked = 0;
 	ireq->ecn_ok = 0;
-	ireq->rmt_port = tcp_hdr(skb)->source;
-	ireq->loc_port = tcp_hdr(skb)->dest;
+	ireq->ir_rmt_port = tcp_hdr(skb)->source;
+	ireq->ir_loc_port = tcp_hdr(skb)->dest;
 }
 
 void tcp_enter_memory_pressure(struct sock *sk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ebc54fef85a5..720c36225ed9 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -409,9 +409,9 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	newinet		   = inet_sk(newsk);
 	ireq		   = inet_rsk(req);
-	newinet->inet_daddr	= ireq->rmt_addr;
-	newinet->inet_rcv_saddr = ireq->loc_addr;
-	newinet->inet_saddr	= ireq->loc_addr;
+	newinet->inet_daddr	= ireq->ir_rmt_addr;
+	newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+	newinet->inet_saddr	= ireq->ir_loc_addr;
 	newinet->inet_opt	= ireq->opt;
 	ireq->opt	   = NULL;
 	newinet->mc_index  = inet_iif(skb);
@@ -516,10 +516,10 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct dccp_hdr *dh = dccp_hdr(skb);
 
-		dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->loc_addr,
-							      ireq->rmt_addr);
-		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
-					    ireq->rmt_addr,
+		dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
+							      ireq->ir_rmt_addr);
+		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
+					    ireq->ir_rmt_addr,
 					    ireq->opt);
 		err = net_xmit_eval(err);
 	}
@@ -641,8 +641,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	ireq = inet_rsk(req);
-	ireq->loc_addr = ip_hdr(skb)->daddr;
-	ireq->rmt_addr = ip_hdr(skb)->saddr;
+	ireq->ir_loc_addr = ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
 
 	/*
 	 * Step 3: Process LISTEN state
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7f075b83128a..5cc5b24a956e 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -216,7 +216,7 @@ out:
 
 static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 {
-	struct inet6_request_sock *ireq6 = inet6_rsk(req);
+	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;
 	struct in6_addr *final_p, final;
@@ -226,12 +226,12 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_DCCP;
-	fl6.daddr = ireq6->rmt_addr;
-	fl6.saddr = ireq6->loc_addr;
+	fl6.daddr = ireq->ir_v6_rmt_addr;
+	fl6.saddr = ireq->ir_v6_loc_addr;
 	fl6.flowlabel = 0;
-	fl6.flowi6_oif = ireq6->iif;
-	fl6.fl6_dport = inet_rsk(req)->rmt_port;
-	fl6.fl6_sport = inet_rsk(req)->loc_port;
+	fl6.flowi6_oif = ireq->ir_iif;
+	fl6.fl6_dport = ireq->ir_rmt_port;
+	fl6.fl6_sport = ireq->ir_loc_port;
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
@@ -249,9 +249,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 		struct dccp_hdr *dh = dccp_hdr(skb);
 
 		dh->dccph_checksum = dccp_v6_csum_finish(skb,
-							 &ireq6->loc_addr,
-							 &ireq6->rmt_addr);
-		fl6.daddr = ireq6->rmt_addr;
+							 &ireq->ir_v6_loc_addr,
+							 &ireq->ir_v6_rmt_addr);
+		fl6.daddr = ireq->ir_v6_rmt_addr;
 		err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
@@ -264,8 +264,7 @@ done:
 static void dccp_v6_reqsk_destructor(struct request_sock *req)
 {
 	dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
-	if (inet6_rsk(req)->pktopts != NULL)
-		kfree_skb(inet6_rsk(req)->pktopts);
+	kfree_skb(inet_rsk(req)->pktopts);
 }
 
 static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
@@ -359,7 +358,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct request_sock *req;
 	struct dccp_request_sock *dreq;
-	struct inet6_request_sock *ireq6;
+	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
 	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
@@ -398,22 +397,22 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
 
-	ireq6 = inet6_rsk(req);
-	ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
-	ireq6->loc_addr = ipv6_hdr(skb)->daddr;
+	ireq = inet_rsk(req);
+	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
 	if (ipv6_opt_accepted(sk, skb) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
-		ireq6->pktopts = skb;
+		ireq->pktopts = skb;
 	}
-	ireq6->iif = sk->sk_bound_dev_if;
+	ireq->ir_iif = sk->sk_bound_dev_if;
 
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
-	    ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq6->iif = inet6_iif(skb);
+	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		ireq->ir_iif = inet6_iif(skb);
 
 	/*
 	 * Step 3: Process LISTEN state
@@ -446,7 +445,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 					      struct request_sock *req,
 					      struct dst_entry *dst)
 {
-	struct inet6_request_sock *ireq6 = inet6_rsk(req);
+	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct inet_sock *newinet;
 	struct dccp6_sock *newdp6;
@@ -505,12 +504,12 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_DCCP;
-		fl6.daddr = ireq6->rmt_addr;
+		fl6.daddr = ireq->ir_v6_rmt_addr;
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
-		fl6.saddr = ireq6->loc_addr;
+		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
-		fl6.fl6_dport = inet_rsk(req)->rmt_port;
-		fl6.fl6_sport = inet_rsk(req)->loc_port;
+		fl6.fl6_dport = ireq->ir_rmt_port;
+		fl6.fl6_sport = ireq->ir_loc_port;
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
@@ -538,10 +537,10 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newsk->sk_v6_daddr = ireq6->rmt_addr;
-	newnp->saddr = ireq6->loc_addr;
-	newsk->sk_v6_rcv_saddr = ireq6->loc_addr;
-	newsk->sk_bound_dev_if = ireq6->iif;
+	newsk->sk_v6_daddr	= ireq->ir_v6_rmt_addr;
+	newnp->saddr		= ireq->ir_v6_loc_addr;
+	newsk->sk_v6_rcv_saddr	= ireq->ir_v6_loc_addr;
+	newsk->sk_bound_dev_if	= ireq->ir_iif;
 
 	/* Now IPv6 options...
 
@@ -554,10 +553,10 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	/* Clone pktoptions received with SYN */
 	newnp->pktoptions = NULL;
-	if (ireq6->pktopts != NULL) {
-		newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
-		consume_skb(ireq6->pktopts);
-		ireq6->pktopts = NULL;
+	if (ireq->pktopts != NULL) {
+		newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
+		consume_skb(ireq->pktopts);
+		ireq->pktopts = NULL;
 		if (newnp->pktoptions)
 			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
index 6604fc3fe953..af259e15e7f0 100644
--- a/net/dccp/ipv6.h
+++ b/net/dccp/ipv6.h
@@ -25,7 +25,6 @@ struct dccp6_sock {
 
 struct dccp6_request_sock {
 	struct dccp_request_sock  dccp;
-	struct inet6_request_sock inet6;
 };
 
 struct dccp6_timewait_sock {
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 32e80d96d4c0..66afbcec2941 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -266,8 +266,8 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
-	inet_rsk(req)->rmt_port	  = dccp_hdr(skb)->dccph_sport;
-	inet_rsk(req)->loc_port	  = dccp_hdr(skb)->dccph_dport;
+	inet_rsk(req)->ir_rmt_port	  = dccp_hdr(skb)->dccph_sport;
+	inet_rsk(req)->ir_loc_port	  = dccp_hdr(skb)->dccph_dport;
 	inet_rsk(req)->acked	  = 0;
 	dreq->dreq_timestamp_echo = 0;
 
diff --git a/net/dccp/output.c b/net/dccp/output.c
index d17fc90a74b6..9bf195d1b87a 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -424,8 +424,8 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
 	/* Build and checksum header */
 	dh = dccp_zeroed_hdr(skb, dccp_header_size);
 
-	dh->dccph_sport	= inet_rsk(req)->loc_port;
-	dh->dccph_dport	= inet_rsk(req)->rmt_port;
+	dh->dccph_sport	= inet_rsk(req)->ir_loc_port;
+	dh->dccph_dport	= inet_rsk(req)->ir_rmt_port;
 	dh->dccph_doff	= (dccp_header_size +
 			   DCCP_SKB_CB(skb)->dccpd_opt_len) / 4;
 	dh->dccph_type	= DCCP_PKT_RESPONSE;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 56e82a4027b4..2ffd931d652f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -412,8 +412,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol,
 			   flags,
-			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -448,8 +448,8 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
-			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
-			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
@@ -495,9 +495,9 @@ struct request_sock *inet_csk_search_req(const struct sock *sk,
 	     prev = &req->dl_next) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 
-		if (ireq->rmt_port == rport &&
-		    ireq->rmt_addr == raddr &&
-		    ireq->loc_addr == laddr &&
+		if (ireq->ir_rmt_port == rport &&
+		    ireq->ir_rmt_addr == raddr &&
+		    ireq->ir_loc_addr == laddr &&
 		    AF_INET_FAMILY(req->rsk_ops->family)) {
 			WARN_ON(req->sk);
 			*prevp = prev;
@@ -514,7 +514,8 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	const u32 h = inet_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port,
+	const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr,
+				     inet_rsk(req)->ir_rmt_port,
 				     lopt->hash_rnd, lopt->nr_table_entries);
 
 	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
@@ -674,9 +675,9 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newsk->sk_state = TCP_SYN_RECV;
 		newicsk->icsk_bind_hash = NULL;
 
-		inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port;
-		inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port);
-		inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
+		inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
+		inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->ir_loc_port);
+		inet_sk(newsk)->inet_sport = inet_rsk(req)->ir_loc_port;
 		newsk->sk_write_space = sk_stream_write_space;
 
 		newicsk->icsk_retransmits = 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index ecc179d676e4..41e1c3ea8b51 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -679,12 +679,12 @@ static inline void inet_diag_req_addrs(const struct sock *sk,
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6) {
 		if (req->rsk_ops->family == AF_INET6) {
-			entry->saddr = inet6_rsk(req)->loc_addr.s6_addr32;
-			entry->daddr = inet6_rsk(req)->rmt_addr.s6_addr32;
+			entry->saddr = ireq->ir_v6_loc_addr.s6_addr32;
+			entry->daddr = ireq->ir_v6_rmt_addr.s6_addr32;
 		} else if (req->rsk_ops->family == AF_INET) {
-			ipv6_addr_set_v4mapped(ireq->loc_addr,
+			ipv6_addr_set_v4mapped(ireq->ir_loc_addr,
 					       &entry->saddr_storage);
-			ipv6_addr_set_v4mapped(ireq->rmt_addr,
+			ipv6_addr_set_v4mapped(ireq->ir_rmt_addr,
 					       &entry->daddr_storage);
 			entry->saddr = entry->saddr_storage.s6_addr32;
 			entry->daddr = entry->daddr_storage.s6_addr32;
@@ -692,8 +692,8 @@ static inline void inet_diag_req_addrs(const struct sock *sk,
 	} else
 #endif
 	{
-		entry->saddr = &ireq->loc_addr;
-		entry->daddr = &ireq->rmt_addr;
+		entry->saddr = &ireq->ir_loc_addr;
+		entry->daddr = &ireq->ir_rmt_addr;
 	}
 }
 
@@ -728,9 +728,9 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 		tmo = 0;
 
 	r->id.idiag_sport = inet->inet_sport;
-	r->id.idiag_dport = ireq->rmt_port;
-	r->id.idiag_src[0] = ireq->loc_addr;
-	r->id.idiag_dst[0] = ireq->rmt_addr;
+	r->id.idiag_dport = ireq->ir_rmt_port;
+	r->id.idiag_src[0] = ireq->ir_loc_addr;
+	r->id.idiag_dst[0] = ireq->ir_rmt_addr;
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
@@ -789,13 +789,13 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 
 			if (reqnum < s_reqnum)
 				continue;
-			if (r->id.idiag_dport != ireq->rmt_port &&
+			if (r->id.idiag_dport != ireq->ir_rmt_port &&
 			    r->id.idiag_dport)
 				continue;
 
 			if (bc) {
 				inet_diag_req_addrs(sk, req, &entry);
-				entry.dport = ntohs(ireq->rmt_port);
+				entry.dport = ntohs(ireq->ir_rmt_port);
 
 				if (!inet_diag_bc_run(bc, &entry))
 					continue;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 15e024105f91..984e21cf3c50 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -304,10 +304,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	req->mss		= mss;
-	ireq->loc_port		= th->dest;
-	ireq->rmt_port		= th->source;
-	ireq->loc_addr		= ip_hdr(skb)->daddr;
-	ireq->rmt_addr		= ip_hdr(skb)->saddr;
+	ireq->ir_loc_port		= th->dest;
+	ireq->ir_rmt_port		= th->source;
+	ireq->ir_loc_addr		= ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr		= ip_hdr(skb)->saddr;
 	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
@@ -347,8 +347,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
-			   (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
-			   ireq->loc_addr, th->source, th->dest);
+			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+			   ireq->ir_loc_addr, th->source, th->dest);
 	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e4695dde1af6..114d1b748cbb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -835,11 +835,11 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 	skb = tcp_make_synack(sk, dst, req, NULL);
 
 	if (skb) {
-		__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
+		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
 		skb_set_queue_mapping(skb, queue_mapping);
-		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
-					    ireq->rmt_addr,
+		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
+					    ireq->ir_rmt_addr,
 					    ireq->opt);
 		err = net_xmit_eval(err);
 		if (!tcp_rsk(req)->snt_synack && !err)
@@ -972,7 +972,7 @@ static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
 {
 	union tcp_md5_addr *addr;
 
-	addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr;
+	addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr;
 	return tcp_md5_do_lookup(sk, addr, AF_INET);
 }
 
@@ -1149,8 +1149,8 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 		saddr = inet_sk(sk)->inet_saddr;
 		daddr = inet_sk(sk)->inet_daddr;
 	} else if (req) {
-		saddr = inet_rsk(req)->loc_addr;
-		daddr = inet_rsk(req)->rmt_addr;
+		saddr = inet_rsk(req)->ir_loc_addr;
+		daddr = inet_rsk(req)->ir_rmt_addr;
 	} else {
 		const struct iphdr *iph = ip_hdr(skb);
 		saddr = iph->saddr;
@@ -1366,8 +1366,8 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
 		kfree_skb(skb_synack);
 		return -1;
 	}
-	err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
-				    ireq->rmt_addr, ireq->opt);
+	err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
+				    ireq->ir_rmt_addr, ireq->opt);
 	err = net_xmit_eval(err);
 	if (!err)
 		tcp_rsk(req)->snt_synack = tcp_time_stamp;
@@ -1502,8 +1502,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_openreq_init(req, &tmp_opt, skb);
 
 	ireq = inet_rsk(req);
-	ireq->loc_addr = daddr;
-	ireq->rmt_addr = saddr;
+	ireq->ir_loc_addr = daddr;
+	ireq->ir_rmt_addr = saddr;
 	ireq->no_srccheck = inet_sk(sk)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
 
@@ -1578,15 +1578,15 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
 
 	if (skb_synack) {
-		__tcp_v4_send_check(skb_synack, ireq->loc_addr, ireq->rmt_addr);
+		__tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 		skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));
 	} else
 		goto drop_and_free;
 
 	if (likely(!do_fastopen)) {
 		int err;
-		err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
-		     ireq->rmt_addr, ireq->opt);
+		err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
+		     ireq->ir_rmt_addr, ireq->opt);
 		err = net_xmit_eval(err);
 		if (err || want_cookie)
 			goto drop_and_free;
@@ -1644,9 +1644,9 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	newtp		      = tcp_sk(newsk);
 	newinet		      = inet_sk(newsk);
 	ireq		      = inet_rsk(req);
-	newinet->inet_daddr   = ireq->rmt_addr;
-	newinet->inet_rcv_saddr = ireq->loc_addr;
-	newinet->inet_saddr	      = ireq->loc_addr;
+	newinet->inet_daddr   = ireq->ir_rmt_addr;
+	newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+	newinet->inet_saddr	      = ireq->ir_loc_addr;
 	inet_opt	      = ireq->opt;
 	rcu_assign_pointer(newinet->inet_opt, inet_opt);
 	ireq->opt	      = NULL;
@@ -2548,10 +2548,10 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK%n",
 		i,
-		ireq->loc_addr,
+		ireq->ir_loc_addr,
 		ntohs(inet_sk(sk)->inet_sport),
-		ireq->rmt_addr,
-		ntohs(ireq->rmt_port),
+		ireq->ir_rmt_addr,
+		ntohs(ireq->ir_rmt_port),
 		TCP_SYN_RECV,
 		0, 0, /* could print option size, but that is af dependent. */
 		1,    /* timers active (only the expire timer) */
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 8fcc2cb9dba4..4a2a84110dfb 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -215,13 +215,15 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 	addr.family = req->rsk_ops->family;
 	switch (addr.family) {
 	case AF_INET:
-		addr.addr.a4 = inet_rsk(req)->rmt_addr;
+		addr.addr.a4 = inet_rsk(req)->ir_rmt_addr;
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = inet6_rsk(req)->rmt_addr;
-		hash = ipv6_addr_hash(&inet6_rsk(req)->rmt_addr);
+		*(struct in6_addr *)addr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr;
+		hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
 		break;
+#endif
 	default:
 		return NULL;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c6f01f2cdb32..faec81353522 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2734,8 +2734,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->syn = 1;
 	th->ack = 1;
 	TCP_ECN_make_synack(req, th);
-	th->source = ireq->loc_port;
-	th->dest = ireq->rmt_port;
+	th->source = ireq->ir_loc_port;
+	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
 	 * not even correctly set)
 	 */
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index b7400b480e74..1317c569b58f 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -70,20 +70,20 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 				      struct flowi6 *fl6,
 				      const struct request_sock *req)
 {
-	struct inet6_request_sock *treq = inet6_rsk(req);
+	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct in6_addr *final_p, final;
 	struct dst_entry *dst;
 
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_proto = IPPROTO_TCP;
-	fl6->daddr = treq->rmt_addr;
+	fl6->daddr = ireq->ir_v6_rmt_addr;
 	final_p = fl6_update_dst(fl6, np->opt, &final);
-	fl6->saddr = treq->loc_addr;
-	fl6->flowi6_oif = treq->iif;
+	fl6->saddr = ireq->ir_v6_loc_addr;
+	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = sk->sk_mark;
-	fl6->fl6_dport = inet_rsk(req)->rmt_port;
-	fl6->fl6_sport = inet_rsk(req)->loc_port;
+	fl6->fl6_dport = ireq->ir_rmt_port;
+	fl6->fl6_sport = ireq->ir_loc_port;
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
 	dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
@@ -129,13 +129,13 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk,
 						     lopt->nr_table_entries)];
 	     (req = *prev) != NULL;
 	     prev = &req->dl_next) {
-		const struct inet6_request_sock *treq = inet6_rsk(req);
+		const struct inet_request_sock *ireq = inet_rsk(req);
 
-		if (inet_rsk(req)->rmt_port == rport &&
+		if (ireq->ir_rmt_port == rport &&
 		    req->rsk_ops->family == AF_INET6 &&
-		    ipv6_addr_equal(&treq->rmt_addr, raddr) &&
-		    ipv6_addr_equal(&treq->loc_addr, laddr) &&
-		    (!treq->iif || treq->iif == iif)) {
+		    ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) &&
+		    ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) &&
+		    (!ireq->ir_iif || ireq->ir_iif == iif)) {
 			WARN_ON(req->sk != NULL);
 			*prevp = prev;
 			return req;
@@ -153,8 +153,8 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
-	const u32 h = inet6_synq_hash(&inet6_rsk(req)->rmt_addr,
-				      inet_rsk(req)->rmt_port,
+	const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr,
+				      inet_rsk(req)->ir_rmt_port,
 				      lopt->hash_rnd, lopt->nr_table_entries);
 
 	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index d703218a653b..bc5698f9e4cd 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -150,7 +150,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_options_received tcp_opt;
 	struct inet_request_sock *ireq;
-	struct inet6_request_sock *ireq6;
 	struct tcp_request_sock *treq;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -187,7 +186,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		goto out;
 
 	ireq = inet_rsk(req);
-	ireq6 = inet6_rsk(req);
 	treq = tcp_rsk(req);
 	treq->listener = NULL;
 
@@ -195,22 +193,22 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		goto out_free;
 
 	req->mss = mss;
-	ireq->rmt_port = th->source;
-	ireq->loc_port = th->dest;
-	ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
-	ireq6->loc_addr = ipv6_hdr(skb)->daddr;
+	ireq->ir_rmt_port = th->source;
+	ireq->ir_loc_port = th->dest;
+	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 	if (ipv6_opt_accepted(sk, skb) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 		atomic_inc(&skb->users);
-		ireq6->pktopts = skb;
+		ireq->pktopts = skb;
 	}
 
-	ireq6->iif = sk->sk_bound_dev_if;
+	ireq->ir_iif = sk->sk_bound_dev_if;
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
-	    ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		ireq6->iif = inet6_iif(skb);
+	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		ireq->ir_iif = inet6_iif(skb);
 
 	req->expires = 0UL;
 	req->num_retrans = 0;
@@ -234,12 +232,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		struct flowi6 fl6;
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
-		fl6.daddr = ireq6->rmt_addr;
+		fl6.daddr = ireq->ir_v6_rmt_addr;
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
-		fl6.saddr = ireq6->loc_addr;
+		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = sk->sk_mark;
-		fl6.fl6_dport = inet_rsk(req)->rmt_port;
+		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 541dfc40c7b3..db234d609b33 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -465,7 +465,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
 			      u16 queue_mapping)
 {
-	struct inet6_request_sock *treq = inet6_rsk(req);
+	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff * skb;
 	int err = -ENOMEM;
@@ -477,9 +477,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 	skb = tcp_make_synack(sk, dst, req, NULL);
 
 	if (skb) {
-		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
+		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
+				    &ireq->ir_v6_rmt_addr);
 
-		fl6->daddr = treq->rmt_addr;
+		fl6->daddr = ireq->ir_v6_rmt_addr;
 		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
 		err = net_xmit_eval(err);
@@ -502,7 +503,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
 {
-	kfree_skb(inet6_rsk(req)->pktopts);
+	kfree_skb(inet_rsk(req)->pktopts);
 }
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -521,7 +522,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk,
 static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
 						      struct request_sock *req)
 {
-	return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr);
+	return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr);
 }
 
 static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
@@ -623,8 +624,8 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key,
 		saddr = &inet6_sk(sk)->saddr;
 		daddr = &sk->sk_v6_daddr;
 	} else if (req) {
-		saddr = &inet6_rsk(req)->loc_addr;
-		daddr = &inet6_rsk(req)->rmt_addr;
+		saddr = &inet_rsk(req)->ir_v6_loc_addr;
+		daddr = &inet_rsk(req)->ir_v6_rmt_addr;
 	} else {
 		const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 		saddr = &ip6h->saddr;
@@ -949,7 +950,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_options_received tmp_opt;
 	struct request_sock *req;
-	struct inet6_request_sock *treq;
+	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 isn = TCP_SKB_CB(skb)->when;
@@ -994,25 +995,25 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 	tcp_openreq_init(req, &tmp_opt, skb);
 
-	treq = inet6_rsk(req);
-	treq->rmt_addr = ipv6_hdr(skb)->saddr;
-	treq->loc_addr = ipv6_hdr(skb)->daddr;
+	ireq = inet_rsk(req);
+	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 	if (!want_cookie || tmp_opt.tstamp_ok)
 		TCP_ECN_create_request(req, skb, sock_net(sk));
 
-	treq->iif = sk->sk_bound_dev_if;
+	ireq->ir_iif = sk->sk_bound_dev_if;
 
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
-	    ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
-		treq->iif = inet6_iif(skb);
+	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		ireq->ir_iif = inet6_iif(skb);
 
 	if (!isn) {
 		if (ipv6_opt_accepted(sk, skb) ||
 		    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 		    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
 			atomic_inc(&skb->users);
-			treq->pktopts = skb;
+			ireq->pktopts = skb;
 		}
 
 		if (want_cookie) {
@@ -1051,7 +1052,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 			 * to the moment of synflood.
 			 */
 			LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n",
-				       &treq->rmt_addr, ntohs(tcp_hdr(skb)->source));
+				       &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source));
 			goto drop_and_release;
 		}
 
@@ -1086,7 +1087,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 					  struct request_sock *req,
 					  struct dst_entry *dst)
 {
-	struct inet6_request_sock *treq;
+	struct inet_request_sock *ireq;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct tcp6_sock *newtcp6sk;
 	struct inet_sock *newinet;
@@ -1151,7 +1152,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		return newsk;
 	}
 
-	treq = inet6_rsk(req);
+	ireq = inet_rsk(req);
 
 	if (sk_acceptq_is_full(sk))
 		goto out_overflow;
@@ -1185,10 +1186,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newsk->sk_v6_daddr = treq->rmt_addr;
-	newnp->saddr = treq->loc_addr;
-	newsk->sk_v6_rcv_saddr = treq->loc_addr;
-	newsk->sk_bound_dev_if = treq->iif;
+	newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+	newnp->saddr = ireq->ir_v6_loc_addr;
+	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+	newsk->sk_bound_dev_if = ireq->ir_iif;
 
 	/* Now IPv6 options...
 
@@ -1203,11 +1204,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	/* Clone pktoptions received with SYN */
 	newnp->pktoptions = NULL;
-	if (treq->pktopts != NULL) {
-		newnp->pktoptions = skb_clone(treq->pktopts,
+	if (ireq->pktopts != NULL) {
+		newnp->pktoptions = skb_clone(ireq->pktopts,
 					      sk_gfp_atomic(sk, GFP_ATOMIC));
-		consume_skb(treq->pktopts);
-		treq->pktopts = NULL;
+		consume_skb(ireq->pktopts);
+		ireq->pktopts = NULL;
 		if (newnp->pktoptions)
 			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
@@ -1722,8 +1723,8 @@ static void get_openreq6(struct seq_file *seq,
 			 const struct sock *sk, struct request_sock *req, int i, kuid_t uid)
 {
 	int ttd = req->expires - jiffies;
-	const struct in6_addr *src = &inet6_rsk(req)->loc_addr;
-	const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
+	const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
+	const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr;
 
 	if (ttd < 0)
 		ttd = 0;
@@ -1734,10 +1735,10 @@ static void get_openreq6(struct seq_file *seq,
 		   i,
 		   src->s6_addr32[0], src->s6_addr32[1],
 		   src->s6_addr32[2], src->s6_addr32[3],
-		   ntohs(inet_rsk(req)->loc_port),
+		   ntohs(inet_rsk(req)->ir_loc_port),
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3],
-		   ntohs(inet_rsk(req)->rmt_port),
+		   ntohs(inet_rsk(req)->ir_rmt_port),
 		   TCP_SYN_RECV,
 		   0,0, /* could print option size, but that is af dependent. */
 		   1,   /* timers active (only the expire timer) */
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 96a458e12f60..dce1bebf7aec 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -817,7 +817,7 @@ int netlbl_req_setattr(struct request_sock *req,
 	switch (req->rsk_ops->family) {
 	case AF_INET:
 		entry = netlbl_domhsh_getentry_af4(secattr->domain,
-						   inet_rsk(req)->rmt_addr);
+						   inet_rsk(req)->ir_rmt_addr);
 		if (entry == NULL) {
 			ret_val = -ENOENT;
 			goto req_setattr_return;
-- 
cgit 


From 1b65c4e5a9af1a1c61e792e2d0ed481e0c1f21a9 Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Thu, 10 Oct 2013 13:41:10 +0000
Subject: swiotlb-xen: use xen_alloc/free_coherent_pages

Use xen_alloc_coherent_pages and xen_free_coherent_pages to allocate or
free coherent pages.

We need to be careful handling the pointer returned by
xen_alloc_coherent_pages, because on ARM the pointer is not equal to
phys_to_virt(*dma_handle). In fact virt_to_phys only works for kernel
direct mapped RAM memory.
In ARM case the pointer could be an ioremap address, therefore passing
it to virt_to_phys would give you another physical address that doesn't
correspond to it.

Make xen_create_contiguous_region take a phys_addr_t as start parameter to
avoid the virt_to_phys calls which would be incorrect.

Changes in v6:
- remove extra spaces.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/arm/xen/mm.c         |  6 +++---
 arch/x86/xen/mmu.c        |  7 +++++--
 drivers/xen/swiotlb-xen.c | 31 +++++++++++++++++++++----------
 include/xen/xen-ops.h     |  4 ++--
 4 files changed, 31 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 0d69b874d249..b0e77de99148 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -16,7 +16,7 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
-int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
 {
@@ -24,12 +24,12 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 		return -EINVAL;
 
 	/* we assume that dom0 is mapped 1:1 for now */
-	*dma_handle = virt_to_phys(pstart);
+	*dma_handle = pstart;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
-void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
 	return;
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6c34d7c03d5b..883088368ff0 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2328,13 +2328,14 @@ static int xen_exchange_memory(unsigned long extents_in, unsigned int order_in,
 	return success;
 }
 
-int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				 unsigned int address_bits,
 				 dma_addr_t *dma_handle)
 {
 	unsigned long *in_frames = discontig_frames, out_frame;
 	unsigned long  flags;
 	int            success;
+	unsigned long vstart = (unsigned long)phys_to_virt(pstart);
 
 	/*
 	 * Currently an auto-translated guest will not perform I/O, nor will
@@ -2374,11 +2375,12 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 }
 EXPORT_SYMBOL_GPL(xen_create_contiguous_region);
 
-void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 {
 	unsigned long *out_frames = discontig_frames, in_frame;
 	unsigned long  flags;
 	int success;
+	unsigned long vstart;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return;
@@ -2386,6 +2388,7 @@ void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order)
 	if (unlikely(order > MAX_CONTIG_ORDER))
 		return;
 
+	vstart = (unsigned long)phys_to_virt(pstart);
 	memset((void *) vstart, 0, PAGE_SIZE << order);
 
 	spin_lock_irqsave(&xen_reservation_lock, flags);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index d8ef0bf577d2..189b8db5c983 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -43,6 +43,7 @@
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
 #include <asm/dma-mapping.h>
+#include <asm/xen/page-coherent.h>
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
@@ -142,6 +143,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 	int i, rc;
 	int dma_bits;
 	dma_addr_t dma_handle;
+	phys_addr_t p = virt_to_phys(buf);
 
 	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
 
@@ -151,7 +153,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 
 		do {
 			rc = xen_create_contiguous_region(
-				(unsigned long)buf + (i << IO_TLB_SHIFT),
+				p + (i << IO_TLB_SHIFT),
 				get_order(slabs << IO_TLB_SHIFT),
 				dma_bits, &dma_handle);
 		} while (rc && dma_bits++ < max_dma_bits);
@@ -279,7 +281,6 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	void *ret;
 	int order = get_order(size);
 	u64 dma_mask = DMA_BIT_MASK(32);
-	unsigned long vstart;
 	phys_addr_t phys;
 	dma_addr_t dev_addr;
 
@@ -294,8 +295,12 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
 		return ret;
 
-	vstart = __get_free_pages(flags, order);
-	ret = (void *)vstart;
+	/* On ARM this function returns an ioremap'ped virtual address for
+	 * which virt_to_phys doesn't return the corresponding physical
+	 * address. In fact on ARM virt_to_phys only works for kernel direct
+	 * mapped RAM memory. Also see comment below.
+	 */
+	ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
 
 	if (!ret)
 		return ret;
@@ -303,15 +308,19 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (hwdev && hwdev->coherent_dma_mask)
 		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
 
-	phys = virt_to_phys(ret);
+	/* At this point dma_handle is the physical address, next we are
+	 * going to set it to the machine address.
+	 * Do not use virt_to_phys(ret) because on ARM it doesn't correspond
+	 * to *dma_handle. */
+	phys = *dma_handle;
 	dev_addr = xen_phys_to_bus(phys);
 	if (((dev_addr + size - 1 <= dma_mask)) &&
 	    !range_straddles_page_boundary(phys, size))
 		*dma_handle = dev_addr;
 	else {
-		if (xen_create_contiguous_region(vstart, order,
+		if (xen_create_contiguous_region(phys, order,
 						 fls64(dma_mask), dma_handle) != 0) {
-			free_pages(vstart, order);
+			xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
 			return NULL;
 		}
 	}
@@ -334,13 +343,15 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	if (hwdev && hwdev->coherent_dma_mask)
 		dma_mask = hwdev->coherent_dma_mask;
 
-	phys = virt_to_phys(vaddr);
+	/* do not use virt_to_phys because on ARM it doesn't return you the
+	 * physical address */
+	phys = xen_bus_to_phys(dev_addr);
 
 	if (((dev_addr + size - 1 > dma_mask)) ||
 	    range_straddles_page_boundary(phys, size))
-		xen_destroy_contiguous_region((unsigned long)vaddr, order);
+		xen_destroy_contiguous_region(phys, order);
 
-	free_pages((unsigned long)vaddr, order);
+	xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 9ef704d3a9dd..fb2ea8f26552 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -19,11 +19,11 @@ void xen_arch_resume(void);
 int xen_setup_shutdown_event(void);
 
 extern unsigned long *xen_contiguous_bitmap;
-int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
+int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				unsigned int address_bits,
 				dma_addr_t *dma_handle);
 
-void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
+void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
 
 struct vm_area_struct;
 int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
-- 
cgit 


From 5578b266e9ae05391d53b446acf23818256ff13f Mon Sep 17 00:00:00 2001
From: Valentine Barshak <valentine.barshak@cogentembedded.com>
Date: Thu, 10 Oct 2013 20:35:17 +0400
Subject: usb: phy: Add RCAR Gen2 USB phy

This adds RCAR Gen2 USB phy support. The driver configures
USB channels 0/2 which are shared between PCI USB hosts and
USBHS/USBSS devices. It also controls internal USBHS phy.

Signed-off-by: Valentine Barshak <valentine.barshak@cogentembedded.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/phy/Kconfig                         |  13 ++
 drivers/usb/phy/Makefile                        |   1 +
 drivers/usb/phy/phy-rcar-gen2-usb.c             | 248 ++++++++++++++++++++++++
 include/linux/platform_data/usb-rcar-gen2-phy.h |  22 +++
 4 files changed, 284 insertions(+)
 create mode 100644 drivers/usb/phy/phy-rcar-gen2-usb.c
 create mode 100644 include/linux/platform_data/usb-rcar-gen2-phy.h

(limited to 'include')

diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index d5589f9c60a9..c0c8cd37648e 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -214,6 +214,19 @@ config USB_RCAR_PHY
 	  To compile this driver as a module, choose M here: the
 	  module will be called phy-rcar-usb.
 
+config USB_RCAR_GEN2_PHY
+	tristate "Renesas R-Car Gen2 USB PHY support"
+	depends on ARCH_R8A7790 || ARCH_R8A7791 || COMPILE_TEST
+	select USB_PHY
+	help
+	  Say Y here to add support for the Renesas R-Car Gen2 USB PHY driver.
+	  It is typically used to control internal USB PHY for USBHS,
+	  and to configure shared USB channels 0 and 2.
+	  This driver supports R8A7790 and R8A7791.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called phy-rcar-gen2-usb.
+
 config USB_ULPI
 	bool "Generic ULPI Transceiver Driver"
 	depends on ARM
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index 2135e85f46ed..8c5b14764b72 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -29,5 +29,6 @@ obj-$(CONFIG_USB_MSM_OTG)		+= phy-msm-usb.o
 obj-$(CONFIG_USB_MV_OTG)		+= phy-mv-usb.o
 obj-$(CONFIG_USB_MXS_PHY)		+= phy-mxs-usb.o
 obj-$(CONFIG_USB_RCAR_PHY)		+= phy-rcar-usb.o
+obj-$(CONFIG_USB_RCAR_GEN2_PHY)		+= phy-rcar-gen2-usb.o
 obj-$(CONFIG_USB_ULPI)			+= phy-ulpi.o
 obj-$(CONFIG_USB_ULPI_VIEWPORT)		+= phy-ulpi-viewport.o
diff --git a/drivers/usb/phy/phy-rcar-gen2-usb.c b/drivers/usb/phy/phy-rcar-gen2-usb.c
new file mode 100644
index 000000000000..a99a6953f11c
--- /dev/null
+++ b/drivers/usb/phy/phy-rcar-gen2-usb.c
@@ -0,0 +1,248 @@
+/*
+ * Renesas R-Car Gen2 USB phy driver
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_data/usb-rcar-gen2-phy.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/usb/otg.h>
+
+struct rcar_gen2_usb_phy_priv {
+	struct usb_phy phy;
+	void __iomem *base;
+	struct clk *clk;
+	spinlock_t lock;
+	int usecount;
+	u32 ugctrl2;
+};
+
+#define usb_phy_to_priv(p) container_of(p, struct rcar_gen2_usb_phy_priv, phy)
+
+/* Low Power Status register */
+#define USBHS_LPSTS_REG			0x02
+#define USBHS_LPSTS_SUSPM		(1 << 14)
+
+/* USB General control register */
+#define USBHS_UGCTRL_REG		0x80
+#define USBHS_UGCTRL_CONNECT		(1 << 2)
+#define USBHS_UGCTRL_PLLRESET		(1 << 0)
+
+/* USB General control register 2 */
+#define USBHS_UGCTRL2_REG		0x84
+#define USBHS_UGCTRL2_USB0_PCI		(1 << 4)
+#define USBHS_UGCTRL2_USB0_HS		(3 << 4)
+#define USBHS_UGCTRL2_USB2_PCI		(0 << 31)
+#define USBHS_UGCTRL2_USB2_SS		(1 << 31)
+
+/* USB General status register */
+#define USBHS_UGSTS_REG			0x88
+#define USBHS_UGSTS_LOCK		(3 << 8)
+
+/* Enable USBHS internal phy */
+static int __rcar_gen2_usbhs_phy_enable(void __iomem *base)
+{
+	u32 val;
+	int i;
+
+	/* USBHS PHY power on */
+	val = ioread32(base + USBHS_UGCTRL_REG);
+	val &= ~USBHS_UGCTRL_PLLRESET;
+	iowrite32(val, base + USBHS_UGCTRL_REG);
+
+	val = ioread16(base + USBHS_LPSTS_REG);
+	val |= USBHS_LPSTS_SUSPM;
+	iowrite16(val, base + USBHS_LPSTS_REG);
+
+	for (i = 0; i < 20; i++) {
+		val = ioread32(base + USBHS_UGSTS_REG);
+		if ((val & USBHS_UGSTS_LOCK) == USBHS_UGSTS_LOCK) {
+			val = ioread32(base + USBHS_UGCTRL_REG);
+			val |= USBHS_UGCTRL_CONNECT;
+			iowrite32(val, base + USBHS_UGCTRL_REG);
+			return 0;
+		}
+		udelay(1);
+	}
+
+	/* Timed out waiting for the PLL lock */
+	return -ETIMEDOUT;
+}
+
+/* Disable USBHS internal phy */
+static int __rcar_gen2_usbhs_phy_disable(void __iomem *base)
+{
+	u32 val;
+
+	/* USBHS PHY power off */
+	val = ioread32(base + USBHS_UGCTRL_REG);
+	val &= ~USBHS_UGCTRL_CONNECT;
+	iowrite32(val, base + USBHS_UGCTRL_REG);
+
+	val = ioread16(base + USBHS_LPSTS_REG);
+	val &= ~USBHS_LPSTS_SUSPM;
+	iowrite16(val, base + USBHS_LPSTS_REG);
+
+	val = ioread32(base + USBHS_UGCTRL_REG);
+	val |= USBHS_UGCTRL_PLLRESET;
+	iowrite32(val, base + USBHS_UGCTRL_REG);
+	return 0;
+}
+
+/* Setup USB channels */
+static void __rcar_gen2_usb_phy_init(struct rcar_gen2_usb_phy_priv *priv)
+{
+	u32 val;
+
+	clk_prepare_enable(priv->clk);
+
+	/* Set USB channels in the USBHS UGCTRL2 register */
+	val = ioread32(priv->base);
+	val &= ~(USBHS_UGCTRL2_USB0_HS | USBHS_UGCTRL2_USB2_SS);
+	val |= priv->ugctrl2;
+	iowrite32(val, priv->base);
+}
+
+/* Shutdown USB channels */
+static void __rcar_gen2_usb_phy_shutdown(struct rcar_gen2_usb_phy_priv *priv)
+{
+	__rcar_gen2_usbhs_phy_disable(priv->base);
+	clk_disable_unprepare(priv->clk);
+}
+
+static int rcar_gen2_usb_phy_set_suspend(struct usb_phy *phy, int suspend)
+{
+	struct rcar_gen2_usb_phy_priv *priv = usb_phy_to_priv(phy);
+	unsigned long flags;
+	int retval;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	retval = suspend ? __rcar_gen2_usbhs_phy_disable(priv->base) :
+			   __rcar_gen2_usbhs_phy_enable(priv->base);
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return retval;
+}
+
+static int rcar_gen2_usb_phy_init(struct usb_phy *phy)
+{
+	struct rcar_gen2_usb_phy_priv *priv = usb_phy_to_priv(phy);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	/*
+	 * Enable the clock and setup USB channels
+	 * if it's the first user
+	 */
+	if (!priv->usecount++)
+		__rcar_gen2_usb_phy_init(priv);
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return 0;
+}
+
+static void rcar_gen2_usb_phy_shutdown(struct usb_phy *phy)
+{
+	struct rcar_gen2_usb_phy_priv *priv = usb_phy_to_priv(phy);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (!priv->usecount) {
+		dev_warn(phy->dev, "Trying to disable phy with 0 usecount\n");
+		goto out;
+	}
+
+	/* Disable everything if it's the last user */
+	if (!--priv->usecount)
+		__rcar_gen2_usb_phy_shutdown(priv);
+out:
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int rcar_gen2_usb_phy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rcar_gen2_phy_platform_data *pdata;
+	struct rcar_gen2_usb_phy_priv *priv;
+	struct resource *res;
+	void __iomem *base;
+	struct clk *clk;
+	int retval;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	clk = devm_clk_get(&pdev->dev, "usbhs");
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "Can't get the clock\n");
+		return PTR_ERR(clk);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		dev_err(dev, "Memory allocation failed\n");
+		return -ENOMEM;
+	}
+
+	spin_lock_init(&priv->lock);
+	priv->clk = clk;
+	priv->base = base;
+	priv->ugctrl2 = pdata->chan0_pci ?
+			USBHS_UGCTRL2_USB0_PCI : USBHS_UGCTRL2_USB0_HS;
+	priv->ugctrl2 |= pdata->chan2_pci ?
+			USBHS_UGCTRL2_USB2_PCI : USBHS_UGCTRL2_USB2_SS;
+	priv->phy.dev = dev;
+	priv->phy.label = dev_name(dev);
+	priv->phy.init = rcar_gen2_usb_phy_init;
+	priv->phy.shutdown = rcar_gen2_usb_phy_shutdown;
+	priv->phy.set_suspend = rcar_gen2_usb_phy_set_suspend;
+
+	retval = usb_add_phy(&priv->phy, USB_PHY_TYPE_USB2);
+	if (retval < 0) {
+		dev_err(dev, "Failed to add USB phy\n");
+		return retval;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return retval;
+}
+
+static int rcar_gen2_usb_phy_remove(struct platform_device *pdev)
+{
+	struct rcar_gen2_usb_phy_priv *priv = platform_get_drvdata(pdev);
+
+	usb_remove_phy(&priv->phy);
+
+	return 0;
+}
+
+static struct platform_driver rcar_gen2_usb_phy_driver = {
+	.driver = {
+		.name = "usb_phy_rcar_gen2",
+	},
+	.probe = rcar_gen2_usb_phy_probe,
+	.remove = rcar_gen2_usb_phy_remove,
+};
+
+module_platform_driver(rcar_gen2_usb_phy_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Renesas R-Car Gen2 USB phy");
+MODULE_AUTHOR("Valentine Barshak <valentine.barshak@cogentembedded.com>");
diff --git a/include/linux/platform_data/usb-rcar-gen2-phy.h b/include/linux/platform_data/usb-rcar-gen2-phy.h
new file mode 100644
index 000000000000..dd3ba46c0d90
--- /dev/null
+++ b/include/linux/platform_data/usb-rcar-gen2-phy.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ * Copyright (C) 2013 Cogent Embedded, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __USB_RCAR_GEN2_PHY_H
+#define __USB_RCAR_GEN2_PHY_H
+
+#include <linux/types.h>
+
+struct rcar_gen2_phy_platform_data {
+	/* USB channel 0 configuration */
+	bool chan0_pci:1;	/* true: PCI USB host 0, false: USBHS */
+	/* USB channel 2 configuration */
+	bool chan2_pci:1;	/* true: PCI USB host 2, false: USBSS */
+};
+
+#endif
-- 
cgit 


From 5910895f0e868d4f70303922ed00ccdc328b3c30 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 12 Sep 2013 14:10:25 -0400
Subject: random: fix the tracepoint for get_random_bytes(_arch)

Fix a problem where get_random_bytes_arch() was calling the tracepoint
get_random_bytes().  So add a new tracepoint for
get_random_bytes_arch(), and make get_random_bytes() and
get_random_bytes_arch() call their correct tracepoint.

Also, add a new tracepoint for add_device_randomness()

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 drivers/char/random.c         |  4 +++-
 include/trace/events/random.h | 33 ++++++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 867b823e7fea..80b58774e891 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -711,6 +711,7 @@ void add_device_randomness(const void *buf, unsigned int size)
 {
 	unsigned long time = random_get_entropy() ^ jiffies;
 
+	trace_add_device_randomness(size, _RET_IP_);
 	mix_pool_bytes(&input_pool, buf, size, NULL);
 	mix_pool_bytes(&input_pool, &time, sizeof(time), NULL);
 	mix_pool_bytes(&nonblocking_pool, buf, size, NULL);
@@ -1127,6 +1128,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
  */
 void get_random_bytes(void *buf, int nbytes)
 {
+	trace_get_random_bytes(nbytes, _RET_IP_);
 	extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
 }
 EXPORT_SYMBOL(get_random_bytes);
@@ -1145,7 +1147,7 @@ void get_random_bytes_arch(void *buf, int nbytes)
 {
 	char *p = buf;
 
-	trace_get_random_bytes(nbytes, _RET_IP_);
+	trace_get_random_bytes_arch(nbytes, _RET_IP_);
 	while (nbytes) {
 		unsigned long v;
 		int chunk = min(nbytes, (int)sizeof(unsigned long));
diff --git a/include/trace/events/random.h b/include/trace/events/random.h
index 422df19de732..2ffcaec5860a 100644
--- a/include/trace/events/random.h
+++ b/include/trace/events/random.h
@@ -7,6 +7,25 @@
 #include <linux/writeback.h>
 #include <linux/tracepoint.h>
 
+TRACE_EVENT(add_device_randomness,
+	TP_PROTO(int bytes, unsigned long IP),
+
+	TP_ARGS(bytes, IP),
+
+	TP_STRUCT__entry(
+		__field(	  int,	bytes			)
+		__field(unsigned long,	IP			)
+	),
+
+	TP_fast_assign(
+		__entry->bytes		= bytes;
+		__entry->IP		= IP;
+	),
+
+	TP_printk("bytes %d caller %pF",
+		__entry->bytes, (void *)__entry->IP)
+);
+
 DECLARE_EVENT_CLASS(random__mix_pool_bytes,
 	TP_PROTO(const char *pool_name, int bytes, unsigned long IP),
 
@@ -68,7 +87,7 @@ TRACE_EVENT(credit_entropy_bits,
 		  (void *)__entry->IP)
 );
 
-TRACE_EVENT(get_random_bytes,
+DECLARE_EVENT_CLASS(random__get_random_bytes,
 	TP_PROTO(int nbytes, unsigned long IP),
 
 	TP_ARGS(nbytes, IP),
@@ -86,6 +105,18 @@ TRACE_EVENT(get_random_bytes,
 	TP_printk("nbytes %d caller %pF", __entry->nbytes, (void *)__entry->IP)
 );
 
+DEFINE_EVENT(random__get_random_bytes, get_random_bytes,
+	TP_PROTO(int nbytes, unsigned long IP),
+
+	TP_ARGS(nbytes, IP)
+);
+
+DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch,
+	TP_PROTO(int nbytes, unsigned long IP),
+
+	TP_ARGS(nbytes, IP)
+);
+
 DECLARE_EVENT_CLASS(random__extract_entropy,
 	TP_PROTO(const char *pool_name, int nbytes, int entropy_count,
 		 unsigned long IP),
-- 
cgit 


From 6265e169cd313d6f3aad3c33d0a5b0d9624f69f5 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 3 Oct 2013 01:08:15 -0400
Subject: random: push extra entropy to the output pools

As the input pool gets filled, start transfering entropy to the output
pools until they get filled.  This allows us to use the output pools
to store more system entropy.  Waste not, want not....

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 drivers/char/random.c         | 118 ++++++++++++++++++++++++++++++------------
 include/trace/events/random.h |  22 ++++++++
 2 files changed, 108 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 6da3f250804c..84c576ec20e9 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -255,6 +255,7 @@
 #include <linux/fips.h>
 #include <linux/ptrace.h>
 #include <linux/kmemcheck.h>
+#include <linux/workqueue.h>
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 # include <linux/irq.h>
@@ -302,7 +303,7 @@ static int random_read_wakeup_thresh = 64;
  * should wake up processes which are selecting or polling on write
  * access to /dev/random.
  */
-static int random_write_wakeup_thresh = 128;
+static int random_write_wakeup_thresh = 28 * OUTPUT_POOL_WORDS;
 
 /*
  * The minimum number of seconds between urandom pool resending.  We
@@ -428,6 +429,7 @@ struct entropy_store {
 	__u32 *pool;
 	const char *name;
 	struct entropy_store *pull;
+	struct work_struct push_work;
 
 	/* read-write data: */
 	unsigned long last_pulled;
@@ -442,6 +444,7 @@ struct entropy_store {
 	__u8 last_data[EXTRACT_SIZE];
 };
 
+static void push_to_pool(struct work_struct *work);
 static __u32 input_pool_data[INPUT_POOL_WORDS];
 static __u32 blocking_pool_data[OUTPUT_POOL_WORDS];
 static __u32 nonblocking_pool_data[OUTPUT_POOL_WORDS];
@@ -460,7 +463,9 @@ static struct entropy_store blocking_pool = {
 	.limit = 1,
 	.pull = &input_pool,
 	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
-	.pool = blocking_pool_data
+	.pool = blocking_pool_data,
+	.push_work = __WORK_INITIALIZER(blocking_pool.push_work,
+					push_to_pool),
 };
 
 static struct entropy_store nonblocking_pool = {
@@ -468,7 +473,9 @@ static struct entropy_store nonblocking_pool = {
 	.name = "nonblocking",
 	.pull = &input_pool,
 	.lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock),
-	.pool = nonblocking_pool_data
+	.pool = nonblocking_pool_data,
+	.push_work = __WORK_INITIALIZER(nonblocking_pool.push_work,
+					push_to_pool),
 };
 
 static __u32 const twist_table[8] = {
@@ -655,21 +662,48 @@ retry:
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
 
+	r->entropy_total += nbits;
 	if (!r->initialized && nbits > 0) {
-		r->entropy_total += nbits;
-		if (r->entropy_total > 128)
+		if (r->entropy_total > 128) {
 			r->initialized = 1;
+			r->entropy_total = 0;
+		}
 	}
 
 	trace_credit_entropy_bits(r->name, nbits,
 				  entropy_count >> ENTROPY_SHIFT,
 				  r->entropy_total, _RET_IP_);
 
-	/* should we wake readers? */
-	if (r == &input_pool &&
-	    (entropy_count >> ENTROPY_SHIFT) >= random_read_wakeup_thresh) {
-		wake_up_interruptible(&random_read_wait);
-		kill_fasync(&fasync, SIGIO, POLL_IN);
+	if (r == &input_pool) {
+		int entropy_bytes = entropy_count >> ENTROPY_SHIFT;
+
+		/* should we wake readers? */
+		if (entropy_bytes >= random_read_wakeup_thresh) {
+			wake_up_interruptible(&random_read_wait);
+			kill_fasync(&fasync, SIGIO, POLL_IN);
+		}
+		/* If the input pool is getting full, send some
+		 * entropy to the two output pools, flipping back and
+		 * forth between them, until the output pools are 75%
+		 * full.
+		 */
+		if (entropy_bytes > random_write_wakeup_thresh &&
+		    r->initialized &&
+		    r->entropy_total >= 2*random_read_wakeup_thresh) {
+			static struct entropy_store *last = &blocking_pool;
+			struct entropy_store *other = &blocking_pool;
+
+			if (last == &blocking_pool)
+				other = &nonblocking_pool;
+			if (other->entropy_count <=
+			    3 * other->poolinfo->poolfracbits / 4)
+				last = other;
+			if (last->entropy_count <=
+			    3 * last->poolinfo->poolfracbits / 4) {
+				schedule_work(&last->push_work);
+				r->entropy_total = 0;
+			}
+		}
 	}
 }
 
@@ -877,10 +911,9 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
  * from the primary pool to the secondary extraction pool. We make
  * sure we pull enough for a 'catastrophic reseed'.
  */
+static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes);
 static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 {
-	__u32	tmp[OUTPUT_POOL_WORDS];
-
 	if (r->limit == 0 && random_min_urandom_seed) {
 		unsigned long now = jiffies;
 
@@ -891,26 +924,47 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	}
 	if (r->pull &&
 	    r->entropy_count < (nbytes << (ENTROPY_SHIFT + 3)) &&
-	    r->entropy_count < r->poolinfo->poolfracbits) {
-		/* If we're limited, always leave two wakeup worth's BITS */
-		int rsvd = r->limit ? 0 : random_read_wakeup_thresh/4;
-		int bytes = nbytes;
-
-		/* pull at least as many as BYTES as wakeup BITS */
-		bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
-		/* but never more than the buffer size */
-		bytes = min_t(int, bytes, sizeof(tmp));
-
-		DEBUG_ENT("going to reseed %s with %d bits "
-			  "(%zu of %d requested)\n",
-			  r->name, bytes * 8, nbytes * 8,
-			  r->entropy_count >> ENTROPY_SHIFT);
-
-		bytes = extract_entropy(r->pull, tmp, bytes,
-					random_read_wakeup_thresh / 8, rsvd);
-		mix_pool_bytes(r, tmp, bytes, NULL);
-		credit_entropy_bits(r, bytes*8);
-	}
+	    r->entropy_count < r->poolinfo->poolfracbits)
+		_xfer_secondary_pool(r, nbytes);
+}
+
+static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
+{
+	__u32	tmp[OUTPUT_POOL_WORDS];
+
+	/* For /dev/random's pool, always leave two wakeup worth's BITS */
+	int rsvd = r->limit ? 0 : random_read_wakeup_thresh/4;
+	int bytes = nbytes;
+
+	/* pull at least as many as BYTES as wakeup BITS */
+	bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
+	/* but never more than the buffer size */
+	bytes = min_t(int, bytes, sizeof(tmp));
+
+	DEBUG_ENT("going to reseed %s with %d bits (%zu of %d requested)\n",
+		  r->name, bytes * 8, nbytes * 8,
+		  r->entropy_count >> ENTROPY_SHIFT);
+
+	bytes = extract_entropy(r->pull, tmp, bytes,
+				random_read_wakeup_thresh / 8, rsvd);
+	mix_pool_bytes(r, tmp, bytes, NULL);
+	credit_entropy_bits(r, bytes*8);
+}
+
+/*
+ * Used as a workqueue function so that when the input pool is getting
+ * full, we can "spill over" some entropy to the output pools.  That
+ * way the output pools can store some of the excess entropy instead
+ * of letting it go to waste.
+ */
+static void push_to_pool(struct work_struct *work)
+{
+	struct entropy_store *r = container_of(work, struct entropy_store,
+					      push_work);
+	BUG_ON(!r);
+	_xfer_secondary_pool(r, random_read_wakeup_thresh/8);
+	trace_push_to_pool(r->name, r->entropy_count >> ENTROPY_SHIFT,
+			   r->pull->entropy_count >> ENTROPY_SHIFT);
 }
 
 /*
diff --git a/include/trace/events/random.h b/include/trace/events/random.h
index 2ffcaec5860a..527b5dc1b416 100644
--- a/include/trace/events/random.h
+++ b/include/trace/events/random.h
@@ -87,6 +87,28 @@ TRACE_EVENT(credit_entropy_bits,
 		  (void *)__entry->IP)
 );
 
+TRACE_EVENT(push_to_pool,
+	TP_PROTO(const char *pool_name, int pool_bits, int input_bits),
+
+	TP_ARGS(pool_name, pool_bits, input_bits),
+
+	TP_STRUCT__entry(
+		__field( const char *,	pool_name		)
+		__field(	  int,	pool_bits		)
+		__field(	  int,	input_bits		)
+	),
+
+	TP_fast_assign(
+		__entry->pool_name	= pool_name;
+		__entry->pool_bits	= pool_bits;
+		__entry->input_bits	= input_bits;
+	),
+
+	TP_printk("%s: pool_bits %d input_pool_bits %d",
+		  __entry->pool_name, __entry->pool_bits,
+		  __entry->input_bits)
+);
+
 DECLARE_EVENT_CLASS(random__get_random_bytes,
 	TP_PROTO(int nbytes, unsigned long IP),
 
-- 
cgit 


From f80bbd8b92987f55f26691cd53785c4a54622eb0 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 3 Oct 2013 12:02:37 -0400
Subject: random: convert DEBUG_ENT to tracepoints

Instead of using the random driver's ad-hoc DEBUG_ENT() mechanism, use
tracepoints instead.  This allows for a much more fine-grained control
of which debugging mechanism which a developer might need, and unifies
the debugging messages with all of the existing tracepoints.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 drivers/char/random.c         |  52 ++++++-----------
 include/trace/events/random.h | 128 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 144 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 84c576ec20e9..f126bd2f69fe 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -404,17 +404,6 @@ static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
 static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static struct fasync_struct *fasync;
 
-static bool debug;
-module_param(debug, bool, 0644);
-#define DEBUG_ENT(fmt, arg...) do { \
-	if (debug) \
-		printk(KERN_DEBUG "random %04d %04d %04d: " \
-		fmt,\
-		input_pool.entropy_count,\
-		blocking_pool.entropy_count,\
-		nonblocking_pool.entropy_count,\
-		## arg); } while (0)
-
 /**********************************************************************
  *
  * OS independent entropy store.   Here are the functions which handle
@@ -612,7 +601,6 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
 	if (!nbits)
 		return;
 
-	DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
 	if (nfrac < 0) {
@@ -655,7 +643,9 @@ retry:
 	}
 
 	if (entropy_count < 0) {
-		DEBUG_ENT("negative entropy/overflow\n");
+		pr_warn("random: negative entropy/overflow: pool %s count %d\n",
+			r->name, entropy_count);
+		WARN_ON(1);
 		entropy_count = 0;
 	} else if (entropy_count > pool_size)
 		entropy_count = pool_size;
@@ -832,10 +822,10 @@ void add_input_randomness(unsigned int type, unsigned int code,
 	if (value == last_value)
 		return;
 
-	DEBUG_ENT("input event\n");
 	last_value = value;
 	add_timer_randomness(&input_timer_state,
 			     (type << 4) ^ code ^ (code >> 4) ^ value);
+	trace_add_input_randomness(ENTROPY_BITS(&input_pool));
 }
 EXPORT_SYMBOL_GPL(add_input_randomness);
 
@@ -890,10 +880,8 @@ void add_disk_randomness(struct gendisk *disk)
 	if (!disk || !disk->random)
 		return;
 	/* first major is 1, so we get >= 0x200 here */
-	DEBUG_ENT("disk event %d:%d\n",
-		  MAJOR(disk_devt(disk)), MINOR(disk_devt(disk)));
-
 	add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
+	trace_add_disk_randomness(disk_devt(disk), ENTROPY_BITS(&input_pool));
 }
 #endif
 
@@ -941,10 +929,8 @@ static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
 	/* but never more than the buffer size */
 	bytes = min_t(int, bytes, sizeof(tmp));
 
-	DEBUG_ENT("going to reseed %s with %d bits (%zu of %d requested)\n",
-		  r->name, bytes * 8, nbytes * 8,
-		  r->entropy_count >> ENTROPY_SHIFT);
-
+	trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
+				  ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
 	bytes = extract_entropy(r->pull, tmp, bytes,
 				random_read_wakeup_thresh / 8, rsvd);
 	mix_pool_bytes(r, tmp, bytes, NULL);
@@ -992,8 +978,6 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
 	spin_lock_irqsave(&r->lock, flags);
 
 	BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
-	DEBUG_ENT("trying to extract %zu bits from %s\n",
-		  nbytes * 8, r->name);
 
 	/* Can we pull enough? */
 retry:
@@ -1019,12 +1003,9 @@ retry:
 		    < random_write_wakeup_thresh)
 			wakeup_write = 1;
 	}
-
-	DEBUG_ENT("debiting %zu entropy credits from %s%s\n",
-		  ibytes * 8, r->name, r->limit ? "" : " (unlimited)");
-
 	spin_unlock_irqrestore(&r->lock, flags);
 
+	trace_debit_entropy(r->name, 8 * ibytes);
 	if (wakeup_write) {
 		wake_up_interruptible(&random_write_wait);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
@@ -1303,8 +1284,6 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 		if (n > SEC_XFER_SIZE)
 			n = SEC_XFER_SIZE;
 
-		DEBUG_ENT("reading %zu bits\n", n*8);
-
 		n = extract_entropy_user(&blocking_pool, buf, n);
 
 		if (n < 0) {
@@ -1312,8 +1291,9 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 			break;
 		}
 
-		DEBUG_ENT("read got %zd bits (%zd still needed)\n",
-			  n*8, (nbytes-n)*8);
+		trace_random_read(n*8, (nbytes-n)*8,
+				  ENTROPY_BITS(&blocking_pool),
+				  ENTROPY_BITS(&input_pool));
 
 		if (n == 0) {
 			if (file->f_flags & O_NONBLOCK) {
@@ -1321,14 +1301,10 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 				break;
 			}
 
-			DEBUG_ENT("sleeping?\n");
-
 			wait_event_interruptible(random_read_wait,
 				ENTROPY_BITS(&input_pool) >=
 				random_read_wakeup_thresh);
 
-			DEBUG_ENT("awake\n");
-
 			if (signal_pending(current)) {
 				retval = -ERESTARTSYS;
 				break;
@@ -1350,7 +1326,11 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 static ssize_t
 urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
-	return extract_entropy_user(&nonblocking_pool, buf, nbytes);
+	int ret = extract_entropy_user(&nonblocking_pool, buf, nbytes);
+
+	trace_urandom_read(8 * nbytes, ENTROPY_BITS(&nonblocking_pool),
+			   ENTROPY_BITS(&input_pool));
+	return ret;
 }
 
 static unsigned int
diff --git a/include/trace/events/random.h b/include/trace/events/random.h
index 527b5dc1b416..805af6db41cc 100644
--- a/include/trace/events/random.h
+++ b/include/trace/events/random.h
@@ -109,6 +109,89 @@ TRACE_EVENT(push_to_pool,
 		  __entry->input_bits)
 );
 
+TRACE_EVENT(debit_entropy,
+	TP_PROTO(const char *pool_name, int debit_bits),
+
+	TP_ARGS(pool_name, debit_bits),
+
+	TP_STRUCT__entry(
+		__field( const char *,	pool_name		)
+		__field(	  int,	debit_bits		)
+	),
+
+	TP_fast_assign(
+		__entry->pool_name	= pool_name;
+		__entry->debit_bits	= debit_bits;
+	),
+
+	TP_printk("%s: debit_bits %d", __entry->pool_name,
+		  __entry->debit_bits)
+);
+
+TRACE_EVENT(add_input_randomness,
+	TP_PROTO(int input_bits),
+
+	TP_ARGS(input_bits),
+
+	TP_STRUCT__entry(
+		__field(	  int,	input_bits		)
+	),
+
+	TP_fast_assign(
+		__entry->input_bits	= input_bits;
+	),
+
+	TP_printk("input_pool_bits %d", __entry->input_bits)
+);
+
+TRACE_EVENT(add_disk_randomness,
+	TP_PROTO(dev_t dev, int input_bits),
+
+	TP_ARGS(dev, input_bits),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	  int,	input_bits		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= dev;
+		__entry->input_bits	= input_bits;
+	),
+
+	TP_printk("dev %d,%d input_pool_bits %d", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), __entry->input_bits)
+);
+
+TRACE_EVENT(xfer_secondary_pool,
+	TP_PROTO(const char *pool_name, int xfer_bits, int request_bits,
+		 int pool_entropy, int input_entropy),
+
+	TP_ARGS(pool_name, xfer_bits, request_bits, pool_entropy,
+		input_entropy),
+
+	TP_STRUCT__entry(
+		__field( const char *,	pool_name		)
+		__field(	  int,	xfer_bits		)
+		__field(	  int,	request_bits		)
+		__field(	  int,	pool_entropy		)
+		__field(	  int,	input_entropy		)
+	),
+
+	TP_fast_assign(
+		__entry->pool_name	= pool_name;
+		__entry->xfer_bits	= xfer_bits;
+		__entry->request_bits	= request_bits;
+		__entry->pool_entropy	= pool_entropy;
+		__entry->input_entropy	= input_entropy;
+	),
+
+	TP_printk("pool %s xfer_bits %d request_bits %d pool_entropy %d "
+		  "input_entropy %d", __entry->pool_name, __entry->xfer_bits,
+		  __entry->request_bits, __entry->pool_entropy,
+		  __entry->input_entropy)
+);
+
 DECLARE_EVENT_CLASS(random__get_random_bytes,
 	TP_PROTO(int nbytes, unsigned long IP),
 
@@ -179,7 +262,52 @@ DEFINE_EVENT(random__extract_entropy, extract_entropy_user,
 	TP_ARGS(pool_name, nbytes, entropy_count, IP)
 );
 
+TRACE_EVENT(random_read,
+	TP_PROTO(int got_bits, int need_bits, int pool_left, int input_left),
 
+	TP_ARGS(got_bits, need_bits, pool_left, input_left),
+
+	TP_STRUCT__entry(
+		__field(	  int,	got_bits		)
+		__field(	  int,	need_bits		)
+		__field(	  int,	pool_left		)
+		__field(	  int,	input_left		)
+	),
+
+	TP_fast_assign(
+		__entry->got_bits	= got_bits;
+		__entry->need_bits	= need_bits;
+		__entry->pool_left	= pool_left;
+		__entry->input_left	= input_left;
+	),
+
+	TP_printk("got_bits %d still_needed_bits %d "
+		  "blocking_pool_entropy_left %d input_entropy_left %d",
+		  __entry->got_bits, __entry->got_bits, __entry->pool_left,
+		  __entry->input_left)
+);
+
+TRACE_EVENT(urandom_read,
+	TP_PROTO(int got_bits, int pool_left, int input_left),
+
+	TP_ARGS(got_bits, pool_left, input_left),
+
+	TP_STRUCT__entry(
+		__field(	  int,	got_bits		)
+		__field(	  int,	pool_left		)
+		__field(	  int,	input_left		)
+	),
+
+	TP_fast_assign(
+		__entry->got_bits	= got_bits;
+		__entry->pool_left	= pool_left;
+		__entry->input_left	= input_left;
+	),
+
+	TP_printk("got_bits %d nonblocking_pool_entropy_left %d "
+		  "input_entropy_left %d", __entry->got_bits,
+		  __entry->pool_left, __entry->input_left)
+);
 
 #endif /* _TRACE_RANDOM_H */
 
-- 
cgit 


From b44084c2c822f99dd3f2334b288b7e463d222662 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2013 00:04:37 -0700
Subject: inet: rename ir_loc_port to ir_num

In commit 634fb979e8f ("inet: includes a sock_common in request_sock")
I forgot that the two ports in sock_common do not have same byte order :

skc_dport is __be16 (network order), but skc_num is __u16 (host order)

So sparse complains because ir_loc_port (mapped into skc_num) is
considered as __u16 while it should be __be16

Let rename ir_loc_port to ireq->ir_num (analogy with inet->inet_num),
and perform appropriate htons/ntohs conversions.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h          | 2 +-
 include/net/tcp.h                | 2 +-
 net/dccp/ipv6.c                  | 4 ++--
 net/dccp/minisocks.c             | 8 ++++----
 net/dccp/output.c                | 2 +-
 net/ipv4/inet_connection_sock.c  | 4 ++--
 net/ipv4/syncookies.c            | 8 ++++----
 net/ipv4/tcp_output.c            | 2 +-
 net/ipv6/inet6_connection_sock.c | 2 +-
 net/ipv6/syncookies.c            | 2 +-
 net/ipv6/tcp_ipv6.c              | 2 +-
 11 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index f91204442efa..06da91efbc83 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -72,7 +72,7 @@ struct inet_request_sock {
 	struct request_sock	req;
 #define ir_loc_addr		req.__req_common.skc_rcv_saddr
 #define ir_rmt_addr		req.__req_common.skc_daddr
-#define ir_loc_port		req.__req_common.skc_num
+#define ir_num			req.__req_common.skc_num
 #define ir_rmt_port		req.__req_common.skc_dport
 #define ir_v6_rmt_addr		req.__req_common.skc_v6_daddr
 #define ir_v6_loc_addr		req.__req_common.skc_v6_rcv_saddr
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 24a06161d174..1db3a016bff6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1110,7 +1110,7 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->acked = 0;
 	ireq->ecn_ok = 0;
 	ireq->ir_rmt_port = tcp_hdr(skb)->source;
-	ireq->ir_loc_port = tcp_hdr(skb)->dest;
+	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
 }
 
 void tcp_enter_memory_pressure(struct sock *sk);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5cc5b24a956e..4ac71ff7c2e4 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -231,7 +231,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
 	fl6.flowlabel = 0;
 	fl6.flowi6_oif = ireq->ir_iif;
 	fl6.fl6_dport = ireq->ir_rmt_port;
-	fl6.fl6_sport = ireq->ir_loc_port;
+	fl6.fl6_sport = htons(ireq->ir_num);
 	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
@@ -509,7 +509,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.fl6_dport = ireq->ir_rmt_port;
-		fl6.fl6_sport = ireq->ir_loc_port;
+		fl6.fl6_sport = htons(ireq->ir_num);
 		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
 		dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 66afbcec2941..9e2f78bc1553 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -266,10 +266,10 @@ int dccp_reqsk_init(struct request_sock *req,
 {
 	struct dccp_request_sock *dreq = dccp_rsk(req);
 
-	inet_rsk(req)->ir_rmt_port	  = dccp_hdr(skb)->dccph_sport;
-	inet_rsk(req)->ir_loc_port	  = dccp_hdr(skb)->dccph_dport;
-	inet_rsk(req)->acked	  = 0;
-	dreq->dreq_timestamp_echo = 0;
+	inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
+	inet_rsk(req)->ir_num	   = ntohs(dccp_hdr(skb)->dccph_dport);
+	inet_rsk(req)->acked	   = 0;
+	dreq->dreq_timestamp_echo  = 0;
 
 	/* inherit feature negotiation options from listening socket */
 	return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 9bf195d1b87a..8876078859da 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -424,7 +424,7 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
 	/* Build and checksum header */
 	dh = dccp_zeroed_hdr(skb, dccp_header_size);
 
-	dh->dccph_sport	= inet_rsk(req)->ir_loc_port;
+	dh->dccph_sport	= htons(inet_rsk(req)->ir_num);
 	dh->dccph_dport	= inet_rsk(req)->ir_rmt_port;
 	dh->dccph_doff	= (dccp_header_size +
 			   DCCP_SKB_CB(skb)->dccpd_opt_len) / 4;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2ffd931d652f..fc0e649cc002 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -676,8 +676,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newicsk->icsk_bind_hash = NULL;
 
 		inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
-		inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->ir_loc_port);
-		inet_sk(newsk)->inet_sport = inet_rsk(req)->ir_loc_port;
+		inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
+		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
 		newsk->sk_write_space = sk_stream_write_space;
 
 		newicsk->icsk_retransmits = 0;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 984e21cf3c50..3b64c59b4109 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -304,10 +304,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= cookie;
 	req->mss		= mss;
-	ireq->ir_loc_port		= th->dest;
-	ireq->ir_rmt_port		= th->source;
-	ireq->ir_loc_addr		= ip_hdr(skb)->daddr;
-	ireq->ir_rmt_addr		= ip_hdr(skb)->saddr;
+	ireq->ir_num		= ntohs(th->dest);
+	ireq->ir_rmt_port	= th->source;
+	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
+	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
 	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index faec81353522..2822ad021a48 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2734,7 +2734,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	th->syn = 1;
 	th->ack = 1;
 	TCP_ECN_make_synack(req, th);
-	th->source = ireq->ir_loc_port;
+	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
 	/* Setting of flags are superfluous here for callers (and ECE is
 	 * not even correctly set)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 1317c569b58f..77bb8afb141d 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -83,7 +83,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	fl6->flowi6_oif = ireq->ir_iif;
 	fl6->flowi6_mark = sk->sk_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
-	fl6->fl6_sport = ireq->ir_loc_port;
+	fl6->fl6_sport = htons(ireq->ir_num);
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
 
 	dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bc5698f9e4cd..d04d3f1dd9b7 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -194,7 +194,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 
 	req->mss = mss;
 	ireq->ir_rmt_port = th->source;
-	ireq->ir_loc_port = th->dest;
+	ireq->ir_num = ntohs(th->dest);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 	if (ipv6_opt_accepted(sk, skb) ||
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index db234d609b33..b996ee2005a9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1735,7 +1735,7 @@ static void get_openreq6(struct seq_file *seq,
 		   i,
 		   src->s6_addr32[0], src->s6_addr32[1],
 		   src->s6_addr32[2], src->s6_addr32[3],
-		   ntohs(inet_rsk(req)->ir_loc_port),
+		   inet_rsk(req)->ir_num,
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3],
 		   ntohs(inet_rsk(req)->ir_rmt_port),
-- 
cgit 


From 324d36ed26a22bc14b2dd4505f3dba3fb2676bcc Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 10 Oct 2013 10:50:06 -0700
Subject: Bluetooth: Remove hdev->ioctl driver callback

Since there is no use of hdev->ioctl by any Bluetooth driver since
ever, so just lets remove it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 -
 net/bluetooth/hci_sock.c         | 5 +----
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c06552769644..237bf8c03fb4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -287,7 +287,6 @@ struct hci_dev {
 	int (*setup)(struct hci_dev *hdev);
 	int (*send)(struct sk_buff *skb);
 	void (*notify)(struct hci_dev *hdev, unsigned int evt);
-	int (*ioctl)(struct hci_dev *hdev, unsigned int cmd, unsigned long arg);
 };
 
 #define HCI_PHY_HANDLE(handle)	(handle & 0xff)
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 5b2d3f3c9b67..3beaa0594009 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -553,10 +553,7 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 		return hci_sock_blacklist_del(hdev, (void __user *) arg);
 	}
 
-	if (hdev->ioctl)
-		return hdev->ioctl(hdev, cmd, arg);
-
-	return -EINVAL;
+	return -ENOIOCTLCMD;
 }
 
 static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,
-- 
cgit 


From 7ef9fbf08818fa1cb8ae89fca29f193dd78d5dd8 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 10 Oct 2013 14:54:14 -0700
Subject: Bluetooth: Move amp.h header file into net/bluetooth/

The amp.h header file is only used internally by the bluetooth.ko
module and is not a public API. So make it local to the core
Bluetooth module.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/amp.h | 54 ---------------------------------------------
 net/bluetooth/a2mp.c        |  3 ++-
 net/bluetooth/amp.c         |  3 ++-
 net/bluetooth/amp.h         | 54 +++++++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_event.c   |  3 ++-
 net/bluetooth/l2cap_core.c  |  3 ++-
 6 files changed, 62 insertions(+), 58 deletions(-)
 delete mode 100644 include/net/bluetooth/amp.h
 create mode 100644 net/bluetooth/amp.h

(limited to 'include')

diff --git a/include/net/bluetooth/amp.h b/include/net/bluetooth/amp.h
deleted file mode 100644
index 7ea3db77ba89..000000000000
--- a/include/net/bluetooth/amp.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
-   Copyright (c) 2011,2012 Intel Corp.
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License version 2 and
-   only version 2 as published by the Free Software Foundation.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-*/
-
-#ifndef __AMP_H
-#define __AMP_H
-
-struct amp_ctrl {
-	struct list_head	list;
-	struct kref		kref;
-	__u8			id;
-	__u16			assoc_len_so_far;
-	__u16			assoc_rem_len;
-	__u16			assoc_len;
-	__u8			*assoc;
-};
-
-int amp_ctrl_put(struct amp_ctrl *ctrl);
-void amp_ctrl_get(struct amp_ctrl *ctrl);
-struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id);
-struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
-void amp_ctrl_list_flush(struct amp_mgr *mgr);
-
-struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
-			     u8 remote_id, bool out);
-
-int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
-
-void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
-void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
-void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
-void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
-				   struct hci_conn *hcon);
-void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
-			struct hci_conn *hcon);
-void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
-			struct hci_conn *hcon);
-void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
-void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
-void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon);
-void amp_create_logical_link(struct l2cap_chan *chan);
-void amp_disconnect_logical_link(struct hci_chan *hchan);
-void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason);
-
-#endif /* __AMP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index b38d07477c20..9ae32cef1762 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -16,7 +16,8 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/a2mp.h>
-#include <net/bluetooth/amp.h>
+
+#include "amp.h"
 
 /* Global AMP Manager list */
 LIST_HEAD(amp_mgr_list);
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index d459ed43c779..b7b8f4eed661 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -15,9 +15,10 @@
 #include <net/bluetooth/hci.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/a2mp.h>
-#include <net/bluetooth/amp.h>
 #include <crypto/hash.h>
 
+#include "amp.h"
+
 /* Remote AMP Controllers interface */
 void amp_ctrl_get(struct amp_ctrl *ctrl)
 {
diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h
new file mode 100644
index 000000000000..7ea3db77ba89
--- /dev/null
+++ b/net/bluetooth/amp.h
@@ -0,0 +1,54 @@
+/*
+   Copyright (c) 2011,2012 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#ifndef __AMP_H
+#define __AMP_H
+
+struct amp_ctrl {
+	struct list_head	list;
+	struct kref		kref;
+	__u8			id;
+	__u16			assoc_len_so_far;
+	__u16			assoc_rem_len;
+	__u16			assoc_len;
+	__u8			*assoc;
+};
+
+int amp_ctrl_put(struct amp_ctrl *ctrl);
+void amp_ctrl_get(struct amp_ctrl *ctrl);
+struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id);
+struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id);
+void amp_ctrl_list_flush(struct amp_mgr *mgr);
+
+struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr,
+			     u8 remote_id, bool out);
+
+int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type);
+
+void amp_read_loc_info(struct hci_dev *hdev, struct amp_mgr *mgr);
+void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle);
+void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr);
+void amp_read_loc_assoc_final_data(struct hci_dev *hdev,
+				   struct hci_conn *hcon);
+void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon);
+void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr,
+			struct hci_conn *hcon);
+void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle);
+void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle);
+void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon);
+void amp_create_logical_link(struct l2cap_chan *chan);
+void amp_disconnect_logical_link(struct hci_chan *hchan);
+void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason);
+
+#endif /* __AMP_H */
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ada3bf4d7e2a..67316b3e9304 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -30,7 +30,8 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
 #include <net/bluetooth/a2mp.h>
-#include <net/bluetooth/amp.h>
+
+#include "amp.h"
 
 /* Handle HCI Event packets */
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 06e7173c2d13..09f6f61423ff 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -38,7 +38,8 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/smp.h>
 #include <net/bluetooth/a2mp.h>
-#include <net/bluetooth/amp.h>
+
+#include "amp.h"
 
 bool disable_ertm;
 
-- 
cgit 


From 7024728ee534d739380dc4fd31f020cfc6e86c28 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 10 Oct 2013 14:54:15 -0700
Subject: Bluetooth: Move a2mp.h header file into net/bluetooth/

The a2mp.h header file is only used internally by the bluetooth.ko
module and is not a public API. So make it local to the core
Bluetooth module.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/a2mp.h | 150 -------------------------------------------
 net/bluetooth/a2mp.c         |   2 +-
 net/bluetooth/a2mp.h         | 150 +++++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/amp.c          |   2 +-
 net/bluetooth/hci_conn.c     |   3 +-
 net/bluetooth/hci_event.c    |   2 +-
 net/bluetooth/l2cap_core.c   |   2 +-
 7 files changed, 156 insertions(+), 155 deletions(-)
 delete mode 100644 include/net/bluetooth/a2mp.h
 create mode 100644 net/bluetooth/a2mp.h

(limited to 'include')

diff --git a/include/net/bluetooth/a2mp.h b/include/net/bluetooth/a2mp.h
deleted file mode 100644
index 487b54c1308f..000000000000
--- a/include/net/bluetooth/a2mp.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
-   Copyright (c) 2010,2011 Code Aurora Forum.  All rights reserved.
-   Copyright (c) 2011,2012 Intel Corp.
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License version 2 and
-   only version 2 as published by the Free Software Foundation.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-*/
-
-#ifndef __A2MP_H
-#define __A2MP_H
-
-#include <net/bluetooth/l2cap.h>
-
-#define A2MP_FEAT_EXT	0x8000
-
-enum amp_mgr_state {
-	READ_LOC_AMP_INFO,
-	READ_LOC_AMP_ASSOC,
-	READ_LOC_AMP_ASSOC_FINAL,
-	WRITE_REMOTE_AMP_ASSOC,
-};
-
-struct amp_mgr {
-	struct list_head	list;
-	struct l2cap_conn	*l2cap_conn;
-	struct l2cap_chan	*a2mp_chan;
-	struct l2cap_chan	*bredr_chan;
-	struct kref		kref;
-	__u8			ident;
-	__u8			handle;
-	unsigned long		state;
-	unsigned long		flags;
-
-	struct list_head	amp_ctrls;
-	struct mutex		amp_ctrls_lock;
-};
-
-struct a2mp_cmd {
-	__u8	code;
-	__u8	ident;
-	__le16	len;
-	__u8	data[0];
-} __packed;
-
-/* A2MP command codes */
-#define A2MP_COMMAND_REJ         0x01
-struct a2mp_cmd_rej {
-	__le16	reason;
-	__u8	data[0];
-} __packed;
-
-#define A2MP_DISCOVER_REQ        0x02
-struct a2mp_discov_req {
-	__le16	mtu;
-	__le16	ext_feat;
-} __packed;
-
-struct a2mp_cl {
-	__u8	id;
-	__u8	type;
-	__u8	status;
-} __packed;
-
-#define A2MP_DISCOVER_RSP        0x03
-struct a2mp_discov_rsp {
-	__le16     mtu;
-	__le16     ext_feat;
-	struct a2mp_cl cl[0];
-} __packed;
-
-#define A2MP_CHANGE_NOTIFY       0x04
-#define A2MP_CHANGE_RSP          0x05
-
-#define A2MP_GETINFO_REQ         0x06
-struct a2mp_info_req {
-	__u8       id;
-} __packed;
-
-#define A2MP_GETINFO_RSP         0x07
-struct a2mp_info_rsp {
-	__u8	id;
-	__u8	status;
-	__le32	total_bw;
-	__le32	max_bw;
-	__le32	min_latency;
-	__le16	pal_cap;
-	__le16	assoc_size;
-} __packed;
-
-#define A2MP_GETAMPASSOC_REQ     0x08
-struct a2mp_amp_assoc_req {
-	__u8	id;
-} __packed;
-
-#define A2MP_GETAMPASSOC_RSP     0x09
-struct a2mp_amp_assoc_rsp {
-	__u8	id;
-	__u8	status;
-	__u8	amp_assoc[0];
-} __packed;
-
-#define A2MP_CREATEPHYSLINK_REQ  0x0A
-#define A2MP_DISCONNPHYSLINK_REQ 0x0C
-struct a2mp_physlink_req {
-	__u8	local_id;
-	__u8	remote_id;
-	__u8	amp_assoc[0];
-} __packed;
-
-#define A2MP_CREATEPHYSLINK_RSP  0x0B
-#define A2MP_DISCONNPHYSLINK_RSP 0x0D
-struct a2mp_physlink_rsp {
-	__u8	local_id;
-	__u8	remote_id;
-	__u8	status;
-} __packed;
-
-/* A2MP response status */
-#define A2MP_STATUS_SUCCESS			0x00
-#define A2MP_STATUS_INVALID_CTRL_ID		0x01
-#define A2MP_STATUS_UNABLE_START_LINK_CREATION	0x02
-#define A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS	0x02
-#define A2MP_STATUS_COLLISION_OCCURED		0x03
-#define A2MP_STATUS_DISCONN_REQ_RECVD		0x04
-#define A2MP_STATUS_PHYS_LINK_EXISTS		0x05
-#define A2MP_STATUS_SECURITY_VIOLATION		0x06
-
-extern struct list_head amp_mgr_list;
-extern struct mutex amp_mgr_list_lock;
-
-struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr);
-int amp_mgr_put(struct amp_mgr *mgr);
-u8 __next_ident(struct amp_mgr *mgr);
-struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
-				       struct sk_buff *skb);
-struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
-void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
-void a2mp_discover_amp(struct l2cap_chan *chan);
-void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
-void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
-void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status);
-void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status);
-
-#endif /* __A2MP_H */
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 9ae32cef1762..7e25be3e8a79 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -15,8 +15,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
-#include <net/bluetooth/a2mp.h>
 
+#include "a2mp.h"
 #include "amp.h"
 
 /* Global AMP Manager list */
diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h
new file mode 100644
index 000000000000..487b54c1308f
--- /dev/null
+++ b/net/bluetooth/a2mp.h
@@ -0,0 +1,150 @@
+/*
+   Copyright (c) 2010,2011 Code Aurora Forum.  All rights reserved.
+   Copyright (c) 2011,2012 Intel Corp.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 and
+   only version 2 as published by the Free Software Foundation.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+#ifndef __A2MP_H
+#define __A2MP_H
+
+#include <net/bluetooth/l2cap.h>
+
+#define A2MP_FEAT_EXT	0x8000
+
+enum amp_mgr_state {
+	READ_LOC_AMP_INFO,
+	READ_LOC_AMP_ASSOC,
+	READ_LOC_AMP_ASSOC_FINAL,
+	WRITE_REMOTE_AMP_ASSOC,
+};
+
+struct amp_mgr {
+	struct list_head	list;
+	struct l2cap_conn	*l2cap_conn;
+	struct l2cap_chan	*a2mp_chan;
+	struct l2cap_chan	*bredr_chan;
+	struct kref		kref;
+	__u8			ident;
+	__u8			handle;
+	unsigned long		state;
+	unsigned long		flags;
+
+	struct list_head	amp_ctrls;
+	struct mutex		amp_ctrls_lock;
+};
+
+struct a2mp_cmd {
+	__u8	code;
+	__u8	ident;
+	__le16	len;
+	__u8	data[0];
+} __packed;
+
+/* A2MP command codes */
+#define A2MP_COMMAND_REJ         0x01
+struct a2mp_cmd_rej {
+	__le16	reason;
+	__u8	data[0];
+} __packed;
+
+#define A2MP_DISCOVER_REQ        0x02
+struct a2mp_discov_req {
+	__le16	mtu;
+	__le16	ext_feat;
+} __packed;
+
+struct a2mp_cl {
+	__u8	id;
+	__u8	type;
+	__u8	status;
+} __packed;
+
+#define A2MP_DISCOVER_RSP        0x03
+struct a2mp_discov_rsp {
+	__le16     mtu;
+	__le16     ext_feat;
+	struct a2mp_cl cl[0];
+} __packed;
+
+#define A2MP_CHANGE_NOTIFY       0x04
+#define A2MP_CHANGE_RSP          0x05
+
+#define A2MP_GETINFO_REQ         0x06
+struct a2mp_info_req {
+	__u8       id;
+} __packed;
+
+#define A2MP_GETINFO_RSP         0x07
+struct a2mp_info_rsp {
+	__u8	id;
+	__u8	status;
+	__le32	total_bw;
+	__le32	max_bw;
+	__le32	min_latency;
+	__le16	pal_cap;
+	__le16	assoc_size;
+} __packed;
+
+#define A2MP_GETAMPASSOC_REQ     0x08
+struct a2mp_amp_assoc_req {
+	__u8	id;
+} __packed;
+
+#define A2MP_GETAMPASSOC_RSP     0x09
+struct a2mp_amp_assoc_rsp {
+	__u8	id;
+	__u8	status;
+	__u8	amp_assoc[0];
+} __packed;
+
+#define A2MP_CREATEPHYSLINK_REQ  0x0A
+#define A2MP_DISCONNPHYSLINK_REQ 0x0C
+struct a2mp_physlink_req {
+	__u8	local_id;
+	__u8	remote_id;
+	__u8	amp_assoc[0];
+} __packed;
+
+#define A2MP_CREATEPHYSLINK_RSP  0x0B
+#define A2MP_DISCONNPHYSLINK_RSP 0x0D
+struct a2mp_physlink_rsp {
+	__u8	local_id;
+	__u8	remote_id;
+	__u8	status;
+} __packed;
+
+/* A2MP response status */
+#define A2MP_STATUS_SUCCESS			0x00
+#define A2MP_STATUS_INVALID_CTRL_ID		0x01
+#define A2MP_STATUS_UNABLE_START_LINK_CREATION	0x02
+#define A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS	0x02
+#define A2MP_STATUS_COLLISION_OCCURED		0x03
+#define A2MP_STATUS_DISCONN_REQ_RECVD		0x04
+#define A2MP_STATUS_PHYS_LINK_EXISTS		0x05
+#define A2MP_STATUS_SECURITY_VIOLATION		0x06
+
+extern struct list_head amp_mgr_list;
+extern struct mutex amp_mgr_list_lock;
+
+struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr);
+int amp_mgr_put(struct amp_mgr *mgr);
+u8 __next_ident(struct amp_mgr *mgr);
+struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn,
+				       struct sk_buff *skb);
+struct amp_mgr *amp_mgr_lookup_by_state(u8 state);
+void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data);
+void a2mp_discover_amp(struct l2cap_chan *chan);
+void a2mp_send_getinfo_rsp(struct hci_dev *hdev);
+void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status);
+void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status);
+void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status);
+
+#endif /* __A2MP_H */
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index b7b8f4eed661..5497ed3f2e3d 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -14,9 +14,9 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci.h>
 #include <net/bluetooth/hci_core.h>
-#include <net/bluetooth/a2mp.h>
 #include <crypto/hash.h>
 
+#include "a2mp.h"
 #include "amp.h"
 
 /* Remote AMP Controllers interface */
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index dedd1ea5dd4c..8141c8d83139 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -28,9 +28,10 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
-#include <net/bluetooth/a2mp.h>
 #include <net/bluetooth/smp.h>
 
+#include "a2mp.h"
+
 struct sco_param {
 	u16 pkt_type;
 	u16 max_latency;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 67316b3e9304..bbe2d292c4a9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -29,8 +29,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
-#include <net/bluetooth/a2mp.h>
 
+#include "a2mp.h"
 #include "amp.h"
 
 /* Handle HCI Event packets */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 09f6f61423ff..947e18691e92 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -37,8 +37,8 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/smp.h>
-#include <net/bluetooth/a2mp.h>
 
+#include "a2mp.h"
 #include "amp.h"
 
 bool disable_ertm;
-- 
cgit 


From ac4b7236610cef99821f40f44a74030b85d85270 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 10 Oct 2013 14:54:16 -0700
Subject: Bluetooth: Move smp.h header file into net/bluetooth/

The smp.h header file is only used internally by the bluetooth.ko
module and is not a public API. So make it local to the core
Bluetooth module.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/smp.h | 146 --------------------------------------------
 net/bluetooth/hci_conn.c    |   2 +-
 net/bluetooth/l2cap_core.c  |   2 +-
 net/bluetooth/l2cap_sock.c  |   3 +-
 net/bluetooth/mgmt.c        |   3 +-
 net/bluetooth/smp.c         |   3 +-
 net/bluetooth/smp.h         | 146 ++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 154 insertions(+), 151 deletions(-)
 delete mode 100644 include/net/bluetooth/smp.h
 create mode 100644 net/bluetooth/smp.h

(limited to 'include')

diff --git a/include/net/bluetooth/smp.h b/include/net/bluetooth/smp.h
deleted file mode 100644
index f8ba07f3e5fa..000000000000
--- a/include/net/bluetooth/smp.h
+++ /dev/null
@@ -1,146 +0,0 @@
-/*
-   BlueZ - Bluetooth protocol stack for Linux
-   Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License version 2 as
-   published by the Free Software Foundation;
-
-   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
-   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
-   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
-   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
-   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
-   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
-   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
-
-   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
-   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
-   SOFTWARE IS DISCLAIMED.
-*/
-
-#ifndef __SMP_H
-#define __SMP_H
-
-struct smp_command_hdr {
-	__u8	code;
-} __packed;
-
-#define SMP_CMD_PAIRING_REQ	0x01
-#define SMP_CMD_PAIRING_RSP	0x02
-struct smp_cmd_pairing {
-	__u8	io_capability;
-	__u8	oob_flag;
-	__u8	auth_req;
-	__u8	max_key_size;
-	__u8	init_key_dist;
-	__u8	resp_key_dist;
-} __packed;
-
-#define SMP_IO_DISPLAY_ONLY	0x00
-#define SMP_IO_DISPLAY_YESNO	0x01
-#define SMP_IO_KEYBOARD_ONLY	0x02
-#define SMP_IO_NO_INPUT_OUTPUT	0x03
-#define SMP_IO_KEYBOARD_DISPLAY	0x04
-
-#define SMP_OOB_NOT_PRESENT	0x00
-#define SMP_OOB_PRESENT		0x01
-
-#define SMP_DIST_ENC_KEY	0x01
-#define SMP_DIST_ID_KEY		0x02
-#define SMP_DIST_SIGN		0x04
-
-#define SMP_AUTH_NONE		0x00
-#define SMP_AUTH_BONDING	0x01
-#define SMP_AUTH_MITM		0x04
-
-#define SMP_CMD_PAIRING_CONFIRM	0x03
-struct smp_cmd_pairing_confirm {
-	__u8	confirm_val[16];
-} __packed;
-
-#define SMP_CMD_PAIRING_RANDOM	0x04
-struct smp_cmd_pairing_random {
-	__u8	rand_val[16];
-} __packed;
-
-#define SMP_CMD_PAIRING_FAIL	0x05
-struct smp_cmd_pairing_fail {
-	__u8	reason;
-} __packed;
-
-#define SMP_CMD_ENCRYPT_INFO	0x06
-struct smp_cmd_encrypt_info {
-	__u8	ltk[16];
-} __packed;
-
-#define SMP_CMD_MASTER_IDENT	0x07
-struct smp_cmd_master_ident {
-	__le16	ediv;
-	__u8	rand[8];
-} __packed;
-
-#define SMP_CMD_IDENT_INFO	0x08
-struct smp_cmd_ident_info {
-	__u8	irk[16];
-} __packed;
-
-#define SMP_CMD_IDENT_ADDR_INFO	0x09
-struct smp_cmd_ident_addr_info {
-	__u8	addr_type;
-	bdaddr_t bdaddr;
-} __packed;
-
-#define SMP_CMD_SIGN_INFO	0x0a
-struct smp_cmd_sign_info {
-	__u8	csrk[16];
-} __packed;
-
-#define SMP_CMD_SECURITY_REQ	0x0b
-struct smp_cmd_security_req {
-	__u8	auth_req;
-} __packed;
-
-#define SMP_PASSKEY_ENTRY_FAILED	0x01
-#define SMP_OOB_NOT_AVAIL		0x02
-#define SMP_AUTH_REQUIREMENTS		0x03
-#define SMP_CONFIRM_FAILED		0x04
-#define SMP_PAIRING_NOTSUPP		0x05
-#define SMP_ENC_KEY_SIZE		0x06
-#define SMP_CMD_NOTSUPP			0x07
-#define SMP_UNSPECIFIED			0x08
-#define SMP_REPEATED_ATTEMPTS		0x09
-
-#define SMP_MIN_ENC_KEY_SIZE		7
-#define SMP_MAX_ENC_KEY_SIZE		16
-
-#define SMP_FLAG_TK_VALID	1
-#define SMP_FLAG_CFM_PENDING	2
-#define SMP_FLAG_MITM_AUTH	3
-
-struct smp_chan {
-	struct l2cap_conn *conn;
-	u8		preq[7]; /* SMP Pairing Request */
-	u8		prsp[7]; /* SMP Pairing Response */
-	u8		prnd[16]; /* SMP Pairing Random (local) */
-	u8		rrnd[16]; /* SMP Pairing Random (remote) */
-	u8		pcnf[16]; /* SMP Pairing Confirm */
-	u8		tk[16]; /* SMP Temporary Key */
-	u8		enc_key_size;
-	unsigned long	smp_flags;
-	struct crypto_blkcipher	*tfm;
-	struct work_struct confirm;
-	struct work_struct random;
-
-};
-
-/* SMP Commands */
-int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
-int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb);
-int smp_distribute_keys(struct l2cap_conn *conn, __u8 force);
-int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
-
-void smp_chan_destroy(struct l2cap_conn *conn);
-
-#endif /* __SMP_H */
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 8141c8d83139..139587159200 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -28,8 +28,8 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
-#include <net/bluetooth/smp.h>
 
+#include "smp.h"
 #include "a2mp.h"
 
 struct sco_param {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 947e18691e92..a7d10c3596e3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -36,8 +36,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
-#include <net/bluetooth/smp.h>
 
+#include "smp.h"
 #include "a2mp.h"
 #include "amp.h"
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 1daa4c579eb2..69e42db8a707 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -32,7 +32,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
-#include <net/bluetooth/smp.h>
+
+#include "smp.h"
 
 static struct bt_sock_list l2cap_sk_list = {
 	.lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9a069b532bde..143dd7319981 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -30,7 +30,8 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
-#include <net/bluetooth/smp.h>
+
+#include "smp.h"
 
 #define MGMT_VERSION	1
 #define MGMT_REVISION	4
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 884b2081a262..9272094bd429 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -28,7 +28,8 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
-#include <net/bluetooth/smp.h>
+
+#include "smp.h"
 
 #define SMP_TIMEOUT	msecs_to_jiffies(30000)
 
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
new file mode 100644
index 000000000000..f8ba07f3e5fa
--- /dev/null
+++ b/net/bluetooth/smp.h
@@ -0,0 +1,146 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 as
+   published by the Free Software Foundation;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#ifndef __SMP_H
+#define __SMP_H
+
+struct smp_command_hdr {
+	__u8	code;
+} __packed;
+
+#define SMP_CMD_PAIRING_REQ	0x01
+#define SMP_CMD_PAIRING_RSP	0x02
+struct smp_cmd_pairing {
+	__u8	io_capability;
+	__u8	oob_flag;
+	__u8	auth_req;
+	__u8	max_key_size;
+	__u8	init_key_dist;
+	__u8	resp_key_dist;
+} __packed;
+
+#define SMP_IO_DISPLAY_ONLY	0x00
+#define SMP_IO_DISPLAY_YESNO	0x01
+#define SMP_IO_KEYBOARD_ONLY	0x02
+#define SMP_IO_NO_INPUT_OUTPUT	0x03
+#define SMP_IO_KEYBOARD_DISPLAY	0x04
+
+#define SMP_OOB_NOT_PRESENT	0x00
+#define SMP_OOB_PRESENT		0x01
+
+#define SMP_DIST_ENC_KEY	0x01
+#define SMP_DIST_ID_KEY		0x02
+#define SMP_DIST_SIGN		0x04
+
+#define SMP_AUTH_NONE		0x00
+#define SMP_AUTH_BONDING	0x01
+#define SMP_AUTH_MITM		0x04
+
+#define SMP_CMD_PAIRING_CONFIRM	0x03
+struct smp_cmd_pairing_confirm {
+	__u8	confirm_val[16];
+} __packed;
+
+#define SMP_CMD_PAIRING_RANDOM	0x04
+struct smp_cmd_pairing_random {
+	__u8	rand_val[16];
+} __packed;
+
+#define SMP_CMD_PAIRING_FAIL	0x05
+struct smp_cmd_pairing_fail {
+	__u8	reason;
+} __packed;
+
+#define SMP_CMD_ENCRYPT_INFO	0x06
+struct smp_cmd_encrypt_info {
+	__u8	ltk[16];
+} __packed;
+
+#define SMP_CMD_MASTER_IDENT	0x07
+struct smp_cmd_master_ident {
+	__le16	ediv;
+	__u8	rand[8];
+} __packed;
+
+#define SMP_CMD_IDENT_INFO	0x08
+struct smp_cmd_ident_info {
+	__u8	irk[16];
+} __packed;
+
+#define SMP_CMD_IDENT_ADDR_INFO	0x09
+struct smp_cmd_ident_addr_info {
+	__u8	addr_type;
+	bdaddr_t bdaddr;
+} __packed;
+
+#define SMP_CMD_SIGN_INFO	0x0a
+struct smp_cmd_sign_info {
+	__u8	csrk[16];
+} __packed;
+
+#define SMP_CMD_SECURITY_REQ	0x0b
+struct smp_cmd_security_req {
+	__u8	auth_req;
+} __packed;
+
+#define SMP_PASSKEY_ENTRY_FAILED	0x01
+#define SMP_OOB_NOT_AVAIL		0x02
+#define SMP_AUTH_REQUIREMENTS		0x03
+#define SMP_CONFIRM_FAILED		0x04
+#define SMP_PAIRING_NOTSUPP		0x05
+#define SMP_ENC_KEY_SIZE		0x06
+#define SMP_CMD_NOTSUPP			0x07
+#define SMP_UNSPECIFIED			0x08
+#define SMP_REPEATED_ATTEMPTS		0x09
+
+#define SMP_MIN_ENC_KEY_SIZE		7
+#define SMP_MAX_ENC_KEY_SIZE		16
+
+#define SMP_FLAG_TK_VALID	1
+#define SMP_FLAG_CFM_PENDING	2
+#define SMP_FLAG_MITM_AUTH	3
+
+struct smp_chan {
+	struct l2cap_conn *conn;
+	u8		preq[7]; /* SMP Pairing Request */
+	u8		prsp[7]; /* SMP Pairing Response */
+	u8		prnd[16]; /* SMP Pairing Random (local) */
+	u8		rrnd[16]; /* SMP Pairing Random (remote) */
+	u8		pcnf[16]; /* SMP Pairing Confirm */
+	u8		tk[16]; /* SMP Temporary Key */
+	u8		enc_key_size;
+	unsigned long	smp_flags;
+	struct crypto_blkcipher	*tfm;
+	struct work_struct confirm;
+	struct work_struct random;
+
+};
+
+/* SMP Commands */
+int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
+int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb);
+int smp_distribute_keys(struct l2cap_conn *conn, __u8 force);
+int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey);
+
+void smp_chan_destroy(struct l2cap_conn *conn);
+
+#endif /* __SMP_H */
-- 
cgit 


From dc7743aa3c49fabbc6dc9edbcf7df74d776ac32e Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 2 Oct 2013 21:39:40 -0700
Subject: pinctrl: single: Add support for auxdata

For omaps, we still have dependencies to the legacy code
for handling the PRM (Power Reset Management) interrupts,
and also for reconfiguring the io wake-up chain after
changes.

Let's pass the PRM interrupt and the rearm functions via
auxdata. Then when at some point we have a proper PRM
driver, we can get the interrupt via device tree and
set up the rearm function as exported function in the
PRM driver.

By using auxdata we can remove a dependency to the
wake-up events for converting omap3 to be device
tree only.

Cc: Peter Ujfalusi <peter.ujfalusi@ti.com>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Prakash Manjunathappa <prakash.pm@ti.com>
Cc: Roger Quadros <rogerq@ti.com>
Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Kevin Hilman <khilman@linaro.org>
Tested-by: Kevin Hilman <khilman@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/pinctrl/pinctrl-single.c             | 23 +++++++++++++++++++++++
 include/linux/platform_data/pinctrl-single.h | 12 ++++++++++++
 2 files changed, 35 insertions(+)
 create mode 100644 include/linux/platform_data/pinctrl-single.h

(limited to 'include')

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index dad65df36f4b..c2aada71c915 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -28,6 +28,8 @@
 #include <linux/pinctrl/pinmux.h>
 #include <linux/pinctrl/pinconf-generic.h>
 
+#include <linux/platform_data/pinctrl-single.h>
+
 #include "core.h"
 #include "pinconf.h"
 
@@ -159,12 +161,14 @@ struct pcs_name {
  * @irq:	optional interrupt for the controller
  * @irq_enable_mask:	optional SoC specific interrupt enable mask
  * @irq_status_mask:	optional SoC specific interrupt status mask
+ * @rearm:	optional SoC specific wake-up rearm function
  */
 struct pcs_soc_data {
 	unsigned flags;
 	int irq;
 	unsigned irq_enable_mask;
 	unsigned irq_status_mask;
+	void (*rearm)(void);
 };
 
 /**
@@ -1622,6 +1626,8 @@ static void pcs_irq_unmask(struct irq_data *d)
 	struct pcs_soc_data *pcs_soc = irq_data_get_irq_chip_data(d);
 
 	pcs_irq_set(pcs_soc, d->irq, true);
+	if (pcs_soc->rearm)
+		pcs_soc->rearm();
 }
 
 /**
@@ -1672,6 +1678,11 @@ static int pcs_irq_handle(struct pcs_soc_data *pcs_soc)
 		}
 	}
 
+	/*
+	 * For debugging on omaps, you may want to call pcs_soc->rearm()
+	 * here to see wake-up interrupts during runtime also.
+	 */
+
 	return count;
 }
 
@@ -1835,6 +1846,7 @@ static int pcs_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *match;
+	struct pcs_pdata *pdata;
 	struct resource *res;
 	struct pcs_device *pcs;
 	const struct pcs_soc_data *soc;
@@ -1949,6 +1961,17 @@ static int pcs_probe(struct platform_device *pdev)
 	if (pcs->socdata.irq)
 		pcs->flags |= PCS_FEAT_IRQ;
 
+	/* We still need auxdata for some omaps for PRM interrupts */
+	pdata = dev_get_platdata(&pdev->dev);
+	if (pdata) {
+		if (pdata->rearm)
+			pcs->socdata.rearm = pdata->rearm;
+		if (pdata->irq) {
+			pcs->socdata.irq = pdata->irq;
+			pcs->flags |= PCS_FEAT_IRQ;
+		}
+	}
+
 	if (PCS_HAS_IRQ) {
 		ret = pcs_irq_init_chained_handler(pcs, np);
 		if (ret < 0)
diff --git a/include/linux/platform_data/pinctrl-single.h b/include/linux/platform_data/pinctrl-single.h
new file mode 100644
index 000000000000..72eacda9b360
--- /dev/null
+++ b/include/linux/platform_data/pinctrl-single.h
@@ -0,0 +1,12 @@
+/**
+ * irq:		optional wake-up interrupt
+ * rearm:	optional soc specific rearm function
+ *
+ * Note that the irq and rearm setup should come from device
+ * tree except for omap where there are still some dependencies
+ * to the legacy PRM code.
+ */
+struct pcs_pdata {
+	int irq;
+	void (*rearm)(void);
+};
-- 
cgit 


From 644f17ad7fc12768cd619532383343e514eab2ac Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 10 Oct 2013 13:28:46 +0300
Subject: ACPI / PM: allow child devices to ignore parent power state

Some serial buses like I2C and SPI don't require that the parent device is
in D0 before any of its children transitions to D0, but instead the parent
device can control its own power independently from the children.

This does not follow the ACPI specification as it requires the parent to be
powered on before its children. However, Windows seems to ignore this
requirement so I think we can do the same in Linux.

Implement this by adding a new power flag 'ignore_parent' to struct
acpi_device.  If this flag is set the ACPI core ignores checking of the
parent device power state when the device is powered on/off.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/device_pm.c | 8 +++++---
 include/acpi/acpi_bus.h  | 3 ++-
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 59d3202f6b36..ca723a4c120a 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -118,9 +118,10 @@ int acpi_device_get_power(struct acpi_device *device, int *state)
 	/*
 	 * If we were unsure about the device parent's power state up to this
 	 * point, the fact that the device is in D0 implies that the parent has
-	 * to be in D0 too.
+	 * to be in D0 too, except if ignore_parent is set.
 	 */
-	if (device->parent && device->parent->power.state == ACPI_STATE_UNKNOWN
+	if (!device->power.flags.ignore_parent && device->parent
+	    && device->parent->power.state == ACPI_STATE_UNKNOWN
 	    && result == ACPI_STATE_D0)
 		device->parent->power.state = ACPI_STATE_D0;
 
@@ -177,7 +178,8 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 			 acpi_power_state_string(state));
 		return -ENODEV;
 	}
-	if (device->parent && (state < device->parent->power.state)) {
+	if (!device->power.flags.ignore_parent &&
+	    device->parent && (state < device->parent->power.state)) {
 		dev_warn(&device->dev,
 			 "Cannot transition to power state %s for parent in %s\n",
 			 acpi_power_state_string(state),
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 02e113bb8b7d..e830ab029340 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -222,7 +222,8 @@ struct acpi_device_power_flags {
 	u32 power_resources:1;	/* Power resources */
 	u32 inrush_current:1;	/* Serialize Dx->D0 */
 	u32 power_removed:1;	/* Optimize Dx->D0 */
-	u32 reserved:28;
+	u32 ignore_parent:1;	/* Power is independent of parent power state */
+	u32 reserved:27;
 };
 
 struct acpi_device_power_state {
-- 
cgit 


From 81fcfb813fe99c30f77dd3ed9a4e541d14a9ed01 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Wed, 28 Aug 2013 18:37:39 +1000
Subject: hashtable: add hash_for_each_possible_rcu_notrace()

This adds hash_for_each_possible_rcu_notrace() which is basically
a notrace clone of hash_for_each_possible_rcu() which cannot be
used in real mode due to its tracing/debugging capability.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 include/linux/hashtable.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h
index a9df51f5d54c..519b6e2d769e 100644
--- a/include/linux/hashtable.h
+++ b/include/linux/hashtable.h
@@ -173,6 +173,21 @@ static inline void hash_del_rcu(struct hlist_node *node)
 	hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\
 		member)
 
+/**
+ * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing
+ * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ *
+ * This is the same as hash_for_each_possible_rcu() except that it does
+ * not do any RCU debugging or tracing.
+ */
+#define hash_for_each_possible_rcu_notrace(name, obj, member, key) \
+	hlist_for_each_entry_rcu_notrace(obj, \
+		&name[hash_min(key, HASH_BITS(name))], member)
+
 /**
  * hash_for_each_possible_safe - iterate over all possible objects hashing to the
  * same bucket safe against removals
-- 
cgit 


From 8e0861fa3c4edfc2f30dd4cf4d58d3929f7c1b23 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Wed, 28 Aug 2013 18:37:42 +1000
Subject: powerpc: Prepare to support kernel handling of IOMMU map/unmap

The current VFIO-on-POWER implementation supports only user mode
driven mapping, i.e. QEMU is sending requests to map/unmap pages.
However this approach is really slow, so we want to move that to KVM.
Since H_PUT_TCE can be extremely performance sensitive (especially with
network adapters where each packet needs to be mapped/unmapped) we chose
to implement that as a "fast" hypercall directly in "real
mode" (processor still in the guest context but MMU off).

To be able to do that, we need to provide some facilities to
access the struct page count within that real mode environment as things
like the sparsemem vmemmap mappings aren't accessible.

This adds an API function realmode_pfn_to_page() to get page struct when
MMU is off.

This adds to MM a new function put_page_unless_one() which drops a page
if counter is bigger than 1. It is going to be used when MMU is off
(for example, real mode on PPC64) and we want to make sure that page
release will not happen in real mode as it may crash the kernel in
a horrible way.

CONFIG_SPARSEMEM_VMEMMAP and CONFIG_FLATMEM are supported.

Cc: linux-mm@kvack.org
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pgtable-ppc64.h |  2 ++
 arch/powerpc/mm/init_64.c                | 51 +++++++++++++++++++++++++++++++-
 include/linux/mm.h                       | 14 +++++++++
 include/linux/page-flags.h               |  4 ++-
 4 files changed, 69 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 46db09414a10..4a191c472867 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -394,6 +394,8 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
 	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
 }
 
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
 static inline char *get_hpte_slot_array(pmd_t *pmdp)
 {
 	/*
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 8ed035d2edb5..e3734edffa69 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -304,5 +304,54 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
 {
 }
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * realmode_pfn_to_page functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct vmemmap_backing *vmem_back;
+	struct page *page;
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+		if (pg_va < vmem_back->virt_addr)
+			continue;
+
+		/* Check that page struct is not split between real pages */
+		if ((pg_va + sizeof(struct page)) >
+				(vmem_back->virt_addr + page_size))
+			return NULL;
+
+		page = (struct page *) (vmem_back->phys + pg_va -
+				vmem_back->virt_addr);
+		return page;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b6e55ee8855..1a0668e5a4ee 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -297,12 +297,26 @@ static inline int put_page_testzero(struct page *page)
 /*
  * Try to grab a ref unless the page has a refcount of zero, return false if
  * that is the case.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
  */
 static inline int get_page_unless_zero(struct page *page)
 {
 	return atomic_inc_not_zero(&page->_count);
 }
 
+/*
+ * Try to drop a ref unless the page has a refcount of one, return false if
+ * that is the case.
+ * This is to make sure that the refcount won't become zero after this drop.
+ * This can be called when MMU is off so it must not access
+ * any of the virtual mappings.
+ */
+static inline int put_page_unless_one(struct page *page)
+{
+	return atomic_add_unless(&page->_count, -1, 1);
+}
+
 extern int page_is_ram(unsigned long pfn);
 
 /* Support for virtually mapped pages */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6d53675c2b54..98ada58f9942 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -329,7 +329,9 @@ static inline void set_page_writeback(struct page *page)
  * System with lots of page flags available. This allows separate
  * flags for PageHead() and PageTail() checks of compound pages so that bit
  * tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths.
+ * generally not used in hot code paths except arch/powerpc/mm/init_64.c
+ * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
+ * and avoid handling those in real mode.
  */
 __PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
 __PAGEFLAG(Tail, tail)
-- 
cgit 


From e1a26170692dc1e5fbe0ccd98ef86cc9fcd31a64 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 10 Oct 2013 16:52:43 -0700
Subject: Bluetooth: Provide hdev parameter to hci_recv_frame() driver callback

To avoid casting skb->dev into hdev, just let the drivers provide
the hdev directly when calling hci_recv_frame() function.

This patch also fixes up all drivers to provide the hdev.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 drivers/bluetooth/bfusb.c        |  3 +--
 drivers/bluetooth/bluecard_cs.c  |  3 +--
 drivers/bluetooth/bpa10x.c       |  4 +---
 drivers/bluetooth/bt3c_cs.c      |  3 +--
 drivers/bluetooth/btmrvl_sdio.c  |  8 +++-----
 drivers/bluetooth/btsdio.c       |  3 +--
 drivers/bluetooth/btuart_cs.c    |  3 +--
 drivers/bluetooth/btwilink.c     |  4 +---
 drivers/bluetooth/dtl1_cs.c      |  3 +--
 drivers/bluetooth/hci_bcsp.c     |  5 ++---
 drivers/bluetooth/hci_h5.c       |  2 +-
 drivers/bluetooth/hci_ll.c       | 13 ++++++-------
 drivers/bluetooth/hci_vhci.c     |  3 +--
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/hci_core.c         |  6 ++----
 15 files changed, 24 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index 66faad0c6237..b7b5bb879f08 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -318,7 +318,6 @@ static inline int bfusb_recv_block(struct bfusb_data *data, int hdr, unsigned ch
 			return -ENOMEM;
 		}
 
-		skb->dev = (void *) data->hdev;
 		bt_cb(skb)->pkt_type = pkt_type;
 
 		data->reassembly = skb;
@@ -333,7 +332,7 @@ static inline int bfusb_recv_block(struct bfusb_data *data, int hdr, unsigned ch
 		memcpy(skb_put(data->reassembly, len), buf, len);
 
 	if (hdr & 0x08) {
-		hci_recv_frame(data->reassembly);
+		hci_recv_frame(data->hdev, data->reassembly);
 		data->reassembly = NULL;
 	}
 
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index aa872c9b3fc2..395acde99d78 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -399,7 +399,6 @@ static void bluecard_receive(bluecard_info_t *info, unsigned int offset)
 
 		if (info->rx_state == RECV_WAIT_PACKET_TYPE) {
 
-			info->rx_skb->dev = (void *) info->hdev;
 			bt_cb(info->rx_skb)->pkt_type = buf[i];
 
 			switch (bt_cb(info->rx_skb)->pkt_type) {
@@ -477,7 +476,7 @@ static void bluecard_receive(bluecard_info_t *info, unsigned int offset)
 					break;
 
 				case RECV_WAIT_DATA:
-					hci_recv_frame(info->rx_skb);
+					hci_recv_frame(info->hdev, info->rx_skb);
 					info->rx_skb = NULL;
 					break;
 
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index 2fe4a8031348..3188fb48bf4b 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -129,8 +129,6 @@ static int bpa10x_recv(struct hci_dev *hdev, int queue, void *buf, int count)
 				return -ENOMEM;
 			}
 
-			skb->dev = (void *) hdev;
-
 			data->rx_skb[queue] = skb;
 
 			scb = (void *) skb->cb;
@@ -155,7 +153,7 @@ static int bpa10x_recv(struct hci_dev *hdev, int queue, void *buf, int count)
 			data->rx_skb[queue] = NULL;
 
 			bt_cb(skb)->pkt_type = scb->type;
-			hci_recv_frame(skb);
+			hci_recv_frame(hdev, skb);
 		}
 
 		count -= len; buf += len;
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 673455cbde4c..d8e4b0d7926e 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -247,7 +247,6 @@ static void bt3c_receive(bt3c_info_t *info)
 
 		if (info->rx_state == RECV_WAIT_PACKET_TYPE) {
 
-			info->rx_skb->dev = (void *) info->hdev;
 			bt_cb(info->rx_skb)->pkt_type = inb(iobase + DATA_L);
 			inb(iobase + DATA_H);
 			//printk("bt3c: PACKET_TYPE=%02x\n", bt_cb(info->rx_skb)->pkt_type);
@@ -318,7 +317,7 @@ static void bt3c_receive(bt3c_info_t *info)
 					break;
 
 				case RECV_WAIT_DATA:
-					hci_recv_frame(info->rx_skb);
+					hci_recv_frame(info->hdev, info->rx_skb);
 					info->rx_skb = NULL;
 					break;
 
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 332475e400cf..fabcf5bb48af 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -600,15 +600,14 @@ static int btmrvl_sdio_card_to_host(struct btmrvl_private *priv)
 	case HCI_SCODATA_PKT:
 	case HCI_EVENT_PKT:
 		bt_cb(skb)->pkt_type = type;
-		skb->dev = (void *)hdev;
 		skb_put(skb, buf_len);
 		skb_pull(skb, SDIO_HEADER_LEN);
 
 		if (type == HCI_EVENT_PKT) {
 			if (btmrvl_check_evtpkt(priv, skb))
-				hci_recv_frame(skb);
+				hci_recv_frame(hdev, skb);
 		} else {
-			hci_recv_frame(skb);
+			hci_recv_frame(hdev, skb);
 		}
 
 		hdev->stat.byte_rx += buf_len;
@@ -616,12 +615,11 @@ static int btmrvl_sdio_card_to_host(struct btmrvl_private *priv)
 
 	case MRVL_VENDOR_PKT:
 		bt_cb(skb)->pkt_type = HCI_VENDOR_PKT;
-		skb->dev = (void *)hdev;
 		skb_put(skb, buf_len);
 		skb_pull(skb, SDIO_HEADER_LEN);
 
 		if (btmrvl_process_event(priv, skb))
-			hci_recv_frame(skb);
+			hci_recv_frame(hdev, skb);
 
 		hdev->stat.byte_rx += buf_len;
 		break;
diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c
index 4a9909713874..72fe49e60359 100644
--- a/drivers/bluetooth/btsdio.c
+++ b/drivers/bluetooth/btsdio.c
@@ -157,10 +157,9 @@ static int btsdio_rx_packet(struct btsdio_data *data)
 
 	data->hdev->stat.byte_rx += len;
 
-	skb->dev = (void *) data->hdev;
 	bt_cb(skb)->pkt_type = hdr[3];
 
-	err = hci_recv_frame(skb);
+	err = hci_recv_frame(data->hdev, skb);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/bluetooth/btuart_cs.c b/drivers/bluetooth/btuart_cs.c
index 970e2d3dd3c2..d0b89ecf1c59 100644
--- a/drivers/bluetooth/btuart_cs.c
+++ b/drivers/bluetooth/btuart_cs.c
@@ -198,7 +198,6 @@ static void btuart_receive(btuart_info_t *info)
 
 		if (info->rx_state == RECV_WAIT_PACKET_TYPE) {
 
-			info->rx_skb->dev = (void *) info->hdev;
 			bt_cb(info->rx_skb)->pkt_type = inb(iobase + UART_RX);
 
 			switch (bt_cb(info->rx_skb)->pkt_type) {
@@ -265,7 +264,7 @@ static void btuart_receive(btuart_info_t *info)
 					break;
 
 				case RECV_WAIT_DATA:
-					hci_recv_frame(info->rx_skb);
+					hci_recv_frame(info->hdev, info->rx_skb);
 					info->rx_skb = NULL;
 					break;
 
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index 60abf596f60e..5e10fb0a7e05 100644
--- a/drivers/bluetooth/btwilink.c
+++ b/drivers/bluetooth/btwilink.c
@@ -108,10 +108,8 @@ static long st_receive(void *priv_data, struct sk_buff *skb)
 		return -EFAULT;
 	}
 
-	skb->dev = (void *) lhst->hdev;
-
 	/* Forward skb to HCI core layer */
-	err = hci_recv_frame(skb);
+	err = hci_recv_frame(lhst->hdev, skb);
 	if (err < 0) {
 		BT_ERR("Unable to push skb to HCI core(%d)", err);
 		return err;
diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c
index c43aff8ec995..29451413bc04 100644
--- a/drivers/bluetooth/dtl1_cs.c
+++ b/drivers/bluetooth/dtl1_cs.c
@@ -256,9 +256,8 @@ static void dtl1_receive(dtl1_info_t *info)
 				case 0x83:
 				case 0x84:
 					/* send frame to the HCI layer */
-					info->rx_skb->dev = (void *) info->hdev;
 					bt_cb(info->rx_skb)->pkt_type &= 0x0f;
-					hci_recv_frame(info->rx_skb);
+					hci_recv_frame(info->hdev, info->rx_skb);
 					break;
 				default:
 					/* unknown packet */
diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c
index 57e502e06080..0bc87f7abd95 100644
--- a/drivers/bluetooth/hci_bcsp.c
+++ b/drivers/bluetooth/hci_bcsp.c
@@ -522,7 +522,7 @@ static void bcsp_complete_rx_pkt(struct hci_uart *hu)
 				memcpy(skb_push(bcsp->rx_skb, HCI_EVENT_HDR_SIZE), &hdr, HCI_EVENT_HDR_SIZE);
 				bt_cb(bcsp->rx_skb)->pkt_type = HCI_EVENT_PKT;
 
-				hci_recv_frame(bcsp->rx_skb);
+				hci_recv_frame(hu->hdev, bcsp->rx_skb);
 			} else {
 				BT_ERR ("Packet for unknown channel (%u %s)",
 					bcsp->rx_skb->data[1] & 0x0f,
@@ -536,7 +536,7 @@ static void bcsp_complete_rx_pkt(struct hci_uart *hu)
 		/* Pull out BCSP hdr */
 		skb_pull(bcsp->rx_skb, 4);
 
-		hci_recv_frame(bcsp->rx_skb);
+		hci_recv_frame(hu->hdev, bcsp->rx_skb);
 	}
 
 	bcsp->rx_state = BCSP_W4_PKT_DELIMITER;
@@ -655,7 +655,6 @@ static int bcsp_recv(struct hci_uart *hu, void *data, int count)
 					bcsp->rx_count = 0;
 					return 0;
 				}
-				bcsp->rx_skb->dev = (void *) hu->hdev;
 				break;
 			}
 			break;
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index b6154d5a07a5..f6f497450560 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -340,7 +340,7 @@ static void h5_complete_rx_pkt(struct hci_uart *hu)
 		/* Remove Three-wire header */
 		skb_pull(h5->rx_skb, 4);
 
-		hci_recv_frame(h5->rx_skb);
+		hci_recv_frame(hu->hdev, h5->rx_skb);
 		h5->rx_skb = NULL;
 
 		break;
diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index cfc767938589..58a9541feba6 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -346,14 +346,14 @@ static int ll_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 	return 0;
 }
 
-static inline int ll_check_data_len(struct ll_struct *ll, int len)
+static inline int ll_check_data_len(struct hci_dev *hdev, struct ll_struct *ll, int len)
 {
 	int room = skb_tailroom(ll->rx_skb);
 
 	BT_DBG("len %d room %d", len, room);
 
 	if (!len) {
-		hci_recv_frame(ll->rx_skb);
+		hci_recv_frame(hdev, ll->rx_skb);
 	} else if (len > room) {
 		BT_ERR("Data length is too large");
 		kfree_skb(ll->rx_skb);
@@ -395,7 +395,7 @@ static int ll_recv(struct hci_uart *hu, void *data, int count)
 			switch (ll->rx_state) {
 			case HCILL_W4_DATA:
 				BT_DBG("Complete data");
-				hci_recv_frame(ll->rx_skb);
+				hci_recv_frame(hu->hdev, ll->rx_skb);
 
 				ll->rx_state = HCILL_W4_PACKET_TYPE;
 				ll->rx_skb = NULL;
@@ -406,7 +406,7 @@ static int ll_recv(struct hci_uart *hu, void *data, int count)
 
 				BT_DBG("Event header: evt 0x%2.2x plen %d", eh->evt, eh->plen);
 
-				ll_check_data_len(ll, eh->plen);
+				ll_check_data_len(hu->hdev, ll, eh->plen);
 				continue;
 
 			case HCILL_W4_ACL_HDR:
@@ -415,7 +415,7 @@ static int ll_recv(struct hci_uart *hu, void *data, int count)
 
 				BT_DBG("ACL header: dlen %d", dlen);
 
-				ll_check_data_len(ll, dlen);
+				ll_check_data_len(hu->hdev, ll, dlen);
 				continue;
 
 			case HCILL_W4_SCO_HDR:
@@ -423,7 +423,7 @@ static int ll_recv(struct hci_uart *hu, void *data, int count)
 
 				BT_DBG("SCO header: dlen %d", sh->dlen);
 
-				ll_check_data_len(ll, sh->dlen);
+				ll_check_data_len(hu->hdev, ll, sh->dlen);
 				continue;
 			}
 		}
@@ -494,7 +494,6 @@ static int ll_recv(struct hci_uart *hu, void *data, int count)
 			return -ENOMEM;
 		}
 
-		ll->rx_skb->dev = (void *) hu->hdev;
 		bt_cb(ll->rx_skb)->pkt_type = type;
 	}
 
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index c04a3e6fb37c..0fd522e85a71 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -179,10 +179,9 @@ static inline ssize_t vhci_get_user(struct vhci_data *data,
 			return -ENODEV;
 		}
 
-		skb->dev = (void *) data->hdev;
 		bt_cb(skb)->pkt_type = pkt_type;
 
-		ret = hci_recv_frame(skb);
+		ret = hci_recv_frame(data->hdev, skb);
 		break;
 
 	case HCI_VENDOR_PKT:
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 237bf8c03fb4..29b81476424c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -755,7 +755,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
-int hci_recv_frame(struct sk_buff *skb);
+int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb);
 int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count);
 int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count);
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6cc2f86499f8..4f0d4b443171 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2485,9 +2485,8 @@ int hci_resume_dev(struct hci_dev *hdev)
 EXPORT_SYMBOL(hci_resume_dev);
 
 /* Receive frame from HCI drivers */
-int hci_recv_frame(struct sk_buff *skb)
+int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	if (!hdev || (!test_bit(HCI_UP, &hdev->flags)
 		      && !test_bit(HCI_INIT, &hdev->flags))) {
 		kfree_skb(skb);
@@ -2546,7 +2545,6 @@ static int hci_reassembly(struct hci_dev *hdev, int type, void *data,
 		scb->expect = hlen;
 		scb->pkt_type = type;
 
-		skb->dev = (void *) hdev;
 		hdev->reassembly[index] = skb;
 	}
 
@@ -2606,7 +2604,7 @@ static int hci_reassembly(struct hci_dev *hdev, int type, void *data,
 			/* Complete frame */
 
 			bt_cb(skb)->pkt_type = type;
-			hci_recv_frame(skb);
+			hci_recv_frame(hdev, skb);
 
 			hdev->reassembly[index] = NULL;
 			return remain;
-- 
cgit 


From e277e656804c85a0729d4fd8cdd3c8ab3e6b3b86 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Fri, 11 Oct 2013 09:30:24 +0800
Subject: regulator: Remove max_uV from struct regulator_linear_range

linear ranges means each range has linear voltage settings.
So we can calculate max_uV for each linear range in regulator core rather than
set the max_uV field in drivers.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/88pm800.c            | 14 ++++++--------
 drivers/regulator/as3711-regulator.c   | 25 +++++++++++--------------
 drivers/regulator/as3722-regulator.c   |  1 -
 drivers/regulator/da903x.c             |  6 ++----
 drivers/regulator/helpers.c            |  6 +++++-
 drivers/regulator/tps65217-regulator.c | 24 ++++++++----------------
 drivers/regulator/tps65912-regulator.c |  9 +++------
 drivers/regulator/wm831x-ldo.c         | 12 ++++--------
 drivers/regulator/wm8350-regulator.c   |  6 ++----
 drivers/regulator/wm8400-regulator.c   |  6 ++----
 include/linux/regulator/driver.h       |  2 --
 11 files changed, 43 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/88pm800.c b/drivers/regulator/88pm800.c
index 3459f60dcfd1..22ba4c4280ee 100644
--- a/drivers/regulator/88pm800.c
+++ b/drivers/regulator/88pm800.c
@@ -141,18 +141,16 @@ struct pm800_regulators {
 
 /* Ranges are sorted in ascending order. */
 static const struct regulator_linear_range buck1_volt_range[] = {
-	{ .min_uV = 600000, .max_uV = 1587500, .min_sel = 0, .max_sel = 0x4f,
-	  .uV_step = 12500 },
-	{ .min_uV = 1600000, .max_uV = 1800000, .min_sel = 0x50,
-	  .max_sel = 0x54, .uV_step = 50000 },
+	{ .min_uV = 600000, .min_sel = 0, .max_sel = 0x4f, .uV_step = 12500 },
+	{ .min_uV = 1600000, .min_sel = 0x50, .max_sel = 0x54,
+	  .uV_step = 50000 },
 };
 
 /* BUCK 2~5 have same ranges. */
 static const struct regulator_linear_range buck2_5_volt_range[] = {
-	{ .min_uV = 600000, .max_uV = 1587500,	.min_sel = 0, .max_sel = 0x4f,
-	  .uV_step = 12500 },
-	{ .min_uV = 1600000, .max_uV = 3300000, .min_sel = 0x50,
-	  .max_sel = 0x72, .uV_step = 50000 },
+	{ .min_uV = 600000, .min_sel = 0, .max_sel = 0x4f, .uV_step = 12500 },
+	{ .min_uV = 1600000, .min_sel = 0x50, .max_sel = 0x72,
+	  .uV_step = 50000 },
 };
 
 static const unsigned int ldo1_volt_table[] = {
diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c
index 8406cd745da2..d0a97e5ea431 100644
--- a/drivers/regulator/as3711-regulator.c
+++ b/drivers/regulator/as3711-regulator.c
@@ -117,26 +117,23 @@ static struct regulator_ops as3711_dldo_ops = {
 };
 
 static const struct regulator_linear_range as3711_sd_ranges[] = {
-	{ .min_uV = 612500, .max_uV = 1400000,
-	  .min_sel = 0x1, .max_sel = 0x40, .uV_step = 12500 },
-	{ .min_uV = 1425000, .max_uV = 2600000,
-	  .min_sel = 0x41, .max_sel = 0x70, .uV_step = 25000 },
-	{ .min_uV = 2650000, .max_uV = 3350000,
-	  .min_sel = 0x71, .max_sel = 0x7f, .uV_step = 50000 },
+	{ .min_uV = 612500, .min_sel = 0x1, .max_sel = 0x40, .uV_step = 12500 },
+	{ .min_uV = 1425000, .min_sel = 0x41, .max_sel = 0x70,
+	  .uV_step = 25000 },
+	{ .min_uV = 2650000, .min_sel = 0x71, .max_sel = 0x7f,
+	  .uV_step = 50000 },
 };
 
 static const struct regulator_linear_range as3711_aldo_ranges[] = {
-	{ .min_uV = 1200000, .max_uV = 1950000,
-	  .min_sel = 0, .max_sel = 0xf, .uV_step = 50000 },
-	{ .min_uV = 1800000, .max_uV = 3300000,
-	  .min_sel = 0x10, .max_sel = 0x1f, .uV_step = 100000 },
+	{ .min_uV = 1200000, .min_sel = 0, .max_sel = 0xf, .uV_step = 50000 },
+	{ .min_uV = 1800000, .min_sel = 0x10, .max_sel = 0x1f,
+	  .uV_step = 100000 },
 };
 
 static const struct regulator_linear_range as3711_dldo_ranges[] = {
-	{ .min_uV = 900000, .max_uV = 1700000,
-	  .min_sel = 0, .max_sel = 0x10, .uV_step = 50000 },
-	{ .min_uV = 1750000, .max_uV = 3300000,
-	  .min_sel = 0x20, .max_sel = 0x3f, .uV_step = 50000 },
+	{ .min_uV = 900000, .min_sel = 0, .max_sel = 0x10, .uV_step = 50000 },
+	{ .min_uV = 1750000, .min_sel = 0x20, .max_sel = 0x3f,
+	  .uV_step = 50000 },
 };
 
 #define AS3711_REG(_id, _en_reg, _en_bit, _vmask, _vshift, _min_uV, _max_uV, _sfx)	\
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index d7b71a9c41f1..240ae6d2ee2a 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -441,7 +441,6 @@ static struct regulator_ops as3722_ldo3_extcntrl_ops = {
 		.max_sel = _max_sel,					\
 		.uV_step = _step_uV,					\
 		.min_uV = _min_uV,					\
-		.max_uV = _min_uV + (_max_sel - _min_sel) * _step_uV,	\
 	}
 
 static const struct regulator_linear_range as3722_ldo_ranges[] = {
diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c
index f06854cf8cf5..90d55e066447 100644
--- a/drivers/regulator/da903x.c
+++ b/drivers/regulator/da903x.c
@@ -253,10 +253,8 @@ static int da9034_set_dvc_voltage_sel(struct regulator_dev *rdev,
 }
 
 static const struct regulator_linear_range da9034_ldo12_ranges[] = {
-	{ .min_uV = 1700000, .max_uV = 2050000, .min_sel =  0, .max_sel = 7,
-	  .uV_step =  50000 },
-	{ .min_uV = 2700000, .max_uV = 3050000, .min_sel =  8, .max_sel = 15,
-	  .uV_step =  50000 },
+	{ .min_uV = 1700000, .min_sel =  0, .max_sel = 7, .uV_step =  50000 },
+	{ .min_uV = 2700000, .min_sel =  8, .max_sel = 15, .uV_step =  50000 },
 };
 
 static struct regulator_ops da903x_regulator_ldo_ops = {
diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index 6e30df14714b..e221a271ba56 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -284,9 +284,13 @@ int regulator_map_voltage_linear_range(struct regulator_dev *rdev,
 	}
 
 	for (i = 0; i < rdev->desc->n_linear_ranges; i++) {
+		int linear_max_uV;
+
 		range = &rdev->desc->linear_ranges[i];
+		linear_max_uV = range->min_uV +
+			(range->max_sel - range->min_sel) * range->uV_step;
 
-		if (!(min_uV <= range->max_uV && max_uV >= range->min_uV))
+		if (!(min_uV <= linear_max_uV && max_uV >= range->min_uV))
 			continue;
 
 		if (min_uV <= range->min_uV)
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index 90861d68a0b0..484866f43681 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -52,25 +52,17 @@ static const unsigned int LDO1_VSEL_table[] = {
 };
 
 static const struct regulator_linear_range tps65217_uv1_ranges[] = {
-	{ .min_uV = 900000, .max_uV = 1500000, .min_sel =  0, .max_sel = 24,
-	  .uV_step = 25000 },
-	{ .min_uV = 1550000, .max_uV = 1800000, .min_sel = 25, .max_sel = 30,
-	  .uV_step = 50000 },
-	{ .min_uV = 1850000, .max_uV = 2900000, .min_sel = 31, .max_sel = 52,
-	  .uV_step = 50000 },
-	{ .min_uV = 3000000, .max_uV = 3200000, .min_sel = 53, .max_sel = 55,
-	  .uV_step = 100000 },
-	{ .min_uV = 3300000, .max_uV = 3300000, .min_sel = 56, .max_sel = 62,
-	  .uV_step = 0 },
+	{ .min_uV = 900000, .min_sel =  0, .max_sel = 24, .uV_step = 25000 },
+	{ .min_uV = 1550000, .min_sel = 25, .max_sel = 30, .uV_step = 50000 },
+	{ .min_uV = 1850000, .min_sel = 31, .max_sel = 52, .uV_step = 50000 },
+	{ .min_uV = 3000000, .min_sel = 53, .max_sel = 55, .uV_step = 100000 },
+	{ .min_uV = 3300000, .min_sel = 56, .max_sel = 62, .uV_step = 0 },
 };
 
 static const struct regulator_linear_range tps65217_uv2_ranges[] = {
-	{ .min_uV = 1500000, .max_uV = 1900000, .min_sel =  0, .max_sel = 8,
-	  .uV_step = 50000 },
-	{ .min_uV = 2000000, .max_uV = 2400000, .min_sel = 9, .max_sel = 13,
-	  .uV_step = 100000 },
-	{ .min_uV = 2450000, .max_uV = 3300000, .min_sel = 14, .max_sel = 31,
-	  .uV_step = 50000 },
+	{ .min_uV = 1500000, .min_sel =  0, .max_sel = 8, .uV_step = 50000 },
+	{ .min_uV = 2000000, .min_sel = 9, .max_sel = 13, .uV_step = 100000 },
+	{ .min_uV = 2450000, .min_sel = 14, .max_sel = 31, .uV_step = 50000 },
 };
 
 static int tps65217_pmic_enable(struct regulator_dev *dev)
diff --git a/drivers/regulator/tps65912-regulator.c b/drivers/regulator/tps65912-regulator.c
index 281e52ac64ba..9fc87d8c9ce5 100644
--- a/drivers/regulator/tps65912-regulator.c
+++ b/drivers/regulator/tps65912-regulator.c
@@ -119,12 +119,9 @@ struct tps65912_reg {
 };
 
 static const struct regulator_linear_range tps65912_ldo_ranges[] = {
-	{ .min_uV = 800000, .max_uV = 1600000, .min_sel =  0, .max_sel = 32,
-	  .uV_step = 25000 },
-	{ .min_uV = 1650000, .max_uV = 3000000, .min_sel = 33, .max_sel = 60,
-	  .uV_step = 50000 },
-	{ .min_uV = 3100000, .max_uV = 3300000, .min_sel = 61, .max_sel = 63,
-	  .uV_step = 100000 },
+	{ .min_uV = 800000, .min_sel =  0, .max_sel = 32, .uV_step = 25000 },
+	{ .min_uV = 1650000, .min_sel = 33, .max_sel = 60, .uV_step = 50000 },
+	{ .min_uV = 3100000, .min_sel = 61, .max_sel = 63, .uV_step = 100000 },
 };
 
 static int tps65912_get_range(struct tps65912_reg *pmic, int id)
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index 2205fbc2c37b..a95814027b24 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -63,10 +63,8 @@ static irqreturn_t wm831x_ldo_uv_irq(int irq, void *data)
  */
 
 static const struct regulator_linear_range wm831x_gp_ldo_ranges[] = {
-	{ .min_uV =  900000, .max_uV = 1600000, .min_sel =  0, .max_sel = 14,
-	  .uV_step =  50000 },
-	{ .min_uV = 1700000, .max_uV = 3300000, .min_sel = 15, .max_sel = 31,
-	  .uV_step = 100000 },
+	{ .min_uV =  900000, .min_sel =  0, .max_sel = 14, .uV_step =  50000 },
+	{ .min_uV = 1700000, .min_sel = 15, .max_sel = 31, .uV_step = 100000 },
 };
 
 static int wm831x_gp_ldo_set_suspend_voltage(struct regulator_dev *rdev,
@@ -332,10 +330,8 @@ static struct platform_driver wm831x_gp_ldo_driver = {
  */
 
 static const struct regulator_linear_range wm831x_aldo_ranges[] = {
-	{ .min_uV = 1000000, .max_uV = 1600000, .min_sel =  0, .max_sel = 12,
-	  .uV_step =  50000 },
-	{ .min_uV = 1700000, .max_uV = 3500000, .min_sel = 13, .max_sel = 31,
-	  .uV_step = 100000 },
+	{ .min_uV = 1000000, .min_sel =  0, .max_sel = 12, .uV_step =  50000 },
+	{ .min_uV = 1700000, .min_sel = 13, .max_sel = 31, .uV_step = 100000 },
 };
 
 static int wm831x_aldo_set_suspend_voltage(struct regulator_dev *rdev,
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index 61ca9292a429..de9de26d0bfc 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -543,10 +543,8 @@ static int wm8350_dcdc_set_suspend_mode(struct regulator_dev *rdev,
 }
 
 static const struct regulator_linear_range wm8350_ldo_ranges[] = {
-	{ .min_uV =  900000, .max_uV = 1650000, .min_sel =  0, .max_sel = 15,
-	  .uV_step =  50000 },
-	{ .min_uV = 1800000, .max_uV = 3300000, .min_sel = 16, .max_sel = 31,
-	  .uV_step = 100000 },
+	{ .min_uV =  900000, .min_sel =  0, .max_sel = 15, .uV_step =  50000 },
+	{ .min_uV = 1800000, .min_sel = 16, .max_sel = 31, .uV_step = 100000 },
 };
 
 static int wm8350_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV)
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index 58f51bec13f2..3352b2090ed5 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -20,10 +20,8 @@
 #include <linux/mfd/wm8400-private.h>
 
 static const struct regulator_linear_range wm8400_ldo_ranges[] = {
-	{ .min_uV =  900000, .max_uV = 1600000, .min_sel = 0, .max_sel = 14,
-	  .uV_step =  50000 },
-	{ .min_uV = 1700000, .max_uV = 3300000, .min_sel = 15, .max_sel = 31,
-	  .uV_step = 100000 },
+	{ .min_uV =  900000, .min_sel = 0, .max_sel = 14, .uV_step =  50000 },
+	{ .min_uV = 1700000, .min_sel = 15, .max_sel = 31, .uV_step = 100000 },
 };
 
 static struct regulator_ops wm8400_ldo_ops = {
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 9bdad43ad228..997ff5c4d880 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -46,14 +46,12 @@ enum regulator_status {
  * regulator_list_linear_range().
  *
  * @min_uV:  Lowest voltage in range
- * @max_uV:  Highest voltage in range
  * @min_sel: Lowest selector for range
  * @max_sel: Highest selector for range
  * @uV_step: Step size
  */
 struct regulator_linear_range {
 	unsigned int min_uV;
-	unsigned int max_uV;
 	unsigned int min_sel;
 	unsigned int max_sel;
 	unsigned int uV_step;
-- 
cgit 


From 8828bae464b129abed95b748263f1ab53bdc5755 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Fri, 11 Oct 2013 09:32:18 +0800
Subject: regulator: Add REGULATOR_LINEAR_RANGE macro

Add REGULATOR_LINEAR_RANGE macro and convert regulator drivers to use it.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/88pm800.c            | 10 ++++------
 drivers/regulator/as3711-regulator.c   | 18 +++++++-----------
 drivers/regulator/as3722-regulator.c   | 18 +++++-------------
 drivers/regulator/da903x.c             |  4 ++--
 drivers/regulator/tps65217-regulator.c | 16 ++++++++--------
 drivers/regulator/tps65912-regulator.c |  6 +++---
 drivers/regulator/wm831x-ldo.c         |  8 ++++----
 drivers/regulator/wm8350-regulator.c   |  4 ++--
 drivers/regulator/wm8400-regulator.c   |  4 ++--
 include/linux/regulator/driver.h       |  9 +++++++++
 10 files changed, 46 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/88pm800.c b/drivers/regulator/88pm800.c
index 22ba4c4280ee..d333f7eac106 100644
--- a/drivers/regulator/88pm800.c
+++ b/drivers/regulator/88pm800.c
@@ -141,16 +141,14 @@ struct pm800_regulators {
 
 /* Ranges are sorted in ascending order. */
 static const struct regulator_linear_range buck1_volt_range[] = {
-	{ .min_uV = 600000, .min_sel = 0, .max_sel = 0x4f, .uV_step = 12500 },
-	{ .min_uV = 1600000, .min_sel = 0x50, .max_sel = 0x54,
-	  .uV_step = 50000 },
+	REGULATOR_LINEAR_RANGE(600000, 0, 0x4f, 12500),
+	REGULATOR_LINEAR_RANGE(1600000, 0x50, 0x54, 50000),
 };
 
 /* BUCK 2~5 have same ranges. */
 static const struct regulator_linear_range buck2_5_volt_range[] = {
-	{ .min_uV = 600000, .min_sel = 0, .max_sel = 0x4f, .uV_step = 12500 },
-	{ .min_uV = 1600000, .min_sel = 0x50, .max_sel = 0x72,
-	  .uV_step = 50000 },
+	REGULATOR_LINEAR_RANGE(600000, 0, 0x4f, 12500),
+	REGULATOR_LINEAR_RANGE(1600000, 0x50, 0x72, 50000),
 };
 
 static const unsigned int ldo1_volt_table[] = {
diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c
index d0a97e5ea431..f8524f988bdc 100644
--- a/drivers/regulator/as3711-regulator.c
+++ b/drivers/regulator/as3711-regulator.c
@@ -117,23 +117,19 @@ static struct regulator_ops as3711_dldo_ops = {
 };
 
 static const struct regulator_linear_range as3711_sd_ranges[] = {
-	{ .min_uV = 612500, .min_sel = 0x1, .max_sel = 0x40, .uV_step = 12500 },
-	{ .min_uV = 1425000, .min_sel = 0x41, .max_sel = 0x70,
-	  .uV_step = 25000 },
-	{ .min_uV = 2650000, .min_sel = 0x71, .max_sel = 0x7f,
-	  .uV_step = 50000 },
+	REGULATOR_LINEAR_RANGE(612500, 0x1, 0x40, 12500),
+	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
+	REGULATOR_LINEAR_RANGE(2650000, 0x71, 0x7f, 50000),
 };
 
 static const struct regulator_linear_range as3711_aldo_ranges[] = {
-	{ .min_uV = 1200000, .min_sel = 0, .max_sel = 0xf, .uV_step = 50000 },
-	{ .min_uV = 1800000, .min_sel = 0x10, .max_sel = 0x1f,
-	  .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(1200000, 0, 0xf, 50000),
+	REGULATOR_LINEAR_RANGE(1800000, 0x10, 0x1f, 100000),
 };
 
 static const struct regulator_linear_range as3711_dldo_ranges[] = {
-	{ .min_uV = 900000, .min_sel = 0, .max_sel = 0x10, .uV_step = 50000 },
-	{ .min_uV = 1750000, .min_sel = 0x20, .max_sel = 0x3f,
-	  .uV_step = 50000 },
+	REGULATOR_LINEAR_RANGE(900000, 0, 0x10, 50000),
+	REGULATOR_LINEAR_RANGE(1750000, 0x20, 0x3f, 50000),
 };
 
 #define AS3711_REG(_id, _en_reg, _en_bit, _vmask, _vshift, _min_uV, _max_uV, _sfx)	\
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index 240ae6d2ee2a..5917fe3dc983 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -435,17 +435,9 @@ static struct regulator_ops as3722_ldo3_extcntrl_ops = {
 	.get_current_limit = as3722_ldo3_get_current_limit,
 };
 
-#define regulator_lin_range(_min_sel, _max_sel, _min_uV, _step_uV)	\
-	{								\
-		.min_sel = _min_sel,					\
-		.max_sel = _max_sel,					\
-		.uV_step = _step_uV,					\
-		.min_uV = _min_uV,					\
-	}
-
 static const struct regulator_linear_range as3722_ldo_ranges[] = {
-	regulator_lin_range(0x01, 0x24,  825000, 25000),
-	regulator_lin_range(0x40, 0x7F, 1725000, 25000),
+	REGULATOR_LINEAR_RANGE(825000, 0x01, 0x24, 25000),
+	REGULATOR_LINEAR_RANGE(1725000, 0x40, 0x7F, 25000),
 };
 
 static struct regulator_ops as3722_ldo_ops = {
@@ -604,9 +596,9 @@ static int as3722_sd016_set_current_limit(struct regulator_dev *rdev,
 }
 
 static const struct regulator_linear_range as3722_sd2345_ranges[] = {
-	regulator_lin_range(0x01, 0x40,  612500, 12500),
-	regulator_lin_range(0x41, 0x70, 1425000, 25000),
-	regulator_lin_range(0x71, 0x7F, 2650000, 50000),
+	REGULATOR_LINEAR_RANGE(612500, 0x01, 0x40, 12500),
+	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
+	REGULATOR_LINEAR_RANGE(2650000, 0x71, 0x7F, 50000),
 };
 
 static struct regulator_ops as3722_sd016_ops = {
diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c
index 90d55e066447..6d1b799ad86b 100644
--- a/drivers/regulator/da903x.c
+++ b/drivers/regulator/da903x.c
@@ -253,8 +253,8 @@ static int da9034_set_dvc_voltage_sel(struct regulator_dev *rdev,
 }
 
 static const struct regulator_linear_range da9034_ldo12_ranges[] = {
-	{ .min_uV = 1700000, .min_sel =  0, .max_sel = 7, .uV_step =  50000 },
-	{ .min_uV = 2700000, .min_sel =  8, .max_sel = 15, .uV_step =  50000 },
+	REGULATOR_LINEAR_RANGE(1700000, 0, 7, 50000),
+	REGULATOR_LINEAR_RANGE(2700000, 8, 15, 50000),
 };
 
 static struct regulator_ops da903x_regulator_ldo_ops = {
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index 484866f43681..bbc7277fa097 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -52,17 +52,17 @@ static const unsigned int LDO1_VSEL_table[] = {
 };
 
 static const struct regulator_linear_range tps65217_uv1_ranges[] = {
-	{ .min_uV = 900000, .min_sel =  0, .max_sel = 24, .uV_step = 25000 },
-	{ .min_uV = 1550000, .min_sel = 25, .max_sel = 30, .uV_step = 50000 },
-	{ .min_uV = 1850000, .min_sel = 31, .max_sel = 52, .uV_step = 50000 },
-	{ .min_uV = 3000000, .min_sel = 53, .max_sel = 55, .uV_step = 100000 },
-	{ .min_uV = 3300000, .min_sel = 56, .max_sel = 62, .uV_step = 0 },
+	REGULATOR_LINEAR_RANGE(900000, 0, 24, 25000),
+	REGULATOR_LINEAR_RANGE(1550000, 25, 30, 50000),
+	REGULATOR_LINEAR_RANGE(1850000, 31, 52, 50000),
+	REGULATOR_LINEAR_RANGE(3000000, 53, 55, 100000),
+	REGULATOR_LINEAR_RANGE(3300000, 56, 62, 0),
 };
 
 static const struct regulator_linear_range tps65217_uv2_ranges[] = {
-	{ .min_uV = 1500000, .min_sel =  0, .max_sel = 8, .uV_step = 50000 },
-	{ .min_uV = 2000000, .min_sel = 9, .max_sel = 13, .uV_step = 100000 },
-	{ .min_uV = 2450000, .min_sel = 14, .max_sel = 31, .uV_step = 50000 },
+	REGULATOR_LINEAR_RANGE(1500000, 0, 8, 50000),
+	REGULATOR_LINEAR_RANGE(2000000, 9, 13, 100000),
+	REGULATOR_LINEAR_RANGE(2450000, 14, 31, 50000),
 };
 
 static int tps65217_pmic_enable(struct regulator_dev *dev)
diff --git a/drivers/regulator/tps65912-regulator.c b/drivers/regulator/tps65912-regulator.c
index 9fc87d8c9ce5..697eab8e74d8 100644
--- a/drivers/regulator/tps65912-regulator.c
+++ b/drivers/regulator/tps65912-regulator.c
@@ -119,9 +119,9 @@ struct tps65912_reg {
 };
 
 static const struct regulator_linear_range tps65912_ldo_ranges[] = {
-	{ .min_uV = 800000, .min_sel =  0, .max_sel = 32, .uV_step = 25000 },
-	{ .min_uV = 1650000, .min_sel = 33, .max_sel = 60, .uV_step = 50000 },
-	{ .min_uV = 3100000, .min_sel = 61, .max_sel = 63, .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(800000, 0, 32, 25000),
+	REGULATOR_LINEAR_RANGE(1650000, 33, 60, 50000),
+	REGULATOR_LINEAR_RANGE(3100000, 61, 63, 100000),
 };
 
 static int tps65912_get_range(struct tps65912_reg *pmic, int id)
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index a95814027b24..9111b651c353 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -63,8 +63,8 @@ static irqreturn_t wm831x_ldo_uv_irq(int irq, void *data)
  */
 
 static const struct regulator_linear_range wm831x_gp_ldo_ranges[] = {
-	{ .min_uV =  900000, .min_sel =  0, .max_sel = 14, .uV_step =  50000 },
-	{ .min_uV = 1700000, .min_sel = 15, .max_sel = 31, .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(900000, 0, 14, 50000),
+	REGULATOR_LINEAR_RANGE(1700000, 15, 31, 100000),
 };
 
 static int wm831x_gp_ldo_set_suspend_voltage(struct regulator_dev *rdev,
@@ -330,8 +330,8 @@ static struct platform_driver wm831x_gp_ldo_driver = {
  */
 
 static const struct regulator_linear_range wm831x_aldo_ranges[] = {
-	{ .min_uV = 1000000, .min_sel =  0, .max_sel = 12, .uV_step =  50000 },
-	{ .min_uV = 1700000, .min_sel = 13, .max_sel = 31, .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(1000000, 0, 12, 50000),
+	REGULATOR_LINEAR_RANGE(1700000, 13, 31, 100000),
 };
 
 static int wm831x_aldo_set_suspend_voltage(struct regulator_dev *rdev,
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index de9de26d0bfc..3827539f3ad7 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -543,8 +543,8 @@ static int wm8350_dcdc_set_suspend_mode(struct regulator_dev *rdev,
 }
 
 static const struct regulator_linear_range wm8350_ldo_ranges[] = {
-	{ .min_uV =  900000, .min_sel =  0, .max_sel = 15, .uV_step =  50000 },
-	{ .min_uV = 1800000, .min_sel = 16, .max_sel = 31, .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(900000, 0, 15, 50000),
+	REGULATOR_LINEAR_RANGE(1800000, 16, 31, 100000),
 };
 
 static int wm8350_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV)
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index 3352b2090ed5..8eedba2953f9 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -20,8 +20,8 @@
 #include <linux/mfd/wm8400-private.h>
 
 static const struct regulator_linear_range wm8400_ldo_ranges[] = {
-	{ .min_uV =  900000, .min_sel = 0, .max_sel = 14, .uV_step =  50000 },
-	{ .min_uV = 1700000, .min_sel = 15, .max_sel = 31, .uV_step = 100000 },
+	REGULATOR_LINEAR_RANGE(900000, 0, 14, 50000),
+	REGULATOR_LINEAR_RANGE(1700000, 15, 31, 100000),
 };
 
 static struct regulator_ops wm8400_ldo_ops = {
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 997ff5c4d880..edb11b716dd3 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -57,6 +57,15 @@ struct regulator_linear_range {
 	unsigned int uV_step;
 };
 
+/* Initialize struct regulator_linear_range */
+#define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)	\
+{									\
+	.min_uV		= _min_uV,					\
+	.min_sel	= _min_sel,					\
+	.max_sel	= _max_sel,					\
+	.uV_step	= _step_uV,					\
+}
+
 /**
  * struct regulator_ops - regulator operations.
  *
-- 
cgit 


From c01fc9ada926aaad907989ca2eba40c2a2a73afe Mon Sep 17 00:00:00 2001
From: Sunil Dutt <c_duttus@qti.qualcomm.com>
Date: Wed, 9 Oct 2013 20:45:21 +0530
Subject: cfg80211: pass station supported channel and oper class info

The information of the peer's supported channels and supported operating
classes are required for the driver to perform TDLS off channel
operations. This commit enhances the function nl80211_(new)set_station
to pass this information of the peer to the driver.

Signed-off-by: Sunil Dutt <c_duttus@qti.qualcomm.com>
[return errors for malformed tuples]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  8 ++++++++
 include/uapi/linux/nl80211.h |  9 +++++++++
 net/wireless/nl80211.c       | 46 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 45f6bf591104..5db5fe24eff6 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -744,6 +744,10 @@ enum station_parameters_apply_mask {
  * @capability: station capability
  * @ext_capab: extended capabilities of the station
  * @ext_capab_len: number of extended capabilities
+ * @supported_channels: supported channels in IEEE 802.11 format
+ * @supported_channels_len: number of supported channels
+ * @supported_oper_classes: supported oper classes in IEEE 802.11 format
+ * @supported_oper_classes_len: number of supported operating classes
  */
 struct station_parameters {
 	const u8 *supported_rates;
@@ -763,6 +767,10 @@ struct station_parameters {
 	u16 capability;
 	const u8 *ext_capab;
 	u8 ext_capab_len;
+	const u8 *supported_channels;
+	u8 supported_channels_len;
+	const u8 *supported_oper_classes;
+	u8 supported_oper_classes_len;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 8c0417c222c6..f2aef2a7a570 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1496,6 +1496,11 @@ enum nl80211_commands {
  * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32.
  *	As specified in the &enum nl80211_rxmgmt_flags.
  *
+ * @NL80211_ATTR_STA_SUPPORTED_CHANNELS: array of supported channels.
+ *
+ * @NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES: array of supported
+ *      supported operating classes.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1806,6 +1811,10 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_RXMGMT_FLAGS,
 
+	NL80211_ATTR_STA_SUPPORTED_CHANNELS,
+
+	NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2838206ddad3..460638ac2d73 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -354,6 +354,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED },
 	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_U16 },
 	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_U16 },
+	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
+	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
 };
 
 /* policy for the key attributes */
@@ -3896,9 +3898,45 @@ static int nl80211_parse_sta_wme(struct genl_info *info,
 	return 0;
 }
 
+static int nl80211_parse_sta_channel_info(struct genl_info *info,
+				      struct station_parameters *params)
+{
+	if (info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]) {
+		params->supported_channels =
+		     nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]);
+		params->supported_channels_len =
+		     nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]);
+		/*
+		 * Need to include at least one (first channel, number of
+		 * channels) tuple for each subband, and must have proper
+		 * tuples for the rest of the data as well.
+		 */
+		if (params->supported_channels_len < 2)
+			return -EINVAL;
+		if (params->supported_channels_len % 2)
+			return -EINVAL;
+	}
+
+	if (info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]) {
+		params->supported_oper_classes =
+		 nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]);
+		params->supported_oper_classes_len =
+		  nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]);
+		/*
+		 * The value of the Length field of the Supported Operating
+		 * Classes element is between 2 and 253.
+		 */
+		if (params->supported_oper_classes_len < 2 ||
+		    params->supported_oper_classes_len > 253)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int nl80211_set_station_tdls(struct genl_info *info,
 				    struct station_parameters *params)
 {
+	int err;
 	/* Dummy STA entry gets updated once the peer capabilities are known */
 	if (info->attrs[NL80211_ATTR_PEER_AID])
 		params->aid = nla_get_u16(info->attrs[NL80211_ATTR_PEER_AID]);
@@ -3909,6 +3947,10 @@ static int nl80211_set_station_tdls(struct genl_info *info,
 		params->vht_capa =
 			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
 
+	err = nl80211_parse_sta_channel_info(info, params);
+	if (err)
+		return err;
+
 	return nl80211_parse_sta_wme(info, params);
 }
 
@@ -4089,6 +4131,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 	}
 
+	err = nl80211_parse_sta_channel_info(info, &params);
+	if (err)
+		return err;
+
 	err = nl80211_parse_sta_wme(info, &params);
 	if (err)
 		return err;
-- 
cgit 


From 7bd8f09f69f8a190f9b8334a07bb0a9237612314 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 11 Oct 2013 06:19:18 -0700
Subject: Bluetooth: Add hdev parameter to hdev->send driver callback

Instead of masking hdev inside the skb->dev parameter, hand it
directly to the driver as a parameter to hdev->send. This makes
the driver interface more clear and simpler.

This patch fixes all drivers to accept and handle the new parameter
of hdev->send callback. Special care has been taken for bpa10x
and btusb drivers that require having skb->dev set to hdev for
the URB transmit complete handlers.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 drivers/bluetooth/bfusb.c        | 3 +--
 drivers/bluetooth/bluecard_cs.c  | 3 +--
 drivers/bluetooth/bpa10x.c       | 5 +++--
 drivers/bluetooth/bt3c_cs.c      | 3 +--
 drivers/bluetooth/btmrvl_main.c  | 4 +---
 drivers/bluetooth/btsdio.c       | 3 +--
 drivers/bluetooth/btuart_cs.c    | 3 +--
 drivers/bluetooth/btusb.c        | 5 +++--
 drivers/bluetooth/btwilink.c     | 5 +----
 drivers/bluetooth/dtl1_cs.c      | 3 +--
 drivers/bluetooth/hci_ldisc.c    | 3 +--
 drivers/bluetooth/hci_ll.c       | 1 -
 drivers/bluetooth/hci_vhci.c     | 3 +--
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/hci_core.c         | 4 +---
 15 files changed, 18 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index b7b5bb879f08..a6758490fa61 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -464,9 +464,8 @@ static int bfusb_close(struct hci_dev *hdev)
 	return 0;
 }
 
-static int bfusb_send_frame(struct sk_buff *skb)
+static int bfusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	struct bfusb_data *data;
 	struct sk_buff *nskb;
 	unsigned char buf[3];
diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index 395acde99d78..9194a1ba897f 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -658,10 +658,9 @@ static int bluecard_hci_close(struct hci_dev *hdev)
 }
 
 
-static int bluecard_hci_send_frame(struct sk_buff *skb)
+static int bluecard_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	bluecard_info_t *info;
-	struct hci_dev *hdev = (struct hci_dev *)(skb->dev);
 
 	if (!hdev) {
 		BT_ERR("Frame for unknown HCI device (hdev=NULL)");
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index 3188fb48bf4b..b9e4e621fb10 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -350,9 +350,8 @@ static int bpa10x_flush(struct hci_dev *hdev)
 	return 0;
 }
 
-static int bpa10x_send_frame(struct sk_buff *skb)
+static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	struct bpa10x_data *data = hci_get_drvdata(hdev);
 	struct usb_ctrlrequest *dr;
 	struct urb *urb;
@@ -364,6 +363,8 @@ static int bpa10x_send_frame(struct sk_buff *skb)
 	if (!test_bit(HCI_RUNNING, &hdev->flags))
 		return -EBUSY;
 
+	skb->dev = (void *) hdev;
+
 	urb = usb_alloc_urb(0, GFP_ATOMIC);
 	if (!urb)
 		return -ENOMEM;
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index d8e4b0d7926e..fcd5fe993ad0 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -415,10 +415,9 @@ static int bt3c_hci_close(struct hci_dev *hdev)
 }
 
 
-static int bt3c_hci_send_frame(struct sk_buff *skb)
+static int bt3c_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	bt3c_info_t *info;
-	struct hci_dev *hdev = (struct hci_dev *)(skb->dev);
 	unsigned long flags;
 
 	if (!hdev) {
diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c
index 8ac4d938d89c..547a447149d3 100644
--- a/drivers/bluetooth/btmrvl_main.c
+++ b/drivers/bluetooth/btmrvl_main.c
@@ -187,7 +187,6 @@ static int btmrvl_send_sync_cmd(struct btmrvl_private *priv, u16 cmd_no,
 
 	bt_cb(skb)->pkt_type = MRVL_VENDOR_PKT;
 
-	skb->dev = (void *) priv->btmrvl_dev.hcidev;
 	skb_queue_head(&priv->adapter->tx_queue, skb);
 
 	priv->btmrvl_dev.sendcmdflag = true;
@@ -356,9 +355,8 @@ static void btmrvl_free_adapter(struct btmrvl_private *priv)
 	priv->adapter = NULL;
 }
 
-static int btmrvl_send_frame(struct sk_buff *skb)
+static int btmrvl_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	struct btmrvl_private *priv = NULL;
 
 	BT_DBG("type=%d, len=%d", skb->pkt_type, skb->len);
diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c
index 72fe49e60359..b61440aaee65 100644
--- a/drivers/bluetooth/btsdio.c
+++ b/drivers/bluetooth/btsdio.c
@@ -254,9 +254,8 @@ static int btsdio_flush(struct hci_dev *hdev)
 	return 0;
 }
 
-static int btsdio_send_frame(struct sk_buff *skb)
+static int btsdio_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	struct btsdio_data *data = hci_get_drvdata(hdev);
 
 	BT_DBG("%s", hdev->name);
diff --git a/drivers/bluetooth/btuart_cs.c b/drivers/bluetooth/btuart_cs.c
index d0b89ecf1c59..f567cd8424c3 100644
--- a/drivers/bluetooth/btuart_cs.c
+++ b/drivers/bluetooth/btuart_cs.c
@@ -423,10 +423,9 @@ static int btuart_hci_close(struct hci_dev *hdev)
 }
 
 
-static int btuart_hci_send_frame(struct sk_buff *skb)
+static int btuart_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	btuart_info_t *info;
-	struct hci_dev *hdev = (struct hci_dev *)(skb->dev);
 
 	if (!hdev) {
 		BT_ERR("Frame for unknown HCI device (hdev=NULL)");
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index faa429f7d8a1..621069cb3053 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -716,9 +716,8 @@ static int btusb_flush(struct hci_dev *hdev)
 	return 0;
 }
 
-static int btusb_send_frame(struct sk_buff *skb)
+static int btusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev = (struct hci_dev *) skb->dev;
 	struct btusb_data *data = hci_get_drvdata(hdev);
 	struct usb_ctrlrequest *dr;
 	struct urb *urb;
@@ -730,6 +729,8 @@ static int btusb_send_frame(struct sk_buff *skb)
 	if (!test_bit(HCI_RUNNING, &hdev->flags))
 		return -EBUSY;
 
+	skb->dev = (void *) hdev;
+
 	switch (bt_cb(skb)->pkt_type) {
 	case HCI_COMMAND_PKT:
 		urb = usb_alloc_urb(0, GFP_ATOMIC);
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index 5e10fb0a7e05..f038dba19e36 100644
--- a/drivers/bluetooth/btwilink.c
+++ b/drivers/bluetooth/btwilink.c
@@ -251,14 +251,11 @@ static int ti_st_close(struct hci_dev *hdev)
 	return err;
 }
 
-static int ti_st_send_frame(struct sk_buff *skb)
+static int ti_st_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev *hdev;
 	struct ti_st *hst;
 	long len;
 
-	hdev = (struct hci_dev *)skb->dev;
-
 	if (!test_bit(HCI_RUNNING, &hdev->flags))
 		return -EBUSY;
 
diff --git a/drivers/bluetooth/dtl1_cs.c b/drivers/bluetooth/dtl1_cs.c
index 29451413bc04..ad1a2f9dc772 100644
--- a/drivers/bluetooth/dtl1_cs.c
+++ b/drivers/bluetooth/dtl1_cs.c
@@ -382,10 +382,9 @@ static int dtl1_hci_close(struct hci_dev *hdev)
 }
 
 
-static int dtl1_hci_send_frame(struct sk_buff *skb)
+static int dtl1_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	dtl1_info_t *info;
-	struct hci_dev *hdev = (struct hci_dev *)(skb->dev);
 	struct sk_buff *s;
 	nsh_t nsh;
 
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index bc68a440d432..b04054675c48 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -234,9 +234,8 @@ static int hci_uart_close(struct hci_dev *hdev)
 }
 
 /* Send frames from HCI layer */
-static int hci_uart_send_frame(struct sk_buff *skb)
+static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev* hdev = (struct hci_dev *) skb->dev;
 	struct hci_uart *hu;
 
 	if (!hdev) {
diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index 58a9541feba6..69a90b1b5ff5 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -110,7 +110,6 @@ static int send_hcill_cmd(u8 cmd, struct hci_uart *hu)
 	/* prepare packet */
 	hcill_packet = (struct hcill_cmd *) skb_put(skb, 1);
 	hcill_packet->cmd = cmd;
-	skb->dev = (void *) hu->hdev;
 
 	/* send packet */
 	skb_queue_tail(&ll->txq, skb);
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 0fd522e85a71..e6f591969d95 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -81,9 +81,8 @@ static int vhci_flush(struct hci_dev *hdev)
 	return 0;
 }
 
-static int vhci_send_frame(struct sk_buff *skb)
+static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 {
-	struct hci_dev* hdev = (struct hci_dev *) skb->dev;
 	struct vhci_data *data;
 
 	if (!hdev) {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 29b81476424c..0e01dc257880 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -285,7 +285,7 @@ struct hci_dev {
 	int (*close)(struct hci_dev *hdev);
 	int (*flush)(struct hci_dev *hdev);
 	int (*setup)(struct hci_dev *hdev);
-	int (*send)(struct sk_buff *skb);
+	int (*send)(struct hci_dev *hdev, struct sk_buff *skb);
 	void (*notify)(struct hci_dev *hdev, unsigned int evt);
 };
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 4f0d4b443171..a097a623912a 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2713,9 +2713,7 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	/* Get rid of skb owner, prior to sending to the driver. */
 	skb_orphan(skb);
 
-	skb->dev = (void *) hdev;
-
-	if (hdev->send(skb) < 0)
+	if (hdev->send(hdev, skb) < 0)
 		BT_ERR("%s sending frame failed", hdev->name);
 }
 
-- 
cgit 


From bef64738e3fb87eabc6fbeededad0c44ea173384 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 11 Oct 2013 08:23:19 -0700
Subject: Bluetooth: Make LE scan interval and window a controller option

The scan interval and window for LE passive scanning and connection
establishment should be configurable on a per controller basis. So
introduce a setting that later on will allow modifying it.

This setting does not affect LE active scanning during device
discovery phase. As long as that phase uses interleaved discovery,
it will continuously scan.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 ++
 net/bluetooth/hci_conn.c         | 4 ++--
 net/bluetooth/hci_core.c         | 3 +++
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0e01dc257880..690045498420 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -164,6 +164,8 @@ struct hci_dev {
 	__u16		page_scan_interval;
 	__u16		page_scan_window;
 	__u8		page_scan_type;
+	__u16		le_scan_interval;
+	__u16		le_scan_window;
 
 	__u16		devid_source;
 	__u16		devid_vendor;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 139587159200..c52bfb7e44fd 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -562,8 +562,8 @@ static int hci_create_le_conn(struct hci_conn *conn)
 	hci_req_init(&req, hdev);
 
 	memset(&cp, 0, sizeof(cp));
-	cp.scan_interval = __constant_cpu_to_le16(0x0060);
-	cp.scan_window = __constant_cpu_to_le16(0x0030);
+	cp.scan_interval = cpu_to_le16(hdev->le_scan_interval);
+	cp.scan_window = cpu_to_le16(hdev->le_scan_window);
 	bacpy(&cp.peer_addr, &conn->dst);
 	cp.peer_addr_type = conn->dst_type;
 	if (bacmp(&hdev->bdaddr, BDADDR_ANY))
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index a097a623912a..1910dc2d33cf 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2273,6 +2273,9 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->sniff_max_interval = 800;
 	hdev->sniff_min_interval = 80;
 
+	hdev->le_scan_interval = 0x0060;
+	hdev->le_scan_window = 0x0030;
+
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
 
-- 
cgit 


From 14b49b9a49f0d80ef9a3ce7991b373f93016f5e4 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 11 Oct 2013 08:23:20 -0700
Subject: Bluetooth: Add management command for setting LE scan parameters

The scan interval and window parameters are used for LE passive
background scanning and connection establishment. This allows
userspace to change the values.

These two values should be kept in sync with whatever is used for
the scan parameters service on remote devices. And it puts the
controlling daemon (for example bluetoothd) in charge of setting
the values.

Main use case would be to switch between two sets of values. One
for foreground applications and one for background applications.

At this moment, the values are only used for manual connection
establishment, but soon that should be extended to background
scanning and automatic connection establishment.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/mgmt.h |  7 +++++++
 net/bluetooth/mgmt.c         | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 2ad433bb9a2e..518c5c84e39a 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -362,6 +362,13 @@ struct mgmt_cp_set_static_address {
 } __packed;
 #define MGMT_SET_STATIC_ADDRESS_SIZE	6
 
+#define MGMT_OP_SET_SCAN_PARAMS		0x002C
+struct mgmt_cp_set_scan_params {
+	__le16	interval;
+	__le16	window;
+} __packed;
+#define MGMT_SET_SCAN_PARAMS_SIZE	4
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 143dd7319981..f57ec19547af 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3374,6 +3374,43 @@ static int set_static_address(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
+static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
+			   void *data, u16 len)
+{
+	struct mgmt_cp_set_scan_params *cp = data;
+	__u16 interval, window;
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	if (!lmp_le_capable(hdev))
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				  MGMT_STATUS_NOT_SUPPORTED);
+
+	interval = __le16_to_cpu(cp->interval);
+
+	if (interval < 0x0004 || interval > 0x4000)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	window = __le16_to_cpu(cp->window);
+
+	if (window < 0x0004 || window > 0x4000)
+		return cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
+				  MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	hdev->le_scan_interval = interval;
+	hdev->le_scan_window = window;
+
+	err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0);
+
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
 {
 	struct pending_cmd *cmd;
@@ -3710,6 +3747,7 @@ static const struct mgmt_handler {
 	{ set_advertising,        false, MGMT_SETTING_SIZE },
 	{ set_bredr,              false, MGMT_SETTING_SIZE },
 	{ set_static_address,     false, MGMT_SET_STATIC_ADDRESS_SIZE },
+	{ set_scan_params,        false, MGMT_SET_SCAN_PARAMS_SIZE },
 };
 
 
-- 
cgit 


From 2841a5fc375e9c573d10b82db30fa8a4cc25301c Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Sat, 5 Oct 2013 00:23:12 +0100
Subject: spi: Provide per-message prepare and unprepare operations

Many SPI drivers perform setup and tear down on every message, usually
doing things like DMA mapping the message. Provide hooks for them to use
to provide such operations.

This is of limited value for drivers that implement transfer_one_message()
but will be of much greater utility with future factoring out of standard
implementations of that function.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c       | 22 ++++++++++++++++++++++
 include/linux/spi/spi.h | 11 +++++++++++
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8bef0c9a7233..8a30c6b66a64 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -606,6 +606,18 @@ static void spi_pump_messages(struct kthread_work *work)
 
 	trace_spi_message_start(master->cur_msg);
 
+	if (master->prepare_message) {
+		ret = master->prepare_message(master, master->cur_msg);
+		if (ret) {
+			dev_err(&master->dev,
+				"failed to prepare message: %d\n", ret);
+			master->cur_msg->status = ret;
+			spi_finalize_current_message(master);
+			return;
+		}
+		master->cur_msg_prepared = true;
+	}
+
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
@@ -687,6 +699,7 @@ void spi_finalize_current_message(struct spi_master *master)
 {
 	struct spi_message *mesg;
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&master->queue_lock, flags);
 	mesg = master->cur_msg;
@@ -695,6 +708,15 @@ void spi_finalize_current_message(struct spi_master *master)
 	queue_kthread_work(&master->kworker, &master->pump_messages);
 	spin_unlock_irqrestore(&master->queue_lock, flags);
 
+	if (master->cur_msg_prepared && master->unprepare_message) {
+		ret = master->unprepare_message(master, mesg);
+		if (ret) {
+			dev_err(&master->dev,
+				"failed to unprepare message: %d\n", ret);
+		}
+	}
+	master->cur_msg_prepared = false;
+
 	mesg->state = NULL;
 	if (mesg->complete)
 		mesg->complete(mesg->context);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 887116dbce2c..000b50bee6c0 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -257,6 +257,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @queue_lock: spinlock to syncronise access to message queue
  * @queue: message queue
  * @cur_msg: the currently in-flight message
+ * @cur_msg_prepared: spi_prepare_message was called for the currently
+ *                    in-flight message
  * @busy: message pump is busy
  * @running: message pump is running
  * @rt: whether this queue is set to run as a realtime task
@@ -274,6 +276,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @unprepare_transfer_hardware: there are currently no more messages on the
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
+ * @prepare_message: set up the controller to transfer a single message,
+ *                   for example doing DMA mapping.  Called from threaded
+ *                   context.
+ * @unprepare_message: undo any work done by prepare_message().
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
@@ -388,11 +394,16 @@ struct spi_master {
 	bool				running;
 	bool				rt;
 	bool				auto_runtime_pm;
+	bool                            cur_msg_prepared;
 
 	int (*prepare_transfer_hardware)(struct spi_master *master);
 	int (*transfer_one_message)(struct spi_master *master,
 				    struct spi_message *mesg);
 	int (*unprepare_transfer_hardware)(struct spi_master *master);
+	int (*prepare_message)(struct spi_master *master,
+			       struct spi_message *message);
+	int (*unprepare_message)(struct spi_master *master,
+				 struct spi_message *message);
 
 	/* gpio chip select */
 	int			*cs_gpios;
-- 
cgit 


From b158935f70b9c156903338053216dd0adf7ce31c Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Sat, 5 Oct 2013 11:50:40 +0100
Subject: spi: Provide common spi_message processing loop

The loops which SPI controller drivers use to process the list of transfers
in a spi_message are typically very similar and have some error prone areas
such as the handling of /CS. Help simplify drivers by factoring this code
out into the core - if drivers provide a transfer_one() function instead
of a transfer_one_message() function the core will handle processing at the
message level.

/CS can be controlled by either setting cs_gpio or providing a set_cs
function. If this is not possible for hardware reasons then both can be
omitted and the driver should continue to implement manual /CS handling.

This is a first step in refactoring and it is expected that there will be
further enhancements, for example factoring out of the mapping of transfers
for DMA and the initiation and completion of interrupt driven transfers.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c          | 92 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/spi/spi.h    | 21 ++++++++++-
 include/trace/events/spi.h | 42 +++++++++++++++++++++
 3 files changed, 153 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8a30c6b66a64..85c18d8a86b3 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -526,6 +526,95 @@ int spi_register_board_info(struct spi_board_info const *info, unsigned n)
 
 /*-------------------------------------------------------------------------*/
 
+static void spi_set_cs(struct spi_device *spi, bool enable)
+{
+	if (spi->mode & SPI_CS_HIGH)
+		enable = !enable;
+
+	if (spi->cs_gpio >= 0)
+		gpio_set_value(spi->cs_gpio, !enable);
+	else if (spi->master->set_cs)
+		spi->master->set_cs(spi, !enable);
+}
+
+/*
+ * spi_transfer_one_message - Default implementation of transfer_one_message()
+ *
+ * This is a standard implementation of transfer_one_message() for
+ * drivers which impelment a transfer_one() operation.  It provides
+ * standard handling of delays and chip select management.
+ */
+static int spi_transfer_one_message(struct spi_master *master,
+				    struct spi_message *msg)
+{
+	struct spi_transfer *xfer;
+	bool cur_cs = true;
+	bool keep_cs = false;
+	int ret = 0;
+
+	spi_set_cs(msg->spi, true);
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		trace_spi_transfer_start(msg, xfer);
+
+		INIT_COMPLETION(master->xfer_completion);
+
+		ret = master->transfer_one(master, msg->spi, xfer);
+		if (ret < 0) {
+			dev_err(&msg->spi->dev,
+				"SPI transfer failed: %d\n", ret);
+			goto out;
+		}
+
+		if (ret > 0)
+			wait_for_completion(&master->xfer_completion);
+
+		trace_spi_transfer_stop(msg, xfer);
+
+		if (msg->status != -EINPROGRESS)
+			goto out;
+
+		if (xfer->delay_usecs)
+			udelay(xfer->delay_usecs);
+
+		if (xfer->cs_change) {
+			if (list_is_last(&xfer->transfer_list,
+					 &msg->transfers)) {
+				keep_cs = true;
+			} else {
+				cur_cs = !cur_cs;
+				spi_set_cs(msg->spi, cur_cs);
+			}
+		}
+
+		msg->actual_length += xfer->len;
+	}
+
+out:
+	if (ret != 0 || !keep_cs)
+		spi_set_cs(msg->spi, false);
+
+	if (msg->status == -EINPROGRESS)
+		msg->status = ret;
+
+	spi_finalize_current_message(master);
+
+	return ret;
+}
+
+/**
+ * spi_finalize_current_transfer - report completion of a transfer
+ *
+ * Called by SPI drivers using the core transfer_one_message()
+ * implementation to notify it that the current interrupt driven
+ * transfer has finised and the next one may be scheduled.
+ */
+void spi_finalize_current_transfer(struct spi_master *master)
+{
+	complete(&master->xfer_completion);
+}
+EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
+
 /**
  * spi_pump_messages - kthread work function which processes spi message queue
  * @work: pointer to kthread work struct contained in the master struct
@@ -836,6 +925,8 @@ static int spi_master_initialize_queue(struct spi_master *master)
 
 	master->queued = true;
 	master->transfer = spi_queued_transfer;
+	if (!master->transfer_one_message)
+		master->transfer_one_message = spi_transfer_one_message;
 
 	/* Initialize and start queue */
 	ret = spi_init_queue(master);
@@ -1242,6 +1333,7 @@ int spi_register_master(struct spi_master *master)
 	spin_lock_init(&master->bus_lock_spinlock);
 	mutex_init(&master->bus_lock_mutex);
 	master->bus_lock_flag = 0;
+	init_completion(&master->xfer_completion);
 
 	/* register the device, then userspace will see it.
 	 * registration fails if the bus ID is in use.
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 000b50bee6c0..da371ab5ebeb 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -23,6 +23,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/slab.h>
 #include <linux/kthread.h>
+#include <linux/completion.h>
 
 /*
  * INTERFACES between SPI master-side drivers and SPI infrastructure.
@@ -150,8 +151,7 @@ static inline void *spi_get_drvdata(struct spi_device *spi)
 }
 
 struct spi_message;
-
-
+struct spi_transfer;
 
 /**
  * struct spi_driver - Host side "protocol" driver
@@ -259,6 +259,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cur_msg: the currently in-flight message
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
+ * @xfer_completion: used by core tranfer_one_message()
  * @busy: message pump is busy
  * @running: message pump is running
  * @rt: whether this queue is set to run as a realtime task
@@ -276,9 +277,15 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @unprepare_transfer_hardware: there are currently no more messages on the
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
+ * @set_cs: assert or deassert chip select, true to assert.  May be called
+ *          from interrupt context.
  * @prepare_message: set up the controller to transfer a single message,
  *                   for example doing DMA mapping.  Called from threaded
  *                   context.
+ * @transfer_one: transfer a single spi_transfer. When the
+ *	          driver is finished with this transfer it must call
+ *	          spi_finalize_current_transfer() so the subsystem can issue
+ *                the next transfer
  * @unprepare_message: undo any work done by prepare_message().
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
@@ -395,6 +402,7 @@ struct spi_master {
 	bool				rt;
 	bool				auto_runtime_pm;
 	bool                            cur_msg_prepared;
+	struct completion               xfer_completion;
 
 	int (*prepare_transfer_hardware)(struct spi_master *master);
 	int (*transfer_one_message)(struct spi_master *master,
@@ -405,6 +413,14 @@ struct spi_master {
 	int (*unprepare_message)(struct spi_master *master,
 				 struct spi_message *message);
 
+	/*
+	 * These hooks are for drivers that use a generic implementation
+	 * of transfer_one_message() provied by the core.
+	 */
+	void (*set_cs)(struct spi_device *spi, bool enable);
+	int (*transfer_one)(struct spi_master *master, struct spi_device *spi,
+			    struct spi_transfer *transfer);
+
 	/* gpio chip select */
 	int			*cs_gpios;
 };
@@ -439,6 +455,7 @@ extern int spi_master_resume(struct spi_master *master);
 /* Calls the driver make to interact with the message queue */
 extern struct spi_message *spi_get_next_queued_message(struct spi_master *master);
 extern void spi_finalize_current_message(struct spi_master *master);
+extern void spi_finalize_current_transfer(struct spi_master *master);
 
 /* the spi driver core manages memory for the spi_master classdev */
 extern struct spi_master *
diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h
index 5e77e21f885a..7e02c983bbe2 100644
--- a/include/trace/events/spi.h
+++ b/include/trace/events/spi.h
@@ -108,6 +108,48 @@ TRACE_EVENT(spi_message_done,
                   (unsigned)__entry->actual, (unsigned)__entry->frame)
 );
 
+DECLARE_EVENT_CLASS(spi_transfer,
+
+	TP_PROTO(struct spi_message *msg, struct spi_transfer *xfer),
+
+	TP_ARGS(msg, xfer),
+
+	TP_STRUCT__entry(
+		__field(        int,            bus_num         )
+		__field(        int,            chip_select     )
+		__field(        struct spi_transfer *,   xfer   )
+		__field(        int,            len             )
+	),
+
+	TP_fast_assign(
+		__entry->bus_num = msg->spi->master->bus_num;
+		__entry->chip_select = msg->spi->chip_select;
+		__entry->xfer = xfer;
+		__entry->len = xfer->len;
+	),
+
+        TP_printk("spi%d.%d %p len=%d", (int)__entry->bus_num,
+		  (int)__entry->chip_select,
+		  (struct spi_message *)__entry->xfer,
+		  (int)__entry->len)
+);
+
+DEFINE_EVENT(spi_transfer, spi_transfer_start,
+
+	TP_PROTO(struct spi_message *msg, struct spi_transfer *xfer),
+
+	TP_ARGS(msg, xfer)
+
+);
+
+DEFINE_EVENT(spi_transfer, spi_transfer_stop,
+
+	TP_PROTO(struct spi_message *msg, struct spi_transfer *xfer),
+
+	TP_ARGS(msg, xfer)
+
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */
-- 
cgit 


From 9d34876f820d55c94bd0b2a2ed3d2e2976cbd997 Mon Sep 17 00:00:00 2001
From: Robert Love <robert.w.love@intel.com>
Date: Thu, 5 Sep 2013 07:47:27 +0000
Subject: libfcoe: Make fcoe_sysfs optional / fix fnic NULL exception

fnic doesn't use any of the create/destroy/enable/disable interfaces
either from the (legacy) module paramaters or the (new) fcoe_sysfs
interfaces. When fcoe_sysfs was introduced fnic wasn't changed since
it wasn't using the interfaces. libfcoe incorrectly assumed that that
all of its users were using fcoe_sysfs and when adding and deleting
FCFs would assume the existance of a fcoe_ctlr_device. fnic was not
allocating this structure because it doesn't care about the standard
user interfaces (fnic starts on link only). If/When libfcoe tried to use
the fcoe_ctlr_device's lock for the first time a NULL pointer exception
would be triggered.

Since fnic doesn't care about sysfs or user interfaces, the solution
is to drop libfcoe's assumption that all drivers are using fcoe_sysfs.

This patch accomplishes this by changing some of the structure
relationships.

We need a way to determine when a LLD is using fcoe_sysfs or not and
we can do that by checking for the existance of the fcoe_ctlr_device.
Prior to this patch, it was assumed that the fcoe_ctlr structure was
allocated with the fcoe_ctlr_device and immediately followed it in
memory. To reach the fcoe_ctlr_device we would simply go back in memory
from the fcoe_ctlr to get the fcoe_ctlr_device.

Since fnic doesn't allocate the fcoe_ctlr_device, we cannot keep that
assumption. This patch adds a pointer from the fcoe_ctlr to the
fcoe_ctlr_device. For bnx2fc and fcoe we will continue to allocate the
two structures together, but then we'll set the ctlr->cdev pointer
to point at the fcoe_ctlr_device. fnic will not change and will continue
to allocate the fcoe_ctlr itself, and ctlr->cdev will remain NULL.

When libfcoe adds fcoe_fcf's to the fcoe_ctlr it will check if ctlr->cdev
is set and only if so will it continue to interact with fcoe_sysfs.

Signed-off-by: Robert Love <robert.w.love@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Hiral Patel <hiralpat@cisco.com>
---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c |  1 +
 drivers/scsi/fcoe/fcoe.c          |  1 +
 drivers/scsi/fcoe/fcoe_ctlr.c     | 94 ++++++++++++++++++++++++++-------------
 include/scsi/libfcoe.h            |  7 ++-
 4 files changed, 71 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 69ac55495c1d..27f2cc4b97a5 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -1381,6 +1381,7 @@ struct bnx2fc_interface *bnx2fc_interface_create(struct bnx2fc_hba *hba,
 		return NULL;
 	}
 	ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+	ctlr->cdev = ctlr_dev;
 	interface = fcoe_ctlr_priv(ctlr);
 	dev_hold(netdev);
 	kref_init(&interface->kref);
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index dff40b2fccbd..8626988e12a5 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -408,6 +408,7 @@ static struct fcoe_interface *fcoe_interface_create(struct net_device *netdev,
 	}
 
 	ctlr = fcoe_ctlr_device_priv(ctlr_dev);
+	ctlr->cdev = ctlr_dev;
 	fcoe = fcoe_ctlr_priv(ctlr);
 
 	dev_hold(netdev);
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 692c6535fe75..75efdbc54ef8 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -160,10 +160,16 @@ void fcoe_ctlr_init(struct fcoe_ctlr *fip, enum fip_state mode)
 }
 EXPORT_SYMBOL(fcoe_ctlr_init);
 
+/**
+ * fcoe_sysfs_fcf_add() - Add a fcoe_fcf{,_device} to a fcoe_ctlr{,_device}
+ * @new: The newly discovered FCF
+ *
+ * Called with fip->ctlr_mutex held
+ */
 static int fcoe_sysfs_fcf_add(struct fcoe_fcf *new)
 {
 	struct fcoe_ctlr *fip = new->fip;
-	struct fcoe_ctlr_device *ctlr_dev = fcoe_ctlr_to_ctlr_dev(fip);
+	struct fcoe_ctlr_device *ctlr_dev;
 	struct fcoe_fcf_device *temp, *fcf_dev;
 	int rc = -ENOMEM;
 
@@ -174,8 +180,6 @@ static int fcoe_sysfs_fcf_add(struct fcoe_fcf *new)
 	if (!temp)
 		goto out;
 
-	mutex_lock(&ctlr_dev->lock);
-
 	temp->fabric_name = new->fabric_name;
 	temp->switch_name = new->switch_name;
 	temp->fc_map = new->fc_map;
@@ -185,55 +189,83 @@ static int fcoe_sysfs_fcf_add(struct fcoe_fcf *new)
 	temp->fka_period = new->fka_period;
 	temp->selected = 0; /* default to unselected */
 
-	fcf_dev = fcoe_fcf_device_add(ctlr_dev, temp);
-	if (unlikely(!fcf_dev))
-		goto unlock;
-
 	/*
-	 * The fcoe_sysfs layer can return a CONNECTED fcf that
-	 * has a priv (fcf was never deleted) or a CONNECTED fcf
-	 * that doesn't have a priv (fcf was deleted). However,
-	 * libfcoe will always delete FCFs before trying to add
-	 * them. This is ensured because both recv_adv and
-	 * age_fcfs are protected by the the fcoe_ctlr's mutex.
-	 * This means that we should never get a FCF with a
-	 * non-NULL priv pointer.
+	 * If ctlr_dev doesn't exist then it means we're a libfcoe user
+	 * who doesn't use fcoe_syfs and didn't allocate a fcoe_ctlr_device.
+	 * fnic would be an example of a driver with this behavior. In this
+	 * case we want to add the fcoe_fcf to the fcoe_ctlr list, but we
+	 * don't want to make sysfs changes.
 	 */
-	BUG_ON(fcf_dev->priv);
 
-	fcf_dev->priv = new;
-	new->fcf_dev = fcf_dev;
+	ctlr_dev = fcoe_ctlr_to_ctlr_dev(fip);
+	if (ctlr_dev) {
+		mutex_lock(&ctlr_dev->lock);
+		fcf_dev = fcoe_fcf_device_add(ctlr_dev, temp);
+		if (unlikely(!fcf_dev)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		/*
+		 * The fcoe_sysfs layer can return a CONNECTED fcf that
+		 * has a priv (fcf was never deleted) or a CONNECTED fcf
+		 * that doesn't have a priv (fcf was deleted). However,
+		 * libfcoe will always delete FCFs before trying to add
+		 * them. This is ensured because both recv_adv and
+		 * age_fcfs are protected by the the fcoe_ctlr's mutex.
+		 * This means that we should never get a FCF with a
+		 * non-NULL priv pointer.
+		 */
+		BUG_ON(fcf_dev->priv);
+
+		fcf_dev->priv = new;
+		new->fcf_dev = fcf_dev;
+		mutex_unlock(&ctlr_dev->lock);
+	}
 
 	list_add(&new->list, &fip->fcfs);
 	fip->fcf_count++;
 	rc = 0;
 
-unlock:
-	mutex_unlock(&ctlr_dev->lock);
-
 out:
 	kfree(temp);
 	return rc;
 }
 
+/**
+ * fcoe_sysfs_fcf_del() - Remove a fcoe_fcf{,_device} to a fcoe_ctlr{,_device}
+ * @new: The FCF to be removed
+ *
+ * Called with fip->ctlr_mutex held
+ */
 static void fcoe_sysfs_fcf_del(struct fcoe_fcf *new)
 {
 	struct fcoe_ctlr *fip = new->fip;
-	struct fcoe_ctlr_device *ctlr_dev = fcoe_ctlr_to_ctlr_dev(fip);
+	struct fcoe_ctlr_device *cdev;
 	struct fcoe_fcf_device *fcf_dev;
 
 	list_del(&new->list);
 	fip->fcf_count--;
 
-	mutex_lock(&ctlr_dev->lock);
-
-	fcf_dev = fcoe_fcf_to_fcf_dev(new);
-	WARN_ON(!fcf_dev);
-	new->fcf_dev = NULL;
-	fcoe_fcf_device_delete(fcf_dev);
-	kfree(new);
-
-	mutex_unlock(&ctlr_dev->lock);
+	/*
+	 * If ctlr_dev doesn't exist then it means we're a libfcoe user
+	 * who doesn't use fcoe_syfs and didn't allocate a fcoe_ctlr_device
+	 * or a fcoe_fcf_device.
+	 *
+	 * fnic would be an example of a driver with this behavior. In this
+	 * case we want to remove the fcoe_fcf from the fcoe_ctlr list (above),
+	 * but we don't want to make sysfs changes.
+	 */
+	cdev = fcoe_ctlr_to_ctlr_dev(fip);
+	if (cdev) {
+		mutex_lock(&cdev->lock);
+		fcf_dev = fcoe_fcf_to_fcf_dev(new);
+		WARN_ON(!fcf_dev);
+		new->fcf_dev = NULL;
+		fcoe_fcf_device_delete(fcf_dev);
+		kfree(new);
+		mutex_unlock(&cdev->lock);
+	}
 }
 
 /**
diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h
index 4427393115ea..de7e3ee60f0c 100644
--- a/include/scsi/libfcoe.h
+++ b/include/scsi/libfcoe.h
@@ -90,6 +90,7 @@ enum fip_state {
  * @lp:		   &fc_lport: libfc local port.
  * @sel_fcf:	   currently selected FCF, or NULL.
  * @fcfs:	   list of discovered FCFs.
+ * @cdev:          (Optional) pointer to sysfs fcoe_ctlr_device.
  * @fcf_count:	   number of discovered FCF entries.
  * @sol_time:	   time when a multicast solicitation was last sent.
  * @sel_time:	   time after which to select an FCF.
@@ -127,6 +128,7 @@ struct fcoe_ctlr {
 	struct fc_lport *lp;
 	struct fcoe_fcf *sel_fcf;
 	struct list_head fcfs;
+	struct fcoe_ctlr_device *cdev;
 	u16 fcf_count;
 	unsigned long sol_time;
 	unsigned long sel_time;
@@ -168,8 +170,11 @@ static inline void *fcoe_ctlr_priv(const struct fcoe_ctlr *ctlr)
 	return (void *)(ctlr + 1);
 }
 
+/*
+ * This assumes that the fcoe_ctlr (x) is allocated with the fcoe_ctlr_device.
+ */
 #define fcoe_ctlr_to_ctlr_dev(x)					\
-	(struct fcoe_ctlr_device *)(((struct fcoe_ctlr_device *)(x)) - 1)
+	(x)->cdev
 
 /**
  * struct fcoe_fcf - Fibre-Channel Forwarder
-- 
cgit 


From 9ef73dbdd0fc292d183e93cd1d4b21d1a66040d7 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 9 Oct 2013 17:01:40 +0200
Subject: usb-anchor: Ensure poisened gets initialized to 0

And do so in a way which ensures that any fields added in the future will
also get properly zero-ed.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index f726c39097e0..fa8bedf06c6e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1214,6 +1214,7 @@ struct usb_anchor {
 
 static inline void init_usb_anchor(struct usb_anchor *anchor)
 {
+	memset(anchor, 0, sizeof(*anchor));
 	INIT_LIST_HEAD(&anchor->urb_list);
 	init_waitqueue_head(&anchor->wait);
 	spin_lock_init(&anchor->lock);
-- 
cgit 


From 6ec4147e7bdbde168f5bce30de5984aa4f971b22 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 9 Oct 2013 17:01:41 +0200
Subject: usb-anchor: Delay usb_wait_anchor_empty_timeout wake up till
 completion is done

usb_wait_anchor_empty_timeout() should wait till the completion handler
has run. Both the zd1211rw driver and the uas driver (in its task mgmt) depend
on the completion handler having completed when usb_wait_anchor_empty_timeout()
returns, as they read state set by the completion handler after an
usb_wait_anchor_empty_timeout() call.

But __usb_hcd_giveback_urb() calls usb_unanchor_urb before calling the
completion handler. This is necessary as the completion handler may
re-submit and re-anchor the urb. But this introduces a race where the state
these drivers want to read has not been set yet by the completion handler
(this race is easily triggered with the uas task mgmt code).

I've considered adding an anchor_count to struct urb, which would be
incremented on anchor and decremented on unanchor, and then only actually
do the anchor / unanchor on 0 -> 1 and 1 -> 0 transtions, combined with
moving the unanchor call in hcd_giveback_urb to after calling the completion
handler. But this will only work if urb's are only re-anchored to the same
anchor as they were anchored to before the completion handler ran.

And at least one driver re-anchors to another anchor from the completion
handler (rtlwifi).

So I have come up with this patch instead, which adds the ability to
suspend wakeups of usb_wait_anchor_empty_timeout() waiters to the usb_anchor
functionality, and uses this in __usb_hcd_giveback_urb() to delay wake-ups
until the completion handler has run.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c |  3 +++
 drivers/usb/core/urb.c | 44 ++++++++++++++++++++++++++++++++++++++++++--
 include/linux/usb.h    |  3 +++
 3 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 460bb59cb655..149cdf129293 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1652,6 +1652,7 @@ int usb_hcd_unlink_urb (struct urb *urb, int status)
 static void __usb_hcd_giveback_urb(struct urb *urb)
 {
 	struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus);
+	struct usb_anchor *anchor = urb->anchor;
 	int status = urb->unlinked;
 	unsigned long flags;
 
@@ -1663,6 +1664,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 
 	unmap_urb_for_dma(hcd, urb);
 	usbmon_urb_complete(&hcd->self, urb, status);
+	usb_anchor_suspend_wakeups(anchor);
 	usb_unanchor_urb(urb);
 
 	/* pass ownership to the completion handler */
@@ -1682,6 +1684,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	urb->complete(urb);
 	local_irq_restore(flags);
 
+	usb_anchor_resume_wakeups(anchor);
 	atomic_dec(&urb->use_count);
 	if (unlikely(atomic_read(&urb->reject)))
 		wake_up(&usb_kill_urb_queue);
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index c12bc790a6a7..e62208356c89 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -138,13 +138,19 @@ void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor)
 }
 EXPORT_SYMBOL_GPL(usb_anchor_urb);
 
+static int usb_anchor_check_wakeup(struct usb_anchor *anchor)
+{
+	return atomic_read(&anchor->suspend_wakeups) == 0 &&
+		list_empty(&anchor->urb_list);
+}
+
 /* Callers must hold anchor->lock */
 static void __usb_unanchor_urb(struct urb *urb, struct usb_anchor *anchor)
 {
 	urb->anchor = NULL;
 	list_del(&urb->anchor_list);
 	usb_put_urb(urb);
-	if (list_empty(&anchor->urb_list))
+	if (usb_anchor_check_wakeup(anchor))
 		wake_up(&anchor->wait);
 }
 
@@ -845,6 +851,39 @@ void usb_unlink_anchored_urbs(struct usb_anchor *anchor)
 }
 EXPORT_SYMBOL_GPL(usb_unlink_anchored_urbs);
 
+/**
+ * usb_anchor_suspend_wakeups
+ * @anchor: the anchor you want to suspend wakeups on
+ *
+ * Call this to stop the last urb being unanchored from waking up any
+ * usb_wait_anchor_empty_timeout waiters. This is used in the hcd urb give-
+ * back path to delay waking up until after the completion handler has run.
+ */
+void usb_anchor_suspend_wakeups(struct usb_anchor *anchor)
+{
+	if (anchor)
+		atomic_inc(&anchor->suspend_wakeups);
+}
+EXPORT_SYMBOL_GPL(usb_anchor_suspend_wakeups);
+
+/**
+ * usb_anchor_resume_wakeups
+ * @anchor: the anchor you want to resume wakeups on
+ *
+ * Allow usb_wait_anchor_empty_timeout waiters to be woken up again, and
+ * wake up any current waiters if the anchor is empty.
+ */
+void usb_anchor_resume_wakeups(struct usb_anchor *anchor)
+{
+	if (!anchor)
+		return;
+
+	atomic_dec(&anchor->suspend_wakeups);
+	if (usb_anchor_check_wakeup(anchor))
+		wake_up(&anchor->wait);
+}
+EXPORT_SYMBOL_GPL(usb_anchor_resume_wakeups);
+
 /**
  * usb_wait_anchor_empty_timeout - wait for an anchor to be unused
  * @anchor: the anchor you want to become unused
@@ -858,7 +897,8 @@ EXPORT_SYMBOL_GPL(usb_unlink_anchored_urbs);
 int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor,
 				  unsigned int timeout)
 {
-	return wait_event_timeout(anchor->wait, list_empty(&anchor->urb_list),
+	return wait_event_timeout(anchor->wait,
+				  usb_anchor_check_wakeup(anchor),
 				  msecs_to_jiffies(timeout));
 }
 EXPORT_SYMBOL_GPL(usb_wait_anchor_empty_timeout);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index fa8bedf06c6e..055ba74bee80 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1209,6 +1209,7 @@ struct usb_anchor {
 	struct list_head urb_list;
 	wait_queue_head_t wait;
 	spinlock_t lock;
+	atomic_t suspend_wakeups;
 	unsigned int poisoned:1;
 };
 
@@ -1575,6 +1576,8 @@ extern void usb_kill_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_poison_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_unpoison_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor);
+extern void usb_anchor_suspend_wakeups(struct usb_anchor *anchor);
+extern void usb_anchor_resume_wakeups(struct usb_anchor *anchor);
 extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
 extern void usb_unanchor_urb(struct urb *urb);
 extern int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor,
-- 
cgit 


From 63fb3a280061c5a1d9190015e5a074213f9d23c0 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Fri, 11 Oct 2013 11:28:02 -0400
Subject: USB: NS_TO_US should round up

Host controller drivers use the NS_TO_US macro to convert transaction
times, which are computed in nanoseconds, to microseconds for
scheduling.  Periodic scheduling requires worst-case estimates, but
the macro does its conversion using round-to-nearest.  This patch
changes it to use round-up, giving a correct worst-case value.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/hcd.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index fc64b6825f5e..dbe3cd19ffd8 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -564,9 +564,8 @@ extern void usb_ep0_reinit(struct usb_device *);
 		 * of (7/6 * 8 * bytecount) = 9.33 * bytecount */
 		/* bytecount = data payload byte count */
 
-#define NS_TO_US(ns)	((ns + 500L) / 1000L)
-			/* convert & round nanoseconds to microseconds */
-
+#define NS_TO_US(ns)	DIV_ROUND_UP(ns, 1000L)
+			/* convert nanoseconds to microseconds, rounding up */
 
 /*
  * Full/low speed bandwidth allocation constants/support.
-- 
cgit 


From 7c4bb942986fc2aa7ca4fccfed665d24525a0e21 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Fri, 11 Oct 2013 11:29:22 -0400
Subject: USB: add a private-data pointer to struct usb_tt

For improved scheduling of transfers through a Transaction Translator,
ehci-hcd will need to store a bunch of information associated with the
FS/LS bus on the downstream side of the TT.  This patch adds a pointer
for such HCD-private data to the usb_tt structure.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/hcd.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index dbe3cd19ffd8..b8aba196f7f1 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -506,6 +506,7 @@ struct usb_tt {
 	struct usb_device	*hub;	/* upstream highspeed hub */
 	int			multi;	/* true means one TT per port */
 	unsigned		think_time;	/* think time in ns */
+	void			*hcpriv;	/* HCD private data */
 
 	/* for control/bulk error recovery (CLEAR_TT_BUFFER) */
 	spinlock_t		lock;
-- 
cgit 


From 57ae1605c0f511bca212787d28d79a3f82c0a7f9 Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Thu, 10 Oct 2013 16:41:19 +0900
Subject: USB: ehci-s5p: Remove non-DT support

The non-DT for EXYNOS SoCs is not supported from v3.11.
Thus, there is no need to support non-DT for Exynos EHCI driver.

The 'include/linux/platform_data/usb-ehci-s5p.h' file has been
used for non-DT support. Thus, the 'usb-ehci-s5p.h' file can
be removed.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ehci-s5p.c                | 32 ++++--------------------------
 include/linux/platform_data/usb-ehci-s5p.h | 21 --------------------
 2 files changed, 4 insertions(+), 49 deletions(-)
 delete mode 100644 include/linux/platform_data/usb-ehci-s5p.h

(limited to 'include')

diff --git a/drivers/usb/host/ehci-s5p.c b/drivers/usb/host/ehci-s5p.c
index 7c3de95c7054..45e1ad3f56b2 100644
--- a/drivers/usb/host/ehci-s5p.c
+++ b/drivers/usb/host/ehci-s5p.c
@@ -20,7 +20,6 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/platform_device.h>
-#include <linux/platform_data/usb-ehci-s5p.h>
 #include <linux/usb/phy.h>
 #include <linux/usb/samsung_usb_phy.h>
 #include <linux/usb.h>
@@ -47,11 +46,8 @@ struct s5p_ehci_hcd {
 	struct clk *clk;
 	struct usb_phy *phy;
 	struct usb_otg *otg;
-	struct s5p_ehci_platdata *pdata;
 };
 
-static struct s5p_ehci_platdata empty_platdata;
-
 #define to_s5p_ehci(hcd)      (struct s5p_ehci_hcd *)(hcd_to_ehci(hcd)->priv)
 
 static void s5p_setup_vbus_gpio(struct platform_device *pdev)
@@ -75,7 +71,6 @@ static void s5p_setup_vbus_gpio(struct platform_device *pdev)
 
 static int s5p_ehci_probe(struct platform_device *pdev)
 {
-	struct s5p_ehci_platdata *pdata = dev_get_platdata(&pdev->dev);
 	struct s5p_ehci_hcd *s5p_ehci;
 	struct usb_hcd *hcd;
 	struct ehci_hcd *ehci;
@@ -105,21 +100,14 @@ static int s5p_ehci_probe(struct platform_device *pdev)
 	s5p_ehci = to_s5p_ehci(hcd);
 
 	if (of_device_is_compatible(pdev->dev.of_node,
-					"samsung,exynos5440-ehci")) {
-		s5p_ehci->pdata = &empty_platdata;
+					"samsung,exynos5440-ehci"))
 		goto skip_phy;
-	}
 
 	phy = devm_usb_get_phy(&pdev->dev, USB_PHY_TYPE_USB2);
 	if (IS_ERR(phy)) {
-		/* Fallback to pdata */
-		if (!pdata) {
-			usb_put_hcd(hcd);
-			dev_warn(&pdev->dev, "no platform data or transceiver defined\n");
-			return -EPROBE_DEFER;
-		} else {
-			s5p_ehci->pdata = pdata;
-		}
+		usb_put_hcd(hcd);
+		dev_warn(&pdev->dev, "no platform data or transceiver defined\n");
+		return -EPROBE_DEFER;
 	} else {
 		s5p_ehci->phy = phy;
 		s5p_ehci->otg = phy->otg;
@@ -167,8 +155,6 @@ skip_phy:
 
 	if (s5p_ehci->phy)
 		usb_phy_init(s5p_ehci->phy);
-	else if (s5p_ehci->pdata->phy_init)
-		s5p_ehci->pdata->phy_init(pdev, USB_PHY_TYPE_HOST);
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = hcd->regs;
@@ -189,8 +175,6 @@ skip_phy:
 fail_add_hcd:
 	if (s5p_ehci->phy)
 		usb_phy_shutdown(s5p_ehci->phy);
-	else if (s5p_ehci->pdata->phy_exit)
-		s5p_ehci->pdata->phy_exit(pdev, USB_PHY_TYPE_HOST);
 fail_io:
 	clk_disable_unprepare(s5p_ehci->clk);
 fail_clk:
@@ -210,8 +194,6 @@ static int s5p_ehci_remove(struct platform_device *pdev)
 
 	if (s5p_ehci->phy)
 		usb_phy_shutdown(s5p_ehci->phy);
-	else if (s5p_ehci->pdata->phy_exit)
-		s5p_ehci->pdata->phy_exit(pdev, USB_PHY_TYPE_HOST);
 
 	clk_disable_unprepare(s5p_ehci->clk);
 
@@ -225,7 +207,6 @@ static int s5p_ehci_suspend(struct device *dev)
 {
 	struct usb_hcd *hcd = dev_get_drvdata(dev);
 	struct s5p_ehci_hcd *s5p_ehci = to_s5p_ehci(hcd);
-	struct platform_device *pdev = to_platform_device(dev);
 
 	bool do_wakeup = device_may_wakeup(dev);
 	int rc;
@@ -237,8 +218,6 @@ static int s5p_ehci_suspend(struct device *dev)
 
 	if (s5p_ehci->phy)
 		usb_phy_shutdown(s5p_ehci->phy);
-	else if (s5p_ehci->pdata->phy_exit)
-		s5p_ehci->pdata->phy_exit(pdev, USB_PHY_TYPE_HOST);
 
 	clk_disable_unprepare(s5p_ehci->clk);
 
@@ -249,7 +228,6 @@ static int s5p_ehci_resume(struct device *dev)
 {
 	struct usb_hcd *hcd = dev_get_drvdata(dev);
 	struct  s5p_ehci_hcd *s5p_ehci = to_s5p_ehci(hcd);
-	struct platform_device *pdev = to_platform_device(dev);
 
 	clk_prepare_enable(s5p_ehci->clk);
 
@@ -258,8 +236,6 @@ static int s5p_ehci_resume(struct device *dev)
 
 	if (s5p_ehci->phy)
 		usb_phy_init(s5p_ehci->phy);
-	else if (s5p_ehci->pdata->phy_init)
-		s5p_ehci->pdata->phy_init(pdev, USB_PHY_TYPE_HOST);
 
 	/* DMA burst Enable */
 	writel(EHCI_INSNREG00_ENABLE_DMA_BURST, EHCI_INSNREG00(hcd->regs));
diff --git a/include/linux/platform_data/usb-ehci-s5p.h b/include/linux/platform_data/usb-ehci-s5p.h
deleted file mode 100644
index 5f28cae18582..000000000000
--- a/include/linux/platform_data/usb-ehci-s5p.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2011 Samsung Electronics Co.Ltd
- * Author: Joonyoung Shim <jy0922.shim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __PLAT_SAMSUNG_EHCI_H
-#define __PLAT_SAMSUNG_EHCI_H __FILE__
-
-struct s5p_ehci_platdata {
-	int (*phy_init)(struct platform_device *pdev, int type);
-	int (*phy_exit)(struct platform_device *pdev, int type);
-};
-
-extern void s5p_ehci_set_platdata(struct s5p_ehci_platdata *pd);
-
-#endif /* __PLAT_SAMSUNG_EHCI_H */
-- 
cgit 


From 706cd17e8559c96dc883ba692c931f1ef31fbc5c Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Wed, 9 Oct 2013 17:01:12 +0200
Subject: USB: serial: export usb_serial_generic_write_start

Export usb_serial_generic_write_start which is needed when implementing
a custom resume function while still relying on the generic write
implementation.

Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/serial/generic.c | 3 ++-
 include/linux/usb/serial.h   | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 31f78290c0e4..2b01ec8651c2 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -129,7 +129,7 @@ int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port,
  *
  * Return: Zero on success or if busy, otherwise a negative errno value.
  */
-static int usb_serial_generic_write_start(struct usb_serial_port *port,
+int usb_serial_generic_write_start(struct usb_serial_port *port,
 							gfp_t mem_flags)
 {
 	struct urb *urb;
@@ -184,6 +184,7 @@ retry:
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(usb_serial_generic_write_start);
 
 /**
  * usb_serial_generic_write - generic write function
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index d528b8045150..704a1ab8240c 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -320,6 +320,8 @@ extern struct usb_serial_port *usb_serial_port_get_by_minor(unsigned int minor);
 extern void usb_serial_put(struct usb_serial *serial);
 extern int usb_serial_generic_open(struct tty_struct *tty,
 	struct usb_serial_port *port);
+extern int usb_serial_generic_write_start(struct usb_serial_port *port,
+							gfp_t mem_flags);
 extern int usb_serial_generic_write(struct tty_struct *tty,
 	struct usb_serial_port *port, const unsigned char *buf, int count);
 extern void usb_serial_generic_close(struct usb_serial_port *port);
-- 
cgit 


From 96f60e37dc66091bde8d5de136ff6fda09f2d799 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 15 Aug 2012 13:59:49 +0100
Subject: DRM: Armada: Add Armada DRM driver

This patch adds support for the pair of LCD controllers on the Marvell
Armada 510 SoCs.  This driver supports:
- multiple contiguous scanout buffers for video and graphics
- shm backed cacheable buffer objects for X pixmaps for Vivante GPU
  acceleration
- dual lcd0 and lcd1 crt operation
- video overlay on each LCD crt via DRM planes
- page flipping of the main scanout buffers
- DRM prime for buffer export/import

This driver is trivial to extend to other Armada SoCs.

Included in this commit is the core driver with no output support; output
support is platform and encoder driver dependent.

Tested-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/gpu/drm/Kconfig                 |   2 +
 drivers/gpu/drm/Makefile                |   1 +
 drivers/gpu/drm/armada/Kconfig          |  15 +
 drivers/gpu/drm/armada/Makefile         |   7 +
 drivers/gpu/drm/armada/armada_510.c     |  86 ++++
 drivers/gpu/drm/armada/armada_crtc.c    | 861 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/armada/armada_crtc.h    |  74 +++
 drivers/gpu/drm/armada/armada_debugfs.c | 183 +++++++
 drivers/gpu/drm/armada/armada_drm.h     | 112 +++++
 drivers/gpu/drm/armada/armada_drv.c     | 380 ++++++++++++++
 drivers/gpu/drm/armada/armada_fb.c      | 170 +++++++
 drivers/gpu/drm/armada/armada_fb.h      |  24 +
 drivers/gpu/drm/armada/armada_fbdev.c   | 202 ++++++++
 drivers/gpu/drm/armada/armada_gem.c     | 611 ++++++++++++++++++++++
 drivers/gpu/drm/armada/armada_gem.h     |  52 ++
 drivers/gpu/drm/armada/armada_hw.h      | 316 ++++++++++++
 drivers/gpu/drm/armada/armada_ioctlP.h  |  18 +
 drivers/gpu/drm/armada/armada_output.c  | 158 ++++++
 drivers/gpu/drm/armada/armada_output.h  |  39 ++
 drivers/gpu/drm/armada/armada_overlay.c | 477 ++++++++++++++++++
 drivers/gpu/drm/armada/armada_slave.c   | 139 ++++++
 drivers/gpu/drm/armada/armada_slave.h   |  26 +
 include/drm/drm_crtc.h                  |  17 +
 include/uapi/drm/armada_drm.h           |  45 ++
 24 files changed, 4015 insertions(+)
 create mode 100644 drivers/gpu/drm/armada/Kconfig
 create mode 100644 drivers/gpu/drm/armada/Makefile
 create mode 100644 drivers/gpu/drm/armada/armada_510.c
 create mode 100644 drivers/gpu/drm/armada/armada_crtc.c
 create mode 100644 drivers/gpu/drm/armada/armada_crtc.h
 create mode 100644 drivers/gpu/drm/armada/armada_debugfs.c
 create mode 100644 drivers/gpu/drm/armada/armada_drm.h
 create mode 100644 drivers/gpu/drm/armada/armada_drv.c
 create mode 100644 drivers/gpu/drm/armada/armada_fb.c
 create mode 100644 drivers/gpu/drm/armada/armada_fb.h
 create mode 100644 drivers/gpu/drm/armada/armada_fbdev.c
 create mode 100644 drivers/gpu/drm/armada/armada_gem.c
 create mode 100644 drivers/gpu/drm/armada/armada_gem.h
 create mode 100644 drivers/gpu/drm/armada/armada_hw.h
 create mode 100644 drivers/gpu/drm/armada/armada_ioctlP.h
 create mode 100644 drivers/gpu/drm/armada/armada_output.c
 create mode 100644 drivers/gpu/drm/armada/armada_output.h
 create mode 100644 drivers/gpu/drm/armada/armada_overlay.c
 create mode 100644 drivers/gpu/drm/armada/armada_slave.c
 create mode 100644 drivers/gpu/drm/armada/armada_slave.h
 create mode 100644 include/uapi/drm/armada_drm.h

(limited to 'include')

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 955555d6ec88..3b5176dd1c86 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -225,6 +225,8 @@ source "drivers/gpu/drm/mgag200/Kconfig"
 
 source "drivers/gpu/drm/cirrus/Kconfig"
 
+source "drivers/gpu/drm/armada/Kconfig"
+
 source "drivers/gpu/drm/rcar-du/Kconfig"
 
 source "drivers/gpu/drm/shmobile/Kconfig"
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index f089adfe70ee..385f460459d4 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -49,6 +49,7 @@ obj-$(CONFIG_DRM_EXYNOS) +=exynos/
 obj-$(CONFIG_DRM_GMA500) += gma500/
 obj-$(CONFIG_DRM_UDL) += udl/
 obj-$(CONFIG_DRM_AST) += ast/
+obj-$(CONFIG_DRM_ARMADA) += armada/
 obj-$(CONFIG_DRM_RCAR_DU) += rcar-du/
 obj-$(CONFIG_DRM_SHMOBILE) +=shmobile/
 obj-$(CONFIG_DRM_OMAP)	+= omapdrm/
diff --git a/drivers/gpu/drm/armada/Kconfig b/drivers/gpu/drm/armada/Kconfig
new file mode 100644
index 000000000000..c7a0a944acfe
--- /dev/null
+++ b/drivers/gpu/drm/armada/Kconfig
@@ -0,0 +1,15 @@
+config DRM_ARMADA
+	tristate "DRM support for Marvell Armada SoCs"
+	depends on DRM && HAVE_CLK
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	select DRM_KMS_HELPER
+	help
+	  Support the "LCD" controllers found on the Marvell Armada 510
+	  devices.  There are two controllers on the device, each controller
+	  supports graphics and video overlays.
+
+	  This driver provides no built-in acceleration; acceleration is
+	  performed by other IP found on the SoC.  This driver provides
+	  kernel mode setting and buffer management to userspace.
diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile
new file mode 100644
index 000000000000..d6f43e06150a
--- /dev/null
+++ b/drivers/gpu/drm/armada/Makefile
@@ -0,0 +1,7 @@
+armada-y	:= armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \
+		   armada_gem.o armada_output.o armada_overlay.o \
+		   armada_slave.o
+armada-y	+= armada_510.o
+armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o
+
+obj-$(CONFIG_DRM_ARMADA) := armada.o
diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c
new file mode 100644
index 000000000000..a016888acd29
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_510.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Armada 510 (aka Dove) variant support
+ */
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_hw.h"
+
+static int armada510_init(struct armada_private *priv, struct device *dev)
+{
+	priv->extclk[0] = devm_clk_get(dev, "ext_ref_clk_1");
+
+	if (IS_ERR(priv->extclk[0]) && PTR_ERR(priv->extclk[0]) == -ENOENT)
+		priv->extclk[0] = ERR_PTR(-EPROBE_DEFER);
+
+	return PTR_RET(priv->extclk[0]);
+}
+
+static int armada510_crtc_init(struct armada_crtc *dcrtc)
+{
+	/* Lower the watermark so to eliminate jitter at higher bandwidths */
+	armada_updatel(0x20, (1 << 11) | 0xff, dcrtc->base + LCD_CFG_RDREG4F);
+	return 0;
+}
+
+/*
+ * Armada510 specific SCLK register selection.
+ * This gets called with sclk = NULL to test whether the mode is
+ * supportable, and again with sclk != NULL to set the clocks up for
+ * that.  The former can return an error, but the latter is expected
+ * not to.
+ *
+ * We currently are pretty rudimentary here, always selecting
+ * EXT_REF_CLK_1 for LCD0 and erroring LCD1.  This needs improvement!
+ */
+static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc,
+	const struct drm_display_mode *mode, uint32_t *sclk)
+{
+	struct armada_private *priv = dcrtc->crtc.dev->dev_private;
+	struct clk *clk = priv->extclk[0];
+	int ret;
+
+	if (dcrtc->num == 1)
+		return -EINVAL;
+
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	if (dcrtc->clk != clk) {
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			return ret;
+		dcrtc->clk = clk;
+	}
+
+	if (sclk) {
+		uint32_t rate, ref, div;
+
+		rate = mode->clock * 1000;
+		ref = clk_round_rate(clk, rate);
+		div = DIV_ROUND_UP(ref, rate);
+		if (div < 1)
+			div = 1;
+
+		clk_set_rate(clk, ref);
+		*sclk = div | SCLK_510_EXTCLK1;
+	}
+
+	return 0;
+}
+
+const struct armada_variant armada510_ops = {
+	.has_spu_adv_reg = true,
+	.init = armada510_init,
+	.crtc_init = armada510_crtc_init,
+	.crtc_compute_clock = armada510_crtc_compute_clock,
+};
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
new file mode 100644
index 000000000000..7b379fdb4e8c
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -0,0 +1,861 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clk.h>
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+
+struct armada_frame_work {
+	struct drm_pending_vblank_event *event;
+	struct armada_regs regs[4];
+	struct drm_framebuffer *old_fb;
+};
+
+enum csc_mode {
+	CSC_AUTO = 0,
+	CSC_YUV_CCIR601 = 1,
+	CSC_YUV_CCIR709 = 2,
+	CSC_RGB_COMPUTER = 1,
+	CSC_RGB_STUDIO = 2,
+};
+
+/*
+ * A note about interlacing.  Let's consider HDMI 1920x1080i.
+ * The timing parameters we have from X are:
+ *  Hact HsyA HsyI Htot  Vact VsyA VsyI Vtot
+ *  1920 2448 2492 2640  1080 1084 1094 1125
+ * Which get translated to:
+ *  Hact HsyA HsyI Htot  Vact VsyA VsyI Vtot
+ *  1920 2448 2492 2640   540  542  547  562
+ *
+ * This is how it is defined by CEA-861-D - line and pixel numbers are
+ * referenced to the rising edge of VSYNC and HSYNC.  Total clocks per
+ * line: 2640.  The odd frame, the first active line is at line 21, and
+ * the even frame, the first active line is 584.
+ *
+ * LN:    560     561     562     563             567     568    569
+ * DE:    ~~~|____________________________//__________________________
+ * HSYNC: ____|~|_____|~|_____|~|_____|~|_//__|~|_____|~|_____|~|_____
+ * VSYNC: _________________________|~~~~~~//~~~~~~~~~~~~~~~|__________
+ *  22 blanking lines.  VSYNC at 1320 (referenced to the HSYNC rising edge).
+ *
+ * LN:    1123   1124    1125      1               5       6      7
+ * DE:    ~~~|____________________________//__________________________
+ * HSYNC: ____|~|_____|~|_____|~|_____|~|_//__|~|_____|~|_____|~|_____
+ * VSYNC: ____________________|~~~~~~~~~~~//~~~~~~~~~~|_______________
+ *  23 blanking lines
+ *
+ * The Armada LCD Controller line and pixel numbers are, like X timings,
+ * referenced to the top left of the active frame.
+ *
+ * So, translating these to our LCD controller:
+ *  Odd frame, 563 total lines, VSYNC at line 543-548, pixel 1128.
+ *  Even frame, 562 total lines, VSYNC at line 542-547, pixel 2448.
+ * Note: Vsync front porch remains constant!
+ *
+ * if (odd_frame) {
+ *   vtotal = mode->crtc_vtotal + 1;
+ *   vbackporch = mode->crtc_vsync_start - mode->crtc_vdisplay + 1;
+ *   vhorizpos = mode->crtc_hsync_start - mode->crtc_htotal / 2
+ * } else {
+ *   vtotal = mode->crtc_vtotal;
+ *   vbackporch = mode->crtc_vsync_start - mode->crtc_vdisplay;
+ *   vhorizpos = mode->crtc_hsync_start;
+ * }
+ * vfrontporch = mode->crtc_vtotal - mode->crtc_vsync_end;
+ *
+ * So, we need to reprogram these registers on each vsync event:
+ *  LCD_SPU_V_PORCH, LCD_SPU_ADV_REG, LCD_SPUT_V_H_TOTAL
+ *
+ * Note: we do not use the frame done interrupts because these appear
+ * to happen too early, and lead to jitter on the display (presumably
+ * they occur at the end of the last active line, before the vsync back
+ * porch, which we're reprogramming.)
+ */
+
+void
+armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs)
+{
+	while (regs->offset != ~0) {
+		void __iomem *reg = dcrtc->base + regs->offset;
+		uint32_t val;
+
+		val = regs->mask;
+		if (val != 0)
+			val &= readl_relaxed(reg);
+		writel_relaxed(val | regs->val, reg);
+		++regs;
+	}
+}
+
+#define dpms_blanked(dpms)	((dpms) != DRM_MODE_DPMS_ON)
+
+static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
+{
+	uint32_t dumb_ctrl;
+
+	dumb_ctrl = dcrtc->cfg_dumb_ctrl;
+
+	if (!dpms_blanked(dcrtc->dpms))
+		dumb_ctrl |= CFG_DUMB_ENA;
+
+	/*
+	 * When the dumb interface isn't in DUMB24_RGB888_0 mode, it might
+	 * be using SPI or GPIO.  If we set this to DUMB_BLANK, we will
+	 * force LCD_D[23:0] to output blank color, overriding the GPIO or
+	 * SPI usage.  So leave it as-is unless in DUMB24_RGB888_0 mode.
+	 */
+	if (dpms_blanked(dcrtc->dpms) &&
+	    (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
+		dumb_ctrl &= ~DUMB_MASK;
+		dumb_ctrl |= DUMB_BLANK;
+	}
+
+	/*
+	 * The documentation doesn't indicate what the normal state of
+	 * the sync signals are.  Sebastian Hesselbart kindly probed
+	 * these signals on his board to determine their state.
+	 *
+	 * The non-inverted state of the sync signals is active high.
+	 * Setting these bits makes the appropriate signal active low.
+	 */
+	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NCSYNC)
+		dumb_ctrl |= CFG_INV_CSYNC;
+	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NHSYNC)
+		dumb_ctrl |= CFG_INV_HSYNC;
+	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NVSYNC)
+		dumb_ctrl |= CFG_INV_VSYNC;
+
+	if (dcrtc->dumb_ctrl != dumb_ctrl) {
+		dcrtc->dumb_ctrl = dumb_ctrl;
+		writel_relaxed(dumb_ctrl, dcrtc->base + LCD_SPU_DUMB_CTRL);
+	}
+}
+
+static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
+	int x, int y, struct armada_regs *regs, bool interlaced)
+{
+	struct armada_gem_object *obj = drm_fb_obj(fb);
+	unsigned pitch = fb->pitches[0];
+	unsigned offset = y * pitch + x * fb->bits_per_pixel / 8;
+	uint32_t addr_odd, addr_even;
+	unsigned i = 0;
+
+	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
+		pitch, x, y, fb->bits_per_pixel);
+
+	addr_odd = addr_even = obj->dev_addr + offset;
+
+	if (interlaced) {
+		addr_even += pitch;
+		pitch *= 2;
+	}
+
+	/* write offset, base, and pitch */
+	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
+	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
+	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
+
+	return i;
+}
+
+static int armada_drm_crtc_queue_frame_work(struct armada_crtc *dcrtc,
+	struct armada_frame_work *work)
+{
+	struct drm_device *dev = dcrtc->crtc.dev;
+	unsigned long flags;
+	int ret;
+
+	ret = drm_vblank_get(dev, dcrtc->num);
+	if (ret) {
+		DRM_ERROR("failed to acquire vblank counter\n");
+		return ret;
+	}
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (!dcrtc->frame_work)
+		dcrtc->frame_work = work;
+	else
+		ret = -EBUSY;
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+
+	if (ret)
+		drm_vblank_put(dev, dcrtc->num);
+
+	return ret;
+}
+
+static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc)
+{
+	struct drm_device *dev = dcrtc->crtc.dev;
+	struct armada_frame_work *work = dcrtc->frame_work;
+
+	dcrtc->frame_work = NULL;
+
+	armada_drm_crtc_update_regs(dcrtc, work->regs);
+
+	if (work->event)
+		drm_send_vblank_event(dev, dcrtc->num, work->event);
+
+	drm_vblank_put(dev, dcrtc->num);
+
+	/* Finally, queue the process-half of the cleanup. */
+	__armada_drm_queue_unref_work(dcrtc->crtc.dev, work->old_fb);
+	kfree(work);
+}
+
+static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc,
+	struct drm_framebuffer *fb, bool force)
+{
+	struct armada_frame_work *work;
+
+	if (!fb)
+		return;
+
+	if (force) {
+		/* Display is disabled, so just drop the old fb */
+		drm_framebuffer_unreference(fb);
+		return;
+	}
+
+	work = kmalloc(sizeof(*work), GFP_KERNEL);
+	if (work) {
+		int i = 0;
+		work->event = NULL;
+		work->old_fb = fb;
+		armada_reg_queue_end(work->regs, i);
+
+		if (armada_drm_crtc_queue_frame_work(dcrtc, work) == 0)
+			return;
+
+		kfree(work);
+	}
+
+	/*
+	 * Oops - just drop the reference immediately and hope for
+	 * the best.  The worst that will happen is the buffer gets
+	 * reused before it has finished being displayed.
+	 */
+	drm_framebuffer_unreference(fb);
+}
+
+static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
+{
+	struct drm_device *dev = dcrtc->crtc.dev;
+
+	/*
+	 * Tell the DRM core that vblank IRQs aren't going to happen for
+	 * a while.  This cleans up any pending vblank events for us.
+	 */
+	drm_vblank_off(dev, dcrtc->num);
+
+	/* Handle any pending flip event. */
+	spin_lock_irq(&dev->event_lock);
+	if (dcrtc->frame_work)
+		armada_drm_crtc_complete_frame_work(dcrtc);
+	spin_unlock_irq(&dev->event_lock);
+}
+
+void armada_drm_crtc_gamma_set(struct drm_crtc *crtc, u16 r, u16 g, u16 b,
+	int idx)
+{
+}
+
+void armada_drm_crtc_gamma_get(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
+	int idx)
+{
+}
+
+/* The mode_config.mutex will be held for this call */
+static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+
+	if (dcrtc->dpms != dpms) {
+		dcrtc->dpms = dpms;
+		armada_drm_crtc_update(dcrtc);
+		if (dpms_blanked(dpms))
+			armada_drm_vblank_off(dcrtc);
+	}
+}
+
+/*
+ * Prepare for a mode set.  Turn off overlay to ensure that we don't end
+ * up with the overlay size being bigger than the active screen size.
+ * We rely upon X refreshing this state after the mode set has completed.
+ *
+ * The mode_config.mutex will be held for this call
+ */
+static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_plane *plane;
+
+	/*
+	 * If we have an overlay plane associated with this CRTC, disable
+	 * it before the modeset to avoid its coordinates being outside
+	 * the new mode parameters.  DRM doesn't provide help with this.
+	 */
+	plane = dcrtc->plane;
+	if (plane) {
+		struct drm_framebuffer *fb = plane->fb;
+
+		plane->funcs->disable_plane(plane);
+		plane->fb = NULL;
+		plane->crtc = NULL;
+		drm_framebuffer_unreference(fb);
+	}
+}
+
+/* The mode_config.mutex will be held for this call */
+static void armada_drm_crtc_commit(struct drm_crtc *crtc)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+
+	if (dcrtc->dpms != DRM_MODE_DPMS_ON) {
+		dcrtc->dpms = DRM_MODE_DPMS_ON;
+		armada_drm_crtc_update(dcrtc);
+	}
+}
+
+/* The mode_config.mutex will be held for this call */
+static bool armada_drm_crtc_mode_fixup(struct drm_crtc *crtc,
+	const struct drm_display_mode *mode, struct drm_display_mode *adj)
+{
+	struct armada_private *priv = crtc->dev->dev_private;
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	int ret;
+
+	/* We can't do interlaced modes if we don't have the SPU_ADV_REG */
+	if (!priv->variant->has_spu_adv_reg &&
+	    adj->flags & DRM_MODE_FLAG_INTERLACE)
+		return false;
+
+	/* Check whether the display mode is possible */
+	ret = priv->variant->crtc_compute_clock(dcrtc, adj, NULL);
+	if (ret)
+		return false;
+
+	return true;
+}
+
+void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
+{
+	struct armada_vbl_event *e, *n;
+	void __iomem *base = dcrtc->base;
+
+	if (stat & DMA_FF_UNDERFLOW)
+		DRM_ERROR("video underflow on crtc %u\n", dcrtc->num);
+	if (stat & GRA_FF_UNDERFLOW)
+		DRM_ERROR("graphics underflow on crtc %u\n", dcrtc->num);
+
+	if (stat & VSYNC_IRQ)
+		drm_handle_vblank(dcrtc->crtc.dev, dcrtc->num);
+
+	spin_lock(&dcrtc->irq_lock);
+
+	list_for_each_entry_safe(e, n, &dcrtc->vbl_list, node) {
+		list_del_init(&e->node);
+		drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+		e->fn(dcrtc, e->data);
+	}
+
+	if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) {
+		int i = stat & GRA_FRAME_IRQ0 ? 0 : 1;
+		uint32_t val;
+
+		writel_relaxed(dcrtc->v[i].spu_v_porch, base + LCD_SPU_V_PORCH);
+		writel_relaxed(dcrtc->v[i].spu_v_h_total,
+			       base + LCD_SPUT_V_H_TOTAL);
+
+		val = readl_relaxed(base + LCD_SPU_ADV_REG);
+		val &= ~(ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF | ADV_VSYNCOFFEN);
+		val |= dcrtc->v[i].spu_adv_reg;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_ADV_REG);
+	}
+	spin_unlock(&dcrtc->irq_lock);
+
+	if (stat & GRA_FRAME_IRQ) {
+		struct drm_device *dev = dcrtc->crtc.dev;
+
+		spin_lock(&dev->event_lock);
+		if (dcrtc->frame_work)
+			armada_drm_crtc_complete_frame_work(dcrtc);
+		spin_unlock(&dev->event_lock);
+
+		wake_up(&dcrtc->frame_wait);
+	}
+}
+
+/* These are locked by dev->vbl_lock */
+void armada_drm_crtc_disable_irq(struct armada_crtc *dcrtc, u32 mask)
+{
+	if (dcrtc->irq_ena & mask) {
+		dcrtc->irq_ena &= ~mask;
+		writel(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+	}
+}
+
+void armada_drm_crtc_enable_irq(struct armada_crtc *dcrtc, u32 mask)
+{
+	if ((dcrtc->irq_ena & mask) != mask) {
+		dcrtc->irq_ena |= mask;
+		writel(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+		if (readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR) & mask)
+			writel(0, dcrtc->base + LCD_SPU_IRQ_ISR);
+	}
+}
+
+static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
+{
+	struct drm_display_mode *adj = &dcrtc->crtc.mode;
+	uint32_t val = 0;
+
+	if (dcrtc->csc_yuv_mode == CSC_YUV_CCIR709)
+		val |= CFG_CSC_YUV_CCIR709;
+	if (dcrtc->csc_rgb_mode == CSC_RGB_STUDIO)
+		val |= CFG_CSC_RGB_STUDIO;
+
+	/*
+	 * In auto mode, set the colorimetry, based upon the HDMI spec.
+	 * 1280x720p, 1920x1080p and 1920x1080i use ITU709, others use
+	 * ITU601.  It may be more appropriate to set this depending on
+	 * the source - but what if the graphic frame is YUV and the
+	 * video frame is RGB?
+	 */
+	if ((adj->hdisplay == 1280 && adj->vdisplay == 720 &&
+	     !(adj->flags & DRM_MODE_FLAG_INTERLACE)) ||
+	    (adj->hdisplay == 1920 && adj->vdisplay == 1080)) {
+		if (dcrtc->csc_yuv_mode == CSC_AUTO)
+			val |= CFG_CSC_YUV_CCIR709;
+	}
+
+	/*
+	 * We assume we're connected to a TV-like device, so the YUV->RGB
+	 * conversion should produce a limited range.  We should set this
+	 * depending on the connectors attached to this CRTC, and what
+	 * kind of device they report being connected.
+	 */
+	if (dcrtc->csc_rgb_mode == CSC_AUTO)
+		val |= CFG_CSC_RGB_STUDIO;
+
+	return val;
+}
+
+/* The mode_config.mutex will be held for this call */
+static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
+	struct drm_display_mode *mode, struct drm_display_mode *adj,
+	int x, int y, struct drm_framebuffer *old_fb)
+{
+	struct armada_private *priv = crtc->dev->dev_private;
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_regs regs[17];
+	uint32_t lm, rm, tm, bm, val, sclk;
+	unsigned long flags;
+	unsigned i;
+	bool interlaced;
+
+	drm_framebuffer_reference(crtc->fb);
+
+	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
+
+	i = armada_drm_crtc_calc_fb(dcrtc->crtc.fb, x, y, regs, interlaced);
+
+	rm = adj->crtc_hsync_start - adj->crtc_hdisplay;
+	lm = adj->crtc_htotal - adj->crtc_hsync_end;
+	bm = adj->crtc_vsync_start - adj->crtc_vdisplay;
+	tm = adj->crtc_vtotal - adj->crtc_vsync_end;
+
+	DRM_DEBUG_DRIVER("H: %d %d %d %d lm %d rm %d\n",
+		adj->crtc_hdisplay,
+		adj->crtc_hsync_start,
+		adj->crtc_hsync_end,
+		adj->crtc_htotal, lm, rm);
+	DRM_DEBUG_DRIVER("V: %d %d %d %d tm %d bm %d\n",
+		adj->crtc_vdisplay,
+		adj->crtc_vsync_start,
+		adj->crtc_vsync_end,
+		adj->crtc_vtotal, tm, bm);
+
+	/* Wait for pending flips to complete */
+	wait_event(dcrtc->frame_wait, !dcrtc->frame_work);
+
+	drm_vblank_pre_modeset(crtc->dev, dcrtc->num);
+
+	crtc->mode = *adj;
+
+	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
+	if (val != dcrtc->dumb_ctrl) {
+		dcrtc->dumb_ctrl = val;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
+	}
+
+	/* Now compute the divider for real */
+	priv->variant->crtc_compute_clock(dcrtc, adj, &sclk);
+
+	/* Ensure graphic fifo is enabled */
+	armada_reg_queue_mod(regs, i, 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
+	armada_reg_queue_set(regs, i, sclk, LCD_CFG_SCLK_DIV);
+
+	if (interlaced ^ dcrtc->interlaced) {
+		if (adj->flags & DRM_MODE_FLAG_INTERLACE)
+			drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
+		else
+			drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+		dcrtc->interlaced = interlaced;
+	}
+
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
+
+	/* Even interlaced/progressive frame */
+	dcrtc->v[1].spu_v_h_total = adj->crtc_vtotal << 16 |
+				    adj->crtc_htotal;
+	dcrtc->v[1].spu_v_porch = tm << 16 | bm;
+	val = adj->crtc_hsync_start;
+	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
+
+	if (interlaced) {
+		/* Odd interlaced frame */
+		dcrtc->v[0].spu_v_h_total = dcrtc->v[1].spu_v_h_total +
+						(1 << 16);
+		dcrtc->v[0].spu_v_porch = dcrtc->v[1].spu_v_porch + 1;
+		val = adj->crtc_hsync_start - adj->crtc_htotal / 2;
+		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
+	} else {
+		dcrtc->v[0] = dcrtc->v[1];
+	}
+
+	val = adj->crtc_vdisplay << 16 | adj->crtc_hdisplay;
+
+	armada_reg_queue_set(regs, i, val, LCD_SPU_V_H_ACTIVE);
+	armada_reg_queue_set(regs, i, val, LCD_SPU_GRA_HPXL_VLN);
+	armada_reg_queue_set(regs, i, val, LCD_SPU_GZM_HPXL_VLN);
+	armada_reg_queue_set(regs, i, (lm << 16) | rm, LCD_SPU_H_PORCH);
+	armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_porch, LCD_SPU_V_PORCH);
+	armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_h_total,
+			   LCD_SPUT_V_H_TOTAL);
+
+	if (priv->variant->has_spu_adv_reg)
+		armada_reg_queue_mod(regs, i, dcrtc->v[0].spu_adv_reg,
+				     ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF |
+				     ADV_VSYNCOFFEN, LCD_SPU_ADV_REG);
+
+	val = CFG_GRA_ENA | CFG_GRA_HSMOOTH;
+	val |= CFG_GRA_FMT(drm_fb_to_armada_fb(dcrtc->crtc.fb)->fmt);
+	val |= CFG_GRA_MOD(drm_fb_to_armada_fb(dcrtc->crtc.fb)->mod);
+
+	if (drm_fb_to_armada_fb(dcrtc->crtc.fb)->fmt > CFG_420)
+		val |= CFG_PALETTE_ENA;
+
+	if (interlaced)
+		val |= CFG_GRA_FTOGGLE;
+
+	armada_reg_queue_mod(regs, i, val, CFG_GRAFORMAT |
+			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+					 CFG_SWAPYU | CFG_YUV2RGB) |
+			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE,
+			     LCD_SPU_DMA_CTRL0);
+
+	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
+	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
+
+	val = dcrtc->spu_iopad_ctrl | armada_drm_crtc_calculate_csc(dcrtc);
+	armada_reg_queue_set(regs, i, val, LCD_SPU_IOPAD_CONTROL);
+	armada_reg_queue_end(regs, i);
+
+	armada_drm_crtc_update_regs(dcrtc, regs);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+
+	armada_drm_crtc_update(dcrtc);
+
+	drm_vblank_post_modeset(crtc->dev, dcrtc->num);
+	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+
+	return 0;
+}
+
+/* The mode_config.mutex will be held for this call */
+static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
+	struct drm_framebuffer *old_fb)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_regs regs[4];
+	unsigned i;
+
+	i = armada_drm_crtc_calc_fb(crtc->fb, crtc->x, crtc->y, regs,
+				    dcrtc->interlaced);
+	armada_reg_queue_end(regs, i);
+
+	/* Wait for pending flips to complete */
+	wait_event(dcrtc->frame_wait, !dcrtc->frame_work);
+
+	/* Take a reference to the new fb as we're using it */
+	drm_framebuffer_reference(crtc->fb);
+
+	/* Update the base in the CRTC */
+	armada_drm_crtc_update_regs(dcrtc, regs);
+
+	/* Drop our previously held reference */
+	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+
+	return 0;
+}
+
+static void armada_drm_crtc_load_lut(struct drm_crtc *crtc)
+{
+}
+
+/* The mode_config.mutex will be held for this call */
+static void armada_drm_crtc_disable(struct drm_crtc *crtc)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+
+	armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	armada_drm_crtc_finish_fb(dcrtc, crtc->fb, true);
+
+	/* Power down most RAMs and FIFOs */
+	writel_relaxed(CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
+		       CFG_PDWN32x32 | CFG_PDWN16x66 | CFG_PDWN32x66 |
+		       CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
+}
+
+static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
+	.dpms		= armada_drm_crtc_dpms,
+	.prepare	= armada_drm_crtc_prepare,
+	.commit		= armada_drm_crtc_commit,
+	.mode_fixup	= armada_drm_crtc_mode_fixup,
+	.mode_set	= armada_drm_crtc_mode_set,
+	.mode_set_base	= armada_drm_crtc_mode_set_base,
+	.load_lut	= armada_drm_crtc_load_lut,
+	.disable	= armada_drm_crtc_disable,
+};
+
+static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_private *priv = crtc->dev->dev_private;
+
+	priv->dcrtc[dcrtc->num] = NULL;
+	drm_crtc_cleanup(&dcrtc->crtc);
+
+	if (!IS_ERR(dcrtc->clk))
+		clk_disable_unprepare(dcrtc->clk);
+
+	kfree(dcrtc);
+}
+
+/*
+ * The mode_config lock is held here, to prevent races between this
+ * and a mode_set.
+ */
+static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
+	struct drm_framebuffer *fb, struct drm_pending_vblank_event *event)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_frame_work *work;
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+	unsigned i;
+	int ret;
+
+	/* We don't support changing the pixel format */
+	if (fb->pixel_format != crtc->fb->pixel_format)
+		return -EINVAL;
+
+	work = kmalloc(sizeof(*work), GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	work->event = event;
+	work->old_fb = dcrtc->crtc.fb;
+
+	i = armada_drm_crtc_calc_fb(fb, crtc->x, crtc->y, work->regs,
+				    dcrtc->interlaced);
+	armada_reg_queue_end(work->regs, i);
+
+	/*
+	 * Hold the old framebuffer for the work - DRM appears to drop our
+	 * reference to the old framebuffer in drm_mode_page_flip_ioctl().
+	 */
+	drm_framebuffer_reference(work->old_fb);
+
+	ret = armada_drm_crtc_queue_frame_work(dcrtc, work);
+	if (ret) {
+		/*
+		 * Undo our reference above; DRM does not drop the reference
+		 * to this object on error, so that's okay.
+		 */
+		drm_framebuffer_unreference(work->old_fb);
+		kfree(work);
+		return ret;
+	}
+
+	/*
+	 * Don't take a reference on the new framebuffer;
+	 * drm_mode_page_flip_ioctl() has already grabbed a reference and
+	 * will _not_ drop that reference on successful return from this
+	 * function.  Simply mark this new framebuffer as the current one.
+	 */
+	dcrtc->crtc.fb = fb;
+
+	/*
+	 * Finally, if the display is blanked, we won't receive an
+	 * interrupt, so complete it now.
+	 */
+	if (dpms_blanked(dcrtc->dpms)) {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		if (dcrtc->frame_work)
+			armada_drm_crtc_complete_frame_work(dcrtc);
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	return 0;
+}
+
+static int
+armada_drm_crtc_set_property(struct drm_crtc *crtc,
+	struct drm_property *property, uint64_t val)
+{
+	struct armada_private *priv = crtc->dev->dev_private;
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	bool update_csc = false;
+
+	if (property == priv->csc_yuv_prop) {
+		dcrtc->csc_yuv_mode = val;
+		update_csc = true;
+	} else if (property == priv->csc_rgb_prop) {
+		dcrtc->csc_rgb_mode = val;
+		update_csc = true;
+	}
+
+	if (update_csc) {
+		uint32_t val;
+
+		val = dcrtc->spu_iopad_ctrl |
+		      armada_drm_crtc_calculate_csc(dcrtc);
+		writel_relaxed(val, dcrtc->base + LCD_SPU_IOPAD_CONTROL);
+	}
+
+	return 0;
+}
+
+static struct drm_crtc_funcs armada_crtc_funcs = {
+	.destroy	= armada_drm_crtc_destroy,
+	.set_config	= drm_crtc_helper_set_config,
+	.page_flip	= armada_drm_crtc_page_flip,
+	.set_property	= armada_drm_crtc_set_property,
+};
+
+static struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
+	{ CSC_AUTO,        "Auto" },
+	{ CSC_YUV_CCIR601, "CCIR601" },
+	{ CSC_YUV_CCIR709, "CCIR709" },
+};
+
+static struct drm_prop_enum_list armada_drm_csc_rgb_enum_list[] = {
+	{ CSC_AUTO,         "Auto" },
+	{ CSC_RGB_COMPUTER, "Computer system" },
+	{ CSC_RGB_STUDIO,   "Studio" },
+};
+
+static int armada_drm_crtc_create_properties(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+
+	if (priv->csc_yuv_prop)
+		return 0;
+
+	priv->csc_yuv_prop = drm_property_create_enum(dev, 0,
+				"CSC_YUV", armada_drm_csc_yuv_enum_list,
+				ARRAY_SIZE(armada_drm_csc_yuv_enum_list));
+	priv->csc_rgb_prop = drm_property_create_enum(dev, 0,
+				"CSC_RGB", armada_drm_csc_rgb_enum_list,
+				ARRAY_SIZE(armada_drm_csc_rgb_enum_list));
+
+	if (!priv->csc_yuv_prop || !priv->csc_rgb_prop)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int armada_drm_crtc_create(struct drm_device *dev, unsigned num,
+	struct resource *res)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct armada_crtc *dcrtc;
+	void __iomem *base;
+	int ret;
+
+	ret = armada_drm_crtc_create_properties(dev);
+	if (ret)
+		return ret;
+
+	base = devm_request_and_ioremap(dev->dev, res);
+	if (!base) {
+		DRM_ERROR("failed to ioremap register\n");
+		return -ENOMEM;
+	}
+
+	dcrtc = kzalloc(sizeof(*dcrtc), GFP_KERNEL);
+	if (!dcrtc) {
+		DRM_ERROR("failed to allocate Armada crtc\n");
+		return -ENOMEM;
+	}
+
+	dcrtc->base = base;
+	dcrtc->num = num;
+	dcrtc->clk = ERR_PTR(-EINVAL);
+	dcrtc->csc_yuv_mode = CSC_AUTO;
+	dcrtc->csc_rgb_mode = CSC_AUTO;
+	dcrtc->cfg_dumb_ctrl = DUMB24_RGB888_0;
+	dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24;
+	spin_lock_init(&dcrtc->irq_lock);
+	dcrtc->irq_ena = CLEAN_SPU_IRQ_ISR;
+	INIT_LIST_HEAD(&dcrtc->vbl_list);
+	init_waitqueue_head(&dcrtc->frame_wait);
+
+	/* Initialize some registers which we don't otherwise set */
+	writel_relaxed(0x00000001, dcrtc->base + LCD_CFG_SCLK_DIV);
+	writel_relaxed(0x00000000, dcrtc->base + LCD_SPU_BLANKCOLOR);
+	writel_relaxed(dcrtc->spu_iopad_ctrl,
+		       dcrtc->base + LCD_SPU_IOPAD_CONTROL);
+	writel_relaxed(0x00000000, dcrtc->base + LCD_SPU_SRAM_PARA0);
+	writel_relaxed(CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
+		       CFG_PDWN32x32 | CFG_PDWN16x66 | CFG_PDWN32x66 |
+		       CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
+	writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1);
+	writel_relaxed(0x00000000, dcrtc->base + LCD_SPU_GRA_OVSA_HPXL_VLN);
+
+	if (priv->variant->crtc_init) {
+		ret = priv->variant->crtc_init(dcrtc);
+		if (ret) {
+			kfree(dcrtc);
+			return ret;
+		}
+	}
+
+	/* Ensure AXI pipeline is enabled */
+	armada_updatel(CFG_ARBFAST_ENA, 0, dcrtc->base + LCD_SPU_DMA_CTRL0);
+
+	priv->dcrtc[dcrtc->num] = dcrtc;
+
+	drm_crtc_init(dev, &dcrtc->crtc, &armada_crtc_funcs);
+	drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs);
+
+	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop,
+				   dcrtc->csc_yuv_mode);
+	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_rgb_prop,
+				   dcrtc->csc_rgb_mode);
+
+	return armada_overlay_plane_create(dev, 1 << dcrtc->num);
+}
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
new file mode 100644
index 000000000000..972da535921d
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_CRTC_H
+#define ARMADA_CRTC_H
+
+struct armada_gem_object;
+
+struct armada_regs {
+	uint32_t offset;
+	uint32_t mask;
+	uint32_t val;
+};
+
+#define armada_reg_queue_mod(_r, _i, _v, _m, _o)	\
+	do {					\
+		struct armada_regs *__reg = _r;	\
+		__reg[_i].offset = _o;		\
+		__reg[_i].mask = ~(_m);		\
+		__reg[_i].val = _v;		\
+		_i++;				\
+	} while (0)
+
+#define armada_reg_queue_set(_r, _i, _v, _o)	\
+	armada_reg_queue_mod(_r, _i, _v, ~0, _o)
+
+#define armada_reg_queue_end(_r, _i)		\
+	armada_reg_queue_mod(_r, _i, 0, 0, ~0)
+
+struct armada_frame_work;
+
+struct armada_crtc {
+	struct drm_crtc		crtc;
+	unsigned		num;
+	void __iomem		*base;
+	struct clk		*clk;
+	struct {
+		uint32_t	spu_v_h_total;
+		uint32_t	spu_v_porch;
+		uint32_t	spu_adv_reg;
+	} v[2];
+	bool			interlaced;
+	uint8_t			csc_yuv_mode;
+	uint8_t			csc_rgb_mode;
+
+	struct drm_plane	*plane;
+
+	int			dpms;
+	uint32_t		cfg_dumb_ctrl;
+	uint32_t		dumb_ctrl;
+	uint32_t		spu_iopad_ctrl;
+
+	wait_queue_head_t	frame_wait;
+	struct armada_frame_work *frame_work;
+
+	spinlock_t		irq_lock;
+	uint32_t		irq_ena;
+	struct list_head	vbl_list;
+};
+#define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc)
+
+int armada_drm_crtc_create(struct drm_device *, unsigned, struct resource *);
+void armada_drm_crtc_gamma_set(struct drm_crtc *, u16, u16, u16, int);
+void armada_drm_crtc_gamma_get(struct drm_crtc *, u16 *, u16 *, u16 *, int);
+void armada_drm_crtc_irq(struct armada_crtc *, u32);
+void armada_drm_crtc_disable_irq(struct armada_crtc *, u32);
+void armada_drm_crtc_enable_irq(struct armada_crtc *, u32);
+void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *);
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_debugfs.c b/drivers/gpu/drm/armada/armada_debugfs.c
new file mode 100644
index 000000000000..612f3753cd92
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_debugfs.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <drm/drmP.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+
+static int armada_debugfs_gem_linear_show(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct armada_private *priv = dev->dev_private;
+	int ret;
+
+	mutex_lock(&dev->struct_mutex);
+	ret = drm_mm_dump_table(m, &priv->linear);
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+static int armada_debugfs_reg_show(struct seq_file *m, void *data)
+{
+	struct drm_device *dev = m->private;
+	struct armada_private *priv = dev->dev_private;
+	int n, i;
+
+	if (priv) {
+		for (n = 0; n < ARRAY_SIZE(priv->dcrtc); n++) {
+			struct armada_crtc *dcrtc = priv->dcrtc[n];
+			if (!dcrtc)
+				continue;
+
+			for (i = 0x84; i <= 0x1c4; i += 4) {
+				uint32_t v = readl_relaxed(dcrtc->base + i);
+				seq_printf(m, "%u: 0x%04x: 0x%08x\n", n, i, v);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int armada_debugfs_reg_r_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, armada_debugfs_reg_show, inode->i_private);
+}
+
+static const struct file_operations fops_reg_r = {
+	.owner = THIS_MODULE,
+	.open = armada_debugfs_reg_r_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int armada_debugfs_write(struct file *file, const char __user *ptr,
+	size_t len, loff_t *off)
+{
+	struct drm_device *dev = file->private_data;
+	struct armada_private *priv = dev->dev_private;
+	struct armada_crtc *dcrtc = priv->dcrtc[0];
+	char buf[32], *p;
+	uint32_t reg, val;
+	int ret;
+
+	if (*off != 0)
+		return 0;
+
+	if (len > sizeof(buf) - 1)
+		len = sizeof(buf) - 1;
+
+	ret = strncpy_from_user(buf, ptr, len);
+	if (ret < 0)
+		return ret;
+	buf[len] = '\0';
+
+	reg = simple_strtoul(buf, &p, 16);
+	if (!isspace(*p))
+		return -EINVAL;
+	val = simple_strtoul(p + 1, NULL, 16);
+
+	if (reg >= 0x84 && reg <= 0x1c4)
+		writel(val, dcrtc->base + reg);
+
+	return len;
+}
+
+static int armada_debugfs_reg_w_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+static const struct file_operations fops_reg_w = {
+	.owner = THIS_MODULE,
+	.open = armada_debugfs_reg_w_open,
+	.write = armada_debugfs_write,
+	.llseek = noop_llseek,
+};
+
+static struct drm_info_list armada_debugfs_list[] = {
+	{ "gem_linear", armada_debugfs_gem_linear_show, 0 },
+};
+#define ARMADA_DEBUGFS_ENTRIES ARRAY_SIZE(armada_debugfs_list)
+
+static int drm_add_fake_info_node(struct drm_minor *minor, struct dentry *ent,
+	const void *key)
+{
+	struct drm_info_node *node;
+
+	node = kmalloc(sizeof(struct drm_info_node), GFP_KERNEL);
+	if (node == NULL) {
+		debugfs_remove(ent);
+		return -ENOMEM;
+	}
+
+	node->minor = minor;
+	node->dent = ent;
+	node->info_ent = (void *) key;
+
+	mutex_lock(&minor->debugfs_lock);
+	list_add(&node->list, &minor->debugfs_list);
+	mutex_unlock(&minor->debugfs_lock);
+
+	return 0;
+}
+
+static int armada_debugfs_create(struct dentry *root, struct drm_minor *minor,
+	const char *name, umode_t mode, const struct file_operations *fops)
+{
+	struct dentry *de;
+
+	de = debugfs_create_file(name, mode, root, minor->dev, fops);
+
+	return drm_add_fake_info_node(minor, de, fops);
+}
+
+int armada_drm_debugfs_init(struct drm_minor *minor)
+{
+	int ret;
+
+	ret = drm_debugfs_create_files(armada_debugfs_list,
+				       ARMADA_DEBUGFS_ENTRIES,
+				       minor->debugfs_root, minor);
+	if (ret)
+		return ret;
+
+	ret = armada_debugfs_create(minor->debugfs_root, minor,
+				   "reg", S_IFREG | S_IRUSR, &fops_reg_r);
+	if (ret)
+		goto err_1;
+
+	ret = armada_debugfs_create(minor->debugfs_root, minor,
+				"reg_wr", S_IFREG | S_IWUSR, &fops_reg_w);
+	if (ret)
+		goto err_2;
+	return ret;
+
+ err_2:
+	drm_debugfs_remove_files((struct drm_info_list *)&fops_reg_r, 1, minor);
+ err_1:
+	drm_debugfs_remove_files(armada_debugfs_list, ARMADA_DEBUGFS_ENTRIES,
+				 minor);
+	return ret;
+}
+
+void armada_drm_debugfs_cleanup(struct drm_minor *minor)
+{
+	drm_debugfs_remove_files((struct drm_info_list *)&fops_reg_w, 1, minor);
+	drm_debugfs_remove_files((struct drm_info_list *)&fops_reg_r, 1, minor);
+	drm_debugfs_remove_files(armada_debugfs_list, ARMADA_DEBUGFS_ENTRIES,
+				 minor);
+}
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
new file mode 100644
index 000000000000..e8c4f80c61d4
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_DRM_H
+#define ARMADA_DRM_H
+
+#include <linux/kfifo.h>
+#include <linux/io.h>
+#include <linux/workqueue.h>
+#include <drm/drmP.h>
+
+struct armada_crtc;
+struct armada_gem_object;
+struct clk;
+struct drm_fb_helper;
+
+static inline void
+armada_updatel(uint32_t val, uint32_t mask, void __iomem *ptr)
+{
+	uint32_t ov, v;
+
+	ov = v = readl_relaxed(ptr);
+	v = (v & ~mask) | val;
+	if (ov != v)
+		writel_relaxed(v, ptr);
+}
+
+static inline uint32_t armada_pitch(uint32_t width, uint32_t bpp)
+{
+	uint32_t pitch = bpp != 4 ? width * ((bpp + 7) / 8) : width / 2;
+
+	/* 88AP510 spec recommends pitch be a multiple of 128 */
+	return ALIGN(pitch, 128);
+}
+
+struct armada_vbl_event {
+	struct list_head	node;
+	void			*data;
+	void			(*fn)(struct armada_crtc *, void *);
+};
+void armada_drm_vbl_event_add(struct armada_crtc *,
+	struct armada_vbl_event *);
+void armada_drm_vbl_event_remove(struct armada_crtc *,
+	struct armada_vbl_event *);
+void armada_drm_vbl_event_remove_unlocked(struct armada_crtc *,
+	struct armada_vbl_event *);
+#define armada_drm_vbl_event_init(_e, _f, _d) do {	\
+	struct armada_vbl_event *__e = _e;		\
+	INIT_LIST_HEAD(&__e->node);			\
+	__e->data = _d;					\
+	__e->fn = _f;					\
+} while (0)
+
+
+struct armada_private;
+
+struct armada_variant {
+	bool	has_spu_adv_reg;
+	int (*init)(struct armada_private *, struct device *);
+	int (*crtc_init)(struct armada_crtc *);
+	int (*crtc_compute_clock)(struct armada_crtc *,
+				  const struct drm_display_mode *,
+				  uint32_t *);
+};
+
+/* Variant ops */
+extern const struct armada_variant armada510_ops;
+
+struct armada_private {
+	const struct armada_variant *variant;
+	struct work_struct	fb_unref_work;
+	DECLARE_KFIFO(fb_unref, struct drm_framebuffer *, 8);
+	struct drm_fb_helper	*fbdev;
+	struct armada_crtc	*dcrtc[2];
+	struct drm_mm		linear;
+	struct clk		*extclk[2];
+	struct drm_property	*csc_yuv_prop;
+	struct drm_property	*csc_rgb_prop;
+	struct drm_property	*colorkey_prop;
+	struct drm_property	*colorkey_min_prop;
+	struct drm_property	*colorkey_max_prop;
+	struct drm_property	*colorkey_val_prop;
+	struct drm_property	*colorkey_alpha_prop;
+	struct drm_property	*colorkey_mode_prop;
+	struct drm_property	*brightness_prop;
+	struct drm_property	*contrast_prop;
+	struct drm_property	*saturation_prop;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry		*de;
+#endif
+};
+
+void __armada_drm_queue_unref_work(struct drm_device *,
+	struct drm_framebuffer *);
+void armada_drm_queue_unref_work(struct drm_device *,
+	struct drm_framebuffer *);
+
+extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
+
+int armada_fbdev_init(struct drm_device *);
+void armada_fbdev_fini(struct drm_device *);
+
+int armada_overlay_plane_create(struct drm_device *, unsigned long);
+
+int armada_drm_debugfs_init(struct drm_minor *);
+void armada_drm_debugfs_cleanup(struct drm_minor *);
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
new file mode 100644
index 000000000000..7bfab9a286ae
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -0,0 +1,380 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+#include <drm/armada_drm.h>
+#include "armada_ioctlP.h"
+
+static void armada_drm_unref_work(struct work_struct *work)
+{
+	struct armada_private *priv =
+		container_of(work, struct armada_private, fb_unref_work);
+	struct drm_framebuffer *fb;
+
+	while (kfifo_get(&priv->fb_unref, &fb))
+		drm_framebuffer_unreference(fb);
+}
+
+/* Must be called with dev->event_lock held */
+void __armada_drm_queue_unref_work(struct drm_device *dev,
+	struct drm_framebuffer *fb)
+{
+	struct armada_private *priv = dev->dev_private;
+
+	/*
+	 * Yes, we really must jump through these hoops just to store a
+	 * _pointer_ to something into the kfifo.  This is utterly insane
+	 * and idiotic, because it kfifo requires the _data_ pointed to by
+	 * the pointer const, not the pointer itself.  Not only that, but
+	 * you have to pass a pointer _to_ the pointer you want stored.
+	 */
+	const struct drm_framebuffer *silly_api_alert = fb;
+	WARN_ON(!kfifo_put(&priv->fb_unref, &silly_api_alert));
+	schedule_work(&priv->fb_unref_work);
+}
+
+void armada_drm_queue_unref_work(struct drm_device *dev,
+	struct drm_framebuffer *fb)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	__armada_drm_queue_unref_work(dev, fb);
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+static int armada_drm_load(struct drm_device *dev, unsigned long flags)
+{
+	const struct platform_device_id *id;
+	struct armada_private *priv;
+	struct resource *res[ARRAY_SIZE(priv->dcrtc)];
+	struct resource *mem = NULL;
+	int ret, n, i;
+
+	memset(res, 0, sizeof(res));
+
+	for (n = i = 0; ; n++) {
+		struct resource *r = platform_get_resource(dev->platformdev,
+							   IORESOURCE_MEM, n);
+		if (!r)
+			break;
+
+		/* Resources above 64K are graphics memory */
+		if (resource_size(r) > SZ_64K)
+			mem = r;
+		else if (i < ARRAY_SIZE(priv->dcrtc))
+			res[i++] = r;
+		else
+			return -EINVAL;
+	}
+
+	if (!res[0] || !mem)
+		return -ENXIO;
+
+	if (!devm_request_mem_region(dev->dev, mem->start,
+			resource_size(mem), "armada-drm"))
+		return -EBUSY;
+
+	priv = devm_kzalloc(dev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		DRM_ERROR("failed to allocate private\n");
+		return -ENOMEM;
+	}
+
+	dev->dev_private = priv;
+
+	/* Get the implementation specific driver data. */
+	id = platform_get_device_id(dev->platformdev);
+	if (!id)
+		return -ENXIO;
+
+	priv->variant = (struct armada_variant *)id->driver_data;
+
+	ret = priv->variant->init(priv, dev->dev);
+	if (ret)
+		return ret;
+
+	INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work);
+	INIT_KFIFO(priv->fb_unref);
+
+	/* Mode setting support */
+	drm_mode_config_init(dev);
+	dev->mode_config.min_width = 320;
+	dev->mode_config.min_height = 200;
+
+	/*
+	 * With vscale enabled, the maximum width is 1920 due to the
+	 * 1920 by 3 lines RAM
+	 */
+	dev->mode_config.max_width = 1920;
+	dev->mode_config.max_height = 2048;
+
+	dev->mode_config.preferred_depth = 24;
+	dev->mode_config.funcs = &armada_drm_mode_config_funcs;
+	drm_mm_init(&priv->linear, mem->start, resource_size(mem));
+
+	/* Create all LCD controllers */
+	for (n = 0; n < ARRAY_SIZE(priv->dcrtc); n++) {
+		if (!res[n])
+			break;
+
+		ret = armada_drm_crtc_create(dev, n, res[n]);
+		if (ret)
+			goto err_kms;
+	}
+
+	ret = drm_vblank_init(dev, n);
+	if (ret)
+		goto err_kms;
+
+	ret = drm_irq_install(dev);
+	if (ret)
+		goto err_kms;
+
+	dev->vblank_disable_allowed = 1;
+
+	ret = armada_fbdev_init(dev);
+	if (ret)
+		goto err_irq;
+
+	drm_kms_helper_poll_init(dev);
+
+	return 0;
+
+ err_irq:
+	drm_irq_uninstall(dev);
+ err_kms:
+	drm_mode_config_cleanup(dev);
+	drm_mm_takedown(&priv->linear);
+	flush_work(&priv->fb_unref_work);
+
+	return ret;
+}
+
+static int armada_drm_unload(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+
+	drm_kms_helper_poll_fini(dev);
+	armada_fbdev_fini(dev);
+	drm_irq_uninstall(dev);
+	drm_mode_config_cleanup(dev);
+	drm_mm_takedown(&priv->linear);
+	flush_work(&priv->fb_unref_work);
+	dev->dev_private = NULL;
+
+	return 0;
+}
+
+void armada_drm_vbl_event_add(struct armada_crtc *dcrtc,
+	struct armada_vbl_event *evt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
+	if (list_empty(&evt->node)) {
+		list_add_tail(&evt->node, &dcrtc->vbl_list);
+
+		drm_vblank_get(dcrtc->crtc.dev, dcrtc->num);
+	}
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+}
+
+void armada_drm_vbl_event_remove(struct armada_crtc *dcrtc,
+	struct armada_vbl_event *evt)
+{
+	if (!list_empty(&evt->node)) {
+		list_del_init(&evt->node);
+		drm_vblank_put(dcrtc->crtc.dev, dcrtc->num);
+	}
+}
+
+void armada_drm_vbl_event_remove_unlocked(struct armada_crtc *dcrtc,
+	struct armada_vbl_event *evt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
+	armada_drm_vbl_event_remove(dcrtc, evt);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+}
+
+/* These are called under the vbl_lock. */
+static int armada_drm_enable_vblank(struct drm_device *dev, int crtc)
+{
+	struct armada_private *priv = dev->dev_private;
+	armada_drm_crtc_enable_irq(priv->dcrtc[crtc], VSYNC_IRQ_ENA);
+	return 0;
+}
+
+static void armada_drm_disable_vblank(struct drm_device *dev, int crtc)
+{
+	struct armada_private *priv = dev->dev_private;
+	armada_drm_crtc_disable_irq(priv->dcrtc[crtc], VSYNC_IRQ_ENA);
+}
+
+static irqreturn_t armada_drm_irq_handler(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct armada_private *priv = dev->dev_private;
+	struct armada_crtc *dcrtc = priv->dcrtc[0];
+	uint32_t v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
+	irqreturn_t handled = IRQ_NONE;
+
+	/*
+	 * This is rediculous - rather than writing bits to clear, we
+	 * have to set the actual status register value.  This is racy.
+	 */
+	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
+
+	/* Mask out those interrupts we haven't enabled */
+	v = stat & dcrtc->irq_ena;
+
+	if (v & (VSYNC_IRQ|GRA_FRAME_IRQ|DUMB_FRAMEDONE)) {
+		armada_drm_crtc_irq(dcrtc, stat);
+		handled = IRQ_HANDLED;
+	}
+
+	return handled;
+}
+
+static int armada_drm_irq_postinstall(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct armada_crtc *dcrtc = priv->dcrtc[0];
+
+	spin_lock_irq(&dev->vbl_lock);
+	writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+	writel(0, dcrtc->base + LCD_SPU_IRQ_ISR);
+	spin_unlock_irq(&dev->vbl_lock);
+
+	return 0;
+}
+
+static void armada_drm_irq_uninstall(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct armada_crtc *dcrtc = priv->dcrtc[0];
+
+	writel(0, dcrtc->base + LCD_SPU_IRQ_ENA);
+}
+
+static struct drm_ioctl_desc armada_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(ARMADA_GEM_CREATE, armada_gem_create_ioctl,
+		DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(ARMADA_GEM_MMAP, armada_gem_mmap_ioctl,
+		DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(ARMADA_GEM_PWRITE, armada_gem_pwrite_ioctl,
+		DRM_UNLOCKED),
+};
+
+static const struct file_operations armada_drm_fops = {
+	.owner			= THIS_MODULE,
+	.llseek			= no_llseek,
+	.read			= drm_read,
+	.poll			= drm_poll,
+	.unlocked_ioctl		= drm_ioctl,
+	.mmap			= drm_gem_mmap,
+	.open			= drm_open,
+	.release		= drm_release,
+};
+
+static struct drm_driver armada_drm_driver = {
+	.load			= armada_drm_load,
+	.open			= NULL,
+	.preclose		= NULL,
+	.postclose		= NULL,
+	.lastclose		= NULL,
+	.unload			= armada_drm_unload,
+	.get_vblank_counter	= drm_vblank_count,
+	.enable_vblank		= armada_drm_enable_vblank,
+	.disable_vblank		= armada_drm_disable_vblank,
+	.irq_handler		= armada_drm_irq_handler,
+	.irq_postinstall	= armada_drm_irq_postinstall,
+	.irq_uninstall		= armada_drm_irq_uninstall,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init		= armada_drm_debugfs_init,
+	.debugfs_cleanup	= armada_drm_debugfs_cleanup,
+#endif
+	.gem_init_object	= NULL,
+	.gem_free_object	= armada_gem_free_object,
+	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
+	.gem_prime_export	= armada_gem_prime_export,
+	.gem_prime_import	= armada_gem_prime_import,
+	.dumb_create		= armada_gem_dumb_create,
+	.dumb_map_offset	= armada_gem_dumb_map_offset,
+	.dumb_destroy		= armada_gem_dumb_destroy,
+	.gem_vm_ops		= &armada_gem_vm_ops,
+	.major			= 1,
+	.minor			= 0,
+	.name			= "armada-drm",
+	.desc			= "Armada SoC DRM",
+	.date			= "20120730",
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET |
+				  DRIVER_HAVE_IRQ | DRIVER_PRIME,
+	.ioctls			= armada_ioctls,
+	.fops			= &armada_drm_fops,
+};
+
+static int armada_drm_probe(struct platform_device *pdev)
+{
+	return drm_platform_init(&armada_drm_driver, pdev);
+}
+
+static int armada_drm_remove(struct platform_device *pdev)
+{
+	drm_platform_exit(&armada_drm_driver, pdev);
+	return 0;
+}
+
+static const struct platform_device_id armada_drm_platform_ids[] = {
+	{
+		.name		= "armada-drm",
+		.driver_data	= (unsigned long)&armada510_ops,
+	}, {
+		.name		= "armada-510-drm",
+		.driver_data	= (unsigned long)&armada510_ops,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, armada_drm_platform_ids);
+
+static struct platform_driver armada_drm_platform_driver = {
+	.probe	= armada_drm_probe,
+	.remove	= armada_drm_remove,
+	.driver	= {
+		.name	= "armada-drm",
+		.owner	= THIS_MODULE,
+	},
+	.id_table = armada_drm_platform_ids,
+};
+
+static int __init armada_drm_init(void)
+{
+	armada_drm_driver.num_ioctls = DRM_ARRAY_SIZE(armada_ioctls);
+	return platform_driver_register(&armada_drm_platform_driver);
+}
+module_init(armada_drm_init);
+
+static void __exit armada_drm_exit(void)
+{
+	platform_driver_unregister(&armada_drm_platform_driver);
+}
+module_exit(armada_drm_exit);
+
+MODULE_AUTHOR("Russell King <rmk+kernel@arm.linux.org.uk>");
+MODULE_DESCRIPTION("Armada DRM Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:armada-drm");
diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
new file mode 100644
index 000000000000..1c90969def3e
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_helper.h>
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+
+static void armada_fb_destroy(struct drm_framebuffer *fb)
+{
+	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
+
+	drm_framebuffer_cleanup(&dfb->fb);
+	drm_gem_object_unreference_unlocked(&dfb->obj->obj);
+	kfree(dfb);
+}
+
+static int armada_fb_create_handle(struct drm_framebuffer *fb,
+	struct drm_file *dfile, unsigned int *handle)
+{
+	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
+	return drm_gem_handle_create(dfile, &dfb->obj->obj, handle);
+}
+
+static const struct drm_framebuffer_funcs armada_fb_funcs = {
+	.destroy	= armada_fb_destroy,
+	.create_handle	= armada_fb_create_handle,
+};
+
+struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
+	struct drm_mode_fb_cmd2 *mode, struct armada_gem_object *obj)
+{
+	struct armada_framebuffer *dfb;
+	uint8_t format, config;
+	int ret;
+
+	switch (mode->pixel_format) {
+#define FMT(drm, fmt, mod)		\
+	case DRM_FORMAT_##drm:		\
+		format = CFG_##fmt;	\
+		config = mod;		\
+		break
+	FMT(RGB565,	565,		CFG_SWAPRB);
+	FMT(BGR565,	565,		0);
+	FMT(ARGB1555,	1555,		CFG_SWAPRB);
+	FMT(ABGR1555,	1555,		0);
+	FMT(RGB888,	888PACK,	CFG_SWAPRB);
+	FMT(BGR888,	888PACK,	0);
+	FMT(XRGB8888,	X888,		CFG_SWAPRB);
+	FMT(XBGR8888,	X888,		0);
+	FMT(ARGB8888,	8888,		CFG_SWAPRB);
+	FMT(ABGR8888,	8888,		0);
+	FMT(YUYV,	422PACK,	CFG_YUV2RGB | CFG_SWAPYU | CFG_SWAPUV);
+	FMT(UYVY,	422PACK,	CFG_YUV2RGB);
+	FMT(VYUY,	422PACK,	CFG_YUV2RGB | CFG_SWAPUV);
+	FMT(YVYU,	422PACK,	CFG_YUV2RGB | CFG_SWAPYU);
+	FMT(YUV422,	422,		CFG_YUV2RGB);
+	FMT(YVU422,	422,		CFG_YUV2RGB | CFG_SWAPUV);
+	FMT(YUV420,	420,		CFG_YUV2RGB);
+	FMT(YVU420,	420,		CFG_YUV2RGB | CFG_SWAPUV);
+	FMT(C8,		PSEUDO8,	0);
+#undef FMT
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	dfb = kzalloc(sizeof(*dfb), GFP_KERNEL);
+	if (!dfb) {
+		DRM_ERROR("failed to allocate Armada fb object\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dfb->fmt = format;
+	dfb->mod = config;
+	dfb->obj = obj;
+
+	drm_helper_mode_fill_fb_struct(&dfb->fb, mode);
+
+	ret = drm_framebuffer_init(dev, &dfb->fb, &armada_fb_funcs);
+	if (ret) {
+		kfree(dfb);
+		return ERR_PTR(ret);
+	}
+
+	/*
+	 * Take a reference on our object as we're successful - the
+	 * caller already holds a reference, which keeps us safe for
+	 * the above call, but the caller will drop their reference
+	 * to it.  Hence we need to take our own reference.
+	 */
+	drm_gem_object_reference(&obj->obj);
+
+	return dfb;
+}
+
+static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+	struct drm_file *dfile, struct drm_mode_fb_cmd2 *mode)
+{
+	struct armada_gem_object *obj;
+	struct armada_framebuffer *dfb;
+	int ret;
+
+	DRM_DEBUG_DRIVER("w%u h%u pf%08x f%u p%u,%u,%u\n",
+		mode->width, mode->height, mode->pixel_format,
+		mode->flags, mode->pitches[0], mode->pitches[1],
+		mode->pitches[2]);
+
+	/* We can only handle a single plane at the moment */
+	if (drm_format_num_planes(mode->pixel_format) > 1 &&
+	    (mode->handles[0] != mode->handles[1] ||
+	     mode->handles[0] != mode->handles[2])) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	obj = armada_gem_object_lookup(dev, dfile, mode->handles[0]);
+	if (!obj) {
+		ret = -ENOENT;
+		goto err;
+	}
+
+	if (obj->obj.import_attach && !obj->sgt) {
+		ret = armada_gem_map_import(obj);
+		if (ret)
+			goto err_unref;
+	}
+
+	/* Framebuffer objects must have a valid device address for scanout */
+	if (obj->dev_addr == DMA_ERROR_CODE) {
+		ret = -EINVAL;
+		goto err_unref;
+	}
+
+	dfb = armada_framebuffer_create(dev, mode, obj);
+	if (IS_ERR(dfb)) {
+		ret = PTR_ERR(dfb);
+		goto err;
+	}
+
+	drm_gem_object_unreference_unlocked(&obj->obj);
+
+	return &dfb->fb;
+
+ err_unref:
+	drm_gem_object_unreference_unlocked(&obj->obj);
+ err:
+	DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
+	return ERR_PTR(ret);
+}
+
+static void armada_output_poll_changed(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct drm_fb_helper *fbh = priv->fbdev;
+
+	if (fbh)
+		drm_fb_helper_hotplug_event(fbh);
+}
+
+const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
+	.fb_create		= armada_fb_create,
+	.output_poll_changed	= armada_output_poll_changed,
+};
diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h
new file mode 100644
index 000000000000..ce3f12ebfc53
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_fb.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_FB_H
+#define ARMADA_FB_H
+
+struct armada_framebuffer {
+	struct drm_framebuffer	fb;
+	struct armada_gem_object *obj;
+	uint8_t			fmt;
+	uint8_t			mod;
+};
+#define drm_fb_to_armada_fb(dfb) \
+	container_of(dfb, struct armada_framebuffer, fb)
+#define drm_fb_obj(fb) drm_fb_to_armada_fb(fb)->obj
+
+struct armada_framebuffer *armada_framebuffer_create(struct drm_device *,
+	struct drm_mode_fb_cmd2 *, struct armada_gem_object *);
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
new file mode 100644
index 000000000000..dd5ea77dac96
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Written from the i915 driver.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/errno.h>
+#include <linux/fb.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_fb_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+
+static /*const*/ struct fb_ops armada_fb_ops = {
+	.owner		= THIS_MODULE,
+	.fb_check_var	= drm_fb_helper_check_var,
+	.fb_set_par	= drm_fb_helper_set_par,
+	.fb_fillrect	= cfb_fillrect,
+	.fb_copyarea	= cfb_copyarea,
+	.fb_imageblit	= cfb_imageblit,
+	.fb_pan_display	= drm_fb_helper_pan_display,
+	.fb_blank	= drm_fb_helper_blank,
+	.fb_setcmap	= drm_fb_helper_setcmap,
+	.fb_debug_enter	= drm_fb_helper_debug_enter,
+	.fb_debug_leave	= drm_fb_helper_debug_leave,
+};
+
+static int armada_fb_create(struct drm_fb_helper *fbh,
+	struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_device *dev = fbh->dev;
+	struct drm_mode_fb_cmd2 mode;
+	struct armada_framebuffer *dfb;
+	struct armada_gem_object *obj;
+	struct fb_info *info;
+	int size, ret;
+	void *ptr;
+
+	memset(&mode, 0, sizeof(mode));
+	mode.width = sizes->surface_width;
+	mode.height = sizes->surface_height;
+	mode.pitches[0] = armada_pitch(mode.width, sizes->surface_bpp);
+	mode.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
+					sizes->surface_depth);
+
+	size = mode.pitches[0] * mode.height;
+	obj = armada_gem_alloc_private_object(dev, size);
+	if (!obj) {
+		DRM_ERROR("failed to allocate fb memory\n");
+		return -ENOMEM;
+	}
+
+	ret = armada_gem_linear_back(dev, obj);
+	if (ret) {
+		drm_gem_object_unreference_unlocked(&obj->obj);
+		return ret;
+	}
+
+	ptr = armada_gem_map_object(dev, obj);
+	if (!ptr) {
+		drm_gem_object_unreference_unlocked(&obj->obj);
+		return -ENOMEM;
+	}
+
+	dfb = armada_framebuffer_create(dev, &mode, obj);
+
+	/*
+	 * A reference is now held by the framebuffer object if
+	 * successful, otherwise this drops the ref for the error path.
+	 */
+	drm_gem_object_unreference_unlocked(&obj->obj);
+
+	if (IS_ERR(dfb))
+		return PTR_ERR(dfb);
+
+	info = framebuffer_alloc(0, dev->dev);
+	if (!info) {
+		ret = -ENOMEM;
+		goto err_fballoc;
+	}
+
+	ret = fb_alloc_cmap(&info->cmap, 256, 0);
+	if (ret) {
+		ret = -ENOMEM;
+		goto err_fbcmap;
+	}
+
+	strlcpy(info->fix.id, "armada-drmfb", sizeof(info->fix.id));
+	info->par = fbh;
+	info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT;
+	info->fbops = &armada_fb_ops;
+	info->fix.smem_start = obj->phys_addr;
+	info->fix.smem_len = obj->obj.size;
+	info->screen_size = obj->obj.size;
+	info->screen_base = ptr;
+	fbh->fb = &dfb->fb;
+	fbh->fbdev = info;
+	drm_fb_helper_fill_fix(info, dfb->fb.pitches[0], dfb->fb.depth);
+	drm_fb_helper_fill_var(info, fbh, sizes->fb_width, sizes->fb_height);
+
+	DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08x\n",
+		dfb->fb.width, dfb->fb.height,
+		dfb->fb.bits_per_pixel, obj->phys_addr);
+
+	return 0;
+
+ err_fbcmap:
+	framebuffer_release(info);
+ err_fballoc:
+	dfb->fb.funcs->destroy(&dfb->fb);
+	return ret;
+}
+
+static int armada_fb_probe(struct drm_fb_helper *fbh,
+	struct drm_fb_helper_surface_size *sizes)
+{
+	int ret = 0;
+
+	if (!fbh->fb) {
+		ret = armada_fb_create(fbh, sizes);
+		if (ret == 0)
+			ret = 1;
+	}
+	return ret;
+}
+
+static struct drm_fb_helper_funcs armada_fb_helper_funcs = {
+	.gamma_set	= armada_drm_crtc_gamma_set,
+	.gamma_get	= armada_drm_crtc_gamma_get,
+	.fb_probe	= armada_fb_probe,
+};
+
+int armada_fbdev_init(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct drm_fb_helper *fbh;
+	int ret;
+
+	fbh = devm_kzalloc(dev->dev, sizeof(*fbh), GFP_KERNEL);
+	if (!fbh)
+		return -ENOMEM;
+
+	priv->fbdev = fbh;
+
+	fbh->funcs = &armada_fb_helper_funcs;
+
+	ret = drm_fb_helper_init(dev, fbh, 1, 1);
+	if (ret) {
+		DRM_ERROR("failed to initialize drm fb helper\n");
+		goto err_fb_helper;
+	}
+
+	ret = drm_fb_helper_single_add_all_connectors(fbh);
+	if (ret) {
+		DRM_ERROR("failed to add fb connectors\n");
+		goto err_fb_setup;
+	}
+
+	ret = drm_fb_helper_initial_config(fbh, 32);
+	if (ret) {
+		DRM_ERROR("failed to set initial config\n");
+		goto err_fb_setup;
+	}
+
+	return 0;
+ err_fb_setup:
+	drm_fb_helper_fini(fbh);
+ err_fb_helper:
+	priv->fbdev = NULL;
+	return ret;
+}
+
+void armada_fbdev_fini(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct drm_fb_helper *fbh = priv->fbdev;
+
+	if (fbh) {
+		struct fb_info *info = fbh->fbdev;
+
+		if (info) {
+			unregister_framebuffer(info);
+			if (info->cmap.len)
+				fb_dealloc_cmap(&info->cmap);
+			framebuffer_release(info);
+		}
+
+		if (fbh->fb)
+			fbh->fb->funcs->destroy(fbh->fb);
+
+		drm_fb_helper_fini(fbh);
+
+		priv->fbdev = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
new file mode 100644
index 000000000000..9f2356bae7fd
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -0,0 +1,611 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/dma-buf.h>
+#include <linux/dma-mapping.h>
+#include <linux/shmem_fs.h>
+#include <drm/drmP.h>
+#include "armada_drm.h"
+#include "armada_gem.h"
+#include <drm/armada_drm.h>
+#include "armada_ioctlP.h"
+
+static int armada_gem_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct armada_gem_object *obj = drm_to_armada_gem(vma->vm_private_data);
+	unsigned long addr = (unsigned long)vmf->virtual_address;
+	unsigned long pfn = obj->phys_addr >> PAGE_SHIFT;
+	int ret;
+
+	pfn += (addr - vma->vm_start) >> PAGE_SHIFT;
+	ret = vm_insert_pfn(vma, addr, pfn);
+
+	switch (ret) {
+	case 0:
+	case -EBUSY:
+		return VM_FAULT_NOPAGE;
+	case -ENOMEM:
+		return VM_FAULT_OOM;
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+const struct vm_operations_struct armada_gem_vm_ops = {
+	.fault	= armada_gem_vm_fault,
+	.open	= drm_gem_vm_open,
+	.close	= drm_gem_vm_close,
+};
+
+static size_t roundup_gem_size(size_t size)
+{
+	return roundup(size, PAGE_SIZE);
+}
+
+/* dev->struct_mutex is held here */
+void armada_gem_free_object(struct drm_gem_object *obj)
+{
+	struct armada_gem_object *dobj = drm_to_armada_gem(obj);
+
+	DRM_DEBUG_DRIVER("release obj %p\n", dobj);
+
+	drm_gem_free_mmap_offset(&dobj->obj);
+
+	if (dobj->page) {
+		/* page backed memory */
+		unsigned int order = get_order(dobj->obj.size);
+		__free_pages(dobj->page, order);
+	} else if (dobj->linear) {
+		/* linear backed memory */
+		drm_mm_remove_node(dobj->linear);
+		kfree(dobj->linear);
+		if (dobj->addr)
+			iounmap(dobj->addr);
+	}
+
+	if (dobj->obj.import_attach) {
+		/* We only ever display imported data */
+		dma_buf_unmap_attachment(dobj->obj.import_attach, dobj->sgt,
+					 DMA_TO_DEVICE);
+		drm_prime_gem_destroy(&dobj->obj, NULL);
+	}
+
+	drm_gem_object_release(&dobj->obj);
+
+	kfree(dobj);
+}
+
+int
+armada_gem_linear_back(struct drm_device *dev, struct armada_gem_object *obj)
+{
+	struct armada_private *priv = dev->dev_private;
+	size_t size = obj->obj.size;
+
+	if (obj->page || obj->linear)
+		return 0;
+
+	/*
+	 * If it is a small allocation (typically cursor, which will
+	 * be 32x64 or 64x32 ARGB pixels) try to get it from the system.
+	 * Framebuffers will never be this small (our minimum size for
+	 * framebuffers is larger than this anyway.)  Such objects are
+	 * only accessed by the CPU so we don't need any special handing
+	 * here.
+	 */
+	if (size <= 8192) {
+		unsigned int order = get_order(size);
+		struct page *p = alloc_pages(GFP_KERNEL, order);
+
+		if (p) {
+			obj->addr = page_address(p);
+			obj->phys_addr = page_to_phys(p);
+			obj->page = p;
+
+			memset(obj->addr, 0, PAGE_ALIGN(size));
+		}
+	}
+
+	/*
+	 * We could grab something from CMA if it's enabled, but that
+	 * involves building in a problem:
+	 *
+	 * CMA's interface uses dma_alloc_coherent(), which provides us
+	 * with an CPU virtual address and a device address.
+	 *
+	 * The CPU virtual address may be either an address in the kernel
+	 * direct mapped region (for example, as it would be on x86) or
+	 * it may be remapped into another part of kernel memory space
+	 * (eg, as it would be on ARM.)  This means virt_to_phys() on the
+	 * returned virtual address is invalid depending on the architecture
+	 * implementation.
+	 *
+	 * The device address may also not be a physical address; it may
+	 * be that there is some kind of remapping between the device and
+	 * system RAM, which makes the use of the device address also
+	 * unsafe to re-use as a physical address.
+	 *
+	 * This makes DRM usage of dma_alloc_coherent() in a generic way
+	 * at best very questionable and unsafe.
+	 */
+
+	/* Otherwise, grab it from our linear allocation */
+	if (!obj->page) {
+		struct drm_mm_node *node;
+		unsigned align = min_t(unsigned, size, SZ_2M);
+		void __iomem *ptr;
+		int ret;
+
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node)
+			return -ENOSPC;
+
+		mutex_lock(&dev->struct_mutex);
+		ret = drm_mm_insert_node(&priv->linear, node, size, align,
+					 DRM_MM_SEARCH_DEFAULT);
+		mutex_unlock(&dev->struct_mutex);
+		if (ret) {
+			kfree(node);
+			return ret;
+		}
+
+		obj->linear = node;
+
+		/* Ensure that the memory we're returning is cleared. */
+		ptr = ioremap_wc(obj->linear->start, size);
+		if (!ptr) {
+			mutex_lock(&dev->struct_mutex);
+			drm_mm_remove_node(obj->linear);
+			mutex_unlock(&dev->struct_mutex);
+			kfree(obj->linear);
+			obj->linear = NULL;
+			return -ENOMEM;
+		}
+
+		memset_io(ptr, 0, size);
+		iounmap(ptr);
+
+		obj->phys_addr = obj->linear->start;
+		obj->dev_addr = obj->linear->start;
+	}
+
+	DRM_DEBUG_DRIVER("obj %p phys %#x dev %#x\n",
+			 obj, obj->phys_addr, obj->dev_addr);
+
+	return 0;
+}
+
+void *
+armada_gem_map_object(struct drm_device *dev, struct armada_gem_object *dobj)
+{
+	/* only linear objects need to be ioremap'd */
+	if (!dobj->addr && dobj->linear)
+		dobj->addr = ioremap_wc(dobj->phys_addr, dobj->obj.size);
+	return dobj->addr;
+}
+
+struct armada_gem_object *
+armada_gem_alloc_private_object(struct drm_device *dev, size_t size)
+{
+	struct armada_gem_object *obj;
+
+	size = roundup_gem_size(size);
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return NULL;
+
+	drm_gem_private_object_init(dev, &obj->obj, size);
+	obj->dev_addr = DMA_ERROR_CODE;
+
+	DRM_DEBUG_DRIVER("alloc private obj %p size %zu\n", obj, size);
+
+	return obj;
+}
+
+struct armada_gem_object *armada_gem_alloc_object(struct drm_device *dev,
+	size_t size)
+{
+	struct armada_gem_object *obj;
+	struct address_space *mapping;
+
+	size = roundup_gem_size(size);
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return NULL;
+
+	if (drm_gem_object_init(dev, &obj->obj, size)) {
+		kfree(obj);
+		return NULL;
+	}
+
+	obj->dev_addr = DMA_ERROR_CODE;
+
+	mapping = obj->obj.filp->f_path.dentry->d_inode->i_mapping;
+	mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE);
+
+	DRM_DEBUG_DRIVER("alloc obj %p size %zu\n", obj, size);
+
+	return obj;
+}
+
+/* Dumb alloc support */
+int armada_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
+	struct drm_mode_create_dumb *args)
+{
+	struct armada_gem_object *dobj;
+	u32 handle;
+	size_t size;
+	int ret;
+
+	args->pitch = armada_pitch(args->width, args->bpp);
+	args->size = size = args->pitch * args->height;
+
+	dobj = armada_gem_alloc_private_object(dev, size);
+	if (dobj == NULL)
+		return -ENOMEM;
+
+	ret = armada_gem_linear_back(dev, dobj);
+	if (ret)
+		goto err;
+
+	ret = drm_gem_handle_create(file, &dobj->obj, &handle);
+	if (ret)
+		goto err;
+
+	args->handle = handle;
+
+	/* drop reference from allocate - handle holds it now */
+	DRM_DEBUG_DRIVER("obj %p size %zu handle %#x\n", dobj, size, handle);
+ err:
+	drm_gem_object_unreference_unlocked(&dobj->obj);
+	return ret;
+}
+
+int armada_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
+	uint32_t handle, uint64_t *offset)
+{
+	struct armada_gem_object *obj;
+	int ret = 0;
+
+	mutex_lock(&dev->struct_mutex);
+	obj = armada_gem_object_lookup(dev, file, handle);
+	if (!obj) {
+		DRM_ERROR("failed to lookup gem object\n");
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	/* Don't allow imported objects to be mapped */
+	if (obj->obj.import_attach) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	ret = drm_gem_create_mmap_offset(&obj->obj);
+	if (ret == 0) {
+		*offset = drm_vma_node_offset_addr(&obj->obj.vma_node);
+		DRM_DEBUG_DRIVER("handle %#x offset %llx\n", handle, *offset);
+	}
+
+	drm_gem_object_unreference(&obj->obj);
+ err_unlock:
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+int armada_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
+	uint32_t handle)
+{
+	return drm_gem_handle_delete(file, handle);
+}
+
+/* Private driver gem ioctls */
+int armada_gem_create_ioctl(struct drm_device *dev, void *data,
+	struct drm_file *file)
+{
+	struct drm_armada_gem_create *args = data;
+	struct armada_gem_object *dobj;
+	size_t size;
+	u32 handle;
+	int ret;
+
+	if (args->size == 0)
+		return -ENOMEM;
+
+	size = args->size;
+
+	dobj = armada_gem_alloc_object(dev, size);
+	if (dobj == NULL)
+		return -ENOMEM;
+
+	ret = drm_gem_handle_create(file, &dobj->obj, &handle);
+	if (ret)
+		goto err;
+
+	args->handle = handle;
+
+	/* drop reference from allocate - handle holds it now */
+	DRM_DEBUG_DRIVER("obj %p size %zu handle %#x\n", dobj, size, handle);
+ err:
+	drm_gem_object_unreference_unlocked(&dobj->obj);
+	return ret;
+}
+
+/* Map a shmem-backed object into process memory space */
+int armada_gem_mmap_ioctl(struct drm_device *dev, void *data,
+	struct drm_file *file)
+{
+	struct drm_armada_gem_mmap *args = data;
+	struct armada_gem_object *dobj;
+	unsigned long addr;
+
+	dobj = armada_gem_object_lookup(dev, file, args->handle);
+	if (dobj == NULL)
+		return -ENOENT;
+
+	if (!dobj->obj.filp) {
+		drm_gem_object_unreference(&dobj->obj);
+		return -EINVAL;
+	}
+
+	addr = vm_mmap(dobj->obj.filp, 0, args->size, PROT_READ | PROT_WRITE,
+		       MAP_SHARED, args->offset);
+	drm_gem_object_unreference(&dobj->obj);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	args->addr = addr;
+
+	return 0;
+}
+
+int armada_gem_pwrite_ioctl(struct drm_device *dev, void *data,
+	struct drm_file *file)
+{
+	struct drm_armada_gem_pwrite *args = data;
+	struct armada_gem_object *dobj;
+	char __user *ptr;
+	int ret;
+
+	DRM_DEBUG_DRIVER("handle %u off %u size %u ptr 0x%llx\n",
+		args->handle, args->offset, args->size, args->ptr);
+
+	if (args->size == 0)
+		return 0;
+
+	ptr = (char __user *)(uintptr_t)args->ptr;
+
+	if (!access_ok(VERIFY_READ, ptr, args->size))
+		return -EFAULT;
+
+	ret = fault_in_multipages_readable(ptr, args->size);
+	if (ret)
+		return ret;
+
+	dobj = armada_gem_object_lookup(dev, file, args->handle);
+	if (dobj == NULL)
+		return -ENOENT;
+
+	/* Must be a kernel-mapped object */
+	if (!dobj->addr)
+		return -EINVAL;
+
+	if (args->offset > dobj->obj.size ||
+	    args->size > dobj->obj.size - args->offset) {
+		DRM_ERROR("invalid size: object size %u\n", dobj->obj.size);
+		ret = -EINVAL;
+		goto unref;
+	}
+
+	if (copy_from_user(dobj->addr + args->offset, ptr, args->size)) {
+		ret = -EFAULT;
+	} else if (dobj->update) {
+		dobj->update(dobj->update_data);
+		ret = 0;
+	}
+
+ unref:
+	drm_gem_object_unreference_unlocked(&dobj->obj);
+	return ret;
+}
+
+/* Prime support */
+struct sg_table *
+armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
+	enum dma_data_direction dir)
+{
+	struct drm_gem_object *obj = attach->dmabuf->priv;
+	struct armada_gem_object *dobj = drm_to_armada_gem(obj);
+	struct scatterlist *sg;
+	struct sg_table *sgt;
+	int i, num;
+
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt)
+		return NULL;
+
+	if (dobj->obj.filp) {
+		struct address_space *mapping;
+		gfp_t gfp;
+		int count;
+
+		count = dobj->obj.size / PAGE_SIZE;
+		if (sg_alloc_table(sgt, count, GFP_KERNEL))
+			goto free_sgt;
+
+		mapping = file_inode(dobj->obj.filp)->i_mapping;
+		gfp = mapping_gfp_mask(mapping);
+
+		for_each_sg(sgt->sgl, sg, count, i) {
+			struct page *page;
+
+			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+			if (IS_ERR(page)) {
+				num = i;
+				goto release;
+			}
+
+			sg_set_page(sg, page, PAGE_SIZE, 0);
+		}
+
+		if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) {
+			num = sgt->nents;
+			goto release;
+		}
+	} else if (dobj->page) {
+		/* Single contiguous page */
+		if (sg_alloc_table(sgt, 1, GFP_KERNEL))
+			goto free_sgt;
+
+		sg_set_page(sgt->sgl, dobj->page, dobj->obj.size, 0);
+
+		if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0)
+			goto free_table;
+	} else if (dobj->linear) {
+		/* Single contiguous physical region - no struct page */
+		if (sg_alloc_table(sgt, 1, GFP_KERNEL))
+			goto free_sgt;
+		sg_dma_address(sgt->sgl) = dobj->dev_addr;
+		sg_dma_len(sgt->sgl) = dobj->obj.size;
+	} else {
+		goto free_sgt;
+	}
+	return sgt;
+
+ release:
+	for_each_sg(sgt->sgl, sg, num, i)
+		page_cache_release(sg_page(sg));
+ free_table:
+	sg_free_table(sgt);
+ free_sgt:
+	kfree(sgt);
+	return NULL;
+}
+
+static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
+	struct sg_table *sgt, enum dma_data_direction dir)
+{
+	struct drm_gem_object *obj = attach->dmabuf->priv;
+	struct armada_gem_object *dobj = drm_to_armada_gem(obj);
+	int i;
+
+	if (!dobj->linear)
+		dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+
+	if (dobj->obj.filp) {
+		struct scatterlist *sg;
+		for_each_sg(sgt->sgl, sg, sgt->nents, i)
+			page_cache_release(sg_page(sg));
+	}
+
+	sg_free_table(sgt);
+	kfree(sgt);
+}
+
+static void *armada_gem_dmabuf_no_kmap(struct dma_buf *buf, unsigned long n)
+{
+	return NULL;
+}
+
+static void
+armada_gem_dmabuf_no_kunmap(struct dma_buf *buf, unsigned long n, void *addr)
+{
+}
+
+static int
+armada_gem_dmabuf_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
+{
+	return -EINVAL;
+}
+
+static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = {
+	.map_dma_buf	= armada_gem_prime_map_dma_buf,
+	.unmap_dma_buf	= armada_gem_prime_unmap_dma_buf,
+	.release	= drm_gem_dmabuf_release,
+	.kmap_atomic	= armada_gem_dmabuf_no_kmap,
+	.kunmap_atomic	= armada_gem_dmabuf_no_kunmap,
+	.kmap		= armada_gem_dmabuf_no_kmap,
+	.kunmap		= armada_gem_dmabuf_no_kunmap,
+	.mmap		= armada_gem_dmabuf_mmap,
+};
+
+struct dma_buf *
+armada_gem_prime_export(struct drm_device *dev, struct drm_gem_object *obj,
+	int flags)
+{
+	return dma_buf_export(obj, &armada_gem_prime_dmabuf_ops, obj->size,
+			      O_RDWR);
+}
+
+struct drm_gem_object *
+armada_gem_prime_import(struct drm_device *dev, struct dma_buf *buf)
+{
+	struct dma_buf_attachment *attach;
+	struct armada_gem_object *dobj;
+
+	if (buf->ops == &armada_gem_prime_dmabuf_ops) {
+		struct drm_gem_object *obj = buf->priv;
+		if (obj->dev == dev) {
+			/*
+			 * Importing our own dmabuf(s) increases the
+			 * refcount on the gem object itself.
+			 */
+			drm_gem_object_reference(obj);
+			dma_buf_put(buf);
+			return obj;
+		}
+	}
+
+	attach = dma_buf_attach(buf, dev->dev);
+	if (IS_ERR(attach))
+		return ERR_CAST(attach);
+
+	dobj = armada_gem_alloc_private_object(dev, buf->size);
+	if (!dobj) {
+		dma_buf_detach(buf, attach);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dobj->obj.import_attach = attach;
+
+	/*
+	 * Don't call dma_buf_map_attachment() here - it maps the
+	 * scatterlist immediately for DMA, and this is not always
+	 * an appropriate thing to do.
+	 */
+	return &dobj->obj;
+}
+
+int armada_gem_map_import(struct armada_gem_object *dobj)
+{
+	int ret;
+
+	dobj->sgt = dma_buf_map_attachment(dobj->obj.import_attach,
+					  DMA_TO_DEVICE);
+	if (!dobj->sgt) {
+		DRM_ERROR("dma_buf_map_attachment() returned NULL\n");
+		return -EINVAL;
+	}
+	if (IS_ERR(dobj->sgt)) {
+		ret = PTR_ERR(dobj->sgt);
+		dobj->sgt = NULL;
+		DRM_ERROR("dma_buf_map_attachment() error: %d\n", ret);
+		return ret;
+	}
+	if (dobj->sgt->nents > 1) {
+		DRM_ERROR("dma_buf_map_attachment() returned an (unsupported) scattered list\n");
+		return -EINVAL;
+	}
+	if (sg_dma_len(dobj->sgt->sgl) < dobj->obj.size) {
+		DRM_ERROR("dma_buf_map_attachment() returned a small buffer\n");
+		return -EINVAL;
+	}
+	dobj->dev_addr = sg_dma_address(dobj->sgt->sgl);
+	return 0;
+}
diff --git a/drivers/gpu/drm/armada/armada_gem.h b/drivers/gpu/drm/armada/armada_gem.h
new file mode 100644
index 000000000000..00b6cd461a03
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_gem.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_GEM_H
+#define ARMADA_GEM_H
+
+/* GEM */
+struct armada_gem_object {
+	struct drm_gem_object	obj;
+	void			*addr;
+	phys_addr_t		phys_addr;
+	resource_size_t		dev_addr;
+	struct drm_mm_node	*linear;	/* for linear backed */
+	struct page		*page;		/* for page backed */
+	struct sg_table		*sgt;		/* for imported */
+	void			(*update)(void *);
+	void			*update_data;
+};
+
+extern const struct vm_operations_struct armada_gem_vm_ops;
+
+#define drm_to_armada_gem(o) container_of(o, struct armada_gem_object, obj)
+
+void armada_gem_free_object(struct drm_gem_object *);
+int armada_gem_linear_back(struct drm_device *, struct armada_gem_object *);
+void *armada_gem_map_object(struct drm_device *, struct armada_gem_object *);
+struct armada_gem_object *armada_gem_alloc_private_object(struct drm_device *,
+	size_t);
+int armada_gem_dumb_create(struct drm_file *, struct drm_device *,
+	struct drm_mode_create_dumb *);
+int armada_gem_dumb_map_offset(struct drm_file *, struct drm_device *,
+	uint32_t, uint64_t *);
+int armada_gem_dumb_destroy(struct drm_file *, struct drm_device *,
+	uint32_t);
+struct dma_buf *armada_gem_prime_export(struct drm_device *dev,
+	struct drm_gem_object *obj, int flags);
+struct drm_gem_object *armada_gem_prime_import(struct drm_device *,
+	struct dma_buf *);
+int armada_gem_map_import(struct armada_gem_object *);
+
+static inline struct armada_gem_object *armada_gem_object_lookup(
+	struct drm_device *dev, struct drm_file *dfile, unsigned handle)
+{
+	struct drm_gem_object *obj = drm_gem_object_lookup(dev, dfile, handle);
+
+	return obj ? drm_to_armada_gem(obj) : NULL;
+}
+#endif
diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h
new file mode 100644
index 000000000000..216a4b50c36b
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_hw.h
@@ -0,0 +1,316 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_HW_H
+#define ARMADA_HW_H
+
+/*
+ * Note: the following registers are written from IRQ context:
+ *  LCD_SPU_V_PORCH, LCD_SPU_ADV_REG, LCD_SPUT_V_H_TOTAL
+ *  LCD_SPU_DMA_START_ADDR_[YUV][01], LCD_SPU_DMA_PITCH_YC,
+ *  LCD_SPU_DMA_PITCH_UV, LCD_SPU_DMA_OVSA_HPXL_VLN,
+ *  LCD_SPU_DMA_HPXL_VLN, LCD_SPU_DZM_HPXL_VLN, LCD_SPU_DMA_CTRL0
+ */
+enum {
+	LCD_SPU_ADV_REG			= 0x0084,	/* Armada 510 */
+	LCD_SPU_DMA_START_ADDR_Y0	= 0x00c0,
+	LCD_SPU_DMA_START_ADDR_U0	= 0x00c4,
+	LCD_SPU_DMA_START_ADDR_V0	= 0x00c8,
+	LCD_CFG_DMA_START_ADDR_0	= 0x00cc,
+	LCD_SPU_DMA_START_ADDR_Y1	= 0x00d0,
+	LCD_SPU_DMA_START_ADDR_U1	= 0x00d4,
+	LCD_SPU_DMA_START_ADDR_V1	= 0x00d8,
+	LCD_CFG_DMA_START_ADDR_1	= 0x00dc,
+	LCD_SPU_DMA_PITCH_YC		= 0x00e0,
+	LCD_SPU_DMA_PITCH_UV		= 0x00e4,
+	LCD_SPU_DMA_OVSA_HPXL_VLN	= 0x00e8,
+	LCD_SPU_DMA_HPXL_VLN		= 0x00ec,
+	LCD_SPU_DZM_HPXL_VLN		= 0x00f0,
+	LCD_CFG_GRA_START_ADDR0		= 0x00f4,
+	LCD_CFG_GRA_START_ADDR1		= 0x00f8,
+	LCD_CFG_GRA_PITCH		= 0x00fc,
+	LCD_SPU_GRA_OVSA_HPXL_VLN	= 0x0100,
+	LCD_SPU_GRA_HPXL_VLN		= 0x0104,
+	LCD_SPU_GZM_HPXL_VLN		= 0x0108,
+	LCD_SPU_HWC_OVSA_HPXL_VLN	= 0x010c,
+	LCD_SPU_HWC_HPXL_VLN		= 0x0110,
+	LCD_SPUT_V_H_TOTAL		= 0x0114,
+	LCD_SPU_V_H_ACTIVE		= 0x0118,
+	LCD_SPU_H_PORCH			= 0x011c,
+	LCD_SPU_V_PORCH			= 0x0120,
+	LCD_SPU_BLANKCOLOR		= 0x0124,
+	LCD_SPU_ALPHA_COLOR1		= 0x0128,
+	LCD_SPU_ALPHA_COLOR2		= 0x012c,
+	LCD_SPU_COLORKEY_Y		= 0x0130,
+	LCD_SPU_COLORKEY_U		= 0x0134,
+	LCD_SPU_COLORKEY_V		= 0x0138,
+	LCD_CFG_RDREG4F			= 0x013c,	/* Armada 510 */
+	LCD_SPU_SPI_RXDATA		= 0x0140,
+	LCD_SPU_ISA_RXDATA		= 0x0144,
+	LCD_SPU_HWC_RDDAT		= 0x0158,
+	LCD_SPU_GAMMA_RDDAT		= 0x015c,
+	LCD_SPU_PALETTE_RDDAT		= 0x0160,
+	LCD_SPU_IOPAD_IN		= 0x0178,
+	LCD_CFG_RDREG5F			= 0x017c,
+	LCD_SPU_SPI_CTRL		= 0x0180,
+	LCD_SPU_SPI_TXDATA		= 0x0184,
+	LCD_SPU_SMPN_CTRL		= 0x0188,
+	LCD_SPU_DMA_CTRL0		= 0x0190,
+	LCD_SPU_DMA_CTRL1		= 0x0194,
+	LCD_SPU_SRAM_CTRL		= 0x0198,
+	LCD_SPU_SRAM_WRDAT		= 0x019c,
+	LCD_SPU_SRAM_PARA0		= 0x01a0,	/* Armada 510 */
+	LCD_SPU_SRAM_PARA1		= 0x01a4,
+	LCD_CFG_SCLK_DIV		= 0x01a8,
+	LCD_SPU_CONTRAST		= 0x01ac,
+	LCD_SPU_SATURATION		= 0x01b0,
+	LCD_SPU_CBSH_HUE		= 0x01b4,
+	LCD_SPU_DUMB_CTRL		= 0x01b8,
+	LCD_SPU_IOPAD_CONTROL		= 0x01bc,
+	LCD_SPU_IRQ_ENA			= 0x01c0,
+	LCD_SPU_IRQ_ISR			= 0x01c4,
+};
+
+/* For LCD_SPU_ADV_REG */
+enum {
+	ADV_VSYNC_L_OFF	= 0xfff << 20,
+	ADV_GRACOLORKEY	= 1 << 19,
+	ADV_VIDCOLORKEY	= 1 << 18,
+	ADV_HWC32BLEND	= 1 << 15,
+	ADV_HWC32ARGB	= 1 << 14,
+	ADV_HWC32ENABLE	= 1 << 13,
+	ADV_VSYNCOFFEN	= 1 << 12,
+	ADV_VSYNC_H_OFF	= 0xfff << 0,
+};
+
+enum {
+	CFG_565		= 0,
+	CFG_1555	= 1,
+	CFG_888PACK	= 2,
+	CFG_X888	= 3,
+	CFG_8888	= 4,
+	CFG_422PACK	= 5,
+	CFG_422		= 6,
+	CFG_420		= 7,
+	CFG_PSEUDO4	= 9,
+	CFG_PSEUDO8	= 10,
+	CFG_SWAPRB	= 1 << 4,
+	CFG_SWAPUV	= 1 << 3,
+	CFG_SWAPYU	= 1 << 2,
+	CFG_YUV2RGB	= 1 << 1,
+};
+
+/* For LCD_SPU_DMA_CTRL0 */
+enum {
+	CFG_NOBLENDING	= 1 << 31,
+	CFG_GAMMA_ENA	= 1 << 30,
+	CFG_CBSH_ENA	= 1 << 29,
+	CFG_PALETTE_ENA	= 1 << 28,
+	CFG_ARBFAST_ENA	= 1 << 27,
+	CFG_HWC_1BITMOD	= 1 << 26,
+	CFG_HWC_1BITENA	= 1 << 25,
+	CFG_HWC_ENA	= 1 << 24,
+	CFG_DMAFORMAT	= 0xf << 20,
+#define	CFG_DMA_FMT(x)	((x) << 20)
+	CFG_GRAFORMAT	= 0xf << 16,
+#define	CFG_GRA_FMT(x)	((x) << 16)
+#define CFG_GRA_MOD(x)	((x) << 8)
+	CFG_GRA_FTOGGLE	= 1 << 15,
+	CFG_GRA_HSMOOTH	= 1 << 14,
+	CFG_GRA_TSTMODE	= 1 << 13,
+	CFG_GRA_ENA	= 1 << 8,
+#define CFG_DMA_MOD(x)	((x) << 0)
+	CFG_DMA_FTOGGLE	= 1 << 7,
+	CFG_DMA_HSMOOTH	= 1 << 6,
+	CFG_DMA_TSTMODE	= 1 << 5,
+	CFG_DMA_ENA	= 1 << 0,
+};
+
+enum {
+	CKMODE_DISABLE	= 0,
+	CKMODE_Y	= 1,
+	CKMODE_U	= 2,
+	CKMODE_RGB	= 3,
+	CKMODE_V	= 4,
+	CKMODE_R	= 5,
+	CKMODE_G	= 6,
+	CKMODE_B	= 7,
+};
+
+/* For LCD_SPU_DMA_CTRL1 */
+enum {
+	CFG_FRAME_TRIG		= 1 << 31,
+	CFG_VSYNC_INV		= 1 << 27,
+	CFG_CKMODE_MASK		= 0x7 << 24,
+#define CFG_CKMODE(x)		((x) << 24)
+	CFG_CARRY		= 1 << 23,
+	CFG_GATED_CLK		= 1 << 21,
+	CFG_PWRDN_ENA		= 1 << 20,
+	CFG_DSCALE_MASK		= 0x3 << 18,
+	CFG_DSCALE_NONE		= 0x0 << 18,
+	CFG_DSCALE_HALF		= 0x1 << 18,
+	CFG_DSCALE_QUAR		= 0x2 << 18,
+	CFG_ALPHAM_MASK		= 0x3 << 16,
+	CFG_ALPHAM_VIDEO	= 0x0 << 16,
+	CFG_ALPHAM_GRA		= 0x1 << 16,
+	CFG_ALPHAM_CFG		= 0x2 << 16,
+	CFG_ALPHA_MASK		= 0xff << 8,
+	CFG_PIXCMD_MASK		= 0xff,
+};
+
+/* For LCD_SPU_SRAM_CTRL */
+enum {
+	SRAM_READ	= 0 << 14,
+	SRAM_WRITE	= 2 << 14,
+	SRAM_INIT	= 3 << 14,
+	SRAM_HWC32_RAMR	= 0xc << 8,
+	SRAM_HWC32_RAMG	= 0xd << 8,
+	SRAM_HWC32_RAMB	= 0xe << 8,
+	SRAM_HWC32_TRAN	= 0xf << 8,
+	SRAM_HWC	= 0xf << 8,
+};
+
+/* For LCD_SPU_SRAM_PARA1 */
+enum {
+	CFG_CSB_256x32	= 1 << 15,	/* cursor */
+	CFG_CSB_256x24	= 1 << 14,	/* palette */
+	CFG_CSB_256x8	= 1 << 13,	/* gamma */
+	CFG_PDWN1920x32	= 1 << 8,	/* Armada 510: power down vscale ram */
+	CFG_PDWN256x32	= 1 << 7,	/* power down cursor */
+	CFG_PDWN256x24	= 1 << 6,	/* power down palette */
+	CFG_PDWN256x8	= 1 << 5,	/* power down gamma */
+	CFG_PDWNHWC	= 1 << 4,	/* Armada 510: power down all hwc ram */
+	CFG_PDWN32x32	= 1 << 3,	/* power down slave->smart ram */
+	CFG_PDWN16x66	= 1 << 2,	/* power down UV fifo */
+	CFG_PDWN32x66	= 1 << 1,	/* power down Y fifo */
+	CFG_PDWN64x66	= 1 << 0,	/* power down graphic fifo */
+};
+
+/* For LCD_CFG_SCLK_DIV */
+enum {
+	/* Armada 510 */
+	SCLK_510_AXI		= 0x0 << 30,
+	SCLK_510_EXTCLK0	= 0x1 << 30,
+	SCLK_510_PLL		= 0x2 << 30,
+	SCLK_510_EXTCLK1	= 0x3 << 30,
+	SCLK_510_DIV_CHANGE	= 1 << 29,
+	SCLK_510_FRAC_DIV_MASK	= 0xfff << 16,
+	SCLK_510_INT_DIV_MASK	= 0xffff << 0,
+
+	/* Armada 16x */
+	SCLK_16X_AHB		= 0x0 << 28,
+	SCLK_16X_PCLK		= 0x1 << 28,
+	SCLK_16X_AXI		= 0x4 << 28,
+	SCLK_16X_PLL		= 0x8 << 28,
+	SCLK_16X_FRAC_DIV_MASK	= 0xfff << 16,
+	SCLK_16X_INT_DIV_MASK	= 0xffff << 0,
+};
+
+/* For LCD_SPU_DUMB_CTRL */
+enum {
+	DUMB16_RGB565_0	= 0x0 << 28,
+	DUMB16_RGB565_1	= 0x1 << 28,
+	DUMB18_RGB666_0	= 0x2 << 28,
+	DUMB18_RGB666_1	= 0x3 << 28,
+	DUMB12_RGB444_0	= 0x4 << 28,
+	DUMB12_RGB444_1	= 0x5 << 28,
+	DUMB24_RGB888_0	= 0x6 << 28,
+	DUMB_BLANK	= 0x7 << 28,
+	DUMB_MASK	= 0xf << 28,
+	CFG_BIAS_OUT	= 1 << 8,
+	CFG_REV_RGB	= 1 << 7,
+	CFG_INV_CBLANK	= 1 << 6,
+	CFG_INV_CSYNC	= 1 << 5,	/* Normally active high */
+	CFG_INV_HENA	= 1 << 4,
+	CFG_INV_VSYNC	= 1 << 3,	/* Normally active high */
+	CFG_INV_HSYNC	= 1 << 2,	/* Normally active high */
+	CFG_INV_PCLK	= 1 << 1,
+	CFG_DUMB_ENA	= 1 << 0,
+};
+
+/* For LCD_SPU_IOPAD_CONTROL */
+enum {
+	CFG_VSCALE_LN_EN	= 3 << 18,
+	CFG_GRA_VM_ENA		= 1 << 15,
+	CFG_DMA_VM_ENA		= 1 << 13,
+	CFG_CMD_VM_ENA		= 1 << 11,
+	CFG_CSC_MASK		= 3 << 8,
+	CFG_CSC_YUV_CCIR709	= 1 << 9,
+	CFG_CSC_YUV_CCIR601	= 0 << 9,
+	CFG_CSC_RGB_STUDIO	= 1 << 8,
+	CFG_CSC_RGB_COMPUTER	= 0 << 8,
+	CFG_IOPAD_MASK		= 0xf << 0,
+	CFG_IOPAD_DUMB24	= 0x0 << 0,
+	CFG_IOPAD_DUMB18SPI	= 0x1 << 0,
+	CFG_IOPAD_DUMB18GPIO	= 0x2 << 0,
+	CFG_IOPAD_DUMB16SPI	= 0x3 << 0,
+	CFG_IOPAD_DUMB16GPIO	= 0x4 << 0,
+	CFG_IOPAD_DUMB12GPIO	= 0x5 << 0,
+	CFG_IOPAD_SMART18	= 0x6 << 0,
+	CFG_IOPAD_SMART16	= 0x7 << 0,
+	CFG_IOPAD_SMART8	= 0x8 << 0,
+};
+
+#define IOPAD_DUMB24                0x0
+
+/* For LCD_SPU_IRQ_ENA */
+enum {
+	DMA_FRAME_IRQ0_ENA	= 1 << 31,
+	DMA_FRAME_IRQ1_ENA	= 1 << 30,
+	DMA_FRAME_IRQ_ENA	= DMA_FRAME_IRQ0_ENA | DMA_FRAME_IRQ1_ENA,
+	DMA_FF_UNDERFLOW_ENA	= 1 << 29,
+	GRA_FRAME_IRQ0_ENA	= 1 << 27,
+	GRA_FRAME_IRQ1_ENA	= 1 << 26,
+	GRA_FRAME_IRQ_ENA	= GRA_FRAME_IRQ0_ENA | GRA_FRAME_IRQ1_ENA,
+	GRA_FF_UNDERFLOW_ENA	= 1 << 25,
+	VSYNC_IRQ_ENA		= 1 << 23,
+	DUMB_FRAMEDONE_ENA	= 1 << 22,
+	TWC_FRAMEDONE_ENA	= 1 << 21,
+	HWC_FRAMEDONE_ENA	= 1 << 20,
+	SLV_IRQ_ENA		= 1 << 19,
+	SPI_IRQ_ENA		= 1 << 18,
+	PWRDN_IRQ_ENA		= 1 << 17,
+	ERR_IRQ_ENA		= 1 << 16,
+	CLEAN_SPU_IRQ_ISR	= 0xffff,
+};
+
+/* For LCD_SPU_IRQ_ISR */
+enum {
+	DMA_FRAME_IRQ0		= 1 << 31,
+	DMA_FRAME_IRQ1		= 1 << 30,
+	DMA_FRAME_IRQ		= DMA_FRAME_IRQ0 | DMA_FRAME_IRQ1,
+	DMA_FF_UNDERFLOW	= 1 << 29,
+	GRA_FRAME_IRQ0		= 1 << 27,
+	GRA_FRAME_IRQ1		= 1 << 26,
+	GRA_FRAME_IRQ		= GRA_FRAME_IRQ0 | GRA_FRAME_IRQ1,
+	GRA_FF_UNDERFLOW	= 1 << 25,
+	VSYNC_IRQ		= 1 << 23,
+	DUMB_FRAMEDONE		= 1 << 22,
+	TWC_FRAMEDONE		= 1 << 21,
+	HWC_FRAMEDONE		= 1 << 20,
+	SLV_IRQ			= 1 << 19,
+	SPI_IRQ			= 1 << 18,
+	PWRDN_IRQ		= 1 << 17,
+	ERR_IRQ			= 1 << 16,
+	DMA_FRAME_IRQ0_LEVEL	= 1 << 15,
+	DMA_FRAME_IRQ1_LEVEL	= 1 << 14,
+	DMA_FRAME_CNT_ISR	= 3 << 12,
+	GRA_FRAME_IRQ0_LEVEL	= 1 << 11,
+	GRA_FRAME_IRQ1_LEVEL	= 1 << 10,
+	GRA_FRAME_CNT_ISR	= 3 << 8,
+	VSYNC_IRQ_LEVEL		= 1 << 7,
+	DUMB_FRAMEDONE_LEVEL	= 1 << 6,
+	TWC_FRAMEDONE_LEVEL	= 1 << 5,
+	HWC_FRAMEDONE_LEVEL	= 1 << 4,
+	SLV_FF_EMPTY		= 1 << 3,
+	DMA_FF_ALLEMPTY		= 1 << 2,
+	GRA_FF_ALLEMPTY		= 1 << 1,
+	PWRDN_IRQ_LEVEL		= 1 << 0,
+};
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_ioctlP.h b/drivers/gpu/drm/armada/armada_ioctlP.h
new file mode 100644
index 000000000000..bd8c4562066c
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_ioctlP.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_IOCTLP_H
+#define ARMADA_IOCTLP_H
+
+#define ARMADA_IOCTL_PROTO(name)\
+extern int armada_##name##_ioctl(struct drm_device *, void *, struct drm_file *)
+
+ARMADA_IOCTL_PROTO(gem_create);
+ARMADA_IOCTL_PROTO(gem_mmap);
+ARMADA_IOCTL_PROTO(gem_pwrite);
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_output.c b/drivers/gpu/drm/armada/armada_output.c
new file mode 100644
index 000000000000..d685a5421485
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_output.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_encoder_slave.h>
+#include "armada_output.h"
+#include "armada_drm.h"
+
+struct armada_connector {
+	struct drm_connector conn;
+	const struct armada_output_type *type;
+};
+
+#define drm_to_armada_conn(c) container_of(c, struct armada_connector, conn)
+
+struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn)
+{
+	struct drm_encoder *enc = conn->encoder;
+
+	return enc ? enc : drm_encoder_find(conn->dev, conn->encoder_ids[0]);
+}
+
+static enum drm_connector_status armada_drm_connector_detect(
+	struct drm_connector *conn, bool force)
+{
+	struct armada_connector *dconn = drm_to_armada_conn(conn);
+	enum drm_connector_status status = connector_status_disconnected;
+
+	if (dconn->type->detect) {
+		status = dconn->type->detect(conn, force);
+	} else {
+		struct drm_encoder *enc = armada_drm_connector_encoder(conn);
+
+		if (enc)
+			status = encoder_helper_funcs(enc)->detect(enc, conn);
+	}
+
+	return status;
+}
+
+static void armada_drm_connector_destroy(struct drm_connector *conn)
+{
+	struct armada_connector *dconn = drm_to_armada_conn(conn);
+
+	drm_sysfs_connector_remove(conn);
+	drm_connector_cleanup(conn);
+	kfree(dconn);
+}
+
+static int armada_drm_connector_set_property(struct drm_connector *conn,
+	struct drm_property *property, uint64_t value)
+{
+	struct armada_connector *dconn = drm_to_armada_conn(conn);
+
+	if (!dconn->type->set_property)
+		return -EINVAL;
+
+	return dconn->type->set_property(conn, property, value);
+}
+
+static const struct drm_connector_funcs armada_drm_conn_funcs = {
+	.dpms		= drm_helper_connector_dpms,
+	.fill_modes	= drm_helper_probe_single_connector_modes,
+	.detect		= armada_drm_connector_detect,
+	.destroy	= armada_drm_connector_destroy,
+	.set_property	= armada_drm_connector_set_property,
+};
+
+void armada_drm_encoder_prepare(struct drm_encoder *encoder)
+{
+	encoder_helper_funcs(encoder)->dpms(encoder, DRM_MODE_DPMS_OFF);
+}
+
+void armada_drm_encoder_commit(struct drm_encoder *encoder)
+{
+	encoder_helper_funcs(encoder)->dpms(encoder, DRM_MODE_DPMS_ON);
+}
+
+bool armada_drm_encoder_mode_fixup(struct drm_encoder *encoder,
+	const struct drm_display_mode *mode, struct drm_display_mode *adjusted)
+{
+	return true;
+}
+
+/* Shouldn't this be a generic helper function? */
+int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn,
+	struct drm_display_mode *mode)
+{
+	struct drm_encoder *encoder = armada_drm_connector_encoder(conn);
+	int valid = MODE_BAD;
+
+	if (encoder) {
+		struct drm_encoder_slave *slave = to_encoder_slave(encoder);
+
+		valid = slave->slave_funcs->mode_valid(encoder, mode);
+	}
+	return valid;
+}
+
+int armada_drm_slave_encoder_set_property(struct drm_connector *conn,
+	struct drm_property *property, uint64_t value)
+{
+	struct drm_encoder *encoder = armada_drm_connector_encoder(conn);
+	int rc = -EINVAL;
+
+	if (encoder) {
+		struct drm_encoder_slave *slave = to_encoder_slave(encoder);
+
+		rc = slave->slave_funcs->set_property(encoder, conn, property,
+						      value);
+	}
+	return rc;
+}
+
+int armada_output_create(struct drm_device *dev,
+	const struct armada_output_type *type, const void *data)
+{
+	struct armada_connector *dconn;
+	int ret;
+
+	dconn = kzalloc(sizeof(*dconn), GFP_KERNEL);
+	if (!dconn)
+		return -ENOMEM;
+
+	dconn->type = type;
+
+	ret = drm_connector_init(dev, &dconn->conn, &armada_drm_conn_funcs,
+				 type->connector_type);
+	if (ret) {
+		DRM_ERROR("unable to init connector\n");
+		goto err_destroy_dconn;
+	}
+
+	ret = type->create(&dconn->conn, data);
+	if (ret)
+		goto err_conn;
+
+	ret = drm_sysfs_connector_add(&dconn->conn);
+	if (ret)
+		goto err_sysfs;
+
+	return 0;
+
+ err_sysfs:
+	if (dconn->conn.encoder)
+		dconn->conn.encoder->funcs->destroy(dconn->conn.encoder);
+ err_conn:
+	drm_connector_cleanup(&dconn->conn);
+ err_destroy_dconn:
+	kfree(dconn);
+	return ret;
+}
diff --git a/drivers/gpu/drm/armada/armada_output.h b/drivers/gpu/drm/armada/armada_output.h
new file mode 100644
index 000000000000..4126d43b5057
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_output.h
@@ -0,0 +1,39 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_CONNETOR_H
+#define ARMADA_CONNETOR_H
+
+#define encoder_helper_funcs(encoder) \
+	((struct drm_encoder_helper_funcs *)encoder->helper_private)
+
+struct armada_output_type {
+	int connector_type;
+	enum drm_connector_status (*detect)(struct drm_connector *, bool);
+	int (*create)(struct drm_connector *, const void *);
+	int (*set_property)(struct drm_connector *, struct drm_property *,
+			    uint64_t);
+};
+
+struct drm_encoder *armada_drm_connector_encoder(struct drm_connector *conn);
+
+void armada_drm_encoder_prepare(struct drm_encoder *encoder);
+void armada_drm_encoder_commit(struct drm_encoder *encoder);
+
+bool armada_drm_encoder_mode_fixup(struct drm_encoder *encoder,
+	const struct drm_display_mode *mode, struct drm_display_mode *adj);
+
+int armada_drm_slave_encoder_mode_valid(struct drm_connector *conn,
+	struct drm_display_mode *mode);
+
+int armada_drm_slave_encoder_set_property(struct drm_connector *conn,
+	struct drm_property *property, uint64_t value);
+
+int armada_output_create(struct drm_device *dev,
+	const struct armada_output_type *type, const void *data);
+
+#endif
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
new file mode 100644
index 000000000000..c5b06fdb459c
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -0,0 +1,477 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+#include <drm/armada_drm.h>
+#include "armada_ioctlP.h"
+
+struct armada_plane_properties {
+	uint32_t colorkey_yr;
+	uint32_t colorkey_ug;
+	uint32_t colorkey_vb;
+#define K2R(val) (((val) >> 0) & 0xff)
+#define K2G(val) (((val) >> 8) & 0xff)
+#define K2B(val) (((val) >> 16) & 0xff)
+	int16_t  brightness;
+	uint16_t contrast;
+	uint16_t saturation;
+	uint32_t colorkey_mode;
+};
+
+struct armada_plane {
+	struct drm_plane base;
+	spinlock_t lock;
+	struct drm_framebuffer *old_fb;
+	uint32_t src_hw;
+	uint32_t dst_hw;
+	uint32_t dst_yx;
+	uint32_t ctrl0;
+	struct {
+		struct armada_vbl_event update;
+		struct armada_regs regs[13];
+		wait_queue_head_t wait;
+	} vbl;
+	struct armada_plane_properties prop;
+};
+#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
+
+
+static void
+armada_ovl_update_attr(struct armada_plane_properties *prop,
+	struct armada_crtc *dcrtc)
+{
+	writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y);
+	writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U);
+	writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V);
+
+	writel_relaxed(prop->brightness << 16 | prop->contrast,
+		       dcrtc->base + LCD_SPU_CONTRAST);
+	/* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */
+	writel_relaxed(prop->saturation << 16,
+		       dcrtc->base + LCD_SPU_SATURATION);
+	writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
+
+	spin_lock_irq(&dcrtc->irq_lock);
+	armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA,
+		     CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+		     dcrtc->base + LCD_SPU_DMA_CTRL1);
+
+	armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG);
+	spin_unlock_irq(&dcrtc->irq_lock);
+}
+
+/* === Plane support === */
+static void armada_plane_vbl(struct armada_crtc *dcrtc, void *data)
+{
+	struct armada_plane *dplane = data;
+	struct drm_framebuffer *fb;
+
+	armada_drm_crtc_update_regs(dcrtc, dplane->vbl.regs);
+
+	spin_lock(&dplane->lock);
+	fb = dplane->old_fb;
+	dplane->old_fb = NULL;
+	spin_unlock(&dplane->lock);
+
+	if (fb)
+		armada_drm_queue_unref_work(dcrtc->crtc.dev, fb);
+}
+
+static unsigned armada_limit(int start, unsigned size, unsigned max)
+{
+	int end = start + size;
+	if (end < 0)
+		return 0;
+	if (start < 0)
+		start = 0;
+	return (unsigned)end > max ? max - start : end - start;
+}
+
+static int
+armada_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+	struct drm_framebuffer *fb,
+	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
+	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h)
+{
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	uint32_t val, ctrl0;
+	unsigned idx = 0;
+	int ret;
+
+	crtc_w = armada_limit(crtc_x, crtc_w, dcrtc->crtc.mode.hdisplay);
+	crtc_h = armada_limit(crtc_y, crtc_h, dcrtc->crtc.mode.vdisplay);
+	ctrl0 = CFG_DMA_FMT(drm_fb_to_armada_fb(fb)->fmt) |
+		CFG_DMA_MOD(drm_fb_to_armada_fb(fb)->mod) |
+		CFG_CBSH_ENA | CFG_DMA_HSMOOTH | CFG_DMA_ENA;
+
+	/* Does the position/size result in nothing to display? */
+	if (crtc_w == 0 || crtc_h == 0) {
+		ctrl0 &= ~CFG_DMA_ENA;
+	}
+
+	/*
+	 * FIXME: if the starting point is off screen, we need to
+	 * adjust src_x, src_y, src_w, src_h appropriately, and
+	 * according to the scale.
+	 */
+
+	if (!dcrtc->plane) {
+		dcrtc->plane = plane;
+		armada_ovl_update_attr(&dplane->prop, dcrtc);
+	}
+
+	/* FIXME: overlay on an interlaced display */
+	/* Just updating the position/size? */
+	if (plane->fb == fb && dplane->ctrl0 == ctrl0) {
+		val = (src_h & 0xffff0000) | src_w >> 16;
+		dplane->src_hw = val;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_HPXL_VLN);
+		val = crtc_h << 16 | crtc_w;
+		dplane->dst_hw = val;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_DZM_HPXL_VLN);
+		val = crtc_y << 16 | crtc_x;
+		dplane->dst_yx = val;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_OVSA_HPXL_VLN);
+		return 0;
+	} else if (~dplane->ctrl0 & ctrl0 & CFG_DMA_ENA) {
+		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
+		armada_updatel(0, CFG_PDWN16x66 | CFG_PDWN32x66,
+			       dcrtc->base + LCD_SPU_SRAM_PARA1);
+	}
+
+	ret = wait_event_timeout(dplane->vbl.wait,
+				 list_empty(&dplane->vbl.update.node),
+				 HZ/25);
+	if (ret < 0)
+		return ret;
+
+	if (plane->fb != fb) {
+		struct armada_gem_object *obj = drm_fb_obj(fb);
+		uint32_t sy, su, sv;
+
+		/*
+		 * Take a reference on the new framebuffer - we want to
+		 * hold on to it while the hardware is displaying it.
+		 */
+		drm_framebuffer_reference(fb);
+
+		if (plane->fb) {
+			struct drm_framebuffer *older_fb;
+
+			spin_lock_irq(&dplane->lock);
+			older_fb = dplane->old_fb;
+			dplane->old_fb = plane->fb;
+			spin_unlock_irq(&dplane->lock);
+			if (older_fb)
+				armada_drm_queue_unref_work(dcrtc->crtc.dev,
+							    older_fb);
+		}
+
+		src_y >>= 16;
+		src_x >>= 16;
+		sy = obj->dev_addr + fb->offsets[0] + src_y * fb->pitches[0] +
+			src_x * fb->bits_per_pixel / 8;
+		su = obj->dev_addr + fb->offsets[1] + src_y * fb->pitches[1] +
+			src_x;
+		sv = obj->dev_addr + fb->offsets[2] + src_y * fb->pitches[2] +
+			src_x;
+
+		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+				     LCD_SPU_DMA_START_ADDR_Y0);
+		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+				     LCD_SPU_DMA_START_ADDR_U0);
+		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+				     LCD_SPU_DMA_START_ADDR_V0);
+		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+				     LCD_SPU_DMA_START_ADDR_Y1);
+		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+				     LCD_SPU_DMA_START_ADDR_U1);
+		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+				     LCD_SPU_DMA_START_ADDR_V1);
+
+		val = fb->pitches[0] << 16 | fb->pitches[0];
+		armada_reg_queue_set(dplane->vbl.regs, idx, val,
+				     LCD_SPU_DMA_PITCH_YC);
+		val = fb->pitches[1] << 16 | fb->pitches[2];
+		armada_reg_queue_set(dplane->vbl.regs, idx, val,
+				     LCD_SPU_DMA_PITCH_UV);
+	}
+
+	val = (src_h & 0xffff0000) | src_w >> 16;
+	if (dplane->src_hw != val) {
+		dplane->src_hw = val;
+		armada_reg_queue_set(dplane->vbl.regs, idx, val,
+				     LCD_SPU_DMA_HPXL_VLN);
+	}
+	val = crtc_h << 16 | crtc_w;
+	if (dplane->dst_hw != val) {
+		dplane->dst_hw = val;
+		armada_reg_queue_set(dplane->vbl.regs, idx, val,
+				     LCD_SPU_DZM_HPXL_VLN);
+	}
+	val = crtc_y << 16 | crtc_x;
+	if (dplane->dst_yx != val) {
+		dplane->dst_yx = val;
+		armada_reg_queue_set(dplane->vbl.regs, idx, val,
+				     LCD_SPU_DMA_OVSA_HPXL_VLN);
+	}
+	if (dplane->ctrl0 != ctrl0) {
+		dplane->ctrl0 = ctrl0;
+		armada_reg_queue_mod(dplane->vbl.regs, idx, ctrl0,
+			CFG_CBSH_ENA | CFG_DMAFORMAT | CFG_DMA_FTOGGLE |
+			CFG_DMA_HSMOOTH | CFG_DMA_TSTMODE |
+			CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | CFG_SWAPYU |
+			CFG_YUV2RGB) | CFG_DMA_ENA,
+			LCD_SPU_DMA_CTRL0);
+	}
+	if (idx) {
+		armada_reg_queue_end(dplane->vbl.regs, idx);
+		armada_drm_vbl_event_add(dcrtc, &dplane->vbl.update);
+	}
+	return 0;
+}
+
+static int armada_plane_disable(struct drm_plane *plane)
+{
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+	struct drm_framebuffer *fb;
+	struct armada_crtc *dcrtc;
+
+	if (!dplane->base.crtc)
+		return 0;
+
+	dcrtc = drm_to_armada_crtc(dplane->base.crtc);
+	dcrtc->plane = NULL;
+
+	spin_lock_irq(&dcrtc->irq_lock);
+	armada_drm_vbl_event_remove(dcrtc, &dplane->vbl.update);
+	armada_updatel(0, CFG_DMA_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
+	dplane->ctrl0 = 0;
+	spin_unlock_irq(&dcrtc->irq_lock);
+
+	/* Power down the Y/U/V FIFOs */
+	armada_updatel(CFG_PDWN16x66 | CFG_PDWN32x66, 0,
+		       dcrtc->base + LCD_SPU_SRAM_PARA1);
+
+	if (plane->fb)
+		drm_framebuffer_unreference(plane->fb);
+
+	spin_lock_irq(&dplane->lock);
+	fb = dplane->old_fb;
+	dplane->old_fb = NULL;
+	spin_unlock_irq(&dplane->lock);
+	if (fb)
+		drm_framebuffer_unreference(fb);
+
+	return 0;
+}
+
+static void armada_plane_destroy(struct drm_plane *plane)
+{
+	kfree(plane);
+}
+
+static int armada_plane_set_property(struct drm_plane *plane,
+	struct drm_property *property, uint64_t val)
+{
+	struct armada_private *priv = plane->dev->dev_private;
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+	bool update_attr = false;
+
+	if (property == priv->colorkey_prop) {
+#define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8)
+		dplane->prop.colorkey_yr = CCC(K2R(val));
+		dplane->prop.colorkey_ug = CCC(K2G(val));
+		dplane->prop.colorkey_vb = CCC(K2B(val));
+#undef CCC
+		update_attr = true;
+	} else if (property == priv->colorkey_min_prop) {
+		dplane->prop.colorkey_yr &= ~0x00ff0000;
+		dplane->prop.colorkey_yr |= K2R(val) << 16;
+		dplane->prop.colorkey_ug &= ~0x00ff0000;
+		dplane->prop.colorkey_ug |= K2G(val) << 16;
+		dplane->prop.colorkey_vb &= ~0x00ff0000;
+		dplane->prop.colorkey_vb |= K2B(val) << 16;
+		update_attr = true;
+	} else if (property == priv->colorkey_max_prop) {
+		dplane->prop.colorkey_yr &= ~0xff000000;
+		dplane->prop.colorkey_yr |= K2R(val) << 24;
+		dplane->prop.colorkey_ug &= ~0xff000000;
+		dplane->prop.colorkey_ug |= K2G(val) << 24;
+		dplane->prop.colorkey_vb &= ~0xff000000;
+		dplane->prop.colorkey_vb |= K2B(val) << 24;
+		update_attr = true;
+	} else if (property == priv->colorkey_val_prop) {
+		dplane->prop.colorkey_yr &= ~0x0000ff00;
+		dplane->prop.colorkey_yr |= K2R(val) << 8;
+		dplane->prop.colorkey_ug &= ~0x0000ff00;
+		dplane->prop.colorkey_ug |= K2G(val) << 8;
+		dplane->prop.colorkey_vb &= ~0x0000ff00;
+		dplane->prop.colorkey_vb |= K2B(val) << 8;
+		update_attr = true;
+	} else if (property == priv->colorkey_alpha_prop) {
+		dplane->prop.colorkey_yr &= ~0x000000ff;
+		dplane->prop.colorkey_yr |= K2R(val);
+		dplane->prop.colorkey_ug &= ~0x000000ff;
+		dplane->prop.colorkey_ug |= K2G(val);
+		dplane->prop.colorkey_vb &= ~0x000000ff;
+		dplane->prop.colorkey_vb |= K2B(val);
+		update_attr = true;
+	} else if (property == priv->colorkey_mode_prop) {
+		dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK;
+		dplane->prop.colorkey_mode |= CFG_CKMODE(val);
+		update_attr = true;
+	} else if (property == priv->brightness_prop) {
+		dplane->prop.brightness = val - 256;
+		update_attr = true;
+	} else if (property == priv->contrast_prop) {
+		dplane->prop.contrast = val;
+		update_attr = true;
+	} else if (property == priv->saturation_prop) {
+		dplane->prop.saturation = val;
+		update_attr = true;
+	}
+
+	if (update_attr && dplane->base.crtc)
+		armada_ovl_update_attr(&dplane->prop,
+				       drm_to_armada_crtc(dplane->base.crtc));
+
+	return 0;
+}
+
+static const struct drm_plane_funcs armada_plane_funcs = {
+	.update_plane	= armada_plane_update,
+	.disable_plane	= armada_plane_disable,
+	.destroy	= armada_plane_destroy,
+	.set_property	= armada_plane_set_property,
+};
+
+static const uint32_t armada_formats[] = {
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YUV420,
+	DRM_FORMAT_YVU420,
+	DRM_FORMAT_YUV422,
+	DRM_FORMAT_YVU422,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+};
+
+static struct drm_prop_enum_list armada_drm_colorkey_enum_list[] = {
+	{ CKMODE_DISABLE, "disabled" },
+	{ CKMODE_Y,       "Y component" },
+	{ CKMODE_U,       "U component" },
+	{ CKMODE_V,       "V component" },
+	{ CKMODE_RGB,     "RGB" },
+	{ CKMODE_R,       "R component" },
+	{ CKMODE_G,       "G component" },
+	{ CKMODE_B,       "B component" },
+};
+
+static int armada_overlay_create_properties(struct drm_device *dev)
+{
+	struct armada_private *priv = dev->dev_private;
+
+	if (priv->colorkey_prop)
+		return 0;
+
+	priv->colorkey_prop = drm_property_create_range(dev, 0,
+				"colorkey", 0, 0xffffff);
+	priv->colorkey_min_prop = drm_property_create_range(dev, 0,
+				"colorkey_min", 0, 0xffffff);
+	priv->colorkey_max_prop = drm_property_create_range(dev, 0,
+				"colorkey_max", 0, 0xffffff);
+	priv->colorkey_val_prop = drm_property_create_range(dev, 0,
+				"colorkey_val", 0, 0xffffff);
+	priv->colorkey_alpha_prop = drm_property_create_range(dev, 0,
+				"colorkey_alpha", 0, 0xffffff);
+	priv->colorkey_mode_prop = drm_property_create_enum(dev, 0,
+				"colorkey_mode",
+				armada_drm_colorkey_enum_list,
+				ARRAY_SIZE(armada_drm_colorkey_enum_list));
+	priv->brightness_prop = drm_property_create_range(dev, 0,
+				"brightness", 0, 256 + 255);
+	priv->contrast_prop = drm_property_create_range(dev, 0,
+				"contrast", 0, 0x7fff);
+	priv->saturation_prop = drm_property_create_range(dev, 0,
+				"saturation", 0, 0x7fff);
+
+	if (!priv->colorkey_prop)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
+{
+	struct armada_private *priv = dev->dev_private;
+	struct drm_mode_object *mobj;
+	struct armada_plane *dplane;
+	int ret;
+
+	ret = armada_overlay_create_properties(dev);
+	if (ret)
+		return ret;
+
+	dplane = kzalloc(sizeof(*dplane), GFP_KERNEL);
+	if (!dplane)
+		return -ENOMEM;
+
+	spin_lock_init(&dplane->lock);
+	init_waitqueue_head(&dplane->vbl.wait);
+	armada_drm_vbl_event_init(&dplane->vbl.update, armada_plane_vbl,
+				  dplane);
+
+	drm_plane_init(dev, &dplane->base, crtcs, &armada_plane_funcs,
+		       armada_formats, ARRAY_SIZE(armada_formats), false);
+
+	dplane->prop.colorkey_yr = 0xfefefe00;
+	dplane->prop.colorkey_ug = 0x01010100;
+	dplane->prop.colorkey_vb = 0x01010100;
+	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB);
+	dplane->prop.brightness = 0;
+	dplane->prop.contrast = 0x4000;
+	dplane->prop.saturation = 0x4000;
+
+	mobj = &dplane->base.base;
+	drm_object_attach_property(mobj, priv->colorkey_prop,
+				   0x0101fe);
+	drm_object_attach_property(mobj, priv->colorkey_min_prop,
+				   0x0101fe);
+	drm_object_attach_property(mobj, priv->colorkey_max_prop,
+				   0x0101fe);
+	drm_object_attach_property(mobj, priv->colorkey_val_prop,
+				   0x0101fe);
+	drm_object_attach_property(mobj, priv->colorkey_alpha_prop,
+				   0x000000);
+	drm_object_attach_property(mobj, priv->colorkey_mode_prop,
+				   CKMODE_RGB);
+	drm_object_attach_property(mobj, priv->brightness_prop, 256);
+	drm_object_attach_property(mobj, priv->contrast_prop,
+				   dplane->prop.contrast);
+	drm_object_attach_property(mobj, priv->saturation_prop,
+				   dplane->prop.saturation);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/armada/armada_slave.c b/drivers/gpu/drm/armada/armada_slave.c
new file mode 100644
index 000000000000..00d0facb42f3
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_slave.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_encoder_slave.h>
+#include "armada_drm.h"
+#include "armada_output.h"
+#include "armada_slave.h"
+
+static int armada_drm_slave_get_modes(struct drm_connector *conn)
+{
+	struct drm_encoder *enc = armada_drm_connector_encoder(conn);
+	int count = 0;
+
+	if (enc) {
+		struct drm_encoder_slave *slave = to_encoder_slave(enc);
+
+		count = slave->slave_funcs->get_modes(enc, conn);
+	}
+
+	return count;
+}
+
+static void armada_drm_slave_destroy(struct drm_encoder *enc)
+{
+	struct drm_encoder_slave *slave = to_encoder_slave(enc);
+	struct i2c_client *client = drm_i2c_encoder_get_client(enc);
+
+	if (slave->slave_funcs)
+		slave->slave_funcs->destroy(enc);
+	if (client)
+		i2c_put_adapter(client->adapter);
+
+	drm_encoder_cleanup(&slave->base);
+	kfree(slave);
+}
+
+static const struct drm_encoder_funcs armada_drm_slave_encoder_funcs = {
+	.destroy	= armada_drm_slave_destroy,
+};
+
+static const struct drm_connector_helper_funcs armada_drm_slave_helper_funcs = {
+	.get_modes	= armada_drm_slave_get_modes,
+	.mode_valid	= armada_drm_slave_encoder_mode_valid,
+	.best_encoder	= armada_drm_connector_encoder,
+};
+
+static const struct drm_encoder_helper_funcs drm_slave_encoder_helpers = {
+	.dpms = drm_i2c_encoder_dpms,
+	.save = drm_i2c_encoder_save,
+	.restore = drm_i2c_encoder_restore,
+	.mode_fixup = drm_i2c_encoder_mode_fixup,
+	.prepare = drm_i2c_encoder_prepare,
+	.commit = drm_i2c_encoder_commit,
+	.mode_set = drm_i2c_encoder_mode_set,
+	.detect = drm_i2c_encoder_detect,
+};
+
+static int
+armada_drm_conn_slave_create(struct drm_connector *conn, const void *data)
+{
+	const struct armada_drm_slave_config *config = data;
+	struct drm_encoder_slave *slave;
+	struct i2c_adapter *adap;
+	int ret;
+
+	conn->interlace_allowed = config->interlace_allowed;
+	conn->doublescan_allowed = config->doublescan_allowed;
+	conn->polled = config->polled;
+
+	drm_connector_helper_add(conn, &armada_drm_slave_helper_funcs);
+
+	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
+	if (!slave)
+		return -ENOMEM;
+
+	slave->base.possible_crtcs = config->crtcs;
+
+	adap = i2c_get_adapter(config->i2c_adapter_id);
+	if (!adap) {
+		kfree(slave);
+		return -EPROBE_DEFER;
+	}
+
+	ret = drm_encoder_init(conn->dev, &slave->base,
+			       &armada_drm_slave_encoder_funcs,
+			       DRM_MODE_ENCODER_TMDS);
+	if (ret) {
+		DRM_ERROR("unable to init encoder\n");
+		i2c_put_adapter(adap);
+		kfree(slave);
+		return ret;
+	}
+
+	ret = drm_i2c_encoder_init(conn->dev, slave, adap, &config->info);
+	i2c_put_adapter(adap);
+	if (ret) {
+		DRM_ERROR("unable to init encoder slave\n");
+		armada_drm_slave_destroy(&slave->base);
+		return ret;
+	}
+
+	drm_encoder_helper_add(&slave->base, &drm_slave_encoder_helpers);
+
+	ret = slave->slave_funcs->create_resources(&slave->base, conn);
+	if (ret) {
+		armada_drm_slave_destroy(&slave->base);
+		return ret;
+	}
+
+	ret = drm_mode_connector_attach_encoder(conn, &slave->base);
+	if (ret) {
+		armada_drm_slave_destroy(&slave->base);
+		return ret;
+	}
+
+	conn->encoder = &slave->base;
+
+	return ret;
+}
+
+static const struct armada_output_type armada_drm_conn_slave = {
+	.connector_type	= DRM_MODE_CONNECTOR_HDMIA,
+	.create		= armada_drm_conn_slave_create,
+	.set_property	= armada_drm_slave_encoder_set_property,
+};
+
+int armada_drm_connector_slave_create(struct drm_device *dev,
+	const struct armada_drm_slave_config *config)
+{
+	return armada_output_create(dev, &armada_drm_conn_slave, config);
+}
diff --git a/drivers/gpu/drm/armada/armada_slave.h b/drivers/gpu/drm/armada/armada_slave.h
new file mode 100644
index 000000000000..bf2374c96fc1
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_slave.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef ARMADA_SLAVE_H
+#define ARMADA_SLAVE_H
+
+#include <linux/i2c.h>
+#include <drm/drmP.h>
+
+struct armada_drm_slave_config {
+	int i2c_adapter_id;
+	uint32_t crtcs;
+	uint8_t polled;
+	bool interlace_allowed;
+	bool doublescan_allowed;
+	struct i2c_board_info info;
+};
+
+int armada_drm_connector_slave_create(struct drm_device *dev,
+	const struct armada_drm_slave_config *);
+
+#endif
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 24f499569a2f..e5e6e9124cbc 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1135,4 +1135,21 @@ extern int drm_format_horz_chroma_subsampling(uint32_t format);
 extern int drm_format_vert_chroma_subsampling(uint32_t format);
 extern const char *drm_get_format_name(uint32_t format);
 
+/* Helpers */
+static inline struct drm_crtc *drm_crtc_find(struct drm_device *dev,
+	uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_CRTC);
+	return mo ? obj_to_crtc(mo) : NULL;
+}
+
+static inline struct drm_encoder *drm_encoder_find(struct drm_device *dev,
+	uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_ENCODER);
+	return mo ? obj_to_encoder(mo) : NULL;
+}
+
 #endif /* __DRM_CRTC_H__ */
diff --git a/include/uapi/drm/armada_drm.h b/include/uapi/drm/armada_drm.h
new file mode 100644
index 000000000000..8dec3fdc99c7
--- /dev/null
+++ b/include/uapi/drm/armada_drm.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  With inspiration from the i915 driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef DRM_ARMADA_IOCTL_H
+#define DRM_ARMADA_IOCTL_H
+
+#define DRM_ARMADA_GEM_CREATE		0x00
+#define DRM_ARMADA_GEM_MMAP		0x02
+#define DRM_ARMADA_GEM_PWRITE		0x03
+
+#define ARMADA_IOCTL(dir, name, str) \
+	DRM_##dir(DRM_COMMAND_BASE + DRM_ARMADA_##name, struct drm_armada_##str)
+
+struct drm_armada_gem_create {
+	uint32_t handle;
+	uint32_t size;
+};
+#define DRM_IOCTL_ARMADA_GEM_CREATE \
+	ARMADA_IOCTL(IOWR, GEM_CREATE, gem_create)
+
+struct drm_armada_gem_mmap {
+	uint32_t handle;
+	uint32_t pad;
+	uint64_t offset;
+	uint64_t size;
+	uint64_t addr;
+};
+#define DRM_IOCTL_ARMADA_GEM_MMAP \
+	ARMADA_IOCTL(IOWR, GEM_MMAP, gem_mmap)
+
+struct drm_armada_gem_pwrite {
+	uint64_t ptr;
+	uint32_t handle;
+	uint32_t offset;
+	uint32_t size;
+};
+#define DRM_IOCTL_ARMADA_GEM_PWRITE \
+	ARMADA_IOCTL(IOW, GEM_PWRITE, gem_pwrite)
+
+#endif
-- 
cgit 


From 9e69c935fad9fd5f0550c51e3bd251cd30033136 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 4 Oct 2013 12:06:00 +0100
Subject: iio: Add reference counting for buffers

Since the buffer is accessed by userspace we can not just free the buffers
memory once we are done with it in kernel space. There might still be open file
descriptors and userspace still might be accessing the buffer. This patch adds
support for reference counting to the IIO buffers. When a buffer is created and
initialized its initial reference count is set to 1. Instead of freeing the
memory of the buffer the buffer's _free() function will drop that reference
again. But only after the last reference to the buffer has been dropped the
buffer the buffer's memory will be freed. The IIO device will take a reference
to its primary buffer. The patch adds a small helper function for this called
iio_device_attach_buffer() which will get a reference to the buffer and assign
the buffer to the IIO device. This function must be used instead of assigning
the buffer to the device by hand. The reference is only dropped once the IIO
device is freed and we can be sure that there are no more open file handles. A
reference to a buffer will also be taken whenever the buffer is active to avoid
the buffer being freed while data is still being send to it.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/buffer_cb.c                         | 21 +++++---
 drivers/iio/industrialio-buffer.c               | 66 +++++++++++++++++++++++--
 drivers/iio/industrialio-core.c                 |  3 ++
 drivers/iio/industrialio-triggered-buffer.c     |  7 ++-
 drivers/iio/kfifo_buf.c                         |  8 ++-
 drivers/staging/iio/accel/lis3l02dq_ring.c      |  2 +-
 drivers/staging/iio/accel/sca3000_ring.c        | 13 +++--
 drivers/staging/iio/iio_simple_dummy_buffer.c   |  2 +-
 drivers/staging/iio/impedance-analyzer/ad5933.c |  8 ++-
 drivers/staging/iio/meter/ade7758_ring.c        |  7 ++-
 include/linux/iio/buffer.h                      | 28 +++++++++++
 11 files changed, 141 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/buffer_cb.c b/drivers/iio/buffer_cb.c
index 841fec1e78b2..2d9c6f8c06db 100644
--- a/drivers/iio/buffer_cb.c
+++ b/drivers/iio/buffer_cb.c
@@ -12,17 +12,27 @@ struct iio_cb_buffer {
 	struct iio_channel *channels;
 };
 
-static int iio_buffer_cb_store_to(struct iio_buffer *buffer, const void *data)
+static struct iio_cb_buffer *buffer_to_cb_buffer(struct iio_buffer *buffer)
 {
-	struct iio_cb_buffer *cb_buff = container_of(buffer,
-						     struct iio_cb_buffer,
-						     buffer);
+	return container_of(buffer, struct iio_cb_buffer, buffer);
+}
 
+static int iio_buffer_cb_store_to(struct iio_buffer *buffer, const void *data)
+{
+	struct iio_cb_buffer *cb_buff = buffer_to_cb_buffer(buffer);
 	return cb_buff->cb(data, cb_buff->private);
 }
 
+static void iio_buffer_cb_release(struct iio_buffer *buffer)
+{
+	struct iio_cb_buffer *cb_buff = buffer_to_cb_buffer(buffer);
+	kfree(cb_buff->buffer.scan_mask);
+	kfree(cb_buff);
+}
+
 static const struct iio_buffer_access_funcs iio_cb_access = {
 	.store_to = &iio_buffer_cb_store_to,
+	.release = &iio_buffer_cb_release,
 };
 
 struct iio_cb_buffer *iio_channel_get_all_cb(struct device *dev,
@@ -104,9 +114,8 @@ EXPORT_SYMBOL_GPL(iio_channel_stop_all_cb);
 
 void iio_channel_release_all_cb(struct iio_cb_buffer *cb_buff)
 {
-	kfree(cb_buff->buffer.scan_mask);
 	iio_channel_release_all(cb_buff->channels);
-	kfree(cb_buff);
+	iio_buffer_put(&cb_buff->buffer);
 }
 EXPORT_SYMBOL_GPL(iio_channel_release_all_cb);
 
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index e9f389b9da69..36c39dcad850 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -74,6 +74,7 @@ void iio_buffer_init(struct iio_buffer *buffer)
 	INIT_LIST_HEAD(&buffer->demux_list);
 	INIT_LIST_HEAD(&buffer->buffer_list);
 	init_waitqueue_head(&buffer->pollq);
+	kref_init(&buffer->ref);
 }
 EXPORT_SYMBOL(iio_buffer_init);
 
@@ -454,6 +455,19 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev,
 	return bytes;
 }
 
+static void iio_buffer_activate(struct iio_dev *indio_dev,
+	struct iio_buffer *buffer)
+{
+	iio_buffer_get(buffer);
+	list_add(&buffer->buffer_list, &indio_dev->buffer_list);
+}
+
+static void iio_buffer_deactivate(struct iio_buffer *buffer)
+{
+	list_del_init(&buffer->buffer_list);
+	iio_buffer_put(buffer);
+}
+
 void iio_disable_all_buffers(struct iio_dev *indio_dev)
 {
 	struct iio_buffer *buffer, *_buffer;
@@ -466,7 +480,7 @@ void iio_disable_all_buffers(struct iio_dev *indio_dev)
 
 	list_for_each_entry_safe(buffer, _buffer,
 			&indio_dev->buffer_list, buffer_list)
-		list_del_init(&buffer->buffer_list);
+		iio_buffer_deactivate(buffer);
 
 	indio_dev->currentmode = INDIO_DIRECT_MODE;
 	if (indio_dev->setup_ops->postdisable)
@@ -503,9 +517,9 @@ int iio_update_buffers(struct iio_dev *indio_dev,
 		indio_dev->active_scan_mask = NULL;
 
 	if (remove_buffer)
-		list_del_init(&remove_buffer->buffer_list);
+		iio_buffer_deactivate(remove_buffer);
 	if (insert_buffer)
-		list_add(&insert_buffer->buffer_list, &indio_dev->buffer_list);
+		iio_buffer_activate(indio_dev, insert_buffer);
 
 	/* If no buffers in list, we are done */
 	if (list_empty(&indio_dev->buffer_list)) {
@@ -540,7 +554,7 @@ int iio_update_buffers(struct iio_dev *indio_dev,
 			 * Roll back.
 			 * Note can only occur when adding a buffer.
 			 */
-			list_del_init(&insert_buffer->buffer_list);
+			iio_buffer_deactivate(insert_buffer);
 			if (old_mask) {
 				indio_dev->active_scan_mask = old_mask;
 				success = -EINVAL;
@@ -631,7 +645,7 @@ error_run_postdisable:
 error_remove_inserted:
 
 	if (insert_buffer)
-		list_del_init(&insert_buffer->buffer_list);
+		iio_buffer_deactivate(insert_buffer);
 	indio_dev->active_scan_mask = old_mask;
 	kfree(compound_mask);
 error_ret:
@@ -952,3 +966,45 @@ error_clear_mux_table:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iio_update_demux);
+
+/**
+ * iio_buffer_release() - Free a buffer's resources
+ * @ref: Pointer to the kref embedded in the iio_buffer struct
+ *
+ * This function is called when the last reference to the buffer has been
+ * dropped. It will typically free all resources allocated by the buffer. Do not
+ * call this function manually, always use iio_buffer_put() when done using a
+ * buffer.
+ */
+static void iio_buffer_release(struct kref *ref)
+{
+	struct iio_buffer *buffer = container_of(ref, struct iio_buffer, ref);
+
+	buffer->access->release(buffer);
+}
+
+/**
+ * iio_buffer_get() - Grab a reference to the buffer
+ * @buffer: The buffer to grab a reference for, may be NULL
+ *
+ * Returns the pointer to the buffer that was passed into the function.
+ */
+struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer)
+{
+	if (buffer)
+		kref_get(&buffer->ref);
+
+	return buffer;
+}
+EXPORT_SYMBOL_GPL(iio_buffer_get);
+
+/**
+ * iio_buffer_put() - Release the reference to the buffer
+ * @buffer: The buffer to release the reference for, may be NULL
+ */
+void iio_buffer_put(struct iio_buffer *buffer)
+{
+	if (buffer)
+		kref_put(&buffer->ref, iio_buffer_release);
+}
+EXPORT_SYMBOL_GPL(iio_buffer_put);
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index ecf58963ac24..f939bad31ca1 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -28,6 +28,7 @@
 #include "iio_core_trigger.h"
 #include <linux/iio/sysfs.h>
 #include <linux/iio/events.h>
+#include <linux/iio/buffer.h>
 
 /* IDA to assign each registered device a unique id */
 static DEFINE_IDA(iio_ida);
@@ -895,6 +896,8 @@ static void iio_dev_release(struct device *device)
 	iio_device_unregister_eventset(indio_dev);
 	iio_device_unregister_sysfs(indio_dev);
 
+	iio_buffer_put(indio_dev->buffer);
+
 	ida_simple_remove(&iio_ida, indio_dev->id);
 	kfree(indio_dev);
 }
diff --git a/drivers/iio/industrialio-triggered-buffer.c b/drivers/iio/industrialio-triggered-buffer.c
index 46c619b0d8c5..c1cb1f94fe2e 100644
--- a/drivers/iio/industrialio-triggered-buffer.c
+++ b/drivers/iio/industrialio-triggered-buffer.c
@@ -47,14 +47,17 @@ int iio_triggered_buffer_setup(struct iio_dev *indio_dev,
 	irqreturn_t (*pollfunc_th)(int irq, void *p),
 	const struct iio_buffer_setup_ops *setup_ops)
 {
+	struct iio_buffer *buffer;
 	int ret;
 
-	indio_dev->buffer = iio_kfifo_allocate(indio_dev);
-	if (!indio_dev->buffer) {
+	buffer = iio_kfifo_allocate(indio_dev);
+	if (!buffer) {
 		ret = -ENOMEM;
 		goto error_ret;
 	}
 
+	iio_device_attach_buffer(indio_dev, buffer);
+
 	indio_dev->pollfunc = iio_alloc_pollfunc(pollfunc_bh,
 						 pollfunc_th,
 						 IRQF_ONESHOT,
diff --git a/drivers/iio/kfifo_buf.c b/drivers/iio/kfifo_buf.c
index 538d4616e48f..b4ac55a29fc4 100644
--- a/drivers/iio/kfifo_buf.c
+++ b/drivers/iio/kfifo_buf.c
@@ -130,6 +130,11 @@ static int iio_read_first_n_kfifo(struct iio_buffer *r,
 	return copied;
 }
 
+static void iio_kfifo_buffer_release(struct iio_buffer *buffer)
+{
+	kfree(iio_to_kfifo(buffer));
+}
+
 static const struct iio_buffer_access_funcs kfifo_access_funcs = {
 	.store_to = &iio_store_to_kfifo,
 	.read_first_n = &iio_read_first_n_kfifo,
@@ -138,6 +143,7 @@ static const struct iio_buffer_access_funcs kfifo_access_funcs = {
 	.set_bytes_per_datum = &iio_set_bytes_per_datum_kfifo,
 	.get_length = &iio_get_length_kfifo,
 	.set_length = &iio_set_length_kfifo,
+	.release = &iio_kfifo_buffer_release,
 };
 
 struct iio_buffer *iio_kfifo_allocate(struct iio_dev *indio_dev)
@@ -158,7 +164,7 @@ EXPORT_SYMBOL(iio_kfifo_allocate);
 
 void iio_kfifo_free(struct iio_buffer *r)
 {
-	kfree(iio_to_kfifo(r));
+	iio_buffer_put(r);
 }
 EXPORT_SYMBOL(iio_kfifo_free);
 
diff --git a/drivers/staging/iio/accel/lis3l02dq_ring.c b/drivers/staging/iio/accel/lis3l02dq_ring.c
index ed7de471e3f3..2d559ba353d2 100644
--- a/drivers/staging/iio/accel/lis3l02dq_ring.c
+++ b/drivers/staging/iio/accel/lis3l02dq_ring.c
@@ -396,7 +396,7 @@ int lis3l02dq_configure_buffer(struct iio_dev *indio_dev)
 	if (!buffer)
 		return -ENOMEM;
 
-	indio_dev->buffer = buffer;
+	iio_device_attach_buffer(indio_dev, buffer);
 
 	buffer->scan_timestamp = true;
 	indio_dev->setup_ops = &lis3l02dq_buffer_setup_ops;
diff --git a/drivers/staging/iio/accel/sca3000_ring.c b/drivers/staging/iio/accel/sca3000_ring.c
index 0f2ee3373d9a..4a27beb1451a 100644
--- a/drivers/staging/iio/accel/sca3000_ring.c
+++ b/drivers/staging/iio/accel/sca3000_ring.c
@@ -265,7 +265,7 @@ static struct iio_buffer *sca3000_rb_allocate(struct iio_dev *indio_dev)
 	return buf;
 }
 
-static inline void sca3000_rb_free(struct iio_buffer *r)
+static void sca3000_ring_release(struct iio_buffer *r)
 {
 	kfree(iio_to_hw_buf(r));
 }
@@ -274,23 +274,28 @@ static const struct iio_buffer_access_funcs sca3000_ring_access_funcs = {
 	.read_first_n = &sca3000_read_first_n_hw_rb,
 	.get_length = &sca3000_ring_get_length,
 	.get_bytes_per_datum = &sca3000_ring_get_bytes_per_datum,
+	.release = sca3000_ring_release,
 };
 
 int sca3000_configure_ring(struct iio_dev *indio_dev)
 {
-	indio_dev->buffer = sca3000_rb_allocate(indio_dev);
-	if (indio_dev->buffer == NULL)
+	struct iio_buffer *buffer;
+
+	buffer = sca3000_rb_allocate(indio_dev);
+	if (buffer == NULL)
 		return -ENOMEM;
 	indio_dev->modes |= INDIO_BUFFER_HARDWARE;
 
 	indio_dev->buffer->access = &sca3000_ring_access_funcs;
 
+	iio_device_attach_buffer(indio_dev, buffer);
+
 	return 0;
 }
 
 void sca3000_unconfigure_ring(struct iio_dev *indio_dev)
 {
-	sca3000_rb_free(indio_dev->buffer);
+	iio_buffer_put(indio_dev->buffer);
 }
 
 static inline
diff --git a/drivers/staging/iio/iio_simple_dummy_buffer.c b/drivers/staging/iio/iio_simple_dummy_buffer.c
index 09c93ac7351a..2612e87fbcb4 100644
--- a/drivers/staging/iio/iio_simple_dummy_buffer.c
+++ b/drivers/staging/iio/iio_simple_dummy_buffer.c
@@ -135,7 +135,7 @@ int iio_simple_dummy_configure_buffer(struct iio_dev *indio_dev,
 		goto error_ret;
 	}
 
-	indio_dev->buffer = buffer;
+	iio_device_attach_buffer(indio_dev, buffer);
 
 	/* Enable timestamps by default */
 	buffer->scan_timestamp = true;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 712f3c22ce64..f5701159bf36 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -630,10 +630,14 @@ static const struct iio_buffer_setup_ops ad5933_ring_setup_ops = {
 
 static int ad5933_register_ring_funcs_and_init(struct iio_dev *indio_dev)
 {
-	indio_dev->buffer = iio_kfifo_allocate(indio_dev);
-	if (!indio_dev->buffer)
+	struct iio_buffer *buffer;
+
+	buffer = iio_kfifo_allocate(indio_dev);
+	if (buffer)
 		return -ENOMEM;
 
+	iio_device_attach_buffer(indio_dev, buffer);
+
 	/* Ring buffer functions - here trigger setup related */
 	indio_dev->setup_ops = &ad5933_ring_setup_ops;
 
diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c
index 4080995c99b6..7a448ffaeb14 100644
--- a/drivers/staging/iio/meter/ade7758_ring.c
+++ b/drivers/staging/iio/meter/ade7758_ring.c
@@ -121,14 +121,17 @@ void ade7758_unconfigure_ring(struct iio_dev *indio_dev)
 int ade7758_configure_ring(struct iio_dev *indio_dev)
 {
 	struct ade7758_state *st = iio_priv(indio_dev);
+	struct iio_buffer *buffer;
 	int ret = 0;
 
-	indio_dev->buffer = iio_kfifo_allocate(indio_dev);
-	if (!indio_dev->buffer) {
+	buffer = iio_kfifo_allocate(indio_dev);
+	if (!buffer) {
 		ret = -ENOMEM;
 		return ret;
 	}
 
+	iio_device_attach_buffer(indio_dev, buffer);
+
 	indio_dev->setup_ops = &ade7758_ring_setup_ops;
 
 	indio_dev->pollfunc = iio_alloc_pollfunc(&iio_pollfunc_store_time,
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index a1124bdc4cac..6e428d96d570 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -11,6 +11,7 @@
 #define _IIO_BUFFER_GENERIC_H_
 #include <linux/sysfs.h>
 #include <linux/iio/iio.h>
+#include <linux/kref.h>
 
 #ifdef CONFIG_IIO_BUFFER
 
@@ -26,6 +27,8 @@ struct iio_buffer;
  * @set_bytes_per_datum:set number of bytes per datum
  * @get_length:		get number of datums in buffer
  * @set_length:		set number of datums in buffer
+ * @release:		called when the last reference to the buffer is dropped,
+ *			should free all resources allocated by the buffer.
  *
  * The purpose of this structure is to make the buffer element
  * modular as event for a given driver, different usecases may require
@@ -47,6 +50,8 @@ struct iio_buffer_access_funcs {
 	int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd);
 	int (*get_length)(struct iio_buffer *buffer);
 	int (*set_length)(struct iio_buffer *buffer, int length);
+
+	void (*release)(struct iio_buffer *buffer);
 };
 
 /**
@@ -67,6 +72,7 @@ struct iio_buffer_access_funcs {
  * @demux_list:		[INTERN] list of operations required to demux the scan.
  * @demux_bounce:	[INTERN] buffer for doing gather from incoming scan.
  * @buffer_list:	[INTERN] entry in the devices list of current buffers.
+ * @ref:		[INTERN] reference count of the buffer.
  */
 struct iio_buffer {
 	int					length;
@@ -83,6 +89,7 @@ struct iio_buffer {
 	struct list_head			demux_list;
 	void					*demux_bounce;
 	struct list_head			buffer_list;
+	struct kref				ref;
 };
 
 /**
@@ -204,6 +211,24 @@ int iio_sw_buffer_preenable(struct iio_dev *indio_dev);
 bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev,
 	const unsigned long *mask);
 
+struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer);
+void iio_buffer_put(struct iio_buffer *buffer);
+
+/**
+ * iio_device_attach_buffer - Attach a buffer to a IIO device
+ * @indio_dev: The device the buffer should be attached to
+ * @buffer: The buffer to attach to the device
+ *
+ * This function attaches a buffer to a IIO device. The buffer stays attached to
+ * the device until the device is freed. The function should only be called at
+ * most once per device.
+ */
+static inline void iio_device_attach_buffer(struct iio_dev *indio_dev,
+	struct iio_buffer *buffer)
+{
+	indio_dev->buffer = iio_buffer_get(buffer);
+}
+
 #else /* CONFIG_IIO_BUFFER */
 
 static inline int iio_buffer_register(struct iio_dev *indio_dev,
@@ -216,6 +241,9 @@ static inline int iio_buffer_register(struct iio_dev *indio_dev,
 static inline void iio_buffer_unregister(struct iio_dev *indio_dev)
 {}
 
+static inline void iio_buffer_get(struct iio_buffer *buffer) {}
+static inline void iio_buffer_put(struct iio_buffer *buffer) {}
+
 #endif /* CONFIG_IIO_BUFFER */
 
 #endif /* _IIO_BUFFER_GENERIC_H_ */
-- 
cgit 


From b4e3ac0a204ff1775c69924510f49922a56910a7 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 7 Oct 2013 15:11:00 +0100
Subject: iio: Extend the event config interface

The event configuration interface of the IIO framework has not been getting the
same attention as other parts. As a result it has not seen the same improvements
as e.g. the channel interface has seen with the introduction of the channel spec
struct. Currently all the event config callbacks take a u64 (the so called event
code) to pass all the different information about for which event the callback
is invoked. The callback function then has to extract the information it is
interested in using some macros with rather long names. Most information encoded
in the event code comes straight from the iio_chan_spec struct the event was
registered for. Since we always have a handle to the channel spec when we call
the event callbacks the first step is to add the channel spec as a parameter to
the event callbacks. The two remaining things encoded in the event code are the
type and direction of the event. Instead of passing them in one parameter, add
one parameter for each of them and remove the eventcode from the event
callbacks. The patch also adds a new iio_event_info parameter to the
{read,write}_event_value callbacks. This makes it possible, similar to the
iio_chan_info_enum for channels, to specify additional properties other than
just the value for an event. Furthermore the new interface will allow to
register shared events. This is e.g. useful if a device allows configuring a
threshold event, but the threshold setting is the same for all channels.

To implement this the patch adds a new iio_event_spec struct which is similar to
the iio_chan_spec struct. It as two field to specify the type and the direction
of the event. Furthermore it has a mask field for each one of the different
iio_shared_by types. These mask fields holds which kind of attributes should be
registered for the event. Creation of the attributes follows the same rules as
the for the channel attributes. E.g. for the separate_mask there will be a
attribute for each channel with this event, for the shared_by_type there will
only be one attribute per channel type. The iio_chan_spec struct gets two new
fields, 'event_spec' and 'num_event_specs', which is used to specify which the
events for this channel. These two fields are going to replace the channel's
event_mask field.

For now both the old and the new event config interface coexist, but over the
few patches all drivers will be converted from the old to the new interface.
Once that is done all code for supporting the old interface will be removed.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/industrialio-event.c | 193 ++++++++++++++++++++++++++++++++++-----
 include/linux/iio/events.h       |  14 ---
 include/linux/iio/iio.h          |  58 ++++++++++++
 include/linux/iio/types.h        |  19 ++++
 4 files changed, 248 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 4a3fd5acda94..b7a5d7cbed42 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -201,6 +201,26 @@ static const char * const iio_ev_dir_text[] = {
 	[IIO_EV_DIR_FALLING] = "falling"
 };
 
+static const char * const iio_ev_info_text[] = {
+	[IIO_EV_INFO_ENABLE] = "en",
+	[IIO_EV_INFO_VALUE] = "value",
+};
+
+static enum iio_event_direction iio_ev_attr_dir(struct iio_dev_attr *attr)
+{
+	return attr->c->event_spec[attr->address & 0xffff].dir;
+}
+
+static enum iio_event_type iio_ev_attr_type(struct iio_dev_attr *attr)
+{
+	return attr->c->event_spec[attr->address & 0xffff].type;
+}
+
+static enum iio_event_info iio_ev_attr_info(struct iio_dev_attr *attr)
+{
+	return (attr->address >> 16) & 0xffff;
+}
+
 static ssize_t iio_ev_state_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf,
@@ -215,9 +235,14 @@ static ssize_t iio_ev_state_store(struct device *dev,
 	if (ret < 0)
 		return ret;
 
-	ret = indio_dev->info->write_event_config(indio_dev,
-						  this_attr->address,
-						  val);
+	if (indio_dev->info->write_event_config)
+		ret = indio_dev->info->write_event_config(indio_dev,
+			this_attr->address, val);
+	else
+		ret = indio_dev->info->write_event_config_new(indio_dev,
+			this_attr->c, iio_ev_attr_type(this_attr),
+			iio_ev_attr_dir(this_attr), val);
+
 	return (ret < 0) ? ret : len;
 }
 
@@ -227,9 +252,15 @@ static ssize_t iio_ev_state_show(struct device *dev,
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
-	int val = indio_dev->info->read_event_config(indio_dev,
-						     this_attr->address);
+	int val;
 
+	if (indio_dev->info->read_event_config)
+		val = indio_dev->info->read_event_config(indio_dev,
+			this_attr->address);
+	else
+		val = indio_dev->info->read_event_config_new(indio_dev,
+			this_attr->c, iio_ev_attr_type(this_attr),
+			iio_ev_attr_dir(this_attr));
 	if (val < 0)
 		return val;
 	else
@@ -242,14 +273,24 @@ static ssize_t iio_ev_value_show(struct device *dev,
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
-	int val, ret;
-
-	ret = indio_dev->info->read_event_value(indio_dev,
-						this_attr->address, &val);
-	if (ret < 0)
-		return ret;
+	int val, val2;
+	int ret;
 
-	return sprintf(buf, "%d\n", val);
+	if (indio_dev->info->read_event_value) {
+		ret = indio_dev->info->read_event_value(indio_dev,
+			this_attr->address, &val);
+		if (ret < 0)
+			return ret;
+		return sprintf(buf, "%d\n", val);
+	} else {
+		ret = indio_dev->info->read_event_value_new(indio_dev,
+			this_attr->c, iio_ev_attr_type(this_attr),
+			iio_ev_attr_dir(this_attr), iio_ev_attr_info(this_attr),
+			&val, &val2);
+		if (ret < 0)
+			return ret;
+		return iio_format_value(buf, ret, val, val2);
+	}
 }
 
 static ssize_t iio_ev_value_store(struct device *dev,
@@ -259,25 +300,120 @@ static ssize_t iio_ev_value_store(struct device *dev,
 {
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 	struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
-	int val;
+	int val, val2;
 	int ret;
 
-	if (!indio_dev->info->write_event_value)
+	if (!indio_dev->info->write_event_value &&
+		!indio_dev->info->write_event_value_new)
 		return -EINVAL;
 
-	ret = kstrtoint(buf, 10, &val);
-	if (ret)
-		return ret;
-
-	ret = indio_dev->info->write_event_value(indio_dev, this_attr->address,
-						 val);
+	if (indio_dev->info->write_event_value) {
+		ret = kstrtoint(buf, 10, &val);
+		if (ret)
+			return ret;
+		ret = indio_dev->info->write_event_value(indio_dev,
+			this_attr->address, val);
+	} else {
+		ret = iio_str_to_fixpoint(buf, 100000, &val, &val2);
+		if (ret)
+			return ret;
+		ret = indio_dev->info->write_event_value_new(indio_dev,
+			this_attr->c, iio_ev_attr_type(this_attr),
+			iio_ev_attr_dir(this_attr), iio_ev_attr_info(this_attr),
+			val, val2);
+	}
 	if (ret < 0)
 		return ret;
 
 	return len;
 }
 
-static int iio_device_add_event_sysfs(struct iio_dev *indio_dev,
+static int iio_device_add_event(struct iio_dev *indio_dev,
+	const struct iio_chan_spec *chan, unsigned int spec_index,
+	enum iio_event_type type, enum iio_event_direction dir,
+	enum iio_shared_by shared_by, const unsigned long *mask)
+{
+	ssize_t (*show)(struct device *, struct device_attribute *, char *);
+	ssize_t (*store)(struct device *, struct device_attribute *,
+		const char *, size_t);
+	unsigned int attrcount = 0;
+	unsigned int i;
+	char *postfix;
+	int ret;
+
+	for_each_set_bit(i, mask, sizeof(*mask)) {
+		postfix = kasprintf(GFP_KERNEL, "%s_%s_%s",
+				iio_ev_type_text[type], iio_ev_dir_text[dir],
+				iio_ev_info_text[i]);
+		if (postfix == NULL)
+			return -ENOMEM;
+
+		if (i == IIO_EV_INFO_ENABLE) {
+			show = iio_ev_state_show;
+			store = iio_ev_state_store;
+		} else {
+			show = iio_ev_value_show;
+			store = iio_ev_value_store;
+		}
+
+		ret = __iio_add_chan_devattr(postfix, chan, show, store,
+			 (i << 16) | spec_index, shared_by, &indio_dev->dev,
+			&indio_dev->event_interface->dev_attr_list);
+		kfree(postfix);
+
+		if (ret)
+			return ret;
+
+		attrcount++;
+	}
+
+	return attrcount;
+}
+
+static int iio_device_add_event_sysfs_new(struct iio_dev *indio_dev,
+	struct iio_chan_spec const *chan)
+{
+	int ret = 0, i, attrcount = 0;
+	enum iio_event_direction dir;
+	enum iio_event_type type;
+
+	for (i = 0; i < chan->num_event_specs; i++) {
+		type = chan->event_spec[i].type;
+		dir = chan->event_spec[i].dir;
+
+		ret = iio_device_add_event(indio_dev, chan, i, type, dir,
+			IIO_SEPARATE, &chan->event_spec[i].mask_separate);
+		if (ret < 0)
+			goto error_ret;
+		attrcount += ret;
+
+		ret = iio_device_add_event(indio_dev, chan, i, type, dir,
+			IIO_SHARED_BY_TYPE,
+			&chan->event_spec[i].mask_shared_by_type);
+		if (ret < 0)
+			goto error_ret;
+		attrcount += ret;
+
+		ret = iio_device_add_event(indio_dev, chan, i, type, dir,
+			IIO_SHARED_BY_DIR,
+			&chan->event_spec[i].mask_shared_by_dir);
+		if (ret < 0)
+			goto error_ret;
+		attrcount += ret;
+
+		ret = iio_device_add_event(indio_dev, chan, i, type, dir,
+			IIO_SHARED_BY_ALL,
+			&chan->event_spec[i].mask_shared_by_all);
+		if (ret < 0)
+			goto error_ret;
+		attrcount += ret;
+	}
+	ret = attrcount;
+error_ret:
+	return ret;
+}
+
+static int iio_device_add_event_sysfs_old(struct iio_dev *indio_dev,
 				      struct iio_chan_spec const *chan)
 {
 	int ret = 0, i, attrcount = 0;
@@ -350,6 +486,16 @@ error_ret:
 	return ret;
 }
 
+
+static int iio_device_add_event_sysfs(struct iio_dev *indio_dev,
+				      struct iio_chan_spec const *chan)
+{
+	if (chan->event_mask)
+		return iio_device_add_event_sysfs_old(indio_dev, chan);
+	else
+		return iio_device_add_event_sysfs_new(indio_dev, chan);
+}
+
 static inline int __iio_add_event_config_attrs(struct iio_dev *indio_dev)
 {
 	int j, ret, attrcount = 0;
@@ -369,9 +515,12 @@ static bool iio_check_for_dynamic_events(struct iio_dev *indio_dev)
 {
 	int j;
 
-	for (j = 0; j < indio_dev->num_channels; j++)
+	for (j = 0; j < indio_dev->num_channels; j++) {
 		if (indio_dev->channels[j].event_mask != 0)
 			return true;
+		if (indio_dev->channels[j].num_event_specs != 0)
+			return true;
+	}
 	return false;
 }
 
diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h
index 13ce220c7003..5dab2c41031f 100644
--- a/include/linux/iio/events.h
+++ b/include/linux/iio/events.h
@@ -26,20 +26,6 @@ struct iio_event_data {
 
 #define IIO_GET_EVENT_FD_IOCTL _IOR('i', 0x90, int)
 
-enum iio_event_type {
-	IIO_EV_TYPE_THRESH,
-	IIO_EV_TYPE_MAG,
-	IIO_EV_TYPE_ROC,
-	IIO_EV_TYPE_THRESH_ADAPTIVE,
-	IIO_EV_TYPE_MAG_ADAPTIVE,
-};
-
-enum iio_event_direction {
-	IIO_EV_DIR_EITHER,
-	IIO_EV_DIR_RISING,
-	IIO_EV_DIR_FALLING,
-};
-
 /**
  * IIO_EVENT_CODE() - create event identifier
  * @chan_type:	Type of the channel. Should be one of enum iio_chan_type.
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index ac1cb8f1858c..256a90a1bea6 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -138,6 +138,29 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev,
 	.private = (uintptr_t)(_e), \
 }
 
+/**
+ * struct iio_event_spec - specification for a channel event
+ * @type:		    Type of the event
+ * @dir:		    Direction of the event
+ * @mask_separate:	    Bit mask of enum iio_event_info values. Attributes
+ *			    set in this mask will be registered per channel.
+ * @mask_shared_by_type:    Bit mask of enum iio_event_info values. Attributes
+ *			    set in this mask will be shared by channel type.
+ * @mask_shared_by_dir:	    Bit mask of enum iio_event_info values. Attributes
+ *			    set in this mask will be shared by channel type and
+ *			    direction.
+ * @mask_shared_by_all:	    Bit mask of enum iio_event_info values. Attributes
+ *			    set in this mask will be shared by all channels.
+ */
+struct iio_event_spec {
+	enum iio_event_type type;
+	enum iio_event_direction dir;
+	unsigned long mask_separate;
+	unsigned long mask_shared_by_type;
+	unsigned long mask_shared_by_dir;
+	unsigned long mask_shared_by_all;
+};
+
 /**
  * struct iio_chan_spec - specification of a single channel
  * @type:		What type of measurement is the channel making.
@@ -163,6 +186,9 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev,
  * @info_mask_shared_by_all: What information is to be exported that is shared
  *			by all channels.
  * @event_mask:		What events can this channel produce.
+ * @event_spec:		Array of events which should be registered for this
+ *			channel.
+ * @num_event_specs:	Size of the event_spec array.
  * @ext_info:		Array of extended info attributes for this channel.
  *			The array is NULL terminated, the last element should
  *			have its name field set to NULL.
@@ -201,6 +227,8 @@ struct iio_chan_spec {
 	long			info_mask_shared_by_dir;
 	long			info_mask_shared_by_all;
 	long			event_mask;
+	const struct iio_event_spec *event_spec;
+	unsigned int		num_event_specs;
 	const struct iio_chan_spec_ext_info *ext_info;
 	const char		*extend_name;
 	const char		*datasheet_name;
@@ -283,6 +311,12 @@ struct iio_dev;
  *			is event dependant. event_code specifies which event.
  * @write_event_value:	write the value associated with the event.
  *			Meaning is event dependent.
+ * @read_event_config_new: find out if the event is enabled. New style interface.
+ * @write_event_config_new: set if the event is enabled. New style interface.
+ * @read_event_value_new: read a configuration value associated with the event.
+ *                         New style interface.
+ * @write_event_value_new: write a configuration value for the event. New style
+ *			   interface.
  * @validate_trigger:	function to validate the trigger when the
  *			current trigger gets changed.
  * @update_scan_mode:	function to configure device and scan buffer when
@@ -323,6 +357,30 @@ struct iio_info {
 	int (*write_event_value)(struct iio_dev *indio_dev,
 				 u64 event_code,
 				 int val);
+
+	int (*read_event_config_new)(struct iio_dev *indio_dev,
+				 const struct iio_chan_spec *chan,
+				 enum iio_event_type type,
+				 enum iio_event_direction dir);
+
+	int (*write_event_config_new)(struct iio_dev *indio_dev,
+				  const struct iio_chan_spec *chan,
+				  enum iio_event_type type,
+				  enum iio_event_direction dir,
+				  int state);
+
+	int (*read_event_value_new)(struct iio_dev *indio_dev,
+				const struct iio_chan_spec *chan,
+				enum iio_event_type type,
+				enum iio_event_direction dir,
+				enum iio_event_info info, int *val, int *val2);
+
+	int (*write_event_value_new)(struct iio_dev *indio_dev,
+				 const struct iio_chan_spec *chan,
+				 enum iio_event_type type,
+				 enum iio_event_direction dir,
+				 enum iio_event_info info, int val, int val2);
+
 	int (*validate_trigger)(struct iio_dev *indio_dev,
 				struct iio_trigger *trig);
 	int (*update_scan_mode)(struct iio_dev *indio_dev,
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 88bf0f0d27b4..18339ef4ff5d 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -54,6 +54,25 @@ enum iio_modifier {
 	IIO_MOD_LIGHT_BLUE,
 };
 
+enum iio_event_type {
+	IIO_EV_TYPE_THRESH,
+	IIO_EV_TYPE_MAG,
+	IIO_EV_TYPE_ROC,
+	IIO_EV_TYPE_THRESH_ADAPTIVE,
+	IIO_EV_TYPE_MAG_ADAPTIVE,
+};
+
+enum iio_event_info {
+	IIO_EV_INFO_ENABLE,
+	IIO_EV_INFO_VALUE,
+};
+
+enum iio_event_direction {
+	IIO_EV_DIR_EITHER,
+	IIO_EV_DIR_RISING,
+	IIO_EV_DIR_FALLING,
+};
+
 #define IIO_VAL_INT 1
 #define IIO_VAL_INT_PLUS_MICRO 2
 #define IIO_VAL_INT_PLUS_NANO 3
-- 
cgit 


From ec6670ae53c13d767bdb7b3e37755ad661395380 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 7 Oct 2013 15:11:00 +0100
Subject: iio: Add a hysteresis event info attribute

For some devices it is possible to configure a hysteresis for threshold (or
similar) events. This patch adds a new hysteresis event info type which allows
for easy creation and read/write handling of the sysfs attribute.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 Documentation/ABI/testing/sysfs-bus-iio | 56 +++++++++++++++++++++++++++++++++
 drivers/iio/industrialio-event.c        |  1 +
 include/linux/iio/types.h               |  1 +
 3 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 2d73620874b2..b20e829d350f 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -537,6 +537,62 @@ Description:
 		value is in raw device units or in processed units (as _raw
 		and _input do on sysfs direct channel read attributes).
 
+What:		/sys/.../events/in_accel_x_thresh_rising_hysteresis
+What:		/sys/.../events/in_accel_x_thresh_falling_hysteresis
+What:		/sys/.../events/in_accel_x_thresh_either_hysteresis
+What:		/sys/.../events/in_accel_y_thresh_rising_hysteresis
+What:		/sys/.../events/in_accel_y_thresh_falling_hysteresis
+What:		/sys/.../events/in_accel_y_thresh_either_hysteresis
+What:		/sys/.../events/in_accel_z_thresh_rising_hysteresis
+What:		/sys/.../events/in_accel_z_thresh_falling_hysteresis
+What:		/sys/.../events/in_accel_z_thresh_either_hysteresis
+What:		/sys/.../events/in_anglvel_x_thresh_rising_hysteresis
+What:		/sys/.../events/in_anglvel_x_thresh_falling_hysteresis
+What:		/sys/.../events/in_anglvel_x_thresh_either_hysteresis
+What:		/sys/.../events/in_anglvel_y_thresh_rising_hysteresis
+What:		/sys/.../events/in_anglvel_y_thresh_falling_hysteresis
+What:		/sys/.../events/in_anglvel_y_thresh_either_hysteresis
+What:		/sys/.../events/in_anglvel_z_thresh_rising_hysteresis
+What:		/sys/.../events/in_anglvel_z_thresh_falling_hysteresis
+What:		/sys/.../events/in_anglvel_z_thresh_either_hysteresis
+What:		/sys/.../events/in_magn_x_thresh_rising_hysteresis
+What:		/sys/.../events/in_magn_x_thresh_falling_hysteresis
+What:		/sys/.../events/in_magn_x_thresh_either_hysteresis
+What:		/sys/.../events/in_magn_y_thresh_rising_hysteresis
+What:		/sys/.../events/in_magn_y_thresh_falling_hysteresis
+What:		/sys/.../events/in_magn_y_thresh_either_hysteresis
+What:		/sys/.../events/in_magn_z_thresh_rising_hysteresis
+What:		/sys/.../events/in_magn_z_thresh_falling_hysteresis
+What:		/sys/.../events/in_magn_z_thresh_either_hysteresis
+What:		/sys/.../events/in_voltageY_thresh_rising_hysteresis
+What:		/sys/.../events/in_voltageY_thresh_falling_hysteresis
+What:		/sys/.../events/in_voltageY_thresh_either_hysteresis
+What:		/sys/.../events/in_tempY_thresh_rising_hysteresis
+What:		/sys/.../events/in_tempY_thresh_falling_hysteresis
+What:		/sys/.../events/in_tempY_thresh_either_hysteresis
+What:		/sys/.../events/in_illuminance0_thresh_falling_hysteresis
+what:		/sys/.../events/in_illuminance0_thresh_rising_hysteresis
+what:		/sys/.../events/in_illuminance0_thresh_either_hysteresis
+what:		/sys/.../events/in_proximity0_thresh_falling_hysteresis
+what:		/sys/.../events/in_proximity0_thresh_rising_hysteresis
+what:		/sys/.../events/in_proximity0_thresh_either_hysteresis
+KernelVersion:	3.13
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Specifies the hysteresis of threshold that the device is comparing
+		against for the events enabled by
+		<type>Y[_name]_thresh[_(rising|falling)]_hysteresis.
+		If separate attributes exist for the two directions, but
+		direction is not specified for this attribute, then a single
+		hysteresis value applies to both directions.
+		For falling events the hysteresis is added to the _value attribute for
+		this event to get the upper threshold for when the event goes back to
+		normal, for rising events the hysteresis is subtracted from the _value
+		attribute. E.g. if in_voltage0_raw_thresh_rising_value is set to 1200
+		and in_voltage0_raw_thresh_rising_hysteresis is set to 50. The event
+		will get activated once in_voltage0_raw goes above 1200 and will become
+		deactived again once the value falls below 1150.
+
 What:		/sys/.../events/in_accel_x_raw_roc_rising_value
 What:		/sys/.../events/in_accel_x_raw_roc_falling_value
 What:		/sys/.../events/in_accel_y_raw_roc_rising_value
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index b7a5d7cbed42..dac15b9f9df8 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -204,6 +204,7 @@ static const char * const iio_ev_dir_text[] = {
 static const char * const iio_ev_info_text[] = {
 	[IIO_EV_INFO_ENABLE] = "en",
 	[IIO_EV_INFO_VALUE] = "value",
+	[IIO_EV_INFO_HYSTERESIS] = "hysteresis",
 };
 
 static enum iio_event_direction iio_ev_attr_dir(struct iio_dev_attr *attr)
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 18339ef4ff5d..4ac928ee31c5 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -65,6 +65,7 @@ enum iio_event_type {
 enum iio_event_info {
 	IIO_EV_INFO_ENABLE,
 	IIO_EV_INFO_VALUE,
+	IIO_EV_INFO_HYSTERESIS,
 };
 
 enum iio_event_direction {
-- 
cgit 


From 3124b84309a0699c98bdc0ef1fc8cd5e058ad5fa Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 12 Oct 2013 07:19:32 -0700
Subject: Bluetooth: Allow 3D profile to use security mode 4 level 0

The PSM 0x0021 is dedicated to the 3D profile and has permission to
use security mode 4 level 0 for L2CAP connectionless unicast data
transfers.

When establishing a L2CAP connectionless channel on PSM 0x0021, it
will no longer force Secure Simple Pairing.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/l2cap_core.c    | 10 ++++++++++
 net/bluetooth/l2cap_sock.c    |  4 ++++
 3 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index f141b5f6e4f1..12523c79eb3b 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -237,6 +237,7 @@ struct l2cap_conn_rsp {
 /* protocol/service multiplexer (PSM) */
 #define L2CAP_PSM_SDP		0x0001
 #define L2CAP_PSM_RFCOMM	0x0003
+#define L2CAP_PSM_3DSP		0x0021
 
 /* channel indentifier */
 #define L2CAP_CID_SIGNALING	0x0001
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index cc51cb860c40..e932ffda5445 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -688,6 +688,16 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan)
 			return HCI_AT_NO_BONDING;
 		}
 		break;
+	case L2CAP_CHAN_CONN_LESS:
+		if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_3DSP)) {
+			if (chan->sec_level == BT_SECURITY_LOW)
+				chan->sec_level = BT_SECURITY_SDP;
+		}
+		if (chan->sec_level == BT_SECURITY_HIGH)
+			return HCI_AT_NO_BONDING_MITM;
+		else
+			return HCI_AT_NO_BONDING;
+		break;
 	case L2CAP_CHAN_CONN_ORIENTED:
 		if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_SDP)) {
 			if (chan->sec_level == BT_SECURITY_LOW)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index bee98ebfae4d..bd6fe7fd2737 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -101,6 +101,10 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 		goto done;
 
 	switch (chan->chan_type) {
+	case L2CAP_CHAN_CONN_LESS:
+		if (__le16_to_cpu(la.l2_psm) == L2CAP_PSM_3DSP)
+			chan->sec_level = BT_SECURITY_SDP;
+		break;
 	case L2CAP_CHAN_CONN_ORIENTED:
 		if (__le16_to_cpu(la.l2_psm) == L2CAP_PSM_SDP ||
 		    __le16_to_cpu(la.l2_psm) == L2CAP_PSM_RFCOMM)
-- 
cgit 


From d40bffbc4e9afce9c0be6ea399b4103f72e50ec2 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 12 Oct 2013 08:18:18 -0700
Subject: Bluetooth: The L2CAP fixed channel connectionless data is supported

The implementation actually supports the L2CAP connectionless data
channel. So set it as supported in the fixed channels bitmask.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h | 1 +
 net/bluetooth/l2cap_core.c    | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 12523c79eb3b..56f540e7a8fc 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -131,6 +131,7 @@ struct l2cap_conninfo {
 
 /* L2CAP fixed channels */
 #define L2CAP_FC_L2CAP		0x02
+#define L2CAP_FC_CONNLESS	0x04
 #define L2CAP_FC_A2MP		0x08
 
 /* L2CAP Control Field bit masks */
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e932ffda5445..8b5437c44c7b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -44,7 +44,7 @@
 bool disable_ertm;
 
 static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN;
-static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP, };
+static u8 l2cap_fixed_chan[8] = { L2CAP_FC_L2CAP | L2CAP_FC_CONNLESS, };
 
 static LIST_HEAD(chan_list);
 static DEFINE_RWLOCK(chan_list_lock);
-- 
cgit 


From a4de24d4370d0e7fbfbc47244ceb203e959b23aa Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 02:23:41 -0700
Subject: Bluetooth: Remove l2cap_conn->src and l2cap_conn->dst pointers

The l2cap_conn->src and l2cap_conn->dst pointers are no longer in use
and so just remove them.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 56f540e7a8fc..1a929afe4f16 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -559,9 +559,6 @@ struct l2cap_conn {
 	struct hci_conn		*hcon;
 	struct hci_chan		*hchan;
 
-	bdaddr_t		*dst;
-	bdaddr_t		*src;
-
 	unsigned int		mtu;
 
 	__u32			feat_mask;
-- 
cgit 


From 79d95a19a445f5758571b3342064f2c1e40b6c5f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 03:57:38 -0700
Subject: Bluetooth: Remove pointless bdaddr_to_le() helper function

The bdaddr_to_le() function tries to convert the internal address
type to one that matches the HCI address type for LE. It does not
handle any address types not used by LE and in the end just make
the code a lot harder to read.

So instead of just hiding behind a magic function, just convert
the internal address type where it needs to be converted. And it
turns out that these are only two cases anyway. One when creating
new LE connections and the other when loading the long term keys.
In both cases this makes it more clear on what it going on.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 --
 net/bluetooth/hci_conn.c         |  5 ++++-
 net/bluetooth/hci_core.c         | 12 ------------
 net/bluetooth/mgmt.c             | 10 +++++++---
 4 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 690045498420..7889495da843 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1187,8 +1187,6 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max,
 void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8],
 							__u8 ltk[16]);
 
-u8 bdaddr_to_le(u8 bdaddr_type);
-
 #define SCO_AIRMODE_MASK       0x0003
 #define SCO_AIRMODE_CVSD       0x0000
 #define SCO_AIRMODE_TRANSP     0x0003
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index c52bfb7e44fd..bb32f48b88f9 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -622,7 +622,10 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	if (!conn)
 		return ERR_PTR(-ENOMEM);
 
-	conn->dst_type = bdaddr_to_le(dst_type);
+	if (dst_type == BDADDR_LE_PUBLIC)
+		conn->dst_type = ADDR_LE_DEV_PUBLIC;
+	else
+		conn->dst_type = ADDR_LE_DEV_RANDOM;
 	conn->state = BT_CONNECT;
 	conn->out = true;
 	conn->link_mode |= HCI_LM_MASTER;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 082f3966f894..0e05edee0962 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3695,15 +3695,3 @@ static void hci_cmd_work(struct work_struct *work)
 		}
 	}
 }
-
-u8 bdaddr_to_le(u8 bdaddr_type)
-{
-	switch (bdaddr_type) {
-	case BDADDR_LE_PUBLIC:
-		return ADDR_LE_DEV_PUBLIC;
-
-	default:
-		/* Fallback to LE Random address type */
-		return ADDR_LE_DEV_RANDOM;
-	}
-}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 338878c13571..020f95b84b09 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3678,15 +3678,19 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
-		u8 type;
+		u8 type, addr_type;
+
+		if (key->addr.type == BDADDR_LE_PUBLIC)
+			addr_type = ADDR_LE_DEV_PUBLIC;
+		else
+			addr_type = ADDR_LE_DEV_RANDOM;
 
 		if (key->master)
 			type = HCI_SMP_LTK;
 		else
 			type = HCI_SMP_LTK_SLAVE;
 
-		hci_add_ltk(hdev, &key->addr.bdaddr,
-			    bdaddr_to_le(key->addr.type),
+		hci_add_ltk(hdev, &key->addr.bdaddr, addr_type,
 			    type, 0, key->authenticated, key->val,
 			    key->enc_size, key->ediv, key->rand);
 	}
-- 
cgit 


From e7c4096e16f0e362c6cf902baab0de37ebfc1266 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 03:57:39 -0700
Subject: Bluetooth: Store the source address type of LE connections

When establishing LE connections, it is possible to use a public
address (if available) or a random address. The type of address
is only known when creating connections, so make sure it is
stored in hci_conn structure.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_conn.c         | 11 +++++++----
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7889495da843..714da9ea465e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -300,6 +300,7 @@ struct hci_conn {
 
 	bdaddr_t	dst;
 	__u8		dst_type;
+	__u8		src_type;
 	__u16		handle;
 	__u16		state;
 	__u8		mode;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index bb32f48b88f9..d9f7f93b813e 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -566,10 +566,7 @@ static int hci_create_le_conn(struct hci_conn *conn)
 	cp.scan_window = cpu_to_le16(hdev->le_scan_window);
 	bacpy(&cp.peer_addr, &conn->dst);
 	cp.peer_addr_type = conn->dst_type;
-	if (bacmp(&hdev->bdaddr, BDADDR_ANY))
-		cp.own_address_type = ADDR_LE_DEV_PUBLIC;
-	else
-		cp.own_address_type = ADDR_LE_DEV_RANDOM;
+	cp.own_address_type = conn->src_type;
 	cp.conn_interval_min = __constant_cpu_to_le16(0x0028);
 	cp.conn_interval_max = __constant_cpu_to_le16(0x0038);
 	cp.supervision_timeout = __constant_cpu_to_le16(0x002a);
@@ -626,6 +623,12 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 		conn->dst_type = ADDR_LE_DEV_PUBLIC;
 	else
 		conn->dst_type = ADDR_LE_DEV_RANDOM;
+
+	if (bacmp(&hdev->bdaddr, BDADDR_ANY))
+		conn->src_type = ADDR_LE_DEV_PUBLIC;
+	else
+		conn->src_type = ADDR_LE_DEV_RANDOM;
+
 	conn->state = BT_CONNECT;
 	conn->out = true;
 	conn->link_mode |= HCI_LM_MASTER;
-- 
cgit 


From 662e8820f38dcc458e0d4769194db5ed3469224f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 05:23:59 -0700
Subject: Bluetooth: Store source address of HCI connections

The source addressed was based on the public address of the HCI device,
but with LE connections this not always the case. For example single
mode LE-only controllers would use a static random address. And this
address is configured by userspace.

To not complicate the lookup of what kind of address is in use, store
the correct source address for each HCI connection.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/hci_conn.c         | 7 +++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 714da9ea465e..0326b160b89a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -300,6 +300,7 @@ struct hci_conn {
 
 	bdaddr_t	dst;
 	__u8		dst_type;
+	bdaddr_t	src;
 	__u8		src_type;
 	__u16		handle;
 	__u16		state;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d9f7f93b813e..ff04b051792d 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -381,6 +381,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 		return NULL;
 
 	bacpy(&conn->dst, dst);
+	bacpy(&conn->src, &hdev->bdaddr);
 	conn->hdev  = hdev;
 	conn->type  = type;
 	conn->mode  = HCI_CM_ACTIVE;
@@ -624,10 +625,12 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	else
 		conn->dst_type = ADDR_LE_DEV_RANDOM;
 
-	if (bacmp(&hdev->bdaddr, BDADDR_ANY))
+	if (bacmp(&conn->src, BDADDR_ANY)) {
 		conn->src_type = ADDR_LE_DEV_PUBLIC;
-	else
+	} else {
+		bacpy(&conn->src, &hdev->static_addr);
 		conn->src_type = ADDR_LE_DEV_RANDOM;
+	}
 
 	conn->state = BT_CONNECT;
 	conn->out = true;
-- 
cgit 


From 7eafc59e2f547fce3a31b3e2d03c14d57e9162b2 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 08:12:47 -0700
Subject: Bluetooth: Store address information in L2CAP channel structure

With the effort of abstracting the L2CAP socket from the underlying
L2CAP channel it is important to store the source and destination
address information directly in the L2CAP channel structure.

Direct access to the HCI connection address information is not
possible since they might not be avaiable at L2CAP channel
creation time. The address information will be updated when
the underlying BR/EDR or LE connection status changes.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h |  2 ++
 net/bluetooth/l2cap_core.c    | 61 +++++++++++++++++--------------------------
 net/bluetooth/l2cap_sock.c    |  6 ++---
 3 files changed, 29 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1a929afe4f16..26b5066e74e2 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -444,6 +444,8 @@ struct l2cap_chan {
 
 	__u8		state;
 
+	bdaddr_t	dst;
+	bdaddr_t	src;
 	__le16		psm;
 	__u16		dcid;
 	__u16		scid;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 062e28e4722b..be3e0f8c6f8b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -149,7 +149,7 @@ static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src)
 	struct l2cap_chan *c;
 
 	list_for_each_entry(c, &chan_list, global_l) {
-		if (c->sport == psm && !bacmp(&bt_sk(c->sk)->src, src))
+		if (c->sport == psm && !bacmp(&c->src, src))
 			return c;
 	}
 	return NULL;
@@ -621,10 +621,8 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err)
 void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 {
 	struct l2cap_conn *conn = chan->conn;
-	struct sock *sk = chan->sk;
 
-	BT_DBG("chan %p state %s sk %p", chan, state_to_string(chan->state),
-	       sk);
+	BT_DBG("chan %p state %s", chan, state_to_string(chan->state));
 
 	switch (chan->state) {
 	case BT_LISTEN:
@@ -635,6 +633,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 	case BT_CONFIG:
 		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
 		    conn->hcon->type == ACL_LINK) {
+			struct sock *sk = chan->sk;
 			__set_chan_timer(chan, sk->sk_sndtimeo);
 			l2cap_send_disconn_req(chan, reason);
 		} else
@@ -644,6 +643,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 	case BT_CONNECT2:
 		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
 		    conn->hcon->type == ACL_LINK) {
+			struct sock *sk = chan->sk;
 			struct l2cap_conn_rsp rsp;
 			__u16 result;
 
@@ -1257,8 +1257,6 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 	mutex_lock(&conn->chan_lock);
 
 	list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) {
-		struct sock *sk = chan->sk;
-
 		l2cap_chan_lock(chan);
 
 		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {
@@ -1284,6 +1282,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 			l2cap_start_connection(chan);
 
 		} else if (chan->state == BT_CONNECT2) {
+			struct sock *sk = chan->sk;
 			struct l2cap_conn_rsp rsp;
 			char buf[128];
 			rsp.scid = cpu_to_le16(chan->dcid);
@@ -1341,8 +1340,6 @@ static struct l2cap_chan *l2cap_global_chan_by_scid(int state, u16 cid,
 	read_lock(&chan_list_lock);
 
 	list_for_each_entry(c, &chan_list, global_l) {
-		struct sock *sk = c->sk;
-
 		if (state && c->state != state)
 			continue;
 
@@ -1351,16 +1348,16 @@ static struct l2cap_chan *l2cap_global_chan_by_scid(int state, u16 cid,
 			int src_any, dst_any;
 
 			/* Exact match. */
-			src_match = !bacmp(&bt_sk(sk)->src, src);
-			dst_match = !bacmp(&bt_sk(sk)->dst, dst);
+			src_match = !bacmp(&c->src, src);
+			dst_match = !bacmp(&c->dst, dst);
 			if (src_match && dst_match) {
 				read_unlock(&chan_list_lock);
 				return c;
 			}
 
 			/* Closest match */
-			src_any = !bacmp(&bt_sk(sk)->src, BDADDR_ANY);
-			dst_any = !bacmp(&bt_sk(sk)->dst, BDADDR_ANY);
+			src_any = !bacmp(&c->src, BDADDR_ANY);
+			dst_any = !bacmp(&c->dst, BDADDR_ANY);
 			if ((src_match && dst_any) || (src_any && dst_match) ||
 			    (src_any && dst_any))
 				c1 = c;
@@ -1399,8 +1396,8 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
 
 	chan->dcid = L2CAP_CID_ATT;
 
-	bacpy(&bt_sk(chan->sk)->src, &conn->hcon->src);
-	bacpy(&bt_sk(chan->sk)->dst, &conn->hcon->dst);
+	bacpy(&chan->src, &conn->hcon->src);
+	bacpy(&chan->dst, &conn->hcon->dst);
 
 	__l2cap_chan_add(conn, chan);
 
@@ -1721,8 +1718,6 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 	read_lock(&chan_list_lock);
 
 	list_for_each_entry(c, &chan_list, global_l) {
-		struct sock *sk = c->sk;
-
 		if (state && c->state != state)
 			continue;
 
@@ -1731,16 +1726,16 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 			int src_any, dst_any;
 
 			/* Exact match. */
-			src_match = !bacmp(&bt_sk(sk)->src, src);
-			dst_match = !bacmp(&bt_sk(sk)->dst, dst);
+			src_match = !bacmp(&c->src, src);
+			dst_match = !bacmp(&c->dst, dst);
 			if (src_match && dst_match) {
 				read_unlock(&chan_list_lock);
 				return c;
 			}
 
 			/* Closest match */
-			src_any = !bacmp(&bt_sk(sk)->src, BDADDR_ANY);
-			dst_any = !bacmp(&bt_sk(sk)->dst, BDADDR_ANY);
+			src_any = !bacmp(&c->src, BDADDR_ANY);
+			dst_any = !bacmp(&c->dst, BDADDR_ANY);
 			if ((src_match && dst_any) || (src_any && dst_match) ||
 			    (src_any && dst_any))
 				c1 = c;
@@ -1762,10 +1757,10 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 	__u8 auth_type;
 	int err;
 
-	BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &bt_sk(sk)->src, dst,
+	BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst,
 	       dst_type, __le16_to_cpu(psm));
 
-	hdev = hci_get_route(dst, &bt_sk(sk)->src);
+	hdev = hci_get_route(dst, &chan->src);
 	if (!hdev)
 		return -EHOSTUNREACH;
 
@@ -1822,9 +1817,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 	}
 
 	/* Set destination address and psm */
-	lock_sock(sk);
-	bacpy(&bt_sk(sk)->dst, dst);
-	release_sock(sk);
+	bacpy(&chan->dst, dst);
 
 	chan->psm = psm;
 	chan->dcid = cid;
@@ -1857,9 +1850,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 	}
 
 	/* Update source addr of the socket */
-	lock_sock(sk);
-	bacpy(&bt_sk(sk)->src, &hcon->src);
-	release_sock(sk);
+	bacpy(&chan->src, &hcon->src);
 
 	l2cap_chan_unlock(chan);
 	l2cap_chan_add(conn, chan);
@@ -3798,8 +3789,8 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 	 */
 	conn->hcon->disc_timeout = HCI_DISCONN_TIMEOUT;
 
-	bacpy(&bt_sk(sk)->src, &conn->hcon->src);
-	bacpy(&bt_sk(sk)->dst, &conn->hcon->dst);
+	bacpy(&chan->src, &conn->hcon->src);
+	bacpy(&chan->dst, &conn->hcon->dst);
 	chan->psm  = psm;
 	chan->dcid = scid;
 	chan->local_amp_id = amp_id;
@@ -6542,17 +6533,15 @@ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr)
 	/* Find listening sockets and check their link_mode */
 	read_lock(&chan_list_lock);
 	list_for_each_entry(c, &chan_list, global_l) {
-		struct sock *sk = c->sk;
-
 		if (c->state != BT_LISTEN)
 			continue;
 
-		if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr)) {
+		if (!bacmp(&c->src, &hdev->bdaddr)) {
 			lm1 |= HCI_LM_ACCEPT;
 			if (test_bit(FLAG_ROLE_SWITCH, &c->flags))
 				lm1 |= HCI_LM_MASTER;
 			exact++;
-		} else if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY)) {
+		} else if (!bacmp(&c->src, BDADDR_ANY)) {
 			lm2 |= HCI_LM_ACCEPT;
 			if (test_bit(FLAG_ROLE_SWITCH, &c->flags))
 				lm2 |= HCI_LM_MASTER;
@@ -6840,10 +6829,8 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p)
 	read_lock(&chan_list_lock);
 
 	list_for_each_entry(c, &chan_list, global_l) {
-		struct sock *sk = c->sk;
-
 		seq_printf(f, "%pMR %pMR %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n",
-			   &bt_sk(sk)->src, &bt_sk(sk)->dst,
+			   &c->src, &c->dst,
 			   c->state, __le16_to_cpu(c->psm),
 			   c->scid, c->dcid, c->imtu, c->omtu,
 			   c->sec_level, c->mode);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index bd6fe7fd2737..9fe80d228c19 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -112,7 +112,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 		break;
 	}
 
-	bacpy(&bt_sk(sk)->src, &la.l2_bdaddr);
+	bacpy(&chan->src, &la.l2_bdaddr);
 
 	chan->state = BT_BOUND;
 	sk->sk_state = BT_BOUND;
@@ -274,11 +274,11 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
 
 	if (peer) {
 		la->l2_psm = chan->psm;
-		bacpy(&la->l2_bdaddr, &bt_sk(sk)->dst);
+		bacpy(&la->l2_bdaddr, &chan->dst);
 		la->l2_cid = cpu_to_le16(chan->dcid);
 	} else {
 		la->l2_psm = chan->sport;
-		bacpy(&la->l2_bdaddr, &bt_sk(sk)->src);
+		bacpy(&la->l2_bdaddr, &chan->src);
 		la->l2_cid = cpu_to_le16(chan->scid);
 	}
 
-- 
cgit 


From 4f1654e08464abad06487e173661cb73721d27a7 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 08:50:41 -0700
Subject: Bluetooth: Return the correct address type for L2CAP sockets

The L2CAP sockets can use BR/EDR public, LE public and LE random
addresses for various combinations of source and destination
devices. So make sure that getsockname(), getpeername() and
accept() return the correct address type.

For this the address type of the source and destination is stored
with the L2CAP channel information. The stored address type is
not the one specific for the HCI protocol. It is the address
type used for the L2CAP sockets and the management interface.

The underlying HCI connections store the HCI address type. If
needed, it gets converted to the socket address type.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h |  5 +++--
 net/bluetooth/l2cap_core.c    | 18 ++++++++++++++++++
 net/bluetooth/l2cap_sock.c    |  3 +++
 3 files changed, 24 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 26b5066e74e2..a27d51dc39a4 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -445,8 +445,11 @@ struct l2cap_chan {
 	__u8		state;
 
 	bdaddr_t	dst;
+	__u8		dst_type;
 	bdaddr_t	src;
+	__u8		src_type;
 	__le16		psm;
+	__le16		sport;
 	__u16		dcid;
 	__u16		scid;
 
@@ -457,8 +460,6 @@ struct l2cap_chan {
 	__u8		chan_type;
 	__u8		chan_policy;
 
-	__le16		sport;
-
 	__u8		sec_level;
 
 	__u8		ident;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index be3e0f8c6f8b..769c379b3eeb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -59,6 +59,18 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err);
 static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
 		     struct sk_buff_head *skbs, u8 event);
 
+static inline __u8 bdaddr_type(struct hci_conn *hcon, __u8 type)
+{
+	if (hcon->type == LE_LINK) {
+		if (type == ADDR_LE_DEV_PUBLIC)
+			return BDADDR_LE_PUBLIC;
+		else
+			return BDADDR_LE_RANDOM;
+	}
+
+	return BDADDR_BREDR;
+}
+
 /* ---- L2CAP channels ---- */
 
 static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
@@ -1398,6 +1410,8 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn)
 
 	bacpy(&chan->src, &conn->hcon->src);
 	bacpy(&chan->dst, &conn->hcon->dst);
+	chan->src_type = bdaddr_type(conn->hcon, conn->hcon->src_type);
+	chan->dst_type = bdaddr_type(conn->hcon, conn->hcon->dst_type);
 
 	__l2cap_chan_add(conn, chan);
 
@@ -1818,6 +1832,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 
 	/* Set destination address and psm */
 	bacpy(&chan->dst, dst);
+	chan->dst_type = dst_type;
 
 	chan->psm = psm;
 	chan->dcid = cid;
@@ -1851,6 +1866,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 
 	/* Update source addr of the socket */
 	bacpy(&chan->src, &hcon->src);
+	chan->src_type = bdaddr_type(hcon, hcon->src_type);
 
 	l2cap_chan_unlock(chan);
 	l2cap_chan_add(conn, chan);
@@ -3791,6 +3807,8 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 
 	bacpy(&chan->src, &conn->hcon->src);
 	bacpy(&chan->dst, &conn->hcon->dst);
+	chan->src_type = bdaddr_type(conn->hcon, conn->hcon->src_type);
+	chan->dst_type = bdaddr_type(conn->hcon, conn->hcon->dst_type);
 	chan->psm  = psm;
 	chan->dcid = scid;
 	chan->local_amp_id = amp_id;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 9fe80d228c19..6262e23b71a4 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -113,6 +113,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	}
 
 	bacpy(&chan->src, &la.l2_bdaddr);
+	chan->src_type = la.l2_bdaddr_type;
 
 	chan->state = BT_BOUND;
 	sk->sk_state = BT_BOUND;
@@ -276,10 +277,12 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr,
 		la->l2_psm = chan->psm;
 		bacpy(&la->l2_bdaddr, &chan->dst);
 		la->l2_cid = cpu_to_le16(chan->dcid);
+		la->l2_bdaddr_type = chan->dst_type;
 	} else {
 		la->l2_psm = chan->sport;
 		bacpy(&la->l2_bdaddr, &chan->src);
 		la->l2_cid = cpu_to_le16(chan->scid);
+		la->l2_bdaddr_type = chan->src_type;
 	}
 
 	return 0;
-- 
cgit 


From 041987cff6fb7d2e7acd5897390ad0eef575ed39 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 10:15:22 -0700
Subject: Bluetooth: Use SCO addresses from HCI connection directly

Instead of storing a pointer to the addresses for the HCI device
and HCI connection, use them directly. With the recent changes
to address tracking of HCI connections, this becomes simple.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/sco.h |  3 ---
 net/bluetooth/sco.c         | 20 ++++++++------------
 2 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h
index e252a31ee6b6..94703a25d1c2 100644
--- a/include/net/bluetooth/sco.h
+++ b/include/net/bluetooth/sco.h
@@ -55,9 +55,6 @@ struct sco_conninfo {
 struct sco_conn {
 	struct hci_conn	*hcon;
 
-	bdaddr_t	*dst;
-	bdaddr_t	*src;
-
 	spinlock_t	lock;
 	struct sock	*sk;
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 96bd388d93a4..2cc8f425613a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -92,9 +92,6 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon)
 	hcon->sco_data = conn;
 	conn->hcon = hcon;
 
-	conn->src = &hdev->bdaddr;
-	conn->dst = &hcon->dst;
-
 	if (hdev->sco_mtu > 0)
 		conn->mtu = hdev->sco_mtu;
 	else
@@ -156,16 +153,14 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk,
 
 static int sco_connect(struct sock *sk)
 {
-	bdaddr_t *src = &bt_sk(sk)->src;
-	bdaddr_t *dst = &bt_sk(sk)->dst;
 	struct sco_conn *conn;
 	struct hci_conn *hcon;
 	struct hci_dev  *hdev;
 	int err, type;
 
-	BT_DBG("%pMR -> %pMR", src, dst);
+	BT_DBG("%pMR -> %pMR", &bt_sk(sk)->src, &bt_sk(sk)->dst);
 
-	hdev = hci_get_route(dst, src);
+	hdev = hci_get_route(&bt_sk(sk)->dst, &bt_sk(sk)->src);
 	if (!hdev)
 		return -EHOSTUNREACH;
 
@@ -182,7 +177,8 @@ static int sco_connect(struct sock *sk)
 		goto done;
 	}
 
-	hcon = hci_connect_sco(hdev, type, dst, sco_pi(sk)->setting);
+	hcon = hci_connect_sco(hdev, type, &bt_sk(sk)->dst,
+			       sco_pi(sk)->setting);
 	if (IS_ERR(hcon)) {
 		err = PTR_ERR(hcon);
 		goto done;
@@ -196,7 +192,7 @@ static int sco_connect(struct sock *sk)
 	}
 
 	/* Update source addr of the socket */
-	bacpy(src, conn->src);
+	bacpy(&bt_sk(sk)->src, &hcon->src);
 
 	err = sco_chan_add(conn, sk, NULL);
 	if (err)
@@ -999,7 +995,7 @@ static void sco_conn_ready(struct sco_conn *conn)
 	} else {
 		sco_conn_lock(conn);
 
-		parent = sco_get_sock_listen(conn->src);
+		parent = sco_get_sock_listen(&conn->hcon->src);
 		if (!parent) {
 			sco_conn_unlock(conn);
 			return;
@@ -1017,8 +1013,8 @@ static void sco_conn_ready(struct sco_conn *conn)
 
 		sco_sock_init(sk, parent);
 
-		bacpy(&bt_sk(sk)->src, conn->src);
-		bacpy(&bt_sk(sk)->dst, conn->dst);
+		bacpy(&bt_sk(sk)->src, &conn->hcon->src);
+		bacpy(&bt_sk(sk)->dst, &conn->hcon->dst);
 
 		hci_conn_hold(conn->hcon);
 		__sco_chan_add(conn, sk, parent);
-- 
cgit 


From eea963641bf548bda164b92aa20ccda56c5cf349 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 10:34:01 -0700
Subject: Bluetooth: Store SCO address information in its own socket structure

The address information of SCO sockets should be stored in its own
socket structure. Trying to generalize them is not helpful since
different transports have different address types.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/sco.h |  2 ++
 net/bluetooth/sco.c         | 36 ++++++++++++++++++------------------
 2 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h
index 94703a25d1c2..2019d1a0996a 100644
--- a/include/net/bluetooth/sco.h
+++ b/include/net/bluetooth/sco.h
@@ -69,6 +69,8 @@ struct sco_conn {
 
 struct sco_pinfo {
 	struct bt_sock	bt;
+	bdaddr_t	src;
+	bdaddr_t	dst;
 	__u32		flags;
 	__u16		setting;
 	struct sco_conn	*conn;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 2cc8f425613a..a92aebac56ca 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -158,9 +158,9 @@ static int sco_connect(struct sock *sk)
 	struct hci_dev  *hdev;
 	int err, type;
 
-	BT_DBG("%pMR -> %pMR", &bt_sk(sk)->src, &bt_sk(sk)->dst);
+	BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst);
 
-	hdev = hci_get_route(&bt_sk(sk)->dst, &bt_sk(sk)->src);
+	hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src);
 	if (!hdev)
 		return -EHOSTUNREACH;
 
@@ -177,7 +177,7 @@ static int sco_connect(struct sock *sk)
 		goto done;
 	}
 
-	hcon = hci_connect_sco(hdev, type, &bt_sk(sk)->dst,
+	hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst,
 			       sco_pi(sk)->setting);
 	if (IS_ERR(hcon)) {
 		err = PTR_ERR(hcon);
@@ -192,7 +192,7 @@ static int sco_connect(struct sock *sk)
 	}
 
 	/* Update source addr of the socket */
-	bacpy(&bt_sk(sk)->src, &hcon->src);
+	bacpy(&sco_pi(sk)->src, &hcon->src);
 
 	err = sco_chan_add(conn, sk, NULL);
 	if (err)
@@ -266,7 +266,7 @@ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba)
 		if (sk->sk_state != BT_LISTEN)
 			continue;
 
-		if (!bacmp(&bt_sk(sk)->src, ba))
+		if (!bacmp(&sco_pi(sk)->src, ba))
 			return sk;
 	}
 
@@ -287,11 +287,11 @@ static struct sock *sco_get_sock_listen(bdaddr_t *src)
 			continue;
 
 		/* Exact match. */
-		if (!bacmp(&bt_sk(sk)->src, src))
+		if (!bacmp(&sco_pi(sk)->src, src))
 			break;
 
 		/* Closest match */
-		if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY))
+		if (!bacmp(&sco_pi(sk)->src, BDADDR_ANY))
 			sk1 = sk;
 	}
 
@@ -471,7 +471,7 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le
 		goto done;
 	}
 
-	bacpy(&bt_sk(sk)->src, &sa->sco_bdaddr);
+	bacpy(&sco_pi(sk)->src, &sa->sco_bdaddr);
 
 	sk->sk_state = BT_BOUND;
 
@@ -501,7 +501,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen
 	lock_sock(sk);
 
 	/* Set destination address and psm */
-	bacpy(&bt_sk(sk)->dst, &sa->sco_bdaddr);
+	bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
 
 	err = sco_connect(sk);
 	if (err)
@@ -518,7 +518,7 @@ done:
 static int sco_sock_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
-	bdaddr_t *src = &bt_sk(sk)->src;
+	bdaddr_t *src = &sco_pi(sk)->src;
 	int err = 0;
 
 	BT_DBG("sk %p backlog %d", sk, backlog);
@@ -622,9 +622,9 @@ static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int *len
 	*len = sizeof(struct sockaddr_sco);
 
 	if (peer)
-		bacpy(&sa->sco_bdaddr, &bt_sk(sk)->dst);
+		bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst);
 	else
-		bacpy(&sa->sco_bdaddr, &bt_sk(sk)->src);
+		bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src);
 
 	return 0;
 }
@@ -1013,8 +1013,8 @@ static void sco_conn_ready(struct sco_conn *conn)
 
 		sco_sock_init(sk, parent);
 
-		bacpy(&bt_sk(sk)->src, &conn->hcon->src);
-		bacpy(&bt_sk(sk)->dst, &conn->hcon->dst);
+		bacpy(&sco_pi(sk)->src, &conn->hcon->src);
+		bacpy(&sco_pi(sk)->dst, &conn->hcon->dst);
 
 		hci_conn_hold(conn->hcon);
 		__sco_chan_add(conn, sk, parent);
@@ -1047,8 +1047,8 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 		if (sk->sk_state != BT_LISTEN)
 			continue;
 
-		if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr) ||
-		    !bacmp(&bt_sk(sk)->src, BDADDR_ANY)) {
+		if (!bacmp(&sco_pi(sk)->src, &hdev->bdaddr) ||
+		    !bacmp(&sco_pi(sk)->src, BDADDR_ANY)) {
 			lm |= HCI_LM_ACCEPT;
 
 			if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))
@@ -1107,8 +1107,8 @@ static int sco_debugfs_show(struct seq_file *f, void *p)
 	read_lock(&sco_sk_list.lock);
 
 	sk_for_each(sk, &sco_sk_list.head) {
-		seq_printf(f, "%pMR %pMR %d\n", &bt_sk(sk)->src,
-			   &bt_sk(sk)->dst, sk->sk_state);
+		seq_printf(f, "%pMR %pMR %d\n", &sco_pi(sk)->src,
+			   &sco_pi(sk)->dst, sk->sk_state);
 	}
 
 	read_unlock(&sco_sk_list.lock);
-- 
cgit 


From 94a86df01082557e2de45865e538d7fb6c46231c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 10:34:02 -0700
Subject: Bluetooth: Store RFCOMM address information in its own socket
 structure

The address information of RFCOMM sockets should be stored in its
own socket structure. Trying to generalize them is not helpful since
different transports have different address types.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/rfcomm.h |  2 ++
 net/bluetooth/rfcomm/sock.c    | 28 +++++++++++++++-------------
 2 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 7afd4199d6b6..3588f48bfd35 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -300,6 +300,8 @@ struct rfcomm_conninfo {
 
 struct rfcomm_pinfo {
 	struct bt_sock bt;
+	bdaddr_t src;
+	bdaddr_t dst;
 	struct rfcomm_dlc   *dlc;
 	u8     channel;
 	u8     sec_level;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 072938dc527d..df17276eb32b 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -87,7 +87,8 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 		parent->sk_data_ready(parent, 0);
 	} else {
 		if (d->state == BT_CONNECTED)
-			rfcomm_session_getaddr(d->session, &bt_sk(sk)->src, NULL);
+			rfcomm_session_getaddr(d->session,
+					       &rfcomm_pi(sk)->src, NULL);
 		sk->sk_state_change(sk);
 	}
 
@@ -110,7 +111,7 @@ static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src)
 
 	sk_for_each(sk, &rfcomm_sk_list.head) {
 		if (rfcomm_pi(sk)->channel == channel &&
-				!bacmp(&bt_sk(sk)->src, src))
+				!bacmp(&rfcomm_pi(sk)->src, src))
 			break;
 	}
 
@@ -132,11 +133,11 @@ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *
 
 		if (rfcomm_pi(sk)->channel == channel) {
 			/* Exact match. */
-			if (!bacmp(&bt_sk(sk)->src, src))
+			if (!bacmp(&rfcomm_pi(sk)->src, src))
 				break;
 
 			/* Closest match */
-			if (!bacmp(&bt_sk(sk)->src, BDADDR_ANY))
+			if (!bacmp(&rfcomm_pi(sk)->src, BDADDR_ANY))
 				sk1 = sk;
 		}
 	}
@@ -355,7 +356,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr
 		err = -EADDRINUSE;
 	} else {
 		/* Save source address */
-		bacpy(&bt_sk(sk)->src, &sa->rc_bdaddr);
+		bacpy(&rfcomm_pi(sk)->src, &sa->rc_bdaddr);
 		rfcomm_pi(sk)->channel = sa->rc_channel;
 		sk->sk_state = BT_BOUND;
 	}
@@ -393,13 +394,14 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a
 	}
 
 	sk->sk_state = BT_CONNECT;
-	bacpy(&bt_sk(sk)->dst, &sa->rc_bdaddr);
+	bacpy(&rfcomm_pi(sk)->dst, &sa->rc_bdaddr);
 	rfcomm_pi(sk)->channel = sa->rc_channel;
 
 	d->sec_level = rfcomm_pi(sk)->sec_level;
 	d->role_switch = rfcomm_pi(sk)->role_switch;
 
-	err = rfcomm_dlc_open(d, &bt_sk(sk)->src, &sa->rc_bdaddr, sa->rc_channel);
+	err = rfcomm_dlc_open(d, &rfcomm_pi(sk)->src, &sa->rc_bdaddr,
+			      sa->rc_channel);
 	if (!err)
 		err = bt_sock_wait_state(sk, BT_CONNECTED,
 				sock_sndtimeo(sk, flags & O_NONBLOCK));
@@ -429,7 +431,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog)
 	}
 
 	if (!rfcomm_pi(sk)->channel) {
-		bdaddr_t *src = &bt_sk(sk)->src;
+		bdaddr_t *src = &rfcomm_pi(sk)->src;
 		u8 channel;
 
 		err = -EINVAL;
@@ -530,9 +532,9 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int *
 	sa->rc_family  = AF_BLUETOOTH;
 	sa->rc_channel = rfcomm_pi(sk)->channel;
 	if (peer)
-		bacpy(&sa->rc_bdaddr, &bt_sk(sk)->dst);
+		bacpy(&sa->rc_bdaddr, &rfcomm_pi(sk)->dst);
 	else
-		bacpy(&sa->rc_bdaddr, &bt_sk(sk)->src);
+		bacpy(&sa->rc_bdaddr, &rfcomm_pi(sk)->src);
 
 	*len = sizeof(struct sockaddr_rc);
 	return 0;
@@ -951,8 +953,8 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
 	bt_sock_reclassify_lock(sk, BTPROTO_RFCOMM);
 
 	rfcomm_sock_init(sk, parent);
-	bacpy(&bt_sk(sk)->src, &src);
-	bacpy(&bt_sk(sk)->dst, &dst);
+	bacpy(&rfcomm_pi(sk)->src, &src);
+	bacpy(&rfcomm_pi(sk)->dst, &dst);
 	rfcomm_pi(sk)->channel = channel;
 
 	sk->sk_state = BT_CONFIG;
@@ -979,7 +981,7 @@ static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p)
 
 	sk_for_each(sk, &rfcomm_sk_list.head) {
 		seq_printf(f, "%pMR %pMR %d %d\n",
-			   &bt_sk(sk)->src, &bt_sk(sk)->dst,
+			   &rfcomm_pi(sk)->src, &rfcomm_pi(sk)->dst,
 			   sk->sk_state, rfcomm_pi(sk)->channel);
 	}
 
-- 
cgit 


From 5f6cd79f477743cab98fd49feb03a39e0138b32f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 10:34:03 -0700
Subject: Bluetooth: Remove src and dst fields from bt_sock structure

Every socket protocol now stores its own address information. So
just remove the generic src and dst fields since they are no longer
needed.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h | 2 --
 net/bluetooth/af_bluetooth.c      | 4 +---
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 5fd510675cfa..1d6e484e08ef 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -218,8 +218,6 @@ void baswap(bdaddr_t *dst, bdaddr_t *src);
 
 struct bt_sock {
 	struct sock sk;
-	bdaddr_t    src;
-	bdaddr_t    dst;
 	struct list_head accept_q;
 	struct sock *parent;
 	unsigned long flags;
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index e6e1278dca89..9c7e4edc6504 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -617,15 +617,13 @@ static int bt_seq_show(struct seq_file *seq, void *v)
 		struct bt_sock *bt = bt_sk(sk);
 
 		seq_printf(seq,
-			   "%pK %-6d %-6u %-6u %-6u %-6lu %pMR %pMR %-6lu",
+			   "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu",
 			   sk,
 			   atomic_read(&sk->sk_refcnt),
 			   sk_rmem_alloc_get(sk),
 			   sk_wmem_alloc_get(sk),
 			   from_kuid(seq_user_ns(seq), sock_i_uid(sk)),
 			   sock_i_ino(sk),
-			   &bt->src,
-			   &bt->dst,
 			   bt->parent? sock_i_ino(bt->parent): 0LU);
 
 		if (l->custom_seq_show) {
-- 
cgit 


From d97636980f6ba7344c8aa6fa349b9059c60ee478 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 12:55:28 -0700
Subject: Bluetooth: Add support for per socket msg_name callback

This allows to add a per socket msg_name callback that can be used
for updating the msg_name information for recvmsg() system calls.

This feature is used by another patch to support address information
on L2CAP connectionless channels.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h |  1 +
 net/bluetooth/af_bluetooth.c      | 15 +++++++++++----
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 1d6e484e08ef..896aad80bc4d 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -221,6 +221,7 @@ struct bt_sock {
 	struct list_head accept_q;
 	struct sock *parent;
 	unsigned long flags;
+	void (*skb_msg_name)(struct sk_buff *, void *, int *);
 };
 
 enum {
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9c7e4edc6504..f0aadeac4455 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -221,12 +221,12 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags & (MSG_OOB))
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
-		if (sk->sk_shutdown & RCV_SHUTDOWN)
+		if (sk->sk_shutdown & RCV_SHUTDOWN) {
+			msg->msg_namelen = 0;
 			return 0;
+		}
 		return err;
 	}
 
@@ -238,9 +238,16 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb_reset_transport_header(skb);
 	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err == 0)
+	if (err == 0) {
 		sock_recv_ts_and_drops(msg, sk, skb);
 
+		if (bt_sk(sk)->skb_msg_name)
+			bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
+						&msg->msg_namelen);
+		else
+			msg->msg_namelen = 0;
+	}
+
 	skb_free_datagram(sk, skb);
 
 	return err ? : copied;
-- 
cgit 


From 2edf870d198adeb43d5a2a5ddfa7e3cea4fc999b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 13 Oct 2013 12:55:29 -0700
Subject: Bluetooth: Provide msg_name callback for L2CAP connectionless
 channels

The L2CAP connectionless channels use SOCK_DGRAM and recvmsg() and need
to receive the remote BD_ADDR and PSM information via msg_name from
the recvmsg() system call.

So in case the L2CAP socket is for connectionless channels, provide
a msg_name callback that can update the data. Also store the remote
BD_ADDR and PSM in the skb so it can be extracted later on.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h |  2 ++
 net/bluetooth/l2cap_core.c        |  4 ++++
 net/bluetooth/l2cap_sock.c        | 15 ++++++++++++++-
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 896aad80bc4d..bf2ddffdae2d 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -284,6 +284,8 @@ struct bt_skb_cb {
 	__u8 force_active;
 	struct l2cap_ctrl control;
 	struct hci_req_ctrl req;
+	bdaddr_t bdaddr;
+	__le16 psm;
 };
 #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb))
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 769c379b3eeb..f6b5f94cbf39 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6459,6 +6459,10 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
 	if (chan->imtu < skb->len)
 		goto drop;
 
+	/* Store remote BD_ADDR and PSM for msg_name */
+	bacpy(&bt_cb(skb)->bdaddr, &conn->hcon->dst);
+	bt_cb(skb)->psm = psm;
+
 	if (!chan->ops->recv(chan, skb))
 		return;
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 8fe9f497c645..f1b462faf649 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1137,6 +1137,19 @@ static void l2cap_sock_destruct(struct sock *sk)
 	skb_queue_purge(&sk->sk_write_queue);
 }
 
+static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
+			       int *msg_namelen)
+{
+	struct sockaddr_l2 *la = (struct sockaddr_l2 *) msg_name;
+
+	memset(la, 0, sizeof(struct sockaddr_l2));
+	la->l2_family = AF_BLUETOOTH;
+	la->l2_psm = bt_cb(skb)->psm;
+	bacpy(&la->l2_bdaddr, &bt_cb(skb)->bdaddr);
+
+	*msg_namelen = sizeof(struct sockaddr_l2);
+}
+
 static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 {
 	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
@@ -1163,13 +1176,13 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent)
 
 		security_sk_clone(parent, sk);
 	} else {
-
 		switch (sk->sk_type) {
 		case SOCK_RAW:
 			chan->chan_type = L2CAP_CHAN_RAW;
 			break;
 		case SOCK_DGRAM:
 			chan->chan_type = L2CAP_CHAN_CONN_LESS;
+			bt_sk(sk)->skb_msg_name = l2cap_skb_msg_name;
 			break;
 		case SOCK_SEQPACKET:
 		case SOCK_STREAM:
-- 
cgit 


From 674d0ed8588c11ec9f70c8427ac83a73e0d156d5 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 13 Sep 2013 10:59:27 -0700
Subject: hwmon: (atxp1) Set and use error code from vid_to_reg()

vid_to_reg() returns -1 if it encounters an error. Return -EINVAL instead.
Its only caller, atxp1_storevcore(), doesn't use the return code but
returns -1 instead, which is wrong anyway as it means -EPERM.
Use the return value from vid_to_reg() instead to report the error.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Jean Delvare <khali@linux-fr.org>
---
 drivers/hwmon/atxp1.c     | 3 +--
 include/linux/hwmon-vid.h | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index aecb9ea7beb5..ddff02e3e66f 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -147,10 +147,9 @@ static ssize_t atxp1_storevcore(struct device *dev,
 
 	/* Calculate VID */
 	vid = vid_to_reg(vcore, data->vrm);
-
 	if (vid < 0) {
 		dev_err(dev, "VID calculation failed.\n");
-		return -1;
+		return vid;
 	}
 
 	/*
diff --git a/include/linux/hwmon-vid.h b/include/linux/hwmon-vid.h
index f346e4d5381c..da0a680e2f6d 100644
--- a/include/linux/hwmon-vid.h
+++ b/include/linux/hwmon-vid.h
@@ -38,7 +38,7 @@ static inline int vid_to_reg(int val, u8 vrm)
 		return ((val >= 1100) && (val <= 1850) ?
 			((18499 - val * 10) / 25 + 5) / 10 : -1);
 	default:
-		return -1;
+		return -EINVAL;
 	}
 }
 
-- 
cgit 


From bab2243ce1897865e31ea6d59b0478391f51812b Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sat, 6 Jul 2013 13:57:23 -0700
Subject: hwmon: Introduce hwmon_device_register_with_groups

hwmon_device_register_with_groups() lets callers register a hwmon device
together with all sysfs attributes in a single call.

When using hwmon_device_register_with_groups(), hwmon attributes are attached
to the hwmon device directly and no longer with its parent device.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/hwmon.c | 122 +++++++++++++++++++++++++++++++++++++++++++-------
 include/linux/hwmon.h |   5 +++
 2 files changed, 111 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 646314f7c839..a982528293ea 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 #include <linux/kdev_t.h>
 #include <linux/idr.h>
 #include <linux/hwmon.h>
@@ -25,35 +26,122 @@
 #define HWMON_ID_PREFIX "hwmon"
 #define HWMON_ID_FORMAT HWMON_ID_PREFIX "%d"
 
-static struct class *hwmon_class;
+struct hwmon_device {
+	const char *name;
+	struct device dev;
+};
+#define to_hwmon_device(d) container_of(d, struct hwmon_device, dev)
+
+static ssize_t
+show_name(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s\n", to_hwmon_device(dev)->name);
+}
+static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+
+static struct attribute *hwmon_dev_attrs[] = {
+	&dev_attr_name.attr,
+	NULL
+};
+
+static umode_t hwmon_dev_name_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+
+	if (to_hwmon_device(dev)->name == NULL)
+		return 0;
+
+	return attr->mode;
+}
+
+static struct attribute_group hwmon_dev_attr_group = {
+	.attrs		= hwmon_dev_attrs,
+	.is_visible	= hwmon_dev_name_is_visible,
+};
+
+static const struct attribute_group *hwmon_dev_attr_groups[] = {
+	&hwmon_dev_attr_group,
+	NULL
+};
+
+static void hwmon_dev_release(struct device *dev)
+{
+	kfree(to_hwmon_device(dev));
+}
+
+static struct class hwmon_class = {
+	.name = "hwmon",
+	.owner = THIS_MODULE,
+	.dev_groups = hwmon_dev_attr_groups,
+	.dev_release = hwmon_dev_release,
+};
 
 static DEFINE_IDA(hwmon_ida);
 
 /**
- * hwmon_device_register - register w/ hwmon
- * @dev: the device to register
+ * hwmon_device_register_with_groups - register w/ hwmon
+ * @dev: the parent device
+ * @name: hwmon name attribute
+ * @drvdata: driver data to attach to created device
+ * @groups: List of attribute groups to create
  *
  * hwmon_device_unregister() must be called when the device is no
  * longer needed.
  *
  * Returns the pointer to the new device.
  */
-struct device *hwmon_device_register(struct device *dev)
+struct device *
+hwmon_device_register_with_groups(struct device *dev, const char *name,
+				  void *drvdata,
+				  const struct attribute_group **groups)
 {
-	struct device *hwdev;
-	int id;
+	struct hwmon_device *hwdev;
+	int err, id;
 
 	id = ida_simple_get(&hwmon_ida, 0, 0, GFP_KERNEL);
 	if (id < 0)
 		return ERR_PTR(id);
 
-	hwdev = device_create(hwmon_class, dev, MKDEV(0, 0), NULL,
-			      HWMON_ID_FORMAT, id);
+	hwdev = kzalloc(sizeof(*hwdev), GFP_KERNEL);
+	if (hwdev == NULL) {
+		err = -ENOMEM;
+		goto ida_remove;
+	}
 
-	if (IS_ERR(hwdev))
-		ida_simple_remove(&hwmon_ida, id);
+	hwdev->name = name;
+	hwdev->dev.class = &hwmon_class;
+	hwdev->dev.parent = dev;
+	hwdev->dev.groups = groups;
+	hwdev->dev.of_node = dev ? dev->of_node : NULL;
+	dev_set_drvdata(&hwdev->dev, drvdata);
+	dev_set_name(&hwdev->dev, HWMON_ID_FORMAT, id);
+	err = device_register(&hwdev->dev);
+	if (err)
+		goto free;
+
+	return &hwdev->dev;
+
+free:
+	kfree(hwdev);
+ida_remove:
+	ida_simple_remove(&hwmon_ida, id);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups);
 
-	return hwdev;
+/**
+ * hwmon_device_register - register w/ hwmon
+ * @dev: the device to register
+ *
+ * hwmon_device_unregister() must be called when the device is no
+ * longer needed.
+ *
+ * Returns the pointer to the new device.
+ */
+struct device *hwmon_device_register(struct device *dev)
+{
+	return hwmon_device_register_with_groups(dev, NULL, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(hwmon_device_register);
 
@@ -105,19 +193,21 @@ static void __init hwmon_pci_quirks(void)
 
 static int __init hwmon_init(void)
 {
+	int err;
+
 	hwmon_pci_quirks();
 
-	hwmon_class = class_create(THIS_MODULE, "hwmon");
-	if (IS_ERR(hwmon_class)) {
-		pr_err("couldn't create sysfs class\n");
-		return PTR_ERR(hwmon_class);
+	err = class_register(&hwmon_class);
+	if (err) {
+		pr_err("couldn't register hwmon sysfs class\n");
+		return err;
 	}
 	return 0;
 }
 
 static void __exit hwmon_exit(void)
 {
-	class_destroy(hwmon_class);
+	class_unregister(&hwmon_class);
 }
 
 subsys_initcall(hwmon_init);
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index b2514f70d591..6d02ff77ae1a 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -15,8 +15,13 @@
 #define _HWMON_H_
 
 struct device;
+struct attribute_group;
 
 struct device *hwmon_device_register(struct device *dev);
+struct device *
+hwmon_device_register_with_groups(struct device *dev, const char *name,
+				  void *drvdata,
+				  const struct attribute_group **groups);
 
 void hwmon_device_unregister(struct device *dev);
 
-- 
cgit 


From 74188cba088192e14cd7fd5433876e8c947bcdd8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 11 Jul 2013 20:00:12 -0700
Subject: hwmon: Provide managed hwmon registration

Drivers using the new hwmon_device_register_with_groups API often have a
remove function which consists solely of a call hwmon_device_unregister().

Provide support for devm_hwmon_device_register_with_groups and
devm_hwmon_device_unregister to allow this repeated code to be removed
and help eliminate error handling code.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/hwmon.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hwmon.h |  5 ++++
 2 files changed, 68 insertions(+)

(limited to 'include')

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index a982528293ea..e176a43af63d 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -163,6 +163,69 @@ void hwmon_device_unregister(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(hwmon_device_unregister);
 
+static void devm_hwmon_release(struct device *dev, void *res)
+{
+	struct device *hwdev = *(struct device **)res;
+
+	hwmon_device_unregister(hwdev);
+}
+
+/**
+ * devm_hwmon_device_register_with_groups - register w/ hwmon
+ * @dev: the parent device
+ * @name: hwmon name attribute
+ * @drvdata: driver data to attach to created device
+ * @groups: List of attribute groups to create
+ *
+ * Returns the pointer to the new device. The new device is automatically
+ * unregistered with the parent device.
+ */
+struct device *
+devm_hwmon_device_register_with_groups(struct device *dev, const char *name,
+				       void *drvdata,
+				       const struct attribute_group **groups)
+{
+	struct device **ptr, *hwdev;
+
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
+	ptr = devres_alloc(devm_hwmon_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hwdev = hwmon_device_register_with_groups(dev, name, drvdata, groups);
+	if (IS_ERR(hwdev))
+		goto error;
+
+	*ptr = hwdev;
+	devres_add(dev, ptr);
+	return hwdev;
+
+error:
+	devres_free(ptr);
+	return hwdev;
+}
+EXPORT_SYMBOL_GPL(devm_hwmon_device_register_with_groups);
+
+static int devm_hwmon_match(struct device *dev, void *res, void *data)
+{
+	struct device **hwdev = res;
+
+	return *hwdev == data;
+}
+
+/**
+ * devm_hwmon_device_unregister - removes a previously registered hwmon device
+ *
+ * @dev: the parent device of the device to unregister
+ */
+void devm_hwmon_device_unregister(struct device *dev)
+{
+	WARN_ON(devres_release(dev, devm_hwmon_release, devm_hwmon_match, dev));
+}
+EXPORT_SYMBOL_GPL(devm_hwmon_device_unregister);
+
 static void __init hwmon_pci_quirks(void)
 {
 #if defined CONFIG_X86 && defined CONFIG_PCI
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 6d02ff77ae1a..09354f6c1d63 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -22,7 +22,12 @@ struct device *
 hwmon_device_register_with_groups(struct device *dev, const char *name,
 				  void *drvdata,
 				  const struct attribute_group **groups);
+struct device *
+devm_hwmon_device_register_with_groups(struct device *dev, const char *name,
+				       void *drvdata,
+				       const struct attribute_group **groups);
 
 void hwmon_device_unregister(struct device *dev);
+void devm_hwmon_device_unregister(struct device *dev);
 
 #endif
-- 
cgit 


From 6d9d41e57440e32a3400f37aa05ef7a1a09ced64 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Wed, 2 Oct 2013 14:22:28 -0700
Subject: KVM: Move gfn_to_index to x86 specific code

The gfn_to_index function relies on huge page defines which either may
not make sense on systems that don't support huge pages or are defined
in an unconvenient way for other architectures.  Since this is
x86-specific, move the function to arch/x86/include/asm/kvm_host.h.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 7 +++++++
 include/linux/kvm_host.h        | 7 -------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8dd143a65d60..5cbf3166257c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,6 +79,13 @@
 #define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
 #define SELECTOR_TI_MASK (1 << 2)
 #define SELECTOR_RPL_MASK 0x03
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7c961e1e9270..f6dccde755f6 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -841,13 +841,6 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 	return gfn_to_memslot(kvm, gfn)->id;
 }
 
-static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
-{
-	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
-	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
-		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
-}
-
 static inline gfn_t
 hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
 {
-- 
cgit 


From 795aa6ef6a1aba99050735eadd0c2341b789b53b Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 10 Oct 2013 09:21:55 +0200
Subject: netfilter: pass hook ops to hookfn

Pass the hook ops to the hookfn to allow for generic hook
functions. This change is required by nf_tables.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                      |  3 +-
 net/bridge/br_netfilter.c                      | 22 +++++++++-----
 net/bridge/netfilter/ebtable_filter.c          | 16 ++++++----
 net/bridge/netfilter/ebtable_nat.c             | 16 ++++++----
 net/decnet/netfilter/dn_rtmsg.c                |  2 +-
 net/ipv4/netfilter/arptable_filter.c           |  5 +--
 net/ipv4/netfilter/ipt_CLUSTERIP.c             |  2 +-
 net/ipv4/netfilter/ipt_SYNPROXY.c              |  2 +-
 net/ipv4/netfilter/iptable_filter.c            |  7 +++--
 net/ipv4/netfilter/iptable_mangle.c            | 10 +++---
 net/ipv4/netfilter/iptable_nat.c               | 26 ++++++++--------
 net/ipv4/netfilter/iptable_raw.c               |  6 ++--
 net/ipv4/netfilter/iptable_security.c          |  7 +++--
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 12 ++++----
 net/ipv4/netfilter/nf_defrag_ipv4.c            |  6 ++--
 net/ipv6/netfilter/ip6t_SYNPROXY.c             |  2 +-
 net/ipv6/netfilter/ip6table_filter.c           |  5 +--
 net/ipv6/netfilter/ip6table_mangle.c           | 10 +++---
 net/ipv6/netfilter/ip6table_nat.c              | 27 +++++++++--------
 net/ipv6/netfilter/ip6table_raw.c              |  5 +--
 net/ipv6/netfilter/ip6table_security.c         |  5 +--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 14 +++++----
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |  6 ++--
 net/netfilter/core.c                           |  2 +-
 net/netfilter/ipvs/ip_vs_core.c                | 42 +++++++++++++-------------
 security/selinux/hooks.c                       | 10 +++---
 26 files changed, 148 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 61223c52414f..fef7e67f7101 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -42,7 +42,8 @@ int netfilter_init(void);
 
 struct sk_buff;
 
-typedef unsigned int nf_hookfn(unsigned int hooknum,
+struct nf_hook_ops;
+typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops,
 			       struct sk_buff *skb,
 			       const struct net_device *in,
 			       const struct net_device *out,
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index f87736270eaa..878f008afefa 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -619,7 +619,7 @@ bad:
 
 /* Replicate the checks that IPv6 does on packet reception and pass the packet
  * to ip6tables, which doesn't support NAT, so things are fairly simple. */
-static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
+static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
@@ -669,7 +669,8 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
  * receiving device) to make netfilter happy, the REDIRECT
  * target in particular.  Save the original destination IP
  * address to be able to detect DNAT afterwards. */
-static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
@@ -691,7 +692,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
 			return NF_ACCEPT;
 
 		nf_bridge_pull_encap_header_rcsum(skb);
-		return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn);
+		return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn);
 	}
 
 	if (!brnf_call_iptables && !br->nf_call_iptables)
@@ -727,7 +728,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb,
  * took place when the packet entered the bridge), but we
  * register an IPv4 PRE_ROUTING 'sabotage' hook that will
  * prevent this from happening. */
-static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_local_in(const struct nf_hook_ops *ops,
+				   struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
@@ -765,7 +767,8 @@ static int br_nf_forward_finish(struct sk_buff *skb)
  * but we are still able to filter on the 'real' indev/outdev
  * because of the physdev module. For ARP, indev and outdev are the
  * bridge ports. */
-static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
 				     const struct net_device *in,
 				     const struct net_device *out,
 				     int (*okfn)(struct sk_buff *))
@@ -818,7 +821,8 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
@@ -878,7 +882,8 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 #endif
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
-static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
+static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
+				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
 				       int (*okfn)(struct sk_buff *))
@@ -923,7 +928,8 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb,
 /* IP/SABOTAGE *****************************************************/
 /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING
  * for the second time. */
-static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb,
+static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
+				   struct sk_buff *skb,
 				   const struct net_device *in,
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 94b2b700cff8..bb2da7b706e7 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -60,17 +60,21 @@ static const struct ebt_table frame_filter =
 };
 
 static unsigned int
-ebt_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
-   const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	    const struct net_device *in, const struct net_device *out,
+	    int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(in)->xt.frame_filter);
 }
 
 static unsigned int
-ebt_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in,
-   const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	     const struct net_device *in, const struct net_device *out,
+	     int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_filter);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(out)->xt.frame_filter);
 }
 
 static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 322555acdd40..bd238f1f105b 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -60,17 +60,21 @@ static struct ebt_table frame_nat =
 };
 
 static unsigned int
-ebt_nat_in(unsigned int hook, struct sk_buff *skb, const struct net_device *in
-   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	   const struct net_device *in, const struct net_device *out,
+	   int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(in)->xt.frame_nat);
 }
 
 static unsigned int
-ebt_nat_out(unsigned int hook, struct sk_buff *skb, const struct net_device *in
-   , const struct net_device *out, int (*okfn)(struct sk_buff *))
+ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	    const struct net_device *in, const struct net_device *out,
+	    int (*okfn)(struct sk_buff *))
 {
-	return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_nat);
+	return ebt_do_table(ops->hooknum, skb, in, out,
+			    dev_net(out)->xt.frame_nat);
 }
 
 static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 2a7efe388344..e83015cecfa7 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -87,7 +87,7 @@ static void dnrmg_send_peer(struct sk_buff *skb)
 }
 
 
-static unsigned int dnrmg_hook(unsigned int hook,
+static unsigned int dnrmg_hook(const struct nf_hook_ops *ops,
 			struct sk_buff *skb,
 			const struct net_device *in,
 			const struct net_device *out,
diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index a865f6f94013..802ddecb30b8 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -27,13 +27,14 @@ static const struct xt_table packet_filter = {
 
 /* The work comes in here from netfilter.c */
 static unsigned int
-arptable_filter_hook(unsigned int hook, struct sk_buff *skb,
+arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return arpt_do_table(skb, hook, in, out, net->ipv4.arptable_filter);
+	return arpt_do_table(skb, ops->hooknum, in, out,
+			     net->ipv4.arptable_filter);
 }
 
 static struct nf_hook_ops *arpfilter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 0b732efd32e2..a2e2b61cd7da 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -483,7 +483,7 @@ static void arp_print(struct arp_payload *payload)
 #endif
 
 static unsigned int
-arp_mangle(unsigned int hook,
+arp_mangle(const struct nf_hook_ops *ops,
 	   struct sk_buff *skb,
 	   const struct net_device *in,
 	   const struct net_device *out,
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index b6346bf2fde3..01cffeaa0085 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -297,7 +297,7 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-static unsigned int ipv4_synproxy_hook(unsigned int hooknum,
+static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 50af5b45c050..e08a74a243a8 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -33,20 +33,21 @@ static const struct xt_table packet_filter = {
 };
 
 static unsigned int
-iptable_filter_hook(unsigned int hook, struct sk_buff *skb,
+iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		    const struct net_device *in, const struct net_device *out,
 		    int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT &&
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_filter);
+	return ipt_do_table(skb, ops->hooknum, in, out,
+			    net->ipv4.iptable_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index 0d8cd82e0fad..6a5079c34bb3 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -79,19 +79,19 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out)
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-iptable_mangle_hook(unsigned int hook,
+iptable_mangle_hook(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	if (hook == NF_INET_LOCAL_OUT)
+	if (ops->hooknum == NF_INET_LOCAL_OUT)
 		return ipt_mangle_out(skb, out);
-	if (hook == NF_INET_POST_ROUTING)
-		return ipt_do_table(skb, hook, in, out,
+	if (ops->hooknum == NF_INET_POST_ROUTING)
+		return ipt_do_table(skb, ops->hooknum, in, out,
 				    dev_net(out)->ipv4.iptable_mangle);
 	/* PREROUTING/INPUT/FORWARD: */
-	return ipt_do_table(skb, hook, in, out,
+	return ipt_do_table(skb, ops->hooknum, in, out,
 			    dev_net(in)->ipv4.iptable_mangle);
 }
 
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 683bfaffed65..ee2886126e3d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -61,7 +61,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_fn(unsigned int hooknum,
+nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -71,7 +71,7 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn_nat *nat;
 	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
 
 	/* We never see fragments: conntrack defrags on pre-routing
 	 * and local-out, and nf_nat_out protects post-routing.
@@ -108,7 +108,7 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 	case IP_CT_RELATED_REPLY:
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   hooknum))
+							   ops->hooknum))
 				return NF_DROP;
 			else
 				return NF_ACCEPT;
@@ -121,14 +121,14 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 		} else {
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 				goto oif_changed;
 		}
 		break;
@@ -137,11 +137,11 @@ nf_nat_ipv4_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
 
 oif_changed:
 	nf_ct_kill_acct(ct, ctinfo, skb);
@@ -149,7 +149,7 @@ oif_changed:
 }
 
 static unsigned int
-nf_nat_ipv4_in(unsigned int hooknum,
+nf_nat_ipv4_in(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -158,7 +158,7 @@ nf_nat_ipv4_in(unsigned int hooknum,
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
@@ -167,7 +167,7 @@ nf_nat_ipv4_in(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_out(unsigned int hooknum,
+nf_nat_ipv4_out(const struct nf_hook_ops *ops,
 		struct sk_buff *skb,
 		const struct net_device *in,
 		const struct net_device *out,
@@ -185,7 +185,7 @@ nf_nat_ipv4_out(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -207,7 +207,7 @@ nf_nat_ipv4_out(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv4_local_fn(unsigned int hooknum,
+nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
@@ -223,7 +223,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 1f82aea11df6..b2f7e8f98316 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -20,20 +20,20 @@ static const struct xt_table packet_raw = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-iptable_raw_hook(unsigned int hook, struct sk_buff *skb,
+iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		 const struct net_device *in, const struct net_device *out,
 		 int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT && 
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* root is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_raw);
+	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.iptable_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index f867a8d38bf7..c86647ed2078 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -37,21 +37,22 @@ static const struct xt_table security_table = {
 };
 
 static unsigned int
-iptable_security_hook(unsigned int hook, struct sk_buff *skb,
+iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
 	const struct net *net;
 
-	if (hook == NF_INET_LOCAL_OUT &&
+	if (ops->hooknum == NF_INET_LOCAL_OUT &&
 	    (skb->len < sizeof(struct iphdr) ||
 	     ip_hdrlen(skb) < sizeof(struct iphdr)))
 		/* Somebody is playing with raw sockets. */
 		return NF_ACCEPT;
 
 	net = dev_net((in != NULL) ? in : out);
-	return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_security);
+	return ipt_do_table(skb, ops->hooknum, in, out,
+			    net->ipv4.iptable_security);
 }
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 86f5b34a4ed1..ecd8bec411c9 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	return NF_ACCEPT;
 }
 
-static unsigned int ipv4_helper(unsigned int hooknum,
+static unsigned int ipv4_helper(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -121,7 +121,7 @@ static unsigned int ipv4_helper(unsigned int hooknum,
 			    ct, ctinfo);
 }
 
-static unsigned int ipv4_confirm(unsigned int hooknum,
+static unsigned int ipv4_confirm(const struct nf_hook_ops *ops,
 				 struct sk_buff *skb,
 				 const struct net_device *in,
 				 const struct net_device *out,
@@ -147,16 +147,16 @@ out:
 	return nf_conntrack_confirm(skb);
 }
 
-static unsigned int ipv4_conntrack_in(unsigned int hooknum,
+static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return nf_conntrack_in(dev_net(in), PF_INET, hooknum, skb);
+	return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb);
 }
 
-static unsigned int ipv4_conntrack_local(unsigned int hooknum,
+static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -166,7 +166,7 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum,
 	if (skb->len < sizeof(struct iphdr) ||
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
-	return nf_conntrack_in(dev_net(out), PF_INET, hooknum, skb);
+	return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb);
 }
 
 /* Connection tracking may drop packets, but never alters them, so
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 742815518b0f..12e13bd82b5b 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -60,7 +60,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 		return IP_DEFRAG_CONNTRACK_OUT + zone;
 }
 
-static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
+static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
 					  struct sk_buff *skb,
 					  const struct net_device *in,
 					  const struct net_device *out,
@@ -83,7 +83,9 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
 #endif
 	/* Gather fragments. */
 	if (ip_is_fragment(ip_hdr(skb))) {
-		enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb);
+		enum ip_defrag_users user =
+			nf_ct_defrag_user(ops->hooknum, skb);
+
 		if (nf_ct_ipv4_gather_frags(skb, user))
 			return NF_STOLEN;
 	}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 2748b042da72..bf9f612c1bc2 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -312,7 +312,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-static unsigned int ipv6_synproxy_hook(unsigned int hooknum,
+static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
 				       const struct net_device *in,
 				       const struct net_device *out,
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 29b44b14c5ea..ca7f6c128086 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -32,13 +32,14 @@ static const struct xt_table packet_filter = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_filter_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_filter);
 }
 
 static struct nf_hook_ops *filter_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index c705907ae6ab..307bbb782d14 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -76,17 +76,17 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	if (hook == NF_INET_LOCAL_OUT)
+	if (ops->hooknum == NF_INET_LOCAL_OUT)
 		return ip6t_mangle_out(skb, out);
-	if (hook == NF_INET_POST_ROUTING)
-		return ip6t_do_table(skb, hook, in, out,
+	if (ops->hooknum == NF_INET_POST_ROUTING)
+		return ip6t_do_table(skb, ops->hooknum, in, out,
 				     dev_net(out)->ipv6.ip6table_mangle);
 	/* INPUT/FORWARD */
-	return ip6t_do_table(skb, hook, in, out,
+	return ip6t_do_table(skb, ops->hooknum, in, out,
 			     dev_net(in)->ipv6.ip6table_mangle);
 }
 
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 9b076d2d3a7b..84c7f33d0cf8 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -63,7 +63,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_fn(unsigned int hooknum,
+nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -72,7 +72,7 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
 	__be16 frag_off;
 	int hdrlen;
 	u8 nexthdr;
@@ -111,7 +111,8 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 
 		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
 			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
-							     hooknum, hdrlen))
+							     ops->hooknum,
+							     hdrlen))
 				return NF_DROP;
 			else
 				return NF_ACCEPT;
@@ -124,14 +125,14 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 		if (!nf_nat_initialized(ct, maniptype)) {
 			unsigned int ret;
 
-			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
 			if (ret != NF_ACCEPT)
 				return ret;
 		} else {
 			pr_debug("Already setup manip %s for ct %p\n",
 				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
 				 ct);
-			if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 				goto oif_changed;
 		}
 		break;
@@ -140,11 +141,11 @@ nf_nat_ipv6_fn(unsigned int hooknum,
 		/* ESTABLISHED */
 		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
 			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
 			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
 
 oif_changed:
 	nf_ct_kill_acct(ct, ctinfo, skb);
@@ -152,7 +153,7 @@ oif_changed:
 }
 
 static unsigned int
-nf_nat_ipv6_in(unsigned int hooknum,
+nf_nat_ipv6_in(const struct nf_hook_ops *ops,
 	       struct sk_buff *skb,
 	       const struct net_device *in,
 	       const struct net_device *out,
@@ -161,7 +162,7 @@ nf_nat_ipv6_in(unsigned int hooknum,
 	unsigned int ret;
 	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
 		skb_dst_drop(skb);
@@ -170,7 +171,7 @@ nf_nat_ipv6_in(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_out(unsigned int hooknum,
+nf_nat_ipv6_out(const struct nf_hook_ops *ops,
 		struct sk_buff *skb,
 		const struct net_device *in,
 		const struct net_device *out,
@@ -187,7 +188,7 @@ nf_nat_ipv6_out(unsigned int hooknum,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
@@ -209,7 +210,7 @@ nf_nat_ipv6_out(unsigned int hooknum,
 }
 
 static unsigned int
-nf_nat_ipv6_local_fn(unsigned int hooknum,
+nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops,
 		     struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
@@ -224,7 +225,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum,
 	if (skb->len < sizeof(struct ipv6hdr))
 		return NF_ACCEPT;
 
-	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 9a626d86720f..5274740acecc 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -19,13 +19,14 @@ static const struct xt_table packet_raw = {
 
 /* The work comes in here from netfilter.c. */
 static unsigned int
-ip6table_raw_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		  const struct net_device *in, const struct net_device *out,
 		  int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_raw);
 }
 
 static struct nf_hook_ops *rawtable_ops __read_mostly;
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index ce88d1d7e525..ab3b0219ecfa 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -36,14 +36,15 @@ static const struct xt_table security_table = {
 };
 
 static unsigned int
-ip6table_security_hook(unsigned int hook, struct sk_buff *skb,
+ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		       const struct net_device *in,
 		       const struct net_device *out,
 		       int (*okfn)(struct sk_buff *))
 {
 	const struct net *net = dev_net((in != NULL) ? in : out);
 
-	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security);
+	return ip6t_do_table(skb, ops->hooknum, in, out,
+			     net->ipv6.ip6table_security);
 }
 
 static struct nf_hook_ops *sectbl_ops __read_mostly;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 54b75ead5a69..486545eb42ce 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -95,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	return NF_ACCEPT;
 }
 
-static unsigned int ipv6_helper(unsigned int hooknum,
+static unsigned int ipv6_helper(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -133,7 +133,7 @@ static unsigned int ipv6_helper(unsigned int hooknum,
 	return helper->help(skb, protoff, ct, ctinfo);
 }
 
-static unsigned int ipv6_confirm(unsigned int hooknum,
+static unsigned int ipv6_confirm(const struct nf_hook_ops *ops,
 				 struct sk_buff *skb,
 				 const struct net_device *in,
 				 const struct net_device *out,
@@ -219,16 +219,17 @@ static unsigned int __ipv6_conntrack_in(struct net *net,
 	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
 }
 
-static unsigned int ipv6_conntrack_in(unsigned int hooknum,
+static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+	return __ipv6_conntrack_in(dev_net(in), ops->hooknum, skb, in, out,
+				   okfn);
 }
 
-static unsigned int ipv6_conntrack_local(unsigned int hooknum,
+static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -239,7 +240,8 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+	return __ipv6_conntrack_in(dev_net(out), ops->hooknum, skb, in, out,
+				   okfn);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index aacd121fe8c5..ec483aa3f60f 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -52,7 +52,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
 
 }
 
-static unsigned int ipv6_defrag(unsigned int hooknum,
+static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
 				struct sk_buff *skb,
 				const struct net_device *in,
 				const struct net_device *out,
@@ -66,7 +66,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 		return NF_ACCEPT;
 #endif
 
-	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
+	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb));
 	/* queued */
 	if (reasm == NULL)
 		return NF_STOLEN;
@@ -75,7 +75,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
+	nf_ct_frag6_output(ops->hooknum, reasm, (struct net_device *)in,
 			   (struct net_device *)out, okfn);
 
 	return NF_STOLEN;
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 593b16ea45e0..1fbab0cdd302 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -146,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head,
 		/* Optimization: we don't need to hold module
 		   reference here, since function can't sleep. --RR */
 repeat:
-		verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn);
+		verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn);
 		if (verdict != NF_ACCEPT) {
 #ifdef CONFIG_NETFILTER_DEBUG
 			if (unlikely((verdict & NF_VERDICT_MASK)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 74fd00c27210..34fda62f40f6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1239,11 +1239,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	     const struct net_device *in, const struct net_device *out,
 	     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET);
+	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
 
 /*
@@ -1251,11 +1251,11 @@ ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET);
+	return ip_vs_out(ops->hooknum, skb, AF_INET);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1266,11 +1266,11 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 	     const struct net_device *in, const struct net_device *out,
 	     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET6);
+	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
 
 /*
@@ -1278,11 +1278,11 @@ ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
  *	Check if packet is reply for established ip_vs_conn.
  */
 static unsigned int
-ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_out(hooknum, skb, AF_INET6);
+	return ip_vs_out(ops->hooknum, skb, AF_INET6);
 }
 
 #endif
@@ -1733,12 +1733,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
  *	Schedule and forward packets from remote clients
  */
 static unsigned int
-ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET);
+	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
 
 /*
@@ -1746,11 +1746,11 @@ ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from local clients
  */
 static unsigned int
-ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET);
+	return ip_vs_in(ops->hooknum, skb, AF_INET);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1760,7 +1760,7 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
  * Copy info from first fragment, to the rest of them.
  */
 static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_preroute_frag6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in,
 		     const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
@@ -1792,12 +1792,12 @@ ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from remote clients
  */
 static unsigned int
-ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in,
 		      const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET6);
+	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
 
 /*
@@ -1805,11 +1805,11 @@ ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
  *	Schedule and forward packets from local clients
  */
 static unsigned int
-ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		     const struct net_device *in, const struct net_device *out,
 		     int (*okfn)(struct sk_buff *))
 {
-	return ip_vs_in(hooknum, skb, AF_INET6);
+	return ip_vs_in(ops->hooknum, skb, AF_INET6);
 }
 
 #endif
@@ -1825,7 +1825,7 @@ ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
  *      and send them to ip_vs_in_icmp.
  */
 static unsigned int
-ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		   const struct net_device *in, const struct net_device *out,
 		   int (*okfn)(struct sk_buff *))
 {
@@ -1842,12 +1842,12 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
 	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp(skb, &r, hooknum);
+	return ip_vs_in_icmp(skb, &r, ops->hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
 static unsigned int
-ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		      const struct net_device *in, const struct net_device *out,
 		      int (*okfn)(struct sk_buff *))
 {
@@ -1866,7 +1866,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
-	return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
+	return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr);
 }
 #endif
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 568c7699abf1..3f224d7795f5 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4668,7 +4668,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_forward(unsigned int hooknum,
+static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -4678,7 +4678,7 @@ static unsigned int selinux_ipv4_forward(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_forward(unsigned int hooknum,
+static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops,
 					 struct sk_buff *skb,
 					 const struct net_device *in,
 					 const struct net_device *out,
@@ -4710,7 +4710,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_output(unsigned int hooknum,
+static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops,
 					struct sk_buff *skb,
 					const struct net_device *in,
 					const struct net_device *out,
@@ -4837,7 +4837,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
@@ -4847,7 +4847,7 @@ static unsigned int selinux_ipv4_postroute(unsigned int hooknum,
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static unsigned int selinux_ipv6_postroute(unsigned int hooknum,
+static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops,
 					   struct sk_buff *skb,
 					   const struct net_device *in,
 					   const struct net_device *out,
-- 
cgit 


From f59cb0453cd885736daa11ae2445982c5ab2fc83 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 14 Oct 2013 10:57:04 +0200
Subject: netfilter: nf_nat: move alloc_null_binding to nf_nat_core.c

Similar to nat_decode_session, alloc_null_binding is needed for both
ip_tables and nf_tables, so move it to nf_nat_core.c. This change
is required by nf_tables.

This is an adapted version of the original patch from Patrick McHardy.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat.h |  3 +++
 net/netfilter/nf_nat_core.c    | 20 ++++++++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index c29b4e545f87..07eaaf604092 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -45,6 +45,9 @@ unsigned int nf_nat_setup_info(struct nf_conn *ct,
 			       const struct nf_nat_range *range,
 			       enum nf_nat_manip_type maniptype);
 
+extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct,
+					      unsigned int hooknum);
+
 /* Is this tuple already taken? (not by us)*/
 int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conn *ignored_conntrack);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 6f0f4f7f68a5..63a815402211 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -432,6 +432,26 @@ nf_nat_setup_info(struct nf_conn *ct,
 }
 EXPORT_SYMBOL(nf_nat_setup_info);
 
+unsigned int
+nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	/* Force range to this IP; let proto decide mapping for
+	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
+	 * Use reply in case it's already been mangled (eg local packet).
+	 */
+	union nf_inet_addr ip =
+		(HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 :
+		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3);
+	struct nf_nat_range range = {
+		.flags		= NF_NAT_RANGE_MAP_IPS,
+		.min_addr	= ip,
+		.max_addr	= ip,
+	};
+	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+}
+EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding);
+
 /* Do packet manipulations according to nf_nat_setup_info. */
 unsigned int nf_nat_packet(struct nf_conn *ct,
 			   enum ip_conntrack_info ctinfo,
-- 
cgit 


From bdc257830760a784370ae4ab2d682b252b983e77 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 14 Oct 2013 02:45:34 -0700
Subject: Bluetooth: Introduce L2CAP channel flag for defer setup

The L2CAP core should not look into the socket flags to figure out the
setting of defer setup. So introduce a L2CAP channel flag that mirrors
the socket flag.

Since the defer setup option is only set in one place this becomes a
really easy thing to do.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/l2cap_core.c    | 15 +++++++--------
 net/bluetooth/l2cap_sock.c    |  7 +++++--
 3 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index a27d51dc39a4..1a38edee38e4 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -652,6 +652,7 @@ enum {
 	FLAG_FLUSHABLE,
 	FLAG_EXT_CTRL,
 	FLAG_EFS_ENABLE,
+	FLAG_DEFER_SETUP,
 };
 
 enum {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index f6b5f94cbf39..e5819cb67372 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -655,14 +655,14 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 	case BT_CONNECT2:
 		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
 		    conn->hcon->type == ACL_LINK) {
-			struct sock *sk = chan->sk;
 			struct l2cap_conn_rsp rsp;
 			__u16 result;
 
-			if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))
+			if (test_bit(FLAG_DEFER_SETUP, &chan->flags))
 				result = L2CAP_CR_SEC_BLOCK;
 			else
 				result = L2CAP_CR_BAD_PSM;
+
 			l2cap_state_change(chan, BT_DISCONN);
 
 			rsp.scid   = cpu_to_le16(chan->dcid);
@@ -1294,16 +1294,16 @@ static void l2cap_conn_start(struct l2cap_conn *conn)
 			l2cap_start_connection(chan);
 
 		} else if (chan->state == BT_CONNECT2) {
-			struct sock *sk = chan->sk;
 			struct l2cap_conn_rsp rsp;
 			char buf[128];
 			rsp.scid = cpu_to_le16(chan->dcid);
 			rsp.dcid = cpu_to_le16(chan->scid);
 
 			if (l2cap_chan_check_security(chan)) {
+				struct sock *sk = chan->sk;
+
 				lock_sock(sk);
-				if (test_bit(BT_SK_DEFER_SETUP,
-					     &bt_sk(sk)->flags)) {
+				if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
 					rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND);
 					rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
 					chan->ops->defer(chan);
@@ -3823,7 +3823,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 
 	if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) {
 		if (l2cap_chan_check_security(chan)) {
-			if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
+			if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
 				__l2cap_state_change(chan, BT_CONNECT2);
 				result = L2CAP_CR_PEND;
 				status = L2CAP_CS_AUTHOR_PEND;
@@ -6693,8 +6693,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 			lock_sock(sk);
 
 			if (!status) {
-				if (test_bit(BT_SK_DEFER_SETUP,
-					     &bt_sk(sk)->flags)) {
+				if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) {
 					res = L2CAP_CR_PEND;
 					stat = L2CAP_CS_AUTHOR_PEND;
 					chan->ops->defer(chan);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f1b462faf649..f5d957328545 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -672,10 +672,13 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		if (opt)
+		if (opt) {
 			set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
-		else
+			set_bit(FLAG_DEFER_SETUP, &chan->flags);
+		} else {
 			clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
+			clear_bit(FLAG_DEFER_SETUP, &chan->flags);
+		}
 		break;
 
 	case BT_FLUSHABLE:
-- 
cgit 


From d97c899bde330cd1c76c3a162558177563a74362 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 14 Oct 2013 02:53:54 -0700
Subject: Bluetooth: Introduce L2CAP channel callback for resuming

Clearing the BT_SK_SUSPEND socket flag from the L2CAP core is causing
a dependency on the socket. So intead of doing that, use a channel
callback into the socket handling to resume.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/l2cap.h | 1 +
 net/bluetooth/l2cap_core.c    | 6 +-----
 net/bluetooth/l2cap_sock.c    | 9 +++++++++
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1a38edee38e4..07757a2af942 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -554,6 +554,7 @@ struct l2cap_ops {
 						 int state);
 	void			(*ready) (struct l2cap_chan *chan);
 	void			(*defer) (struct l2cap_chan *chan);
+	void			(*resume) (struct l2cap_chan *chan);
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long len, int nb);
 };
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index e5819cb67372..0c3446da1ec9 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6669,11 +6669,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt)
 
 		if (!status && (chan->state == BT_CONNECTED ||
 				chan->state == BT_CONFIG)) {
-			struct sock *sk = chan->sk;
-
-			clear_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags);
-			sk->sk_state_change(sk);
-
+			chan->ops->resume(chan);
 			l2cap_check_encryption(chan, encrypt);
 			l2cap_chan_unlock(chan);
 			continue;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f5d957328545..fcf012a422fd 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1112,6 +1112,14 @@ static void l2cap_sock_defer_cb(struct l2cap_chan *chan)
 		parent->sk_data_ready(parent, 0);
 }
 
+static void l2cap_sock_resume_cb(struct l2cap_chan *chan)
+{
+	struct sock *sk = chan->data;
+
+	clear_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags);
+	sk->sk_state_change(sk);
+}
+
 static struct l2cap_ops l2cap_chan_ops = {
 	.name		= "L2CAP Socket Interface",
 	.new_connection	= l2cap_sock_new_connection_cb,
@@ -1121,6 +1129,7 @@ static struct l2cap_ops l2cap_chan_ops = {
 	.state_change	= l2cap_sock_state_change_cb,
 	.ready		= l2cap_sock_ready_cb,
 	.defer		= l2cap_sock_defer_cb,
+	.resume		= l2cap_sock_resume_cb,
 	.alloc_skb	= l2cap_sock_alloc_skb_cb,
 };
 
-- 
cgit 


From 0585123ebbd07a4fb49558ed6dea5fced967841a Mon Sep 17 00:00:00 2001
From: LABBE Corentin <clabbe.montjoie@gmail.com>
Date: Thu, 26 Sep 2013 16:50:21 +0200
Subject: Correct some typos for word frequency

Signed-off-by: LABBE Corentin <clabbe.montjoie@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/cpufreq/exynos-cpufreq.c | 2 +-
 include/linux/devfreq.h          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 0fac34439e31..b4afd078fe05 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -77,7 +77,7 @@ static int exynos_cpufreq_scale(unsigned int target_freq)
 	/*
 	 * The policy max have been changed so that we cannot get proper
 	 * old_index with cpufreq_frequency_table_target(). Thus, ignore
-	 * policy and get the index from the raw freqeuncy table.
+	 * policy and get the index from the raw frequency table.
 	 */
 	old_index = exynos_cpufreq_get_index(freqs.old);
 	if (old_index < 0) {
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 5f1ab92107e6..32acc0090ce6 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -168,7 +168,7 @@ struct devfreq {
 	unsigned long max_freq;
 	bool stop_polling;
 
-	/* information for device freqeuncy transition */
+	/* information for device frequency transition */
 	unsigned int total_trans;
 	unsigned int *trans_table;
 	unsigned long *time_in_state;
-- 
cgit 


From 1a49123b34346154ffd70f0b60dce007f1605676 Mon Sep 17 00:00:00 2001
From: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Date: Thu, 3 Oct 2013 19:38:14 +0800
Subject: __page_to_pfn: Fix typo in comment

Fix typo in __page_to_pfn comment: s/encorded/encoded.

Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/asm-generic/memory_model.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index aea9e45efce6..14909b0b9cae 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -53,7 +53,7 @@
 
 #elif defined(CONFIG_SPARSEMEM)
 /*
- * Note: section's mem_map is encorded to reflect its start_pfn.
+ * Note: section's mem_map is encoded to reflect its start_pfn.
  * section[i].section_mem_map == mem_map's address - start_pfn;
  */
 #define __page_to_pfn(pg)					\
-- 
cgit 


From 3f79410c7c9c8ef33ccff60c61e1f1166f5ed64a Mon Sep 17 00:00:00 2001
From: Maxime Jayat <maxime@artisandeveloppeur.fr>
Date: Sat, 12 Oct 2013 01:29:46 +0200
Subject: treewide: Fix common typo in "identify"

Correct common misspelling of "identify" as "indentify" throughout
the kernel

Signed-off-by: Maxime Jayat <maxime@artisandeveloppeur.fr>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/mips/include/asm/octeon/cvmx-pip.h   |  4 ++--
 arch/x86/kernel/cpu/intel_cacheinfo.c     |  2 +-
 arch/x86/kernel/cpu/scattered.c           |  2 +-
 drivers/media/rc/keymaps/rc-dib0700-nec.c |  2 +-
 drivers/media/rc/keymaps/rc-dib0700-rc5.c |  2 +-
 drivers/net/irda/ali-ircc.c               |  2 +-
 drivers/net/irda/nsc-ircc.c               |  2 +-
 drivers/s390/scsi/zfcp_dbf.c              |  6 +++---
 drivers/scsi/bnx2i/bnx2i_hwi.c            | 16 ++++++++--------
 drivers/scsi/bnx2i/bnx2i_iscsi.c          | 14 +++++++-------
 drivers/scsi/ncr53c8xx.c                  |  2 +-
 drivers/scsi/sym53c8xx_2/sym_glue.h       |  2 +-
 drivers/staging/iio/adc/ad7606.h          |  2 +-
 include/linux/amba/serial.h               |  2 +-
 include/linux/mfd/si476x-core.h           |  2 +-
 include/linux/netdevice.h                 |  2 +-
 include/net/bluetooth/l2cap.h             |  2 +-
 net/can/af_can.c                          |  2 +-
 net/netfilter/xt_set.c                    |  4 ++--
 19 files changed, 36 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/arch/mips/include/asm/octeon/cvmx-pip.h b/arch/mips/include/asm/octeon/cvmx-pip.h
index a76fe5a57a9f..df69bfd2b006 100644
--- a/arch/mips/include/asm/octeon/cvmx-pip.h
+++ b/arch/mips/include/asm/octeon/cvmx-pip.h
@@ -192,13 +192,13 @@ typedef struct {
 	/* Number of packets processed by PIP */
 	uint32_t packets;
 	/*
-	 * Number of indentified L2 multicast packets.	Does not
+	 * Number of identified L2 multicast packets.	Does not
 	 * include broadcast packets.  Only includes packets whose
 	 * parse mode is SKIP_TO_L2
 	 */
 	uint32_t multicast_packets;
 	/*
-	 * Number of indentified L2 broadcast packets.	Does not
+	 * Number of identified L2 broadcast packets.	Does not
 	 * include multicast packets.  Only includes packets whose
 	 * parse mode is SKIP_TO_L2
 	 */
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 1414c90feaba..0641113e2965 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1,5 +1,5 @@
 /*
- *	Routines to indentify caches on Intel CPU.
+ *	Routines to identify caches on Intel CPU.
  *
  *	Changes:
  *	Venkatesh Pallipadi	: Adding cache identification through cpuid(4)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index f2cc63e9cf08..b6f794aa1693 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -1,5 +1,5 @@
 /*
- *	Routines to indentify additional cpu features that are scattered in
+ *	Routines to identify additional cpu features that are scattered in
  *	cpuid space.
  */
 #include <linux/cpu.h>
diff --git a/drivers/media/rc/keymaps/rc-dib0700-nec.c b/drivers/media/rc/keymaps/rc-dib0700-nec.c
index 4d13a7f2e5c3..492a05ade7e1 100644
--- a/drivers/media/rc/keymaps/rc-dib0700-nec.c
+++ b/drivers/media/rc/keymaps/rc-dib0700-nec.c
@@ -5,7 +5,7 @@
  * TODO: This table is a real mess, as it merges RC codes from several
  * devices into a big table. It also has both RC-5 and NEC codes inside.
  * It should be broken into small tables, and the protocols should properly
- * be indentificated.
+ * be identificated.
  *
  * The table were imported from dib0700_devices.c.
  *
diff --git a/drivers/media/rc/keymaps/rc-dib0700-rc5.c b/drivers/media/rc/keymaps/rc-dib0700-rc5.c
index ba81d9697cfc..454ea596a7ee 100644
--- a/drivers/media/rc/keymaps/rc-dib0700-rc5.c
+++ b/drivers/media/rc/keymaps/rc-dib0700-rc5.c
@@ -5,7 +5,7 @@
  * TODO: This table is a real mess, as it merges RC codes from several
  * devices into a big table. It also has both RC-5 and NEC codes inside.
  * It should be broken into small tables, and the protocols should properly
- * be indentificated.
+ * be identificated.
  *
  * The table were imported from dib0700_devices.c.
  *
diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c
index 7bbd318bc93e..befa45f809c3 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -627,7 +627,7 @@ static int ali_ircc_setup(chipio_t *info)
 /*
  * Function ali_ircc_read_dongle_id (int index, info)
  *
- * Try to read dongle indentification. This procedure needs to be executed
+ * Try to read dongle identification. This procedure needs to be executed
  * once after power-on/reset. It also needs to be used whenever you suspect
  * that the user may have plugged/unplugged the IrDA Dongle.
  */
diff --git a/drivers/net/irda/nsc-ircc.c b/drivers/net/irda/nsc-ircc.c
index ceeb53737f86..66bc03bdb138 100644
--- a/drivers/net/irda/nsc-ircc.c
+++ b/drivers/net/irda/nsc-ircc.c
@@ -1035,7 +1035,7 @@ static int nsc_ircc_setup(chipio_t *info)
 /*
  * Function nsc_ircc_read_dongle_id (void)
  *
- * Try to read dongle indentification. This procedure needs to be executed
+ * Try to read dongle identification. This procedure needs to be executed
  * once after power-on/reset. It also needs to be used whenever you suspect
  * that the user may have plugged/unplugged the IrDA Dongle.
  */
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 132a905b6bdb..0ca64484cfa3 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -344,7 +344,7 @@ void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf, void *data, u8 id, u16 len,
 
 /**
  * zfcp_dbf_san_req - trace event for issued SAN request
- * @tag: indentifier for event
+ * @tag: identifier for event
  * @fsf_req: request containing issued CT data
  * d_id: destination ID
  */
@@ -361,7 +361,7 @@ void zfcp_dbf_san_req(char *tag, struct zfcp_fsf_req *fsf, u32 d_id)
 
 /**
  * zfcp_dbf_san_res - trace event for received SAN request
- * @tag: indentifier for event
+ * @tag: identifier for event
  * @fsf_req: request containing issued CT data
  */
 void zfcp_dbf_san_res(char *tag, struct zfcp_fsf_req *fsf)
@@ -377,7 +377,7 @@ void zfcp_dbf_san_res(char *tag, struct zfcp_fsf_req *fsf)
 
 /**
  * zfcp_dbf_san_in_els - trace event for incoming ELS
- * @tag: indentifier for event
+ * @tag: identifier for event
  * @fsf_req: request containing issued CT data
  */
 void zfcp_dbf_san_in_els(char *tag, struct zfcp_fsf_req *fsf)
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index af3e675d4d48..886e2f9eb0ea 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -126,7 +126,7 @@ static void bnx2i_iscsi_license_error(struct bnx2i_hba *hba, u32 error_code)
 
 /**
  * bnx2i_arm_cq_event_coalescing - arms CQ to enable EQ notification
- * @ep:		endpoint (transport indentifier) structure
+ * @ep:		endpoint (transport identifier) structure
  * @action:	action, ARM or DISARM. For now only ARM_CQE is used
  *
  * Arm'ing CQ will enable chip to generate global EQ events inorder to interrupt
@@ -756,7 +756,7 @@ void bnx2i_send_cmd_cleanup_req(struct bnx2i_hba *hba, struct bnx2i_cmd *cmd)
 /**
  * bnx2i_send_conn_destroy - initiates iscsi connection teardown process
  * @hba:	adapter structure pointer
- * @ep:		endpoint (transport indentifier) structure
+ * @ep:		endpoint (transport identifier) structure
  *
  * this routine prepares and posts CONN_OFLD_REQ1/2 KWQE to initiate
  * 	iscsi connection context clean-up process
@@ -791,7 +791,7 @@ int bnx2i_send_conn_destroy(struct bnx2i_hba *hba, struct bnx2i_endpoint *ep)
 /**
  * bnx2i_570x_send_conn_ofld_req - initiates iscsi conn context setup process
  * @hba: 		adapter structure pointer
- * @ep: 		endpoint (transport indentifier) structure
+ * @ep: 		endpoint (transport identifier) structure
  *
  * 5706/5708/5709 specific - prepares and posts CONN_OFLD_REQ1/2 KWQE
  */
@@ -851,7 +851,7 @@ static int bnx2i_570x_send_conn_ofld_req(struct bnx2i_hba *hba,
 /**
  * bnx2i_5771x_send_conn_ofld_req - initiates iscsi connection context creation
  * @hba: 		adapter structure pointer
- * @ep: 		endpoint (transport indentifier) structure
+ * @ep: 		endpoint (transport identifier) structure
  *
  * 57710 specific - prepares and posts CONN_OFLD_REQ1/2 KWQE
  */
@@ -920,7 +920,7 @@ static int bnx2i_5771x_send_conn_ofld_req(struct bnx2i_hba *hba,
  * bnx2i_send_conn_ofld_req - initiates iscsi connection context setup process
  *
  * @hba: 		adapter structure pointer
- * @ep: 		endpoint (transport indentifier) structure
+ * @ep: 		endpoint (transport identifier) structure
  *
  * this routine prepares and posts CONN_OFLD_REQ1/2 KWQE
  */
@@ -939,7 +939,7 @@ int bnx2i_send_conn_ofld_req(struct bnx2i_hba *hba, struct bnx2i_endpoint *ep)
 
 /**
  * setup_qp_page_tables - iscsi QP page table setup function
- * @ep:		endpoint (transport indentifier) structure
+ * @ep:		endpoint (transport identifier) structure
  *
  * Sets up page tables for SQ/RQ/CQ, 1G/sec (5706/5708/5709) devices requires
  * 	64-bit address in big endian format. Whereas 10G/sec (57710) requires
@@ -1046,7 +1046,7 @@ static void setup_qp_page_tables(struct bnx2i_endpoint *ep)
 /**
  * bnx2i_alloc_qp_resc - allocates required resources for QP.
  * @hba:	adapter structure pointer
- * @ep:		endpoint (transport indentifier) structure
+ * @ep:		endpoint (transport identifier) structure
  *
  * Allocate QP (transport layer for iSCSI connection) resources, DMA'able
  *	memory for SQ/RQ/CQ and page tables. EP structure elements such
@@ -1191,7 +1191,7 @@ mem_alloc_err:
 /**
  * bnx2i_free_qp_resc - free memory resources held by QP
  * @hba:	adapter structure pointer
- * @ep:	endpoint (transport indentifier) structure
+ * @ep:	endpoint (transport identifier) structure
  *
  * Free QP resources - SQ/RQ/CQ memory and page tables.
  */
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index fabeb88602ac..854dad7d5b03 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -596,7 +596,7 @@ void bnx2i_drop_session(struct iscsi_cls_session *cls_session)
 /**
  * bnx2i_ep_destroy_list_add - add an entry to EP destroy list
  * @hba:	pointer to adapter instance
- * @ep:		pointer to endpoint (transport indentifier) structure
+ * @ep:		pointer to endpoint (transport identifier) structure
  *
  * EP destroy queue manager
  */
@@ -613,7 +613,7 @@ static int bnx2i_ep_destroy_list_add(struct bnx2i_hba *hba,
  * bnx2i_ep_destroy_list_del - add an entry to EP destroy list
  *
  * @hba: 		pointer to adapter instance
- * @ep: 		pointer to endpoint (transport indentifier) structure
+ * @ep: 		pointer to endpoint (transport identifier) structure
  *
  * EP destroy queue manager
  */
@@ -630,7 +630,7 @@ static int bnx2i_ep_destroy_list_del(struct bnx2i_hba *hba,
 /**
  * bnx2i_ep_ofld_list_add - add an entry to ep offload pending list
  * @hba:	pointer to adapter instance
- * @ep:		pointer to endpoint (transport indentifier) structure
+ * @ep:		pointer to endpoint (transport identifier) structure
  *
  * pending conn offload completion queue manager
  */
@@ -646,7 +646,7 @@ static int bnx2i_ep_ofld_list_add(struct bnx2i_hba *hba,
 /**
  * bnx2i_ep_ofld_list_del - add an entry to ep offload pending list
  * @hba: 		pointer to adapter instance
- * @ep: 		pointer to endpoint (transport indentifier) structure
+ * @ep: 		pointer to endpoint (transport identifier) structure
  *
  * pending conn offload completion queue manager
  */
@@ -721,7 +721,7 @@ bnx2i_find_ep_in_destroy_list(struct bnx2i_hba *hba, u32 iscsi_cid)
 /**
  * bnx2i_ep_active_list_add - add an entry to ep active list
  * @hba:	pointer to adapter instance
- * @ep:		pointer to endpoint (transport indentifier) structure
+ * @ep:		pointer to endpoint (transport identifier) structure
  *
  * current active conn queue manager
  */
@@ -737,7 +737,7 @@ static void bnx2i_ep_active_list_add(struct bnx2i_hba *hba,
 /**
  * bnx2i_ep_active_list_del - deletes an entry to ep active list
  * @hba:	pointer to adapter instance
- * @ep:		pointer to endpoint (transport indentifier) structure
+ * @ep:		pointer to endpoint (transport identifier) structure
  *
  * current active conn queue manager
  */
@@ -1695,7 +1695,7 @@ no_nx2_route:
 /**
  * bnx2i_tear_down_conn - tear down iscsi/tcp connection and free resources
  * @hba:	pointer to adapter instance
- * @ep:		endpoint (transport indentifier) structure
+ * @ep:		endpoint (transport identifier) structure
  *
  * destroys cm_sock structure and on chip iscsi context
  */
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index 5982a587babc..7d014b11df62 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -1615,7 +1615,7 @@ struct ncb {
 	spinlock_t	smp_lock;	/* Lock for SMP threading       */
 
 	/*----------------------------------------------------------------
-	**	Chip and controller indentification.
+	**	Chip and controller identification.
 	**----------------------------------------------------------------
 	*/
 	int		unit;		/* Unit number			*/
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.h b/drivers/scsi/sym53c8xx_2/sym_glue.h
index b80bf709f104..805369521df8 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.h
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.h
@@ -174,7 +174,7 @@ struct sym_slcb {
  */
 struct sym_shcb {
 	/*
-	 *  Chip and controller indentification.
+	 *  Chip and controller identification.
 	 */
 	int		unit;
 	char		inst_name[16];
diff --git a/drivers/staging/iio/adc/ad7606.h b/drivers/staging/iio/adc/ad7606.h
index 9221a74efd18..93c7299e8353 100644
--- a/drivers/staging/iio/adc/ad7606.h
+++ b/drivers/staging/iio/adc/ad7606.h
@@ -42,7 +42,7 @@ struct ad7606_platform_data {
 
 /**
  * struct ad7606_chip_info - chip specifc information
- * @name:		indentification string for chip
+ * @name:		identification string for chip
  * @int_vref_mv:	the internal reference voltage
  * @channels:		channel specification
  * @num_channels:	number of channels
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index 62d9303c2837..0ddb5c02ad8b 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -40,7 +40,7 @@
 #define UART010_LCRL		0x10	/* Line control register, low byte. */
 #define UART010_CR		0x14	/* Control register. */
 #define UART01x_FR		0x18	/* Flag register (Read only). */
-#define UART010_IIR		0x1C	/* Interrupt indentification register (Read). */
+#define UART010_IIR		0x1C	/* Interrupt identification register (Read). */
 #define UART010_ICR		0x1C	/* Interrupt clear register (Write). */
 #define ST_UART011_LCRH_RX	0x1C    /* Rx line control register. */
 #define UART01x_ILPR		0x20	/* IrDA low power counter register. */
diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h
index ba89b94e4a56..674b45d5a757 100644
--- a/include/linux/mfd/si476x-core.h
+++ b/include/linux/mfd/si476x-core.h
@@ -316,7 +316,7 @@ enum si476x_smoothmetrics {
  * response to 'FM_RD_STATUS' command
  * @rdstpptyint: Traffic program flag(TP) and/or program type(PTY)
  * code has changed.
- * @rdspiint: Program indentifiaction(PI) code has changed.
+ * @rdspiint: Program identification(PI) code has changed.
  * @rdssyncint: RDS synchronization has changed.
  * @rdsfifoint: RDS was received and the RDS FIFO has at least
  * 'FM_RDS_INTERRUPT_FIFO_COUNT' elements in it.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8ed4ae943053..9ff50c9a0009 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1546,7 +1546,7 @@ static inline void *netdev_priv(const struct net_device *dev)
 #define SET_NETDEV_DEV(net, pdev)	((net)->dev.parent = (pdev))
 
 /* Set the sysfs device type for the network logical device to allow
- * fin grained indentification of different network device types. For
+ * fine-grained identification of different network device types. For
  * example Ethernet, Wirelss LAN, Bluetooth, WiMAX etc.
  */
 #define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 1a966afbbfa8..7170b4b434e1 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -238,7 +238,7 @@ struct l2cap_conn_rsp {
 #define L2CAP_PSM_SDP		0x0001
 #define L2CAP_PSM_RFCOMM	0x0003
 
-/* channel indentifier */
+/* channel identifier */
 #define L2CAP_CID_SIGNALING	0x0001
 #define L2CAP_CID_CONN_LESS	0x0002
 #define L2CAP_CID_A2MP		0x0003
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 3ab8dd2e1282..d249874a366d 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -420,7 +420,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @mask: CAN mask (see description)
  * @func: callback function on filter match
  * @data: returned parameter for callback function
- * @ident: string for calling module indentification
+ * @ident: string for calling module identification
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 31790e789e22..4b9d6b4f1eb0 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -84,7 +84,7 @@ set_match_v0_checkentry(const struct xt_mtchk_param *par)
 	index = ip_set_nfnl_get_byindex(info->match_set.index);
 
 	if (index == IPSET_INVALID_ID) {
-		pr_warning("Cannot find set indentified by id %u to match\n",
+		pr_warning("Cannot find set identified by id %u to match\n",
 			   info->match_set.index);
 		return -ENOENT;
 	}
@@ -205,7 +205,7 @@ set_match_v1_checkentry(const struct xt_mtchk_param *par)
 	index = ip_set_nfnl_get_byindex(info->match_set.index);
 
 	if (index == IPSET_INVALID_ID) {
-		pr_warning("Cannot find set indentified by id %u to match\n",
+		pr_warning("Cannot find set identified by id %u to match\n",
 			   info->match_set.index);
 		return -ENOENT;
 	}
-- 
cgit 


From e33fabd365596178e72f62bb4b89f0aaad0509ad Mon Sep 17 00:00:00 2001
From: Anthony Olech <anthony.olech.opensource@diasemi.com>
Date: Fri, 11 Oct 2013 15:31:11 +0100
Subject: regmap: new API regmap_multi_reg_write() definition

New API regmap_multi_reg_write() is defined that allows a set of reg,val
pairs to be written to a I2C client device as one block transfer from the
point of view of a single I2C master system.

A simple demonstration implementation is included that just splits the
block write request into a sequence of single register writes.

The implementation will be modified later to support those I2C clients
that implement the alternative non-standard MULTIWRITE block write mode
so to achieve a single I2C transfer that will be atomic even in multiple
I2C master systems.

Signed-off-by: Anthony Olech <anthony.olech.opensource@diasemi.com>
Signed-off-by: David Dajun Chen <david.chen@diasemi.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/regmap.c | 41 +++++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h       |  2 ++
 2 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 7d689a15c500..c42ad69e527f 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1439,6 +1439,47 @@ out:
 }
 EXPORT_SYMBOL_GPL(regmap_bulk_write);
 
+/*
+ * regmap_multi_reg_write(): Write multiple registers to the device
+ *
+ * where the set of register are supplied in any order
+ *
+ * @map: Register map to write to
+ * @regs: Array of structures containing register,value to be written
+ * @num_regs: Number of registers to write
+ *
+ * This function is intended to be used for writing a large block of data
+ * atomically to the device in single transfer for those I2C client devices
+ * that implement this alternative block write mode.
+ *
+ * A value of zero will be returned on success, a negative errno will
+ * be returned in error cases.
+ */
+int regmap_multi_reg_write(struct regmap *map, struct reg_default *regs,
+				int num_regs)
+{
+	int ret = 0, i;
+
+	for (i = 0; i < num_regs; i++) {
+		int reg = regs[i].reg;
+		if (reg % map->reg_stride)
+			return -EINVAL;
+	}
+
+	map->lock(map->lock_arg);
+
+	for (i = 0; i < num_regs; i++) {
+		ret = _regmap_write(map, regs[i].reg, regs[i].def);
+		if (ret != 0)
+			goto out;
+	}
+out:
+	map->unlock(map->lock_arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_multi_reg_write);
+
 /**
  * regmap_raw_write_async(): Write raw values to one or more registers
  *                           asynchronously
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index a10380bfbeac..4b933a31f84f 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -378,6 +378,8 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 		     const void *val, size_t val_len);
 int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 			size_t val_count);
+int regmap_multi_reg_write(struct regmap *map, struct reg_default *regs,
+			int num_regs);
 int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 			   const void *val, size_t val_len);
 int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val);
-- 
cgit 


From 96518518cc417bb0a8c80b9fb736202e28acdf96 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 14 Oct 2013 11:00:02 +0200
Subject: netfilter: add nftables

This patch adds nftables which is the intended successor of iptables.
This packet filtering framework reuses the existing netfilter hooks,
the connection tracking system, the NAT subsystem, the transparent
proxying engine, the logging infrastructure and the userspace packet
queueing facilities.

In a nutshell, nftables provides a pseudo-state machine with 4 general
purpose registers of 128 bits and 1 specific purpose register to store
verdicts. This pseudo-machine comes with an extensible instruction set,
a.k.a. "expressions" in the nftables jargon. The expressions included
in this patch provide the basic functionality, they are:

* bitwise: to perform bitwise operations.
* byteorder: to change from host/network endianess.
* cmp: to compare data with the content of the registers.
* counter: to enable counters on rules.
* ct: to store conntrack keys into register.
* exthdr: to match IPv6 extension headers.
* immediate: to load data into registers.
* limit: to limit matching based on packet rate.
* log: to log packets.
* meta: to match metainformation that usually comes with the skbuff.
* nat: to perform Network Address Translation.
* payload: to fetch data from the packet payload and store it into
  registers.
* reject (IPv4 only): to explicitly close connection, eg. TCP RST.

Using this instruction-set, the userspace utility 'nft' can transform
the rules expressed in human-readable text representation (using a
new syntax, inspired by tcpdump) to nftables bytecode.

nftables also inherits the table, chain and rule objects from
iptables, but in a more configurable way, and it also includes the
original datatype-agnostic set infrastructure with mapping support.
This set infrastructure is enhanced in the follow up patch (netfilter:
nf_tables: add netlink set API).

This patch includes the following components:

* the netlink API: net/netfilter/nf_tables_api.c and
  include/uapi/netfilter/nf_tables.h
* the packet filter core: net/netfilter/nf_tables_core.c
* the expressions (described above): net/netfilter/nft_*.c
* the filter tables: arp, IPv4, IPv6 and bridge:
  net/ipv4/netfilter/nf_tables_ipv4.c
  net/ipv6/netfilter/nf_tables_ipv6.c
  net/ipv4/netfilter/nf_tables_arp.c
  net/bridge/netfilter/nf_tables_bridge.c
* the NAT table (IPv4 only):
  net/ipv4/netfilter/nf_table_nat_ipv4.c
* the route table (similar to mangle):
  net/ipv4/netfilter/nf_table_route_ipv4.c
  net/ipv6/netfilter/nf_table_route_ipv6.c
* internal definitions under:
  include/net/netfilter/nf_tables.h
  include/net/netfilter/nf_tables_core.h
* It also includes an skeleton expression:
  net/netfilter/nft_expr_template.c
  and the preliminary implementation of the meta target
  net/netfilter/nft_meta_target.c

It also includes a change in struct nf_hook_ops to add a new
pointer to store private data to the hook, that is used to store
the rule list per chain.

This patch is based on the patch from Patrick McHardy, plus merged
accumulated cleanups, fixes and small enhancements to the nftables
code that has been done since 2009, which are:

From Patrick McHardy:
* nf_tables: adjust netlink handler function signatures
* nf_tables: only retry table lookup after successful table module load
* nf_tables: fix event notification echo and avoid unnecessary messages
* nft_ct: add l3proto support
* nf_tables: pass expression context to nft_validate_data_load()
* nf_tables: remove redundant definition
* nft_ct: fix maxattr initialization
* nf_tables: fix invalid event type in nf_tables_getrule()
* nf_tables: simplify nft_data_init() usage
* nf_tables: build in more core modules
* nf_tables: fix double lookup expression unregistation
* nf_tables: move expression initialization to nf_tables_core.c
* nf_tables: build in payload module
* nf_tables: use NFPROTO constants
* nf_tables: rename pid variables to portid
* nf_tables: save 48 bits per rule
* nf_tables: introduce chain rename
* nf_tables: check for duplicate names on chain rename
* nf_tables: remove ability to specify handles for new rules
* nf_tables: return error for rule change request
* nf_tables: return error for NLM_F_REPLACE without rule handle
* nf_tables: include NLM_F_APPEND/NLM_F_REPLACE flags in rule notification
* nf_tables: fix NLM_F_MULTI usage in netlink notifications
* nf_tables: include NLM_F_APPEND in rule dumps

From Pablo Neira Ayuso:
* nf_tables: fix stack overflow in nf_tables_newrule
* nf_tables: nft_ct: fix compilation warning
* nf_tables: nft_ct: fix crash with invalid packets
* nft_log: group and qthreshold are 2^16
* nf_tables: nft_meta: fix socket uid,gid handling
* nft_counter: allow to restore counters
* nf_tables: fix module autoload
* nf_tables: allow to remove all rules placed in one chain
* nf_tables: use 64-bits rule handle instead of 16-bits
* nf_tables: fix chain after rule deletion
* nf_tables: improve deletion performance
* nf_tables: add missing code in route chain type
* nf_tables: rise maximum number of expressions from 12 to 128
* nf_tables: don't delete table if in use
* nf_tables: fix basechain release

From Tomasz Bursztyka:
* nf_tables: Add support for changing users chain's name
* nf_tables: Change chain's name to be fixed sized
* nf_tables: Add support for replacing a rule by another one
* nf_tables: Update uapi nftables netlink header documentation

From Florian Westphal:
* nft_log: group is u16, snaplen u32

From Phil Oester:
* nf_tables: operational limit match

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                          |   11 +-
 include/net/netfilter/nf_tables.h                  |  301 ++++
 include/net/netfilter/nf_tables_core.h             |   25 +
 include/uapi/linux/netfilter/Kbuild                |    1 +
 include/uapi/linux/netfilter/nf_conntrack_common.h |    4 +
 include/uapi/linux/netfilter/nf_tables.h           |  582 +++++++
 include/uapi/linux/netfilter/nfnetlink.h           |    5 +-
 net/bridge/netfilter/Kconfig                       |    3 +
 net/bridge/netfilter/Makefile                      |    2 +
 net/bridge/netfilter/nf_tables_bridge.c            |   37 +
 net/ipv4/netfilter/Kconfig                         |   16 +
 net/ipv4/netfilter/Makefile                        |    5 +
 net/ipv4/netfilter/nf_table_nat_ipv4.c             |  409 +++++
 net/ipv4/netfilter/nf_table_route_ipv4.c           |   97 ++
 net/ipv4/netfilter/nf_tables_ipv4.c                |   59 +
 net/ipv4/netfilter/nft_reject_ipv4.c               |  117 ++
 net/ipv6/netfilter/Kconfig                         |    8 +
 net/ipv6/netfilter/Makefile                        |    4 +
 net/ipv6/netfilter/nf_table_route_ipv6.c           |   93 ++
 net/ipv6/netfilter/nf_tables_ipv6.c                |   57 +
 net/netfilter/Kconfig                              |   37 +
 net/netfilter/Makefile                             |   16 +
 net/netfilter/nf_tables_api.c                      | 1760 ++++++++++++++++++++
 net/netfilter/nf_tables_core.c                     |  152 ++
 net/netfilter/nft_bitwise.c                        |  140 ++
 net/netfilter/nft_byteorder.c                      |  167 ++
 net/netfilter/nft_cmp.c                            |  146 ++
 net/netfilter/nft_counter.c                        |  107 ++
 net/netfilter/nft_ct.c                             |  252 +++
 net/netfilter/nft_expr_template.c                  |   88 +
 net/netfilter/nft_exthdr.c                         |  127 ++
 net/netfilter/nft_hash.c                           |  348 ++++
 net/netfilter/nft_immediate.c                      |  113 ++
 net/netfilter/nft_limit.c                          |  113 ++
 net/netfilter/nft_log.c                            |  140 ++
 net/netfilter/nft_meta.c                           |  222 +++
 net/netfilter/nft_meta_target.c                    |  117 ++
 net/netfilter/nft_payload.c                        |  137 ++
 net/netfilter/nft_set.c                            |  381 +++++
 39 files changed, 6393 insertions(+), 6 deletions(-)
 create mode 100644 include/net/netfilter/nf_tables.h
 create mode 100644 include/net/netfilter/nf_tables_core.h
 create mode 100644 include/uapi/linux/netfilter/nf_tables.h
 create mode 100644 net/bridge/netfilter/nf_tables_bridge.c
 create mode 100644 net/ipv4/netfilter/nf_table_nat_ipv4.c
 create mode 100644 net/ipv4/netfilter/nf_table_route_ipv4.c
 create mode 100644 net/ipv4/netfilter/nf_tables_ipv4.c
 create mode 100644 net/ipv4/netfilter/nft_reject_ipv4.c
 create mode 100644 net/ipv6/netfilter/nf_table_route_ipv6.c
 create mode 100644 net/ipv6/netfilter/nf_tables_ipv6.c
 create mode 100644 net/netfilter/nf_tables_api.c
 create mode 100644 net/netfilter/nf_tables_core.c
 create mode 100644 net/netfilter/nft_bitwise.c
 create mode 100644 net/netfilter/nft_byteorder.c
 create mode 100644 net/netfilter/nft_cmp.c
 create mode 100644 net/netfilter/nft_counter.c
 create mode 100644 net/netfilter/nft_ct.c
 create mode 100644 net/netfilter/nft_expr_template.c
 create mode 100644 net/netfilter/nft_exthdr.c
 create mode 100644 net/netfilter/nft_hash.c
 create mode 100644 net/netfilter/nft_immediate.c
 create mode 100644 net/netfilter/nft_limit.c
 create mode 100644 net/netfilter/nft_log.c
 create mode 100644 net/netfilter/nft_meta.c
 create mode 100644 net/netfilter/nft_meta_target.c
 create mode 100644 net/netfilter/nft_payload.c
 create mode 100644 net/netfilter/nft_set.c

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index fef7e67f7101..2077489f9887 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -53,12 +53,13 @@ struct nf_hook_ops {
 	struct list_head list;
 
 	/* User fills in from here down. */
-	nf_hookfn *hook;
-	struct module *owner;
-	u_int8_t pf;
-	unsigned int hooknum;
+	nf_hookfn	*hook;
+	struct module	*owner;
+	void		*priv;
+	u_int8_t	pf;
+	unsigned int	hooknum;
 	/* Hooks are ordered in ascending priority. */
-	int priority;
+	int		priority;
 };
 
 struct nf_sockopt_ops {
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
new file mode 100644
index 000000000000..d26dfa345f49
--- /dev/null
+++ b/include/net/netfilter/nf_tables.h
@@ -0,0 +1,301 @@
+#ifndef _NET_NF_TABLES_H
+#define _NET_NF_TABLES_H
+
+#include <linux/list.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netlink.h>
+
+struct nft_pktinfo {
+	struct sk_buff			*skb;
+	const struct net_device		*in;
+	const struct net_device		*out;
+	u8				hooknum;
+	u8				nhoff;
+	u8				thoff;
+};
+
+struct nft_data {
+	union {
+		u32				data[4];
+		struct {
+			u32			verdict;
+			struct nft_chain	*chain;
+		};
+	};
+} __attribute__((aligned(__alignof__(u64))));
+
+static inline int nft_data_cmp(const struct nft_data *d1,
+			       const struct nft_data *d2,
+			       unsigned int len)
+{
+	return memcmp(d1->data, d2->data, len);
+}
+
+static inline void nft_data_copy(struct nft_data *dst,
+				 const struct nft_data *src)
+{
+	BUILD_BUG_ON(__alignof__(*dst) != __alignof__(u64));
+	*(u64 *)&dst->data[0] = *(u64 *)&src->data[0];
+	*(u64 *)&dst->data[2] = *(u64 *)&src->data[2];
+}
+
+static inline void nft_data_debug(const struct nft_data *data)
+{
+	pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n",
+		 data->data[0], data->data[1],
+		 data->data[2], data->data[3]);
+}
+
+/**
+ *	struct nft_ctx - nf_tables rule context
+ *
+ * 	@afi: address family info
+ * 	@table: the table the chain is contained in
+ * 	@chain: the chain the rule is contained in
+ */
+struct nft_ctx {
+	const struct nft_af_info	*afi;
+	const struct nft_table		*table;
+	const struct nft_chain		*chain;
+};
+
+enum nft_data_types {
+	NFT_DATA_VALUE,
+	NFT_DATA_VERDICT,
+};
+
+struct nft_data_desc {
+	enum nft_data_types		type;
+	unsigned int			len;
+};
+
+extern int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+			 struct nft_data_desc *desc, const struct nlattr *nla);
+extern void nft_data_uninit(const struct nft_data *data,
+			    enum nft_data_types type);
+extern int nft_data_dump(struct sk_buff *skb, int attr,
+			 const struct nft_data *data,
+			 enum nft_data_types type, unsigned int len);
+
+static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg)
+{
+	return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE;
+}
+
+extern int nft_validate_input_register(enum nft_registers reg);
+extern int nft_validate_output_register(enum nft_registers reg);
+extern int nft_validate_data_load(const struct nft_ctx *ctx,
+				  enum nft_registers reg,
+				  const struct nft_data *data,
+				  enum nft_data_types type);
+
+/**
+ *	struct nft_expr_ops - nf_tables expression operations
+ *
+ *	@eval: Expression evaluation function
+ *	@init: initialization function
+ *	@destroy: destruction function
+ *	@dump: function to dump parameters
+ *	@list: used internally
+ *	@name: Identifier
+ *	@owner: module reference
+ *	@policy: netlink attribute policy
+ *	@maxattr: highest netlink attribute number
+ *	@size: full expression size, including private data size
+ */
+struct nft_expr;
+struct nft_expr_ops {
+	void				(*eval)(const struct nft_expr *expr,
+						struct nft_data data[NFT_REG_MAX + 1],
+						const struct nft_pktinfo *pkt);
+	int				(*init)(const struct nft_ctx *ctx,
+						const struct nft_expr *expr,
+						const struct nlattr * const tb[]);
+	void				(*destroy)(const struct nft_expr *expr);
+	int				(*dump)(struct sk_buff *skb,
+						const struct nft_expr *expr);
+
+	struct list_head		list;
+	const char			*name;
+	struct module			*owner;
+	const struct nla_policy		*policy;
+	unsigned int			maxattr;
+	unsigned int			size;
+};
+
+#define NFT_EXPR_SIZE(size)		(sizeof(struct nft_expr) + \
+					 ALIGN(size, __alignof__(struct nft_expr)))
+
+/**
+ *	struct nft_expr - nf_tables expression
+ *
+ *	@ops: expression ops
+ *	@data: expression private data
+ */
+struct nft_expr {
+	const struct nft_expr_ops	*ops;
+	unsigned char			data[];
+};
+
+static inline void *nft_expr_priv(const struct nft_expr *expr)
+{
+	return (void *)expr->data;
+}
+
+/**
+ *	struct nft_rule - nf_tables rule
+ *
+ *	@list: used internally
+ *	@rcu_head: used internally for rcu
+ *	@handle: rule handle
+ *	@dlen: length of expression data
+ *	@data: expression data
+ */
+struct nft_rule {
+	struct list_head		list;
+	struct rcu_head			rcu_head;
+	u64				handle:48,
+					dlen:16;
+	unsigned char			data[]
+		__attribute__((aligned(__alignof__(struct nft_expr))));
+};
+
+static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
+{
+	return (struct nft_expr *)&rule->data[0];
+}
+
+static inline struct nft_expr *nft_expr_next(const struct nft_expr *expr)
+{
+	return ((void *)expr) + expr->ops->size;
+}
+
+static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule)
+{
+	return (struct nft_expr *)&rule->data[rule->dlen];
+}
+
+/*
+ * The last pointer isn't really necessary, but the compiler isn't able to
+ * determine that the result of nft_expr_last() is always the same since it
+ * can't assume that the dlen value wasn't changed within calls in the loop.
+ */
+#define nft_rule_for_each_expr(expr, last, rule) \
+	for ((expr) = nft_expr_first(rule), (last) = nft_expr_last(rule); \
+	     (expr) != (last); \
+	     (expr) = nft_expr_next(expr))
+
+enum nft_chain_flags {
+	NFT_BASE_CHAIN			= 0x1,
+	NFT_CHAIN_BUILTIN		= 0x2,
+};
+
+/**
+ *	struct nft_chain - nf_tables chain
+ *
+ *	@rules: list of rules in the chain
+ *	@list: used internally
+ *	@rcu_head: used internally
+ *	@handle: chain handle
+ *	@flags: bitmask of enum nft_chain_flags
+ *	@use: number of jump references to this chain
+ *	@level: length of longest path to this chain
+ *	@name: name of the chain
+ */
+struct nft_chain {
+	struct list_head		rules;
+	struct list_head		list;
+	struct rcu_head			rcu_head;
+	u64				handle;
+	u8				flags;
+	u16				use;
+	u16				level;
+	char				name[NFT_CHAIN_MAXNAMELEN];
+};
+
+/**
+ *	struct nft_base_chain - nf_tables base chain
+ *
+ *	@ops: netfilter hook ops
+ *	@chain: the chain
+ */
+struct nft_base_chain {
+	struct nf_hook_ops		ops;
+	struct nft_chain		chain;
+};
+
+static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
+{
+	return container_of(chain, struct nft_base_chain, chain);
+}
+
+extern unsigned int nft_do_chain(const struct nf_hook_ops *ops,
+				 struct sk_buff *skb,
+				 const struct net_device *in,
+				 const struct net_device *out,
+				 int (*okfn)(struct sk_buff *));
+
+enum nft_table_flags {
+	NFT_TABLE_BUILTIN		= 0x1,
+};
+
+/**
+ *	struct nft_table - nf_tables table
+ *
+ *	@list: used internally
+ *	@chains: chains in the table
+ *	@sets: sets in the table
+ *	@hgenerator: handle generator state
+ *	@use: number of chain references to this table
+ *	@flags: table flag (see enum nft_table_flags)
+ *	@name: name of the table
+ */
+struct nft_table {
+	struct list_head		list;
+	struct list_head		chains;
+	struct list_head		sets;
+	u64				hgenerator;
+	u32				use;
+	u16				flags;
+	char				name[];
+};
+
+/**
+ *	struct nft_af_info - nf_tables address family info
+ *
+ *	@list: used internally
+ *	@family: address family
+ *	@nhooks: number of hooks in this family
+ *	@owner: module owner
+ *	@tables: used internally
+ *	@hooks: hookfn overrides for packet validation
+ */
+struct nft_af_info {
+	struct list_head		list;
+	int				family;
+	unsigned int			nhooks;
+	struct module			*owner;
+	struct list_head		tables;
+	nf_hookfn			*hooks[NF_MAX_HOOKS];
+};
+
+extern int nft_register_afinfo(struct nft_af_info *);
+extern void nft_unregister_afinfo(struct nft_af_info *);
+
+extern int nft_register_table(struct nft_table *, int family);
+extern void nft_unregister_table(struct nft_table *, int family);
+
+extern int nft_register_expr(struct nft_expr_ops *);
+extern void nft_unregister_expr(struct nft_expr_ops *);
+
+#define MODULE_ALIAS_NFT_FAMILY(family)	\
+	MODULE_ALIAS("nft-afinfo-" __stringify(family))
+
+#define MODULE_ALIAS_NFT_TABLE(family, name) \
+	MODULE_ALIAS("nft-table-" __stringify(family) "-" name)
+
+#define MODULE_ALIAS_NFT_EXPR(name) \
+	MODULE_ALIAS("nft-expr-" name)
+
+#endif /* _NET_NF_TABLES_H */
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
new file mode 100644
index 000000000000..283396c916e0
--- /dev/null
+++ b/include/net/netfilter/nf_tables_core.h
@@ -0,0 +1,25 @@
+#ifndef _NET_NF_TABLES_CORE_H
+#define _NET_NF_TABLES_CORE_H
+
+extern int nf_tables_core_module_init(void);
+extern void nf_tables_core_module_exit(void);
+
+extern int nft_immediate_module_init(void);
+extern void nft_immediate_module_exit(void);
+
+extern int nft_cmp_module_init(void);
+extern void nft_cmp_module_exit(void);
+
+extern int nft_lookup_module_init(void);
+extern void nft_lookup_module_exit(void);
+
+extern int nft_bitwise_module_init(void);
+extern void nft_bitwise_module_exit(void);
+
+extern int nft_byteorder_module_init(void);
+extern void nft_byteorder_module_exit(void);
+
+extern int nft_payload_module_init(void);
+extern void nft_payload_module_exit(void);
+
+#endif /* _NET_NF_TABLES_CORE_H */
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 174915420d3f..6ce0b7f566a7 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -5,6 +5,7 @@ header-y += nf_conntrack_ftp.h
 header-y += nf_conntrack_sctp.h
 header-y += nf_conntrack_tcp.h
 header-y += nf_conntrack_tuple_common.h
+header-y += nf_tables.h
 header-y += nf_nat.h
 header-y += nfnetlink.h
 header-y += nfnetlink_acct.h
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 8dd803818ebe..319f47128db8 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -25,6 +25,10 @@ enum ip_conntrack_info {
 	IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
 };
 
+#define NF_CT_STATE_INVALID_BIT			(1 << 0)
+#define NF_CT_STATE_BIT(ctinfo)			(1 << ((ctinfo) % IP_CT_IS_REPLY + 1))
+#define NF_CT_STATE_UNTRACKED_BIT		(1 << (IP_CT_NUMBER + 1))
+
 /* Bitset representing status of connection. */
 enum ip_conntrack_status {
 	/* It's an expected connection: bit 0 set.  This bit never changed */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
new file mode 100644
index 000000000000..ec6d84a8ed1e
--- /dev/null
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -0,0 +1,582 @@
+#ifndef _LINUX_NF_TABLES_H
+#define _LINUX_NF_TABLES_H
+
+#define NFT_CHAIN_MAXNAMELEN 32
+
+enum nft_registers {
+	NFT_REG_VERDICT,
+	NFT_REG_1,
+	NFT_REG_2,
+	NFT_REG_3,
+	NFT_REG_4,
+	__NFT_REG_MAX
+};
+#define NFT_REG_MAX	(__NFT_REG_MAX - 1)
+
+/**
+ * enum nft_verdicts - nf_tables internal verdicts
+ *
+ * @NFT_CONTINUE: continue evaluation of the current rule
+ * @NFT_BREAK: terminate evaluation of the current rule
+ * @NFT_JUMP: push the current chain on the jump stack and jump to a chain
+ * @NFT_GOTO: jump to a chain without pushing the current chain on the jump stack
+ * @NFT_RETURN: return to the topmost chain on the jump stack
+ *
+ * The nf_tables verdicts share their numeric space with the netfilter verdicts.
+ */
+enum nft_verdicts {
+	NFT_CONTINUE	= -1,
+	NFT_BREAK	= -2,
+	NFT_JUMP	= -3,
+	NFT_GOTO	= -4,
+	NFT_RETURN	= -5,
+};
+
+/**
+ * enum nf_tables_msg_types - nf_tables netlink message types
+ *
+ * @NFT_MSG_NEWTABLE: create a new table (enum nft_table_attributes)
+ * @NFT_MSG_GETTABLE: get a table (enum nft_table_attributes)
+ * @NFT_MSG_DELTABLE: delete a table (enum nft_table_attributes)
+ * @NFT_MSG_NEWCHAIN: create a new chain (enum nft_chain_attributes)
+ * @NFT_MSG_GETCHAIN: get a chain (enum nft_chain_attributes)
+ * @NFT_MSG_DELCHAIN: delete a chain (enum nft_chain_attributes)
+ * @NFT_MSG_NEWRULE: create a new rule (enum nft_rule_attributes)
+ * @NFT_MSG_GETRULE: get a rule (enum nft_rule_attributes)
+ * @NFT_MSG_DELRULE: delete a rule (enum nft_rule_attributes)
+ */
+enum nf_tables_msg_types {
+	NFT_MSG_NEWTABLE,
+	NFT_MSG_GETTABLE,
+	NFT_MSG_DELTABLE,
+	NFT_MSG_NEWCHAIN,
+	NFT_MSG_GETCHAIN,
+	NFT_MSG_DELCHAIN,
+	NFT_MSG_NEWRULE,
+	NFT_MSG_GETRULE,
+	NFT_MSG_DELRULE,
+	NFT_MSG_MAX,
+};
+
+enum nft_list_attributes {
+	NFTA_LIST_UNPEC,
+	NFTA_LIST_ELEM,
+	__NFTA_LIST_MAX
+};
+#define NFTA_LIST_MAX		(__NFTA_LIST_MAX - 1)
+
+/**
+ * enum nft_hook_attributes - nf_tables netfilter hook netlink attributes
+ *
+ * @NFTA_HOOK_HOOKNUM: netfilter hook number (NLA_U32)
+ * @NFTA_HOOK_PRIORITY: netfilter hook priority (NLA_U32)
+ */
+enum nft_hook_attributes {
+	NFTA_HOOK_UNSPEC,
+	NFTA_HOOK_HOOKNUM,
+	NFTA_HOOK_PRIORITY,
+	__NFTA_HOOK_MAX
+};
+#define NFTA_HOOK_MAX		(__NFTA_HOOK_MAX - 1)
+
+/**
+ * enum nft_table_attributes - nf_tables table netlink attributes
+ *
+ * @NFTA_TABLE_NAME: name of the table (NLA_STRING)
+ */
+enum nft_table_attributes {
+	NFTA_TABLE_UNSPEC,
+	NFTA_TABLE_NAME,
+	__NFTA_TABLE_MAX
+};
+#define NFTA_TABLE_MAX		(__NFTA_TABLE_MAX - 1)
+
+/**
+ * enum nft_chain_attributes - nf_tables chain netlink attributes
+ *
+ * @NFTA_CHAIN_TABLE: name of the table containing the chain (NLA_STRING)
+ * @NFTA_CHAIN_HANDLE: numeric handle of the chain (NLA_U64)
+ * @NFTA_CHAIN_NAME: name of the chain (NLA_STRING)
+ * @NFTA_CHAIN_HOOK: hook specification for basechains (NLA_NESTED: nft_hook_attributes)
+ */
+enum nft_chain_attributes {
+	NFTA_CHAIN_UNSPEC,
+	NFTA_CHAIN_TABLE,
+	NFTA_CHAIN_HANDLE,
+	NFTA_CHAIN_NAME,
+	NFTA_CHAIN_HOOK,
+	__NFTA_CHAIN_MAX
+};
+#define NFTA_CHAIN_MAX		(__NFTA_CHAIN_MAX - 1)
+
+/**
+ * enum nft_rule_attributes - nf_tables rule netlink attributes
+ *
+ * @NFTA_RULE_TABLE: name of the table containing the rule (NLA_STRING)
+ * @NFTA_RULE_CHAIN: name of the chain containing the rule (NLA_STRING)
+ * @NFTA_RULE_HANDLE: numeric handle of the rule (NLA_U64)
+ * @NFTA_RULE_EXPRESSIONS: list of expressions (NLA_NESTED: nft_expr_attributes)
+ */
+enum nft_rule_attributes {
+	NFTA_RULE_UNSPEC,
+	NFTA_RULE_TABLE,
+	NFTA_RULE_CHAIN,
+	NFTA_RULE_HANDLE,
+	NFTA_RULE_EXPRESSIONS,
+	__NFTA_RULE_MAX
+};
+#define NFTA_RULE_MAX		(__NFTA_RULE_MAX - 1)
+
+enum nft_data_attributes {
+	NFTA_DATA_UNSPEC,
+	NFTA_DATA_VALUE,
+	NFTA_DATA_VERDICT,
+	__NFTA_DATA_MAX
+};
+#define NFTA_DATA_MAX		(__NFTA_DATA_MAX - 1)
+
+/**
+ * enum nft_verdict_attributes - nf_tables verdict netlink attributes
+ *
+ * @NFTA_VERDICT_CODE: nf_tables verdict (NLA_U32: enum nft_verdicts)
+ * @NFTA_VERDICT_CHAIN: jump target chain name (NLA_STRING)
+ */
+enum nft_verdict_attributes {
+	NFTA_VERDICT_UNSPEC,
+	NFTA_VERDICT_CODE,
+	NFTA_VERDICT_CHAIN,
+	__NFTA_VERDICT_MAX
+};
+#define NFTA_VERDICT_MAX	(__NFTA_VERDICT_MAX - 1)
+
+/**
+ * enum nft_expr_attributes - nf_tables expression netlink attributes
+ *
+ * @NFTA_EXPR_NAME: name of the expression type (NLA_STRING)
+ * @NFTA_EXPR_DATA: type specific data (NLA_NESTED)
+ */
+enum nft_expr_attributes {
+	NFTA_EXPR_UNSPEC,
+	NFTA_EXPR_NAME,
+	NFTA_EXPR_DATA,
+	__NFTA_EXPR_MAX
+};
+#define NFTA_EXPR_MAX		(__NFTA_EXPR_MAX - 1)
+
+/**
+ * enum nft_immediate_attributes - nf_tables immediate expression netlink attributes
+ *
+ * @NFTA_IMMEDIATE_DREG: destination register to load data into (NLA_U32)
+ * @NFTA_IMMEDIATE_DATA: data to load (NLA_NESTED: nft_data_attributes)
+ */
+enum nft_immediate_attributes {
+	NFTA_IMMEDIATE_UNSPEC,
+	NFTA_IMMEDIATE_DREG,
+	NFTA_IMMEDIATE_DATA,
+	__NFTA_IMMEDIATE_MAX
+};
+#define NFTA_IMMEDIATE_MAX	(__NFTA_IMMEDIATE_MAX - 1)
+
+/**
+ * enum nft_bitwise_attributes - nf_tables bitwise expression netlink attributes
+ *
+ * @NFTA_BITWISE_SREG: source register (NLA_U32: nft_registers)
+ * @NFTA_BITWISE_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_BITWISE_LEN: length of operands (NLA_U32)
+ * @NFTA_BITWISE_MASK: mask value (NLA_NESTED: nft_data_attributes)
+ * @NFTA_BITWISE_XOR: xor value (NLA_NESTED: nft_data_attributes)
+ *
+ * The bitwise expression performs the following operation:
+ *
+ * dreg = (sreg & mask) ^ xor
+ *
+ * which allow to express all bitwise operations:
+ *
+ * 		mask	xor
+ * NOT:		1	1
+ * OR:		0	x
+ * XOR:		1	x
+ * AND:		x	0
+ */
+enum nft_bitwise_attributes {
+	NFTA_BITWISE_UNSPEC,
+	NFTA_BITWISE_SREG,
+	NFTA_BITWISE_DREG,
+	NFTA_BITWISE_LEN,
+	NFTA_BITWISE_MASK,
+	NFTA_BITWISE_XOR,
+	__NFTA_BITWISE_MAX
+};
+#define NFTA_BITWISE_MAX	(__NFTA_BITWISE_MAX - 1)
+
+/**
+ * enum nft_byteorder_ops - nf_tables byteorder operators
+ *
+ * @NFT_BYTEORDER_NTOH: network to host operator
+ * @NFT_BYTEORDER_HTON: host to network opertaor
+ */
+enum nft_byteorder_ops {
+	NFT_BYTEORDER_NTOH,
+	NFT_BYTEORDER_HTON,
+};
+
+/**
+ * enum nft_byteorder_attributes - nf_tables byteorder expression netlink attributes
+ *
+ * @NFTA_BYTEORDER_SREG: source register (NLA_U32: nft_registers)
+ * @NFTA_BYTEORDER_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_BYTEORDER_OP: operator (NLA_U32: enum nft_byteorder_ops)
+ * @NFTA_BYTEORDER_LEN: length of the data (NLA_U32)
+ * @NFTA_BYTEORDER_SIZE: data size in bytes (NLA_U32: 2 or 4)
+ */
+enum nft_byteorder_attributes {
+	NFTA_BYTEORDER_UNSPEC,
+	NFTA_BYTEORDER_SREG,
+	NFTA_BYTEORDER_DREG,
+	NFTA_BYTEORDER_OP,
+	NFTA_BYTEORDER_LEN,
+	NFTA_BYTEORDER_SIZE,
+	__NFTA_BYTEORDER_MAX
+};
+#define NFTA_BYTEORDER_MAX	(__NFTA_BYTEORDER_MAX - 1)
+
+/**
+ * enum nft_cmp_ops - nf_tables relational operator
+ *
+ * @NFT_CMP_EQ: equal
+ * @NFT_CMP_NEQ: not equal
+ * @NFT_CMP_LT: less than
+ * @NFT_CMP_LTE: less than or equal to
+ * @NFT_CMP_GT: greater than
+ * @NFT_CMP_GTE: greater than or equal to
+ */
+enum nft_cmp_ops {
+	NFT_CMP_EQ,
+	NFT_CMP_NEQ,
+	NFT_CMP_LT,
+	NFT_CMP_LTE,
+	NFT_CMP_GT,
+	NFT_CMP_GTE,
+};
+
+/**
+ * enum nft_cmp_attributes - nf_tables cmp expression netlink attributes
+ *
+ * @NFTA_CMP_SREG: source register of data to compare (NLA_U32: nft_registers)
+ * @NFTA_CMP_OP: cmp operation (NLA_U32: nft_cmp_ops)
+ * @NFTA_CMP_DATA: data to compare against (NLA_NESTED: nft_data_attributes)
+ */
+enum nft_cmp_attributes {
+	NFTA_CMP_UNSPEC,
+	NFTA_CMP_SREG,
+	NFTA_CMP_OP,
+	NFTA_CMP_DATA,
+	__NFTA_CMP_MAX
+};
+#define NFTA_CMP_MAX		(__NFTA_CMP_MAX - 1)
+
+enum nft_set_elem_flags {
+	NFT_SE_INTERVAL_END	= 0x1,
+};
+
+enum nft_set_elem_attributes {
+	NFTA_SE_UNSPEC,
+	NFTA_SE_KEY,
+	NFTA_SE_DATA,
+	NFTA_SE_FLAGS,
+	__NFTA_SE_MAX
+};
+#define NFTA_SE_MAX		(__NFTA_SE_MAX - 1)
+
+enum nft_set_flags {
+	NFT_SET_INTERVAL	= 0x1,
+	NFT_SET_MAP		= 0x2,
+};
+
+enum nft_set_attributes {
+	NFTA_SET_UNSPEC,
+	NFTA_SET_FLAGS,
+	NFTA_SET_SREG,
+	NFTA_SET_DREG,
+	NFTA_SET_KLEN,
+	NFTA_SET_DLEN,
+	NFTA_SET_ELEMENTS,
+	__NFTA_SET_MAX
+};
+#define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
+
+enum nft_hash_flags {
+	NFT_HASH_MAP		= 0x1,
+};
+
+enum nft_hash_elem_attributes {
+	NFTA_HE_UNSPEC,
+	NFTA_HE_KEY,
+	NFTA_HE_DATA,
+	__NFTA_HE_MAX
+};
+#define NFTA_HE_MAX		(__NFTA_HE_MAX - 1)
+
+enum nft_hash_attributes {
+	NFTA_HASH_UNSPEC,
+	NFTA_HASH_FLAGS,
+	NFTA_HASH_SREG,
+	NFTA_HASH_DREG,
+	NFTA_HASH_KLEN,
+	NFTA_HASH_ELEMENTS,
+	__NFTA_HASH_MAX
+};
+#define NFTA_HASH_MAX		(__NFTA_HASH_MAX - 1)
+
+/**
+ * enum nft_payload_bases - nf_tables payload expression offset bases
+ *
+ * @NFT_PAYLOAD_LL_HEADER: link layer header
+ * @NFT_PAYLOAD_NETWORK_HEADER: network header
+ * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header
+ */
+enum nft_payload_bases {
+	NFT_PAYLOAD_LL_HEADER,
+	NFT_PAYLOAD_NETWORK_HEADER,
+	NFT_PAYLOAD_TRANSPORT_HEADER,
+};
+
+/**
+ * enum nft_payload_attributes - nf_tables payload expression netlink attributes
+ *
+ * @NFTA_PAYLOAD_DREG: destination register to load data into (NLA_U32: nft_registers)
+ * @NFTA_PAYLOAD_BASE: payload base (NLA_U32: nft_payload_bases)
+ * @NFTA_PAYLOAD_OFFSET: payload offset relative to base (NLA_U32)
+ * @NFTA_PAYLOAD_LEN: payload length (NLA_U32)
+ */
+enum nft_payload_attributes {
+	NFTA_PAYLOAD_UNSPEC,
+	NFTA_PAYLOAD_DREG,
+	NFTA_PAYLOAD_BASE,
+	NFTA_PAYLOAD_OFFSET,
+	NFTA_PAYLOAD_LEN,
+	__NFTA_PAYLOAD_MAX
+};
+#define NFTA_PAYLOAD_MAX	(__NFTA_PAYLOAD_MAX - 1)
+
+/**
+ * enum nft_exthdr_attributes - nf_tables IPv6 extension header expression netlink attributes
+ *
+ * @NFTA_EXTHDR_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_EXTHDR_TYPE: extension header type (NLA_U8)
+ * @NFTA_EXTHDR_OFFSET: extension header offset (NLA_U32)
+ * @NFTA_EXTHDR_LEN: extension header length (NLA_U32)
+ */
+enum nft_exthdr_attributes {
+	NFTA_EXTHDR_UNSPEC,
+	NFTA_EXTHDR_DREG,
+	NFTA_EXTHDR_TYPE,
+	NFTA_EXTHDR_OFFSET,
+	NFTA_EXTHDR_LEN,
+	__NFTA_EXTHDR_MAX
+};
+#define NFTA_EXTHDR_MAX		(__NFTA_EXTHDR_MAX - 1)
+
+/**
+ * enum nft_meta_keys - nf_tables meta expression keys
+ *
+ * @NFT_META_LEN: packet length (skb->len)
+ * @NFT_META_PROTOCOL: packet ethertype protocol (skb->protocol), invalid in OUTPUT
+ * @NFT_META_PRIORITY: packet priority (skb->priority)
+ * @NFT_META_MARK: packet mark (skb->mark)
+ * @NFT_META_IIF: packet input interface index (dev->ifindex)
+ * @NFT_META_OIF: packet output interface index (dev->ifindex)
+ * @NFT_META_IIFNAME: packet input interface name (dev->name)
+ * @NFT_META_OIFNAME: packet output interface name (dev->name)
+ * @NFT_META_IIFTYPE: packet input interface type (dev->type)
+ * @NFT_META_OIFTYPE: packet output interface type (dev->type)
+ * @NFT_META_SKUID: originating socket UID (fsuid)
+ * @NFT_META_SKGID: originating socket GID (fsgid)
+ * @NFT_META_NFTRACE: packet nftrace bit
+ * @NFT_META_RTCLASSID: realm value of packet's route (skb->dst->tclassid)
+ * @NFT_META_SECMARK: packet secmark (skb->secmark)
+ */
+enum nft_meta_keys {
+	NFT_META_LEN,
+	NFT_META_PROTOCOL,
+	NFT_META_PRIORITY,
+	NFT_META_MARK,
+	NFT_META_IIF,
+	NFT_META_OIF,
+	NFT_META_IIFNAME,
+	NFT_META_OIFNAME,
+	NFT_META_IIFTYPE,
+	NFT_META_OIFTYPE,
+	NFT_META_SKUID,
+	NFT_META_SKGID,
+	NFT_META_NFTRACE,
+	NFT_META_RTCLASSID,
+	NFT_META_SECMARK,
+};
+
+/**
+ * enum nft_meta_attributes - nf_tables meta expression netlink attributes
+ *
+ * @NFTA_META_DREG: destination register (NLA_U32)
+ * @NFTA_META_KEY: meta data item to load (NLA_U32: nft_meta_keys)
+ */
+enum nft_meta_attributes {
+	NFTA_META_UNSPEC,
+	NFTA_META_DREG,
+	NFTA_META_KEY,
+	__NFTA_META_MAX
+};
+#define NFTA_META_MAX		(__NFTA_META_MAX - 1)
+
+/**
+ * enum nft_ct_keys - nf_tables ct expression keys
+ *
+ * @NFT_CT_STATE: conntrack state (bitmask of enum ip_conntrack_info)
+ * @NFT_CT_DIRECTION: conntrack direction (enum ip_conntrack_dir)
+ * @NFT_CT_STATUS: conntrack status (bitmask of enum ip_conntrack_status)
+ * @NFT_CT_MARK: conntrack mark value
+ * @NFT_CT_SECMARK: conntrack secmark value
+ * @NFT_CT_EXPIRATION: relative conntrack expiration time in ms
+ * @NFT_CT_HELPER: connection tracking helper assigned to conntrack
+ * @NFT_CT_L3PROTOCOL: conntrack layer 3 protocol
+ * @NFT_CT_SRC: conntrack layer 3 protocol source (IPv4/IPv6 address)
+ * @NFT_CT_DST: conntrack layer 3 protocol destination (IPv4/IPv6 address)
+ * @NFT_CT_PROTOCOL: conntrack layer 4 protocol
+ * @NFT_CT_PROTO_SRC: conntrack layer 4 protocol source
+ * @NFT_CT_PROTO_DST: conntrack layer 4 protocol destination
+ */
+enum nft_ct_keys {
+	NFT_CT_STATE,
+	NFT_CT_DIRECTION,
+	NFT_CT_STATUS,
+	NFT_CT_MARK,
+	NFT_CT_SECMARK,
+	NFT_CT_EXPIRATION,
+	NFT_CT_HELPER,
+	NFT_CT_L3PROTOCOL,
+	NFT_CT_SRC,
+	NFT_CT_DST,
+	NFT_CT_PROTOCOL,
+	NFT_CT_PROTO_SRC,
+	NFT_CT_PROTO_DST,
+};
+
+/**
+ * enum nft_ct_attributes - nf_tables ct expression netlink attributes
+ *
+ * @NFTA_CT_DREG: destination register (NLA_U32)
+ * @NFTA_CT_KEY: conntrack data item to load (NLA_U32: nft_ct_keys)
+ * @NFTA_CT_DIRECTION: direction in case of directional keys (NLA_U8)
+ */
+enum nft_ct_attributes {
+	NFTA_CT_UNSPEC,
+	NFTA_CT_DREG,
+	NFTA_CT_KEY,
+	NFTA_CT_DIRECTION,
+	__NFTA_CT_MAX
+};
+#define NFTA_CT_MAX		(__NFTA_CT_MAX - 1)
+
+/**
+ * enum nft_limit_attributes - nf_tables limit expression netlink attributes
+ *
+ * @NFTA_LIMIT_RATE: refill rate (NLA_U64)
+ * @NFTA_LIMIT_UNIT: refill unit (NLA_U64)
+ */
+enum nft_limit_attributes {
+	NFTA_LIMIT_UNSPEC,
+	NFTA_LIMIT_RATE,
+	NFTA_LIMIT_UNIT,
+	__NFTA_LIMIT_MAX
+};
+#define NFTA_LIMIT_MAX		(__NFTA_LIMIT_MAX - 1)
+
+/**
+ * enum nft_counter_attributes - nf_tables counter expression netlink attributes
+ *
+ * @NFTA_COUNTER_BYTES: number of bytes (NLA_U64)
+ * @NFTA_COUNTER_PACKETS: number of packets (NLA_U64)
+ */
+enum nft_counter_attributes {
+	NFTA_COUNTER_UNSPEC,
+	NFTA_COUNTER_BYTES,
+	NFTA_COUNTER_PACKETS,
+	__NFTA_COUNTER_MAX
+};
+#define NFTA_COUNTER_MAX	(__NFTA_COUNTER_MAX - 1)
+
+/**
+ * enum nft_log_attributes - nf_tables log expression netlink attributes
+ *
+ * @NFTA_LOG_GROUP: netlink group to send messages to (NLA_U32)
+ * @NFTA_LOG_PREFIX: prefix to prepend to log messages (NLA_STRING)
+ * @NFTA_LOG_SNAPLEN: length of payload to include in netlink message (NLA_U32)
+ * @NFTA_LOG_QTHRESHOLD: queue threshold (NLA_U32)
+ */
+enum nft_log_attributes {
+	NFTA_LOG_UNSPEC,
+	NFTA_LOG_GROUP,
+	NFTA_LOG_PREFIX,
+	NFTA_LOG_SNAPLEN,
+	NFTA_LOG_QTHRESHOLD,
+	__NFTA_LOG_MAX
+};
+#define NFTA_LOG_MAX		(__NFTA_LOG_MAX - 1)
+
+/**
+ * enum nft_reject_types - nf_tables reject expression reject types
+ *
+ * @NFT_REJECT_ICMP_UNREACH: reject using ICMP unreachable
+ * @NFT_REJECT_TCP_RST: reject using TCP RST
+ */
+enum nft_reject_types {
+	NFT_REJECT_ICMP_UNREACH,
+	NFT_REJECT_TCP_RST,
+};
+
+/**
+ * enum nft_reject_attributes - nf_tables reject expression netlink attributes
+ *
+ * @NFTA_REJECT_TYPE: packet type to use (NLA_U32: nft_reject_types)
+ * @NFTA_REJECT_ICMP_CODE: ICMP code to use (NLA_U8)
+ */
+enum nft_reject_attributes {
+	NFTA_REJECT_UNSPEC,
+	NFTA_REJECT_TYPE,
+	NFTA_REJECT_ICMP_CODE,
+	__NFTA_REJECT_MAX
+};
+#define NFTA_REJECT_MAX		(__NFTA_REJECT_MAX - 1)
+
+/**
+ * enum nft_nat_types - nf_tables nat expression NAT types
+ *
+ * @NFT_NAT_SNAT: source NAT
+ * @NFT_NAT_DNAT: destination NAT
+ */
+enum nft_nat_types {
+	NFT_NAT_SNAT,
+	NFT_NAT_DNAT,
+};
+
+/**
+ * enum nft_nat_attributes - nf_tables nat expression netlink attributes
+ *
+ * @NFTA_NAT_TYPE: NAT type (NLA_U32: nft_nat_types)
+ * @NFTA_NAT_ADDR_MIN: source register of address range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ */
+enum nft_nat_attributes {
+	NFTA_NAT_UNSPEC,
+	NFTA_NAT_TYPE,
+	NFTA_NAT_ADDR_MIN,
+	NFTA_NAT_ADDR_MAX,
+	NFTA_NAT_PROTO_MIN,
+	NFTA_NAT_PROTO_MAX,
+	__NFTA_NAT_MAX
+};
+#define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
+
+#endif /* _LINUX_NF_TABLES_H */
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index 4a4efafad5f4..d276c3bd55b8 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -18,6 +18,8 @@ enum nfnetlink_groups {
 #define NFNLGRP_CONNTRACK_EXP_UPDATE	NFNLGRP_CONNTRACK_EXP_UPDATE
 	NFNLGRP_CONNTRACK_EXP_DESTROY,
 #define NFNLGRP_CONNTRACK_EXP_DESTROY	NFNLGRP_CONNTRACK_EXP_DESTROY
+	NFNLGRP_NFTABLES,
+#define NFNLGRP_NFTABLES                NFNLGRP_NFTABLES
 	__NFNLGRP_MAX,
 };
 #define NFNLGRP_MAX	(__NFNLGRP_MAX - 1)
@@ -51,6 +53,7 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_ACCT		7
 #define NFNL_SUBSYS_CTNETLINK_TIMEOUT	8
 #define NFNL_SUBSYS_CTHELPER		9
-#define NFNL_SUBSYS_COUNT		10
+#define NFNL_SUBSYS_NFTABLES		10
+#define NFNL_SUBSYS_COUNT		11
 
 #endif /* _UAPI_NFNETLINK_H */
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index a9aff9c7d027..68f8128147be 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -1,6 +1,9 @@
 #
 # Bridge netfilter configuration
 #
+#
+config NF_TABLES_BRIDGE
+	tristate "Ethernet Bridge nf_tables support"
 
 menuconfig BRIDGE_NF_EBTABLES
 	tristate "Ethernet Bridge tables (ebtables) support"
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index 0718699540b0..ea7629f58b3d 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -2,6 +2,8 @@
 # Makefile for the netfilter modules for Link Layer filtering on a bridge.
 #
 
+obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o
+
 obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
 
 # tables
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
new file mode 100644
index 000000000000..bc5c21c911c0
--- /dev/null
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter_bridge.h>
+#include <net/netfilter/nf_tables.h>
+
+static struct nft_af_info nft_af_bridge __read_mostly = {
+	.family		= NFPROTO_BRIDGE,
+	.nhooks		= NF_BR_NUMHOOKS,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nf_tables_bridge_init(void)
+{
+	return nft_register_afinfo(&nft_af_bridge);
+}
+
+static void __exit nf_tables_bridge_exit(void)
+{
+	nft_unregister_afinfo(&nft_af_bridge);
+}
+
+module_init(nf_tables_bridge_init);
+module_exit(nf_tables_bridge_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_BRIDGE);
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 1657e39b291f..eb1d56ece361 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -36,6 +36,22 @@ config NF_CONNTRACK_PROC_COMPAT
 
 	  If unsure, say Y.
 
+config NF_TABLES_IPV4
+	depends on NF_TABLES
+	tristate "IPv4 nf_tables support"
+
+config NFT_REJECT_IPV4
+	depends on NF_TABLES_IPV4
+	tristate "nf_tables IPv4 reject support"
+
+config NF_TABLE_ROUTE_IPV4
+	depends on NF_TABLES_IPV4
+	tristate "IPv4 nf_tables route table support"
+
+config NF_TABLE_NAT_IPV4
+	depends on NF_TABLES_IPV4
+	tristate "IPv4 nf_tables nat table support"
+
 config IP_NF_IPTABLES
 	tristate "IP tables support (required for filtering/masq/NAT)"
 	default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 3622b248b6dd..b2f01cd2cd65 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -27,6 +27,11 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
 
+obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NF_TABLE_ROUTE_IPV4) += nf_table_route_ipv4.o
+obj-$(CONFIG_NF_TABLE_NAT_IPV4) += nf_table_nat_ipv4.o
+
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
 
diff --git a/net/ipv4/netfilter/nf_table_nat_ipv4.c b/net/ipv4/netfilter/nf_table_nat_ipv4.c
new file mode 100644
index 000000000000..2a6f184c10bd
--- /dev/null
+++ b/net/ipv4/netfilter/nf_table_nat_ipv4.c
@@ -0,0 +1,409 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/ip.h>
+
+struct nft_nat {
+	enum nft_registers	sreg_addr_min:8;
+	enum nft_registers	sreg_addr_max:8;
+	enum nft_registers	sreg_proto_min:8;
+	enum nft_registers	sreg_proto_max:8;
+	enum nf_nat_manip_type	type;
+};
+
+static void nft_nat_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
+	struct nf_nat_range range;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_addr_min) {
+		range.min_addr.ip = data[priv->sreg_addr_min].data[0];
+		range.max_addr.ip = data[priv->sreg_addr_max].data[0];
+		range.flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = data[priv->sreg_proto_min].data[0];
+		range.max_proto.all = data[priv->sreg_proto_max].data[0];
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	data[NFT_REG_VERDICT].verdict =
+		nf_nat_setup_info(ct, &range, priv->type);
+}
+
+static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
+	[NFTA_NAT_ADDR_MIN]	= { .type = NLA_U32 },
+	[NFTA_NAT_ADDR_MAX]	= { .type = NLA_U32 },
+	[NFTA_NAT_PROTO_MIN]	= { .type = NLA_U32 },
+	[NFTA_NAT_PROTO_MAX]	= { .type = NLA_U32 },
+	[NFTA_NAT_TYPE]		= { .type = NLA_U32 },
+};
+
+static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_NAT_TYPE] == NULL)
+		return -EINVAL;
+
+	switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
+	case NFT_NAT_SNAT:
+		priv->type = NF_NAT_MANIP_SRC;
+		break;
+	case NFT_NAT_DNAT:
+		priv->type = NF_NAT_MANIP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (tb[NFTA_NAT_ADDR_MIN]) {
+		priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN]));
+		err = nft_validate_input_register(priv->sreg_addr_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_ADDR_MAX]) {
+		priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX]));
+		err = nft_validate_input_register(priv->sreg_addr_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_addr_max = priv->sreg_addr_min;
+
+	if (tb[NFTA_NAT_PROTO_MIN]) {
+		priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN]));
+		err = nft_validate_input_register(priv->sreg_proto_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_PROTO_MAX]) {
+		priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX]));
+		err = nft_validate_input_register(priv->sreg_proto_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_proto_max = priv->sreg_proto_min;
+
+	return 0;
+}
+
+static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NF_NAT_MANIP_SRC:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
+			goto nla_put_failure;
+		break;
+	case NF_NAT_MANIP_DST:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
+			goto nla_put_failure;
+		break;
+	}
+
+	if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_nat_ops __read_mostly = {
+	.name		= "nat",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_nat_eval,
+	.init		= nft_nat_init,
+	.dump		= nft_nat_dump,
+	.policy		= nft_nat_policy,
+	.maxattr	= NFTA_NAT_MAX,
+};
+
+/*
+ * NAT table
+ */
+
+static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
+			      struct sk_buff *skb,
+			      const struct net_device *in,
+			      const struct net_device *out,
+			      int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	unsigned int ret;
+
+	if (ct == NULL || nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
+
+	nat = nfct_nat(ct);
+	if (nat == NULL) {
+		/* Conntrack module was loaded late, can't add extension. */
+		if (nf_ct_is_confirmed(ct))
+			return NF_ACCEPT;
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+		if (nat == NULL)
+			return NF_ACCEPT;
+	}
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED + IP_CT_IS_REPLY:
+		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   ops->hooknum))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall through */
+	case IP_CT_NEW:
+		if (nf_nat_initialized(ct, maniptype))
+			break;
+
+		ret = nft_do_chain(ops, skb, in, out, okfn);
+		if (ret != NF_ACCEPT)
+			return ret;
+		if (!nf_nat_initialized(ct, maniptype)) {
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		}
+	default:
+		break;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+}
+
+static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	__be32 daddr = ip_hdr(skb)->daddr;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ip_hdr(skb)->daddr != daddr) {
+		skb_dst_drop(skb);
+	}
+	return ret;
+}
+
+static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops,
+				       struct sk_buff *skb,
+				       const struct net_device *in,
+				       const struct net_device *out,
+				       int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo __maybe_unused;
+	const struct nf_conn *ct __maybe_unused;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.src.u3.ip !=
+		    ct->tuplehash[!dir].tuple.dst.u3.ip ||
+		    ct->tuplehash[dir].tuple.src.u.all !=
+		    ct->tuplehash[!dir].tuple.dst.u.all)
+			return nf_xfrm_me_harder(skb, AF_INET) == 0 ?
+								ret : NF_DROP;
+	}
+#endif
+	return ret;
+}
+
+static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	const struct nf_conn *ct;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+		    ct->tuplehash[!dir].tuple.src.u3.ip) {
+			if (ip_route_me_harder(skb, RTN_UNSPEC))
+				ret = NF_DROP;
+		}
+#ifdef CONFIG_XFRM
+		else if (ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all)
+			if (nf_xfrm_me_harder(skb, AF_INET))
+				ret = NF_DROP;
+#endif
+	}
+	return ret;
+}
+
+static struct nft_base_chain nf_chain_nat_prerouting __read_mostly = {
+	.chain	= {
+		.name		= "PREROUTING",
+		.rules		= LIST_HEAD_INIT(nf_chain_nat_prerouting.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_nat_prerouting,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP_PRI_NAT_DST,
+		.priv		= &nf_chain_nat_prerouting.chain,
+	},
+};
+
+static struct nft_base_chain nf_chain_nat_postrouting __read_mostly = {
+	.chain	= {
+		.name		= "POSTROUTING",
+		.rules		= LIST_HEAD_INIT(nf_chain_nat_postrouting.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_nat_postrouting,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_NAT_SRC,
+		.priv		= &nf_chain_nat_postrouting.chain,
+	},
+};
+
+static struct nft_base_chain nf_chain_nat_output __read_mostly = {
+	.chain	= {
+		.name		= "OUTPUT",
+		.rules		= LIST_HEAD_INIT(nf_chain_nat_output.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_nat_output,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP_PRI_NAT_DST,
+		.priv		= &nf_chain_nat_output.chain,
+	},
+};
+
+static struct nft_base_chain nf_chain_nat_input __read_mostly = {
+	.chain	= {
+		.name		= "INPUT",
+		.rules		= LIST_HEAD_INIT(nf_chain_nat_input.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_nat_fn,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_NAT_SRC,
+		.priv		= &nf_chain_nat_input.chain,
+	},
+};
+
+
+static struct nft_table nf_table_nat_ipv4 __read_mostly = {
+	.name	= "nat",
+	.chains	= LIST_HEAD_INIT(nf_table_nat_ipv4.chains),
+};
+
+static int __init nf_table_nat_init(void)
+{
+	int err;
+
+	list_add_tail(&nf_chain_nat_prerouting.chain.list,
+		      &nf_table_nat_ipv4.chains);
+	list_add_tail(&nf_chain_nat_postrouting.chain.list,
+		      &nf_table_nat_ipv4.chains);
+	list_add_tail(&nf_chain_nat_output.chain.list,
+		      &nf_table_nat_ipv4.chains);
+	list_add_tail(&nf_chain_nat_input.chain.list,
+		      &nf_table_nat_ipv4.chains);
+
+	err = nft_register_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
+	if (err < 0)
+		goto err1;
+
+	err = nft_register_expr(&nft_nat_ops);
+	if (err < 0)
+		goto err2;
+
+	return 0;
+
+err2:
+	nft_unregister_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
+err1:
+	return err;
+}
+
+static void __exit nf_table_nat_exit(void)
+{
+	nft_unregister_expr(&nft_nat_ops);
+	nft_unregister_table(&nf_table_nat_ipv4, AF_INET);
+}
+
+module_init(nf_table_nat_init);
+module_exit(nf_table_nat_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET, "nat");
+MODULE_ALIAS_NFT_EXPR("nat");
diff --git a/net/ipv4/netfilter/nf_table_route_ipv4.c b/net/ipv4/netfilter/nf_table_route_ipv4.c
new file mode 100644
index 000000000000..4f257a1ed661
--- /dev/null
+++ b/net/ipv4/netfilter/nf_table_route_ipv4.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	u32 mark;
+	__be32 saddr, daddr;
+	u_int8_t tos;
+	const struct iphdr *iph;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	mark = skb->mark;
+	iph = ip_hdr(skb);
+	saddr = iph->saddr;
+	daddr = iph->daddr;
+	tos = iph->tos;
+
+	ret = nft_do_chain(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_QUEUE) {
+		iph = ip_hdr(skb);
+
+		if (iph->saddr != saddr ||
+		    iph->daddr != daddr ||
+		    skb->mark != mark ||
+		    iph->tos != tos)
+			if (ip_route_me_harder(skb, RTN_UNSPEC))
+				ret = NF_DROP;
+	}
+	return ret;
+}
+
+static struct nft_base_chain nf_chain_route_output __read_mostly = {
+	.chain	= {
+		.name		= "OUTPUT",
+		.rules		= LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_route_table_hook,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP_PRI_MANGLE,
+		.priv		= &nf_chain_route_output.chain,
+	},
+};
+
+static struct nft_table nf_table_route_ipv4 __read_mostly = {
+	.name	= "route",
+	.chains	= LIST_HEAD_INIT(nf_table_route_ipv4.chains),
+};
+
+static int __init nf_table_route_init(void)
+{
+	list_add_tail(&nf_chain_route_output.chain.list,
+		      &nf_table_route_ipv4.chains);
+	return nft_register_table(&nf_table_route_ipv4, NFPROTO_IPV4);
+}
+
+static void __exit nf_table_route_exit(void)
+{
+	nft_unregister_table(&nf_table_route_ipv4, NFPROTO_IPV4);
+}
+
+module_init(nf_table_route_init);
+module_exit(nf_table_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET, "route");
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
new file mode 100644
index 000000000000..63d0a3bf53d3
--- /dev/null
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/ip.h>
+
+static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
+{
+	if (unlikely(skb->len < sizeof(struct iphdr) ||
+		     ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) {
+		if (net_ratelimit())
+			pr_info("nf_tables_ipv4: ignoring short SOCK_RAW "
+				"packet\n");
+		return NF_ACCEPT;
+	}
+
+	return nft_do_chain(ops, skb, in, out, okfn);
+}
+
+static struct nft_af_info nft_af_ipv4 __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.nhooks		= NF_INET_NUMHOOKS,
+	.owner		= THIS_MODULE,
+	.hooks		= {
+		[NF_INET_LOCAL_OUT]	= nft_ipv4_output,
+	},
+};
+
+static int __init nf_tables_ipv4_init(void)
+{
+	return nft_register_afinfo(&nft_af_ipv4);
+}
+
+static void __exit nf_tables_ipv4_exit(void)
+{
+	nft_unregister_afinfo(&nft_af_ipv4);
+}
+
+module_init(nf_tables_ipv4_init);
+module_exit(nf_tables_ipv4_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_INET);
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
new file mode 100644
index 000000000000..b4ee8d3bb1e4
--- /dev/null
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/icmp.h>
+
+struct nft_reject {
+	enum nft_reject_types	type:8;
+	u8			icmp_code;
+};
+
+static void nft_reject_eval(const struct nft_expr *expr,
+			      struct nft_data data[NFT_REG_MAX + 1],
+			      const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		icmp_send(pkt->skb, ICMP_DEST_UNREACH, priv->icmp_code, 0);
+		break;
+	case NFT_REJECT_TCP_RST:
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+
+static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
+	[NFTA_REJECT_ICMP_CODE]		= { .type = NLA_U8 },
+};
+
+static int nft_reject_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_REJECT_TYPE] == NULL)
+		return -EINVAL;
+
+	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
+			return -EINVAL;
+		priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+	case NFT_REJECT_TCP_RST:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_reject *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type))
+		goto nla_put_failure;
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
+			goto nla_put_failure;
+		break;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops reject_ops __read_mostly = {
+	.name		= "reject",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_reject_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+};
+
+static int __init nft_reject_module_init(void)
+{
+	return nft_register_expr(&reject_ops);
+}
+
+static void __exit nft_reject_module_exit(void)
+{
+	nft_unregister_expr(&reject_ops);
+}
+
+module_init(nft_reject_module_init);
+module_exit(nft_reject_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("reject");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index a7f842b29b67..5677e38eeca3 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -25,6 +25,14 @@ config NF_CONNTRACK_IPV6
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NF_TABLES_IPV6
+	depends on NF_TABLES
+	tristate "IPv6 nf_tables support"
+
+config NF_TABLE_ROUTE_IPV6
+	depends on NF_TABLES_IPV6
+	tristate "IPv6 nf_tables route table support"
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 2b53738f798c..956af4492d10 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -23,6 +23,10 @@ obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
 nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
 obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 
+# nf_tables
+obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
+obj-$(CONFIG_NF_TABLE_ROUTE_IPV6) += nf_table_route_ipv6.o
+
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
 obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_table_route_ipv6.c b/net/ipv6/netfilter/nf_table_route_ipv6.c
new file mode 100644
index 000000000000..48ac65c7b398
--- /dev/null
+++ b/net/ipv6/netfilter/nf_table_route_ipv6.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	struct in6_addr saddr, daddr;
+	u_int8_t hop_limit;
+	u32 mark, flowlabel;
+
+	/* save source/dest address, mark, hoplimit, flowlabel, priority */
+	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+	mark = skb->mark;
+	hop_limit = ipv6_hdr(skb)->hop_limit;
+
+	/* flowlabel and prio (includes version, which shouldn't change either */
+	flowlabel = *((u32 *)ipv6_hdr(skb));
+
+	ret = nft_do_chain(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_QUEUE &&
+	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+	     skb->mark != mark ||
+	     ipv6_hdr(skb)->hop_limit != hop_limit ||
+	     flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
+		return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP;
+
+	return ret;
+}
+
+static struct nft_base_chain nf_chain_route_output __read_mostly = {
+	.chain	= {
+		.name		= "OUTPUT",
+		.rules		= LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
+		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
+	},
+	.ops	= {
+		.hook		= nf_route_table_hook,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_MANGLE,
+		.priv		= &nf_chain_route_output.chain,
+	},
+};
+
+static struct nft_table nf_table_route_ipv6 __read_mostly = {
+	.name	= "route",
+	.chains	= LIST_HEAD_INIT(nf_table_route_ipv6.chains),
+};
+
+static int __init nf_table_route_init(void)
+{
+	list_add_tail(&nf_chain_route_output.chain.list,
+		      &nf_table_route_ipv6.chains);
+	return nft_register_table(&nf_table_route_ipv6, NFPROTO_IPV6);
+}
+
+static void __exit nf_table_route_exit(void)
+{
+	nft_unregister_table(&nf_table_route_ipv6, NFPROTO_IPV6);
+}
+
+module_init(nf_table_route_init);
+module_exit(nf_table_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_TABLE(AF_INET6, "route");
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
new file mode 100644
index 000000000000..e0717cea4913
--- /dev/null
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_tables.h>
+
+static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
+{
+	if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
+		if (net_ratelimit())
+			pr_info("nf_tables_ipv6: ignoring short SOCK_RAW "
+				"packet\n");
+		return NF_ACCEPT;
+	}
+
+	return nft_do_chain(ops, skb, in, out, okfn);
+}
+
+static struct nft_af_info nft_af_ipv6 __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.nhooks		= NF_INET_NUMHOOKS,
+	.owner		= THIS_MODULE,
+	.hooks		= {
+		[NF_INET_LOCAL_OUT]	= nft_ipv6_output,
+	},
+};
+
+static int __init nf_tables_ipv6_init(void)
+{
+	return nft_register_afinfo(&nft_af_ipv6);
+}
+
+static void __exit nf_tables_ipv6_exit(void)
+{
+	nft_unregister_afinfo(&nft_af_ipv6);
+}
+
+module_init(nf_tables_ipv6_init);
+module_exit(nf_tables_ipv6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(AF_INET6);
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6e839b6dff2b..c271e1af93b5 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -413,6 +413,43 @@ config NETFILTER_SYNPROXY
 
 endif # NF_CONNTRACK
 
+config NF_TABLES
+	depends on NETFILTER_NETLINK
+	tristate "Netfilter nf_tables support"
+
+config NFT_EXTHDR
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables IPv6 exthdr module"
+
+config NFT_META
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables meta module"
+
+config NFT_CT
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	tristate "Netfilter nf_tables conntrack module"
+
+config NFT_SET
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables set module"
+
+config NFT_HASH
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables hash module"
+
+config NFT_COUNTER
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables counter module"
+
+config NFT_LOG
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables log module"
+
+config NFT_LIMIT
+	depends on NF_TABLES
+	tristate "Netfilter nf_tables limit module"
+
 config NETFILTER_XTABLES
 	tristate "Netfilter Xtables support (required for ip_tables)"
 	default m if NETFILTER_ADVANCED=n
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index c3a0a12907f6..1ca3f3932826 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -64,6 +64,22 @@ obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
 # SYNPROXY
 obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
 
+# nf_tables
+nf_tables-objs += nf_tables_core.o nf_tables_api.o
+nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
+nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
+
+obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
+obj-$(CONFIG_NFT_META)		+= nft_meta.o
+obj-$(CONFIG_NFT_CT)		+= nft_ct.o
+obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
+#nf_tables-objs			+= nft_meta_target.o
+obj-$(CONFIG_NFT_SET)		+= nft_set.o
+obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
+obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
+obj-$(CONFIG_NFT_LOG)		+= nft_log.o
+
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
new file mode 100644
index 000000000000..7d59c89c6c75
--- /dev/null
+++ b/net/netfilter/nf_tables_api.c
@@ -0,0 +1,1760 @@
+/*
+ * Copyright (c) 2007, 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/sock.h>
+
+static LIST_HEAD(nf_tables_afinfo);
+static LIST_HEAD(nf_tables_expressions);
+
+/**
+ *	nft_register_afinfo - register nf_tables address family info
+ *
+ *	@afi: address family info to register
+ *
+ *	Register the address family for use with nf_tables. Returns zero on
+ *	success or a negative errno code otherwise.
+ */
+int nft_register_afinfo(struct nft_af_info *afi)
+{
+	INIT_LIST_HEAD(&afi->tables);
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_add_tail(&afi->list, &nf_tables_afinfo);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_register_afinfo);
+
+/**
+ *	nft_unregister_afinfo - unregister nf_tables address family info
+ *
+ *	@afi: address family info to unregister
+ *
+ *	Unregister the address family for use with nf_tables.
+ */
+void nft_unregister_afinfo(struct nft_af_info *afi)
+{
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_del(&afi->list);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
+
+static struct nft_af_info *nft_afinfo_lookup(int family)
+{
+	struct nft_af_info *afi;
+
+	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+		if (afi->family == family)
+			return afi;
+	}
+	return NULL;
+}
+
+static struct nft_af_info *nf_tables_afinfo_lookup(int family, bool autoload)
+{
+	struct nft_af_info *afi;
+
+	afi = nft_afinfo_lookup(family);
+	if (afi != NULL)
+		return afi;
+#ifdef CONFIG_MODULES
+	if (autoload) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-afinfo-%u", family);
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		afi = nft_afinfo_lookup(family);
+		if (afi != NULL)
+			return ERR_PTR(-EAGAIN);
+	}
+#endif
+	return ERR_PTR(-EAFNOSUPPORT);
+}
+
+/*
+ * Tables
+ */
+
+static struct nft_table *nft_table_lookup(const struct nft_af_info *afi,
+					  const struct nlattr *nla)
+{
+	struct nft_table *table;
+
+	list_for_each_entry(table, &afi->tables, list) {
+		if (!nla_strcmp(nla, table->name))
+			return table;
+	}
+	return NULL;
+}
+
+static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
+						const struct nlattr *nla,
+						bool autoload)
+{
+	struct nft_table *table;
+
+	if (nla == NULL)
+		return ERR_PTR(-EINVAL);
+
+	table = nft_table_lookup(afi, nla);
+	if (table != NULL)
+		return table;
+
+#ifdef CONFIG_MODULES
+	if (autoload) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-table-%u-%*.s", afi->family,
+			       nla_len(nla)-1, (const char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (nft_table_lookup(afi, nla))
+			return ERR_PTR(-EAGAIN);
+	}
+#endif
+	return ERR_PTR(-ENOENT);
+}
+
+static inline u64 nf_tables_alloc_handle(struct nft_table *table)
+{
+	return ++table->hgenerator;
+}
+
+static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
+	[NFTA_TABLE_NAME]	= { .type = NLA_STRING },
+};
+
+static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
+				     int event, u32 flags, int family,
+				     const struct nft_table *table)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name))
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_table_notify(const struct sk_buff *oskb,
+				  const struct nlmsghdr *nlh,
+				  const struct nft_table *table,
+				  int event, int family)
+{
+	struct sk_buff *skb;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+	u32 seq = nlh ? nlh->nlmsg_seq : 0;
+	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+	bool report;
+	int err;
+
+	report = nlh ? nlmsg_report(nlh) : false;
+	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_table_info(skb, portid, seq, event, 0,
+					family, table);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static int nf_tables_dump_tables(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	unsigned int idx = 0, s_idx = cb->args[0];
+	int family = nfmsg->nfgen_family;
+
+	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+		if (family != NFPROTO_UNSPEC && family != afi->family)
+			continue;
+
+		list_for_each_entry(table, &afi->tables, list) {
+			if (idx < s_idx)
+				goto cont;
+			if (idx > s_idx)
+				memset(&cb->args[1], 0,
+				       sizeof(cb->args) - sizeof(cb->args[0]));
+			if (nf_tables_fill_table_info(skb,
+						      NETLINK_CB(cb->skb).portid,
+						      cb->nlh->nlmsg_seq,
+						      NFT_MSG_NEWTABLE,
+						      NLM_F_MULTI,
+						      afi->family, table) < 0)
+				goto done;
+cont:
+			idx++;
+		}
+	}
+done:
+	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	struct sk_buff *skb2;
+	int family = nfmsg->nfgen_family;
+	int err;
+
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = nf_tables_dump_tables,
+		};
+		return netlink_dump_start(nlsk, skb, nlh, &c);
+	}
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	err = nf_tables_fill_table_info(skb2, NETLINK_CB(skb).portid,
+					nlh->nlmsg_seq, NFT_MSG_NEWTABLE, 0,
+					family, table);
+	if (err < 0)
+		goto err;
+
+	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+	kfree_skb(skb2);
+	return err;
+}
+
+static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nlattr *name;
+	struct nft_af_info *afi;
+	struct nft_table *table;
+	int family = nfmsg->nfgen_family;
+
+	afi = nf_tables_afinfo_lookup(family, true);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	name = nla[NFTA_TABLE_NAME];
+	table = nf_tables_table_lookup(afi, name, false);
+	if (IS_ERR(table)) {
+		if (PTR_ERR(table) != -ENOENT)
+			return PTR_ERR(table);
+		table = NULL;
+	}
+
+	if (table != NULL) {
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
+		if (nlh->nlmsg_flags & NLM_F_REPLACE)
+			return -EOPNOTSUPP;
+		return 0;
+	}
+
+	table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL);
+	if (table == NULL)
+		return -ENOMEM;
+
+	nla_strlcpy(table->name, name, nla_len(name));
+	INIT_LIST_HEAD(&table->chains);
+
+	list_add_tail(&table->list, &afi->tables);
+	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+	return 0;
+}
+
+static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	struct nft_af_info *afi;
+	struct nft_table *table;
+	int family = nfmsg->nfgen_family;
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	if (table->flags & NFT_TABLE_BUILTIN)
+		return -EOPNOTSUPP;
+
+	if (table->use)
+		return -EBUSY;
+
+	list_del(&table->list);
+	nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family);
+	kfree(table);
+	return 0;
+}
+
+static struct nft_table *__nf_tables_table_lookup(const struct nft_af_info *afi,
+						  const char *name)
+{
+	struct nft_table *table;
+
+	list_for_each_entry(table, &afi->tables, list) {
+		if (!strcmp(name, table->name))
+			return table;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
+static int nf_tables_chain_notify(const struct sk_buff *oskb,
+				  const struct nlmsghdr *nlh,
+				  const struct nft_table *table,
+				  const struct nft_chain *chain,
+				  int event, int family);
+
+/**
+ *	nft_register_table - register a built-in table
+ *
+ *	@table: the table to register
+ *	@family: protocol family to register table with
+ *
+ *	Register a built-in table for use with nf_tables. Returns zero on
+ *	success or a negative errno code otherwise.
+ */
+int nft_register_table(struct nft_table *table, int family)
+{
+	struct nft_af_info *afi;
+	struct nft_table *t;
+	struct nft_chain *chain;
+	int err;
+
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+again:
+	afi = nf_tables_afinfo_lookup(family, true);
+	if (IS_ERR(afi)) {
+		err = PTR_ERR(afi);
+		if (err == -EAGAIN)
+			goto again;
+		goto err;
+	}
+
+	t = __nf_tables_table_lookup(afi, table->name);
+	if (IS_ERR(t)) {
+		err = PTR_ERR(t);
+		if (err != -ENOENT)
+			goto err;
+		t = NULL;
+	}
+
+	if (t != NULL) {
+		err = -EEXIST;
+		goto err;
+	}
+
+	table->flags |= NFT_TABLE_BUILTIN;
+	list_add_tail(&table->list, &afi->tables);
+	nf_tables_table_notify(NULL, NULL, table, NFT_MSG_NEWTABLE, family);
+	list_for_each_entry(chain, &table->chains, list)
+		nf_tables_chain_notify(NULL, NULL, table, chain,
+				       NFT_MSG_NEWCHAIN, family);
+	err = 0;
+err:
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	return err;
+}
+EXPORT_SYMBOL_GPL(nft_register_table);
+
+/**
+ *	nft_unregister_table - unregister a built-in table
+ *
+ *	@table: the table to unregister
+ *	@family: protocol family to unregister table with
+ *
+ *	Unregister a built-in table for use with nf_tables.
+ */
+void nft_unregister_table(struct nft_table *table, int family)
+{
+	struct nft_chain *chain;
+
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_del(&table->list);
+	list_for_each_entry(chain, &table->chains, list)
+		nf_tables_chain_notify(NULL, NULL, table, chain,
+				       NFT_MSG_DELCHAIN, family);
+	nf_tables_table_notify(NULL, NULL, table, NFT_MSG_DELTABLE, family);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_table);
+
+/*
+ * Chains
+ */
+
+static struct nft_chain *
+nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle)
+{
+	struct nft_chain *chain;
+
+	list_for_each_entry(chain, &table->chains, list) {
+		if (chain->handle == handle)
+			return chain;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
+static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
+						const struct nlattr *nla)
+{
+	struct nft_chain *chain;
+
+	if (nla == NULL)
+		return ERR_PTR(-EINVAL);
+
+	list_for_each_entry(chain, &table->chains, list) {
+		if (!nla_strcmp(nla, chain->name))
+			return chain;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
+static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
+	[NFTA_CHAIN_TABLE]	= { .type = NLA_STRING },
+	[NFTA_CHAIN_HANDLE]	= { .type = NLA_U64 },
+	[NFTA_CHAIN_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
+	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
+	[NFTA_HOOK_HOOKNUM]	= { .type = NLA_U32 },
+	[NFTA_HOOK_PRIORITY]	= { .type = NLA_U32 },
+};
+
+static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
+				     int event, u32 flags, int family,
+				     const struct nft_table *table,
+				     const struct nft_chain *chain)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name))
+		goto nla_put_failure;
+	if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle)))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_CHAIN_NAME, chain->name))
+		goto nla_put_failure;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		const struct nf_hook_ops *ops = &nft_base_chain(chain)->ops;
+		struct nlattr *nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
+		if (nest == NULL)
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
+			goto nla_put_failure;
+		nla_nest_end(skb, nest);
+	}
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_chain_notify(const struct sk_buff *oskb,
+				  const struct nlmsghdr *nlh,
+				  const struct nft_table *table,
+				  const struct nft_chain *chain,
+				  int event, int family)
+{
+	struct sk_buff *skb;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+	u32 seq = nlh ? nlh->nlmsg_seq : 0;
+	bool report;
+	int err;
+
+	report = nlh ? nlmsg_report(nlh) : false;
+	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_chain_info(skb, portid, seq, event, 0, family,
+					table, chain);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static int nf_tables_dump_chains(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	const struct nft_chain *chain;
+	unsigned int idx = 0, s_idx = cb->args[0];
+	int family = nfmsg->nfgen_family;
+
+	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+		if (family != NFPROTO_UNSPEC && family != afi->family)
+			continue;
+
+		list_for_each_entry(table, &afi->tables, list) {
+			list_for_each_entry(chain, &table->chains, list) {
+				if (idx < s_idx)
+					goto cont;
+				if (idx > s_idx)
+					memset(&cb->args[1], 0,
+					       sizeof(cb->args) - sizeof(cb->args[0]));
+				if (nf_tables_fill_chain_info(skb, NETLINK_CB(cb->skb).portid,
+							      cb->nlh->nlmsg_seq,
+							      NFT_MSG_NEWCHAIN,
+							      NLM_F_MULTI,
+							      afi->family, table, chain) < 0)
+					goto done;
+cont:
+				idx++;
+			}
+		}
+	}
+done:
+	cb->args[0] = idx;
+	return skb->len;
+}
+
+
+static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	const struct nft_chain *chain;
+	struct sk_buff *skb2;
+	int family = nfmsg->nfgen_family;
+	int err;
+
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = nf_tables_dump_chains,
+		};
+		return netlink_dump_start(nlsk, skb, nlh, &c);
+	}
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
+	if (IS_ERR(chain))
+		return PTR_ERR(chain);
+
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	err = nf_tables_fill_chain_info(skb2, NETLINK_CB(skb).portid,
+					nlh->nlmsg_seq, NFT_MSG_NEWCHAIN, 0,
+					family, table, chain);
+	if (err < 0)
+		goto err;
+
+	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+	kfree_skb(skb2);
+	return err;
+}
+
+static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nlattr * uninitialized_var(name);
+	const struct nft_af_info *afi;
+	struct nft_table *table;
+	struct nft_chain *chain;
+	struct nft_base_chain *basechain;
+	struct nlattr *ha[NFTA_HOOK_MAX + 1];
+	int family = nfmsg->nfgen_family;
+	u64 handle = 0;
+	int err;
+	bool create;
+
+	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
+
+	afi = nf_tables_afinfo_lookup(family, true);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], create);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	if (table->use == UINT_MAX)
+		return -EOVERFLOW;
+
+	chain = NULL;
+	name = nla[NFTA_CHAIN_NAME];
+
+	if (nla[NFTA_CHAIN_HANDLE]) {
+		handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
+		chain = nf_tables_chain_lookup_byhandle(table, handle);
+		if (IS_ERR(chain))
+			return PTR_ERR(chain);
+	} else {
+		chain = nf_tables_chain_lookup(table, name);
+		if (IS_ERR(chain)) {
+			if (PTR_ERR(chain) != -ENOENT)
+				return PTR_ERR(chain);
+			chain = NULL;
+		}
+	}
+
+	if (chain != NULL) {
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
+		if (nlh->nlmsg_flags & NLM_F_REPLACE)
+			return -EOPNOTSUPP;
+
+		if (nla[NFTA_CHAIN_HANDLE] && name &&
+		    !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME])))
+			return -EEXIST;
+
+		if (nla[NFTA_CHAIN_HANDLE] && name)
+			nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+
+		goto notify;
+	}
+
+	if (nla[NFTA_CHAIN_HOOK]) {
+		struct nf_hook_ops *ops;
+
+		err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
+				       nft_hook_policy);
+		if (err < 0)
+			return err;
+		if (ha[NFTA_HOOK_HOOKNUM] == NULL ||
+		    ha[NFTA_HOOK_PRIORITY] == NULL)
+			return -EINVAL;
+		if (ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])) >= afi->nhooks)
+			return -EINVAL;
+
+		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
+		if (basechain == NULL)
+			return -ENOMEM;
+		chain = &basechain->chain;
+
+		ops = &basechain->ops;
+		ops->pf		= family;
+		ops->owner	= afi->owner;
+		ops->hooknum	= ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
+		ops->priority	= ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
+		ops->priv	= chain;
+		ops->hook	= nft_do_chain;
+		if (afi->hooks[ops->hooknum])
+			ops->hook = afi->hooks[ops->hooknum];
+
+		chain->flags |= NFT_BASE_CHAIN;
+	} else {
+		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
+		if (chain == NULL)
+			return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&chain->rules);
+	chain->handle = nf_tables_alloc_handle(table);
+	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+
+	list_add_tail(&chain->list, &table->chains);
+	table->use++;
+notify:
+	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
+			       family);
+	return 0;
+}
+
+static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
+{
+	struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
+
+	BUG_ON(chain->use > 0);
+
+	if (chain->flags & NFT_BASE_CHAIN)
+		kfree(nft_base_chain(chain));
+	else
+		kfree(chain);
+}
+
+static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	struct nft_table *table;
+	struct nft_chain *chain;
+	int family = nfmsg->nfgen_family;
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
+	if (IS_ERR(chain))
+		return PTR_ERR(chain);
+
+	if (chain->flags & NFT_CHAIN_BUILTIN)
+		return -EOPNOTSUPP;
+
+	if (!list_empty(&chain->rules))
+		return -EBUSY;
+
+	list_del(&chain->list);
+	table->use--;
+
+	if (chain->flags & NFT_BASE_CHAIN)
+		nf_unregister_hook(&nft_base_chain(chain)->ops);
+
+	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN,
+			       family);
+
+	/* Make sure all rule references are gone before this is released */
+	call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+	return 0;
+}
+
+static void nft_ctx_init(struct nft_ctx *ctx,
+			 const struct nft_af_info *afi,
+			 const struct nft_table *table,
+			 const struct nft_chain *chain)
+{
+	ctx->afi   = afi;
+	ctx->table = table;
+	ctx->chain = chain;
+}
+
+/*
+ * Expressions
+ */
+
+/**
+ *	nft_register_expr - register nf_tables expr operations
+ *	@ops: expr operations
+ *
+ *	Registers the expr operations for use with nf_tables. Returns zero on
+ *	success or a negative errno code otherwise.
+ */
+int nft_register_expr(struct nft_expr_ops *ops)
+{
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_add_tail(&ops->list, &nf_tables_expressions);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_register_expr);
+
+/**
+ *	nft_unregister_expr - unregister nf_tables expr operations
+ *	@ops: expr operations
+ *
+ * 	Unregisters the expr operations for use with nf_tables.
+ */
+void nft_unregister_expr(struct nft_expr_ops *ops)
+{
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_del(&ops->list);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_expr);
+
+static const struct nft_expr_ops *__nft_expr_ops_get(struct nlattr *nla)
+{
+	const struct nft_expr_ops *ops;
+
+	list_for_each_entry(ops, &nf_tables_expressions, list) {
+		if (!nla_strcmp(nla, ops->name))
+			return ops;
+	}
+	return NULL;
+}
+
+static const struct nft_expr_ops *nft_expr_ops_get(struct nlattr *nla)
+{
+	const struct nft_expr_ops *ops;
+
+	if (nla == NULL)
+		return ERR_PTR(-EINVAL);
+
+	ops = __nft_expr_ops_get(nla);
+	if (ops != NULL && try_module_get(ops->owner))
+		return ops;
+
+#ifdef CONFIG_MODULES
+	if (ops == NULL) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-expr-%.*s",
+			       nla_len(nla), (char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (__nft_expr_ops_get(nla))
+			return ERR_PTR(-EAGAIN);
+	}
+#endif
+	return ERR_PTR(-ENOENT);
+}
+
+static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
+	[NFTA_EXPR_NAME]	= { .type = NLA_STRING },
+	[NFTA_EXPR_DATA]	= { .type = NLA_NESTED },
+};
+
+static int nf_tables_fill_expr_info(struct sk_buff *skb,
+				    const struct nft_expr *expr)
+{
+	if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->name))
+		goto nla_put_failure;
+
+	if (expr->ops->dump) {
+		struct nlattr *data = nla_nest_start(skb, NFTA_EXPR_DATA);
+		if (data == NULL)
+			goto nla_put_failure;
+		if (expr->ops->dump(skb, expr) < 0)
+			goto nla_put_failure;
+		nla_nest_end(skb, data);
+	}
+
+	return skb->len;
+
+nla_put_failure:
+	return -1;
+};
+
+struct nft_expr_info {
+	const struct nft_expr_ops	*ops;
+	struct nlattr			*tb[NFTA_EXPR_MAX + 1];
+};
+
+static int nf_tables_expr_parse(const struct nlattr *nla,
+				struct nft_expr_info *info)
+{
+	const struct nft_expr_ops *ops;
+	int err;
+
+	err = nla_parse_nested(info->tb, NFTA_EXPR_MAX, nla, nft_expr_policy);
+	if (err < 0)
+		return err;
+
+	ops = nft_expr_ops_get(info->tb[NFTA_EXPR_NAME]);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	info->ops = ops;
+	return 0;
+}
+
+static int nf_tables_newexpr(const struct nft_ctx *ctx,
+			     struct nft_expr_info *info,
+			     struct nft_expr *expr)
+{
+	const struct nft_expr_ops *ops = info->ops;
+	int err;
+
+	expr->ops = ops;
+	if (ops->init) {
+		struct nlattr *ma[ops->maxattr + 1];
+
+		if (info->tb[NFTA_EXPR_DATA]) {
+			err = nla_parse_nested(ma, ops->maxattr,
+					       info->tb[NFTA_EXPR_DATA],
+					       ops->policy);
+			if (err < 0)
+				goto err1;
+		} else
+			memset(ma, 0, sizeof(ma[0]) * (ops->maxattr + 1));
+
+		err = ops->init(ctx, expr, (const struct nlattr **)ma);
+		if (err < 0)
+			goto err1;
+	}
+
+	info->ops = NULL;
+	return 0;
+
+err1:
+	expr->ops = NULL;
+	return err;
+}
+
+static void nf_tables_expr_destroy(struct nft_expr *expr)
+{
+	if (expr->ops->destroy)
+		expr->ops->destroy(expr);
+	module_put(expr->ops->owner);
+}
+
+/*
+ * Rules
+ */
+
+static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain,
+						u64 handle)
+{
+	struct nft_rule *rule;
+
+	// FIXME: this sucks
+	list_for_each_entry(rule, &chain->rules, list) {
+		if (handle == rule->handle)
+			return rule;
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+
+static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
+					      const struct nlattr *nla)
+{
+	if (nla == NULL)
+		return ERR_PTR(-EINVAL);
+
+	return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla)));
+}
+
+static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
+	[NFTA_RULE_TABLE]	= { .type = NLA_STRING },
+	[NFTA_RULE_CHAIN]	= { .type = NLA_STRING,
+				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
+	[NFTA_RULE_HANDLE]	= { .type = NLA_U64 },
+	[NFTA_RULE_EXPRESSIONS]	= { .type = NLA_NESTED },
+};
+
+static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
+				    int event, u32 flags, int family,
+				    const struct nft_table *table,
+				    const struct nft_chain *chain,
+				    const struct nft_rule *rule)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	const struct nft_expr *expr, *next;
+	struct nlattr *list;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+			flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_RULE_TABLE, table->name))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name))
+		goto nla_put_failure;
+	if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle)))
+		goto nla_put_failure;
+
+	list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS);
+	if (list == NULL)
+		goto nla_put_failure;
+	nft_rule_for_each_expr(expr, next, rule) {
+		struct nlattr *elem = nla_nest_start(skb, NFTA_LIST_ELEM);
+		if (elem == NULL)
+			goto nla_put_failure;
+		if (nf_tables_fill_expr_info(skb, expr) < 0)
+			goto nla_put_failure;
+		nla_nest_end(skb, elem);
+	}
+	nla_nest_end(skb, list);
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_rule_notify(const struct sk_buff *oskb,
+				 const struct nlmsghdr *nlh,
+				 const struct nft_table *table,
+				 const struct nft_chain *chain,
+				 const struct nft_rule *rule,
+				 int event, u32 flags, int family)
+{
+	struct sk_buff *skb;
+	u32 portid = NETLINK_CB(oskb).portid;
+	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
+	u32 seq = nlh->nlmsg_seq;
+	bool report;
+	int err;
+
+	report = nlmsg_report(nlh);
+	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_rule_info(skb, portid, seq, event, flags,
+				       family, table, chain, rule);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static int nf_tables_dump_rules(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	const struct nft_chain *chain;
+	const struct nft_rule *rule;
+	unsigned int idx = 0, s_idx = cb->args[0];
+	int family = nfmsg->nfgen_family;
+
+	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+		if (family != NFPROTO_UNSPEC && family != afi->family)
+			continue;
+
+		list_for_each_entry(table, &afi->tables, list) {
+			list_for_each_entry(chain, &table->chains, list) {
+				list_for_each_entry(rule, &chain->rules, list) {
+					if (idx < s_idx)
+						goto cont;
+					if (idx > s_idx)
+						memset(&cb->args[1], 0,
+						       sizeof(cb->args) - sizeof(cb->args[0]));
+					if (nf_tables_fill_rule_info(skb, NETLINK_CB(cb->skb).portid,
+								      cb->nlh->nlmsg_seq,
+								      NFT_MSG_NEWRULE,
+								      NLM_F_MULTI | NLM_F_APPEND,
+								      afi->family, table, chain, rule) < 0)
+						goto done;
+cont:
+					idx++;
+				}
+			}
+		}
+	}
+done:
+	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
+			     const struct nlmsghdr *nlh,
+			     const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	const struct nft_chain *chain;
+	const struct nft_rule *rule;
+	struct sk_buff *skb2;
+	int family = nfmsg->nfgen_family;
+	int err;
+
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = nf_tables_dump_rules,
+		};
+		return netlink_dump_start(nlsk, skb, nlh, &c);
+	}
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+	if (IS_ERR(chain))
+		return PTR_ERR(chain);
+
+	rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+	if (IS_ERR(rule))
+		return PTR_ERR(rule);
+
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	err = nf_tables_fill_rule_info(skb2, NETLINK_CB(skb).portid,
+				       nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0,
+				       family, table, chain, rule);
+	if (err < 0)
+		goto err;
+
+	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+	kfree_skb(skb2);
+	return err;
+}
+
+static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+{
+	struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
+	struct nft_expr *expr;
+
+	/*
+	 * Careful: some expressions might not be initialized in case this
+	 * is called on error from nf_tables_newrule().
+	 */
+	expr = nft_expr_first(rule);
+	while (expr->ops && expr != nft_expr_last(rule)) {
+		nf_tables_expr_destroy(expr);
+		expr = nft_expr_next(expr);
+	}
+	kfree(rule);
+}
+
+static void nf_tables_rule_destroy(struct nft_rule *rule)
+{
+	call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
+}
+
+#define NFT_RULE_MAXEXPRS	128
+
+static struct nft_expr_info *info;
+
+static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
+			     const struct nlmsghdr *nlh,
+			     const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	struct nft_table *table;
+	struct nft_chain *chain;
+	struct nft_rule *rule, *old_rule = NULL;
+	struct nft_expr *expr;
+	struct nft_ctx ctx;
+	struct nlattr *tmp;
+	unsigned int size, i, n;
+	int err, rem;
+	bool create;
+	u64 handle;
+
+	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
+
+	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, create);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], create);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+	if (IS_ERR(chain))
+		return PTR_ERR(chain);
+
+	if (nla[NFTA_RULE_HANDLE]) {
+		handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE]));
+		rule = __nf_tables_rule_lookup(chain, handle);
+		if (IS_ERR(rule))
+			return PTR_ERR(rule);
+
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
+		if (nlh->nlmsg_flags & NLM_F_REPLACE)
+			old_rule = rule;
+		else
+			return -EOPNOTSUPP;
+	} else {
+		if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
+			return -EINVAL;
+		handle = nf_tables_alloc_handle(table);
+	}
+
+	n = 0;
+	size = 0;
+	if (nla[NFTA_RULE_EXPRESSIONS]) {
+		nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) {
+			err = -EINVAL;
+			if (nla_type(tmp) != NFTA_LIST_ELEM)
+				goto err1;
+			if (n == NFT_RULE_MAXEXPRS)
+				goto err1;
+			err = nf_tables_expr_parse(tmp, &info[n]);
+			if (err < 0)
+				goto err1;
+			size += info[n].ops->size;
+			n++;
+		}
+	}
+
+	err = -ENOMEM;
+	rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL);
+	if (rule == NULL)
+		goto err1;
+
+	rule->handle = handle;
+	rule->dlen   = size;
+
+	nft_ctx_init(&ctx, afi, table, chain);
+	expr = nft_expr_first(rule);
+	for (i = 0; i < n; i++) {
+		err = nf_tables_newexpr(&ctx, &info[i], expr);
+		if (err < 0)
+			goto err2;
+		expr = nft_expr_next(expr);
+	}
+
+	/* Register hook when first rule is inserted into a base chain */
+	if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN) {
+		err = nf_register_hook(&nft_base_chain(chain)->ops);
+		if (err < 0)
+			goto err2;
+	}
+
+	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
+		list_replace_rcu(&old_rule->list, &rule->list);
+		nf_tables_rule_destroy(old_rule);
+	} else if (nlh->nlmsg_flags & NLM_F_APPEND)
+		list_add_tail_rcu(&rule->list, &chain->rules);
+	else
+		list_add_rcu(&rule->list, &chain->rules);
+
+	nf_tables_rule_notify(skb, nlh, table, chain, rule, NFT_MSG_NEWRULE,
+			      nlh->nlmsg_flags & (NLM_F_APPEND | NLM_F_REPLACE),
+			      nfmsg->nfgen_family);
+	return 0;
+
+err2:
+	nf_tables_rule_destroy(rule);
+err1:
+	for (i = 0; i < n; i++) {
+		if (info[i].ops != NULL)
+			module_put(info[i].ops->owner);
+	}
+	return err;
+}
+
+static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
+			     const struct nlmsghdr *nlh,
+			     const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+	struct nft_chain *chain;
+	struct nft_rule *rule, *tmp;
+	int family = nfmsg->nfgen_family;
+
+	afi = nf_tables_afinfo_lookup(family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
+	if (IS_ERR(chain))
+		return PTR_ERR(chain);
+
+	if (nla[NFTA_RULE_HANDLE]) {
+		rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
+		if (IS_ERR(rule))
+			return PTR_ERR(rule);
+
+		/* List removal must be visible before destroying expressions */
+		list_del_rcu(&rule->list);
+
+		nf_tables_rule_notify(skb, nlh, table, chain, rule,
+				      NFT_MSG_DELRULE, 0, family);
+		nf_tables_rule_destroy(rule);
+	} else {
+		/* Remove all rules in this chain */
+		list_for_each_entry_safe(rule, tmp, &chain->rules, list) {
+			list_del_rcu(&rule->list);
+
+			nf_tables_rule_notify(skb, nlh, table, chain, rule,
+					      NFT_MSG_DELRULE, 0, family);
+			nf_tables_rule_destroy(rule);
+		}
+	}
+
+	/* Unregister hook when last rule from base chain is deleted */
+	if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN)
+		nf_unregister_hook(&nft_base_chain(chain)->ops);
+
+	return 0;
+}
+
+static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
+	[NFT_MSG_NEWTABLE] = {
+		.call		= nf_tables_newtable,
+		.attr_count	= NFTA_TABLE_MAX,
+		.policy		= nft_table_policy,
+	},
+	[NFT_MSG_GETTABLE] = {
+		.call		= nf_tables_gettable,
+		.attr_count	= NFTA_TABLE_MAX,
+		.policy		= nft_table_policy,
+	},
+	[NFT_MSG_DELTABLE] = {
+		.call		= nf_tables_deltable,
+		.attr_count	= NFTA_TABLE_MAX,
+		.policy		= nft_table_policy,
+	},
+	[NFT_MSG_NEWCHAIN] = {
+		.call		= nf_tables_newchain,
+		.attr_count	= NFTA_CHAIN_MAX,
+		.policy		= nft_chain_policy,
+	},
+	[NFT_MSG_GETCHAIN] = {
+		.call		= nf_tables_getchain,
+		.attr_count	= NFTA_CHAIN_MAX,
+		.policy		= nft_chain_policy,
+	},
+	[NFT_MSG_DELCHAIN] = {
+		.call		= nf_tables_delchain,
+		.attr_count	= NFTA_CHAIN_MAX,
+		.policy		= nft_chain_policy,
+	},
+	[NFT_MSG_NEWRULE] = {
+		.call		= nf_tables_newrule,
+		.attr_count	= NFTA_RULE_MAX,
+		.policy		= nft_rule_policy,
+	},
+	[NFT_MSG_GETRULE] = {
+		.call		= nf_tables_getrule,
+		.attr_count	= NFTA_RULE_MAX,
+		.policy		= nft_rule_policy,
+	},
+	[NFT_MSG_DELRULE] = {
+		.call		= nf_tables_delrule,
+		.attr_count	= NFTA_RULE_MAX,
+		.policy		= nft_rule_policy,
+	},
+};
+
+static const struct nfnetlink_subsystem nf_tables_subsys = {
+	.name		= "nf_tables",
+	.subsys_id	= NFNL_SUBSYS_NFTABLES,
+	.cb_count	= NFT_MSG_MAX,
+	.cb		= nf_tables_cb,
+};
+
+/**
+ *	nft_validate_input_register - validate an expressions' input register
+ *
+ *	@reg: the register number
+ *
+ * 	Validate that the input register is one of the general purpose
+ * 	registers.
+ */
+int nft_validate_input_register(enum nft_registers reg)
+{
+	if (reg <= NFT_REG_VERDICT)
+		return -EINVAL;
+	if (reg > NFT_REG_MAX)
+		return -ERANGE;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_validate_input_register);
+
+/**
+ *	nft_validate_output_register - validate an expressions' output register
+ *
+ *	@reg: the register number
+ *
+ * 	Validate that the output register is one of the general purpose
+ * 	registers or the verdict register.
+ */
+int nft_validate_output_register(enum nft_registers reg)
+{
+	if (reg < NFT_REG_VERDICT)
+		return -EINVAL;
+	if (reg > NFT_REG_MAX)
+		return -ERANGE;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_validate_output_register);
+
+/**
+ *	nft_validate_data_load - validate an expressions' data load
+ *
+ *	@ctx: context of the expression performing the load
+ * 	@reg: the destination register number
+ * 	@data: the data to load
+ * 	@type: the data type
+ *
+ * 	Validate that a data load uses the appropriate data type for
+ * 	the destination register. A value of NULL for the data means
+ * 	that its runtime gathered data, which is always of type
+ * 	NFT_DATA_VALUE.
+ */
+int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg,
+			   const struct nft_data *data,
+			   enum nft_data_types type)
+{
+	switch (reg) {
+	case NFT_REG_VERDICT:
+		if (data == NULL || type != NFT_DATA_VERDICT)
+			return -EINVAL;
+		// FIXME: do loop detection
+		return 0;
+	default:
+		if (data != NULL && type != NFT_DATA_VALUE)
+			return -EINVAL;
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(nft_validate_data_load);
+
+static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = {
+	[NFTA_VERDICT_CODE]	= { .type = NLA_U32 },
+	[NFTA_VERDICT_CHAIN]	= { .type = NLA_STRING,
+				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
+};
+
+static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
+			    struct nft_data_desc *desc, const struct nlattr *nla)
+{
+	struct nlattr *tb[NFTA_VERDICT_MAX + 1];
+	struct nft_chain *chain;
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_VERDICT_CODE])
+		return -EINVAL;
+	data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE]));
+
+	switch (data->verdict) {
+	case NF_ACCEPT:
+	case NF_DROP:
+	case NF_QUEUE:
+	case NFT_CONTINUE:
+	case NFT_BREAK:
+	case NFT_RETURN:
+		desc->len = sizeof(data->verdict);
+		break;
+	case NFT_JUMP:
+	case NFT_GOTO:
+		if (!tb[NFTA_VERDICT_CHAIN])
+			return -EINVAL;
+		chain = nf_tables_chain_lookup(ctx->table,
+					       tb[NFTA_VERDICT_CHAIN]);
+		if (IS_ERR(chain))
+			return PTR_ERR(chain);
+		if (chain->flags & NFT_BASE_CHAIN)
+			return -EOPNOTSUPP;
+
+		if (ctx->chain->level + 1 > chain->level) {
+			if (ctx->chain->level + 1 == 16)
+				return -EMLINK;
+			chain->level = ctx->chain->level + 1;
+		}
+		chain->use++;
+		data->chain = chain;
+		desc->len = sizeof(data);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	desc->type = NFT_DATA_VERDICT;
+	return 0;
+}
+
+static void nft_verdict_uninit(const struct nft_data *data)
+{
+	switch (data->verdict) {
+	case NFT_JUMP:
+	case NFT_GOTO:
+		data->chain->use--;
+		break;
+	}
+}
+
+static int nft_verdict_dump(struct sk_buff *skb, const struct nft_data *data)
+{
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, NFTA_DATA_VERDICT);
+	if (!nest)
+		goto nla_put_failure;
+
+	if (nla_put_be32(skb, NFTA_VERDICT_CODE, htonl(data->verdict)))
+		goto nla_put_failure;
+
+	switch (data->verdict) {
+	case NFT_JUMP:
+	case NFT_GOTO:
+		if (nla_put_string(skb, NFTA_VERDICT_CHAIN, data->chain->name))
+			goto nla_put_failure;
+	}
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_value_init(const struct nft_ctx *ctx, struct nft_data *data,
+			  struct nft_data_desc *desc, const struct nlattr *nla)
+{
+	unsigned int len;
+
+	len = nla_len(nla);
+	if (len == 0)
+		return -EINVAL;
+	if (len > sizeof(data->data))
+		return -EOVERFLOW;
+
+	nla_memcpy(data->data, nla, sizeof(data->data));
+	desc->type = NFT_DATA_VALUE;
+	desc->len  = len;
+	return 0;
+}
+
+static int nft_value_dump(struct sk_buff *skb, const struct nft_data *data,
+			  unsigned int len)
+{
+	return nla_put(skb, NFTA_DATA_VALUE, len, data->data);
+}
+
+static const struct nla_policy nft_data_policy[NFTA_DATA_MAX + 1] = {
+	[NFTA_DATA_VALUE]	= { .type = NLA_BINARY,
+				    .len  = FIELD_SIZEOF(struct nft_data, data) },
+	[NFTA_DATA_VERDICT]	= { .type = NLA_NESTED },
+};
+
+/**
+ *	nft_data_init - parse nf_tables data netlink attributes
+ *
+ *	@ctx: context of the expression using the data
+ *	@data: destination struct nft_data
+ *	@desc: data description
+ *	@nla: netlink attribute containing data
+ *
+ *	Parse the netlink data attributes and initialize a struct nft_data.
+ *	The type and length of data are returned in the data description.
+ *
+ *	The caller can indicate that it only wants to accept data of type
+ *	NFT_DATA_VALUE by passing NULL for the ctx argument.
+ */
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+		  struct nft_data_desc *desc, const struct nlattr *nla)
+{
+	struct nlattr *tb[NFTA_DATA_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_DATA_MAX, nla, nft_data_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_DATA_VALUE])
+		return nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]);
+	if (tb[NFTA_DATA_VERDICT] && ctx != NULL)
+		return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(nft_data_init);
+
+/**
+ *	nft_data_uninit - release a nft_data item
+ *
+ *	@data: struct nft_data to release
+ *	@type: type of data
+ *
+ *	Release a nft_data item. NFT_DATA_VALUE types can be silently discarded,
+ *	all others need to be released by calling this function.
+ */
+void nft_data_uninit(const struct nft_data *data, enum nft_data_types type)
+{
+	switch (type) {
+	case NFT_DATA_VALUE:
+		return;
+	case NFT_DATA_VERDICT:
+		return nft_verdict_uninit(data);
+	default:
+		WARN_ON(1);
+	}
+}
+EXPORT_SYMBOL_GPL(nft_data_uninit);
+
+int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
+		  enum nft_data_types type, unsigned int len)
+{
+	struct nlattr *nest;
+	int err;
+
+	nest = nla_nest_start(skb, attr);
+	if (nest == NULL)
+		return -1;
+
+	switch (type) {
+	case NFT_DATA_VALUE:
+		err = nft_value_dump(skb, data, len);
+		break;
+	case NFT_DATA_VERDICT:
+		err = nft_verdict_dump(skb, data);
+		break;
+	default:
+		err = -EINVAL;
+		WARN_ON(1);
+	}
+
+	nla_nest_end(skb, nest);
+	return err;
+}
+EXPORT_SYMBOL_GPL(nft_data_dump);
+
+static int __init nf_tables_module_init(void)
+{
+	int err;
+
+	info = kmalloc(sizeof(struct nft_expr_info) * NFT_RULE_MAXEXPRS,
+		       GFP_KERNEL);
+	if (info == NULL) {
+		err = -ENOMEM;
+		goto err1;
+	}
+
+	err = nf_tables_core_module_init();
+	if (err < 0)
+		goto err2;
+
+	err = nfnetlink_subsys_register(&nf_tables_subsys);
+	if (err < 0)
+		goto err3;
+
+	pr_info("nf_tables: (c) 2007-2009 Patrick McHardy <kaber@trash.net>\n");
+	return 0;
+err3:
+	nf_tables_core_module_exit();
+err2:
+	kfree(info);
+err1:
+	return err;
+}
+
+static void __exit nf_tables_module_exit(void)
+{
+	nfnetlink_subsys_unregister(&nf_tables_subsys);
+	nf_tables_core_module_exit();
+	kfree(info);
+}
+
+module_init(nf_tables_module_init);
+module_exit(nf_tables_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES);
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
new file mode 100644
index 000000000000..bc7fb85d4002
--- /dev/null
+++ b/net/netfilter/nf_tables_core.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+#define NFT_JUMP_STACK_SIZE	16
+
+unsigned int nft_do_chain(const struct nf_hook_ops *ops,
+			  struct sk_buff *skb,
+			  const struct net_device *in,
+			  const struct net_device *out,
+			  int (*okfn)(struct sk_buff *))
+{
+	const struct nft_chain *chain = ops->priv;
+	const struct nft_rule *rule;
+	const struct nft_expr *expr, *last;
+	struct nft_data data[NFT_REG_MAX + 1];
+	const struct nft_pktinfo pkt = {
+		.skb		= skb,
+		.in		= in,
+		.out		= out,
+		.hooknum	= ops->hooknum,
+	};
+	unsigned int stackptr = 0;
+	struct {
+		const struct nft_chain	*chain;
+		const struct nft_rule	*rule;
+	} jumpstack[NFT_JUMP_STACK_SIZE];
+
+do_chain:
+	rule = list_entry(&chain->rules, struct nft_rule, list);
+next_rule:
+	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+	list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
+		nft_rule_for_each_expr(expr, last, rule) {
+			expr->ops->eval(expr, data, &pkt);
+			if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
+				break;
+		}
+
+		switch (data[NFT_REG_VERDICT].verdict) {
+		case NFT_BREAK:
+			data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+			/* fall through */
+		case NFT_CONTINUE:
+			continue;
+		}
+		break;
+	}
+
+	switch (data[NFT_REG_VERDICT].verdict) {
+	case NF_ACCEPT:
+	case NF_DROP:
+	case NF_QUEUE:
+		return data[NFT_REG_VERDICT].verdict;
+	case NFT_JUMP:
+		BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
+		jumpstack[stackptr].chain = chain;
+		jumpstack[stackptr].rule  = rule;
+		stackptr++;
+		/* fall through */
+	case NFT_GOTO:
+		chain = data[NFT_REG_VERDICT].chain;
+		goto do_chain;
+	case NFT_RETURN:
+	case NFT_CONTINUE:
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	if (stackptr > 0) {
+		stackptr--;
+		chain = jumpstack[stackptr].chain;
+		rule  = jumpstack[stackptr].rule;
+		goto next_rule;
+	}
+
+	return NF_ACCEPT;
+}
+EXPORT_SYMBOL_GPL(nft_do_chain);
+
+int __init nf_tables_core_module_init(void)
+{
+	int err;
+
+	err = nft_immediate_module_init();
+	if (err < 0)
+		goto err1;
+
+	err = nft_cmp_module_init();
+	if (err < 0)
+		goto err2;
+
+	err = nft_lookup_module_init();
+	if (err < 0)
+		goto err3;
+
+	err = nft_bitwise_module_init();
+	if (err < 0)
+		goto err4;
+
+	err = nft_byteorder_module_init();
+	if (err < 0)
+		goto err5;
+
+	err = nft_payload_module_init();
+	if (err < 0)
+		goto err6;
+
+	return 0;
+
+err6:
+	nft_byteorder_module_exit();
+err5:
+	nft_bitwise_module_exit();
+err4:
+	nft_lookup_module_exit();
+err3:
+	nft_cmp_module_exit();
+err2:
+	nft_immediate_module_exit();
+err1:
+	return err;
+}
+
+void nf_tables_core_module_exit(void)
+{
+	nft_payload_module_exit();
+	nft_byteorder_module_exit();
+	nft_bitwise_module_exit();
+	nft_lookup_module_exit();
+	nft_cmp_module_exit();
+	nft_immediate_module_exit();
+}
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
new file mode 100644
index 000000000000..0f7501506367
--- /dev/null
+++ b/net/netfilter/nft_bitwise.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_bitwise {
+	enum nft_registers	sreg:8;
+	enum nft_registers	dreg:8;
+	u8			len;
+	struct nft_data		mask;
+	struct nft_data		xor;
+};
+
+static void nft_bitwise_eval(const struct nft_expr *expr,
+			     struct nft_data data[NFT_REG_MAX + 1],
+			     const struct nft_pktinfo *pkt)
+{
+	const struct nft_bitwise *priv = nft_expr_priv(expr);
+	const struct nft_data *src = &data[priv->sreg];
+	struct nft_data *dst = &data[priv->dreg];
+	unsigned int i;
+
+	for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) {
+		dst->data[i] = (src->data[i] & priv->mask.data[i]) ^
+			       priv->xor.data[i];
+	}
+}
+
+static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = {
+	[NFTA_BITWISE_SREG]	= { .type = NLA_U32 },
+	[NFTA_BITWISE_DREG]	= { .type = NLA_U32 },
+	[NFTA_BITWISE_LEN]	= { .type = NLA_U32 },
+	[NFTA_BITWISE_MASK]	= { .type = NLA_NESTED },
+	[NFTA_BITWISE_XOR]	= { .type = NLA_NESTED },
+};
+
+static int nft_bitwise_init(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nlattr * const tb[])
+{
+	struct nft_bitwise *priv = nft_expr_priv(expr);
+	struct nft_data_desc d1, d2;
+	int err;
+
+	if (tb[NFTA_BITWISE_SREG] == NULL ||
+	    tb[NFTA_BITWISE_DREG] == NULL ||
+	    tb[NFTA_BITWISE_LEN] == NULL ||
+	    tb[NFTA_BITWISE_MASK] == NULL ||
+	    tb[NFTA_BITWISE_XOR] == NULL)
+		return -EINVAL;
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_BITWISE_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	priv->len = ntohl(nla_get_be32(tb[NFTA_BITWISE_LEN]));
+
+	err = nft_data_init(NULL, &priv->mask, &d1, tb[NFTA_BITWISE_MASK]);
+	if (err < 0)
+		return err;
+	if (d1.len != priv->len)
+		return -EINVAL;
+
+	err = nft_data_init(NULL, &priv->xor, &d2, tb[NFTA_BITWISE_XOR]);
+	if (err < 0)
+		return err;
+	if (d2.len != priv->len)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_bitwise *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_BITWISE_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BITWISE_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_BITWISE_XOR, &priv->xor,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_bitwise_ops __read_mostly = {
+	.name		= "bitwise",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_bitwise)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_bitwise_eval,
+	.init		= nft_bitwise_init,
+	.dump		= nft_bitwise_dump,
+	.policy		= nft_bitwise_policy,
+	.maxattr	= NFTA_BITWISE_MAX,
+};
+
+int __init nft_bitwise_module_init(void)
+{
+	return nft_register_expr(&nft_bitwise_ops);
+}
+
+void nft_bitwise_module_exit(void)
+{
+	nft_unregister_expr(&nft_bitwise_ops);
+}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
new file mode 100644
index 000000000000..8b0657a4d17b
--- /dev/null
+++ b/net/netfilter/nft_byteorder.c
@@ -0,0 +1,167 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_byteorder {
+	enum nft_registers	sreg:8;
+	enum nft_registers	dreg:8;
+	enum nft_byteorder_ops	op:8;
+	u8			len;
+	u8			size;
+};
+
+static void nft_byteorder_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	const struct nft_byteorder *priv = nft_expr_priv(expr);
+	struct nft_data *src = &data[priv->sreg], *dst = &data[priv->dreg];
+	union { u32 u32; u16 u16; } *s, *d;
+	unsigned int i;
+
+	s = (void *)src->data;
+	d = (void *)dst->data;
+
+	switch (priv->size) {
+	case 4:
+		switch (priv->op) {
+		case NFT_BYTEORDER_NTOH:
+			for (i = 0; i < priv->len / 4; i++)
+				d[i].u32 = ntohl((__force __be32)s[i].u32);
+			break;
+		case NFT_BYTEORDER_HTON:
+			for (i = 0; i < priv->len / 4; i++)
+				d[i].u32 = (__force __u32)htonl(s[i].u32);
+			break;
+		}
+		break;
+	case 2:
+		switch (priv->op) {
+		case NFT_BYTEORDER_NTOH:
+			for (i = 0; i < priv->len / 2; i++)
+				d[i].u16 = ntohs((__force __be16)s[i].u16);
+			break;
+		case NFT_BYTEORDER_HTON:
+			for (i = 0; i < priv->len / 2; i++)
+				d[i].u16 = (__force __u16)htons(s[i].u16);
+			break;
+		}
+		break;
+	}
+}
+
+static const struct nla_policy nft_byteorder_policy[NFTA_BYTEORDER_MAX + 1] = {
+	[NFTA_BYTEORDER_SREG]	= { .type = NLA_U32 },
+	[NFTA_BYTEORDER_DREG]	= { .type = NLA_U32 },
+	[NFTA_BYTEORDER_OP]	= { .type = NLA_U32 },
+	[NFTA_BYTEORDER_LEN]	= { .type = NLA_U32 },
+	[NFTA_BYTEORDER_SIZE]	= { .type = NLA_U32 },
+};
+
+static int nft_byteorder_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	struct nft_byteorder *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_BYTEORDER_SREG] == NULL ||
+	    tb[NFTA_BYTEORDER_DREG] == NULL ||
+	    tb[NFTA_BYTEORDER_LEN] == NULL ||
+	    tb[NFTA_BYTEORDER_SIZE] == NULL ||
+	    tb[NFTA_BYTEORDER_OP] == NULL)
+		return -EINVAL;
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	priv->op = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_OP]));
+	switch (priv->op) {
+	case NFT_BYTEORDER_NTOH:
+	case NFT_BYTEORDER_HTON:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	priv->len = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_LEN]));
+	if (priv->len == 0 || priv->len > FIELD_SIZEOF(struct nft_data, data))
+		return -EINVAL;
+
+	priv->size = ntohl(nla_get_be32(tb[NFTA_BYTEORDER_SIZE]));
+	switch (priv->size) {
+	case 2:
+	case 4:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_byteorder *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_BYTEORDER_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BYTEORDER_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BYTEORDER_OP, htonl(priv->op)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BYTEORDER_LEN, htonl(priv->len)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_BYTEORDER_SIZE, htonl(priv->size)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_byteorder_ops __read_mostly = {
+	.name		= "byteorder",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_byteorder_eval,
+	.init		= nft_byteorder_init,
+	.dump		= nft_byteorder_dump,
+	.policy		= nft_byteorder_policy,
+	.maxattr	= NFTA_BYTEORDER_MAX,
+};
+
+int __init nft_byteorder_module_init(void)
+{
+	return nft_register_expr(&nft_byteorder_ops);
+}
+
+void nft_byteorder_module_exit(void)
+{
+	nft_unregister_expr(&nft_byteorder_ops);
+}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
new file mode 100644
index 000000000000..e734d670120a
--- /dev/null
+++ b/net/netfilter/nft_cmp.c
@@ -0,0 +1,146 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_cmp_expr {
+	struct nft_data		data;
+	enum nft_registers	sreg:8;
+	u8			len;
+	enum nft_cmp_ops	op:8;
+};
+
+static void nft_cmp_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+	int d;
+
+	d = nft_data_cmp(&data[priv->sreg], &priv->data, priv->len);
+	switch (priv->op) {
+	case NFT_CMP_EQ:
+		if (d != 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_NEQ:
+		if (d == 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_LT:
+		if (d == 0)
+			goto mismatch;
+	case NFT_CMP_LTE:
+		if (d > 0)
+			goto mismatch;
+		break;
+	case NFT_CMP_GT:
+		if (d == 0)
+			goto mismatch;
+	case NFT_CMP_GTE:
+		if (d < 0)
+			goto mismatch;
+		break;
+	}
+	return;
+
+mismatch:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_cmp_policy[NFTA_CMP_MAX + 1] = {
+	[NFTA_CMP_SREG]		= { .type = NLA_U32 },
+	[NFTA_CMP_OP]		= { .type = NLA_U32 },
+	[NFTA_CMP_DATA]		= { .type = NLA_NESTED },
+};
+
+static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_cmp_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc;
+	int err;
+
+	if (tb[NFTA_CMP_SREG] == NULL ||
+	    tb[NFTA_CMP_OP] == NULL ||
+	    tb[NFTA_CMP_DATA] == NULL)
+		return -EINVAL;
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
+	switch (priv->op) {
+	case NFT_CMP_EQ:
+	case NFT_CMP_NEQ:
+	case NFT_CMP_LT:
+	case NFT_CMP_LTE:
+	case NFT_CMP_GT:
+	case NFT_CMP_GTE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return err;
+
+	priv->len = desc.len;
+	return 0;
+}
+
+static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(priv->op)))
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &priv->data,
+			  NFT_DATA_VALUE, priv->len) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_cmp_ops __read_mostly = {
+	.name		= "cmp",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_cmp_eval,
+	.init		= nft_cmp_init,
+	.dump		= nft_cmp_dump,
+	.policy		= nft_cmp_policy,
+	.maxattr	= NFTA_CMP_MAX,
+};
+
+int __init nft_cmp_module_init(void)
+{
+	return nft_register_expr(&nft_cmp_ops);
+}
+
+void nft_cmp_module_exit(void)
+{
+	nft_unregister_expr(&nft_cmp_ops);
+}
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
new file mode 100644
index 000000000000..33c5d36819bb
--- /dev/null
+++ b/net/netfilter/nft_counter.c
@@ -0,0 +1,107 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/seqlock.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_counter {
+	seqlock_t	lock;
+	u64		bytes;
+	u64		packets;
+};
+
+static void nft_counter_eval(const struct nft_expr *expr,
+			     struct nft_data data[NFT_REG_MAX + 1],
+			     const struct nft_pktinfo *pkt)
+{
+	struct nft_counter *priv = nft_expr_priv(expr);
+
+	write_seqlock_bh(&priv->lock);
+	priv->bytes += pkt->skb->len;
+	priv->packets++;
+	write_sequnlock_bh(&priv->lock);
+}
+
+static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	struct nft_counter *priv = nft_expr_priv(expr);
+	unsigned int seq;
+	u64 bytes;
+	u64 packets;
+
+	do {
+		seq = read_seqbegin(&priv->lock);
+		bytes	= priv->bytes;
+		packets	= priv->packets;
+	} while (read_seqretry(&priv->lock, seq));
+
+	if (nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(bytes)))
+		goto nla_put_failure;
+	if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(packets)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
+	[NFTA_COUNTER_PACKETS]	= { .type = NLA_U64 },
+	[NFTA_COUNTER_BYTES]	= { .type = NLA_U64 },
+};
+
+static int nft_counter_init(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nlattr * const tb[])
+{
+	struct nft_counter *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_COUNTER_PACKETS])
+	        priv->packets = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+	if (tb[NFTA_COUNTER_BYTES])
+		priv->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+
+	seqlock_init(&priv->lock);
+	return 0;
+}
+
+static struct nft_expr_ops nft_counter_ops __read_mostly = {
+	.name		= "counter",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_counter)),
+	.policy		= nft_counter_policy,
+	.maxattr	= NFTA_COUNTER_MAX,
+	.owner		= THIS_MODULE,
+	.eval		= nft_counter_eval,
+	.init		= nft_counter_init,
+	.dump		= nft_counter_dump,
+};
+
+static int __init nft_counter_module_init(void)
+{
+	return nft_register_expr(&nft_counter_ops);
+}
+
+static void __exit nft_counter_module_exit(void)
+{
+	nft_unregister_expr(&nft_counter_ops);
+}
+
+module_init(nft_counter_module_init);
+module_exit(nft_counter_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("counter");
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
new file mode 100644
index 000000000000..a1756d678226
--- /dev/null
+++ b/net/netfilter/nft_ct.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+
+struct nft_ct {
+	enum nft_ct_keys	key:8;
+	enum ip_conntrack_dir	dir:8;
+	enum nft_registers	dreg:8;
+	uint8_t			family;
+};
+
+static void nft_ct_eval(const struct nft_expr *expr,
+			struct nft_data data[NFT_REG_MAX + 1],
+			const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+	struct nft_data *dest = &data[priv->dreg];
+	enum ip_conntrack_info ctinfo;
+	const struct nf_conn *ct;
+	const struct nf_conn_help *help;
+	const struct nf_conntrack_tuple *tuple;
+	const struct nf_conntrack_helper *helper;
+	long diff;
+	unsigned int state;
+
+	ct = nf_ct_get(pkt->skb, &ctinfo);
+
+	switch (priv->key) {
+	case NFT_CT_STATE:
+		if (ct == NULL)
+			state = NF_CT_STATE_INVALID_BIT;
+		else if (nf_ct_is_untracked(ct))
+			state = NF_CT_STATE_UNTRACKED_BIT;
+		else
+			state = NF_CT_STATE_BIT(ctinfo);
+		dest->data[0] = state;
+		return;
+	}
+
+	if (ct == NULL)
+		goto err;
+
+	switch (priv->key) {
+	case NFT_CT_DIRECTION:
+		dest->data[0] = CTINFO2DIR(ctinfo);
+		return;
+	case NFT_CT_STATUS:
+		dest->data[0] = ct->status;
+		return;
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+		dest->data[0] = ct->mark;
+		return;
+#endif
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+	case NFT_CT_SECMARK:
+		dest->data[0] = ct->secmark;
+		return;
+#endif
+	case NFT_CT_EXPIRATION:
+		diff = (long)jiffies - (long)ct->timeout.expires;
+		if (diff < 0)
+			diff = 0;
+		dest->data[0] = jiffies_to_msecs(diff);
+		return;
+	case NFT_CT_HELPER:
+		if (ct->master == NULL)
+			goto err;
+		help = nfct_help(ct->master);
+		if (help == NULL)
+			goto err;
+		helper = rcu_dereference(help->helper);
+		if (helper == NULL)
+			goto err;
+		if (strlen(helper->name) >= sizeof(dest->data))
+			goto err;
+		strncpy((char *)dest->data, helper->name, sizeof(dest->data));
+		return;
+	}
+
+	tuple = &ct->tuplehash[priv->dir].tuple;
+	switch (priv->key) {
+	case NFT_CT_L3PROTOCOL:
+		dest->data[0] = nf_ct_l3num(ct);
+		return;
+	case NFT_CT_SRC:
+		memcpy(dest->data, tuple->src.u3.all,
+		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+		return;
+	case NFT_CT_DST:
+		memcpy(dest->data, tuple->dst.u3.all,
+		       nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16);
+		return;
+	case NFT_CT_PROTOCOL:
+		dest->data[0] = nf_ct_protonum(ct);
+		return;
+	case NFT_CT_PROTO_SRC:
+		dest->data[0] = (__force __u16)tuple->src.u.all;
+		return;
+	case NFT_CT_PROTO_DST:
+		dest->data[0] = (__force __u16)tuple->dst.u.all;
+		return;
+	}
+	return;
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = {
+	[NFTA_CT_DREG]		= { .type = NLA_U32 },
+	[NFTA_CT_KEY]		= { .type = NLA_U32 },
+	[NFTA_CT_DIRECTION]	= { .type = NLA_U8 },
+};
+
+static int nft_ct_init(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nlattr * const tb[])
+{
+	struct nft_ct *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_CT_DREG] == NULL ||
+	    tb[NFTA_CT_KEY] == NULL)
+		return -EINVAL;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
+	if (tb[NFTA_CT_DIRECTION] != NULL) {
+		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
+		switch (priv->dir) {
+		case IP_CT_DIR_ORIGINAL:
+		case IP_CT_DIR_REPLY:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	switch (priv->key) {
+	case NFT_CT_STATE:
+	case NFT_CT_DIRECTION:
+	case NFT_CT_STATUS:
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+#endif
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+	case NFT_CT_SECMARK:
+#endif
+	case NFT_CT_EXPIRATION:
+	case NFT_CT_HELPER:
+		if (tb[NFTA_CT_DIRECTION] != NULL)
+			return -EINVAL;
+		break;
+	case NFT_CT_PROTOCOL:
+	case NFT_CT_SRC:
+	case NFT_CT_DST:
+	case NFT_CT_PROTO_SRC:
+	case NFT_CT_PROTO_DST:
+		if (tb[NFTA_CT_DIRECTION] == NULL)
+			return -EINVAL;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	err = nf_ct_l3proto_try_module_get(ctx->afi->family);
+	if (err < 0)
+		return err;
+	priv->family = ctx->afi->family;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		goto err1;
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		goto err1;
+	return 0;
+
+err1:
+	nf_ct_l3proto_module_put(ctx->afi->family);
+	return err;
+}
+
+static void nft_ct_destroy(const struct nft_expr *expr)
+{
+	struct nft_ct *priv = nft_expr_priv(expr);
+
+	nf_ct_l3proto_module_put(priv->family);
+}
+
+static int nft_ct_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_ct *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_CT_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_ct_ops __read_mostly = {
+	.name		= "ct",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_ct_eval,
+	.init		= nft_ct_init,
+	.destroy	= nft_ct_destroy,
+	.dump		= nft_ct_dump,
+	.policy		= nft_ct_policy,
+	.maxattr	= NFTA_CT_MAX,
+};
+
+static int __init nft_ct_module_init(void)
+{
+	return nft_register_expr(&nft_ct_ops);
+}
+
+static void __exit nft_ct_module_exit(void)
+{
+	nft_unregister_expr(&nft_ct_ops);
+}
+
+module_init(nft_ct_module_init);
+module_exit(nft_ct_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("ct");
diff --git a/net/netfilter/nft_expr_template.c b/net/netfilter/nft_expr_template.c
new file mode 100644
index 000000000000..9fc8eb308193
--- /dev/null
+++ b/net/netfilter/nft_expr_template.c
@@ -0,0 +1,88 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_template {
+
+};
+
+static void nft_template_eval(const struct nft_expr *expr,
+			      struct nft_data data[NFT_REG_MAX + 1],
+			      const struct nft_pktinfo *pkt)
+{
+	struct nft_template *priv = nft_expr_priv(expr);
+
+}
+
+static const struct nla_policy nft_template_policy[NFTA_TEMPLATE_MAX + 1] = {
+	[NFTA_TEMPLATE_ATTR]		= { .type = NLA_U32 },
+};
+
+static int nft_template_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr *tb[])
+{
+	struct nft_template *priv = nft_expr_priv(expr);
+
+	return 0;
+}
+
+static void nft_template_destroy(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr)
+{
+	struct nft_template *priv = nft_expr_priv(expr);
+
+}
+
+static int nft_template_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_template *priv = nft_expr_priv(expr);
+
+	NLA_PUT_BE32(skb, NFTA_TEMPLATE_ATTR, priv->field);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops template_ops __read_mostly = {
+	.name		= "template",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_template)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_template_eval,
+	.init		= nft_template_init,
+	.destroy	= nft_template_destroy,
+	.dump		= nft_template_dump,
+	.policy		= nft_template_policy,
+	.maxattr	= NFTA_TEMPLATE_MAX,
+};
+
+static int __init nft_template_module_init(void)
+{
+	return nft_register_expr(&template_ops);
+}
+
+static void __exit nft_template_module_exit(void)
+{
+	nft_unregister_expr(&template_ops);
+}
+
+module_init(nft_template_module_init);
+module_exit(nft_template_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("template");
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
new file mode 100644
index 000000000000..21c6a6b7b662
--- /dev/null
+++ b/net/netfilter/nft_exthdr.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+// FIXME:
+#include <net/ipv6.h>
+
+struct nft_exthdr {
+	u8			type;
+	u8			offset;
+	u8			len;
+	enum nft_registers	dreg:8;
+};
+
+static void nft_exthdr_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	struct nft_data *dest = &data[priv->dreg];
+	unsigned int offset;
+	int err;
+
+	err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
+	if (err < 0)
+		goto err;
+	offset += priv->offset;
+
+	if (skb_copy_bits(pkt->skb, offset, dest->data, priv->len) < 0)
+		goto err;
+	return;
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
+	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
+	[NFTA_EXTHDR_TYPE]		= { .type = NLA_U8 },
+	[NFTA_EXTHDR_OFFSET]		= { .type = NLA_U32 },
+	[NFTA_EXTHDR_LEN]		= { .type = NLA_U32 },
+};
+
+static int nft_exthdr_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_EXTHDR_DREG] == NULL ||
+	    tb[NFTA_EXTHDR_TYPE] == NULL ||
+	    tb[NFTA_EXTHDR_OFFSET] == NULL ||
+	    tb[NFTA_EXTHDR_LEN] == NULL)
+		return -EINVAL;
+
+	priv->type   = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
+	priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET]));
+	priv->len    = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN]));
+	if (priv->len == 0 ||
+	    priv->len > FIELD_SIZEOF(struct nft_data, data))
+		return -EINVAL;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_EXTHDR_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_exthdr *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_EXTHDR_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+	if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_EXTHDR_OFFSET, htonl(priv->offset)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_EXTHDR_LEN, htonl(priv->len)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops exthdr_ops __read_mostly = {
+	.name		= "exthdr",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_exthdr_eval,
+	.init		= nft_exthdr_init,
+	.dump		= nft_exthdr_dump,
+	.policy		= nft_exthdr_policy,
+	.maxattr	= NFTA_EXTHDR_MAX,
+};
+
+static int __init nft_exthdr_module_init(void)
+{
+	return nft_register_expr(&exthdr_ops);
+}
+
+static void __exit nft_exthdr_module_exit(void)
+{
+	nft_unregister_expr(&exthdr_ops);
+}
+
+module_init(nft_exthdr_module_init);
+module_exit(nft_exthdr_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("exthdr");
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
new file mode 100644
index 000000000000..67cc502881f1
--- /dev/null
+++ b/net/netfilter/nft_hash.c
@@ -0,0 +1,348 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_hash {
+	struct hlist_head	*hash;
+	unsigned int		hsize;
+	enum nft_registers	sreg:8;
+	enum nft_registers	dreg:8;
+	u8			klen;
+	u8			dlen;
+	u16			flags;
+};
+
+struct nft_hash_elem {
+	struct hlist_node	hnode;
+	struct nft_data		key;
+	struct nft_data		data[];
+};
+
+static u32 nft_hash_rnd __read_mostly;
+static bool nft_hash_rnd_initted __read_mostly;
+
+static unsigned int nft_hash_data(const struct nft_data *data,
+				  unsigned int hsize, unsigned int len)
+{
+	unsigned int h;
+
+	// FIXME: can we reasonably guarantee the upper bits are fixed?
+	h = jhash2(data->data, len >> 2, nft_hash_rnd);
+	return ((u64)h * hsize) >> 32;
+}
+
+static void nft_hash_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	const struct nft_hash *priv = nft_expr_priv(expr);
+	const struct nft_hash_elem *elem;
+	const struct nft_data *key = &data[priv->sreg];
+	unsigned int h;
+
+	h = nft_hash_data(key, priv->hsize, priv->klen);
+	hlist_for_each_entry(elem, &priv->hash[h], hnode) {
+		if (nft_data_cmp(&elem->key, key, priv->klen))
+			continue;
+		if (priv->flags & NFT_HASH_MAP)
+			nft_data_copy(&data[priv->dreg], elem->data);
+		return;
+	}
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static void nft_hash_elem_destroy(const struct nft_expr *expr,
+				  struct nft_hash_elem *elem)
+{
+	const struct nft_hash *priv = nft_expr_priv(expr);
+
+	nft_data_uninit(&elem->key, NFT_DATA_VALUE);
+	if (priv->flags & NFT_HASH_MAP)
+		nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
+	kfree(elem);
+}
+
+static const struct nla_policy nft_he_policy[NFTA_HE_MAX + 1] = {
+	[NFTA_HE_KEY]		= { .type = NLA_NESTED },
+	[NFTA_HE_DATA]		= { .type = NLA_NESTED },
+};
+
+static int nft_hash_elem_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr *nla,
+			      struct nft_hash_elem **new)
+{
+	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nlattr *tb[NFTA_HE_MAX + 1];
+	struct nft_hash_elem *elem;
+	struct nft_data_desc d1, d2;
+	unsigned int size;
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_HE_MAX, nla, nft_he_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_HE_KEY] == NULL)
+		return -EINVAL;
+	size = sizeof(*elem);
+
+	if (priv->flags & NFT_HASH_MAP) {
+		if (tb[NFTA_HE_DATA] == NULL)
+			return -EINVAL;
+		size += sizeof(elem->data[0]);
+	} else {
+		if (tb[NFTA_HE_DATA] != NULL)
+			return -EINVAL;
+	}
+
+	elem = kzalloc(size, GFP_KERNEL);
+	if (elem == NULL)
+		return -ENOMEM;
+
+	err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_HE_KEY]);
+	if (err < 0)
+		goto err1;
+	err = -EINVAL;
+	if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
+		goto err2;
+
+	if (tb[NFTA_HE_DATA] != NULL) {
+		err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_HE_DATA]);
+		if (err < 0)
+			goto err2;
+		err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
+		if (err < 0)
+			goto err3;
+	}
+
+	*new = elem;
+	return 0;
+
+err3:
+	nft_data_uninit(elem->data, d2.type);
+err2:
+	nft_data_uninit(&elem->key, d1.type);
+err1:
+	kfree(elem);
+	return err;
+}
+
+static int nft_hash_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
+			      const struct nft_hash_elem *elem)
+
+{
+	const struct nft_hash *priv = nft_expr_priv(expr);
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_HE_KEY, &elem->key,
+			  NFT_DATA_VALUE, priv->klen) < 0)
+		goto nla_put_failure;
+
+	if (priv->flags & NFT_HASH_MAP) {
+		if (nft_data_dump(skb, NFTA_HE_DATA, elem->data,
+				  NFT_DATA_VALUE, priv->dlen) < 0)
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static void nft_hash_destroy(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr)
+{
+	const struct nft_hash *priv = nft_expr_priv(expr);
+	const struct hlist_node *next;
+	struct nft_hash_elem *elem;
+	unsigned int i;
+
+	for (i = 0; i < priv->hsize; i++) {
+		hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
+			hlist_del(&elem->hnode);
+			nft_hash_elem_destroy(expr, elem);
+		}
+	}
+	kfree(priv->hash);
+}
+
+static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
+	[NFTA_HASH_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_HASH_SREG]	= { .type = NLA_U32 },
+	[NFTA_HASH_DREG]	= { .type = NLA_U32 },
+	[NFTA_HASH_KLEN]	= { .type = NLA_U32 },
+	[NFTA_HASH_ELEMENTS]	= { .type = NLA_NESTED },
+};
+
+static int nft_hash_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			 const struct nlattr * const tb[])
+{
+	struct nft_hash *priv = nft_expr_priv(expr);
+	struct nft_hash_elem *elem, *uninitialized_var(new);
+	const struct nlattr *nla;
+	unsigned int cnt, i;
+	unsigned int h;
+	int err, rem;
+
+	if (unlikely(!nft_hash_rnd_initted)) {
+		get_random_bytes(&nft_hash_rnd, 4);
+		nft_hash_rnd_initted = true;
+	}
+
+	if (tb[NFTA_HASH_SREG] == NULL ||
+	    tb[NFTA_HASH_KLEN] == NULL ||
+	    tb[NFTA_HASH_ELEMENTS] == NULL)
+		return -EINVAL;
+
+	if (tb[NFTA_HASH_FLAGS] != NULL) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_HASH_FLAGS]));
+		if (priv->flags & ~NFT_HASH_MAP)
+			return -EINVAL;
+	}
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_HASH_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_HASH_DREG] != NULL) {
+		if (!(priv->flags & NFT_HASH_MAP))
+			return -EINVAL;
+		priv->dreg = ntohl(nla_get_be32(tb[NFTA_HASH_DREG]));
+		err = nft_validate_output_register(priv->dreg);
+		if (err < 0)
+			return err;
+	}
+
+	priv->klen = ntohl(nla_get_be32(tb[NFTA_HASH_KLEN]));
+	if (priv->klen == 0)
+		return -EINVAL;
+
+	cnt = 0;
+	nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
+		if (nla_type(nla) != NFTA_LIST_ELEM)
+			return -EINVAL;
+		cnt++;
+	}
+
+	/* Aim for a load factor of 0.75 */
+	cnt = cnt * 4 / 3;
+
+	priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL);
+	if (priv->hash == NULL)
+		return -ENOMEM;
+	priv->hsize = cnt;
+
+	for (i = 0; i < cnt; i++)
+		INIT_HLIST_HEAD(&priv->hash[i]);
+
+	err = -ENOMEM;
+	nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
+		err = nft_hash_elem_init(ctx, expr, nla, &new);
+		if (err < 0)
+			goto err1;
+
+		h = nft_hash_data(&new->key, priv->hsize, priv->klen);
+		hlist_for_each_entry(elem, &priv->hash[h], hnode) {
+			if (nft_data_cmp(&elem->key, &new->key, priv->klen))
+				continue;
+			nft_hash_elem_destroy(expr, new);
+			err = -EEXIST;
+			goto err1;
+		}
+		hlist_add_head(&new->hnode, &priv->hash[h]);
+	}
+	return 0;
+
+err1:
+	nft_hash_destroy(ctx, expr);
+	return err;
+}
+
+static int nft_hash_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_hash *priv = nft_expr_priv(expr);
+	const struct nft_hash_elem *elem;
+	struct nlattr *list;
+	unsigned int i;
+
+	if (priv->flags)
+		if (nla_put_be32(skb, NFTA_HASH_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (priv->flags & NFT_HASH_MAP)
+		if (nla_put_be32(skb, NFTA_HASH_DREG, htonl(priv->dreg)))
+			goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_HASH_KLEN, htonl(priv->klen)))
+		goto nla_put_failure;
+
+	list = nla_nest_start(skb, NFTA_HASH_ELEMENTS);
+	if (list == NULL)
+		goto nla_put_failure;
+
+	for (i = 0; i < priv->hsize; i++) {
+		hlist_for_each_entry(elem, &priv->hash[i], hnode) {
+			if (nft_hash_elem_dump(skb, expr, elem) < 0)
+				goto nla_put_failure;
+		}
+	}
+
+	nla_nest_end(skb, list);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_hash_ops __read_mostly = {
+	.name		= "hash",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_hash)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_hash_eval,
+	.init		= nft_hash_init,
+	.destroy	= nft_hash_destroy,
+	.dump		= nft_hash_dump,
+	.policy		= nft_hash_policy,
+	.maxattr	= NFTA_HASH_MAX,
+};
+
+static int __init nft_hash_module_init(void)
+{
+	return nft_register_expr(&nft_hash_ops);
+}
+
+static void __exit nft_hash_module_exit(void)
+{
+	nft_unregister_expr(&nft_hash_ops);
+}
+
+module_init(nft_hash_module_init);
+module_exit(nft_hash_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("hash");
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
new file mode 100644
index 000000000000..3bf42c3cc49a
--- /dev/null
+++ b/net/netfilter/nft_immediate.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_immediate_expr {
+	struct nft_data		data;
+	enum nft_registers	dreg:8;
+	u8			dlen;
+};
+
+static void nft_immediate_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+	nft_data_copy(&data[priv->dreg], &priv->data);
+}
+
+static const struct nla_policy nft_immediate_policy[NFTA_IMMEDIATE_MAX + 1] = {
+	[NFTA_IMMEDIATE_DREG]	= { .type = NLA_U32 },
+	[NFTA_IMMEDIATE_DATA]	= { .type = NLA_NESTED },
+};
+
+static int nft_immediate_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc;
+	int err;
+
+	if (tb[NFTA_IMMEDIATE_DREG] == NULL ||
+	    tb[NFTA_IMMEDIATE_DATA] == NULL)
+		return -EINVAL;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_IMMEDIATE_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+
+	err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
+	if (err < 0)
+		return err;
+	priv->dlen = desc.len;
+
+	err = nft_validate_data_load(ctx, priv->dreg, &priv->data, desc.type);
+	if (err < 0)
+		goto err1;
+
+	return 0;
+
+err1:
+	nft_data_uninit(&priv->data, desc.type);
+	return err;
+}
+
+static void nft_immediate_destroy(const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg));
+}
+
+static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_IMMEDIATE_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+
+	return nft_data_dump(skb, NFTA_IMMEDIATE_DATA, &priv->data,
+			     nft_dreg_to_type(priv->dreg), priv->dlen);
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_imm_ops __read_mostly = {
+	.name		= "immediate",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_immediate_eval,
+	.init		= nft_immediate_init,
+	.destroy	= nft_immediate_destroy,
+	.dump		= nft_immediate_dump,
+	.policy		= nft_immediate_policy,
+	.maxattr	= NFTA_IMMEDIATE_MAX,
+};
+
+int __init nft_immediate_module_init(void)
+{
+	return nft_register_expr(&nft_imm_ops);
+}
+
+void nft_immediate_module_exit(void)
+{
+	nft_unregister_expr(&nft_imm_ops);
+}
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
new file mode 100644
index 000000000000..e0e3fc8aebc3
--- /dev/null
+++ b/net/netfilter/nft_limit.c
@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+static DEFINE_SPINLOCK(limit_lock);
+
+struct nft_limit {
+	u64		tokens;
+	u64		rate;
+	u64		unit;
+	unsigned long	stamp;
+};
+
+static void nft_limit_eval(const struct nft_expr *expr,
+			   struct nft_data data[NFT_REG_MAX + 1],
+			   const struct nft_pktinfo *pkt)
+{
+	struct nft_limit *priv = nft_expr_priv(expr);
+
+	spin_lock_bh(&limit_lock);
+	if (time_after_eq(jiffies, priv->stamp)) {
+		priv->tokens = priv->rate;
+		priv->stamp = jiffies + priv->unit * HZ;
+	}
+
+	if (priv->tokens >= 1) {
+		priv->tokens--;
+		spin_unlock_bh(&limit_lock);
+		return;
+	}
+	spin_unlock_bh(&limit_lock);
+
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_limit_policy[NFTA_LIMIT_MAX + 1] = {
+	[NFTA_LIMIT_RATE]	= { .type = NLA_U64 },
+	[NFTA_LIMIT_UNIT]	= { .type = NLA_U64 },
+};
+
+static int nft_limit_init(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr,
+			  const struct nlattr * const tb[])
+{
+	struct nft_limit *priv = nft_expr_priv(expr);
+
+	if (tb[NFTA_LIMIT_RATE] == NULL ||
+	    tb[NFTA_LIMIT_UNIT] == NULL)
+		return -EINVAL;
+
+	priv->rate   = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_RATE]));
+	priv->unit   = be64_to_cpu(nla_get_be64(tb[NFTA_LIMIT_UNIT]));
+	priv->stamp  = jiffies + priv->unit * HZ;
+	priv->tokens = priv->rate;
+	return 0;
+}
+
+static int nft_limit_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_limit *priv = nft_expr_priv(expr);
+
+	if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(priv->rate)))
+		goto nla_put_failure;
+	if (nla_put_be64(skb, NFTA_LIMIT_UNIT, cpu_to_be64(priv->unit)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_limit_ops __read_mostly = {
+	.name		= "limit",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_limit)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_limit_eval,
+	.init		= nft_limit_init,
+	.dump		= nft_limit_dump,
+	.policy		= nft_limit_policy,
+	.maxattr	= NFTA_LIMIT_MAX,
+};
+
+static int __init nft_limit_module_init(void)
+{
+	return nft_register_expr(&nft_limit_ops);
+}
+
+static void __exit nft_limit_module_exit(void)
+{
+	nft_unregister_expr(&nft_limit_ops);
+}
+
+module_init(nft_limit_module_init);
+module_exit(nft_limit_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("limit");
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
new file mode 100644
index 000000000000..da495c3b1e7e
--- /dev/null
+++ b/net/netfilter/nft_log.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/netdevice.h>
+
+static const char *nft_log_null_prefix = "";
+
+struct nft_log {
+	struct nf_loginfo	loginfo;
+	char			*prefix;
+	int			family;
+};
+
+static void nft_log_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_log *priv = nft_expr_priv(expr);
+	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
+
+	nf_log_packet(net, priv->family, pkt->hooknum, pkt->skb, pkt->in,
+		      pkt->out, &priv->loginfo, "%s", priv->prefix);
+}
+
+static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
+	[NFTA_LOG_GROUP]	= { .type = NLA_U16 },
+	[NFTA_LOG_PREFIX]	= { .type = NLA_STRING },
+	[NFTA_LOG_SNAPLEN]	= { .type = NLA_U32 },
+	[NFTA_LOG_QTHRESHOLD]	= { .type = NLA_U16 },
+};
+
+static int nft_log_init(const struct nft_ctx *ctx,
+			const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_log *priv = nft_expr_priv(expr);
+	struct nf_loginfo *li = &priv->loginfo;
+	const struct nlattr *nla;
+
+	priv->family = ctx->afi->family;
+
+	nla = tb[NFTA_LOG_PREFIX];
+	if (nla != NULL) {
+		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
+		if (priv->prefix == NULL)
+			return -ENOMEM;
+		nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+	} else
+		priv->prefix = (char *)nft_log_null_prefix;
+
+	li->type = NF_LOG_TYPE_ULOG;
+	if (tb[NFTA_LOG_GROUP] != NULL)
+		li->u.ulog.group = ntohs(nla_get_be16(tb[NFTA_LOG_GROUP]));
+
+	if (tb[NFTA_LOG_SNAPLEN] != NULL)
+		li->u.ulog.copy_len = ntohl(nla_get_be32(tb[NFTA_LOG_SNAPLEN]));
+	if (tb[NFTA_LOG_QTHRESHOLD] != NULL) {
+		li->u.ulog.qthreshold =
+			ntohs(nla_get_be16(tb[NFTA_LOG_QTHRESHOLD]));
+	}
+
+	return 0;
+}
+
+static void nft_log_destroy(const struct nft_expr *expr)
+{
+	struct nft_log *priv = nft_expr_priv(expr);
+
+	if (priv->prefix != nft_log_null_prefix)
+		kfree(priv->prefix);
+}
+
+static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_log *priv = nft_expr_priv(expr);
+	const struct nf_loginfo *li = &priv->loginfo;
+
+	if (priv->prefix != nft_log_null_prefix)
+		if (nla_put_string(skb, NFTA_LOG_PREFIX, priv->prefix))
+			goto nla_put_failure;
+	if (li->u.ulog.group)
+		if (nla_put_be16(skb, NFTA_LOG_GROUP, htons(li->u.ulog.group)))
+			goto nla_put_failure;
+	if (li->u.ulog.copy_len)
+		if (nla_put_be32(skb, NFTA_LOG_SNAPLEN,
+				 htonl(li->u.ulog.copy_len)))
+			goto nla_put_failure;
+	if (li->u.ulog.qthreshold)
+		if (nla_put_be16(skb, NFTA_LOG_QTHRESHOLD,
+				 htons(li->u.ulog.qthreshold)))
+			goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_log_ops __read_mostly = {
+	.name		= "log",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_log)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_log_eval,
+	.init		= nft_log_init,
+	.destroy	= nft_log_destroy,
+	.dump		= nft_log_dump,
+	.policy		= nft_log_policy,
+	.maxattr	= NFTA_LOG_MAX,
+};
+
+static int __init nft_log_module_init(void)
+{
+	return nft_register_expr(&nft_log_ops);
+}
+
+static void __exit nft_log_module_exit(void)
+{
+	nft_unregister_expr(&nft_log_ops);
+}
+
+module_init(nft_log_module_init);
+module_exit(nft_log_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("log");
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
new file mode 100644
index 000000000000..96735aa2f039
--- /dev/null
+++ b/net/netfilter/nft_meta.c
@@ -0,0 +1,222 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/tcp_states.h> /* for TCP_TIME_WAIT */
+#include <net/netfilter/nf_tables.h>
+
+struct nft_meta {
+	enum nft_meta_keys	key:8;
+	enum nft_registers	dreg:8;
+};
+
+static void nft_meta_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	const struct sk_buff *skb = pkt->skb;
+	const struct net_device *in = pkt->in, *out = pkt->out;
+	struct nft_data *dest = &data[priv->dreg];
+
+	switch (priv->key) {
+	case NFT_META_LEN:
+		dest->data[0] = skb->len;
+		break;
+	case NFT_META_PROTOCOL:
+		*(__be16 *)dest->data = skb->protocol;
+		break;
+	case NFT_META_PRIORITY:
+		dest->data[0] = skb->priority;
+		break;
+	case NFT_META_MARK:
+		dest->data[0] = skb->mark;
+		break;
+	case NFT_META_IIF:
+		if (in == NULL)
+			goto err;
+		dest->data[0] = in->ifindex;
+		break;
+	case NFT_META_OIF:
+		if (out == NULL)
+			goto err;
+		dest->data[0] = out->ifindex;
+		break;
+	case NFT_META_IIFNAME:
+		if (in == NULL)
+			goto err;
+		strncpy((char *)dest->data, in->name, sizeof(dest->data));
+		break;
+	case NFT_META_OIFNAME:
+		if (out == NULL)
+			goto err;
+		strncpy((char *)dest->data, out->name, sizeof(dest->data));
+		break;
+	case NFT_META_IIFTYPE:
+		if (in == NULL)
+			goto err;
+		*(u16 *)dest->data = in->type;
+		break;
+	case NFT_META_OIFTYPE:
+		if (out == NULL)
+			goto err;
+		*(u16 *)dest->data = out->type;
+		break;
+	case NFT_META_SKUID:
+		if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+			goto err;
+
+		read_lock_bh(&skb->sk->sk_callback_lock);
+		if (skb->sk->sk_socket == NULL ||
+		    skb->sk->sk_socket->file == NULL) {
+			read_unlock_bh(&skb->sk->sk_callback_lock);
+			goto err;
+		}
+
+		dest->data[0] =
+			from_kuid_munged(&init_user_ns,
+				skb->sk->sk_socket->file->f_cred->fsuid);
+		read_unlock_bh(&skb->sk->sk_callback_lock);
+		break;
+	case NFT_META_SKGID:
+		if (skb->sk == NULL || skb->sk->sk_state == TCP_TIME_WAIT)
+			goto err;
+
+		read_lock_bh(&skb->sk->sk_callback_lock);
+		if (skb->sk->sk_socket == NULL ||
+		    skb->sk->sk_socket->file == NULL) {
+			read_unlock_bh(&skb->sk->sk_callback_lock);
+			goto err;
+		}
+		dest->data[0] =
+			from_kgid_munged(&init_user_ns,
+				 skb->sk->sk_socket->file->f_cred->fsgid);
+		read_unlock_bh(&skb->sk->sk_callback_lock);
+		break;
+#ifdef CONFIG_NET_CLS_ROUTE
+	case NFT_META_RTCLASSID: {
+		const struct dst_entry *dst = skb_dst(skb);
+
+		if (dst == NULL)
+			goto err;
+		dest->data[0] = dst->tclassid;
+		break;
+	}
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+		dest->data[0] = skb->secmark;
+		break;
+#endif
+	default:
+		WARN_ON(1);
+		goto err;
+	}
+	return;
+
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+	[NFTA_META_DREG]	= { .type = NLA_U32 },
+	[NFTA_META_KEY]		= { .type = NLA_U32 },
+};
+
+static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			 const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_META_DREG] == NULL ||
+	    tb[NFTA_META_KEY] == NULL)
+		return -EINVAL;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_LEN:
+	case NFT_META_PROTOCOL:
+	case NFT_META_PRIORITY:
+	case NFT_META_MARK:
+	case NFT_META_IIF:
+	case NFT_META_OIF:
+	case NFT_META_IIFNAME:
+	case NFT_META_OIFNAME:
+	case NFT_META_IIFTYPE:
+	case NFT_META_OIFTYPE:
+	case NFT_META_SKUID:
+	case NFT_META_SKGID:
+#ifdef CONFIG_NET_CLS_ROUTE
+	case NFT_META_RTCLASSID:
+#endif
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+#endif
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_META_DREG, htonl(priv->dreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_META_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_meta_ops __read_mostly = {
+	.name		= "meta",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_meta_eval,
+	.init		= nft_meta_init,
+	.dump		= nft_meta_dump,
+	.policy		= nft_meta_policy,
+	.maxattr	= NFTA_META_MAX,
+};
+
+static int __init nft_meta_module_init(void)
+{
+	return nft_register_expr(&nft_meta_ops);
+}
+
+static void __exit nft_meta_module_exit(void)
+{
+	nft_unregister_expr(&nft_meta_ops);
+}
+
+module_init(nft_meta_module_init);
+module_exit(nft_meta_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("meta");
diff --git a/net/netfilter/nft_meta_target.c b/net/netfilter/nft_meta_target.c
new file mode 100644
index 000000000000..71177df75ffb
--- /dev/null
+++ b/net/netfilter/nft_meta_target.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_meta {
+	enum nft_meta_keys	key;
+};
+
+static void nft_meta_eval(const struct nft_expr *expr,
+			  struct nft_data *nfres,
+			  struct nft_data *data,
+			  const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *meta = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	u32 val = data->data[0];
+
+	switch (meta->key) {
+	case NFT_META_MARK:
+		skb->mark = val;
+		break;
+	case NFT_META_PRIORITY:
+		skb->priority = val;
+		break;
+	case NFT_META_NFTRACE:
+		skb->nf_trace = val;
+		break;
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+		skb->secmark = val;
+		break;
+#endif
+	default:
+		WARN_ON(1);
+	}
+}
+
+static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+	[NFTA_META_KEY]		= { .type = NLA_U32 },
+};
+
+static int nft_meta_init(const struct nft_expr *expr, struct nlattr *tb[])
+{
+	struct nft_meta *meta = nft_expr_priv(expr);
+
+	if (tb[NFTA_META_KEY] == NULL)
+		return -EINVAL;
+
+	meta->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (meta->key) {
+	case NFT_META_MARK:
+	case NFT_META_PRIORITY:
+	case NFT_META_NFTRACE:
+#ifdef CONFIG_NETWORK_SECMARK
+	case NFT_META_SECMARK:
+#endif
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nft_meta_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	struct nft_meta *meta = nft_expr_priv(expr);
+
+	NLA_PUT_BE32(skb, NFTA_META_KEY, htonl(meta->key));
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops meta_target __read_mostly = {
+	.name		= "meta",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_meta_eval,
+	.init		= nft_meta_init,
+	.dump		= nft_meta_dump,
+	.policy		= nft_meta_policy,
+	.maxattr	= NFTA_META_MAX,
+};
+
+static int __init nft_meta_target_init(void)
+{
+	return nft_register_expr(&meta_target);
+}
+
+static void __exit nft_meta_target_exit(void)
+{
+	nft_unregister_expr(&meta_target);
+}
+
+module_init(nft_meta_target_init);
+module_exit(nft_meta_target_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("meta");
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
new file mode 100644
index 000000000000..329f134b3f89
--- /dev/null
+++ b/net/netfilter/nft_payload.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_payload {
+	enum nft_payload_bases	base:8;
+	u8			offset;
+	u8			len;
+	enum nft_registers	dreg:8;
+};
+
+static void nft_payload_eval(const struct nft_expr *expr,
+			     struct nft_data data[NFT_REG_MAX + 1],
+			     const struct nft_pktinfo *pkt)
+{
+	const struct nft_payload *priv = nft_expr_priv(expr);
+	const struct sk_buff *skb = pkt->skb;
+	struct nft_data *dest = &data[priv->dreg];
+	int offset;
+
+	switch (priv->base) {
+	case NFT_PAYLOAD_LL_HEADER:
+		if (!skb_mac_header_was_set(skb))
+			goto err;
+		offset = skb_mac_header(skb) - skb->data;
+		break;
+	case NFT_PAYLOAD_NETWORK_HEADER:
+		offset = skb_network_offset(skb);
+		break;
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		offset = skb_transport_offset(skb);
+		break;
+	default:
+		BUG();
+	}
+	offset += priv->offset;
+
+	if (skb_copy_bits(skb, offset, dest->data, priv->len) < 0)
+		goto err;
+	return;
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
+	[NFTA_PAYLOAD_DREG]	= { .type = NLA_U32 },
+	[NFTA_PAYLOAD_BASE]	= { .type = NLA_U32 },
+	[NFTA_PAYLOAD_OFFSET]	= { .type = NLA_U32 },
+	[NFTA_PAYLOAD_LEN]	= { .type = NLA_U32 },
+};
+
+static int nft_payload_init(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nlattr * const tb[])
+{
+	struct nft_payload *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_PAYLOAD_DREG] == NULL ||
+	    tb[NFTA_PAYLOAD_BASE] == NULL ||
+	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||
+	    tb[NFTA_PAYLOAD_LEN] == NULL)
+		return -EINVAL;
+
+	priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
+	switch (priv->base) {
+	case NFT_PAYLOAD_LL_HEADER:
+	case NFT_PAYLOAD_NETWORK_HEADER:
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
+	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	if (priv->len == 0 ||
+	    priv->len > FIELD_SIZEOF(struct nft_data, data))
+		return -EINVAL;
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+	return nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+}
+
+static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_payload *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_PAYLOAD_DREG, htonl(priv->dreg)) ||
+	    nla_put_be32(skb, NFTA_PAYLOAD_BASE, htonl(priv->base)) ||
+	    nla_put_be32(skb, NFTA_PAYLOAD_OFFSET, htonl(priv->offset)) ||
+	    nla_put_be32(skb, NFTA_PAYLOAD_LEN, htonl(priv->len)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_payload_ops __read_mostly = {
+	.name		= "payload",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_payload)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_payload_eval,
+	.init		= nft_payload_init,
+	.dump		= nft_payload_dump,
+	.policy		= nft_payload_policy,
+	.maxattr	= NFTA_PAYLOAD_MAX,
+};
+
+int __init nft_payload_module_init(void)
+{
+	return nft_register_expr(&nft_payload_ops);
+}
+
+void nft_payload_module_exit(void)
+{
+	nft_unregister_expr(&nft_payload_ops);
+}
diff --git a/net/netfilter/nft_set.c b/net/netfilter/nft_set.c
new file mode 100644
index 000000000000..7b7c8354c327
--- /dev/null
+++ b/net/netfilter/nft_set.c
@@ -0,0 +1,381 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_set {
+	struct rb_root		root;
+	enum nft_registers	sreg:8;
+	enum nft_registers	dreg:8;
+	u8			klen;
+	u8			dlen;
+	u16			flags;
+};
+
+struct nft_set_elem {
+	struct rb_node		node;
+	enum nft_set_elem_flags	flags;
+	struct nft_data		key;
+	struct nft_data		data[];
+};
+
+static void nft_set_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_set *priv = nft_expr_priv(expr);
+	const struct rb_node *parent = priv->root.rb_node;
+	const struct nft_set_elem *elem, *interval = NULL;
+	const struct nft_data *key = &data[priv->sreg];
+	int d;
+
+	while (parent != NULL) {
+		elem = rb_entry(parent, struct nft_set_elem, node);
+
+		d = nft_data_cmp(&elem->key, key, priv->klen);
+		if (d < 0) {
+			parent = parent->rb_left;
+			interval = elem;
+		} else if (d > 0)
+			parent = parent->rb_right;
+		else {
+found:
+			if (elem->flags & NFT_SE_INTERVAL_END)
+				goto out;
+			if (priv->flags & NFT_SET_MAP)
+				nft_data_copy(&data[priv->dreg], elem->data);
+			return;
+		}
+	}
+
+	if (priv->flags & NFT_SET_INTERVAL && interval != NULL) {
+		elem = interval;
+		goto found;
+	}
+out:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static void nft_set_elem_destroy(const struct nft_expr *expr,
+				 struct nft_set_elem *elem)
+{
+	const struct nft_set *priv = nft_expr_priv(expr);
+
+	nft_data_uninit(&elem->key, NFT_DATA_VALUE);
+	if (priv->flags & NFT_SET_MAP)
+		nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
+	kfree(elem);
+}
+
+static const struct nla_policy nft_se_policy[NFTA_SE_MAX + 1] = {
+	[NFTA_SE_KEY]		= { .type = NLA_NESTED },
+	[NFTA_SE_DATA]		= { .type = NLA_NESTED },
+	[NFTA_SE_FLAGS]		= { .type = NLA_U32 },
+};
+
+static int nft_set_elem_init(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr,
+			     const struct nlattr *nla,
+			     struct nft_set_elem **new)
+{
+	struct nft_set *priv = nft_expr_priv(expr);
+	struct nlattr *tb[NFTA_SE_MAX + 1];
+	struct nft_set_elem *elem;
+	struct nft_data_desc d1, d2;
+	enum nft_set_elem_flags flags = 0;
+	unsigned int size;
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_SE_MAX, nla, nft_se_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_SE_KEY] == NULL)
+		return -EINVAL;
+
+	if (tb[NFTA_SE_FLAGS] != NULL) {
+		flags = ntohl(nla_get_be32(tb[NFTA_SE_FLAGS]));
+		if (flags & ~NFT_SE_INTERVAL_END)
+			return -EINVAL;
+	}
+
+	size = sizeof(*elem);
+	if (priv->flags & NFT_SET_MAP) {
+		if (tb[NFTA_SE_DATA] == NULL && !(flags & NFT_SE_INTERVAL_END))
+			return -EINVAL;
+		size += sizeof(elem->data[0]);
+	} else {
+		if (tb[NFTA_SE_DATA] != NULL)
+			return -EINVAL;
+	}
+
+	elem = kzalloc(size, GFP_KERNEL);
+	if (elem == NULL)
+		return -ENOMEM;
+	elem->flags = flags;
+
+	err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_SE_KEY]);
+	if (err < 0)
+		goto err1;
+	err = -EINVAL;
+	if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
+		goto err2;
+
+	if (tb[NFTA_SE_DATA] != NULL) {
+		err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_SE_DATA]);
+		if (err < 0)
+			goto err2;
+		err = -EINVAL;
+		if (priv->dreg != NFT_REG_VERDICT && d2.len != priv->dlen)
+			goto err2;
+		err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
+		if (err < 0)
+			goto err3;
+	}
+
+	*new = elem;
+	return 0;
+
+err3:
+	nft_data_uninit(elem->data, d2.type);
+err2:
+	nft_data_uninit(&elem->key, d1.type);
+err1:
+	kfree(elem);
+	return err;
+}
+
+static int nft_set_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
+			     const struct nft_set_elem *elem)
+
+{
+	const struct nft_set *priv = nft_expr_priv(expr);
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_SE_KEY, &elem->key,
+			  NFT_DATA_VALUE, priv->klen) < 0)
+		goto nla_put_failure;
+
+	if (priv->flags & NFT_SET_MAP && !(elem->flags & NFT_SE_INTERVAL_END)) {
+		if (nft_data_dump(skb, NFTA_SE_DATA, elem->data,
+				  nft_dreg_to_type(priv->dreg), priv->dlen) < 0)
+			goto nla_put_failure;
+	}
+
+	if (elem->flags){
+		if (nla_put_be32(skb, NFTA_SE_FLAGS, htonl(elem->flags)))
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static void nft_set_destroy(const struct nft_expr *expr)
+{
+	struct nft_set *priv = nft_expr_priv(expr);
+	struct nft_set_elem *elem;
+	struct rb_node *node;
+
+	while ((node = priv->root.rb_node) != NULL) {
+		rb_erase(node, &priv->root);
+		elem = rb_entry(node, struct nft_set_elem, node);
+		nft_set_elem_destroy(expr, elem);
+	}
+}
+
+static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
+	[NFTA_SET_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_SET_SREG]		= { .type = NLA_U32 },
+	[NFTA_SET_DREG]		= { .type = NLA_U32 },
+	[NFTA_SET_KLEN]		= { .type = NLA_U32 },
+	[NFTA_SET_DLEN]		= { .type = NLA_U32 },
+	[NFTA_SET_ELEMENTS]	= { .type = NLA_NESTED },
+};
+
+static int nft_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_set *priv = nft_expr_priv(expr);
+	struct nft_set_elem *elem, *uninitialized_var(new);
+	struct rb_node *parent, **p;
+	const struct nlattr *nla;
+	int err, rem, d;
+
+	if (tb[NFTA_SET_SREG] == NULL ||
+	    tb[NFTA_SET_KLEN] == NULL ||
+	    tb[NFTA_SET_ELEMENTS] == NULL)
+		return -EINVAL;
+
+	priv->root = RB_ROOT;
+
+	if (tb[NFTA_SET_FLAGS] != NULL) {
+		priv->flags = ntohl(nla_get_be32(tb[NFTA_SET_FLAGS]));
+		if (priv->flags & ~(NFT_SET_INTERVAL | NFT_SET_MAP))
+			return -EINVAL;
+	}
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_SET_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_SET_DREG] != NULL) {
+		if (!(priv->flags & NFT_SET_MAP))
+			return -EINVAL;
+		if (tb[NFTA_SET_DLEN] == NULL)
+			return -EINVAL;
+
+		priv->dreg = ntohl(nla_get_be32(tb[NFTA_SET_DREG]));
+		err = nft_validate_output_register(priv->dreg);
+		if (err < 0)
+			return err;
+
+		if (priv->dreg == NFT_REG_VERDICT)
+			priv->dlen = FIELD_SIZEOF(struct nft_data, data);
+		else {
+			priv->dlen = ntohl(nla_get_be32(tb[NFTA_SET_DLEN]));
+			if (priv->dlen == 0 ||
+			    priv->dlen > FIELD_SIZEOF(struct nft_data, data))
+				return -EINVAL;
+		}
+	} else {
+		if (priv->flags & NFT_SET_MAP)
+			return -EINVAL;
+		if (tb[NFTA_SET_DLEN] != NULL)
+			return -EINVAL;
+	}
+
+	priv->klen = ntohl(nla_get_be32(tb[NFTA_SET_KLEN]));
+	if (priv->klen == 0 ||
+	    priv->klen > FIELD_SIZEOF(struct nft_data, data))
+		return -EINVAL;
+
+	nla_for_each_nested(nla, tb[NFTA_SET_ELEMENTS], rem) {
+		err = -EINVAL;
+		if (nla_type(nla) != NFTA_LIST_ELEM)
+			goto err1;
+
+		err = nft_set_elem_init(ctx, expr, nla, &new);
+		if (err < 0)
+			goto err1;
+
+		parent = NULL;
+		p = &priv->root.rb_node;
+		while (*p != NULL) {
+			parent = *p;
+			elem = rb_entry(parent, struct nft_set_elem, node);
+			d = nft_data_cmp(&elem->key, &new->key, priv->klen);
+			if (d < 0)
+				p = &parent->rb_left;
+			else if (d > 0)
+				p = &parent->rb_right;
+			else {
+				err = -EEXIST;
+				goto err2;
+			}
+		}
+		rb_link_node(&new->node, parent, p);
+		rb_insert_color(&new->node, &priv->root);
+	}
+
+	return 0;
+
+err2:
+	nft_set_elem_destroy(expr, new);
+err1:
+	nft_set_destroy(expr);
+	return err;
+}
+
+static int nft_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	struct nft_set *priv = nft_expr_priv(expr);
+	const struct nft_set_elem *elem;
+	struct rb_node *node;
+	struct nlattr *list;
+
+	if (priv->flags) {
+		if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(priv->flags)))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_be32(skb, NFTA_SET_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_SET_KLEN, htonl(priv->klen)))
+		goto nla_put_failure;
+
+	if (priv->flags & NFT_SET_MAP) {
+		if (nla_put_be32(skb, NFTA_SET_DREG, htonl(priv->dreg)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_SET_DLEN, htonl(priv->dlen)))
+			goto nla_put_failure;
+	}
+
+	list = nla_nest_start(skb, NFTA_SET_ELEMENTS);
+	if (list == NULL)
+		goto nla_put_failure;
+
+	for (node = rb_first(&priv->root); node; node = rb_next(node)) {
+		elem = rb_entry(node, struct nft_set_elem, node);
+		if (nft_set_elem_dump(skb, expr, elem) < 0)
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, list);
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_set_ops __read_mostly = {
+	.name		= "set",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_set)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_set_eval,
+	.init		= nft_set_init,
+	.destroy	= nft_set_destroy,
+	.dump		= nft_set_dump,
+	.policy		= nft_set_policy,
+	.maxattr	= NFTA_SET_MAX,
+};
+
+static int __init nft_set_module_init(void)
+{
+	return nft_register_expr(&nft_set_ops);
+}
+
+static void __exit nft_set_module_exit(void)
+{
+	nft_unregister_expr(&nft_set_ops);
+}
+
+module_init(nft_set_module_init);
+module_exit(nft_set_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_EXPR("set");
-- 
cgit 


From 20a69341f2d00cd042e81c82289fba8a13c05a25 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 11 Oct 2013 12:06:22 +0200
Subject: netfilter: nf_tables: add netlink set API

This patch adds the new netlink API for maintaining nf_tables sets
independently of the ruleset. The API supports the following operations:

- creation of sets
- deletion of sets
- querying of specific sets
- dumping of all sets

- addition of set elements
- removal of set elements
- dumping of all set elements

Sets are identified by name, each table defines an individual namespace.
The name of a set may be allocated automatically, this is mostly useful
in combination with the NFT_SET_ANONYMOUS flag, which destroys a set
automatically once the last reference has been released.

Sets can be marked constant, meaning they're not allowed to change while
linked to a rule. This allows to perform lockless operation for set
types that would otherwise require locking.

Additionally, if the implementation supports it, sets can (as before) be
used as maps, associating a data value with each key (or range), by
specifying the NFT_SET_MAP flag and can be used for interval queries by
specifying the NFT_SET_INTERVAL flag.

Set elements are added and removed incrementally. All element operations
support batching, reducing netlink message and set lookup overhead.

The old "set" and "hash" expressions are replaced by a generic "lookup"
expression, which binds to the specified set. Userspace is not aware
of the actual set implementation used by the kernel anymore, all
configuration options are generic.

Currently the implementation selection logic is largely missing and the
kernel will simply use the first registered implementation supporting the
requested operation. Eventually, the plan is to have userspace supply a
description of the data characteristics and select the implementation
based on expected performance and memory use.

This patch includes the new 'lookup' expression to look up for element
matching in the set.

This patch includes kernel-doc descriptions for this set API and it
also includes the following fixes.

From Patrick McHardy:
* netfilter: nf_tables: fix set element data type in dumps
* netfilter: nf_tables: fix indentation of struct nft_set_elem comments
* netfilter: nf_tables: fix oops in nft_validate_data_load()
* netfilter: nf_tables: fix oops while listing sets of built-in tables
* netfilter: nf_tables: destroy anonymous sets immediately if binding fails
* netfilter: nf_tables: propagate context to set iter callback
* netfilter: nf_tables: add loop detection

From Pablo Neira Ayuso:
* netfilter: nf_tables: allow to dump all existing sets
* netfilter: nf_tables: fix wrong type for flags variable in newelem

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  149 ++++-
 include/uapi/linux/netfilter/nf_tables.h |  191 ++++--
 net/netfilter/Kconfig                    |    6 +-
 net/netfilter/Makefile                   |    2 +-
 net/netfilter/nf_tables_api.c            | 1078 +++++++++++++++++++++++++++++-
 net/netfilter/nf_tables_core.c           |    2 -
 net/netfilter/nft_hash.c                 |  329 +++------
 net/netfilter/nft_immediate.c            |   11 +
 net/netfilter/nft_lookup.c               |  135 ++++
 net/netfilter/nft_rbtree.c               |  247 +++++++
 net/netfilter/nft_set.c                  |  381 -----------
 11 files changed, 1854 insertions(+), 677 deletions(-)
 create mode 100644 net/netfilter/nft_lookup.c
 create mode 100644 net/netfilter/nft_rbtree.c
 delete mode 100644 net/netfilter/nft_set.c

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index d26dfa345f49..677dd79380ed 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -6,6 +6,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netlink.h>
 
+#define NFT_JUMP_STACK_SIZE	16
+
 struct nft_pktinfo {
 	struct sk_buff			*skb;
 	const struct net_device		*in;
@@ -48,23 +50,22 @@ static inline void nft_data_debug(const struct nft_data *data)
 }
 
 /**
- *	struct nft_ctx - nf_tables rule context
+ *	struct nft_ctx - nf_tables rule/set context
  *
+ * 	@skb: netlink skb
+ * 	@nlh: netlink message header
  * 	@afi: address family info
  * 	@table: the table the chain is contained in
  * 	@chain: the chain the rule is contained in
  */
 struct nft_ctx {
+	const struct sk_buff		*skb;
+	const struct nlmsghdr		*nlh;
 	const struct nft_af_info	*afi;
 	const struct nft_table		*table;
 	const struct nft_chain		*chain;
 };
 
-enum nft_data_types {
-	NFT_DATA_VALUE,
-	NFT_DATA_VERDICT,
-};
-
 struct nft_data_desc {
 	enum nft_data_types		type;
 	unsigned int			len;
@@ -83,6 +84,11 @@ static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg)
 	return reg == NFT_REG_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE;
 }
 
+static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
+{
+	return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1;
+}
+
 extern int nft_validate_input_register(enum nft_registers reg);
 extern int nft_validate_output_register(enum nft_registers reg);
 extern int nft_validate_data_load(const struct nft_ctx *ctx,
@@ -90,6 +96,132 @@ extern int nft_validate_data_load(const struct nft_ctx *ctx,
 				  const struct nft_data *data,
 				  enum nft_data_types type);
 
+/**
+ *	struct nft_set_elem - generic representation of set elements
+ *
+ *	@cookie: implementation specific element cookie
+ *	@key: element key
+ *	@data: element data (maps only)
+ *	@flags: element flags (end of interval)
+ *
+ *	The cookie can be used to store a handle to the element for subsequent
+ *	removal.
+ */
+struct nft_set_elem {
+	void			*cookie;
+	struct nft_data		key;
+	struct nft_data		data;
+	u32			flags;
+};
+
+struct nft_set;
+struct nft_set_iter {
+	unsigned int	count;
+	unsigned int	skip;
+	int		err;
+	int		(*fn)(const struct nft_ctx *ctx,
+			      const struct nft_set *set,
+			      const struct nft_set_iter *iter,
+			      const struct nft_set_elem *elem);
+};
+
+/**
+ *	struct nft_set_ops - nf_tables set operations
+ *
+ *	@lookup: look up an element within the set
+ *	@insert: insert new element into set
+ *	@remove: remove element from set
+ *	@walk: iterate over all set elemeennts
+ *	@privsize: function to return size of set private data
+ *	@init: initialize private data of new set instance
+ *	@destroy: destroy private data of set instance
+ *	@list: nf_tables_set_ops list node
+ *	@owner: module reference
+ *	@features: features supported by the implementation
+ */
+struct nft_set_ops {
+	bool				(*lookup)(const struct nft_set *set,
+						  const struct nft_data *key,
+						  struct nft_data *data);
+	int				(*get)(const struct nft_set *set,
+					       struct nft_set_elem *elem);
+	int				(*insert)(const struct nft_set *set,
+						  const struct nft_set_elem *elem);
+	void				(*remove)(const struct nft_set *set,
+						  const struct nft_set_elem *elem);
+	void				(*walk)(const struct nft_ctx *ctx,
+						const struct nft_set *set,
+						struct nft_set_iter *iter);
+
+	unsigned int			(*privsize)(const struct nlattr * const nla[]);
+	int				(*init)(const struct nft_set *set,
+						const struct nlattr * const nla[]);
+	void				(*destroy)(const struct nft_set *set);
+
+	struct list_head		list;
+	struct module			*owner;
+	u32				features;
+};
+
+extern int nft_register_set(struct nft_set_ops *ops);
+extern void nft_unregister_set(struct nft_set_ops *ops);
+
+/**
+ * 	struct nft_set - nf_tables set instance
+ *
+ *	@list: table set list node
+ *	@bindings: list of set bindings
+ * 	@name: name of the set
+ * 	@ktype: key type (numeric type defined by userspace, not used in the kernel)
+ * 	@dtype: data type (verdict or numeric type defined by userspace)
+ * 	@ops: set ops
+ * 	@flags: set flags
+ * 	@klen: key length
+ * 	@dlen: data length
+ * 	@data: private set data
+ */
+struct nft_set {
+	struct list_head		list;
+	struct list_head		bindings;
+	char				name[IFNAMSIZ];
+	u32				ktype;
+	u32				dtype;
+	/* runtime data below here */
+	const struct nft_set_ops	*ops ____cacheline_aligned;
+	u16				flags;
+	u8				klen;
+	u8				dlen;
+	unsigned char			data[]
+		__attribute__((aligned(__alignof__(u64))));
+};
+
+static inline void *nft_set_priv(const struct nft_set *set)
+{
+	return (void *)set->data;
+}
+
+extern struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+					    const struct nlattr *nla);
+
+/**
+ *	struct nft_set_binding - nf_tables set binding
+ *
+ *	@list: set bindings list node
+ *	@chain: chain containing the rule bound to the set
+ *
+ *	A set binding contains all information necessary for validation
+ *	of new elements added to a bound set.
+ */
+struct nft_set_binding {
+	struct list_head		list;
+	const struct nft_chain		*chain;
+};
+
+extern int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
+			      struct nft_set_binding *binding);
+extern void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+				 struct nft_set_binding *binding);
+
 /**
  *	struct nft_expr_ops - nf_tables expression operations
  *
@@ -115,7 +247,7 @@ struct nft_expr_ops {
 	void				(*destroy)(const struct nft_expr *expr);
 	int				(*dump)(struct sk_buff *skb,
 						const struct nft_expr *expr);
-
+	const struct nft_data *		(*get_verdict)(const struct nft_expr *expr);
 	struct list_head		list;
 	const char			*name;
 	struct module			*owner;
@@ -298,4 +430,7 @@ extern void nft_unregister_expr(struct nft_expr_ops *);
 #define MODULE_ALIAS_NFT_EXPR(name) \
 	MODULE_ALIAS("nft-expr-" name)
 
+#define MODULE_ALIAS_NFT_SET() \
+	MODULE_ALIAS("nft-set")
+
 #endif /* _NET_NF_TABLES_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index ec6d84a8ed1e..9e924014efe3 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -44,6 +44,12 @@ enum nft_verdicts {
  * @NFT_MSG_NEWRULE: create a new rule (enum nft_rule_attributes)
  * @NFT_MSG_GETRULE: get a rule (enum nft_rule_attributes)
  * @NFT_MSG_DELRULE: delete a rule (enum nft_rule_attributes)
+ * @NFT_MSG_NEWSET: create a new set (enum nft_set_attributes)
+ * @NFT_MSG_GETSET: get a set (enum nft_set_attributes)
+ * @NFT_MSG_DELSET: delete a set (enum nft_set_attributes)
+ * @NFT_MSG_NEWSETELEM: create a new set element (enum nft_set_elem_attributes)
+ * @NFT_MSG_GETSETELEM: get a set element (enum nft_set_elem_attributes)
+ * @NFT_MSG_DELSETELEM: delete a set element (enum nft_set_elem_attributes)
  */
 enum nf_tables_msg_types {
 	NFT_MSG_NEWTABLE,
@@ -55,9 +61,20 @@ enum nf_tables_msg_types {
 	NFT_MSG_NEWRULE,
 	NFT_MSG_GETRULE,
 	NFT_MSG_DELRULE,
+	NFT_MSG_NEWSET,
+	NFT_MSG_GETSET,
+	NFT_MSG_DELSET,
+	NFT_MSG_NEWSETELEM,
+	NFT_MSG_GETSETELEM,
+	NFT_MSG_DELSETELEM,
 	NFT_MSG_MAX,
 };
 
+/**
+ * enum nft_list_attributes - nf_tables generic list netlink attributes
+ *
+ * @NFTA_LIST_ELEM: list element (NLA_NESTED)
+ */
 enum nft_list_attributes {
 	NFTA_LIST_UNPEC,
 	NFTA_LIST_ELEM,
@@ -127,6 +144,113 @@ enum nft_rule_attributes {
 };
 #define NFTA_RULE_MAX		(__NFTA_RULE_MAX - 1)
 
+/**
+ * enum nft_set_flags - nf_tables set flags
+ *
+ * @NFT_SET_ANONYMOUS: name allocation, automatic cleanup on unlink
+ * @NFT_SET_CONSTANT: set contents may not change while bound
+ * @NFT_SET_INTERVAL: set contains intervals
+ * @NFT_SET_MAP: set is used as a dictionary
+ */
+enum nft_set_flags {
+	NFT_SET_ANONYMOUS		= 0x1,
+	NFT_SET_CONSTANT		= 0x2,
+	NFT_SET_INTERVAL		= 0x4,
+	NFT_SET_MAP			= 0x8,
+};
+
+/**
+ * enum nft_set_attributes - nf_tables set netlink attributes
+ *
+ * @NFTA_SET_TABLE: table name (NLA_STRING)
+ * @NFTA_SET_NAME: set name (NLA_STRING)
+ * @NFTA_SET_FLAGS: bitmask of enum nft_set_flags (NLA_U32)
+ * @NFTA_SET_KEY_TYPE: key data type, informational purpose only (NLA_U32)
+ * @NFTA_SET_KEY_LEN: key data length (NLA_U32)
+ * @NFTA_SET_DATA_TYPE: mapping data type (NLA_U32)
+ * @NFTA_SET_DATA_LEN: mapping data length (NLA_U32)
+ */
+enum nft_set_attributes {
+	NFTA_SET_UNSPEC,
+	NFTA_SET_TABLE,
+	NFTA_SET_NAME,
+	NFTA_SET_FLAGS,
+	NFTA_SET_KEY_TYPE,
+	NFTA_SET_KEY_LEN,
+	NFTA_SET_DATA_TYPE,
+	NFTA_SET_DATA_LEN,
+	__NFTA_SET_MAX
+};
+#define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
+
+/**
+ * enum nft_set_elem_flags - nf_tables set element flags
+ *
+ * @NFT_SET_ELEM_INTERVAL_END: element ends the previous interval
+ */
+enum nft_set_elem_flags {
+	NFT_SET_ELEM_INTERVAL_END	= 0x1,
+};
+
+/**
+ * enum nft_set_elem_attributes - nf_tables set element netlink attributes
+ *
+ * @NFTA_SET_ELEM_KEY: key value (NLA_NESTED: nft_data)
+ * @NFTA_SET_ELEM_DATA: data value of mapping (NLA_NESTED: nft_data_attributes)
+ * @NFTA_SET_ELEM_FLAGS: bitmask of nft_set_elem_flags (NLA_U32)
+ */
+enum nft_set_elem_attributes {
+	NFTA_SET_ELEM_UNSPEC,
+	NFTA_SET_ELEM_KEY,
+	NFTA_SET_ELEM_DATA,
+	NFTA_SET_ELEM_FLAGS,
+	__NFTA_SET_ELEM_MAX
+};
+#define NFTA_SET_ELEM_MAX	(__NFTA_SET_ELEM_MAX - 1)
+
+/**
+ * enum nft_set_elem_list_attributes - nf_tables set element list netlink attributes
+ *
+ * @NFTA_SET_ELEM_LIST_TABLE: table of the set to be changed (NLA_STRING)
+ * @NFTA_SET_ELEM_LIST_SET: name of the set to be changed (NLA_STRING)
+ * @NFTA_SET_ELEM_LIST_ELEMENTS: list of set elements (NLA_NESTED: nft_set_elem_attributes)
+ */
+enum nft_set_elem_list_attributes {
+	NFTA_SET_ELEM_LIST_UNSPEC,
+	NFTA_SET_ELEM_LIST_TABLE,
+	NFTA_SET_ELEM_LIST_SET,
+	NFTA_SET_ELEM_LIST_ELEMENTS,
+	__NFTA_SET_ELEM_LIST_MAX
+};
+#define NFTA_SET_ELEM_LIST_MAX	(__NFTA_SET_ELEM_LIST_MAX - 1)
+
+/**
+ * enum nft_data_types - nf_tables data types
+ *
+ * @NFT_DATA_VALUE: generic data
+ * @NFT_DATA_VERDICT: netfilter verdict
+ *
+ * The type of data is usually determined by the kernel directly and is not
+ * explicitly specified by userspace. The only difference are sets, where
+ * userspace specifies the key and mapping data types.
+ *
+ * The values 0xffffff00-0xffffffff are reserved for internally used types.
+ * The remaining range can be freely used by userspace to encode types, all
+ * values are equivalent to NFT_DATA_VALUE.
+ */
+enum nft_data_types {
+	NFT_DATA_VALUE,
+	NFT_DATA_VERDICT	= 0xffffff00U,
+};
+
+#define NFT_DATA_RESERVED_MASK	0xffffff00U
+
+/**
+ * enum nft_data_attributes - nf_tables data netlink attributes
+ *
+ * @NFTA_DATA_VALUE: generic data (NLA_BINARY)
+ * @NFTA_DATA_VERDICT: nf_tables verdict (NLA_NESTED: nft_verdict_attributes)
+ */
 enum nft_data_attributes {
 	NFTA_DATA_UNSPEC,
 	NFTA_DATA_VALUE,
@@ -275,58 +399,21 @@ enum nft_cmp_attributes {
 };
 #define NFTA_CMP_MAX		(__NFTA_CMP_MAX - 1)
 
-enum nft_set_elem_flags {
-	NFT_SE_INTERVAL_END	= 0x1,
-};
-
-enum nft_set_elem_attributes {
-	NFTA_SE_UNSPEC,
-	NFTA_SE_KEY,
-	NFTA_SE_DATA,
-	NFTA_SE_FLAGS,
-	__NFTA_SE_MAX
-};
-#define NFTA_SE_MAX		(__NFTA_SE_MAX - 1)
-
-enum nft_set_flags {
-	NFT_SET_INTERVAL	= 0x1,
-	NFT_SET_MAP		= 0x2,
-};
-
-enum nft_set_attributes {
-	NFTA_SET_UNSPEC,
-	NFTA_SET_FLAGS,
-	NFTA_SET_SREG,
-	NFTA_SET_DREG,
-	NFTA_SET_KLEN,
-	NFTA_SET_DLEN,
-	NFTA_SET_ELEMENTS,
-	__NFTA_SET_MAX
-};
-#define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
-
-enum nft_hash_flags {
-	NFT_HASH_MAP		= 0x1,
-};
-
-enum nft_hash_elem_attributes {
-	NFTA_HE_UNSPEC,
-	NFTA_HE_KEY,
-	NFTA_HE_DATA,
-	__NFTA_HE_MAX
-};
-#define NFTA_HE_MAX		(__NFTA_HE_MAX - 1)
-
-enum nft_hash_attributes {
-	NFTA_HASH_UNSPEC,
-	NFTA_HASH_FLAGS,
-	NFTA_HASH_SREG,
-	NFTA_HASH_DREG,
-	NFTA_HASH_KLEN,
-	NFTA_HASH_ELEMENTS,
-	__NFTA_HASH_MAX
-};
-#define NFTA_HASH_MAX		(__NFTA_HASH_MAX - 1)
+/**
+ * enum nft_lookup_attributes - nf_tables set lookup expression netlink attributes
+ *
+ * @NFTA_LOOKUP_SET: name of the set where to look for (NLA_STRING)
+ * @NFTA_LOOKUP_SREG: source register of the data to look for (NLA_U32: nft_registers)
+ * @NFTA_LOOKUP_DREG: destination register (NLA_U32: nft_registers)
+ */
+enum nft_lookup_attributes {
+	NFTA_LOOKUP_UNSPEC,
+	NFTA_LOOKUP_SET,
+	NFTA_LOOKUP_SREG,
+	NFTA_LOOKUP_DREG,
+	__NFTA_LOOKUP_MAX
+};
+#define NFTA_LOOKUP_MAX		(__NFTA_LOOKUP_MAX - 1)
 
 /**
  * enum nft_payload_bases - nf_tables payload expression offset bases
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c271e1af93b5..aa184a46bbf3 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -430,13 +430,13 @@ config NFT_CT
 	depends on NF_CONNTRACK
 	tristate "Netfilter nf_tables conntrack module"
 
-config NFT_SET
+config NFT_RBTREE
 	depends on NF_TABLES
-	tristate "Netfilter nf_tables set module"
+	tristate "Netfilter nf_tables rbtree set module"
 
 config NFT_HASH
 	depends on NF_TABLES
-	tristate "Netfilter nf_tables hash module"
+	tristate "Netfilter nf_tables hash set module"
 
 config NFT_COUNTER
 	depends on NF_TABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 1ca3f3932826..b6b78754e4cc 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -75,7 +75,7 @@ obj-$(CONFIG_NFT_META)		+= nft_meta.o
 obj-$(CONFIG_NFT_CT)		+= nft_ct.o
 obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
 #nf_tables-objs			+= nft_meta_target.o
-obj-$(CONFIG_NFT_SET)		+= nft_set.o
+obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 7d59c89c6c75..5092c817c222 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007, 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2007-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -315,6 +315,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 
 	nla_strlcpy(table->name, name, nla_len(name));
 	INIT_LIST_HEAD(&table->chains);
+	INIT_LIST_HEAD(&table->sets);
 
 	list_add_tail(&table->list, &afi->tables);
 	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
@@ -409,6 +410,7 @@ again:
 	}
 
 	table->flags |= NFT_TABLE_BUILTIN;
+	INIT_LIST_HEAD(&table->sets);
 	list_add_tail(&table->list, &afi->tables);
 	nf_tables_table_notify(NULL, NULL, table, NFT_MSG_NEWTABLE, family);
 	list_for_each_entry(chain, &table->chains, list)
@@ -820,10 +822,14 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 }
 
 static void nft_ctx_init(struct nft_ctx *ctx,
+			 const struct sk_buff *skb,
+			 const struct nlmsghdr *nlh,
 			 const struct nft_af_info *afi,
 			 const struct nft_table *table,
 			 const struct nft_chain *chain)
 {
+	ctx->skb   = skb;
+	ctx->nlh   = nlh;
 	ctx->afi   = afi;
 	ctx->table = table;
 	ctx->chain = chain;
@@ -1301,7 +1307,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	rule->handle = handle;
 	rule->dlen   = size;
 
-	nft_ctx_init(&ctx, afi, table, chain);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain);
 	expr = nft_expr_first(rule);
 	for (i = 0; i < n; i++) {
 		err = nf_tables_newexpr(&ctx, &info[i], expr);
@@ -1392,6 +1398,939 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	return 0;
 }
 
+/*
+ * Sets
+ */
+
+static LIST_HEAD(nf_tables_set_ops);
+
+int nft_register_set(struct nft_set_ops *ops)
+{
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_add_tail(&ops->list, &nf_tables_set_ops);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_register_set);
+
+void nft_unregister_set(struct nft_set_ops *ops)
+{
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	list_del(&ops->list);
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+}
+EXPORT_SYMBOL_GPL(nft_unregister_set);
+
+static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const nla[])
+{
+	const struct nft_set_ops *ops;
+	u32 features;
+
+#ifdef CONFIG_MODULES
+	if (list_empty(&nf_tables_set_ops)) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-set");
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (!list_empty(&nf_tables_set_ops))
+			return ERR_PTR(-EAGAIN);
+	}
+#endif
+	features = 0;
+	if (nla[NFTA_SET_FLAGS] != NULL) {
+		features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS]));
+		features &= NFT_SET_INTERVAL | NFT_SET_MAP;
+	}
+
+	// FIXME: implement selection properly
+	list_for_each_entry(ops, &nf_tables_set_ops, list) {
+		if ((ops->features & features) != features)
+			continue;
+		if (!try_module_get(ops->owner))
+			continue;
+		return ops;
+	}
+
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
+	[NFTA_SET_TABLE]		= { .type = NLA_STRING },
+	[NFTA_SET_NAME]			= { .type = NLA_STRING },
+	[NFTA_SET_FLAGS]		= { .type = NLA_U32 },
+	[NFTA_SET_KEY_TYPE]		= { .type = NLA_U32 },
+	[NFTA_SET_KEY_LEN]		= { .type = NLA_U32 },
+	[NFTA_SET_DATA_TYPE]		= { .type = NLA_U32 },
+	[NFTA_SET_DATA_LEN]		= { .type = NLA_U32 },
+};
+
+static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
+				     const struct sk_buff *skb,
+				     const struct nlmsghdr *nlh,
+				     const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table = NULL;
+
+	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	if (nla[NFTA_SET_TABLE] != NULL) {
+		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], false);
+		if (IS_ERR(table))
+			return PTR_ERR(table);
+	}
+
+	nft_ctx_init(ctx, skb, nlh, afi, table, NULL);
+	return 0;
+}
+
+struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+				     const struct nlattr *nla)
+{
+	struct nft_set *set;
+
+	if (nla == NULL)
+		return ERR_PTR(-EINVAL);
+
+	list_for_each_entry(set, &table->sets, list) {
+		if (!nla_strcmp(nla, set->name))
+			return set;
+	}
+	return ERR_PTR(-ENOENT);
+}
+
+static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
+				    const char *name)
+{
+	const struct nft_set *i;
+	const char *p;
+	unsigned long *inuse;
+	unsigned int n = 0;
+
+	p = strnchr(name, IFNAMSIZ, '%');
+	if (p != NULL) {
+		if (p[1] != 'd' || strchr(p + 2, '%'))
+			return -EINVAL;
+
+		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
+		if (inuse == NULL)
+			return -ENOMEM;
+
+		list_for_each_entry(i, &ctx->table->sets, list) {
+			if (!sscanf(i->name, name, &n))
+				continue;
+			if (n < 0 || n > BITS_PER_LONG * PAGE_SIZE)
+				continue;
+			set_bit(n, inuse);
+		}
+
+		n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE);
+		free_page((unsigned long)inuse);
+	}
+
+	snprintf(set->name, sizeof(set->name), name, n);
+	list_for_each_entry(i, &ctx->table->sets, list) {
+		if (!strcmp(set->name, i->name))
+			return -ENFILE;
+	}
+	return 0;
+}
+
+static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
+			      const struct nft_set *set, u16 event, u16 flags)
+{
+	struct nfgenmsg *nfmsg;
+	struct nlmsghdr *nlh;
+	u32 portid = NETLINK_CB(ctx->skb).portid;
+	u32 seq = ctx->nlh->nlmsg_seq;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+			flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= ctx->afi->family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_SET_NAME, set->name))
+		goto nla_put_failure;
+	if (set->flags != 0)
+		if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(set->flags)))
+			goto nla_put_failure;
+
+	if (nla_put_be32(skb, NFTA_SET_KEY_TYPE, htonl(set->ktype)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_SET_KEY_LEN, htonl(set->klen)))
+		goto nla_put_failure;
+	if (set->flags & NFT_SET_MAP) {
+		if (nla_put_be32(skb, NFTA_SET_DATA_TYPE, htonl(set->dtype)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_SET_DATA_LEN, htonl(set->dlen)))
+			goto nla_put_failure;
+	}
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_set_notify(const struct nft_ctx *ctx,
+				const struct nft_set *set,
+				int event)
+{
+	struct sk_buff *skb;
+	u32 portid = NETLINK_CB(ctx->skb).portid;
+	struct net *net = sock_net(ctx->skb->sk);
+	bool report;
+	int err;
+
+	report = nlmsg_report(ctx->nlh);
+	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_set(skb, ctx, set, event, 0);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb,
+				     struct netlink_callback *cb)
+{
+	const struct nft_set *set;
+	unsigned int idx = 0, s_idx = cb->args[0];
+
+	if (cb->args[1])
+		return skb->len;
+
+	list_for_each_entry(set, &ctx->table->sets, list) {
+		if (idx < s_idx)
+			goto cont;
+		if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
+				       NLM_F_MULTI) < 0) {
+			cb->args[0] = idx;
+			goto done;
+		}
+cont:
+		idx++;
+	}
+	cb->args[1] = 1;
+done:
+	return skb->len;
+}
+
+static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	const struct nft_set *set;
+	unsigned int idx = 0, s_idx = cb->args[0];
+	struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
+
+	if (cb->args[1])
+		return skb->len;
+
+	list_for_each_entry(table, &ctx->afi->tables, list) {
+		if (cur_table && cur_table != table)
+			continue;
+
+		ctx->table = table;
+		list_for_each_entry(set, &ctx->table->sets, list) {
+			if (idx < s_idx)
+				goto cont;
+			if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
+					       NLM_F_MULTI) < 0) {
+				cb->args[0] = idx;
+				cb->args[2] = (unsigned long) table;
+				goto done;
+			}
+cont:
+			idx++;
+		}
+	}
+	cb->args[1] = 1;
+done:
+	return skb->len;
+}
+
+static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
+	struct nlattr *nla[NFTA_SET_MAX + 1];
+	struct nft_ctx ctx;
+	int err, ret;
+
+	err = nlmsg_parse(cb->nlh, sizeof(*nfmsg), nla, NFTA_SET_MAX,
+			  nft_set_policy);
+	if (err < 0)
+		return err;
+
+	err = nft_ctx_init_from_setattr(&ctx, cb->skb, cb->nlh, (void *)nla);
+	if (err < 0)
+		return err;
+
+	if (ctx.table == NULL)
+		ret = nf_tables_dump_sets_all(&ctx, skb, cb);
+	else
+		ret = nf_tables_dump_sets_table(&ctx, skb, cb);
+
+	return ret;
+}
+
+static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
+			    const struct nlmsghdr *nlh,
+			    const struct nlattr * const nla[])
+{
+	const struct nft_set *set;
+	struct nft_ctx ctx;
+	struct sk_buff *skb2;
+	int err;
+
+	/* Verify existance before starting dump */
+	err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+	if (err < 0)
+		return err;
+
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = nf_tables_dump_sets,
+		};
+		return netlink_dump_start(nlsk, skb, nlh, &c);
+	}
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+
+	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	err = nf_tables_fill_set(skb2, &ctx, set, NFT_MSG_NEWSET, 0);
+	if (err < 0)
+		goto err;
+
+	return nlmsg_unicast(nlsk, skb2, NETLINK_CB(skb).portid);
+
+err:
+	kfree_skb(skb2);
+	return err;
+}
+
+static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
+			    const struct nlmsghdr *nlh,
+			    const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_set_ops *ops;
+	const struct nft_af_info *afi;
+	struct nft_table *table;
+	struct nft_set *set;
+	struct nft_ctx ctx;
+	char name[IFNAMSIZ];
+	unsigned int size;
+	bool create;
+	u32 ktype, klen, dlen, dtype, flags;
+	int err;
+
+	if (nla[NFTA_SET_TABLE] == NULL ||
+	    nla[NFTA_SET_NAME] == NULL ||
+	    nla[NFTA_SET_KEY_LEN] == NULL)
+		return -EINVAL;
+
+	ktype = NFT_DATA_VALUE;
+	if (nla[NFTA_SET_KEY_TYPE] != NULL) {
+		ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
+		if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
+			return -EINVAL;
+	}
+
+	klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
+	if (klen == 0 || klen > FIELD_SIZEOF(struct nft_data, data))
+		return -EINVAL;
+
+	flags = 0;
+	if (nla[NFTA_SET_FLAGS] != NULL) {
+		flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS]));
+		if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
+			      NFT_SET_INTERVAL | NFT_SET_MAP))
+			return -EINVAL;
+	}
+
+	dtype = 0;
+	dlen  = 0;
+	if (nla[NFTA_SET_DATA_TYPE] != NULL) {
+		if (!(flags & NFT_SET_MAP))
+			return -EINVAL;
+
+		dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
+		if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
+		    dtype != NFT_DATA_VERDICT)
+			return -EINVAL;
+
+		if (dtype != NFT_DATA_VERDICT) {
+			if (nla[NFTA_SET_DATA_LEN] == NULL)
+				return -EINVAL;
+			dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
+			if (dlen == 0 ||
+			    dlen > FIELD_SIZEOF(struct nft_data, data))
+				return -EINVAL;
+		} else
+			dlen = sizeof(struct nft_data);
+	} else if (flags & NFT_SET_MAP)
+		return -EINVAL;
+
+	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
+
+	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, create);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], create);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL);
+
+	set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]);
+	if (IS_ERR(set)) {
+		if (PTR_ERR(set) != -ENOENT)
+			return PTR_ERR(set);
+		set = NULL;
+	}
+
+	if (set != NULL) {
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			return -EEXIST;
+		if (nlh->nlmsg_flags & NLM_F_REPLACE)
+			return -EOPNOTSUPP;
+		return 0;
+	}
+
+	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
+		return -ENOENT;
+
+	ops = nft_select_set_ops(nla);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	size = 0;
+	if (ops->privsize != NULL)
+		size = ops->privsize(nla);
+
+	err = -ENOMEM;
+	set = kzalloc(sizeof(*set) + size, GFP_KERNEL);
+	if (set == NULL)
+		goto err1;
+
+	nla_strlcpy(name, nla[NFTA_SET_NAME], sizeof(set->name));
+	err = nf_tables_set_alloc_name(&ctx, set, name);
+	if (err < 0)
+		goto err2;
+
+	INIT_LIST_HEAD(&set->bindings);
+	set->ops   = ops;
+	set->ktype = ktype;
+	set->klen  = klen;
+	set->dtype = dtype;
+	set->dlen  = dlen;
+	set->flags = flags;
+
+	err = ops->init(set, nla);
+	if (err < 0)
+		goto err2;
+
+	list_add_tail(&set->list, &table->sets);
+	nf_tables_set_notify(&ctx, set, NFT_MSG_NEWSET);
+	return 0;
+
+err2:
+	kfree(set);
+err1:
+	module_put(ops->owner);
+	return err;
+}
+
+static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	list_del(&set->list);
+	if (!(set->flags & NFT_SET_ANONYMOUS))
+		nf_tables_set_notify(ctx, set, NFT_MSG_DELSET);
+
+	set->ops->destroy(set);
+	module_put(set->ops->owner);
+	kfree(set);
+}
+
+static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
+			    const struct nlmsghdr *nlh,
+			    const struct nlattr * const nla[])
+{
+	struct nft_set *set;
+	struct nft_ctx ctx;
+	int err;
+
+	if (nla[NFTA_SET_TABLE] == NULL)
+		return -EINVAL;
+
+	err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+	if (err < 0)
+		return err;
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+	if (!list_empty(&set->bindings))
+		return -EBUSY;
+
+	nf_tables_set_destroy(&ctx, set);
+	return 0;
+}
+
+static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
+					const struct nft_set *set,
+					const struct nft_set_iter *iter,
+					const struct nft_set_elem *elem)
+{
+	enum nft_registers dreg;
+
+	dreg = nft_type_to_reg(set->dtype);
+	return nft_validate_data_load(ctx, dreg, &elem->data, set->dtype);
+}
+
+int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
+		       struct nft_set_binding *binding)
+{
+	struct nft_set_binding *i;
+	struct nft_set_iter iter;
+
+	if (!list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
+		return -EBUSY;
+
+	if (set->flags & NFT_SET_MAP) {
+		/* If the set is already bound to the same chain all
+		 * jumps are already validated for that chain.
+		 */
+		list_for_each_entry(i, &set->bindings, list) {
+			if (i->chain == binding->chain)
+				goto bind;
+		}
+
+		iter.skip 	= 0;
+		iter.count	= 0;
+		iter.err	= 0;
+		iter.fn		= nf_tables_bind_check_setelem;
+
+		set->ops->walk(ctx, set, &iter);
+		if (iter.err < 0) {
+			/* Destroy anonymous sets if binding fails */
+			if (set->flags & NFT_SET_ANONYMOUS)
+				nf_tables_set_destroy(ctx, set);
+
+			return iter.err;
+		}
+	}
+bind:
+	binding->chain = ctx->chain;
+	list_add_tail(&binding->list, &set->bindings);
+	return 0;
+}
+
+void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+			  struct nft_set_binding *binding)
+{
+	list_del(&binding->list);
+
+	if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
+		nf_tables_set_destroy(ctx, set);
+}
+
+/*
+ * Set elements
+ */
+
+static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
+	[NFTA_SET_ELEM_KEY]		= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_DATA]		= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_FLAGS]		= { .type = NLA_U32 },
+};
+
+static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
+	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING },
+	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING },
+	[NFTA_SET_ELEM_LIST_ELEMENTS]	= { .type = NLA_NESTED },
+};
+
+static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
+				      const struct sk_buff *skb,
+				      const struct nlmsghdr *nlh,
+				      const struct nlattr * const nla[])
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	const struct nft_af_info *afi;
+	const struct nft_table *table;
+
+	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, false);
+	if (IS_ERR(afi))
+		return PTR_ERR(afi);
+
+	table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE], false);
+	if (IS_ERR(table))
+		return PTR_ERR(table);
+
+	nft_ctx_init(ctx, skb, nlh, afi, table, NULL);
+	return 0;
+}
+
+static int nf_tables_fill_setelem(struct sk_buff *skb,
+				  const struct nft_set *set,
+				  const struct nft_set_elem *elem)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nft_data_dump(skb, NFTA_SET_ELEM_KEY, &elem->key, NFT_DATA_VALUE,
+			  set->klen) < 0)
+		goto nla_put_failure;
+
+	if (set->flags & NFT_SET_MAP &&
+	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END) &&
+	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, &elem->data,
+			  set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
+			  set->dlen) < 0)
+		goto nla_put_failure;
+
+	if (elem->flags != 0)
+		if (nla_put_be32(skb, NFTA_SET_ELEM_FLAGS, htonl(elem->flags)))
+			goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -EMSGSIZE;
+}
+
+struct nft_set_dump_args {
+	const struct netlink_callback	*cb;
+	struct nft_set_iter		iter;
+	struct sk_buff			*skb;
+};
+
+static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
+				  const struct nft_set *set,
+				  const struct nft_set_iter *iter,
+				  const struct nft_set_elem *elem)
+{
+	struct nft_set_dump_args *args;
+
+	args = container_of(iter, struct nft_set_dump_args, iter);
+	return nf_tables_fill_setelem(args->skb, set, elem);
+}
+
+static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	const struct nft_set *set;
+	struct nft_set_dump_args args;
+	struct nft_ctx ctx;
+	struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1];
+	struct nfgenmsg *nfmsg;
+	struct nlmsghdr *nlh;
+	struct nlattr *nest;
+	u32 portid, seq;
+	int event, err;
+
+	nfmsg = nlmsg_data(cb->nlh);
+	err = nlmsg_parse(cb->nlh, sizeof(*nfmsg), nla, NFTA_SET_ELEM_LIST_MAX,
+			  nft_set_elem_list_policy);
+	if (err < 0)
+		return err;
+
+	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla);
+	if (err < 0)
+		return err;
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+
+	event  = NFT_MSG_NEWSETELEM;
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	portid = NETLINK_CB(cb->skb).portid;
+	seq    = cb->nlh->nlmsg_seq;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+			NLM_F_MULTI);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family = NFPROTO_UNSPEC;
+	nfmsg->version      = NFNETLINK_V0;
+	nfmsg->res_id       = 0;
+
+	if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, ctx.table->name))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name))
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	args.cb		= cb;
+	args.skb	= skb;
+	args.iter.skip	= cb->args[0];
+	args.iter.count	= 0;
+	args.iter.err   = 0;
+	args.iter.fn	= nf_tables_dump_setelem;
+	set->ops->walk(&ctx, set, &args.iter);
+
+	nla_nest_end(skb, nest);
+	nlmsg_end(skb, nlh);
+
+	if (args.iter.err && args.iter.err != -EMSGSIZE)
+		return args.iter.err;
+	if (args.iter.count == cb->args[0])
+		return 0;
+
+	cb->args[0] = args.iter.count;
+	return skb->len;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
+static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
+				const struct nlmsghdr *nlh,
+				const struct nlattr * const nla[])
+{
+	const struct nft_set *set;
+	struct nft_ctx ctx;
+	int err;
+
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	if (err < 0)
+		return err;
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+
+	if (nlh->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = nf_tables_dump_set,
+		};
+		return netlink_dump_start(nlsk, skb, nlh, &c);
+	}
+	return -EOPNOTSUPP;
+}
+
+static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
+			    const struct nlattr *attr)
+{
+	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
+	struct nft_data_desc d1, d2;
+	struct nft_set_elem elem;
+	struct nft_set_binding *binding;
+	enum nft_registers dreg;
+	int err;
+
+	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
+			       nft_set_elem_policy);
+	if (err < 0)
+		return err;
+
+	if (nla[NFTA_SET_ELEM_KEY] == NULL)
+		return -EINVAL;
+
+	elem.flags = 0;
+	if (nla[NFTA_SET_ELEM_FLAGS] != NULL) {
+		elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
+		if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
+	}
+
+	if (set->flags & NFT_SET_MAP) {
+		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
+		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
+			return -EINVAL;
+	} else {
+		if (nla[NFTA_SET_ELEM_DATA] != NULL)
+			return -EINVAL;
+	}
+
+	err = nft_data_init(ctx, &elem.key, &d1, nla[NFTA_SET_ELEM_KEY]);
+	if (err < 0)
+		goto err1;
+	err = -EINVAL;
+	if (d1.type != NFT_DATA_VALUE || d1.len != set->klen)
+		goto err2;
+
+	err = -EEXIST;
+	if (set->ops->get(set, &elem) == 0)
+		goto err2;
+
+	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
+		err = nft_data_init(ctx, &elem.data, &d2, nla[NFTA_SET_ELEM_DATA]);
+		if (err < 0)
+			goto err2;
+
+		err = -EINVAL;
+		if (set->dtype != NFT_DATA_VERDICT && d2.len != set->dlen)
+			goto err3;
+
+		dreg = nft_type_to_reg(set->dtype);
+		list_for_each_entry(binding, &set->bindings, list) {
+			struct nft_ctx bind_ctx = {
+				.afi	= ctx->afi,
+				.table	= ctx->table,
+				.chain	= binding->chain,
+			};
+
+			err = nft_validate_data_load(&bind_ctx, dreg,
+						     &elem.data, d2.type);
+			if (err < 0)
+				goto err3;
+		}
+	}
+
+	err = set->ops->insert(set, &elem);
+	if (err < 0)
+		goto err3;
+
+	return 0;
+
+err3:
+	if (nla[NFTA_SET_ELEM_DATA] != NULL)
+		nft_data_uninit(&elem.data, d2.type);
+err2:
+	nft_data_uninit(&elem.key, d1.type);
+err1:
+	return err;
+}
+
+static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
+				const struct nlmsghdr *nlh,
+				const struct nlattr * const nla[])
+{
+	const struct nlattr *attr;
+	struct nft_set *set;
+	struct nft_ctx ctx;
+	int rem, err;
+
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	if (err < 0)
+		return err;
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
+		return -EBUSY;
+
+	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
+		err = nft_add_set_elem(&ctx, set, attr);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
+static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set,
+			   const struct nlattr *attr)
+{
+	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
+	struct nft_data_desc desc;
+	struct nft_set_elem elem;
+	int err;
+
+	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
+			       nft_set_elem_policy);
+	if (err < 0)
+		goto err1;
+
+	err = -EINVAL;
+	if (nla[NFTA_SET_ELEM_KEY] == NULL)
+		goto err1;
+
+	err = nft_data_init(ctx, &elem.key, &desc, nla[NFTA_SET_ELEM_KEY]);
+	if (err < 0)
+		goto err1;
+
+	err = -EINVAL;
+	if (desc.type != NFT_DATA_VALUE || desc.len != set->klen)
+		goto err2;
+
+	err = set->ops->get(set, &elem);
+	if (err < 0)
+		goto err2;
+
+	set->ops->remove(set, &elem);
+
+	nft_data_uninit(&elem.key, NFT_DATA_VALUE);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_uninit(&elem.data, set->dtype);
+
+err2:
+	nft_data_uninit(&elem.key, desc.type);
+err1:
+	return err;
+}
+
+static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
+				const struct nlmsghdr *nlh,
+				const struct nlattr * const nla[])
+{
+	const struct nlattr *attr;
+	struct nft_set *set;
+	struct nft_ctx ctx;
+	int rem, err;
+
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	if (err < 0)
+		return err;
+
+	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
+		return -EBUSY;
+
+	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
+		err = nft_del_setelem(&ctx, set, attr);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
 static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 	[NFT_MSG_NEWTABLE] = {
 		.call		= nf_tables_newtable,
@@ -1438,6 +2377,36 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.attr_count	= NFTA_RULE_MAX,
 		.policy		= nft_rule_policy,
 	},
+	[NFT_MSG_NEWSET] = {
+		.call		= nf_tables_newset,
+		.attr_count	= NFTA_SET_MAX,
+		.policy		= nft_set_policy,
+	},
+	[NFT_MSG_GETSET] = {
+		.call		= nf_tables_getset,
+		.attr_count	= NFTA_SET_MAX,
+		.policy		= nft_set_policy,
+	},
+	[NFT_MSG_DELSET] = {
+		.call		= nf_tables_delset,
+		.attr_count	= NFTA_SET_MAX,
+		.policy		= nft_set_policy,
+	},
+	[NFT_MSG_NEWSETELEM] = {
+		.call		= nf_tables_newsetelem,
+		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
+		.policy		= nft_set_elem_list_policy,
+	},
+	[NFT_MSG_GETSETELEM] = {
+		.call		= nf_tables_getsetelem,
+		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
+		.policy		= nft_set_elem_list_policy,
+	},
+	[NFT_MSG_DELSETELEM] = {
+		.call		= nf_tables_delsetelem,
+		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
+		.policy		= nft_set_elem_list_policy,
+	},
 };
 
 static const struct nfnetlink_subsystem nf_tables_subsys = {
@@ -1447,6 +2416,90 @@ static const struct nfnetlink_subsystem nf_tables_subsys = {
 	.cb		= nf_tables_cb,
 };
 
+/*
+ * Loop detection - walk through the ruleset beginning at the destination chain
+ * of a new jump until either the source chain is reached (loop) or all
+ * reachable chains have been traversed.
+ *
+ * The loop check is performed whenever a new jump verdict is added to an
+ * expression or verdict map or a verdict map is bound to a new chain.
+ */
+
+static int nf_tables_check_loops(const struct nft_ctx *ctx,
+				 const struct nft_chain *chain);
+
+static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
+					const struct nft_set *set,
+					const struct nft_set_iter *iter,
+					const struct nft_set_elem *elem)
+{
+	switch (elem->data.verdict) {
+	case NFT_JUMP:
+	case NFT_GOTO:
+		return nf_tables_check_loops(ctx, elem->data.chain);
+	default:
+		return 0;
+	}
+}
+
+static int nf_tables_check_loops(const struct nft_ctx *ctx,
+				 const struct nft_chain *chain)
+{
+	const struct nft_rule *rule;
+	const struct nft_expr *expr, *last;
+	const struct nft_data *data;
+	const struct nft_set *set;
+	struct nft_set_binding *binding;
+	struct nft_set_iter iter;
+	int err;
+
+	if (ctx->chain == chain)
+		return -ELOOP;
+
+	list_for_each_entry(rule, &chain->rules, list) {
+		nft_rule_for_each_expr(expr, last, rule) {
+			if (!expr->ops->get_verdict)
+				continue;
+
+			data = expr->ops->get_verdict(expr);
+			if (data == NULL)
+				break;
+
+			switch (data->verdict) {
+			case NFT_JUMP:
+			case NFT_GOTO:
+				err = nf_tables_check_loops(ctx, data->chain);
+				if (err < 0)
+					return err;
+			default:
+				break;
+			}
+		}
+	}
+
+	list_for_each_entry(set, &ctx->table->sets, list) {
+		if (!(set->flags & NFT_SET_MAP) ||
+		    set->dtype != NFT_DATA_VERDICT)
+			continue;
+
+		list_for_each_entry(binding, &set->bindings, list) {
+			if (binding->chain != chain)
+				continue;
+
+			iter.skip 	= 0;
+			iter.count	= 0;
+			iter.err	= 0;
+			iter.fn		= nf_tables_loop_check_setelem;
+
+			set->ops->walk(ctx, set, &iter);
+			if (iter.err < 0)
+				return iter.err;
+		}
+	}
+
+	return 0;
+}
+
 /**
  *	nft_validate_input_register - validate an expressions' input register
  *
@@ -1500,11 +2553,25 @@ int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg,
 			   const struct nft_data *data,
 			   enum nft_data_types type)
 {
+	int err;
+
 	switch (reg) {
 	case NFT_REG_VERDICT:
 		if (data == NULL || type != NFT_DATA_VERDICT)
 			return -EINVAL;
-		// FIXME: do loop detection
+
+		if (data->verdict == NFT_GOTO || data->verdict == NFT_JUMP) {
+			err = nf_tables_check_loops(ctx, data->chain);
+			if (err < 0)
+				return err;
+
+			if (ctx->chain->level + 1 > data->chain->level) {
+				if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
+					return -EMLINK;
+				data->chain->level = ctx->chain->level + 1;
+			}
+		}
+
 		return 0;
 	default:
 		if (data != NULL && type != NFT_DATA_VALUE)
@@ -1555,11 +2622,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 		if (chain->flags & NFT_BASE_CHAIN)
 			return -EOPNOTSUPP;
 
-		if (ctx->chain->level + 1 > chain->level) {
-			if (ctx->chain->level + 1 == 16)
-				return -EMLINK;
-			chain->level = ctx->chain->level + 1;
-		}
 		chain->use++;
 		data->chain = chain;
 		desc->len = sizeof(data);
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index bc7fb85d4002..fd0ecd3255c1 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -20,8 +20,6 @@
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
 
-#define NFT_JUMP_STACK_SIZE	16
-
 unsigned int nft_do_chain(const struct nf_hook_ops *ops,
 			  struct sk_buff *skb,
 			  const struct net_device *in,
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 67cc502881f1..3d3f8fce10a5 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -21,11 +21,6 @@
 struct nft_hash {
 	struct hlist_head	*hash;
 	unsigned int		hsize;
-	enum nft_registers	sreg:8;
-	enum nft_registers	dreg:8;
-	u8			klen;
-	u8			dlen;
-	u16			flags;
 };
 
 struct nft_hash_elem {
@@ -42,213 +37,140 @@ static unsigned int nft_hash_data(const struct nft_data *data,
 {
 	unsigned int h;
 
-	// FIXME: can we reasonably guarantee the upper bits are fixed?
-	h = jhash2(data->data, len >> 2, nft_hash_rnd);
+	h = jhash(data->data, len, nft_hash_rnd);
 	return ((u64)h * hsize) >> 32;
 }
 
-static void nft_hash_eval(const struct nft_expr *expr,
-			  struct nft_data data[NFT_REG_MAX + 1],
-			  const struct nft_pktinfo *pkt)
+static bool nft_hash_lookup(const struct nft_set *set,
+			    const struct nft_data *key,
+			    struct nft_data *data)
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
-	const struct nft_hash_elem *elem;
-	const struct nft_data *key = &data[priv->sreg];
+	const struct nft_hash *priv = nft_set_priv(set);
+	const struct nft_hash_elem *he;
 	unsigned int h;
 
-	h = nft_hash_data(key, priv->hsize, priv->klen);
-	hlist_for_each_entry(elem, &priv->hash[h], hnode) {
-		if (nft_data_cmp(&elem->key, key, priv->klen))
+	h = nft_hash_data(key, priv->hsize, set->klen);
+	hlist_for_each_entry(he, &priv->hash[h], hnode) {
+		if (nft_data_cmp(&he->key, key, set->klen))
 			continue;
-		if (priv->flags & NFT_HASH_MAP)
-			nft_data_copy(&data[priv->dreg], elem->data);
-		return;
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(data, he->data);
+		return true;
 	}
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+	return false;
 }
 
-static void nft_hash_elem_destroy(const struct nft_expr *expr,
-				  struct nft_hash_elem *elem)
+static void nft_hash_elem_destroy(const struct nft_set *set,
+				  struct nft_hash_elem *he)
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
-
-	nft_data_uninit(&elem->key, NFT_DATA_VALUE);
-	if (priv->flags & NFT_HASH_MAP)
-		nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
-	kfree(elem);
+	nft_data_uninit(&he->key, NFT_DATA_VALUE);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_uninit(he->data, set->dtype);
+	kfree(he);
 }
 
-static const struct nla_policy nft_he_policy[NFTA_HE_MAX + 1] = {
-	[NFTA_HE_KEY]		= { .type = NLA_NESTED },
-	[NFTA_HE_DATA]		= { .type = NLA_NESTED },
-};
-
-static int nft_hash_elem_init(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nlattr *nla,
-			      struct nft_hash_elem **new)
+static int nft_hash_insert(const struct nft_set *set,
+			   const struct nft_set_elem *elem)
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
-	struct nlattr *tb[NFTA_HE_MAX + 1];
-	struct nft_hash_elem *elem;
-	struct nft_data_desc d1, d2;
-	unsigned int size;
-	int err;
+	struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he;
+	unsigned int size, h;
 
-	err = nla_parse_nested(tb, NFTA_HE_MAX, nla, nft_he_policy);
-	if (err < 0)
-		return err;
-
-	if (tb[NFTA_HE_KEY] == NULL)
+	if (elem->flags != 0)
 		return -EINVAL;
-	size = sizeof(*elem);
-
-	if (priv->flags & NFT_HASH_MAP) {
-		if (tb[NFTA_HE_DATA] == NULL)
-			return -EINVAL;
-		size += sizeof(elem->data[0]);
-	} else {
-		if (tb[NFTA_HE_DATA] != NULL)
-			return -EINVAL;
-	}
 
-	elem = kzalloc(size, GFP_KERNEL);
-	if (elem == NULL)
+	size = sizeof(*he);
+	if (set->flags & NFT_SET_MAP)
+		size += sizeof(he->data[0]);
+
+	he = kzalloc(size, GFP_KERNEL);
+	if (he == NULL)
 		return -ENOMEM;
 
-	err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_HE_KEY]);
-	if (err < 0)
-		goto err1;
-	err = -EINVAL;
-	if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
-		goto err2;
-
-	if (tb[NFTA_HE_DATA] != NULL) {
-		err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_HE_DATA]);
-		if (err < 0)
-			goto err2;
-		err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
-		if (err < 0)
-			goto err3;
-	}
+	nft_data_copy(&he->key, &elem->key);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_copy(he->data, &elem->data);
 
-	*new = elem;
+	h = nft_hash_data(&he->key, priv->hsize, set->klen);
+	hlist_add_head_rcu(&he->hnode, &priv->hash[h]);
 	return 0;
-
-err3:
-	nft_data_uninit(elem->data, d2.type);
-err2:
-	nft_data_uninit(&elem->key, d1.type);
-err1:
-	kfree(elem);
-	return err;
 }
 
-static int nft_hash_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
-			      const struct nft_hash_elem *elem)
-
+static void nft_hash_remove(const struct nft_set *set,
+			    const struct nft_set_elem *elem)
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
-	struct nlattr *nest;
+	struct nft_hash_elem *he = elem->cookie;
 
-	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
-	if (nest == NULL)
-		goto nla_put_failure;
-
-	if (nft_data_dump(skb, NFTA_HE_KEY, &elem->key,
-			  NFT_DATA_VALUE, priv->klen) < 0)
-		goto nla_put_failure;
+	hlist_del_rcu(&he->hnode);
+	kfree(he);
+}
 
-	if (priv->flags & NFT_HASH_MAP) {
-		if (nft_data_dump(skb, NFTA_HE_DATA, elem->data,
-				  NFT_DATA_VALUE, priv->dlen) < 0)
-			goto nla_put_failure;
-	}
+static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
+{
+	const struct nft_hash *priv = nft_set_priv(set);
+	struct nft_hash_elem *he;
+	unsigned int h;
 
-	nla_nest_end(skb, nest);
-	return 0;
+	h = nft_hash_data(&elem->key, priv->hsize, set->klen);
+	hlist_for_each_entry(he, &priv->hash[h], hnode) {
+		if (nft_data_cmp(&he->key, &elem->key, set->klen))
+			continue;
 
-nla_put_failure:
-	return -1;
+		elem->cookie = he;
+		elem->flags  = 0;
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(&elem->data, he->data);
+		return 0;
+	}
+	return -ENOENT;
 }
 
-static void nft_hash_destroy(const struct nft_ctx *ctx,
-			     const struct nft_expr *expr)
+static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
+			  struct nft_set_iter *iter)
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
-	const struct hlist_node *next;
-	struct nft_hash_elem *elem;
+	const struct nft_hash *priv = nft_set_priv(set);
+	const struct nft_hash_elem *he;
+	struct nft_set_elem elem;
 	unsigned int i;
 
 	for (i = 0; i < priv->hsize; i++) {
-		hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
-			hlist_del(&elem->hnode);
-			nft_hash_elem_destroy(expr, elem);
+		hlist_for_each_entry(he, &priv->hash[i], hnode) {
+			if (iter->count < iter->skip)
+				goto cont;
+
+			memcpy(&elem.key, &he->key, sizeof(elem.key));
+			if (set->flags & NFT_SET_MAP)
+				memcpy(&elem.data, he->data, sizeof(elem.data));
+			elem.flags = 0;
+
+			iter->err = iter->fn(ctx, set, iter, &elem);
+			if (iter->err < 0)
+				return;
+cont:
+			iter->count++;
 		}
 	}
-	kfree(priv->hash);
 }
 
-static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
-	[NFTA_HASH_FLAGS]	= { .type = NLA_U32 },
-	[NFTA_HASH_SREG]	= { .type = NLA_U32 },
-	[NFTA_HASH_DREG]	= { .type = NLA_U32 },
-	[NFTA_HASH_KLEN]	= { .type = NLA_U32 },
-	[NFTA_HASH_ELEMENTS]	= { .type = NLA_NESTED },
-};
+static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
+{
+	return sizeof(struct nft_hash);
+}
 
-static int nft_hash_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+static int nft_hash_init(const struct nft_set *set,
 			 const struct nlattr * const tb[])
 {
-	struct nft_hash *priv = nft_expr_priv(expr);
-	struct nft_hash_elem *elem, *uninitialized_var(new);
-	const struct nlattr *nla;
+	struct nft_hash *priv = nft_set_priv(set);
 	unsigned int cnt, i;
-	unsigned int h;
-	int err, rem;
 
 	if (unlikely(!nft_hash_rnd_initted)) {
 		get_random_bytes(&nft_hash_rnd, 4);
 		nft_hash_rnd_initted = true;
 	}
 
-	if (tb[NFTA_HASH_SREG] == NULL ||
-	    tb[NFTA_HASH_KLEN] == NULL ||
-	    tb[NFTA_HASH_ELEMENTS] == NULL)
-		return -EINVAL;
-
-	if (tb[NFTA_HASH_FLAGS] != NULL) {
-		priv->flags = ntohl(nla_get_be32(tb[NFTA_HASH_FLAGS]));
-		if (priv->flags & ~NFT_HASH_MAP)
-			return -EINVAL;
-	}
-
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_HASH_SREG]));
-	err = nft_validate_input_register(priv->sreg);
-	if (err < 0)
-		return err;
-
-	if (tb[NFTA_HASH_DREG] != NULL) {
-		if (!(priv->flags & NFT_HASH_MAP))
-			return -EINVAL;
-		priv->dreg = ntohl(nla_get_be32(tb[NFTA_HASH_DREG]));
-		err = nft_validate_output_register(priv->dreg);
-		if (err < 0)
-			return err;
-	}
-
-	priv->klen = ntohl(nla_get_be32(tb[NFTA_HASH_KLEN]));
-	if (priv->klen == 0)
-		return -EINVAL;
-
-	cnt = 0;
-	nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
-		if (nla_type(nla) != NFTA_LIST_ELEM)
-			return -EINVAL;
-		cnt++;
-	}
-
 	/* Aim for a load factor of 0.75 */
+	// FIXME: temporarily broken until we have set descriptions
+	cnt = 100;
 	cnt = cnt * 4 / 3;
 
 	priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL);
@@ -259,85 +181,46 @@ static int nft_hash_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	for (i = 0; i < cnt; i++)
 		INIT_HLIST_HEAD(&priv->hash[i]);
 
-	err = -ENOMEM;
-	nla_for_each_nested(nla, tb[NFTA_HASH_ELEMENTS], rem) {
-		err = nft_hash_elem_init(ctx, expr, nla, &new);
-		if (err < 0)
-			goto err1;
-
-		h = nft_hash_data(&new->key, priv->hsize, priv->klen);
-		hlist_for_each_entry(elem, &priv->hash[h], hnode) {
-			if (nft_data_cmp(&elem->key, &new->key, priv->klen))
-				continue;
-			nft_hash_elem_destroy(expr, new);
-			err = -EEXIST;
-			goto err1;
-		}
-		hlist_add_head(&new->hnode, &priv->hash[h]);
-	}
 	return 0;
-
-err1:
-	nft_hash_destroy(ctx, expr);
-	return err;
 }
 
-static int nft_hash_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static void nft_hash_destroy(const struct nft_set *set)
 {
-	const struct nft_hash *priv = nft_expr_priv(expr);
-	const struct nft_hash_elem *elem;
-	struct nlattr *list;
+	const struct nft_hash *priv = nft_set_priv(set);
+	const struct hlist_node *next;
+	struct nft_hash_elem *elem;
 	unsigned int i;
 
-	if (priv->flags)
-		if (nla_put_be32(skb, NFTA_HASH_FLAGS, htonl(priv->flags)))
-			goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_HASH_SREG, htonl(priv->sreg)))
-		goto nla_put_failure;
-	if (priv->flags & NFT_HASH_MAP)
-		if (nla_put_be32(skb, NFTA_HASH_DREG, htonl(priv->dreg)))
-			goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_HASH_KLEN, htonl(priv->klen)))
-		goto nla_put_failure;
-
-	list = nla_nest_start(skb, NFTA_HASH_ELEMENTS);
-	if (list == NULL)
-		goto nla_put_failure;
-
 	for (i = 0; i < priv->hsize; i++) {
-		hlist_for_each_entry(elem, &priv->hash[i], hnode) {
-			if (nft_hash_elem_dump(skb, expr, elem) < 0)
-				goto nla_put_failure;
+		hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) {
+			hlist_del(&elem->hnode);
+			nft_hash_elem_destroy(set, elem);
 		}
 	}
-
-	nla_nest_end(skb, list);
-	return 0;
-
-nla_put_failure:
-	return -1;
+	kfree(priv->hash);
 }
 
-static struct nft_expr_ops nft_hash_ops __read_mostly = {
-	.name		= "hash",
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_hash)),
-	.owner		= THIS_MODULE,
-	.eval		= nft_hash_eval,
+static struct nft_set_ops nft_hash_ops __read_mostly = {
+	.privsize       = nft_hash_privsize,
 	.init		= nft_hash_init,
 	.destroy	= nft_hash_destroy,
-	.dump		= nft_hash_dump,
-	.policy		= nft_hash_policy,
-	.maxattr	= NFTA_HASH_MAX,
+	.get		= nft_hash_get,
+	.insert		= nft_hash_insert,
+	.remove		= nft_hash_remove,
+	.lookup		= nft_hash_lookup,
+	.walk		= nft_hash_walk,
+	.features	= NFT_SET_MAP,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_hash_module_init(void)
 {
-	return nft_register_expr(&nft_hash_ops);
+	return nft_register_set(&nft_hash_ops);
 }
 
 static void __exit nft_hash_module_exit(void)
 {
-	nft_unregister_expr(&nft_hash_ops);
+	nft_unregister_set(&nft_hash_ops);
 }
 
 module_init(nft_hash_module_init);
@@ -345,4 +228,4 @@ module_exit(nft_hash_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("hash");
+MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 3bf42c3cc49a..78334bf37007 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -90,6 +90,16 @@ nla_put_failure:
 	return -1;
 }
 
+static const struct nft_data *nft_immediate_get_verdict(const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+
+	if (priv->dreg == NFT_REG_VERDICT)
+		return &priv->data;
+	else
+		return NULL;
+}
+
 static struct nft_expr_ops nft_imm_ops __read_mostly = {
 	.name		= "immediate",
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
@@ -98,6 +108,7 @@ static struct nft_expr_ops nft_imm_ops __read_mostly = {
 	.init		= nft_immediate_init,
 	.destroy	= nft_immediate_destroy,
 	.dump		= nft_immediate_dump,
+	.get_verdict	= nft_immediate_get_verdict,
 	.policy		= nft_immediate_policy,
 	.maxattr	= NFTA_IMMEDIATE_MAX,
 };
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
new file mode 100644
index 000000000000..4962d2173678
--- /dev/null
+++ b/net/netfilter/nft_lookup.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright (c) 2009 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_lookup {
+	struct nft_set			*set;
+	enum nft_registers		sreg:8;
+	enum nft_registers		dreg:8;
+	struct nft_set_binding		binding;
+};
+
+static void nft_lookup_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
+{
+	const struct nft_lookup *priv = nft_expr_priv(expr);
+	const struct nft_set *set = priv->set;
+
+	if (set->ops->lookup(set, &data[priv->sreg], &data[priv->dreg]))
+		return;
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
+	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING },
+	[NFTA_LOOKUP_SREG]	= { .type = NLA_U32 },
+	[NFTA_LOOKUP_DREG]	= { .type = NLA_U32 },
+};
+
+static int nft_lookup_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_lookup *priv = nft_expr_priv(expr);
+	struct nft_set *set;
+	int err;
+
+	if (tb[NFTA_LOOKUP_SET] == NULL ||
+	    tb[NFTA_LOOKUP_SREG] == NULL)
+		return -EINVAL;
+
+	set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_LOOKUP_DREG] != NULL) {
+		if (!(set->flags & NFT_SET_MAP))
+			return -EINVAL;
+
+		priv->dreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_DREG]));
+		err = nft_validate_output_register(priv->dreg);
+		if (err < 0)
+			return err;
+
+		if (priv->dreg == NFT_REG_VERDICT) {
+			if (set->dtype != NFT_DATA_VERDICT)
+				return -EINVAL;
+		} else if (set->dtype == NFT_DATA_VERDICT)
+			return -EINVAL;
+	} else if (set->flags & NFT_SET_MAP)
+		return -EINVAL;
+
+	err = nf_tables_bind_set(ctx, set, &priv->binding);
+	if (err < 0)
+		return err;
+
+	priv->set = set;
+	return 0;
+}
+
+static void nft_lookup_destroy(const struct nft_expr *expr)
+{
+	struct nft_lookup *priv = nft_expr_priv(expr);
+
+	nf_tables_unbind_set(NULL, priv->set, &priv->binding);
+}
+
+static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_lookup *priv = nft_expr_priv(expr);
+
+	if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_LOOKUP_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (priv->set->flags & NFT_SET_MAP)
+		if (nla_put_be32(skb, NFTA_LOOKUP_DREG, htonl(priv->dreg)))
+			goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_ops nft_lookup_ops __read_mostly = {
+	.name		= "lookup",
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
+	.owner		= THIS_MODULE,
+	.eval		= nft_lookup_eval,
+	.init		= nft_lookup_init,
+	.destroy	= nft_lookup_destroy,
+	.dump		= nft_lookup_dump,
+	.policy		= nft_lookup_policy,
+	.maxattr	= NFTA_LOOKUP_MAX,
+};
+
+int __init nft_lookup_module_init(void)
+{
+	return nft_register_expr(&nft_lookup_ops);
+}
+
+void nft_lookup_module_exit(void)
+{
+	nft_unregister_expr(&nft_lookup_ops);
+}
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
new file mode 100644
index 000000000000..ca0c1b231bfe
--- /dev/null
+++ b/net/netfilter/nft_rbtree.c
@@ -0,0 +1,247 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_rbtree {
+	struct rb_root		root;
+};
+
+struct nft_rbtree_elem {
+	struct rb_node		node;
+	u16			flags;
+	struct nft_data		key;
+	struct nft_data		data[];
+};
+
+static bool nft_rbtree_lookup(const struct nft_set *set,
+			      const struct nft_data *key,
+			      struct nft_data *data)
+{
+	const struct nft_rbtree *priv = nft_set_priv(set);
+	const struct nft_rbtree_elem *rbe, *interval = NULL;
+	const struct rb_node *parent = priv->root.rb_node;
+	int d;
+
+	while (parent != NULL) {
+		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+
+		d = nft_data_cmp(&rbe->key, key, set->klen);
+		if (d < 0) {
+			parent = parent->rb_left;
+			interval = rbe;
+		} else if (d > 0)
+			parent = parent->rb_right;
+		else {
+found:
+			if (rbe->flags & NFT_SET_ELEM_INTERVAL_END)
+				goto out;
+			if (set->flags & NFT_SET_MAP)
+				nft_data_copy(data, rbe->data);
+			return true;
+		}
+	}
+
+	if (set->flags & NFT_SET_INTERVAL && interval != NULL) {
+		rbe = interval;
+		goto found;
+	}
+out:
+	return false;
+}
+
+static void nft_rbtree_elem_destroy(const struct nft_set *set,
+				    struct nft_rbtree_elem *rbe)
+{
+	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_uninit(rbe->data, set->dtype);
+	kfree(rbe);
+}
+
+static int __nft_rbtree_insert(const struct nft_set *set,
+			       struct nft_rbtree_elem *new)
+{
+	struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree_elem *rbe;
+	struct rb_node *parent, **p;
+	int d;
+
+	parent = NULL;
+	p = &priv->root.rb_node;
+	while (*p != NULL) {
+		parent = *p;
+		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+		d = nft_data_cmp(&rbe->key, &new->key, set->klen);
+		if (d < 0)
+			p = &parent->rb_left;
+		else if (d > 0)
+			p = &parent->rb_right;
+		else
+			return -EEXIST;
+	}
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, &priv->root);
+	return 0;
+}
+
+static int nft_rbtree_insert(const struct nft_set *set,
+			     const struct nft_set_elem *elem)
+{
+	struct nft_rbtree_elem *rbe;
+	unsigned int size;
+	int err;
+
+	size = sizeof(*rbe);
+	if (set->flags & NFT_SET_MAP)
+		size += sizeof(rbe->data[0]);
+
+	rbe = kzalloc(size, GFP_KERNEL);
+	if (rbe == NULL)
+		return -ENOMEM;
+
+	rbe->flags = elem->flags;
+	nft_data_copy(&rbe->key, &elem->key);
+	if (set->flags & NFT_SET_MAP)
+		nft_data_copy(rbe->data, &elem->data);
+
+	err = __nft_rbtree_insert(set, rbe);
+	if (err < 0)
+		kfree(rbe);
+	return err;
+}
+
+static void nft_rbtree_remove(const struct nft_set *set,
+			      const struct nft_set_elem *elem)
+{
+	struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree_elem *rbe = elem->cookie;
+
+	rb_erase(&rbe->node, &priv->root);
+	kfree(rbe);
+}
+
+static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
+{
+	const struct nft_rbtree *priv = nft_set_priv(set);
+	const struct rb_node *parent = priv->root.rb_node;
+	struct nft_rbtree_elem *rbe;
+	int d;
+
+	while (parent != NULL) {
+		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+
+		d = nft_data_cmp(&rbe->key, &elem->key, set->klen);
+		if (d < 0)
+			parent = parent->rb_left;
+		else if (d > 0)
+			parent = parent->rb_right;
+		else {
+			elem->cookie = rbe;
+			if (set->flags & NFT_SET_MAP)
+				nft_data_copy(&elem->data, rbe->data);
+			elem->flags = rbe->flags;
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+static void nft_rbtree_walk(const struct nft_ctx *ctx,
+			    const struct nft_set *set,
+			    struct nft_set_iter *iter)
+{
+	const struct nft_rbtree *priv = nft_set_priv(set);
+	const struct nft_rbtree_elem *rbe;
+	struct nft_set_elem elem;
+	struct rb_node *node;
+
+	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
+		if (iter->count < iter->skip)
+			goto cont;
+
+		rbe = rb_entry(node, struct nft_rbtree_elem, node);
+		nft_data_copy(&elem.key, &rbe->key);
+		if (set->flags & NFT_SET_MAP)
+			nft_data_copy(&elem.data, rbe->data);
+		elem.flags = rbe->flags;
+
+		iter->err = iter->fn(ctx, set, iter, &elem);
+		if (iter->err < 0)
+			return;
+cont:
+		iter->count++;
+	}
+}
+
+static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
+{
+	return sizeof(struct nft_rbtree);
+}
+
+static int nft_rbtree_init(const struct nft_set *set,
+			   const struct nlattr * const nla[])
+{
+	struct nft_rbtree *priv = nft_set_priv(set);
+
+	priv->root = RB_ROOT;
+	return 0;
+}
+
+static void nft_rbtree_destroy(const struct nft_set *set)
+{
+	struct nft_rbtree *priv = nft_set_priv(set);
+	struct nft_rbtree_elem *rbe;
+	struct rb_node *node;
+
+	while ((node = priv->root.rb_node) != NULL) {
+		rb_erase(node, &priv->root);
+		rbe = rb_entry(node, struct nft_rbtree_elem, node);
+		nft_rbtree_elem_destroy(set, rbe);
+	}
+}
+
+static struct nft_set_ops nft_rbtree_ops __read_mostly = {
+	.privsize	= nft_rbtree_privsize,
+	.init		= nft_rbtree_init,
+	.destroy	= nft_rbtree_destroy,
+	.insert		= nft_rbtree_insert,
+	.remove		= nft_rbtree_remove,
+	.get		= nft_rbtree_get,
+	.lookup		= nft_rbtree_lookup,
+	.walk		= nft_rbtree_walk,
+	.features	= NFT_SET_INTERVAL | NFT_SET_MAP,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_rbtree_module_init(void)
+{
+	return nft_register_set(&nft_rbtree_ops);
+}
+
+static void __exit nft_rbtree_module_exit(void)
+{
+	nft_unregister_set(&nft_rbtree_ops);
+}
+
+module_init(nft_rbtree_module_init);
+module_exit(nft_rbtree_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_set.c b/net/netfilter/nft_set.c
deleted file mode 100644
index 7b7c8354c327..000000000000
--- a/net/netfilter/nft_set.c
+++ /dev/null
@@ -1,381 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-
-struct nft_set {
-	struct rb_root		root;
-	enum nft_registers	sreg:8;
-	enum nft_registers	dreg:8;
-	u8			klen;
-	u8			dlen;
-	u16			flags;
-};
-
-struct nft_set_elem {
-	struct rb_node		node;
-	enum nft_set_elem_flags	flags;
-	struct nft_data		key;
-	struct nft_data		data[];
-};
-
-static void nft_set_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
-			 const struct nft_pktinfo *pkt)
-{
-	const struct nft_set *priv = nft_expr_priv(expr);
-	const struct rb_node *parent = priv->root.rb_node;
-	const struct nft_set_elem *elem, *interval = NULL;
-	const struct nft_data *key = &data[priv->sreg];
-	int d;
-
-	while (parent != NULL) {
-		elem = rb_entry(parent, struct nft_set_elem, node);
-
-		d = nft_data_cmp(&elem->key, key, priv->klen);
-		if (d < 0) {
-			parent = parent->rb_left;
-			interval = elem;
-		} else if (d > 0)
-			parent = parent->rb_right;
-		else {
-found:
-			if (elem->flags & NFT_SE_INTERVAL_END)
-				goto out;
-			if (priv->flags & NFT_SET_MAP)
-				nft_data_copy(&data[priv->dreg], elem->data);
-			return;
-		}
-	}
-
-	if (priv->flags & NFT_SET_INTERVAL && interval != NULL) {
-		elem = interval;
-		goto found;
-	}
-out:
-	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
-}
-
-static void nft_set_elem_destroy(const struct nft_expr *expr,
-				 struct nft_set_elem *elem)
-{
-	const struct nft_set *priv = nft_expr_priv(expr);
-
-	nft_data_uninit(&elem->key, NFT_DATA_VALUE);
-	if (priv->flags & NFT_SET_MAP)
-		nft_data_uninit(elem->data, nft_dreg_to_type(priv->dreg));
-	kfree(elem);
-}
-
-static const struct nla_policy nft_se_policy[NFTA_SE_MAX + 1] = {
-	[NFTA_SE_KEY]		= { .type = NLA_NESTED },
-	[NFTA_SE_DATA]		= { .type = NLA_NESTED },
-	[NFTA_SE_FLAGS]		= { .type = NLA_U32 },
-};
-
-static int nft_set_elem_init(const struct nft_ctx *ctx,
-			     const struct nft_expr *expr,
-			     const struct nlattr *nla,
-			     struct nft_set_elem **new)
-{
-	struct nft_set *priv = nft_expr_priv(expr);
-	struct nlattr *tb[NFTA_SE_MAX + 1];
-	struct nft_set_elem *elem;
-	struct nft_data_desc d1, d2;
-	enum nft_set_elem_flags flags = 0;
-	unsigned int size;
-	int err;
-
-	err = nla_parse_nested(tb, NFTA_SE_MAX, nla, nft_se_policy);
-	if (err < 0)
-		return err;
-
-	if (tb[NFTA_SE_KEY] == NULL)
-		return -EINVAL;
-
-	if (tb[NFTA_SE_FLAGS] != NULL) {
-		flags = ntohl(nla_get_be32(tb[NFTA_SE_FLAGS]));
-		if (flags & ~NFT_SE_INTERVAL_END)
-			return -EINVAL;
-	}
-
-	size = sizeof(*elem);
-	if (priv->flags & NFT_SET_MAP) {
-		if (tb[NFTA_SE_DATA] == NULL && !(flags & NFT_SE_INTERVAL_END))
-			return -EINVAL;
-		size += sizeof(elem->data[0]);
-	} else {
-		if (tb[NFTA_SE_DATA] != NULL)
-			return -EINVAL;
-	}
-
-	elem = kzalloc(size, GFP_KERNEL);
-	if (elem == NULL)
-		return -ENOMEM;
-	elem->flags = flags;
-
-	err = nft_data_init(ctx, &elem->key, &d1, tb[NFTA_SE_KEY]);
-	if (err < 0)
-		goto err1;
-	err = -EINVAL;
-	if (d1.type != NFT_DATA_VALUE || d1.len != priv->klen)
-		goto err2;
-
-	if (tb[NFTA_SE_DATA] != NULL) {
-		err = nft_data_init(ctx, elem->data, &d2, tb[NFTA_SE_DATA]);
-		if (err < 0)
-			goto err2;
-		err = -EINVAL;
-		if (priv->dreg != NFT_REG_VERDICT && d2.len != priv->dlen)
-			goto err2;
-		err = nft_validate_data_load(ctx, priv->dreg, elem->data, d2.type);
-		if (err < 0)
-			goto err3;
-	}
-
-	*new = elem;
-	return 0;
-
-err3:
-	nft_data_uninit(elem->data, d2.type);
-err2:
-	nft_data_uninit(&elem->key, d1.type);
-err1:
-	kfree(elem);
-	return err;
-}
-
-static int nft_set_elem_dump(struct sk_buff *skb, const struct nft_expr *expr,
-			     const struct nft_set_elem *elem)
-
-{
-	const struct nft_set *priv = nft_expr_priv(expr);
-	struct nlattr *nest;
-
-	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
-	if (nest == NULL)
-		goto nla_put_failure;
-
-	if (nft_data_dump(skb, NFTA_SE_KEY, &elem->key,
-			  NFT_DATA_VALUE, priv->klen) < 0)
-		goto nla_put_failure;
-
-	if (priv->flags & NFT_SET_MAP && !(elem->flags & NFT_SE_INTERVAL_END)) {
-		if (nft_data_dump(skb, NFTA_SE_DATA, elem->data,
-				  nft_dreg_to_type(priv->dreg), priv->dlen) < 0)
-			goto nla_put_failure;
-	}
-
-	if (elem->flags){
-		if (nla_put_be32(skb, NFTA_SE_FLAGS, htonl(elem->flags)))
-			goto nla_put_failure;
-	}
-
-	nla_nest_end(skb, nest);
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static void nft_set_destroy(const struct nft_expr *expr)
-{
-	struct nft_set *priv = nft_expr_priv(expr);
-	struct nft_set_elem *elem;
-	struct rb_node *node;
-
-	while ((node = priv->root.rb_node) != NULL) {
-		rb_erase(node, &priv->root);
-		elem = rb_entry(node, struct nft_set_elem, node);
-		nft_set_elem_destroy(expr, elem);
-	}
-}
-
-static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
-	[NFTA_SET_FLAGS]	= { .type = NLA_U32 },
-	[NFTA_SET_SREG]		= { .type = NLA_U32 },
-	[NFTA_SET_DREG]		= { .type = NLA_U32 },
-	[NFTA_SET_KLEN]		= { .type = NLA_U32 },
-	[NFTA_SET_DLEN]		= { .type = NLA_U32 },
-	[NFTA_SET_ELEMENTS]	= { .type = NLA_NESTED },
-};
-
-static int nft_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			const struct nlattr * const tb[])
-{
-	struct nft_set *priv = nft_expr_priv(expr);
-	struct nft_set_elem *elem, *uninitialized_var(new);
-	struct rb_node *parent, **p;
-	const struct nlattr *nla;
-	int err, rem, d;
-
-	if (tb[NFTA_SET_SREG] == NULL ||
-	    tb[NFTA_SET_KLEN] == NULL ||
-	    tb[NFTA_SET_ELEMENTS] == NULL)
-		return -EINVAL;
-
-	priv->root = RB_ROOT;
-
-	if (tb[NFTA_SET_FLAGS] != NULL) {
-		priv->flags = ntohl(nla_get_be32(tb[NFTA_SET_FLAGS]));
-		if (priv->flags & ~(NFT_SET_INTERVAL | NFT_SET_MAP))
-			return -EINVAL;
-	}
-
-	priv->sreg = ntohl(nla_get_be32(tb[NFTA_SET_SREG]));
-	err = nft_validate_input_register(priv->sreg);
-	if (err < 0)
-		return err;
-
-	if (tb[NFTA_SET_DREG] != NULL) {
-		if (!(priv->flags & NFT_SET_MAP))
-			return -EINVAL;
-		if (tb[NFTA_SET_DLEN] == NULL)
-			return -EINVAL;
-
-		priv->dreg = ntohl(nla_get_be32(tb[NFTA_SET_DREG]));
-		err = nft_validate_output_register(priv->dreg);
-		if (err < 0)
-			return err;
-
-		if (priv->dreg == NFT_REG_VERDICT)
-			priv->dlen = FIELD_SIZEOF(struct nft_data, data);
-		else {
-			priv->dlen = ntohl(nla_get_be32(tb[NFTA_SET_DLEN]));
-			if (priv->dlen == 0 ||
-			    priv->dlen > FIELD_SIZEOF(struct nft_data, data))
-				return -EINVAL;
-		}
-	} else {
-		if (priv->flags & NFT_SET_MAP)
-			return -EINVAL;
-		if (tb[NFTA_SET_DLEN] != NULL)
-			return -EINVAL;
-	}
-
-	priv->klen = ntohl(nla_get_be32(tb[NFTA_SET_KLEN]));
-	if (priv->klen == 0 ||
-	    priv->klen > FIELD_SIZEOF(struct nft_data, data))
-		return -EINVAL;
-
-	nla_for_each_nested(nla, tb[NFTA_SET_ELEMENTS], rem) {
-		err = -EINVAL;
-		if (nla_type(nla) != NFTA_LIST_ELEM)
-			goto err1;
-
-		err = nft_set_elem_init(ctx, expr, nla, &new);
-		if (err < 0)
-			goto err1;
-
-		parent = NULL;
-		p = &priv->root.rb_node;
-		while (*p != NULL) {
-			parent = *p;
-			elem = rb_entry(parent, struct nft_set_elem, node);
-			d = nft_data_cmp(&elem->key, &new->key, priv->klen);
-			if (d < 0)
-				p = &parent->rb_left;
-			else if (d > 0)
-				p = &parent->rb_right;
-			else {
-				err = -EEXIST;
-				goto err2;
-			}
-		}
-		rb_link_node(&new->node, parent, p);
-		rb_insert_color(&new->node, &priv->root);
-	}
-
-	return 0;
-
-err2:
-	nft_set_elem_destroy(expr, new);
-err1:
-	nft_set_destroy(expr);
-	return err;
-}
-
-static int nft_set_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	struct nft_set *priv = nft_expr_priv(expr);
-	const struct nft_set_elem *elem;
-	struct rb_node *node;
-	struct nlattr *list;
-
-	if (priv->flags) {
-		if (nla_put_be32(skb, NFTA_SET_FLAGS, htonl(priv->flags)))
-			goto nla_put_failure;
-	}
-
-	if (nla_put_be32(skb, NFTA_SET_SREG, htonl(priv->sreg)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_SET_KLEN, htonl(priv->klen)))
-		goto nla_put_failure;
-
-	if (priv->flags & NFT_SET_MAP) {
-		if (nla_put_be32(skb, NFTA_SET_DREG, htonl(priv->dreg)))
-			goto nla_put_failure;
-		if (nla_put_be32(skb, NFTA_SET_DLEN, htonl(priv->dlen)))
-			goto nla_put_failure;
-	}
-
-	list = nla_nest_start(skb, NFTA_SET_ELEMENTS);
-	if (list == NULL)
-		goto nla_put_failure;
-
-	for (node = rb_first(&priv->root); node; node = rb_next(node)) {
-		elem = rb_entry(node, struct nft_set_elem, node);
-		if (nft_set_elem_dump(skb, expr, elem) < 0)
-			goto nla_put_failure;
-	}
-
-	nla_nest_end(skb, list);
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_ops nft_set_ops __read_mostly = {
-	.name		= "set",
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_set)),
-	.owner		= THIS_MODULE,
-	.eval		= nft_set_eval,
-	.init		= nft_set_init,
-	.destroy	= nft_set_destroy,
-	.dump		= nft_set_dump,
-	.policy		= nft_set_policy,
-	.maxattr	= NFTA_SET_MAX,
-};
-
-static int __init nft_set_module_init(void)
-{
-	return nft_register_expr(&nft_set_ops);
-}
-
-static void __exit nft_set_module_exit(void)
-{
-	nft_unregister_expr(&nft_set_ops);
-}
-
-module_init(nft_set_module_init);
-module_exit(nft_set_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("set");
-- 
cgit 


From ef1f7df9170dbd875ce198ba84e6ab80f6fc139e Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 10 Oct 2013 11:41:20 +0200
Subject: netfilter: nf_tables: expression ops overloading

Split the expression ops into two parts and support overloading of
the runtime expression ops based on the requested function through
a ->select_ops() callback.

This can be used to provide optimized implementations, for instance
for loading small aligned amounts of data from the packet or inlining
frequently used operations into the main evaluation loop.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h      |  42 +++++++++-----
 net/ipv4/netfilter/nf_table_nat_ipv4.c |  18 ++++--
 net/ipv4/netfilter/nft_reject_ipv4.c   |  18 ++++--
 net/netfilter/nf_tables_api.c          | 101 +++++++++++++++++++--------------
 net/netfilter/nft_bitwise.c            |  18 ++++--
 net/netfilter/nft_byteorder.c          |  18 ++++--
 net/netfilter/nft_cmp.c                |  18 ++++--
 net/netfilter/nft_counter.c            |  22 ++++---
 net/netfilter/nft_ct.c                 |  18 ++++--
 net/netfilter/nft_expr_template.c      |  20 ++++---
 net/netfilter/nft_exthdr.c             |  16 ++++--
 net/netfilter/nft_immediate.c          |  18 ++++--
 net/netfilter/nft_limit.c              |  18 ++++--
 net/netfilter/nft_log.c                |  18 ++++--
 net/netfilter/nft_lookup.c             |  16 ++++--
 net/netfilter/nft_meta.c               |  18 ++++--
 net/netfilter/nft_payload.c            |  18 ++++--
 17 files changed, 267 insertions(+), 148 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 677dd79380ed..66d0359702c6 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -222,25 +222,45 @@ extern int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 extern void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 				 struct nft_set_binding *binding);
 
+
 /**
- *	struct nft_expr_ops - nf_tables expression operations
+ *	struct nft_expr_type - nf_tables expression type
  *
- *	@eval: Expression evaluation function
- *	@init: initialization function
- *	@destroy: destruction function
- *	@dump: function to dump parameters
+ *	@select_ops: function to select nft_expr_ops
+ *	@ops: default ops, used when no select_ops functions is present
  *	@list: used internally
  *	@name: Identifier
  *	@owner: module reference
  *	@policy: netlink attribute policy
  *	@maxattr: highest netlink attribute number
+ */
+struct nft_expr_type {
+	const struct nft_expr_ops	*(*select_ops)(const struct nlattr * const tb[]);
+	const struct nft_expr_ops	*ops;
+	struct list_head		list;
+	const char			*name;
+	struct module			*owner;
+	const struct nla_policy		*policy;
+	unsigned int			maxattr;
+};
+
+/**
+ *	struct nft_expr_ops - nf_tables expression operations
+ *
+ *	@eval: Expression evaluation function
  *	@size: full expression size, including private data size
+ *	@init: initialization function
+ *	@destroy: destruction function
+ *	@dump: function to dump parameters
+ *	@type: expression type
  */
 struct nft_expr;
 struct nft_expr_ops {
 	void				(*eval)(const struct nft_expr *expr,
 						struct nft_data data[NFT_REG_MAX + 1],
 						const struct nft_pktinfo *pkt);
+	unsigned int			size;
+
 	int				(*init)(const struct nft_ctx *ctx,
 						const struct nft_expr *expr,
 						const struct nlattr * const tb[]);
@@ -248,14 +268,10 @@ struct nft_expr_ops {
 	int				(*dump)(struct sk_buff *skb,
 						const struct nft_expr *expr);
 	const struct nft_data *		(*get_verdict)(const struct nft_expr *expr);
-	struct list_head		list;
-	const char			*name;
-	struct module			*owner;
-	const struct nla_policy		*policy;
-	unsigned int			maxattr;
-	unsigned int			size;
+	const struct nft_expr_type	*type;
 };
 
+#define NFT_EXPR_MAXATTR		16
 #define NFT_EXPR_SIZE(size)		(sizeof(struct nft_expr) + \
 					 ALIGN(size, __alignof__(struct nft_expr)))
 
@@ -418,8 +434,8 @@ extern void nft_unregister_afinfo(struct nft_af_info *);
 extern int nft_register_table(struct nft_table *, int family);
 extern void nft_unregister_table(struct nft_table *, int family);
 
-extern int nft_register_expr(struct nft_expr_ops *);
-extern void nft_unregister_expr(struct nft_expr_ops *);
+extern int nft_register_expr(struct nft_expr_type *);
+extern void nft_unregister_expr(struct nft_expr_type *);
 
 #define MODULE_ALIAS_NFT_FAMILY(family)	\
 	MODULE_ALIAS("nft-afinfo-" __stringify(family))
diff --git a/net/ipv4/netfilter/nf_table_nat_ipv4.c b/net/ipv4/netfilter/nf_table_nat_ipv4.c
index 2a6f184c10bd..2ecce39077a3 100644
--- a/net/ipv4/netfilter/nf_table_nat_ipv4.c
+++ b/net/ipv4/netfilter/nf_table_nat_ipv4.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -149,15 +149,21 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_nat_ops __read_mostly = {
-	.name		= "nat",
+static struct nft_expr_type nft_nat_type;
+static const struct nft_expr_ops nft_nat_ops = {
+	.type		= &nft_nat_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_nat)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_nat_eval,
 	.init		= nft_nat_init,
 	.dump		= nft_nat_dump,
+};
+
+static struct nft_expr_type nft_nat_type __read_mostly = {
+	.name		= "nat",
+	.ops		= &nft_nat_ops,
 	.policy		= nft_nat_policy,
 	.maxattr	= NFTA_NAT_MAX,
+	.owner		= THIS_MODULE,
 };
 
 /*
@@ -382,7 +388,7 @@ static int __init nf_table_nat_init(void)
 	if (err < 0)
 		goto err1;
 
-	err = nft_register_expr(&nft_nat_ops);
+	err = nft_register_expr(&nft_nat_type);
 	if (err < 0)
 		goto err2;
 
@@ -396,7 +402,7 @@ err1:
 
 static void __exit nf_table_nat_exit(void)
 {
-	nft_unregister_expr(&nft_nat_ops);
+	nft_unregister_expr(&nft_nat_type);
 	nft_unregister_table(&nf_table_nat_ipv4, AF_INET);
 }
 
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index b4ee8d3bb1e4..fff5ba1a33b7 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -88,25 +88,31 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops reject_ops __read_mostly = {
-	.name		= "reject",
+static struct nft_expr_type nft_reject_type;
+static const struct nft_expr_ops nft_reject_ops = {
+	.type		= &nft_reject_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_reject_eval,
 	.init		= nft_reject_init,
 	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_type __read_mostly = {
+	.name		= "reject",
+	.ops		= &nft_reject_ops,
 	.policy		= nft_reject_policy,
 	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_reject_module_init(void)
 {
-	return nft_register_expr(&reject_ops);
+	return nft_register_expr(&nft_reject_type);
 }
 
 static void __exit nft_reject_module_exit(void)
 {
-	nft_unregister_expr(&reject_ops);
+	nft_unregister_expr(&nft_reject_type);
 }
 
 module_init(nft_reject_module_init);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5092c817c222..6dac9a3c9c40 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -840,64 +840,64 @@ static void nft_ctx_init(struct nft_ctx *ctx,
  */
 
 /**
- *	nft_register_expr - register nf_tables expr operations
- *	@ops: expr operations
+ *	nft_register_expr - register nf_tables expr type
+ *	@ops: expr type
  *
- *	Registers the expr operations for use with nf_tables. Returns zero on
+ *	Registers the expr type for use with nf_tables. Returns zero on
  *	success or a negative errno code otherwise.
  */
-int nft_register_expr(struct nft_expr_ops *ops)
+int nft_register_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&ops->list, &nf_tables_expressions);
+	list_add_tail(&type->list, &nf_tables_expressions);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_register_expr);
 
 /**
- *	nft_unregister_expr - unregister nf_tables expr operations
- *	@ops: expr operations
+ *	nft_unregister_expr - unregister nf_tables expr type
+ *	@ops: expr type
  *
- * 	Unregisters the expr operations for use with nf_tables.
+ * 	Unregisters the expr typefor use with nf_tables.
  */
-void nft_unregister_expr(struct nft_expr_ops *ops)
+void nft_unregister_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&ops->list);
+	list_del(&type->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_expr);
 
-static const struct nft_expr_ops *__nft_expr_ops_get(struct nlattr *nla)
+static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla)
 {
-	const struct nft_expr_ops *ops;
+	const struct nft_expr_type *type;
 
-	list_for_each_entry(ops, &nf_tables_expressions, list) {
-		if (!nla_strcmp(nla, ops->name))
-			return ops;
+	list_for_each_entry(type, &nf_tables_expressions, list) {
+		if (!nla_strcmp(nla, type->name))
+			return type;
 	}
 	return NULL;
 }
 
-static const struct nft_expr_ops *nft_expr_ops_get(struct nlattr *nla)
+static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla)
 {
-	const struct nft_expr_ops *ops;
+	const struct nft_expr_type *type;
 
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	ops = __nft_expr_ops_get(nla);
-	if (ops != NULL && try_module_get(ops->owner))
-		return ops;
+	type = __nft_expr_type_get(nla);
+	if (type != NULL && try_module_get(type->owner))
+		return type;
 
 #ifdef CONFIG_MODULES
-	if (ops == NULL) {
+	if (type == NULL) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		request_module("nft-expr-%.*s",
 			       nla_len(nla), (char *)nla_data(nla));
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		if (__nft_expr_ops_get(nla))
+		if (__nft_expr_type_get(nla))
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -912,7 +912,7 @@ static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = {
 static int nf_tables_fill_expr_info(struct sk_buff *skb,
 				    const struct nft_expr *expr)
 {
-	if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->name))
+	if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name))
 		goto nla_put_failure;
 
 	if (expr->ops->dump) {
@@ -932,28 +932,52 @@ nla_put_failure:
 
 struct nft_expr_info {
 	const struct nft_expr_ops	*ops;
-	struct nlattr			*tb[NFTA_EXPR_MAX + 1];
+	struct nlattr			*tb[NFT_EXPR_MAXATTR + 1];
 };
 
 static int nf_tables_expr_parse(const struct nlattr *nla,
 				struct nft_expr_info *info)
 {
+	const struct nft_expr_type *type;
 	const struct nft_expr_ops *ops;
+	struct nlattr *tb[NFTA_EXPR_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(info->tb, NFTA_EXPR_MAX, nla, nft_expr_policy);
+	err = nla_parse_nested(tb, NFTA_EXPR_MAX, nla, nft_expr_policy);
 	if (err < 0)
 		return err;
 
-	ops = nft_expr_ops_get(info->tb[NFTA_EXPR_NAME]);
-	if (IS_ERR(ops))
-		return PTR_ERR(ops);
+	type = nft_expr_type_get(tb[NFTA_EXPR_NAME]);
+	if (IS_ERR(type))
+		return PTR_ERR(type);
+
+	if (tb[NFTA_EXPR_DATA]) {
+		err = nla_parse_nested(info->tb, type->maxattr,
+				       tb[NFTA_EXPR_DATA], type->policy);
+		if (err < 0)
+			goto err1;
+	} else
+		memset(info->tb, 0, sizeof(info->tb[0]) * (type->maxattr + 1));
+
+	if (type->select_ops != NULL) {
+		ops = type->select_ops((const struct nlattr * const *)info->tb);
+		if (IS_ERR(ops)) {
+			err = PTR_ERR(ops);
+			goto err1;
+		}
+	} else
+		ops = type->ops;
+
 	info->ops = ops;
 	return 0;
+
+err1:
+	module_put(type->owner);
+	return err;
 }
 
 static int nf_tables_newexpr(const struct nft_ctx *ctx,
-			     struct nft_expr_info *info,
+			     const struct nft_expr_info *info,
 			     struct nft_expr *expr)
 {
 	const struct nft_expr_ops *ops = info->ops;
@@ -961,23 +985,11 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx,
 
 	expr->ops = ops;
 	if (ops->init) {
-		struct nlattr *ma[ops->maxattr + 1];
-
-		if (info->tb[NFTA_EXPR_DATA]) {
-			err = nla_parse_nested(ma, ops->maxattr,
-					       info->tb[NFTA_EXPR_DATA],
-					       ops->policy);
-			if (err < 0)
-				goto err1;
-		} else
-			memset(ma, 0, sizeof(ma[0]) * (ops->maxattr + 1));
-
-		err = ops->init(ctx, expr, (const struct nlattr **)ma);
+		err = ops->init(ctx, expr, (const struct nlattr **)info->tb);
 		if (err < 0)
 			goto err1;
 	}
 
-	info->ops = NULL;
 	return 0;
 
 err1:
@@ -989,7 +1001,7 @@ static void nf_tables_expr_destroy(struct nft_expr *expr)
 {
 	if (expr->ops->destroy)
 		expr->ops->destroy(expr);
-	module_put(expr->ops->owner);
+	module_put(expr->ops->type->owner);
 }
 
 /*
@@ -1313,6 +1325,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		err = nf_tables_newexpr(&ctx, &info[i], expr);
 		if (err < 0)
 			goto err2;
+		info[i].ops = NULL;
 		expr = nft_expr_next(expr);
 	}
 
@@ -1341,7 +1354,7 @@ err2:
 err1:
 	for (i = 0; i < n; i++) {
 		if (info[i].ops != NULL)
-			module_put(info[i].ops->owner);
+			module_put(info[i].ops->type->owner);
 	}
 	return err;
 }
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 0f7501506367..4fb6ee2c1106 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -118,23 +118,29 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_bitwise_ops __read_mostly = {
-	.name		= "bitwise",
+static struct nft_expr_type nft_bitwise_type;
+static const struct nft_expr_ops nft_bitwise_ops = {
+	.type		= &nft_bitwise_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_bitwise)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_bitwise_eval,
 	.init		= nft_bitwise_init,
 	.dump		= nft_bitwise_dump,
+};
+
+static struct nft_expr_type nft_bitwise_type __read_mostly = {
+	.name		= "bitwise",
+	.ops		= &nft_bitwise_ops,
 	.policy		= nft_bitwise_policy,
 	.maxattr	= NFTA_BITWISE_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_bitwise_module_init(void)
 {
-	return nft_register_expr(&nft_bitwise_ops);
+	return nft_register_expr(&nft_bitwise_type);
 }
 
 void nft_bitwise_module_exit(void)
 {
-	nft_unregister_expr(&nft_bitwise_ops);
+	nft_unregister_expr(&nft_bitwise_type);
 }
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 8b0657a4d17b..c39ed8d29df1 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -145,23 +145,29 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_byteorder_ops __read_mostly = {
-	.name		= "byteorder",
+static struct nft_expr_type nft_byteorder_type;
+static const struct nft_expr_ops nft_byteorder_ops = {
+	.type		= &nft_byteorder_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_byteorder_eval,
 	.init		= nft_byteorder_init,
 	.dump		= nft_byteorder_dump,
+};
+
+static struct nft_expr_type nft_byteorder_type __read_mostly = {
+	.name		= "byteorder",
+	.ops		= &nft_byteorder_ops,
 	.policy		= nft_byteorder_policy,
 	.maxattr	= NFTA_BYTEORDER_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_byteorder_module_init(void)
 {
-	return nft_register_expr(&nft_byteorder_ops);
+	return nft_register_expr(&nft_byteorder_type);
 }
 
 void nft_byteorder_module_exit(void)
 {
-	nft_unregister_expr(&nft_byteorder_ops);
+	nft_unregister_expr(&nft_byteorder_type);
 }
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index e734d670120a..2c9d5fef2e63 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -124,23 +124,29 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_cmp_ops __read_mostly = {
-	.name		= "cmp",
+static struct nft_expr_type nft_cmp_type;
+static const struct nft_expr_ops nft_cmp_ops = {
+	.type		= &nft_cmp_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_cmp_eval,
 	.init		= nft_cmp_init,
 	.dump		= nft_cmp_dump,
+};
+
+static struct nft_expr_type nft_cmp_type __read_mostly = {
+	.name		= "cmp",
+	.ops		= &nft_cmp_ops,
 	.policy		= nft_cmp_policy,
 	.maxattr	= NFTA_CMP_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_cmp_module_init(void)
 {
-	return nft_register_expr(&nft_cmp_ops);
+	return nft_register_expr(&nft_cmp_type);
 }
 
 void nft_cmp_module_exit(void)
 {
-	nft_unregister_expr(&nft_cmp_ops);
+	nft_unregister_expr(&nft_cmp_type);
 }
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 33c5d36819bb..c89ee486ce54 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -78,25 +78,31 @@ static int nft_counter_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
-static struct nft_expr_ops nft_counter_ops __read_mostly = {
-	.name		= "counter",
+static struct nft_expr_type nft_counter_type;
+static const struct nft_expr_ops nft_counter_ops = {
+	.type		= &nft_counter_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_counter)),
-	.policy		= nft_counter_policy,
-	.maxattr	= NFTA_COUNTER_MAX,
-	.owner		= THIS_MODULE,
 	.eval		= nft_counter_eval,
 	.init		= nft_counter_init,
 	.dump		= nft_counter_dump,
 };
 
+static struct nft_expr_type nft_counter_type __read_mostly = {
+	.name		= "counter",
+	.ops		= &nft_counter_ops,
+	.policy		= nft_counter_policy,
+	.maxattr	= NFTA_COUNTER_MAX,
+	.owner		= THIS_MODULE,
+};
+
 static int __init nft_counter_module_init(void)
 {
-	return nft_register_expr(&nft_counter_ops);
+	return nft_register_expr(&nft_counter_type);
 }
 
 static void __exit nft_counter_module_exit(void)
 {
-	nft_unregister_expr(&nft_counter_ops);
+	nft_unregister_expr(&nft_counter_type);
 }
 
 module_init(nft_counter_module_init);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index a1756d678226..955f4e6e7089 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -222,26 +222,32 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_ct_ops __read_mostly = {
-	.name		= "ct",
+static struct nft_expr_type nft_ct_type;
+static const struct nft_expr_ops nft_ct_ops = {
+	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_ct_eval,
 	.init		= nft_ct_init,
 	.destroy	= nft_ct_destroy,
 	.dump		= nft_ct_dump,
+};
+
+static struct nft_expr_type nft_ct_type __read_mostly = {
+	.name		= "ct",
+	.ops		= &nft_ct_ops,
 	.policy		= nft_ct_policy,
 	.maxattr	= NFTA_CT_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_ct_module_init(void)
 {
-	return nft_register_expr(&nft_ct_ops);
+	return nft_register_expr(&nft_ct_type);
 }
 
 static void __exit nft_ct_module_exit(void)
 {
-	nft_unregister_expr(&nft_ct_ops);
+	nft_unregister_expr(&nft_ct_type);
 }
 
 module_init(nft_ct_module_init);
diff --git a/net/netfilter/nft_expr_template.c b/net/netfilter/nft_expr_template.c
index 9fc8eb308193..b6eed4d5a096 100644
--- a/net/netfilter/nft_expr_template.c
+++ b/net/netfilter/nft_expr_template.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -33,7 +33,7 @@ static const struct nla_policy nft_template_policy[NFTA_TEMPLATE_MAX + 1] = {
 
 static int nft_template_init(const struct nft_ctx *ctx,
 			   const struct nft_expr *expr,
-			   const struct nlattr *tb[])
+			   const struct nlattr * const tb[])
 {
 	struct nft_template *priv = nft_expr_priv(expr);
 
@@ -58,26 +58,32 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops template_ops __read_mostly = {
-	.name		= "template",
+static struct nft_expr_type nft_template_type;
+static const struct nft_expr_ops nft_template_ops = {
+	.type		= &nft_template_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_template)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_template_eval,
 	.init		= nft_template_init,
 	.destroy	= nft_template_destroy,
 	.dump		= nft_template_dump,
+};
+
+static struct nft_expr_type nft_template_type __read_mostly = {
+	.name		= "template",
+	.ops		= &nft_template_ops,
 	.policy		= nft_template_policy,
 	.maxattr	= NFTA_TEMPLATE_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_template_module_init(void)
 {
-	return nft_register_expr(&template_ops);
+	return nft_register_expr(&nft_template_type);
 }
 
 static void __exit nft_template_module_exit(void)
 {
-	nft_unregister_expr(&template_ops);
+	nft_unregister_expr(&nft_template_type);
 }
 
 module_init(nft_template_module_init);
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 21c6a6b7b662..8e0bb75e7c51 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -98,25 +98,31 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops exthdr_ops __read_mostly = {
-	.name		= "exthdr",
+static struct nft_expr_type nft_exthdr_type;
+static const struct nft_expr_ops nft_exthdr_ops = {
+	.type		= &nft_exthdr_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_exthdr_eval,
 	.init		= nft_exthdr_init,
 	.dump		= nft_exthdr_dump,
+};
+
+static struct nft_expr_type nft_exthdr_type __read_mostly = {
+	.name		= "exthdr",
+	.ops		= &nft_exthdr_ops,
 	.policy		= nft_exthdr_policy,
 	.maxattr	= NFTA_EXTHDR_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_exthdr_module_init(void)
 {
-	return nft_register_expr(&exthdr_ops);
+	return nft_register_expr(&nft_exthdr_type);
 }
 
 static void __exit nft_exthdr_module_exit(void)
 {
-	nft_unregister_expr(&exthdr_ops);
+	nft_unregister_expr(&nft_exthdr_type);
 }
 
 module_init(nft_exthdr_module_init);
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 78334bf37007..1bfeeaf865b6 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -100,25 +100,31 @@ static const struct nft_data *nft_immediate_get_verdict(const struct nft_expr *e
 		return NULL;
 }
 
-static struct nft_expr_ops nft_imm_ops __read_mostly = {
-	.name		= "immediate",
+static struct nft_expr_type nft_imm_type;
+static const struct nft_expr_ops nft_imm_ops = {
+	.type		= &nft_imm_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_immediate_eval,
 	.init		= nft_immediate_init,
 	.destroy	= nft_immediate_destroy,
 	.dump		= nft_immediate_dump,
 	.get_verdict	= nft_immediate_get_verdict,
+};
+
+static struct nft_expr_type nft_imm_type __read_mostly = {
+	.name		= "immediate",
+	.ops		= &nft_imm_ops,
 	.policy		= nft_immediate_policy,
 	.maxattr	= NFTA_IMMEDIATE_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_immediate_module_init(void)
 {
-	return nft_register_expr(&nft_imm_ops);
+	return nft_register_expr(&nft_imm_type);
 }
 
 void nft_immediate_module_exit(void)
 {
-	nft_unregister_expr(&nft_imm_ops);
+	nft_unregister_expr(&nft_imm_type);
 }
diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c
index e0e3fc8aebc3..85da5bd02f64 100644
--- a/net/netfilter/nft_limit.c
+++ b/net/netfilter/nft_limit.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -84,25 +84,31 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_limit_ops __read_mostly = {
-	.name		= "limit",
+static struct nft_expr_type nft_limit_type;
+static const struct nft_expr_ops nft_limit_ops = {
+	.type		= &nft_limit_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_limit)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_limit_eval,
 	.init		= nft_limit_init,
 	.dump		= nft_limit_dump,
+};
+
+static struct nft_expr_type nft_limit_type __read_mostly = {
+	.name		= "limit",
+	.ops		= &nft_limit_ops,
 	.policy		= nft_limit_policy,
 	.maxattr	= NFTA_LIMIT_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_limit_module_init(void)
 {
-	return nft_register_expr(&nft_limit_ops);
+	return nft_register_expr(&nft_limit_type);
 }
 
 static void __exit nft_limit_module_exit(void)
 {
-	nft_unregister_expr(&nft_limit_ops);
+	nft_unregister_expr(&nft_limit_type);
 }
 
 module_init(nft_limit_module_init);
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index da495c3b1e7e..57cad072a13e 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -110,26 +110,32 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_log_ops __read_mostly = {
-	.name		= "log",
+static struct nft_expr_type nft_log_type;
+static const struct nft_expr_ops nft_log_ops = {
+	.type		= &nft_log_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_log)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_log_eval,
 	.init		= nft_log_init,
 	.destroy	= nft_log_destroy,
 	.dump		= nft_log_dump,
+};
+
+static struct nft_expr_type nft_log_type __read_mostly = {
+	.name		= "log",
+	.ops		= &nft_log_ops,
 	.policy		= nft_log_policy,
 	.maxattr	= NFTA_LOG_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_log_module_init(void)
 {
-	return nft_register_expr(&nft_log_ops);
+	return nft_register_expr(&nft_log_type);
 }
 
 static void __exit nft_log_module_exit(void)
 {
-	nft_unregister_expr(&nft_log_ops);
+	nft_unregister_expr(&nft_log_type);
 }
 
 module_init(nft_log_module_init);
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 4962d2173678..8a6116b75b5a 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -112,24 +112,30 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_lookup_ops __read_mostly = {
-	.name		= "lookup",
+static struct nft_expr_type nft_lookup_type;
+static const struct nft_expr_ops nft_lookup_ops = {
+	.type		= &nft_lookup_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_lookup_eval,
 	.init		= nft_lookup_init,
 	.destroy	= nft_lookup_destroy,
 	.dump		= nft_lookup_dump,
+};
+
+static struct nft_expr_type nft_lookup_type __read_mostly = {
+	.name		= "lookup",
+	.ops		= &nft_lookup_ops,
 	.policy		= nft_lookup_policy,
 	.maxattr	= NFTA_LOOKUP_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_lookup_module_init(void)
 {
-	return nft_register_expr(&nft_lookup_ops);
+	return nft_register_expr(&nft_lookup_type);
 }
 
 void nft_lookup_module_exit(void)
 {
-	nft_unregister_expr(&nft_lookup_ops);
+	nft_unregister_expr(&nft_lookup_type);
 }
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 96735aa2f039..8c28220a90b3 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -193,25 +193,31 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_meta_ops __read_mostly = {
-	.name		= "meta",
+static struct nft_expr_type nft_meta_type;
+static const struct nft_expr_ops nft_meta_ops = {
+	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_meta_eval,
 	.init		= nft_meta_init,
 	.dump		= nft_meta_dump,
+};
+
+static struct nft_expr_type nft_meta_type __read_mostly = {
+	.name		= "meta",
+	.ops		= &nft_meta_ops,
 	.policy		= nft_meta_policy,
 	.maxattr	= NFTA_META_MAX,
+	.owner		= THIS_MODULE,
 };
 
 static int __init nft_meta_module_init(void)
 {
-	return nft_register_expr(&nft_meta_ops);
+	return nft_register_expr(&nft_meta_type);
 }
 
 static void __exit nft_meta_module_exit(void)
 {
-	nft_unregister_expr(&nft_meta_ops);
+	nft_unregister_expr(&nft_meta_type);
 }
 
 module_init(nft_meta_module_init);
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 329f134b3f89..d99db6e37fb1 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -115,23 +115,29 @@ nla_put_failure:
 	return -1;
 }
 
-static struct nft_expr_ops nft_payload_ops __read_mostly = {
-	.name		= "payload",
+static struct nft_expr_type nft_payload_type;
+static const struct nft_expr_ops nft_payload_ops = {
+	.type		= &nft_payload_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_payload)),
-	.owner		= THIS_MODULE,
 	.eval		= nft_payload_eval,
 	.init		= nft_payload_init,
 	.dump		= nft_payload_dump,
+};
+
+static struct nft_expr_type nft_payload_type __read_mostly = {
+	.name		= "payload",
+	.ops		= &nft_payload_ops,
 	.policy		= nft_payload_policy,
 	.maxattr	= NFTA_PAYLOAD_MAX,
+	.owner		= THIS_MODULE,
 };
 
 int __init nft_payload_module_init(void)
 {
-	return nft_register_expr(&nft_payload_ops);
+	return nft_register_expr(&nft_payload_type);
 }
 
 void nft_payload_module_exit(void)
 {
-	nft_unregister_expr(&nft_payload_ops);
+	nft_unregister_expr(&nft_payload_type);
 }
-- 
cgit 


From cb7dbfd0390c9e244339f3270fe8649568241812 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 10 Oct 2013 23:35:40 +0200
Subject: netfilter: nf_tables: add optimized data comparison for small values

Add an optimized version of nft_data_cmp() that only handles values of to
4 bytes length.

This patch includes original Patrick McHardy's patch entitled (nf_tables:
inline nft_cmp_fast_eval() into main evaluation loop).

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_core.h |   8 +++
 net/netfilter/nf_tables_core.c         |  18 ++++-
 net/netfilter/nft_cmp.c                | 116 ++++++++++++++++++++++++++-------
 3 files changed, 118 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 283396c916e0..3df6a9be3bdd 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -7,6 +7,14 @@ extern void nf_tables_core_module_exit(void);
 extern int nft_immediate_module_init(void);
 extern void nft_immediate_module_exit(void);
 
+struct nft_cmp_fast_expr {
+	u32			data;
+	enum nft_registers	sreg:8;
+	u8			len;
+};
+
+extern const struct nft_expr_ops nft_cmp_fast_ops;
+
 extern int nft_cmp_module_init(void);
 extern void nft_cmp_module_exit(void);
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index fd0ecd3255c1..24000182c8e7 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -20,6 +20,18 @@
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
 
+static void nft_cmp_fast_eval(const struct nft_expr *expr,
+			      struct nft_data data[NFT_REG_MAX + 1])
+{
+	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	u32 mask;
+
+	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - priv->len);
+	if ((data[priv->sreg].data[0] & mask) == priv->data)
+		return;
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
 unsigned int nft_do_chain(const struct nf_hook_ops *ops,
 			  struct sk_buff *skb,
 			  const struct net_device *in,
@@ -48,7 +60,11 @@ next_rule:
 	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
 	list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
 		nft_rule_for_each_expr(expr, last, rule) {
-			expr->ops->eval(expr, data, &pkt);
+			if (expr->ops == &nft_cmp_fast_ops)
+				nft_cmp_fast_eval(expr, data);
+			else
+				expr->ops->eval(expr, data, &pkt);
+
 			if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
 				break;
 		}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 2c9d5fef2e63..37134f3e84fb 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -75,32 +75,11 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct nft_data_desc desc;
 	int err;
 
-	if (tb[NFTA_CMP_SREG] == NULL ||
-	    tb[NFTA_CMP_OP] == NULL ||
-	    tb[NFTA_CMP_DATA] == NULL)
-		return -EINVAL;
-
 	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
-	err = nft_validate_input_register(priv->sreg);
-	if (err < 0)
-		return err;
-
 	priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
-	switch (priv->op) {
-	case NFT_CMP_EQ:
-	case NFT_CMP_NEQ:
-	case NFT_CMP_LT:
-	case NFT_CMP_LTE:
-	case NFT_CMP_GT:
-	case NFT_CMP_GTE:
-		break;
-	default:
-		return -EINVAL;
-	}
 
 	err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
-	if (err < 0)
-		return err;
+	BUG_ON(err < 0);
 
 	priv->len = desc.len;
 	return 0;
@@ -133,9 +112,100 @@ static const struct nft_expr_ops nft_cmp_ops = {
 	.dump		= nft_cmp_dump,
 };
 
+static int nft_cmp_fast_init(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr,
+			     const struct nlattr * const tb[])
+{
+	struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data_desc desc;
+	struct nft_data data;
+	u32 mask;
+	int err;
+
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
+
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	BUG_ON(err < 0);
+	desc.len *= BITS_PER_BYTE;
+
+	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - desc.len);
+	priv->data = data.data[0] & mask;
+	priv->len  = desc.len;
+	return 0;
+}
+
+static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data data;
+
+	if (nla_put_be32(skb, NFTA_CMP_SREG, htonl(priv->sreg)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ)))
+		goto nla_put_failure;
+
+	data.data[0] = priv->data;
+	if (nft_data_dump(skb, NFTA_CMP_DATA, &data,
+			  NFT_DATA_VALUE, priv->len / BITS_PER_BYTE) < 0)
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+const struct nft_expr_ops nft_cmp_fast_ops = {
+	.type		= &nft_cmp_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_fast_expr)),
+	.eval		= NULL,	/* inlined */
+	.init		= nft_cmp_fast_init,
+	.dump		= nft_cmp_fast_dump,
+};
+
+static const struct nft_expr_ops *nft_cmp_select_ops(const struct nlattr * const tb[])
+{
+	struct nft_data_desc desc;
+	struct nft_data data;
+	enum nft_registers sreg;
+	enum nft_cmp_ops op;
+	int err;
+
+	if (tb[NFTA_CMP_SREG] == NULL ||
+	    tb[NFTA_CMP_OP] == NULL ||
+	    tb[NFTA_CMP_DATA] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
+	err = nft_validate_input_register(sreg);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
+	switch (op) {
+	case NFT_CMP_EQ:
+	case NFT_CMP_NEQ:
+	case NFT_CMP_LT:
+	case NFT_CMP_LTE:
+	case NFT_CMP_GT:
+	case NFT_CMP_GTE:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	if (desc.len <= sizeof(u32) && op == NFT_CMP_EQ)
+		return &nft_cmp_fast_ops;
+	else
+		return &nft_cmp_ops;
+}
+
 static struct nft_expr_type nft_cmp_type __read_mostly = {
 	.name		= "cmp",
-	.ops		= &nft_cmp_ops,
+	.select_ops	= nft_cmp_select_ops,
 	.policy		= nft_cmp_policy,
 	.maxattr	= NFTA_CMP_MAX,
 	.owner		= THIS_MODULE,
-- 
cgit 


From c29b72e02573b8fe5e6cae5d192a6a4772e7bbd6 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 10 Oct 2013 11:06:41 +0200
Subject: netfilter: nft_payload: add optimized payload implementation for
 small loads

Add an optimized payload expression implementation for small (up to 4 bytes)
aligned data loads from the linear packet area.

This patch also includes original Patrick McHardy's entitled (nf_tables:
inline nft_payload_fast_eval() into main evaluation loop).

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_core.h |  9 +++++
 net/netfilter/nf_tables_core.c         | 31 ++++++++++++++-
 net/netfilter/nft_payload.c            | 69 +++++++++++++++++++++-------------
 3 files changed, 81 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 3df6a9be3bdd..fe7b16206a4e 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -27,6 +27,15 @@ extern void nft_bitwise_module_exit(void);
 extern int nft_byteorder_module_init(void);
 extern void nft_byteorder_module_exit(void);
 
+struct nft_payload {
+	enum nft_payload_bases	base:8;
+	u8			offset;
+	u8			len;
+	enum nft_registers	dreg:8;
+};
+
+extern const struct nft_expr_ops nft_payload_fast_ops;
+
 extern int nft_payload_module_init(void);
 extern void nft_payload_module_exit(void);
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 24000182c8e7..9aede59ed2d7 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -32,6 +32,34 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
 
+static bool nft_payload_fast_eval(const struct nft_expr *expr,
+				  struct nft_data data[NFT_REG_MAX + 1],
+				  const struct nft_pktinfo *pkt)
+{
+	const struct nft_payload *priv = nft_expr_priv(expr);
+	const struct sk_buff *skb = pkt->skb;
+	struct nft_data *dest = &data[priv->dreg];
+	unsigned char *ptr;
+
+	if (priv->base == NFT_PAYLOAD_NETWORK_HEADER)
+		ptr = skb_network_header(skb);
+	else
+		ptr = skb_transport_header(skb);
+
+	ptr += priv->offset;
+
+	if (unlikely(ptr + priv->len >= skb_tail_pointer(skb)))
+		return false;
+
+	if (priv->len == 2)
+		*(u16 *)dest->data = *(u16 *)ptr;
+	else if (priv->len == 4)
+		*(u32 *)dest->data = *(u32 *)ptr;
+	else
+		*(u8 *)dest->data = *(u8 *)ptr;
+	return true;
+}
+
 unsigned int nft_do_chain(const struct nf_hook_ops *ops,
 			  struct sk_buff *skb,
 			  const struct net_device *in,
@@ -62,7 +90,8 @@ next_rule:
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, data);
-			else
+			else if (expr->ops != &nft_payload_fast_ops ||
+				 !nft_payload_fast_eval(expr, data, &pkt))
 				expr->ops->eval(expr, data, &pkt);
 
 			if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index d99db6e37fb1..7cf13f7e1e94 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -17,13 +17,6 @@
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
 
-struct nft_payload {
-	enum nft_payload_bases	base:8;
-	u8			offset;
-	u8			len;
-	enum nft_registers	dreg:8;
-};
-
 static void nft_payload_eval(const struct nft_expr *expr,
 			     struct nft_data data[NFT_REG_MAX + 1],
 			     const struct nft_pktinfo *pkt)
@@ -71,27 +64,9 @@ static int nft_payload_init(const struct nft_ctx *ctx,
 	struct nft_payload *priv = nft_expr_priv(expr);
 	int err;
 
-	if (tb[NFTA_PAYLOAD_DREG] == NULL ||
-	    tb[NFTA_PAYLOAD_BASE] == NULL ||
-	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||
-	    tb[NFTA_PAYLOAD_LEN] == NULL)
-		return -EINVAL;
-
-	priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
-	switch (priv->base) {
-	case NFT_PAYLOAD_LL_HEADER:
-	case NFT_PAYLOAD_NETWORK_HEADER:
-	case NFT_PAYLOAD_TRANSPORT_HEADER:
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
+	priv->base   = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
 	priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
 	priv->len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
-	if (priv->len == 0 ||
-	    priv->len > FIELD_SIZEOF(struct nft_data, data))
-		return -EINVAL;
 
 	priv->dreg = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_DREG]));
 	err = nft_validate_output_register(priv->dreg);
@@ -124,9 +99,49 @@ static const struct nft_expr_ops nft_payload_ops = {
 	.dump		= nft_payload_dump,
 };
 
+const struct nft_expr_ops nft_payload_fast_ops = {
+	.type		= &nft_payload_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_payload)),
+	.eval		= nft_payload_eval,
+	.init		= nft_payload_init,
+	.dump		= nft_payload_dump,
+};
+
+static const struct nft_expr_ops *nft_payload_select_ops(const struct nlattr * const tb[])
+{
+	enum nft_payload_bases base;
+	unsigned int offset, len;
+
+	if (tb[NFTA_PAYLOAD_DREG] == NULL ||
+	    tb[NFTA_PAYLOAD_BASE] == NULL ||
+	    tb[NFTA_PAYLOAD_OFFSET] == NULL ||
+	    tb[NFTA_PAYLOAD_LEN] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
+	switch (base) {
+	case NFT_PAYLOAD_LL_HEADER:
+	case NFT_PAYLOAD_NETWORK_HEADER:
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		break;
+	default:
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
+	len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
+	if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data))
+		return ERR_PTR(-EINVAL);
+
+	if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER)
+		return &nft_payload_fast_ops;
+	else
+		return &nft_payload_ops;
+}
+
 static struct nft_expr_type nft_payload_type __read_mostly = {
 	.name		= "payload",
-	.ops		= &nft_payload_ops,
+	.select_ops	= nft_payload_select_ops,
 	.policy		= nft_payload_policy,
 	.maxattr	= NFTA_PAYLOAD_MAX,
 	.owner		= THIS_MODULE,
-- 
cgit 


From 9370761c56b66aa5c65e069a7b010111a025018d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 10 Oct 2013 23:21:26 +0200
Subject: netfilter: nf_tables: convert built-in tables/chains to chain types

This patch converts built-in tables/chains to chain types that
allows you to deploy customized table and chain configurations from
userspace.

After this patch, you have to specify the chain type when
creating a new chain:

 add chain ip filter output { type filter hook input priority 0; }
                              ^^^^ ------

The existing chain types after this patch are: filter, route and
nat. Note that tables are just containers of chains with no specific
semantics, which is a significant change with regards to iptables.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h         |  31 ++-
 include/uapi/linux/netfilter/nf_tables.h  |   2 +
 net/ipv4/netfilter/Kconfig                |   8 +-
 net/ipv4/netfilter/Makefile               |   4 +-
 net/ipv4/netfilter/nf_table_nat_ipv4.c    | 415 ------------------------------
 net/ipv4/netfilter/nf_table_route_ipv4.c  |  97 -------
 net/ipv4/netfilter/nf_tables_ipv4.c       |  21 ++
 net/ipv4/netfilter/nft_chain_nat_ipv4.c   | 353 +++++++++++++++++++++++++
 net/ipv4/netfilter/nft_chain_route_ipv4.c |  86 +++++++
 net/ipv6/netfilter/Kconfig                |   4 +-
 net/ipv6/netfilter/Makefile               |   2 +-
 net/ipv6/netfilter/nf_table_route_ipv6.c  |  93 -------
 net/ipv6/netfilter/nf_tables_ipv6.c       |  22 +-
 net/ipv6/netfilter/nft_chain_route_ipv6.c |  82 ++++++
 net/netfilter/nf_tables_api.c             | 197 +++++++-------
 15 files changed, 682 insertions(+), 735 deletions(-)
 delete mode 100644 net/ipv4/netfilter/nf_table_nat_ipv4.c
 delete mode 100644 net/ipv4/netfilter/nf_table_route_ipv4.c
 create mode 100644 net/ipv4/netfilter/nft_chain_nat_ipv4.c
 create mode 100644 net/ipv4/netfilter/nft_chain_route_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nf_table_route_ipv6.c
 create mode 100644 net/ipv6/netfilter/nft_chain_route_ipv6.c

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 66d0359702c6..8403f7f52e81 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -336,7 +336,6 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule)
 
 enum nft_chain_flags {
 	NFT_BASE_CHAIN			= 0x1,
-	NFT_CHAIN_BUILTIN		= 0x2,
 };
 
 /**
@@ -362,14 +361,23 @@ struct nft_chain {
 	char				name[NFT_CHAIN_MAXNAMELEN];
 };
 
+enum nft_chain_type {
+	NFT_CHAIN_T_DEFAULT = 0,
+	NFT_CHAIN_T_ROUTE,
+	NFT_CHAIN_T_NAT,
+	NFT_CHAIN_T_MAX
+};
+
 /**
  *	struct nft_base_chain - nf_tables base chain
  *
  *	@ops: netfilter hook ops
+ *	@type: chain type
  *	@chain: the chain
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
+	enum nft_chain_type		type;
 	struct nft_chain		chain;
 };
 
@@ -384,10 +392,6 @@ extern unsigned int nft_do_chain(const struct nf_hook_ops *ops,
 				 const struct net_device *out,
 				 int (*okfn)(struct sk_buff *));
 
-enum nft_table_flags {
-	NFT_TABLE_BUILTIN		= 0x1,
-};
-
 /**
  *	struct nft_table - nf_tables table
  *
@@ -431,8 +435,17 @@ struct nft_af_info {
 extern int nft_register_afinfo(struct nft_af_info *);
 extern void nft_unregister_afinfo(struct nft_af_info *);
 
-extern int nft_register_table(struct nft_table *, int family);
-extern void nft_unregister_table(struct nft_table *, int family);
+struct nf_chain_type {
+	unsigned int		hook_mask;
+	const char		*name;
+	enum nft_chain_type	type;
+	nf_hookfn		*fn[NF_MAX_HOOKS];
+	struct module		*me;
+	int			family;
+};
+
+extern int nft_register_chain_type(struct nf_chain_type *);
+extern void nft_unregister_chain_type(struct nf_chain_type *);
 
 extern int nft_register_expr(struct nft_expr_type *);
 extern void nft_unregister_expr(struct nft_expr_type *);
@@ -440,8 +453,8 @@ extern void nft_unregister_expr(struct nft_expr_type *);
 #define MODULE_ALIAS_NFT_FAMILY(family)	\
 	MODULE_ALIAS("nft-afinfo-" __stringify(family))
 
-#define MODULE_ALIAS_NFT_TABLE(family, name) \
-	MODULE_ALIAS("nft-table-" __stringify(family) "-" name)
+#define MODULE_ALIAS_NFT_CHAIN(family, name) \
+	MODULE_ALIAS("nft-chain-" __stringify(family) "-" name)
 
 #define MODULE_ALIAS_NFT_EXPR(name) \
 	MODULE_ALIAS("nft-expr-" name)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 9e924014efe3..779cf951c8de 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -115,6 +115,7 @@ enum nft_table_attributes {
  * @NFTA_CHAIN_HANDLE: numeric handle of the chain (NLA_U64)
  * @NFTA_CHAIN_NAME: name of the chain (NLA_STRING)
  * @NFTA_CHAIN_HOOK: hook specification for basechains (NLA_NESTED: nft_hook_attributes)
+ * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING)
  */
 enum nft_chain_attributes {
 	NFTA_CHAIN_UNSPEC,
@@ -122,6 +123,7 @@ enum nft_chain_attributes {
 	NFTA_CHAIN_HANDLE,
 	NFTA_CHAIN_NAME,
 	NFTA_CHAIN_HOOK,
+	NFTA_CHAIN_TYPE,
 	__NFTA_CHAIN_MAX
 };
 #define NFTA_CHAIN_MAX		(__NFTA_CHAIN_MAX - 1)
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index eb1d56ece361..ae65fe98bfbe 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -44,13 +44,13 @@ config NFT_REJECT_IPV4
 	depends on NF_TABLES_IPV4
 	tristate "nf_tables IPv4 reject support"
 
-config NF_TABLE_ROUTE_IPV4
+config NFT_CHAIN_ROUTE_IPV4
 	depends on NF_TABLES_IPV4
-	tristate "IPv4 nf_tables route table support"
+	tristate "IPv4 nf_tables route chain support"
 
-config NF_TABLE_NAT_IPV4
+config NFT_CHAIN_NAT_IPV4
 	depends on NF_TABLES_IPV4
-	tristate "IPv4 nf_tables nat table support"
+	tristate "IPv4 nf_tables nat chain support"
 
 config IP_NF_IPTABLES
 	tristate "IP tables support (required for filtering/masq/NAT)"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index b2f01cd2cd65..91e0bd71a6d3 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -29,8 +29,8 @@ obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
 
 obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
-obj-$(CONFIG_NF_TABLE_ROUTE_IPV4) += nf_table_route_ipv4.o
-obj-$(CONFIG_NF_TABLE_NAT_IPV4) += nf_table_nat_ipv4.o
+obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
+obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
diff --git a/net/ipv4/netfilter/nf_table_nat_ipv4.c b/net/ipv4/netfilter/nf_table_nat_ipv4.c
deleted file mode 100644
index 2ecce39077a3..000000000000
--- a/net/ipv4/netfilter/nf_table_nat_ipv4.c
+++ /dev/null
@@ -1,415 +0,0 @@
-/*
- * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_nat_core.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_nat_l3proto.h>
-#include <net/ip.h>
-
-struct nft_nat {
-	enum nft_registers	sreg_addr_min:8;
-	enum nft_registers	sreg_addr_max:8;
-	enum nft_registers	sreg_proto_min:8;
-	enum nft_registers	sreg_proto_max:8;
-	enum nf_nat_manip_type	type;
-};
-
-static void nft_nat_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
-			 const struct nft_pktinfo *pkt)
-{
-	const struct nft_nat *priv = nft_expr_priv(expr);
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
-	struct nf_nat_range range;
-
-	memset(&range, 0, sizeof(range));
-	if (priv->sreg_addr_min) {
-		range.min_addr.ip = data[priv->sreg_addr_min].data[0];
-		range.max_addr.ip = data[priv->sreg_addr_max].data[0];
-		range.flags |= NF_NAT_RANGE_MAP_IPS;
-	}
-
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = data[priv->sreg_proto_max].data[0];
-		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-
-	data[NFT_REG_VERDICT].verdict =
-		nf_nat_setup_info(ct, &range, priv->type);
-}
-
-static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
-	[NFTA_NAT_ADDR_MIN]	= { .type = NLA_U32 },
-	[NFTA_NAT_ADDR_MAX]	= { .type = NLA_U32 },
-	[NFTA_NAT_PROTO_MIN]	= { .type = NLA_U32 },
-	[NFTA_NAT_PROTO_MAX]	= { .type = NLA_U32 },
-	[NFTA_NAT_TYPE]		= { .type = NLA_U32 },
-};
-
-static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			const struct nlattr * const tb[])
-{
-	struct nft_nat *priv = nft_expr_priv(expr);
-	int err;
-
-	if (tb[NFTA_NAT_TYPE] == NULL)
-		return -EINVAL;
-
-	switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
-	case NFT_NAT_SNAT:
-		priv->type = NF_NAT_MANIP_SRC;
-		break;
-	case NFT_NAT_DNAT:
-		priv->type = NF_NAT_MANIP_DST;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (tb[NFTA_NAT_ADDR_MIN]) {
-		priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN]));
-		err = nft_validate_input_register(priv->sreg_addr_min);
-		if (err < 0)
-			return err;
-	}
-
-	if (tb[NFTA_NAT_ADDR_MAX]) {
-		priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX]));
-		err = nft_validate_input_register(priv->sreg_addr_max);
-		if (err < 0)
-			return err;
-	} else
-		priv->sreg_addr_max = priv->sreg_addr_min;
-
-	if (tb[NFTA_NAT_PROTO_MIN]) {
-		priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN]));
-		err = nft_validate_input_register(priv->sreg_proto_min);
-		if (err < 0)
-			return err;
-	}
-
-	if (tb[NFTA_NAT_PROTO_MAX]) {
-		priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX]));
-		err = nft_validate_input_register(priv->sreg_proto_max);
-		if (err < 0)
-			return err;
-	} else
-		priv->sreg_proto_max = priv->sreg_proto_min;
-
-	return 0;
-}
-
-static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	const struct nft_nat *priv = nft_expr_priv(expr);
-
-	switch (priv->type) {
-	case NF_NAT_MANIP_SRC:
-		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
-			goto nla_put_failure;
-		break;
-	case NF_NAT_MANIP_DST:
-		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
-			goto nla_put_failure;
-		break;
-	}
-
-	if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max)))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_type nft_nat_type;
-static const struct nft_expr_ops nft_nat_ops = {
-	.type		= &nft_nat_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_nat)),
-	.eval		= nft_nat_eval,
-	.init		= nft_nat_init,
-	.dump		= nft_nat_dump,
-};
-
-static struct nft_expr_type nft_nat_type __read_mostly = {
-	.name		= "nat",
-	.ops		= &nft_nat_ops,
-	.policy		= nft_nat_policy,
-	.maxattr	= NFTA_NAT_MAX,
-	.owner		= THIS_MODULE,
-};
-
-/*
- * NAT table
- */
-
-static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
-			      struct sk_buff *skb,
-			      const struct net_device *in,
-			      const struct net_device *out,
-			      int (*okfn)(struct sk_buff *))
-{
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
-	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-	unsigned int ret;
-
-	if (ct == NULL || nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
-
-	nat = nfct_nat(ct);
-	if (nat == NULL) {
-		/* Conntrack module was loaded late, can't add extension. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL)
-			return NF_ACCEPT;
-	}
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED + IP_CT_IS_REPLY:
-		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall through */
-	case IP_CT_NEW:
-		if (nf_nat_initialized(ct, maniptype))
-			break;
-
-		ret = nft_do_chain(ops, skb, in, out, okfn);
-		if (ret != NF_ACCEPT)
-			return ret;
-		if (!nf_nat_initialized(ct, maniptype)) {
-			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-	default:
-		break;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-}
-
-static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops,
-				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
-				      int (*okfn)(struct sk_buff *))
-{
-	__be32 daddr = ip_hdr(skb)->daddr;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ip_hdr(skb)->daddr != daddr) {
-		skb_dst_drop(skb);
-	}
-	return ret;
-}
-
-static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops,
-				       struct sk_buff *skb,
-				       const struct net_device *in,
-				       const struct net_device *out,
-				       int (*okfn)(struct sk_buff *))
-{
-	enum ip_conntrack_info ctinfo __maybe_unused;
-	const struct nf_conn *ct __maybe_unused;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.src.u3.ip !=
-		    ct->tuplehash[!dir].tuple.dst.u3.ip ||
-		    ct->tuplehash[dir].tuple.src.u.all !=
-		    ct->tuplehash[!dir].tuple.dst.u.all)
-			return nf_xfrm_me_harder(skb, AF_INET) == 0 ?
-								ret : NF_DROP;
-	}
-#endif
-	return ret;
-}
-
-static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
-				  struct sk_buff *skb,
-				  const struct net_device *in,
-				  const struct net_device *out,
-				  int (*okfn)(struct sk_buff *))
-{
-	enum ip_conntrack_info ctinfo;
-	const struct nf_conn *ct;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
-		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			if (ip_route_me_harder(skb, RTN_UNSPEC))
-				ret = NF_DROP;
-		}
-#ifdef CONFIG_XFRM
-		else if (ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all)
-			if (nf_xfrm_me_harder(skb, AF_INET))
-				ret = NF_DROP;
-#endif
-	}
-	return ret;
-}
-
-static struct nft_base_chain nf_chain_nat_prerouting __read_mostly = {
-	.chain	= {
-		.name		= "PREROUTING",
-		.rules		= LIST_HEAD_INIT(nf_chain_nat_prerouting.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_nat_prerouting,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP_PRI_NAT_DST,
-		.priv		= &nf_chain_nat_prerouting.chain,
-	},
-};
-
-static struct nft_base_chain nf_chain_nat_postrouting __read_mostly = {
-	.chain	= {
-		.name		= "POSTROUTING",
-		.rules		= LIST_HEAD_INIT(nf_chain_nat_postrouting.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_nat_postrouting,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP_PRI_NAT_SRC,
-		.priv		= &nf_chain_nat_postrouting.chain,
-	},
-};
-
-static struct nft_base_chain nf_chain_nat_output __read_mostly = {
-	.chain	= {
-		.name		= "OUTPUT",
-		.rules		= LIST_HEAD_INIT(nf_chain_nat_output.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_nat_output,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP_PRI_NAT_DST,
-		.priv		= &nf_chain_nat_output.chain,
-	},
-};
-
-static struct nft_base_chain nf_chain_nat_input __read_mostly = {
-	.chain	= {
-		.name		= "INPUT",
-		.rules		= LIST_HEAD_INIT(nf_chain_nat_input.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_nat_fn,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP_PRI_NAT_SRC,
-		.priv		= &nf_chain_nat_input.chain,
-	},
-};
-
-
-static struct nft_table nf_table_nat_ipv4 __read_mostly = {
-	.name	= "nat",
-	.chains	= LIST_HEAD_INIT(nf_table_nat_ipv4.chains),
-};
-
-static int __init nf_table_nat_init(void)
-{
-	int err;
-
-	list_add_tail(&nf_chain_nat_prerouting.chain.list,
-		      &nf_table_nat_ipv4.chains);
-	list_add_tail(&nf_chain_nat_postrouting.chain.list,
-		      &nf_table_nat_ipv4.chains);
-	list_add_tail(&nf_chain_nat_output.chain.list,
-		      &nf_table_nat_ipv4.chains);
-	list_add_tail(&nf_chain_nat_input.chain.list,
-		      &nf_table_nat_ipv4.chains);
-
-	err = nft_register_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
-	if (err < 0)
-		goto err1;
-
-	err = nft_register_expr(&nft_nat_type);
-	if (err < 0)
-		goto err2;
-
-	return 0;
-
-err2:
-	nft_unregister_table(&nf_table_nat_ipv4, NFPROTO_IPV4);
-err1:
-	return err;
-}
-
-static void __exit nf_table_nat_exit(void)
-{
-	nft_unregister_expr(&nft_nat_type);
-	nft_unregister_table(&nf_table_nat_ipv4, AF_INET);
-}
-
-module_init(nf_table_nat_init);
-module_exit(nf_table_nat_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_TABLE(AF_INET, "nat");
-MODULE_ALIAS_NFT_EXPR("nat");
diff --git a/net/ipv4/netfilter/nf_table_route_ipv4.c b/net/ipv4/netfilter/nf_table_route_ipv4.c
deleted file mode 100644
index 4f257a1ed661..000000000000
--- a/net/ipv4/netfilter/nf_table_route_ipv4.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/route.h>
-#include <net/ip.h>
-
-static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
-					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
-					int (*okfn)(struct sk_buff *))
-{
-	unsigned int ret;
-	u32 mark;
-	__be32 saddr, daddr;
-	u_int8_t tos;
-	const struct iphdr *iph;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	mark = skb->mark;
-	iph = ip_hdr(skb);
-	saddr = iph->saddr;
-	daddr = iph->daddr;
-	tos = iph->tos;
-
-	ret = nft_do_chain(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_QUEUE) {
-		iph = ip_hdr(skb);
-
-		if (iph->saddr != saddr ||
-		    iph->daddr != daddr ||
-		    skb->mark != mark ||
-		    iph->tos != tos)
-			if (ip_route_me_harder(skb, RTN_UNSPEC))
-				ret = NF_DROP;
-	}
-	return ret;
-}
-
-static struct nft_base_chain nf_chain_route_output __read_mostly = {
-	.chain	= {
-		.name		= "OUTPUT",
-		.rules		= LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_route_table_hook,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP_PRI_MANGLE,
-		.priv		= &nf_chain_route_output.chain,
-	},
-};
-
-static struct nft_table nf_table_route_ipv4 __read_mostly = {
-	.name	= "route",
-	.chains	= LIST_HEAD_INIT(nf_table_route_ipv4.chains),
-};
-
-static int __init nf_table_route_init(void)
-{
-	list_add_tail(&nf_chain_route_output.chain.list,
-		      &nf_table_route_ipv4.chains);
-	return nft_register_table(&nf_table_route_ipv4, NFPROTO_IPV4);
-}
-
-static void __exit nf_table_route_exit(void)
-{
-	nft_unregister_table(&nf_table_route_ipv4, NFPROTO_IPV4);
-}
-
-module_init(nf_table_route_init);
-module_exit(nf_table_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_TABLE(AF_INET, "route");
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 63d0a3bf53d3..23525c4c0192 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -41,14 +42,34 @@ static struct nft_af_info nft_af_ipv4 __read_mostly = {
 	},
 };
 
+static struct nf_chain_type filter_ipv4 = {
+	.family		= NFPROTO_IPV4,
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+	.fn		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain,
+		[NF_INET_LOCAL_OUT]	= nft_do_chain,
+		[NF_INET_FORWARD]	= nft_do_chain,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain,
+		[NF_INET_POST_ROUTING]	= nft_do_chain,
+	},
+};
+
 static int __init nf_tables_ipv4_init(void)
 {
+	nft_register_chain_type(&filter_ipv4);
 	return nft_register_afinfo(&nft_af_ipv4);
 }
 
 static void __exit nf_tables_ipv4_exit(void)
 {
 	nft_unregister_afinfo(&nft_af_ipv4);
+	nft_unregister_chain_type(&filter_ipv4);
 }
 
 module_init(nf_tables_ipv4_init);
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
new file mode 100644
index 000000000000..cd286306be85
--- /dev/null
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/ip.h>
+
+struct nft_nat {
+	enum nft_registers	sreg_addr_min:8;
+	enum nft_registers	sreg_addr_max:8;
+	enum nft_registers	sreg_proto_min:8;
+	enum nft_registers	sreg_proto_max:8;
+	enum nf_nat_manip_type	type;
+};
+
+static void nft_nat_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
+	struct nf_nat_range range;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_addr_min) {
+		range.min_addr.ip = data[priv->sreg_addr_min].data[0];
+		range.max_addr.ip = data[priv->sreg_addr_max].data[0];
+		range.flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = data[priv->sreg_proto_min].data[0];
+		range.max_proto.all = data[priv->sreg_proto_max].data[0];
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	data[NFT_REG_VERDICT].verdict =
+		nf_nat_setup_info(ct, &range, priv->type);
+}
+
+static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
+	[NFTA_NAT_ADDR_MIN]	= { .type = NLA_U32 },
+	[NFTA_NAT_ADDR_MAX]	= { .type = NLA_U32 },
+	[NFTA_NAT_PROTO_MIN]	= { .type = NLA_U32 },
+	[NFTA_NAT_PROTO_MAX]	= { .type = NLA_U32 },
+	[NFTA_NAT_TYPE]		= { .type = NLA_U32 },
+};
+
+static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_NAT_TYPE] == NULL)
+		return -EINVAL;
+
+	switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
+	case NFT_NAT_SNAT:
+		priv->type = NF_NAT_MANIP_SRC;
+		break;
+	case NFT_NAT_DNAT:
+		priv->type = NF_NAT_MANIP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (tb[NFTA_NAT_ADDR_MIN]) {
+		priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN]));
+		err = nft_validate_input_register(priv->sreg_addr_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_ADDR_MAX]) {
+		priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX]));
+		err = nft_validate_input_register(priv->sreg_addr_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_addr_max = priv->sreg_addr_min;
+
+	if (tb[NFTA_NAT_PROTO_MIN]) {
+		priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN]));
+		err = nft_validate_input_register(priv->sreg_proto_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_PROTO_MAX]) {
+		priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX]));
+		err = nft_validate_input_register(priv->sreg_proto_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_proto_max = priv->sreg_proto_min;
+
+	return 0;
+}
+
+static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NF_NAT_MANIP_SRC:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
+			goto nla_put_failure;
+		break;
+	case NF_NAT_MANIP_DST:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
+			goto nla_put_failure;
+		break;
+	}
+
+	if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_nat_type;
+static const struct nft_expr_ops nft_nat_ops = {
+	.type		= &nft_nat_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+	.eval		= nft_nat_eval,
+	.init		= nft_nat_init,
+	.dump		= nft_nat_dump,
+};
+
+static struct nft_expr_type nft_nat_type __read_mostly = {
+	.name		= "nat",
+	.ops		= &nft_nat_ops,
+	.policy		= nft_nat_policy,
+	.maxattr	= NFTA_NAT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * NAT chains
+ */
+
+static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
+			      struct sk_buff *skb,
+			      const struct net_device *in,
+			      const struct net_device *out,
+			      int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	unsigned int ret;
+
+	if (ct == NULL || nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
+
+	nat = nfct_nat(ct);
+	if (nat == NULL) {
+		/* Conntrack module was loaded late, can't add extension. */
+		if (nf_ct_is_confirmed(ct))
+			return NF_ACCEPT;
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+		if (nat == NULL)
+			return NF_ACCEPT;
+	}
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED + IP_CT_IS_REPLY:
+		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   ops->hooknum))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall through */
+	case IP_CT_NEW:
+		if (nf_nat_initialized(ct, maniptype))
+			break;
+
+		ret = nft_do_chain(ops, skb, in, out, okfn);
+		if (ret != NF_ACCEPT)
+			return ret;
+		if (!nf_nat_initialized(ct, maniptype)) {
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		}
+	default:
+		break;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+}
+
+static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	__be32 daddr = ip_hdr(skb)->daddr;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ip_hdr(skb)->daddr != daddr) {
+		skb_dst_drop(skb);
+	}
+	return ret;
+}
+
+static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops,
+				       struct sk_buff *skb,
+				       const struct net_device *in,
+				       const struct net_device *out,
+				       int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo __maybe_unused;
+	const struct nf_conn *ct __maybe_unused;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.src.u3.ip !=
+		    ct->tuplehash[!dir].tuple.dst.u3.ip ||
+		    ct->tuplehash[dir].tuple.src.u.all !=
+		    ct->tuplehash[!dir].tuple.dst.u.all)
+			return nf_xfrm_me_harder(skb, AF_INET) == 0 ?
+								ret : NF_DROP;
+	}
+#endif
+	return ret;
+}
+
+static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	const struct nf_conn *ct;
+	unsigned int ret;
+
+	ret = nf_nat_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+		    ct->tuplehash[!dir].tuple.src.u3.ip) {
+			if (ip_route_me_harder(skb, RTN_UNSPEC))
+				ret = NF_DROP;
+		}
+#ifdef CONFIG_XFRM
+		else if (ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all)
+			if (nf_xfrm_me_harder(skb, AF_INET))
+				ret = NF_DROP;
+#endif
+	}
+	return ret;
+}
+
+struct nf_chain_type nft_chain_nat_ipv4 = {
+	.family		= NFPROTO_IPV4,
+	.name		= "nat",
+	.type		= NFT_CHAIN_T_NAT,
+	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.fn		= {
+		[NF_INET_PRE_ROUTING]	= nf_nat_prerouting,
+		[NF_INET_POST_ROUTING]	= nf_nat_postrouting,
+		[NF_INET_LOCAL_OUT]	= nf_nat_output,
+		[NF_INET_LOCAL_IN]	= nf_nat_fn,
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init nft_chain_nat_init(void)
+{
+	int err;
+
+	err = nft_register_chain_type(&nft_chain_nat_ipv4);
+	if (err < 0)
+		return err;
+
+	err = nft_register_expr(&nft_nat_type);
+	if (err < 0)
+		goto err;
+
+	return 0;
+
+err:
+	nft_unregister_chain_type(&nft_chain_nat_ipv4);
+	return err;
+}
+
+static void __exit nft_chain_nat_exit(void)
+{
+	nft_unregister_expr(&nft_nat_type);
+	nft_unregister_chain_type(&nft_chain_nat_ipv4);
+}
+
+module_init(nft_chain_nat_init);
+module_exit(nft_chain_nat_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
+MODULE_ALIAS_NFT_EXPR("nat");
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
new file mode 100644
index 000000000000..6b84e097b8fc
--- /dev/null
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	u32 mark;
+	__be32 saddr, daddr;
+	u_int8_t tos;
+	const struct iphdr *iph;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	mark = skb->mark;
+	iph = ip_hdr(skb);
+	saddr = iph->saddr;
+	daddr = iph->daddr;
+	tos = iph->tos;
+
+	ret = nft_do_chain(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_QUEUE) {
+		iph = ip_hdr(skb);
+
+		if (iph->saddr != saddr ||
+		    iph->daddr != daddr ||
+		    skb->mark != mark ||
+		    iph->tos != tos)
+			if (ip_route_me_harder(skb, RTN_UNSPEC))
+				ret = NF_DROP;
+	}
+	return ret;
+}
+
+static struct nf_chain_type nft_chain_route_ipv4 = {
+	.family		= NFPROTO_IPV4,
+	.name		= "route",
+	.type		= NFT_CHAIN_T_ROUTE,
+	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
+	.fn		= {
+		[NF_INET_LOCAL_OUT]	= nf_route_table_hook,
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init nft_chain_route_init(void)
+{
+	return nft_register_chain_type(&nft_chain_route_ipv4);
+}
+
+static void __exit nft_chain_route_exit(void)
+{
+	nft_unregister_chain_type(&nft_chain_route_ipv4);
+}
+
+module_init(nft_chain_route_init);
+module_exit(nft_chain_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_CHAIN(AF_INET, "route");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 5677e38eeca3..23833064b7b5 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -29,9 +29,9 @@ config NF_TABLES_IPV6
 	depends on NF_TABLES
 	tristate "IPv6 nf_tables support"
 
-config NF_TABLE_ROUTE_IPV6
+config NFT_CHAIN_ROUTE_IPV6
 	depends on NF_TABLES_IPV6
-	tristate "IPv6 nf_tables route table support"
+	tristate "IPv6 nf_tables route chain support"
 
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 956af4492d10..be4913aa524d 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 
 # nf_tables
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
-obj-$(CONFIG_NF_TABLE_ROUTE_IPV6) += nf_table_route_ipv6.o
+obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nf_table_route_ipv6.c b/net/ipv6/netfilter/nf_table_route_ipv6.c
deleted file mode 100644
index 48ac65c7b398..000000000000
--- a/net/ipv6/netfilter/nf_table_route_ipv6.c
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/route.h>
-
-static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
-					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
-					int (*okfn)(struct sk_buff *))
-{
-	unsigned int ret;
-	struct in6_addr saddr, daddr;
-	u_int8_t hop_limit;
-	u32 mark, flowlabel;
-
-	/* save source/dest address, mark, hoplimit, flowlabel, priority */
-	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
-	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
-	mark = skb->mark;
-	hop_limit = ipv6_hdr(skb)->hop_limit;
-
-	/* flowlabel and prio (includes version, which shouldn't change either */
-	flowlabel = *((u32 *)ipv6_hdr(skb));
-
-	ret = nft_do_chain(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_QUEUE &&
-	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
-	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
-	     skb->mark != mark ||
-	     ipv6_hdr(skb)->hop_limit != hop_limit ||
-	     flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
-		return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP;
-
-	return ret;
-}
-
-static struct nft_base_chain nf_chain_route_output __read_mostly = {
-	.chain	= {
-		.name		= "OUTPUT",
-		.rules		= LIST_HEAD_INIT(nf_chain_route_output.chain.rules),
-		.flags		= NFT_BASE_CHAIN | NFT_CHAIN_BUILTIN,
-	},
-	.ops	= {
-		.hook		= nf_route_table_hook,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP6_PRI_MANGLE,
-		.priv		= &nf_chain_route_output.chain,
-	},
-};
-
-static struct nft_table nf_table_route_ipv6 __read_mostly = {
-	.name	= "route",
-	.chains	= LIST_HEAD_INIT(nf_table_route_ipv6.chains),
-};
-
-static int __init nf_table_route_init(void)
-{
-	list_add_tail(&nf_chain_route_output.chain.list,
-		      &nf_table_route_ipv6.chains);
-	return nft_register_table(&nf_table_route_ipv6, NFPROTO_IPV6);
-}
-
-static void __exit nf_table_route_exit(void)
-{
-	nft_unregister_table(&nf_table_route_ipv6, NFPROTO_IPV6);
-}
-
-module_init(nf_table_route_init);
-module_exit(nf_table_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_TABLE(AF_INET6, "route");
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index e0717cea4913..3631d6238e6f 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -39,14 +40,33 @@ static struct nft_af_info nft_af_ipv6 __read_mostly = {
 	},
 };
 
+static struct nf_chain_type filter_ipv6 = {
+	.family		= NFPROTO_IPV6,
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING),
+	.fn		= {
+		[NF_INET_LOCAL_IN]	= nft_do_chain,
+		[NF_INET_LOCAL_OUT]	= nft_do_chain,
+		[NF_INET_FORWARD]	= nft_do_chain,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain,
+		[NF_INET_POST_ROUTING]	= nft_do_chain,
+	},
+};
+
 static int __init nf_tables_ipv6_init(void)
 {
+	nft_register_chain_type(&filter_ipv6);
 	return nft_register_afinfo(&nft_af_ipv6);
 }
-
 static void __exit nf_tables_ipv6_exit(void)
 {
 	nft_unregister_afinfo(&nft_af_ipv6);
+	nft_unregister_chain_type(&filter_ipv6);
 }
 
 module_init(nf_tables_ipv6_init);
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
new file mode 100644
index 000000000000..4cdc992fa067
--- /dev/null
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/route.h>
+
+static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	struct in6_addr saddr, daddr;
+	u_int8_t hop_limit;
+	u32 mark, flowlabel;
+
+	/* save source/dest address, mark, hoplimit, flowlabel, priority */
+	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+	mark = skb->mark;
+	hop_limit = ipv6_hdr(skb)->hop_limit;
+
+	/* flowlabel and prio (includes version, which shouldn't change either */
+	flowlabel = *((u32 *)ipv6_hdr(skb));
+
+	ret = nft_do_chain(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_QUEUE &&
+	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+	     skb->mark != mark ||
+	     ipv6_hdr(skb)->hop_limit != hop_limit ||
+	     flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
+		return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP;
+
+	return ret;
+}
+
+static struct nf_chain_type nft_chain_route_ipv6 = {
+	.family		= NFPROTO_IPV6,
+	.name		= "route",
+	.type		= NFT_CHAIN_T_ROUTE,
+	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
+	.fn		= {
+                [NF_INET_LOCAL_OUT]	= nf_route_table_hook,
+        },
+        .me		= THIS_MODULE,
+};
+
+static int __init nft_chain_route_init(void)
+{
+	return nft_register_chain_type(&nft_chain_route_ipv6);
+}
+
+static void __exit nft_chain_route_exit(void)
+{
+	nft_unregister_chain_type(&nft_chain_route_ipv6);
+}
+
+module_init(nft_chain_route_init);
+module_exit(nft_chain_route_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route");
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6dac9a3c9c40..9c2d8d5af843 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -104,8 +104,7 @@ static struct nft_table *nft_table_lookup(const struct nft_af_info *afi,
 }
 
 static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
-						const struct nlattr *nla,
-						bool autoload)
+						const struct nlattr *nla)
 {
 	struct nft_table *table;
 
@@ -116,16 +115,6 @@ static struct nft_table *nf_tables_table_lookup(const struct nft_af_info *afi,
 	if (table != NULL)
 		return table;
 
-#ifdef CONFIG_MODULES
-	if (autoload) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-table-%u-%*.s", afi->family,
-			       nla_len(nla)-1, (const char *)nla_data(nla));
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		if (nft_table_lookup(afi, nla))
-			return ERR_PTR(-EAGAIN);
-	}
-#endif
 	return ERR_PTR(-ENOENT);
 }
 
@@ -134,6 +123,39 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
 	return ++table->hgenerator;
 }
 
+static struct nf_chain_type *chain_type[AF_MAX][NFT_CHAIN_T_MAX];
+
+static int __nf_tables_chain_type_lookup(int family, const struct nlattr *nla)
+{
+	int i;
+
+	for (i=0; i<NFT_CHAIN_T_MAX; i++) {
+		if (chain_type[family][i] != NULL &&
+		    !nla_strcmp(nla, chain_type[family][i]->name))
+			return i;
+	}
+	return -1;
+}
+
+static int nf_tables_chain_type_lookup(const struct nft_af_info *afi,
+				       const struct nlattr *nla,
+				       bool autoload)
+{
+	int type;
+
+	type = __nf_tables_chain_type_lookup(afi->family, nla);
+#ifdef CONFIG_MODULES
+	if (type < 0 && autoload) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-chain-%u-%*.s", afi->family,
+			       nla_len(nla)-1, (const char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		type = __nf_tables_chain_type_lookup(afi->family, nla);
+	}
+#endif
+	return type;
+}
+
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 	[NFTA_TABLE_NAME]	= { .type = NLA_STRING },
 };
@@ -258,7 +280,7 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -294,7 +316,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 		return PTR_ERR(afi);
 
 	name = nla[NFTA_TABLE_NAME];
-	table = nf_tables_table_lookup(afi, name, false);
+	table = nf_tables_table_lookup(afi, name);
 	if (IS_ERR(table)) {
 		if (PTR_ERR(table) != -ENOENT)
 			return PTR_ERR(table);
@@ -335,13 +357,10 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-	if (table->flags & NFT_TABLE_BUILTIN)
-		return -EOPNOTSUPP;
-
 	if (table->use)
 		return -EBUSY;
 
@@ -351,99 +370,34 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	return 0;
 }
 
-static struct nft_table *__nf_tables_table_lookup(const struct nft_af_info *afi,
-						  const char *name)
+int nft_register_chain_type(struct nf_chain_type *ctype)
 {
-	struct nft_table *table;
-
-	list_for_each_entry(table, &afi->tables, list) {
-		if (!strcmp(name, table->name))
-			return table;
-	}
-
-	return ERR_PTR(-ENOENT);
-}
-
-static int nf_tables_chain_notify(const struct sk_buff *oskb,
-				  const struct nlmsghdr *nlh,
-				  const struct nft_table *table,
-				  const struct nft_chain *chain,
-				  int event, int family);
-
-/**
- *	nft_register_table - register a built-in table
- *
- *	@table: the table to register
- *	@family: protocol family to register table with
- *
- *	Register a built-in table for use with nf_tables. Returns zero on
- *	success or a negative errno code otherwise.
- */
-int nft_register_table(struct nft_table *table, int family)
-{
-	struct nft_af_info *afi;
-	struct nft_table *t;
-	struct nft_chain *chain;
-	int err;
+	int err = 0;
 
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-again:
-	afi = nf_tables_afinfo_lookup(family, true);
-	if (IS_ERR(afi)) {
-		err = PTR_ERR(afi);
-		if (err == -EAGAIN)
-			goto again;
-		goto err;
-	}
-
-	t = __nf_tables_table_lookup(afi, table->name);
-	if (IS_ERR(t)) {
-		err = PTR_ERR(t);
-		if (err != -ENOENT)
-			goto err;
-		t = NULL;
+	if (chain_type[ctype->family][ctype->type] != NULL) {
+		err = -EBUSY;
+		goto out;
 	}
 
-	if (t != NULL) {
-		err = -EEXIST;
-		goto err;
-	}
+	if (!try_module_get(ctype->me))
+		goto out;
 
-	table->flags |= NFT_TABLE_BUILTIN;
-	INIT_LIST_HEAD(&table->sets);
-	list_add_tail(&table->list, &afi->tables);
-	nf_tables_table_notify(NULL, NULL, table, NFT_MSG_NEWTABLE, family);
-	list_for_each_entry(chain, &table->chains, list)
-		nf_tables_chain_notify(NULL, NULL, table, chain,
-				       NFT_MSG_NEWCHAIN, family);
-	err = 0;
-err:
+	chain_type[ctype->family][ctype->type] = ctype;
+out:
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return err;
 }
-EXPORT_SYMBOL_GPL(nft_register_table);
+EXPORT_SYMBOL_GPL(nft_register_chain_type);
 
-/**
- *	nft_unregister_table - unregister a built-in table
- *
- *	@table: the table to unregister
- *	@family: protocol family to unregister table with
- *
- *	Unregister a built-in table for use with nf_tables.
- */
-void nft_unregister_table(struct nft_table *table, int family)
+void nft_unregister_chain_type(struct nf_chain_type *ctype)
 {
-	struct nft_chain *chain;
-
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&table->list);
-	list_for_each_entry(chain, &table->chains, list)
-		nf_tables_chain_notify(NULL, NULL, table, chain,
-				       NFT_MSG_DELCHAIN, family);
-	nf_tables_table_notify(NULL, NULL, table, NFT_MSG_DELTABLE, family);
+	chain_type[ctype->family][ctype->type] = NULL;
+	module_put(ctype->me);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
-EXPORT_SYMBOL_GPL(nft_unregister_table);
+EXPORT_SYMBOL_GPL(nft_unregister_chain_type);
 
 /*
  * Chains
@@ -484,6 +438,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 	[NFTA_CHAIN_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
+	[NFTA_CHAIN_TYPE]	= { .type = NLA_NUL_STRING },
 };
 
 static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
@@ -526,6 +481,10 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 		if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
 			goto nla_put_failure;
 		nla_nest_end(skb, nest);
+
+		if (nla_put_string(skb, NFTA_CHAIN_TYPE,
+			chain_type[ops->pf][nft_base_chain(chain)->type]->name))
+				goto nla_put_failure;
 	}
 
 	return nlmsg_end(skb, nlh);
@@ -633,7 +592,7 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -680,7 +639,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], create);
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -722,6 +681,17 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nla[NFTA_CHAIN_HOOK]) {
 		struct nf_hook_ops *ops;
+		nf_hookfn *hookfn;
+		u32 hooknum;
+		int type = NFT_CHAIN_T_DEFAULT;
+
+		if (nla[NFTA_CHAIN_TYPE]) {
+			type = nf_tables_chain_type_lookup(afi,
+							   nla[NFTA_CHAIN_TYPE],
+							   create);
+			if (type < 0)
+				return -ENOENT;
+		}
 
 		err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
 				       nft_hook_policy);
@@ -730,12 +700,20 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		if (ha[NFTA_HOOK_HOOKNUM] == NULL ||
 		    ha[NFTA_HOOK_PRIORITY] == NULL)
 			return -EINVAL;
-		if (ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])) >= afi->nhooks)
+
+		hooknum = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
+		if (hooknum >= afi->nhooks)
 			return -EINVAL;
 
+		hookfn = chain_type[family][type]->fn[hooknum];
+		if (hookfn == NULL)
+			return -EOPNOTSUPP;
+
 		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
 		if (basechain == NULL)
 			return -ENOMEM;
+
+		basechain->type = type;
 		chain = &basechain->chain;
 
 		ops = &basechain->ops;
@@ -744,7 +722,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		ops->hooknum	= ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
 		ops->priority	= ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
 		ops->priv	= chain;
-		ops->hook	= nft_do_chain;
+		ops->hook       = hookfn;
 		if (afi->hooks[ops->hooknum])
 			ops->hook = afi->hooks[ops->hooknum];
 
@@ -793,7 +771,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -801,9 +779,6 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
 
-	if (chain->flags & NFT_CHAIN_BUILTIN)
-		return -EOPNOTSUPP;
-
 	if (!list_empty(&chain->rules))
 		return -EBUSY;
 
@@ -1190,7 +1165,7 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -1268,7 +1243,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], create);
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -1374,7 +1349,7 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -1490,7 +1465,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 		return PTR_ERR(afi);
 
 	if (nla[NFTA_SET_TABLE] != NULL) {
-		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], false);
+		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 		if (IS_ERR(table))
 			return PTR_ERR(table);
 	}
@@ -1820,7 +1795,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE], create);
+	table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
@@ -2008,7 +1983,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
-	table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE], false);
+	table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-- 
cgit 


From 0ca743a5599199152a31a7146b83213c786c2eb2 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 14 Oct 2013 00:06:06 +0200
Subject: netfilter: nf_tables: add compatibility layer for x_tables

This patch adds the x_tables compatibility layer. This allows you
to use existing x_tables matches and targets from nf_tables.

This compatibility later allows us to use existing matches/targets
for features that are still missing in nf_tables. We can progressively
replace them with native nf_tables extensions. It also provides the
userspace compatibility software that allows you to express the
rule-set using the iptables syntax but using the nf_tables kernel
components.

In order to get this compatibility layer working, I've done the
following things:

* add NFNL_SUBSYS_NFT_COMPAT: this new nfnetlink subsystem is used
to query the x_tables match/target revision, so we don't need to
use the native x_table getsockopt interface.

* emulate xt structures: this required extending the struct nft_pktinfo
to include the fragment offset, which is already obtained from
ip[6]_tables and that is used by some matches/targets.

* add support for default policy to base chains, required to emulate
  x_tables.

* add NFTA_CHAIN_USE attribute to obtain the number of references to
  chains, required by x_tables emulation.

* add chain packet/byte counters using per-cpu.

* support 32-64 bits compat.

For historical reasons, this patch includes the following patches
that were posted in the netfilter-devel mailing list.

From Pablo Neira Ayuso:
* nf_tables: add default policy to base chains
* netfilter: nf_tables: add NFTA_CHAIN_USE attribute
* nf_tables: nft_compat: private data of target and matches in contiguous area
* nf_tables: validate hooks for compat match/target
* nf_tables: nft_compat: release cached matches/targets
* nf_tables: x_tables support as a compile time option
* nf_tables: fix alias for xtables over nftables module
* nf_tables: add packet and byte counters per chain
* nf_tables: fix per-chain counter stats if no counters are passed
* nf_tables: don't bump chain stats
* nf_tables: add protocol and flags for xtables over nf_tables
* nf_tables: add ip[6]t_entry emulation
* nf_tables: move specific layer 3 compat code to nf_tables_ipv[4|6]
* nf_tables: support 32bits-64bits x_tables compat
* nf_tables: fix compilation if CONFIG_COMPAT is disabled

From Patrick McHardy:
* nf_tables: move policy to struct nft_base_chain
* nf_tables: send notifications for base chain policy changes

From Alexander Primak:
* nf_tables: remove the duplicate NF_INET_LOCAL_OUT

From Nicolas Dichtel:
* nf_tables: fix compilation when nf-netlink is a module

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h               |  44 +-
 include/net/netfilter/nf_tables_ipv4.h          |  23 +
 include/net/netfilter/nf_tables_ipv6.h          |  30 +
 include/uapi/linux/netfilter/Kbuild             |   1 +
 include/uapi/linux/netfilter/nf_tables.h        |  32 +
 include/uapi/linux/netfilter/nf_tables_compat.h |  38 ++
 include/uapi/linux/netfilter/nfnetlink.h        |   3 +-
 net/ipv4/netfilter/nf_tables_ipv4.c             |  32 +-
 net/ipv4/netfilter/nft_chain_nat_ipv4.c         |   6 +-
 net/ipv4/netfilter/nft_chain_route_ipv4.c       |   6 +-
 net/ipv6/netfilter/nf_tables_ipv6.c             |  33 +-
 net/ipv6/netfilter/nft_chain_route_ipv6.c       |   8 +-
 net/netfilter/Kconfig                           |   9 +
 net/netfilter/Makefile                          |   1 +
 net/netfilter/nf_tables_api.c                   | 220 ++++++-
 net/netfilter/nf_tables_core.c                  |  46 +-
 net/netfilter/nft_cmp.c                         |   3 +-
 net/netfilter/nft_compat.c                      | 768 ++++++++++++++++++++++++
 net/netfilter/nft_immediate.c                   |  12 +-
 net/netfilter/nft_payload.c                     |   4 +-
 20 files changed, 1241 insertions(+), 78 deletions(-)
 create mode 100644 include/net/netfilter/nf_tables_ipv4.h
 create mode 100644 include/net/netfilter/nf_tables_ipv6.h
 create mode 100644 include/uapi/linux/netfilter/nf_tables_compat.h
 create mode 100644 net/netfilter/nft_compat.c

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 8403f7f52e81..a68f45f0fe2e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -3,6 +3,7 @@
 
 #include <linux/list.h>
 #include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netlink.h>
 
@@ -15,8 +16,23 @@ struct nft_pktinfo {
 	u8				hooknum;
 	u8				nhoff;
 	u8				thoff;
+	/* for x_tables compatibility */
+	struct xt_action_param		xt;
 };
 
+static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
+				   const struct nf_hook_ops *ops,
+				   struct sk_buff *skb,
+				   const struct net_device *in,
+				   const struct net_device *out)
+{
+	pkt->skb = skb;
+	pkt->in = pkt->xt.in = in;
+	pkt->out = pkt->xt.out = out;
+	pkt->hooknum = pkt->xt.hooknum = ops->hooknum;
+	pkt->xt.family = ops->pf;
+}
+
 struct nft_data {
 	union {
 		u32				data[4];
@@ -57,6 +73,7 @@ static inline void nft_data_debug(const struct nft_data *data)
  * 	@afi: address family info
  * 	@table: the table the chain is contained in
  * 	@chain: the chain the rule is contained in
+ *	@nla: netlink attributes
  */
 struct nft_ctx {
 	const struct sk_buff		*skb;
@@ -64,6 +81,7 @@ struct nft_ctx {
 	const struct nft_af_info	*afi;
 	const struct nft_table		*table;
 	const struct nft_chain		*chain;
+	const struct nlattr * const 	*nla;
 };
 
 struct nft_data_desc {
@@ -235,7 +253,8 @@ extern void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
  *	@maxattr: highest netlink attribute number
  */
 struct nft_expr_type {
-	const struct nft_expr_ops	*(*select_ops)(const struct nlattr * const tb[]);
+	const struct nft_expr_ops	*(*select_ops)(const struct nft_ctx *,
+						       const struct nlattr * const tb[]);
 	const struct nft_expr_ops	*ops;
 	struct list_head		list;
 	const char			*name;
@@ -253,6 +272,8 @@ struct nft_expr_type {
  *	@destroy: destruction function
  *	@dump: function to dump parameters
  *	@type: expression type
+ *	@validate: validate expression, called during loop detection
+ *	@data: extra data to attach to this expression operation
  */
 struct nft_expr;
 struct nft_expr_ops {
@@ -267,8 +288,11 @@ struct nft_expr_ops {
 	void				(*destroy)(const struct nft_expr *expr);
 	int				(*dump)(struct sk_buff *skb,
 						const struct nft_expr *expr);
-	const struct nft_data *		(*get_verdict)(const struct nft_expr *expr);
+	int				(*validate)(const struct nft_ctx *ctx,
+						    const struct nft_expr *expr,
+						    const struct nft_data **data);
 	const struct nft_expr_type	*type;
+	void				*data;
 };
 
 #define NFT_EXPR_MAXATTR		16
@@ -368,16 +392,25 @@ enum nft_chain_type {
 	NFT_CHAIN_T_MAX
 };
 
+struct nft_stats {
+	u64 bytes;
+	u64 pkts;
+};
+
 /**
  *	struct nft_base_chain - nf_tables base chain
  *
  *	@ops: netfilter hook ops
  *	@type: chain type
+ *	@policy: default policy
+ *	@stats: per-cpu chain stats
  *	@chain: the chain
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
 	enum nft_chain_type		type;
+	u8				policy;
+	struct nft_stats __percpu	*stats;
 	struct nft_chain		chain;
 };
 
@@ -386,11 +419,8 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai
 	return container_of(chain, struct nft_base_chain, chain);
 }
 
-extern unsigned int nft_do_chain(const struct nf_hook_ops *ops,
-				 struct sk_buff *skb,
-				 const struct net_device *in,
-				 const struct net_device *out,
-				 int (*okfn)(struct sk_buff *));
+extern unsigned int nft_do_chain_pktinfo(struct nft_pktinfo *pkt,
+					 const struct nf_hook_ops *ops);
 
 /**
  *	struct nft_table - nf_tables table
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
new file mode 100644
index 000000000000..1be1c2c197ee
--- /dev/null
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -0,0 +1,23 @@
+#ifndef _NF_TABLES_IPV4_H_
+#define _NF_TABLES_IPV4_H_
+
+#include <net/netfilter/nf_tables.h>
+#include <net/ip.h>
+
+static inline void
+nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
+		     const struct nf_hook_ops *ops,
+		     struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out)
+{
+	struct iphdr *ip;
+
+	nft_set_pktinfo(pkt, ops, skb, in, out);
+
+	pkt->xt.thoff = ip_hdrlen(pkt->skb);
+	ip = ip_hdr(pkt->skb);
+	pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
+}
+
+#endif
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
new file mode 100644
index 000000000000..4a9b88a65963
--- /dev/null
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -0,0 +1,30 @@
+#ifndef _NF_TABLES_IPV6_H_
+#define _NF_TABLES_IPV6_H_
+
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <net/ipv6.h>
+
+static inline int
+nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
+		     const struct nf_hook_ops *ops,
+		     struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out)
+{
+	int protohdr, thoff = 0;
+	unsigned short frag_off;
+
+	nft_set_pktinfo(pkt, ops, skb, in, out);
+
+	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+	/* If malformed, drop it */
+	if (protohdr < 0)
+		return -1;
+
+	pkt->xt.thoff = thoff;
+	pkt->xt.fragoff = frag_off;
+
+	return 0;
+}
+
+#endif
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 6ce0b7f566a7..17c3af2c4bb9 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -6,6 +6,7 @@ header-y += nf_conntrack_sctp.h
 header-y += nf_conntrack_tcp.h
 header-y += nf_conntrack_tuple_common.h
 header-y += nf_tables.h
+header-y += nf_tables_compat.h
 header-y += nf_nat.h
 header-y += nfnetlink.h
 header-y += nfnetlink_acct.h
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 779cf951c8de..1563875e6942 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -115,7 +115,10 @@ enum nft_table_attributes {
  * @NFTA_CHAIN_HANDLE: numeric handle of the chain (NLA_U64)
  * @NFTA_CHAIN_NAME: name of the chain (NLA_STRING)
  * @NFTA_CHAIN_HOOK: hook specification for basechains (NLA_NESTED: nft_hook_attributes)
+ * @NFTA_CHAIN_POLICY: numeric policy of the chain (NLA_U32)
+ * @NFTA_CHAIN_USE: number of references to this chain (NLA_U32)
  * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING)
+ * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes)
  */
 enum nft_chain_attributes {
 	NFTA_CHAIN_UNSPEC,
@@ -123,7 +126,10 @@ enum nft_chain_attributes {
 	NFTA_CHAIN_HANDLE,
 	NFTA_CHAIN_NAME,
 	NFTA_CHAIN_HOOK,
+	NFTA_CHAIN_POLICY,
+	NFTA_CHAIN_USE,
 	NFTA_CHAIN_TYPE,
+	NFTA_CHAIN_COUNTERS,
 	__NFTA_CHAIN_MAX
 };
 #define NFTA_CHAIN_MAX		(__NFTA_CHAIN_MAX - 1)
@@ -135,6 +141,7 @@ enum nft_chain_attributes {
  * @NFTA_RULE_CHAIN: name of the chain containing the rule (NLA_STRING)
  * @NFTA_RULE_HANDLE: numeric handle of the rule (NLA_U64)
  * @NFTA_RULE_EXPRESSIONS: list of expressions (NLA_NESTED: nft_expr_attributes)
+ * @NFTA_RULE_COMPAT: compatibility specifications of the rule (NLA_NESTED: nft_rule_compat_attributes)
  */
 enum nft_rule_attributes {
 	NFTA_RULE_UNSPEC,
@@ -142,10 +149,35 @@ enum nft_rule_attributes {
 	NFTA_RULE_CHAIN,
 	NFTA_RULE_HANDLE,
 	NFTA_RULE_EXPRESSIONS,
+	NFTA_RULE_COMPAT,
 	__NFTA_RULE_MAX
 };
 #define NFTA_RULE_MAX		(__NFTA_RULE_MAX - 1)
 
+/**
+ * enum nft_rule_compat_flags - nf_tables rule compat flags
+ *
+ * @NFT_RULE_COMPAT_F_INV: invert the check result
+ */
+enum nft_rule_compat_flags {
+	NFT_RULE_COMPAT_F_INV	= (1 << 1),
+	NFT_RULE_COMPAT_F_MASK	= NFT_RULE_COMPAT_F_INV,
+};
+
+/**
+ * enum nft_rule_compat_attributes - nf_tables rule compat attributes
+ *
+ * @NFTA_RULE_COMPAT_PROTO: numerice value of handled protocol (NLA_U32)
+ * @NFTA_RULE_COMPAT_FLAGS: bitmask of enum nft_rule_compat_flags (NLA_U32)
+ */
+enum nft_rule_compat_attributes {
+	NFTA_RULE_COMPAT_UNSPEC,
+	NFTA_RULE_COMPAT_PROTO,
+	NFTA_RULE_COMPAT_FLAGS,
+	__NFTA_RULE_COMPAT_MAX
+};
+#define NFTA_RULE_COMPAT_MAX	(__NFTA_RULE_COMPAT_MAX - 1)
+
 /**
  * enum nft_set_flags - nf_tables set flags
  *
diff --git a/include/uapi/linux/netfilter/nf_tables_compat.h b/include/uapi/linux/netfilter/nf_tables_compat.h
new file mode 100644
index 000000000000..8310f5f76551
--- /dev/null
+++ b/include/uapi/linux/netfilter/nf_tables_compat.h
@@ -0,0 +1,38 @@
+#ifndef _NFT_COMPAT_NFNETLINK_H_
+#define _NFT_COMPAT_NFNETLINK_H_
+
+enum nft_target_attributes {
+	NFTA_TARGET_UNSPEC,
+	NFTA_TARGET_NAME,
+	NFTA_TARGET_REV,
+	NFTA_TARGET_INFO,
+	__NFTA_TARGET_MAX
+};
+#define NFTA_TARGET_MAX		(__NFTA_TARGET_MAX - 1)
+
+enum nft_match_attributes {
+	NFTA_MATCH_UNSPEC,
+	NFTA_MATCH_NAME,
+	NFTA_MATCH_REV,
+	NFTA_MATCH_INFO,
+	__NFTA_MATCH_MAX
+};
+#define NFTA_MATCH_MAX		(__NFTA_MATCH_MAX - 1)
+
+#define NFT_COMPAT_NAME_MAX	32
+
+enum {
+	NFNL_MSG_COMPAT_GET,
+	NFNL_MSG_COMPAT_MAX
+};
+
+enum {
+	NFTA_COMPAT_UNSPEC = 0,
+	NFTA_COMPAT_NAME,
+	NFTA_COMPAT_REV,
+	NFTA_COMPAT_TYPE,
+	__NFTA_COMPAT_MAX,
+};
+#define NFTA_COMPAT_MAX (__NFTA_COMPAT_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index d276c3bd55b8..288959404d54 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -54,6 +54,7 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_CTNETLINK_TIMEOUT	8
 #define NFNL_SUBSYS_CTHELPER		9
 #define NFNL_SUBSYS_NFTABLES		10
-#define NFNL_SUBSYS_COUNT		11
+#define NFNL_SUBSYS_NFT_COMPAT		11
+#define NFNL_SUBSYS_COUNT		12
 
 #endif /* _UAPI_NFNETLINK_H */
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index 23525c4c0192..c61cffb9b760 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -15,6 +15,8 @@
 #include <linux/netfilter_ipv4.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/ip.h>
+#include <net/net_namespace.h>
+#include <net/netfilter/nf_tables_ipv4.h>
 
 static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 				    struct sk_buff *skb,
@@ -22,6 +24,8 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
+	struct nft_pktinfo pkt;
+
 	if (unlikely(skb->len < sizeof(struct iphdr) ||
 		     ip_hdr(skb)->ihl < sizeof(struct iphdr) / 4)) {
 		if (net_ratelimit())
@@ -29,8 +33,9 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops,
 				"packet\n");
 		return NF_ACCEPT;
 	}
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
 
-	return nft_do_chain(ops, skb, in, out, okfn);
+	return nft_do_chain_pktinfo(&pkt, ops);
 }
 
 static struct nft_af_info nft_af_ipv4 __read_mostly = {
@@ -42,6 +47,21 @@ static struct nft_af_info nft_af_ipv4 __read_mostly = {
 	},
 };
 
+
+static unsigned int
+nft_do_chain_ipv4(const struct nf_hook_ops *ops,
+		  struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+
+	return nft_do_chain_pktinfo(&pkt, ops);
+}
+
 static struct nf_chain_type filter_ipv4 = {
 	.family		= NFPROTO_IPV4,
 	.name		= "filter",
@@ -52,11 +72,11 @@ static struct nf_chain_type filter_ipv4 = {
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
 	.fn		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain,
-		[NF_INET_FORWARD]	= nft_do_chain,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain,
-		[NF_INET_POST_ROUTING]	= nft_do_chain,
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv4,
+		[NF_INET_LOCAL_OUT]	= nft_ipv4_output,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv4,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv4,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv4,
 	},
 };
 
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index cd286306be85..e09c201adf84 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/ip.h>
 
@@ -181,6 +182,7 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 	struct nf_conn_nat *nat;
 	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	struct nft_pktinfo pkt;
 	unsigned int ret;
 
 	if (ct == NULL || nf_ct_is_untracked(ct))
@@ -213,7 +215,9 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
 		if (nf_nat_initialized(ct, maniptype))
 			break;
 
-		ret = nft_do_chain(ops, skb, in, out, okfn);
+		nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+
+		ret = nft_do_chain_pktinfo(&pkt, ops);
 		if (ret != NF_ACCEPT)
 			return ret;
 		if (!nf_nat_initialized(ct, maniptype)) {
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
index 6b84e097b8fc..4e6bf9a3d7aa 100644
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c
@@ -17,6 +17,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
 #include <net/route.h>
 #include <net/ip.h>
 
@@ -27,6 +28,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 					int (*okfn)(struct sk_buff *))
 {
 	unsigned int ret;
+	struct nft_pktinfo pkt;
 	u32 mark;
 	__be32 saddr, daddr;
 	u_int8_t tos;
@@ -37,13 +39,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	    ip_hdrlen(skb) < sizeof(struct iphdr))
 		return NF_ACCEPT;
 
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+
 	mark = skb->mark;
 	iph = ip_hdr(skb);
 	saddr = iph->saddr;
 	daddr = iph->daddr;
 	tos = iph->tos;
 
-	ret = nft_do_chain(ops, skb, in, out, okfn);
+	ret = nft_do_chain_pktinfo(&pkt, ops);
 	if (ret != NF_DROP && ret != NF_QUEUE) {
 		iph = ip_hdr(skb);
 
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 3631d6238e6f..42f905a808a3 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -14,6 +14,7 @@
 #include <linux/ipv6.h>
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv6.h>
 
 static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 				    struct sk_buff *skb,
@@ -21,14 +22,18 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
+	struct nft_pktinfo pkt;
+
 	if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
 		if (net_ratelimit())
 			pr_info("nf_tables_ipv6: ignoring short SOCK_RAW "
 				"packet\n");
 		return NF_ACCEPT;
 	}
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
 
-	return nft_do_chain(ops, skb, in, out, okfn);
+	return nft_do_chain_pktinfo(&pkt, ops);
 }
 
 static struct nft_af_info nft_af_ipv6 __read_mostly = {
@@ -40,6 +45,22 @@ static struct nft_af_info nft_af_ipv6 __read_mostly = {
 	},
 };
 
+static unsigned int
+nft_do_chain_ipv6(const struct nf_hook_ops *ops,
+		  struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	/* malformed packet, drop it */
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
+
+	return nft_do_chain_pktinfo(&pkt, ops);
+}
+
 static struct nf_chain_type filter_ipv6 = {
 	.family		= NFPROTO_IPV6,
 	.name		= "filter",
@@ -50,11 +71,11 @@ static struct nf_chain_type filter_ipv6 = {
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
 	.fn		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain,
-		[NF_INET_FORWARD]	= nft_do_chain,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain,
-		[NF_INET_POST_ROUTING]	= nft_do_chain,
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
+		[NF_INET_LOCAL_OUT]	= nft_ipv6_output,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
 	},
 };
 
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 4cdc992fa067..3fe40f0456ad 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -19,6 +19,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv6.h>
 #include <net/route.h>
 
 static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
@@ -28,10 +29,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 					int (*okfn)(struct sk_buff *))
 {
 	unsigned int ret;
+	struct nft_pktinfo pkt;
 	struct in6_addr saddr, daddr;
 	u_int8_t hop_limit;
 	u32 mark, flowlabel;
 
+	/* malformed packet, drop it */
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
+
 	/* save source/dest address, mark, hoplimit, flowlabel, priority */
 	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
 	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
@@ -41,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	/* flowlabel and prio (includes version, which shouldn't change either */
 	flowlabel = *((u32 *)ipv6_hdr(skb));
 
-	ret = nft_do_chain(ops, skb, in, out, okfn);
+	ret = nft_do_chain_pktinfo(&pkt, ops);
 	if (ret != NF_DROP && ret != NF_QUEUE &&
 	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
 	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index aa184a46bbf3..49e362707379 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -450,6 +450,15 @@ config NFT_LIMIT
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables limit module"
 
+config NFT_COMPAT
+	depends on NF_TABLES
+	depends on NETFILTER_XTABLES
+	tristate "Netfilter x_tables over nf_tables module"
+	help
+	  This is required if you intend to use any of existing
+	  x_tables match/target extensions over the nf_tables
+	  framework.
+
 config NETFILTER_XTABLES
 	tristate "Netfilter Xtables support (required for ip_tables)"
 	default m if NETFILTER_ADVANCED=n
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index b6b78754e4cc..a6781450b6fb 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,6 +70,7 @@ nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
 nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
 obj-$(CONFIG_NFT_META)		+= nft_meta.o
 obj-$(CONFIG_NFT_CT)		+= nft_ct.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9c2d8d5af843..61e017b349cb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -438,7 +438,9 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 	[NFTA_CHAIN_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
+	[NFTA_CHAIN_POLICY]	= { .type = NLA_U32 },
 	[NFTA_CHAIN_TYPE]	= { .type = NLA_NUL_STRING },
+	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
@@ -446,6 +448,33 @@ static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
 	[NFTA_HOOK_PRIORITY]	= { .type = NLA_U32 },
 };
 
+static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats)
+{
+	struct nft_stats *cpu_stats, total;
+	struct nlattr *nest;
+	int cpu;
+
+	memset(&total, 0, sizeof(total));
+	for_each_possible_cpu(cpu) {
+		cpu_stats = per_cpu_ptr(stats, cpu);
+		total.pkts += cpu_stats->pkts;
+		total.bytes += cpu_stats->bytes;
+	}
+	nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nla_put_be64(skb, NFTA_COUNTER_PACKETS, cpu_to_be64(total.pkts)) ||
+	    nla_put_be64(skb, NFTA_COUNTER_BYTES, cpu_to_be64(total.bytes)))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
 static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 				     int event, u32 flags, int family,
 				     const struct nft_table *table,
@@ -472,8 +501,11 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 		goto nla_put_failure;
 
 	if (chain->flags & NFT_BASE_CHAIN) {
-		const struct nf_hook_ops *ops = &nft_base_chain(chain)->ops;
-		struct nlattr *nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
+		const struct nft_base_chain *basechain = nft_base_chain(chain);
+		const struct nf_hook_ops *ops = &basechain->ops;
+		struct nlattr *nest;
+
+		nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
 		if (nest == NULL)
 			goto nla_put_failure;
 		if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
@@ -482,11 +514,21 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, u32 portid, u32 seq,
 			goto nla_put_failure;
 		nla_nest_end(skb, nest);
 
+		if (nla_put_be32(skb, NFTA_CHAIN_POLICY,
+				 htonl(basechain->policy)))
+			goto nla_put_failure;
+
 		if (nla_put_string(skb, NFTA_CHAIN_TYPE,
 			chain_type[ops->pf][nft_base_chain(chain)->type]->name))
 				goto nla_put_failure;
+
+		if (nft_dump_stats(skb, nft_base_chain(chain)->stats))
+			goto nla_put_failure;
 	}
 
+	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
+		goto nla_put_failure;
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -617,6 +659,67 @@ err:
 	return err;
 }
 
+static int
+nf_tables_chain_policy(struct nft_base_chain *chain, const struct nlattr *attr)
+{
+	switch (ntohl(nla_get_be32(attr))) {
+	case NF_DROP:
+		chain->policy = NF_DROP;
+		break;
+	case NF_ACCEPT:
+		chain->policy = NF_ACCEPT;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
+	[NFTA_COUNTER_PACKETS]	= { .type = NLA_U64 },
+	[NFTA_COUNTER_BYTES]	= { .type = NLA_U64 },
+};
+
+static int
+nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
+{
+	struct nlattr *tb[NFTA_COUNTER_MAX+1];
+	struct nft_stats __percpu *newstats;
+	struct nft_stats *stats;
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS])
+		return -EINVAL;
+
+	newstats = alloc_percpu(struct nft_stats);
+	if (newstats == NULL)
+		return -ENOMEM;
+
+	/* Restore old counters on this cpu, no problem. Per-cpu statistics
+	 * are not exposed to userspace.
+	 */
+	stats = this_cpu_ptr(newstats);
+	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+
+	if (chain->stats) {
+		/* nfnl_lock is held, add some nfnl function for this, later */
+		struct nft_stats __percpu *oldstats =
+			rcu_dereference_protected(chain->stats, 1);
+
+		rcu_assign_pointer(chain->stats, newstats);
+		synchronize_rcu();
+		free_percpu(oldstats);
+	} else
+		rcu_assign_pointer(chain->stats, newstats);
+
+	return 0;
+}
+
 static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -626,7 +729,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
-	struct nft_base_chain *basechain;
+	struct nft_base_chain *basechain = NULL;
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
 	int family = nfmsg->nfgen_family;
 	u64 handle = 0;
@@ -673,6 +776,26 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 		    !IS_ERR(nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME])))
 			return -EEXIST;
 
+		if (nla[NFTA_CHAIN_POLICY]) {
+			if (!(chain->flags & NFT_BASE_CHAIN))
+				return -EOPNOTSUPP;
+
+			err = nf_tables_chain_policy(nft_base_chain(chain),
+						     nla[NFTA_CHAIN_POLICY]);
+			if (err < 0)
+				return err;
+		}
+
+		if (nla[NFTA_CHAIN_COUNTERS]) {
+			if (!(chain->flags & NFT_BASE_CHAIN))
+				return -EOPNOTSUPP;
+
+			err = nf_tables_counters(nft_base_chain(chain),
+						 nla[NFTA_CHAIN_COUNTERS]);
+			if (err < 0)
+				return err;
+		}
+
 		if (nla[NFTA_CHAIN_HANDLE] && name)
 			nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
@@ -727,6 +850,36 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			ops->hook = afi->hooks[ops->hooknum];
 
 		chain->flags |= NFT_BASE_CHAIN;
+
+		if (nla[NFTA_CHAIN_POLICY]) {
+			err = nf_tables_chain_policy(basechain,
+						     nla[NFTA_CHAIN_POLICY]);
+			if (err < 0) {
+				free_percpu(basechain->stats);
+				kfree(basechain);
+				return err;
+			}
+		} else
+			basechain->policy = NF_ACCEPT;
+
+		if (nla[NFTA_CHAIN_COUNTERS]) {
+			err = nf_tables_counters(basechain,
+						 nla[NFTA_CHAIN_COUNTERS]);
+			if (err < 0) {
+				free_percpu(basechain->stats);
+				kfree(basechain);
+				return err;
+			}
+		} else {
+			struct nft_stats __percpu *newstats;
+
+			newstats = alloc_percpu(struct nft_stats);
+			if (newstats == NULL)
+				return -ENOMEM;
+
+			rcu_assign_pointer(nft_base_chain(chain)->stats,
+					   newstats);
+		}
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 		if (chain == NULL)
@@ -739,6 +892,15 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	list_add_tail(&chain->list, &table->chains);
 	table->use++;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		err = nf_register_hook(&nft_base_chain(chain)->ops);
+		if (err < 0) {
+			free_percpu(basechain->stats);
+			kfree(basechain);
+			return err;
+		}
+	}
 notify:
 	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
 			       family);
@@ -751,9 +913,10 @@ static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
 
 	BUG_ON(chain->use > 0);
 
-	if (chain->flags & NFT_BASE_CHAIN)
+	if (chain->flags & NFT_BASE_CHAIN) {
+		free_percpu(nft_base_chain(chain)->stats);
 		kfree(nft_base_chain(chain));
-	else
+	} else
 		kfree(chain);
 }
 
@@ -801,13 +964,15 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 			 const struct nlmsghdr *nlh,
 			 const struct nft_af_info *afi,
 			 const struct nft_table *table,
-			 const struct nft_chain *chain)
+			 const struct nft_chain *chain,
+			 const struct nlattr * const *nla)
 {
 	ctx->skb   = skb;
 	ctx->nlh   = nlh;
 	ctx->afi   = afi;
 	ctx->table = table;
 	ctx->chain = chain;
+	ctx->nla   = nla;
 }
 
 /*
@@ -910,7 +1075,8 @@ struct nft_expr_info {
 	struct nlattr			*tb[NFT_EXPR_MAXATTR + 1];
 };
 
-static int nf_tables_expr_parse(const struct nlattr *nla,
+static int nf_tables_expr_parse(const struct nft_ctx *ctx,
+				const struct nlattr *nla,
 				struct nft_expr_info *info)
 {
 	const struct nft_expr_type *type;
@@ -935,7 +1101,8 @@ static int nf_tables_expr_parse(const struct nlattr *nla,
 		memset(info->tb, 0, sizeof(info->tb[0]) * (type->maxattr + 1));
 
 	if (type->select_ops != NULL) {
-		ops = type->select_ops((const struct nlattr * const *)info->tb);
+		ops = type->select_ops(ctx,
+				       (const struct nlattr * const *)info->tb);
 		if (IS_ERR(ops)) {
 			err = PTR_ERR(ops);
 			goto err1;
@@ -1012,6 +1179,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_RULE_HANDLE]	= { .type = NLA_U64 },
 	[NFTA_RULE_EXPRESSIONS]	= { .type = NLA_NESTED },
+	[NFTA_RULE_COMPAT]	= { .type = NLA_NESTED },
 };
 
 static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1269,6 +1437,8 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		handle = nf_tables_alloc_handle(table);
 	}
 
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+
 	n = 0;
 	size = 0;
 	if (nla[NFTA_RULE_EXPRESSIONS]) {
@@ -1278,7 +1448,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 				goto err1;
 			if (n == NFT_RULE_MAXEXPRS)
 				goto err1;
-			err = nf_tables_expr_parse(tmp, &info[n]);
+			err = nf_tables_expr_parse(&ctx, tmp, &info[n]);
 			if (err < 0)
 				goto err1;
 			size += info[n].ops->size;
@@ -1294,7 +1464,6 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	rule->handle = handle;
 	rule->dlen   = size;
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, chain);
 	expr = nft_expr_first(rule);
 	for (i = 0; i < n; i++) {
 		err = nf_tables_newexpr(&ctx, &info[i], expr);
@@ -1304,13 +1473,6 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		expr = nft_expr_next(expr);
 	}
 
-	/* Register hook when first rule is inserted into a base chain */
-	if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN) {
-		err = nf_register_hook(&nft_base_chain(chain)->ops);
-		if (err < 0)
-			goto err2;
-	}
-
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
 		list_replace_rcu(&old_rule->list, &rule->list);
 		nf_tables_rule_destroy(old_rule);
@@ -1379,10 +1541,6 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 		}
 	}
 
-	/* Unregister hook when last rule from base chain is deleted */
-	if (list_empty(&chain->rules) && chain->flags & NFT_BASE_CHAIN)
-		nf_unregister_hook(&nft_base_chain(chain)->ops);
-
 	return 0;
 }
 
@@ -1470,7 +1628,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 			return PTR_ERR(table);
 	}
 
-	nft_ctx_init(ctx, skb, nlh, afi, table, NULL);
+	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
 	return 0;
 }
 
@@ -1799,7 +1957,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
 
 	set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set)) {
@@ -1987,7 +2145,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	if (IS_ERR(table))
 		return PTR_ERR(table);
 
-	nft_ctx_init(ctx, skb, nlh, afi, table, NULL);
+	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
 	return 0;
 }
 
@@ -2435,23 +2593,27 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 {
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
-	const struct nft_data *data;
 	const struct nft_set *set;
 	struct nft_set_binding *binding;
 	struct nft_set_iter iter;
-	int err;
 
 	if (ctx->chain == chain)
 		return -ELOOP;
 
 	list_for_each_entry(rule, &chain->rules, list) {
 		nft_rule_for_each_expr(expr, last, rule) {
-			if (!expr->ops->get_verdict)
+			const struct nft_data *data = NULL;
+			int err;
+
+			if (!expr->ops->validate)
 				continue;
 
-			data = expr->ops->get_verdict(expr);
+			err = expr->ops->validate(ctx, expr, &data);
+			if (err < 0)
+				return err;
+
 			if (data == NULL)
-				break;
+				continue;
 
 			switch (data->verdict) {
 			case NFT_JUMP:
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 9aede59ed2d7..e51a45c12128 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -60,27 +60,34 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	return true;
 }
 
-unsigned int nft_do_chain(const struct nf_hook_ops *ops,
-			  struct sk_buff *skb,
-			  const struct net_device *in,
-			  const struct net_device *out,
-			  int (*okfn)(struct sk_buff *))
+struct nft_jumpstack {
+	const struct nft_chain	*chain;
+	const struct nft_rule	*rule;
+};
+
+static inline void
+nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
+		struct nft_jumpstack *jumpstack, unsigned int stackptr)
+{
+	struct nft_stats __percpu *stats;
+	const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this;
+
+	rcu_read_lock_bh();
+	stats = rcu_dereference(nft_base_chain(chain)->stats);
+	__this_cpu_inc(stats->pkts);
+	__this_cpu_add(stats->bytes, pkt->skb->len);
+	rcu_read_unlock_bh();
+}
+
+unsigned int
+nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
 	const struct nft_chain *chain = ops->priv;
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
 	struct nft_data data[NFT_REG_MAX + 1];
-	const struct nft_pktinfo pkt = {
-		.skb		= skb,
-		.in		= in,
-		.out		= out,
-		.hooknum	= ops->hooknum,
-	};
 	unsigned int stackptr = 0;
-	struct {
-		const struct nft_chain	*chain;
-		const struct nft_rule	*rule;
-	} jumpstack[NFT_JUMP_STACK_SIZE];
+	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 
 do_chain:
 	rule = list_entry(&chain->rules, struct nft_rule, list);
@@ -91,8 +98,8 @@ next_rule:
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, data);
 			else if (expr->ops != &nft_payload_fast_ops ||
-				 !nft_payload_fast_eval(expr, data, &pkt))
-				expr->ops->eval(expr, data, &pkt);
+				 !nft_payload_fast_eval(expr, data, pkt))
+				expr->ops->eval(expr, data, pkt);
 
 			if (data[NFT_REG_VERDICT].verdict != NFT_CONTINUE)
 				break;
@@ -135,10 +142,11 @@ next_rule:
 		rule  = jumpstack[stackptr].rule;
 		goto next_rule;
 	}
+	nft_chain_stats(chain, pkt, jumpstack, stackptr);
 
-	return NF_ACCEPT;
+	return nft_base_chain(chain)->policy;
 }
-EXPORT_SYMBOL_GPL(nft_do_chain);
+EXPORT_SYMBOL_GPL(nft_do_chain_pktinfo);
 
 int __init nf_tables_core_module_init(void)
 {
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 37134f3e84fb..954925db414d 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -162,7 +162,8 @@ const struct nft_expr_ops nft_cmp_fast_ops = {
 	.dump		= nft_cmp_fast_dump,
 };
 
-static const struct nft_expr_ops *nft_cmp_select_ops(const struct nlattr * const tb[])
+static const struct nft_expr_ops *
+nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 {
 	struct nft_data_desc desc;
 	struct nft_data data;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
new file mode 100644
index 000000000000..4811f762e060
--- /dev/null
+++ b/net/netfilter/nft_compat.c
@@ -0,0 +1,768 @@
+/*
+ * (C) 2012-2013 by Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This software has been sponsored by Sophos Astaro <http://www.sophos.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <linux/netfilter/nf_tables_compat.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <asm/uaccess.h> /* for set_fs */
+#include <net/netfilter/nf_tables.h>
+
+union nft_entry {
+	struct ipt_entry e4;
+	struct ip6t_entry e6;
+};
+
+static inline void
+nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info)
+{
+	par->target	= xt;
+	par->targinfo	= xt_info;
+	par->hotdrop	= false;
+}
+
+static void nft_target_eval(const struct nft_expr *expr,
+			    struct nft_data data[NFT_REG_MAX + 1],
+			    const struct nft_pktinfo *pkt)
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_target *target = expr->ops->data;
+	struct sk_buff *skb = pkt->skb;
+	int ret;
+
+	nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info);
+
+	ret = target->target(skb, &pkt->xt);
+
+	if (pkt->xt.hotdrop)
+		ret = NF_DROP;
+
+	switch(ret) {
+	case XT_CONTINUE:
+		data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+		break;
+	default:
+		data[NFT_REG_VERDICT].verdict = ret;
+		break;
+	}
+	return;
+}
+
+static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = {
+	[NFTA_TARGET_NAME]	= { .type = NLA_NUL_STRING },
+	[NFTA_TARGET_REV]	= { .type = NLA_U32 },
+	[NFTA_TARGET_INFO]	= { .type = NLA_BINARY },
+};
+
+static void
+nft_target_set_tgchk_param(struct xt_tgchk_param *par,
+			   const struct nft_ctx *ctx,
+			   struct xt_target *target, void *info,
+			   union nft_entry *entry, u8 proto, bool inv)
+{
+	par->net	= &init_net;
+	par->table	= ctx->table->name;
+	switch (ctx->afi->family) {
+	case AF_INET:
+		entry->e4.ip.proto = proto;
+		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
+		break;
+	case AF_INET6:
+		entry->e6.ipv6.proto = proto;
+		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
+		break;
+	}
+	par->entryinfo	= entry;
+	par->target	= target;
+	par->targinfo	= info;
+	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+		const struct nft_base_chain *basechain =
+						nft_base_chain(ctx->chain);
+		const struct nf_hook_ops *ops = &basechain->ops;
+
+		par->hook_mask = 1 << ops->hooknum;
+	}
+	par->family	= ctx->afi->family;
+}
+
+static void target_compat_from_user(struct xt_target *t, void *in, void *out)
+{
+#ifdef CONFIG_COMPAT
+	if (t->compat_from_user) {
+		int pad;
+
+		t->compat_from_user(out, in);
+		pad = XT_ALIGN(t->targetsize) - t->targetsize;
+		if (pad > 0)
+			memset(out + t->targetsize, 0, pad);
+	} else
+#endif
+		memcpy(out, in, XT_ALIGN(t->targetsize));
+}
+
+static inline int nft_compat_target_offset(struct xt_target *target)
+{
+#ifdef CONFIG_COMPAT
+	return xt_compat_target_offset(target);
+#else
+	return 0;
+#endif
+}
+
+static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] = {
+	[NFTA_RULE_COMPAT_PROTO]	= { .type = NLA_U32 },
+	[NFTA_RULE_COMPAT_FLAGS]	= { .type = NLA_U32 },
+};
+
+static u8 nft_parse_compat(const struct nlattr *attr, bool *inv)
+{
+	struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1];
+	u32 flags;
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_RULE_COMPAT_MAX, attr,
+			       nft_rule_compat_policy);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_RULE_COMPAT_PROTO] || !tb[NFTA_RULE_COMPAT_FLAGS])
+		return -EINVAL;
+
+	flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS]));
+	if (flags & ~NFT_RULE_COMPAT_F_MASK)
+		return -EINVAL;
+	if (flags & NFT_RULE_COMPAT_F_INV)
+		*inv = true;
+
+	return ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO]));
+}
+
+static int
+nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		const struct nlattr * const tb[])
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_target *target = expr->ops->data;
+	struct xt_tgchk_param par;
+	size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO]));
+	u8 proto = 0;
+	bool inv = false;
+	union nft_entry e = {};
+	int ret;
+
+	target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info);
+
+	if (ctx->nla[NFTA_RULE_COMPAT])
+		proto = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &inv);
+
+	nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
+
+	ret = xt_check_target(&par, size, proto, inv);
+	if (ret < 0)
+		goto err;
+
+	/* The standard target cannot be used */
+	if (target->target == NULL) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return 0;
+err:
+	module_put(target->me);
+	return ret;
+}
+
+static void
+nft_target_destroy(const struct nft_expr *expr)
+{
+	struct xt_target *target = expr->ops->data;
+
+	module_put(target->me);
+}
+
+static int
+target_dump_info(struct sk_buff *skb, const struct xt_target *t, const void *in)
+{
+	int ret;
+
+#ifdef CONFIG_COMPAT
+	if (t->compat_to_user) {
+		mm_segment_t old_fs;
+		void *out;
+
+		out = kmalloc(XT_ALIGN(t->targetsize), GFP_ATOMIC);
+		if (out == NULL)
+			return -ENOMEM;
+
+		/* We want to reuse existing compat_to_user */
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		t->compat_to_user(out, in);
+		set_fs(old_fs);
+		ret = nla_put(skb, NFTA_TARGET_INFO, XT_ALIGN(t->targetsize), out);
+		kfree(out);
+	} else
+#endif
+		ret = nla_put(skb, NFTA_TARGET_INFO, XT_ALIGN(t->targetsize), in);
+
+	return ret;
+}
+
+static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct xt_target *target = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+
+	if (nla_put_string(skb, NFTA_TARGET_NAME, target->name) ||
+	    nla_put_be32(skb, NFTA_TARGET_REV, htonl(target->revision)) ||
+	    target_dump_info(skb, target, info))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_target_validate(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nft_data **data)
+{
+	struct xt_target *target = expr->ops->data;
+	unsigned int hook_mask = 0;
+
+	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+		const struct nft_base_chain *basechain =
+						nft_base_chain(ctx->chain);
+		const struct nf_hook_ops *ops = &basechain->ops;
+
+		hook_mask = 1 << ops->hooknum;
+		if (hook_mask & target->hooks)
+			return 0;
+
+		/* This target is being called from an invalid chain */
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void nft_match_eval(const struct nft_expr *expr,
+			   struct nft_data data[NFT_REG_MAX + 1],
+			   const struct nft_pktinfo *pkt)
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_match *match = expr->ops->data;
+	struct sk_buff *skb = pkt->skb;
+	bool ret;
+
+	nft_compat_set_par((struct xt_action_param *)&pkt->xt, match, info);
+
+	ret = match->match(skb, (struct xt_action_param *)&pkt->xt);
+
+	if (pkt->xt.hotdrop) {
+		data[NFT_REG_VERDICT].verdict = NF_DROP;
+		return;
+	}
+
+	switch(ret) {
+	case true:
+		data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
+		break;
+	case false:
+		data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+		break;
+	}
+}
+
+static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = {
+	[NFTA_MATCH_NAME]	= { .type = NLA_NUL_STRING },
+	[NFTA_MATCH_REV]	= { .type = NLA_U32 },
+	[NFTA_MATCH_INFO]	= { .type = NLA_BINARY },
+};
+
+/* struct xt_mtchk_param and xt_tgchk_param look very similar */
+static void
+nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
+			  struct xt_match *match, void *info,
+			  union nft_entry *entry, u8 proto, bool inv)
+{
+	par->net	= &init_net;
+	par->table	= ctx->table->name;
+	switch (ctx->afi->family) {
+	case AF_INET:
+		entry->e4.ip.proto = proto;
+		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
+		break;
+	case AF_INET6:
+		entry->e6.ipv6.proto = proto;
+		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
+		break;
+	}
+	par->entryinfo	= entry;
+	par->match	= match;
+	par->matchinfo	= info;
+	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+		const struct nft_base_chain *basechain =
+						nft_base_chain(ctx->chain);
+		const struct nf_hook_ops *ops = &basechain->ops;
+
+		par->hook_mask = 1 << ops->hooknum;
+	}
+	par->family	= ctx->afi->family;
+}
+
+static void match_compat_from_user(struct xt_match *m, void *in, void *out)
+{
+#ifdef CONFIG_COMPAT
+	if (m->compat_from_user) {
+		int pad;
+
+		m->compat_from_user(out, in);
+		pad = XT_ALIGN(m->matchsize) - m->matchsize;
+		if (pad > 0)
+			memset(out + m->matchsize, 0, pad);
+	} else
+#endif
+		memcpy(out, in, XT_ALIGN(m->matchsize));
+}
+
+static int
+nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+		const struct nlattr * const tb[])
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_match *match = expr->ops->data;
+	struct xt_mtchk_param par;
+	size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO]));
+	u8 proto = 0;
+	bool inv = false;
+	union nft_entry e = {};
+	int ret;
+
+	match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info);
+
+	if (ctx->nla[NFTA_RULE_COMPAT])
+		proto = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &inv);
+
+	nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
+
+	ret = xt_check_match(&par, size, proto, inv);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+err:
+	module_put(match->me);
+	return ret;
+}
+
+static void
+nft_match_destroy(const struct nft_expr *expr)
+{
+	struct xt_match *match = expr->ops->data;
+
+	module_put(match->me);
+}
+
+static int
+match_dump_info(struct sk_buff *skb, const struct xt_match *m, const void *in)
+{
+	int ret;
+
+#ifdef CONFIG_COMPAT
+	if (m->compat_to_user) {
+		mm_segment_t old_fs;
+		void *out;
+
+		out = kmalloc(XT_ALIGN(m->matchsize), GFP_ATOMIC);
+		if (out == NULL)
+			return -ENOMEM;
+
+		/* We want to reuse existing compat_to_user */
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		m->compat_to_user(out, in);
+		set_fs(old_fs);
+		ret = nla_put(skb, NFTA_MATCH_INFO, XT_ALIGN(m->matchsize), out);
+		kfree(out);
+	} else
+#endif
+		ret = nla_put(skb, NFTA_MATCH_INFO, XT_ALIGN(m->matchsize), in);
+
+	return ret;
+}
+
+static inline int nft_compat_match_offset(struct xt_match *match)
+{
+#ifdef CONFIG_COMPAT
+	return xt_compat_match_offset(match);
+#else
+	return 0;
+#endif
+}
+
+static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	void *info = nft_expr_priv(expr);
+	struct xt_match *match = expr->ops->data;
+
+	if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) ||
+	    nla_put_be32(skb, NFTA_MATCH_REV, htonl(match->revision)) ||
+	    match_dump_info(skb, match, info))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static int nft_match_validate(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nft_data **data)
+{
+	struct xt_match *match = expr->ops->data;
+	unsigned int hook_mask = 0;
+
+	if (ctx->chain->flags & NFT_BASE_CHAIN) {
+		const struct nft_base_chain *basechain =
+						nft_base_chain(ctx->chain);
+		const struct nf_hook_ops *ops = &basechain->ops;
+
+		hook_mask = 1 << ops->hooknum;
+		if (hook_mask & match->hooks)
+			return 0;
+
+		/* This match is being called from an invalid chain */
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int
+nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
+		      int event, u16 family, const char *name,
+		      int rev, int target)
+{
+	struct nlmsghdr *nlh;
+	struct nfgenmsg *nfmsg;
+	unsigned int flags = portid ? NLM_F_MULTI : 0;
+
+	event |= NFNL_SUBSYS_NFT_COMPAT << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family = family;
+	nfmsg->version = NFNETLINK_V0;
+	nfmsg->res_id = 0;
+
+	if (nla_put_string(skb, NFTA_COMPAT_NAME, name) ||
+	    nla_put_be32(skb, NFTA_COMPAT_REV, htonl(rev)) ||
+	    nla_put_be32(skb, NFTA_COMPAT_TYPE, htonl(target)))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -1;
+}
+
+static int
+nfnl_compat_get(struct sock *nfnl, struct sk_buff *skb,
+		const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+	int ret = 0, target;
+	struct nfgenmsg *nfmsg;
+	const char *fmt;
+	const char *name;
+	u32 rev;
+	struct sk_buff *skb2;
+
+	if (tb[NFTA_COMPAT_NAME] == NULL ||
+	    tb[NFTA_COMPAT_REV] == NULL ||
+	    tb[NFTA_COMPAT_TYPE] == NULL)
+		return -EINVAL;
+
+	name = nla_data(tb[NFTA_COMPAT_NAME]);
+	rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV]));
+	target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE]));
+
+	nfmsg = nlmsg_data(nlh);
+
+	switch(nfmsg->nfgen_family) {
+	case AF_INET:
+		fmt = "ipt_%s";
+		break;
+	case AF_INET6:
+		fmt = "ip6t_%s";
+		break;
+	default:
+		pr_err("nft_compat: unsupported protocol %d\n",
+			nfmsg->nfgen_family);
+		return -EINVAL;
+	}
+
+	try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name,
+						 rev, target, &ret),
+						 fmt, name);
+
+	if (ret < 0)
+		return ret;
+
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL)
+		return -ENOMEM;
+
+	/* include the best revision for this extension in the message */
+	if (nfnl_compat_fill_info(skb2, NETLINK_CB(skb).portid,
+				  nlh->nlmsg_seq,
+				  NFNL_MSG_TYPE(nlh->nlmsg_type),
+				  NFNL_MSG_COMPAT_GET,
+				  nfmsg->nfgen_family,
+				  name, ret, target) <= 0) {
+		kfree_skb(skb2);
+		return -ENOSPC;
+	}
+
+	ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+				MSG_DONTWAIT);
+	if (ret > 0)
+		ret = 0;
+
+	return ret == -EAGAIN ? -ENOBUFS : ret;
+}
+
+static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = {
+	[NFTA_COMPAT_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = NFT_COMPAT_NAME_MAX-1 },
+	[NFTA_COMPAT_REV]	= { .type = NLA_U32 },
+	[NFTA_COMPAT_TYPE]	= { .type = NLA_U32 },
+};
+
+static const struct nfnl_callback nfnl_nft_compat_cb[NFNL_MSG_COMPAT_MAX] = {
+	[NFNL_MSG_COMPAT_GET]		= { .call = nfnl_compat_get,
+					    .attr_count = NFTA_COMPAT_MAX,
+					    .policy = nfnl_compat_policy_get },
+};
+
+static const struct nfnetlink_subsystem nfnl_compat_subsys = {
+	.name		= "nft-compat",
+	.subsys_id	= NFNL_SUBSYS_NFT_COMPAT,
+	.cb_count	= NFNL_MSG_COMPAT_MAX,
+	.cb		= nfnl_nft_compat_cb,
+};
+
+static LIST_HEAD(nft_match_list);
+
+struct nft_xt {
+	struct list_head	head;
+	struct nft_expr_ops	ops;
+};
+
+static struct nft_expr_type nft_match_type;
+
+static const struct nft_expr_ops *
+nft_match_select_ops(const struct nft_ctx *ctx,
+		     const struct nlattr * const tb[])
+{
+	struct nft_xt *nft_match;
+	struct xt_match *match;
+	char *mt_name;
+	__u32 rev, family;
+
+	if (tb[NFTA_MATCH_NAME] == NULL ||
+	    tb[NFTA_MATCH_REV] == NULL ||
+	    tb[NFTA_MATCH_INFO] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	mt_name = nla_data(tb[NFTA_MATCH_NAME]);
+	rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
+	family = ctx->afi->family;
+
+	/* Re-use the existing match if it's already loaded. */
+	list_for_each_entry(nft_match, &nft_match_list, head) {
+		struct xt_match *match = nft_match->ops.data;
+
+		if (strcmp(match->name, mt_name) == 0 &&
+		    match->revision == rev && match->family == family)
+			return &nft_match->ops;
+	}
+
+	match = xt_request_find_match(family, mt_name, rev);
+	if (IS_ERR(match))
+		return ERR_PTR(-ENOENT);
+
+	/* This is the first time we use this match, allocate operations */
+	nft_match = kzalloc(sizeof(struct nft_xt), GFP_KERNEL);
+	if (nft_match == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	nft_match->ops.type = &nft_match_type;
+	nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize) +
+					    nft_compat_match_offset(match));
+	nft_match->ops.eval = nft_match_eval;
+	nft_match->ops.init = nft_match_init;
+	nft_match->ops.destroy = nft_match_destroy;
+	nft_match->ops.dump = nft_match_dump;
+	nft_match->ops.validate = nft_match_validate;
+	nft_match->ops.data = match;
+
+	list_add(&nft_match->head, &nft_match_list);
+
+	return &nft_match->ops;
+}
+
+static void nft_match_release(void)
+{
+	struct nft_xt *nft_match;
+
+	list_for_each_entry(nft_match, &nft_match_list, head)
+		kfree(nft_match);
+}
+
+static struct nft_expr_type nft_match_type __read_mostly = {
+	.name		= "match",
+	.select_ops	= nft_match_select_ops,
+	.policy		= nft_match_policy,
+	.maxattr	= NFTA_MATCH_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static LIST_HEAD(nft_target_list);
+
+static struct nft_expr_type nft_target_type;
+
+static const struct nft_expr_ops *
+nft_target_select_ops(const struct nft_ctx *ctx,
+		      const struct nlattr * const tb[])
+{
+	struct nft_xt *nft_target;
+	struct xt_target *target;
+	char *tg_name;
+	__u32 rev, family;
+
+	if (tb[NFTA_TARGET_NAME] == NULL ||
+	    tb[NFTA_TARGET_REV] == NULL ||
+	    tb[NFTA_TARGET_INFO] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	tg_name = nla_data(tb[NFTA_TARGET_NAME]);
+	rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV]));
+	family = ctx->afi->family;
+
+	/* Re-use the existing target if it's already loaded. */
+	list_for_each_entry(nft_target, &nft_match_list, head) {
+		struct xt_target *target = nft_target->ops.data;
+
+		if (strcmp(target->name, tg_name) == 0 &&
+		    target->revision == rev && target->family == family)
+			return &nft_target->ops;
+	}
+
+	target = xt_request_find_target(family, tg_name, rev);
+	if (IS_ERR(target))
+		return ERR_PTR(-ENOENT);
+
+	/* This is the first time we use this target, allocate operations */
+	nft_target = kzalloc(sizeof(struct nft_xt), GFP_KERNEL);
+	if (nft_target == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	nft_target->ops.type = &nft_target_type;
+	nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize) +
+					     nft_compat_target_offset(target));
+	nft_target->ops.eval = nft_target_eval;
+	nft_target->ops.init = nft_target_init;
+	nft_target->ops.destroy = nft_target_destroy;
+	nft_target->ops.dump = nft_target_dump;
+	nft_target->ops.validate = nft_target_validate;
+	nft_target->ops.data = target;
+
+	list_add(&nft_target->head, &nft_target_list);
+
+	return &nft_target->ops;
+}
+
+static void nft_target_release(void)
+{
+	struct nft_xt *nft_target;
+
+	list_for_each_entry(nft_target, &nft_target_list, head)
+		kfree(nft_target);
+}
+
+static struct nft_expr_type nft_target_type __read_mostly = {
+	.name		= "target",
+	.select_ops	= nft_target_select_ops,
+	.policy		= nft_target_policy,
+	.maxattr	= NFTA_TARGET_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_compat_module_init(void)
+{
+	int ret;
+
+	ret = nft_register_expr(&nft_match_type);
+	if (ret < 0)
+		return ret;
+
+	ret = nft_register_expr(&nft_target_type);
+	if (ret < 0)
+		goto err_match;
+
+	ret = nfnetlink_subsys_register(&nfnl_compat_subsys);
+	if (ret < 0) {
+		pr_err("nft_compat: cannot register with nfnetlink.\n");
+		goto err_target;
+	}
+
+	pr_info("nf_tables_compat: (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>\n");
+
+	return ret;
+
+err_target:
+	nft_unregister_expr(&nft_target_type);
+err_match:
+	nft_unregister_expr(&nft_match_type);
+	return ret;
+}
+
+static void __exit nft_compat_module_exit(void)
+{
+	nfnetlink_subsys_unregister(&nfnl_compat_subsys);
+	nft_unregister_expr(&nft_target_type);
+	nft_unregister_expr(&nft_match_type);
+	nft_match_release();
+	nft_target_release();
+}
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
+
+module_init(nft_compat_module_init);
+module_exit(nft_compat_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_EXPR("match");
+MODULE_ALIAS_NFT_EXPR("target");
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 1bfeeaf865b6..f169501f1ad4 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -90,14 +90,16 @@ nla_put_failure:
 	return -1;
 }
 
-static const struct nft_data *nft_immediate_get_verdict(const struct nft_expr *expr)
+static int nft_immediate_validate(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr,
+				  const struct nft_data **data)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 
 	if (priv->dreg == NFT_REG_VERDICT)
-		return &priv->data;
-	else
-		return NULL;
+		*data = &priv->data;
+
+	return 0;
 }
 
 static struct nft_expr_type nft_imm_type;
@@ -108,7 +110,7 @@ static const struct nft_expr_ops nft_imm_ops = {
 	.init		= nft_immediate_init,
 	.destroy	= nft_immediate_destroy,
 	.dump		= nft_immediate_dump,
-	.get_verdict	= nft_immediate_get_verdict,
+	.validate	= nft_immediate_validate,
 };
 
 static struct nft_expr_type nft_imm_type __read_mostly = {
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 7cf13f7e1e94..bc8bdb2c1ba7 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -107,7 +107,9 @@ const struct nft_expr_ops nft_payload_fast_ops = {
 	.dump		= nft_payload_dump,
 };
 
-static const struct nft_expr_ops *nft_payload_select_ops(const struct nlattr * const tb[])
+static const struct nft_expr_ops *
+nft_payload_select_ops(const struct nft_ctx *ctx,
+		       const struct nlattr * const tb[])
 {
 	enum nft_payload_bases base;
 	unsigned int offset, len;
-- 
cgit 


From 9ddf63235749a9efa1fad2eeb74be2ee9b580f8d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 10 Oct 2013 13:26:33 +0200
Subject: netfilter: nf_tables: add support for dormant tables

This patch allows you to temporarily disable an entire table.
You can change the state of a dormant table via NFT_MSG_NEWTABLE
messages. Using this operation you can wake up a table, so their
chains are registered.

This provides atomicity at chain level. Thus, the rule-set of one
chain is applied at once, avoiding any possible intermediate state
in every chain. Still, the chains that belongs to a table are
registered consecutively. This also allows you to have inactive
tables in the kernel.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 11 ++++
 net/netfilter/nf_tables_api.c            | 97 +++++++++++++++++++++++++++++---
 2 files changed, 101 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 1563875e6942..a9c4bce1988f 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -96,14 +96,25 @@ enum nft_hook_attributes {
 };
 #define NFTA_HOOK_MAX		(__NFTA_HOOK_MAX - 1)
 
+/**
+ * enum nft_table_flags - nf_tables table flags
+ *
+ * @NFT_TABLE_F_DORMANT: this table is not active
+ */
+enum nft_table_flags {
+	NFT_TABLE_F_DORMANT	= 0x1,
+};
+
 /**
  * enum nft_table_attributes - nf_tables table netlink attributes
  *
  * @NFTA_TABLE_NAME: name of the table (NLA_STRING)
+ * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32)
  */
 enum nft_table_attributes {
 	NFTA_TABLE_UNSPEC,
 	NFTA_TABLE_NAME,
+	NFTA_TABLE_FLAGS,
 	__NFTA_TABLE_MAX
 };
 #define NFTA_TABLE_MAX		(__NFTA_TABLE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 61e017b349cb..a4dd7ce5ec3e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -158,6 +158,7 @@ static int nf_tables_chain_type_lookup(const struct nft_af_info *afi,
 
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 	[NFTA_TABLE_NAME]	= { .type = NLA_STRING },
+	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 };
 
 static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
@@ -177,7 +178,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, u32 portid, u32 seq,
 	nfmsg->version		= NFNETLINK_V0;
 	nfmsg->res_id		= 0;
 
-	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name))
+	if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
+	    nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)))
 		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
@@ -301,6 +303,74 @@ err:
 	return err;
 }
 
+static int nf_tables_table_enable(struct nft_table *table)
+{
+	struct nft_chain *chain;
+	int err, i = 0;
+
+	list_for_each_entry(chain, &table->chains, list) {
+		err = nf_register_hook(&nft_base_chain(chain)->ops);
+		if (err < 0)
+			goto err;
+
+		i++;
+	}
+	return 0;
+err:
+	list_for_each_entry(chain, &table->chains, list) {
+		if (i-- <= 0)
+			break;
+
+		nf_unregister_hook(&nft_base_chain(chain)->ops);
+	}
+	return err;
+}
+
+static int nf_tables_table_disable(struct nft_table *table)
+{
+	struct nft_chain *chain;
+
+	list_for_each_entry(chain, &table->chains, list)
+		nf_unregister_hook(&nft_base_chain(chain)->ops);
+
+	return 0;
+}
+
+static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb,
+			      const struct nlmsghdr *nlh,
+			      const struct nlattr * const nla[],
+			      struct nft_af_info *afi, struct nft_table *table)
+{
+	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
+	int family = nfmsg->nfgen_family, ret = 0;
+
+	if (nla[NFTA_TABLE_FLAGS]) {
+		__be32 flags;
+
+		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
+		if (flags & ~NFT_TABLE_F_DORMANT)
+			return -EINVAL;
+
+		if ((flags & NFT_TABLE_F_DORMANT) &&
+		    !(table->flags & NFT_TABLE_F_DORMANT)) {
+			ret = nf_tables_table_disable(table);
+			if (ret >= 0)
+				table->flags |= NFT_TABLE_F_DORMANT;
+		} else if (!(flags & NFT_TABLE_F_DORMANT) &&
+			   table->flags & NFT_TABLE_F_DORMANT) {
+			ret = nf_tables_table_enable(table);
+			if (ret >= 0)
+				table->flags &= ~NFT_TABLE_F_DORMANT;
+		}
+		if (ret < 0)
+			goto err;
+	}
+
+	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+err:
+	return ret;
+}
+
 static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -328,7 +398,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 			return -EEXIST;
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
-		return 0;
+		return nf_tables_updtable(nlsk, skb, nlh, nla, afi, table);
 	}
 
 	table = kzalloc(sizeof(*table) + nla_len(name), GFP_KERNEL);
@@ -339,6 +409,18 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&table->chains);
 	INIT_LIST_HEAD(&table->sets);
 
+	if (nla[NFTA_TABLE_FLAGS]) {
+		__be32 flags;
+
+		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
+		if (flags & ~NFT_TABLE_F_DORMANT) {
+			kfree(table);
+			return -EINVAL;
+		}
+
+		table->flags |= flags;
+	}
+
 	list_add_tail(&table->list, &afi->tables);
 	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
 	return 0;
@@ -890,10 +972,8 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	chain->handle = nf_tables_alloc_handle(table);
 	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
-	list_add_tail(&chain->list, &table->chains);
-	table->use++;
-
-	if (chain->flags & NFT_BASE_CHAIN) {
+	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
+	    chain->flags & NFT_BASE_CHAIN) {
 		err = nf_register_hook(&nft_base_chain(chain)->ops);
 		if (err < 0) {
 			free_percpu(basechain->stats);
@@ -901,6 +981,8 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			return err;
 		}
 	}
+	list_add_tail(&chain->list, &table->chains);
+	table->use++;
 notify:
 	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
 			       family);
@@ -948,7 +1030,8 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	list_del(&chain->list);
 	table->use--;
 
-	if (chain->flags & NFT_BASE_CHAIN)
+	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
+	    chain->flags & NFT_BASE_CHAIN)
 		nf_unregister_hook(&nft_base_chain(chain)->ops);
 
 	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN,
-- 
cgit 


From eb31628e37a0a4e01fffd79dcc7f815d2357f53a Mon Sep 17 00:00:00 2001
From: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
Date: Thu, 10 Oct 2013 13:39:19 +0200
Subject: netfilter: nf_tables: Add support for IPv6 NAT

This patch generalizes the NAT expression to support both IPv4 and IPv6
using the existing IPv4/IPv6 NAT infrastructure. This also adds the
NAT chain type for IPv6.

This patch collapses the following patches that were posted to the
netfilter-devel mailing list, from Tomasz:

* nf_tables: Change NFTA_NAT_ attributes to better semantic significance
* nf_tables: Split IPv4 NAT into NAT expression and IPv4 NAT chain
* nf_tables: Add support for IPv6 NAT expression
* nf_tables: Add support for IPv6 NAT chain
* nf_tables: Fix up build issue on IPv6 NAT support

And, from Pablo Neira Ayuso:

* fix missing dependencies in nft_chain_nat

Signed-off-by: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  18 +--
 net/ipv4/netfilter/Kconfig               |   1 +
 net/ipv4/netfilter/nft_chain_nat_ipv4.c  | 156 +---------------------
 net/ipv6/netfilter/Kconfig               |   5 +
 net/ipv6/netfilter/Makefile              |   1 +
 net/ipv6/netfilter/nft_chain_nat_ipv6.c  | 211 +++++++++++++++++++++++++++++
 net/netfilter/Kconfig                    |   6 +
 net/netfilter/Makefile                   |   1 +
 net/netfilter/nft_nat.c                  | 220 +++++++++++++++++++++++++++++++
 9 files changed, 457 insertions(+), 162 deletions(-)
 create mode 100644 net/ipv6/netfilter/nft_chain_nat_ipv6.c
 create mode 100644 net/netfilter/nft_nat.c

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index a9c4bce1988f..7d4a1992f89c 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -695,18 +695,20 @@ enum nft_nat_types {
  * enum nft_nat_attributes - nf_tables nat expression netlink attributes
  *
  * @NFTA_NAT_TYPE: NAT type (NLA_U32: nft_nat_types)
- * @NFTA_NAT_ADDR_MIN: source register of address range start (NLA_U32: nft_registers)
- * @NFTA_NAT_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
- * @NFTA_NAT_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
- * @NFTA_NAT_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_FAMILY: NAT family (NLA_U32)
+ * @NFTA_NAT_REG_ADDR_MIN: source register of address range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_REG_ADDR_MAX: source register of address range end (NLA_U32: nft_registers)
+ * @NFTA_NAT_REG_PROTO_MIN: source register of proto range start (NLA_U32: nft_registers)
+ * @NFTA_NAT_REG_PROTO_MAX: source register of proto range end (NLA_U32: nft_registers)
  */
 enum nft_nat_attributes {
 	NFTA_NAT_UNSPEC,
 	NFTA_NAT_TYPE,
-	NFTA_NAT_ADDR_MIN,
-	NFTA_NAT_ADDR_MAX,
-	NFTA_NAT_PROTO_MIN,
-	NFTA_NAT_PROTO_MAX,
+	NFTA_NAT_FAMILY,
+	NFTA_NAT_REG_ADDR_MIN,
+	NFTA_NAT_REG_ADDR_MAX,
+	NFTA_NAT_REG_PROTO_MIN,
+	NFTA_NAT_REG_PROTO_MAX,
 	__NFTA_NAT_MAX
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index ae65fe98bfbe..1f37ef67f1ac 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -50,6 +50,7 @@ config NFT_CHAIN_ROUTE_IPV4
 
 config NFT_CHAIN_NAT_IPV4
 	depends on NF_TABLES_IPV4
+	depends on NF_NAT_IPV4 && NFT_NAT
 	tristate "IPv4 nf_tables nat chain support"
 
 config IP_NF_IPTABLES
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index e09c201adf84..cf2c792cd971 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
  * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ * Copyright (c) 2012 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,10 +15,8 @@
 #include <linux/list.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
-#include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_nat.h>
@@ -27,147 +26,6 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/ip.h>
 
-struct nft_nat {
-	enum nft_registers	sreg_addr_min:8;
-	enum nft_registers	sreg_addr_max:8;
-	enum nft_registers	sreg_proto_min:8;
-	enum nft_registers	sreg_proto_max:8;
-	enum nf_nat_manip_type	type;
-};
-
-static void nft_nat_eval(const struct nft_expr *expr,
-			 struct nft_data data[NFT_REG_MAX + 1],
-			 const struct nft_pktinfo *pkt)
-{
-	const struct nft_nat *priv = nft_expr_priv(expr);
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
-	struct nf_nat_range range;
-
-	memset(&range, 0, sizeof(range));
-	if (priv->sreg_addr_min) {
-		range.min_addr.ip = data[priv->sreg_addr_min].data[0];
-		range.max_addr.ip = data[priv->sreg_addr_max].data[0];
-		range.flags |= NF_NAT_RANGE_MAP_IPS;
-	}
-
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = data[priv->sreg_proto_max].data[0];
-		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-
-	data[NFT_REG_VERDICT].verdict =
-		nf_nat_setup_info(ct, &range, priv->type);
-}
-
-static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
-	[NFTA_NAT_ADDR_MIN]	= { .type = NLA_U32 },
-	[NFTA_NAT_ADDR_MAX]	= { .type = NLA_U32 },
-	[NFTA_NAT_PROTO_MIN]	= { .type = NLA_U32 },
-	[NFTA_NAT_PROTO_MAX]	= { .type = NLA_U32 },
-	[NFTA_NAT_TYPE]		= { .type = NLA_U32 },
-};
-
-static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			const struct nlattr * const tb[])
-{
-	struct nft_nat *priv = nft_expr_priv(expr);
-	int err;
-
-	if (tb[NFTA_NAT_TYPE] == NULL)
-		return -EINVAL;
-
-	switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
-	case NFT_NAT_SNAT:
-		priv->type = NF_NAT_MANIP_SRC;
-		break;
-	case NFT_NAT_DNAT:
-		priv->type = NF_NAT_MANIP_DST;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (tb[NFTA_NAT_ADDR_MIN]) {
-		priv->sreg_addr_min = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MIN]));
-		err = nft_validate_input_register(priv->sreg_addr_min);
-		if (err < 0)
-			return err;
-	}
-
-	if (tb[NFTA_NAT_ADDR_MAX]) {
-		priv->sreg_addr_max = ntohl(nla_get_be32(tb[NFTA_NAT_ADDR_MAX]));
-		err = nft_validate_input_register(priv->sreg_addr_max);
-		if (err < 0)
-			return err;
-	} else
-		priv->sreg_addr_max = priv->sreg_addr_min;
-
-	if (tb[NFTA_NAT_PROTO_MIN]) {
-		priv->sreg_proto_min = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MIN]));
-		err = nft_validate_input_register(priv->sreg_proto_min);
-		if (err < 0)
-			return err;
-	}
-
-	if (tb[NFTA_NAT_PROTO_MAX]) {
-		priv->sreg_proto_max = ntohl(nla_get_be32(tb[NFTA_NAT_PROTO_MAX]));
-		err = nft_validate_input_register(priv->sreg_proto_max);
-		if (err < 0)
-			return err;
-	} else
-		priv->sreg_proto_max = priv->sreg_proto_min;
-
-	return 0;
-}
-
-static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
-{
-	const struct nft_nat *priv = nft_expr_priv(expr);
-
-	switch (priv->type) {
-	case NF_NAT_MANIP_SRC:
-		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
-			goto nla_put_failure;
-		break;
-	case NF_NAT_MANIP_DST:
-		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
-			goto nla_put_failure;
-		break;
-	}
-
-	if (nla_put_be32(skb, NFTA_NAT_ADDR_MIN, htonl(priv->sreg_addr_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_ADDR_MAX, htonl(priv->sreg_addr_max)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_PROTO_MIN, htonl(priv->sreg_proto_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_NAT_PROTO_MAX, htonl(priv->sreg_proto_max)))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static struct nft_expr_type nft_nat_type;
-static const struct nft_expr_ops nft_nat_ops = {
-	.type		= &nft_nat_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_nat)),
-	.eval		= nft_nat_eval,
-	.init		= nft_nat_init,
-	.dump		= nft_nat_dump,
-};
-
-static struct nft_expr_type nft_nat_type __read_mostly = {
-	.name		= "nat",
-	.ops		= &nft_nat_ops,
-	.policy		= nft_nat_policy,
-	.maxattr	= NFTA_NAT_MAX,
-	.owner		= THIS_MODULE,
-};
-
 /*
  * NAT chains
  */
@@ -306,7 +164,7 @@ static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
 	return ret;
 }
 
-struct nf_chain_type nft_chain_nat_ipv4 = {
+static struct nf_chain_type nft_chain_nat_ipv4 = {
 	.family		= NFPROTO_IPV4,
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,
@@ -331,20 +189,11 @@ static int __init nft_chain_nat_init(void)
 	if (err < 0)
 		return err;
 
-	err = nft_register_expr(&nft_nat_type);
-	if (err < 0)
-		goto err;
-
 	return 0;
-
-err:
-	nft_unregister_chain_type(&nft_chain_nat_ipv4);
-	return err;
 }
 
 static void __exit nft_chain_nat_exit(void)
 {
-	nft_unregister_expr(&nft_nat_type);
 	nft_unregister_chain_type(&nft_chain_nat_ipv4);
 }
 
@@ -354,4 +203,3 @@ module_exit(nft_chain_nat_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
-MODULE_ALIAS_NFT_EXPR("nat");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 23833064b7b5..7702f9e90a04 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -33,6 +33,11 @@ config NFT_CHAIN_ROUTE_IPV6
 	depends on NF_TABLES_IPV6
 	tristate "IPv6 nf_tables route chain support"
 
+config NFT_CHAIN_NAT_IPV6
+	depends on NF_TABLES_IPV6
+	depends on NF_NAT_IPV6 && NFT_NAT
+	tristate "IPv6 nf_tables nat chain support"
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index be4913aa524d..d1b4928f34f7 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 # nf_tables
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
+obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
new file mode 100644
index 000000000000..e86dcd70dc76
--- /dev/null
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/ipv6.h>
+
+/*
+ * IPv6 NAT chains
+ */
+
+static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
+			      struct sk_buff *skb,
+			      const struct net_device *in,
+			      const struct net_device *out,
+			      int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+	__be16 frag_off;
+	int hdrlen;
+	u8 nexthdr;
+	struct nft_pktinfo pkt;
+	unsigned int ret;
+
+	if (ct == NULL || nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nfct_nat(ct);
+	if (nat == NULL) {
+		/* Conntrack module was loaded late, can't add extension. */
+		if (nf_ct_is_confirmed(ct))
+			return NF_ACCEPT;
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+		if (nat == NULL)
+			return NF_ACCEPT;
+	}
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED + IP_CT_IS_REPLY:
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+					  &nexthdr, &frag_off);
+
+		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
+							   ops->hooknum,
+							   hdrlen))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall through */
+	case IP_CT_NEW:
+		if (nf_nat_initialized(ct, maniptype))
+			break;
+
+		nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out);
+
+		ret = nft_do_chain_pktinfo(&pkt, ops);
+		if (ret != NF_ACCEPT)
+			return ret;
+		if (!nf_nat_initialized(ct, maniptype)) {
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		}
+	default:
+		break;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+}
+
+static unsigned int nf_nat_ipv6_prerouting(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+	unsigned int ret;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+
+static unsigned int nf_nat_ipv6_postrouting(const struct nf_hook_ops *ops,
+				       struct sk_buff *skb,
+				       const struct net_device *in,
+				       const struct net_device *out,
+				       int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo __maybe_unused;
+	const struct nf_conn *ct __maybe_unused;
+	unsigned int ret;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
+				      &ct->tuplehash[!dir].tuple.dst.u3) ||
+		    (ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all))
+			if (nf_xfrm_me_harder(skb, AF_INET6) < 0)
+				ret = NF_DROP;
+	}
+#endif
+	return ret;
+}
+
+static unsigned int nf_nat_ipv6_output(const struct nf_hook_ops *ops,
+				  struct sk_buff *skb,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  int (*okfn)(struct sk_buff *))
+{
+	enum ip_conntrack_info ctinfo;
+	const struct nf_conn *ct;
+	unsigned int ret;
+
+	ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+				      &ct->tuplehash[!dir].tuple.src.u3)) {
+			if (ip6_route_me_harder(skb))
+				ret = NF_DROP;
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all)
+			if (nf_xfrm_me_harder(skb, AF_INET6))
+				ret = NF_DROP;
+#endif
+	}
+	return ret;
+}
+
+static struct nf_chain_type nft_chain_nat_ipv6 = {
+	.family		= NFPROTO_IPV6,
+	.name		= "nat",
+	.type		= NFT_CHAIN_T_NAT,
+	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.fn		= {
+		[NF_INET_PRE_ROUTING]	= nf_nat_ipv6_prerouting,
+		[NF_INET_POST_ROUTING]	= nf_nat_ipv6_postrouting,
+		[NF_INET_LOCAL_OUT]	= nf_nat_ipv6_output,
+		[NF_INET_LOCAL_IN]	= nf_nat_ipv6_fn,
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init nft_chain_nat_ipv6_init(void)
+{
+	int err;
+
+	err = nft_register_chain_type(&nft_chain_nat_ipv6);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static void __exit nft_chain_nat_ipv6_exit(void)
+{
+	nft_unregister_chain_type(&nft_chain_nat_ipv6);
+}
+
+module_init(nft_chain_nat_ipv6_init);
+module_exit(nft_chain_nat_ipv6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
+MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 49e362707379..48acec17e27a 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -450,6 +450,12 @@ config NFT_LIMIT
 	depends on NF_TABLES
 	tristate "Netfilter nf_tables limit module"
 
+config NFT_NAT
+	depends on NF_TABLES
+	depends on NF_CONNTRACK
+	depends on NF_NAT
+	tristate "Netfilter nf_tables nat module"
+
 config NFT_COMPAT
 	depends on NF_TABLES
 	depends on NETFILTER_XTABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a6781450b6fb..394483b2c193 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -75,6 +75,7 @@ obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
 obj-$(CONFIG_NFT_META)		+= nft_meta.o
 obj-$(CONFIG_NFT_CT)		+= nft_ct.o
 obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
+obj-$(CONFIG_NFT_NAT)		+= nft_nat.o
 #nf_tables-objs			+= nft_meta_target.o
 obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
new file mode 100644
index 000000000000..b0b87b2d2411
--- /dev/null
+++ b/net/netfilter/nft_nat.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ * Copyright (c) 2012 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/string.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/ip.h>
+
+struct nft_nat {
+	enum nft_registers      sreg_addr_min:8;
+	enum nft_registers      sreg_addr_max:8;
+	enum nft_registers      sreg_proto_min:8;
+	enum nft_registers      sreg_proto_max:8;
+	int                     family;
+	enum nf_nat_manip_type  type;
+};
+
+static void nft_nat_eval(const struct nft_expr *expr,
+			 struct nft_data data[NFT_REG_MAX + 1],
+			 const struct nft_pktinfo *pkt)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo);
+	struct nf_nat_range range;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_addr_min) {
+		if (priv->family == AF_INET) {
+			range.min_addr.ip = data[priv->sreg_addr_min].data[0];
+			range.max_addr.ip = data[priv->sreg_addr_max].data[0];
+
+		} else {
+			memcpy(range.min_addr.ip6,
+			       data[priv->sreg_addr_min].data,
+			       sizeof(struct nft_data));
+			memcpy(range.max_addr.ip6,
+			       data[priv->sreg_addr_max].data,
+			       sizeof(struct nft_data));
+		}
+		range.flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = data[priv->sreg_proto_min].data[0];
+		range.max_proto.all = data[priv->sreg_proto_max].data[0];
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	data[NFT_REG_VERDICT].verdict =
+		nf_nat_setup_info(ct, &range, priv->type);
+}
+
+static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
+	[NFTA_NAT_TYPE]		 = { .type = NLA_U32 },
+	[NFTA_NAT_FAMILY]	 = { .type = NLA_U32 },
+	[NFTA_NAT_REG_ADDR_MIN]	 = { .type = NLA_U32 },
+	[NFTA_NAT_REG_ADDR_MAX]	 = { .type = NLA_U32 },
+	[NFTA_NAT_REG_PROTO_MIN] = { .type = NLA_U32 },
+	[NFTA_NAT_REG_PROTO_MAX] = { .type = NLA_U32 },
+};
+
+static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_NAT_TYPE] == NULL)
+		return -EINVAL;
+
+	switch (ntohl(nla_get_be32(tb[NFTA_NAT_TYPE]))) {
+	case NFT_NAT_SNAT:
+		priv->type = NF_NAT_MANIP_SRC;
+		break;
+	case NFT_NAT_DNAT:
+		priv->type = NF_NAT_MANIP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (tb[NFTA_NAT_FAMILY] == NULL)
+		return -EINVAL;
+
+	priv->family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
+	if (priv->family != AF_INET && priv->family != AF_INET6)
+		return -EINVAL;
+
+	if (tb[NFTA_NAT_REG_ADDR_MIN]) {
+		priv->sreg_addr_min = ntohl(nla_get_be32(
+						tb[NFTA_NAT_REG_ADDR_MIN]));
+		err = nft_validate_input_register(priv->sreg_addr_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_REG_ADDR_MAX]) {
+		priv->sreg_addr_max = ntohl(nla_get_be32(
+						tb[NFTA_NAT_REG_ADDR_MAX]));
+		err = nft_validate_input_register(priv->sreg_addr_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_addr_max = priv->sreg_addr_min;
+
+	if (tb[NFTA_NAT_REG_PROTO_MIN]) {
+		priv->sreg_proto_min = ntohl(nla_get_be32(
+						tb[NFTA_NAT_REG_PROTO_MIN]));
+		err = nft_validate_input_register(priv->sreg_proto_min);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_NAT_REG_PROTO_MAX]) {
+		priv->sreg_proto_max = ntohl(nla_get_be32(
+						tb[NFTA_NAT_REG_PROTO_MAX]));
+		err = nft_validate_input_register(priv->sreg_proto_max);
+		if (err < 0)
+			return err;
+	} else
+		priv->sreg_proto_max = priv->sreg_proto_min;
+
+	return 0;
+}
+
+static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NF_NAT_MANIP_SRC:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_SNAT)))
+			goto nla_put_failure;
+		break;
+	case NF_NAT_MANIP_DST:
+		if (nla_put_be32(skb, NFTA_NAT_TYPE, htonl(NFT_NAT_DNAT)))
+			goto nla_put_failure;
+		break;
+	}
+
+	if (nla_put_be32(skb, NFTA_NAT_FAMILY, htonl(priv->family)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb,
+			 NFTA_NAT_REG_ADDR_MIN, htonl(priv->sreg_addr_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb,
+			 NFTA_NAT_REG_ADDR_MAX, htonl(priv->sreg_addr_max)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb,
+			 NFTA_NAT_REG_PROTO_MIN, htonl(priv->sreg_proto_min)))
+		goto nla_put_failure;
+	if (nla_put_be32(skb,
+			 NFTA_NAT_REG_PROTO_MAX, htonl(priv->sreg_proto_max)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_nat_type;
+static const struct nft_expr_ops nft_nat_ops = {
+	.type           = &nft_nat_type,
+	.size           = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+	.eval           = nft_nat_eval,
+	.init           = nft_nat_init,
+	.dump           = nft_nat_dump,
+};
+
+static struct nft_expr_type nft_nat_type __read_mostly = {
+	.name           = "nat",
+	.ops            = &nft_nat_ops,
+	.policy         = nft_nat_policy,
+	.maxattr        = NFTA_NAT_MAX,
+	.owner          = THIS_MODULE,
+};
+
+static int __init nft_nat_module_init(void)
+{
+	int err;
+
+	err = nft_register_expr(&nft_nat_type);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static void __exit nft_nat_module_exit(void)
+{
+	nft_unregister_expr(&nft_nat_type);
+}
+
+module_init(nft_nat_module_init);
+module_exit(nft_nat_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
+MODULE_ALIAS_NFT_EXPR("nat");
-- 
cgit 


From 99633ab29b2131b68089a6c7f60458390860e044 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 10 Oct 2013 23:28:33 +0200
Subject: netfilter: nf_tables: complete net namespace support

Register family per netnamespace to ensure that sets are
only visible in its approapriate namespace.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/net_namespace.h             |  4 ++
 include/net/netfilter/nf_tables.h       |  4 +-
 include/net/netns/nftables.h            | 15 ++++++
 net/bridge/netfilter/nf_tables_bridge.c | 32 ++++++++++++-
 net/ipv4/netfilter/nf_tables_ipv4.c     | 32 ++++++++++++-
 net/ipv6/netfilter/nf_tables_ipv6.c     | 33 ++++++++++++-
 net/netfilter/nf_tables_api.c           | 83 ++++++++++++++++++++++-----------
 7 files changed, 168 insertions(+), 35 deletions(-)
 create mode 100644 include/net/netns/nftables.h

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index bcc4a8ed4450..da68c9a90ac5 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -22,6 +22,7 @@
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netns/conntrack.h>
 #endif
+#include <net/netns/nftables.h>
 #include <net/netns/xfrm.h>
 
 struct user_namespace;
@@ -101,6 +102,9 @@ struct net {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct netns_ct		ct;
 #endif
+#if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE)
+	struct netns_nftables	nft;
+#endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	struct netns_nf_frag	nf_frag;
 #endif
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index a68f45f0fe2e..d3272e943aac 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -68,6 +68,7 @@ static inline void nft_data_debug(const struct nft_data *data)
 /**
  *	struct nft_ctx - nf_tables rule/set context
  *
+ *	@net: net namespace
  * 	@skb: netlink skb
  * 	@nlh: netlink message header
  * 	@afi: address family info
@@ -76,6 +77,7 @@ static inline void nft_data_debug(const struct nft_data *data)
  *	@nla: netlink attributes
  */
 struct nft_ctx {
+	struct net			*net;
 	const struct sk_buff		*skb;
 	const struct nlmsghdr		*nlh;
 	const struct nft_af_info	*afi;
@@ -462,7 +464,7 @@ struct nft_af_info {
 	nf_hookfn			*hooks[NF_MAX_HOOKS];
 };
 
-extern int nft_register_afinfo(struct nft_af_info *);
+extern int nft_register_afinfo(struct net *, struct nft_af_info *);
 extern void nft_unregister_afinfo(struct nft_af_info *);
 
 struct nf_chain_type {
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
new file mode 100644
index 000000000000..a98b1c5d9913
--- /dev/null
+++ b/include/net/netns/nftables.h
@@ -0,0 +1,15 @@
+#ifndef _NETNS_NFTABLES_H_
+#define _NETNS_NFTABLES_H_
+
+#include <linux/list.h>
+
+struct nft_af_info;
+
+struct netns_nftables {
+	struct list_head	af_info;
+	struct nft_af_info	*ipv4;
+	struct nft_af_info	*ipv6;
+	struct nft_af_info	*bridge;
+};
+
+#endif
diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c
index bc5c21c911c0..e8cb016fa34d 100644
--- a/net/bridge/netfilter/nf_tables_bridge.c
+++ b/net/bridge/netfilter/nf_tables_bridge.c
@@ -19,14 +19,42 @@ static struct nft_af_info nft_af_bridge __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
+static int nf_tables_bridge_init_net(struct net *net)
+{
+	net->nft.bridge = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.bridge == NULL)
+		return -ENOMEM;
+
+	memcpy(net->nft.bridge, &nft_af_bridge, sizeof(nft_af_bridge));
+
+	if (nft_register_afinfo(net, net->nft.bridge) < 0)
+		goto err;
+
+	return 0;
+err:
+	kfree(net->nft.bridge);
+	return -ENOMEM;
+}
+
+static void nf_tables_bridge_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.bridge);
+	kfree(net->nft.bridge);
+}
+
+static struct pernet_operations nf_tables_bridge_net_ops = {
+	.init	= nf_tables_bridge_init_net,
+	.exit	= nf_tables_bridge_exit_net,
+};
+
 static int __init nf_tables_bridge_init(void)
 {
-	return nft_register_afinfo(&nft_af_bridge);
+	return register_pernet_subsys(&nf_tables_bridge_net_ops);
 }
 
 static void __exit nf_tables_bridge_exit(void)
 {
-	nft_unregister_afinfo(&nft_af_bridge);
+	return unregister_pernet_subsys(&nf_tables_bridge_net_ops);
 }
 
 module_init(nf_tables_bridge_init);
diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c
index c61cffb9b760..8f7536be1322 100644
--- a/net/ipv4/netfilter/nf_tables_ipv4.c
+++ b/net/ipv4/netfilter/nf_tables_ipv4.c
@@ -14,6 +14,7 @@
 #include <linux/ip.h>
 #include <linux/netfilter_ipv4.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/net_namespace.h>
 #include <net/netfilter/nf_tables_ipv4.h>
@@ -47,6 +48,33 @@ static struct nft_af_info nft_af_ipv4 __read_mostly = {
 	},
 };
 
+static int nf_tables_ipv4_init_net(struct net *net)
+{
+	net->nft.ipv4 = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.ipv4 == NULL)
+		return -ENOMEM;
+
+	memcpy(net->nft.ipv4, &nft_af_ipv4, sizeof(nft_af_ipv4));
+
+	if (nft_register_afinfo(net, net->nft.ipv4) < 0)
+		goto err;
+
+	return 0;
+err:
+	kfree(net->nft.ipv4);
+	return -ENOMEM;
+}
+
+static void nf_tables_ipv4_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.ipv4);
+	kfree(net->nft.ipv4);
+}
+
+static struct pernet_operations nf_tables_ipv4_net_ops = {
+	.init	= nf_tables_ipv4_init_net,
+	.exit	= nf_tables_ipv4_exit_net,
+};
 
 static unsigned int
 nft_do_chain_ipv4(const struct nf_hook_ops *ops,
@@ -83,12 +111,12 @@ static struct nf_chain_type filter_ipv4 = {
 static int __init nf_tables_ipv4_init(void)
 {
 	nft_register_chain_type(&filter_ipv4);
-	return nft_register_afinfo(&nft_af_ipv4);
+	return register_pernet_subsys(&nf_tables_ipv4_net_ops);
 }
 
 static void __exit nf_tables_ipv4_exit(void)
 {
-	nft_unregister_afinfo(&nft_af_ipv4);
+	unregister_pernet_subsys(&nf_tables_ipv4_net_ops);
 	nft_unregister_chain_type(&filter_ipv4);
 }
 
diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 42f905a808a3..d77db8a13505 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -45,6 +45,34 @@ static struct nft_af_info nft_af_ipv6 __read_mostly = {
 	},
 };
 
+static int nf_tables_ipv6_init_net(struct net *net)
+{
+	net->nft.ipv6 = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.ipv6 == NULL)
+		return -ENOMEM;
+
+	memcpy(net->nft.ipv6, &nft_af_ipv6, sizeof(nft_af_ipv6));
+
+	if (nft_register_afinfo(net, net->nft.ipv6) < 0)
+		goto err;
+
+	return 0;
+err:
+	kfree(net->nft.ipv6);
+	return -ENOMEM;
+}
+
+static void nf_tables_ipv6_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.ipv6);
+	kfree(net->nft.ipv6);
+}
+
+static struct pernet_operations nf_tables_ipv6_net_ops = {
+	.init	= nf_tables_ipv6_init_net,
+	.exit	= nf_tables_ipv6_exit_net,
+};
+
 static unsigned int
 nft_do_chain_ipv6(const struct nf_hook_ops *ops,
 		  struct sk_buff *skb,
@@ -82,11 +110,12 @@ static struct nf_chain_type filter_ipv6 = {
 static int __init nf_tables_ipv6_init(void)
 {
 	nft_register_chain_type(&filter_ipv6);
-	return nft_register_afinfo(&nft_af_ipv6);
+	return register_pernet_subsys(&nf_tables_ipv6_net_ops);
 }
+
 static void __exit nf_tables_ipv6_exit(void)
 {
-	nft_unregister_afinfo(&nft_af_ipv6);
+	unregister_pernet_subsys(&nf_tables_ipv6_net_ops);
 	nft_unregister_chain_type(&filter_ipv6);
 }
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a4dd7ce5ec3e..e1ee85047ec1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -18,9 +18,9 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/net_namespace.h>
 #include <net/sock.h>
 
-static LIST_HEAD(nf_tables_afinfo);
 static LIST_HEAD(nf_tables_expressions);
 
 /**
@@ -31,11 +31,11 @@ static LIST_HEAD(nf_tables_expressions);
  *	Register the address family for use with nf_tables. Returns zero on
  *	success or a negative errno code otherwise.
  */
-int nft_register_afinfo(struct nft_af_info *afi)
+int nft_register_afinfo(struct net *net, struct nft_af_info *afi)
 {
 	INIT_LIST_HEAD(&afi->tables);
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&afi->list, &nf_tables_afinfo);
+	list_add_tail(&afi->list, &net->nft.af_info);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -56,22 +56,23 @@ void nft_unregister_afinfo(struct nft_af_info *afi)
 }
 EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
 
-static struct nft_af_info *nft_afinfo_lookup(int family)
+static struct nft_af_info *nft_afinfo_lookup(struct net *net, int family)
 {
 	struct nft_af_info *afi;
 
-	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+	list_for_each_entry(afi, &net->nft.af_info, list) {
 		if (afi->family == family)
 			return afi;
 	}
 	return NULL;
 }
 
-static struct nft_af_info *nf_tables_afinfo_lookup(int family, bool autoload)
+static struct nft_af_info *
+nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
 {
 	struct nft_af_info *afi;
 
-	afi = nft_afinfo_lookup(family);
+	afi = nft_afinfo_lookup(net, family);
 	if (afi != NULL)
 		return afi;
 #ifdef CONFIG_MODULES
@@ -79,7 +80,7 @@ static struct nft_af_info *nf_tables_afinfo_lookup(int family, bool autoload)
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		request_module("nft-afinfo-%u", family);
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		afi = nft_afinfo_lookup(family);
+		afi = nft_afinfo_lookup(net, family);
 		if (afi != NULL)
 			return ERR_PTR(-EAGAIN);
 	}
@@ -232,9 +233,10 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 	const struct nft_af_info *afi;
 	const struct nft_table *table;
 	unsigned int idx = 0, s_idx = cb->args[0];
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+	list_for_each_entry(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
@@ -268,6 +270,7 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_af_info *afi;
 	const struct nft_table *table;
 	struct sk_buff *skb2;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	int err;
 
@@ -278,7 +281,7 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 		return netlink_dump_start(nlsk, skb, nlh, &c);
 	}
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -379,9 +382,10 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	const struct nlattr *name;
 	struct nft_af_info *afi;
 	struct nft_table *table;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	afi = nf_tables_afinfo_lookup(family, true);
+	afi = nf_tables_afinfo_lookup(net, family, true);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -433,9 +437,10 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct nft_af_info *afi;
 	struct nft_table *table;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -663,9 +668,10 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 	const struct nft_table *table;
 	const struct nft_chain *chain;
 	unsigned int idx = 0, s_idx = cb->args[0];
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+	list_for_each_entry(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
@@ -702,6 +708,7 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_table *table;
 	const struct nft_chain *chain;
 	struct sk_buff *skb2;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	int err;
 
@@ -712,7 +719,7 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 		return netlink_dump_start(nlsk, skb, nlh, &c);
 	}
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -813,6 +820,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_chain *chain;
 	struct nft_base_chain *basechain = NULL;
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	u64 handle = 0;
 	int err;
@@ -820,7 +828,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
-	afi = nf_tables_afinfo_lookup(family, true);
+	afi = nf_tables_afinfo_lookup(net, family, true);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1010,9 +1018,10 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1050,6 +1059,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 			 const struct nft_chain *chain,
 			 const struct nlattr * const *nla)
 {
+	ctx->net   = sock_net(skb->sk);
 	ctx->skb   = skb;
 	ctx->nlh   = nlh;
 	ctx->afi   = afi;
@@ -1361,9 +1371,10 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 	const struct nft_chain *chain;
 	const struct nft_rule *rule;
 	unsigned int idx = 0, s_idx = cb->args[0];
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &nf_tables_afinfo, list) {
+	list_for_each_entry(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
@@ -1402,6 +1413,7 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_chain *chain;
 	const struct nft_rule *rule;
 	struct sk_buff *skb2;
+	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	int err;
 
@@ -1412,7 +1424,7 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 		return netlink_dump_start(nlsk, skb, nlh, &c);
 	}
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1477,6 +1489,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_af_info *afi;
+	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
@@ -1490,7 +1503,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
-	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, create);
+	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1585,12 +1598,13 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_af_info *afi;
+	struct net *net = sock_net(skb->sk);
 	const struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *tmp;
 	int family = nfmsg->nfgen_family;
 
-	afi = nf_tables_afinfo_lookup(family, false);
+	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1697,11 +1711,12 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 				     const struct nlmsghdr *nlh,
 				     const struct nlattr * const nla[])
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_af_info *afi;
 	const struct nft_table *table = NULL;
 
-	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, false);
+	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -1818,12 +1833,11 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 {
 	struct sk_buff *skb;
 	u32 portid = NETLINK_CB(ctx->skb).portid;
-	struct net *net = sock_net(ctx->skb->sk);
 	bool report;
 	int err;
 
 	report = nlmsg_report(ctx->nlh);
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -1837,11 +1851,11 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
+	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, report,
 			     GFP_KERNEL);
 err:
 	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+		nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, err);
 	return err;
 }
 
@@ -1974,6 +1988,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_set_ops *ops;
 	const struct nft_af_info *afi;
+	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_set *set;
 	struct nft_ctx ctx;
@@ -2032,7 +2047,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
-	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, create);
+	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -2219,8 +2234,9 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_af_info *afi;
 	const struct nft_table *table;
+	struct net *net = sock_net(skb->sk);
 
-	afi = nf_tables_afinfo_lookup(nfmsg->nfgen_family, false);
+	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
 	if (IS_ERR(afi))
 		return PTR_ERR(afi);
 
@@ -3011,6 +3027,16 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
 }
 EXPORT_SYMBOL_GPL(nft_data_dump);
 
+static int nf_tables_init_net(struct net *net)
+{
+	INIT_LIST_HEAD(&net->nft.af_info);
+	return 0;
+}
+
+static struct pernet_operations nf_tables_net_ops = {
+	.init	= nf_tables_init_net,
+};
+
 static int __init nf_tables_module_init(void)
 {
 	int err;
@@ -3031,7 +3057,7 @@ static int __init nf_tables_module_init(void)
 		goto err3;
 
 	pr_info("nf_tables: (c) 2007-2009 Patrick McHardy <kaber@trash.net>\n");
-	return 0;
+	return register_pernet_subsys(&nf_tables_net_ops);
 err3:
 	nf_tables_core_module_exit();
 err2:
@@ -3042,6 +3068,7 @@ err1:
 
 static void __exit nf_tables_module_exit(void)
 {
+	unregister_pernet_subsys(&nf_tables_net_ops);
 	nfnetlink_subsys_unregister(&nf_tables_subsys);
 	nf_tables_core_module_exit();
 	kfree(info);
-- 
cgit 


From 5e94846686d027a4c8ecc5d9d52b18036d3e8f7a Mon Sep 17 00:00:00 2001
From: Eric Leblond <eric@regit.org>
Date: Thu, 10 Oct 2013 13:41:44 +0200
Subject: netfilter: nf_tables: add insert operation

This patch adds a new rule attribute NFTA_RULE_POSITION which is
used to store the position of a rule relatively to the others.
By providing the create command and specifying the position, the
rule is inserted after the rule with the handle equal to the
provided position.

Regarding notification, the position attribute specifies the
handle of the previous rule to make sure we don't point to any
stale rule in notifications coming from the commit path.

This patch includes the following fix from Pablo:

* nf_tables: fix rule deletion event reporting

Signed-off-by: Eric Leblond <eric@regit.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 38 +++++++++++++++++++++++++++-----
 2 files changed, 34 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 7d4a1992f89c..fbfd229a8e99 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -153,6 +153,7 @@ enum nft_chain_attributes {
  * @NFTA_RULE_HANDLE: numeric handle of the rule (NLA_U64)
  * @NFTA_RULE_EXPRESSIONS: list of expressions (NLA_NESTED: nft_expr_attributes)
  * @NFTA_RULE_COMPAT: compatibility specifications of the rule (NLA_NESTED: nft_rule_compat_attributes)
+ * @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64)
  */
 enum nft_rule_attributes {
 	NFTA_RULE_UNSPEC,
@@ -161,6 +162,7 @@ enum nft_rule_attributes {
 	NFTA_RULE_HANDLE,
 	NFTA_RULE_EXPRESSIONS,
 	NFTA_RULE_COMPAT,
+	NFTA_RULE_POSITION,
 	__NFTA_RULE_MAX
 };
 #define NFTA_RULE_MAX		(__NFTA_RULE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index e1ee85047ec1..0f140663ec71 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1273,6 +1273,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 	[NFTA_RULE_HANDLE]	= { .type = NLA_U64 },
 	[NFTA_RULE_EXPRESSIONS]	= { .type = NLA_NESTED },
 	[NFTA_RULE_COMPAT]	= { .type = NLA_NESTED },
+	[NFTA_RULE_POSITION]	= { .type = NLA_U64 },
 };
 
 static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1285,9 +1286,10 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
 	struct nfgenmsg *nfmsg;
 	const struct nft_expr *expr, *next;
 	struct nlattr *list;
+	const struct nft_rule *prule;
+	int type = event | NFNL_SUBSYS_NFTABLES << 8;
 
-	event |= NFNL_SUBSYS_NFTABLES << 8;
-	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+	nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg),
 			flags);
 	if (nlh == NULL)
 		goto nla_put_failure;
@@ -1304,6 +1306,13 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq,
 	if (nla_put_be64(skb, NFTA_RULE_HANDLE, cpu_to_be64(rule->handle)))
 		goto nla_put_failure;
 
+	if ((event != NFT_MSG_DELRULE) && (rule->list.prev != &chain->rules)) {
+		prule = list_entry(rule->list.prev, struct nft_rule, list);
+		if (nla_put_be64(skb, NFTA_RULE_POSITION,
+				 cpu_to_be64(prule->handle)))
+			goto nla_put_failure;
+	}
+
 	list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS);
 	if (list == NULL)
 		goto nla_put_failure;
@@ -1499,7 +1508,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	unsigned int size, i, n;
 	int err, rem;
 	bool create;
-	u64 handle;
+	u64 handle, pos_handle;
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
@@ -1533,6 +1542,16 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		handle = nf_tables_alloc_handle(table);
 	}
 
+	if (nla[NFTA_RULE_POSITION]) {
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
+			return -EOPNOTSUPP;
+
+		pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
+		old_rule = __nf_tables_rule_lookup(chain, pos_handle);
+		if (IS_ERR(old_rule))
+			return PTR_ERR(old_rule);
+	}
+
 	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
 
 	n = 0;
@@ -1573,9 +1592,16 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		list_replace_rcu(&old_rule->list, &rule->list);
 		nf_tables_rule_destroy(old_rule);
 	} else if (nlh->nlmsg_flags & NLM_F_APPEND)
-		list_add_tail_rcu(&rule->list, &chain->rules);
-	else
-		list_add_rcu(&rule->list, &chain->rules);
+		if (old_rule)
+			list_add_rcu(&rule->list, &old_rule->list);
+		else
+			list_add_tail_rcu(&rule->list, &chain->rules);
+	else {
+		if (old_rule)
+			list_add_tail_rcu(&rule->list, &old_rule->list);
+		else
+			list_add_rcu(&rule->list, &chain->rules);
+	}
 
 	nf_tables_rule_notify(skb, nlh, table, chain, rule, NFT_MSG_NEWRULE,
 			      nlh->nlmsg_flags & (NLM_F_APPEND | NLM_F_REPLACE),
-- 
cgit 


From 0628b123c96d126e617beb3b4fd63b874d0e4f17 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 14 Oct 2013 11:05:33 +0200
Subject: netfilter: nfnetlink: add batch support and use it from nf_tables

This patch adds a batch support to nfnetlink. Basically, it adds
two new control messages:

* NFNL_MSG_BATCH_BEGIN, that indicates the beginning of a batch,
  the nfgenmsg->res_id indicates the nfnetlink subsystem ID.

* NFNL_MSG_BATCH_END, that results in the invocation of the
  ss->commit callback function. If not specified or an error
  ocurred in the batch, the ss->abort function is invoked
  instead.

The end message represents the commit operation in nftables, the
lack of end message results in an abort. This patch also adds the
.call_batch function that is only called from the batch receival
path.

This patch adds atomic rule updates and dumps based on
bitmask generations. This allows to atomically commit a set of
rule-set updates incrementally without altering the internal
state of existing nf_tables expressions/matches/targets.

The idea consists of using a generation cursor of 1 bit and
a bitmask of 2 bits per rule. Assuming the gencursor is 0,
then the genmask (expressed as a bitmask) can be interpreted
as:

00 active in the present, will be active in the next generation.
01 inactive in the present, will be active in the next generation.
10 active in the present, will be deleted in the next generation.
 ^
 gencursor

Once you invoke the transition to the next generation, the global
gencursor is updated:

00 active in the present, will be active in the next generation.
01 active in the present, needs to zero its future, it becomes 00.
10 inactive in the present, delete now.
^
gencursor

If a dump is in progress and nf_tables enters a new generation,
the dump will stop and return -EBUSY to let userspace know that
it has to retry again. In order to invalidate dumps, a global
genctr counter is increased everytime nf_tables enters a new
generation.

This new operation can be used from the user-space utility
that controls the firewall, eg.

nft -f restore

The rule updates contained in `file' will be applied atomically.

cat file
-----
add filter INPUT ip saddr 1.1.1.1 counter accept #1
del filter INPUT ip daddr 2.2.2.2 counter drop   #2
-EOF-

Note that the rule 1 will be inactive until the transition to the
next generation, the rule 2 will be evicted in the next generation.

There is a penalty during the rule update due to the branch
misprediction in the packet matching framework. But that should be
quickly resolved once the iteration over the commit list that
contain rules that require updates is finished.

Event notification happens once the rule-set update has been
committed. So we skip notifications is case the rule-set update
is aborted, which can happen in case that the rule-set is tested
to apply correctly.

This patch squashed the following patches from Pablo:

* nf_tables: atomic rule updates and dumps
* nf_tables: get rid of per rule list_head for commits
* nf_tables: use per netns commit list
* nfnetlink: add batch support and use it from nf_tables
* nf_tables: all rule updates are transactional
* nf_tables: attach replacement rule after stale one
* nf_tables: do not allow deletion/replacement of stale rules
* nf_tables: remove unused NFTA_RULE_FLAGS

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink.h      |   5 +
 include/net/netfilter/nf_tables.h        |  25 +++-
 include/net/netns/nftables.h             |   3 +
 include/uapi/linux/netfilter/nfnetlink.h |   4 +
 net/netfilter/nf_tables_api.c            | 202 ++++++++++++++++++++++++++++---
 net/netfilter/nf_tables_core.c           |  10 ++
 net/netfilter/nfnetlink.c                | 175 +++++++++++++++++++++++++-
 7 files changed, 401 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 4f68cd7141d2..28c74367e900 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -14,6 +14,9 @@ struct nfnl_callback {
 	int (*call_rcu)(struct sock *nl, struct sk_buff *skb, 
 		    const struct nlmsghdr *nlh,
 		    const struct nlattr * const cda[]);
+	int (*call_batch)(struct sock *nl, struct sk_buff *skb,
+			  const struct nlmsghdr *nlh,
+			  const struct nlattr * const cda[]);
 	const struct nla_policy *policy;	/* netlink attribute policy */
 	const u_int16_t attr_count;		/* number of nlattr's */
 };
@@ -23,6 +26,8 @@ struct nfnetlink_subsystem {
 	__u8 subsys_id;			/* nfnetlink subsystem ID */
 	__u8 cb_count;			/* number of callbacks */
 	const struct nfnl_callback *cb;	/* callback for individual types */
+	int (*commit)(struct sk_buff *skb);
+	int (*abort)(struct sk_buff *skb);
 };
 
 int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index d3272e943aac..975ad3c573c7 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -323,18 +323,39 @@ static inline void *nft_expr_priv(const struct nft_expr *expr)
  *	@list: used internally
  *	@rcu_head: used internally for rcu
  *	@handle: rule handle
+ *	@genmask: generation mask
  *	@dlen: length of expression data
  *	@data: expression data
  */
 struct nft_rule {
 	struct list_head		list;
 	struct rcu_head			rcu_head;
-	u64				handle:48,
+	u64				handle:46,
+					genmask:2,
 					dlen:16;
 	unsigned char			data[]
 		__attribute__((aligned(__alignof__(struct nft_expr))));
 };
 
+/**
+ *	struct nft_rule_trans - nf_tables rule update in transaction
+ *
+ *	@list: used internally
+ *	@rule: rule that needs to be updated
+ *	@chain: chain that this rule belongs to
+ *	@table: table for which this chain applies
+ *	@nlh: netlink header of the message that contain this update
+ *	@family: family expressesed as AF_*
+ */
+struct nft_rule_trans {
+	struct list_head		list;
+	struct nft_rule			*rule;
+	const struct nft_chain		*chain;
+	const struct nft_table		*table;
+	const struct nlmsghdr		*nlh;
+	u8				family;
+};
+
 static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
 {
 	return (struct nft_expr *)&rule->data[0];
@@ -370,6 +391,7 @@ enum nft_chain_flags {
  *	@rules: list of rules in the chain
  *	@list: used internally
  *	@rcu_head: used internally
+ *	@net: net namespace that this chain belongs to
  *	@handle: chain handle
  *	@flags: bitmask of enum nft_chain_flags
  *	@use: number of jump references to this chain
@@ -380,6 +402,7 @@ struct nft_chain {
 	struct list_head		rules;
 	struct list_head		list;
 	struct rcu_head			rcu_head;
+	struct net			*net;
 	u64				handle;
 	u8				flags;
 	u16				use;
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index a98b1c5d9913..08a4248a12b5 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -7,9 +7,12 @@ struct nft_af_info;
 
 struct netns_nftables {
 	struct list_head	af_info;
+	struct list_head	commit_list;
 	struct nft_af_info	*ipv4;
 	struct nft_af_info	*ipv6;
 	struct nft_af_info	*bridge;
+	u8			gencursor;
+	u8			genctr;
 };
 
 #endif
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index 288959404d54..596ddd45253c 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -57,4 +57,8 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_NFT_COMPAT		11
 #define NFNL_SUBSYS_COUNT		12
 
+/* Reserved control nfnetlink messages */
+#define NFNL_MSG_BATCH_BEGIN		NLMSG_MIN_TYPE
+#define NFNL_MSG_BATCH_END		NLMSG_MIN_TYPE+1
+
 #endif /* _UAPI_NFNETLINK_H */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0f140663ec71..79e1418a6043 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -978,6 +978,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
+	chain->net = net;
 	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
@@ -1371,6 +1372,41 @@ err:
 	return err;
 }
 
+static inline bool
+nft_rule_is_active(struct net *net, const struct nft_rule *rule)
+{
+	return (rule->genmask & (1 << net->nft.gencursor)) == 0;
+}
+
+static inline int gencursor_next(struct net *net)
+{
+	return net->nft.gencursor+1 == 1 ? 1 : 0;
+}
+
+static inline int
+nft_rule_is_active_next(struct net *net, const struct nft_rule *rule)
+{
+	return (rule->genmask & (1 << gencursor_next(net))) == 0;
+}
+
+static inline void
+nft_rule_activate_next(struct net *net, struct nft_rule *rule)
+{
+	/* Now inactive, will be active in the future */
+	rule->genmask = (1 << net->nft.gencursor);
+}
+
+static inline void
+nft_rule_disactivate_next(struct net *net, struct nft_rule *rule)
+{
+	rule->genmask = (1 << gencursor_next(net));
+}
+
+static inline void nft_rule_clear(struct net *net, struct nft_rule *rule)
+{
+	rule->genmask = 0;
+}
+
 static int nf_tables_dump_rules(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
@@ -1382,6 +1418,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 	unsigned int idx = 0, s_idx = cb->args[0];
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	u8 genctr = ACCESS_ONCE(net->nft.genctr);
+	u8 gencursor = ACCESS_ONCE(net->nft.gencursor);
 
 	list_for_each_entry(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
@@ -1390,6 +1428,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 		list_for_each_entry(table, &afi->tables, list) {
 			list_for_each_entry(chain, &table->chains, list) {
 				list_for_each_entry(rule, &chain->rules, list) {
+					if (!nft_rule_is_active(net, rule))
+						goto cont;
 					if (idx < s_idx)
 						goto cont;
 					if (idx > s_idx)
@@ -1408,6 +1448,10 @@ cont:
 		}
 	}
 done:
+	/* Invalidate this dump, a transition to the new generation happened */
+	if (gencursor != net->nft.gencursor || genctr != net->nft.genctr)
+		return -EBUSY;
+
 	cb->args[0] = idx;
 	return skb->len;
 }
@@ -1492,6 +1536,25 @@ static void nf_tables_rule_destroy(struct nft_rule *rule)
 
 static struct nft_expr_info *info;
 
+static struct nft_rule_trans *
+nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx)
+{
+	struct nft_rule_trans *rupd;
+
+	rupd = kmalloc(sizeof(struct nft_rule_trans), GFP_KERNEL);
+	if (rupd == NULL)
+	       return NULL;
+
+	rupd->chain = ctx->chain;
+	rupd->table = ctx->table;
+	rupd->rule = rule;
+	rupd->family = ctx->afi->family;
+	rupd->nlh = ctx->nlh;
+	list_add_tail(&rupd->list, &ctx->net->nft.commit_list);
+
+	return rupd;
+}
+
 static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
@@ -1502,6 +1565,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
+	struct nft_rule_trans *repl = NULL;
 	struct nft_expr *expr;
 	struct nft_ctx ctx;
 	struct nlattr *tmp;
@@ -1576,6 +1640,8 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	if (rule == NULL)
 		goto err1;
 
+	nft_rule_activate_next(net, rule);
+
 	rule->handle = handle;
 	rule->dlen   = size;
 
@@ -1589,8 +1655,18 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		list_replace_rcu(&old_rule->list, &rule->list);
-		nf_tables_rule_destroy(old_rule);
+		if (nft_rule_is_active_next(net, old_rule)) {
+			repl = nf_tables_trans_add(old_rule, &ctx);
+			if (repl == NULL) {
+				err = -ENOMEM;
+				goto err2;
+			}
+			nft_rule_disactivate_next(net, old_rule);
+			list_add_tail(&rule->list, &old_rule->list);
+		} else {
+			err = -ENOENT;
+			goto err2;
+		}
 	} else if (nlh->nlmsg_flags & NLM_F_APPEND)
 		if (old_rule)
 			list_add_rcu(&rule->list, &old_rule->list);
@@ -1603,11 +1679,20 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			list_add_rcu(&rule->list, &chain->rules);
 	}
 
-	nf_tables_rule_notify(skb, nlh, table, chain, rule, NFT_MSG_NEWRULE,
-			      nlh->nlmsg_flags & (NLM_F_APPEND | NLM_F_REPLACE),
-			      nfmsg->nfgen_family);
+	if (nf_tables_trans_add(rule, &ctx) == NULL) {
+		err = -ENOMEM;
+		goto err3;
+	}
 	return 0;
 
+err3:
+	list_del_rcu(&rule->list);
+	if (repl) {
+		list_del_rcu(&repl->rule->list);
+		list_del(&repl->list);
+		nft_rule_clear(net, repl->rule);
+		kfree(repl);
+	}
 err2:
 	nf_tables_rule_destroy(rule);
 err1:
@@ -1618,6 +1703,19 @@ err1:
 	return err;
 }
 
+static int
+nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule)
+{
+	/* You cannot delete the same rule twice */
+	if (nft_rule_is_active_next(ctx->net, rule)) {
+		if (nf_tables_trans_add(rule, ctx) == NULL)
+			return -ENOMEM;
+		nft_rule_disactivate_next(ctx->net, rule);
+		return 0;
+	}
+	return -ENOENT;
+}
+
 static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
@@ -1628,7 +1726,8 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	const struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *tmp;
-	int family = nfmsg->nfgen_family;
+	int family = nfmsg->nfgen_family, err = 0;
+	struct nft_ctx ctx;
 
 	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
@@ -1642,31 +1741,95 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
 
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+
 	if (nla[NFTA_RULE_HANDLE]) {
 		rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
 		if (IS_ERR(rule))
 			return PTR_ERR(rule);
 
-		/* List removal must be visible before destroying expressions */
-		list_del_rcu(&rule->list);
-
-		nf_tables_rule_notify(skb, nlh, table, chain, rule,
-				      NFT_MSG_DELRULE, 0, family);
-		nf_tables_rule_destroy(rule);
+		err = nf_tables_delrule_one(&ctx, rule);
 	} else {
 		/* Remove all rules in this chain */
 		list_for_each_entry_safe(rule, tmp, &chain->rules, list) {
-			list_del_rcu(&rule->list);
+			err = nf_tables_delrule_one(&ctx, rule);
+			if (err < 0)
+				break;
+		}
+	}
+
+	return err;
+}
+
+static int nf_tables_commit(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_rule_trans *rupd, *tmp;
 
-			nf_tables_rule_notify(skb, nlh, table, chain, rule,
-					      NFT_MSG_DELRULE, 0, family);
-			nf_tables_rule_destroy(rule);
+	/* Bump generation counter, invalidate any dump in progress */
+	net->nft.genctr++;
+
+	/* A new generation has just started */
+	net->nft.gencursor = gencursor_next(net);
+
+	/* Make sure all packets have left the previous generation before
+	 * purging old rules.
+	 */
+	synchronize_rcu();
+
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
+		/* Delete this rule from the dirty list */
+		list_del(&rupd->list);
+
+		/* This rule was inactive in the past and just became active.
+		 * Clear the next bit of the genmask since its meaning has
+		 * changed, now it is the future.
+		 */
+		if (nft_rule_is_active(net, rupd->rule)) {
+			nft_rule_clear(net, rupd->rule);
+			nf_tables_rule_notify(skb, rupd->nlh, rupd->table,
+					      rupd->chain, rupd->rule,
+					      NFT_MSG_NEWRULE, 0,
+					      rupd->family);
+			kfree(rupd);
+			continue;
 		}
+
+		/* This rule is in the past, get rid of it */
+		list_del_rcu(&rupd->rule->list);
+		nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain,
+				      rupd->rule, NFT_MSG_DELRULE, 0,
+				      rupd->family);
+		nf_tables_rule_destroy(rupd->rule);
+		kfree(rupd);
 	}
 
 	return 0;
 }
 
+static int nf_tables_abort(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_rule_trans *rupd, *tmp;
+
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
+		/* Delete all rules from the dirty list */
+		list_del(&rupd->list);
+
+		if (!nft_rule_is_active_next(net, rupd->rule)) {
+			nft_rule_clear(net, rupd->rule);
+			kfree(rupd);
+			continue;
+		}
+
+		/* This rule is inactive, get rid of it */
+		list_del_rcu(&rupd->rule->list);
+		nf_tables_rule_destroy(rupd->rule);
+		kfree(rupd);
+	}
+	return 0;
+}
+
 /*
  * Sets
  */
@@ -2634,7 +2797,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_chain_policy,
 	},
 	[NFT_MSG_NEWRULE] = {
-		.call		= nf_tables_newrule,
+		.call_batch	= nf_tables_newrule,
 		.attr_count	= NFTA_RULE_MAX,
 		.policy		= nft_rule_policy,
 	},
@@ -2644,7 +2807,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_rule_policy,
 	},
 	[NFT_MSG_DELRULE] = {
-		.call		= nf_tables_delrule,
+		.call_batch	= nf_tables_delrule,
 		.attr_count	= NFTA_RULE_MAX,
 		.policy		= nft_rule_policy,
 	},
@@ -2685,6 +2848,8 @@ static const struct nfnetlink_subsystem nf_tables_subsys = {
 	.subsys_id	= NFNL_SUBSYS_NFTABLES,
 	.cb_count	= NFT_MSG_MAX,
 	.cb		= nf_tables_cb,
+	.commit		= nf_tables_commit,
+	.abort		= nf_tables_abort,
 };
 
 /*
@@ -3056,6 +3221,7 @@ EXPORT_SYMBOL_GPL(nft_data_dump);
 static int nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.af_info);
+	INIT_LIST_HEAD(&net->nft.commit_list);
 	return 0;
 }
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 3c13007d80df..d581ef660248 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -88,12 +88,22 @@ nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
+	/*
+	 * Cache cursor to avoid problems in case that the cursor is updated
+	 * while traversing the ruleset.
+	 */
+	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
 
 do_chain:
 	rule = list_entry(&chain->rules, struct nft_rule, list);
 next_rule:
 	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
 	list_for_each_entry_continue_rcu(rule, &chain->rules, list) {
+
+		/* This rule is not active, skip. */
+		if (unlikely(rule->genmask & (1 << gencursor)))
+			continue;
+
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, data);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 572d87dc116f..027f16af51a0 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -147,9 +147,6 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	const struct nfnetlink_subsystem *ss;
 	int type, err;
 
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
-		return -EPERM;
-
 	/* All the messages must at least contain nfgenmsg */
 	if (nlmsg_len(nlh) < sizeof(struct nfgenmsg))
 		return 0;
@@ -217,9 +214,179 @@ replay:
 	}
 }
 
+static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
+				u_int16_t subsys_id)
+{
+	struct sk_buff *nskb, *oskb = skb;
+	struct net *net = sock_net(skb->sk);
+	const struct nfnetlink_subsystem *ss;
+	const struct nfnl_callback *nc;
+	bool success = true, done = false;
+	int err;
+
+	if (subsys_id >= NFNL_SUBSYS_COUNT)
+		return netlink_ack(skb, nlh, -EINVAL);
+replay:
+	nskb = netlink_skb_clone(oskb, GFP_KERNEL);
+	if (!nskb)
+		return netlink_ack(oskb, nlh, -ENOMEM);
+
+	nskb->sk = oskb->sk;
+	skb = nskb;
+
+	nfnl_lock(subsys_id);
+	ss = rcu_dereference_protected(table[subsys_id].subsys,
+				       lockdep_is_held(&table[subsys_id].mutex));
+	if (!ss) {
+#ifdef CONFIG_MODULES
+		nfnl_unlock(subsys_id);
+		request_module("nfnetlink-subsys-%d", subsys_id);
+		nfnl_lock(subsys_id);
+		ss = rcu_dereference_protected(table[subsys_id].subsys,
+					       lockdep_is_held(&table[subsys_id].mutex));
+		if (!ss)
+#endif
+		{
+			nfnl_unlock(subsys_id);
+			kfree_skb(nskb);
+			return netlink_ack(skb, nlh, -EOPNOTSUPP);
+		}
+	}
+
+	if (!ss->commit || !ss->abort) {
+		nfnl_unlock(subsys_id);
+		kfree_skb(nskb);
+		return netlink_ack(skb, nlh, -EOPNOTSUPP);
+	}
+
+	while (skb->len >= nlmsg_total_size(0)) {
+		int msglen, type;
+
+		nlh = nlmsg_hdr(skb);
+		err = 0;
+
+		if (nlh->nlmsg_len < NLMSG_HDRLEN) {
+			err = -EINVAL;
+			goto ack;
+		}
+
+		/* Only requests are handled by the kernel */
+		if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) {
+			err = -EINVAL;
+			goto ack;
+		}
+
+		type = nlh->nlmsg_type;
+		if (type == NFNL_MSG_BATCH_BEGIN) {
+			/* Malformed: Batch begin twice */
+			success = false;
+			goto done;
+		} else if (type == NFNL_MSG_BATCH_END) {
+			done = true;
+			goto done;
+		} else if (type < NLMSG_MIN_TYPE) {
+			err = -EINVAL;
+			goto ack;
+		}
+
+		/* We only accept a batch with messages for the same
+		 * subsystem.
+		 */
+		if (NFNL_SUBSYS_ID(type) != subsys_id) {
+			err = -EINVAL;
+			goto ack;
+		}
+
+		nc = nfnetlink_find_client(type, ss);
+		if (!nc) {
+			err = -EINVAL;
+			goto ack;
+		}
+
+		{
+			int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
+			u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type);
+			struct nlattr *cda[ss->cb[cb_id].attr_count + 1];
+			struct nlattr *attr = (void *)nlh + min_len;
+			int attrlen = nlh->nlmsg_len - min_len;
+
+			err = nla_parse(cda, ss->cb[cb_id].attr_count,
+					attr, attrlen, ss->cb[cb_id].policy);
+			if (err < 0)
+				goto ack;
+
+			if (nc->call_batch) {
+				err = nc->call_batch(net->nfnl, skb, nlh,
+						     (const struct nlattr **)cda);
+			}
+
+			/* The lock was released to autoload some module, we
+			 * have to abort and start from scratch using the
+			 * original skb.
+			 */
+			if (err == -EAGAIN) {
+				ss->abort(skb);
+				nfnl_unlock(subsys_id);
+				kfree_skb(nskb);
+				goto replay;
+			}
+		}
+ack:
+		if (nlh->nlmsg_flags & NLM_F_ACK || err) {
+			/* We don't stop processing the batch on errors, thus,
+			 * userspace gets all the errors that the batch
+			 * triggers.
+			 */
+			netlink_ack(skb, nlh, err);
+			if (err)
+				success = false;
+		}
+
+		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msglen > skb->len)
+			msglen = skb->len;
+		skb_pull(skb, msglen);
+	}
+done:
+	if (success && done)
+		ss->commit(skb);
+	else
+		ss->abort(skb);
+
+	nfnl_unlock(subsys_id);
+	kfree_skb(nskb);
+}
+
 static void nfnetlink_rcv(struct sk_buff *skb)
 {
-	netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
+	struct nlmsghdr *nlh = nlmsg_hdr(skb);
+	struct net *net = sock_net(skb->sk);
+	int msglen;
+
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return netlink_ack(skb, nlh, -EPERM);
+
+	if (nlh->nlmsg_len < NLMSG_HDRLEN ||
+	    skb->len < nlh->nlmsg_len)
+		return;
+
+	if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) {
+		struct nfgenmsg *nfgenmsg;
+
+		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msglen > skb->len)
+			msglen = skb->len;
+
+		if (nlh->nlmsg_len < NLMSG_HDRLEN ||
+		    skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg))
+			return;
+
+		nfgenmsg = nlmsg_data(nlh);
+		skb_pull(skb, msglen);
+		nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id);
+	} else {
+		netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
+	}
 }
 
 #ifdef CONFIG_MODULES
-- 
cgit 


From b5bc89bfa0b46de37754610f46c0ef4e2280edb4 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 10 Oct 2013 16:49:19 +0200
Subject: netfilter: nf_tables: add trace support

This patch adds support for tracing the packet travel through
the ruleset, in a similar fashion to x_tables.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     |  1 +
 net/netfilter/nf_tables_core.c    | 57 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 975ad3c573c7..54c4a5cafb64 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -392,6 +392,7 @@ enum nft_chain_flags {
  *	@list: used internally
  *	@rcu_head: used internally
  *	@net: net namespace that this chain belongs to
+ *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@flags: bitmask of enum nft_chain_flags
  *	@use: number of jump references to this chain
@@ -403,6 +404,7 @@ struct nft_chain {
 	struct list_head		list;
 	struct rcu_head			rcu_head;
 	struct net			*net;
+	struct nft_table		*table;
 	u64				handle;
 	u8				flags;
 	u16				use;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 79e1418a6043..dcddc49c0e08 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -979,6 +979,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
 	chain->net = net;
+	chain->table = table;
 	nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
 
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index d581ef660248..cb9e685caae1 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -19,6 +19,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_log.h>
 
 static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_data data[NFT_REG_MAX + 1])
@@ -63,6 +64,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 struct nft_jumpstack {
 	const struct nft_chain	*chain;
 	const struct nft_rule	*rule;
+	int			rulenum;
 };
 
 static inline void
@@ -79,6 +81,40 @@ nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
 	rcu_read_unlock_bh();
 }
 
+enum nft_trace {
+	NFT_TRACE_RULE,
+	NFT_TRACE_RETURN,
+	NFT_TRACE_POLICY,
+};
+
+static const char *const comments[] = {
+	[NFT_TRACE_RULE]	= "rule",
+	[NFT_TRACE_RETURN]	= "return",
+	[NFT_TRACE_POLICY]	= "policy",
+};
+
+static struct nf_loginfo trace_loginfo = {
+	.type = NF_LOG_TYPE_LOG,
+	.u = {
+		.log = {
+			.level = 4,
+			.logflags = NF_LOG_MASK,
+	        },
+	},
+};
+
+static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
+				    const struct nft_chain *chain,
+				    int rulenum, enum nft_trace type)
+{
+	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
+
+	nf_log_packet(net, pkt->xt.family, pkt->hooknum, pkt->skb, pkt->in,
+		      pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
+		      chain->table->name, chain->name, comments[type],
+		      rulenum);
+}
+
 unsigned int
 nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
@@ -88,6 +124,7 @@ nft_do_chain_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
+	int rulenum = 0;
 	/*
 	 * Cache cursor to avoid problems in case that the cursor is updated
 	 * while traversing the ruleset.
@@ -104,6 +141,8 @@ next_rule:
 		if (unlikely(rule->genmask & (1 << gencursor)))
 			continue;
 
+		rulenum++;
+
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, data);
@@ -129,17 +168,28 @@ next_rule:
 	case NF_ACCEPT:
 	case NF_DROP:
 	case NF_QUEUE:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
 		return data[NFT_REG_VERDICT].verdict;
 	case NFT_JUMP:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
 		BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE);
 		jumpstack[stackptr].chain = chain;
 		jumpstack[stackptr].rule  = rule;
+		jumpstack[stackptr].rulenum = rulenum;
 		stackptr++;
 		/* fall through */
 	case NFT_GOTO:
 		chain = data[NFT_REG_VERDICT].chain;
 		goto do_chain;
 	case NFT_RETURN:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
+
+		/* fall through */
 	case NFT_CONTINUE:
 		break;
 	default:
@@ -147,13 +197,20 @@ next_rule:
 	}
 
 	if (stackptr > 0) {
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
+
 		stackptr--;
 		chain = jumpstack[stackptr].chain;
 		rule  = jumpstack[stackptr].rule;
+		rulenum = jumpstack[stackptr].rulenum;
 		goto next_rule;
 	}
 	nft_chain_stats(chain, pkt, jumpstack, stackptr);
 
+	if (unlikely(pkt->skb->nf_trace))
+		nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY);
+
 	return nft_base_chain(chain)->policy;
 }
 EXPORT_SYMBOL_GPL(nft_do_chain_pktinfo);
-- 
cgit 


From ed683f138b3dbc8a5e878e24a0bfa0bb61043a09 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 7 Oct 2013 22:53:08 +0200
Subject: netfilter: nf_tables: add ARP filtering support

This patch registers the ARP family and he filter chain type
for this family.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/nftables.h       |   1 +
 net/ipv4/netfilter/Kconfig         |   4 ++
 net/ipv4/netfilter/Makefile        |   1 +
 net/ipv4/netfilter/nf_tables_arp.c | 102 +++++++++++++++++++++++++++++++++++++
 4 files changed, 108 insertions(+)
 create mode 100644 net/ipv4/netfilter/nf_tables_arp.c

(limited to 'include')

diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 08a4248a12b5..15d056d534e3 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -10,6 +10,7 @@ struct netns_nftables {
 	struct list_head	commit_list;
 	struct nft_af_info	*ipv4;
 	struct nft_af_info	*ipv6;
+	struct nft_af_info	*arp;
 	struct nft_af_info	*bridge;
 	u8			gencursor;
 	u8			genctr;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 1f37ef67f1ac..40d56073cd19 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -53,6 +53,10 @@ config NFT_CHAIN_NAT_IPV4
 	depends on NF_NAT_IPV4 && NFT_NAT
 	tristate "IPv4 nf_tables nat chain support"
 
+config NF_TABLES_ARP
+	depends on NF_TABLES
+	tristate "ARP nf_tables support"
+
 config IP_NF_IPTABLES
 	tristate "IP tables support (required for filtering/masq/NAT)"
 	default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 91e0bd71a6d3..19df72b7ba88 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
+obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
 obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c
new file mode 100644
index 000000000000..3e67ef1c676f
--- /dev/null
+++ b/net/ipv4/netfilter/nf_tables_arp.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright (c) 2008-2010 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/netfilter_arp.h>
+#include <net/netfilter/nf_tables.h>
+
+static struct nft_af_info nft_af_arp __read_mostly = {
+	.family		= NFPROTO_ARP,
+	.nhooks		= NF_ARP_NUMHOOKS,
+	.owner		= THIS_MODULE,
+};
+
+static int nf_tables_arp_init_net(struct net *net)
+{
+	net->nft.arp = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.arp== NULL)
+		return -ENOMEM;
+
+	memcpy(net->nft.arp, &nft_af_arp, sizeof(nft_af_arp));
+
+	if (nft_register_afinfo(net, net->nft.arp) < 0)
+		goto err;
+
+	return 0;
+err:
+	kfree(net->nft.arp);
+	return -ENOMEM;
+}
+
+static void nf_tables_arp_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.arp);
+	kfree(net->nft.arp);
+}
+
+static struct pernet_operations nf_tables_arp_net_ops = {
+	.init   = nf_tables_arp_init_net,
+	.exit   = nf_tables_arp_exit_net,
+};
+
+static unsigned int
+nft_do_chain_arp(const struct nf_hook_ops *ops,
+		  struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, ops, skb, in, out);
+
+	return nft_do_chain_pktinfo(&pkt, ops);
+}
+
+static struct nf_chain_type filter_arp = {
+	.family		= NFPROTO_ARP,
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.hook_mask	= (1 << NF_ARP_IN) |
+			  (1 << NF_ARP_OUT) |
+			  (1 << NF_ARP_FORWARD),
+	.fn		= {
+		[NF_ARP_IN]		= nft_do_chain_arp,
+		[NF_ARP_OUT]		= nft_do_chain_arp,
+		[NF_ARP_FORWARD]	= nft_do_chain_arp,
+	},
+};
+
+static int __init nf_tables_arp_init(void)
+{
+	int ret;
+
+	nft_register_chain_type(&filter_arp);
+	ret = register_pernet_subsys(&nf_tables_arp_net_ops);
+	if (ret < 0)
+		nft_unregister_chain_type(&filter_arp);
+
+	return ret;
+}
+
+static void __exit nf_tables_arp_exit(void)
+{
+	unregister_pernet_subsys(&nf_tables_arp_net_ops);
+	nft_unregister_chain_type(&filter_arp);
+}
+
+module_init(nf_tables_arp_init);
+module_exit(nf_tables_arp_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_FAMILY(3); /* NFPROTO_ARP */
-- 
cgit 


From c00809d330cfe42469fcd1cfd63f0690b47ea9bb Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Mon, 14 Oct 2013 09:18:54 +0900
Subject: USB: ohci-exynos: Remove non-DT support

The non-DT for EXYNOS SoCs is not supported from v3.11.
Thus, there is no need to support non-DT for Exynos OHCI driver.

The 'include/linux/platform_data/usb-ohci-exynos.h' file has been
used for non-DT support. Thus, the 'usb-ohci-exynos.h' file can
be removed.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ohci-exynos.c                | 18 +++---------------
 include/linux/platform_data/usb-ohci-exynos.h | 21 ---------------------
 2 files changed, 3 insertions(+), 36 deletions(-)
 delete mode 100644 include/linux/platform_data/usb-ohci-exynos.h

(limited to 'include')

diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c
index 17f46fbf047d..a87baedc0aa7 100644
--- a/drivers/usb/host/ohci-exynos.c
+++ b/drivers/usb/host/ohci-exynos.c
@@ -18,7 +18,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/platform_data/usb-ohci-exynos.h>
 #include <linux/usb/phy.h>
 #include <linux/usb/samsung_usb_phy.h>
 #include <linux/usb.h>
@@ -38,7 +37,6 @@ struct exynos_ohci_hcd {
 	struct clk *clk;
 	struct usb_phy *phy;
 	struct usb_otg *otg;
-	struct exynos4_ohci_platdata *pdata;
 };
 
 static void exynos_ohci_phy_enable(struct platform_device *pdev)
@@ -48,8 +46,6 @@ static void exynos_ohci_phy_enable(struct platform_device *pdev)
 
 	if (exynos_ohci->phy)
 		usb_phy_init(exynos_ohci->phy);
-	else if (exynos_ohci->pdata && exynos_ohci->pdata->phy_init)
-		exynos_ohci->pdata->phy_init(pdev, USB_PHY_TYPE_HOST);
 }
 
 static void exynos_ohci_phy_disable(struct platform_device *pdev)
@@ -59,13 +55,10 @@ static void exynos_ohci_phy_disable(struct platform_device *pdev)
 
 	if (exynos_ohci->phy)
 		usb_phy_shutdown(exynos_ohci->phy);
-	else if (exynos_ohci->pdata && exynos_ohci->pdata->phy_exit)
-		exynos_ohci->pdata->phy_exit(pdev, USB_PHY_TYPE_HOST);
 }
 
 static int exynos_ohci_probe(struct platform_device *pdev)
 {
-	struct exynos4_ohci_platdata *pdata = dev_get_platdata(&pdev->dev);
 	struct exynos_ohci_hcd *exynos_ohci;
 	struct usb_hcd *hcd;
 	struct resource *res;
@@ -98,14 +91,9 @@ static int exynos_ohci_probe(struct platform_device *pdev)
 
 	phy = devm_usb_get_phy(&pdev->dev, USB_PHY_TYPE_USB2);
 	if (IS_ERR(phy)) {
-		/* Fallback to pdata */
-		if (!pdata) {
-			usb_put_hcd(hcd);
-			dev_warn(&pdev->dev, "no platform data or transceiver defined\n");
-			return -EPROBE_DEFER;
-		} else {
-			exynos_ohci->pdata = pdata;
-		}
+		usb_put_hcd(hcd);
+		dev_warn(&pdev->dev, "no platform data or transceiver defined\n");
+		return -EPROBE_DEFER;
 	} else {
 		exynos_ohci->phy = phy;
 		exynos_ohci->otg = phy->otg;
diff --git a/include/linux/platform_data/usb-ohci-exynos.h b/include/linux/platform_data/usb-ohci-exynos.h
deleted file mode 100644
index c256c595be5e..000000000000
--- a/include/linux/platform_data/usb-ohci-exynos.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2011 Samsung Electronics Co.Ltd
- *		http://www.samsung.com/
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef __MACH_EXYNOS_OHCI_H
-#define __MACH_EXYNOS_OHCI_H
-
-struct exynos4_ohci_platdata {
-	int (*phy_init)(struct platform_device *pdev, int type);
-	int (*phy_exit)(struct platform_device *pdev, int type);
-};
-
-extern void exynos4_ohci_set_platdata(struct exynos4_ohci_platdata *pd);
-
-#endif /* __MACH_EXYNOS_OHCI_H */
-- 
cgit 


From b4cb9fb25e9eae749f456e9e94446650389e736b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 14 Oct 2013 13:56:16 -0700
Subject: Bluetooth: Read number of supported IAC on controller setup

When initializing a controller make sure to read out the number of
supported IAC and store its result. This value is needed to determine
if limited discoverable for BR/EDR can be configured or not.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h      |  6 ++++++
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         |  6 +++++-
 net/bluetooth/hci_event.c        | 19 +++++++++++++++++++
 4 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index c8a91cb20173..8567f44aa618 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -815,6 +815,12 @@ struct hci_cp_host_buffer_size {
 	__le16   sco_max_pkt;
 } __packed;
 
+#define HCI_OP_READ_NUM_SUPPORTED_IAC	0x0c38
+struct hci_rp_read_num_supported_iac {
+	__u8	status;
+	__u8	num_iac;
+} __packed;
+
 #define HCI_OP_WRITE_INQUIRY_MODE	0x0c45
 
 #define HCI_MAX_EIR_LENGTH		240
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0326b160b89a..4e208420d84c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -159,6 +159,7 @@ struct hci_dev {
 	__u16		manufacturer;
 	__u16		lmp_subver;
 	__u16		voice_setting;
+	__u8		num_iac;
 	__u8		io_capability;
 	__s8		inq_tx_power;
 	__u16		page_scan_interval;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 0e05edee0962..b5ef05e66a2d 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -370,6 +370,9 @@ static void bredr_setup(struct hci_request *req)
 	/* Read Voice Setting */
 	hci_req_add(req, HCI_OP_READ_VOICE_SETTING, 0, NULL);
 
+	/* Read Number of Supported IAC */
+	hci_req_add(req, HCI_OP_READ_NUM_SUPPORTED_IAC, 0, NULL);
+
 	/* Clear Event Filters */
 	flt_type = HCI_FLT_CLEAR_ALL;
 	hci_req_add(req, HCI_OP_SET_EVENT_FLT, 1, &flt_type);
@@ -2271,7 +2274,8 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->pkt_type  = (HCI_DM1 | HCI_DH1 | HCI_HV1);
 	hdev->esco_type = (ESCO_HV1);
 	hdev->link_mode = (HCI_LM_ACCEPT);
-	hdev->io_capability = 0x03; /* No Input No Output */
+	hdev->num_iac = 0x01;		/* One IAC support is mandatory */
+	hdev->io_capability = 0x03;	/* No Input No Output */
 	hdev->inq_tx_power = HCI_TX_POWER_INVALID;
 	hdev->adv_tx_power = HCI_TX_POWER_INVALID;
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index da2bc3d3d289..5391469ff1a5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -418,6 +418,21 @@ static void hci_cc_write_voice_setting(struct hci_dev *hdev,
 		hdev->notify(hdev, HCI_NOTIFY_VOICE_SETTING);
 }
 
+static void hci_cc_read_num_supported_iac(struct hci_dev *hdev,
+					  struct sk_buff *skb)
+{
+	struct hci_rp_read_num_supported_iac *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->num_iac = rp->num_iac;
+
+	BT_DBG("%s num iac %d", hdev->name, hdev->num_iac);
+}
+
 static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2135,6 +2150,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_write_voice_setting(hdev, skb);
 		break;
 
+	case HCI_OP_READ_NUM_SUPPORTED_IAC:
+		hci_cc_read_num_supported_iac(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_SSP_MODE:
 		hci_cc_write_ssp_mode(hdev, skb);
 		break;
-- 
cgit 


From 4b836f393bd8ed111857a6ee1865e44627266ec6 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 14 Oct 2013 14:06:36 -0700
Subject: Bluetooth: Read current IAC LAP on controller setup

Read the current IAC LAP values when initializing the controller. The
values are not used, but it is good to have them in the trace files
for debugging purposes.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci.h | 2 ++
 net/bluetooth/hci_core.c    | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8567f44aa618..b096f5f73789 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -821,6 +821,8 @@ struct hci_rp_read_num_supported_iac {
 	__u8	num_iac;
 } __packed;
 
+#define HCI_OP_READ_CURRENT_IAC_LAP	0x0c39
+
 #define HCI_OP_WRITE_INQUIRY_MODE	0x0c45
 
 #define HCI_MAX_EIR_LENGTH		240
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b5ef05e66a2d..7add9c96e32c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -373,6 +373,9 @@ static void bredr_setup(struct hci_request *req)
 	/* Read Number of Supported IAC */
 	hci_req_add(req, HCI_OP_READ_NUM_SUPPORTED_IAC, 0, NULL);
 
+	/* Read Current IAC LAP */
+	hci_req_add(req, HCI_OP_READ_CURRENT_IAC_LAP, 0, NULL);
+
 	/* Clear Event Filters */
 	flt_type = HCI_FLT_CLEAR_ALL;
 	hci_req_add(req, HCI_OP_SET_EVENT_FLT, 1, &flt_type);
-- 
cgit 


From 120c9794a3ee2f9b1548a1b0b252652e3c134f59 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 28 Aug 2013 19:31:22 +0300
Subject: ipvs: fix the IPVS_CMD_ATTR_MAX definition

It was wrong (bigger) but problem is harmless.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/uapi/linux/ip_vs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index 29458223d044..fbcffe8041f7 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -334,7 +334,7 @@ enum {
 	__IPVS_CMD_ATTR_MAX,
 };
 
-#define IPVS_CMD_ATTR_MAX (__IPVS_SVC_ATTR_MAX - 1)
+#define IPVS_CMD_ATTR_MAX (__IPVS_CMD_ATTR_MAX - 1)
 
 /*
  * Attributes used to describe a service
-- 
cgit 


From 9e4e948a3edafd2b7f4dc14c395e146ffd0d9611 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Wed, 9 Oct 2013 09:24:27 +0300
Subject: ipvs: avoid rcu_barrier during netns cleanup

commit 578bc3ef1e473a ("ipvs: reorganize dest trash") added
rcu_barrier() on cleanup to wait dest users and schedulers
like LBLC and LBLCR to put their last dest reference.
Using rcu_barrier with many namespaces is problematic.

Trying to fix it by freeing dest with kfree_rcu is not
a solution, RCU callbacks can run in parallel and execution
order is random.

Fix it by creating new function ip_vs_dest_put_and_free()
which is heavier than ip_vs_dest_put(). We will use it just
for schedulers like LBLC, LBLCR that can delay their dest
release.

By default, dests reference is above 0 if they are present in
service and it is 0 when deleted but still in trash list.
Change the dest trash code to use ip_vs_dest_put_and_free(),
so that refcnt -1 can be used for freeing. As result,
such checks remain in slow path and the rcu_barrier() from
netns cleanup can be removed.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              | 6 ++++++
 net/netfilter/ipvs/ip_vs_ctl.c   | 6 +-----
 net/netfilter/ipvs/ip_vs_lblc.c  | 2 +-
 net/netfilter/ipvs/ip_vs_lblcr.c | 2 +-
 4 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 1c2e1b9f6b86..cd7275f9c463 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1442,6 +1442,12 @@ static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
 	atomic_dec(&dest->refcnt);
 }
 
+static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
+{
+	if (atomic_dec_return(&dest->refcnt) < 0)
+		kfree(dest);
+}
+
 /*
  *      IPVS sync daemon data and function prototypes
  *      (from ip_vs_sync.c)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a3df9bddc4f7..62786a495cea 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -704,7 +704,7 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest)
 	__ip_vs_dst_cache_reset(dest);
 	__ip_vs_svc_put(svc, false);
 	free_percpu(dest->stats.cpustats);
-	kfree(dest);
+	ip_vs_dest_put_and_free(dest);
 }
 
 /*
@@ -3820,10 +3820,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	/* Some dest can be in grace period even before cleanup, we have to
-	 * defer ip_vs_trash_cleanup until ip_vs_dest_wait_readers is called.
-	 */
-	rcu_barrier();
 	ip_vs_trash_cleanup(net);
 	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	ip_vs_control_net_cleanup_sysctl(net);
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index eff13c94498e..ca056a331e60 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -136,7 +136,7 @@ static void ip_vs_lblc_rcu_free(struct rcu_head *head)
 						   struct ip_vs_lblc_entry,
 						   rcu_head);
 
-	ip_vs_dest_put(en->dest);
+	ip_vs_dest_put_and_free(en->dest);
 	kfree(en);
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 0b8550089a2e..3f21a2f47de1 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -130,7 +130,7 @@ static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head)
 	struct ip_vs_dest_set_elem *e;
 
 	e = container_of(head, struct ip_vs_dest_set_elem, rcu_head);
-	ip_vs_dest_put(e->dest);
+	ip_vs_dest_put_and_free(e->dest);
 	kfree(e);
 }
 
-- 
cgit 


From f2e106692d5189303997ad7b96de8d8123aa5613 Mon Sep 17 00:00:00 2001
From: chai wen <chaiw.fnst@cn.fujitsu.com>
Date: Mon, 14 Oct 2013 22:22:33 +0800
Subject: KVM: Drop FOLL_GET in GUP when doing async page fault

Page pinning is not mandatory in kvm async page fault processing since
after async page fault event is delivered to a guest it accesses page once
again and does its own GUP.  Drop the FOLL_GET flag in GUP in async_pf
code, and do some simplifying in check/clear processing.

Suggested-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Gu zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: chai wen <chaiw.fnst@cn.fujitsu.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kvm/x86.c         |  4 ++--
 include/linux/kvm_host.h   |  2 +-
 include/trace/events/kvm.h | 10 ++++------
 virt/kvm/async_pf.c        | 17 +++++------------
 4 files changed, 12 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c951c71dc80b..edf2a07df3a3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7298,7 +7298,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	int r;
 
 	if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
-	      is_error_page(work->page))
+	      work->wakeup_all)
 		return;
 
 	r = kvm_mmu_reload(vcpu);
@@ -7408,7 +7408,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 	struct x86_exception fault;
 
 	trace_kvm_async_pf_ready(work->arch.token, work->gva);
-	if (is_error_page(work->page))
+	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f6dccde755f6..c9d4236ab442 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -189,7 +189,7 @@ struct kvm_async_pf {
 	gva_t gva;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
-	struct page *page;
+	bool   wakeup_all;
 };
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 7005d1109ec9..131a0bda7aec 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -296,23 +296,21 @@ DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready,
 
 TRACE_EVENT(
 	kvm_async_pf_completed,
-	TP_PROTO(unsigned long address, struct page *page, u64 gva),
-	TP_ARGS(address, page, gva),
+	TP_PROTO(unsigned long address, u64 gva),
+	TP_ARGS(address, gva),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, address)
-		__field(pfn_t, pfn)
 		__field(u64, gva)
 		),
 
 	TP_fast_assign(
 		__entry->address = address;
-		__entry->pfn = page ? page_to_pfn(page) : 0;
 		__entry->gva = gva;
 		),
 
-	TP_printk("gva %#llx address %#lx pfn %#llx",  __entry->gva,
-		  __entry->address, __entry->pfn)
+	TP_printk("gva %#llx address %#lx",  __entry->gva,
+		  __entry->address)
 );
 
 #endif
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index b197950ac4d5..8631d9c14320 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -56,7 +56,6 @@ void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu)
 
 static void async_pf_execute(struct work_struct *work)
 {
-	struct page *page = NULL;
 	struct kvm_async_pf *apf =
 		container_of(work, struct kvm_async_pf, work);
 	struct mm_struct *mm = apf->mm;
@@ -68,13 +67,12 @@ static void async_pf_execute(struct work_struct *work)
 
 	use_mm(mm);
 	down_read(&mm->mmap_sem);
-	get_user_pages(current, mm, addr, 1, 1, 0, &page, NULL);
+	get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
 	unuse_mm(mm);
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
-	apf->page = page;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -82,7 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * this point
 	 */
 
-	trace_kvm_async_pf_completed(addr, page, gva);
+	trace_kvm_async_pf_completed(addr, gva);
 
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
@@ -112,8 +110,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			list_entry(vcpu->async_pf.done.next,
 				   typeof(*work), link);
 		list_del(&work->link);
-		if (!is_error_page(work->page))
-			kvm_release_page_clean(work->page);
 		kmem_cache_free(async_pf_cache, work);
 	}
 	spin_unlock(&vcpu->async_pf.lock);
@@ -133,14 +129,11 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 		list_del(&work->link);
 		spin_unlock(&vcpu->async_pf.lock);
 
-		if (work->page)
-			kvm_arch_async_page_ready(vcpu, work);
+		kvm_arch_async_page_ready(vcpu, work);
 		kvm_arch_async_page_present(vcpu, work);
 
 		list_del(&work->queue);
 		vcpu->async_pf.queued--;
-		if (!is_error_page(work->page))
-			kvm_release_page_clean(work->page);
 		kmem_cache_free(async_pf_cache, work);
 	}
 }
@@ -163,7 +156,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	if (!work)
 		return 0;
 
-	work->page = NULL;
+	work->wakeup_all = false;
 	work->vcpu = vcpu;
 	work->gva = gva;
 	work->addr = gfn_to_hva(vcpu->kvm, gfn);
@@ -203,7 +196,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
 	if (!work)
 		return -ENOMEM;
 
-	work->page = KVM_ERR_PTR_BAD_PAGE;
+	work->wakeup_all = true;
 	INIT_LIST_HEAD(&work->queue); /* for list_del to work */
 
 	spin_lock(&vcpu->async_pf.lock);
-- 
cgit 


From e66cf161098a634dc96e32d0089c5767cf25668a Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Tue, 15 Oct 2013 15:18:08 +0100
Subject: GFS2: Use lockref for glocks

Currently glocks have an atomic reference count and also a spinlock
which covers various internal fields, such as the state. This intent of
this patch is to replace the spinlock and the atomic reference count
with a lockref structure. This contains a spinlock which we can continue
to use as before, and a reference counter which is used in conjuction
with the spinlock to replace the previous atomic counter.

As a result of this there are some new rules for reference counting on
glocks. We need to distinguish between reference count changes under
gl_spin (which are now just increment or decrement of the new counter,
provided the count cannot hit zero) and those which are outside of
gl_spin, but which now take gl_spin internally.

The conversion is relatively straight forward. There is probably some
further clean up which can be done, but the priority at this stage is to
make the change in as simple a manner as possible.

A consequence of this change is that the reference count is being
decoupled from the lru list processing. This should allow future
adoption of the lru_list code with glocks in due course.

The reason for using the "dead" state and not just relying on 0 being
the "invalid state" is so that in due course 0 ref counts can be
allowable. The intent is to eventually be able to remove the ref count
changes which are currently hidden away in state_change().

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
---
 fs/gfs2/glock.c         | 83 ++++++++++++++++++++++++-------------------------
 fs/gfs2/glock.h         |  2 --
 fs/gfs2/glops.c         |  4 +--
 fs/gfs2/incore.h        |  5 +--
 include/linux/lockref.h |  6 ++++
 lib/lockref.c           |  1 +
 6 files changed, 52 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c2f41b4d00b9..e66a8009aff1 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -31,6 +31,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/percpu.h>
 #include <linux/list_sort.h>
+#include <linux/lockref.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -129,10 +130,10 @@ void gfs2_glock_free(struct gfs2_glock *gl)
  *
  */
 
-void gfs2_glock_hold(struct gfs2_glock *gl)
+static void gfs2_glock_hold(struct gfs2_glock *gl)
 {
-	GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0);
-	atomic_inc(&gl->gl_ref);
+	GLOCK_BUG_ON(gl, __lockref_is_dead(&gl->gl_lockref));
+	lockref_get(&gl->gl_lockref);
 }
 
 /**
@@ -186,20 +187,6 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 	spin_unlock(&lru_lock);
 }
 
-/**
- * gfs2_glock_put_nolock() - Decrement reference count on glock
- * @gl: The glock to put
- *
- * This function should only be used if the caller has its own reference
- * to the glock, in addition to the one it is dropping.
- */
-
-void gfs2_glock_put_nolock(struct gfs2_glock *gl)
-{
-	if (atomic_dec_and_test(&gl->gl_ref))
-		GLOCK_BUG_ON(gl, 1);
-}
-
 /**
  * gfs2_glock_put() - Decrement reference count on glock
  * @gl: The glock to put
@@ -211,17 +198,22 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct address_space *mapping = gfs2_glock2aspace(gl);
 
-	if (atomic_dec_and_lock(&gl->gl_ref, &lru_lock)) {
-		__gfs2_glock_remove_from_lru(gl);
-		spin_unlock(&lru_lock);
-		spin_lock_bucket(gl->gl_hash);
-		hlist_bl_del_rcu(&gl->gl_list);
-		spin_unlock_bucket(gl->gl_hash);
-		GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
-		GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
-		trace_gfs2_glock_put(gl);
-		sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
-	}
+	if (lockref_put_or_lock(&gl->gl_lockref))
+		return;
+
+	lockref_mark_dead(&gl->gl_lockref);
+
+	spin_lock(&lru_lock);
+	__gfs2_glock_remove_from_lru(gl);
+	spin_unlock(&lru_lock);
+	spin_unlock(&gl->gl_lockref.lock);
+	spin_lock_bucket(gl->gl_hash);
+	hlist_bl_del_rcu(&gl->gl_list);
+	spin_unlock_bucket(gl->gl_hash);
+	GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
+	GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
+	trace_gfs2_glock_put(gl);
+	sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
 }
 
 /**
@@ -244,7 +236,7 @@ static struct gfs2_glock *search_bucket(unsigned int hash,
 			continue;
 		if (gl->gl_sbd != sdp)
 			continue;
-		if (atomic_inc_not_zero(&gl->gl_ref))
+		if (lockref_get_not_dead(&gl->gl_lockref))
 			return gl;
 	}
 
@@ -396,10 +388,11 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 	held2 = (new_state != LM_ST_UNLOCKED);
 
 	if (held1 != held2) {
+		GLOCK_BUG_ON(gl, __lockref_is_dead(&gl->gl_lockref));
 		if (held2)
-			gfs2_glock_hold(gl);
+			gl->gl_lockref.count++;
 		else
-			gfs2_glock_put_nolock(gl);
+			gl->gl_lockref.count--;
 	}
 	if (held1 && held2 && list_empty(&gl->gl_holders))
 		clear_bit(GLF_QUEUED, &gl->gl_flags);
@@ -626,9 +619,9 @@ out:
 out_sched:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 	smp_mb__after_clear_bit();
-	gfs2_glock_hold(gl);
+	gl->gl_lockref.count++;
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-		gfs2_glock_put_nolock(gl);
+		gl->gl_lockref.count--;
 	return;
 
 out_unlock:
@@ -754,7 +747,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_sbd = sdp;
 	gl->gl_flags = 0;
 	gl->gl_name = name;
-	atomic_set(&gl->gl_ref, 1);
+	gl->gl_lockref.count = 1;
 	gl->gl_state = LM_ST_UNLOCKED;
 	gl->gl_target = LM_ST_UNLOCKED;
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
@@ -1356,10 +1349,10 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 		}
 	}
 
-	spin_unlock(&gl->gl_spin);
+	gl->gl_lockref.count++;
 	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
-	smp_wmb();
-	gfs2_glock_hold(gl);
+	spin_unlock(&gl->gl_spin);
+
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 		gfs2_glock_put(gl);
 }
@@ -1404,15 +1397,19 @@ __acquires(&lru_lock)
 	while(!list_empty(list)) {
 		gl = list_entry(list->next, struct gfs2_glock, gl_lru);
 		list_del_init(&gl->gl_lru);
+		if (!spin_trylock(&gl->gl_spin)) {
+			list_add(&gl->gl_lru, &lru_list);
+			atomic_inc(&lru_count);
+			continue;
+		}
 		clear_bit(GLF_LRU, &gl->gl_flags);
-		gfs2_glock_hold(gl);
 		spin_unlock(&lru_lock);
-		spin_lock(&gl->gl_spin);
+		gl->gl_lockref.count++;
 		if (demote_ok(gl))
 			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
 		WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-			gfs2_glock_put_nolock(gl);
+			gl->gl_lockref.count--;
 		spin_unlock(&gl->gl_spin);
 		spin_lock(&lru_lock);
 	}
@@ -1493,7 +1490,7 @@ static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
 
 	rcu_read_lock();
 	hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
-		if ((gl->gl_sbd == sdp) && atomic_inc_not_zero(&gl->gl_ref))
+		if ((gl->gl_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref))
 			examiner(gl);
 	}
 	rcu_read_unlock();
@@ -1746,7 +1743,7 @@ int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
 		  state2str(gl->gl_demote_state), dtime,
 		  atomic_read(&gl->gl_ail_count),
 		  atomic_read(&gl->gl_revokes),
-		  atomic_read(&gl->gl_ref), gl->gl_hold_time);
+		  (int)gl->gl_lockref.count, gl->gl_hold_time);
 
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
 		error = dump_holder(seq, gh);
@@ -1902,7 +1899,7 @@ static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 			gi->nhash = 0;
 		}
 	/* Skip entries for other sb and dead entries */
-	} while (gi->sdp != gi->gl->gl_sbd || atomic_read(&gi->gl->gl_ref) == 0);
+	} while (gi->sdp != gi->gl->gl_sbd || __lockref_is_dead(&gl->gl_lockref));
 
 	return 0;
 }
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 69f66e3d22bf..6647d77366ba 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -181,8 +181,6 @@ static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl)
 extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 			  const struct gfs2_glock_operations *glops,
 			  int create, struct gfs2_glock **glp);
-extern void gfs2_glock_hold(struct gfs2_glock *gl);
-extern void gfs2_glock_put_nolock(struct gfs2_glock *gl);
 extern void gfs2_glock_put(struct gfs2_glock *gl);
 extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
 			     unsigned flags, struct gfs2_holder *gh);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index e2e0a90396e7..db908f697139 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -525,9 +525,9 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 
 	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
 	    gl->gl_state == LM_ST_SHARED && ip) {
-		gfs2_glock_hold(gl);
+		gl->gl_lockref.count++;
 		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
-			gfs2_glock_put_nolock(gl);
+			gl->gl_lockref.count--;
 	}
 }
 
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 2ab4f8d8f4c4..bb88e417231f 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -21,6 +21,7 @@
 #include <linux/rbtree.h>
 #include <linux/ktime.h>
 #include <linux/percpu.h>
+#include <linux/lockref.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -321,9 +322,9 @@ struct gfs2_glock {
 	struct gfs2_sbd *gl_sbd;
 	unsigned long gl_flags;		/* GLF_... */
 	struct lm_lockname gl_name;
-	atomic_t gl_ref;
 
-	spinlock_t gl_spin;
+	struct lockref gl_lockref;
+#define gl_spin gl_lockref.lock
 
 	/* State fields protected by gl_spin */
 	unsigned int gl_state:2,	/* Current state */
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index f279ed9a9163..13dfd36a3294 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -36,4 +36,10 @@ extern int lockref_put_or_lock(struct lockref *);
 extern void lockref_mark_dead(struct lockref *);
 extern int lockref_get_not_dead(struct lockref *);
 
+/* Must be called under spinlock for reliable results */
+static inline int __lockref_is_dead(const struct lockref *l)
+{
+	return ((int)l->count < 0);
+}
+
 #endif /* __LINUX_LOCKREF_H */
diff --git a/lib/lockref.c b/lib/lockref.c
index e2cd2c0a8821..8ff162fe3413 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -136,6 +136,7 @@ void lockref_mark_dead(struct lockref *lockref)
 	assert_spin_locked(&lockref->lock);
 	lockref->count = -128;
 }
+EXPORT_SYMBOL(lockref_mark_dead);
 
 /**
  * lockref_get_not_dead - Increments count unless the ref is dead
-- 
cgit 


From 441ad2d04123eecb06d7c14948a0e7b07bf75aa5 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 06:33:52 -0700
Subject: Bluetooth: Update advertising data based on management commands

Magically updating the advertising data when some random command enables
advertising in the controller is not really a good idea. It also caused
a bit of complicated code with the exported hci_udpate_ad function that
is shared from many places.

This patch consolidates the advertising data update into the management
core. It also makes sure that when powering on with LE enabled or later
on enabling LE the controller has a good default for advertising data.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |   2 -
 net/bluetooth/hci_core.c         |  87 +--------------------------
 net/bluetooth/hci_event.c        |   8 ---
 net/bluetooth/mgmt.c             | 126 +++++++++++++++++++++++++++++++++++----
 4 files changed, 116 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4e208420d84c..4a186ec99132 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1183,8 +1183,6 @@ struct hci_sec_filter {
 #define hci_req_lock(d)		mutex_lock(&d->req_lock)
 #define hci_req_unlock(d)	mutex_unlock(&d->req_lock)
 
-void hci_update_ad(struct hci_request *req);
-
 void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max,
 					u16 latency, u16 to_multiplier);
 void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8],
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index c53f7f9c630a..a49ca4869621 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -685,10 +685,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 	if (hdev->commands[5] & 0x10)
 		hci_setup_link_policy(req);
 
-	if (lmp_le_capable(hdev)) {
+	if (lmp_le_capable(hdev))
 		hci_set_le_support(req);
-		hci_update_ad(req);
-	}
 
 	/* Read features beyond page 1 if available */
 	for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) {
@@ -1127,89 +1125,6 @@ done:
 	return err;
 }
 
-static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
-{
-	u8 ad_len = 0, flags = 0;
-	size_t name_len;
-
-	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
-		flags |= LE_AD_GENERAL;
-
-	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
-		if (lmp_le_br_capable(hdev))
-			flags |= LE_AD_SIM_LE_BREDR_CTRL;
-		if (lmp_host_le_br_capable(hdev))
-			flags |= LE_AD_SIM_LE_BREDR_HOST;
-	} else {
-		flags |= LE_AD_NO_BREDR;
-	}
-
-	if (flags) {
-		BT_DBG("adv flags 0x%02x", flags);
-
-		ptr[0] = 2;
-		ptr[1] = EIR_FLAGS;
-		ptr[2] = flags;
-
-		ad_len += 3;
-		ptr += 3;
-	}
-
-	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) {
-		ptr[0] = 2;
-		ptr[1] = EIR_TX_POWER;
-		ptr[2] = (u8) hdev->adv_tx_power;
-
-		ad_len += 3;
-		ptr += 3;
-	}
-
-	name_len = strlen(hdev->dev_name);
-	if (name_len > 0) {
-		size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
-
-		if (name_len > max_len) {
-			name_len = max_len;
-			ptr[1] = EIR_NAME_SHORT;
-		} else
-			ptr[1] = EIR_NAME_COMPLETE;
-
-		ptr[0] = name_len + 1;
-
-		memcpy(ptr + 2, hdev->dev_name, name_len);
-
-		ad_len += (name_len + 2);
-		ptr += (name_len + 2);
-	}
-
-	return ad_len;
-}
-
-void hci_update_ad(struct hci_request *req)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_adv_data cp;
-	u8 len;
-
-	if (!lmp_le_capable(hdev))
-		return;
-
-	memset(&cp, 0, sizeof(cp));
-
-	len = create_ad(hdev, cp.data);
-
-	if (hdev->adv_data_len == len &&
-	    memcmp(cp.data, hdev->adv_data, len) == 0)
-		return;
-
-	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
-	hdev->adv_data_len = len;
-
-	cp.length = len;
-
-	hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
-}
-
 static int hci_dev_do_open(struct hci_dev *hdev)
 {
 	int ret = 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5391469ff1a5..7b133f0e0c3c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -939,14 +939,6 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 			clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
 	}
 
-	if (*sent && !test_bit(HCI_INIT, &hdev->flags)) {
-		struct hci_request req;
-
-		hci_req_init(&req, hdev);
-		hci_update_ad(&req);
-		hci_req_run(&req, NULL);
-	}
-
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c071708aac24..285d571eee6b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -536,6 +536,89 @@ static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len)
 	return ptr;
 }
 
+static u8 create_ad(struct hci_dev *hdev, u8 *ptr)
+{
+	u8 ad_len = 0, flags = 0;
+	size_t name_len;
+
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+		flags |= LE_AD_GENERAL;
+
+	if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
+		if (lmp_le_br_capable(hdev))
+			flags |= LE_AD_SIM_LE_BREDR_CTRL;
+		if (lmp_host_le_br_capable(hdev))
+			flags |= LE_AD_SIM_LE_BREDR_HOST;
+	} else {
+		flags |= LE_AD_NO_BREDR;
+	}
+
+	if (flags) {
+		BT_DBG("adv flags 0x%02x", flags);
+
+		ptr[0] = 2;
+		ptr[1] = EIR_FLAGS;
+		ptr[2] = flags;
+
+		ad_len += 3;
+		ptr += 3;
+	}
+
+	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID) {
+		ptr[0] = 2;
+		ptr[1] = EIR_TX_POWER;
+		ptr[2] = (u8) hdev->adv_tx_power;
+
+		ad_len += 3;
+		ptr += 3;
+	}
+
+	name_len = strlen(hdev->dev_name);
+	if (name_len > 0) {
+		size_t max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
+
+		if (name_len > max_len) {
+			name_len = max_len;
+			ptr[1] = EIR_NAME_SHORT;
+		} else
+			ptr[1] = EIR_NAME_COMPLETE;
+
+		ptr[0] = name_len + 1;
+
+		memcpy(ptr + 2, hdev->dev_name, name_len);
+
+		ad_len += (name_len + 2);
+		ptr += (name_len + 2);
+	}
+
+	return ad_len;
+}
+
+static void update_ad(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_adv_data cp;
+	u8 len;
+
+	if (!lmp_le_capable(hdev))
+		return;
+
+	memset(&cp, 0, sizeof(cp));
+
+	len = create_ad(hdev, cp.data);
+
+	if (hdev->adv_data_len == len &&
+	    memcmp(cp.data, hdev->adv_data, len) == 0)
+		return;
+
+	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+	hdev->adv_data_len = len;
+
+	cp.length = len;
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
+}
+
 static void create_eir(struct hci_dev *hdev, u8 *data)
 {
 	u8 *ptr = data;
@@ -1555,6 +1638,23 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status)
 
 	if (match.sk)
 		sock_put(match.sk);
+
+	/* Make sure the controller has a good default for
+	 * advertising data. Restrict the update to when LE
+	 * has actually been enabled. During power on, the
+	 * update in powered_update_hci will take care of it.
+	 */
+	if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
+		struct hci_request req;
+
+		hci_dev_lock(hdev);
+
+		hci_req_init(&req, hdev);
+		update_ad(&req);
+		hci_req_run(&req, NULL);
+
+		hci_dev_unlock(hdev);
+	}
 }
 
 static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
@@ -1622,18 +1722,18 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto unlock;
 	}
 
+	hci_req_init(&req, hdev);
+
 	memset(&hci_cp, 0, sizeof(hci_cp));
 
 	if (val) {
 		hci_cp.le = val;
 		hci_cp.simul = lmp_le_br_capable(hdev);
+	} else {
+		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
+			disable_advertising(&req);
 	}
 
-	hci_req_init(&req, hdev);
-
-	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) && !val)
-		disable_advertising(&req);
-
 	hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
 		    &hci_cp);
 
@@ -2772,7 +2872,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	if (lmp_le_capable(hdev))
-		hci_update_ad(&req);
+		update_ad(&req);
 
 	err = hci_req_run(&req, set_name_complete);
 	if (err < 0)
@@ -3724,7 +3824,7 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		goto unlock;
 	}
 
-	/* We need to flip the bit already here so that hci_update_ad
+	/* We need to flip the bit already here so that update_ad
 	 * generates the correct flags.
 	 */
 	set_bit(HCI_BREDR_ENABLED, &hdev->dev_flags);
@@ -3734,7 +3834,7 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
 		set_bredr_scan(&req);
 
-	hci_update_ad(&req);
+	update_ad(&req);
 
 	err = hci_req_run(&req, set_bredr_complete);
 	if (err < 0)
@@ -4035,9 +4135,6 @@ static int powered_update_hci(struct hci_dev *hdev)
 		    cp.simul != lmp_host_le_br_capable(hdev))
 			hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED,
 				    sizeof(cp), &cp);
-
-		/* In case BR/EDR was toggled during the AUTO_OFF phase */
-		hci_update_ad(&req);
 	}
 
 	if (lmp_le_capable(hdev)) {
@@ -4046,6 +4143,13 @@ static int powered_update_hci(struct hci_dev *hdev)
 			hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
 				    &hdev->static_addr);
 
+		/* Make sure the controller has a good default for
+		 * advertising data. This also applies to the case
+		 * where BR/EDR was toggled during the AUTO_OFF phase.
+		 */
+		if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+			update_ad(&req);
+
 		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 			enable_advertising(&req);
 	}
-- 
cgit 


From 6acd7db41dc2b6bc91b930edf21fbfd8654cbb68 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 06:33:53 -0700
Subject: Bluetooth: Introduce flag for limited discoverable mode

Add a new flag that can be set when in limited discoverable mode. This
flag will cause the limited discoverable bit in the class of device
value to bet set.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 1 +
 net/bluetooth/mgmt.c        | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index b096f5f73789..f4650a8c1194 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -125,6 +125,7 @@ enum {
 	HCI_ADVERTISING,
 	HCI_CONNECTABLE,
 	HCI_DISCOVERABLE,
+	HCI_LIMITED_DISCOVERABLE,
 	HCI_LINK_SECURITY,
 	HCI_PERIODIC_INQ,
 	HCI_FAST_CONNECTABLE,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 285d571eee6b..d5eaa28bfd52 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -724,6 +724,9 @@ static void update_class(struct hci_request *req)
 	cod[1] = hdev->major_class;
 	cod[2] = get_service_classes(hdev);
 
+	if (test_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags))
+		cod[1] |= 0x20;
+
 	if (memcmp(cod, hdev->dev_class, 3) == 0)
 		return;
 
-- 
cgit 


From 86a7564573a7de9e01aa9a2e26faa993d8f962ac Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 06:33:54 -0700
Subject: Bluetooth: Make mgmt_discoverable() return void

The return value of mgmt_discoverable() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/mgmt.c             | 22 ++++++++--------------
 2 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4a186ec99132..783c70cf305a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1100,7 +1100,7 @@ void mgmt_index_added(struct hci_dev *hdev);
 void mgmt_index_removed(struct hci_dev *hdev);
 void mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
-int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
+void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
 int mgmt_connectable(struct hci_dev *hdev, u8 connectable);
 int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
 int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d5eaa28bfd52..62c531269927 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4227,30 +4227,24 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err)
 	mgmt_pending_remove(cmd);
 }
 
-int mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
+void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
 {
-	bool changed = false;
-	int err = 0;
+	bool changed;
 
 	/* Nothing needed here if there's a pending command since that
 	 * commands request completion callback takes care of everything
 	 * necessary.
 	 */
 	if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev))
-		return 0;
+		return;
 
-	if (discoverable) {
-		if (!test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
-			changed = true;
-	} else {
-		if (test_and_clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
-			changed = true;
-	}
+	if (discoverable)
+		changed = !test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
+	else
+		changed = test_and_clear_bit(HCI_DISCOVERABLE, &hdev->dev_flags);
 
 	if (changed)
-		err = new_settings(hdev, NULL);
-
-	return err;
+		new_settings(hdev, NULL);
 }
 
 int mgmt_connectable(struct hci_dev *hdev, u8 connectable)
-- 
cgit 


From a330916c4f29898b93708b6bec8f59f7a7956f41 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 06:33:55 -0700
Subject: Bluetooth: Make mgmt_connectable() return void

The return value of mgmt_connectable() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/mgmt.c             | 22 ++++++++--------------
 2 files changed, 9 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 783c70cf305a..997d43d1996e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1101,7 +1101,7 @@ void mgmt_index_removed(struct hci_dev *hdev);
 void mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
-int mgmt_connectable(struct hci_dev *hdev, u8 connectable);
+void mgmt_connectable(struct hci_dev *hdev, u8 connectable);
 int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
 int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 		      bool persistent);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 62c531269927..9ffca590566a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4247,30 +4247,24 @@ void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
 		new_settings(hdev, NULL);
 }
 
-int mgmt_connectable(struct hci_dev *hdev, u8 connectable)
+void mgmt_connectable(struct hci_dev *hdev, u8 connectable)
 {
-	bool changed = false;
-	int err = 0;
+	bool changed;
 
 	/* Nothing needed here if there's a pending command since that
 	 * commands request completion callback takes care of everything
 	 * necessary.
 	 */
 	if (mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev))
-		return 0;
+		return;
 
-	if (connectable) {
-		if (!test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags))
-			changed = true;
-	} else {
-		if (test_and_clear_bit(HCI_CONNECTABLE, &hdev->dev_flags))
-			changed = true;
-	}
+	if (connectable)
+		changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags);
+	else
+		changed = test_and_clear_bit(HCI_CONNECTABLE, &hdev->dev_flags);
 
 	if (changed)
-		err = new_settings(hdev, NULL);
-
-	return err;
+		new_settings(hdev, NULL);
 }
 
 int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
-- 
cgit 


From 4796e8af60ee7d2922386ef9fd4389d21e2c1665 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 06:33:56 -0700
Subject: Bluetooth: Make mgmt_write_scan_failed() return void

The return value of mgmt_write_scan_failed() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/mgmt.c             | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 997d43d1996e..da21a8d2b4a1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1102,7 +1102,7 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
 void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
 void mgmt_connectable(struct hci_dev *hdev, u8 connectable);
-int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
+void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
 int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 		      bool persistent);
 void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9ffca590566a..12d1cb02c2a1 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4267,7 +4267,7 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable)
 		new_settings(hdev, NULL);
 }
 
-int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
+void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
 {
 	u8 mgmt_err = mgmt_status(status);
 
@@ -4278,8 +4278,6 @@ int mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
 	if (scan & SCAN_INQUIRY)
 		mgmt_pending_foreach(MGMT_OP_SET_DISCOVERABLE, hdev,
 				     cmd_status_rsp, &mgmt_err);
-
-	return 0;
 }
 
 int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
-- 
cgit 


From 3d5053127fc51b11f10a2cc3ad638736f2fa814c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 08:34:15 -0700
Subject: Bluetooth: Add HCI command structure for writing current IAC LAP

This patch just adds the HCI command structure for configuring the
current IAC LAP setting. The length of the command is variable and
supports more than two IAC. However since there is only general
discoverable and limited discoverable modes, this can be limited
to two possible IACs.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index f4650a8c1194..8b8c3e2ddb06 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -824,6 +824,12 @@ struct hci_rp_read_num_supported_iac {
 
 #define HCI_OP_READ_CURRENT_IAC_LAP	0x0c39
 
+#define HCI_OP_WRITE_CURRENT_IAC_LAP	0x0c3a
+struct hci_cp_write_current_iac_lap {
+	__u8	num_iac;
+	__u8	iac_lap[6];
+} __packed;
+
 #define HCI_OP_WRITE_INQUIRY_MODE	0x0c45
 
 #define HCI_MAX_EIR_LENGTH		240
-- 
cgit 


From dc4a5ee2a3282a1044b164979609b4bfab43900b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 10:15:57 -0700
Subject: Bluetooth: Make mgmt_new_link_key() return void

The return value of mgmt_new_link_key() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/mgmt.c             | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index da21a8d2b4a1..cf6be04336aa 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1103,8 +1103,8 @@ int mgmt_powered(struct hci_dev *hdev, u8 powered);
 void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
 void mgmt_connectable(struct hci_dev *hdev, u8 connectable);
 void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
-int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
-		      bool persistent);
+void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
+		       bool persistent);
 void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
 			   u8 *dev_class);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c70094014d46..6fb302e04cd8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4341,8 +4341,8 @@ void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status)
 				     cmd_status_rsp, &mgmt_err);
 }
 
-int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
-		      bool persistent)
+void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
+		       bool persistent)
 {
 	struct mgmt_ev_new_link_key ev;
 
@@ -4355,7 +4355,7 @@ int mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 	memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE);
 	ev.key.pin_len = key->pin_len;
 
-	return mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL);
+	mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
-- 
cgit 


From 9493399108a186492bb828417a43ff37d9ae48fa Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 10:26:39 -0700
Subject: Bluetooth: Move eir_append_data() function into mgmt.c

The eir_append_data() function is only used from mgmt.c and so
instead of having a public function move it to the location where
it is used.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 11 -----------
 net/bluetooth/mgmt.c             | 11 +++++++++++
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index cf6be04336aa..42591a41baf0 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1026,17 +1026,6 @@ static inline size_t eir_get_length(u8 *eir, size_t eir_len)
 	return eir_len;
 }
 
-static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
-				  u8 data_len)
-{
-	eir[eir_len++] = sizeof(type) + data_len;
-	eir[eir_len++] = type;
-	memcpy(&eir[eir_len], data, data_len);
-	eir_len += data_len;
-
-	return eir_len;
-}
-
 int hci_register_cb(struct hci_cb *hcb);
 int hci_unregister_cb(struct hci_cb *hcb);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 6fb302e04cd8..292e81fcfa95 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4381,6 +4381,17 @@ int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
 			  NULL);
 }
 
+static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
+				  u8 data_len)
+{
+	eir[eir_len++] = sizeof(type) + data_len;
+	eir[eir_len++] = type;
+	memcpy(&eir[eir_len], data, data_len);
+	eir_len += data_len;
+
+	return eir_len;
+}
+
 void mgmt_device_connected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			   u8 addr_type, u32 flags, u8 *name, u8 name_len,
 			   u8 *dev_class)
-- 
cgit 


From efdcf8e3d716730d2212dfd973571a0ed00c9b10 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 10:31:12 -0700
Subject: Bluetooth: Move eir_get_length() function into hci_event.c

The eir_get_length() function is only used from hci_event.c and so
instead of having a public function move it to the location where
it is used.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 17 -----------------
 net/bluetooth/hci_event.c        | 17 +++++++++++++++++
 2 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 42591a41baf0..b076cd9f6683 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1009,23 +1009,6 @@ static inline bool eir_has_data_type(u8 *data, size_t data_len, u8 type)
 	return false;
 }
 
-static inline size_t eir_get_length(u8 *eir, size_t eir_len)
-{
-	size_t parsed = 0;
-
-	while (parsed < eir_len) {
-		u8 field_len = eir[0];
-
-		if (field_len == 0)
-			return parsed;
-
-		parsed += field_len + 1;
-		eir += field_len + 1;
-	}
-
-	return eir_len;
-}
-
 int hci_register_cb(struct hci_cb *hcb);
 int hci_unregister_cb(struct hci_cb *hcb);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 071c0df118d5..7450626b7704 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2928,6 +2928,23 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static inline size_t eir_get_length(u8 *eir, size_t eir_len)
+{
+	size_t parsed = 0;
+
+	while (parsed < eir_len) {
+		u8 field_len = eir[0];
+
+		if (field_len == 0)
+			return parsed;
+
+		parsed += field_len + 1;
+		eir += field_len + 1;
+	}
+
+	return eir_len;
+}
+
 static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
-- 
cgit 


From d1967ff88b3854d1bb002cccd15d28ad0d9223a9 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 10:57:40 -0700
Subject: Bluetooth: Update class of device on discoverable timeout

When the discoverable timeout triggers and limited discoverable mode
was used, then the class of device needs to be updated to remove
the limited discoverable bit.

To keep the class of device logic in a central place, expose a new
function mgmt_discoverable_timeout that can be called from the
timeout callback. In case the class of device value needs updating,
it will add the HCI command to the transaction.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 19 +------------------
 net/bluetooth/mgmt.c             | 24 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b076cd9f6683..fc04bc846617 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1072,6 +1072,7 @@ void mgmt_index_added(struct hci_dev *hdev);
 void mgmt_index_removed(struct hci_dev *hdev);
 void mgmt_set_powered_failed(struct hci_dev *hdev, int err);
 int mgmt_powered(struct hci_dev *hdev, u8 powered);
+void mgmt_discoverable_timeout(struct hci_dev *hdev);
 void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable);
 void mgmt_connectable(struct hci_dev *hdev, u8 connectable);
 void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 7a3d17990b43..2af0baca6dc1 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1705,29 +1705,12 @@ static void hci_power_off(struct work_struct *work)
 static void hci_discov_off(struct work_struct *work)
 {
 	struct hci_dev *hdev;
-	struct hci_request req;
-	u8 scan = SCAN_PAGE;
 
 	hdev = container_of(work, struct hci_dev, discov_off.work);
 
 	BT_DBG("%s", hdev->name);
 
-	hci_dev_lock(hdev);
-
-	hci_req_init(&req, hdev);
-	hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan);
-	hci_req_run(&req, NULL);
-
-	/* When discoverable timeout triggers, then just make sure
-	 * the limited discoverable flag is cleared. Even in the case
-	 * of a timeout triggered from general discoverable, it is
-	 * safe to unconditionally clear the flag.
-	 */
-	clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
-
-	hdev->discov_timeout = 0;
-
-	hci_dev_unlock(hdev);
+	mgmt_discoverable_timeout(hdev);
 }
 
 int hci_uuids_clear(struct hci_dev *hdev)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 292e81fcfa95..ca3cdb520b2f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4288,6 +4288,30 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err)
 	mgmt_pending_remove(cmd);
 }
 
+void mgmt_discoverable_timeout(struct hci_dev *hdev)
+{
+	struct hci_request req;
+	u8 scan = SCAN_PAGE;
+
+	hci_dev_lock(hdev);
+
+	/* When discoverable timeout triggers, then just make sure
+	 * the limited discoverable flag is cleared. Even in the case
+	 * of a timeout triggered from general discoverable, it is
+	 * safe to unconditionally clear the flag.
+	 */
+	clear_bit(HCI_LIMITED_DISCOVERABLE, &hdev->dev_flags);
+
+	hci_req_init(&req, hdev);
+	hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, sizeof(scan), &scan);
+	update_class(&req);
+	hci_req_run(&req, NULL);
+
+	hdev->discov_timeout = 0;
+
+	hci_dev_unlock(hdev);
+}
+
 void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable)
 {
 	bool changed;
-- 
cgit 


From d1cb9d1af0bc11b7450a6032f43935c746609418 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Thu, 3 Oct 2013 17:24:51 -0400
Subject: of: Make cpu node handling more portable.

Use for_each_node_by_type() to iterate all cpu nodes in the
system.

Provide and overridable function arch_find_n_match_cpu_physical_id,
which sees if the given device node matches 'cpu' and if so sets
'*thread' when non-NULL to the cpu thread number within the core.

The default implementation behaves the same as the existing code.

Add a sparc64 implementation.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Sudeep KarkadaNagesha <Sudeep.KarkadaNagesha@arm.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 arch/sparc/kernel/prom_64.c | 53 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/of/base.c           | 45 +++++++++++++++++++++++---------------
 include/linux/cpu.h         |  3 +++
 3 files changed, 84 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index d397d7fc5c28..6b39125eb927 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -373,6 +373,59 @@ static const char *get_mid_prop(void)
 	return (tlb_type == spitfire ? "upa-portid" : "portid");
 }
 
+bool arch_find_n_match_cpu_physical_id(struct device_node *cpun,
+				       int cpu, unsigned int *thread)
+{
+	const char *mid_prop = get_mid_prop();
+	int this_cpu_id;
+
+	/* On hypervisor based platforms we interrogate the 'reg'
+	 * property.  On everything else we look for a 'upa-portis',
+	 * 'portid', or 'cpuid' property.
+	 */
+
+	if (tlb_type == hypervisor) {
+		struct property *prop = of_find_property(cpun, "reg", NULL);
+		u32 *regs;
+
+		if (!prop) {
+			pr_warn("CPU node missing reg property\n");
+			return false;
+		}
+		regs = prop->value;
+		this_cpu_id = regs[0] & 0x0fffffff;
+	} else {
+		this_cpu_id = of_getintprop_default(cpun, mid_prop, -1);
+
+		if (this_cpu_id < 0) {
+			mid_prop = "cpuid";
+			this_cpu_id = of_getintprop_default(cpun, mid_prop, -1);
+		}
+		if (this_cpu_id < 0) {
+			pr_warn("CPU node missing cpu ID property\n");
+			return false;
+		}
+	}
+	if (this_cpu_id == cpu) {
+		if (thread) {
+			int proc_id = cpu_data(cpu).proc_id;
+
+			/* On sparc64, the cpu thread information is obtained
+			 * either from OBP or the machine description.  We've
+			 * actually probed this information already long before
+			 * this interface gets called so instead of interrogating
+			 * both the OF node and the MDESC again, just use what
+			 * we discovered already.
+			 */
+			if (proc_id < 0)
+				proc_id = 0;
+			*thread = proc_id;
+		}
+		return true;
+	}
+	return false;
+}
+
 static void *of_iterate_over_cpus(void *(*func)(struct device_node *, int, int), int arg)
 {
 	struct device_node *dp;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 7d4c70f859e3..e4c99453adf1 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -280,6 +280,31 @@ static bool __of_find_n_match_cpu_property(struct device_node *cpun,
 	return false;
 }
 
+/*
+ * arch_find_n_match_cpu_physical_id - See if the given device node is
+ * for the cpu corresponding to logical cpu 'cpu'.  Return true if so,
+ * else false.  If 'thread' is non-NULL, the local thread number within the
+ * core is returned in it.
+ */
+bool __weak arch_find_n_match_cpu_physical_id(struct device_node *cpun,
+					      int cpu, unsigned int *thread)
+{
+	/* Check for non-standard "ibm,ppc-interrupt-server#s" property
+	 * for thread ids on PowerPC. If it doesn't exist fallback to
+	 * standard "reg" property.
+	 */
+	if (IS_ENABLED(CONFIG_PPC) &&
+	    __of_find_n_match_cpu_property(cpun,
+					   "ibm,ppc-interrupt-server#s",
+					   cpu, thread))
+		return true;
+
+	if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+		return true;
+
+	return false;
+}
+
 /**
  * of_get_cpu_node - Get device node associated with the given logical CPU
  *
@@ -300,24 +325,10 @@ static bool __of_find_n_match_cpu_property(struct device_node *cpun,
  */
 struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
 {
-	struct device_node *cpun, *cpus;
-
-	cpus = of_find_node_by_path("/cpus");
-	if (!cpus)
-		return NULL;
+	struct device_node *cpun;
 
-	for_each_child_of_node(cpus, cpun) {
-		if (of_node_cmp(cpun->type, "cpu"))
-			continue;
-		/* Check for non-standard "ibm,ppc-interrupt-server#s" property
-		 * for thread ids on PowerPC. If it doesn't exist fallback to
-		 * standard "reg" property.
-		 */
-		if (IS_ENABLED(CONFIG_PPC) &&
-			__of_find_n_match_cpu_property(cpun,
-				"ibm,ppc-interrupt-server#s", cpu, thread))
-			return cpun;
-		if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+	for_each_node_by_type(cpun, "cpu") {
+		if (arch_find_n_match_cpu_physical_id(cpun, cpu, thread))
 			return cpun;
 	}
 	return NULL;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 801ff9e73679..fbd25c3c2923 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -18,6 +18,7 @@
 #include <linux/cpumask.h>
 
 struct device;
+struct device_node;
 
 struct cpu {
 	int node_id;		/* The node which contains the CPU */
@@ -29,6 +30,8 @@ extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
 extern bool cpu_is_hotpluggable(unsigned cpu);
 extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id);
+extern bool arch_find_n_match_cpu_physical_id(struct device_node *cpun,
+					      int cpu, unsigned int *thread);
 
 extern int cpu_add_dev_attr(struct device_attribute *attr);
 extern void cpu_remove_dev_attr(struct device_attribute *attr);
-- 
cgit 


From 6461f018e7ad08863b55c386bf694683e4e2e86e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 2 Oct 2013 14:13:17 +0530
Subject: cpufreq: rewrite cpufreq_driver->flags using shift operator

Currently cpufreq_driver's flags are defined directly using 0x1, 0x2, 0x4, 0x8,
etc.. As the list grows it becomes less readable..

Use bitwise shift operator << to generate these numbers for respective
positions.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpufreq.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 6b199ed7aa58..00c80a5372db 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -211,13 +211,14 @@ struct cpufreq_driver {
 };
 
 /* flags */
-#define CPUFREQ_STICKY		0x01	/* the driver isn't removed even if
-					 * all ->init() calls failed */
-#define CPUFREQ_CONST_LOOPS	0x02	/* loops_per_jiffy or other kernel
-					 * "constants" aren't affected by
-					 * frequency transitions */
-#define CPUFREQ_PM_NO_WARN	0x04	/* don't warn on suspend/resume speed
-					 * mismatches */
+#define CPUFREQ_STICKY		(1 << 0)	/* driver isn't removed even if
+						   all ->init() calls failed */
+#define CPUFREQ_CONST_LOOPS	(1 << 1)	/* loops_per_jiffy or other
+						   kernel "constants" aren't
+						   affected by frequency
+						   transitions */
+#define CPUFREQ_PM_NO_WARN	(1 << 2)	/* don't warn on suspend/resume
+						   speed mismatches */
 
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
-- 
cgit 


From 0b981e70748861a3e10ea2e2a689bdcee3e15085 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 2 Oct 2013 14:13:18 +0530
Subject: cpufreq: use cpufreq_driver->flags to mark
 CPUFREQ_HAVE_GOVERNOR_PER_POLICY

Use cpufreq_driver->flags to mark CPUFREQ_HAVE_GOVERNOR_PER_POLICY instead
of a separate field within cpufreq_driver. This will save some bytes of
memory.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/arm_big_little.c   |  4 ++--
 drivers/cpufreq/cpufreq.c          |  2 +-
 drivers/cpufreq/cpufreq_governor.h |  5 ++++-
 include/linux/cpufreq.h            | 15 ++++++++-------
 4 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 9acfb82c1cfb..2c7c13494825 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -213,13 +213,13 @@ static struct freq_attr *bL_cpufreq_attr[] = {
 
 static struct cpufreq_driver bL_cpufreq_driver = {
 	.name			= "arm-big-little",
-	.flags			= CPUFREQ_STICKY,
+	.flags			= CPUFREQ_STICKY |
+					CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
 	.verify			= bL_cpufreq_verify_policy,
 	.target			= bL_cpufreq_set_target,
 	.get			= bL_cpufreq_get,
 	.init			= bL_cpufreq_init,
 	.exit			= bL_cpufreq_exit,
-	.have_governor_per_policy = true,
 	.attr			= bL_cpufreq_attr,
 };
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3a811df43e14..fc9110c9f10d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -133,7 +133,7 @@ static DEFINE_MUTEX(cpufreq_governor_mutex);
 
 bool have_governor_per_policy(void)
 {
-	return cpufreq_driver->have_governor_per_policy;
+	return !!(cpufreq_driver->flags & CPUFREQ_HAVE_GOVERNOR_PER_POLICY);
 }
 EXPORT_SYMBOL_GPL(have_governor_per_policy);
 
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 88cd39f7b0e9..b5f2b8618949 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -191,7 +191,10 @@ struct common_dbs_data {
 	struct attribute_group *attr_group_gov_sys; /* one governor - system */
 	struct attribute_group *attr_group_gov_pol; /* one governor - policy */
 
-	/* Common data for platforms that don't set have_governor_per_policy */
+	/*
+	 * Common data for platforms that don't set
+	 * CPUFREQ_HAVE_GOVERNOR_PER_POLICY
+	 */
 	struct dbs_data *gdbs_data;
 
 	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 00c80a5372db..24b84f7e7f8d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -180,13 +180,6 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 struct cpufreq_driver {
 	char			name[CPUFREQ_NAME_LEN];
 	u8			flags;
-	/*
-	 * This should be set by platforms having multiple clock-domains, i.e.
-	 * supporting multiple policies. With this sysfs directories of governor
-	 * would be created in cpu/cpu<num>/cpufreq/ directory and so they can
-	 * use the same governor with different tunables for different clusters.
-	 */
-	bool			have_governor_per_policy;
 
 	/* needed by all drivers */
 	int	(*init)		(struct cpufreq_policy *policy);
@@ -220,6 +213,14 @@ struct cpufreq_driver {
 #define CPUFREQ_PM_NO_WARN	(1 << 2)	/* don't warn on suspend/resume
 						   speed mismatches */
 
+/*
+ * This should be set by platforms having multiple clock-domains, i.e.
+ * supporting multiple policies. With this sysfs directories of governor would
+ * be created in cpu/cpu<num>/cpufreq/ directory and so they can use the same
+ * governor with different tunables for different clusters.
+ */
+#define CPUFREQ_HAVE_GOVERNOR_PER_POLICY (1 << 3)
+
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
-- 
cgit 


From be49e3465f222b4b796be8a21d14afbfd8f5d20f Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 2 Oct 2013 14:13:19 +0530
Subject: cpufreq: add new routine cpufreq_verify_within_cpu_limits()

Most of the users of cpufreq_verify_within_limits() calls it for
limiting with min/max from policy->cpuinfo. We can make that code
simple by introducing another routine which will do this for them
automatically.

This patch adds another routine cpufreq_verify_within_cpu_limits()
and updates others to use it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Dirk Brandewie <dirk.j.brandewie@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq-nforce2.c    | 4 +---
 drivers/cpufreq/davinci-cpufreq.c    | 4 +---
 drivers/cpufreq/freq_table.c         | 6 ++----
 drivers/cpufreq/integrator-cpufreq.c | 9 ++-------
 drivers/cpufreq/intel_pstate.c       | 4 +---
 drivers/cpufreq/longrun.c            | 4 +---
 drivers/cpufreq/pcc-cpufreq.c        | 3 +--
 drivers/cpufreq/sh-cpufreq.c         | 7 ++-----
 drivers/cpufreq/unicore2-cpufreq.c   | 4 +---
 include/linux/cpufreq.h              | 7 +++++++
 10 files changed, 19 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index b83d45f68574..56c964c16a66 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -303,9 +303,7 @@ static int nforce2_verify(struct cpufreq_policy *policy)
 	if (policy->min < (fsb_pol_max * fid * 100))
 		policy->max = (fsb_pol_max + 1) * fid * 100;
 
-	cpufreq_verify_within_limits(policy,
-				     policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index f67196e21fc9..ba03e6f91d47 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -50,9 +50,7 @@ static int davinci_verify_speed(struct cpufreq_policy *policy)
 	if (policy->cpu)
 		return -EINVAL;
 
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
-
+	cpufreq_verify_within_cpu_limits(policy);
 	policy->min = clk_round_rate(armclk, policy->min * 1000) / 1000;
 	policy->max = clk_round_rate(armclk, policy->max * 1000) / 1000;
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 10f3cfb6b513..b9336edb9bd6 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -60,8 +60,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 	pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n",
 					policy->min, policy->max, policy->cpu);
 
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 
 	for (; freq = table[i].frequency, freq != CPUFREQ_TABLE_END; i++) {
 		if (freq == CPUFREQ_ENTRY_INVALID)
@@ -77,8 +76,7 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 
 	if (!found) {
 		policy->max = next_larger;
-		cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				policy->cpuinfo.max_freq);
+		cpufreq_verify_within_cpu_limits(policy);
 	}
 
 	pr_debug("verification lead to (%u - %u kHz) for cpu %u\n",
diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c
index f7c99df0880b..8152a9bb7e2c 100644
--- a/drivers/cpufreq/integrator-cpufreq.c
+++ b/drivers/cpufreq/integrator-cpufreq.c
@@ -59,9 +59,7 @@ static int integrator_verify_policy(struct cpufreq_policy *policy)
 {
 	struct icst_vco vco;
 
-	cpufreq_verify_within_limits(policy, 
-				     policy->cpuinfo.min_freq, 
-				     policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 
 	vco = icst_hz_to_vco(&cclk_params, policy->max * 1000);
 	policy->max = icst_hz(&cclk_params, vco) / 1000;
@@ -69,10 +67,7 @@ static int integrator_verify_policy(struct cpufreq_policy *policy)
 	vco = icst_hz_to_vco(&cclk_params, policy->min * 1000);
 	policy->min = icst_hz(&cclk_params, vco) / 1000;
 
-	cpufreq_verify_within_limits(policy, 
-				     policy->cpuinfo.min_freq, 
-				     policy->cpuinfo.max_freq);
-
+	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9733f29ed148..a02bd77cbfe8 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -611,9 +611,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 {
-	cpufreq_verify_within_limits(policy,
-				policy->cpuinfo.min_freq,
-				policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 
 	if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
 		(policy->policy != CPUFREQ_POLICY_PERFORMANCE))
diff --git a/drivers/cpufreq/longrun.c b/drivers/cpufreq/longrun.c
index 5aa031612d53..074971b12635 100644
--- a/drivers/cpufreq/longrun.c
+++ b/drivers/cpufreq/longrun.c
@@ -129,9 +129,7 @@ static int longrun_verify_policy(struct cpufreq_policy *policy)
 		return -EINVAL;
 
 	policy->cpu = 0;
-	cpufreq_verify_within_limits(policy,
-		policy->cpuinfo.min_freq,
-		policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 
 	if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
 	    (policy->policy != CPUFREQ_POLICY_PERFORMANCE))
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index d81c4e5ea0ad..78787e965e0b 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -111,8 +111,7 @@ static struct pcc_cpu __percpu *pcc_cpu_info;
 
 static int pcc_cpufreq_verify(struct cpufreq_policy *policy)
 {
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 1362e8894ee1..f1fb944d714c 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -87,15 +87,12 @@ static int sh_cpufreq_verify(struct cpufreq_policy *policy)
 	if (freq_table)
 		return cpufreq_frequency_table_verify(policy, freq_table);
 
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
+	cpufreq_verify_within_cpu_limits(policy);
 
 	policy->min = (clk_round_rate(cpuclk, 1) + 500) / 1000;
 	policy->max = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
 
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     policy->cpuinfo.max_freq);
-
+	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c
index b225f04d8ae5..14e6d3106355 100644
--- a/drivers/cpufreq/unicore2-cpufreq.c
+++ b/drivers/cpufreq/unicore2-cpufreq.c
@@ -29,9 +29,7 @@ static int ucv2_verify_speed(struct cpufreq_policy *policy)
 	if (policy->cpu)
 		return -EINVAL;
 
-	cpufreq_verify_within_limits(policy,
-			policy->cpuinfo.min_freq, policy->cpuinfo.max_freq);
-
+	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 24b84f7e7f8d..c7495915932d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -242,6 +242,13 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
 	return;
 }
 
+static inline void
+cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
+{
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+			policy->cpuinfo.max_freq);
+}
+
 /*********************************************************************
  *                     CPUFREQ NOTIFIER INTERFACE                    *
  *********************************************************************/
-- 
cgit 


From 184345129c53e76069c209f9912ed7c457eceb31 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 3 Oct 2013 20:27:55 +0530
Subject: cpufreq: define generic .attr, .exit() and .verify() routines

Most of the CPUFreq drivers do similar things in .exit() and .verify() routines
and .attr. So its better if we have generic routines for them which can be used
by cpufreq drivers then.

This patch introduces generic .attr, .exit() and .verify() cpufreq drivers.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/freq_table.c | 20 ++++++++++++++++++++
 include/linux/cpufreq.h      |  8 ++++++++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index b9336edb9bd6..3458d27f63b4 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -86,6 +86,20 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
 
+/*
+ * Generic routine to verify policy & frequency table, requires driver to call
+ * cpufreq_frequency_table_get_attr() prior to it.
+ */
+int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *table =
+		cpufreq_frequency_get_table(policy->cpu);
+	if (!table)
+		return -ENODEV;
+
+	return cpufreq_frequency_table_verify(policy, table);
+}
+EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
 
 int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table,
@@ -199,6 +213,12 @@ struct freq_attr cpufreq_freq_attr_scaling_available_freqs = {
 };
 EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
 
+struct freq_attr *cpufreq_generic_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
+
 /*
  * if you use these, you must assure that the frequency table is valid
  * all the time between get_attr and put_attr!
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index c7495915932d..36ccd0bf1304 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -401,6 +401,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 
 int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table);
+int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy);
 
 int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 				   struct cpufreq_frequency_table *table,
@@ -416,10 +417,17 @@ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
+extern struct freq_attr *cpufreq_generic_attr[];
 void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
 				      unsigned int cpu);
 void cpufreq_frequency_table_put_attr(unsigned int cpu);
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table);
 
+static inline int cpufreq_generic_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
 #endif /* _LINUX_CPUFREQ_H */
-- 
cgit 


From 70e9e778337973d5bf57004092b360bd3f3c412f Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 3 Oct 2013 20:29:07 +0530
Subject: cpufreq: create cpufreq_generic_init() routine

Many CPUFreq drivers for SMP system (where all cores share same clock lines), do
similar stuff in their ->init() part.

This patch creates a generic routine in cpufreq core which can be used by these
so that we can remove some redundant code.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/Kconfig   |  1 +
 drivers/cpufreq/cpufreq.c | 31 +++++++++++++++++++++++++++++++
 include/linux/cpufreq.h   |  3 +++
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 534fcb825153..2d06754f4a04 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -2,6 +2,7 @@ menu "CPU Frequency scaling"
 
 config CPU_FREQ
 	bool "CPU Frequency scaling"
+	select CPU_FREQ_TABLE
 	help
 	  CPU Frequency scaling allows you to change the clock speed of 
 	  CPUs on the fly. This is a nice method to save power, because 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f033adf06eaf..985f325adc4f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -181,6 +181,37 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
+/*
+ * This is a generic cpufreq init() routine which can be used by cpufreq
+ * drivers of SMP systems. It will do following:
+ * - validate & show freq table passed
+ * - set policies transition latency
+ * - policy->cpus with all possible CPUs
+ */
+int cpufreq_generic_init(struct cpufreq_policy *policy,
+		struct cpufreq_frequency_table *table,
+		unsigned int transition_latency)
+{
+	int ret;
+
+	ret = cpufreq_table_validate_and_show(policy, table);
+	if (ret) {
+		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
+		return ret;
+	}
+
+	policy->cpuinfo.transition_latency = transition_latency;
+
+	/*
+	 * The driver only supports the SMP configuartion where all processors
+	 * share the clock and voltage and clock.
+	 */
+	cpumask_setall(policy->cpus);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_generic_init);
+
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 36ccd0bf1304..0aba2a6cadaf 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -424,6 +424,9 @@ void cpufreq_frequency_table_put_attr(unsigned int cpu);
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table);
 
+int cpufreq_generic_init(struct cpufreq_policy *policy,
+		struct cpufreq_frequency_table *table,
+		unsigned int transition_latency);
 static inline int cpufreq_generic_exit(struct cpufreq_policy *policy)
 {
 	cpufreq_frequency_table_put_attr(policy->cpu);
-- 
cgit 


From 5915a3db0c3983f1cd5e046bf70086c7d0c686d2 Mon Sep 17 00:00:00 2001
From: Aaron Lu <aaron.lu@intel.com>
Date: Fri, 11 Oct 2013 21:27:43 +0800
Subject: backlight: introduce backlight_device_registered

Introduce a new API for modules to query if a specific type of backlight
device has been registered. This is useful for some backlight device
provider module (e.g. ACPI video) to know if a native control
interface(e.g. the interface created by i915) is available and then do
things accordingly (e.g. avoid registering its own on Win8 systems).

Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/video/backlight/backlight.c | 31 +++++++++++++++++++++++++++++++
 include/linux/backlight.h           |  4 ++++
 2 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index 94a403a9717a..5d05555fe841 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -21,6 +21,9 @@
 #include <asm/backlight.h>
 #endif
 
+static struct list_head backlight_dev_list;
+static struct mutex backlight_dev_list_mutex;
+
 static const char *const backlight_types[] = {
 	[BACKLIGHT_RAW] = "raw",
 	[BACKLIGHT_PLATFORM] = "platform",
@@ -349,10 +352,32 @@ struct backlight_device *backlight_device_register(const char *name,
 	mutex_unlock(&pmac_backlight_mutex);
 #endif
 
+	mutex_lock(&backlight_dev_list_mutex);
+	list_add(&new_bd->entry, &backlight_dev_list);
+	mutex_unlock(&backlight_dev_list_mutex);
+
 	return new_bd;
 }
 EXPORT_SYMBOL(backlight_device_register);
 
+bool backlight_device_registered(enum backlight_type type)
+{
+	bool found = false;
+	struct backlight_device *bd;
+
+	mutex_lock(&backlight_dev_list_mutex);
+	list_for_each_entry(bd, &backlight_dev_list, entry) {
+		if (bd->props.type == type) {
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&backlight_dev_list_mutex);
+
+	return found;
+}
+EXPORT_SYMBOL(backlight_device_registered);
+
 /**
  * backlight_device_unregister - unregisters a backlight device object.
  * @bd: the backlight device object to be unregistered and freed.
@@ -364,6 +389,10 @@ void backlight_device_unregister(struct backlight_device *bd)
 	if (!bd)
 		return;
 
+	mutex_lock(&backlight_dev_list_mutex);
+	list_del(&bd->entry);
+	mutex_unlock(&backlight_dev_list_mutex);
+
 #ifdef CONFIG_PMAC_BACKLIGHT
 	mutex_lock(&pmac_backlight_mutex);
 	if (pmac_backlight == bd)
@@ -499,6 +528,8 @@ static int __init backlight_class_init(void)
 
 	backlight_class->dev_groups = bl_device_groups;
 	backlight_class->pm = &backlight_class_dev_pm_ops;
+	INIT_LIST_HEAD(&backlight_dev_list);
+	mutex_init(&backlight_dev_list_mutex);
 	return 0;
 }
 
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 53b77949c79d..5f9cd963213d 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -100,6 +100,9 @@ struct backlight_device {
 	/* The framebuffer notifier block */
 	struct notifier_block fb_notif;
 
+	/* list entry of all registered backlight devices */
+	struct list_head entry;
+
 	struct device dev;
 };
 
@@ -123,6 +126,7 @@ extern void devm_backlight_device_unregister(struct device *dev,
 					struct backlight_device *bd);
 extern void backlight_force_update(struct backlight_device *bd,
 				   enum backlight_update_reason reason);
+extern bool backlight_device_registered(enum backlight_type type);
 
 #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev)
 
-- 
cgit 


From 53f5212121fc3bcd0bccb8841c01e08ca942f333 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Tue, 15 Oct 2013 19:24:45 -0300
Subject: Bluetooth: Extend state_change() call to report errors too

Instead of creating an new function pointer to report errors we are just
reusing state_change for that and there is a simple reason for this, one
place in the l2cap_core.c code needs, in a locked sk, set both the sk_state
and sk_err. If we create two different functions for this we would need to
release the lock between the two operation putting the socket in non
desired state.

The change is transparent to the l2cap_core.c code, user that only needs
to set the state won't need any modification.

This is another step of an ongoing work to make l2cap_core.c totally
independent from l2cap's struct sock.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 2 +-
 net/bluetooth/a2mp.c          | 3 ++-
 net/bluetooth/l2cap_core.c    | 6 ++----
 net/bluetooth/l2cap_sock.c    | 6 +++++-
 4 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 07757a2af942..4ec86cec8914 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -551,7 +551,7 @@ struct l2cap_ops {
 	void			(*teardown) (struct l2cap_chan *chan, int err);
 	void			(*close) (struct l2cap_chan *chan);
 	void			(*state_change) (struct l2cap_chan *chan,
-						 int state);
+						 int state, int err);
 	void			(*ready) (struct l2cap_chan *chan);
 	void			(*defer) (struct l2cap_chan *chan);
 	void			(*resume) (struct l2cap_chan *chan);
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 60ca52819247..6b8cc23787e2 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -672,7 +672,8 @@ static void a2mp_chan_close_cb(struct l2cap_chan *chan)
 	l2cap_chan_put(chan);
 }
 
-static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state)
+static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state,
+				      int err)
 {
 	struct amp_mgr *mgr = chan->data;
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 0c3446da1ec9..df5670d8e11d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -229,7 +229,7 @@ static void __l2cap_state_change(struct l2cap_chan *chan, int state)
 	       state_to_string(state));
 
 	chan->state = state;
-	chan->ops->state_change(chan, state);
+	chan->ops->state_change(chan, state, 0);
 }
 
 static void l2cap_state_change(struct l2cap_chan *chan, int state)
@@ -243,9 +243,7 @@ static void l2cap_state_change(struct l2cap_chan *chan, int state)
 
 static inline void __l2cap_chan_set_err(struct l2cap_chan *chan, int err)
 {
-	struct sock *sk = chan->sk;
-
-	sk->sk_err = err;
+	chan->ops->state_change(chan, chan->state, err);
 }
 
 static inline void l2cap_chan_set_err(struct l2cap_chan *chan, int err)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 5ffd75e20bde..0de8a30c06a1 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1072,11 +1072,15 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 	release_sock(sk);
 }
 
-static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state)
+static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state,
+				       int err)
 {
 	struct sock *sk = chan->data;
 
 	sk->sk_state = state;
+
+	if (err)
+		sk->sk_err = err;
 }
 
 static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
-- 
cgit 


From 8d836d71e2223b8961b21112bb4ce89ef8231682 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Tue, 15 Oct 2013 19:24:47 -0300
Subject: Bluetooth: Access sk_sndtimeo indirectly in l2cap_core.c

As part of the work to remove struct sock from l2cap_core.c and make it
more generic we remove in this commit the direct access to sk->sk_sndtimeo
member. This objective of this change is purely remove sk usage from
l2cap_core.c

Now we have a new l2cap ops to get the current value of sk->sndtimeo. A
l2cap_chan_no_get_sndtimeo was added for users of L2CAP that doesn't need
to set a timeout.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 6 ++++++
 net/bluetooth/a2mp.c          | 1 +
 net/bluetooth/l2cap_core.c    | 8 +++-----
 net/bluetooth/l2cap_sock.c    | 8 ++++++++
 4 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 4ec86cec8914..9c6be72b6e4e 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -555,6 +555,7 @@ struct l2cap_ops {
 	void			(*ready) (struct l2cap_chan *chan);
 	void			(*defer) (struct l2cap_chan *chan);
 	void			(*resume) (struct l2cap_chan *chan);
+	long			(*get_sndtimeo) (struct l2cap_chan *chan);
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long len, int nb);
 };
@@ -795,6 +796,11 @@ static inline void l2cap_chan_no_defer(struct l2cap_chan *chan)
 {
 }
 
+static inline long l2cap_chan_no_get_sndtimeo(struct l2cap_chan *chan)
+{
+	return 0;
+}
+
 extern bool disable_ertm;
 
 int l2cap_init_sockets(void);
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 6b8cc23787e2..1e9921024a1d 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -710,6 +710,7 @@ static struct l2cap_ops a2mp_chan_ops = {
 	.teardown = l2cap_chan_no_teardown,
 	.ready = l2cap_chan_no_ready,
 	.defer = l2cap_chan_no_defer,
+	.get_sndtimeo = l2cap_chan_no_get_sndtimeo,
 };
 
 static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index f4e02b453984..c6334fc86d1d 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -649,8 +649,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason)
 	case BT_CONFIG:
 		if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED &&
 		    conn->hcon->type == ACL_LINK) {
-			struct sock *sk = chan->sk;
-			__set_chan_timer(chan, sk->sk_sndtimeo);
+			__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
 			l2cap_send_disconn_req(chan, reason);
 		} else
 			l2cap_chan_del(chan, reason);
@@ -1764,7 +1763,6 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
 int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 		       bdaddr_t *dst, u8 dst_type)
 {
-	struct sock *sk = chan->sk;
 	struct l2cap_conn *conn;
 	struct hci_conn *hcon;
 	struct hci_dev *hdev;
@@ -1876,7 +1874,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 	hci_conn_drop(hcon);
 
 	l2cap_state_change(chan, BT_CONNECT);
-	__set_chan_timer(chan, sk->sk_sndtimeo);
+	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
 
 	if (hcon->state == BT_CONNECTED) {
 		if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) {
@@ -3817,7 +3815,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn,
 
 	dcid = chan->scid;
 
-	__set_chan_timer(chan, sk->sk_sndtimeo);
+	__set_chan_timer(chan, chan->ops->get_sndtimeo(chan));
 
 	chan->ident = cmd->ident;
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 0de8a30c06a1..ffa78d3cd8ac 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1136,6 +1136,13 @@ static void l2cap_sock_resume_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static long l2cap_sock_get_sndtimeo_cb(struct l2cap_chan *chan)
+{
+	struct sock *sk = chan->data;
+
+	return sk->sk_sndtimeo;
+}
+
 static struct l2cap_ops l2cap_chan_ops = {
 	.name		= "L2CAP Socket Interface",
 	.new_connection	= l2cap_sock_new_connection_cb,
@@ -1146,6 +1153,7 @@ static struct l2cap_ops l2cap_chan_ops = {
 	.ready		= l2cap_sock_ready_cb,
 	.defer		= l2cap_sock_defer_cb,
 	.resume		= l2cap_sock_resume_cb,
+	.get_sndtimeo	= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb	= l2cap_sock_alloc_skb_cb,
 };
 
-- 
cgit 


From 5ec1bbe549d939ff1ef88e2cc22b2c3b95d76401 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Tue, 15 Oct 2013 19:24:48 -0300
Subject: Bluetooth: Add chan->ops->set_shutdown()

We need to remove all direct access of struct sock from L2CAP core.
This change is pretty simple and just add a new L2CAP channel callback to
do the work in the L2CAP socket side.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  5 +++++
 net/bluetooth/a2mp.c          |  1 +
 net/bluetooth/l2cap_core.c    |  7 +------
 net/bluetooth/l2cap_sock.c    | 10 ++++++++++
 4 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 9c6be72b6e4e..ae3a99bc31d0 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -555,6 +555,7 @@ struct l2cap_ops {
 	void			(*ready) (struct l2cap_chan *chan);
 	void			(*defer) (struct l2cap_chan *chan);
 	void			(*resume) (struct l2cap_chan *chan);
+	void			(*set_shutdown) (struct l2cap_chan *chan);
 	long			(*get_sndtimeo) (struct l2cap_chan *chan);
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long len, int nb);
@@ -796,6 +797,10 @@ static inline void l2cap_chan_no_defer(struct l2cap_chan *chan)
 {
 }
 
+static inline void l2cap_chan_no_set_shutdown(struct l2cap_chan *chan)
+{
+}
+
 static inline long l2cap_chan_no_get_sndtimeo(struct l2cap_chan *chan)
 {
 	return 0;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 1e9921024a1d..74c14779bed6 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -710,6 +710,7 @@ static struct l2cap_ops a2mp_chan_ops = {
 	.teardown = l2cap_chan_no_teardown,
 	.ready = l2cap_chan_no_ready,
 	.defer = l2cap_chan_no_defer,
+	.set_shutdown = l2cap_chan_no_set_shutdown,
 	.get_sndtimeo = l2cap_chan_no_get_sndtimeo,
 };
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c6334fc86d1d..634781a60d3f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4241,7 +4241,6 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,
 	struct l2cap_disconn_rsp rsp;
 	u16 dcid, scid;
 	struct l2cap_chan *chan;
-	struct sock *sk;
 
 	if (cmd_len != sizeof(*req))
 		return -EPROTO;
@@ -4261,15 +4260,11 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn,
 
 	l2cap_chan_lock(chan);
 
-	sk = chan->sk;
-
 	rsp.dcid = cpu_to_le16(chan->scid);
 	rsp.scid = cpu_to_le16(chan->dcid);
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp);
 
-	lock_sock(sk);
-	sk->sk_shutdown = SHUTDOWN_MASK;
-	release_sock(sk);
+	chan->ops->set_shutdown(chan);
 
 	l2cap_chan_hold(chan);
 	l2cap_chan_del(chan, ECONNRESET);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index ffa78d3cd8ac..301f25b9b521 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1136,6 +1136,15 @@ static void l2cap_sock_resume_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static void l2cap_sock_set_shutdown_cb(struct l2cap_chan *chan)
+{
+	struct sock *sk = chan->data;
+
+	lock_sock(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
+	release_sock(sk);
+}
+
 static long l2cap_sock_get_sndtimeo_cb(struct l2cap_chan *chan)
 {
 	struct sock *sk = chan->data;
@@ -1153,6 +1162,7 @@ static struct l2cap_ops l2cap_chan_ops = {
 	.ready		= l2cap_sock_ready_cb,
 	.defer		= l2cap_sock_defer_cb,
 	.resume		= l2cap_sock_resume_cb,
+	.set_shutdown	= l2cap_sock_set_shutdown_cb,
 	.get_sndtimeo	= l2cap_sock_get_sndtimeo_cb,
 	.alloc_skb	= l2cap_sock_alloc_skb_cb,
 };
-- 
cgit 


From dc25306b033cc27ca2a45b4bb307a437092408d1 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Tue, 15 Oct 2013 19:24:49 -0300
Subject: Bluetooth: Move l2cap_wait_ack() to l2cap_sock.c

The wait_ack code has a heavy dependency on the socket data structures
and, as of now, it won't be worthless change it to use non-socket
structures as the only user of such feature is a socket.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  1 -
 net/bluetooth/l2cap_core.c    | 32 --------------------------------
 net/bluetooth/l2cap_sock.c    | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 32 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ae3a99bc31d0..377db2aa89f9 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -813,7 +813,6 @@ void l2cap_cleanup_sockets(void);
 bool l2cap_is_socket(struct socket *sock);
 
 void __l2cap_connect_rsp_defer(struct l2cap_chan *chan);
-int __l2cap_wait_ack(struct sock *sk);
 
 int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm);
 int l2cap_add_scid(struct l2cap_chan *chan,  __u16 scid);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 634781a60d3f..39f02c08a882 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1894,38 +1894,6 @@ done:
 	return err;
 }
 
-int __l2cap_wait_ack(struct sock *sk)
-{
-	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
-	DECLARE_WAITQUEUE(wait, current);
-	int err = 0;
-	int timeo = HZ/5;
-
-	add_wait_queue(sk_sleep(sk), &wait);
-	set_current_state(TASK_INTERRUPTIBLE);
-	while (chan->unacked_frames > 0 && chan->conn) {
-		if (!timeo)
-			timeo = HZ/5;
-
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeo);
-			break;
-		}
-
-		release_sock(sk);
-		timeo = schedule_timeout(timeo);
-		lock_sock(sk);
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		err = sock_error(sk);
-		if (err)
-			break;
-	}
-	set_current_state(TASK_RUNNING);
-	remove_wait_queue(sk_sleep(sk), &wait);
-	return err;
-}
-
 static void l2cap_monitor_timeout(struct work_struct *work)
 {
 	struct l2cap_chan *chan = container_of(work, struct l2cap_chan,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 301f25b9b521..68f486a586ff 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -879,6 +879,38 @@ static void l2cap_sock_kill(struct sock *sk)
 	sock_put(sk);
 }
 
+static int __l2cap_wait_ack(struct sock *sk)
+{
+	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
+	DECLARE_WAITQUEUE(wait, current);
+	int err = 0;
+	int timeo = HZ/5;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (chan->unacked_frames > 0 && chan->conn) {
+		if (!timeo)
+			timeo = HZ/5;
+
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeo);
+			break;
+		}
+
+		release_sock(sk);
+		timeo = schedule_timeout(timeo);
+		lock_sock(sk);
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		err = sock_error(sk);
+		if (err)
+			break;
+	}
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return err;
+}
+
 static int l2cap_sock_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
-- 
cgit 


From 2ce5fb510fc0ba50c8e1b6bcb991848084ea67ec Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 16:47:11 -0700
Subject: Bluetooth: Add l2cap_chan_no_resume stub for A2MP

The A2MP client for L2CAP channels needs to use l2cap_chan_no_resume
empty stub function.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/l2cap.h | 4 ++++
 net/bluetooth/a2mp.c          | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 377db2aa89f9..3d922b938141 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -797,6 +797,10 @@ static inline void l2cap_chan_no_defer(struct l2cap_chan *chan)
 {
 }
 
+static inline void l2cap_chan_no_resume(struct l2cap_chan *chan)
+{
+}
+
 static inline void l2cap_chan_no_set_shutdown(struct l2cap_chan *chan)
 {
 }
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 74c14779bed6..fe32a334a52d 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -710,6 +710,7 @@ static struct l2cap_ops a2mp_chan_ops = {
 	.teardown = l2cap_chan_no_teardown,
 	.ready = l2cap_chan_no_ready,
 	.defer = l2cap_chan_no_defer,
+	.resume = l2cap_chan_no_resume,
 	.set_shutdown = l2cap_chan_no_set_shutdown,
 	.get_sndtimeo = l2cap_chan_no_get_sndtimeo,
 };
-- 
cgit 


From ce0e4a0d7b84d4ceebc91f97de8c08da23a7bda3 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:20 -0700
Subject: Bluetooth: Make mgmt_pin_code_request() return void

The return value of mgmt_pin_code_request() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/mgmt.c             | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index fc04bc846617..a167a9dda7c7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1087,7 +1087,7 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 link_type, u8 addr_type, u8 status);
 void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			 u8 addr_type, u8 status);
-int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
+void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
 int mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				 u8 status);
 int mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ca3cdb520b2f..efa2c524fcf8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4533,7 +4533,7 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL);
 }
 
-int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
+void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
 {
 	struct mgmt_ev_pin_code_request ev;
 
@@ -4541,8 +4541,7 @@ int mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
 	ev.addr.type = BDADDR_BREDR;
 	ev.secure = secure;
 
-	return mgmt_event(MGMT_EV_PIN_CODE_REQUEST, hdev, &ev, sizeof(ev),
-			  NULL);
+	mgmt_event(MGMT_EV_PIN_CODE_REQUEST, hdev, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-- 
cgit 


From e669cf803cb14d63d0b7c612286e5cfdec6e34f7 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:21 -0700
Subject: Bluetooth: Make mgmt_pin_code_reply_complete() return void

The return value of mgmt_pin_code_reply_complete() function is not
used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 13 +++++--------
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a167a9dda7c7..95baf3561dad 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1088,8 +1088,8 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			 u8 addr_type, u8 status);
 void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
-int mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				 u8 status);
+void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				  u8 status);
 int mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				     u8 status);
 int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index efa2c524fcf8..608aa0f8bf7b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4544,26 +4544,23 @@ void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure)
 	mgmt_event(MGMT_EV_PIN_CODE_REQUEST, hdev, &ev, sizeof(ev), NULL);
 }
 
-int mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				 u8 status)
+void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				  u8 status)
 {
 	struct pending_cmd *cmd;
 	struct mgmt_rp_pin_code_reply rp;
-	int err;
 
 	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_REPLY, hdev);
 	if (!cmd)
-		return -ENOENT;
+		return;
 
 	bacpy(&rp.addr.bdaddr, bdaddr);
 	rp.addr.type = BDADDR_BREDR;
 
-	err = cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
-			   mgmt_status(status), &rp, sizeof(rp));
+	cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_REPLY,
+		     mgmt_status(status), &rp, sizeof(rp));
 
 	mgmt_pending_remove(cmd);
-
-	return err;
 }
 
 int mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-- 
cgit 


From 3eb385289a8b71db40b1a4a4d739817bd437db4f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:22 -0700
Subject: Bluetooth: Make mgmt_pin_code_neg_reply_complete() return void

The return value of mgmt_pin_code_neg_reply_complete() function is
not used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 13 +++++--------
 2 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 95baf3561dad..aaa897f3b50a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1090,8 +1090,8 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
 void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				  u8 status);
-int mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 status);
+void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				      u8 status);
 int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			      u8 link_type, u8 addr_type, __le32 value,
 			      u8 confirm_hint);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 608aa0f8bf7b..c959915d308e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4563,26 +4563,23 @@ void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	mgmt_pending_remove(cmd);
 }
 
-int mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
-				     u8 status)
+void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				      u8 status)
 {
 	struct pending_cmd *cmd;
 	struct mgmt_rp_pin_code_reply rp;
-	int err;
 
 	cmd = mgmt_pending_find(MGMT_OP_PIN_CODE_NEG_REPLY, hdev);
 	if (!cmd)
-		return -ENOENT;
+		return;
 
 	bacpy(&rp.addr.bdaddr, bdaddr);
 	rp.addr.type = BDADDR_BREDR;
 
-	err = cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_NEG_REPLY,
-			   mgmt_status(status), &rp, sizeof(rp));
+	cmd_complete(cmd->sk, hdev->id, MGMT_OP_PIN_CODE_NEG_REPLY,
+		     mgmt_status(status), &rp, sizeof(rp));
 
 	mgmt_pending_remove(cmd);
-
-	return err;
 }
 
 int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr,
-- 
cgit 


From e546099c3194ef6ecf46a8a50414005c29a46bc4 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:23 -0700
Subject: Bluetooth: Make mgmt_auth_failed() return void

The return value of mgmt_auth_failed() function is not used
and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 net/bluetooth/mgmt.c             | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index aaa897f3b50a..c7427160c7c2 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1108,8 +1108,8 @@ int mgmt_user_passkey_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 link_type, u8 addr_type, u32 passkey,
 			     u8 entered);
-int mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		     u8 addr_type, u8 status);
+void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		      u8 addr_type, u8 status);
 int mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c959915d308e..3c4499041aeb 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4681,8 +4681,8 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	return mgmt_event(MGMT_EV_PASSKEY_NOTIFY, hdev, &ev, sizeof(ev), NULL);
 }
 
-int mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		     u8 addr_type, u8 status)
+void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+		      u8 addr_type, u8 status)
 {
 	struct mgmt_ev_auth_failed ev;
 
@@ -4690,7 +4690,7 @@ int mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.status = mgmt_status(status);
 
-	return mgmt_event(MGMT_EV_AUTH_FAILED, hdev, &ev, sizeof(ev), NULL);
+	mgmt_event(MGMT_EV_AUTH_FAILED, hdev, &ev, sizeof(ev), NULL);
 }
 
 int mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
-- 
cgit 


From 464996aea48aa1ec3d7d60098dbb0f7623da6c92 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:24 -0700
Subject: Bluetooth: Make mgmt_auth_enable_complete() return void

The return value of mgmt_auth_enable_complete() function is not
used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/mgmt.c             | 24 ++++++++++--------------
 2 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c7427160c7c2..3ee5691b247f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1110,7 +1110,7 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			     u8 entered);
 void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, u8 status);
-int mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
+void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				   u8 status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3c4499041aeb..0672a8cb662e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4693,37 +4693,33 @@ void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	mgmt_event(MGMT_EV_AUTH_FAILED, hdev, &ev, sizeof(ev), NULL);
 }
 
-int mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
+void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
 {
 	struct cmd_lookup match = { NULL, hdev };
-	bool changed = false;
-	int err = 0;
+	bool changed;
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
 		mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev,
 				     cmd_status_rsp, &mgmt_err);
-		return 0;
+		return;
 	}
 
-	if (test_bit(HCI_AUTH, &hdev->flags)) {
-		if (!test_and_set_bit(HCI_LINK_SECURITY, &hdev->dev_flags))
-			changed = true;
-	} else {
-		if (test_and_clear_bit(HCI_LINK_SECURITY, &hdev->dev_flags))
-			changed = true;
-	}
+	if (test_bit(HCI_AUTH, &hdev->flags))
+		changed = !test_and_set_bit(HCI_LINK_SECURITY,
+					    &hdev->dev_flags);
+	else
+		changed = test_and_clear_bit(HCI_LINK_SECURITY,
+					     &hdev->dev_flags);
 
 	mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp,
 			     &match);
 
 	if (changed)
-		err = new_settings(hdev, match.sk);
+		new_settings(hdev, match.sk);
 
 	if (match.sk)
 		sock_put(match.sk);
-
-	return err;
 }
 
 static void clear_eir(struct hci_request *req)
-- 
cgit 


From 3e248560d951b4a99aaa1d1332030853e2ebc3fd Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:25 -0700
Subject: Bluetooth: Make mgmt_ssp_enable_complete() return void

The return value of mgmt_ssp_enable_complete() function is not
used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/mgmt.c             | 12 ++++--------
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3ee5691b247f..734b09f28f8c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1111,7 +1111,7 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, u8 status);
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
-int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
+void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				   u8 status);
 int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 0672a8cb662e..969dbaaf243a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4737,12 +4737,11 @@ static void clear_eir(struct hci_request *req)
 	hci_req_add(req, HCI_OP_WRITE_EIR, sizeof(cp), &cp);
 }
 
-int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
+void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 {
 	struct cmd_lookup match = { NULL, hdev };
 	struct hci_request req;
 	bool changed = false;
-	int err = 0;
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
@@ -4750,13 +4749,12 @@ int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 		if (enable && test_and_clear_bit(HCI_SSP_ENABLED,
 						 &hdev->dev_flags)) {
 			clear_bit(HCI_HS_ENABLED, &hdev->dev_flags);
-			err = new_settings(hdev, NULL);
+			new_settings(hdev, NULL);
 		}
 
 		mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, cmd_status_rsp,
 				     &mgmt_err);
-
-		return err;
+		return;
 	}
 
 	if (enable) {
@@ -4773,7 +4771,7 @@ int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 	mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match);
 
 	if (changed)
-		err = new_settings(hdev, match.sk);
+		new_settings(hdev, match.sk);
 
 	if (match.sk)
 		sock_put(match.sk);
@@ -4786,8 +4784,6 @@ int mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 		clear_eir(&req);
 
 	hci_req_run(&req, NULL);
-
-	return err;
 }
 
 static void sk_lookup(struct pending_cmd *cmd, void *data)
-- 
cgit 


From 4e1b0245f2394a6ee4a79bb183f56f8fe2c7af33 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:26 -0700
Subject: Bluetooth: Make mgmt_set_class_of_dev_complete() return void

The return value of mgmt_set_class_of_dev_complete() function is
not used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 11 ++++-------
 2 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 734b09f28f8c..b2b472cbb611 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1112,8 +1112,8 @@ void mgmt_auth_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, u8 status);
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
-int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
-				   u8 status);
+void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
+				    u8 status);
 int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
 int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 					    u8 *randomizer, u8 status);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 969dbaaf243a..24da84ecd062 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4796,24 +4796,21 @@ static void sk_lookup(struct pending_cmd *cmd, void *data)
 	}
 }
 
-int mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
-				   u8 status)
+void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
+				    u8 status)
 {
 	struct cmd_lookup match = { NULL, hdev, mgmt_status(status) };
-	int err = 0;
 
 	mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, sk_lookup, &match);
 	mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, sk_lookup, &match);
 	mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match);
 
 	if (!status)
-		err = mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class,
-				 3, NULL);
+		mgmt_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class, 3,
+			   NULL);
 
 	if (match.sk)
 		sock_put(match.sk);
-
-	return err;
 }
 
 int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
-- 
cgit 


From 7667da3423cdf06a818e73adaf2f675455cc8e99 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:27 -0700
Subject: Bluetooth: Make mgmt_set_local_name_complete() return void

The return value of mgmt_set_local_name_complete() function is
not used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/mgmt.c             | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index b2b472cbb611..d40212b94c8a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1114,7 +1114,7 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				    u8 status);
-int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
+void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
 int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
 					    u8 *randomizer, u8 status);
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 24da84ecd062..b4b5cb7786df 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4813,13 +4813,13 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 		sock_put(match.sk);
 }
 
-int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
+void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 {
 	struct mgmt_cp_set_local_name ev;
 	struct pending_cmd *cmd;
 
 	if (status)
-		return 0;
+		return;
 
 	memset(&ev, 0, sizeof(ev));
 	memcpy(ev.name, name, HCI_MAX_NAME_LENGTH);
@@ -4833,11 +4833,11 @@ int mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 		 * HCI dev don't send any mgmt signals.
 		 */
 		if (mgmt_pending_find(MGMT_OP_SET_POWERED, hdev))
-			return 0;
+			return;
 	}
 
-	return mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev),
-			  cmd ? cmd->sk : NULL);
+	mgmt_event(MGMT_EV_LOCAL_NAME_CHANGED, hdev, &ev, sizeof(ev),
+		   cmd ? cmd->sk : NULL);
 }
 
 int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
-- 
cgit 


From 3edaf092c271d91228c66a48b415c92925b83d0b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:28 -0700
Subject: Bluetooth: Make mgmt_read_local_oob_data_reply_complete() return void

The return value of mgmt_read_local_oob_data_reply_complete() function
is not used and so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/mgmt.c             | 18 +++++++-----------
 2 files changed, 9 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d40212b94c8a..5d8d322a0855 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1115,8 +1115,8 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				    u8 status);
 void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
-int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
-					    u8 *randomizer, u8 status);
+void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
+					     u8 *randomizer, u8 status);
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
 		       u8 ssp, u8 *eir, u16 eir_len);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index b4b5cb7786df..1ed0b3e1b9ff 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4840,35 +4840,31 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status)
 		   cmd ? cmd->sk : NULL);
 }
 
-int mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
-					    u8 *randomizer, u8 status)
+void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash,
+					     u8 *randomizer, u8 status)
 {
 	struct pending_cmd *cmd;
-	int err;
 
 	BT_DBG("%s status %u", hdev->name, status);
 
 	cmd = mgmt_pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev);
 	if (!cmd)
-		return -ENOENT;
+		return;
 
 	if (status) {
-		err = cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
-				 mgmt_status(status));
+		cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+			   mgmt_status(status));
 	} else {
 		struct mgmt_rp_read_local_oob_data rp;
 
 		memcpy(rp.hash, hash, sizeof(rp.hash));
 		memcpy(rp.randomizer, randomizer, sizeof(rp.randomizer));
 
-		err = cmd_complete(cmd->sk, hdev->id,
-				   MGMT_OP_READ_LOCAL_OOB_DATA, 0, &rp,
-				   sizeof(rp));
+		cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
+			     0, &rp, sizeof(rp));
 	}
 
 	mgmt_pending_remove(cmd);
-
-	return err;
 }
 
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-- 
cgit 


From 083368f7b8c03a0b3eaa048e84eb9fa9573745d4 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 15 Oct 2013 14:26:29 -0700
Subject: Bluetooth: Make mgmt_new_ltk() return void

The return value of mgmt_new_ltk() function is not used and
so just change it to return void.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
---
 include/net/bluetooth/hci_core.h | 2 +-
 net/bluetooth/mgmt.c             | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5d8d322a0855..0a3a10a76b6c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1125,7 +1125,7 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
 int mgmt_device_blocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int mgmt_device_unblocked(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
-int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent);
+void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent);
 void mgmt_reenable_advertising(struct hci_dev *hdev);
 
 /* HCI info for socket */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1ed0b3e1b9ff..90d935373449 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4382,7 +4382,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 	mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
-int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
+void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
 {
 	struct mgmt_ev_new_long_term_key ev;
 
@@ -4401,8 +4401,7 @@ int mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent)
 	memcpy(ev.key.rand, key->rand, sizeof(key->rand));
 	memcpy(ev.key.val, key->val, sizeof(key->val));
 
-	return mgmt_event(MGMT_EV_NEW_LONG_TERM_KEY, hdev, &ev, sizeof(ev),
-			  NULL);
+	mgmt_event(MGMT_EV_NEW_LONG_TERM_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
 static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data,
-- 
cgit 


From 2b9b1620349e325f184c68cddf3b484499c163c0 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 30 Aug 2013 11:51:22 +0200
Subject: pwm-backlight: Add optional enable GPIO

To support a wider variety of backlight setups, introduce an optional
enable GPIO. Legacy users of the platform data already have a means of
supporting GPIOs by using the .init(), .exit() and .notify() hooks. DT
users however cannot use those, so an alternative method is required.

In order to ease the introduction of the optional enable GPIO, make it
available in the platform data first, so that existing users can be
converted. Once that has happened a second patch will add code to make
use of it in the driver.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 include/linux/pwm_backlight.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h
index 56f4a866539a..2de2e275b2cb 100644
--- a/include/linux/pwm_backlight.h
+++ b/include/linux/pwm_backlight.h
@@ -6,6 +6,9 @@
 
 #include <linux/backlight.h>
 
+/* TODO: convert to gpiod_*() API once it has been merged */
+#define PWM_BACKLIGHT_GPIO_ACTIVE_LOW	(1 << 0)
+
 struct platform_pwm_backlight_data {
 	int pwm_id;
 	unsigned int max_brightness;
@@ -13,6 +16,8 @@ struct platform_pwm_backlight_data {
 	unsigned int lth_brightness;
 	unsigned int pwm_period_ns;
 	unsigned int *levels;
+	int enable_gpio;
+	unsigned long enable_gpio_flags;
 	int (*init)(struct device *dev);
 	int (*notify)(struct device *dev, int brightness);
 	void (*notify_after)(struct device *dev, int brightness);
-- 
cgit 


From f8e808bd6853f1ada3614f99c95beac1bc2f2140 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 16 Oct 2013 00:16:47 -0700
Subject: Bluetooth: Store scan response data in HCI device

The scan response data needs to be stored in HCI device and so
add a buffer for it and also ensure to clear it when resetting
the controller.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 2 ++
 net/bluetooth/hci_event.c        | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0a3a10a76b6c..d987c795ba14 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -283,6 +283,8 @@ struct hci_dev {
 	__s8			adv_tx_power;
 	__u8			adv_data[HCI_MAX_AD_LENGTH];
 	__u8			adv_data_len;
+	__u8			scan_rsp_data[HCI_MAX_AD_LENGTH];
+	__u8			scan_rsp_data_len;
 
 	int (*open)(struct hci_dev *hdev);
 	int (*close)(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 7450626b7704..e71c98fedc9b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -195,6 +195,9 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 
 	memset(hdev->adv_data, 0, sizeof(hdev->adv_data));
 	hdev->adv_data_len = 0;
+
+	memset(hdev->scan_rsp_data, 0, sizeof(hdev->scan_rsp_data));
+	hdev->scan_rsp_data_len = 0;
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
-- 
cgit 


From f14d8f643733a564b299ec24464ae23a0d7eb230 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 16 Oct 2013 00:16:48 -0700
Subject: Bluetooth: Set the scan response data when needed

On controller power on and when enabling LE functionality,
make sure that also the scan response data is correctly set.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  6 ++++++
 net/bluetooth/mgmt.c        | 38 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 43 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8b8c3e2ddb06..aca8944b3e30 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1094,6 +1094,12 @@ struct hci_cp_le_set_adv_data {
 	__u8	data[HCI_MAX_AD_LENGTH];
 } __packed;
 
+#define HCI_OP_LE_SET_SCAN_RSP_DATA	0x2009
+struct hci_cp_le_set_scan_rsp_data {
+	__u8	length;
+	__u8	data[HCI_MAX_AD_LENGTH];
+} __packed;
+
 #define HCI_OP_LE_SET_ADV_ENABLE	0x200a
 
 #define LE_SCAN_PASSIVE			0x00
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 54f14547259b..59bbf434ba9a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -536,6 +536,36 @@ static u8 *create_uuid128_list(struct hci_dev *hdev, u8 *data, ptrdiff_t len)
 	return ptr;
 }
 
+static u8 create_scan_rsp_data(struct hci_dev *hdev, u8 *ptr)
+{
+	return 0;
+}
+
+static void update_scan_rsp_data(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_scan_rsp_data cp;
+	u8 len;
+
+	if (!lmp_le_capable(hdev))
+		return;
+
+	memset(&cp, 0, sizeof(cp));
+
+	len = create_scan_rsp_data(hdev, cp.data);
+
+	if (hdev->adv_data_len == len &&
+	    memcmp(cp.data, hdev->adv_data, len) == 0)
+		return;
+
+	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+	hdev->adv_data_len = len;
+
+	cp.length = len;
+
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp);
+}
+
 static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr)
 {
 	u8 ad_len = 0, flags = 0;
@@ -1715,6 +1745,7 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status)
 
 		hci_req_init(&req, hdev);
 		update_ad(&req);
+		update_scan_rsp_data(&req);
 		hci_req_run(&req, NULL);
 
 		hci_dev_unlock(hdev);
@@ -3898,6 +3929,9 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	if (test_bit(HCI_CONNECTABLE, &hdev->dev_flags))
 		set_bredr_scan(&req);
 
+	/* Since only the advertising data flags will change, there
+	 * is no need to update the scan response data.
+	 */
 	update_ad(&req);
 
 	err = hci_req_run(&req, set_bredr_complete);
@@ -4211,8 +4245,10 @@ static int powered_update_hci(struct hci_dev *hdev)
 		 * advertising data. This also applies to the case
 		 * where BR/EDR was toggled during the AUTO_OFF phase.
 		 */
-		if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+		if (test_bit(HCI_LE_ENABLED, &hdev->dev_flags)) {
 			update_ad(&req);
+			update_scan_rsp_data(&req);
+		}
 
 		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 			enable_advertising(&req);
-- 
cgit 


From db3aebf4a13562c60761e5530f2cbf6ef9fdee2b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 16 Oct 2013 00:16:51 -0700
Subject: Bluetooth: Remove duplicate definitions for advertising event types

The constants for advertising event types have been defined twice. So
remove one copy of it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index aca8944b3e30..c8bc7bfffaf5 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1063,11 +1063,6 @@ struct hci_rp_le_read_local_features {
 
 #define HCI_OP_LE_SET_RANDOM_ADDR	0x2005
 
-#define LE_ADV_IND			0x00
-#define LE_ADV_DIRECT_IND		0x01
-#define LE_ADV_SCAN_IND			0x02
-#define LE_ADV_NONCONN_IND		0x03
-
 #define HCI_OP_LE_SET_ADV_PARAM		0x2006
 struct hci_cp_le_set_adv_param {
 	__le16   min_interval;
@@ -1580,11 +1575,11 @@ struct hci_ev_le_ltk_req {
 } __packed;
 
 /* Advertising report event types */
-#define ADV_IND		0x00
-#define ADV_DIRECT_IND	0x01
-#define ADV_SCAN_IND	0x02
-#define ADV_NONCONN_IND	0x03
-#define ADV_SCAN_RSP	0x04
+#define LE_ADV_IND		0x00
+#define LE_ADV_DIRECT_IND	0x01
+#define LE_ADV_SCAN_IND		0x02
+#define LE_ADV_NONCONN_IND	0x03
+#define LE_ADV_SCAN_RSP		0x04
 
 #define ADDR_LE_DEV_PUBLIC	0x00
 #define ADDR_LE_DEV_RANDOM	0x01
-- 
cgit 


From d468bf9ecaabd3bf3a6134e5a369ced82b1d1ca1 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 24 Sep 2013 11:54:38 +0200
Subject: gpio: add API to be strict about GPIO IRQ usage

It is currently often possible in many GPIO drivers to request
a GPIO line to be used as IRQ after calling gpio_to_irq() and,
as the gpiolib is not aware of this, set the same line to
output and start driving it, with undesired side effects.

As it is a bogus usage scenario to request a line flagged as
output to used as IRQ, we introduce APIs to let gpiolib track
the use of a line as IRQ, and also set this flag from the
userspace ABI.

The API is symmetric so that lines can also be flagged from
.irq_enable() and unflagged from IRQ by .irq_disable().
The debugfs file is altered so that we see if a line is
reserved for IRQ.

Cc: Enric Balletbo i Serra <eballetbo@gmail.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Stephen Warren <swarren@nvidia.com>
Reviewed-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c     | 88 ++++++++++++++++++++++++++++++++++++++++++++--
 include/asm-generic/gpio.h |  3 ++
 include/linux/gpio.h       | 12 +++++++
 3 files changed, 101 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 4fc28603a742..1014cb5e10b0 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -60,6 +60,7 @@ struct gpio_desc {
 #define FLAG_ACTIVE_LOW	6	/* sysfs value has active low */
 #define FLAG_OPEN_DRAIN	7	/* Gpio is open drain type */
 #define FLAG_OPEN_SOURCE 8	/* Gpio is open source type */
+#define FLAG_USED_AS_IRQ 9	/* GPIO is connected to an IRQ */
 
 #define ID_SHIFT	16	/* add new flags before this one */
 
@@ -96,6 +97,8 @@ static int gpiod_get_value(const struct gpio_desc *desc);
 static void gpiod_set_value(struct gpio_desc *desc, int value);
 static int gpiod_cansleep(const struct gpio_desc *desc);
 static int gpiod_to_irq(const struct gpio_desc *desc);
+static int gpiod_lock_as_irq(struct gpio_desc *desc);
+static void gpiod_unlock_as_irq(struct gpio_desc *desc);
 static int gpiod_export(struct gpio_desc *desc, bool direction_may_change);
 static int gpiod_export_link(struct device *dev, const char *name,
 			     struct gpio_desc *desc);
@@ -162,6 +165,17 @@ static struct gpio_desc *gpio_to_desc(unsigned gpio)
 		return &gpio_desc[gpio];
 }
 
+/**
+ * Convert an offset on a certain chip to a corresponding descriptor
+ */
+static struct gpio_desc *gpiochip_offset_to_desc(struct gpio_chip *chip,
+						 unsigned int offset)
+{
+	unsigned int gpio = chip->base + offset;
+
+	return gpio_to_desc(gpio);
+}
+
 /**
  * Convert a GPIO descriptor to the integer namespace.
  * This should disappear in the future but is needed since we still
@@ -428,6 +442,7 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 	desc->flags &= ~GPIO_TRIGGER_MASK;
 
 	if (!gpio_flags) {
+		gpiod_unlock_as_irq(desc);
 		ret = 0;
 		goto free_id;
 	}
@@ -466,6 +481,12 @@ static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 	if (ret < 0)
 		goto free_id;
 
+	ret = gpiod_lock_as_irq(desc);
+	if (ret < 0) {
+		gpiod_warn(desc, "failed to flag the GPIO for IRQ\n");
+		goto free_id;
+	}
+
 	desc->flags |= gpio_flags;
 	return 0;
 
@@ -1730,6 +1751,14 @@ static int gpiod_direction_output(struct gpio_desc *desc, int value)
 		return -EINVAL;
 	}
 
+	/* GPIOs used for IRQs shall not be set as output */
+	if (test_bit(FLAG_USED_AS_IRQ, &desc->flags)) {
+		gpiod_err(desc,
+			  "%s: tried to set a GPIO tied to an IRQ as output\n",
+			  __func__);
+		return -EIO;
+	}
+
 	/* Open drain pin should not be driven to 1 */
 	if (value && test_bit(FLAG_OPEN_DRAIN,  &desc->flags))
 		return gpiod_direction_input(desc);
@@ -2050,6 +2079,58 @@ int __gpio_to_irq(unsigned gpio)
 }
 EXPORT_SYMBOL_GPL(__gpio_to_irq);
 
+/**
+ * gpiod_lock_as_irq() - lock a GPIO to be used as IRQ
+ * @gpio: the GPIO line to lock as used for IRQ
+ *
+ * This is used directly by GPIO drivers that want to lock down
+ * a certain GPIO line to be used as IRQs, for example in the
+ * .to_irq() callback of their gpio_chip, or in the .irq_enable()
+ * of its irq_chip implementation if the GPIO is known from that
+ * code.
+ */
+static int gpiod_lock_as_irq(struct gpio_desc *desc)
+{
+	if (!desc)
+		return -EINVAL;
+
+	if (test_bit(FLAG_IS_OUT, &desc->flags)) {
+		gpiod_err(desc,
+			  "%s: tried to flag a GPIO set as output for IRQ\n",
+			  __func__);
+		return -EIO;
+	}
+
+	set_bit(FLAG_USED_AS_IRQ, &desc->flags);
+	return 0;
+}
+
+int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
+{
+	return gpiod_lock_as_irq(gpiochip_offset_to_desc(chip, offset));
+}
+EXPORT_SYMBOL_GPL(gpio_lock_as_irq);
+
+/**
+ * gpiod_unlock_as_irq() - unlock a GPIO used as IRQ
+ * @gpio: the GPIO line to unlock from IRQ usage
+ *
+ * This is used directly by GPIO drivers that want to indicate
+ * that a certain GPIO is no longer used exclusively for IRQ.
+ */
+static void gpiod_unlock_as_irq(struct gpio_desc *desc)
+{
+	if (!desc)
+		return;
+
+	clear_bit(FLAG_USED_AS_IRQ, &desc->flags);
+}
+
+void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
+{
+	return gpiod_unlock_as_irq(gpiochip_offset_to_desc(chip, offset));
+}
+EXPORT_SYMBOL_GPL(gpio_unlock_as_irq);
 
 /* There's no value in making it easy to inline GPIO calls that may sleep.
  * Common examples include ones connected to I2C or SPI chips.
@@ -2091,6 +2172,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 	unsigned		gpio = chip->base;
 	struct gpio_desc	*gdesc = &chip->desc[0];
 	int			is_out;
+	int			is_irq;
 
 	for (i = 0; i < chip->ngpio; i++, gpio++, gdesc++) {
 		if (!test_bit(FLAG_REQUESTED, &gdesc->flags))
@@ -2098,12 +2180,14 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 
 		gpiod_get_direction(gdesc);
 		is_out = test_bit(FLAG_IS_OUT, &gdesc->flags);
-		seq_printf(s, " gpio-%-3d (%-20.20s) %s %s",
+		is_irq = test_bit(FLAG_USED_AS_IRQ, &gdesc->flags);
+		seq_printf(s, " gpio-%-3d (%-20.20s) %s %s %s",
 			gpio, gdesc->label,
 			is_out ? "out" : "in ",
 			chip->get
 				? (chip->get(chip, i) ? "hi" : "lo")
-				: "?  ");
+				: "?  ",
+			is_irq ? "IRQ" : "   ");
 		seq_printf(s, "\n");
 	}
 }
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index bde646995d10..b309a5c0019e 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -192,6 +192,9 @@ extern int __gpio_cansleep(unsigned gpio);
 
 extern int __gpio_to_irq(unsigned gpio);
 
+extern int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset);
+extern void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset);
+
 extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
 extern int gpio_request_array(const struct gpio *array, size_t num);
 extern void gpio_free_array(const struct gpio *array, size_t num);
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 552e3f46e4a3..a06ec3e85ba3 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -204,6 +204,18 @@ static inline int gpio_to_irq(unsigned gpio)
 	return -EINVAL;
 }
 
+static inline int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
+
+static inline void gpio_unlock_as_irq(struct gpio_chip *chip,
+				      unsigned int offset)
+{
+	WARN_ON(1);
+}
+
 static inline int irq_to_gpio(unsigned irq)
 {
 	/* irq can never have been returned from gpio_to_irq() */
-- 
cgit 


From d3900cb25de21476758f1ae8b8d3e4602e3cd4ed Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 16 Oct 2013 02:09:01 -0700
Subject: Bluetooth: Remove enable_hs declaration

This seems to be a left-over. The module parameter enable_hs has
been removed, but its extern declaration is still present. It is
not needed anymore, so just remove it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index c8bc7bfffaf5..77a971aefcff 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1787,6 +1787,4 @@ struct hci_inquiry_req {
 };
 #define IREQ_CACHE_FLUSH 0x0001
 
-extern bool enable_hs;
-
 #endif /* __HCI_H */
-- 
cgit 


From 8922915b38cd8b72f8e5af614b95be71d1d299d4 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 7 Oct 2013 20:31:06 +0200
Subject: sched/wait: Add ___wait_cond_timeout() to wait_event*_timeout() too

Commit 4c663cfc ("wait: fix false timeouts when using
wait_event_timeout()") introduced the additional condition checks
after a timeout but only in the "slow" __wait*() paths.

wait_event_timeout(wq, CONDITION, 0) still returns 0 if CONDITION
is already true and we do not call __wait*().

Now that we have ___wait_cond_timeout() we can use it instead to
ensure that __ret will be properly updated.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131007183106.GA10973@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index a2726c7dd244..04c0260bda8f 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -270,7 +270,7 @@ do {									\
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
 	long __ret = timeout;						\
-	if (!(condition))						\
+	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_timeout(wq, condition, timeout);	\
 	__ret;								\
 })
@@ -328,7 +328,7 @@ do {									\
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
-	if (!(condition))						\
+	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_interruptible_timeout(wq,		\
 						condition, timeout);	\
 	__ret;								\
@@ -769,7 +769,7 @@ do {									\
 						  timeout)		\
 ({									\
 	long __ret = timeout;						\
-	if (!(condition))						\
+	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_interruptible_lock_irq_timeout(	\
 					wq, condition, lock, timeout);	\
 	__ret;								\
-- 
cgit 


From c2d816443ef305aba8eaf0bf368f4d3d87494f06 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 7 Oct 2013 18:18:24 +0200
Subject: sched/wait: Introduce prepare_to_wait_event()

Add the new helper, prepare_to_wait_event() which should only be used
by ___wait_event().

prepare_to_wait_event() returns -ERESTARTSYS if signal_pending_state()
is true, otherwise it does prepare_to_wait/exclusive.  This allows to
uninline the signal-pending checks in wait_event*() macros.

Also, it can initialize wait->private/func. We do not care if they were
already initialized, the values are the same. This also shaves a couple
of insns from the inlined code.

This obviously makes prepare_*() path a little bit slower, but we are
likely going to sleep anyway, so I think it makes sense to shrink .text:

               text    data      bss      dec     hex  filename
            ===================================================
   before:  5126092 2959248 10117120 18202460 115bf5c   vmlinux
    after:  5124618 2955152 10117120 18196890 115a99a   vmlinux

on my build.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131007161824.GA29757@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 24 ++++++++++++++----------
 kernel/wait.c        | 24 ++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 04c0260bda8f..ec099b03e11b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -187,27 +187,30 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 	__cond || !__ret;						\
 })
 
-#define ___wait_signal_pending(state)					\
-	((state == TASK_INTERRUPTIBLE && signal_pending(current)) ||	\
-	 (state == TASK_KILLABLE && fatal_signal_pending(current)))
+#define ___wait_is_interruptible(state)					\
+	(!__builtin_constant_p(state) ||				\
+		state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE)	\
 
 #define ___wait_event(wq, condition, state, exclusive, ret, cmd)	\
 ({									\
 	__label__ __out;						\
-	DEFINE_WAIT(__wait);						\
+	wait_queue_t __wait;						\
 	long __ret = ret;						\
 									\
+	INIT_LIST_HEAD(&__wait.task_list);				\
+	if (exclusive)							\
+		__wait.flags = WQ_FLAG_EXCLUSIVE;			\
+	else								\
+		__wait.flags = 0;					\
+									\
 	for (;;) {							\
-		if (exclusive)						\
-			prepare_to_wait_exclusive(&wq, &__wait, state); \
-		else							\
-			prepare_to_wait(&wq, &__wait, state);		\
+		long __int = prepare_to_wait_event(&wq, &__wait, state);\
 									\
 		if (condition)						\
 			break;						\
 									\
-		if (___wait_signal_pending(state)) {			\
-			__ret = -ERESTARTSYS;				\
+		if (___wait_is_interruptible(state) && __int) {		\
+			__ret = __int;					\
 			if (exclusive) {				\
 				abort_exclusive_wait(&wq, &__wait,	\
 						     state, NULL);	\
@@ -791,6 +794,7 @@ extern long interruptible_sleep_on_timeout(wait_queue_head_t *q, signed long tim
  */
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state);
+long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
 void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
diff --git a/kernel/wait.c b/kernel/wait.c
index d550920e040c..de21c6305a44 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -92,6 +92,30 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	if (signal_pending_state(state, current))
+		return -ERESTARTSYS;
+
+	wait->private = current;
+	wait->func = autoremove_wake_function;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list)) {
+		if (wait->flags & WQ_FLAG_EXCLUSIVE)
+			__add_wait_queue_tail(q, wait);
+		else
+			__add_wait_queue(q, wait);
+	}
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(prepare_to_wait_event);
+
 /**
  * finish_wait - clean up after waiting in a queue
  * @q: waitqueue waited on
-- 
cgit 


From 586a87e6edc936d6d3c3585af504b33b9c3f0a06 Mon Sep 17 00:00:00 2001
From: Christian Ruppert <christian.ruppert@abilis.com>
Date: Tue, 15 Oct 2013 15:37:54 +0200
Subject: pinctrl/gpio: non-linear GPIO ranges accesible from gpiolib

This patch adds the infrastructure required to register non-linear gpio
ranges through gpiolib and the standard GPIO device tree bindings.

Signed-off-by: Christian Ruppert <christian.ruppert@abilis.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/gpio/gpio.txt | 40 +++++++++++++++-
 drivers/gpio/gpiolib-of.c                       | 63 +++++++++++++++++++++----
 drivers/gpio/gpiolib.c                          | 47 ++++++++++++++++++
 drivers/pinctrl/core.c                          | 14 ++++++
 include/asm-generic/gpio.h                      | 10 ++++
 include/linux/gpio.h                            | 10 ++++
 include/linux/pinctrl/pinctrl.h                 |  3 ++
 7 files changed, 177 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/gpio/gpio.txt b/Documentation/devicetree/bindings/gpio/gpio.txt
index 6cec6ff20d2e..0c85bb6e3a80 100644
--- a/Documentation/devicetree/bindings/gpio/gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio.txt
@@ -87,8 +87,10 @@ controllers. The gpio-ranges property described below represents this, and
 contains information structures as follows:
 
 	gpio-range-list ::= <single-gpio-range> [gpio-range-list]
-	single-gpio-range ::=
+	single-gpio-range ::= <numeric-gpio-range> | <named-gpio-range>
+	numeric-gpio-range ::=
 			<pinctrl-phandle> <gpio-base> <pinctrl-base> <count>
+	named-gpio-range ::= <pinctrl-phandle> <gpio-base> '<0 0>'
 	gpio-phandle : phandle to pin controller node.
 	gpio-base : Base GPIO ID in the GPIO controller
 	pinctrl-base : Base pinctrl pin ID in the pin controller
@@ -97,6 +99,19 @@ contains information structures as follows:
 The "pin controller node" mentioned above must conform to the bindings
 described in ../pinctrl/pinctrl-bindings.txt.
 
+In case named gpio ranges are used (ranges with both <pinctrl-base> and
+<count> set to 0), the property gpio-ranges-group-names contains one string
+for every single-gpio-range in gpio-ranges:
+	gpiorange-names-list ::= <gpiorange-name> [gpiorange-names-list]
+	gpiorange-name : Name of the pingroup associated to the GPIO range in
+			the respective pin controller.
+
+Elements of gpiorange-names-list corresponding to numeric ranges contain
+the empty string. Elements of gpiorange-names-list corresponding to named
+ranges contain the name of a pin group defined in the respective pin
+controller. The number of pins/GPIOs in the range is the number of pins in
+that pin group.
+
 Previous versions of this binding required all pin controller nodes that
 were referenced by any gpio-ranges property to contain a property named
 #gpio-range-cells with value <3>. This requirement is now deprecated.
@@ -104,7 +119,7 @@ However, that property may still exist in older device trees for
 compatibility reasons, and would still be required even in new device
 trees that need to be compatible with older software.
 
-Example:
+Example 1:
 
 	qe_pio_e: gpio-controller@1460 {
 		#gpio-cells = <2>;
@@ -117,3 +132,24 @@ Example:
 Here, a single GPIO controller has GPIOs 0..9 routed to pin controller
 pinctrl1's pins 20..29, and GPIOs 10..19 routed to pin controller pinctrl2's
 pins 50..59.
+
+Example 2:
+
+	gpio_pio_i: gpio-controller@14B0 {
+		#gpio-cells = <2>;
+		compatible = "fsl,qe-pario-bank-e", "fsl,qe-pario-bank";
+		reg = <0x1480 0x18>;
+		gpio-controller;
+		gpio-ranges =			<&pinctrl1 0 20 10>,
+						<&pinctrl2 10 0 0>,
+						<&pinctrl1 15 0 10>,
+						<&pinctrl2 25 0 0>;
+		gpio-ranges-group-names =	"",
+						"foo",
+						"",
+						"bar";
+	};
+
+Here, three GPIO ranges are defined wrt. two pin controllers. pinctrl1 GPIO
+ranges are defined using pin numbers whereas the GPIO ranges wrt. pinctrl2
+are named "foo" and "bar".
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 0dfaf20e4dad..e78760921bd7 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -190,10 +190,15 @@ static void of_gpiochip_add_pin_range(struct gpio_chip *chip)
 	struct of_phandle_args pinspec;
 	struct pinctrl_dev *pctldev;
 	int index = 0, ret;
+	const char *name;
+	static const char group_names_propname[] = "gpio-ranges-group-names";
+	struct property *group_names;
 
 	if (!np)
 		return;
 
+	group_names = of_find_property(np, group_names_propname, NULL);
+
 	for (;; index++) {
 		ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3,
 				index, &pinspec);
@@ -204,14 +209,56 @@ static void of_gpiochip_add_pin_range(struct gpio_chip *chip)
 		if (!pctldev)
 			break;
 
-		ret = gpiochip_add_pin_range(chip,
-					     pinctrl_dev_get_devname(pctldev),
-					     pinspec.args[0],
-					     pinspec.args[1],
-					     pinspec.args[2]);
-
-		if (ret)
-			break;
+		if (pinspec.args[2]) {
+			if (group_names) {
+				ret = of_property_read_string_index(np,
+						group_names_propname,
+						index, &name);
+				if (strlen(name)) {
+					pr_err("%s: Group name of numeric GPIO ranges must be the empty string.\n",
+						np->full_name);
+					break;
+				}
+			}
+			/* npins != 0: linear range */
+			ret = gpiochip_add_pin_range(chip,
+					pinctrl_dev_get_devname(pctldev),
+					pinspec.args[0],
+					pinspec.args[1],
+					pinspec.args[2]);
+			if (ret)
+				break;
+		} else {
+			/* npins == 0: special range */
+			if (pinspec.args[1]) {
+				pr_err("%s: Illegal gpio-range format.\n",
+					np->full_name);
+				break;
+			}
+
+			if (!group_names) {
+				pr_err("%s: GPIO group range requested but no %s property.\n",
+					np->full_name, group_names_propname);
+				break;
+			}
+
+			ret = of_property_read_string_index(np,
+						group_names_propname,
+						index, &name);
+			if (ret)
+				break;
+
+			if (!strlen(name)) {
+				pr_err("%s: Group name of GPIO group range cannot be the empty string.\n",
+				np->full_name);
+				break;
+			}
+
+			ret = gpiochip_add_pingroup_range(chip, pctldev,
+						pinspec.args[0], name);
+			if (ret)
+				break;
+		}
 	}
 }
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86ef3461ec06..b83b7e491f76 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1319,6 +1319,53 @@ EXPORT_SYMBOL_GPL(gpiochip_find);
 
 #ifdef CONFIG_PINCTRL
 
+/**
+ * gpiochip_add_pingroup_range() - add a range for GPIO <-> pin mapping
+ * @chip: the gpiochip to add the range for
+ * @pinctrl: the dev_name() of the pin controller to map to
+ * @gpio_offset: the start offset in the current gpio_chip number space
+ * @pin_group: name of the pin group inside the pin controller
+ */
+int gpiochip_add_pingroup_range(struct gpio_chip *chip,
+			struct pinctrl_dev *pctldev,
+			unsigned int gpio_offset, const char *pin_group)
+{
+	struct gpio_pin_range *pin_range;
+	int ret;
+
+	pin_range = kzalloc(sizeof(*pin_range), GFP_KERNEL);
+	if (!pin_range) {
+		pr_err("%s: GPIO chip: failed to allocate pin ranges\n",
+				chip->label);
+		return -ENOMEM;
+	}
+
+	/* Use local offset as range ID */
+	pin_range->range.id = gpio_offset;
+	pin_range->range.gc = chip;
+	pin_range->range.name = chip->label;
+	pin_range->range.base = chip->base + gpio_offset;
+	pin_range->pctldev = pctldev;
+
+	ret = pinctrl_get_group_pins(pctldev, pin_group,
+					&pin_range->range.pins,
+					&pin_range->range.npins);
+	if (ret < 0)
+		return ret;
+
+	pinctrl_add_gpio_range(pctldev, &pin_range->range);
+
+	pr_debug("GPIO chip %s: created GPIO range %d->%d ==> %s PINGRP %s\n",
+		 chip->label, gpio_offset,
+		 gpio_offset + pin_range->range.npins - 1,
+		 pinctrl_dev_get_devname(pctldev), pin_group);
+
+	list_add_tail(&pin_range->node, &chip->pin_ranges);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gpiochip_add_pingroup_range);
+
 /**
  * gpiochip_add_pin_range() - add a range for GPIO <-> pin mapping
  * @chip: the gpiochip to add the range for
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 92f86ab30a13..5ee61a470016 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -462,6 +462,20 @@ struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname,
 }
 EXPORT_SYMBOL_GPL(pinctrl_find_and_add_gpio_range);
 
+int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group,
+				const unsigned **pins, unsigned *num_pins)
+{
+	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
+	int gs;
+
+	gs = pinctrl_get_group_selector(pctldev, pin_group);
+	if (gs < 0)
+		return gs;
+
+	return pctlops->get_group_pins(pctldev, gs, pins, num_pins);
+}
+EXPORT_SYMBOL_GPL(pinctrl_get_group_pins);
+
 /**
  * pinctrl_find_gpio_range_from_pin() - locate the GPIO range for a pin
  * @pctldev: the pin controller device to look in
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index bde646995d10..523f40525535 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -228,6 +228,9 @@ struct gpio_pin_range {
 int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
 			   unsigned int gpio_offset, unsigned int pin_offset,
 			   unsigned int npins);
+int gpiochip_add_pingroup_range(struct gpio_chip *chip,
+			struct pinctrl_dev *pctldev,
+			unsigned int gpio_offset, const char *pin_group);
 void gpiochip_remove_pin_ranges(struct gpio_chip *chip);
 
 #else
@@ -239,6 +242,13 @@ gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
 {
 	return 0;
 }
+static inline int
+gpiochip_add_pingroup_range(struct gpio_chip *chip,
+			struct pinctrl_dev *pctldev,
+			unsigned int gpio_offset, const char *pin_group)
+{
+	return 0;
+}
 
 static inline void
 gpiochip_remove_pin_ranges(struct gpio_chip *chip)
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 552e3f46e4a3..b8d0e53a802f 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -80,6 +80,7 @@ static inline int irq_to_gpio(unsigned int irq)
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/bug.h>
+#include <linux/pinctrl/pinctrl.h>
 
 struct device;
 struct gpio_chip;
@@ -220,6 +221,15 @@ gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
 	return -EINVAL;
 }
 
+static inline int
+gpiochip_add_pingroup_range(struct gpio_chip *chip,
+			struct pinctrl_dev *pctldev,
+			unsigned int gpio_offset, const char *pin_group)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
+
 static inline void
 gpiochip_remove_pin_ranges(struct gpio_chip *chip)
 {
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 5979147d2bda..fefb88663975 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -144,6 +144,9 @@ extern struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname,
 extern struct pinctrl_gpio_range *
 pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 				 unsigned int pin);
+extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
+				const char *pin_group, const unsigned **pins,
+				unsigned *num_pins);
 
 #ifdef CONFIG_OF
 extern struct pinctrl_dev *of_pinctrl_get(struct device_node *np);
-- 
cgit 


From 7bc18d9d3d7ffbc09dabb201933a063583a39027 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 16 Oct 2013 18:11:39 +0300
Subject: Bluetooth: Convert auto accept timer to use delayed work

Since the entire Bluetooth subsystem runs in workqueues these days there
is no need to use a timer for deferring work.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/hci_conn.c         | 14 ++++++--------
 net/bluetooth/hci_event.c        |  3 ++-
 3 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d987c795ba14..2504a2553baa 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -341,8 +341,8 @@ struct hci_conn {
 	struct list_head chan_list;
 
 	struct delayed_work disc_work;
+	struct delayed_work auto_accept_work;
 	struct timer_list idle_timer;
-	struct timer_list auto_accept_timer;
 
 	struct device	dev;
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ff04b051792d..8d1f466520a5 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -361,12 +361,12 @@ static void hci_conn_idle(unsigned long arg)
 	hci_conn_enter_sniff_mode(conn);
 }
 
-static void hci_conn_auto_accept(unsigned long arg)
+static void hci_conn_auto_accept(struct work_struct *work)
 {
-	struct hci_conn *conn = (void *) arg;
-	struct hci_dev *hdev = conn->hdev;
+	struct hci_conn *conn = container_of(work, struct hci_conn,
+					     auto_accept_work.work);
 
-	hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(conn->dst),
+	hci_send_cmd(conn->hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(conn->dst),
 		     &conn->dst);
 }
 
@@ -415,9 +415,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	INIT_LIST_HEAD(&conn->chan_list);
 
 	INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout);
+	INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept);
 	setup_timer(&conn->idle_timer, hci_conn_idle, (unsigned long)conn);
-	setup_timer(&conn->auto_accept_timer, hci_conn_auto_accept,
-		    (unsigned long) conn);
 
 	atomic_set(&conn->refcnt, 0);
 
@@ -441,8 +440,7 @@ int hci_conn_del(struct hci_conn *conn)
 	del_timer(&conn->idle_timer);
 
 	cancel_delayed_work_sync(&conn->disc_work);
-
-	del_timer(&conn->auto_accept_timer);
+	cancel_delayed_work_sync(&conn->auto_accept_work);
 
 	if (conn->type == ACL_LINK) {
 		struct hci_conn *sco = conn->link;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index e71c98fedc9b..6c3b193951ad 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3188,7 +3188,8 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		if (hdev->auto_accept_delay > 0) {
 			int delay = msecs_to_jiffies(hdev->auto_accept_delay);
-			mod_timer(&conn->auto_accept_timer, jiffies + delay);
+			queue_delayed_work(conn->hdev->workqueue,
+					   &conn->auto_accept_work, delay);
 			goto unlock;
 		}
 
-- 
cgit 


From a74a84f696537f38fa994c1b95a0dca9ae386865 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Wed, 16 Oct 2013 18:11:40 +0300
Subject: Bluetooth: Convert idle timer to use delayed work

There is no need to use a timer since the entire Bluetooth subsystem
runs using workqueues these days.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/hci_conn.c         | 22 +++++++---------------
 2 files changed, 9 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2504a2553baa..07c2da4854ab 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -342,7 +342,7 @@ struct hci_conn {
 
 	struct delayed_work disc_work;
 	struct delayed_work auto_accept_work;
-	struct timer_list idle_timer;
+	struct delayed_work idle_work;
 
 	struct device	dev;
 
@@ -651,7 +651,7 @@ static inline void hci_conn_drop(struct hci_conn *conn)
 		switch (conn->type) {
 		case ACL_LINK:
 		case LE_LINK:
-			del_timer(&conn->idle_timer);
+			cancel_delayed_work(&conn->idle_work);
 			if (conn->state == BT_CONNECTED) {
 				timeo = conn->disc_timeout;
 				if (!conn->out)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 8d1f466520a5..4e726505f52b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -317,8 +317,10 @@ static void hci_conn_timeout(struct work_struct *work)
 }
 
 /* Enter sniff mode */
-static void hci_conn_enter_sniff_mode(struct hci_conn *conn)
+static void hci_conn_idle(struct work_struct *work)
 {
+	struct hci_conn *conn = container_of(work, struct hci_conn,
+					     idle_work.work);
 	struct hci_dev *hdev = conn->hdev;
 
 	BT_DBG("hcon %p mode %d", conn, conn->mode);
@@ -352,15 +354,6 @@ static void hci_conn_enter_sniff_mode(struct hci_conn *conn)
 	}
 }
 
-static void hci_conn_idle(unsigned long arg)
-{
-	struct hci_conn *conn = (void *) arg;
-
-	BT_DBG("hcon %p mode %d", conn, conn->mode);
-
-	hci_conn_enter_sniff_mode(conn);
-}
-
 static void hci_conn_auto_accept(struct work_struct *work)
 {
 	struct hci_conn *conn = container_of(work, struct hci_conn,
@@ -416,7 +409,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 
 	INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout);
 	INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept);
-	setup_timer(&conn->idle_timer, hci_conn_idle, (unsigned long)conn);
+	INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle);
 
 	atomic_set(&conn->refcnt, 0);
 
@@ -437,10 +430,9 @@ int hci_conn_del(struct hci_conn *conn)
 
 	BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle);
 
-	del_timer(&conn->idle_timer);
-
 	cancel_delayed_work_sync(&conn->disc_work);
 	cancel_delayed_work_sync(&conn->auto_accept_work);
+	cancel_delayed_work_sync(&conn->idle_work);
 
 	if (conn->type == ACL_LINK) {
 		struct hci_conn *sco = conn->link;
@@ -920,8 +912,8 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active)
 
 timer:
 	if (hdev->idle_timeout > 0)
-		mod_timer(&conn->idle_timer,
-			  jiffies + msecs_to_jiffies(hdev->idle_timeout));
+		queue_delayed_work(hdev->workqueue, &conn->idle_work,
+				   msecs_to_jiffies(hdev->idle_timeout));
 }
 
 /* Drop all connection on the device */
-- 
cgit 


From bf741c08af194ed0448799ff2690c8dd3da709e5 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 14 Oct 2013 17:49:00 +0100
Subject: iio: Remove unused iio_sw_buffer_preenable()

The functionality implemented by iio_sw_buffer_preenable() is now done directly
in the IIO core and previous users of iio_sw_buffer_preenable() have all been
updated to not use it anymore. It is unused now and can be remove.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/industrialio-buffer.c | 18 ------------------
 include/linux/iio/buffer.h        |  2 --
 2 files changed, 20 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 186f501e6415..d7ab258e3a42 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -749,24 +749,6 @@ done:
 }
 EXPORT_SYMBOL(iio_buffer_store_enable);
 
-int iio_sw_buffer_preenable(struct iio_dev *indio_dev)
-{
-	struct iio_buffer *buffer;
-	unsigned bytes;
-	dev_dbg(&indio_dev->dev, "%s\n", __func__);
-
-	list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list)
-		if (buffer->access->set_bytes_per_datum) {
-			bytes = iio_compute_scan_bytes(indio_dev,
-						       buffer->scan_mask,
-						       buffer->scan_timestamp);
-
-			buffer->access->set_bytes_per_datum(buffer, bytes);
-		}
-	return 0;
-}
-EXPORT_SYMBOL(iio_sw_buffer_preenable);
-
 /**
  * iio_validate_scan_mask_onehot() - Validates that exactly one channel is selected
  * @indio_dev: the iio device
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index 6e428d96d570..15607b45221a 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -206,8 +206,6 @@ ssize_t iio_buffer_show_enable(struct device *dev,
 					   iio_buffer_show_enable,	\
 					   iio_buffer_store_enable)
 
-int iio_sw_buffer_preenable(struct iio_dev *indio_dev);
-
 bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev,
 	const unsigned long *mask);
 
-- 
cgit 


From de68bab4fa96014cfaa6fcbcdb9750e32969fb86 Mon Sep 17 00:00:00 2001
From: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Date: Mon, 30 Sep 2013 17:26:28 +0300
Subject: usb: Don't enable USB 2.0 Link PM by default.

How it's supposed to work:
--------------------------

USB 2.0 Link PM is a lower power state that some newer USB 2.0 devices
support.  USB 3.0 devices certified by the USB-IF are required to
support it if they are plugged into a USB 2.0 only port, or a USB 2.0
cable is used.  USB 2.0 Link PM requires both a USB device and a host
controller that supports USB 2.0 hardware-enabled LPM.

USB 2.0 Link PM is designed to be enabled once by software, and the host
hardware handles transitions to the L1 state automatically.  The premise
of USB 2.0 Link PM is to be able to put the device into a lower power
link state when the bus is idle or the device NAKs USB IN transfers for
a specified amount of time.

...but hardware is broken:
--------------------------

It turns out many USB 3.0 devices claim to support USB 2.0 Link PM (by
setting the LPM bit in their USB 2.0 BOS descriptor), but they don't
actually implement it correctly.  This manifests as the USB device
refusing to respond to transfers when it is plugged into a USB 2.0 only
port under the Haswell-ULT/Lynx Point LP xHCI host.

These devices pass the xHCI driver's simple test to enable USB 2.0 Link
PM, wait for the port to enter L1, and then bring it back into L0.  They
only start to break when L1 entry is interleaved with transfers.

Some devices then fail to respond to the next control transfer (usually
a Set Configuration).  This results in devices never enumerating.

Other mass storage devices (such as a later model Western Digital My
Passport USB 3.0 hard drive) respond fine to going into L1 between
control transfers.  They ACK the entry, come out of L1 when the host
needs to send a control transfer, and respond properly to those control
transfers.  However, when the first READ10 SCSI command is sent, the
device NAKs the data phase while it's reading from the spinning disk.
Eventually, the host requests to put the link into L1, and the device
ACKs that request.  Then it never responds to the data phase of the
READ10 command.  This results in not being able to read from the drive.

Some mass storage devices (like the Corsair Survivor USB 3.0 flash
drive) are well behaved.  They ACK the entry into L1 during control
transfers, and when SCSI commands start coming in, they NAK the requests
to go into L1, because they need to be at full power.

Not all USB 3.0 devices advertise USB 2.0 link PM support.  My Point
Grey USB 3.0 webcam advertises itself as a USB 2.1 device, but doesn't
have a USB 2.0 BOS descriptor, so we don't enable USB 2.0 Link PM.  I
suspect that means the device isn't certified.

What do we do about it?
-----------------------

There's really no good way for the kernel to test these devices.
Therefore, the kernel needs to disable USB 2.0 Link PM by default, and
distros will have to enable it by writing 1 to the sysfs file
/sys/bus/usb/devices/../power/usb2_hardware_lpm.  Rip out the xHCI Link
PM test, since it's not sufficient to detect these buggy devices, and
don't automatically enable LPM after the device is addressed.

This patch should be backported to kernels as old as 3.11, that
contain the commit a558ccdcc71c7770c5e80c926a31cfe8a3892a09 "usb: xhci:
add USB2 Link power management BESL support".  Without this fix, some
USB 3.0 devices will not enumerate or work properly under USB 2.0 ports
on Haswell-ULT systems.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Cc: stable@vger.kernel.org
---
 drivers/usb/core/driver.c   |   3 +
 drivers/usb/core/hub.c      |   1 +
 drivers/usb/core/sysfs.c    |   6 +-
 drivers/usb/host/xhci-mem.c |  10 ---
 drivers/usb/host/xhci.c     | 161 +++++---------------------------------------
 include/linux/usb.h         |   4 +-
 6 files changed, 29 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index f7841d44feda..689433cdef25 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1790,6 +1790,9 @@ int usb_set_usb2_hardware_lpm(struct usb_device *udev, int enable)
 	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
 	int ret = -EPERM;
 
+	if (enable && !udev->usb2_hw_lpm_allowed)
+		return 0;
+
 	if (hcd->driver->set_usb2_hw_lpm) {
 		ret = hcd->driver->set_usb2_hw_lpm(hcd, udev, enable);
 		if (!ret)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index d3a1d79d663d..9be1a2d5fba6 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5203,6 +5203,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 
 done:
 	/* Now that the alt settings are re-installed, enable LTM and LPM. */
+	usb_set_usb2_hardware_lpm(udev, 1);
 	usb_unlocked_enable_lpm(udev);
 	usb_enable_ltm(udev);
 	usb_release_bos_descriptor(udev);
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index 5cf431b0424c..52a97adf02a0 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -458,7 +458,7 @@ static ssize_t usb2_hardware_lpm_show(struct device *dev,
 	struct usb_device *udev = to_usb_device(dev);
 	const char *p;
 
-	if (udev->usb2_hw_lpm_enabled == 1)
+	if (udev->usb2_hw_lpm_allowed == 1)
 		p = "enabled";
 	else
 		p = "disabled";
@@ -478,8 +478,10 @@ static ssize_t usb2_hardware_lpm_store(struct device *dev,
 
 	ret = strtobool(buf, &value);
 
-	if (!ret)
+	if (!ret) {
+		udev->usb2_hw_lpm_allowed = value;
 		ret = usb_set_usb2_hardware_lpm(udev, value);
+	}
 
 	usb_unlock_device(udev);
 
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 83bcd13622c3..49b8bd063fab 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1693,9 +1693,7 @@ void xhci_free_command(struct xhci_hcd *xhci,
 void xhci_mem_cleanup(struct xhci_hcd *xhci)
 {
 	struct pci_dev	*pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
-	struct dev_info	*dev_info, *next;
 	struct xhci_cd  *cur_cd, *next_cd;
-	unsigned long	flags;
 	int size;
 	int i, j, num_ports;
 
@@ -1756,13 +1754,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 
 	scratchpad_free(xhci);
 
-	spin_lock_irqsave(&xhci->lock, flags);
-	list_for_each_entry_safe(dev_info, next, &xhci->lpm_failed_devs, list) {
-		list_del(&dev_info->list);
-		kfree(dev_info);
-	}
-	spin_unlock_irqrestore(&xhci->lock, flags);
-
 	if (!xhci->rh_bw)
 		goto no_bw;
 
@@ -2231,7 +2222,6 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	u32 page_size, temp;
 	int i;
 
-	INIT_LIST_HEAD(&xhci->lpm_failed_devs);
 	INIT_LIST_HEAD(&xhci->cancel_cmd_list);
 
 	page_size = xhci_readl(xhci, &xhci->op_regs->page_size);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 2983e5dd98bf..0ea253ec813d 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4013,133 +4013,6 @@ static int xhci_calculate_usb2_hw_lpm_params(struct usb_device *udev)
 	return PORT_BESLD(besld) | PORT_L1_TIMEOUT(l1) | PORT_HIRDM(hirdm);
 }
 
-static int xhci_usb2_software_lpm_test(struct usb_hcd *hcd,
-					struct usb_device *udev)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	struct dev_info	*dev_info;
-	__le32 __iomem	**port_array;
-	__le32 __iomem	*addr, *pm_addr;
-	u32		temp, dev_id;
-	unsigned int	port_num;
-	unsigned long	flags;
-	int		hird;
-	int		ret;
-
-	if (hcd->speed == HCD_USB3 || !xhci->sw_lpm_support ||
-			!udev->lpm_capable)
-		return -EINVAL;
-
-	/* we only support lpm for non-hub device connected to root hub yet */
-	if (!udev->parent || udev->parent->parent ||
-			udev->descriptor.bDeviceClass == USB_CLASS_HUB)
-		return -EINVAL;
-
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	/* Look for devices in lpm_failed_devs list */
-	dev_id = le16_to_cpu(udev->descriptor.idVendor) << 16 |
-			le16_to_cpu(udev->descriptor.idProduct);
-	list_for_each_entry(dev_info, &xhci->lpm_failed_devs, list) {
-		if (dev_info->dev_id == dev_id) {
-			ret = -EINVAL;
-			goto finish;
-		}
-	}
-
-	port_array = xhci->usb2_ports;
-	port_num = udev->portnum - 1;
-
-	if (port_num > HCS_MAX_PORTS(xhci->hcs_params1)) {
-		xhci_dbg(xhci, "invalid port number %d\n", udev->portnum);
-		ret = -EINVAL;
-		goto finish;
-	}
-
-	/*
-	 * Test USB 2.0 software LPM.
-	 * FIXME: some xHCI 1.0 hosts may implement a new register to set up
-	 * hardware-controlled USB 2.0 LPM. See section 5.4.11 and 4.23.5.1.1.1
-	 * in the June 2011 errata release.
-	 */
-	xhci_dbg(xhci, "test port %d software LPM\n", port_num);
-	/*
-	 * Set L1 Device Slot and HIRD/BESL.
-	 * Check device's USB 2.0 extension descriptor to determine whether
-	 * HIRD or BESL shoule be used. See USB2.0 LPM errata.
-	 */
-	pm_addr = port_array[port_num] + PORTPMSC;
-	hird = xhci_calculate_hird_besl(xhci, udev);
-	temp = PORT_L1DS(udev->slot_id) | PORT_HIRD(hird);
-	xhci_writel(xhci, temp, pm_addr);
-
-	/* Set port link state to U2(L1) */
-	addr = port_array[port_num];
-	xhci_set_link_state(xhci, port_array, port_num, XDEV_U2);
-
-	/* wait for ACK */
-	spin_unlock_irqrestore(&xhci->lock, flags);
-	msleep(10);
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	/* Check L1 Status */
-	ret = xhci_handshake(xhci, pm_addr,
-			PORT_L1S_MASK, PORT_L1S_SUCCESS, 125);
-	if (ret != -ETIMEDOUT) {
-		/* enter L1 successfully */
-		temp = xhci_readl(xhci, addr);
-		xhci_dbg(xhci, "port %d entered L1 state, port status 0x%x\n",
-				port_num, temp);
-		ret = 0;
-	} else {
-		temp = xhci_readl(xhci, pm_addr);
-		xhci_dbg(xhci, "port %d software lpm failed, L1 status %d\n",
-				port_num, temp & PORT_L1S_MASK);
-		ret = -EINVAL;
-	}
-
-	/* Resume the port */
-	xhci_set_link_state(xhci, port_array, port_num, XDEV_U0);
-
-	spin_unlock_irqrestore(&xhci->lock, flags);
-	msleep(10);
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	/* Clear PLC */
-	xhci_test_and_clear_bit(xhci, port_array, port_num, PORT_PLC);
-
-	/* Check PORTSC to make sure the device is in the right state */
-	if (!ret) {
-		temp = xhci_readl(xhci, addr);
-		xhci_dbg(xhci, "resumed port %d status 0x%x\n",	port_num, temp);
-		if (!(temp & PORT_CONNECT) || !(temp & PORT_PE) ||
-				(temp & PORT_PLS_MASK) != XDEV_U0) {
-			xhci_dbg(xhci, "port L1 resume fail\n");
-			ret = -EINVAL;
-		}
-	}
-
-	if (ret) {
-		/* Insert dev to lpm_failed_devs list */
-		xhci_warn(xhci, "device LPM test failed, may disconnect and "
-				"re-enumerate\n");
-		dev_info = kzalloc(sizeof(struct dev_info), GFP_ATOMIC);
-		if (!dev_info) {
-			ret = -ENOMEM;
-			goto finish;
-		}
-		dev_info->dev_id = dev_id;
-		INIT_LIST_HEAD(&dev_info->list);
-		list_add(&dev_info->list, &xhci->lpm_failed_devs);
-	} else {
-		xhci_ring_device(xhci, udev->slot_id);
-	}
-
-finish:
-	spin_unlock_irqrestore(&xhci->lock, flags);
-	return ret;
-}
-
 int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 			struct usb_device *udev, int enable)
 {
@@ -4267,24 +4140,26 @@ static int xhci_check_usb2_port_capability(struct xhci_hcd *xhci, int port,
 int xhci_update_device(struct usb_hcd *hcd, struct usb_device *udev)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	int		ret;
 	int		portnum = udev->portnum - 1;
 
-	ret = xhci_usb2_software_lpm_test(hcd, udev);
-	if (!ret) {
-		xhci_dbg(xhci, "software LPM test succeed\n");
-		if (xhci->hw_lpm_support == 1 &&
-		    xhci_check_usb2_port_capability(xhci, portnum, XHCI_HLC)) {
-			udev->usb2_hw_lpm_capable = 1;
-			udev->l1_params.timeout = XHCI_L1_TIMEOUT;
-			udev->l1_params.besl = XHCI_DEFAULT_BESL;
-			if (xhci_check_usb2_port_capability(xhci, portnum,
-							    XHCI_BLC))
-				udev->usb2_hw_lpm_besl_capable = 1;
-			ret = xhci_set_usb2_hardware_lpm(hcd, udev, 1);
-			if (!ret)
-				udev->usb2_hw_lpm_enabled = 1;
-		}
+	if (hcd->speed == HCD_USB3 || !xhci->sw_lpm_support ||
+			!udev->lpm_capable)
+		return 0;
+
+	/* we only support lpm for non-hub device connected to root hub yet */
+	if (!udev->parent || udev->parent->parent ||
+			udev->descriptor.bDeviceClass == USB_CLASS_HUB)
+		return 0;
+
+	if (xhci->hw_lpm_support == 1 &&
+			xhci_check_usb2_port_capability(
+				xhci, portnum, XHCI_HLC)) {
+		udev->usb2_hw_lpm_capable = 1;
+		udev->l1_params.timeout = XHCI_L1_TIMEOUT;
+		udev->l1_params.besl = XHCI_DEFAULT_BESL;
+		if (xhci_check_usb2_port_capability(xhci, portnum,
+					XHCI_BLC))
+			udev->usb2_hw_lpm_besl_capable = 1;
 	}
 
 	return 0;
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 055ba74bee80..7454865ad148 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -475,7 +475,8 @@ struct usb3_lpm_parameters {
  * @lpm_capable: device supports LPM
  * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM
  * @usb2_hw_lpm_besl_capable: device can perform USB2 hardware BESL LPM
- * @usb2_hw_lpm_enabled: USB2 hardware LPM enabled
+ * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled
+ * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled
  * @usb3_lpm_enabled: USB3 hardware LPM enabled
  * @string_langid: language ID for strings
  * @product: iProduct string, if present (static)
@@ -548,6 +549,7 @@ struct usb_device {
 	unsigned usb2_hw_lpm_capable:1;
 	unsigned usb2_hw_lpm_besl_capable:1;
 	unsigned usb2_hw_lpm_enabled:1;
+	unsigned usb2_hw_lpm_allowed:1;
 	unsigned usb3_lpm_enabled:1;
 	int string_langid;
 
-- 
cgit 


From 8eaede49dfdc1ff1d727f9c913665b8009945191 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Mon, 7 Oct 2013 01:05:46 +0100
Subject: sysrq: Allow magic SysRq key functions to be disabled through Kconfig

Turn the initial value of sysctl kernel.sysrq (SYSRQ_DEFAULT_ENABLE)
into a Kconfig variable.

Original version by Bastian Blank <waldi@debian.org>.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/sysrq.txt | 13 ++++++-------
 drivers/tty/sysrq.c     |  2 +-
 include/linux/sysrq.h   |  3 ---
 kernel/sysctl.c         |  2 +-
 lib/Kconfig.debug       |  9 +++++++++
 5 files changed, 17 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 1c0471dc70fe..0e307c94809a 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -11,11 +11,9 @@ regardless of whatever else it is doing, unless it is completely locked up.
 You need to say "yes" to 'Magic SysRq key (CONFIG_MAGIC_SYSRQ)' when
 configuring the kernel. When running a kernel with SysRq compiled in,
 /proc/sys/kernel/sysrq controls the functions allowed to be invoked via
-the SysRq key. By default the file contains 1 which means that every
-possible SysRq request is allowed (in older versions SysRq was disabled
-by default, and you were required to specifically enable it at run-time
-but this is not the case any more). Here is the list of possible values
-in /proc/sys/kernel/sysrq:
+the SysRq key. The default value in this file is set by the
+CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE config symbol, which itself defaults
+to 1. Here is the list of possible values in /proc/sys/kernel/sysrq:
    0 - disable sysrq completely
    1 - enable all functions of sysrq
   >1 - bitmask of allowed sysrq functions (see below for detailed function
@@ -32,8 +30,9 @@ in /proc/sys/kernel/sysrq:
 You can set the value in the file by the following command:
     echo "number" >/proc/sys/kernel/sysrq
 
-The number may be written either as decimal or as hexadecimal with the
-0x prefix.
+The number may be written here either as decimal or as hexadecimal
+with the 0x prefix. CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE must always be
+written in hexadecimal.
 
 Note that the value of /proc/sys/kernel/sysrq influences only the invocation
 via a keyboard. Invocation of any operation via /proc/sysrq-trigger is always
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 40a9fe9d3b10..ce396ecdf412 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -51,7 +51,7 @@
 #include <asm/irq_regs.h>
 
 /* Whether we react on sysrq keys or just ignore them */
-static int __read_mostly sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
+static int __read_mostly sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
 static bool __read_mostly sysrq_always_enabled;
 
 unsigned short platform_sysrq_reset_seq[] __weak = { KEY_RESERVED };
diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
index 7faf933cced7..387fa7d05c98 100644
--- a/include/linux/sysrq.h
+++ b/include/linux/sysrq.h
@@ -17,9 +17,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
-/* Enable/disable SYSRQ support by default (0==no, 1==yes). */
-#define SYSRQ_DEFAULT_ENABLE	1
-
 /* Possible values of bitmask for enabling sysrq functions */
 /* 0x0001 is reserved for enable everything */
 #define SYSRQ_ENABLE_LOG	0x0002
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b2f06f3c6a3f..8b80f1bae21a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -190,7 +190,7 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
 
 #ifdef CONFIG_MAGIC_SYSRQ
 /* Note: sysrq code uses it's own private copy */
-static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
+static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
 
 static int sysrq_sysctl_handler(ctl_table *table, int write,
 				void __user *buffer, size_t *lenp,
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 06344d986eb9..29329374ff0d 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -312,6 +312,15 @@ config MAGIC_SYSRQ
 	  keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
 	  unless you really know what this hack does.
 
+config MAGIC_SYSRQ_DEFAULT_ENABLE
+	hex "Enable magic SysRq key functions by default"
+	depends on MAGIC_SYSRQ
+	default 0x1
+	help
+	  Specifies which SysRq key functions are enabled by default.
+	  This may be set to 1 or 0 to enable or disable them all, or
+	  to a bitmask as described in Documentation/sysrq.txt.
+
 config DEBUG_KERNEL
 	bool "Kernel debugging"
 	help
-- 
cgit 


From fa2b5ea09e48186041f68649ab8192447b31bffc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 15 Oct 2013 09:20:52 +0200
Subject: serial: core: delete .set_wake() callback

This deletes the .set_wake() callback in the struct uart_ops.
Apparently this has been unused since pre-git times. In the
old-2.6-bkcvs it is deleted as part of a changeset removing
the PM_SET_WAKEUP from pm_request_t which is since also deleted
from the kernel.

The apropriate way to set wakeups in the kernel is to have a
code snippet like this in .suspend() or .runtime_suspend()
callbacks:

static int foo_suspend(struct device *dev)
{
	if (device_may_wakeup(dev)) {
		/* Enable wakeups, set internal states */
	}
}

This specific callback is not coming back.

Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Kevin Hilman <khilman@deeprootsystems.com>
Cc: Dmitry Artamonow <mad_soft@inbox.ru>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/serial/driver | 4 ----
 include/linux/serial_core.h | 1 -
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/serial/driver b/Documentation/serial/driver
index 067c47d46917..c3a7689a90e6 100644
--- a/Documentation/serial/driver
+++ b/Documentation/serial/driver
@@ -264,10 +264,6 @@ hardware.
 	Locking: none.
 	Interrupts: caller dependent.
 
-  set_wake(port,state)
-	Enable/disable power management wakeup on serial activity.  Not
-	currently implemented.
-
   type(port)
 	Return a pointer to a string constant describing the specified
 	port, or return NULL, in which case the string 'unknown' is
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index b98291ac7f14..f729be981da0 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -66,7 +66,6 @@ struct uart_ops {
 	void		(*set_ldisc)(struct uart_port *, int new);
 	void		(*pm)(struct uart_port *, unsigned int state,
 			      unsigned int oldstate);
-	int		(*set_wake)(struct uart_port *, unsigned int state);
 
 	/*
 	 * Return a string describing the type of the port
-- 
cgit 


From d80e224dd52dfc448e820aefa5f86c441ab76e1a Mon Sep 17 00:00:00 2001
From: Andy Grover <agrover@redhat.com>
Date: Wed, 9 Oct 2013 11:05:56 -0700
Subject: target: Remove TF_CIT_TMPL macro

Remove a lingering macro that just hid a dereference.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andy Grover <agrover@redhat.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 Documentation/target/tcm_mod_builder.py      | 18 ++++++-------
 drivers/scsi/qla2xxx/tcm_qla2xxx.c           | 36 +++++++++++++-------------
 drivers/target/iscsi/iscsi_target_configfs.c | 22 ++++++++--------
 drivers/target/loopback/tcm_loop.c           | 10 ++++----
 drivers/target/sbp/sbp_target.c              | 18 ++++++-------
 drivers/target/target_core_configfs.c        |  6 ++---
 drivers/target/target_core_fabric_configfs.c | 38 ++++++++++++++--------------
 drivers/target/tcm_fc/tfc_conf.c             | 18 ++++++-------
 drivers/usb/gadget/tcm_usb_gadget.c          | 18 ++++++-------
 drivers/vhost/scsi.c                         | 18 ++++++-------
 include/target/target_core_configfs.h        |  1 -
 11 files changed, 101 insertions(+), 102 deletions(-)

(limited to 'include')

diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 54d29c1320ed..230ce71f4d75 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -440,15 +440,15 @@ def tcm_mod_build_configfs(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "	/*\n"
 	buf += "	 * Setup default attribute lists for various fabric->tf_cit_tmpl\n"
 	buf += "	 */\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = " + fabric_mod_name + "_wwn_attrs;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;\n"
-	buf += "	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = " + fabric_mod_name + "_wwn_attrs;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;\n"
+	buf += "	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;\n"
 	buf += "	/*\n"
 	buf += "	 * Register the fabric for use within TCM\n"
 	buf += "	 */\n"
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index f85b9e5c1f05..92b1654f8e20 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1830,16 +1830,16 @@ static int tcm_qla2xxx_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_qla2xxx_tpg_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs =
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_qla2xxx_tpg_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs =
 						tcm_qla2xxx_tpg_attrib_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 	/*
 	 * Register the fabric for use within TCM
 	 */
@@ -1870,15 +1870,15 @@ static int tcm_qla2xxx_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various npiv_fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(npiv_fabric)->tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(npiv_fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	npiv_fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 	/*
 	 * Register the npiv_fabric for use within TCM
 	 */
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index fd145259361d..c2d504425da6 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1995,17 +1995,17 @@ int iscsi_target_register_configfs(void)
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 * sturct config_item_type's
 	 */
-	TF_CIT_TMPL(fabric)->tfc_discovery_cit.ct_attrs = lio_target_discovery_auth_attrs;
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = lio_target_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = lio_target_tpg_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = lio_target_tpg_attrib_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_auth_cit.ct_attrs = lio_target_tpg_auth_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = lio_target_tpg_param_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = lio_target_portal_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = lio_target_initiator_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = lio_target_nacl_attrib_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = lio_target_nacl_auth_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = lio_target_nacl_param_attrs;
+	fabric->tf_cit_tmpl.tfc_discovery_cit.ct_attrs = lio_target_discovery_auth_attrs;
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = lio_target_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = lio_target_tpg_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = lio_target_tpg_attrib_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_auth_cit.ct_attrs = lio_target_tpg_auth_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = lio_target_tpg_param_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = lio_target_portal_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = lio_target_initiator_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = lio_target_nacl_attrib_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = lio_target_nacl_auth_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = lio_target_nacl_param_attrs;
 
 	ret = target_fabric_configfs_register(fabric);
 	if (ret < 0) {
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 0f6d69dabca1..150bdb426fc4 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -1334,11 +1334,11 @@ static int tcm_loop_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_loop_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_loop_tpg_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_loop_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_loop_tpg_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
 	/*
 	 * Once fabric->tf_ops has been setup, now register the fabric for
 	 * use within TCM
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index e51b09a04d52..24884cac19ce 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -2556,15 +2556,15 @@ static int sbp_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = sbp_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = sbp_tpg_base_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = sbp_tpg_attrib_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = sbp_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = sbp_tpg_base_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = sbp_tpg_attrib_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 
 	ret = target_fabric_configfs_register(fabric);
 	if (ret < 0) {
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 82e81c542e43..b04edc12f9d5 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -177,16 +177,16 @@ static struct config_group *target_core_register_fabric(
 	 * struct target_fabric_configfs *tf will contain a usage reference.
 	 */
 	pr_debug("Target_Core_ConfigFS: REGISTER tfc_wwn_cit -> %p\n",
-			&TF_CIT_TMPL(tf)->tfc_wwn_cit);
+			&tf->tf_cit_tmpl.tfc_wwn_cit);
 
 	tf->tf_group.default_groups = tf->tf_default_groups;
 	tf->tf_group.default_groups[0] = &tf->tf_disc_group;
 	tf->tf_group.default_groups[1] = NULL;
 
 	config_group_init_type_name(&tf->tf_group, name,
-			&TF_CIT_TMPL(tf)->tfc_wwn_cit);
+			&tf->tf_cit_tmpl.tfc_wwn_cit);
 	config_group_init_type_name(&tf->tf_disc_group, "discovery_auth",
-			&TF_CIT_TMPL(tf)->tfc_discovery_cit);
+			&tf->tf_cit_tmpl.tfc_discovery_cit);
 
 	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
 			" %s\n", tf->tf_group.cg_item.ci_name);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 3503996d7d10..dae2ad6a669e 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -385,9 +385,9 @@ static struct config_group *target_fabric_make_mappedlun(
 	}
 
 	config_group_init_type_name(&lacl->se_lun_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_mappedlun_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_mappedlun_cit);
 	config_group_init_type_name(&lacl->ml_stat_grps.stat_group,
-			"statistics", &TF_CIT_TMPL(tf)->tfc_tpg_mappedlun_stat_cit);
+			"statistics", &tf->tf_cit_tmpl.tfc_tpg_mappedlun_stat_cit);
 	lacl_cg->default_groups[0] = &lacl->ml_stat_grps.stat_group;
 	lacl_cg->default_groups[1] = NULL;
 
@@ -504,16 +504,16 @@ static struct config_group *target_fabric_make_nodeacl(
 	nacl_cg->default_groups[4] = NULL;
 
 	config_group_init_type_name(&se_nacl->acl_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_base_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_base_cit);
 	config_group_init_type_name(&se_nacl->acl_attrib_group, "attrib",
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_attrib_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit);
 	config_group_init_type_name(&se_nacl->acl_auth_group, "auth",
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_auth_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_auth_cit);
 	config_group_init_type_name(&se_nacl->acl_param_group, "param",
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_param_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_param_cit);
 	config_group_init_type_name(&se_nacl->acl_fabric_stat_group,
 			"fabric_statistics",
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_stat_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_stat_cit);
 
 	return &se_nacl->acl_group;
 }
@@ -595,7 +595,7 @@ static struct config_group *target_fabric_make_np(
 
 	se_tpg_np->tpg_np_parent = se_tpg;
 	config_group_init_type_name(&se_tpg_np->tpg_np_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_np_base_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_np_base_cit);
 
 	return &se_tpg_np->tpg_np_group;
 }
@@ -899,9 +899,9 @@ static struct config_group *target_fabric_make_lun(
 	}
 
 	config_group_init_type_name(&lun->lun_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_port_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_port_cit);
 	config_group_init_type_name(&lun->port_stat_grps.stat_group,
-			"statistics", &TF_CIT_TMPL(tf)->tfc_tpg_port_stat_cit);
+			"statistics", &tf->tf_cit_tmpl.tfc_tpg_port_stat_cit);
 	lun_cg->default_groups[0] = &lun->port_stat_grps.stat_group;
 	lun_cg->default_groups[1] = NULL;
 
@@ -1056,19 +1056,19 @@ static struct config_group *target_fabric_make_tpg(
 	se_tpg->tpg_group.default_groups[6] = NULL;
 
 	config_group_init_type_name(&se_tpg->tpg_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_base_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_base_cit);
 	config_group_init_type_name(&se_tpg->tpg_lun_group, "lun",
-			&TF_CIT_TMPL(tf)->tfc_tpg_lun_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_lun_cit);
 	config_group_init_type_name(&se_tpg->tpg_np_group, "np",
-			&TF_CIT_TMPL(tf)->tfc_tpg_np_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_np_cit);
 	config_group_init_type_name(&se_tpg->tpg_acl_group, "acls",
-			&TF_CIT_TMPL(tf)->tfc_tpg_nacl_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_nacl_cit);
 	config_group_init_type_name(&se_tpg->tpg_attrib_group, "attrib",
-			&TF_CIT_TMPL(tf)->tfc_tpg_attrib_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_attrib_cit);
 	config_group_init_type_name(&se_tpg->tpg_auth_group, "auth",
-			&TF_CIT_TMPL(tf)->tfc_tpg_auth_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_auth_cit);
 	config_group_init_type_name(&se_tpg->tpg_param_group, "param",
-			&TF_CIT_TMPL(tf)->tfc_tpg_param_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_param_cit);
 
 	return &se_tpg->tpg_group;
 }
@@ -1155,9 +1155,9 @@ static struct config_group *target_fabric_make_wwn(
 	wwn->wwn_group.default_groups[1] = NULL;
 
 	config_group_init_type_name(&wwn->wwn_group, name,
-			&TF_CIT_TMPL(tf)->tfc_tpg_cit);
+			&tf->tf_cit_tmpl.tfc_tpg_cit);
 	config_group_init_type_name(&wwn->fabric_stat_group, "fabric_statistics",
-			&TF_CIT_TMPL(tf)->tfc_wwn_fabric_stats_cit);
+			&tf->tf_cit_tmpl.tfc_wwn_fabric_stats_cit);
 
 	return &wwn->wwn_group;
 }
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index 4e0050840a72..c6932fb53a8d 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -571,16 +571,16 @@ int ft_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = ft_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs =
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = ft_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs =
 						    ft_nacl_base_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 	/*
 	 * register the fabric for use within TCM
 	 */
diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c
index 0ff33396eef3..9d89905e2318 100644
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -1923,15 +1923,15 @@ static int usbg_register_configfs(void)
 	}
 
 	fabric->tf_ops = usbg_ops;
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = usbg_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = usbg_base_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = usbg_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = usbg_base_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 	ret = target_fabric_configfs_register(fabric);
 	if (ret < 0) {
 		printk(KERN_ERR "target_fabric_configfs_register() failed"
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 592b31698fc8..0225c1f5eb39 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -2163,15 +2163,15 @@ static int tcm_vhost_register_configfs(void)
 	/*
 	 * Setup default attribute lists for various fabric->tf_cit_tmpl
 	 */
-	TF_CIT_TMPL(fabric)->tfc_wwn_cit.ct_attrs = tcm_vhost_wwn_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_base_cit.ct_attrs = tcm_vhost_tpg_attrs;
-	TF_CIT_TMPL(fabric)->tfc_tpg_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_param_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_np_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_base_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
-	TF_CIT_TMPL(fabric)->tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_vhost_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = tcm_vhost_tpg_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
 	/*
 	 * Register the fabric for use within TCM
 	 */
diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h
index 713c5004f4ae..e0801386e4dc 100644
--- a/include/target/target_core_configfs.h
+++ b/include/target/target_core_configfs.h
@@ -54,4 +54,3 @@ struct target_fabric_configfs {
 	struct target_fabric_configfs_template tf_cit_tmpl;
 };
 
-#define TF_CIT_TMPL(tf) (&(tf)->tf_cit_tmpl)
-- 
cgit 


From f1468a2077e8c00fddb6cecec41b356637195ca3 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
Date: Wed, 16 Oct 2013 21:58:11 +0530
Subject: exynos4-is: Use the generic MIPI CSIS PHY driver

Use the generic PHY API instead of the platform callback
to control the MIPI CSIS DPHY.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Felipe Balbi <balbi@ti.com>
Acked-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/media/platform/exynos4-is/Kconfig     |  2 +-
 drivers/media/platform/exynos4-is/mipi-csis.c | 13 ++++++++++---
 include/linux/platform_data/mipi-csis.h       |  9 ---------
 3 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/exynos4-is/Kconfig b/drivers/media/platform/exynos4-is/Kconfig
index 53ad0f080179..d2d3b4b61435 100644
--- a/drivers/media/platform/exynos4-is/Kconfig
+++ b/drivers/media/platform/exynos4-is/Kconfig
@@ -29,7 +29,7 @@ config VIDEO_S5P_FIMC
 config VIDEO_S5P_MIPI_CSIS
 	tristate "S5P/EXYNOS MIPI-CSI2 receiver (MIPI-CSIS) driver"
 	depends on REGULATOR
-	select S5P_SETUP_MIPIPHY
+	select GENERIC_PHY
 	help
 	  This is a V4L2 driver for Samsung S5P and EXYNOS4 SoC MIPI-CSI2
 	  receiver (MIPI-CSIS) devices.
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index 0914230b42de..9fc2af6a0446 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -20,6 +20,7 @@
 #include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/phy/phy.h>
 #include <linux/platform_data/mipi-csis.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -180,6 +181,7 @@ struct csis_drvdata {
  * @sd: v4l2_subdev associated with CSIS device instance
  * @index: the hardware instance index
  * @pdev: CSIS platform device
+ * @phy: pointer to the CSIS generic PHY
  * @regs: mmaped I/O registers memory
  * @supplies: CSIS regulator supplies
  * @clock: CSIS clocks
@@ -203,6 +205,7 @@ struct csis_state {
 	struct v4l2_subdev sd;
 	u8 index;
 	struct platform_device *pdev;
+	struct phy *phy;
 	void __iomem *regs;
 	struct regulator_bulk_data supplies[CSIS_NUM_SUPPLIES];
 	struct clk *clock[NUM_CSIS_CLOCKS];
@@ -779,8 +782,8 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 					"samsung,csis-wclk");
 
 	state->num_lanes = endpoint.bus.mipi_csi2.num_data_lanes;
-
 	of_node_put(node);
+
 	return 0;
 }
 #else
@@ -829,6 +832,10 @@ static int s5pcsis_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	state->phy = devm_phy_get(dev, "csis");
+	if (IS_ERR(state->phy))
+		return PTR_ERR(state->phy);
+
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	state->regs = devm_ioremap_resource(dev, mem_res);
 	if (IS_ERR(state->regs))
@@ -922,7 +929,7 @@ static int s5pcsis_pm_suspend(struct device *dev, bool runtime)
 	mutex_lock(&state->lock);
 	if (state->flags & ST_POWERED) {
 		s5pcsis_stop_stream(state);
-		ret = s5p_csis_phy_enable(state->index, false);
+		ret = phy_power_off(state->phy);
 		if (ret)
 			goto unlock;
 		ret = regulator_bulk_disable(CSIS_NUM_SUPPLIES,
@@ -958,7 +965,7 @@ static int s5pcsis_pm_resume(struct device *dev, bool runtime)
 					    state->supplies);
 		if (ret)
 			goto unlock;
-		ret = s5p_csis_phy_enable(state->index, true);
+		ret = phy_power_on(state->phy);
 		if (!ret) {
 			state->flags |= ST_POWERED;
 		} else {
diff --git a/include/linux/platform_data/mipi-csis.h b/include/linux/platform_data/mipi-csis.h
index bf34e17cee7f..c2fd9024717c 100644
--- a/include/linux/platform_data/mipi-csis.h
+++ b/include/linux/platform_data/mipi-csis.h
@@ -25,13 +25,4 @@ struct s5p_platform_mipi_csis {
 	u8 hs_settle;
 };
 
-/**
- * s5p_csis_phy_enable - global MIPI-CSI receiver D-PHY control
- * @id:     MIPI-CSIS harware instance index (0...1)
- * @on:     true to enable D-PHY and deassert its reset
- *          false to disable D-PHY
- * @return: 0 on success, or negative error code on failure
- */
-int s5p_csis_phy_enable(int id, bool on);
-
 #endif /* __PLAT_SAMSUNG_MIPI_CSIS_H_ */
-- 
cgit 


From 7e0be9f9f7cba3356f75b86737dbe3a005da067e Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
Date: Wed, 16 Oct 2013 21:58:12 +0530
Subject: video: exynos_mipi_dsim: Use the generic PHY driver

Use the generic PHY API instead of the platform callback
for the MIPI DSIM DPHY enable/reset control.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Felipe Balbi <balbi@ti.com>
Acked-by: Donghwa Lee <dh09.lee@samsung.com>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/video/exynos/Kconfig           |  1 +
 drivers/video/exynos/exynos_mipi_dsi.c | 19 ++++++++++---------
 include/video/exynos_mipi_dsim.h       |  5 ++---
 3 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/video/exynos/Kconfig b/drivers/video/exynos/Kconfig
index 1b035b2eb6b6..976594d578a9 100644
--- a/drivers/video/exynos/Kconfig
+++ b/drivers/video/exynos/Kconfig
@@ -16,6 +16,7 @@ if EXYNOS_VIDEO
 config EXYNOS_MIPI_DSI
 	bool "EXYNOS MIPI DSI driver support."
 	depends on ARCH_S5PV210 || ARCH_EXYNOS
+	select GENERIC_PHY
 	help
 	  This enables support for MIPI-DSI device.
 
diff --git a/drivers/video/exynos/exynos_mipi_dsi.c b/drivers/video/exynos/exynos_mipi_dsi.c
index 32e540600f99..00b3a52c1d68 100644
--- a/drivers/video/exynos/exynos_mipi_dsi.c
+++ b/drivers/video/exynos/exynos_mipi_dsi.c
@@ -30,6 +30,7 @@
 #include <linux/interrupt.h>
 #include <linux/kthread.h>
 #include <linux/notifier.h>
+#include <linux/phy/phy.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/err.h>
@@ -156,8 +157,7 @@ static int exynos_mipi_dsi_blank_mode(struct mipi_dsim_device *dsim, int power)
 		exynos_mipi_regulator_enable(dsim);
 
 		/* enable MIPI-DSI PHY. */
-		if (dsim->pd->phy_enable)
-			dsim->pd->phy_enable(pdev, true);
+		phy_power_on(dsim->phy);
 
 		clk_enable(dsim->clock);
 
@@ -373,6 +373,10 @@ static int exynos_mipi_dsi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	dsim->phy = devm_phy_get(&pdev->dev, "dsim");
+	if (IS_ERR(dsim->phy))
+		return PTR_ERR(dsim->phy);
+
 	dsim->clock = devm_clk_get(&pdev->dev, "dsim0");
 	if (IS_ERR(dsim->clock)) {
 		dev_err(&pdev->dev, "failed to get dsim clock source\n");
@@ -439,8 +443,7 @@ static int exynos_mipi_dsi_probe(struct platform_device *pdev)
 	exynos_mipi_regulator_enable(dsim);
 
 	/* enable MIPI-DSI PHY. */
-	if (dsim->pd->phy_enable)
-		dsim->pd->phy_enable(pdev, true);
+	phy_power_on(dsim->phy);
 
 	exynos_mipi_update_cfg(dsim);
 
@@ -504,9 +507,8 @@ static int exynos_mipi_dsi_suspend(struct device *dev)
 	if (client_drv && client_drv->suspend)
 		client_drv->suspend(client_dev);
 
-	/* enable MIPI-DSI PHY. */
-	if (dsim->pd->phy_enable)
-		dsim->pd->phy_enable(pdev, false);
+	/* disable MIPI-DSI PHY. */
+	phy_power_off(dsim->phy);
 
 	clk_disable(dsim->clock);
 
@@ -536,8 +538,7 @@ static int exynos_mipi_dsi_resume(struct device *dev)
 	exynos_mipi_regulator_enable(dsim);
 
 	/* enable MIPI-DSI PHY. */
-	if (dsim->pd->phy_enable)
-		dsim->pd->phy_enable(pdev, true);
+	phy_power_on(dsim->phy);
 
 	clk_enable(dsim->clock);
 
diff --git a/include/video/exynos_mipi_dsim.h b/include/video/exynos_mipi_dsim.h
index 89dc88a171af..6a578f8a1b3e 100644
--- a/include/video/exynos_mipi_dsim.h
+++ b/include/video/exynos_mipi_dsim.h
@@ -216,6 +216,7 @@ struct mipi_dsim_config {
  *	automatically.
  * @e_clk_src: select byte clock source.
  * @pd: pointer to MIPI-DSI driver platform data.
+ * @phy: pointer to the MIPI-DSI PHY
  */
 struct mipi_dsim_device {
 	struct device			*dev;
@@ -236,6 +237,7 @@ struct mipi_dsim_device {
 	bool				suspended;
 
 	struct mipi_dsim_platform_data	*pd;
+	struct phy			*phy;
 };
 
 /*
@@ -248,7 +250,6 @@ struct mipi_dsim_device {
  * @enabled: indicate whether mipi controller got enabled or not.
  * @lcd_panel_info: pointer for lcd panel specific structure.
  *	this structure specifies width, height, timing and polarity and so on.
- * @phy_enable: pointer to a callback controlling D-PHY enable/reset
  */
 struct mipi_dsim_platform_data {
 	char				lcd_panel_name[PANEL_NAME_SIZE];
@@ -256,8 +257,6 @@ struct mipi_dsim_platform_data {
 	struct mipi_dsim_config		*dsim_config;
 	unsigned int			enabled;
 	void				*lcd_panel_info;
-
-	int (*phy_enable)(struct platform_device *pdev, bool on);
 };
 
 /*
-- 
cgit 


From f9b1e013f1c6723798b8f7f5b83297e2837aaef7 Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Wed, 16 Oct 2013 21:58:15 +0530
Subject: video: exynos_dp: remove non-DT support for Exynos Display Port

Exynos Display Port can be used only for Exynos SoCs. In addition,
non-DT for EXYNOS SoCs is not supported from v3.11; thus, there is
no need to support non-DT for Exynos Display Port.

The 'include/video/exynos_dp.h' file has been used for non-DT
support and the content of file include/video/exynos_dp.h is moved
to drivers/video/exynos/exynos_dp_core.h. Thus, the 'exynos_dp.h'
file is removed. Also, 'struct exynos_dp_platdata' is removed,
because it is not used any more.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Reviewed-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/video/exynos/Kconfig          |   2 +-
 drivers/video/exynos/exynos_dp_core.c | 116 +++++++-----------------------
 drivers/video/exynos/exynos_dp_core.h | 109 ++++++++++++++++++++++++++++
 drivers/video/exynos/exynos_dp_reg.c  |   2 -
 include/video/exynos_dp.h             | 131 ----------------------------------
 5 files changed, 135 insertions(+), 225 deletions(-)
 delete mode 100644 include/video/exynos_dp.h

(limited to 'include')

diff --git a/drivers/video/exynos/Kconfig b/drivers/video/exynos/Kconfig
index 976594d578a9..1129d0e9e640 100644
--- a/drivers/video/exynos/Kconfig
+++ b/drivers/video/exynos/Kconfig
@@ -30,7 +30,7 @@ config EXYNOS_LCD_S6E8AX0
 
 config EXYNOS_DP
 	bool "EXYNOS DP driver support"
-	depends on ARCH_EXYNOS
+	depends on OF && ARCH_EXYNOS
 	default n
 	help
 	  This enables support for DP device.
diff --git a/drivers/video/exynos/exynos_dp_core.c b/drivers/video/exynos/exynos_dp_core.c
index 12bbede3b091..05fed7dc67da 100644
--- a/drivers/video/exynos/exynos_dp_core.c
+++ b/drivers/video/exynos/exynos_dp_core.c
@@ -20,8 +20,6 @@
 #include <linux/delay.h>
 #include <linux/of.h>
 
-#include <video/exynos_dp.h>
-
 #include "exynos_dp_core.h"
 
 static int exynos_dp_init_dp(struct exynos_dp_device *dp)
@@ -894,26 +892,17 @@ static void exynos_dp_hotplug(struct work_struct *work)
 		dev_err(dp->dev, "unable to config video\n");
 }
 
-#ifdef CONFIG_OF
-static struct exynos_dp_platdata *exynos_dp_dt_parse_pdata(struct device *dev)
+static struct video_info *exynos_dp_dt_parse_pdata(struct device *dev)
 {
 	struct device_node *dp_node = dev->of_node;
-	struct exynos_dp_platdata *pd;
 	struct video_info *dp_video_config;
 
-	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
-	if (!pd) {
-		dev_err(dev, "memory allocation for pdata failed\n");
-		return ERR_PTR(-ENOMEM);
-	}
 	dp_video_config = devm_kzalloc(dev,
 				sizeof(*dp_video_config), GFP_KERNEL);
-
 	if (!dp_video_config) {
 		dev_err(dev, "memory allocation for video config failed\n");
 		return ERR_PTR(-ENOMEM);
 	}
-	pd->video_info = dp_video_config;
 
 	dp_video_config->h_sync_polarity =
 		of_property_read_bool(dp_node, "hsync-active-high");
@@ -960,7 +949,7 @@ static struct exynos_dp_platdata *exynos_dp_dt_parse_pdata(struct device *dev)
 		return ERR_PTR(-EINVAL);
 	}
 
-	return pd;
+	return dp_video_config;
 }
 
 static int exynos_dp_dt_parse_phydata(struct exynos_dp_device *dp)
@@ -1003,48 +992,30 @@ err:
 
 static void exynos_dp_phy_init(struct exynos_dp_device *dp)
 {
-	u32 reg;
+	if (dp->phy_addr) {
+		u32 reg;
 
-	reg = __raw_readl(dp->phy_addr);
-	reg |= dp->enable_mask;
-	__raw_writel(reg, dp->phy_addr);
+		reg = __raw_readl(dp->phy_addr);
+		reg |= dp->enable_mask;
+		__raw_writel(reg, dp->phy_addr);
+	}
 }
 
 static void exynos_dp_phy_exit(struct exynos_dp_device *dp)
 {
-	u32 reg;
-
-	reg = __raw_readl(dp->phy_addr);
-	reg &= ~(dp->enable_mask);
-	__raw_writel(reg, dp->phy_addr);
-}
-#else
-static struct exynos_dp_platdata *exynos_dp_dt_parse_pdata(struct device *dev)
-{
-	return NULL;
-}
-
-static int exynos_dp_dt_parse_phydata(struct exynos_dp_device *dp)
-{
-	return -EINVAL;
-}
-
-static void exynos_dp_phy_init(struct exynos_dp_device *dp)
-{
-	return;
-}
+	if (dp->phy_addr) {
+		u32 reg;
 
-static void exynos_dp_phy_exit(struct exynos_dp_device *dp)
-{
-	return;
+		reg = __raw_readl(dp->phy_addr);
+		reg &= ~(dp->enable_mask);
+		__raw_writel(reg, dp->phy_addr);
+	}
 }
-#endif /* CONFIG_OF */
 
 static int exynos_dp_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	struct exynos_dp_device *dp;
-	struct exynos_dp_platdata *pdata;
 
 	int ret = 0;
 
@@ -1057,21 +1028,13 @@ static int exynos_dp_probe(struct platform_device *pdev)
 
 	dp->dev = &pdev->dev;
 
-	if (pdev->dev.of_node) {
-		pdata = exynos_dp_dt_parse_pdata(&pdev->dev);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
+	dp->video_info = exynos_dp_dt_parse_pdata(&pdev->dev);
+	if (IS_ERR(dp->video_info))
+		return PTR_ERR(dp->video_info);
 
-		ret = exynos_dp_dt_parse_phydata(dp);
-		if (ret)
-			return ret;
-	} else {
-		pdata = pdev->dev.platform_data;
-		if (!pdata) {
-			dev_err(&pdev->dev, "no platform data\n");
-			return -EINVAL;
-		}
-	}
+	ret = exynos_dp_dt_parse_phydata(dp);
+	if (ret)
+		return ret;
 
 	dp->clock = devm_clk_get(&pdev->dev, "dp");
 	if (IS_ERR(dp->clock)) {
@@ -1095,15 +1058,7 @@ static int exynos_dp_probe(struct platform_device *pdev)
 
 	INIT_WORK(&dp->hotplug_work, exynos_dp_hotplug);
 
-	dp->video_info = pdata->video_info;
-
-	if (pdev->dev.of_node) {
-		if (dp->phy_addr)
-			exynos_dp_phy_init(dp);
-	} else {
-		if (pdata->phy_init)
-			pdata->phy_init();
-	}
+	exynos_dp_phy_init(dp);
 
 	exynos_dp_init_dp(dp);
 
@@ -1121,18 +1076,11 @@ static int exynos_dp_probe(struct platform_device *pdev)
 
 static int exynos_dp_remove(struct platform_device *pdev)
 {
-	struct exynos_dp_platdata *pdata = pdev->dev.platform_data;
 	struct exynos_dp_device *dp = platform_get_drvdata(pdev);
 
 	flush_work(&dp->hotplug_work);
 
-	if (pdev->dev.of_node) {
-		if (dp->phy_addr)
-			exynos_dp_phy_exit(dp);
-	} else {
-		if (pdata->phy_exit)
-			pdata->phy_exit();
-	}
+	exynos_dp_phy_exit(dp);
 
 	clk_disable_unprepare(dp->clock);
 
@@ -1143,20 +1091,13 @@ static int exynos_dp_remove(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int exynos_dp_suspend(struct device *dev)
 {
-	struct exynos_dp_platdata *pdata = dev->platform_data;
 	struct exynos_dp_device *dp = dev_get_drvdata(dev);
 
 	disable_irq(dp->irq);
 
 	flush_work(&dp->hotplug_work);
 
-	if (dev->of_node) {
-		if (dp->phy_addr)
-			exynos_dp_phy_exit(dp);
-	} else {
-		if (pdata->phy_exit)
-			pdata->phy_exit();
-	}
+	exynos_dp_phy_exit(dp);
 
 	clk_disable_unprepare(dp->clock);
 
@@ -1165,16 +1106,9 @@ static int exynos_dp_suspend(struct device *dev)
 
 static int exynos_dp_resume(struct device *dev)
 {
-	struct exynos_dp_platdata *pdata = dev->platform_data;
 	struct exynos_dp_device *dp = dev_get_drvdata(dev);
 
-	if (dev->of_node) {
-		if (dp->phy_addr)
-			exynos_dp_phy_init(dp);
-	} else {
-		if (pdata->phy_init)
-			pdata->phy_init();
-	}
+	exynos_dp_phy_init(dp);
 
 	clk_prepare_enable(dp->clock);
 
@@ -1203,7 +1137,7 @@ static struct platform_driver exynos_dp_driver = {
 		.name	= "exynos-dp",
 		.owner	= THIS_MODULE,
 		.pm	= &exynos_dp_pm_ops,
-		.of_match_table = of_match_ptr(exynos_dp_match),
+		.of_match_table = exynos_dp_match,
 	},
 };
 
diff --git a/drivers/video/exynos/exynos_dp_core.h b/drivers/video/exynos/exynos_dp_core.h
index 6c567bbf2fb8..56cfec890b46 100644
--- a/drivers/video/exynos/exynos_dp_core.h
+++ b/drivers/video/exynos/exynos_dp_core.h
@@ -13,6 +13,99 @@
 #ifndef _EXYNOS_DP_CORE_H
 #define _EXYNOS_DP_CORE_H
 
+#define DP_TIMEOUT_LOOP_COUNT 100
+#define MAX_CR_LOOP 5
+#define MAX_EQ_LOOP 5
+
+enum link_rate_type {
+	LINK_RATE_1_62GBPS = 0x06,
+	LINK_RATE_2_70GBPS = 0x0a
+};
+
+enum link_lane_count_type {
+	LANE_COUNT1 = 1,
+	LANE_COUNT2 = 2,
+	LANE_COUNT4 = 4
+};
+
+enum link_training_state {
+	START,
+	CLOCK_RECOVERY,
+	EQUALIZER_TRAINING,
+	FINISHED,
+	FAILED
+};
+
+enum voltage_swing_level {
+	VOLTAGE_LEVEL_0,
+	VOLTAGE_LEVEL_1,
+	VOLTAGE_LEVEL_2,
+	VOLTAGE_LEVEL_3,
+};
+
+enum pre_emphasis_level {
+	PRE_EMPHASIS_LEVEL_0,
+	PRE_EMPHASIS_LEVEL_1,
+	PRE_EMPHASIS_LEVEL_2,
+	PRE_EMPHASIS_LEVEL_3,
+};
+
+enum pattern_set {
+	PRBS7,
+	D10_2,
+	TRAINING_PTN1,
+	TRAINING_PTN2,
+	DP_NONE
+};
+
+enum color_space {
+	COLOR_RGB,
+	COLOR_YCBCR422,
+	COLOR_YCBCR444
+};
+
+enum color_depth {
+	COLOR_6,
+	COLOR_8,
+	COLOR_10,
+	COLOR_12
+};
+
+enum color_coefficient {
+	COLOR_YCBCR601,
+	COLOR_YCBCR709
+};
+
+enum dynamic_range {
+	VESA,
+	CEA
+};
+
+enum pll_status {
+	PLL_UNLOCKED,
+	PLL_LOCKED
+};
+
+enum clock_recovery_m_value_type {
+	CALCULATED_M,
+	REGISTER_M
+};
+
+enum video_timing_recognition_type {
+	VIDEO_TIMING_FROM_CAPTURE,
+	VIDEO_TIMING_FROM_REGISTER
+};
+
+enum analog_power_block {
+	AUX_BLOCK,
+	CH0_BLOCK,
+	CH1_BLOCK,
+	CH2_BLOCK,
+	CH3_BLOCK,
+	ANALOG_TOTAL,
+	POWER_ALL
+};
+
 enum dp_irq_type {
 	DP_IRQ_TYPE_HP_CABLE_IN,
 	DP_IRQ_TYPE_HP_CABLE_OUT,
@@ -20,6 +113,22 @@ enum dp_irq_type {
 	DP_IRQ_TYPE_UNKNOWN,
 };
 
+struct video_info {
+	char *name;
+
+	bool h_sync_polarity;
+	bool v_sync_polarity;
+	bool interlaced;
+
+	enum color_space color_space;
+	enum dynamic_range dynamic_range;
+	enum color_coefficient ycbcr_coeff;
+	enum color_depth color_depth;
+
+	enum link_rate_type link_rate;
+	enum link_lane_count_type lane_count;
+};
+
 struct link_train {
 	int eq_loop;
 	int cr_loop[4];
diff --git a/drivers/video/exynos/exynos_dp_reg.c b/drivers/video/exynos/exynos_dp_reg.c
index 29d9d035c73a..b70da5052ff0 100644
--- a/drivers/video/exynos/exynos_dp_reg.c
+++ b/drivers/video/exynos/exynos_dp_reg.c
@@ -14,8 +14,6 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 
-#include <video/exynos_dp.h>
-
 #include "exynos_dp_core.h"
 #include "exynos_dp_reg.h"
 
diff --git a/include/video/exynos_dp.h b/include/video/exynos_dp.h
deleted file mode 100644
index bd8cabd344db..000000000000
--- a/include/video/exynos_dp.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/*
- * Samsung SoC DP device support
- *
- * Copyright (C) 2012 Samsung Electronics Co., Ltd.
- * Author: Jingoo Han <jg1.han@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _EXYNOS_DP_H
-#define _EXYNOS_DP_H
-
-#define DP_TIMEOUT_LOOP_COUNT 100
-#define MAX_CR_LOOP 5
-#define MAX_EQ_LOOP 5
-
-enum link_rate_type {
-	LINK_RATE_1_62GBPS = 0x06,
-	LINK_RATE_2_70GBPS = 0x0a
-};
-
-enum link_lane_count_type {
-	LANE_COUNT1 = 1,
-	LANE_COUNT2 = 2,
-	LANE_COUNT4 = 4
-};
-
-enum link_training_state {
-	START,
-	CLOCK_RECOVERY,
-	EQUALIZER_TRAINING,
-	FINISHED,
-	FAILED
-};
-
-enum voltage_swing_level {
-	VOLTAGE_LEVEL_0,
-	VOLTAGE_LEVEL_1,
-	VOLTAGE_LEVEL_2,
-	VOLTAGE_LEVEL_3,
-};
-
-enum pre_emphasis_level {
-	PRE_EMPHASIS_LEVEL_0,
-	PRE_EMPHASIS_LEVEL_1,
-	PRE_EMPHASIS_LEVEL_2,
-	PRE_EMPHASIS_LEVEL_3,
-};
-
-enum pattern_set {
-	PRBS7,
-	D10_2,
-	TRAINING_PTN1,
-	TRAINING_PTN2,
-	DP_NONE
-};
-
-enum color_space {
-	COLOR_RGB,
-	COLOR_YCBCR422,
-	COLOR_YCBCR444
-};
-
-enum color_depth {
-	COLOR_6,
-	COLOR_8,
-	COLOR_10,
-	COLOR_12
-};
-
-enum color_coefficient {
-	COLOR_YCBCR601,
-	COLOR_YCBCR709
-};
-
-enum dynamic_range {
-	VESA,
-	CEA
-};
-
-enum pll_status {
-	PLL_UNLOCKED,
-	PLL_LOCKED
-};
-
-enum clock_recovery_m_value_type {
-	CALCULATED_M,
-	REGISTER_M
-};
-
-enum video_timing_recognition_type {
-	VIDEO_TIMING_FROM_CAPTURE,
-	VIDEO_TIMING_FROM_REGISTER
-};
-
-enum analog_power_block {
-	AUX_BLOCK,
-	CH0_BLOCK,
-	CH1_BLOCK,
-	CH2_BLOCK,
-	CH3_BLOCK,
-	ANALOG_TOTAL,
-	POWER_ALL
-};
-
-struct video_info {
-	char *name;
-
-	bool h_sync_polarity;
-	bool v_sync_polarity;
-	bool interlaced;
-
-	enum color_space color_space;
-	enum dynamic_range dynamic_range;
-	enum color_coefficient ycbcr_coeff;
-	enum color_depth color_depth;
-
-	enum link_rate_type link_rate;
-	enum link_lane_count_type lane_count;
-};
-
-struct exynos_dp_platdata {
-	struct video_info *video_info;
-
-	void (*phy_init)(void);
-	void (*phy_exit)(void);
-};
-
-#endif /* _EXYNOS_DP_H */
-- 
cgit 


From 75d2364ea0cab3a95be3f8d1f8dabd20ac4b1b2a Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 11 Oct 2013 16:54:56 -0700
Subject: PowerCap: Add class driver

The power capping framework providing a consistent interface between the
kernel and user space that allows power capping drivers to expose their
settings to user space in a uniform way.
The overall design of the framework is described in the documentation
added by the previous patch in this series.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/Kconfig        |  19 ++
 drivers/powercap/Makefile       |   1 +
 drivers/powercap/powercap_sys.c | 683 ++++++++++++++++++++++++++++++++++++++++
 include/linux/powercap.h        | 325 +++++++++++++++++++
 4 files changed, 1028 insertions(+)
 create mode 100644 drivers/powercap/Kconfig
 create mode 100644 drivers/powercap/Makefile
 create mode 100644 drivers/powercap/powercap_sys.c
 create mode 100644 include/linux/powercap.h

(limited to 'include')

diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
new file mode 100644
index 000000000000..a37055eb5ebc
--- /dev/null
+++ b/drivers/powercap/Kconfig
@@ -0,0 +1,19 @@
+#
+# Generic power capping sysfs interface configuration
+#
+
+menuconfig POWERCAP
+	bool "Generic powercap sysfs driver"
+	help
+	  The power capping sysfs interface allows kernel subsystems to expose power
+	  capping settings to user space in a consistent way.  Usually, it consists
+	  of multiple control types that determine which settings may be exposed and
+	  power zones representing parts of the system that can be subject to power
+	  capping.
+
+	  If you want this code to be compiled in, say Y here.
+
+if POWERCAP
+# Client driver configurations go here.
+
+endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
new file mode 100644
index 000000000000..6defbc8dc4bf
--- /dev/null
+++ b/drivers/powercap/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
new file mode 100644
index 000000000000..c22fa4c78eaa
--- /dev/null
+++ b/drivers/powercap/powercap_sys.c
@@ -0,0 +1,683 @@
+/*
+ * Power capping class
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/powercap.h>
+
+#define to_powercap_zone(n) container_of(n, struct powercap_zone, dev)
+#define to_powercap_control_type(n) \
+			container_of(n, struct powercap_control_type, dev)
+
+/* Power zone show function */
+#define define_power_zone_show(_attr)		\
+static ssize_t _attr##_show(struct device *dev, \
+					struct device_attribute *dev_attr,\
+					char *buf) \
+{ \
+	u64 value; \
+	ssize_t len = -EINVAL; \
+	struct powercap_zone *power_zone = to_powercap_zone(dev); \
+	\
+	if (power_zone->ops->get_##_attr) { \
+		if (!power_zone->ops->get_##_attr(power_zone, &value)) \
+			len = sprintf(buf, "%lld\n", value); \
+	} \
+	\
+	return len; \
+}
+
+/* The only meaningful input is 0 (reset), others are silently ignored */
+#define define_power_zone_store(_attr)		\
+static ssize_t _attr##_store(struct device *dev,\
+				struct device_attribute *dev_attr, \
+				const char *buf, size_t count) \
+{ \
+	int err; \
+	struct powercap_zone *power_zone = to_powercap_zone(dev); \
+	u64 value; \
+	\
+	err = kstrtoull(buf, 10, &value); \
+	if (err) \
+		return -EINVAL; \
+	if (value) \
+		return count; \
+	if (power_zone->ops->reset_##_attr) { \
+		if (!power_zone->ops->reset_##_attr(power_zone)) \
+			return count; \
+	} \
+	\
+	return -EINVAL; \
+}
+
+/* Power zone constraint show function */
+#define define_power_zone_constraint_show(_attr) \
+static ssize_t show_constraint_##_attr(struct device *dev, \
+				struct device_attribute *dev_attr,\
+				char *buf) \
+{ \
+	u64 value; \
+	ssize_t len = -ENODATA; \
+	struct powercap_zone *power_zone = to_powercap_zone(dev); \
+	int id; \
+	struct powercap_zone_constraint *pconst;\
+	\
+	if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \
+		return -EINVAL; \
+	if (id >= power_zone->const_id_cnt)	\
+		return -EINVAL; \
+	pconst = &power_zone->constraints[id]; \
+	if (pconst && pconst->ops && pconst->ops->get_##_attr) { \
+		if (!pconst->ops->get_##_attr(power_zone, id, &value)) \
+			len = sprintf(buf, "%lld\n", value); \
+	} \
+	\
+	return len; \
+}
+
+/* Power zone constraint store function */
+#define define_power_zone_constraint_store(_attr) \
+static ssize_t store_constraint_##_attr(struct device *dev,\
+				struct device_attribute *dev_attr, \
+				const char *buf, size_t count) \
+{ \
+	int err; \
+	u64 value; \
+	struct powercap_zone *power_zone = to_powercap_zone(dev); \
+	int id; \
+	struct powercap_zone_constraint *pconst;\
+	\
+	if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id)) \
+		return -EINVAL; \
+	if (id >= power_zone->const_id_cnt)	\
+		return -EINVAL; \
+	pconst = &power_zone->constraints[id]; \
+	err = kstrtoull(buf, 10, &value); \
+	if (err) \
+		return -EINVAL; \
+	if (pconst && pconst->ops && pconst->ops->set_##_attr) { \
+		if (!pconst->ops->set_##_attr(power_zone, id, value)) \
+			return count; \
+	} \
+	\
+	return -ENODATA; \
+}
+
+/* Power zone information callbacks */
+define_power_zone_show(power_uw);
+define_power_zone_show(max_power_range_uw);
+define_power_zone_show(energy_uj);
+define_power_zone_store(energy_uj);
+define_power_zone_show(max_energy_range_uj);
+
+/* Power zone attributes */
+static DEVICE_ATTR_RO(max_power_range_uw);
+static DEVICE_ATTR_RO(power_uw);
+static DEVICE_ATTR_RO(max_energy_range_uj);
+static DEVICE_ATTR_RW(energy_uj);
+
+/* Power zone constraint attributes callbacks */
+define_power_zone_constraint_show(power_limit_uw);
+define_power_zone_constraint_store(power_limit_uw);
+define_power_zone_constraint_show(time_window_us);
+define_power_zone_constraint_store(time_window_us);
+define_power_zone_constraint_show(max_power_uw);
+define_power_zone_constraint_show(min_power_uw);
+define_power_zone_constraint_show(max_time_window_us);
+define_power_zone_constraint_show(min_time_window_us);
+
+/* For one time seeding of constraint device attributes */
+struct powercap_constraint_attr {
+	struct device_attribute power_limit_attr;
+	struct device_attribute time_window_attr;
+	struct device_attribute max_power_attr;
+	struct device_attribute min_power_attr;
+	struct device_attribute max_time_window_attr;
+	struct device_attribute min_time_window_attr;
+	struct device_attribute name_attr;
+};
+
+static struct powercap_constraint_attr
+				constraint_attrs[MAX_CONSTRAINTS_PER_ZONE];
+
+/* A list of powercap control_types */
+static LIST_HEAD(powercap_cntrl_list);
+/* Mutex to protect list of powercap control_types */
+static DEFINE_MUTEX(powercap_cntrl_list_lock);
+
+#define POWERCAP_CONSTRAINT_NAME_LEN	30 /* Some limit to avoid overflow */
+static ssize_t show_constraint_name(struct device *dev,
+				struct device_attribute *dev_attr,
+				char *buf)
+{
+	const char *name;
+	struct powercap_zone *power_zone = to_powercap_zone(dev);
+	int id;
+	ssize_t len = -ENODATA;
+	struct powercap_zone_constraint *pconst;
+
+	if (!sscanf(dev_attr->attr.name, "constraint_%d_", &id))
+		return -EINVAL;
+	if (id >= power_zone->const_id_cnt)
+		return -EINVAL;
+	pconst = &power_zone->constraints[id];
+
+	if (pconst && pconst->ops && pconst->ops->get_name) {
+		name = pconst->ops->get_name(power_zone, id);
+		if (name) {
+			snprintf(buf, POWERCAP_CONSTRAINT_NAME_LEN,
+								"%s\n", name);
+			buf[POWERCAP_CONSTRAINT_NAME_LEN] = '\0';
+			len = strlen(buf);
+		}
+	}
+
+	return len;
+}
+
+static int create_constraint_attribute(int id, const char *name,
+				int mode,
+				struct device_attribute *dev_attr,
+				ssize_t (*show)(struct device *,
+					struct device_attribute *, char *),
+				ssize_t (*store)(struct device *,
+					struct device_attribute *,
+				const char *, size_t)
+				)
+{
+
+	dev_attr->attr.name = kasprintf(GFP_KERNEL, "constraint_%d_%s",
+								id, name);
+	if (!dev_attr->attr.name)
+		return -ENOMEM;
+	dev_attr->attr.mode = mode;
+	dev_attr->show = show;
+	dev_attr->store = store;
+
+	return 0;
+}
+
+static void free_constraint_attributes(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_CONSTRAINTS_PER_ZONE; ++i) {
+		kfree(constraint_attrs[i].power_limit_attr.attr.name);
+		kfree(constraint_attrs[i].time_window_attr.attr.name);
+		kfree(constraint_attrs[i].name_attr.attr.name);
+		kfree(constraint_attrs[i].max_power_attr.attr.name);
+		kfree(constraint_attrs[i].min_power_attr.attr.name);
+		kfree(constraint_attrs[i].max_time_window_attr.attr.name);
+		kfree(constraint_attrs[i].min_time_window_attr.attr.name);
+	}
+}
+
+static int seed_constraint_attributes(void)
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < MAX_CONSTRAINTS_PER_ZONE; ++i) {
+		ret = create_constraint_attribute(i, "power_limit_uw",
+					S_IWUSR | S_IRUGO,
+					&constraint_attrs[i].power_limit_attr,
+					show_constraint_power_limit_uw,
+					store_constraint_power_limit_uw);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "time_window_us",
+					S_IWUSR | S_IRUGO,
+					&constraint_attrs[i].time_window_attr,
+					show_constraint_time_window_us,
+					store_constraint_time_window_us);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "name", S_IRUGO,
+				&constraint_attrs[i].name_attr,
+				show_constraint_name,
+				NULL);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "max_power_uw", S_IRUGO,
+				&constraint_attrs[i].max_power_attr,
+				show_constraint_max_power_uw,
+				NULL);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "min_power_uw", S_IRUGO,
+				&constraint_attrs[i].min_power_attr,
+				show_constraint_min_power_uw,
+				NULL);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "max_time_window_us",
+				S_IRUGO,
+				&constraint_attrs[i].max_time_window_attr,
+				show_constraint_max_time_window_us,
+				NULL);
+		if (ret)
+			goto err_alloc;
+		ret = create_constraint_attribute(i, "min_time_window_us",
+				S_IRUGO,
+				&constraint_attrs[i].min_time_window_attr,
+				show_constraint_min_time_window_us,
+				NULL);
+		if (ret)
+			goto err_alloc;
+
+	}
+
+	return 0;
+
+err_alloc:
+	free_constraint_attributes();
+
+	return ret;
+}
+
+static int create_constraints(struct powercap_zone *power_zone,
+				int nr_constraints,
+				struct powercap_zone_constraint_ops *const_ops)
+{
+	int i;
+	int ret = 0;
+	int count;
+	struct powercap_zone_constraint *pconst;
+
+	if (!power_zone || !const_ops || !const_ops->get_power_limit_uw ||
+					!const_ops->set_power_limit_uw ||
+					!const_ops->get_time_window_us ||
+					!const_ops->set_time_window_us)
+		return -EINVAL;
+
+	count = power_zone->zone_attr_count;
+	for (i = 0; i < nr_constraints; ++i) {
+		pconst = &power_zone->constraints[i];
+		pconst->ops = const_ops;
+		pconst->id = power_zone->const_id_cnt;
+		power_zone->const_id_cnt++;
+		power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].power_limit_attr.attr;
+		power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].time_window_attr.attr;
+		if (pconst->ops->get_name)
+			power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].name_attr.attr;
+		if (pconst->ops->get_max_power_uw)
+			power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].max_power_attr.attr;
+		if (pconst->ops->get_min_power_uw)
+			power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].min_power_attr.attr;
+		if (pconst->ops->get_max_time_window_us)
+			power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].max_time_window_attr.attr;
+		if (pconst->ops->get_min_time_window_us)
+			power_zone->zone_dev_attrs[count++] =
+				&constraint_attrs[i].min_time_window_attr.attr;
+	}
+	power_zone->zone_attr_count = count;
+
+	return ret;
+}
+
+static bool control_type_valid(void *control_type)
+{
+	struct powercap_control_type *pos = NULL;
+	bool found = false;
+
+	mutex_lock(&powercap_cntrl_list_lock);
+
+	list_for_each_entry(pos, &powercap_cntrl_list, node) {
+		if (pos == control_type) {
+			found = true;
+			break;
+		}
+	}
+	mutex_unlock(&powercap_cntrl_list_lock);
+
+	return found;
+}
+
+static ssize_t name_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct powercap_zone *power_zone = to_powercap_zone(dev);
+
+	return sprintf(buf, "%s\n", power_zone->name);
+}
+
+static DEVICE_ATTR_RO(name);
+
+/* Create zone and attributes in sysfs */
+static void create_power_zone_common_attributes(
+					struct powercap_zone *power_zone)
+{
+	int count = 0;
+
+	power_zone->zone_dev_attrs[count++] = &dev_attr_name.attr;
+	if (power_zone->ops->get_max_energy_range_uj)
+		power_zone->zone_dev_attrs[count++] =
+					&dev_attr_max_energy_range_uj.attr;
+	if (power_zone->ops->get_energy_uj)
+		power_zone->zone_dev_attrs[count++] =
+					&dev_attr_energy_uj.attr;
+	if (power_zone->ops->get_power_uw)
+		power_zone->zone_dev_attrs[count++] =
+					&dev_attr_power_uw.attr;
+	if (power_zone->ops->get_max_power_range_uw)
+		power_zone->zone_dev_attrs[count++] =
+					&dev_attr_max_power_range_uw.attr;
+	power_zone->zone_dev_attrs[count] = NULL;
+	power_zone->zone_attr_count = count;
+}
+
+static void powercap_release(struct device *dev)
+{
+	bool allocated;
+
+	if (dev->parent) {
+		struct powercap_zone *power_zone = to_powercap_zone(dev);
+
+		/* Store flag as the release() may free memory */
+		allocated = power_zone->allocated;
+		/* Remove id from parent idr struct */
+		idr_remove(power_zone->parent_idr, power_zone->id);
+		/* Destroy idrs allocated for this zone */
+		idr_destroy(&power_zone->idr);
+		kfree(power_zone->name);
+		kfree(power_zone->zone_dev_attrs);
+		kfree(power_zone->constraints);
+		if (power_zone->ops->release)
+			power_zone->ops->release(power_zone);
+		if (allocated)
+			kfree(power_zone);
+	} else {
+		struct powercap_control_type *control_type =
+						to_powercap_control_type(dev);
+
+		/* Store flag as the release() may free memory */
+		allocated = control_type->allocated;
+		idr_destroy(&control_type->idr);
+		mutex_destroy(&control_type->lock);
+		if (control_type->ops && control_type->ops->release)
+			control_type->ops->release(control_type);
+		if (allocated)
+			kfree(control_type);
+	}
+}
+
+static ssize_t enabled_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	bool mode = true;
+
+	/* Default is enabled */
+	if (dev->parent) {
+		struct powercap_zone *power_zone = to_powercap_zone(dev);
+		if (power_zone->ops->get_enable)
+			if (power_zone->ops->get_enable(power_zone, &mode))
+				mode = false;
+	} else {
+		struct powercap_control_type *control_type =
+						to_powercap_control_type(dev);
+		if (control_type->ops && control_type->ops->get_enable)
+			if (control_type->ops->get_enable(control_type, &mode))
+				mode = false;
+	}
+
+	return sprintf(buf, "%d\n", mode);
+}
+
+static ssize_t enabled_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf,  size_t len)
+{
+	bool mode;
+
+	if (strtobool(buf, &mode))
+		return -EINVAL;
+	if (dev->parent) {
+		struct powercap_zone *power_zone = to_powercap_zone(dev);
+		if (power_zone->ops->set_enable)
+			if (!power_zone->ops->set_enable(power_zone, mode))
+				return len;
+	} else {
+		struct powercap_control_type *control_type =
+						to_powercap_control_type(dev);
+		if (control_type->ops && control_type->ops->set_enable)
+			if (!control_type->ops->set_enable(control_type, mode))
+				return len;
+	}
+
+	return -ENOSYS;
+}
+
+static struct device_attribute powercap_def_attrs[] = {
+		__ATTR(enabled, S_IWUSR | S_IRUGO, enabled_show,
+							enabled_store),
+		__ATTR_NULL
+};
+
+static struct class powercap_class = {
+	.name = "powercap",
+	.dev_release = powercap_release,
+	.dev_attrs = powercap_def_attrs,
+};
+
+struct powercap_zone *powercap_register_zone(
+				struct powercap_zone *power_zone,
+				struct powercap_control_type *control_type,
+				const char *name,
+				struct powercap_zone *parent,
+				const struct powercap_zone_ops *ops,
+				int nr_constraints,
+				struct powercap_zone_constraint_ops *const_ops)
+{
+	int result;
+	int nr_attrs;
+
+	if (!name || !control_type || !ops ||
+			nr_constraints > MAX_CONSTRAINTS_PER_ZONE ||
+			(!ops->get_energy_uj && !ops->get_power_uw) ||
+			!control_type_valid(control_type))
+		return ERR_PTR(-EINVAL);
+
+	if (power_zone) {
+		if (!ops->release)
+			return ERR_PTR(-EINVAL);
+		memset(power_zone, 0, sizeof(*power_zone));
+	} else {
+		power_zone = kzalloc(sizeof(*power_zone), GFP_KERNEL);
+		if (!power_zone)
+			return ERR_PTR(-ENOMEM);
+		power_zone->allocated = true;
+	}
+	power_zone->ops = ops;
+	power_zone->control_type_inst = control_type;
+	if (!parent) {
+		power_zone->dev.parent = &control_type->dev;
+		power_zone->parent_idr = &control_type->idr;
+	} else {
+		power_zone->dev.parent = &parent->dev;
+		power_zone->parent_idr = &parent->idr;
+	}
+	power_zone->dev.class = &powercap_class;
+
+	mutex_lock(&control_type->lock);
+	/* Using idr to get the unique id */
+	result = idr_alloc(power_zone->parent_idr, NULL, 0, 0, GFP_KERNEL);
+	if (result < 0)
+		goto err_idr_alloc;
+
+	power_zone->id = result;
+	idr_init(&power_zone->idr);
+	power_zone->name = kstrdup(name, GFP_KERNEL);
+	if (!power_zone->name)
+		goto err_name_alloc;
+	dev_set_name(&power_zone->dev, "%s:%x",
+					dev_name(power_zone->dev.parent),
+					power_zone->id);
+	power_zone->constraints = kzalloc(sizeof(*power_zone->constraints) *
+					 nr_constraints, GFP_KERNEL);
+	if (!power_zone->constraints)
+		goto err_const_alloc;
+
+	nr_attrs = nr_constraints * POWERCAP_CONSTRAINTS_ATTRS +
+						POWERCAP_ZONE_MAX_ATTRS + 1;
+	power_zone->zone_dev_attrs = kzalloc(sizeof(void *) *
+						nr_attrs, GFP_KERNEL);
+	if (!power_zone->zone_dev_attrs)
+		goto err_attr_alloc;
+	create_power_zone_common_attributes(power_zone);
+	result = create_constraints(power_zone, nr_constraints, const_ops);
+	if (result)
+		goto err_dev_ret;
+
+	power_zone->zone_dev_attrs[power_zone->zone_attr_count] = NULL;
+	power_zone->dev_zone_attr_group.attrs = power_zone->zone_dev_attrs;
+	power_zone->dev_attr_groups[0] = &power_zone->dev_zone_attr_group;
+	power_zone->dev_attr_groups[1] = NULL;
+	power_zone->dev.groups = power_zone->dev_attr_groups;
+	result = device_register(&power_zone->dev);
+	if (result)
+		goto err_dev_ret;
+
+	control_type->nr_zones++;
+	mutex_unlock(&control_type->lock);
+
+	return power_zone;
+
+err_dev_ret:
+	kfree(power_zone->zone_dev_attrs);
+err_attr_alloc:
+	kfree(power_zone->constraints);
+err_const_alloc:
+	kfree(power_zone->name);
+err_name_alloc:
+	idr_remove(power_zone->parent_idr, power_zone->id);
+err_idr_alloc:
+	if (power_zone->allocated)
+		kfree(power_zone);
+	mutex_unlock(&control_type->lock);
+
+	return ERR_PTR(result);
+}
+EXPORT_SYMBOL_GPL(powercap_register_zone);
+
+int powercap_unregister_zone(struct powercap_control_type *control_type,
+				struct powercap_zone *power_zone)
+{
+	if (!power_zone || !control_type)
+		return -EINVAL;
+
+	mutex_lock(&control_type->lock);
+	control_type->nr_zones--;
+	mutex_unlock(&control_type->lock);
+
+	device_unregister(&power_zone->dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(powercap_unregister_zone);
+
+struct powercap_control_type *powercap_register_control_type(
+				struct powercap_control_type *control_type,
+				const char *name,
+				const struct powercap_control_type_ops *ops)
+{
+	int result;
+
+	if (!name)
+		return ERR_PTR(-EINVAL);
+	if (control_type) {
+		if (!ops || !ops->release)
+			return ERR_PTR(-EINVAL);
+		memset(control_type, 0, sizeof(*control_type));
+	} else {
+		control_type = kzalloc(sizeof(*control_type), GFP_KERNEL);
+		if (!control_type)
+			return ERR_PTR(-ENOMEM);
+		control_type->allocated = true;
+	}
+	mutex_init(&control_type->lock);
+	control_type->ops = ops;
+	INIT_LIST_HEAD(&control_type->node);
+	control_type->dev.class = &powercap_class;
+	dev_set_name(&control_type->dev, name);
+	result = device_register(&control_type->dev);
+	if (result) {
+		if (control_type->allocated)
+			kfree(control_type);
+		return ERR_PTR(result);
+	}
+	idr_init(&control_type->idr);
+
+	mutex_lock(&powercap_cntrl_list_lock);
+	list_add_tail(&control_type->node, &powercap_cntrl_list);
+	mutex_unlock(&powercap_cntrl_list_lock);
+
+	return control_type;
+}
+EXPORT_SYMBOL_GPL(powercap_register_control_type);
+
+int powercap_unregister_control_type(struct powercap_control_type *control_type)
+{
+	struct powercap_control_type *pos = NULL;
+
+	if (control_type->nr_zones) {
+		dev_err(&control_type->dev, "Zones of this type still not freed\n");
+		return -EINVAL;
+	}
+	mutex_lock(&powercap_cntrl_list_lock);
+	list_for_each_entry(pos, &powercap_cntrl_list, node) {
+		if (pos == control_type) {
+			list_del(&control_type->node);
+			mutex_unlock(&powercap_cntrl_list_lock);
+			device_unregister(&control_type->dev);
+			return 0;
+		}
+	}
+	mutex_unlock(&powercap_cntrl_list_lock);
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(powercap_unregister_control_type);
+
+static int __init powercap_init(void)
+{
+	int result = 0;
+
+	result = seed_constraint_attributes();
+	if (result)
+		return result;
+
+	result = class_register(&powercap_class);
+
+	return result;
+}
+
+device_initcall(powercap_init);
+
+MODULE_DESCRIPTION("PowerCap sysfs Driver");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/powercap.h b/include/linux/powercap.h
new file mode 100644
index 000000000000..4e250417ee30
--- /dev/null
+++ b/include/linux/powercap.h
@@ -0,0 +1,325 @@
+/*
+ * powercap.h: Data types and headers for sysfs power capping interface
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.
+ *
+ */
+
+#ifndef __POWERCAP_H__
+#define __POWERCAP_H__
+
+#include <linux/device.h>
+#include <linux/idr.h>
+
+/*
+ * A power cap class device can contain multiple powercap control_types.
+ * Each control_type can have multiple power zones, which can be independently
+ * controlled. Each power zone can have one or more constraints.
+ */
+
+struct powercap_control_type;
+struct powercap_zone;
+struct powercap_zone_constraint;
+
+/**
+ * struct powercap_control_type_ops - Define control type callbacks
+ * @set_enable:		Enable/Disable whole control type.
+ *			Default is enabled. But this callback allows all zones
+ *			to be in disable state and remove any applied power
+ *			limits. If disabled power zone can only be monitored
+ *			not controlled.
+ * @get_enable:		get Enable/Disable status.
+ * @release:		Callback to inform that last reference to this
+ *			control type is closed. So it is safe to free data
+ *			structure associated with this control type.
+ *			This callback is mandatory if the client own memory
+ *			for the control type.
+ *
+ * This structure defines control type callbacks to be implemented by client
+ * drivers
+ */
+struct powercap_control_type_ops {
+	int (*set_enable) (struct powercap_control_type *, bool mode);
+	int (*get_enable) (struct powercap_control_type *, bool *mode);
+	int (*release) (struct powercap_control_type *);
+};
+
+/**
+ * struct powercap_control_type- Defines a powercap control_type
+ * @name:		name of control_type
+ * @dev:		device for this control_type
+ * @idr:		idr to have unique id for its child
+ * @root_node:		Root holding power zones for this control_type
+ * @ops:		Pointer to callback struct
+ * @node_lock:		mutex for control type
+ * @allocated:		This is possible that client owns the memory
+ *			used by this structure. In this case
+ *			this flag is set to false by framework to
+ *			prevent deallocation during release process.
+ *			Otherwise this flag is set to true.
+ * @ctrl_inst:		link to the control_type list
+ *
+ * Defines powercap control_type. This acts as a container for power
+ * zones, which use same method to control power. E.g. RAPL, RAPL-PCI etc.
+ * All fields are private and should not be used by client drivers.
+ */
+struct powercap_control_type {
+	struct device dev;
+	struct idr idr;
+	int nr_zones;
+	const struct powercap_control_type_ops *ops;
+	struct mutex lock;
+	bool allocated;
+	struct list_head node;
+};
+
+/**
+ * struct powercap_zone_ops - Define power zone callbacks
+ * @get_max_energy_range_uj:	Get maximum range of energy counter in
+ *				micro-joules.
+ * @get_energy_uj:		Get current energy counter in micro-joules.
+ * @reset_energy_uj:		Reset micro-joules energy counter.
+ * @get_max_power_range_uw:	Get maximum range of power counter in
+ *				micro-watts.
+ * @get_power_uw:		Get current power counter in micro-watts.
+ * @set_enable:			Enable/Disable power zone controls.
+ *				Default is enabled.
+ * @get_enable:			get Enable/Disable status.
+ * @release:			Callback to inform that last reference to this
+ *				control type is closed. So it is safe to free
+ *				data structure associated with this
+ *				control type. Mandatory, if client driver owns
+ *				the power_zone memory.
+ *
+ * This structure defines zone callbacks to be implemented by client drivers.
+ * Client drives can define both energy and power related callbacks. But at
+ * the least one type (either power or energy) is mandatory. Client drivers
+ * should handle mutual exclusion, if required in callbacks.
+ */
+struct powercap_zone_ops {
+	int (*get_max_energy_range_uj) (struct powercap_zone *, u64 *);
+	int (*get_energy_uj) (struct powercap_zone *, u64 *);
+	int (*reset_energy_uj) (struct powercap_zone *);
+	int (*get_max_power_range_uw) (struct powercap_zone *, u64 *);
+	int (*get_power_uw) (struct powercap_zone *, u64 *);
+	int (*set_enable) (struct powercap_zone *, bool mode);
+	int (*get_enable) (struct powercap_zone *, bool *mode);
+	int (*release) (struct powercap_zone *);
+};
+
+#define	POWERCAP_ZONE_MAX_ATTRS		6
+#define	POWERCAP_CONSTRAINTS_ATTRS	8
+#define MAX_CONSTRAINTS_PER_ZONE	10
+/**
+ * struct powercap_zone- Defines instance of a power cap zone
+ * @id:			Unique id
+ * @name:		Power zone name.
+ * @control_type_inst:	Control type instance for this zone.
+ * @ops:		Pointer to the zone operation structure.
+ * @dev:		Instance of a device.
+ * @const_id_cnt:	Number of constraint defined.
+ * @idr:		Instance to an idr entry for children zones.
+ * @parent_idr:		To remove reference from the parent idr.
+ * @private_data:	Private data pointer if any for this zone.
+ * @zone_dev_attrs:	Attributes associated with this device.
+ * @zone_attr_count:	Attribute count.
+ * @dev_zone_attr_group: Attribute group for attributes.
+ * @dev_attr_groups:	Attribute group store to register with device.
+ * @allocated:		This is possible that client owns the memory
+ *			used by this structure. In this case
+ *			this flag is set to false by framework to
+ *			prevent deallocation during release process.
+ *			Otherwise this flag is set to true.
+ * @constraint_ptr:	List of constraints for this zone.
+ *
+ * This defines a power zone instance. The fields of this structure are
+ * private, and should not be used by client drivers.
+ */
+struct powercap_zone {
+	int id;
+	char *name;
+	void *control_type_inst;
+	const struct powercap_zone_ops *ops;
+	struct device dev;
+	int const_id_cnt;
+	struct idr idr;
+	struct idr *parent_idr;
+	void *private_data;
+	struct attribute **zone_dev_attrs;
+	int zone_attr_count;
+	struct attribute_group dev_zone_attr_group;
+	const struct attribute_group *dev_attr_groups[2]; /* 1 group + NULL */
+	bool allocated;
+	struct powercap_zone_constraint *constraints;
+};
+
+/**
+ * struct powercap_zone_constraint_ops - Define constraint callbacks
+ * @set_power_limit_uw:		Set power limit in micro-watts.
+ * @get_power_limit_uw:		Get power limit in micro-watts.
+ * @set_time_window_us:		Set time window in micro-seconds.
+ * @get_time_window_us:		Get time window in micro-seconds.
+ * @get_max_power_uw:		Get max power allowed in micro-watts.
+ * @get_min_power_uw:		Get min power allowed in micro-watts.
+ * @get_max_time_window_us:	Get max time window allowed in micro-seconds.
+ * @get_min_time_window_us:	Get min time window allowed in micro-seconds.
+ * @get_name:			Get the name of constraint
+ *
+ * This structure is used to define the constraint callbacks for the client
+ * drivers. The following callbacks are mandatory and can't be NULL:
+ *  set_power_limit_uw
+ *  get_power_limit_uw
+ *  set_time_window_us
+ *  get_time_window_us
+ *  get_name
+ *  Client drivers should handle mutual exclusion, if required in callbacks.
+ */
+struct powercap_zone_constraint_ops {
+	int (*set_power_limit_uw) (struct powercap_zone *, int, u64);
+	int (*get_power_limit_uw) (struct powercap_zone *, int, u64 *);
+	int (*set_time_window_us) (struct powercap_zone *, int, u64);
+	int (*get_time_window_us) (struct powercap_zone *, int, u64 *);
+	int (*get_max_power_uw) (struct powercap_zone *, int, u64 *);
+	int (*get_min_power_uw) (struct powercap_zone *, int, u64 *);
+	int (*get_max_time_window_us) (struct powercap_zone *, int, u64 *);
+	int (*get_min_time_window_us) (struct powercap_zone *, int, u64 *);
+	const char *(*get_name) (struct powercap_zone *, int);
+};
+
+/**
+ * struct powercap_zone_constraint- Defines instance of a constraint
+ * @id:			Instance Id of this constraint.
+ * @power_zone:		Pointer to the power zone for this constraint.
+ * @ops:		Pointer to the constraint callbacks.
+ *
+ * This defines a constraint instance.
+ */
+struct powercap_zone_constraint {
+	int id;
+	struct powercap_zone *power_zone;
+	struct powercap_zone_constraint_ops *ops;
+};
+
+
+/* For clients to get their device pointer, may be used for dev_dbgs */
+#define POWERCAP_GET_DEV(power_zone)	(&power_zone->dev)
+
+/**
+* powercap_set_zone_data() - Set private data for a zone
+* @power_zone:	A pointer to the valid zone instance.
+* @pdata:	A pointer to the user private data.
+*
+* Allows client drivers to associate some private data to zone instance.
+*/
+static inline void powercap_set_zone_data(struct powercap_zone *power_zone,
+						void *pdata)
+{
+	if (power_zone)
+		power_zone->private_data = pdata;
+}
+
+/**
+* powercap_get_zone_data() - Get private data for a zone
+* @power_zone:	A pointer to the valid zone instance.
+*
+* Allows client drivers to get private data associate with a zone,
+* using call to powercap_set_zone_data.
+*/
+static inline void *powercap_get_zone_data(struct powercap_zone *power_zone)
+{
+	if (power_zone)
+		return power_zone->private_data;
+	return NULL;
+}
+
+/**
+* powercap_register_control_type() - Register a control_type with framework
+* @control_type:	Pointer to client allocated memory for the control type
+*			structure storage. If this is NULL, powercap framework
+*			will allocate memory and own it.
+*			Advantage of this parameter is that client can embed
+*			this data in its data structures and allocate in a
+*			single call, preventing multiple allocations.
+* @control_type_name:	The Name of this control_type, which will be shown
+*			in the sysfs Interface.
+* @ops:			Callbacks for control type. This parameter is optional.
+*
+* Used to create a control_type with the power capping class. Here control_type
+* can represent a type of technology, which can control a range of power zones.
+* For example a control_type can be RAPL (Running Average Power Limit)
+* Intel® 64 and IA-32 Processor Architectures. The name can be any string
+* which must be unique, otherwise this function returns NULL.
+* A pointer to the control_type instance is returned on success.
+*/
+struct powercap_control_type *powercap_register_control_type(
+				struct powercap_control_type *control_type,
+				const char *name,
+				const struct powercap_control_type_ops *ops);
+
+/**
+* powercap_unregister_control_type() - Unregister a control_type from framework
+* @instance:	A pointer to the valid control_type instance.
+*
+* Used to unregister a control_type with the power capping class.
+* All power zones registered under this control type have to be unregistered
+* before calling this function, or it will fail with an error code.
+*/
+int powercap_unregister_control_type(struct powercap_control_type *instance);
+
+/* Zone register/unregister API */
+
+/**
+* powercap_register_zone() - Register a power zone
+* @power_zone:	Pointer to client allocated memory for the power zone structure
+*		storage. If this is NULL, powercap framework will allocate
+*		memory and own it. Advantage of this parameter is that client
+*		can embed this data in its data structures and allocate in a
+*		single call, preventing multiple allocations.
+* @control_type: A control_type instance under which this zone operates.
+* @name:	A name for this zone.
+* @parent:	A pointer to the parent power zone instance if any or NULL
+* @ops:		Pointer to zone operation callback structure.
+* @no_constraints: Number of constraints for this zone
+* @const_ops:	Pointer to constraint callback structure
+*
+* Register a power zone under a given control type. A power zone must register
+* a pointer to a structure representing zone callbacks.
+* A power zone can be located under a parent power zone, in which case @parent
+* should point to it.  Otherwise, if @parent is NULL, the new power zone will
+* be located directly under the given control type
+* For each power zone there may be a number of constraints that appear in the
+* sysfs under that zone as attributes with unique numeric IDs.
+* Returns pointer to the power_zone on success.
+*/
+struct powercap_zone *powercap_register_zone(
+			struct powercap_zone *power_zone,
+			struct powercap_control_type *control_type,
+			const char *name,
+			struct powercap_zone *parent,
+			const struct powercap_zone_ops *ops,
+			int nr_constraints,
+			struct powercap_zone_constraint_ops *const_ops);
+
+/**
+* powercap_unregister_zone() - Unregister a zone device
+* @control_type:	A pointer to the valid instance of a control_type.
+* @power_zone:	A pointer to the valid zone instance for a control_type
+*
+* Used to unregister a zone device for a control_type.  Caller should
+* make sure that children for this zone are unregistered first.
+*/
+int powercap_unregister_zone(struct powercap_control_type *control_type,
+				struct powercap_zone *power_zone);
+
+#endif
-- 
cgit 


From bfd1ff6375c82930bfb3b401eee2c96720fa8e84 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 11 Oct 2013 16:54:59 -0700
Subject: bitops: Introduce BIT_ULL

Adding BIT(x) equivalent for unsigned long long type, BIT_ULL(x). Also
added BIT_ULL_MASK and BIT_ULL_WORD.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/bitops.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3b6b82108b9..5a1c8b71ccd8 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -4,8 +4,11 @@
 
 #ifdef	__KERNEL__
 #define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
-- 
cgit 


From a314d7003ccd4f4886d1280ff4f6c00217fc9ae3 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 16 Oct 2013 09:12:54 +0200
Subject: tcm_loop: separate out tcm_loop_issue_tmr

No functional change.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/loopback/tcm_loop.c | 83 +++++++++++++++++++++++---------------
 include/target/target_core_base.h  |  1 +
 2 files changed, 51 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index a00ad27940b7..783675f7cdab 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -245,41 +245,21 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
  * Called from SCSI EH process context to issue a LUN_RESET TMR
  * to struct scsi_device
  */
-static int tcm_loop_device_reset(struct scsi_cmnd *sc)
+static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
+			      struct tcm_loop_nexus *tl_nexus,
+			      int lun, enum tcm_tmreq_table tmr)
 {
 	struct se_cmd *se_cmd = NULL;
-	struct se_portal_group *se_tpg;
 	struct se_session *se_sess;
+	struct se_portal_group *se_tpg;
 	struct tcm_loop_cmd *tl_cmd = NULL;
-	struct tcm_loop_hba *tl_hba;
-	struct tcm_loop_nexus *tl_nexus;
 	struct tcm_loop_tmr *tl_tmr = NULL;
-	struct tcm_loop_tpg *tl_tpg;
-	int ret = FAILED, rc;
-	/*
-	 * Locate the tcm_loop_hba_t pointer
-	 */
-	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
-	/*
-	 * Locate the tl_nexus and se_sess pointers
-	 */
-	tl_nexus = tl_hba->tl_nexus;
-	if (!tl_nexus) {
-		pr_err("Unable to perform device reset without"
-				" active I_T Nexus\n");
-		return FAILED;
-	}
-	se_sess = tl_nexus->se_sess;
-	/*
-	 * Locate the tl_tpg and se_tpg pointers from TargetID in sc->device->id
-	 */
-	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
-	se_tpg = &tl_tpg->tl_se_tpg;
+	int ret = TMR_FUNCTION_FAILED, rc;
 
 	tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL);
 	if (!tl_cmd) {
 		pr_err("Unable to allocate memory for tl_cmd\n");
-		return FAILED;
+		return ret;
 	}
 
 	tl_tmr = kzalloc(sizeof(struct tcm_loop_tmr), GFP_KERNEL);
@@ -290,6 +270,8 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 	init_waitqueue_head(&tl_tmr->tl_tmr_wait);
 
 	se_cmd = &tl_cmd->tl_se_cmd;
+	se_tpg = &tl_tpg->tl_se_tpg;
+	se_sess = tl_nexus->se_sess;
 	/*
 	 * Initialize struct se_cmd descriptor from target_core_mod infrastructure
 	 */
@@ -297,17 +279,20 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 				DMA_NONE, MSG_SIMPLE_TAG,
 				&tl_cmd->tl_sense_buf[0]);
 
-	rc = core_tmr_alloc_req(se_cmd, tl_tmr, TMR_LUN_RESET, GFP_KERNEL);
+	rc = core_tmr_alloc_req(se_cmd, tl_tmr, tmr, GFP_KERNEL);
 	if (rc < 0)
 		goto release;
+
 	/*
-	 * Locate the underlying TCM struct se_lun from sc->device->lun
+	 * Locate the underlying TCM struct se_lun
 	 */
-	if (transport_lookup_tmr_lun(se_cmd, sc->device->lun) < 0)
+	if (transport_lookup_tmr_lun(se_cmd, lun) < 0) {
+		ret = TMR_LUN_DOES_NOT_EXIST;
 		goto release;
+	}
 	/*
-	 * Queue the TMR to TCM Core and sleep waiting for tcm_loop_queue_tm_rsp()
-	 * to wake us up.
+	 * Queue the TMR to TCM Core and sleep waiting for
+	 * tcm_loop_queue_tm_rsp() to wake us up.
 	 */
 	transport_generic_handle_tmr(se_cmd);
 	wait_event(tl_tmr->tl_tmr_wait, atomic_read(&tl_tmr->tmr_complete));
@@ -315,8 +300,7 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 	 * The TMR LUN_RESET has completed, check the response status and
 	 * then release allocations.
 	 */
-	ret = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ?
-		SUCCESS : FAILED;
+	ret = se_cmd->se_tmr_req->response;
 release:
 	if (se_cmd)
 		transport_generic_free_cmd(se_cmd, 1);
@@ -326,6 +310,39 @@ release:
 	return ret;
 }
 
+/*
+ * Called from SCSI EH process context to issue a LUN_RESET TMR
+ * to struct scsi_device
+ */
+static int tcm_loop_device_reset(struct scsi_cmnd *sc)
+{
+	struct tcm_loop_hba *tl_hba;
+	struct tcm_loop_nexus *tl_nexus;
+	struct tcm_loop_tpg *tl_tpg;
+	int ret = FAILED;
+
+	/*
+	 * Locate the tcm_loop_hba_t pointer
+	 */
+	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+	/*
+	 * Locate the tl_nexus and se_sess pointers
+	 */
+	tl_nexus = tl_hba->tl_nexus;
+	if (!tl_nexus) {
+		pr_err("Unable to perform device reset without"
+				" active I_T Nexus\n");
+		return FAILED;
+	}
+	/*
+	 * Locate the tl_tpg pointer from TargetID in sc->device->id
+	 */
+	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
+	ret = tcm_loop_issue_tmr(tl_tpg, tl_nexus,
+				 sc->device->lun, TMR_LUN_RESET);
+	return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
+}
+
 static int tcm_loop_slave_alloc(struct scsi_device *sd)
 {
 	set_bit(QUEUE_FLAG_BIDI, &sd->request_queue->queue_flags);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5bdb8b7d2a69..22e752c4406d 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -227,6 +227,7 @@ enum tcm_tmreq_table {
 
 /* fabric independent task management response values */
 enum tcm_tmrsp_table {
+	TMR_FUNCTION_FAILED		= 0,
 	TMR_FUNCTION_COMPLETE		= 1,
 	TMR_TASK_DOES_NOT_EXIST		= 2,
 	TMR_LUN_DOES_NOT_EXIST		= 3,
-- 
cgit 


From 0b90d0622ad290b3717a13489b396af52aea9d2d Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Mon, 14 Oct 2013 18:11:51 +1030
Subject: virtio_config: introduce size-based accessors.

This lets the us do endian conversion if necessary, and insulates the
drivers from that change.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/virtio_config.h | 134 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 134 insertions(+)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 29b9104232b4..490a4bbd59a3 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -162,5 +162,139 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
 	return 0;
 }
 
+/* Config space accessors. */
+#define virtio_cread(vdev, structname, member, ptr)			\
+	do {								\
+		/* Must match the member's type, and be integer */	\
+		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
+			(*ptr) = 1;					\
+									\
+		switch (sizeof(*ptr)) {					\
+		case 1:							\
+			*(ptr) = virtio_cread8(vdev,			\
+					       offsetof(structname, member)); \
+			break;						\
+		case 2:							\
+			*(ptr) = virtio_cread16(vdev,			\
+						offsetof(structname, member)); \
+			break;						\
+		case 4:							\
+			*(ptr) = virtio_cread32(vdev,			\
+						offsetof(structname, member)); \
+			break;						\
+		case 8:							\
+			*(ptr) = virtio_cread64(vdev,			\
+						offsetof(structname, member)); \
+			break;						\
+		default:						\
+			BUG();						\
+		}							\
+	} while(0)
+
+/* Config space accessors. */
+#define virtio_cwrite(vdev, structname, member, ptr)			\
+	do {								\
+		/* Must match the member's type, and be integer */	\
+		if (!typecheck(typeof((((structname*)0)->member)), *(ptr))) \
+			BUG_ON((*ptr) == 1);				\
+									\
+		switch (sizeof(*ptr)) {					\
+		case 1:							\
+			virtio_cwrite8(vdev,				\
+				       offsetof(structname, member),	\
+				       *(ptr));				\
+			break;						\
+		case 2:							\
+			virtio_cwrite16(vdev,				\
+					offsetof(structname, member),	\
+					*(ptr));			\
+			break;						\
+		case 4:							\
+			virtio_cwrite32(vdev,				\
+					offsetof(structname, member),	\
+					*(ptr));			\
+			break;						\
+		case 8:							\
+			virtio_cwrite64(vdev,				\
+					offsetof(structname, member),	\
+					*(ptr));			\
+			break;						\
+		default:						\
+			BUG();						\
+		}							\
+	} while(0)
+
+static inline u8 virtio_cread8(struct virtio_device *vdev, unsigned int offset)
+{
+	u8 ret;
+	vdev->config->get(vdev, offset, &ret, sizeof(ret));
+	return ret;
+}
+
+static inline void virtio_cread_bytes(struct virtio_device *vdev,
+				      unsigned int offset,
+				      void *buf, size_t len)
+{
+	vdev->config->get(vdev, offset, buf, len);
+}
+
+static inline void virtio_cwrite8(struct virtio_device *vdev,
+				  unsigned int offset, u8 val)
+{
+	vdev->config->set(vdev, offset, &val, sizeof(val));
+}
+
+static inline u16 virtio_cread16(struct virtio_device *vdev,
+				 unsigned int offset)
+{
+	u16 ret;
+	vdev->config->get(vdev, offset, &ret, sizeof(ret));
+	return ret;
+}
+
+static inline void virtio_cwrite16(struct virtio_device *vdev,
+				   unsigned int offset, u16 val)
+{
+	vdev->config->set(vdev, offset, &val, sizeof(val));
+}
+
+static inline u32 virtio_cread32(struct virtio_device *vdev,
+				 unsigned int offset)
+{
+	u32 ret;
+	vdev->config->get(vdev, offset, &ret, sizeof(ret));
+	return ret;
+}
+
+static inline void virtio_cwrite32(struct virtio_device *vdev,
+				   unsigned int offset, u32 val)
+{
+	vdev->config->set(vdev, offset, &val, sizeof(val));
+}
+
+static inline u64 virtio_cread64(struct virtio_device *vdev,
+				 unsigned int offset)
+{
+	u64 ret;
+	vdev->config->get(vdev, offset, &ret, sizeof(ret));
+	return ret;
+}
+
+static inline void virtio_cwrite64(struct virtio_device *vdev,
+				   unsigned int offset, u64 val)
+{
+	vdev->config->set(vdev, offset, &val, sizeof(val));
+}
+
+/* Conditional config space accessors. */
+#define virtio_cread_feature(vdev, fbit, structname, member, ptr)	\
+	({								\
+		int _r = 0;						\
+		if (!virtio_has_feature(vdev, fbit))			\
+			_r = -ENOENT;					\
+		else							\
+			virtio_cread((vdev), structname, member, ptr);	\
+		_r;							\
+	})
 
 #endif /* _LINUX_VIRTIO_CONFIG_H */
-- 
cgit 


From 630b54d33493d1f67e79b148b5e361c5bbd3f29d Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Mon, 14 Oct 2013 18:11:51 +1030
Subject: virtio_config: remove virtio_config_val

The virtio_cread() functions should now be used.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/virtio_config.h | 27 ---------------------------
 1 file changed, 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 490a4bbd59a3..e8f8f71e843c 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -96,33 +96,6 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 	return test_bit(fbit, vdev->features);
 }
 
-/**
- * virtio_config_val - look for a feature and get a virtio config entry.
- * @vdev: the virtio device
- * @fbit: the feature bit
- * @offset: the type to search for.
- * @v: a pointer to the value to fill in.
- *
- * The return value is -ENOENT if the feature doesn't exist.  Otherwise
- * the config value is copied into whatever is pointed to by v. */
-#define virtio_config_val(vdev, fbit, offset, v) \
-	virtio_config_buf((vdev), (fbit), (offset), (v), sizeof(*v))
-
-#define virtio_config_val_len(vdev, fbit, offset, v, len) \
-	virtio_config_buf((vdev), (fbit), (offset), (v), (len))
-
-static inline int virtio_config_buf(struct virtio_device *vdev,
-				    unsigned int fbit,
-				    unsigned int offset,
-				    void *buf, unsigned len)
-{
-	if (!virtio_has_feature(vdev, fbit))
-		return -ENOENT;
-
-	vdev->config->get(vdev, offset, buf, len);
-	return 0;
-}
-
 static inline
 struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 					vq_callback_t *c, const char *n)
-- 
cgit 


From 64c862a839a8db2c02bbaa88b923d13e1208919d Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 11 Oct 2013 13:11:38 -0700
Subject: devres: add kernel standard devm_k.alloc functions

Currently, devm_ managed memory only supports kzalloc.

Convert the devm_kzalloc implementation to devm_kmalloc and remove the
complete memset to 0 but still set the initial struct devres header and
whatever padding before data to 0.

Add the other normal alloc variants as static inlines with __GFP_ZERO
added to the gfp flag where appropriate:

	devm_kzalloc
	devm_kcalloc
	devm_kmalloc_array

Add gfp.h to device.h for the newly added static inlines.

akpm: the current API forces us to replace kmalloc() with kzalloc() when
performing devm_ conversions.  This adds a relatively minor overhead.
More significantly, it will defeat kmemcheck used-uninitialized checking,
and for a particular driver, losing used-uninitialised checking for their
core controlling data structures will significantly degrade kmemcheck
usefulness.

Signed-off-by: Joe Perches <joe@perches.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Sangjung Woo <sangjung.woo@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devres.c  | 27 ++++++++++++++++-----------
 include/linux/device.h | 21 +++++++++++++++++++--
 2 files changed, 35 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 507379e7b763..37e67a26e388 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -91,7 +91,8 @@ static __always_inline struct devres * alloc_dr(dr_release_t release,
 	if (unlikely(!dr))
 		return NULL;
 
-	memset(dr, 0, tot_size);
+	memset(dr, 0, offsetof(struct devres, data));
+
 	INIT_LIST_HEAD(&dr->node.entry);
 	dr->node.release = release;
 	return dr;
@@ -745,58 +746,62 @@ void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
 EXPORT_SYMBOL_GPL(devm_remove_action);
 
 /*
- * Managed kzalloc/kfree
+ * Managed kmalloc/kfree
  */
-static void devm_kzalloc_release(struct device *dev, void *res)
+static void devm_kmalloc_release(struct device *dev, void *res)
 {
 	/* noop */
 }
 
-static int devm_kzalloc_match(struct device *dev, void *res, void *data)
+static int devm_kmalloc_match(struct device *dev, void *res, void *data)
 {
 	return res == data;
 }
 
 /**
- * devm_kzalloc - Resource-managed kzalloc
+ * devm_kmalloc - Resource-managed kmalloc
  * @dev: Device to allocate memory for
  * @size: Allocation size
  * @gfp: Allocation gfp flags
  *
- * Managed kzalloc.  Memory allocated with this function is
+ * Managed kmalloc.  Memory allocated with this function is
  * automatically freed on driver detach.  Like all other devres
  * resources, guaranteed alignment is unsigned long long.
  *
  * RETURNS:
  * Pointer to allocated memory on success, NULL on failure.
  */
-void * devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 {
 	struct devres *dr;
 
 	/* use raw alloc_dr for kmalloc caller tracing */
-	dr = alloc_dr(devm_kzalloc_release, size, gfp);
+	dr = alloc_dr(devm_kmalloc_release, size, gfp);
 	if (unlikely(!dr))
 		return NULL;
 
+	/*
+	 * This is named devm_kzalloc_release for historical reasons
+	 * The initial implementation did not support kmalloc, only kzalloc
+	 */
 	set_node_dbginfo(&dr->node, "devm_kzalloc_release", size);
 	devres_add(dev, dr->data);
 	return dr->data;
 }
-EXPORT_SYMBOL_GPL(devm_kzalloc);
+EXPORT_SYMBOL_GPL(devm_kmalloc);
 
 /**
  * devm_kfree - Resource-managed kfree
  * @dev: Device this memory belongs to
  * @p: Memory to free
  *
- * Free memory allocated with devm_kzalloc().
+ * Free memory allocated with devm_kmalloc().
  */
 void devm_kfree(struct device *dev, void *p)
 {
 	int rc;
 
-	rc = devres_destroy(dev, devm_kzalloc_release, devm_kzalloc_match, p);
+	rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, p);
 	WARN_ON(rc);
 }
 EXPORT_SYMBOL_GPL(devm_kfree);
diff --git a/include/linux/device.h b/include/linux/device.h
index 94638efa0bf8..5e44cff5bced 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -26,6 +26,7 @@
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
 #include <linux/uidgid.h>
+#include <linux/gfp.h>
 #include <asm/device.h>
 
 struct device;
@@ -606,8 +607,24 @@ extern void devres_close_group(struct device *dev, void *id);
 extern void devres_remove_group(struct device *dev, void *id);
 extern int devres_release_group(struct device *dev, void *id);
 
-/* managed kzalloc/kfree for device drivers, no kmalloc, always use kzalloc */
-extern void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp);
+/* managed devm_k.alloc/kfree for device drivers */
+extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
+static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+{
+	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+static inline void *devm_kmalloc_array(struct device *dev,
+				       size_t n, size_t size, gfp_t flags)
+{
+	if (size != 0 && n > SIZE_MAX / size)
+		return NULL;
+	return devm_kmalloc(dev, n * size, flags);
+}
+static inline void *devm_kcalloc(struct device *dev,
+				 size_t n, size_t size, gfp_t flags)
+{
+	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
 extern void devm_kfree(struct device *dev, void *p);
 
 void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res);
-- 
cgit 


From fb3fed7926545e44ce36574e1b1c5cdeb018db5c Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 7 Oct 2013 18:27:35 -0700
Subject: ide: convert bus code to use dev_groups

The dev_attrs field of struct bus_type is going away soon, dev_groups
should be used instead.  This converts the ide bus code to use the
correct field.

Acked-by: David S. Miller <davem@davemloft.net>
Cc: <linux-ide@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/ide/ide-sysfs.c | 35 ++++++++++++++++++++++++++---------
 drivers/ide/ide.c       |  2 +-
 include/linux/ide.h     |  2 +-
 3 files changed, 28 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-sysfs.c b/drivers/ide/ide-sysfs.c
index 883ffacaf45a..84a6a9e08d64 100644
--- a/drivers/ide/ide-sysfs.c
+++ b/drivers/ide/ide-sysfs.c
@@ -25,6 +25,7 @@ static ssize_t media_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "%s\n", ide_media_string(drive));
 }
+static DEVICE_ATTR_RO(media);
 
 static ssize_t drivename_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
@@ -32,6 +33,7 @@ static ssize_t drivename_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "%s\n", drive->name);
 }
+static DEVICE_ATTR_RO(drivename);
 
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
@@ -39,6 +41,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "ide:m-%s\n", ide_media_string(drive));
 }
+static DEVICE_ATTR_RO(modalias);
 
 static ssize_t model_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -46,6 +49,7 @@ static ssize_t model_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "%s\n", (char *)&drive->id[ATA_ID_PROD]);
 }
+static DEVICE_ATTR_RO(model);
 
 static ssize_t firmware_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
@@ -53,6 +57,7 @@ static ssize_t firmware_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "%s\n", (char *)&drive->id[ATA_ID_FW_REV]);
 }
+static DEVICE_ATTR_RO(firmware);
 
 static ssize_t serial_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
@@ -60,16 +65,28 @@ static ssize_t serial_show(struct device *dev, struct device_attribute *attr,
 	ide_drive_t *drive = to_ide_device(dev);
 	return sprintf(buf, "%s\n", (char *)&drive->id[ATA_ID_SERNO]);
 }
+static DEVICE_ATTR(serial, 0400, serial_show, NULL);
+
+static DEVICE_ATTR(unload_heads, 0644, ide_park_show, ide_park_store);
+
+static struct attribute *ide_attrs[] = {
+	&dev_attr_media.attr,
+	&dev_attr_drivename.attr,
+	&dev_attr_modalias.attr,
+	&dev_attr_model.attr,
+	&dev_attr_firmware.attr,
+	&dev_attr_serial.attr,
+	&dev_attr_unload_heads.attr,
+	NULL,
+};
+
+static const struct attribute_group ide_attr_group = {
+	.attrs = ide_attrs,
+};
 
-struct device_attribute ide_dev_attrs[] = {
-	__ATTR_RO(media),
-	__ATTR_RO(drivename),
-	__ATTR_RO(modalias),
-	__ATTR_RO(model),
-	__ATTR_RO(firmware),
-	__ATTR(serial, 0400, serial_show, NULL),
-	__ATTR(unload_heads, 0644, ide_park_show, ide_park_store),
-	__ATTR_NULL
+const struct attribute_group *ide_dev_groups[] = {
+	&ide_attr_group,
+	NULL,
 };
 
 static ssize_t store_delete_devices(struct device *portdev,
diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c
index fa896210ed7b..2ce6268a2734 100644
--- a/drivers/ide/ide.c
+++ b/drivers/ide/ide.c
@@ -158,7 +158,7 @@ struct bus_type ide_bus_type = {
 	.probe		= generic_ide_probe,
 	.remove		= generic_ide_remove,
 	.shutdown	= generic_ide_shutdown,
-	.dev_attrs	= ide_dev_attrs,
+	.dev_groups	= ide_dev_groups,
 	.suspend	= generic_ide_suspend,
 	.resume		= generic_ide_resume,
 };
diff --git a/include/linux/ide.h b/include/linux/ide.h
index b17974917dbf..46a14229a162 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1514,7 +1514,7 @@ static inline void ide_set_max_pio(ide_drive_t *drive)
 
 char *ide_media_string(ide_drive_t *);
 
-extern struct device_attribute ide_dev_attrs[];
+extern const struct attribute_group *ide_dev_groups[];
 extern struct bus_type ide_bus_type;
 extern struct class *ide_port_class;
 
-- 
cgit 


From eb3057df732c304622aee77c450761746939a2dc Mon Sep 17 00:00:00 2001
From: Frantisek Hrbata <fhrbata@redhat.com>
Date: Mon, 14 Oct 2013 18:08:46 +1030
Subject: kernel: add support for init_array constructors

This adds the .init_array section as yet another section with constructors. This
is needed because gcc could add __gcov_init calls to .init_array or .ctors
section, depending on gcc (and binutils) version .

v2: - reuse mod->ctors for .init_array section for modules, because gcc uses
      .ctors or .init_array, but not both at the same time
v3: - fail to load if that does happen somehow.

Signed-off-by: Frantisek Hrbata <fhrbata@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/asm-generic/vmlinux.lds.h |  1 +
 kernel/module.c                   | 20 ++++++++++++++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 83e2c31e8b00..bc2121fa9132 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -473,6 +473,7 @@
 #define KERNEL_CTORS()	. = ALIGN(8);			   \
 			VMLINUX_SYMBOL(__ctors_start) = .; \
 			*(.ctors)			   \
+			*(.init_array)			   \
 			VMLINUX_SYMBOL(__ctors_end) = .;
 #else
 #define KERNEL_CTORS()
diff --git a/kernel/module.c b/kernel/module.c
index 947105fd4cab..5c9cf84017d5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2708,7 +2708,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
 	return 0;
 }
 
-static void find_module_sections(struct module *mod, struct load_info *info)
+static int find_module_sections(struct module *mod, struct load_info *info)
 {
 	mod->kp = section_objs(info, "__param",
 			       sizeof(*mod->kp), &mod->num_kp);
@@ -2738,6 +2738,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 #ifdef CONFIG_CONSTRUCTORS
 	mod->ctors = section_objs(info, ".ctors",
 				  sizeof(*mod->ctors), &mod->num_ctors);
+	if (!mod->ctors)
+		mod->ctors = section_objs(info, ".init_array",
+				sizeof(*mod->ctors), &mod->num_ctors);
+	else if (find_sec(info, ".init_array")) {
+		/*
+		 * This shouldn't happen with same compiler and binutils
+		 * building all parts of the module.
+		 */
+		printk(KERN_WARNING "%s: has both .ctors and .init_array.\n",
+		       mod->name);
+		return -EINVAL;
+	}
 #endif
 
 #ifdef CONFIG_TRACEPOINTS
@@ -2776,6 +2788,8 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 
 	info->debug = section_objs(info, "__verbose",
 				   sizeof(*info->debug), &info->num_debug);
+
+	return 0;
 }
 
 static int move_module(struct module *mod, struct load_info *info)
@@ -3233,7 +3247,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	/* Now we've got everything in the final locations, we can
 	 * find optional sections. */
-	find_module_sections(mod, info);
+	err = find_module_sections(mod, info);
+	if (err)
+		goto free_unload;
 
 	err = check_module_license_and_versions(mod);
 	if (err)
-- 
cgit 


From b594a75ecae0c7800265988dba90ce2ae5c418d2 Mon Sep 17 00:00:00 2001
From: Frank Schaefer <fschaefer.oss@googlemail.com>
Date: Thu, 10 Oct 2013 14:21:32 -0300
Subject: [media] v4l2-ctrls: fix typo in header file media/v4l2-ctrls.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Frank Schäfer <fschaefer.oss@googlemail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-ctrls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index 47ada23345a1..16f7f2606516 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -571,7 +571,7 @@ static inline void v4l2_ctrl_lock(struct v4l2_ctrl *ctrl)
 	mutex_lock(ctrl->handler->lock);
 }
 
-/** v4l2_ctrl_lock() - Helper function to unlock the handler
+/** v4l2_ctrl_unlock() - Helper function to unlock the handler
   * associated with the control.
   * @ctrl:	The control to unlock.
   */
-- 
cgit 


From 4eed9b337604307d1d31902212f2e8e42a864c51 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
Date: Mon, 14 Oct 2013 20:08:03 -0300
Subject: [media] v4l2-ctrls: Correct v4l2_ctrl_get_int_menu() function's
 return type

Remove the redundant 'const' qualifiers from the function
signature and from the qmenu_int arrays' declarations.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/v4l2-core/v4l2-ctrls.c | 6 +++---
 include/media/v4l2-common.h          | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index df3a67b40f00..60dcc0f3b32e 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -565,13 +565,13 @@ EXPORT_SYMBOL(v4l2_ctrl_get_menu);
  * Returns NULL or an s64 type array containing the menu for given
  * control ID. The total number of the menu items is returned in @len.
  */
-const s64 const *v4l2_ctrl_get_int_menu(u32 id, u32 *len)
+const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len)
 {
-	static const s64 const qmenu_int_vpx_num_partitions[] = {
+	static const s64 qmenu_int_vpx_num_partitions[] = {
 		1, 2, 4, 8,
 	};
 
-	static const s64 const qmenu_int_vpx_num_ref_frames[] = {
+	static const s64 qmenu_int_vpx_num_ref_frames[] = {
 		1, 2, 3,
 	};
 
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 16550c439008..b87692c0b042 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -86,7 +86,7 @@ int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl,
 		const char * const *menu_items);
 const char *v4l2_ctrl_get_name(u32 id);
 const char * const *v4l2_ctrl_get_menu(u32 id);
-const s64 const *v4l2_ctrl_get_int_menu(u32 id, u32 *len);
+const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len);
 int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def);
 int v4l2_ctrl_query_menu(struct v4l2_querymenu *qmenu,
 		struct v4l2_queryctrl *qctrl, const char * const *menu_items);
-- 
cgit 


From 4f1af2a33c9c5fbd2bf31a1679378860aca79f9e Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Thu, 3 Oct 2013 18:55:52 -0300
Subject: [media] v4l2-fh: Include linux/fs.h for struct file definition

v4l2-fh.h dereferences struct file, the structure must thus be defined.
Pull in its definition by including linux/fs.h.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-fh.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h
index a62ee18cb7b7..0d922080667f 100644
--- a/include/media/v4l2-fh.h
+++ b/include/media/v4l2-fh.h
@@ -26,6 +26,7 @@
 #ifndef V4L2_FH_H
 #define V4L2_FH_H
 
+#include <linux/fs.h>
 #include <linux/list.h>
 
 struct video_device;
-- 
cgit 


From c8d185ce33ecd560275f76c590fda4cdba824bd9 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Thu, 3 Oct 2013 18:59:30 -0300
Subject: [media] v4l2-fh: Include linux/videodev2.h for enum v4l2_priority
 definition

struct v4l2_fh has an enum v4l2_priority field. Make sure the enum
definition is available by including linux/videodev2.h.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-fh.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h
index 0d922080667f..528cdaf622e1 100644
--- a/include/media/v4l2-fh.h
+++ b/include/media/v4l2-fh.h
@@ -28,6 +28,7 @@
 
 #include <linux/fs.h>
 #include <linux/list.h>
+#include <linux/videodev2.h>
 
 struct video_device;
 struct v4l2_ctrl_handler;
-- 
cgit 


From 420f9739a62cdb027f5580d25c813501ff93aa6f Mon Sep 17 00:00:00 2001
From: David Henningsson <david.henningsson@canonical.com>
Date: Wed, 16 Oct 2013 23:10:31 +0200
Subject: thinkpad-acpi: Add mute and mic-mute LED functionality

The LEDs are currently not visible to userspace, for security
reasons. They are exported through thinkpad_acpi.h for use by the
snd-hda-intel driver.

Thanks to Alex Hung <alex.hung@canonical.com> and Takashi Iwai
<tiwai@suse.de> for writing parts of this patch.

Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Acked-by: Henrique de Moraes Holschuh <hmh@hmh.eng.br>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/laptops/thinkpad-acpi.txt |  7 ++-
 drivers/platform/x86/thinkpad_acpi.c    | 92 ++++++++++++++++++++++++++++++++-
 include/linux/thinkpad_acpi.h           | 15 ++++++
 3 files changed, 111 insertions(+), 3 deletions(-)
 create mode 100644 include/linux/thinkpad_acpi.h

(limited to 'include')

diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 86c52360ffe7..fc04c14de4bb 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -1,7 +1,7 @@
 		     ThinkPad ACPI Extras Driver
 
-                            Version 0.24
-                        December 11th,  2009
+                            Version 0.25
+                        October 16th,  2013
 
                Borislav Deianov <borislav@users.sf.net>
              Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -741,6 +741,9 @@ compiled with the CONFIG_THINKPAD_ACPI_UNSAFE_LEDS option enabled.
 Distributions must never enable this option.  Individual users that
 are aware of the consequences are welcome to enabling it.
 
+Audio mute and microphone mute LEDs are supported, but currently not
+visible to userspace. They are used by the snd-hda-intel audio driver.
+
 procfs notes:
 
 The available commands are:
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 03ca6c139f1a..0b7efb269cf1 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -23,7 +23,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#define TPACPI_VERSION "0.24"
+#define TPACPI_VERSION "0.25"
 #define TPACPI_SYSFS_VERSION 0x020700
 
 /*
@@ -88,6 +88,7 @@
 
 #include <linux/pci_ids.h>
 
+#include <linux/thinkpad_acpi.h>
 
 /* ThinkPad CMOS commands */
 #define TP_CMOS_VOLUME_DOWN	0
@@ -8350,6 +8351,91 @@ static struct ibm_struct fan_driver_data = {
 	.resume = fan_resume,
 };
 
+/*************************************************************************
+ * Mute LED subdriver
+ */
+
+
+struct tp_led_table {
+	acpi_string name;
+	int on_value;
+	int off_value;
+	int state;
+};
+
+static struct tp_led_table led_tables[] = {
+	[TPACPI_LED_MUTE] = {
+		.name = "SSMS",
+		.on_value = 1,
+		.off_value = 0,
+	},
+	[TPACPI_LED_MICMUTE] = {
+		.name = "MMTS",
+		.on_value = 2,
+		.off_value = 0,
+	},
+};
+
+static int mute_led_on_off(struct tp_led_table *t, bool state)
+{
+	acpi_handle temp;
+	int output;
+
+	if (!ACPI_SUCCESS(acpi_get_handle(hkey_handle, t->name, &temp))) {
+		pr_warn("Thinkpad ACPI has no %s interface.\n", t->name);
+		return -EIO;
+	}
+
+	if (!acpi_evalf(hkey_handle, &output, t->name, "dd",
+			state ? t->on_value : t->off_value))
+		return -EIO;
+
+	t->state = state;
+	return state;
+}
+
+int tpacpi_led_set(int whichled, bool on)
+{
+	struct tp_led_table *t;
+
+	if (whichled < 0 || whichled >= TPACPI_LED_MAX)
+		return -EINVAL;
+
+	t = &led_tables[whichled];
+	if (t->state < 0 || t->state == on)
+		return t->state;
+	return mute_led_on_off(t, on);
+}
+EXPORT_SYMBOL_GPL(tpacpi_led_set);
+
+static int mute_led_init(struct ibm_init_struct *iibm)
+{
+	acpi_handle temp;
+	int i;
+
+	for (i = 0; i < TPACPI_LED_MAX; i++) {
+		struct tp_led_table *t = &led_tables[i];
+		if (ACPI_SUCCESS(acpi_get_handle(hkey_handle, t->name, &temp)))
+			mute_led_on_off(t, false);
+		else
+			t->state = -ENODEV;
+	}
+	return 0;
+}
+
+static void mute_led_exit(void)
+{
+	int i;
+
+	for (i = 0; i < TPACPI_LED_MAX; i++)
+		tpacpi_led_set(i, false);
+}
+
+static struct ibm_struct mute_led_driver_data = {
+	.name = "mute_led",
+	.exit = mute_led_exit,
+};
+
 /****************************************************************************
  ****************************************************************************
  *
@@ -8768,6 +8854,10 @@ static struct ibm_init_struct ibms_init[] __initdata = {
 		.init = fan_init,
 		.data = &fan_driver_data,
 	},
+	{
+		.init = mute_led_init,
+		.data = &mute_led_driver_data,
+	},
 };
 
 static int __init set_ibm_param(const char *val, struct kernel_param *kp)
diff --git a/include/linux/thinkpad_acpi.h b/include/linux/thinkpad_acpi.h
new file mode 100644
index 000000000000..361de59a2285
--- /dev/null
+++ b/include/linux/thinkpad_acpi.h
@@ -0,0 +1,15 @@
+#ifndef __THINKPAD_ACPI_H__
+#define __THINKPAD_ACPI_H__
+
+/* These two functions return 0 if success, or negative error code
+   (e g -ENODEV if no led present) */
+
+enum {
+	TPACPI_LED_MUTE,
+	TPACPI_LED_MICMUTE,
+	TPACPI_LED_MAX,
+};
+
+int tpacpi_led_set(int whichled, bool on);
+
+#endif
-- 
cgit 


From 5587027ce9d59a57aecaa190be1c8e560aaff45d Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:18:00 +0530
Subject: kvm: Add struct kvm arg to memslot APIs

We will use that in the later patch to find the kvm ops handler

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/arm/kvm/arm.c                 |  5 +++--
 arch/ia64/kvm/kvm-ia64.c           |  5 +++--
 arch/mips/kvm/kvm_mips.c           |  5 +++--
 arch/powerpc/include/asm/kvm_ppc.h |  6 ++++--
 arch/powerpc/kvm/book3s.c          |  4 ++--
 arch/powerpc/kvm/booke.c           |  4 ++--
 arch/powerpc/kvm/powerpc.c         |  9 +++++----
 arch/s390/kvm/kvm-s390.c           |  5 +++--
 arch/x86/kvm/x86.c                 |  5 +++--
 include/linux/kvm_host.h           |  5 +++--
 virt/kvm/kvm_main.c                | 12 ++++++------
 11 files changed, 37 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index cc5adb9349ef..e312e4a53f8d 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -152,12 +152,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index bdfd8789b376..985bf80c622e 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1550,12 +1550,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index a7b044536de4..73b34827826c 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -198,12 +198,13 @@ kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	return -ENOIOCTLCMD;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c13f15db476c..20f461637090 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -134,9 +134,11 @@ extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
 extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
-extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+extern void kvmppc_core_free_memslot(struct kvm *kvm,
+				     struct kvm_memory_slot *free,
 				     struct kvm_memory_slot *dont);
-extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+extern int kvmppc_core_create_memslot(struct kvm *kvm,
+				      struct kvm_memory_slot *slot,
 				      unsigned long npages);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 39d2994f9d27..130fe1d75bac 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -761,13 +761,13 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return kvmppc_ops->get_dirty_log(kvm, log);
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
 	kvmppc_ops->free_memslot(free, dont);
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
 	return kvmppc_ops->create_memslot(slot, npages);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1769354d0bf8..cb2d986a3382 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1662,12 +1662,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
 }
 
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
 	return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9aaa07efa4b6..b103d747934a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -417,15 +417,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
-	kvmppc_core_free_memslot(free, dont);
+	kvmppc_core_free_memslot(kvm, free, dont);
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
-	return kvmppc_core_create_memslot(slot, npages);
+	return kvmppc_core_create_memslot(kvm, slot, npages);
 }
 
 void kvm_arch_memslots_updated(struct kvm *kvm)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1e4e7b97337a..bedda67cc222 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1089,12 +1089,13 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edf2a07df3a3..666526a55c46 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7080,7 +7080,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 	int i;
@@ -7101,7 +7101,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	int i;
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c9d4236ab442..8b0107dc2067 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -507,9 +507,10 @@ int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont);
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages);
 void kvm_arch_memslots_updated(struct kvm *kvm);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 94c6e3f6f244..0932c3b64155 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -542,13 +542,13 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /*
  * Free any memory in @free but not in @dont.
  */
-static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
+static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
-	kvm_arch_free_memslot(free, dont);
+	kvm_arch_free_memslot(kvm, free, dont);
 
 	free->npages = 0;
 }
@@ -559,7 +559,7 @@ void kvm_free_physmem(struct kvm *kvm)
 	struct kvm_memory_slot *memslot;
 
 	kvm_for_each_memslot(memslot, slots)
-		kvm_free_physmem_slot(memslot, NULL);
+		kvm_free_physmem_slot(kvm, memslot, NULL);
 
 	kfree(kvm->memslots);
 }
@@ -823,7 +823,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (change == KVM_MR_CREATE) {
 		new.userspace_addr = mem->userspace_addr;
 
-		if (kvm_arch_create_memslot(&new, npages))
+		if (kvm_arch_create_memslot(kvm, &new, npages))
 			goto out_free;
 	}
 
@@ -899,7 +899,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
-	kvm_free_physmem_slot(&old, &new);
+	kvm_free_physmem_slot(kvm, &old, &new);
 	kfree(old_memslots);
 
 	return 0;
@@ -907,7 +907,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 out_slots:
 	kfree(slots);
 out_free:
-	kvm_free_physmem_slot(&new, &old);
+	kvm_free_physmem_slot(kvm, &new, &old);
 out:
 	return r;
 }
-- 
cgit 


From cbbc58d4fdfab1a39a6ac1b41fcb17885952157a Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 22:18:01 +0530
Subject: kvm: powerpc: book3s: Allow the HV and PR selection per virtual
 machine

This moves the kvmppc_ops callbacks to be a per VM entity. This
enables us to select HV and PR mode when creating a VM. We also
allow both kvm-hv and kvm-pr kernel module to be loaded. To
achieve this we move /dev/kvm ownership to kvm.ko module. Depending on
which KVM mode we select during VM creation we take a reference
count on respective module

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: fix coding style]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h |  1 +
 arch/powerpc/include/asm/kvm_ppc.h  |  7 +--
 arch/powerpc/kvm/44x.c              |  7 ++-
 arch/powerpc/kvm/book3s.c           | 89 +++++++++++++++++++++++++------------
 arch/powerpc/kvm/book3s.h           |  2 +
 arch/powerpc/kvm/book3s_hv.c        | 18 ++++----
 arch/powerpc/kvm/book3s_pr.c        | 25 +++++++----
 arch/powerpc/kvm/book3s_xics.c      |  2 +-
 arch/powerpc/kvm/booke.c            | 22 ++++-----
 arch/powerpc/kvm/e500.c             |  8 +++-
 arch/powerpc/kvm/e500mc.c           |  6 ++-
 arch/powerpc/kvm/emulate.c          | 11 ++---
 arch/powerpc/kvm/powerpc.c          | 76 ++++++++++++++++++++++---------
 include/uapi/linux/kvm.h            |  4 ++
 14 files changed, 187 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 61ce4dca45d3..237d1d25b448 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -270,6 +270,7 @@ struct kvm_arch {
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
 #endif
+	struct kvmppc_ops *kvm_ops;
 };
 
 /*
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 20f461637090..3069cf4dcc88 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -182,6 +182,7 @@ union kvmppc_one_reg {
 };
 
 struct kvmppc_ops {
+	struct module *owner;
 	bool is_hv_enabled;
 	int (*get_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 	int (*set_sregs)(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
@@ -217,7 +218,6 @@ struct kvmppc_ops {
 			      unsigned long npages);
 	int (*init_vm)(struct kvm *kvm);
 	void (*destroy_vm)(struct kvm *kvm);
-	int (*check_processor_compat)(void);
 	int (*get_smmu_info)(struct kvm *kvm, struct kvm_ppc_smmu_info *info);
 	int (*emulate_op)(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			  unsigned int inst, int *advance);
@@ -229,7 +229,8 @@ struct kvmppc_ops {
 
 };
 
-extern struct kvmppc_ops *kvmppc_ops;
+extern struct kvmppc_ops *kvmppc_hv_ops;
+extern struct kvmppc_ops *kvmppc_pr_ops;
 
 /*
  * Cuts out inst bits with ordering according to spec.
@@ -326,7 +327,7 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 
 static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->fast_vcpu_kick(vcpu);
+	vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu);
 }
 
 #else
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index a765bcd74fbb..93221e87b911 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -213,16 +213,19 @@ static int __init kvmppc_44x_init(void)
 	if (r)
 		goto err_out;
 
-	r = kvm_init(&kvm_ops_44x, sizeof(struct kvmppc_vcpu_44x),
-		     0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), 0, THIS_MODULE);
 	if (r)
 		goto err_out;
+	kvm_ops_44x.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_44x;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_44x_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 130fe1d75bac..ad8f6ed3f136 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 
+#include "book3s.h"
 #include "trace.h"
 
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@@ -71,7 +72,7 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
-	if (!kvmppc_ops->is_hv_enabled)
+	if (!vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return to_book3s(vcpu)->hior;
 	return 0;
 }
@@ -79,7 +80,7 @@ static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 			unsigned long pending_now, unsigned long old_pending)
 {
-	if (kvmppc_ops->is_hv_enabled)
+	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return;
 	if (pending_now)
 		vcpu->arch.shared->int_pending = 1;
@@ -93,7 +94,7 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 	ulong crit_r1;
 	bool crit;
 
-	if (kvmppc_ops->is_hv_enabled)
+	if (vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return false;
 
 	crit_raw = vcpu->arch.shared->critical;
@@ -477,13 +478,13 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	return kvmppc_ops->get_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
-	return kvmppc_ops->set_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
@@ -562,7 +563,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (size > sizeof(val))
 		return -EINVAL;
 
-	r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -641,7 +642,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
 		return -EFAULT;
 
-	r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 	if (r == -EINVAL) {
 		r = 0;
 		switch (reg->id) {
@@ -702,23 +703,23 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_ops->vcpu_load(vcpu, cpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_put(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
-	kvmppc_ops->set_msr(vcpu, msr);
+	vcpu->kvm->arch.kvm_ops->set_msr(vcpu, msr);
 }
 EXPORT_SYMBOL_GPL(kvmppc_set_msr);
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
-	return kvmppc_ops->vcpu_run(kvm_run, vcpu);
+	return vcpu->kvm->arch.kvm_ops->vcpu_run(kvm_run, vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
@@ -743,84 +744,84 @@ void kvmppc_decrementer_func(unsigned long data)
 
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	return kvmppc_ops->vcpu_create(kvm, id);
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_free(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
 }
 
 int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 {
-	return kvmppc_ops->check_requests(vcpu);
+	return vcpu->kvm->arch.kvm_ops->check_requests(vcpu);
 }
 
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	return kvmppc_ops->get_dirty_log(kvm, log);
+	return kvm->arch.kvm_ops->get_dirty_log(kvm, log);
 }
 
 void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			      struct kvm_memory_slot *dont)
 {
-	kvmppc_ops->free_memslot(free, dont);
+	kvm->arch.kvm_ops->free_memslot(free, dont);
 }
 
 int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       unsigned long npages)
 {
-	return kvmppc_ops->create_memslot(slot, npages);
+	return kvm->arch.kvm_ops->create_memslot(slot, npages);
 }
 
 void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
-	kvmppc_ops->flush_memslot(kvm, memslot);
+	kvm->arch.kvm_ops->flush_memslot(kvm, memslot);
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem)
 {
-	return kvmppc_ops->prepare_memory_region(kvm, memslot, mem);
+	return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old)
 {
-	kvmppc_ops->commit_memory_region(kvm, mem, old);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->unmap_hva(kvm, hva);
+	return kvm->arch.kvm_ops->unmap_hva(kvm, hva);
 }
 EXPORT_SYMBOL_GPL(kvm_unmap_hva);
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvmppc_ops->unmap_hva_range(kvm, start, end);
+	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->age_hva(kvm, hva);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvmppc_ops->test_age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->test_age_hva(kvm, hva);
 }
 
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-	kvmppc_ops->set_spte_hva(kvm, hva, pte);
+	kvm->arch.kvm_ops->set_spte_hva(kvm, hva, pte);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->mmu_destroy(vcpu);
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
@@ -831,12 +832,12 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
 #endif
 
-	return kvmppc_ops->init_vm(kvm);
+	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	kvmppc_ops->destroy_vm(kvm);
+	kvm->arch.kvm_ops->destroy_vm(kvm);
 
 #ifdef CONFIG_PPC64
 	kvmppc_rtas_tokens_free(kvm);
@@ -846,5 +847,35 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 
 int kvmppc_core_check_processor_compat(void)
 {
-	return kvmppc_ops->check_processor_compat();
+	/*
+	 * We always return 0 for book3s. We check
+	 * for compatability while loading the HV
+	 * or PR module
+	 */
+	return 0;
+}
+
+static int kvmppc_book3s_init(void)
+{
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (r)
+		return r;
+#ifdef CONFIG_KVM_BOOK3S_32
+	r = kvmppc_book3s_init_pr();
+#endif
+	return r;
+
+}
+
+static void kvmppc_book3s_exit(void)
+{
+#ifdef CONFIG_KVM_BOOK3S_32
+	kvmppc_book3s_exit_pr();
+#endif
+	kvm_exit();
 }
+
+module_init(kvmppc_book3s_init);
+module_exit(kvmppc_book3s_exit);
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 9e5b3a341943..4bf956cf94d6 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -28,5 +28,7 @@ extern int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu,
 					int sprn, ulong spr_val);
 extern int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu,
 					int sprn, ulong *spr_val);
+extern int kvmppc_book3s_init_pr(void);
+extern void kvmppc_book3s_exit_pr(void);
 
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9e954a81c078..8743048881b7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2159,7 +2159,7 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 	return r;
 }
 
-static struct kvmppc_ops kvmppc_hv_ops = {
+static struct kvmppc_ops kvm_ops_hv = {
 	.is_hv_enabled = true,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -2186,7 +2186,6 @@ static struct kvmppc_ops kvmppc_hv_ops = {
 	.create_memslot = kvmppc_core_create_memslot_hv,
 	.init_vm =  kvmppc_core_init_vm_hv,
 	.destroy_vm = kvmppc_core_destroy_vm_hv,
-	.check_processor_compat = kvmppc_core_check_processor_compat_hv,
 	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
 	.emulate_op = kvmppc_core_emulate_op_hv,
 	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
@@ -2198,20 +2197,23 @@ static struct kvmppc_ops kvmppc_hv_ops = {
 static int kvmppc_book3s_init_hv(void)
 {
 	int r;
-
-	r = kvm_init(&kvmppc_hv_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
-
-	if (r)
+	/*
+	 * FIXME!! Do we need to check on all cpus ?
+	 */
+	r = kvmppc_core_check_processor_compat_hv();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hv_init();
+	kvm_ops_hv.owner = THIS_MODULE;
+	kvmppc_hv_ops = &kvm_ops_hv;
 
+	r = kvmppc_mmu_hv_init();
 	return r;
 }
 
 static void kvmppc_book3s_exit_hv(void)
 {
-	kvm_exit();
+	kvmppc_hv_ops = NULL;
 }
 
 module_init(kvmppc_book3s_init_hv);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 7f583a482161..fbd985f0cb02 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1525,7 +1525,7 @@ static long kvm_arch_vm_ioctl_pr(struct file *filp,
 	return -ENOTTY;
 }
 
-static struct kvmppc_ops kvmppc_pr_ops = {
+static struct kvmppc_ops kvm_ops_pr = {
 	.is_hv_enabled = false,
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_pr,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_pr,
@@ -1552,7 +1552,6 @@ static struct kvmppc_ops kvmppc_pr_ops = {
 	.create_memslot = kvmppc_core_create_memslot_pr,
 	.init_vm = kvmppc_core_init_vm_pr,
 	.destroy_vm = kvmppc_core_destroy_vm_pr,
-	.check_processor_compat = kvmppc_core_check_processor_compat_pr,
 	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_pr,
 	.emulate_op = kvmppc_core_emulate_op_pr,
 	.emulate_mtspr = kvmppc_core_emulate_mtspr_pr,
@@ -1561,27 +1560,35 @@ static struct kvmppc_ops kvmppc_pr_ops = {
 	.arch_vm_ioctl  = kvm_arch_vm_ioctl_pr,
 };
 
-static int kvmppc_book3s_init_pr(void)
+
+int kvmppc_book3s_init_pr(void)
 {
 	int r;
 
-	r = kvm_init(&kvmppc_pr_ops, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
-
-	if (r)
+	r = kvmppc_core_check_processor_compat_pr();
+	if (r < 0)
 		return r;
 
-	r = kvmppc_mmu_hpte_sysinit();
+	kvm_ops_pr.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_pr;
 
+	r = kvmppc_mmu_hpte_sysinit();
 	return r;
 }
 
-static void kvmppc_book3s_exit_pr(void)
+void kvmppc_book3s_exit_pr(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_mmu_hpte_sysexit();
-	kvm_exit();
 }
 
+/*
+ * We only support separate modules for book3s 64
+ */
+#ifdef CONFIG_PPC_BOOK3S_64
+
 module_init(kvmppc_book3s_init_pr);
 module_exit(kvmppc_book3s_exit_pr);
 
 MODULE_LICENSE("GPL");
+#endif
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index c3c832b27ee5..f7a5108a3483 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -818,7 +818,7 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	}
 
 	/* Check for real mode returning too hard */
-	if (xics->real_mode && kvmppc_ops->is_hv_enabled)
+	if (xics->real_mode && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		return kvmppc_xics_rm_complete(vcpu, req);
 
 	switch (req) {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index cb2d986a3382..15d0149511eb 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1472,7 +1472,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 	get_sregs_base(vcpu, sregs);
 	get_sregs_arch206(vcpu, sregs);
-	return kvmppc_ops->get_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
@@ -1491,7 +1491,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (ret < 0)
 		return ret;
 
-	return kvmppc_ops->set_sregs(vcpu, sregs);
+	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
 int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
@@ -1548,7 +1548,7 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		val = get_reg_val(reg->id, vcpu->arch.vrsave);
 		break;
 	default:
-		r = kvmppc_ops->get_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1631,7 +1631,7 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 		vcpu->arch.vrsave = set_reg_val(reg->id, val);
 		break;
 	default:
-		r = kvmppc_ops->set_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
 		break;
 	}
 
@@ -1911,37 +1911,37 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->mmu_destroy(vcpu);
+	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
-	return kvmppc_ops->init_vm(kvm);
+	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	return kvmppc_ops->vcpu_create(kvm, id);
+	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_free(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-	kvmppc_ops->destroy_vm(kvm);
+	kvm->arch.kvm_ops->destroy_vm(kvm);
 }
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	kvmppc_ops->vcpu_load(vcpu, cpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_load(vcpu, cpu);
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvmppc_ops->vcpu_put(vcpu);
+	vcpu->kvm->arch.kvm_ops->vcpu_put(vcpu);
 }
 
 int __init kvmppc_booke_init(void)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index d225d5ebddcc..497b142f651c 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -555,13 +555,19 @@ static int __init kvmppc_e500_init(void)
 	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
 			   ivor[max_ivor] + handler_len);
 
-	r = kvm_init(&kvm_ops_e500, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	if (r)
+		goto err_out;
+	kvm_ops_e500.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_e500_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index db6a383401c7..4132cd2fc171 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -373,15 +373,19 @@ static int __init kvmppc_e500mc_init(void)
 	kvmppc_init_lpid(64);
 	kvmppc_claim_lpid(0); /* host */
 
-	r = kvm_init(&kvm_ops_e500mc, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 	if (r)
 		goto err_out;
+	kvm_ops_e500mc.owner = THIS_MODULE;
+	kvmppc_pr_ops = &kvm_ops_e500mc;
+
 err_out:
 	return r;
 }
 
 static void __exit kvmppc_e500mc_exit(void)
 {
+	kvmppc_pr_ops = NULL;
 	kvmppc_booke_exit();
 }
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index de9a340d22ed..2f9a0873b44f 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -130,8 +130,8 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_PIR: break;
 
 	default:
-		emulated = kvmppc_ops->emulate_mtspr(vcpu, sprn,
-						     spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mtspr(vcpu, sprn,
+								  spr_val);
 		if (emulated == EMULATE_FAIL)
 			printk(KERN_INFO "mtspr: unknown spr "
 				"0x%x\n", sprn);
@@ -191,8 +191,8 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		spr_val = kvmppc_get_dec(vcpu, get_tb());
 		break;
 	default:
-		emulated = kvmppc_ops->emulate_mfspr(vcpu, sprn,
-						     &spr_val);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_mfspr(vcpu, sprn,
+								  &spr_val);
 		if (unlikely(emulated == EMULATE_FAIL)) {
 			printk(KERN_INFO "mfspr: unknown spr "
 				"0x%x\n", sprn);
@@ -464,7 +464,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	if (emulated == EMULATE_FAIL) {
-		emulated = kvmppc_ops->emulate_op(run, vcpu, inst, &advance);
+		emulated = vcpu->kvm->arch.kvm_ops->emulate_op(run, vcpu, inst,
+							       &advance);
 		if (emulated == EMULATE_AGAIN) {
 			advance = 0;
 		} else if (emulated == EMULATE_FAIL) {
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b103d747934a..0320c1721caa 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/module.h>
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
@@ -39,7 +40,11 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-struct kvmppc_ops *kvmppc_ops;
+struct kvmppc_ops *kvmppc_hv_ops;
+EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
+struct kvmppc_ops *kvmppc_pr_ops;
+EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
+
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
@@ -195,7 +200,7 @@ int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
 		goto out;
 
 	/* HV KVM can only do PAPR mode for now */
-	if (!vcpu->arch.papr_enabled && kvmppc_ops->is_hv_enabled)
+	if (!vcpu->arch.papr_enabled && vcpu->kvm->arch.kvm_ops->is_hv_enabled)
 		goto out;
 
 #ifdef CONFIG_KVM_BOOKE_HV
@@ -271,10 +276,35 @@ void kvm_arch_check_processor_compat(void *rtn)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	if (type)
-		return -EINVAL;
-
+	struct kvmppc_ops *kvm_ops = NULL;
+	/*
+	 * if we have both HV and PR enabled, default is HV
+	 */
+	if (type == 0) {
+		if (kvmppc_hv_ops)
+			kvm_ops = kvmppc_hv_ops;
+		else
+			kvm_ops = kvmppc_pr_ops;
+		if (!kvm_ops)
+			goto err_out;
+	} else	if (type == KVM_VM_PPC_HV) {
+		if (!kvmppc_hv_ops)
+			goto err_out;
+		kvm_ops = kvmppc_hv_ops;
+	} else if (type == KVM_VM_PPC_PR) {
+		if (!kvmppc_pr_ops)
+			goto err_out;
+		kvm_ops = kvmppc_pr_ops;
+	} else
+		goto err_out;
+
+	if (kvm_ops->owner && !try_module_get(kvm_ops->owner))
+		return -ENOENT;
+
+	kvm->arch.kvm_ops = kvm_ops;
 	return kvmppc_core_init_vm(kvm);
+err_out:
+	return -EINVAL;
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -294,6 +324,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvmppc_core_destroy_vm(kvm);
 
 	mutex_unlock(&kvm->lock);
+
+	/* drop the module reference */
+	module_put(kvm->arch.kvm_ops->owner);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
@@ -303,6 +336,10 @@ void kvm_arch_sync_events(struct kvm *kvm)
 int kvm_dev_ioctl_check_extension(long ext)
 {
 	int r;
+	/* FIXME!!
+	 * Should some of this be vm ioctl ? is it possible now ?
+	 */
+	int hv_enabled = kvmppc_hv_ops ? 1 : 0;
 
 	switch (ext) {
 #ifdef CONFIG_BOOKE
@@ -329,7 +366,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_SW_TLB:
 #endif
 		/* We support this only for PR */
-		r = !kvmppc_ops->is_hv_enabled;
+		r = !hv_enabled;
 		break;
 #ifdef CONFIG_KVM_MMIO
 	case KVM_CAP_COALESCED_MMIO:
@@ -354,13 +391,13 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = threads_per_core;
 		else
 			r = 0;
 		break;
 	case KVM_CAP_PPC_RMA:
-		r = kvmppc_ops->is_hv_enabled;
+		r = hv_enabled;
 		/* PPC970 requires an RMA */
 		if (r && cpu_has_feature(CPU_FTR_ARCH_201))
 			r = 2;
@@ -368,7 +405,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
 		else
 			r = 0;
@@ -380,7 +417,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
-		r = kvmppc_ops->is_hv_enabled;
+		r = hv_enabled;
 		break;
 #endif
 	case KVM_CAP_NR_VCPUS:
@@ -390,7 +427,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		 * will have secondary threads "offline"), and for other KVM
 		 * implementations just count online CPUs.
 		 */
-		if (kvmppc_ops->is_hv_enabled)
+		if (hv_enabled)
 			r = num_present_cpus();
 		else
 			r = num_online_cpus();
@@ -1039,9 +1076,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 	case KVM_PPC_GET_SMMU_INFO: {
 		struct kvm_ppc_smmu_info info;
+		struct kvm *kvm = filp->private_data;
 
 		memset(&info, 0, sizeof(info));
-		r = kvmppc_ops->get_smmu_info(kvm, &info);
+		r = kvm->arch.kvm_ops->get_smmu_info(kvm, &info);
 		if (r >= 0 && copy_to_user(argp, &info, sizeof(info)))
 			r = -EFAULT;
 		break;
@@ -1052,9 +1090,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_rtas_define_token(kvm, argp);
 		break;
 	}
-	default:
-		r = kvmppc_ops->arch_vm_ioctl(filp, ioctl, arg);
-
+	default: {
+		struct kvm *kvm = filp->private_data;
+		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
+	}
 #else /* CONFIG_PPC_BOOK3S_64 */
 	default:
 		r = -ENOTTY;
@@ -1104,15 +1143,10 @@ EXPORT_SYMBOL_GPL(kvmppc_init_lpid);
 
 int kvm_arch_init(void *opaque)
 {
-	if (kvmppc_ops) {
-		printk(KERN_ERR "kvm: already loaded the other module\n");
-		return -EEXIST;
-	}
-	kvmppc_ops = (struct kvmppc_ops *)opaque;
 	return 0;
 }
 
 void kvm_arch_exit(void)
 {
-	kvmppc_ops = NULL;
+
 }
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e32e776f20c0..5b5341f78368 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -518,6 +518,10 @@ struct kvm_ppc_smmu_info {
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
 #define KVM_VM_S390_UCONTROL	1
 
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
 /*
-- 
cgit 


From 5930e8d0ab3689f1e239566443ca8f53e45e01cc Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 15 Oct 2013 16:55:22 +0200
Subject: net/mlx4: Fix typo, move similar defs to same location

Small code cleanup:

1. change MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN to MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN

2. put MLX4_SET_PORT_PRIO2TC and MLX4_SET_PORT_SCHEDULER in the same union with the
   other MLX4_SET_PORT_yyy

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c        | 2 +-
 include/linux/mlx4/cmd.h                       | 6 ++----
 include/linux/mlx4/device.h                    | 2 +-
 4 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fa37b7a61213..85d91665d400 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1733,7 +1733,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 
 	/* Unregister Mac address for the port */
 	mlx4_en_put_qp(priv);
-	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN))
+	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN))
 		mdev->mac_removed[priv->port] = 1;
 
 	/* Free RX Rings */
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 0d63daa2f422..a377484cf544 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -652,7 +652,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		 QUERY_DEV_CAP_RSVD_LKEY_OFFSET);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC);
 	if (field & 1<<6)
-		dev_cap->flags2 |= MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN;
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN;
 	MLX4_GET(dev_cap->max_icm_sz, outbox,
 		 QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET);
 	if (dev_cap->flags & MLX4_DEV_CAP_FLAG_COUNTERS)
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index cd1fdf75103b..8df61bc5da00 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -154,10 +154,6 @@ enum {
 	MLX4_CMD_QUERY_IF_STAT	 = 0X54,
 	MLX4_CMD_SET_IF_STAT	 = 0X55,
 
-	/* set port opcode modifiers */
-	MLX4_SET_PORT_PRIO2TC = 0x8,
-	MLX4_SET_PORT_SCHEDULER  = 0x9,
-
 	/* register/delete flow steering network rules */
 	MLX4_QP_FLOW_STEERING_ATTACH = 0x65,
 	MLX4_QP_FLOW_STEERING_DETACH = 0x66,
@@ -182,6 +178,8 @@ enum {
 	MLX4_SET_PORT_VLAN_TABLE = 0x3,
 	MLX4_SET_PORT_PRIO_MAP  = 0x4,
 	MLX4_SET_PORT_GID_TABLE = 0x5,
+	MLX4_SET_PORT_PRIO2TC	= 0x8,
+	MLX4_SET_PORT_SCHEDULER = 0x9,
 };
 
 enum {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 24ce6bdd540e..9ad0c18495ad 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -155,7 +155,7 @@ enum {
 	MLX4_DEV_CAP_FLAG2_RSS_TOP		= 1LL <<  1,
 	MLX4_DEV_CAP_FLAG2_RSS_XOR		= 1LL <<  2,
 	MLX4_DEV_CAP_FLAG2_FS_EN		= 1LL <<  3,
-	MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN	= 1LL <<  4,
+	MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN	= 1LL <<  4,
 	MLX4_DEV_CAP_FLAG2_TS			= 1LL <<  5,
 	MLX4_DEV_CAP_FLAG2_VLAN_CONTROL		= 1LL <<  6,
 	MLX4_DEV_CAP_FLAG2_FSM			= 1LL <<  7,
-- 
cgit 


From 78dea8cc4942c6adbcccc8f483463906a078f039 Mon Sep 17 00:00:00 2001
From: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Date: Sun, 13 Oct 2013 08:26:31 +0200
Subject: irda: update comment mentioning IRQF_DISABLED

This patch removes a comment mentioning IRQF_DISABLED,
which is deprecated.

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/irda/irda_device.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/irda/irda_device.h b/include/net/irda/irda_device.h
index 94c852d47d0f..11417475a6c3 100644
--- a/include/net/irda/irda_device.h
+++ b/include/net/irda/irda_device.h
@@ -162,7 +162,7 @@ typedef struct {
         int irq, irq2;        /* Interrupts used */
         int dma, dma2;        /* DMA channel(s) used */
         int fifo_size;        /* FIFO size */
-        int irqflags;         /* interrupt flags (ie, IRQF_SHARED|IRQF_DISABLED) */
+        int irqflags;         /* interrupt flags (ie, IRQF_SHARED) */
 	int direction;        /* Link direction, used by some FIR drivers */
 	int enabled;          /* Powered on? */
 	int suspended;        /* Suspended by APM */
-- 
cgit 


From 82fbb4f7b47683077e0716474d4f1ce65a2146cb Mon Sep 17 00:00:00 2001
From: Clemens Ladisch <clemens@ladisch.de>
Date: Sun, 4 Sep 2011 22:04:49 +0200
Subject: ALSA: add DICE driver

As a start point for further development, this is an incomplete driver
for DICE devices:
- only playback (so no clock source except the bus clock)
- only 44.1 kHz
- no MIDI
- recovery after bus reset is slow
- hwdep device is created, but not actually implemented

Contains compilation fixes by Stefan Richter.

Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
---
 Documentation/ioctl/ioctl-number.txt |    1 +
 include/uapi/sound/Kbuild            |    1 +
 include/uapi/sound/asound.h          |    3 +-
 include/uapi/sound/firewire.h        |   51 ++
 sound/firewire/Kconfig               |   13 +
 sound/firewire/Makefile              |    2 +
 sound/firewire/dice.c                | 1008 ++++++++++++++++++++++++++++++++++
 7 files changed, 1078 insertions(+), 1 deletion(-)
 create mode 100644 include/uapi/sound/firewire.h
 create mode 100644 sound/firewire/dice.c

(limited to 'include')

diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 2a5f0e14efa3..7cbfa3c4fc3d 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -138,6 +138,7 @@ Code  Seq#(hex)	Include File		Comments
 'H'	C0-DF	net/bluetooth/cmtp/cmtp.h	conflict!
 'H'	C0-DF	net/bluetooth/bnep/bnep.h	conflict!
 'H'	F1	linux/hid-roccat.h	<mailto:erazor_de@users.sourceforge.net>
+'H'	F8-FA	sound/firewire.h
 'I'	all	linux/isdn.h		conflict!
 'I'	00-0F	drivers/isdn/divert/isdn_divert.h	conflict!
 'I'	40-4F	linux/mISDNif.h		conflict!
diff --git a/include/uapi/sound/Kbuild b/include/uapi/sound/Kbuild
index 0f7d279ebde3..a7f27704f980 100644
--- a/include/uapi/sound/Kbuild
+++ b/include/uapi/sound/Kbuild
@@ -5,6 +5,7 @@ header-y += asound_fm.h
 header-y += compress_offload.h
 header-y += compress_params.h
 header-y += emu10k1.h
+header-y += firewire.h
 header-y += hdsp.h
 header-y += hdspm.h
 header-y += sb16_csp.h
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 041203f20f6d..9fc6219d3848 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -93,9 +93,10 @@ enum {
 	SNDRV_HWDEP_IFACE_SB_RC,	/* SB Extigy/Audigy2NX remote control */
 	SNDRV_HWDEP_IFACE_HDA,		/* HD-audio */
 	SNDRV_HWDEP_IFACE_USB_STREAM,	/* direct access to usb stream */
+	SNDRV_HWDEP_IFACE_FW_DICE,	/* TC DICE FireWire device */
 
 	/* Don't forget to change the following: */
-	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_USB_STREAM
+	SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_DICE
 };
 
 struct snd_hwdep_info {
diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h
new file mode 100644
index 000000000000..e86131ca49e5
--- /dev/null
+++ b/include/uapi/sound/firewire.h
@@ -0,0 +1,51 @@
+#ifndef UAPI_SOUND_FIREWIRE_H_INCLUDED
+#define UAPI_SOUND_FIREWIRE_H_INCLUDED
+
+#include <linux/ioctl.h>
+
+/* events can be read() from the hwdep device */
+
+#define SNDRV_FIREWIRE_EVENT_LOCK_STATUS	0x000010cc
+#define SNDRV_FIREWIRE_EVENT_DICE_NOTIFICATION	0xd1ce004e
+
+struct snd_firewire_event_common {
+	unsigned int type; /* SNDRV_FIREWIRE_EVENT_xxx */
+};
+
+struct snd_firewire_event_lock_status {
+	unsigned int type;
+	unsigned int status; /* 0/1 = unlocked/locked */
+};
+
+struct snd_firewire_event_dice_notification {
+	unsigned int type;
+	unsigned int notification; /* DICE-specific bits */
+};
+
+union snd_firewire_event {
+	struct snd_firewire_event_common            common;
+	struct snd_firewire_event_lock_status       lock_status;
+	struct snd_firewire_event_dice_notification dice_notification;
+};
+
+
+#define SNDRV_FIREWIRE_IOCTL_GET_INFO _IOR('H', 0xf8, struct snd_firewire_get_info)
+#define SNDRV_FIREWIRE_IOCTL_LOCK      _IO('H', 0xf9)
+#define SNDRV_FIREWIRE_IOCTL_UNLOCK    _IO('H', 0xfa)
+
+#define SNDRV_FIREWIRE_TYPE_DICE	1
+/* Fireworks, AV/C, RME, MOTU, ... */
+
+struct snd_firewire_get_info {
+	unsigned int type; /* SNDRV_FIREWIRE_TYPE_xxx */
+	unsigned int card; /* same as fw_cdev_get_info.card */
+	unsigned char guid[8];
+	char device_name[16]; /* device node in /dev */
+};
+
+/*
+ * SNDRV_FIREWIRE_IOCTL_LOCK prevents the driver from streaming.
+ * Returns -EBUSY if the driver is already streaming.
+ */
+
+#endif
diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig
index ea063e1f8722..915330989412 100644
--- a/sound/firewire/Kconfig
+++ b/sound/firewire/Kconfig
@@ -11,6 +11,19 @@ config SND_FIREWIRE_LIB
 	tristate
 	depends on SND_PCM
 
+config SND_DICE
+	tristate "DICE devices (EXPERIMENTAL)"
+	select SND_HWDEP
+	select SND_PCM
+	select SND_FIREWIRE_LIB
+	help
+	  Say Y here to include support for many FireWire audio interfaces
+	  based on the DICE chip family (DICE-II/Jr/Mini) from TC Applied
+	  Technologies.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called snd-dice.
+
 config SND_FIREWIRE_SPEAKERS
 	tristate "FireWire speakers"
 	select SND_PCM
diff --git a/sound/firewire/Makefile b/sound/firewire/Makefile
index 460179df5bb5..509955061d30 100644
--- a/sound/firewire/Makefile
+++ b/sound/firewire/Makefile
@@ -1,10 +1,12 @@
 snd-firewire-lib-objs := lib.o iso-resources.o packets-buffer.o \
 			 fcp.o cmp.o amdtp.o
+snd-dice-objs := dice.o
 snd-firewire-speakers-objs := speakers.o
 snd-isight-objs := isight.o
 snd-scs1x-objs := scs1x.o
 
 obj-$(CONFIG_SND_FIREWIRE_LIB) += snd-firewire-lib.o
+obj-$(CONFIG_SND_DICE) += snd-dice.o
 obj-$(CONFIG_SND_FIREWIRE_SPEAKERS) += snd-firewire-speakers.o
 obj-$(CONFIG_SND_ISIGHT) += snd-isight.o
 obj-$(CONFIG_SND_SCS1X) += snd-scs1x.o
diff --git a/sound/firewire/dice.c b/sound/firewire/dice.c
new file mode 100644
index 000000000000..ac71b2b94eec
--- /dev/null
+++ b/sound/firewire/dice.c
@@ -0,0 +1,1008 @@
+/*
+ * TC Applied Technologies Digital Interface Communications Engine driver
+ *
+ * Copyright (c) Clemens Ladisch <clemens@ladisch.de>
+ * Licensed under the terms of the GNU General Public License, version 2.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/firewire.h>
+#include <linux/firewire-constants.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <sound/control.h>
+#include <sound/core.h>
+#include <sound/hwdep.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include "amdtp.h"
+#include "iso-resources.h"
+#include "lib.h"
+
+#define DICE_PRIVATE_SPACE		0xffffe0000000uLL
+
+/* offset from DICE_PRIVATE_SPACE; offsets and sizes in quadlets */
+#define DICE_GLOBAL_OFFSET		0x00
+#define DICE_GLOBAL_SIZE		0x04
+#define DICE_TX_OFFSET			0x08
+#define DICE_TX_SIZE			0x0c
+#define DICE_RX_OFFSET			0x10
+#define DICE_RX_SIZE			0x14
+
+/* pointed to by DICE_GLOBAL_OFFSET */
+#define GLOBAL_OWNER			0x000
+#define  OWNER_NO_OWNER			0xffff000000000000uLL
+#define  OWNER_NODE_SHIFT		48
+#define GLOBAL_NOTIFICATION		0x008
+#define  NOTIFY_RX_CFG_CHG		0x00000001
+#define  NOTIFY_TX_CFG_CHG		0x00000002
+#define  NOTIFY_DUP_ISOC		0x00000004
+#define  NOTIFY_BW_ERR			0x00000008
+#define  NOTIFY_LOCK_CHG		0x00000010
+#define  NOTIFY_CLOCK_ACCEPTED		0x00000020
+#define  NOTIFY_INTERFACE_CHG		0x00000040
+#define  NOTIFY_MESSAGE			0x00100000
+#define GLOBAL_NICK_NAME		0x00c
+#define  NICK_NAME_SIZE			64
+#define GLOBAL_CLOCK_SELECT		0x04c
+#define  CLOCK_SOURCE_MASK		0x000000ff
+#define  CLOCK_SOURCE_AES1		0x00000000
+#define  CLOCK_SOURCE_AES2		0x00000001
+#define  CLOCK_SOURCE_AES3		0x00000002
+#define  CLOCK_SOURCE_AES4		0x00000003
+#define  CLOCK_SOURCE_AES_ANY		0x00000004
+#define  CLOCK_SOURCE_ADAT		0x00000005
+#define  CLOCK_SOURCE_TDIF		0x00000006
+#define  CLOCK_SOURCE_WC		0x00000007
+#define  CLOCK_SOURCE_ARX1		0x00000008
+#define  CLOCK_SOURCE_ARX2		0x00000009
+#define  CLOCK_SOURCE_ARX3		0x0000000a
+#define  CLOCK_SOURCE_ARX4		0x0000000b
+#define  CLOCK_SOURCE_INTERNAL		0x0000000c
+#define  CLOCK_RATE_MASK		0x0000ff00
+#define  CLOCK_RATE_32000		0x00000000
+#define  CLOCK_RATE_44100		0x00000100
+#define  CLOCK_RATE_48000		0x00000200
+#define  CLOCK_RATE_88200		0x00000300
+#define  CLOCK_RATE_96000		0x00000400
+#define  CLOCK_RATE_176400		0x00000500
+#define  CLOCK_RATE_192000		0x00000600
+#define  CLOCK_RATE_ANY_LOW		0x00000700
+#define  CLOCK_RATE_ANY_MID		0x00000800
+#define  CLOCK_RATE_ANY_HIGH		0x00000900
+#define  CLOCK_RATE_NONE		0x00000a00
+#define GLOBAL_ENABLE			0x050
+#define  ENABLE				0x00000001
+#define GLOBAL_STATUS			0x054
+#define  STATUS_SOURCE_LOCKED		0x00000001
+#define  STATUS_RATE_CONFLICT		0x00000002
+#define  STATUS_NOMINAL_RATE_MASK	0x0000ff00
+#define GLOBAL_EXTENDED_STATUS		0x058
+#define  EXT_STATUS_AES1_LOCKED		0x00000001
+#define  EXT_STATUS_AES2_LOCKED		0x00000002
+#define  EXT_STATUS_AES3_LOCKED		0x00000004
+#define  EXT_STATUS_AES4_LOCKED		0x00000008
+#define  EXT_STATUS_ADAT_LOCKED		0x00000010
+#define  EXT_STATUS_TDIF_LOCKED		0x00000020
+#define  EXT_STATUS_ARX1_LOCKED		0x00000040
+#define  EXT_STATUS_ARX2_LOCKED		0x00000080
+#define  EXT_STATUS_ARX3_LOCKED		0x00000100
+#define  EXT_STATUS_ARX4_LOCKED		0x00000200
+#define  EXT_STATUS_WC_LOCKED		0x00000400
+#define  EXT_STATUS_AES1_SLIP		0x00010000
+#define  EXT_STATUS_AES2_SLIP		0x00020000
+#define  EXT_STATUS_AES3_SLIP		0x00040000
+#define  EXT_STATUS_AES4_SLIP		0x00080000
+#define  EXT_STATUS_ADAT_SLIP		0x00100000
+#define  EXT_STATUS_TDIF_SLIP		0x00200000
+#define  EXT_STATUS_ARX1_SLIP		0x00400000
+#define  EXT_STATUS_ARX2_SLIP		0x00800000
+#define  EXT_STATUS_ARX3_SLIP		0x01000000
+#define  EXT_STATUS_ARX4_SLIP		0x02000000
+#define  EXT_STATUS_WC_SLIP		0x04000000
+#define GLOBAL_SAMPLE_RATE		0x05c
+#define GLOBAL_VERSION			0x060
+#define GLOBAL_CLOCK_CAPABILITIES	0x064
+#define  CLOCK_CAP_RATE_32000		0x00000001
+#define  CLOCK_CAP_RATE_44100		0x00000002
+#define  CLOCK_CAP_RATE_48000		0x00000004
+#define  CLOCK_CAP_RATE_88200		0x00000008
+#define  CLOCK_CAP_RATE_96000		0x00000010
+#define  CLOCK_CAP_RATE_176400		0x00000020
+#define  CLOCK_CAP_RATE_192000		0x00000040
+#define  CLOCK_CAP_SOURCE_AES1		0x00010000
+#define  CLOCK_CAP_SOURCE_AES2		0x00020000
+#define  CLOCK_CAP_SOURCE_AES3		0x00040000
+#define  CLOCK_CAP_SOURCE_AES4		0x00080000
+#define  CLOCK_CAP_SOURCE_AES_ANY	0x00100000
+#define  CLOCK_CAP_SOURCE_ADAT		0x00200000
+#define  CLOCK_CAP_SOURCE_TDIF		0x00400000
+#define  CLOCK_CAP_SOURCE_WC		0x00800000
+#define  CLOCK_CAP_SOURCE_ARX1		0x01000000
+#define  CLOCK_CAP_SOURCE_ARX2		0x02000000
+#define  CLOCK_CAP_SOURCE_ARX3		0x04000000
+#define  CLOCK_CAP_SOURCE_ARX4		0x08000000
+#define  CLOCK_CAP_SOURCE_INTERNAL	0x10000000
+#define GLOBAL_CLOCK_SOURCE_NAMES	0x068
+#define  CLOCK_SOURCE_NAMES_SIZE	256
+
+/* pointed to by DICE_TX_OFFSET */
+#define TX_NUMBER			0x000
+#define TX_SIZE				0x004
+/* repeated TX_NUMBER times, offset by TX_SIZE quadlets */
+#define TX_ISOCHRONOUS			0x008
+#define TX_NUMBER_AUDIO			0x00c
+#define TX_NUMBER_MIDI			0x010
+#define TX_SPEED			0x014
+#define TX_NAMES			0x018
+#define  TX_NAMES_SIZE			256
+#define TX_AC3_CAPABILITIES		0x118
+#define TX_AC3_ENABLE			0x11c
+
+/* pointed to by DICE_RX_OFFSET */
+#define RX_NUMBER			0x000
+#define RX_SIZE				0x004
+/* repeated RX_NUMBER times, offset by RX_SIZE quadlets */
+#define RX_ISOCHRONOUS			0x008
+#define RX_SEQ_START			0x00c
+#define RX_NUMBER_AUDIO			0x010
+#define RX_NUMBER_MIDI			0x014
+#define RX_NAMES			0x018
+#define  RX_NAMES_SIZE			256
+#define RX_AC3_CAPABILITIES		0x118
+#define RX_AC3_ENABLE			0x11c
+
+
+#define FIRMWARE_LOAD_SPACE		0xffffe0100000uLL
+
+/* offset from FIRMWARE_LOAD_SPACE */
+#define FIRMWARE_VERSION		0x000
+#define FIRMWARE_OPCODE			0x004
+#define  OPCODE_MASK			0x00000fff
+#define  OPCODE_GET_IMAGE_DESC		0x00000000
+#define  OPCODE_DELETE_IMAGE		0x00000001
+#define  OPCODE_CREATE_IMAGE		0x00000002
+#define  OPCODE_UPLOAD			0x00000003
+#define  OPCODE_UPLOAD_STAT		0x00000004
+#define  OPCODE_RESET_IMAGE		0x00000005
+#define  OPCODE_TEST_ACTION		0x00000006
+#define  OPCODE_GET_RUNNING_IMAGE_VINFO	0x0000000a
+#define  OPCODE_EXECUTE			0x80000000
+#define FIRMWARE_RETURN_STATUS		0x008
+#define FIRMWARE_PROGRESS		0x00c
+#define  PROGRESS_CURR_MASK		0x00000fff
+#define  PROGRESS_MAX_MASK		0x00fff000
+#define  PROGRESS_TOUT_MASK		0x0f000000
+#define  PROGRESS_FLAG			0x80000000
+#define FIRMWARE_CAPABILITIES		0x010
+#define  FL_CAP_AUTOERASE		0x00000001
+#define  FL_CAP_PROGRESS		0x00000002
+#define FIRMWARE_DATA			0x02c
+#define  TEST_CMD_POKE			0x00000001
+#define  TEST_CMD_PEEK			0x00000002
+#define  CMD_GET_AVS_CNT		0x00000003
+#define  CMD_CLR_AVS_CNT		0x00000004
+#define  CMD_SET_MODE			0x00000005
+#define  CMD_SET_MIDIBP			0x00000006
+#define  CMD_GET_AVSPHASE		0x00000007
+#define  CMD_ENABLE_BNC_SYNC		0x00000008
+#define  CMD_PULSE_BNC_SYNC		0x00000009
+#define  CMD_EMUL_SLOW_CMD		0x0000000a
+#define FIRMWARE_TEST_DELAY		0xfd8
+#define FIRMWARE_TEST_BUF		0xfdc
+
+
+/* EAP */
+#define EAP_PRIVATE_SPACE		0xffffe0200000uLL
+
+#define EAP_CAPABILITY_OFFSET		0x000
+#define EAP_CAPABILITY_SIZE		0x004
+/* ... */
+
+#define EAP_ROUTER_CAPS			0x000
+#define  ROUTER_EXPOSED			0x00000001
+#define  ROUTER_READ_ONLY		0x00000002
+#define  ROUTER_FLASH			0x00000004
+#define  MAX_ROUTES_MASK		0xffff0000
+#define EAP_MIXER_CAPS			0x004
+#define  MIXER_EXPOSED			0x00000001
+#define  MIXER_READ_ONLY		0x00000002
+#define  MIXER_FLASH			0x00000004
+#define  MIXER_IN_DEV_MASK		0x000000f0
+#define  MIXER_OUT_DEV_MASK		0x00000f00
+#define  MIXER_INPUTS_MASK		0x00ff0000
+#define  MIXER_OUTPUTS_MASK		0xff000000
+#define EAP_GENERAL_CAPS		0x008
+#define  GENERAL_STREAM_CONFIG		0x00000001
+#define  GENERAL_FLASH			0x00000002
+#define  GENERAL_PEAK			0x00000004
+#define  GENERAL_MAX_TX_STREAMS_MASK	0x000000f0
+#define  GENERAL_MAX_RX_STREAMS_MASK	0x00000f00
+#define  GENERAL_STREAM_CONFIG_FLASH	0x00001000
+#define  GENERAL_CHIP_MASK		0x00ff0000
+#define  GENERAL_CHIP_DICE_II		0x00000000
+#define  GENERAL_CHIP_DICE_MINI		0x00010000
+#define  GENERAL_CHIP_DICE_JR		0x00020000
+
+
+struct dice {
+	struct snd_card *card;
+	struct fw_unit *unit;
+	struct mutex mutex;
+	unsigned int global_offset;
+	unsigned int rx_offset;
+	struct fw_address_handler notification_handler;
+	int owner_generation;
+	bool global_enabled;
+	bool stream_running;
+	struct snd_pcm_substream *pcm;
+	struct fw_iso_resources resources;
+	struct amdtp_out_stream stream;
+};
+
+MODULE_DESCRIPTION("DICE driver");
+MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
+MODULE_LICENSE("GPL v2");
+
+static inline u64 global_address(struct dice *dice, unsigned int offset)
+{
+	return DICE_PRIVATE_SPACE + dice->global_offset + offset;
+}
+
+// TODO: rx index
+static inline u64 rx_address(struct dice *dice, unsigned int offset)
+{
+	return DICE_PRIVATE_SPACE + dice->rx_offset + offset;
+}
+
+static int dice_owner_set(struct dice *dice)
+{
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be64 *buffer;
+	int rcode, err, errors = 0;
+
+	buffer = kmalloc(2 * 8, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	for (;;) {
+		buffer[0] = cpu_to_be64(OWNER_NO_OWNER);
+		buffer[1] = cpu_to_be64(
+			((u64)device->card->node_id << OWNER_NODE_SHIFT) |
+			dice->notification_handler.offset);
+
+		dice->owner_generation = device->generation;
+		smp_rmb(); /* node_id vs. generation */
+		rcode = fw_run_transaction(device->card,
+					   TCODE_LOCK_COMPARE_SWAP,
+					   device->node_id,
+					   dice->owner_generation,
+					   device->max_speed,
+					   global_address(dice, GLOBAL_OWNER),
+					   buffer, 2 * 8);
+
+		if (rcode == RCODE_COMPLETE) {
+			if (buffer[0] == cpu_to_be64(OWNER_NO_OWNER)) {
+				err = 0;
+			} else {
+				dev_err(&dice->unit->device,
+					"device is already in use\n");
+				err = -EBUSY;
+			}
+			break;
+		}
+		if (rcode_is_permanent_error(rcode) || ++errors >= 3) {
+			dev_err(&dice->unit->device,
+				"setting device owner failed: %s\n",
+				fw_rcode_string(rcode));
+			err = -EIO;
+			break;
+		}
+		msleep(20);
+	}
+
+	kfree(buffer);
+
+	return err;
+}
+
+static int dice_owner_update(struct dice *dice)
+{
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be64 *buffer;
+	int rcode, err, errors = 0;
+
+	if (dice->owner_generation == -1)
+		return 0;
+
+	buffer = kmalloc(2 * 8, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	for (;;) {
+		buffer[0] = cpu_to_be64(OWNER_NO_OWNER);
+		buffer[1] = cpu_to_be64(
+			((u64)device->card->node_id << OWNER_NODE_SHIFT) |
+			dice->notification_handler.offset);
+
+		dice->owner_generation = device->generation;
+		smp_rmb(); /* node_id vs. generation */
+		rcode = fw_run_transaction(device->card,
+					   TCODE_LOCK_COMPARE_SWAP,
+					   device->node_id,
+					   dice->owner_generation,
+					   device->max_speed,
+					   global_address(dice, GLOBAL_OWNER),
+					   buffer, 2 * 8);
+
+		if (rcode == RCODE_COMPLETE) {
+			if (buffer[0] == cpu_to_be64(OWNER_NO_OWNER)) {
+				err = 0;
+			} else {
+				dev_err(&dice->unit->device,
+					"device is already in use\n");
+				err = -EBUSY;
+			}
+			break;
+		}
+		if (rcode == RCODE_GENERATION) {
+			err = 0; /* try again later */
+			break;
+		}
+		if (rcode_is_permanent_error(rcode) || ++errors >= 3) {
+			dev_err(&dice->unit->device,
+				"setting device owner failed: %s\n",
+				fw_rcode_string(rcode));
+			err = -EIO;
+			break;
+		}
+		msleep(20);
+	}
+
+	kfree(buffer);
+
+	if (err < 0)
+		dice->owner_generation = -1;
+
+	return err;
+}
+
+static void dice_owner_clear(struct dice *dice)
+{
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be64 *buffer;
+	int rcode, errors = 0;
+
+	buffer = kmalloc(2 * 8, GFP_KERNEL);
+	if (!buffer)
+		return;
+
+	for (;;) {
+		buffer[0] = cpu_to_be64(
+			((u64)device->card->node_id << OWNER_NODE_SHIFT) |
+			dice->notification_handler.offset);
+		buffer[1] = cpu_to_be64(OWNER_NO_OWNER);
+
+		rcode = fw_run_transaction(device->card,
+					   TCODE_LOCK_COMPARE_SWAP,
+					   device->node_id,
+					   dice->owner_generation,
+					   device->max_speed,
+					   global_address(dice, GLOBAL_OWNER),
+					   buffer, 2 * 8);
+
+		if (rcode == RCODE_COMPLETE)
+			break;
+		if (rcode == RCODE_GENERATION)
+			break;
+		if (rcode_is_permanent_error(rcode) || ++errors >= 3) {
+			dev_err(&dice->unit->device,
+				"clearing device owner failed: %s\n",
+				fw_rcode_string(rcode));
+			break;
+		}
+		msleep(20);
+	}
+
+	kfree(buffer);
+
+	dice->owner_generation = -1;
+}
+
+static int dice_enable_set(struct dice *dice)
+{
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be32 value;
+	int rcode, err, errors = 0;
+
+	value = cpu_to_be32(ENABLE);
+	for (;;) {
+		rcode = fw_run_transaction(device->card,
+					   TCODE_WRITE_QUADLET_REQUEST,
+					   device->node_id,
+					   dice->owner_generation,
+					   device->max_speed,
+					   global_address(dice, GLOBAL_ENABLE),
+					   &value, 4);
+		if (rcode == RCODE_COMPLETE) {
+			dice->global_enabled = true;
+			err = 0;
+			break;
+		}
+		if (rcode == RCODE_GENERATION) {
+			err = -EAGAIN;
+			break;
+		}
+		if (rcode_is_permanent_error(rcode) || ++errors >= 3) {
+			dev_err(&dice->unit->device,
+				"device enabling failed: %s\n",
+				fw_rcode_string(rcode));
+			err = -EIO;
+			break;
+		}
+		msleep(20);
+	}
+
+	return err;
+}
+
+static void dice_enable_clear(struct dice *dice)
+{
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be32 value;
+	int rcode, errors = 0;
+
+	value = 0;
+	for (;;) {
+		rcode = fw_run_transaction(device->card,
+					   TCODE_WRITE_QUADLET_REQUEST,
+					   device->node_id,
+					   dice->owner_generation,
+					   device->max_speed,
+					   global_address(dice, GLOBAL_ENABLE),
+					   &value, 4);
+		if (rcode == RCODE_COMPLETE ||
+		    rcode == RCODE_GENERATION)
+			break;
+		if (rcode_is_permanent_error(rcode) || ++errors >= 3) {
+			dev_err(&dice->unit->device,
+				"device disabling failed: %s\n",
+				fw_rcode_string(rcode));
+			break;
+		}
+		msleep(20);
+	}
+	dice->global_enabled = false;
+}
+
+static void dice_notification(struct fw_card *card, struct fw_request *request,
+			      int tcode, int destination, int source,
+			      int generation, unsigned long long offset,
+			      void *data, size_t length, void *callback_data)
+{
+	struct dice *dice = callback_data;
+
+	if (tcode != TCODE_WRITE_QUADLET_REQUEST) {
+		fw_send_response(card, request, RCODE_TYPE_ERROR);
+		return;
+	}
+	if ((offset & 3) != 0) {
+		fw_send_response(card, request, RCODE_ADDRESS_ERROR);
+		return;
+	}
+	dev_info(&dice->unit->device,
+		 "notification: %08x\n", be32_to_cpup(data));
+	fw_send_response(card, request, RCODE_COMPLETE);
+}
+
+static int dice_open(struct snd_pcm_substream *substream)
+{
+	static const struct snd_pcm_hardware hardware = {
+		.info = SNDRV_PCM_INFO_MMAP |
+			SNDRV_PCM_INFO_MMAP_VALID |
+			SNDRV_PCM_INFO_BATCH |
+			SNDRV_PCM_INFO_INTERLEAVED |
+			SNDRV_PCM_INFO_BLOCK_TRANSFER,
+		.formats = AMDTP_OUT_PCM_FORMAT_BITS,
+		.rates = SNDRV_PCM_RATE_44100,
+		.rate_min = 44100,
+		.rate_max = 44100,
+		.buffer_bytes_max = 16 * 1024 * 1024,
+		.period_bytes_min = 1,
+		.period_bytes_max = UINT_MAX,
+		.periods_min = 1,
+		.periods_max = UINT_MAX,
+	};
+	struct dice *dice = substream->private_data;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	__be32 number_audio, number_midi;
+	int err;
+
+	err = snd_fw_transaction(dice->unit, TCODE_READ_QUADLET_REQUEST,
+				 rx_address(dice, RX_NUMBER_AUDIO),
+				 &number_audio, 4);
+	if (err < 0)
+		return err;
+	err = snd_fw_transaction(dice->unit, TCODE_READ_QUADLET_REQUEST,
+				 rx_address(dice, RX_NUMBER_MIDI),
+				 &number_midi, 4);
+	if (err < 0)
+		return err;
+
+	runtime->hw = hardware;
+	runtime->hw.channels_min = be32_to_cpu(number_audio);
+	runtime->hw.channels_max = be32_to_cpu(number_audio);
+
+	amdtp_out_stream_set_rate(&dice->stream, 44100);
+	amdtp_out_stream_set_pcm(&dice->stream, be32_to_cpu(number_audio));
+	amdtp_out_stream_set_midi(&dice->stream, be32_to_cpu(number_midi));
+
+	err = snd_pcm_hw_constraint_minmax(runtime,
+					   SNDRV_PCM_HW_PARAM_PERIOD_TIME,
+					   5000, 8192000);
+	if (err < 0)
+		return err;
+
+	err = snd_pcm_hw_constraint_msbits(runtime, 0, 32, 24);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int dice_close(struct snd_pcm_substream *substream)
+{
+	return 0;
+}
+
+static void dice_stop_stream(struct dice *dice)
+{
+	__be32 channel;
+
+	if (dice->stream_running) {
+		dice_enable_clear(dice);
+
+		amdtp_out_stream_stop(&dice->stream);
+
+		channel = cpu_to_be32((u32)-1);
+		snd_fw_transaction(dice->unit, TCODE_WRITE_QUADLET_REQUEST,
+				   rx_address(dice, RX_ISOCHRONOUS),
+				   &channel, 4);
+
+		fw_iso_resources_free(&dice->resources);
+
+		dice->stream_running = false;
+	}
+}
+
+static int dice_hw_params(struct snd_pcm_substream *substream,
+			  struct snd_pcm_hw_params *hw_params)
+{
+	struct dice *dice = substream->private_data;
+	int err;
+
+	mutex_lock(&dice->mutex);
+	dice_stop_stream(dice);
+	mutex_unlock(&dice->mutex);
+
+	err = snd_pcm_lib_alloc_vmalloc_buffer(substream,
+					       params_buffer_bytes(hw_params));
+	if (err < 0)
+		goto error;
+
+	amdtp_out_stream_set_pcm_format(&dice->stream,
+					params_format(hw_params));
+
+	return 0;
+
+error:
+	return err;
+}
+
+static int dice_hw_free(struct snd_pcm_substream *substream)
+{
+	struct dice *dice = substream->private_data;
+
+	mutex_lock(&dice->mutex);
+	dice_stop_stream(dice);
+	mutex_unlock(&dice->mutex);
+
+	return snd_pcm_lib_free_vmalloc_buffer(substream);
+}
+
+static int dice_prepare(struct snd_pcm_substream *substream)
+{
+	struct dice *dice = substream->private_data;
+	struct fw_device *device = fw_parent_device(dice->unit);
+	__be32 channel;
+	int err;
+
+	mutex_lock(&dice->mutex);
+
+	if (amdtp_out_streaming_error(&dice->stream))
+		dice_stop_stream(dice);
+
+	if (!dice->stream_running) {
+		err = fw_iso_resources_allocate(&dice->resources,
+				amdtp_out_stream_get_max_payload(&dice->stream),
+				device->max_speed);
+		if (err < 0)
+			goto error;
+
+		//TODO: RX_SEQ_START
+		channel = cpu_to_be32(dice->resources.channel);
+		err = snd_fw_transaction(dice->unit,
+					 TCODE_WRITE_QUADLET_REQUEST,
+					 rx_address(dice, RX_ISOCHRONOUS),
+					 &channel, 4);
+		if (err < 0)
+			goto err_resources;
+
+		err = amdtp_out_stream_start(&dice->stream,
+					     dice->resources.channel,
+					     device->max_speed);
+		if (err < 0)
+			goto err_resources;
+
+		err = dice_enable_set(dice);
+		if (err < 0)
+			goto err_stream;
+
+		dice->stream_running = true;
+	}
+
+	mutex_unlock(&dice->mutex);
+
+	amdtp_out_stream_pcm_prepare(&dice->stream);
+
+	return 0;
+
+err_stream:
+	amdtp_out_stream_stop(&dice->stream);
+err_resources:
+	fw_iso_resources_free(&dice->resources);
+error:
+	mutex_unlock(&dice->mutex);
+
+	return err;
+}
+
+static int dice_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct dice *dice = substream->private_data;
+	struct snd_pcm_substream *pcm;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+		pcm = substream;
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+		pcm = NULL;
+		break;
+	default:
+		return -EINVAL;
+	}
+	amdtp_out_stream_pcm_trigger(&dice->stream, pcm);
+
+	return 0;
+}
+
+static snd_pcm_uframes_t dice_pointer(struct snd_pcm_substream *substream)
+{
+	struct dice *dice = substream->private_data;
+
+	return amdtp_out_stream_pcm_pointer(&dice->stream);
+}
+
+static int dice_create_pcm(struct dice *dice)
+{
+	static struct snd_pcm_ops ops = {
+		.open      = dice_open,
+		.close     = dice_close,
+		.ioctl     = snd_pcm_lib_ioctl,
+		.hw_params = dice_hw_params,
+		.hw_free   = dice_hw_free,
+		.prepare   = dice_prepare,
+		.trigger   = dice_trigger,
+		.pointer   = dice_pointer,
+		.page      = snd_pcm_lib_get_vmalloc_page,
+		.mmap      = snd_pcm_lib_mmap_vmalloc,
+	};
+	__be32 clock;
+	struct snd_pcm *pcm;
+	int err;
+
+	clock = cpu_to_be32(CLOCK_SOURCE_ARX1 | CLOCK_RATE_44100);
+	err = snd_fw_transaction(dice->unit, TCODE_WRITE_QUADLET_REQUEST,
+				 global_address(dice, GLOBAL_CLOCK_SELECT),
+				 &clock, 4);
+	if (err < 0)
+		return err;
+
+	err = snd_pcm_new(dice->card, "DICE", 0, 1, 0, &pcm);
+	if (err < 0)
+		return err;
+	pcm->private_data = dice;
+	strcpy(pcm->name, dice->card->shortname);
+	dice->pcm = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
+	dice->pcm->ops = &ops;
+
+	return 0;
+}
+
+// TODO: implement these
+
+static long dice_hwdep_read(struct snd_hwdep *hwdep, char __user *buf,
+			    long count, loff_t *offset)
+{
+	return -EIO;
+}
+
+static int dice_hwdep_open(struct snd_hwdep *hwdep, struct file *file)
+{
+	return -EIO;
+}
+
+static int dice_hwdep_release(struct snd_hwdep *hwdep, struct file *file)
+{
+	return 0;
+}
+
+static unsigned int dice_hwdep_poll(struct snd_hwdep *hwdep, struct file *file,
+				    poll_table *wait)
+{
+	return POLLERR | POLLHUP;
+}
+
+static int dice_hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file,
+			    unsigned int cmd, unsigned long arg)
+{
+	return -EIO;
+}
+
+static int dice_create_hwdep(struct dice *dice)
+{
+	static const struct snd_hwdep_ops ops = {
+		.read         = dice_hwdep_read,
+		.open         = dice_hwdep_open,
+		.release      = dice_hwdep_release,
+		.poll         = dice_hwdep_poll,
+		.ioctl        = dice_hwdep_ioctl,
+		.ioctl_compat = dice_hwdep_ioctl,
+	};
+	struct snd_hwdep *hwdep;
+	int err;
+
+	err = snd_hwdep_new(dice->card, "DICE", 0, &hwdep);
+	if (err < 0)
+		return err;
+	strcpy(hwdep->name, "DICE");
+	hwdep->iface = SNDRV_HWDEP_IFACE_FW_DICE;
+	hwdep->ops = ops;
+	hwdep->private_data = dice;
+	hwdep->exclusive = true;
+
+	return 0;
+}
+
+static void dice_card_free(struct snd_card *card)
+{
+	struct dice *dice = card->private_data;
+
+	amdtp_out_stream_destroy(&dice->stream);
+	fw_core_remove_address_handler(&dice->notification_handler);
+	mutex_destroy(&dice->mutex);
+}
+
+static int dice_init_offsets(struct dice *dice)
+{
+	__be32 pointers[6];
+	unsigned int global_size, rx_size;
+	int err;
+
+	err = snd_fw_transaction(dice->unit, TCODE_READ_BLOCK_REQUEST,
+				 DICE_PRIVATE_SPACE, &pointers, 6 * 4);
+	if (err < 0)
+		return err;
+
+	dice->global_offset = be32_to_cpu(pointers[0]) * 4;
+	global_size = be32_to_cpu(pointers[1]);
+	dice->rx_offset = be32_to_cpu(pointers[4]) * 4;
+	rx_size = be32_to_cpu(pointers[5]);
+
+	/* some sanity checks to ensure that we actually have a DICE */
+	if (dice->global_offset < 10 * 4 || global_size < 0x168 / 4 ||
+	    dice->rx_offset < 10 * 4 || rx_size < 0x120 / 4) {
+		dev_err(&dice->unit->device, "invalid register pointers\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void dice_card_strings(struct dice *dice)
+{
+	struct snd_card *card = dice->card;
+	struct fw_device *dev = fw_parent_device(dice->unit);
+	char vendor[32], model[32];
+	unsigned int i;
+	int err;
+
+	strcpy(card->driver, "DICE");
+
+	strcpy(card->shortname, "DICE");
+	BUILD_BUG_ON(NICK_NAME_SIZE < sizeof(card->shortname));
+	err = snd_fw_transaction(dice->unit, TCODE_READ_BLOCK_REQUEST,
+				 global_address(dice, GLOBAL_NICK_NAME),
+				 card->shortname, sizeof(card->shortname));
+	if (err >= 0) {
+		/* DICE strings are returned in "always-wrong" endianness */
+		BUILD_BUG_ON(sizeof(card->shortname) % 4 != 0);
+		for (i = 0; i < sizeof(card->shortname); i += 4)
+			swab32s((u32 *)&card->shortname[i]);
+		card->shortname[sizeof(card->shortname) - 1] = '\0';
+	}
+
+	strcpy(vendor, "?");
+	fw_csr_string(dev->config_rom + 5, CSR_VENDOR, vendor, sizeof(vendor));
+	strcpy(model, "?");
+	fw_csr_string(dice->unit->directory, CSR_MODEL, model, sizeof(model));
+	snprintf(card->longname, sizeof(card->longname),
+		 "%s %s, GUID %08x%08x at %s, S%d",
+		 vendor, model, dev->config_rom[3], dev->config_rom[4],
+		 dev_name(&dice->unit->device), 100 << dev->max_speed);
+
+	strcpy(card->mixername, "DICE");
+}
+
+static int dice_probe(struct fw_unit *unit, const struct ieee1394_device_id *id)
+{
+	struct snd_card *card;
+	struct dice *dice;
+	int err;
+
+	err = snd_card_create(-1, NULL, THIS_MODULE, sizeof(*dice), &card);
+	if (err < 0)
+		return err;
+	snd_card_set_dev(card, &unit->device);
+
+	dice = card->private_data;
+	dice->card = card;
+	mutex_init(&dice->mutex);
+	dice->unit = unit;
+
+	err = dice_init_offsets(dice);
+	if (err < 0)
+		goto err_mutex;
+
+	dice->notification_handler.length = 4;
+	dice->notification_handler.address_callback = dice_notification;
+	dice->notification_handler.callback_data = dice;
+	err = fw_core_add_address_handler(&dice->notification_handler,
+					  &fw_high_memory_region);
+	if (err < 0)
+		goto err_mutex;
+
+	err = fw_iso_resources_init(&dice->resources, unit);
+	if (err < 0)
+		goto err_notification_handler;
+	dice->resources.channels_mask = 0x00000000ffffffffuLL;
+
+	err = amdtp_out_stream_init(&dice->stream, unit, CIP_NONBLOCKING);
+	if (err < 0)
+		goto err_resources;
+
+	err = dice_owner_set(dice);
+	if (err < 0)
+		goto err_stream;
+
+	card->private_free = dice_card_free;
+
+	dice_card_strings(dice);
+
+	err = dice_create_pcm(dice);
+	if (err < 0)
+		goto error;
+
+	err = dice_create_hwdep(dice);
+	if (err < 0)
+		goto error;
+
+	err = snd_card_register(card);
+	if (err < 0)
+		goto error;
+
+	dev_set_drvdata(&unit->device, dice);
+
+	return 0;
+
+err_stream:
+	amdtp_out_stream_destroy(&dice->stream);
+err_resources:
+	fw_iso_resources_destroy(&dice->resources);
+err_notification_handler:
+	fw_core_remove_address_handler(&dice->notification_handler);
+err_mutex:
+	mutex_destroy(&dice->mutex);
+error:
+	snd_card_free(card);
+	return err;
+}
+
+static void dice_remove(struct fw_unit *unit)
+{
+	struct dice *dice = dev_get_drvdata(&unit->device);
+
+	snd_card_disconnect(dice->card);
+
+	mutex_lock(&dice->mutex);
+	amdtp_out_stream_pcm_abort(&dice->stream);
+	dice_stop_stream(dice);
+	dice_owner_clear(dice);
+	mutex_unlock(&dice->mutex);
+
+	snd_card_free_when_closed(dice->card);
+}
+
+static void dice_bus_reset(struct fw_unit *unit)
+{
+	struct dice *dice = dev_get_drvdata(&unit->device);
+
+	mutex_lock(&dice->mutex);
+	/*
+	 * XXX is the following true?
+	 * On a bus reset, the DICE firmware disables streaming and then goes
+	 * off contemplating its own navel for hundreds of milliseconds before
+	 * it can react to any of our attempts to reenable streaming.  This
+	 * means that we lose synchronization anyway, so we force our streams
+	 * to stop so that the application can restart them in an orderly
+	 * manner.
+	 */
+	dice_owner_update(dice);
+	amdtp_out_stream_pcm_abort(&dice->stream);
+	dice_stop_stream(dice);
+	mutex_unlock(&dice->mutex);
+}
+
+#define TC_OUI		0x000166
+#define DICE_INTERFACE	0x000001
+
+static const struct ieee1394_device_id dice_id_table[] = {
+	{
+		.match_flags  = IEEE1394_MATCH_SPECIFIER_ID |
+				IEEE1394_MATCH_VERSION,
+		.specifier_id = TC_OUI,
+		.version      = DICE_INTERFACE,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(ieee1394, dice_id_table);
+
+static struct fw_driver dice_driver = {
+	.driver   = {
+		.owner	= THIS_MODULE,
+		.name	= KBUILD_MODNAME,
+		.bus	= &fw_bus_type,
+	},
+	.probe    = dice_probe,
+	.update   = dice_bus_reset,
+	.remove   = dice_remove,
+	.id_table = dice_id_table,
+};
+
+static int __init alsa_dice_init(void)
+{
+	return driver_register(&dice_driver.driver);
+}
+
+static void __exit alsa_dice_exit(void)
+{
+	driver_unregister(&dice_driver.driver);
+}
+
+module_init(alsa_dice_init);
+module_exit(alsa_dice_exit);
-- 
cgit 


From 146c8a77d27bcbd7722120f70f51e3b287205d0a Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Wed, 16 Oct 2013 17:50:28 +0100
Subject: xen-netback: add support for IPv6 checksum offload to guest

Check xenstore flag feature-ipv6-csum-offload to determine if a
guest is happy to accept IPv6 packets with only partial checksum.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/common.h    |  3 ++-
 drivers/net/xen-netback/interface.c | 10 +++++++---
 drivers/net/xen-netback/xenbus.c    |  7 ++++++-
 include/xen/interface/io/netif.h    |  7 +++++++
 4 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 5715318d6bab..b4a9a3c844b2 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -153,7 +153,8 @@ struct xenvif {
 	u8 can_sg:1;
 	u8 gso:1;
 	u8 gso_prefix:1;
-	u8 csum:1;
+	u8 ip_csum:1;
+	u8 ipv6_csum:1;
 
 	/* Internal feature information. */
 	u8 can_queue:1;	    /* can queue packets for receiver? */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 01bb854c7f62..8e927838652c 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -216,8 +216,10 @@ static netdev_features_t xenvif_fix_features(struct net_device *dev,
 		features &= ~NETIF_F_SG;
 	if (!vif->gso && !vif->gso_prefix)
 		features &= ~NETIF_F_TSO;
-	if (!vif->csum)
+	if (!vif->ip_csum)
 		features &= ~NETIF_F_IP_CSUM;
+	if (!vif->ipv6_csum)
+		features &= ~NETIF_F_IPV6_CSUM;
 
 	return features;
 }
@@ -306,7 +308,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->domid  = domid;
 	vif->handle = handle;
 	vif->can_sg = 1;
-	vif->csum = 1;
+	vif->ip_csum = 1;
 	vif->dev = dev;
 
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
@@ -316,7 +318,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->credit_timeout.expires = jiffies;
 
 	dev->netdev_ops	= &xenvif_netdev_ops;
-	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
+	dev->hw_features = NETIF_F_SG |
+		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+		NETIF_F_TSO;
 	dev->features = dev->hw_features;
 	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
 
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 1b08d8798372..ad27b15242cd 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -574,7 +574,12 @@ static int connect_rings(struct backend_info *be)
 	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
 			 "%d", &val) < 0)
 		val = 0;
-	vif->csum = !val;
+	vif->ip_csum = !val;
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->ipv6_csum = !!val;
 
 	/* Map the shared frame, irq etc. */
 	err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref,
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index eb262e3324d2..c9e81849fcd7 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -50,6 +50,13 @@
  * node as before.
  */
 
+/*
+ * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum
+ * offload off or on. If it is missing then the feature is assumed to be on.
+ * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum
+ * offload on or off. If it is missing then the feature is assumed to be off.
+ */
+
 /*
  * This is the 'wire' format for packets:
  *  Request 1: xen_netif_tx_request  -- XEN_NETTXF_* (any flags)
-- 
cgit 


From a94685876859be30446357db6d6c4a9c951305b4 Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Wed, 16 Oct 2013 17:50:31 +0100
Subject: xen-netback: handle IPv6 TCP GSO packets from the guest

This patch adds a xenstore feature flag, festure-gso-tcpv6, to advertise
that netback can handle IPv6 TCP GSO packets. It creates SKB_GSO_TCPV6 skbs
if the frontend passes an extra segment with the new type
XEN_NETIF_GSO_TYPE_TCPV6 added to netif.h.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 11 ++++++++---
 drivers/net/xen-netback/xenbus.c  |  7 +++++++
 include/xen/interface/io/netif.h  | 10 +++++++++-
 3 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 4271f8d1da7a..0e327d46a139 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1098,15 +1098,20 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
 		return -EINVAL;
 	}
 
-	/* Currently only TCPv4 S.O. is supported. */
-	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
+	switch (gso->u.gso.type) {
+	case XEN_NETIF_GSO_TYPE_TCPV4:
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+		break;
+	case XEN_NETIF_GSO_TYPE_TCPV6:
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+		break;
+	default:
 		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
 		xenvif_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
 	skb_shinfo(skb)->gso_size = gso->u.gso.size;
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 
 	/* Header must be checked, and gso_segs computed. */
 	skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 108e7523017a..02cb00bebdc9 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -105,6 +105,13 @@ static int netback_probe(struct xenbus_device *dev,
 			goto abort_transaction;
 		}
 
+		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6",
+				    "%d", sg);
+		if (err) {
+			message = "writing feature-gso-tcpv6";
+			goto abort_transaction;
+		}
+
 		/* We support partial checksum setup for IPv6 packets */
 		err = xenbus_printf(xbt, dev->nodename,
 				    "feature-ipv6-csum-offload",
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index c9e81849fcd7..5e766ebe77f6 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -57,6 +57,13 @@
  * offload on or off. If it is missing then the feature is assumed to be off.
  */
 
+/*
+ * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to
+ * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither
+ * frontends nor backends are assumed to be capable unless the flags are
+ * present.
+ */
+
 /*
  * This is the 'wire' format for packets:
  *  Request 1: xen_netif_tx_request  -- XEN_NETTXF_* (any flags)
@@ -102,8 +109,9 @@ struct xen_netif_tx_request {
 #define _XEN_NETIF_EXTRA_FLAG_MORE	(0)
 #define  XEN_NETIF_EXTRA_FLAG_MORE	(1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
 
-/* GSO types - only TCPv4 currently supported. */
+/* GSO types */
 #define XEN_NETIF_GSO_TYPE_TCPV4	(1)
+#define XEN_NETIF_GSO_TYPE_TCPV6	(2)
 
 /*
  * This structure needs to fit within both netif_tx_request and
-- 
cgit 


From 82cada22a0bbec6a7afb573ef5fb6c512aaa2739 Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Wed, 16 Oct 2013 17:50:32 +0100
Subject: xen-netback: enable IPv6 TCP GSO to the guest

This patch adds code to handle SKB_GSO_TCPV6 skbs and construct appropriate
extra or prefix segments to pass the large packet to the frontend. New
xenstore flags, feature-gso-tcpv6 and feature-gso-tcpv6-prefix, are sampled
to determine if the frontend is capable of handling such packets.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/common.h    |  9 +++++--
 drivers/net/xen-netback/interface.c |  6 +++--
 drivers/net/xen-netback/netback.c   | 48 +++++++++++++++++++++++++++++--------
 drivers/net/xen-netback/xenbus.c    | 29 ++++++++++++++++++++--
 include/xen/interface/io/netif.h    |  1 +
 5 files changed, 77 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index b4a9a3c844b2..55b8dec86233 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -87,9 +87,13 @@ struct pending_tx_info {
 struct xenvif_rx_meta {
 	int id;
 	int size;
+	int gso_type;
 	int gso_size;
 };
 
+#define GSO_BIT(type) \
+	(1 << XEN_NETIF_GSO_TYPE_ ## type)
+
 /* Discriminate from any valid pending_idx value. */
 #define INVALID_PENDING_IDX 0xFFFF
 
@@ -150,9 +154,10 @@ struct xenvif {
 	u8               fe_dev_addr[6];
 
 	/* Frontend feature information. */
+	int gso_mask;
+	int gso_prefix_mask;
+
 	u8 can_sg:1;
-	u8 gso:1;
-	u8 gso_prefix:1;
 	u8 ip_csum:1;
 	u8 ipv6_csum:1;
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index cb0d8ea3d9f2..e4aa26748f80 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -214,8 +214,10 @@ static netdev_features_t xenvif_fix_features(struct net_device *dev,
 
 	if (!vif->can_sg)
 		features &= ~NETIF_F_SG;
-	if (!vif->gso && !vif->gso_prefix)
+	if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4))
 		features &= ~NETIF_F_TSO;
+	if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6))
+		features &= ~NETIF_F_TSO6;
 	if (!vif->ip_csum)
 		features &= ~NETIF_F_IP_CSUM;
 	if (!vif->ipv6_csum)
@@ -320,7 +322,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		NETIF_F_TSO;
+		NETIF_F_TSO | NETIF_F_TSO6;
 	dev->features = dev->hw_features | NETIF_F_RXCSUM;
 	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 0e327d46a139..828fdab4f1a4 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -142,7 +142,7 @@ static int max_required_rx_slots(struct xenvif *vif)
 	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);
 
 	/* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */
-	if (vif->can_sg || vif->gso || vif->gso_prefix)
+	if (vif->can_sg || vif->gso_mask || vif->gso_prefix_mask)
 		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */
 
 	return max;
@@ -314,6 +314,7 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
 	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
 
 	meta = npo->meta + npo->meta_prod++;
+	meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
 	meta->gso_size = 0;
 	meta->size = 0;
 	meta->id = req->id;
@@ -336,6 +337,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 	struct gnttab_copy *copy_gop;
 	struct xenvif_rx_meta *meta;
 	unsigned long bytes;
+	int gso_type;
 
 	/* Data must not cross a page boundary. */
 	BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));
@@ -394,7 +396,14 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 		}
 
 		/* Leave a gap for the GSO descriptor. */
-		if (*head && skb_shinfo(skb)->gso_size && !vif->gso_prefix)
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+		else
+			gso_type = XEN_NETIF_GSO_TYPE_NONE;
+
+		if (*head && ((1 << gso_type) & vif->gso_mask))
 			vif->rx.req_cons++;
 
 		*head = 0; /* There must be something in this buffer now. */
@@ -425,14 +434,28 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	unsigned char *data;
 	int head = 1;
 	int old_meta_prod;
+	int gso_type;
+	int gso_size;
 
 	old_meta_prod = npo->meta_prod;
 
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
+		gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+		gso_size = skb_shinfo(skb)->gso_size;
+	} else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) {
+		gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+		gso_size = skb_shinfo(skb)->gso_size;
+	} else {
+		gso_type = XEN_NETIF_GSO_TYPE_NONE;
+		gso_size = 0;
+	}
+
 	/* Set up a GSO prefix descriptor, if necessary */
-	if (skb_shinfo(skb)->gso_size && vif->gso_prefix) {
+	if ((1 << skb_shinfo(skb)->gso_type) & vif->gso_prefix_mask) {
 		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
 		meta = npo->meta + npo->meta_prod++;
-		meta->gso_size = skb_shinfo(skb)->gso_size;
+		meta->gso_type = gso_type;
+		meta->gso_size = gso_size;
 		meta->size = 0;
 		meta->id = req->id;
 	}
@@ -440,10 +463,13 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
 	meta = npo->meta + npo->meta_prod++;
 
-	if (!vif->gso_prefix)
-		meta->gso_size = skb_shinfo(skb)->gso_size;
-	else
+	if ((1 << gso_type) & vif->gso_mask) {
+		meta->gso_type = gso_type;
+		meta->gso_size = gso_size;
+	} else {
+		meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
 		meta->gso_size = 0;
+	}
 
 	meta->size = 0;
 	meta->id = req->id;
@@ -589,7 +615,8 @@ void xenvif_rx_action(struct xenvif *vif)
 
 		vif = netdev_priv(skb->dev);
 
-		if (vif->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
+		if ((1 << vif->meta[npo.meta_cons].gso_type) &
+		    vif->gso_prefix_mask) {
 			resp = RING_GET_RESPONSE(&vif->rx,
 						 vif->rx.rsp_prod_pvt++);
 
@@ -626,7 +653,8 @@ void xenvif_rx_action(struct xenvif *vif)
 					vif->meta[npo.meta_cons].size,
 					flags);
 
-		if (vif->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
+		if ((1 << vif->meta[npo.meta_cons].gso_type) &
+		    vif->gso_mask) {
 			struct xen_netif_extra_info *gso =
 				(struct xen_netif_extra_info *)
 				RING_GET_RESPONSE(&vif->rx,
@@ -634,8 +662,8 @@ void xenvif_rx_action(struct xenvif *vif)
 
 			resp->flags |= XEN_NETRXF_extra_info;
 
+			gso->u.gso.type = vif->meta[npo.meta_cons].gso_type;
 			gso->u.gso.size = vif->meta[npo.meta_cons].gso_size;
-			gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
 			gso->u.gso.pad = 0;
 			gso->u.gso.features = 0;
 
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 02cb00bebdc9..f0358992b04f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -577,15 +577,40 @@ static int connect_rings(struct backend_info *be)
 		val = 0;
 	vif->can_sg = !!val;
 
+	vif->gso_mask = 0;
+	vif->gso_prefix_mask = 0;
+
 	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4",
 			 "%d", &val) < 0)
 		val = 0;
-	vif->gso = !!val;
+	if (val)
+		vif->gso_mask |= GSO_BIT(TCPV4);
 
 	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix",
 			 "%d", &val) < 0)
 		val = 0;
-	vif->gso_prefix = !!val;
+	if (val)
+		vif->gso_prefix_mask |= GSO_BIT(TCPV4);
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_mask |= GSO_BIT(TCPV6);
+
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix",
+			 "%d", &val) < 0)
+		val = 0;
+	if (val)
+		vif->gso_prefix_mask |= GSO_BIT(TCPV6);
+
+	if (vif->gso_mask & vif->gso_prefix_mask) {
+		xenbus_dev_fatal(dev, err,
+				 "%s: gso and gso prefix flags are not "
+				 "mutually exclusive",
+				 dev->otherend);
+		return -EOPNOTSUPP;
+	}
 
 	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
 			 "%d", &val) < 0)
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index 5e766ebe77f6..c50061db6098 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -110,6 +110,7 @@ struct xen_netif_tx_request {
 #define  XEN_NETIF_EXTRA_FLAG_MORE	(1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
 
 /* GSO types */
+#define XEN_NETIF_GSO_TYPE_NONE		(0)
 #define XEN_NETIF_GSO_TYPE_TCPV4	(1)
 #define XEN_NETIF_GSO_TYPE_TCPV6	(2)
 
-- 
cgit 


From a5bb202b848c7962f942f81d93290a9ccdfb1a0f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2013 12:36:32 -0700
Subject: netdev: inet_timewait_sock.h missing semi-colon when KMEMCHECK is
 enabled

Fix (a few hundred) build errors due to missing semi-colon when
KMEMCHECK is enabled:

  include/net/inet_timewait_sock.h:139:2: error: expected ',', ';' or '}' before 'int'
  include/net/inet_timewait_sock.h:148:28: error: 'const struct inet_timewait_sock' has no member named 'tw_death_node'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_timewait_sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index b647c6270eb7..71c6e264e5b5 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -135,7 +135,7 @@ struct inet_timewait_sock {
 				tw_transparent  : 1,
 				tw_pad		: 6,	/* 6 bits hole */
 				tw_tos		: 8,
-				tw_pad2		: 16 /* 16 bits hole */
+				tw_pad2		: 16;	/* 16 bits hole */
 	kmemcheck_bitfield_end(flags);
 	u32			tw_ttd;
 	struct inet_bind_bucket	*tw_tb;
-- 
cgit 


From 0baf2b35fc70ab16c385963d2502da26a55d2cb7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Oct 2013 02:49:04 -0700
Subject: ipv4: shrink rt_cache_stat

Half of the rt_cache_stat fields are no longer used after IP
route cache removal, lets shrink this per cpu area.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h |  8 --------
 net/ipv4/route.c    | 16 ++++++++--------
 2 files changed, 8 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index 0ad8e0102386..dd4ae0029fd8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -88,22 +88,14 @@ struct ip_rt_acct {
 };
 
 struct rt_cache_stat {
-        unsigned int in_hit;
         unsigned int in_slow_tot;
         unsigned int in_slow_mc;
         unsigned int in_no_route;
         unsigned int in_brd;
         unsigned int in_martian_dst;
         unsigned int in_martian_src;
-        unsigned int out_hit;
         unsigned int out_slow_tot;
         unsigned int out_slow_mc;
-        unsigned int gc_total;
-        unsigned int gc_ignored;
-        unsigned int gc_goal_miss;
-        unsigned int gc_dst_overflow;
-        unsigned int in_hlist_search;
-        unsigned int out_hlist_search;
 };
 
 extern struct ip_rt_acct __percpu *ip_rt_acct;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6011615e810d..d2d325382b13 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -295,7 +295,7 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq,"%08x  %08x %08x %08x %08x %08x %08x %08x "
 		   " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
 		   dst_entries_get_slow(&ipv4_dst_ops),
-		   st->in_hit,
+		   0, /* st->in_hit */
 		   st->in_slow_tot,
 		   st->in_slow_mc,
 		   st->in_no_route,
@@ -303,16 +303,16 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v)
 		   st->in_martian_dst,
 		   st->in_martian_src,
 
-		   st->out_hit,
+		   0, /* st->out_hit */
 		   st->out_slow_tot,
 		   st->out_slow_mc,
 
-		   st->gc_total,
-		   st->gc_ignored,
-		   st->gc_goal_miss,
-		   st->gc_dst_overflow,
-		   st->in_hlist_search,
-		   st->out_hlist_search
+		   0, /* st->gc_total */
+		   0, /* st->gc_ignored */
+		   0, /* st->gc_goal_miss */
+		   0, /* st->gc_dst_overflow */
+		   0, /* st->in_hlist_search */
+		   0  /* st->out_hlist_search */
 		);
 	return 0;
 }
-- 
cgit 


From 731d9cae0204a8948c7db2f551edcd5d5822ed95 Mon Sep 17 00:00:00 2001
From: Nicolas Ferre <nicolas.ferre@atmel.com>
Date: Thu, 17 Oct 2013 17:37:12 +0200
Subject: tty/serial: at91: add a fallback option to determine uart/usart
 property

On older SoC, the "name" field is not filled in the register map.
Fix the way to figure out if the serial port is an uart or an usart for these
older products (with corresponding properties).

Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/atmel_serial.c | 19 ++++++++++++++++++-
 include/linux/atmel_serial.h      |  1 +
 2 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 6b0f75eac8a2..c7d99af46a96 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -99,6 +99,7 @@ static void atmel_stop_rx(struct uart_port *port);
 #define UART_PUT_RTOR(port,v)	__raw_writel(v, (port)->membase + ATMEL_US_RTOR)
 #define UART_PUT_TTGR(port, v)	__raw_writel(v, (port)->membase + ATMEL_US_TTGR)
 #define UART_GET_IP_NAME(port)	__raw_readl((port)->membase + ATMEL_US_NAME)
+#define UART_GET_IP_VERSION(port) __raw_readl((port)->membase + ATMEL_US_VERSION)
 
  /* PDC registers */
 #define UART_PUT_PTCR(port,v)	__raw_writel(v, (port)->membase + ATMEL_PDC_PTCR)
@@ -1503,6 +1504,7 @@ static void atmel_get_ip_name(struct uart_port *port)
 {
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
 	int name = UART_GET_IP_NAME(port);
+	u32 version;
 	int usart, uart;
 	/* usart and uart ascii */
 	usart = 0x55534152;
@@ -1517,7 +1519,22 @@ static void atmel_get_ip_name(struct uart_port *port)
 		dev_dbg(port->dev, "This is uart\n");
 		atmel_port->is_usart = false;
 	} else {
-		dev_err(port->dev, "Not supported ip name, set to uart\n");
+		/* fallback for older SoCs: use version field */
+		version = UART_GET_IP_VERSION(port);
+		switch (version) {
+		case 0x302:
+		case 0x10213:
+			dev_dbg(port->dev, "This version is usart\n");
+			atmel_port->is_usart = true;
+			break;
+		case 0x203:
+		case 0x10202:
+			dev_dbg(port->dev, "This version is uart\n");
+			atmel_port->is_usart = false;
+			break;
+		default:
+			dev_err(port->dev, "Not supported ip name nor version, set to uart\n");
+		}
 	}
 }
 
diff --git a/include/linux/atmel_serial.h b/include/linux/atmel_serial.h
index be201ca2990c..00beddf6be20 100644
--- a/include/linux/atmel_serial.h
+++ b/include/linux/atmel_serial.h
@@ -125,5 +125,6 @@
 #define ATMEL_US_IF		0x4c			/* IrDA Filter Register */
 
 #define ATMEL_US_NAME		0xf0			/* Ip Name */
+#define ATMEL_US_VERSION	0xfc			/* Ip Version */
 
 #endif
-- 
cgit 


From 40a96d54ee2232045783e657eb9224cd723dcb40 Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Thu, 17 Oct 2013 15:35:36 -0700
Subject: intel_mid: Move platform device setups to their own
 platform_<device>.* files

As Intel rolling out more SoC's after Moorestown, we need to
re-structure the code in a way that is backward compatible and easy to
expand. This patch implements a flexible way to support multiple boards
and devices.

This patch does not add any new functional support. It just refactors
the existing code to increase the modularity and decrease the code
duplication for supporting multiple soc's and boards.

Currently intel-mid.c has both board and soc related code in one file.
This patch moves the board related code to new files and let linker
script to create SFI devite table following this:

1. Move the SFI device specific code to
   arch/x86/platform/intel-mid/device-libs/platform_<device>.*
   A new device file is added for every supported device. This code will
   get conditionally compiled by using corresponding device driver
   CONFIG option.

2. Move the device_ids location to .x86_intel_mid_dev.init section by
   using new sfi_device() macro.

This patch was based on previous code from Sathyanarayanan Kuppuswamy.

Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: http://lkml.kernel.org/r/1382049336-21316-13-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/include/asm/intel-mid.h                   |  16 +
 arch/x86/platform/intel-mid/Makefile               |   8 +-
 arch/x86/platform/intel-mid/device_libs/Makefile   |  22 ++
 .../intel-mid/device_libs/platform_bma023.c        |  20 +
 .../intel-mid/device_libs/platform_emc1403.c       |  41 ++
 .../intel-mid/device_libs/platform_gpio_keys.c     |  83 ++++
 .../platform/intel-mid/device_libs/platform_ipc.c  |  68 ++++
 .../platform/intel-mid/device_libs/platform_ipc.h  |  17 +
 .../intel-mid/device_libs/platform_lis331.c        |  39 ++
 .../intel-mid/device_libs/platform_max3111.c       |  35 ++
 .../intel-mid/device_libs/platform_max7315.c       |  79 ++++
 .../intel-mid/device_libs/platform_mpu3050.c       |  36 ++
 .../platform/intel-mid/device_libs/platform_msic.c |  87 +++++
 .../platform/intel-mid/device_libs/platform_msic.h |  19 +
 .../intel-mid/device_libs/platform_msic_audio.c    |  47 +++
 .../intel-mid/device_libs/platform_msic_battery.c  |  37 ++
 .../intel-mid/device_libs/platform_msic_gpio.c     |  48 +++
 .../intel-mid/device_libs/platform_msic_ocd.c      |  49 +++
 .../device_libs/platform_msic_power_btn.c          |  36 ++
 .../intel-mid/device_libs/platform_msic_thermal.c  |  37 ++
 .../intel-mid/device_libs/platform_pmic_gpio.c     |  54 +++
 .../intel-mid/device_libs/platform_tc35876x.c      |  36 ++
 .../intel-mid/device_libs/platform_tca6416.c       |  57 +++
 arch/x86/platform/intel-mid/intel-mid.c            | 419 ---------------------
 arch/x86/platform/intel-mid/sfi.c                  |  14 +-
 include/linux/sfi.h                                |   3 +
 26 files changed, 978 insertions(+), 429 deletions(-)
 create mode 100644 arch/x86/platform/intel-mid/device_libs/Makefile
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_bma023.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_ipc.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_ipc.h
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_lis331.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_max3111.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_max7315.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic.h
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
 create mode 100644 arch/x86/platform/intel-mid/device_libs/platform_tca6416.c

(limited to 'include')

diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 3b0e7a771cb5..459769d39263 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -12,8 +12,11 @@
 #define _ASM_X86_INTEL_MID_H
 
 #include <linux/sfi.h>
+#include <linux/platform_device.h>
 
 extern int intel_mid_pci_init(void);
+extern int get_gpio_by_name(const char *name);
+extern void intel_scu_device_register(struct platform_device *pdev);
 extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
 extern int __init sfi_parse_mtmr(struct sfi_table_header *table);
 extern int sfi_mrtc_num;
@@ -34,6 +37,10 @@ struct devs_id {
 				struct devs_id *dev);
 };
 
+#define sfi_device(i)   \
+	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \
+	__attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
+
 /*
  * Medfield is the follow-up of Moorestown, it combines two chip solution into
  * one. Other than that it also added always-on and constant tsc and lapic
@@ -55,9 +62,15 @@ static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
 	return __intel_mid_cpu_chip;
 }
 
+static inline bool intel_mid_has_msic(void)
+{
+	return (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL);
+}
+
 #else /* !CONFIG_X86_INTEL_MID */
 
 #define intel_mid_identify_cpu()    (0)
+#define intel_mid_has_msic()    (0)
 
 #endif /* !CONFIG_X86_INTEL_MID */
 
@@ -94,4 +107,7 @@ extern void intel_scu_devices_destroy(void);
 
 extern void intel_mid_rtc_init(void);
 
+/* the offset for the mapping of global gpio pin to irq */
+#define INTEL_MID_IRQ_OFFSET 0x100
+
 #endif /* _ASM_X86_INTEL_MID_H */
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index b11e5b2de336..01cc29ea5ff7 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,5 +1,7 @@
 obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o
-obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_vrtc.o
-obj-$(CONFIG_EARLY_PRINTK_INTEL_MID)	+= early_printk_intel_mid.o
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid_vrtc.o
+obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_intel_mid.o
 # SFI specific code
-obj-$(CONFIG_SFI) += sfi.o
+ifdef CONFIG_X86_INTEL_MID
+obj-$(CONFIG_SFI) += sfi.o device_libs/
+endif
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
new file mode 100644
index 000000000000..097e7a7940d8
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -0,0 +1,22 @@
+# IPC Devices
+obj-y += platform_ipc.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
+obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o
+obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o
+obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
+obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
+# I2C Devices
+obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
+obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o
+obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_max7315.o
+obj-$(subst m,y,$(CONFIG_INPUT_MPU3050)) += platform_mpu3050.o
+obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o
+obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
+obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o
+# SPI Devices
+obj-$(subst m,y,$(CONFIG_SERIAL_MRST_MAX3110)) += platform_max3111.o
+# MISC Devices
+obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c
new file mode 100644
index 000000000000..0ae7f2ae2296
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c
@@ -0,0 +1,20 @@
+/*
+ * platform_bma023.c: bma023 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <asm/intel-mid.h>
+
+static const struct devs_id bma023_dev_id __initconst = {
+	.name = "bma023",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+};
+
+sfi_device(bma023_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
new file mode 100644
index 000000000000..0d942c1d26d5
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
@@ -0,0 +1,41 @@
+/*
+ * platform_emc1403.c: emc1403 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <asm/intel-mid.h>
+
+static void __init *emc1403_platform_data(void *info)
+{
+	static short intr2nd_pdata;
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("thermal_int");
+	int intr2nd = get_gpio_by_name("thermal_alert");
+
+	if (intr == -1 || intr2nd == -1)
+		return NULL;
+
+	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+	intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
+
+	return &intr2nd_pdata;
+}
+
+static const struct devs_id emc1403_dev_id __initconst = {
+	.name = "emc1403",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+	.get_platform_data = &emc1403_platform_data,
+};
+
+sfi_device(emc1403_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
new file mode 100644
index 000000000000..a013a4834bbe
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
@@ -0,0 +1,83 @@
+/*
+ * platform_gpio_keys.c: gpio_keys platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/input.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_keys.h>
+#include <linux/platform_device.h>
+#include <asm/intel-mid.h>
+
+#define DEVICE_NAME "gpio-keys"
+
+/*
+ * we will search these buttons in SFI GPIO table (by name)
+ * and register them dynamically. Please add all possible
+ * buttons here, we will shrink them if no GPIO found.
+ */
+static struct gpio_keys_button gpio_button[] = {
+	{KEY_POWER,		-1, 1, "power_btn",	EV_KEY, 0, 3000},
+	{KEY_PROG1,		-1, 1, "prog_btn1",	EV_KEY, 0, 20},
+	{KEY_PROG2,		-1, 1, "prog_btn2",	EV_KEY, 0, 20},
+	{SW_LID,		-1, 1, "lid_switch",	EV_SW,  0, 20},
+	{KEY_VOLUMEUP,		-1, 1, "vol_up",	EV_KEY, 0, 20},
+	{KEY_VOLUMEDOWN,	-1, 1, "vol_down",	EV_KEY, 0, 20},
+	{KEY_CAMERA,		-1, 1, "camera_full",	EV_KEY, 0, 20},
+	{KEY_CAMERA_FOCUS,	-1, 1, "camera_half",	EV_KEY, 0, 20},
+	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw1",	EV_SW,  0, 20},
+	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw2",	EV_SW,  0, 20},
+};
+
+static struct gpio_keys_platform_data gpio_keys = {
+	.buttons	= gpio_button,
+	.rep		= 1,
+	.nbuttons	= -1, /* will fill it after search */
+};
+
+static struct platform_device pb_device = {
+	.name		= DEVICE_NAME,
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &gpio_keys,
+	},
+};
+
+/*
+ * Shrink the non-existent buttons, register the gpio button
+ * device if there is some
+ */
+static int __init pb_keys_init(void)
+{
+	struct gpio_keys_button *gb = gpio_button;
+	int i, num, good = 0;
+
+	num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
+	for (i = 0; i < num; i++) {
+		gb[i].gpio = get_gpio_by_name(gb[i].desc);
+		pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc,
+					gb[i].gpio);
+		if (gb[i].gpio == -1)
+			continue;
+
+		if (i != good)
+			gb[good] = gb[i];
+		good++;
+	}
+
+	if (good) {
+		gpio_keys.nbuttons = good;
+		return platform_device_register(&pb_device);
+	}
+	return 0;
+}
+late_initcall(pb_keys_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
new file mode 100644
index 000000000000..a84b73d6c4a0
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
@@ -0,0 +1,68 @@
+/*
+ * platform_ipc.c: IPC platform library file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/sfi.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+#include "platform_ipc.h"
+
+void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
+				struct devs_id *dev)
+{
+	struct platform_device *pdev;
+	void *pdata = NULL;
+	static struct resource res __initdata = {
+		.name = "IRQ",
+		.flags = IORESOURCE_IRQ,
+	};
+
+	pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
+		pentry->name, pentry->irq);
+
+	/*
+	 * We need to call platform init of IPC devices to fill misc_pdata
+	 * structure. It will be used in msic_init for initialization.
+	 */
+	if (dev != NULL)
+		pdata = dev->get_platform_data(pentry);
+
+	/*
+	 * On Medfield the platform device creation is handled by the MSIC
+	 * MFD driver so we don't need to do it here.
+	 */
+	if (intel_mid_has_msic())
+		return;
+
+	pdev = platform_device_alloc(pentry->name, 0);
+	if (pdev == NULL) {
+		pr_err("out of memory for SFI platform device '%s'.\n",
+			pentry->name);
+		return;
+	}
+	res.start = pentry->irq;
+	platform_device_add_resources(pdev, &res, 1);
+
+	pdev->dev.platform_data = pdata;
+	intel_scu_device_register(pdev);
+}
+
+static const struct devs_id pmic_audio_dev_id __initconst = {
+	.name = "pmic_audio",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(pmic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
new file mode 100644
index 000000000000..8f568dd79605
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
@@ -0,0 +1,17 @@
+/*
+ * platform_ipc.h: IPC platform library header file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _PLATFORM_IPC_H_
+#define _PLATFORM_IPC_H_
+
+extern void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
+			struct devs_id *dev) __attribute__((weak));
+#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
new file mode 100644
index 000000000000..15278c11f714
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
@@ -0,0 +1,39 @@
+/*
+ * platform_lis331.c:  lis331 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+
+static void __init *lis331dl_platform_data(void *info)
+{
+	static short intr2nd_pdata;
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("accel_int");
+	int intr2nd = get_gpio_by_name("accel_2");
+
+	if (intr == -1 || intr2nd == -1)
+		return NULL;
+
+	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+	intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
+
+	return &intr2nd_pdata;
+}
+
+static const struct devs_id lis331dl_dev_id __initconst = {
+	.name = "i2c_accel",
+	.type = SFI_DEV_TYPE_I2C,
+	.get_platform_data = &lis331dl_platform_data,
+};
+
+sfi_device(lis331dl_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max3111.c b/arch/x86/platform/intel-mid/device_libs/platform_max3111.c
new file mode 100644
index 000000000000..afd1df94e0e5
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_max3111.c
@@ -0,0 +1,35 @@
+/*
+ * platform_max3111.c: max3111 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/gpio.h>
+#include <linux/spi/spi.h>
+#include <asm/intel-mid.h>
+
+static void __init *max3111_platform_data(void *info)
+{
+	struct spi_board_info *spi_info = info;
+	int intr = get_gpio_by_name("max3111_int");
+
+	spi_info->mode = SPI_MODE_0;
+	if (intr == -1)
+		return NULL;
+	spi_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+	return NULL;
+}
+
+static const struct devs_id max3111_dev_id __initconst = {
+	.name = "spi_max3111",
+	.type = SFI_DEV_TYPE_SPI,
+	.get_platform_data = &max3111_platform_data,
+};
+
+sfi_device(max3111_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
new file mode 100644
index 000000000000..94ade10024ae
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
@@ -0,0 +1,79 @@
+/*
+ * platform_max7315.c: max7315 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/platform_data/pca953x.h>
+#include <asm/intel-mid.h>
+
+#define MAX7315_NUM 2
+
+static void __init *max7315_platform_data(void *info)
+{
+	static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
+	static int nr;
+	struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
+	struct i2c_board_info *i2c_info = info;
+	int gpio_base, intr;
+	char base_pin_name[SFI_NAME_LEN + 1];
+	char intr_pin_name[SFI_NAME_LEN + 1];
+
+	if (nr == MAX7315_NUM) {
+		pr_err("too many max7315s, we only support %d\n",
+				MAX7315_NUM);
+		return NULL;
+	}
+	/* we have several max7315 on the board, we only need load several
+	 * instances of the same pca953x driver to cover them
+	 */
+	strcpy(i2c_info->type, "max7315");
+	if (nr++) {
+		sprintf(base_pin_name, "max7315_%d_base", nr);
+		sprintf(intr_pin_name, "max7315_%d_int", nr);
+	} else {
+		strcpy(base_pin_name, "max7315_base");
+		strcpy(intr_pin_name, "max7315_int");
+	}
+
+	gpio_base = get_gpio_by_name(base_pin_name);
+	intr = get_gpio_by_name(intr_pin_name);
+
+	if (gpio_base == -1)
+		return NULL;
+	max7315->gpio_base = gpio_base;
+	if (intr != -1) {
+		i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+		max7315->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+	} else {
+		i2c_info->irq = -1;
+		max7315->irq_base = -1;
+	}
+	return max7315;
+}
+
+static const struct devs_id max7315_dev_id __initconst = {
+	.name = "i2c_max7315",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+	.get_platform_data = &max7315_platform_data,
+};
+
+static const struct devs_id max7315_2_dev_id __initconst = {
+	.name = "i2c_max7315_2",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+	.get_platform_data = &max7315_platform_data,
+};
+
+sfi_device(max7315_dev_id);
+sfi_device(max7315_2_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
new file mode 100644
index 000000000000..dd28d63c84fb
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
@@ -0,0 +1,36 @@
+/*
+ * platform_mpu3050.c: mpu3050 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <asm/intel-mid.h>
+
+static void *mpu3050_platform_data(void *info)
+{
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("mpu3050_int");
+
+	if (intr == -1)
+		return NULL;
+
+	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+	return NULL;
+}
+
+static const struct devs_id mpu3050_dev_id __initconst = {
+	.name = "mpu3050",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+	.get_platform_data = &mpu3050_platform_data,
+};
+
+sfi_device(mpu3050_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.c b/arch/x86/platform/intel-mid/device_libs/platform_msic.c
new file mode 100644
index 000000000000..9f4a775a69d6
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic.c
@@ -0,0 +1,87 @@
+/*
+ * platform_msic.c: MSIC platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel_scu_ipc.h>
+#include <asm/intel-mid.h>
+#include "platform_msic.h"
+
+struct intel_msic_platform_data msic_pdata;
+
+static struct resource msic_resources[] = {
+	{
+		.start	= INTEL_MSIC_IRQ_PHYS_BASE,
+		.end	= INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device msic_device = {
+	.name		= "intel_msic",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= &msic_pdata,
+	},
+	.num_resources	= ARRAY_SIZE(msic_resources),
+	.resource	= msic_resources,
+};
+
+static int msic_scu_status_change(struct notifier_block *nb,
+				  unsigned long code, void *data)
+{
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&msic_device);
+		return 0;
+	}
+
+	return platform_device_register(&msic_device);
+}
+
+static int __init msic_init(void)
+{
+	static struct notifier_block msic_scu_notifier = {
+		.notifier_call	= msic_scu_status_change,
+	};
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before MSIC device
+	 * can be registered.
+	 */
+	if (intel_mid_has_msic())
+		intel_scu_notifier_add(&msic_scu_notifier);
+
+	return 0;
+}
+arch_initcall(msic_init);
+
+/*
+ * msic_generic_platform_data - sets generic platform data for the block
+ * @info: pointer to the SFI device table entry for this block
+ * @block: MSIC block
+ *
+ * Function sets IRQ number from the SFI table entry for given device to
+ * the MSIC platform data.
+ */
+void *msic_generic_platform_data(void *info, enum intel_msic_block block)
+{
+	struct sfi_device_table_entry *entry = info;
+
+	BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST);
+	msic_pdata.irq[block] = entry->irq;
+
+	return NULL;
+}
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.h b/arch/x86/platform/intel-mid/device_libs/platform_msic.h
new file mode 100644
index 000000000000..917eb56d77da
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic.h
@@ -0,0 +1,19 @@
+/*
+ * platform_msic.h: MSIC platform data header file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _PLATFORM_MSIC_H_
+#define _PLATFORM_MSIC_H_
+
+extern struct intel_msic_platform_data msic_pdata;
+
+extern void *msic_generic_platform_data(void *info,
+			enum intel_msic_block block) __attribute__((weak));
+#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
new file mode 100644
index 000000000000..29629397d2b3
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
@@ -0,0 +1,47 @@
+/*
+ * platform_msic_audio.c: MSIC audio platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void *msic_audio_platform_data(void *info)
+{
+	struct platform_device *pdev;
+
+	pdev = platform_device_register_simple("sst-platform", -1, NULL, 0);
+
+	if (IS_ERR(pdev)) {
+		pr_err("failed to create audio platform device\n");
+		return NULL;
+	}
+
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO);
+}
+
+static const struct devs_id msic_audio_dev_id __initconst = {
+	.name = "msic_audio",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_audio_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
new file mode 100644
index 000000000000..f446c33df1a8
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
@@ -0,0 +1,37 @@
+/*
+ * platform_msic_battery.c: MSIC battery platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_battery_platform_data(void *info)
+{
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY);
+}
+
+static const struct devs_id msic_battery_dev_id __initconst = {
+	.name = "msic_battery",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_battery_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_battery_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
new file mode 100644
index 000000000000..2a4f7b1dd917
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
@@ -0,0 +1,48 @@
+/*
+ * platform_msic_gpio.c: MSIC GPIO platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_gpio_platform_data(void *info)
+{
+	static struct intel_msic_gpio_pdata msic_gpio_pdata;
+
+	int gpio = get_gpio_by_name("msic_gpio_base");
+
+	if (gpio < 0)
+		return NULL;
+
+	msic_gpio_pdata.gpio_base = gpio;
+	msic_pdata.gpio = &msic_gpio_pdata;
+
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO);
+}
+
+static const struct devs_id msic_gpio_dev_id __initconst = {
+	.name = "msic_gpio",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_gpio_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_gpio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
new file mode 100644
index 000000000000..6497111ddb54
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
@@ -0,0 +1,49 @@
+/*
+ * platform_msic_ocd.c: MSIC OCD platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_ocd_platform_data(void *info)
+{
+	static struct intel_msic_ocd_pdata msic_ocd_pdata;
+	int gpio;
+
+	gpio = get_gpio_by_name("ocd_gpio");
+
+	if (gpio < 0)
+		return NULL;
+
+	msic_ocd_pdata.gpio = gpio;
+	msic_pdata.ocd = &msic_ocd_pdata;
+
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD);
+}
+
+static const struct devs_id msic_ocd_dev_id __initconst = {
+	.name = "msic_ocd",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_ocd_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_ocd_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
new file mode 100644
index 000000000000..83a3459bc337
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
@@ -0,0 +1,36 @@
+/*
+ * platform_msic_power_btn.c: MSIC power btn platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_power_btn_platform_data(void *info)
+{
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN);
+}
+
+static const struct devs_id msic_power_btn_dev_id __initconst = {
+	.name = "msic_power_btn",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_power_btn_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
new file mode 100644
index 000000000000..a351878b96bc
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
@@ -0,0 +1,37 @@
+/*
+ * platform_msic_thermal.c: msic_thermal platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/input.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_thermal_platform_data(void *info)
+{
+	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL);
+}
+
+static const struct devs_id msic_thermal_dev_id __initconst = {
+	.name = "msic_thermal",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &msic_thermal_platform_data,
+	.device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_thermal_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
new file mode 100644
index 000000000000..d87182a09263
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
@@ -0,0 +1,54 @@
+/*
+ * platform_pmic_gpio.c: PMIC GPIO platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/intel_pmic_gpio.h>
+#include <asm/intel-mid.h>
+
+#include "platform_ipc.h"
+
+static void __init *pmic_gpio_platform_data(void *info)
+{
+	static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
+	int gpio_base = get_gpio_by_name("pmic_gpio_base");
+
+	if (gpio_base == -1)
+		gpio_base = 64;
+	pmic_gpio_pdata.gpio_base = gpio_base;
+	pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+	pmic_gpio_pdata.gpiointr = 0xffffeff8;
+
+	return &pmic_gpio_pdata;
+}
+
+static const struct devs_id pmic_gpio_spi_dev_id __initconst = {
+	.name = "pmic_gpio",
+	.type = SFI_DEV_TYPE_SPI,
+	.delay = 1,
+	.get_platform_data = &pmic_gpio_platform_data,
+};
+
+static const struct devs_id pmic_gpio_ipc_dev_id __initconst = {
+	.name = "pmic_gpio",
+	.type = SFI_DEV_TYPE_IPC,
+	.delay = 1,
+	.get_platform_data = &pmic_gpio_platform_data,
+	.device_handler = &ipc_device_handler
+};
+
+sfi_device(pmic_gpio_spi_dev_id);
+sfi_device(pmic_gpio_ipc_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
new file mode 100644
index 000000000000..740fc757050c
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
@@ -0,0 +1,36 @@
+/*
+ * platform_tc35876x.c: tc35876x platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/gpio.h>
+#include <linux/i2c/tc35876x.h>
+#include <asm/intel-mid.h>
+
+/*tc35876x DSI_LVDS bridge chip and panel platform data*/
+static void *tc35876x_platform_data(void *data)
+{
+	static struct tc35876x_platform_data pdata;
+
+	/* gpio pins set to -1 will not be used by the driver */
+	pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
+	pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
+	pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
+
+	return &pdata;
+}
+
+static const struct devs_id tc35876x_dev_id __initconst = {
+	.name = "i2c_disp_brig",
+	.type = SFI_DEV_TYPE_I2C,
+	.get_platform_data = &tc35876x_platform_data,
+};
+
+sfi_device(tc35876x_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
new file mode 100644
index 000000000000..22881c9a6737
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
@@ -0,0 +1,57 @@
+/*
+ * platform_tca6416.c: tca6416 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/platform_data/pca953x.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+
+#define TCA6416_NAME	"tca6416"
+#define TCA6416_BASE	"tca6416_base"
+#define TCA6416_INTR	"tca6416_int"
+
+static void *tca6416_platform_data(void *info)
+{
+	static struct pca953x_platform_data tca6416;
+	struct i2c_board_info *i2c_info = info;
+	int gpio_base, intr;
+	char base_pin_name[SFI_NAME_LEN + 1];
+	char intr_pin_name[SFI_NAME_LEN + 1];
+
+	strcpy(i2c_info->type, TCA6416_NAME);
+	strcpy(base_pin_name, TCA6416_BASE);
+	strcpy(intr_pin_name, TCA6416_INTR);
+
+	gpio_base = get_gpio_by_name(base_pin_name);
+	intr = get_gpio_by_name(intr_pin_name);
+
+	if (gpio_base == -1)
+		return NULL;
+	tca6416.gpio_base = gpio_base;
+	if (intr != -1) {
+		i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+		tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+	} else {
+		i2c_info->irq = -1;
+		tca6416.irq_base = -1;
+	}
+	return &tca6416;
+}
+
+static const struct devs_id tca6416_dev_id __initconst = {
+	.name = "tca6416",
+	.type = SFI_DEV_TYPE_I2C,
+	.delay = 1,
+	.get_platform_data = &tca6416_platform_data,
+};
+
+sfi_device(tca6416_dev_id);
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 40915698b9b7..523a1c8f7f07 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -61,8 +61,6 @@ enum intel_mid_timer_options intel_mid_timer_options;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
-static void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
-			struct devs_id *dev);
 static void intel_mid_power_off(void)
 {
 }
@@ -213,420 +211,3 @@ static inline int __init setup_x86_intel_mid_timer(char *arg)
 }
 __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer);
 
-/* the offset for the mapping of global gpio pin to irq */
-#define INTEL_MID_IRQ_OFFSET 0x100
-
-static void __init *pmic_gpio_platform_data(void *info)
-{
-	static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
-	int gpio_base = get_gpio_by_name("pmic_gpio_base");
-
-	if (gpio_base == -1)
-		gpio_base = 64;
-	pmic_gpio_pdata.gpio_base = gpio_base;
-	pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
-	pmic_gpio_pdata.gpiointr = 0xffffeff8;
-
-	return &pmic_gpio_pdata;
-}
-
-static void __init *max3111_platform_data(void *info)
-{
-	struct spi_board_info *spi_info = info;
-	int intr = get_gpio_by_name("max3111_int");
-
-	spi_info->mode = SPI_MODE_0;
-	if (intr == -1)
-		return NULL;
-	spi_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-	return NULL;
-}
-
-/* we have multiple max7315 on the board ... */
-#define MAX7315_NUM 2
-static void __init *max7315_platform_data(void *info)
-{
-	static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
-	static int nr;
-	struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
-	struct i2c_board_info *i2c_info = info;
-	int gpio_base, intr;
-	char base_pin_name[SFI_NAME_LEN + 1];
-	char intr_pin_name[SFI_NAME_LEN + 1];
-
-	if (nr == MAX7315_NUM) {
-		pr_err("too many max7315s, we only support %d\n",
-				MAX7315_NUM);
-		return NULL;
-	}
-	/* we have several max7315 on the board, we only need load several
-	 * instances of the same pca953x driver to cover them
-	 */
-	strcpy(i2c_info->type, "max7315");
-	if (nr++) {
-		sprintf(base_pin_name, "max7315_%d_base", nr);
-		sprintf(intr_pin_name, "max7315_%d_int", nr);
-	} else {
-		strcpy(base_pin_name, "max7315_base");
-		strcpy(intr_pin_name, "max7315_int");
-	}
-
-	gpio_base = get_gpio_by_name(base_pin_name);
-	intr = get_gpio_by_name(intr_pin_name);
-
-	if (gpio_base == -1)
-		return NULL;
-	max7315->gpio_base = gpio_base;
-	if (intr != -1) {
-		i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-		max7315->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
-	} else {
-		i2c_info->irq = -1;
-		max7315->irq_base = -1;
-	}
-	return max7315;
-}
-
-static void *tca6416_platform_data(void *info)
-{
-	static struct pca953x_platform_data tca6416;
-	struct i2c_board_info *i2c_info = info;
-	int gpio_base, intr;
-	char base_pin_name[SFI_NAME_LEN + 1];
-	char intr_pin_name[SFI_NAME_LEN + 1];
-
-	strcpy(i2c_info->type, "tca6416");
-	strcpy(base_pin_name, "tca6416_base");
-	strcpy(intr_pin_name, "tca6416_int");
-
-	gpio_base = get_gpio_by_name(base_pin_name);
-	intr = get_gpio_by_name(intr_pin_name);
-
-	if (gpio_base == -1)
-		return NULL;
-	tca6416.gpio_base = gpio_base;
-	if (intr != -1) {
-		i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-		tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
-	} else {
-		i2c_info->irq = -1;
-		tca6416.irq_base = -1;
-	}
-	return &tca6416;
-}
-
-static void *mpu3050_platform_data(void *info)
-{
-	struct i2c_board_info *i2c_info = info;
-	int intr = get_gpio_by_name("mpu3050_int");
-
-	if (intr == -1)
-		return NULL;
-
-	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-	return NULL;
-}
-
-static void __init *emc1403_platform_data(void *info)
-{
-	static short intr2nd_pdata;
-	struct i2c_board_info *i2c_info = info;
-	int intr = get_gpio_by_name("thermal_int");
-	int intr2nd = get_gpio_by_name("thermal_alert");
-
-	if (intr == -1 || intr2nd == -1)
-		return NULL;
-
-	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-	intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
-
-	return &intr2nd_pdata;
-}
-
-static void __init *lis331dl_platform_data(void *info)
-{
-	static short intr2nd_pdata;
-	struct i2c_board_info *i2c_info = info;
-	int intr = get_gpio_by_name("accel_int");
-	int intr2nd = get_gpio_by_name("accel_2");
-
-	if (intr == -1 || intr2nd == -1)
-		return NULL;
-
-	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
-	intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
-
-	return &intr2nd_pdata;
-}
-
-static void __init *no_platform_data(void *info)
-{
-	return NULL;
-}
-
-static struct resource msic_resources[] = {
-	{
-		.start	= INTEL_MSIC_IRQ_PHYS_BASE,
-		.end	= INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct intel_msic_platform_data msic_pdata;
-
-static struct platform_device msic_device = {
-	.name		= "intel_msic",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &msic_pdata,
-	},
-	.num_resources	= ARRAY_SIZE(msic_resources),
-	.resource	= msic_resources,
-};
-
-static inline bool intel_mid_has_msic(void)
-{
-	return intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL;
-}
-
-static int msic_scu_status_change(struct notifier_block *nb,
-				  unsigned long code, void *data)
-{
-	if (code == SCU_DOWN) {
-		platform_device_unregister(&msic_device);
-		return 0;
-	}
-
-	return platform_device_register(&msic_device);
-}
-
-static int __init msic_init(void)
-{
-	static struct notifier_block msic_scu_notifier = {
-		.notifier_call	= msic_scu_status_change,
-	};
-
-	/*
-	 * We need to be sure that the SCU IPC is ready before MSIC device
-	 * can be registered.
-	 */
-	if (intel_mid_has_msic())
-		intel_scu_notifier_add(&msic_scu_notifier);
-
-	return 0;
-}
-arch_initcall(msic_init);
-
-/*
- * msic_generic_platform_data - sets generic platform data for the block
- * @info: pointer to the SFI device table entry for this block
- * @block: MSIC block
- *
- * Function sets IRQ number from the SFI table entry for given device to
- * the MSIC platform data.
- */
-static void *msic_generic_platform_data(void *info, enum intel_msic_block block)
-{
-	struct sfi_device_table_entry *entry = info;
-
-	BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST);
-	msic_pdata.irq[block] = entry->irq;
-
-	return no_platform_data(info);
-}
-
-static void *msic_battery_platform_data(void *info)
-{
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY);
-}
-
-static void *msic_gpio_platform_data(void *info)
-{
-	static struct intel_msic_gpio_pdata pdata;
-	int gpio = get_gpio_by_name("msic_gpio_base");
-
-	if (gpio < 0)
-		return NULL;
-
-	pdata.gpio_base = gpio;
-	msic_pdata.gpio = &pdata;
-
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO);
-}
-
-static void *msic_audio_platform_data(void *info)
-{
-	struct platform_device *pdev;
-
-	pdev = platform_device_register_simple("sst-platform", -1, NULL, 0);
-	if (IS_ERR(pdev)) {
-		pr_err("failed to create audio platform device\n");
-		return NULL;
-	}
-
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO);
-}
-
-static void *msic_power_btn_platform_data(void *info)
-{
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN);
-}
-
-static void *msic_ocd_platform_data(void *info)
-{
-	static struct intel_msic_ocd_pdata pdata;
-	int gpio = get_gpio_by_name("ocd_gpio");
-
-	if (gpio < 0)
-		return NULL;
-
-	pdata.gpio = gpio;
-	msic_pdata.ocd = &pdata;
-
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD);
-}
-
-static void *msic_thermal_platform_data(void *info)
-{
-	return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL);
-}
-
-/* tc35876x DSI-LVDS bridge chip and panel platform data */
-static void *tc35876x_platform_data(void *data)
-{
-	static struct tc35876x_platform_data pdata;
-
-	/* gpio pins set to -1 will not be used by the driver */
-	pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
-	pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
-	pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
-
-	return &pdata;
-}
-
-static const struct devs_id __initconst device_ids[] = {
-	{"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data, NULL},
-	{"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data, NULL},
-	{"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data, &ipc_device_handler},
-	{"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data, NULL},
-	{"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data, NULL},
-	{"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data, NULL},
-	{"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data, NULL},
-	{"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data, NULL},
-	{"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data, NULL},
-	{"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data, &ipc_device_handler},
-	{"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data, NULL},
-	{"i2c_disp_brig", SFI_DEV_TYPE_I2C, 0, &tc35876x_platform_data, NULL},
-
-	/* MSIC subdevices */
-	{"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data, &ipc_device_handler},
-	{"msic_gpio", SFI_DEV_TYPE_IPC, 1, &msic_gpio_platform_data, &ipc_device_handler},
-	{"msic_audio", SFI_DEV_TYPE_IPC, 1, &msic_audio_platform_data, &ipc_device_handler},
-	{"msic_power_btn", SFI_DEV_TYPE_IPC, 1, &msic_power_btn_platform_data, &ipc_device_handler},
-	{"msic_ocd", SFI_DEV_TYPE_IPC, 1, &msic_ocd_platform_data, &ipc_device_handler},
-	{"msic_thermal", SFI_DEV_TYPE_IPC, 1, &msic_thermal_platform_data, &ipc_device_handler},
-	{ 0 }
-};
-
-static void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
-				struct devs_id *dev)
-{
-	struct platform_device *pdev;
-	void *pdata = NULL;
-	static struct resource res __initdata = {
-		.name = "IRQ",
-		.flags = IORESOURCE_IRQ,
-	};
-
-	pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
-		pentry->name, pentry->irq);
-
-	/*
-	 * We need to call platform init of IPC devices to fill misc_pdata
-	 * structure. It will be used in msic_init for initialization.
-	 */
-	if (dev != NULL)
-		pdata = dev->get_platform_data(pentry);
-
-	/*
-	 * On Medfield the platform device creation is handled by the MSIC
-	 * MFD driver so we don't need to do it here.
-	 */
-	if (intel_mid_has_msic())
-		return;
-
-	pdev = platform_device_alloc(pentry->name, 0);
-	if (pdev == NULL) {
-		pr_err("out of memory for SFI platform device '%s'.\n",
-			pentry->name);
-		return;
-	}
-	res.start = pentry->irq;
-	platform_device_add_resources(pdev, &res, 1);
-
-	pdev->dev.platform_data = pdata;
-	intel_scu_device_register(pdev);
-}
-
-
-/*
- * we will search these buttons in SFI GPIO table (by name)
- * and register them dynamically. Please add all possible
- * buttons here, we will shrink them if no GPIO found.
- */
-static struct gpio_keys_button gpio_button[] = {
-	{KEY_POWER,		-1, 1, "power_btn",	EV_KEY, 0, 3000},
-	{KEY_PROG1,		-1, 1, "prog_btn1",	EV_KEY, 0, 20},
-	{KEY_PROG2,		-1, 1, "prog_btn2",	EV_KEY, 0, 20},
-	{SW_LID,		-1, 1, "lid_switch",	EV_SW,  0, 20},
-	{KEY_VOLUMEUP,		-1, 1, "vol_up",	EV_KEY, 0, 20},
-	{KEY_VOLUMEDOWN,	-1, 1, "vol_down",	EV_KEY, 0, 20},
-	{KEY_CAMERA,		-1, 1, "camera_full",	EV_KEY, 0, 20},
-	{KEY_CAMERA_FOCUS,	-1, 1, "camera_half",	EV_KEY, 0, 20},
-	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw1",	EV_SW,  0, 20},
-	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw2",	EV_SW,  0, 20},
-};
-
-static struct gpio_keys_platform_data intel_mid_gpio_keys = {
-	.buttons	= gpio_button,
-	.rep		= 1,
-	.nbuttons	= -1, /* will fill it after search */
-};
-
-static struct platform_device pb_device = {
-	.name		= "gpio-keys",
-	.id		= -1,
-	.dev		= {
-		.platform_data	= &intel_mid_gpio_keys,
-	},
-};
-
-/*
- * Shrink the non-existent buttons, register the gpio button
- * device if there is some
- */
-static int __init pb_keys_init(void)
-{
-	struct gpio_keys_button *gb = gpio_button;
-	int i, num, good = 0;
-
-	num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
-	for (i = 0; i < num; i++) {
-		gb[i].gpio = get_gpio_by_name(gb[i].desc);
-		pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc,
-					gb[i].gpio);
-		if (gb[i].gpio == -1)
-			continue;
-
-		if (i != good)
-			gb[good] = gb[i];
-		good++;
-	}
-
-	if (good) {
-		intel_mid_gpio_keys.nbuttons = good;
-		return platform_device_register(&pb_device);
-	}
-	return 0;
-}
-late_initcall(pb_keys_init);
\ No newline at end of file
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 3f1c171e5ce3..c84c1ca396bf 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -42,7 +42,6 @@
 #include <asm/intel_scu_ipc.h>
 #include <asm/apb_timer.h>
 #include <asm/reboot.h>
-#include "intel_mid_weak_decls.h"
 
 #define	SFI_SIG_OEM0	"OEM0"
 #define MAX_IPCDEVS	24
@@ -403,19 +402,20 @@ static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry,
 		i2c_register_board_info(pentry->host_num, &i2c_info, 1);
 }
 
+extern struct devs_id *const __x86_intel_mid_dev_start[],
+		      *const __x86_intel_mid_dev_end[];
+
 static struct devs_id __init *get_device_id(u8 type, char *name)
 {
-	struct devs_id *dev = device_ids;
-
-	if (device_ids == NULL)
-		return NULL;
+	struct devs_id *const *dev_table;
 
-	while (dev->name[0]) {
+	for (dev_table = __x86_intel_mid_dev_start;
+			dev_table < __x86_intel_mid_dev_end; dev_table++) {
+		struct devs_id *dev = *dev_table;
 		if (dev->type == type &&
 			!strncmp(dev->name, name, SFI_NAME_LEN)) {
 			return dev;
 		}
-		dev++;
 	}
 
 	return NULL;
diff --git a/include/linux/sfi.h b/include/linux/sfi.h
index fe817918b30e..d9b436f09925 100644
--- a/include/linux/sfi.h
+++ b/include/linux/sfi.h
@@ -59,6 +59,9 @@
 #ifndef _LINUX_SFI_H
 #define _LINUX_SFI_H
 
+#include <linux/init.h>
+#include <linux/types.h>
+
 /* Table signatures reserved by the SFI specification */
 #define SFI_SIG_SYST		"SYST"
 #define SFI_SIG_FREQ		"FREQ"
-- 
cgit 


From a06ccd9c3785fa5550917ae036944f4e080b5749 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 15 Oct 2013 20:14:20 +0100
Subject: regulator: core: Add ability to create a lookup alias for supply

These patches add the ability to create an alternative device on which
a lookup for a certain supply should be conducted.

A common use-case for this would be devices that are logically
represented as a collection of drivers within Linux but are are
presented as a single device from device tree. It this case it is
necessary for each sub device to locate their supply data on the main
device.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/core.c           | 170 +++++++++++++++++++++++++++++++++++++
 drivers/regulator/devres.c         | 163 +++++++++++++++++++++++++++++++++++
 include/linux/regulator/consumer.h |  79 +++++++++++++++++
 3 files changed, 412 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 906deb7354ed..16427de56ce8 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -53,6 +53,7 @@ static DEFINE_MUTEX(regulator_list_mutex);
 static LIST_HEAD(regulator_list);
 static LIST_HEAD(regulator_map_list);
 static LIST_HEAD(regulator_ena_gpio_list);
+static LIST_HEAD(regulator_supply_alias_list);
 static bool has_full_constraints;
 static bool board_wants_dummy_regulator;
 
@@ -83,6 +84,19 @@ struct regulator_enable_gpio {
 	unsigned int ena_gpio_invert:1;
 };
 
+/*
+ * struct regulator_supply_alias
+ *
+ * Used to map lookups for a supply onto an alternative device.
+ */
+struct regulator_supply_alias {
+	struct list_head list;
+	struct device *src_dev;
+	const char *src_supply;
+	struct device *alias_dev;
+	const char *alias_supply;
+};
+
 static int _regulator_is_enabled(struct regulator_dev *rdev);
 static int _regulator_disable(struct regulator_dev *rdev);
 static int _regulator_get_voltage(struct regulator_dev *rdev);
@@ -1173,6 +1187,32 @@ static int _regulator_get_enable_time(struct regulator_dev *rdev)
 	return rdev->desc->ops->enable_time(rdev);
 }
 
+static struct regulator_supply_alias *regulator_find_supply_alias(
+		struct device *dev, const char *supply)
+{
+	struct regulator_supply_alias *map;
+
+	list_for_each_entry(map, &regulator_supply_alias_list, list)
+		if (map->src_dev == dev && strcmp(map->src_supply, supply) == 0)
+			return map;
+
+	return NULL;
+}
+
+static void regulator_supply_alias(struct device **dev, const char **supply)
+{
+	struct regulator_supply_alias *map;
+
+	map = regulator_find_supply_alias(*dev, *supply);
+	if (map) {
+		dev_dbg(*dev, "Mapping supply %s to %s,%s\n",
+				*supply, map->alias_supply,
+				dev_name(map->alias_dev));
+		*dev = map->alias_dev;
+		*supply = map->alias_supply;
+	}
+}
+
 static struct regulator_dev *regulator_dev_lookup(struct device *dev,
 						  const char *supply,
 						  int *ret)
@@ -1182,6 +1222,8 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev,
 	struct regulator_map *map;
 	const char *devname = NULL;
 
+	regulator_supply_alias(&dev, &supply);
+
 	/* first do a dt based lookup */
 	if (dev && dev->of_node) {
 		node = of_get_regulator(dev, supply);
@@ -1432,6 +1474,134 @@ void regulator_put(struct regulator *regulator)
 }
 EXPORT_SYMBOL_GPL(regulator_put);
 
+/**
+ * regulator_register_supply_alias - Provide device alias for supply lookup
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: Supply name or regulator ID
+ * @alias_dev: device that should be used to lookup the supply
+ * @alias_id: Supply name or regulator ID that should be used to lookup the
+ * supply
+ *
+ * All lookups for id on dev will instead be conducted for alias_id on
+ * alias_dev.
+ */
+int regulator_register_supply_alias(struct device *dev, const char *id,
+				    struct device *alias_dev,
+				    const char *alias_id)
+{
+	struct regulator_supply_alias *map;
+
+	map = regulator_find_supply_alias(dev, id);
+	if (map)
+		return -EEXIST;
+
+	map = kzalloc(sizeof(struct regulator_supply_alias), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	map->src_dev = dev;
+	map->src_supply = id;
+	map->alias_dev = alias_dev;
+	map->alias_supply = alias_id;
+
+	list_add(&map->list, &regulator_supply_alias_list);
+
+	pr_info("Adding alias for supply %s,%s -> %s,%s\n",
+		id, dev_name(dev), alias_id, dev_name(alias_dev));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regulator_register_supply_alias);
+
+/**
+ * regulator_unregister_supply_alias - Remove device alias
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: Supply name or regulator ID
+ *
+ * Remove a lookup alias if one exists for id on dev.
+ */
+void regulator_unregister_supply_alias(struct device *dev, const char *id)
+{
+	struct regulator_supply_alias *map;
+
+	map = regulator_find_supply_alias(dev, id);
+	if (map) {
+		list_del(&map->list);
+		kfree(map);
+	}
+}
+EXPORT_SYMBOL_GPL(regulator_unregister_supply_alias);
+
+/**
+ * regulator_bulk_register_supply_alias - register multiple aliases
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: List of supply names or regulator IDs
+ * @alias_dev: device that should be used to lookup the supply
+ * @alias_id: List of supply names or regulator IDs that should be used to
+ * lookup the supply
+ * @num_id: Number of aliases to register
+ *
+ * @return 0 on success, an errno on failure.
+ *
+ * This helper function allows drivers to register several supply
+ * aliases in one operation.  If any of the aliases cannot be
+ * registered any aliases that were registered will be removed
+ * before returning to the caller.
+ */
+int regulator_bulk_register_supply_alias(struct device *dev, const char **id,
+					 struct device *alias_dev,
+					 const char **alias_id,
+					 int num_id)
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < num_id; ++i) {
+		ret = regulator_register_supply_alias(dev, id[i], alias_dev,
+						      alias_id[i]);
+		if (ret < 0)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	dev_err(dev,
+		"Failed to create supply alias %s,%s -> %s,%s\n",
+		id[i], dev_name(dev), alias_id[i], dev_name(alias_dev));
+
+	while (--i >= 0)
+		regulator_unregister_supply_alias(dev, id[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regulator_bulk_register_supply_alias);
+
+/**
+ * regulator_bulk_unregister_supply_alias - unregister multiple aliases
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: List of supply names or regulator IDs
+ * @num_id: Number of aliases to unregister
+ *
+ * This helper function allows drivers to unregister several supply
+ * aliases in one operation.
+ */
+void regulator_bulk_unregister_supply_alias(struct device *dev,
+					    const char **id,
+					    int num_id)
+{
+	int i;
+
+	for (i = 0; i < num_id; ++i)
+		regulator_unregister_supply_alias(dev, id[i]);
+}
+EXPORT_SYMBOL_GPL(regulator_bulk_unregister_supply_alias);
+
+
 /* Manage enable GPIO list. Same GPIO pin can be shared among regulators */
 static int regulator_ena_gpio_request(struct regulator_dev *rdev,
 				const struct regulator_config *config)
diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c
index 2672a029fa25..f44818b838dc 100644
--- a/drivers/regulator/devres.c
+++ b/drivers/regulator/devres.c
@@ -250,3 +250,166 @@ void devm_regulator_unregister(struct device *dev, struct regulator_dev *rdev)
 		WARN_ON(rc);
 }
 EXPORT_SYMBOL_GPL(devm_regulator_unregister);
+
+struct regulator_supply_alias_match {
+	struct device *dev;
+	const char *id;
+};
+
+static int devm_regulator_match_supply_alias(struct device *dev, void *res,
+					     void *data)
+{
+	struct regulator_supply_alias_match *match = res;
+	struct regulator_supply_alias_match *target = data;
+
+	return match->dev == target->dev && strcmp(match->id, target->id) == 0;
+}
+
+static void devm_regulator_destroy_supply_alias(struct device *dev, void *res)
+{
+	struct regulator_supply_alias_match *match = res;
+
+	regulator_unregister_supply_alias(match->dev, match->id);
+}
+
+/**
+ * devm_regulator_register_supply_alias - Resource managed
+ * regulator_register_supply_alias()
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: Supply name or regulator ID
+ * @alias_dev: device that should be used to lookup the supply
+ * @alias_id: Supply name or regulator ID that should be used to lookup the
+ * supply
+ *
+ * The supply alias will automatically be unregistered when the source
+ * device is unbound.
+ */
+int devm_regulator_register_supply_alias(struct device *dev, const char *id,
+					 struct device *alias_dev,
+					 const char *alias_id)
+{
+	struct regulator_supply_alias_match *match;
+	int ret;
+
+	match = devres_alloc(devm_regulator_destroy_supply_alias,
+			   sizeof(struct regulator_supply_alias_match),
+			   GFP_KERNEL);
+	if (!match)
+		return -ENOMEM;
+
+	match->dev = dev;
+	match->id = id;
+
+	ret = regulator_register_supply_alias(dev, id, alias_dev, alias_id);
+	if (ret < 0) {
+		devres_free(match);
+		return ret;
+	}
+
+	devres_add(dev, match);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_regulator_register_supply_alias);
+
+/**
+ * devm_regulator_unregister_supply_alias - Resource managed
+ * regulator_unregister_supply_alias()
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: Supply name or regulator ID
+ *
+ * Unregister an alias registered with
+ * devm_regulator_register_supply_alias(). Normally this function
+ * will not need to be called and the resource management code
+ * will ensure that the resource is freed.
+ */
+void devm_regulator_unregister_supply_alias(struct device *dev, const char *id)
+{
+	struct regulator_supply_alias_match match;
+	int rc;
+
+	match.dev = dev;
+	match.id = id;
+
+	rc = devres_release(dev, devm_regulator_destroy_supply_alias,
+			    devm_regulator_match_supply_alias, &match);
+	if (rc != 0)
+		WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_regulator_unregister_supply_alias);
+
+/**
+ * devm_regulator_bulk_register_supply_alias - Managed register
+ * multiple aliases
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: List of supply names or regulator IDs
+ * @alias_dev: device that should be used to lookup the supply
+ * @alias_id: List of supply names or regulator IDs that should be used to
+ * lookup the supply
+ * @num_id: Number of aliases to register
+ *
+ * @return 0 on success, an errno on failure.
+ *
+ * This helper function allows drivers to register several supply
+ * aliases in one operation, the aliases will be automatically
+ * unregisters when the source device is unbound.  If any of the
+ * aliases cannot be registered any aliases that were registered
+ * will be removed before returning to the caller.
+ */
+int devm_regulator_bulk_register_supply_alias(struct device *dev,
+					      const char **id,
+					      struct device *alias_dev,
+					      const char **alias_id,
+					      int num_id)
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < num_id; ++i) {
+		ret = devm_regulator_register_supply_alias(dev, id[i],
+							   alias_dev,
+							   alias_id[i]);
+		if (ret < 0)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	dev_err(dev,
+		"Failed to create supply alias %s,%s -> %s,%s\n",
+		id[i], dev_name(dev), alias_id[i], dev_name(alias_dev));
+
+	while (--i >= 0)
+		devm_regulator_unregister_supply_alias(dev, id[i]);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_regulator_bulk_register_supply_alias);
+
+/**
+ * devm_regulator_bulk_unregister_supply_alias - Managed unregister
+ * multiple aliases
+ *
+ * @dev: device that will be given as the regulator "consumer"
+ * @id: List of supply names or regulator IDs
+ * @num_id: Number of aliases to unregister
+ *
+ * Unregister aliases registered with
+ * devm_regulator_bulk_register_supply_alias(). Normally this function
+ * will not need to be called and the resource management code
+ * will ensure that the resource is freed.
+ */
+void devm_regulator_bulk_unregister_supply_alias(struct device *dev,
+						 const char **id,
+						 int num_id)
+{
+	int i;
+
+	for (i = 0; i < num_id; ++i)
+		devm_regulator_unregister_supply_alias(dev, id[i]);
+}
+EXPORT_SYMBOL_GPL(devm_regulator_bulk_unregister_supply_alias);
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 27be915caa96..e530681bea70 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -146,6 +146,32 @@ struct regulator *__must_check devm_regulator_get_optional(struct device *dev,
 void regulator_put(struct regulator *regulator);
 void devm_regulator_put(struct regulator *regulator);
 
+int regulator_register_supply_alias(struct device *dev, const char *id,
+				    struct device *alias_dev,
+				    const char *alias_id);
+void regulator_unregister_supply_alias(struct device *dev, const char *id);
+
+int regulator_bulk_register_supply_alias(struct device *dev, const char **id,
+					 struct device *alias_dev,
+					 const char **alias_id, int num_id);
+void regulator_bulk_unregister_supply_alias(struct device *dev,
+					    const char **id, int num_id);
+
+int devm_regulator_register_supply_alias(struct device *dev, const char *id,
+					 struct device *alias_dev,
+					 const char *alias_id);
+void devm_regulator_unregister_supply_alias(struct device *dev,
+					    const char *id);
+
+int devm_regulator_bulk_register_supply_alias(struct device *dev,
+					      const char **id,
+					      struct device *alias_dev,
+					      const char **alias_id,
+					      int num_id);
+void devm_regulator_bulk_unregister_supply_alias(struct device *dev,
+						 const char **id,
+						 int num_id);
+
 /* regulator output control and status */
 int __must_check regulator_enable(struct regulator *regulator);
 int regulator_disable(struct regulator *regulator);
@@ -250,6 +276,59 @@ static inline void devm_regulator_put(struct regulator *regulator)
 {
 }
 
+static inline int regulator_register_supply_alias(struct device *dev,
+						  const char *id,
+						  struct device *alias_dev,
+						  const char *alias_id)
+{
+	return 0;
+}
+
+static inline void regulator_unregister_supply_alias(struct device *dev,
+						    const char *id)
+{
+}
+
+static inline int regulator_bulk_register_supply_alias(struct device *dev,
+						       const char **id,
+						       struct device *alias_dev,
+						       const char **alias_id,
+						       int num_id)
+{
+	return 0;
+}
+
+static inline void regulator_bulk_unregister_supply_alias(struct device *dev,
+							  const char **id,
+							  int num_id)
+{
+}
+
+static inline int devm_regulator_register_supply_alias(struct device *dev,
+						       const char *id,
+						       struct device *alias_dev,
+						       const char *alias_id)
+{
+	return 0;
+}
+
+static inline void devm_regulator_unregister_supply_alias(struct device *dev,
+							  const char *id)
+{
+}
+
+static inline int devm_regulator_bulk_register_supply_alias(
+		struct device *dev, const char **id, struct device *alias_dev,
+		const char **alias_id, int num_id)
+{
+	return 0;
+}
+
+static inline void devm_regulator_bulk_unregister_supply_alias(
+		struct device *dev, const char **id, int num_id)
+{
+}
+
 static inline int regulator_enable(struct regulator *regulator)
 {
 	return 0;
-- 
cgit 


From 400dfd3ae899849b27d398ca7894e1b44430887f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 17 Oct 2013 16:27:07 -0700
Subject: net: refactor sk_page_frag_refill()

While working on virtio_net new allocation strategy to increase
payload/truesize ratio, we found that refactoring sk_page_frag_refill()
was needed.

This patch splits sk_page_frag_refill() into two parts, adding
skb_page_frag_refill() which can be used without a socket.

While we are at it, add a minimum frag size of 32 for
sk_page_frag_refill()

Michael will either use netdev_alloc_frag() from softirq context,
or skb_page_frag_refill() from process context in refill_work()
 (GFP_KERNEL allocations)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michael Dalton <mwdalton@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  2 ++
 net/core/sock.c        | 27 +++++++++++++++++++++++----
 2 files changed, 25 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1cd32f96055e..ba74474836c0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2062,6 +2062,8 @@ static inline void skb_frag_set_page(struct sk_buff *skb, int f,
 	__skb_frag_set_page(&skb_shinfo(skb)->frags[f], page);
 }
 
+bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio);
+
 /**
  * skb_frag_dma_map - maps a paged fragment via the DMA API
  * @dev: the device to map the fragment to
diff --git a/net/core/sock.c b/net/core/sock.c
index fd6afa267475..440afdca1e8f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1847,7 +1847,17 @@ EXPORT_SYMBOL(sock_alloc_send_skb);
 /* On 32bit arches, an skb frag is limited to 2^15 */
 #define SKB_FRAG_PAGE_ORDER	get_order(32768)
 
-bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+/**
+ * skb_page_frag_refill - check that a page_frag contains enough room
+ * @sz: minimum size of the fragment we want to get
+ * @pfrag: pointer to page_frag
+ * @prio: priority for memory allocation
+ *
+ * Note: While this allocator tries to use high order pages, there is
+ * no guarantee that allocations succeed. Therefore, @sz MUST be
+ * less or equal than PAGE_SIZE.
+ */
+bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
 {
 	int order;
 
@@ -1856,16 +1866,16 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 			pfrag->offset = 0;
 			return true;
 		}
-		if (pfrag->offset < pfrag->size)
+		if (pfrag->offset + sz <= pfrag->size)
 			return true;
 		put_page(pfrag->page);
 	}
 
 	/* We restrict high order allocations to users that can afford to wait */
-	order = (sk->sk_allocation & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
+	order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
 
 	do {
-		gfp_t gfp = sk->sk_allocation;
+		gfp_t gfp = prio;
 
 		if (order)
 			gfp |= __GFP_COMP | __GFP_NOWARN;
@@ -1877,6 +1887,15 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 		}
 	} while (--order >= 0);
 
+	return false;
+}
+EXPORT_SYMBOL(skb_page_frag_refill);
+
+bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
+{
+	if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
+		return true;
+
 	sk_enter_memory_pressure(sk);
 	sk_stream_moderate_sndbuf(sk);
 	return false;
-- 
cgit 


From 7cc7c5e54b7128195a1403747a63971c3c3f8e25 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Mon, 14 Oct 2013 21:49:21 +0100
Subject: net: Delete trailing semi-colon from definition of netdev_WARN()

Macro definitions should not normally end with a semi-colon, as this
makes it dangerous to use them an if...else statement.  Happily this
has not happened yet.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2e53b44454ad..27f62f746621 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3049,7 +3049,7 @@ do {								\
  * file/line information and a backtrace.
  */
 #define netdev_WARN(dev, format, args...)			\
-	WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args);
+	WARN(1, "netdevice: %s\n" format, netdev_name(dev), ##args)
 
 /* netif printk helpers, similar to netdev_printk */
 
-- 
cgit 


From b9ee0a783a928631bff1f0ea355bb9dc5deeaaf8 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 17 Oct 2013 17:24:13 -0700
Subject: Bluetooth: Add address type to device blacklist table

The device blacklist is not taking care of the address type. Actually
store the address type in the list entries and also use them when
looking up addresses in the table.

This is actually a serious bug. When adding a LE public address to
the blacklist, then it would be blocking a device on BR/EDR. And this
is not the expected behavior.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  3 ++-
 net/bluetooth/hci_core.c         | 21 +++++++++++----------
 net/bluetooth/hci_event.c        |  2 +-
 3 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 07c2da4854ab..c6becda8c466 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -81,6 +81,7 @@ struct hci_conn_hash {
 struct bdaddr_list {
 	struct list_head list;
 	bdaddr_t bdaddr;
+	u8 bdaddr_type;
 };
 
 struct bt_uuid {
@@ -732,7 +733,7 @@ int hci_get_auth_info(struct hci_dev *hdev, void __user *arg);
 int hci_inquiry(void __user *arg);
 
 struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev,
-					 bdaddr_t *bdaddr);
+					 bdaddr_t *bdaddr, u8 type);
 int hci_blacklist_clear(struct hci_dev *hdev);
 int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
 int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b7c4ada1beb6..2376c3040194 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2158,13 +2158,15 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash,
 	return 0;
 }
 
-struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr)
+struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev,
+					 bdaddr_t *bdaddr, u8 type)
 {
 	struct bdaddr_list *b;
 
-	list_for_each_entry(b, &hdev->blacklist, list)
-		if (bacmp(bdaddr, &b->bdaddr) == 0)
+	list_for_each_entry(b, &hdev->blacklist, list) {
+		if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type)
 			return b;
+	}
 
 	return NULL;
 }
@@ -2174,9 +2176,7 @@ int hci_blacklist_clear(struct hci_dev *hdev)
 	struct list_head *p, *n;
 
 	list_for_each_safe(p, n, &hdev->blacklist) {
-		struct bdaddr_list *b;
-
-		b = list_entry(p, struct bdaddr_list, list);
+		struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list);
 
 		list_del(p);
 		kfree(b);
@@ -2189,10 +2189,10 @@ int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 {
 	struct bdaddr_list *entry;
 
-	if (bacmp(bdaddr, BDADDR_ANY) == 0)
+	if (!bacmp(bdaddr, BDADDR_ANY))
 		return -EBADF;
 
-	if (hci_blacklist_lookup(hdev, bdaddr))
+	if (hci_blacklist_lookup(hdev, bdaddr, type))
 		return -EEXIST;
 
 	entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL);
@@ -2200,6 +2200,7 @@ int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 		return -ENOMEM;
 
 	bacpy(&entry->bdaddr, bdaddr);
+	entry->bdaddr_type = type;
 
 	list_add(&entry->list, &hdev->blacklist);
 
@@ -2210,10 +2211,10 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type)
 {
 	struct bdaddr_list *entry;
 
-	if (bacmp(bdaddr, BDADDR_ANY) == 0)
+	if (!bacmp(bdaddr, BDADDR_ANY))
 		return hci_blacklist_clear(hdev);
 
-	entry = hci_blacklist_lookup(hdev, bdaddr);
+	entry = hci_blacklist_lookup(hdev, bdaddr, type);
 	if (!entry)
 		return -ENOENT;
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6c3b193951ad..e43de9876aa0 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1692,7 +1692,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 				      &flags);
 
 	if ((mask & HCI_LM_ACCEPT) &&
-	    !hci_blacklist_lookup(hdev, &ev->bdaddr)) {
+	    !hci_blacklist_lookup(hdev, &ev->bdaddr, BDADDR_BREDR)) {
 		/* Connection accepted */
 		struct inquiry_entry *ie;
 		struct hci_conn *conn;
-- 
cgit 


From bdc3e0f1d2019fbf89f150ed98860b1a7a762fe9 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 17 Oct 2013 17:24:19 -0700
Subject: Bluetooth: Move device_add handling into hci_register_dev

The device_add handling can be done directly in hci_register_dev and
device_remove within hci_unregister_dev.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 --
 net/bluetooth/hci_core.c         |  6 ++++--
 net/bluetooth/hci_sysfs.c        | 18 ------------------
 3 files changed, 4 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c6becda8c466..9b5db01bd1a2 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -768,8 +768,6 @@ int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count);
 int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count);
 
 void hci_init_sysfs(struct hci_dev *hdev);
-int hci_add_sysfs(struct hci_dev *hdev);
-void hci_del_sysfs(struct hci_dev *hdev);
 void hci_conn_init_sysfs(struct hci_conn *conn);
 void hci_conn_add_sysfs(struct hci_conn *conn);
 void hci_conn_del_sysfs(struct hci_conn *conn);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index f7ba81885b42..940da800f5c3 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2482,7 +2482,9 @@ int hci_register_dev(struct hci_dev *hdev)
 	if (!IS_ERR_OR_NULL(bt_debugfs))
 		hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs);
 
-	error = hci_add_sysfs(hdev);
+	dev_set_name(&hdev->dev, "%s", hdev->name);
+
+	error = device_add(&hdev->dev);
 	if (error < 0)
 		goto err_wqueue;
 
@@ -2570,7 +2572,7 @@ void hci_unregister_dev(struct hci_dev *hdev)
 		rfkill_destroy(hdev->rfkill);
 	}
 
-	hci_del_sysfs(hdev);
+	device_del(&hdev->dev);
 
 	debugfs_remove_recursive(hdev->debugfs);
 
diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
index 320a76118252..9cbf8fefb044 100644
--- a/net/bluetooth/hci_sysfs.c
+++ b/net/bluetooth/hci_sysfs.c
@@ -402,24 +402,6 @@ void hci_init_sysfs(struct hci_dev *hdev)
 	device_initialize(dev);
 }
 
-int hci_add_sysfs(struct hci_dev *hdev)
-{
-	struct device *dev = &hdev->dev;
-
-	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
-
-	dev_set_name(dev, "%s", hdev->name);
-
-	return device_add(dev);
-}
-
-void hci_del_sysfs(struct hci_dev *hdev)
-{
-	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
-
-	device_del(&hdev->dev);
-}
-
 int __init bt_sysfs_init(void)
 {
 	bt_class = class_create(THIS_MODULE, "bluetooth");
-- 
cgit 


From c75b505ddaa08098940441226bb3a87c5b3179c0 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 8 Oct 2013 10:56:11 +0200
Subject: cpufreq: Add dummy cpufreq_cpu_get/put for CONFIG_CPU_FREQ=n

The drm/i915 driver wants to adjust it's own power policies using the
cpu policies as a guideline (we can implicitly boost the cpus through
the gpus on some platforms). To avoid a dreaded select (since a
depends will leave users wondering where where their driver has gone
too) add dummy functions.

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Cc: kbuild test robot <fengguang.wu@intel.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: cpufreq@vger.kernel.org
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/linux/cpufreq.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index fcabc42d66ab..5ad9a4e2bc59 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -93,8 +93,16 @@ struct cpufreq_policy {
 #define CPUFREQ_SHARED_TYPE_ALL	 (2) /* All dependent CPUs should set freq */
 #define CPUFREQ_SHARED_TYPE_ANY	 (3) /* Freq can be set from any dependent CPU*/
 
+#ifdef CONFIG_CPU_FREQ
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
 void cpufreq_cpu_put(struct cpufreq_policy *policy);
+#else
+static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
+{
+	return NULL;
+}
+static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { }
+#endif
 
 static inline bool policy_is_shared(struct cpufreq_policy *policy)
 {
-- 
cgit 


From 28be6e07e8bccee76b51bca8fdba52c1b28fc77c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 18 Oct 2013 10:36:17 -0700
Subject: tcp: rename tcp_tso_segment()

Rename tcp_tso_segment() to tcp_gso_segment(), to better reflect
what is going on, and ease grep games.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        | 2 +-
 net/ipv4/tcp_offload.c   | 6 +++---
 net/ipv6/tcpv6_offload.c | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1db3a016bff6..372dcccfeed0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1548,7 +1548,7 @@ extern struct request_sock_ops tcp6_request_sock_ops;
 
 void tcp_v4_destroy_sock(struct sock *sk);
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
 struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb);
 int tcp_gro_complete(struct sk_buff *skb);
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3a7525e6c086..8e3113f46ec1 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -14,7 +14,7 @@
 #include <net/tcp.h>
 #include <net/protocol.h>
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
@@ -139,7 +139,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
 out:
 	return segs;
 }
-EXPORT_SYMBOL(tcp_tso_segment);
+EXPORT_SYMBOL(tcp_gso_segment);
 
 struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
@@ -320,7 +320,7 @@ static int tcp4_gro_complete(struct sk_buff *skb)
 static const struct net_offload tcpv4_offload = {
 	.callbacks = {
 		.gso_send_check	=	tcp_v4_gso_send_check,
-		.gso_segment	=	tcp_tso_segment,
+		.gso_segment	=	tcp_gso_segment,
 		.gro_receive	=	tcp4_gro_receive,
 		.gro_complete	=	tcp4_gro_complete,
 	},
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 2ec6bf6a0aa0..c1097c798900 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -83,7 +83,7 @@ static int tcp6_gro_complete(struct sk_buff *skb)
 static const struct net_offload tcpv6_offload = {
 	.callbacks = {
 		.gso_send_check	=	tcp_v6_gso_send_check,
-		.gso_segment	=	tcp_tso_segment,
+		.gso_segment	=	tcp_gso_segment,
 		.gro_receive	=	tcp6_gro_receive,
 		.gro_complete	=	tcp6_gro_complete,
 	},
-- 
cgit 


From 03f27120fb935f2a7f1a7471acb6450dbc64e564 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
Date: Mon, 14 Oct 2013 17:42:06 -0700
Subject: cfg80211: export reg_initiator_name()

Drivers can now use this to parse the regulatory request and
be more verbose when needed.

Signed-off-by: Luis R. Rodriguez <mcgrof@do-not-panic.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/net/cfg80211.h |  9 +++++++++
 net/wireless/reg.c     | 27 +++++++++++++++++----------
 2 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 45f6bf591104..419202ce3f95 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3483,6 +3483,15 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
 const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 					       u32 center_freq);
 
+/**
+ * reg_initiator_name - map regulatory request initiator enum to name
+ * @initiator: the regulatory request initiator
+ *
+ * You can use this to map the regulatory request initiator enum to a
+ * proper string representation.
+ */
+const char *reg_initiator_name(enum nl80211_reg_initiator initiator);
+
 /*
  * callbacks for asynchronous cfg80211 methods, notification
  * functions and BSS handling helpers
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d62cb1e91475..a0ec143ba3dc 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -768,23 +768,25 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(freq_reg_info);
 
-#ifdef CONFIG_CFG80211_REG_DEBUG
-static const char *reg_initiator_name(enum nl80211_reg_initiator initiator)
+const char *reg_initiator_name(enum nl80211_reg_initiator initiator)
 {
 	switch (initiator) {
 	case NL80211_REGDOM_SET_BY_CORE:
-		return "Set by core";
+		return "core";
 	case NL80211_REGDOM_SET_BY_USER:
-		return "Set by user";
+		return "user";
 	case NL80211_REGDOM_SET_BY_DRIVER:
-		return "Set by driver";
+		return "driver";
 	case NL80211_REGDOM_SET_BY_COUNTRY_IE:
-		return "Set by country IE";
+		return "country IE";
 	default:
 		WARN_ON(1);
-		return "Set by bug";
+		return "bug";
 	}
 }
+EXPORT_SYMBOL(reg_initiator_name);
+
+#ifdef CONFIG_CFG80211_REG_DEBUG
 
 static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan,
 				    const struct ieee80211_reg_rule *reg_rule)
@@ -979,14 +981,17 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 	struct regulatory_request *lr = get_last_request();
 
 	if (!lr) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since last_request is not set\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since last_request is not set\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
 
 	if (initiator == NL80211_REGDOM_SET_BY_CORE &&
 	    wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since the driver uses its own custom regulatory domain\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since the driver uses its own custom "
+			      "regulatory domain\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
@@ -998,7 +1003,9 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 	if (wiphy->flags & WIPHY_FLAG_STRICT_REGULATORY && !wiphy->regd &&
 	    initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
 	    !is_world_regdom(lr->alpha2)) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since the driver requires its own regulatory domain to be set first\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since the driver requires its own regulatory "
+			      "domain to be set first\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
-- 
cgit 


From bd6a9ddcb9f2cb19dae0509341a4cbaf40dc66f0 Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@gmail.com>
Date: Wed, 16 Oct 2013 19:19:02 +0200
Subject: ARM: tegra: Add Tegra114 powergate support

Extend the list of power gates found on Tegra114. Note that there are
now holes in the list, so perhaps a simple array is no longer the best
data structure to represent it.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
---
 arch/arm/mach-tegra/powergate.c | 43 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/tegra-powergate.h |  9 ++++++++-
 2 files changed, 50 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-tegra/powergate.c b/arch/arm/mach-tegra/powergate.c
index bd10822f8b66..85d28e756bb7 100644
--- a/arch/arm/mach-tegra/powergate.c
+++ b/arch/arm/mach-tegra/powergate.c
@@ -45,6 +45,13 @@ static int tegra_num_cpu_domains;
 static const u8 *tegra_cpu_domains;
 
 static const u8 tegra30_cpu_domains[] = {
+	TEGRA_POWERGATE_CPU,
+	TEGRA_POWERGATE_CPU1,
+	TEGRA_POWERGATE_CPU2,
+	TEGRA_POWERGATE_CPU3,
+};
+
+static const u8 tegra114_cpu_domains[] = {
 	TEGRA_POWERGATE_CPU0,
 	TEGRA_POWERGATE_CPU1,
 	TEGRA_POWERGATE_CPU2,
@@ -190,6 +197,11 @@ int __init tegra_powergate_init(void)
 		tegra_num_cpu_domains = 4;
 		tegra_cpu_domains = tegra30_cpu_domains;
 		break;
+	case TEGRA114:
+		tegra_num_powerdomains = 23;
+		tegra_num_cpu_domains = 4;
+		tegra_cpu_domains = tegra114_cpu_domains;
+		break;
 	default:
 		/* Unknown Tegra variant. Disable powergating */
 		tegra_num_powerdomains = 0;
@@ -230,6 +242,27 @@ static const char * const powergate_name_t30[] = {
 	[TEGRA_POWERGATE_3D1]	= "3d1",
 };
 
+static const char * const powergate_name_t114[] = {
+	[TEGRA_POWERGATE_CPU]	= "cpu0",
+	[TEGRA_POWERGATE_3D]	= "3d",
+	[TEGRA_POWERGATE_VENC]	= "venc",
+	[TEGRA_POWERGATE_VDEC]	= "vdec",
+	[TEGRA_POWERGATE_MPE]	= "mpe",
+	[TEGRA_POWERGATE_HEG]	= "heg",
+	[TEGRA_POWERGATE_CPU1]	= "cpu1",
+	[TEGRA_POWERGATE_CPU2]	= "cpu2",
+	[TEGRA_POWERGATE_CPU3]	= "cpu3",
+	[TEGRA_POWERGATE_CELP]	= "celp",
+	[TEGRA_POWERGATE_CPU0]	= "cpu0",
+	[TEGRA_POWERGATE_C0NC]	= "c0nc",
+	[TEGRA_POWERGATE_C1NC]	= "c1nc",
+	[TEGRA_POWERGATE_DIS]	= "dis",
+	[TEGRA_POWERGATE_DISB]	= "disb",
+	[TEGRA_POWERGATE_XUSBA]	= "xusba",
+	[TEGRA_POWERGATE_XUSBB]	= "xusbb",
+	[TEGRA_POWERGATE_XUSBC]	= "xusbc",
+};
+
 static int powergate_show(struct seq_file *s, void *data)
 {
 	int i;
@@ -237,9 +270,14 @@ static int powergate_show(struct seq_file *s, void *data)
 	seq_printf(s, " powergate powered\n");
 	seq_printf(s, "------------------\n");
 
-	for (i = 0; i < tegra_num_powerdomains; i++)
+	for (i = 0; i < tegra_num_powerdomains; i++) {
+		if (!powergate_name[i])
+			continue;
+
 		seq_printf(s, " %9s %7s\n", powergate_name[i],
 			tegra_powergate_is_powered(i) ? "yes" : "no");
+	}
+
 	return 0;
 }
 
@@ -266,6 +304,9 @@ int __init tegra_powergate_debugfs_init(void)
 	case TEGRA30:
 		powergate_name = powergate_name_t30;
 		break;
+	case TEGRA114:
+		powergate_name = powergate_name_t114;
+		break;
 	}
 
 	if (powergate_name) {
diff --git a/include/linux/tegra-powergate.h b/include/linux/tegra-powergate.h
index 55c29a8d5015..c98cfa406952 100644
--- a/include/linux/tegra-powergate.h
+++ b/include/linux/tegra-powergate.h
@@ -34,8 +34,15 @@ struct clk;
 #define TEGRA_POWERGATE_CPU3	11
 #define TEGRA_POWERGATE_CELP	12
 #define TEGRA_POWERGATE_3D1	13
+#define TEGRA_POWERGATE_CPU0	14
+#define TEGRA_POWERGATE_C0NC	15
+#define TEGRA_POWERGATE_C1NC	16
+#define TEGRA_POWERGATE_DIS	18
+#define TEGRA_POWERGATE_DISB	19
+#define TEGRA_POWERGATE_XUSBA	20
+#define TEGRA_POWERGATE_XUSBB	21
+#define TEGRA_POWERGATE_XUSBC	22
 
-#define TEGRA_POWERGATE_CPU0	TEGRA_POWERGATE_CPU
 #define TEGRA_POWERGATE_3D0	TEGRA_POWERGATE_3D
 
 int tegra_powergate_is_powered(int id);
-- 
cgit 


From 29ad23b00474c34e3b5040dda508c78d33a1a3eb Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Mon, 14 Oct 2013 17:24:26 +0900
Subject: ftrace: Add set_graph_notrace filter

The set_graph_notrace filter is analogous to set_ftrace_notrace and
can be used for eliminating uninteresting part of function graph trace
output.  It also works with set_graph_function nicely.

  # cd /sys/kernel/debug/tracing/
  # echo do_page_fault > set_graph_function
  # perf ftrace live true
   2)               |  do_page_fault() {
   2)               |    __do_page_fault() {
   2)   0.381 us    |      down_read_trylock();
   2)   0.055 us    |      __might_sleep();
   2)   0.696 us    |      find_vma();
   2)               |      handle_mm_fault() {
   2)               |        handle_pte_fault() {
   2)               |          __do_fault() {
   2)               |            filemap_fault() {
   2)               |              find_get_page() {
   2)   0.033 us    |                __rcu_read_lock();
   2)   0.035 us    |                __rcu_read_unlock();
   2)   1.696 us    |              }
   2)   0.031 us    |              __might_sleep();
   2)   2.831 us    |            }
   2)               |            _raw_spin_lock() {
   2)   0.046 us    |              add_preempt_count();
   2)   0.841 us    |            }
   2)   0.033 us    |            page_add_file_rmap();
   2)               |            _raw_spin_unlock() {
   2)   0.057 us    |              sub_preempt_count();
   2)   0.568 us    |            }
   2)               |            unlock_page() {
   2)   0.084 us    |              page_waitqueue();
   2)   0.126 us    |              __wake_up_bit();
   2)   1.117 us    |            }
   2)   7.729 us    |          }
   2)   8.397 us    |        }
   2)   8.956 us    |      }
   2)   0.085 us    |      up_read();
   2) + 12.745 us   |    }
   2) + 13.401 us   |  }
  ...

  # echo handle_mm_fault > set_graph_notrace
  # perf ftrace live true
   1)               |  do_page_fault() {
   1)               |    __do_page_fault() {
   1)   0.205 us    |      down_read_trylock();
   1)   0.041 us    |      __might_sleep();
   1)   0.344 us    |      find_vma();
   1)   0.069 us    |      up_read();
   1)   4.692 us    |    }
   1)   5.311 us    |  }
  ...

Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h               |  1 +
 kernel/trace/ftrace.c                | 33 +++++++++++++++++++++
 kernel/trace/trace.h                 | 22 ++++++++++++++
 kernel/trace/trace_functions_graph.c | 56 ++++++++++++++++++++++++++++++++++--
 4 files changed, 109 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9f15c0064c50..ec85d48619e1 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -721,6 +721,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 extern char __irqentry_text_start[];
 extern char __irqentry_text_end[];
 
+#define FTRACE_NOTRACE_DEPTH 65536
 #define FTRACE_RETFUNC_DEPTH 50
 #define FTRACE_RETSTACK_ALLOC_SIZE 32
 extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 26a229ab0c19..44e826a79665 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3776,7 +3776,9 @@ static const struct file_operations ftrace_notrace_fops = {
 static DEFINE_MUTEX(graph_lock);
 
 int ftrace_graph_count;
+int ftrace_graph_notrace_count;
 unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 
 struct ftrace_graph_data {
 	unsigned long *table;
@@ -3890,6 +3892,26 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 	return __ftrace_graph_open(inode, file, fgd);
 }
 
+static int
+ftrace_graph_notrace_open(struct inode *inode, struct file *file)
+{
+	struct ftrace_graph_data *fgd;
+
+	if (unlikely(ftrace_disabled))
+		return -ENODEV;
+
+	fgd = kmalloc(sizeof(*fgd), GFP_KERNEL);
+	if (fgd == NULL)
+		return -ENOMEM;
+
+	fgd->table = ftrace_graph_notrace_funcs;
+	fgd->size = FTRACE_GRAPH_MAX_FUNCS;
+	fgd->count = &ftrace_graph_notrace_count;
+	fgd->seq_ops = &ftrace_graph_seq_ops;
+
+	return __ftrace_graph_open(inode, file, fgd);
+}
+
 static int
 ftrace_graph_release(struct inode *inode, struct file *file)
 {
@@ -4011,6 +4033,14 @@ static const struct file_operations ftrace_graph_fops = {
 	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_graph_release,
 };
+
+static const struct file_operations ftrace_graph_notrace_fops = {
+	.open		= ftrace_graph_notrace_open,
+	.read		= seq_read,
+	.write		= ftrace_graph_write,
+	.llseek		= ftrace_filter_lseek,
+	.release	= ftrace_graph_release,
+};
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
@@ -4032,6 +4062,9 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 	trace_create_file("set_graph_function", 0444, d_tracer,
 				    NULL,
 				    &ftrace_graph_fops);
+	trace_create_file("set_graph_notrace", 0444, d_tracer,
+				    NULL,
+				    &ftrace_graph_notrace_fops);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 	return 0;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 40211cef2796..d1cf5159bec0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -732,6 +732,8 @@ extern void __trace_graph_return(struct trace_array *tr,
 #define FTRACE_GRAPH_MAX_FUNCS		32
 extern int ftrace_graph_count;
 extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
+extern int ftrace_graph_notrace_count;
+extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS];
 
 static inline int ftrace_graph_addr(unsigned long addr)
 {
@@ -757,11 +759,31 @@ static inline int ftrace_graph_addr(unsigned long addr)
 
 	return 0;
 }
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+	int i;
+
+	if (!ftrace_graph_notrace_count)
+		return 0;
+
+	for (i = 0; i < ftrace_graph_notrace_count; i++) {
+		if (addr == ftrace_graph_notrace_funcs[i])
+			return 1;
+	}
+
+	return 0;
+}
 #else
 static inline int ftrace_graph_addr(unsigned long addr)
 {
 	return 1;
 }
+
+static inline int ftrace_graph_notrace_addr(unsigned long addr)
+{
+	return 0;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b5c09242683d..e08c030b8f38 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 		return -EBUSY;
 	}
 
+	/*
+	 * The curr_ret_stack is an index to ftrace return stack of
+	 * current task.  Its value should be in [0, FTRACE_RETFUNC_
+	 * DEPTH) when the function graph tracer is used.  To support
+	 * filtering out specific functions, it makes the index
+	 * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
+	 * so when it sees a negative index the ftrace will ignore
+	 * the record.  And the index gets recovered when returning
+	 * from the filtered function by adding the FTRACE_NOTRACE_
+	 * DEPTH and then it'll continue to record functions normally.
+	 *
+	 * The curr_ret_stack is initialized to -1 and get increased
+	 * in this function.  So it can be less than -1 only if it was
+	 * filtered out via ftrace_graph_notrace_addr() which can be
+	 * set from set_graph_notrace file in debugfs by user.
+	 */
+	if (current->curr_ret_stack < -1)
+		return -EBUSY;
+
 	calltime = trace_clock_local();
 
 	index = ++current->curr_ret_stack;
+	if (ftrace_graph_notrace_addr(func))
+		current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
 	barrier();
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
 	current->ret_stack[index].subtime = 0;
 	current->ret_stack[index].fp = frame_pointer;
-	*depth = index;
+	*depth = current->curr_ret_stack;
 
 	return 0;
 }
@@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 
 	index = current->curr_ret_stack;
 
-	if (unlikely(index < 0)) {
+	/*
+	 * A negative index here means that it's just returned from a
+	 * notrace'd function.  Recover index to get an original
+	 * return address.  See ftrace_push_return_trace().
+	 *
+	 * TODO: Need to check whether the stack gets corrupted.
+	 */
+	if (index < 0)
+		index += FTRACE_NOTRACE_DEPTH;
+
+	if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
 		/* Might as well panic, otherwise we have no where to go */
@@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	trace.rettime = trace_clock_local();
 	barrier();
 	current->curr_ret_stack--;
+	/*
+	 * The curr_ret_stack can be less than -1 only if it was
+	 * filtered out and it's about to return from the function.
+	 * Recover the index and continue to trace normal functions.
+	 */
+	if (current->curr_ret_stack < -1) {
+		current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
+		return ret;
+	}
 
 	/*
 	 * The trace should run after decrementing the ret counter
@@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 
 	/* trace it when it is-nested-in or is a function enabled. */
 	if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
-	     ftrace_graph_ignore_irqs()) ||
+	     ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
 	    (max_depth && trace->depth >= max_depth))
 		return 0;
 
+	/*
+	 * Do not trace a function if it's filtered by set_graph_notrace.
+	 * Make the index of ret stack negative to indicate that it should
+	 * ignore further functions.  But it needs its own ret stack entry
+	 * to recover the original index in order to continue tracing after
+	 * returning from the function.
+	 */
+	if (ftrace_graph_notrace_addr(trace->func))
+		return 1;
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
-- 
cgit 


From 1653d2f88f43f6780eace1faeeb7b7adde8c10fb Mon Sep 17 00:00:00 2001
From: Thomas Pugliese <thomas.pugliese@gmail.com>
Date: Mon, 7 Oct 2013 10:07:51 -0500
Subject: usb: wusbcore: preserve endianness of cached descriptors

Do not overwrite the multi-byte fields of usb_wa_descriptor with their
cpu format values after reading the descriptor.  Leave the values as
__le16 and swap on use.  This is more consistent with other uses of USB
descriptors.

Signed-off-by: Thomas Pugliese <thomas.pugliese@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/hwa-hc.c       | 10 +++-------
 drivers/usb/wusbcore/wa-rpipe.c |  2 +-
 include/linux/usb/wusb-wa.h     |  6 +++---
 3 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/host/hwa-hc.c b/drivers/usb/host/hwa-hc.c
index e58b92491eb1..e5fb3cfd57a9 100644
--- a/drivers/usb/host/hwa-hc.c
+++ b/drivers/usb/host/hwa-hc.c
@@ -570,14 +570,10 @@ found:
 		goto error;
 	}
 	wa->wa_descr = wa_descr = (struct usb_wa_descriptor *) hdr;
-	/* Make LE fields CPU order */
-	wa_descr->bcdWAVersion = le16_to_cpu(wa_descr->bcdWAVersion);
-	wa_descr->wNumRPipes = le16_to_cpu(wa_descr->wNumRPipes);
-	wa_descr->wRPipeMaxBlock = le16_to_cpu(wa_descr->wRPipeMaxBlock);
-	if (wa_descr->bcdWAVersion > 0x0100)
+	if (le16_to_cpu(wa_descr->bcdWAVersion) > 0x0100)
 		dev_warn(dev, "Wire Adapter v%d.%d newer than groked v1.0\n",
-			 wa_descr->bcdWAVersion & 0xff00 >> 8,
-			 wa_descr->bcdWAVersion & 0x00ff);
+			 le16_to_cpu(wa_descr->bcdWAVersion) & 0xff00 >> 8,
+			 le16_to_cpu(wa_descr->bcdWAVersion) & 0x00ff);
 	result = 0;
 error:
 	return result;
diff --git a/drivers/usb/wusbcore/wa-rpipe.c b/drivers/usb/wusbcore/wa-rpipe.c
index 50de1d2c7b72..1ed068accb76 100644
--- a/drivers/usb/wusbcore/wa-rpipe.c
+++ b/drivers/usb/wusbcore/wa-rpipe.c
@@ -480,7 +480,7 @@ error:
  */
 int wa_rpipes_create(struct wahc *wa)
 {
-	wa->rpipes = wa->wa_descr->wNumRPipes;
+	wa->rpipes = le16_to_cpu(wa->wa_descr->wNumRPipes);
 	wa->rpipe_bm = kzalloc(BITS_TO_LONGS(wa->rpipes)*sizeof(unsigned long),
 			       GFP_KERNEL);
 	if (wa->rpipe_bm == NULL)
diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h
index 9ae7e299bf77..c1257130769b 100644
--- a/include/linux/usb/wusb-wa.h
+++ b/include/linux/usb/wusb-wa.h
@@ -279,11 +279,11 @@ struct wa_xfer_result {
 struct usb_wa_descriptor {
 	u8	bLength;
 	u8	bDescriptorType;
-	u16	bcdWAVersion;
+	__le16	bcdWAVersion;
 	u8	bNumPorts;		/* don't use!! */
 	u8	bmAttributes;		/* Reserved == 0 */
-	u16	wNumRPipes;
-	u16	wRPipeMaxBlock;
+	__le16	wNumRPipes;
+	__le16	wRPipeMaxBlock;
 	u8	bRPipeBlockSize;
 	u8	bPwrOn2PwrGood;
 	u8	bNumMMCIEs;
-- 
cgit 


From 79830f66e3cbd224bcf697b032dce9828b5a3c9e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 18 Oct 2013 16:38:09 -0700
Subject: Bluetooth: Select the own address type during initial setup phase

The own address type is based on the fact if the controller has
a public address or not. This means that this detail can be just
configured once during setup phase.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_conn.c         |  7 +------
 net/bluetooth/hci_core.c         | 13 ++++++++++++-
 net/bluetooth/mgmt.c             | 10 ++--------
 4 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9b5db01bd1a2..0daac39c1b6e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -142,6 +142,7 @@ struct hci_dev {
 	__u8		dev_type;
 	bdaddr_t	bdaddr;
 	bdaddr_t	static_addr;
+	__u8		own_addr_type;
 	__u8		dev_name[HCI_MAX_NAME_LENGTH];
 	__u8		short_name[HCI_MAX_SHORT_NAME_LENGTH];
 	__u8		eir[HCI_MAX_EIR_LENGTH];
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 4e726505f52b..974d7bccbb6f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -615,12 +615,7 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	else
 		conn->dst_type = ADDR_LE_DEV_RANDOM;
 
-	if (bacmp(&conn->src, BDADDR_ANY)) {
-		conn->src_type = ADDR_LE_DEV_PUBLIC;
-	} else {
-		bacpy(&conn->src, &hdev->static_addr);
-		conn->src_type = ADDR_LE_DEV_RANDOM;
-	}
+	conn->src_type = hdev->own_addr_type;
 
 	conn->state = BT_CONNECT;
 	conn->out = true;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 6b1844f00fbf..c130a239c0de 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1053,8 +1053,19 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt)
 	if (hdev->commands[5] & 0x10)
 		hci_setup_link_policy(req);
 
-	if (lmp_le_capable(hdev))
+	if (lmp_le_capable(hdev)) {
+		/* If the controller has a public BD_ADDR, then by
+		 * default use that one. If this is a LE only
+		 * controller without one, default to the random
+		 * address.
+		 */
+		if (bacmp(&hdev->bdaddr, BDADDR_ANY))
+			hdev->own_addr_type = ADDR_LE_DEV_PUBLIC;
+		else
+			hdev->own_addr_type = ADDR_LE_DEV_RANDOM;
+
 		hci_set_le_support(req);
+	}
 
 	/* Read features beyond page 1 if available */
 	for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a727b47fcac5..fb7fc9f17af1 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1325,10 +1325,7 @@ static void enable_advertising(struct hci_request *req)
 	cp.min_interval = __constant_cpu_to_le16(0x0800);
 	cp.max_interval = __constant_cpu_to_le16(0x0800);
 	cp.type = get_adv_type(hdev);
-	if (bacmp(&hdev->bdaddr, BDADDR_ANY))
-		cp.own_address_type = ADDR_LE_DEV_PUBLIC;
-	else
-		cp.own_address_type = ADDR_LE_DEV_RANDOM;
+	cp.own_address_type = hdev->own_addr_type;
 	cp.channel_map = 0x07;
 
 	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
@@ -3237,10 +3234,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev,
 		param_cp.type = LE_SCAN_ACTIVE;
 		param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT);
 		param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN);
-		if (bacmp(&hdev->bdaddr, BDADDR_ANY))
-			param_cp.own_address_type = ADDR_LE_DEV_PUBLIC;
-		else
-			param_cp.own_address_type = ADDR_LE_DEV_RANDOM;
+		param_cp.own_address_type = hdev->own_addr_type;
 		hci_req_add(&req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
 			    &param_cp);
 
-- 
cgit 


From 3497ac84bd35bc5b984a3a20625021bfb0ca3f37 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 19 Oct 2013 05:26:57 -0700
Subject: Bluetooth: Remove interval parameter from HCI connection

The conn->interval parameter of HCI connections is not used at all
and so just remove it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 -
 net/bluetooth/hci_event.c        | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0daac39c1b6e..c689bcf4a0f7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -315,7 +315,6 @@ struct hci_conn {
 	__u8		attempt;
 	__u8		dev_class[3];
 	__u8		features[HCI_MAX_PAGES][8];
-	__u16		interval;
 	__u16		pkt_type;
 	__u16		link_policy;
 	__u32		link_mode;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 848045223e98..1214d4b6f541 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2549,7 +2549,6 @@ static void hci_mode_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle));
 	if (conn) {
 		conn->mode = ev->mode;
-		conn->interval = __le16_to_cpu(ev->interval);
 
 		if (!test_and_clear_bit(HCI_CONN_MODE_CHANGE_PEND,
 					&conn->flags)) {
-- 
cgit 


From 06f5b7785af6beebb7b2a452687b5a102c90ca6e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 19 Oct 2013 07:09:11 -0700
Subject: Bluetooth: Add support for setting SSP debug mode

Enabling and disabling SSP debug mode is useful for development. This
adds a debugfs entry that allows to configure the SSP debug mode.

On purpose this has been implemented as debugfs entry and not a public
API since it is really only useful during testing and development.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h      |  2 ++
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 54 +++++++++++++++++++++++++++++++++++++++-
 net/bluetooth/hci_event.c        |  2 ++
 4 files changed, 58 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 77a971aefcff..ac9c4a75e314 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1043,6 +1043,8 @@ struct hci_rp_write_remote_amp_assoc {
 	__u8     phy_handle;
 } __packed;
 
+#define HCI_OP_WRITE_SSP_DEBUG_MODE	0x1804
+
 #define HCI_OP_LE_SET_EVENT_MASK	0x2001
 struct hci_cp_le_set_event_mask {
 	__u8     mask[8];
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index c689bcf4a0f7..d50cc7aca4e4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -169,6 +169,7 @@ struct hci_dev {
 	__u8		page_scan_type;
 	__u16		le_scan_interval;
 	__u16		le_scan_window;
+	__u8		ssp_debug_mode;
 
 	__u16		devid_source;
 	__u16		devid_vendor;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 384b9db16f69..2a9e92503fd6 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -303,6 +303,55 @@ static int auto_accept_delay_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get,
 			auto_accept_delay_set, "%llu\n");
 
+static int ssp_debug_mode_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+	struct sk_buff *skb;
+	__u8 mode;
+	int err;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	if (!test_bit(HCI_UP, &hdev->flags))
+		return -ENETDOWN;
+
+	hci_req_lock(hdev);
+	mode = val;
+	skb = __hci_cmd_sync(hdev, HCI_OP_WRITE_SSP_DEBUG_MODE, sizeof(mode),
+			     &mode, HCI_CMD_TIMEOUT);
+	hci_req_unlock(hdev);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	err = -bt_to_errno(skb->data[0]);
+	kfree_skb(skb);
+
+	if (err < 0)
+		return err;
+
+	hci_dev_lock(hdev);
+	hdev->ssp_debug_mode = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int ssp_debug_mode_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->ssp_debug_mode;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(ssp_debug_mode_fops, ssp_debug_mode_get,
+			ssp_debug_mode_set, "%llu\n");
+
 static int idle_timeout_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -1199,9 +1248,12 @@ static int __hci_init(struct hci_dev *hdev)
 				    hdev, &voice_setting_fops);
 	}
 
-	if (lmp_ssp_capable(hdev))
+	if (lmp_ssp_capable(hdev)) {
 		debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
 				    hdev, &auto_accept_delay_fops);
+		debugfs_create_file("ssp_debug_mode", 0644, hdev->debugfs,
+				    hdev, &ssp_debug_mode_fops);
+	}
 
 	if (lmp_sniff_capable(hdev)) {
 		debugfs_create_file("idle_timeout", 0644, hdev->debugfs,
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 1214d4b6f541..5935f748c0f9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -198,6 +198,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 
 	memset(hdev->scan_rsp_data, 0, sizeof(hdev->scan_rsp_data));
 	hdev->scan_rsp_data_len = 0;
+
+	hdev->ssp_debug_mode = 0;
 }
 
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
-- 
cgit 


From 4e70c7e71c5f9cf11013628ab5a0ced449b1c7b2 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 19 Oct 2013 07:09:13 -0700
Subject: Bluetooth: Expose debugfs settings for LE connection interval

For testing purposes expose the default LE connection interval values
via debugfs.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_conn.c         |  5 ++--
 net/bluetooth/hci_core.c         | 62 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d50cc7aca4e4..8c0ab3d86f95 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -169,6 +169,8 @@ struct hci_dev {
 	__u8		page_scan_type;
 	__u16		le_scan_interval;
 	__u16		le_scan_window;
+	__u16		le_conn_min_interval;
+	__u16		le_conn_max_interval;
 	__u8		ssp_debug_mode;
 
 	__u16		devid_source;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 974d7bccbb6f..ba5366c320da 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -558,11 +558,12 @@ static int hci_create_le_conn(struct hci_conn *conn)
 	bacpy(&cp.peer_addr, &conn->dst);
 	cp.peer_addr_type = conn->dst_type;
 	cp.own_address_type = conn->src_type;
-	cp.conn_interval_min = __constant_cpu_to_le16(0x0028);
-	cp.conn_interval_max = __constant_cpu_to_le16(0x0038);
+	cp.conn_interval_min = cpu_to_le16(hdev->le_conn_min_interval);
+	cp.conn_interval_max = cpu_to_le16(hdev->le_conn_max_interval);
 	cp.supervision_timeout = __constant_cpu_to_le16(0x002a);
 	cp.min_ce_len = __constant_cpu_to_le16(0x0000);
 	cp.max_ce_len = __constant_cpu_to_le16(0x0000);
+
 	hci_req_add(&req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
 
 	err = hci_req_run(&req, create_le_conn_complete);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2a9e92503fd6..8149e1303e2b 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -517,6 +517,62 @@ static const struct file_operations long_term_keys_fops = {
 	.release	= single_release,
 };
 
+static int conn_min_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_conn_min_interval= val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_min_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_conn_min_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_min_interval_fops, conn_min_interval_get,
+			conn_min_interval_set, "%llu\n");
+
+static int conn_max_interval_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->le_conn_max_interval= val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_max_interval_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->le_conn_max_interval;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get,
+			conn_max_interval_set, "%llu\n");
+
 /* ---- HCI requests ---- */
 
 static void hci_req_sync_complete(struct hci_dev *hdev, u8 result)
@@ -1273,6 +1329,10 @@ static int __hci_init(struct hci_dev *hdev)
 				    hdev, &own_address_type_fops);
 		debugfs_create_file("long_term_keys", 0400, hdev->debugfs,
 				    hdev, &long_term_keys_fops);
+		debugfs_create_file("conn_min_interval", 0644, hdev->debugfs,
+				    hdev, &conn_min_interval_fops);
+		debugfs_create_file("conn_max_interval", 0644, hdev->debugfs,
+				    hdev, &conn_max_interval_fops);
 	}
 
 	return 0;
@@ -2738,6 +2798,8 @@ struct hci_dev *hci_alloc_dev(void)
 
 	hdev->le_scan_interval = 0x0060;
 	hdev->le_scan_window = 0x0030;
+	hdev->le_conn_min_interval = 0x0028;
+	hdev->le_conn_max_interval = 0x0038;
 
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
-- 
cgit 


From 4b4148e9acc1a51c454f133637e5dc7e298bd5bb Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 19 Oct 2013 07:09:12 -0700
Subject: Bluetooth: Add support for setting DUT mode

The Device Under Test (DUT) mode is useful for doing certification
testing and so expose this as debugfs option.

This mode is actually special since you can only enter it. Restoring
normal operation means that a HCI Reset is required. The current mode
value gets tracked as a new device flag and when disabling it, the
correct command to reset the controller is sent.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  3 ++
 net/bluetooth/hci_core.c    | 73 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index ac9c4a75e314..1784c48699f0 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -115,6 +115,7 @@ enum {
 	HCI_PAIRABLE,
 	HCI_SERVICE_CACHE,
 	HCI_DEBUG_KEYS,
+	HCI_DUT_MODE,
 	HCI_UNREGISTER,
 	HCI_USER_CHANNEL,
 
@@ -1043,6 +1044,8 @@ struct hci_rp_write_remote_amp_assoc {
 	__u8     phy_handle;
 } __packed;
 
+#define HCI_OP_ENABLE_DUT_MODE		0x1803
+
 #define HCI_OP_WRITE_SSP_DEBUG_MODE	0x1804
 
 #define HCI_OP_LE_SET_EVENT_MASK	0x2001
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 8149e1303e2b..b5c8cb3c96d2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -58,6 +58,71 @@ static void hci_notify(struct hci_dev *hdev, int event)
 
 /* ---- HCI debugfs entries ---- */
 
+static ssize_t dut_mode_read(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_DUT_MODE, &hdev->dev_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t dut_mode_write(struct file *file, const char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	struct sk_buff *skb;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+	bool enable;
+	int err;
+
+	if (!test_bit(HCI_UP, &hdev->flags))
+		return -ENETDOWN;
+
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
+		return -EINVAL;
+
+	if (enable == test_bit(HCI_DUT_MODE, &hdev->dev_flags))
+		return -EALREADY;
+
+	hci_req_lock(hdev);
+	if (enable)
+		skb = __hci_cmd_sync(hdev, HCI_OP_ENABLE_DUT_MODE, 0, NULL,
+				     HCI_CMD_TIMEOUT);
+	else
+		skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL,
+				     HCI_CMD_TIMEOUT);
+	hci_req_unlock(hdev);
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	err = -bt_to_errno(skb->data[0]);
+	kfree_skb(skb);
+
+	if (err < 0)
+		return err;
+
+	change_bit(HCI_DUT_MODE, &hdev->dev_flags);
+
+	return count;
+}
+
+static const struct file_operations dut_mode_fops = {
+	.open		= simple_open,
+	.read		= dut_mode_read,
+	.write		= dut_mode_write,
+	.llseek		= default_llseek,
+};
+
 static int features_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
@@ -1256,6 +1321,14 @@ static int __hci_init(struct hci_dev *hdev)
 	if (err < 0)
 		return err;
 
+	/* The Device Under Test (DUT) mode is special and available for
+	 * all controller types. So just create it early on.
+	 */
+	if (test_bit(HCI_SETUP, &hdev->dev_flags)) {
+		debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
+				    &dut_mode_fops);
+	}
+
 	/* HCI_BREDR covers both single-mode LE, BR/EDR and dual-mode
 	 * BR/EDR/LE type controllers. AMP controllers only need the
 	 * first stage init.
-- 
cgit 


From 79a9becda8940deb2274b5aa4577c86d52ee7ecb Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Thu, 17 Oct 2013 10:21:36 -0700
Subject: gpiolib: export descriptor-based GPIO interface

This patch exports the gpiod_* family of API functions, a safer
alternative to the legacy GPIO interface. Differences between the gpiod
and legacy gpio APIs are:

- gpio works with integers, whereas gpiod operates on opaque handlers
  which cannot be forged or used before proper acquisition
- gpiod get/set functions are aware of the active low state of a GPIO
- gpio consumers should now include <linux/gpio/consumer.h> to access
  the new interface, whereas chips drivers will use
  <linux/gpio/driver.h>

The legacy gpio API is now built as inline functions on top of gpiod.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c        | 422 ++++++++++++++++++++++--------------------
 include/asm-generic/gpio.h    | 222 +++++++---------------
 include/linux/gpio.h          |  11 +-
 include/linux/gpio/consumer.h | 238 ++++++++++++++++++++++++
 include/linux/gpio/driver.h   | 127 +++++++++++++
 5 files changed, 658 insertions(+), 362 deletions(-)
 create mode 100644 include/linux/gpio/consumer.h
 create mode 100644 include/linux/gpio/driver.h

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d66139dc410d..224abdc4b095 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -16,16 +16,11 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/gpio.h>
 
-/* Optional implementation infrastructure for GPIO interfaces.
+/* Implementation infrastructure for GPIO interfaces.
  *
- * Platforms may want to use this if they tend to use very many GPIOs
- * that aren't part of a System-On-Chip core; or across I2C/SPI/etc.
- *
- * When kernel footprint or instruction count is an issue, simpler
- * implementations may be preferred.  The GPIO programming interface
- * allows for inlining speed-critical get/set operations for common
- * cases, so that access to SOC-integrated GPIOs can sometimes cost
- * only an instruction or two per bit.
+ * The GPIO programming interface allows for inlining speed-critical
+ * get/set operations for common cases, so that access to SOC-integrated
+ * GPIOs can sometimes cost only an instruction or two per bit.
  */
 
 
@@ -57,7 +52,7 @@ struct gpio_desc {
 #define FLAG_SYSFS	3	/* exported via /sys/class/gpio/control */
 #define FLAG_TRIG_FALL	4	/* trigger on falling edge */
 #define FLAG_TRIG_RISE	5	/* trigger on rising edge */
-#define FLAG_ACTIVE_LOW	6	/* sysfs value has active low */
+#define FLAG_ACTIVE_LOW	6	/* value has active low */
 #define FLAG_OPEN_DRAIN	7	/* Gpio is open drain type */
 #define FLAG_OPEN_SOURCE 8	/* Gpio is open source type */
 #define FLAG_USED_AS_IRQ 9	/* GPIO is connected to an IRQ */
@@ -81,29 +76,8 @@ static LIST_HEAD(gpio_chips);
 static DEFINE_IDR(dirent_idr);
 #endif
 
-/*
- * Internal gpiod_* API using descriptors instead of the integer namespace.
- * Most of this should eventually go public.
- */
 static int gpiod_request(struct gpio_desc *desc, const char *label);
 static void gpiod_free(struct gpio_desc *desc);
-static int gpiod_direction_input(struct gpio_desc *desc);
-static int gpiod_direction_output(struct gpio_desc *desc, int value);
-static int gpiod_get_direction(const struct gpio_desc *desc);
-static int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
-static int gpiod_get_value_cansleep(const struct gpio_desc *desc);
-static void gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
-static int gpiod_get_value(const struct gpio_desc *desc);
-static void gpiod_set_value(struct gpio_desc *desc, int value);
-static int gpiod_cansleep(const struct gpio_desc *desc);
-static int gpiod_to_irq(const struct gpio_desc *desc);
-static int gpiod_lock_as_irq(struct gpio_desc *desc);
-static void gpiod_unlock_as_irq(struct gpio_desc *desc);
-static int gpiod_export(struct gpio_desc *desc, bool direction_may_change);
-static int gpiod_export_link(struct device *dev, const char *name,
-			     struct gpio_desc *desc);
-static int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value);
-static void gpiod_unexport(struct gpio_desc *desc);
 
 #ifdef CONFIG_DEBUG_FS
 #define gpiod_emerg(desc, fmt, ...)			                \
@@ -157,13 +131,14 @@ static int gpio_chip_hwgpio(const struct gpio_desc *desc)
 /**
  * Convert a GPIO number to its descriptor
  */
-static struct gpio_desc *gpio_to_desc(unsigned gpio)
+struct gpio_desc *gpio_to_desc(unsigned gpio)
 {
 	if (WARN(!gpio_is_valid(gpio), "invalid GPIO %d\n", gpio))
 		return NULL;
 	else
 		return &gpio_desc[gpio];
 }
+EXPORT_SYMBOL_GPL(gpio_to_desc);
 
 /**
  * Convert an offset on a certain chip to a corresponding descriptor
@@ -181,10 +156,11 @@ static struct gpio_desc *gpiochip_offset_to_desc(struct gpio_chip *chip,
  * This should disappear in the future but is needed since we still
  * use GPIO numbers for error messages and sysfs nodes
  */
-static int desc_to_gpio(const struct gpio_desc *desc)
+int desc_to_gpio(const struct gpio_desc *desc)
 {
 	return desc - &gpio_desc[0];
 }
+EXPORT_SYMBOL_GPL(desc_to_gpio);
 
 
 /* Warn when drivers omit gpio_request() calls -- legal but ill-advised
@@ -219,16 +195,15 @@ static int gpio_ensure_requested(struct gpio_desc *desc)
 	return 0;
 }
 
-static struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
+/**
+ * gpiod_to_chip - Return the GPIO chip to which a GPIO descriptor belongs
+ * @desc:	descriptor to return the chip of
+ */
+struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
 {
 	return desc ? desc->chip : NULL;
 }
-
-/* caller holds gpio_lock *OR* gpio is marked as requested */
-struct gpio_chip *gpio_to_chip(unsigned gpio)
-{
-	return gpiod_to_chip(gpio_to_desc(gpio));
-}
+EXPORT_SYMBOL_GPL(gpiod_to_chip);
 
 /* dynamic allocation of GPIOs, e.g. on a hotplugged device */
 static int gpiochip_find_base(int ngpio)
@@ -254,8 +229,15 @@ static int gpiochip_find_base(int ngpio)
 	}
 }
 
-/* caller ensures gpio is valid and requested, chip->get_direction may sleep  */
-static int gpiod_get_direction(const struct gpio_desc *desc)
+/**
+ * gpiod_get_direction - return the current direction of a GPIO
+ * @desc:	GPIO to get the direction of
+ *
+ * Return GPIOF_DIR_IN or GPIOF_DIR_OUT, or an error code in case of error.
+ *
+ * This function may sleep if gpiod_cansleep() is true.
+ */
+int gpiod_get_direction(const struct gpio_desc *desc)
 {
 	struct gpio_chip	*chip;
 	unsigned		offset;
@@ -281,6 +263,7 @@ static int gpiod_get_direction(const struct gpio_desc *desc)
 	}
 	return status;
 }
+EXPORT_SYMBOL_GPL(gpiod_get_direction);
 
 #ifdef CONFIG_GPIO_SYSFS
 
@@ -365,17 +348,10 @@ static ssize_t gpio_value_show(struct device *dev,
 
 	mutex_lock(&sysfs_lock);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags)) {
+	if (!test_bit(FLAG_EXPORT, &desc->flags))
 		status = -EIO;
-	} else {
-		int value;
-
-		value = !!gpiod_get_value_cansleep(desc);
-		if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
-			value = !value;
-
-		status = sprintf(buf, "%d\n", value);
-	}
+	else
+		status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
 
 	mutex_unlock(&sysfs_lock);
 	return status;
@@ -398,9 +374,7 @@ static ssize_t gpio_value_store(struct device *dev,
 
 		status = kstrtol(buf, 0, &value);
 		if (status == 0) {
-			if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
-				value = !value;
-			gpiod_set_value_cansleep(desc, value != 0);
+			gpiod_set_value_cansleep(desc, value);
 			status = size;
 		}
 	}
@@ -790,7 +764,7 @@ static struct class gpio_class = {
 
 
 /**
- * gpio_export - export a GPIO through sysfs
+ * gpiod_export - export a GPIO through sysfs
  * @gpio: gpio to make available, already requested
  * @direction_may_change: true if userspace may change gpio direction
  * Context: arch_initcall or later
@@ -804,7 +778,7 @@ static struct class gpio_class = {
  *
  * Returns zero on success, else an error.
  */
-static int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
+int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 {
 	unsigned long		flags;
 	int			status;
@@ -882,12 +856,7 @@ fail_unlock:
 		 status);
 	return status;
 }
-
-int gpio_export(unsigned gpio, bool direction_may_change)
-{
-	return gpiod_export(gpio_to_desc(gpio), direction_may_change);
-}
-EXPORT_SYMBOL_GPL(gpio_export);
+EXPORT_SYMBOL_GPL(gpiod_export);
 
 static int match_export(struct device *dev, const void *data)
 {
@@ -895,7 +864,7 @@ static int match_export(struct device *dev, const void *data)
 }
 
 /**
- * gpio_export_link - create a sysfs link to an exported GPIO node
+ * gpiod_export_link - create a sysfs link to an exported GPIO node
  * @dev: device under which to create symlink
  * @name: name of the symlink
  * @gpio: gpio to create symlink to, already exported
@@ -905,8 +874,8 @@ static int match_export(struct device *dev, const void *data)
  *
  * Returns zero on success, else an error.
  */
-static int gpiod_export_link(struct device *dev, const char *name,
-			     struct gpio_desc *desc)
+int gpiod_export_link(struct device *dev, const char *name,
+		      struct gpio_desc *desc)
 {
 	int			status = -EINVAL;
 
@@ -937,15 +906,10 @@ static int gpiod_export_link(struct device *dev, const char *name,
 
 	return status;
 }
-
-int gpio_export_link(struct device *dev, const char *name, unsigned gpio)
-{
-	return gpiod_export_link(dev, name, gpio_to_desc(gpio));
-}
-EXPORT_SYMBOL_GPL(gpio_export_link);
+EXPORT_SYMBOL_GPL(gpiod_export_link);
 
 /**
- * gpio_sysfs_set_active_low - set the polarity of gpio sysfs value
+ * gpiod_sysfs_set_active_low - set the polarity of gpio sysfs value
  * @gpio: gpio to change
  * @value: non-zero to use active low, i.e. inverted values
  *
@@ -956,7 +920,7 @@ EXPORT_SYMBOL_GPL(gpio_export_link);
  *
  * Returns zero on success, else an error.
  */
-static int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
+int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
 {
 	struct device		*dev = NULL;
 	int			status = -EINVAL;
@@ -987,20 +951,15 @@ unlock:
 
 	return status;
 }
-
-int gpio_sysfs_set_active_low(unsigned gpio, int value)
-{
-	return gpiod_sysfs_set_active_low(gpio_to_desc(gpio), value);
-}
-EXPORT_SYMBOL_GPL(gpio_sysfs_set_active_low);
+EXPORT_SYMBOL_GPL(gpiod_sysfs_set_active_low);
 
 /**
- * gpio_unexport - reverse effect of gpio_export()
+ * gpiod_unexport - reverse effect of gpio_export()
  * @gpio: gpio to make unavailable
  *
  * This is implicit on gpio_free().
  */
-static void gpiod_unexport(struct gpio_desc *desc)
+void gpiod_unexport(struct gpio_desc *desc)
 {
 	int			status = 0;
 	struct device		*dev = NULL;
@@ -1033,12 +992,7 @@ static void gpiod_unexport(struct gpio_desc *desc)
 		pr_debug("%s: gpio%d status %d\n", __func__, desc_to_gpio(desc),
 			 status);
 }
-
-void gpio_unexport(unsigned gpio)
-{
-	gpiod_unexport(gpio_to_desc(gpio));
-}
-EXPORT_SYMBOL_GPL(gpio_unexport);
+EXPORT_SYMBOL_GPL(gpiod_unexport);
 
 static int gpiochip_export(struct gpio_chip *chip)
 {
@@ -1145,27 +1099,6 @@ static inline void gpiochip_unexport(struct gpio_chip *chip)
 {
 }
 
-static inline int gpiod_export(struct gpio_desc *desc,
-			       bool direction_may_change)
-{
-	return -ENOSYS;
-}
-
-static inline int gpiod_export_link(struct device *dev, const char *name,
-				    struct gpio_desc *desc)
-{
-	return -ENOSYS;
-}
-
-static inline int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
-{
-	return -ENOSYS;
-}
-
-static inline void gpiod_unexport(struct gpio_desc *desc)
-{
-}
-
 #endif /* CONFIG_GPIO_SYSFS */
 
 /*
@@ -1677,7 +1610,16 @@ EXPORT_SYMBOL_GPL(gpiochip_is_requested);
  * rely on gpio_request() having been called beforehand.
  */
 
-static int gpiod_direction_input(struct gpio_desc *desc)
+/**
+ * gpiod_direction_input - set the GPIO direction to input
+ * @desc:	GPIO to set to input
+ *
+ * Set the direction of the passed GPIO to input, such as gpiod_get_value() can
+ * be called safely on it.
+ *
+ * Return 0 in case of success, else an error code.
+ */
+int gpiod_direction_input(struct gpio_desc *desc)
 {
 	unsigned long		flags;
 	struct gpio_chip	*chip;
@@ -1734,14 +1676,19 @@ fail:
 		gpiod_dbg(desc, "%s status %d\n", __func__, status);
 	return status;
 }
+EXPORT_SYMBOL_GPL(gpiod_direction_input);
 
-int gpio_direction_input(unsigned gpio)
-{
-	return gpiod_direction_input(gpio_to_desc(gpio));
-}
-EXPORT_SYMBOL_GPL(gpio_direction_input);
-
-static int gpiod_direction_output(struct gpio_desc *desc, int value)
+/**
+ * gpiod_direction_output - set the GPIO direction to input
+ * @desc:	GPIO to set to output
+ * @value:	initial output value of the GPIO
+ *
+ * Set the direction of the passed GPIO to output, such as gpiod_set_value() can
+ * be called safely on it. The initial value of the output must be specified.
+ *
+ * Return 0 in case of success, else an error code.
+ */
+int gpiod_direction_output(struct gpio_desc *desc, int value)
 {
 	unsigned long		flags;
 	struct gpio_chip	*chip;
@@ -1814,22 +1761,17 @@ fail:
 		gpiod_dbg(desc, "%s: gpio status %d\n", __func__, status);
 	return status;
 }
-
-int gpio_direction_output(unsigned gpio, int value)
-{
-	return gpiod_direction_output(gpio_to_desc(gpio), value);
-}
-EXPORT_SYMBOL_GPL(gpio_direction_output);
+EXPORT_SYMBOL_GPL(gpiod_direction_output);
 
 /**
- * gpio_set_debounce - sets @debounce time for a @gpio
+ * gpiod_set_debounce - sets @debounce time for a @gpio
  * @gpio: the gpio to set debounce time
  * @debounce: debounce time is microseconds
  *
  * returns -ENOTSUPP if the controller does not support setting
  * debounce.
  */
-static int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
+int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 {
 	unsigned long		flags;
 	struct gpio_chip	*chip;
@@ -1871,12 +1813,19 @@ fail:
 
 	return status;
 }
+EXPORT_SYMBOL_GPL(gpiod_set_debounce);
 
-int gpio_set_debounce(unsigned gpio, unsigned debounce)
+/**
+ * gpiod_is_active_low - test whether a GPIO is active-low or not
+ * @desc: the gpio descriptor to test
+ *
+ * Returns 1 if the GPIO is active-low, 0 otherwise.
+ */
+int gpiod_is_active_low(const struct gpio_desc *desc)
 {
-	return gpiod_set_debounce(gpio_to_desc(gpio), debounce);
+	return test_bit(FLAG_ACTIVE_LOW, &desc->flags);
 }
-EXPORT_SYMBOL_GPL(gpio_set_debounce);
+EXPORT_SYMBOL_GPL(gpiod_is_active_low);
 
 /* I/O calls are only valid after configuration completed; the relevant
  * "is this a valid GPIO" error checks should already have been done.
@@ -1900,7 +1849,7 @@ EXPORT_SYMBOL_GPL(gpio_set_debounce);
  * that the GPIO was actually requested.
  */
 
-static int _gpiod_get_value(const struct gpio_desc *desc)
+static int _gpiod_get_raw_value(const struct gpio_desc *desc)
 {
 	struct gpio_chip	*chip;
 	int value;
@@ -1914,33 +1863,54 @@ static int _gpiod_get_value(const struct gpio_desc *desc)
 }
 
 /**
- * __gpio_get_value() - return a gpio's value
- * @gpio: gpio whose value will be returned
- * Context: any
+ * gpiod_get_raw_value() - return a gpio's raw value
+ * @desc: gpio whose value will be returned
  *
- * This is used directly or indirectly to implement gpio_get_value().
- * It returns the zero or nonzero value provided by the associated
- * gpio_chip.get() method; or zero if no such method is provided.
+ * Return the GPIO's raw value, i.e. the value of the physical line disregarding
+ * its ACTIVE_LOW status.
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
  */
-static int gpiod_get_value(const struct gpio_desc *desc)
+int gpiod_get_raw_value(const struct gpio_desc *desc)
 {
 	if (!desc)
 		return 0;
 	/* Should be using gpio_get_value_cansleep() */
 	WARN_ON(desc->chip->can_sleep);
-	return _gpiod_get_value(desc);
+	return _gpiod_get_raw_value(desc);
 }
+EXPORT_SYMBOL_GPL(gpiod_get_raw_value);
 
-int __gpio_get_value(unsigned gpio)
+/**
+ * gpiod_get_value() - return a gpio's value
+ * @desc: gpio whose value will be returned
+ *
+ * Return the GPIO's logical value, i.e. taking the ACTIVE_LOW status into
+ * account.
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
+ */
+int gpiod_get_value(const struct gpio_desc *desc)
 {
-	return gpiod_get_value(gpio_to_desc(gpio));
+	int value;
+	if (!desc)
+		return 0;
+	/* Should be using gpio_get_value_cansleep() */
+	WARN_ON(desc->chip->can_sleep);
+
+	value = _gpiod_get_raw_value(desc);
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+
+	return value;
 }
-EXPORT_SYMBOL_GPL(__gpio_get_value);
+EXPORT_SYMBOL_GPL(gpiod_get_value);
 
 /*
  *  _gpio_set_open_drain_value() - Set the open drain gpio's value.
- * @gpio: Gpio whose state need to be set.
- * @chip: Gpio chip.
+ * @desc: gpio descriptor whose state need to be set.
  * @value: Non-zero for setting it HIGH otherise it will set to LOW.
  */
 static void _gpio_set_open_drain_value(struct gpio_desc *desc, int value)
@@ -1966,9 +1936,8 @@ static void _gpio_set_open_drain_value(struct gpio_desc *desc, int value)
 }
 
 /*
- *  _gpio_set_open_source() - Set the open source gpio's value.
- * @gpio: Gpio whose state need to be set.
- * @chip: Gpio chip.
+ *  _gpio_set_open_source_value() - Set the open source gpio's value.
+ * @desc: gpio descriptor whose state need to be set.
  * @value: Non-zero for setting it HIGH otherise it will set to LOW.
  */
 static void _gpio_set_open_source_value(struct gpio_desc *desc, int value)
@@ -1993,7 +1962,7 @@ static void _gpio_set_open_source_value(struct gpio_desc *desc, int value)
 			  __func__, err);
 }
 
-static void _gpiod_set_value(struct gpio_desc *desc, int value)
+static void _gpiod_set_raw_value(struct gpio_desc *desc, int value)
 {
 	struct gpio_chip	*chip;
 
@@ -2008,62 +1977,70 @@ static void _gpiod_set_value(struct gpio_desc *desc, int value)
 }
 
 /**
- * __gpio_set_value() - assign a gpio's value
- * @gpio: gpio whose value will be assigned
+ * gpiod_set_raw_value() - assign a gpio's raw value
+ * @desc: gpio whose value will be assigned
  * @value: value to assign
- * Context: any
  *
- * This is used directly or indirectly to implement gpio_set_value().
- * It invokes the associated gpio_chip.set() method.
+ * Set the raw value of the GPIO, i.e. the value of its physical line without
+ * regard for its ACTIVE_LOW status.
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
  */
-static void gpiod_set_value(struct gpio_desc *desc, int value)
+void gpiod_set_raw_value(struct gpio_desc *desc, int value)
 {
-
 	if (!desc)
 		return;
 	/* Should be using gpio_set_value_cansleep() */
 	WARN_ON(desc->chip->can_sleep);
-	_gpiod_set_value(desc, value);
+	_gpiod_set_raw_value(desc, value);
 }
+EXPORT_SYMBOL_GPL(gpiod_set_raw_value);
 
-void __gpio_set_value(unsigned gpio, int value)
+/**
+ * gpiod_set_value() - assign a gpio's value
+ * @desc: gpio whose value will be assigned
+ * @value: value to assign
+ *
+ * Set the logical value of the GPIO, i.e. taking its ACTIVE_LOW status into
+ * account
+ *
+ * This function should be called from contexts where we cannot sleep, and will
+ * complain if the GPIO chip functions potentially sleep.
+ */
+void gpiod_set_value(struct gpio_desc *desc, int value)
 {
-	return gpiod_set_value(gpio_to_desc(gpio), value);
+	if (!desc)
+		return;
+	/* Should be using gpio_set_value_cansleep() */
+	WARN_ON(desc->chip->can_sleep);
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+	_gpiod_set_raw_value(desc, value);
 }
-EXPORT_SYMBOL_GPL(__gpio_set_value);
+EXPORT_SYMBOL_GPL(gpiod_set_value);
 
 /**
- * __gpio_cansleep() - report whether gpio value access will sleep
- * @gpio: gpio in question
- * Context: any
+ * gpiod_cansleep() - report whether gpio value access may sleep
+ * @desc: gpio to check
  *
- * This is used directly or indirectly to implement gpio_cansleep().  It
- * returns nonzero if access reading or writing the GPIO value can sleep.
  */
-static int gpiod_cansleep(const struct gpio_desc *desc)
+int gpiod_cansleep(const struct gpio_desc *desc)
 {
 	if (!desc)
 		return 0;
-	/* only call this on GPIOs that are valid! */
 	return desc->chip->can_sleep;
 }
-
-int __gpio_cansleep(unsigned gpio)
-{
-	return gpiod_cansleep(gpio_to_desc(gpio));
-}
-EXPORT_SYMBOL_GPL(__gpio_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_cansleep);
 
 /**
- * __gpio_to_irq() - return the IRQ corresponding to a GPIO
- * @gpio: gpio whose IRQ will be returned (already requested)
- * Context: any
+ * gpiod_to_irq() - return the IRQ corresponding to a GPIO
+ * @desc: gpio whose IRQ will be returned (already requested)
  *
- * This is used directly or indirectly to implement gpio_to_irq().
- * It returns the number of the IRQ signaled by this (input) GPIO,
- * or a negative errno.
+ * Return the IRQ corresponding to the passed GPIO, or an error code in case of
+ * error.
  */
-static int gpiod_to_irq(const struct gpio_desc *desc)
+int gpiod_to_irq(const struct gpio_desc *desc)
 {
 	struct gpio_chip	*chip;
 	int			offset;
@@ -2074,12 +2051,7 @@ static int gpiod_to_irq(const struct gpio_desc *desc)
 	offset = gpio_chip_hwgpio(desc);
 	return chip->to_irq ? chip->to_irq(chip, offset) : -ENXIO;
 }
-
-int __gpio_to_irq(unsigned gpio)
-{
-	return gpiod_to_irq(gpio_to_desc(gpio));
-}
-EXPORT_SYMBOL_GPL(__gpio_to_irq);
+EXPORT_SYMBOL_GPL(gpiod_to_irq);
 
 /**
  * gpiod_lock_as_irq() - lock a GPIO to be used as IRQ
@@ -2091,7 +2063,7 @@ EXPORT_SYMBOL_GPL(__gpio_to_irq);
  * of its irq_chip implementation if the GPIO is known from that
  * code.
  */
-static int gpiod_lock_as_irq(struct gpio_desc *desc)
+int gpiod_lock_as_irq(struct gpio_desc *desc)
 {
 	if (!desc)
 		return -EINVAL;
@@ -2106,6 +2078,7 @@ static int gpiod_lock_as_irq(struct gpio_desc *desc)
 	set_bit(FLAG_USED_AS_IRQ, &desc->flags);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(gpiod_lock_as_irq);
 
 int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
@@ -2120,13 +2093,14 @@ EXPORT_SYMBOL_GPL(gpio_lock_as_irq);
  * This is used directly by GPIO drivers that want to indicate
  * that a certain GPIO is no longer used exclusively for IRQ.
  */
-static void gpiod_unlock_as_irq(struct gpio_desc *desc)
+void gpiod_unlock_as_irq(struct gpio_desc *desc)
 {
 	if (!desc)
 		return;
 
 	clear_bit(FLAG_USED_AS_IRQ, &desc->flags);
 }
+EXPORT_SYMBOL_GPL(gpiod_unlock_as_irq);
 
 void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
@@ -2134,37 +2108,89 @@ void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
 }
 EXPORT_SYMBOL_GPL(gpio_unlock_as_irq);
 
-/* There's no value in making it easy to inline GPIO calls that may sleep.
- * Common examples include ones connected to I2C or SPI chips.
+/**
+ * gpiod_get_raw_value_cansleep() - return a gpio's raw value
+ * @desc: gpio whose value will be returned
+ *
+ * Return the GPIO's raw value, i.e. the value of the physical line disregarding
+ * its ACTIVE_LOW status.
+ *
+ * This function is to be called from contexts that can sleep.
  */
-
-static int gpiod_get_value_cansleep(const struct gpio_desc *desc)
+int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
 {
 	might_sleep_if(extra_checks);
 	if (!desc)
 		return 0;
-	return _gpiod_get_value(desc);
+	return _gpiod_get_raw_value(desc);
 }
+EXPORT_SYMBOL_GPL(gpiod_get_raw_value_cansleep);
 
-int gpio_get_value_cansleep(unsigned gpio)
+/**
+ * gpiod_get_value_cansleep() - return a gpio's value
+ * @desc: gpio whose value will be returned
+ *
+ * Return the GPIO's logical value, i.e. taking the ACTIVE_LOW status into
+ * account.
+ *
+ * This function is to be called from contexts that can sleep.
+ */
+int gpiod_get_value_cansleep(const struct gpio_desc *desc)
 {
-	return gpiod_get_value_cansleep(gpio_to_desc(gpio));
+	int value;
+
+	might_sleep_if(extra_checks);
+	if (!desc)
+		return 0;
+
+	value = _gpiod_get_raw_value(desc);
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+
+	return value;
 }
-EXPORT_SYMBOL_GPL(gpio_get_value_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_get_value_cansleep);
 
-static void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
+/**
+ * gpiod_set_raw_value_cansleep() - assign a gpio's raw value
+ * @desc: gpio whose value will be assigned
+ * @value: value to assign
+ *
+ * Set the raw value of the GPIO, i.e. the value of its physical line without
+ * regard for its ACTIVE_LOW status.
+ *
+ * This function is to be called from contexts that can sleep.
+ */
+void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value)
 {
 	might_sleep_if(extra_checks);
 	if (!desc)
 		return;
-	_gpiod_set_value(desc, value);
+	_gpiod_set_raw_value(desc, value);
 }
+EXPORT_SYMBOL_GPL(gpiod_set_raw_value_cansleep);
 
-void gpio_set_value_cansleep(unsigned gpio, int value)
+/**
+ * gpiod_set_value_cansleep() - assign a gpio's value
+ * @desc: gpio whose value will be assigned
+ * @value: value to assign
+ *
+ * Set the logical value of the GPIO, i.e. taking its ACTIVE_LOW status into
+ * account
+ *
+ * This function is to be called from contexts that can sleep.
+ */
+void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 {
-	return gpiod_set_value_cansleep(gpio_to_desc(gpio), value);
+	might_sleep_if(extra_checks);
+	if (!desc)
+		return;
+
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+	_gpiod_set_raw_value(desc, value);
 }
-EXPORT_SYMBOL_GPL(gpio_set_value_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
 #ifdef CONFIG_DEBUG_FS
 
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index b309a5c0019e..00f8f0a9edcd 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -10,6 +10,8 @@
 #ifdef CONFIG_GPIOLIB
 
 #include <linux/compiler.h>
+#include <linux/gpio/driver.h>
+#include <linux/gpio/consumer.h>
 
 /* Platforms may implement their GPIO interface with library code,
  * at a small performance cost for non-inlined operations and some
@@ -49,122 +51,11 @@ struct module;
 struct device_node;
 struct gpio_desc;
 
-/**
- * struct gpio_chip - abstract a GPIO controller
- * @label: for diagnostics
- * @dev: optional device providing the GPIOs
- * @owner: helps prevent removal of modules exporting active GPIOs
- * @list: links gpio_chips together for traversal
- * @request: optional hook for chip-specific activation, such as
- *	enabling module power and clock; may sleep
- * @free: optional hook for chip-specific deactivation, such as
- *	disabling module power and clock; may sleep
- * @get_direction: returns direction for signal "offset", 0=out, 1=in,
- *	(same as GPIOF_DIR_XXX), or negative error
- * @direction_input: configures signal "offset" as input, or returns error
- * @get: returns value for signal "offset"; for output signals this
- *	returns either the value actually sensed, or zero
- * @direction_output: configures signal "offset" as output, or returns error
- * @set_debounce: optional hook for setting debounce time for specified gpio in
- *      interrupt triggered gpio chips
- * @set: assigns output value for signal "offset"
- * @to_irq: optional hook supporting non-static gpio_to_irq() mappings;
- *	implementation may not sleep
- * @dbg_show: optional routine to show contents in debugfs; default code
- *	will be used when this is omitted, but custom code can show extra
- *	state (such as pullup/pulldown configuration).
- * @base: identifies the first GPIO number handled by this chip; or, if
- *	negative during registration, requests dynamic ID allocation.
- * @ngpio: the number of GPIOs handled by this controller; the last GPIO
- *	handled is (base + ngpio - 1).
- * @desc: array of ngpio descriptors. Private.
- * @can_sleep: flag must be set iff get()/set() methods sleep, as they
- *	must while accessing GPIO expander chips over I2C or SPI
- * @names: if set, must be an array of strings to use as alternative
- *      names for the GPIOs in this chip. Any entry in the array
- *      may be NULL if there is no alias for the GPIO, however the
- *      array must be @ngpio entries long.  A name can include a single printk
- *      format specifier for an unsigned int.  It is substituted by the actual
- *      number of the gpio.
- *
- * A gpio_chip can help platforms abstract various sources of GPIOs so
- * they can all be accessed through a common programing interface.
- * Example sources would be SOC controllers, FPGAs, multifunction
- * chips, dedicated GPIO expanders, and so on.
- *
- * Each chip controls a number of signals, identified in method calls
- * by "offset" values in the range 0..(@ngpio - 1).  When those signals
- * are referenced through calls like gpio_get_value(gpio), the offset
- * is calculated by subtracting @base from the gpio number.
- */
-struct gpio_chip {
-	const char		*label;
-	struct device		*dev;
-	struct module		*owner;
-	struct list_head        list;
-
-	int			(*request)(struct gpio_chip *chip,
-						unsigned offset);
-	void			(*free)(struct gpio_chip *chip,
-						unsigned offset);
-	int			(*get_direction)(struct gpio_chip *chip,
-						unsigned offset);
-	int			(*direction_input)(struct gpio_chip *chip,
-						unsigned offset);
-	int			(*get)(struct gpio_chip *chip,
-						unsigned offset);
-	int			(*direction_output)(struct gpio_chip *chip,
-						unsigned offset, int value);
-	int			(*set_debounce)(struct gpio_chip *chip,
-						unsigned offset, unsigned debounce);
-
-	void			(*set)(struct gpio_chip *chip,
-						unsigned offset, int value);
-
-	int			(*to_irq)(struct gpio_chip *chip,
-						unsigned offset);
-
-	void			(*dbg_show)(struct seq_file *s,
-						struct gpio_chip *chip);
-	int			base;
-	u16			ngpio;
-	struct gpio_desc	*desc;
-	const char		*const *names;
-	unsigned		can_sleep:1;
-	unsigned		exported:1;
-
-#if defined(CONFIG_OF_GPIO)
-	/*
-	 * If CONFIG_OF is enabled, then all GPIO controllers described in the
-	 * device tree automatically may have an OF translation
-	 */
-	struct device_node *of_node;
-	int of_gpio_n_cells;
-	int (*of_xlate)(struct gpio_chip *gc,
-		        const struct of_phandle_args *gpiospec, u32 *flags);
-#endif
-#ifdef CONFIG_PINCTRL
-	/*
-	 * If CONFIG_PINCTRL is enabled, then gpio controllers can optionally
-	 * describe the actual pin range which they serve in an SoC. This
-	 * information would be used by pinctrl subsystem to configure
-	 * corresponding pins for gpio usage.
-	 */
-	struct list_head pin_ranges;
-#endif
-};
-
-extern const char *gpiochip_is_requested(struct gpio_chip *chip,
-			unsigned offset);
-extern struct gpio_chip *gpio_to_chip(unsigned gpio);
-
-/* add/remove chips */
-extern int gpiochip_add(struct gpio_chip *chip);
-extern int __must_check gpiochip_remove(struct gpio_chip *chip);
-extern struct gpio_chip *gpiochip_find(void *data,
-					int (*match)(struct gpio_chip *chip,
-						     void *data));
-
+/* caller holds gpio_lock *OR* gpio is marked as requested */
+static inline struct gpio_chip *gpio_to_chip(unsigned gpio)
+{
+	return gpiod_to_chip(gpio_to_desc(gpio));
+}
 
 /* Always use the library code for GPIO management calls,
  * or when sleeping may be involved.
@@ -172,25 +63,52 @@ extern struct gpio_chip *gpiochip_find(void *data,
 extern int gpio_request(unsigned gpio, const char *label);
 extern void gpio_free(unsigned gpio);
 
-extern int gpio_direction_input(unsigned gpio);
-extern int gpio_direction_output(unsigned gpio, int value);
+static inline int gpio_direction_input(unsigned gpio)
+{
+	return gpiod_direction_input(gpio_to_desc(gpio));
+}
+static inline int gpio_direction_output(unsigned gpio, int value)
+{
+	return gpiod_direction_output(gpio_to_desc(gpio), value);
+}
 
-extern int gpio_set_debounce(unsigned gpio, unsigned debounce);
+static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
+{
+	return gpiod_set_debounce(gpio_to_desc(gpio), debounce);
+}
 
-extern int gpio_get_value_cansleep(unsigned gpio);
-extern void gpio_set_value_cansleep(unsigned gpio, int value);
+static inline int gpio_get_value_cansleep(unsigned gpio)
+{
+	return gpiod_get_raw_value_cansleep(gpio_to_desc(gpio));
+}
+static inline void gpio_set_value_cansleep(unsigned gpio, int value)
+{
+	return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value);
+}
 
 
 /* A platform's <asm/gpio.h> code may want to inline the I/O calls when
  * the GPIO is constant and refers to some always-present controller,
  * giving direct access to chip registers and tight bitbanging loops.
  */
-extern int __gpio_get_value(unsigned gpio);
-extern void __gpio_set_value(unsigned gpio, int value);
+static inline int __gpio_get_value(unsigned gpio)
+{
+	return gpiod_get_raw_value(gpio_to_desc(gpio));
+}
+static inline void __gpio_set_value(unsigned gpio, int value)
+{
+	return gpiod_set_raw_value(gpio_to_desc(gpio), value);
+}
 
-extern int __gpio_cansleep(unsigned gpio);
+static inline int __gpio_cansleep(unsigned gpio)
+{
+	return gpiod_cansleep(gpio_to_desc(gpio));
+}
 
-extern int __gpio_to_irq(unsigned gpio);
+static inline int __gpio_to_irq(unsigned gpio)
+{
+	return gpiod_to_irq(gpio_to_desc(gpio));
+}
 
 extern int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset);
 extern void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset);
@@ -199,19 +117,30 @@ extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *labe
 extern int gpio_request_array(const struct gpio *array, size_t num);
 extern void gpio_free_array(const struct gpio *array, size_t num);
 
-#ifdef CONFIG_GPIO_SYSFS
-
 /*
  * A sysfs interface can be exported by individual drivers if they want,
  * but more typically is configured entirely from userspace.
  */
-extern int gpio_export(unsigned gpio, bool direction_may_change);
-extern int gpio_export_link(struct device *dev, const char *name,
-			unsigned gpio);
-extern int gpio_sysfs_set_active_low(unsigned gpio, int value);
-extern void gpio_unexport(unsigned gpio);
+static inline int gpio_export(unsigned gpio, bool direction_may_change)
+{
+	return gpiod_export(gpio_to_desc(gpio), direction_may_change);
+}
 
-#endif	/* CONFIG_GPIO_SYSFS */
+static inline int gpio_export_link(struct device *dev, const char *name,
+				   unsigned gpio)
+{
+	return gpiod_export_link(dev, name, gpio_to_desc(gpio));
+}
+
+static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
+{
+	return gpiod_sysfs_set_active_low(gpio_to_desc(gpio), value);
+}
+
+static inline void gpio_unexport(unsigned gpio)
+{
+	gpiod_unexport(gpio_to_desc(gpio));
+}
 
 #ifdef CONFIG_PINCTRL
 
@@ -281,31 +210,4 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value)
 
 #endif /* !CONFIG_GPIOLIB */
 
-#ifndef CONFIG_GPIO_SYSFS
-
-struct device;
-
-/* sysfs support is only available with gpiolib, where it's optional */
-
-static inline int gpio_export(unsigned gpio, bool direction_may_change)
-{
-	return -ENOSYS;
-}
-
-static inline int gpio_export_link(struct device *dev, const char *name,
-				unsigned gpio)
-{
-	return -ENOSYS;
-}
-
-static inline int gpio_sysfs_set_active_low(unsigned gpio, int value)
-{
-	return -ENOSYS;
-}
-
-static inline void gpio_unexport(unsigned gpio)
-{
-}
-#endif	/* CONFIG_GPIO_SYSFS */
-
 #endif /* _ASM_GENERIC_GPIO_H */
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index a06ec3e85ba3..c691df044458 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -16,14 +16,17 @@
 #define GPIOF_OUT_INIT_LOW	(GPIOF_DIR_OUT | GPIOF_INIT_LOW)
 #define GPIOF_OUT_INIT_HIGH	(GPIOF_DIR_OUT | GPIOF_INIT_HIGH)
 
+/* Gpio pin is active-low */
+#define GPIOF_ACTIVE_LOW        (1 << 2)
+
 /* Gpio pin is open drain */
-#define GPIOF_OPEN_DRAIN	(1 << 2)
+#define GPIOF_OPEN_DRAIN	(1 << 3)
 
 /* Gpio pin is open source */
-#define GPIOF_OPEN_SOURCE	(1 << 3)
+#define GPIOF_OPEN_SOURCE	(1 << 4)
 
-#define GPIOF_EXPORT		(1 << 4)
-#define GPIOF_EXPORT_CHANGEABLE	(1 << 5)
+#define GPIOF_EXPORT		(1 << 5)
+#define GPIOF_EXPORT_CHANGEABLE	(1 << 6)
 #define GPIOF_EXPORT_DIR_FIXED	(GPIOF_EXPORT)
 #define GPIOF_EXPORT_DIR_CHANGEABLE (GPIOF_EXPORT | GPIOF_EXPORT_CHANGEABLE)
 
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
new file mode 100644
index 000000000000..2088eb50421c
--- /dev/null
+++ b/include/linux/gpio/consumer.h
@@ -0,0 +1,238 @@
+#ifndef __LINUX_GPIO_CONSUMER_H
+#define __LINUX_GPIO_CONSUMER_H
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+
+#ifdef CONFIG_GPIOLIB
+
+struct device;
+struct gpio_chip;
+
+/**
+ * Opaque descriptor for a GPIO. These are obtained using gpiod_get() and are
+ * preferable to the old integer-based handles.
+ *
+ * Contrary to integers, a pointer to a gpio_desc is guaranteed to be valid
+ * until the GPIO is released.
+ */
+struct gpio_desc;
+
+int gpiod_get_direction(const struct gpio_desc *desc);
+int gpiod_direction_input(struct gpio_desc *desc);
+int gpiod_direction_output(struct gpio_desc *desc, int value);
+
+/* Value get/set from non-sleeping context */
+int gpiod_get_value(const struct gpio_desc *desc);
+void gpiod_set_value(struct gpio_desc *desc, int value);
+int gpiod_get_raw_value(const struct gpio_desc *desc);
+void gpiod_set_raw_value(struct gpio_desc *desc, int value);
+
+/* Value get/set from sleeping context */
+int gpiod_get_value_cansleep(const struct gpio_desc *desc);
+void gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
+int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc);
+void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value);
+
+int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce);
+
+int gpiod_is_active_low(const struct gpio_desc *desc);
+int gpiod_cansleep(const struct gpio_desc *desc);
+
+int gpiod_to_irq(const struct gpio_desc *desc);
+
+/* Convert between the old gpio_ and new gpiod_ interfaces */
+struct gpio_desc *gpio_to_desc(unsigned gpio);
+int desc_to_gpio(const struct gpio_desc *desc);
+struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc);
+
+#else /* CONFIG_GPIOLIB */
+
+static inline struct gpio_desc *__must_check gpiod_get(struct device *dev,
+						       const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
+							     const char *con_id,
+							     unsigned int idx)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline void gpiod_put(struct gpio_desc *desc)
+{
+	might_sleep();
+
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+
+static inline struct gpio_desc *__must_check devm_gpiod_get(struct device *dev,
+							    const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline
+struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
+						    const char *con_id,
+						    unsigned int idx)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline void devm_gpiod_put(struct device *dev, struct gpio_desc *desc)
+{
+	might_sleep();
+
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+
+
+static inline int gpiod_get_direction(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -ENOSYS;
+}
+static inline int gpiod_direction_input(struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -ENOSYS;
+}
+static inline int gpiod_direction_output(struct gpio_desc *desc, int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -ENOSYS;
+}
+
+
+static inline int gpiod_get_value(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+static inline void gpiod_set_value(struct gpio_desc *desc, int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+static inline int gpiod_get_raw_value(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+
+static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
+						int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+
+static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -ENOSYS;
+}
+
+static inline int gpiod_is_active_low(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+static inline int gpiod_cansleep(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int gpiod_to_irq(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -EINVAL;
+}
+
+static inline struct gpio_desc *gpio_to_desc(unsigned gpio)
+{
+	return ERR_PTR(-EINVAL);
+}
+static inline int desc_to_gpio(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -EINVAL;
+}
+static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return ERR_PTR(-ENODEV);
+}
+
+
+#endif /* CONFIG_GPIOLIB */
+
+#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS)
+
+int gpiod_export(struct gpio_desc *desc, bool direction_may_change);
+int gpiod_export_link(struct device *dev, const char *name,
+		      struct gpio_desc *desc);
+int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value);
+void gpiod_unexport(struct gpio_desc *desc);
+
+#else  /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */
+
+static inline int gpiod_export(struct gpio_desc *desc,
+			       bool direction_may_change)
+{
+	return -ENOSYS;
+}
+
+static inline int gpiod_export_link(struct device *dev, const char *name,
+				    struct gpio_desc *desc)
+{
+	return -ENOSYS;
+}
+
+static inline int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
+{
+	return -ENOSYS;
+}
+
+static inline void gpiod_unexport(struct gpio_desc *desc)
+{
+}
+
+#endif /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */
+
+#endif
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
new file mode 100644
index 000000000000..5dc172c72f0f
--- /dev/null
+++ b/include/linux/gpio/driver.h
@@ -0,0 +1,127 @@
+#ifndef __LINUX_GPIO_DRIVER_H
+#define __LINUX_GPIO_DRIVER_H
+
+#include <linux/types.h>
+
+struct device;
+struct gpio_desc;
+
+/**
+ * struct gpio_chip - abstract a GPIO controller
+ * @label: for diagnostics
+ * @dev: optional device providing the GPIOs
+ * @owner: helps prevent removal of modules exporting active GPIOs
+ * @list: links gpio_chips together for traversal
+ * @request: optional hook for chip-specific activation, such as
+ *	enabling module power and clock; may sleep
+ * @free: optional hook for chip-specific deactivation, such as
+ *	disabling module power and clock; may sleep
+ * @get_direction: returns direction for signal "offset", 0=out, 1=in,
+ *	(same as GPIOF_DIR_XXX), or negative error
+ * @direction_input: configures signal "offset" as input, or returns error
+ * @direction_output: configures signal "offset" as output, or returns error
+ * @get: returns value for signal "offset"; for output signals this
+ *	returns either the value actually sensed, or zero
+ * @set: assigns output value for signal "offset"
+ * @set_debounce: optional hook for setting debounce time for specified gpio in
+ *      interrupt triggered gpio chips
+ * @to_irq: optional hook supporting non-static gpio_to_irq() mappings;
+ *	implementation may not sleep
+ * @dbg_show: optional routine to show contents in debugfs; default code
+ *	will be used when this is omitted, but custom code can show extra
+ *	state (such as pullup/pulldown configuration).
+ * @base: identifies the first GPIO number handled by this chip; or, if
+ *	negative during registration, requests dynamic ID allocation.
+ * @ngpio: the number of GPIOs handled by this controller; the last GPIO
+ *	handled is (base + ngpio - 1).
+ * @desc: array of ngpio descriptors. Private.
+ * @can_sleep: flag must be set iff get()/set() methods sleep, as they
+ *	must while accessing GPIO expander chips over I2C or SPI
+ * @names: if set, must be an array of strings to use as alternative
+ *      names for the GPIOs in this chip. Any entry in the array
+ *      may be NULL if there is no alias for the GPIO, however the
+ *      array must be @ngpio entries long.  A name can include a single printk
+ *      format specifier for an unsigned int.  It is substituted by the actual
+ *      number of the gpio.
+ *
+ * A gpio_chip can help platforms abstract various sources of GPIOs so
+ * they can all be accessed through a common programing interface.
+ * Example sources would be SOC controllers, FPGAs, multifunction
+ * chips, dedicated GPIO expanders, and so on.
+ *
+ * Each chip controls a number of signals, identified in method calls
+ * by "offset" values in the range 0..(@ngpio - 1).  When those signals
+ * are referenced through calls like gpio_get_value(gpio), the offset
+ * is calculated by subtracting @base from the gpio number.
+ */
+struct gpio_chip {
+	const char		*label;
+	struct device		*dev;
+	struct module		*owner;
+	struct list_head        list;
+
+	int			(*request)(struct gpio_chip *chip,
+						unsigned offset);
+	void			(*free)(struct gpio_chip *chip,
+						unsigned offset);
+	int			(*get_direction)(struct gpio_chip *chip,
+						unsigned offset);
+	int			(*direction_input)(struct gpio_chip *chip,
+						unsigned offset);
+	int			(*direction_output)(struct gpio_chip *chip,
+						unsigned offset, int value);
+	int			(*get)(struct gpio_chip *chip,
+						unsigned offset);
+	void			(*set)(struct gpio_chip *chip,
+						unsigned offset, int value);
+	int			(*set_debounce)(struct gpio_chip *chip,
+						unsigned offset,
+						unsigned debounce);
+
+	int			(*to_irq)(struct gpio_chip *chip,
+						unsigned offset);
+
+	void			(*dbg_show)(struct seq_file *s,
+						struct gpio_chip *chip);
+	int			base;
+	u16			ngpio;
+	struct gpio_desc	*desc;
+	const char		*const *names;
+	unsigned		can_sleep:1;
+	unsigned		exported:1;
+
+#if defined(CONFIG_OF_GPIO)
+	/*
+	 * If CONFIG_OF is enabled, then all GPIO controllers described in the
+	 * device tree automatically may have an OF translation
+	 */
+	struct device_node *of_node;
+	int of_gpio_n_cells;
+	int (*of_xlate)(struct gpio_chip *gc,
+			const struct of_phandle_args *gpiospec, u32 *flags);
+#endif
+#ifdef CONFIG_PINCTRL
+	/*
+	 * If CONFIG_PINCTRL is enabled, then gpio controllers can optionally
+	 * describe the actual pin range which they serve in an SoC. This
+	 * information would be used by pinctrl subsystem to configure
+	 * corresponding pins for gpio usage.
+	 */
+	struct list_head pin_ranges;
+#endif
+};
+
+extern const char *gpiochip_is_requested(struct gpio_chip *chip,
+			unsigned offset);
+
+/* add/remove chips */
+extern int gpiochip_add(struct gpio_chip *chip);
+extern int __must_check gpiochip_remove(struct gpio_chip *chip);
+extern struct gpio_chip *gpiochip_find(void *data,
+			      int (*match)(struct gpio_chip *chip, void *data));
+
+/* lock/unlock as IRQ */
+int gpiod_lock_as_irq(struct gpio_desc *desc);
+void gpiod_unlock_as_irq(struct gpio_desc *desc);
+
+#endif
-- 
cgit 


From af8b6375a8291fe2cf77707f3edec86b98a999cc Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Thu, 17 Oct 2013 10:21:37 -0700
Subject: gpiolib: port of_ functions to use gpiod

Refactor the of_ functions of gpiolib to use the now public gpiod
interface, and export of_get_named_gpiod_flags() and
of_get_gpiod_flags() functions.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-of.c | 28 +++++++++++++++++-----------
 include/linux/of_gpio.h   | 29 ++++++++++++++++++++++++-----
 2 files changed, 41 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 0dfaf20e4dad..32a396d891be 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -15,19 +15,21 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_gpio.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/slab.h>
 
+struct gpio_desc;
+
 /* Private data structure for of_gpiochip_find_and_xlate */
 struct gg_data {
 	enum of_gpio_flags *flags;
 	struct of_phandle_args gpiospec;
 
-	int out_gpio;
+	struct gpio_desc *out_gpio;
 };
 
 /* Private function for resolving node pointer to gpio_chip */
@@ -45,28 +47,31 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data)
 	if (ret < 0)
 		return false;
 
-	gg_data->out_gpio = ret + gc->base;
+	gg_data->out_gpio = gpio_to_desc(ret + gc->base);
 	return true;
 }
 
 /**
- * of_get_named_gpio_flags() - Get a GPIO number and flags to use with GPIO API
+ * of_get_named_gpiod_flags() - Get a GPIO descriptor and flags for GPIO API
  * @np:		device node to get GPIO from
  * @propname:	property name containing gpio specifier(s)
  * @index:	index of the GPIO
  * @flags:	a flags pointer to fill in
  *
- * Returns GPIO number to use with Linux generic GPIO API, or one of the errno
+ * Returns GPIO descriptor to use with Linux GPIO API, or one of the errno
  * value on the error condition. If @flags is not NULL the function also fills
  * in flags for the GPIO.
  */
-int of_get_named_gpio_flags(struct device_node *np, const char *propname,
-			   int index, enum of_gpio_flags *flags)
+struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
+		     const char *propname, int index, enum of_gpio_flags *flags)
 {
 	/* Return -EPROBE_DEFER to support probe() functions to be called
 	 * later when the GPIO actually becomes available
 	 */
-	struct gg_data gg_data = { .flags = flags, .out_gpio = -EPROBE_DEFER };
+	struct gg_data gg_data = {
+		.flags = flags,
+		.out_gpio = ERR_PTR(-EPROBE_DEFER)
+	};
 	int ret;
 
 	/* .of_xlate might decide to not fill in the flags, so clear it. */
@@ -78,16 +83,17 @@ int of_get_named_gpio_flags(struct device_node *np, const char *propname,
 	if (ret) {
 		pr_debug("%s: can't parse gpios property of node '%s[%d]'\n",
 			__func__, np->full_name, index);
-		return ret;
+		return ERR_PTR(ret);
 	}
 
 	gpiochip_find(&gg_data, of_gpiochip_find_and_xlate);
 
 	of_node_put(gg_data.gpiospec.np);
-	pr_debug("%s exited with status %d\n", __func__, gg_data.out_gpio);
+	pr_debug("%s exited with status %d\n", __func__,
+		 PTR_RET(gg_data.out_gpio));
 	return gg_data.out_gpio;
 }
-EXPORT_SYMBOL(of_get_named_gpio_flags);
+EXPORT_SYMBOL(of_get_named_gpiod_flags);
 
 /**
  * of_gpio_simple_xlate - translate gpio_spec to the GPIO number and flags
diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h
index a83dc6f5008e..d71f2cc141ae 100644
--- a/include/linux/of_gpio.h
+++ b/include/linux/of_gpio.h
@@ -21,6 +21,7 @@
 #include <linux/of.h>
 
 struct device_node;
+struct gpio_desc;
 
 /*
  * This is Linux-specific flags. By default controllers' and Linux' mapping
@@ -47,7 +48,7 @@ static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc)
 	return container_of(gc, struct of_mm_gpio_chip, gc);
 }
 
-extern int of_get_named_gpio_flags(struct device_node *np,
+extern struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
 		const char *list_name, int index, enum of_gpio_flags *flags);
 
 extern int of_mm_gpiochip_add(struct device_node *np,
@@ -62,10 +63,10 @@ extern int of_gpio_simple_xlate(struct gpio_chip *gc,
 #else /* CONFIG_OF_GPIO */
 
 /* Drivers may not strictly depend on the GPIO support, so let them link. */
-static inline int of_get_named_gpio_flags(struct device_node *np,
+static inline struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
 		const char *list_name, int index, enum of_gpio_flags *flags)
 {
-	return -ENOSYS;
+	return ERR_PTR(-ENOSYS);
 }
 
 static inline int of_gpio_simple_xlate(struct gpio_chip *gc,
@@ -80,6 +81,18 @@ static inline void of_gpiochip_remove(struct gpio_chip *gc) { }
 
 #endif /* CONFIG_OF_GPIO */
 
+static inline int of_get_named_gpio_flags(struct device_node *np,
+		const char *list_name, int index, enum of_gpio_flags *flags)
+{
+	struct gpio_desc *desc;
+	desc = of_get_named_gpiod_flags(np, list_name, index, flags);
+
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+	else
+		return desc_to_gpio(desc);
+}
+
 /**
  * of_gpio_named_count() - Count GPIOs for a device
  * @np:		device node to count GPIOs for
@@ -117,15 +130,21 @@ static inline int of_gpio_count(struct device_node *np)
 }
 
 /**
- * of_get_gpio_flags() - Get a GPIO number and flags to use with GPIO API
+ * of_get_gpiod_flags() - Get a GPIO descriptor and flags to use with GPIO API
  * @np:		device node to get GPIO from
  * @index:	index of the GPIO
  * @flags:	a flags pointer to fill in
  *
- * Returns GPIO number to use with Linux generic GPIO API, or one of the errno
+ * Returns GPIO descriptor to use with Linux generic GPIO API, or a errno
  * value on the error condition. If @flags is not NULL the function also fills
  * in flags for the GPIO.
  */
+static inline struct gpio_desc *of_get_gpiod_flags(struct device_node *np,
+					int index, enum of_gpio_flags *flags)
+{
+	return of_get_named_gpiod_flags(np, "gpios", index, flags);
+}
+
 static inline int of_get_gpio_flags(struct device_node *np, int index,
 		      enum of_gpio_flags *flags)
 {
-- 
cgit 


From bae48da237fcedd7ad09569025483b988635efb7 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Thu, 17 Oct 2013 10:21:38 -0700
Subject: gpiolib: add gpiod_get() and gpiod_put() functions

Add gpiod_get(), gpiod_get_index() and gpiod_put() functions that
provide safer management of GPIOs.

These functions put the GPIO framework in line with the conventions of
other frameworks in the kernel, and help ensure every GPIO is declared
properly and valid while it is used.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/devres.c         |  83 +++++++++++++++++
 drivers/gpio/gpiolib.c        | 203 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/gpio/consumer.h |  15 ++++
 include/linux/gpio/driver.h   |  56 ++++++++++++
 4 files changed, 357 insertions(+)

(limited to 'include')

diff --git a/drivers/gpio/devres.c b/drivers/gpio/devres.c
index 3e7812f0405e..2caa2571734e 100644
--- a/drivers/gpio/devres.c
+++ b/drivers/gpio/devres.c
@@ -19,6 +19,89 @@
 #include <linux/device.h>
 #include <linux/gfp.h>
 
+static void devm_gpiod_release(struct device *dev, void *res)
+{
+	struct gpio_desc **desc = res;
+
+	gpiod_put(*desc);
+}
+
+static int devm_gpiod_match(struct device *dev, void *res, void *data)
+{
+	struct gpio_desc **this = res, **gpio = data;
+
+	return *this == *gpio;
+}
+
+/**
+ * devm_gpiod_get - Resource-managed gpiod_get()
+ * @dev:	GPIO consumer
+ * @con_id:	function within the GPIO consumer
+ *
+ * Managed gpiod_get(). GPIO descriptors returned from this function are
+ * automatically disposed on driver detach. See gpiod_get() for detailed
+ * information about behavior and return values.
+ */
+struct gpio_desc *__must_check devm_gpiod_get(struct device *dev,
+					      const char *con_id)
+{
+	return devm_gpiod_get_index(dev, con_id, 0);
+}
+EXPORT_SYMBOL(devm_gpiod_get);
+
+/**
+ * devm_gpiod_get_index - Resource-managed gpiod_get_index()
+ * @dev:	GPIO consumer
+ * @con_id:	function within the GPIO consumer
+ * @idx:	index of the GPIO to obtain in the consumer
+ *
+ * Managed gpiod_get_index(). GPIO descriptors returned from this function are
+ * automatically disposed on driver detach. See gpiod_get_index() for detailed
+ * information about behavior and return values.
+ */
+struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
+						    const char *con_id,
+						    unsigned int idx)
+{
+	struct gpio_desc **dr;
+	struct gpio_desc *desc;
+
+	dr = devres_alloc(devm_gpiod_release, sizeof(struct gpiod_desc *),
+			  GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	desc = gpiod_get_index(dev, con_id, idx);
+	if (IS_ERR(desc)) {
+		devres_free(dr);
+		return desc;
+	}
+
+	*dr = desc;
+	devres_add(dev, dr);
+
+	return 0;
+}
+EXPORT_SYMBOL(devm_gpiod_get_index);
+
+/**
+ * devm_gpiod_put - Resource-managed gpiod_put()
+ * @desc:	GPIO descriptor to dispose of
+ *
+ * Dispose of a GPIO descriptor obtained with devm_gpiod_get() or
+ * devm_gpiod_get_index(). Normally this function will not be called as the GPIO
+ * will be disposed of by the resource management code.
+ */
+void devm_gpiod_put(struct device *dev, struct gpio_desc *desc)
+{
+	WARN_ON(devres_release(dev, devm_gpiod_release, devm_gpiod_match,
+		&desc));
+}
+EXPORT_SYMBOL(devm_gpiod_put);
+
+
+
+
 static void devm_gpio_release(struct device *dev, void *res)
 {
 	unsigned *gpio = res;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 224abdc4b095..9263c7b359b7 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -70,6 +70,8 @@ static struct gpio_desc gpio_desc[ARCH_NR_GPIOS];
 
 #define GPIO_OFFSET_VALID(chip, offset) (offset >= 0 && offset < chip->ngpio)
 
+static DEFINE_MUTEX(gpio_lookup_lock);
+static LIST_HEAD(gpio_lookup_list);
 static LIST_HEAD(gpio_chips);
 
 #ifdef CONFIG_GPIO_SYSFS
@@ -2192,6 +2194,207 @@ void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 }
 EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
+/**
+ * gpiod_add_table() - register GPIO device consumers
+ * @table: array of consumers to register
+ * @num: number of consumers in table
+ */
+void gpiod_add_table(struct gpiod_lookup *table, size_t size)
+{
+	mutex_lock(&gpio_lookup_lock);
+
+	while (size--) {
+		list_add_tail(&table->list, &gpio_lookup_list);
+		table++;
+	}
+
+	mutex_unlock(&gpio_lookup_lock);
+}
+
+/*
+ * Caller must have a acquired gpio_lookup_lock
+ */
+static struct gpio_chip *find_chip_by_name(const char *name)
+{
+	struct gpio_chip *chip = NULL;
+
+	list_for_each_entry(chip, &gpio_lookup_list, list) {
+		if (chip->label == NULL)
+			continue;
+		if (!strcmp(chip->label, name))
+			break;
+	}
+
+	return chip;
+}
+
+#ifdef CONFIG_OF
+static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
+				      unsigned int idx, unsigned long *flags)
+{
+	char prop_name[32]; /* 32 is max size of property name */
+	enum of_gpio_flags of_flags;
+	struct gpio_desc *desc;
+
+	if (con_id)
+		snprintf(prop_name, 32, "%s-gpios", con_id);
+	else
+		snprintf(prop_name, 32, "gpios");
+
+	desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx,
+					&of_flags);
+
+	if (IS_ERR(desc))
+		return desc;
+
+	if (of_flags & OF_GPIO_ACTIVE_LOW)
+		*flags |= GPIOF_ACTIVE_LOW;
+
+	return desc;
+}
+#else
+static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
+				      unsigned int idx, unsigned long *flags)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
+static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
+				    unsigned int idx, unsigned long *flags)
+{
+	const char *dev_id = dev ? dev_name(dev) : NULL;
+	struct gpio_desc *desc = ERR_PTR(-ENODEV);
+	unsigned int match, best = 0;
+	struct gpiod_lookup *p;
+
+	mutex_lock(&gpio_lookup_lock);
+
+	list_for_each_entry(p, &gpio_lookup_list, list) {
+		match = 0;
+
+		if (p->dev_id) {
+			if (!dev_id || strcmp(p->dev_id, dev_id))
+				continue;
+
+			match += 2;
+		}
+
+		if (p->con_id) {
+			if (!con_id || strcmp(p->con_id, con_id))
+				continue;
+
+			match += 1;
+		}
+
+		if (p->idx != idx)
+			continue;
+
+		if (match > best) {
+			struct gpio_chip *chip;
+
+			chip = find_chip_by_name(p->chip_label);
+
+			if (!chip) {
+				dev_warn(dev, "cannot find GPIO chip %s\n",
+					 p->chip_label);
+				continue;
+			}
+
+			if (chip->ngpio >= p->chip_hwnum) {
+				dev_warn(dev, "GPIO chip %s has %d GPIOs\n",
+					 chip->label, chip->ngpio);
+				continue;
+			}
+
+			desc = gpio_to_desc(chip->base + p->chip_hwnum);
+			*flags = p->flags;
+
+			if (match != 3)
+				best = match;
+			else
+				break;
+		}
+	}
+
+	mutex_unlock(&gpio_lookup_lock);
+
+	return desc;
+}
+
+/**
+ * gpio_get - obtain a GPIO for a given GPIO function
+ * @dev:	GPIO consumer
+ * @con_id:	function within the GPIO consumer
+ *
+ * Return the GPIO descriptor corresponding to the function con_id of device
+ * dev, or an IS_ERR() condition if an error occured.
+ */
+struct gpio_desc *__must_check gpiod_get(struct device *dev, const char *con_id)
+{
+	return gpiod_get_index(dev, con_id, 0);
+}
+EXPORT_SYMBOL_GPL(gpiod_get);
+
+/**
+ * gpiod_get_index - obtain a GPIO from a multi-index GPIO function
+ * @dev:	GPIO consumer
+ * @con_id:	function within the GPIO consumer
+ * @idx:	index of the GPIO to obtain in the consumer
+ *
+ * This variant of gpiod_get() allows to access GPIOs other than the first
+ * defined one for functions that define several GPIOs.
+ *
+ * Return a valid GPIO descriptor, or an IS_ERR() condition in case of error.
+ */
+struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
+					       const char *con_id,
+					       unsigned int idx)
+{
+	struct gpio_desc *desc;
+	int status;
+	unsigned long flags = 0;
+
+	dev_dbg(dev, "GPIO lookup for consumer %s\n", con_id);
+
+	/* Using device tree? */
+	if (IS_ENABLED(CONFIG_OF) && dev && dev->of_node) {
+		dev_dbg(dev, "using device tree for GPIO lookup\n");
+		desc = of_find_gpio(dev, con_id, idx, &flags);
+	} else {
+		dev_dbg(dev, "using lookup tables for GPIO lookup");
+		desc = gpiod_find(dev, con_id, idx, &flags);
+	}
+
+	if (IS_ERR(desc)) {
+		dev_warn(dev, "lookup for GPIO %s failed\n", con_id);
+		return desc;
+	}
+
+	status = gpiod_request(desc, con_id);
+
+	if (status < 0)
+		return ERR_PTR(status);
+
+	if (flags & GPIOF_ACTIVE_LOW)
+		set_bit(FLAG_ACTIVE_LOW, &desc->flags);
+
+	return desc;
+}
+EXPORT_SYMBOL_GPL(gpiod_get_index);
+
+/**
+ * gpiod_put - dispose of a GPIO descriptor
+ * @desc:	GPIO descriptor to dispose of
+ *
+ * No descriptor can be used after gpiod_put() has been called on it.
+ */
+void gpiod_put(struct gpio_desc *desc)
+{
+	gpiod_free(desc);
+}
+EXPORT_SYMBOL_GPL(gpiod_put);
+
 #ifdef CONFIG_DEBUG_FS
 
 static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 2088eb50421c..4d34dbbbad4d 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -18,6 +18,21 @@ struct gpio_chip;
  */
 struct gpio_desc;
 
+/* Acquire and dispose GPIOs */
+struct gpio_desc *__must_check gpiod_get(struct device *dev,
+					 const char *con_id);
+struct gpio_desc *__must_check gpiod_get_index(struct device *dev,
+					       const char *con_id,
+					       unsigned int idx);
+void gpiod_put(struct gpio_desc *desc);
+
+struct gpio_desc *__must_check devm_gpiod_get(struct device *dev,
+					      const char *con_id);
+struct gpio_desc *__must_check devm_gpiod_get_index(struct device *dev,
+						    const char *con_id,
+						    unsigned int idx);
+void devm_gpiod_put(struct device *dev, struct gpio_desc *desc);
+
 int gpiod_get_direction(const struct gpio_desc *desc);
 int gpiod_direction_input(struct gpio_desc *desc);
 int gpiod_direction_output(struct gpio_desc *desc, int value);
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 5dc172c72f0f..cd9da3885d79 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -124,4 +124,60 @@ extern struct gpio_chip *gpiochip_find(void *data,
 int gpiod_lock_as_irq(struct gpio_desc *desc);
 void gpiod_unlock_as_irq(struct gpio_desc *desc);
 
+/**
+ * Lookup table for associating GPIOs to specific devices and functions using
+ * platform data.
+ */
+struct gpiod_lookup {
+	struct list_head list;
+	/*
+	 * name of the chip the GPIO belongs to
+	 */
+	const char *chip_label;
+	/*
+	 * hardware number (i.e. relative to the chip) of the GPIO
+	 */
+	u16 chip_hwnum;
+	/*
+	 * name of device that can claim this GPIO
+	 */
+	const char *dev_id;
+	/*
+	 * name of the GPIO from the device's point of view
+	 */
+	const char *con_id;
+	/*
+	 * index of the GPIO in case several GPIOs share the same name
+	 */
+	unsigned int idx;
+	/*
+	 * mask of GPIOF_* values
+	 */
+	unsigned long flags;
+};
+
+/*
+ * Simple definition of a single GPIO under a con_id
+ */
+#define GPIO_LOOKUP(_chip_label, _chip_hwnum, _dev_id, _con_id, _flags) \
+	GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _dev_id, _con_id, 0, _flags)
+
+/*
+ * Use this macro if you need to have several GPIOs under the same con_id.
+ * Each GPIO needs to use a different index and can be accessed using
+ * gpiod_get_index()
+ */
+#define GPIO_LOOKUP_IDX(_chip_label, _chip_hwnum, _dev_id, _con_id, _idx, \
+			_flags)                                           \
+{                                                                         \
+	.chip_label = _chip_label,                                        \
+	.chip_hwnum = _chip_hwnum,                                        \
+	.dev_id = _dev_id,                                                \
+	.con_id = _con_id,                                                \
+	.idx = _idx,                                                      \
+	.flags = _flags,                                                  \
+}
+
+void gpiod_add_table(struct gpiod_lookup *table, size_t size);
+
 #endif
-- 
cgit 


From 936e15dd2128eb5aa71251766f1176552b45f43c Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 10 Oct 2013 11:01:08 +0300
Subject: gpiolib / ACPI: convert to gpiod interfaces

The new GPIO descriptor based interface is now preferred over the old
integer based one. This patch converts the ACPI GPIO helpers to use this
new interface internally. In addition to that provide compatibility
function acpi_get_gpio_by_index() that converts the returned GPIO
descriptor to an integer.

We also drop acpi_get_gpio() as it is not used anywhere outside
gpiolib-acpi and even there we use acpi_get_gpiod() instead.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-acpi.c | 51 ++++++++++++++++++++++-----------------------
 include/linux/acpi_gpio.h   | 29 ++++++++++++++++----------
 2 files changed, 43 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 1745ce5983d6..03187d0a3045 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/errno.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/export.h>
 #include <linux/acpi_gpio.h>
 #include <linux/acpi.h>
@@ -33,14 +33,15 @@ static int acpi_gpiochip_find(struct gpio_chip *gc, void *data)
 }
 
 /**
- * acpi_get_gpio() - Translate ACPI GPIO pin to GPIO number usable with GPIO API
+ * acpi_get_gpiod() - Translate ACPI GPIO pin to GPIO descriptor usable with GPIO API
  * @path:	ACPI GPIO controller full path name, (e.g. "\\_SB.GPO1")
  * @pin:	ACPI GPIO pin number (0-based, controller-relative)
  *
- * Returns GPIO number to use with Linux generic GPIO API, or errno error value
+ * Returns GPIO descriptor to use with Linux generic GPIO API, or ERR_PTR
+ * error value
  */
 
-int acpi_get_gpio(char *path, int pin)
+static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 {
 	struct gpio_chip *chip;
 	acpi_handle handle;
@@ -48,18 +49,17 @@ int acpi_get_gpio(char *path, int pin)
 
 	status = acpi_get_handle(NULL, path, &handle);
 	if (ACPI_FAILURE(status))
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
 	chip = gpiochip_find(handle, acpi_gpiochip_find);
 	if (!chip)
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
-	if (!gpio_is_valid(chip->base + pin))
-		return -EINVAL;
+	if (pin < 0 || pin > chip->ngpio)
+		return ERR_PTR(-EINVAL);
 
-	return chip->base + pin;
+	return gpio_to_desc(chip->base + pin);
 }
-EXPORT_SYMBOL_GPL(acpi_get_gpio);
 
 static irqreturn_t acpi_gpio_irq_handler(int irq, void *data)
 {
@@ -235,7 +235,7 @@ EXPORT_SYMBOL(acpi_gpiochip_free_interrupts);
 struct acpi_gpio_lookup {
 	struct acpi_gpio_info info;
 	int index;
-	int gpio;
+	struct gpio_desc *desc;
 	int n;
 };
 
@@ -246,11 +246,11 @@ static int acpi_find_gpio(struct acpi_resource *ares, void *data)
 	if (ares->type != ACPI_RESOURCE_TYPE_GPIO)
 		return 1;
 
-	if (lookup->n++ == lookup->index && lookup->gpio < 0) {
+	if (lookup->n++ == lookup->index && !lookup->desc) {
 		const struct acpi_resource_gpio *agpio = &ares->data.gpio;
 
-		lookup->gpio = acpi_get_gpio(agpio->resource_source.string_ptr,
-					     agpio->pin_table[0]);
+		lookup->desc = acpi_get_gpiod(agpio->resource_source.string_ptr,
+					      agpio->pin_table[0]);
 		lookup->info.gpioint =
 			agpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT;
 	}
@@ -259,24 +259,24 @@ static int acpi_find_gpio(struct acpi_resource *ares, void *data)
 }
 
 /**
- * acpi_get_gpio_by_index() - get a GPIO number from device resources
+ * acpi_get_gpiod_by_index() - get a GPIO descriptor from device resources
  * @dev: pointer to a device to get GPIO from
  * @index: index of GpioIo/GpioInt resource (starting from %0)
  * @info: info pointer to fill in (optional)
  *
  * Function goes through ACPI resources for @dev and based on @index looks
- * up a GpioIo/GpioInt resource, translates it to the Linux GPIO number,
+ * up a GpioIo/GpioInt resource, translates it to the Linux GPIO descriptor,
  * and returns it. @index matches GpioIo/GpioInt resources only so if there
  * are total %3 GPIO resources, the index goes from %0 to %2.
  *
- * If the GPIO cannot be translated or there is an error, negative errno is
+ * If the GPIO cannot be translated or there is an error an ERR_PTR is
  * returned.
  *
  * Note: if the GPIO resource has multiple entries in the pin list, this
  * function only returns the first.
  */
-int acpi_get_gpio_by_index(struct device *dev, int index,
-			   struct acpi_gpio_info *info)
+struct gpio_desc *acpi_get_gpiod_by_index(struct device *dev, int index,
+					  struct acpi_gpio_info *info)
 {
 	struct acpi_gpio_lookup lookup;
 	struct list_head resource_list;
@@ -285,27 +285,26 @@ int acpi_get_gpio_by_index(struct device *dev, int index,
 	int ret;
 
 	if (!dev)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	handle = ACPI_HANDLE(dev);
 	if (!handle || acpi_bus_get_device(handle, &adev))
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
 	memset(&lookup, 0, sizeof(lookup));
 	lookup.index = index;
-	lookup.gpio = -ENODEV;
 
 	INIT_LIST_HEAD(&resource_list);
 	ret = acpi_dev_get_resources(adev, &resource_list, acpi_find_gpio,
 				     &lookup);
 	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
 	acpi_dev_free_resource_list(&resource_list);
 
-	if (lookup.gpio >= 0 && info)
+	if (lookup.desc && info)
 		*info = lookup.info;
 
-	return lookup.gpio;
+	return lookup.desc ? lookup.desc : ERR_PTR(-ENODEV);
 }
-EXPORT_SYMBOL_GPL(acpi_get_gpio_by_index);
+EXPORT_SYMBOL_GPL(acpi_get_gpiod_by_index);
diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h
index 4c120a1e0ca3..b6ce601e55a2 100644
--- a/include/linux/acpi_gpio.h
+++ b/include/linux/acpi_gpio.h
@@ -2,8 +2,10 @@
 #define _LINUX_ACPI_GPIO_H_
 
 #include <linux/device.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 /**
  * struct acpi_gpio_info - ACPI GPIO specific information
@@ -15,23 +17,18 @@ struct acpi_gpio_info {
 
 #ifdef CONFIG_GPIO_ACPI
 
-int acpi_get_gpio(char *path, int pin);
-int acpi_get_gpio_by_index(struct device *dev, int index,
-			   struct acpi_gpio_info *info);
+struct gpio_desc *acpi_get_gpiod_by_index(struct device *dev, int index,
+					  struct acpi_gpio_info *info);
 void acpi_gpiochip_request_interrupts(struct gpio_chip *chip);
 void acpi_gpiochip_free_interrupts(struct gpio_chip *chip);
 
 #else /* CONFIG_GPIO_ACPI */
 
-static inline int acpi_get_gpio(char *path, int pin)
+static inline struct gpio_desc *
+acpi_get_gpiod_by_index(struct device *dev, int index,
+			struct acpi_gpio_info *info)
 {
-	return -ENODEV;
-}
-
-static inline int acpi_get_gpio_by_index(struct device *dev, int index,
-					 struct acpi_gpio_info *info)
-{
-	return -ENODEV;
+	return ERR_PTR(-ENOSYS);
 }
 
 static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { }
@@ -39,4 +36,14 @@ static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { }
 
 #endif /* CONFIG_GPIO_ACPI */
 
+static inline int acpi_get_gpio_by_index(struct device *dev, int index,
+					 struct acpi_gpio_info *info)
+{
+	struct gpio_desc *desc = acpi_get_gpiod_by_index(dev, index, info);
+
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+	return desc_to_gpio(desc);
+}
+
 #endif /* _LINUX_ACPI_GPIO_H_ */
-- 
cgit 


From e01f440a689aeb2d0e81c696fe2069f8d01d5d49 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 10 Oct 2013 11:01:10 +0300
Subject: gpiolib / ACPI: allow passing GPIOF_ACTIVE_LOW for GpioInt resources

The ACPI GpioInt resources contain polarity field that is used to specify
whether the interrupt is active high or low. Since gpiolib supports
GPIOF_ACTIVE_LOW we can pass this information in the flags field in
acpi_find_gpio(), analogous to the DeviceTree version.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-acpi.c |  2 ++
 drivers/gpio/gpiolib.c      | 12 +++++++++++-
 include/linux/acpi_gpio.h   |  2 ++
 3 files changed, 15 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 03187d0a3045..ae0ffdce8bd5 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -253,6 +253,8 @@ static int acpi_find_gpio(struct acpi_resource *ares, void *data)
 					      agpio->pin_table[0]);
 		lookup->info.gpioint =
 			agpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT;
+		lookup->info.active_low =
+			agpio->polarity == ACPI_ACTIVE_LOW;
 	}
 
 	return 1;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index bee93c8c2361..9f3326b95e60 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2264,7 +2264,17 @@ static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 static struct gpio_desc *acpi_find_gpio(struct device *dev, const char *con_id,
 					unsigned int idx, unsigned long *flags)
 {
-	return acpi_get_gpiod_by_index(dev, idx, NULL);
+	struct acpi_gpio_info info;
+	struct gpio_desc *desc;
+
+	desc = acpi_get_gpiod_by_index(dev, idx, &info);
+	if (IS_ERR(desc))
+		return desc;
+
+	if (info.gpioint && info.active_low)
+		*flags |= GPIOF_ACTIVE_LOW;
+
+	return desc;
 }
 
 static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h
index b6ce601e55a2..d875bc3dba3c 100644
--- a/include/linux/acpi_gpio.h
+++ b/include/linux/acpi_gpio.h
@@ -10,9 +10,11 @@
 /**
  * struct acpi_gpio_info - ACPI GPIO specific information
  * @gpioint: if %true this GPIO is of type GpioInt otherwise type is GpioIo
+ * @active_low: in case of @gpioint, the pin is active low
  */
 struct acpi_gpio_info {
 	bool gpioint;
+	bool active_low;
 };
 
 #ifdef CONFIG_GPIO_ACPI
-- 
cgit 


From 90af231106c0b8d223c27d35464af95cb3d9cacf Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 18 Oct 2013 17:43:38 +0200
Subject: bonding: add Netlink support mode option

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 56 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/if_link.h       | 10 +++++++
 2 files changed, 66 insertions(+)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 3e5c5f80c320..a94f870a6b60 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -20,6 +20,10 @@
 #include <net/rtnetlink.h>
 #include "bonding.h"
 
+static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
+	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
+};
+
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	if (tb[IFLA_ADDRESS]) {
@@ -31,11 +35,63 @@ static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
+static int bond_changelink(struct net_device *bond_dev,
+			   struct nlattr *tb[], struct nlattr *data[])
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	int err;
+
+	if (data && data[IFLA_BOND_MODE]) {
+		int mode = nla_get_u8(data[IFLA_BOND_MODE]);
+
+		err = bond_option_mode_set(bond, mode);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
+			struct nlattr *tb[], struct nlattr *data[])
+{
+	int err;
+
+	err = bond_changelink(bond_dev, tb, data);
+	if (err < 0)
+		return err;
+
+	return register_netdevice(bond_dev);
+}
+
+static size_t bond_get_size(const struct net_device *bond_dev)
+{
+	return nla_total_size(sizeof(u8));	/* IFLA_BOND_MODE */
+}
+
+static int bond_fill_info(struct sk_buff *skb,
+			  const struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+
+	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 struct rtnl_link_ops bond_link_ops __read_mostly = {
 	.kind			= "bond",
 	.priv_size		= sizeof(struct bonding),
 	.setup			= bond_setup,
+	.maxtype		= IFLA_BOND_MAX,
+	.policy			= bond_policy,
 	.validate		= bond_validate,
+	.newlink		= bond_newlink,
+	.changelink		= bond_changelink,
+	.get_size		= bond_get_size,
+	.fill_info		= bond_fill_info,
 	.get_num_tx_queues	= bond_get_num_tx_queues,
 	.get_num_rx_queues	= bond_get_num_tx_queues, /* Use the same number
 							     as for TX queues */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 80394e8dc3a3..06fd3fe10f3b 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -325,6 +325,16 @@ struct ifla_vxlan_port_range {
 	__be16	high;
 };
 
+/* Bonding section */
+
+enum {
+	IFLA_BOND_UNSPEC,
+	IFLA_BOND_MODE,
+	__IFLA_BOND_MAX,
+};
+
+#define IFLA_BOND_MAX	(__IFLA_BOND_MAX - 1)
+
 /* SR-IOV virtual function management section */
 
 enum {
-- 
cgit 


From ec76aa49855f6d6fea5e01de179fb57dd47c619d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Fri, 18 Oct 2013 17:43:39 +0200
Subject: bonding: add Netlink support active_slave option

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_netlink.c | 23 ++++++++++++++++++++++-
 include/uapi/linux/if_link.h       |  1 +
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index a94f870a6b60..fe3500bb34e4 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -22,6 +22,7 @@
 
 static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MODE]		= { .type = NLA_U8 },
+	[IFLA_BOND_ACTIVE_SLAVE]	= { .type = NLA_U32 },
 };
 
 static int bond_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -48,6 +49,22 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data && data[IFLA_BOND_ACTIVE_SLAVE]) {
+		int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]);
+		struct net_device *slave_dev;
+
+		if (ifindex == 0) {
+			slave_dev = NULL;
+		} else {
+			slave_dev = __dev_get_by_index(dev_net(bond_dev),
+						       ifindex);
+			if (!slave_dev)
+				return -ENODEV;
+		}
+		err = bond_option_active_slave_set(bond, slave_dev);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -66,14 +83,18 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
 static size_t bond_get_size(const struct net_device *bond_dev)
 {
 	return nla_total_size(sizeof(u8));	/* IFLA_BOND_MODE */
+		+ nla_total_size(sizeof(u32));	/* IFLA_BOND_ACTIVE_SLAVE */
 }
 
 static int bond_fill_info(struct sk_buff *skb,
 			  const struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	struct net_device *slave_dev = bond_option_active_slave_get(bond);
 
-	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
+	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode) ||
+	    (slave_dev &&
+	     nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, slave_dev->ifindex)))
 		goto nla_put_failure;
 	return 0;
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 06fd3fe10f3b..8a1e346243b7 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -330,6 +330,7 @@ struct ifla_vxlan_port_range {
 enum {
 	IFLA_BOND_UNSPEC,
 	IFLA_BOND_MODE,
+	IFLA_BOND_ACTIVE_SLAVE,
 	__IFLA_BOND_MAX,
 };
 
-- 
cgit 


From 2d26f0a3c0e22f6b3096a2503d086e4b5e99d708 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Oct 2013 11:42:55 -0700
Subject: ipv4: generalize gre_handle_offloads

This patch makes gre_handle_offloads() more generic
and rename it to iptunnel_handle_offloads()

This will be used to add GSO/TSO support to IPIP tunnels.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gre.h         |  8 +++++++-
 include/net/ip_tunnels.h  |  3 +++
 net/ipv4/gre_demux.c      | 29 -----------------------------
 net/ipv4/ip_tunnel_core.c | 33 +++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/net/gre.h b/include/net/gre.h
index 57e4afdf7879..dcd9ae3270d3 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -38,7 +38,13 @@ void gre_offload_exit(void);
 
 void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 		      int hdr_len);
-struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum);
+
+static inline struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
+						  bool gre_csum)
+{
+	return iptunnel_handle_offloads(skb, gre_csum, SKB_GSO_GRE);
+}
+
 
 static inline int ip_gre_calc_hlen(__be16 o_flags)
 {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a0a4a100f5c9..732f8c6ae975 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -150,6 +150,9 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet);
 
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum,
+					 int gso_type_mask);
+
 static inline void iptunnel_xmit_stats(int err,
 				       struct net_device_stats *err_stats,
 				       struct pcpu_tstats __percpu *stats)
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 736c9fc3ef93..5893e99e8299 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -93,35 +93,6 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 }
 EXPORT_SYMBOL_GPL(gre_build_header);
 
-struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum)
-{
-	int err;
-
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
-	if (skb_is_gso(skb)) {
-		err = skb_unclone(skb, GFP_ATOMIC);
-		if (unlikely(err))
-			goto error;
-		skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
-		return skb;
-	} else if (skb->ip_summed == CHECKSUM_PARTIAL && gre_csum) {
-		err = skb_checksum_help(skb);
-		if (unlikely(err))
-			goto error;
-	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	return skb;
-error:
-	kfree_skb(skb);
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL_GPL(gre_handle_offloads);
-
 static __sum16 check_checksum(struct sk_buff *skb)
 {
 	__sum16 csum = 0;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index c31e3ad98ef2..42ffbc8d65c6 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -116,3 +116,36 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
+
+struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
+					 bool csum_help,
+					 int gso_type_mask)
+{
+	int err;
+
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
+	if (skb_is_gso(skb)) {
+		err = skb_unclone(skb, GFP_ATOMIC);
+		if (unlikely(err))
+			goto error;
+		skb_shinfo(skb)->gso_type |= gso_type_mask;
+		return skb;
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) {
+		err = skb_checksum_help(skb);
+		if (unlikely(err))
+			goto error;
+	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	return skb;
+error:
+	kfree_skb(skb);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
-- 
cgit 


From 3347c960295583eee3fd58e5c539fb1972fbc005 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Oct 2013 11:42:56 -0700
Subject: ipv4: gso: make inet_gso_segment() stackable

In order to support GSO on IPIP, we need to make
inet_gso_segment() stackable.

It should not assume network header starts right after mac
header.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  7 +++++--
 net/core/dev.c         |  2 ++
 net/ipv4/af_inet.c     | 25 ++++++++++++++++++-------
 3 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ba74474836c0..cad1e0c5cc04 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2722,9 +2722,12 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
 /* Keeps track of mac header offset relative to skb->head.
  * It is useful for TSO of Tunneling protocol. e.g. GRE.
  * For non-tunnel skb it points to skb_mac_header() and for
- * tunnel skb it points to outer mac header. */
+ * tunnel skb it points to outer mac header.
+ * Keeps track of level of encapsulation of network headers.
+ */
 struct skb_gso_cb {
-	int mac_offset;
+	int	mac_offset;
+	int	encap_level;
 };
 #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 1b6eadf69289..0918aadc20fd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2377,6 +2377,8 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 	}
 
 	SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb);
+	SKB_GSO_CB(skb)->encap_level = 0;
+
 	skb_reset_mac_header(skb);
 	skb_reset_mac_len(skb);
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4f8cd4fc451d..5783ab5b5ef8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1273,16 +1273,17 @@ out:
 }
 
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
-	netdev_features_t features)
+					netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
+	unsigned int offset = 0;
 	struct iphdr *iph;
+	bool tunnel;
 	int proto;
+	int nhoff;
 	int ihl;
 	int id;
-	unsigned int offset = 0;
-	bool tunnel;
 
 	if (unlikely(skb_shinfo(skb)->gso_type &
 		     ~(SKB_GSO_TCPV4 |
@@ -1296,6 +1297,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       0)))
 		goto out;
 
+	skb_reset_network_header(skb);
+	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
 		goto out;
 
@@ -1312,7 +1315,10 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		goto out;
 	__skb_pull(skb, ihl);
 
-	tunnel = !!skb->encapsulation;
+	tunnel = SKB_GSO_CB(skb)->encap_level > 0;
+	if (tunnel)
+		features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	SKB_GSO_CB(skb)->encap_level += ihl;
 
 	skb_reset_transport_header(skb);
 
@@ -1327,18 +1333,23 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	skb = segs;
 	do {
-		iph = ip_hdr(skb);
+		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
 		if (!tunnel && proto == IPPROTO_UDP) {
 			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
 			if (skb->next != NULL)
 				iph->frag_off |= htons(IP_MF);
-			offset += (skb->len - skb->mac_len - iph->ihl * 4);
+			offset += skb->len - nhoff - ihl;
 		} else  {
 			iph->id = htons(id++);
 		}
-		iph->tot_len = htons(skb->len - skb->mac_len);
+		iph->tot_len = htons(skb->len - nhoff);
 		ip_send_check(iph);
+		if (tunnel) {
+			skb_reset_inner_headers(skb);
+			skb->encapsulation = 1;
+		}
+		skb->network_header = (u8 *)iph - skb->head;
 	} while ((skb = skb->next));
 
 out:
-- 
cgit 


From cb32f511a70be8967ac9025cf49c44324ced9a39 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 19 Oct 2013 11:42:57 -0700
Subject: ipip: add GSO/TSO support

Now inet_gso_segment() is stackable, its relatively easy to
implement GSO/TSO support for IPIP

Performance results, when segmentation is done after tunnel
device (as no NIC is yet enabled for TSO IPIP support) :

Before patch :

lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      3357.88   5.09     3.70     2.983   2.167

After patch :

lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      7710.19   4.52     6.62     1.152   1.687

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h |  2 ++
 include/linux/skbuff.h          |  6 ++++--
 net/core/ethtool.c              |  1 +
 net/ipv4/af_inet.c              |  9 +++++++++
 net/ipv4/gre_offload.c          |  3 ++-
 net/ipv4/ipip.c                 | 11 ++++++-----
 net/ipv4/tcp_offload.c          |  1 +
 net/ipv4/udp_offload.c          |  1 +
 net/ipv6/ip6_offload.c          |  1 +
 net/ipv6/udp_offload.c          |  1 +
 net/mpls/mpls_gso.c             |  1 +
 11 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index a2a89a5c7be5..8dad68cede1c 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -42,6 +42,7 @@ enum {
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
+	NETIF_F_GSO_IPIP_BIT,		/* ... IPIP tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
@@ -107,6 +108,7 @@ enum {
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
+#define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cad1e0c5cc04..60729134d253 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -318,9 +318,11 @@ enum {
 
 	SKB_GSO_GRE = 1 << 6,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 7,
+	SKB_GSO_IPIP = 1 << 7,
 
-	SKB_GSO_MPLS = 1 << 8,
+	SKB_GSO_UDP_TUNNEL = 1 << 8,
+
+	SKB_GSO_MPLS = 1 << 9,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 78e9d9223e40..8cab7744790e 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -81,6 +81,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
+	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5783ab5b5ef8..4049906010f7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1291,6 +1291,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_IPIP |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
@@ -1656,6 +1657,13 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 	},
 };
 
+static const struct net_offload ipip_offload = {
+	.callbacks = {
+		.gso_send_check = inet_gso_send_check,
+		.gso_segment	= inet_gso_segment,
+	},
+};
+
 static int __init ipv4_offload_init(void)
 {
 	/*
@@ -1667,6 +1675,7 @@ static int __init ipv4_offload_init(void)
 		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
 
 	dev_add_offload(&ip_packet_offload);
+	inet_add_offload(&ipip_offload, IPPROTO_IPIP);
 	return 0;
 }
 
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 55e6bfb3a289..e5d436188464 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -39,7 +39,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
-				  SKB_GSO_GRE)))
+				  SKB_GSO_GRE |
+				  SKB_GSO_IPIP)))
 		goto out;
 
 	if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 7f80fb4b82d3..fe3e9f7f1f0b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -220,17 +220,17 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb->protocol != htons(ETH_P_IP)))
 		goto tx_error;
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto out;
 
 	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
 	return NETDEV_TX_OK;
 
 tx_error:
-	dev->stats.tx_errors++;
 	dev_kfree_skb(skb);
+out:
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -275,6 +275,7 @@ static const struct net_device_ops ipip_netdev_ops = {
 #define IPIP_FEATURES (NETIF_F_SG |		\
 		       NETIF_F_FRAGLIST |	\
 		       NETIF_F_HIGHDMA |	\
+		       NETIF_F_GSO_SOFTWARE |	\
 		       NETIF_F_HW_CSUM)
 
 static void ipip_tunnel_setup(struct net_device *dev)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 8e3113f46ec1..dfc96b00673e 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -56,6 +56,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCP_ECN |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
+			       SKB_GSO_IPIP |
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       0) ||
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f35eccaa855e..83206de2bc76 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -52,6 +52,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_IPIP |
 				      SKB_GSO_GRE | SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b405fba91c72..5c2fc1d04196 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -96,6 +96,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_IPIP |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 60559511bd9c..f63780ff3732 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -64,6 +64,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_GRE |
+				      SKB_GSO_IPIP |
 				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 1bec1219ab81..851cd880b0c0 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -33,6 +33,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_IPIP |
 				  SKB_GSO_MPLS)))
 		goto out;
 
-- 
cgit 


From 65cd8033ff375b68037df61603ee68070dc48578 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:51 +0200
Subject: ipv4: split inet_ehashfn to hash functions per compilation unit

This duplicates a bit of code but let's us easily introduce
separate secret keys later. The separate compilation units are
ipv4/inet_hashtabbles.o, ipv4/udp.o and rds/connection.o.

Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h    | 22 ++++++----------------
 net/ipv4/inet_hashtables.c | 21 +++++++++++++++++++++
 net/ipv4/udp.c             | 16 ++++++++++++----
 net/rds/connection.c       |  6 +++---
 4 files changed, 42 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 06da91efbc83..7a6c7f80a8fd 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -208,26 +208,16 @@ extern u32 inet_ehash_secret;
 extern u32 ipv6_hash_secret;
 void build_ehash_secret(void);
 
-static inline unsigned int inet_ehashfn(struct net *net,
-					const __be32 laddr, const __u16 lport,
-					const __be32 faddr, const __be16 fport)
+static inline unsigned int __inet_ehashfn(const __be32 laddr,
+					  const __u16 lport,
+					  const __be32 faddr,
+					  const __be16 fport,
+					  u32 initval)
 {
 	return jhash_3words((__force __u32) laddr,
 			    (__force __u32) faddr,
 			    ((__u32) lport) << 16 | (__force __u32)fport,
-			    inet_ehash_secret + net_hash_mix(net));
-}
-
-static inline int inet_sk_ehashfn(const struct sock *sk)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	const __be32 laddr = inet->inet_rcv_saddr;
-	const __u16 lport = inet->inet_num;
-	const __be32 faddr = inet->inet_daddr;
-	const __be16 fport = inet->inet_dport;
-	struct net *net = sock_net(sk);
-
-	return inet_ehashfn(net, laddr, lport, faddr, fport);
+			    initval);
 }
 
 static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index a4b66bbe4f21..18aa668d0cc9 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -24,6 +24,27 @@
 #include <net/secure_seq.h>
 #include <net/ip.h>
 
+static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
+				 const __u16 lport, const __be32 faddr,
+				 const __be16 fport)
+{
+	return __inet_ehashfn(laddr, lport, faddr, fport,
+			      inet_ehash_secret + net_hash_mix(net));
+}
+
+
+static unsigned int inet_sk_ehashfn(const struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const __be32 laddr = inet->inet_rcv_saddr;
+	const __u16 lport = inet->inet_num;
+	const __be32 faddr = inet->inet_daddr;
+	const __be16 fport = inet->inet_dport;
+	struct net *net = sock_net(sk);
+
+	return inet_ehashfn(net, laddr, lport, faddr, fport);
+}
+
 /*
  * Allocate and initialize a new local port bind bucket.
  * The bindhash mutex for snum's hash chain must be held here.
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9f27bb800607..b4437c7db6ce 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -407,6 +407,14 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 	return score;
 }
 
+static unsigned int udp_ehashfn(struct net *net, const __be32 laddr,
+				 const __u16 lport, const __be32 faddr,
+				 const __be16 fport)
+{
+	return __inet_ehashfn(laddr, lport, faddr, fport,
+			      inet_ehash_secret + net_hash_mix(net));
+}
+
 
 /* called with read_rcu_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
@@ -430,8 +438,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet_ehashfn(net, daddr, hnum,
-						    saddr, sport);
+				hash = udp_ehashfn(net, daddr, hnum,
+						   saddr, sport);
 				matches = 1;
 			}
 		} else if (score == badness && reuseport) {
@@ -511,8 +519,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet_ehashfn(net, daddr, hnum,
-						    saddr, sport);
+				hash = udp_ehashfn(net, daddr, hnum,
+						   saddr, sport);
 				matches = 1;
 			}
 		} else if (score == badness && reuseport) {
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 642ad42c416b..45e23660437a 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -52,9 +52,9 @@ static struct kmem_cache *rds_conn_slab;
 static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
 {
 	/* Pass NULL, don't need struct net for hash */
-	unsigned long hash = inet_ehashfn(NULL,
-					  be32_to_cpu(laddr), 0,
-					  be32_to_cpu(faddr), 0);
+	unsigned long hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
+					    be32_to_cpu(faddr), 0,
+					    inet_ehash_secret);
 	return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
 }
 
-- 
cgit 


From b50026b5ac8fe2932e6af0c54b21da0913c4c1c7 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:52 +0200
Subject: ipv6: split inet6_ehashfn to hash functions per compilation unit

This patch splits the inet6_ehashfn into separate ones in
ipv6/inet6_hashtables.o and ipv6/udp.o to ease the introduction of
seperate secrets keys later.

Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet6_hashtables.h | 28 +++++++---------------------
 include/net/ipv6.h             |  4 ++--
 net/ipv6/inet6_hashtables.c    | 24 ++++++++++++++++++++++++
 net/ipv6/udp.c                 | 20 ++++++++++++++++----
 4 files changed, 49 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index a105d1a2fc00..ae0613544308 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -28,28 +28,14 @@
 
 struct inet_hashinfo;
 
-static inline unsigned int inet6_ehashfn(struct net *net,
-				const struct in6_addr *laddr, const u16 lport,
-				const struct in6_addr *faddr, const __be16 fport)
+static inline unsigned int __inet6_ehashfn(const u32 lhash,
+				    const u16 lport,
+				    const u32 fhash,
+				    const __be16 fport,
+				    const u32 initval)
 {
-	u32 ports = (((u32)lport) << 16) | (__force u32)fport;
-
-	return jhash_3words((__force u32)laddr->s6_addr32[3],
-			    ipv6_addr_jhash(faddr),
-			    ports,
-			    inet_ehash_secret + net_hash_mix(net));
-}
-
-static inline int inet6_sk_ehashfn(const struct sock *sk)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr;
-	const struct in6_addr *faddr = &sk->sk_v6_daddr;
-	const __u16 lport = inet->inet_num;
-	const __be16 fport = inet->inet_dport;
-	struct net *net = sock_net(sk);
-
-	return inet6_ehashfn(net, laddr, lport, faddr, fport);
+	const u32 ports = (((u32)lport) << 16) | (__force u32)fport;
+	return jhash_3words(lhash, fhash, ports, initval);
 }
 
 int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index fe1c7f6c9217..a35055f4f8da 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -539,14 +539,14 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a)
 }
 
 /* more secured version of ipv6_addr_hash() */
-static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval)
 {
 	u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
 
 	return jhash_3words(v,
 			    (__force u32)a->s6_addr32[2],
 			    (__force u32)a->s6_addr32[3],
-			    ipv6_hash_secret);
+			    initval);
 }
 
 static inline bool ipv6_addr_loopback(const struct in6_addr *a)
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 842d833dfc18..fa7dd3856c55 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -23,6 +23,30 @@
 #include <net/secure_seq.h>
 #include <net/ip.h>
 
+static unsigned int inet6_ehashfn(struct net *net,
+				  const struct in6_addr *laddr,
+				  const u16 lport,
+				  const struct in6_addr *faddr,
+				  const __be16 fport)
+{
+	const u32 lhash = (__force u32)laddr->s6_addr32[3];
+	const u32 fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+	return __inet6_ehashfn(lhash, lport, fhash, fport,
+			       inet_ehash_secret + net_hash_mix(net));
+}
+
+static int inet6_sk_ehashfn(const struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *faddr = &sk->sk_v6_daddr;
+	const __u16 lport = inet->inet_num;
+	const __be16 fport = inet->inet_dport;
+	struct net *net = sock_net(sk);
+
+	return inet6_ehashfn(net, laddr, lport, faddr, fport);
+}
+
 int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b496de19a341..324bd36c23bc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -53,6 +53,18 @@
 #include <trace/events/skb.h>
 #include "udp_impl.h"
 
+static unsigned int udp6_ehashfn(struct net *net,
+				  const struct in6_addr *laddr,
+				  const u16 lport,
+				  const struct in6_addr *faddr,
+				  const __be16 fport)
+{
+	const u32 lhash = (__force u32)laddr->s6_addr32[3];
+	const u32 fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+	return __inet6_ehashfn(lhash, lport, fhash, fport,
+			       inet_ehash_secret + net_hash_mix(net));
+}
+
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
 	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
@@ -214,8 +226,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet6_ehashfn(net, daddr, hnum,
-						     saddr, sport);
+				hash = udp6_ehashfn(net, daddr, hnum,
+						    saddr, sport);
 				matches = 1;
 			} else if (score == SCORE2_MAX)
 				goto exact_match;
@@ -295,8 +307,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet6_ehashfn(net, daddr, hnum,
-						     saddr, sport);
+				hash = udp6_ehashfn(net, daddr, hnum,
+						    saddr, sport);
 				matches = 1;
 			}
 		} else if (score == badness && reuseport) {
-- 
cgit 


From c4b2c0c5f647aa1093e8f9097a30c17ce0f94d4d Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:53 +0200
Subject: static_key: WARN on usage before jump_label_init was called

Usage of the static key primitives to toggle a branch must not be used
before jump_label_init() is called from init/main.c. jump_label_init
reorganizes and wires up the jump_entries so usage before that could
have unforeseen consequences.

Following primitives are now checked for correct use:
* static_key_slow_inc
* static_key_slow_dec
* static_key_slow_dec_deferred
* jump_label_rate_limit

The x86 architecture already checks this by testing if the default_nop
was already replaced with an optimal nop or with a branch instruction. It
will panic then. Other architectures don't check for this.

Because we need to relax this check for the x86 arch to allow code to
transition from default_nop to the enabled state and other architectures
did not check for this at all this patch introduces checking on the
static_key primitives in a non-arch dependent manner.

All checked functions are considered slow-path so the additional check
does no harm to performance.

The warnings are best observed with earlyprintk.

Based on a patch from Andi Kleen.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/jump_label.h           | 10 ++++++++++
 include/linux/jump_label_ratelimit.h |  2 ++
 init/main.c                          |  7 +++++++
 kernel/jump_label.c                  |  5 +++++
 4 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a5079072da66..e96be7245717 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -48,6 +48,13 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/bug.h>
+
+extern bool static_key_initialized;
+
+#define STATIC_KEY_CHECK_USE() WARN(!static_key_initialized,		      \
+				    "%s used before call to jump_label_init", \
+				    __func__)
 
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
 
@@ -128,6 +135,7 @@ struct static_key {
 
 static __always_inline void jump_label_init(void)
 {
+	static_key_initialized = true;
 }
 
 static __always_inline bool static_key_false(struct static_key *key)
@@ -146,11 +154,13 @@ static __always_inline bool static_key_true(struct static_key *key)
 
 static inline void static_key_slow_inc(struct static_key *key)
 {
+	STATIC_KEY_CHECK_USE();
 	atomic_inc(&key->enabled);
 }
 
 static inline void static_key_slow_dec(struct static_key *key)
 {
+	STATIC_KEY_CHECK_USE();
 	atomic_dec(&key->enabled);
 }
 
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index 113788389b3d..089f70f83e97 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -23,12 +23,14 @@ struct static_key_deferred {
 };
 static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
+	STATIC_KEY_CHECK_USE();
 	static_key_slow_dec(&key->key);
 }
 static inline void
 jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
+	STATIC_KEY_CHECK_USE();
 }
 #endif	/* HAVE_JUMP_LABEL */
 #endif	/* _LINUX_JUMP_LABEL_RATELIMIT_H */
diff --git a/init/main.c b/init/main.c
index af310afbef28..27bbec1a5b35 100644
--- a/init/main.c
+++ b/init/main.c
@@ -135,6 +135,13 @@ static char *static_command_line;
 static char *execute_command;
 static char *ramdisk_execute_command;
 
+/*
+ * Used to generate warnings if static_key manipulation functions are used
+ * before jump_label_init is called.
+ */
+bool static_key_initialized __read_mostly = false;
+EXPORT_SYMBOL_GPL(static_key_initialized);
+
 /*
  * If set, this is an indication to the drivers that reset the underlying
  * device before going ahead with the initialization otherwise driver might
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 297a9247a3b3..9019f15deab2 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -58,6 +58,7 @@ static void jump_label_update(struct static_key *key, int enable);
 
 void static_key_slow_inc(struct static_key *key)
 {
+	STATIC_KEY_CHECK_USE();
 	if (atomic_inc_not_zero(&key->enabled))
 		return;
 
@@ -103,12 +104,14 @@ static void jump_label_update_timeout(struct work_struct *work)
 
 void static_key_slow_dec(struct static_key *key)
 {
+	STATIC_KEY_CHECK_USE();
 	__static_key_slow_dec(key, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec);
 
 void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
+	STATIC_KEY_CHECK_USE();
 	__static_key_slow_dec(&key->key, key->timeout, &key->work);
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
@@ -116,6 +119,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
 {
+	STATIC_KEY_CHECK_USE();
 	key->timeout = rl;
 	INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
 }
@@ -212,6 +216,7 @@ void __init jump_label_init(void)
 		key->next = NULL;
 #endif
 	}
+	static_key_initialized = true;
 	jump_label_unlock();
 }
 
-- 
cgit 


From a48e42920ff38bc90bbf75143fff4555723d4540 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:55 +0200
Subject: net: introduce new macro net_get_random_once

net_get_random_once is a new macro which handles the initialization
of secret keys. It is possible to call it in the fast path. Only the
initialization depends on the spinlock and is rather slow. Otherwise
it should get used just before the key is used to delay the entropy
extration as late as possible to get better randomness. It returns true
if the key got initialized.

The usage of static_keys for net_get_random_once is a bit uncommon so
it needs some further explanation why this actually works:

=== In the simple non-HAVE_JUMP_LABEL case we actually have ===
no constrains to use static_key_(true|false) on keys initialized with
STATIC_KEY_INIT_(FALSE|TRUE). So this path just expands in favor of
the likely case that the initialization is already done. The key is
initialized like this:

___done_key = { .enabled = ATOMIC_INIT(0) }

The check

                if (!static_key_true(&___done_key))                     \

expands into (pseudo code)

                if (!likely(___done_key > 0))

, so we take the fast path as soon as ___done_key is increased from the
helper function.

=== If HAVE_JUMP_LABELs are available this depends ===
on patching of jumps into the prepared NOPs, which is done in
jump_label_init at boot-up time (from start_kernel). It is forbidden
and dangerous to use net_get_random_once in functions which are called
before that!

At compilation time NOPs are generated at the call sites of
net_get_random_once. E.g. net/ipv6/inet6_hashtable.c:inet6_ehashfn (we
need to call net_get_random_once two times in inet6_ehashfn, so two NOPs):

      71:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
      76:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)

Both will be patched to the actual jumps to the end of the function to
call __net_get_random_once at boot time as explained above.

arch_static_branch is optimized and inlined for false as return value and
actually also returns false in case the NOP is placed in the instruction
stream. So in the fast case we get a "return false". But because we
initialize ___done_key with (enabled != (entries & 1)) this call-site
will get patched up at boot thus returning true. The final check looks
like this:

                if (!static_key_true(&___done_key))                     \
                        ___ret = __net_get_random_once(buf,             \

expands to

                if (!!static_key_false(&___done_key))                     \
                        ___ret = __net_get_random_once(buf,             \

So we get true at boot time and as soon as static_key_slow_inc is called
on the key it will invert the logic and return false for the fast path.
static_key_slow_inc will change the branch because it got initialized
with .enabled == 0. After static_key_slow_inc is called on the key the
branch is replaced with a nop again.

=== Misc: ===
The helper defers the increment into a workqueue so we don't
have problems calling this code from atomic sections. A seperate boolean
(___done) guards the case where we enter net_get_random_once again before
the increment happend.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 25 +++++++++++++++++++++++++
 net/core/utils.c    | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 73 insertions(+)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index ca9ec8540905..a489705f6fa3 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -239,6 +239,31 @@ do {								\
 #define net_random()		prandom_u32()
 #define net_srandom(seed)	prandom_seed((__force u32)(seed))
 
+bool __net_get_random_once(void *buf, int nbytes, bool *done,
+			   struct static_key *done_key);
+
+#ifdef HAVE_JUMP_LABEL
+#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \
+		{ .enabled = ATOMIC_INIT(0), .entries = (void *)1 })
+#else /* !HAVE_JUMP_LABEL */
+#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
+#endif /* HAVE_JUMP_LABEL */
+
+/* BE CAREFUL: this function is not interrupt safe */
+#define net_get_random_once(buf, nbytes)				\
+	({								\
+		bool ___ret = false;					\
+		static bool ___done = false;				\
+		static struct static_key ___done_key =			\
+			___NET_RANDOM_STATIC_KEY_INIT;			\
+		if (!static_key_true(&___done_key))			\
+			___ret = __net_get_random_once(buf,		\
+						       nbytes,		\
+						       &___done,	\
+						       &___done_key);	\
+		___ret;							\
+	})
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
 int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
diff --git a/net/core/utils.c b/net/core/utils.c
index aa88e23fc87a..bf09371e19b1 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -338,3 +338,51 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 				  csum_unfold(*sum)));
 }
 EXPORT_SYMBOL(inet_proto_csum_replace16);
+
+struct __net_random_once_work {
+	struct work_struct work;
+	struct static_key *key;
+};
+
+static void __net_random_once_deferred(struct work_struct *w)
+{
+	struct __net_random_once_work *work =
+		container_of(w, struct __net_random_once_work, work);
+	if (!static_key_enabled(work->key))
+		static_key_slow_inc(work->key);
+	kfree(work);
+}
+
+static void __net_random_once_disable_jump(struct static_key *key)
+{
+	struct __net_random_once_work *w;
+
+	w = kmalloc(sizeof(*w), GFP_ATOMIC);
+	if (!w)
+		return;
+
+	INIT_WORK(&w->work, __net_random_once_deferred);
+	w->key = key;
+	schedule_work(&w->work);
+}
+
+bool __net_get_random_once(void *buf, int nbytes, bool *done,
+			   struct static_key *done_key)
+{
+	static DEFINE_SPINLOCK(lock);
+
+	spin_lock_bh(&lock);
+	if (*done) {
+		spin_unlock_bh(&lock);
+		return false;
+	}
+
+	get_random_bytes(buf, nbytes);
+	*done = true;
+	spin_unlock_bh(&lock);
+
+	__net_random_once_disable_jump(done_key);
+
+	return true;
+}
+EXPORT_SYMBOL(__net_get_random_once);
-- 
cgit 


From b23a002fc6f0c19846ee0382f019429af54a27e9 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:56 +0200
Subject: inet: split syncookie keys for ipv4 and ipv6 and initialize with
 net_get_random_once

This patch splits the secret key for syncookies for ipv4 and ipv6 and
initializes them with net_get_random_once. This change was the reason I
did this series. I think the initialization of the syncookie_secret is
way to early.

Cc: Florian Westphal <fw@strlen.de>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     |  1 -
 net/ipv4/syncookies.c | 15 +++++----------
 net/ipv6/syncookies.c | 12 +++++++++---
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 372dcccfeed0..f30326f1c92b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -475,7 +475,6 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size);
 void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 
 /* From syncookies.c */
-extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 		      u32 cookie);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3b64c59b4109..b95331e6c077 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -25,15 +25,7 @@
 
 extern int sysctl_tcp_syncookies;
 
-__u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
-EXPORT_SYMBOL(syncookie_secret);
-
-static __init int init_syncookies(void)
-{
-	get_random_bytes(syncookie_secret, sizeof(syncookie_secret));
-	return 0;
-}
-__initcall(init_syncookies);
+static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
 
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
@@ -44,8 +36,11 @@ static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
 {
-	__u32 *tmp = __get_cpu_var(ipv4_cookie_scratch);
+	__u32 *tmp;
+
+	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
 
+	tmp  = __get_cpu_var(ipv4_cookie_scratch);
 	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
 	tmp[0] = (__force u32)saddr;
 	tmp[1] = (__force u32)daddr;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index d04d3f1dd9b7..535a3ad262f1 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,6 +24,8 @@
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
+static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS];
+
 /* RFC 2460, Section 8.3:
  * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
  *
@@ -61,14 +63,18 @@ static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
 static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
 {
-	__u32 *tmp = __get_cpu_var(ipv6_cookie_scratch);
+	__u32 *tmp;
+
+	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
+
+	tmp  = __get_cpu_var(ipv6_cookie_scratch);
 
 	/*
 	 * we have 320 bits of information to hash, copy in the remaining
-	 * 192 bits required for sha_transform, from the syncookie_secret
+	 * 192 bits required for sha_transform, from the syncookie6_secret
 	 * and overwrite the digest with the secret
 	 */
-	memcpy(tmp + 10, syncookie_secret[c], 44);
+	memcpy(tmp + 10, syncookie6_secret[c], 44);
 	memcpy(tmp, saddr, 16);
 	memcpy(tmp + 4, daddr, 16);
 	tmp[8] = ((__force u32)sport << 16) + (__force u32)dport;
-- 
cgit 


From 1bbdceef1e535add893bf71d7b7ab102e4eb69eb Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:57 +0200
Subject: inet: convert inet_ehash_secret and ipv6_hash_secret to
 net_get_random_once

Initialize the ehash and ipv6_hash_secrets with net_get_random_once.

Each compilation unit gets its own secret now:
  ipv4/inet_hashtables.o
  ipv4/udp.o
  ipv6/inet6_hashtables.o
  ipv6/udp.o
  rds/connection.o

The functions still get inlined into the hashing functions. In the fast
path we have at most two (needed in ipv6) if (unlikely(...)).

Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h     |  4 ----
 net/ipv4/af_inet.c          | 27 ---------------------------
 net/ipv4/inet_hashtables.c  |  4 ++++
 net/ipv4/udp.c              |  6 +++++-
 net/ipv6/af_inet6.c         |  5 -----
 net/ipv6/inet6_hashtables.c | 15 ++++++++++++---
 net/ipv6/udp.c              | 17 ++++++++++++++---
 net/rds/connection.c        | 12 +++++++++---
 8 files changed, 44 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 7a6c7f80a8fd..1833c3f389ee 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -204,10 +204,6 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
 
 int inet_sk_rebuild_header(struct sock *sk);
 
-extern u32 inet_ehash_secret;
-extern u32 ipv6_hash_secret;
-void build_ehash_secret(void);
-
 static inline unsigned int __inet_ehashfn(const __be32 laddr,
 					  const __u16 lport,
 					  const __be32 faddr,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4049906010f7..9433a6186f54 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -245,29 +245,6 @@ out:
 }
 EXPORT_SYMBOL(inet_listen);
 
-u32 inet_ehash_secret __read_mostly;
-EXPORT_SYMBOL(inet_ehash_secret);
-
-u32 ipv6_hash_secret __read_mostly;
-EXPORT_SYMBOL(ipv6_hash_secret);
-
-/*
- * inet_ehash_secret must be set exactly once, and to a non nul value
- * ipv6_hash_secret must be set exactly once.
- */
-void build_ehash_secret(void)
-{
-	u32 rnd;
-
-	do {
-		get_random_bytes(&rnd, sizeof(rnd));
-	} while (rnd == 0);
-
-	if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
-		get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
-}
-EXPORT_SYMBOL(build_ehash_secret);
-
 /*
  *	Create an inet socket.
  */
@@ -284,10 +261,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
-	if (unlikely(!inet_ehash_secret))
-		if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
-			build_ehash_secret();
-
 	sock->state = SS_UNCONNECTED;
 
 	/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 18aa668d0cc9..8b9cf279450d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -28,6 +28,10 @@ static unsigned int inet_ehashfn(struct net *net, const __be32 laddr,
 				 const __u16 lport, const __be32 faddr,
 				 const __be16 fport)
 {
+	static u32 inet_ehash_secret __read_mostly;
+
+	net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
+
 	return __inet_ehashfn(laddr, lport, faddr, fport,
 			      inet_ehash_secret + net_hash_mix(net));
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b4437c7db6ce..89909dd730dd 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -411,8 +411,12 @@ static unsigned int udp_ehashfn(struct net *net, const __be32 laddr,
 				 const __u16 lport, const __be32 faddr,
 				 const __be16 fport)
 {
+	static u32 udp_ehash_secret __read_mostly;
+
+	net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret));
+
 	return __inet_ehashfn(laddr, lport, faddr, fport,
-			      inet_ehash_secret + net_hash_mix(net));
+			      udp_ehash_secret + net_hash_mix(net));
 }
 
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index a2cb07cd3850..20af1fb81c83 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -110,11 +110,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	int try_loading_module = 0;
 	int err;
 
-	if (sock->type != SOCK_RAW &&
-	    sock->type != SOCK_DGRAM &&
-	    !inet_ehash_secret)
-		build_ehash_secret();
-
 	/* Look for the requested type/protocol pair. */
 lookup_protocol:
 	err = -ESOCKTNOSUPPORT;
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index fa7dd3856c55..262e13c02ec2 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -29,10 +29,19 @@ static unsigned int inet6_ehashfn(struct net *net,
 				  const struct in6_addr *faddr,
 				  const __be16 fport)
 {
-	const u32 lhash = (__force u32)laddr->s6_addr32[3];
-	const u32 fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+	static u32 inet6_ehash_secret __read_mostly;
+	static u32 ipv6_hash_secret __read_mostly;
+
+	u32 lhash, fhash;
+
+	net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret));
+	net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
+
+	lhash = (__force u32)laddr->s6_addr32[3];
+	fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+
 	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet_ehash_secret + net_hash_mix(net));
+			       inet6_ehash_secret + net_hash_mix(net));
 }
 
 static int inet6_sk_ehashfn(const struct sock *sk)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 324bd36c23bc..44fc4e3d661f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -59,10 +59,21 @@ static unsigned int udp6_ehashfn(struct net *net,
 				  const struct in6_addr *faddr,
 				  const __be16 fport)
 {
-	const u32 lhash = (__force u32)laddr->s6_addr32[3];
-	const u32 fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
+	static u32 udp6_ehash_secret __read_mostly;
+	static u32 udp_ipv6_hash_secret __read_mostly;
+
+	u32 lhash, fhash;
+
+	net_get_random_once(&udp6_ehash_secret,
+			    sizeof(udp6_ehash_secret));
+	net_get_random_once(&udp_ipv6_hash_secret,
+			    sizeof(udp_ipv6_hash_secret));
+
+	lhash = (__force u32)laddr->s6_addr32[3];
+	fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
+
 	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet_ehash_secret + net_hash_mix(net));
+			       udp_ipv6_hash_secret + net_hash_mix(net));
 }
 
 int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 45e23660437a..378c3a6acf84 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -51,10 +51,16 @@ static struct kmem_cache *rds_conn_slab;
 
 static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
 {
+	static u32 rds_hash_secret __read_mostly;
+
+	unsigned long hash;
+
+	net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret));
+
 	/* Pass NULL, don't need struct net for hash */
-	unsigned long hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
-					    be32_to_cpu(faddr), 0,
-					    inet_ehash_secret);
+	hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
+			      be32_to_cpu(faddr), 0,
+			      rds_hash_secret);
 	return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
 }
 
-- 
cgit 


From 222e83d2e0aecb6a5e8d42b1a8d51332a1eba960 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sat, 19 Oct 2013 21:48:58 +0200
Subject: tcp: switch tcp_fastopen key generation to net_get_random_once

Changed key initialization of tcp_fastopen cookies to net_get_random_once.

If the user sets a custom key net_get_random_once must be called at
least once to ensure we don't overwrite the user provided key when the
first cookie is generated later on.

Cc: Yuchung Cheng <ycheng@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h          |  2 +-
 net/ipv4/sysctl_net_ipv4.c |  5 +++++
 net/ipv4/tcp_fastopen.c    | 27 ++++++++++++++++-----------
 3 files changed, 22 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f30326f1c92b..b12e29a76590 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1322,7 +1322,7 @@ extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 int tcp_fastopen_reset_cipher(void *key, unsigned int len);
 void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
 			     struct tcp_fastopen_cookie *foc);
-
+void tcp_fastopen_init_key_once(bool publish);
 #define TCP_FASTOPEN_KEY_LENGTH 16
 
 /* Fastopen key context */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c08f096d46b5..4b161d5aba0b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -274,6 +274,11 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
+		/* Generate a dummy secret but don't publish it. This
+		 * is needed so we don't regenerate a new key on the
+		 * first invocation of tcp_fastopen_cookie_gen
+		 */
+		tcp_fastopen_init_key_once(false);
 		tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
 	}
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index ab7bd35bb312..766032b4a6c3 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -14,6 +14,20 @@ struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 
 static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
 
+void tcp_fastopen_init_key_once(bool publish)
+{
+	static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+	/* tcp_fastopen_reset_cipher publishes the new context
+	 * atomically, so we allow this race happening here.
+	 *
+	 * All call sites of tcp_fastopen_cookie_gen also check
+	 * for a valid cookie, so this is an acceptable risk.
+	 */
+	if (net_get_random_once(key, sizeof(key)) && publish)
+		tcp_fastopen_reset_cipher(key, sizeof(key));
+}
+
 static void tcp_fastopen_ctx_free(struct rcu_head *head)
 {
 	struct tcp_fastopen_context *ctx =
@@ -70,6 +84,8 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
 	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
 
+	tcp_fastopen_init_key_once(true);
+
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
@@ -78,14 +94,3 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
 	}
 	rcu_read_unlock();
 }
-
-static int __init tcp_fastopen_init(void)
-{
-	__u8 key[TCP_FASTOPEN_KEY_LENGTH];
-
-	get_random_bytes(key, sizeof(key));
-	tcp_fastopen_reset_cipher(key, sizeof(key));
-	return 0;
-}
-
-late_initcall(tcp_fastopen_init);
-- 
cgit 


From e54686e4c79a5b2e8d8c77317ac8ab08d3040935 Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Fri, 11 Oct 2013 00:44:54 +0530
Subject: ARM: dts: AM4372: Update Support for EPOS EVM

-> Adding pinmux for cpsw, i2c0.
-> Enabling the modules that are present in AM4372 EPOS EVM
These modules are tested on AM4372 EPOS EVM.

Signed-off-by: Lokesh Vutla <lokeshvutla@ti.com>
Signed-off-by: Sourav Poddar <sourav.poddar@ti.com>
Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: Benoit Cousson <bcousson@baylibre.com>
---
 arch/arm/boot/dts/am43x-epos-evm.dts | 168 +++++++++++++++++++++++++++++++++++
 include/dt-bindings/pinctrl/am43xx.h |  31 +++++++
 2 files changed, 199 insertions(+)
 create mode 100644 include/dt-bindings/pinctrl/am43xx.h

(limited to 'include')

diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 74174d48f476..fbf9c4c7a94f 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -11,8 +11,176 @@
 /dts-v1/;
 
 #include "am4372.dtsi"
+#include <dt-bindings/pinctrl/am43xx.h>
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "TI AM43x EPOS EVM";
 	compatible = "ti,am43x-epos-evm","ti,am4372","ti,am43";
+
+	vmmcsd_fixed: fixedregulator-sd {
+		compatible = "regulator-fixed";
+		regulator-name = "vmmcsd_fixed";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		enable-active-high;
+	};
+
+	am43xx_pinmux: pinmux@44e10800 {
+		cpsw_default: cpsw_default {
+			pinctrl-single,pins = <
+				/* Slave 1 */
+				0x10c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_crs.rmii1_crs */
+				0x110 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxerr.rmii1_rxerr */
+				0x114 (PIN_OUTPUT_PULLDOWN | MUX_MODE1)	/* mii1_txen.rmii1_txen */
+				0x118 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxdv.rmii1_rxdv */
+				0x124 (PIN_OUTPUT_PULLDOWN | MUX_MODE1)	/* mii1_txd1.rmii1_txd1 */
+				0x128 (PIN_OUTPUT_PULLDOWN | MUX_MODE1)	/* mii1_txd0.rmii1_txd0 */
+				0x13c (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxd1.rmii1_rxd1 */
+				0x140 (PIN_INPUT_PULLDOWN | MUX_MODE1)	/* mii1_rxd0.rmii1_rxd0 */
+				0x144 (PIN_INPUT_PULLDOWN | MUX_MODE0)	/* rmii1_refclk.rmii1_refclk */
+			>;
+		};
+
+		cpsw_sleep: cpsw_sleep {
+			pinctrl-single,pins = <
+				/* Slave 1 reset value */
+				0x10c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x110 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x114 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x118 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x124 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x128 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x13c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x140 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x144 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			>;
+		};
+
+		davinci_mdio_default: davinci_mdio_default {
+			pinctrl-single,pins = <
+				/* MDIO */
+				0x148 (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* mdio_data.mdio_data */
+				0x14c (PIN_OUTPUT_PULLUP | MUX_MODE0)			/* mdio_clk.mdio_clk */
+			>;
+		};
+
+		davinci_mdio_sleep: davinci_mdio_sleep {
+			pinctrl-single,pins = <
+				/* MDIO reset value */
+				0x148 (PIN_INPUT_PULLDOWN | MUX_MODE7)
+				0x14c (PIN_INPUT_PULLDOWN | MUX_MODE7)
+			>;
+		};
+
+		i2c0_pins: pinmux_i2c0_pins {
+			pinctrl-single,pins = <
+				0x188 (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* i2c0_sda.i2c0_sda */
+				0x18c (PIN_INPUT_PULLUP | SLEWCTRL_FAST | MUX_MODE0)	/* i2c0_scl.i2c0_scl */
+			>;
+		};
+	};
+
+	matrix_keypad: matrix_keypad@0 {
+			compatible = "gpio-matrix-keypad";
+			debounce-delay-ms = <5>;
+			col-scan-delay-us = <2>;
+
+			row-gpios = <&gpio0 12 GPIO_ACTIVE_HIGH		/* Bank0, pin12 */
+				     &gpio0 13 GPIO_ACTIVE_HIGH		/* Bank0, pin13 */
+				     &gpio0 14 GPIO_ACTIVE_HIGH		/* Bank0, pin14 */
+				     &gpio0 15 GPIO_ACTIVE_HIGH>;	/* Bank0, pin15 */
+
+			col-gpios = <&gpio3 9 GPIO_ACTIVE_HIGH		/* Bank3, pin9 */
+				     &gpio3 10 GPIO_ACTIVE_HIGH		/* Bank3, pin10 */
+				     &gpio2 18 GPIO_ACTIVE_HIGH		/* Bank2, pin18 */
+				     &gpio2 19 GPIO_ACTIVE_HIGH>;	/* Bank2, pin19 */
+
+			linux,keymap = <0x00000201	/* P1 */
+				0x01000204	/* P4 */
+				0x02000207	/* P7 */
+				0x0300020a	/* NUMERIC_STAR */
+				0x00010202	/* P2 */
+				0x01010205	/* P5 */
+				0x02010208	/* P8 */
+				0x03010200	/* P0 */
+				0x00020203	/* P3 */
+				0x01020206	/* P6 */
+				0x02020209	/* P9 */
+				0x0302020b	/* NUMERIC_POUND */
+				0x00030067	/* UP */
+				0x0103006a	/* RIGHT */
+				0x0203006c	/* DOWN */
+				0x03030069>;	/* LEFT */
+		};
+};
+
+&mmc1 {
+	status = "okay";
+	vmmc-supply = <&vmmcsd_fixed>;
+	bus-width = <4>;
+};
+
+&mac {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&cpsw_default>;
+	pinctrl-1 = <&cpsw_sleep>;
+	status = "okay";
+};
+
+&davinci_mdio {
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&davinci_mdio_default>;
+	pinctrl-1 = <&davinci_mdio_sleep>;
+	status = "okay";
+};
+
+&cpsw_emac0 {
+	phy_id = <&davinci_mdio>, <16>;
+	phy-mode = "rmii";
+};
+
+&cpsw_emac1 {
+	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "rmii";
+};
+
+&i2c0 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c0_pins>;
+
+	at24@50 {
+		compatible = "at24,24c256";
+		pagesize = <64>;
+		reg = <0x50>;
+	};
+
+	pixcir_ts@5c {
+		compatible = "pixcir,pixcir_ts";
+		reg = <0x5c>;
+		interrupt-parent = <&gpio1>;
+		interrupts = <17 0>;
+
+		attb-gpio = <&gpio1 17 GPIO_ACTIVE_HIGH>;
+
+		x-size = <1024>;
+		y-size = <768>;
+	};
+};
+
+&gpio0 {
+	status = "okay";
+};
+
+&gpio1 {
+	status = "okay";
+};
+
+&gpio2 {
+	status = "okay";
+};
+
+&gpio3 {
+	status = "okay";
 };
diff --git a/include/dt-bindings/pinctrl/am43xx.h b/include/dt-bindings/pinctrl/am43xx.h
new file mode 100644
index 000000000000..eb6c366adfba
--- /dev/null
+++ b/include/dt-bindings/pinctrl/am43xx.h
@@ -0,0 +1,31 @@
+/*
+ * This header provides constants specific to AM43XX pinctrl bindings.
+ */
+
+#ifndef _DT_BINDINGS_PINCTRL_AM43XX_H
+#define _DT_BINDINGS_PINCTRL_AM43XX_H
+
+#define MUX_MODE0	0
+#define MUX_MODE1	1
+#define MUX_MODE2	2
+#define MUX_MODE3	3
+#define MUX_MODE4	4
+#define MUX_MODE5	5
+#define MUX_MODE6	6
+#define MUX_MODE7	7
+
+#define PULL_DISABLE		(1 << 16)
+#define PULL_UP			(1 << 17)
+#define INPUT_EN		(1 << 18)
+#define SLEWCTRL_FAST		(1 << 19)
+#define DS0_PULL_UP_DOWN_EN	(1 << 27)
+
+#define PIN_OUTPUT		(PULL_DISABLE)
+#define PIN_OUTPUT_PULLUP	(PULL_UP)
+#define PIN_OUTPUT_PULLDOWN	0
+#define PIN_INPUT		(INPUT_EN | PULL_DISABLE)
+#define PIN_INPUT_PULLUP	(INPUT_EN | PULL_UP)
+#define PIN_INPUT_PULLDOWN	(INPUT_EN)
+
+#endif
+
-- 
cgit 


From 1fecf8958eb7f90791f2c7e99afac393b64fa976 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Mon, 21 Oct 2013 05:32:48 +0900
Subject: ARM: S3C24XX: add dma pdata for s3c2410, s3c2440 and s3c2442

s3c2410 and s3c2442 share the same dma channels while s3c2440 has
slight differences. But on all three the reachable sources per dma
channel has constraints attached and thus encodes the usable
combinations using the S3C24XX_DMA_CHANREQ macro.

This also fixes the warning about s3c2410_dma_resource being unused
as reported by Olof Johansson.

Reported-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
---
 arch/arm/mach-s3c24xx/common.c            | 100 ++++++++++++++++++++++++++++++
 arch/arm/mach-s3c24xx/common.h            |   2 +
 include/linux/platform_data/dma-s3c24xx.h |   3 +
 3 files changed, 105 insertions(+)

(limited to 'include')

diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c
index bdcb29f4ea31..4adaa4b43ffe 100644
--- a/arch/arm/mach-s3c24xx/common.c
+++ b/arch/arm/mach-s3c24xx/common.c
@@ -343,6 +343,50 @@ static struct resource s3c2410_dma_resource[] = {
 };
 #endif
 
+#if defined(CONFIG_CPU_S3C2410) || defined(CONFIG_CPU_S3C2442)
+static struct s3c24xx_dma_channel s3c2410_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 0), },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 1), },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, S3C24XX_DMA_CHANREQ(2, 0) |
+						S3C24XX_DMA_CHANREQ(2, 2) |
+						S3C24XX_DMA_CHANREQ(1, 3),
+	},
+	[DMACH_SPI0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 1), },
+	[DMACH_SPI1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 3), },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 0), },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 1), },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 3), },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 0) |
+						 S3C24XX_DMA_CHANREQ(3, 2) |
+						 S3C24XX_DMA_CHANREQ(3, 3),
+	},
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 1) |
+						  S3C24XX_DMA_CHANREQ(1, 2),
+	},
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 2), },
+	[DMACH_USB_EP1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 0), },
+	[DMACH_USB_EP2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 1), },
+	[DMACH_USB_EP3] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 2), },
+	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), },
+};
+
+static struct s3c24xx_dma_platdata s3c2410_dma_platdata = {
+	.num_phy_channels = 4,
+	.channels = s3c2410_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2410_device_dma = {
+	.name		= "s3c2410-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2410_dma_resource),
+	.resource	= s3c2410_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2410_dma_platdata,
+	},
+};
+#endif
+
 #ifdef CONFIG_CPU_S3C2412
 static struct s3c24xx_dma_channel s3c2412_dma_channels[DMACH_MAX] = {
 	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, 17 },
@@ -384,6 +428,62 @@ struct platform_device s3c2412_device_dma = {
 };
 #endif
 
+#if defined(CONFIG_CPU_S3C2440)
+static struct s3c24xx_dma_channel s3c2440_dma_channels[DMACH_MAX] = {
+	[DMACH_XD0] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 0), },
+	[DMACH_XD1] = { S3C24XX_DMA_AHB, true, S3C24XX_DMA_CHANREQ(0, 1), },
+	[DMACH_SDI] = { S3C24XX_DMA_APB, false, S3C24XX_DMA_CHANREQ(2, 0) |
+						S3C24XX_DMA_CHANREQ(6, 1) |
+						S3C24XX_DMA_CHANREQ(2, 2) |
+						S3C24XX_DMA_CHANREQ(1, 3),
+	},
+	[DMACH_SPI0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 1), },
+	[DMACH_SPI1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 3), },
+	[DMACH_UART0] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 0), },
+	[DMACH_UART1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(1, 1), },
+	[DMACH_UART2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(0, 3), },
+	[DMACH_TIMER] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(3, 0) |
+						 S3C24XX_DMA_CHANREQ(3, 2) |
+						 S3C24XX_DMA_CHANREQ(3, 3),
+	},
+	[DMACH_I2S_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(2, 1) |
+						  S3C24XX_DMA_CHANREQ(1, 2),
+	},
+	[DMACH_I2S_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(5, 0) |
+						   S3C24XX_DMA_CHANREQ(0, 2),
+	},
+	[DMACH_PCM_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(6, 0) |
+						  S3C24XX_DMA_CHANREQ(5, 2),
+	},
+	[DMACH_PCM_OUT] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(5, 1) |
+						  S3C24XX_DMA_CHANREQ(6, 3),
+	},
+	[DMACH_MIC_IN] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(6, 2) |
+						  S3C24XX_DMA_CHANREQ(5, 3),
+	},
+	[DMACH_USB_EP1] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 0), },
+	[DMACH_USB_EP2] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 1), },
+	[DMACH_USB_EP3] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 2), },
+	[DMACH_USB_EP4] = { S3C24XX_DMA_APB, true, S3C24XX_DMA_CHANREQ(4, 3), },
+};
+
+static struct s3c24xx_dma_platdata s3c2440_dma_platdata = {
+	.num_phy_channels = 4,
+	.channels = s3c2440_dma_channels,
+	.num_channels = DMACH_MAX,
+};
+
+struct platform_device s3c2440_device_dma = {
+	.name		= "s3c2410-dma",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(s3c2410_dma_resource),
+	.resource	= s3c2410_dma_resource,
+	.dev	= {
+		.platform_data	= &s3c2440_dma_platdata,
+	},
+};
+#endif
+
 #if defined(CONFIG_CPUS_3C2443) || defined(CONFIG_CPU_S3C2416)
 static struct resource s3c2443_dma_resource[] = {
 	[0] = DEFINE_RES_MEM(S3C24XX_PA_DMA, S3C24XX_SZ_DMA),
diff --git a/arch/arm/mach-s3c24xx/common.h b/arch/arm/mach-s3c24xx/common.h
index fe071893275f..e46c10417216 100644
--- a/arch/arm/mach-s3c24xx/common.h
+++ b/arch/arm/mach-s3c24xx/common.h
@@ -109,7 +109,9 @@ extern void s3c2443_init_irq(void);
 
 extern struct syscore_ops s3c24xx_irq_syscore_ops;
 
+extern struct platform_device s3c2410_device_dma;
 extern struct platform_device s3c2412_device_dma;
+extern struct platform_device s3c2440_device_dma;
 extern struct platform_device s3c2443_device_dma;
 
 #endif /* __ARCH_ARM_MACH_S3C24XX_COMMON_H */
diff --git a/include/linux/platform_data/dma-s3c24xx.h b/include/linux/platform_data/dma-s3c24xx.h
index 5a0cfffe3bbb..89ba1b0c90e4 100644
--- a/include/linux/platform_data/dma-s3c24xx.h
+++ b/include/linux/platform_data/dma-s3c24xx.h
@@ -9,6 +9,9 @@
  * any later version.
  */
 
+/* Helper to encode the source selection constraints for early s3c socs. */
+#define S3C24XX_DMA_CHANREQ(src, chan)	((BIT(3) | src) << chan * 4)
+
 enum s3c24xx_dma_bus {
 	S3C24XX_DMA_APB,
 	S3C24XX_DMA_AHB,
-- 
cgit 


From 7f6ac89c1d1e0c654ea02c8c2dd0ee8e1ce2795f Mon Sep 17 00:00:00 2001
From: Fugang Duan <B38611@freescale.com>
Date: Tue, 3 Sep 2013 12:26:24 +0800
Subject: ARM: imx6sl: add imx6sl iomux-gpr field define

Add imx6sl iomux-gpr register field define in "imx6q-iomuxc-gpr.h" header
file, which is not fully define all iomux-gpr registers and fields, only
add fec related macro define.

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
---
 include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
index b6bdcd66c07d..7086b2248c8f 100644
--- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
+++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
@@ -363,4 +363,9 @@
 #define IMX6Q_GPR13_SATA_TX_LVL_1_240_V		(0x1f << 2)
 #define IMX6Q_GPR13_SATA_MPLL_CLK_EN		BIT(1)
 #define IMX6Q_GPR13_SATA_TX_EDGE_RATE		BIT(0)
+
+/* For imx6sl iomux gpr register field define */
+#define IMX6SL_GPR1_FEC_CLOCK_MUX1_SEL_MASK    (0x3 << 17)
+#define IMX6SL_GPR1_FEC_CLOCK_MUX2_SEL_MASK    (0x1 << 14)
+
 #endif /* __LINUX_IMX6Q_IOMUXC_GPR_H */
-- 
cgit 


From 602519b2bd63adfdf9e24b2f94aaddcfeb464e9e Mon Sep 17 00:00:00 2001
From: Dong Aisheng <b29396@freescale.com>
Date: Fri, 18 Oct 2013 19:48:47 +0800
Subject: mmc: sdhci-esdhc-imx: add delay line setting support

The DLL(Delay Line) is newly added to assist in sampling read data.
The DLL provides the ability to programmatically select a quantized
delay (in fractions of the clock period) regardless of on-chip variations
such as process, voltage and temperature (PVT).

This patch adds a user interface to set slave delay line via device tree.
It's usually used in high speed mode like mmc DDR mode when the signal
quality is not good caused by board design, e.g. the signal path is too
long.  User can manually set delay line to find a suitable data sampling
window for card to work properly.

Signed-off-by: Dong Aisheng <b29396@freescale.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 .../devicetree/bindings/mmc/fsl-imx-esdhc.txt          |  5 +++++
 drivers/mmc/host/sdhci-esdhc-imx.c                     | 18 ++++++++++++++++++
 include/linux/platform_data/mmc-esdhc-imx.h            |  1 +
 3 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 1dd622546d06..9046ba06c47a 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -12,6 +12,11 @@ Required properties:
 Optional properties:
 - fsl,cd-controller : Indicate to use controller internal card detection
 - fsl,wp-controller : Indicate to use controller internal write protection
+- fsl,delay-line : Specify the number of delay cells for override mode.
+  This is used to set the clock delay for DLL(Delay Line) on override mode
+  to select a proper data sampling window in case the clock quality is not good
+  due to signal path is too long on the board. Please refer to eSDHC/uSDHC
+  chapter, DLL (Delay Line) section in RM for details.
 
 Examples:
 
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 915fa68e5122..260a81fde18d 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -46,6 +46,11 @@
 /* Bits 3 and 6 are not SDHCI standard definitions */
 #define  ESDHC_MIX_CTRL_SDHCI_MASK	0xb7
 
+/* dll control register */
+#define ESDHC_DLL_CTRL			0x60
+#define ESDHC_DLL_OVERRIDE_VAL_SHIFT	9
+#define ESDHC_DLL_OVERRIDE_EN_SHIFT	8
+
 /* tune control register */
 #define ESDHC_TUNE_CTRL_STATUS		0x68
 #define  ESDHC_TUNE_CTRL_STEP		1
@@ -817,6 +822,7 @@ static int esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+	struct esdhc_platform_data *boarddata = &imx_data->boarddata;
 
 	switch (uhs) {
 	case MMC_TIMING_UHS_SDR12:
@@ -837,6 +843,15 @@ static int esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 				ESDHC_MIX_CTRL_DDREN,
 				host->ioaddr + ESDHC_MIX_CTRL);
 		imx_data->is_ddr = 1;
+		if (boarddata->delay_line) {
+			u32 v;
+			v = boarddata->delay_line <<
+				ESDHC_DLL_OVERRIDE_VAL_SHIFT |
+				(1 << ESDHC_DLL_OVERRIDE_EN_SHIFT);
+			if (is_imx53_esdhc(imx_data))
+				v <<= 1;
+			writel(v, host->ioaddr + ESDHC_DLL_CTRL);
+		}
 		break;
 	}
 
@@ -901,6 +916,9 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 	else
 		boarddata->support_vsel = true;
 
+	if (of_property_read_u32(np, "fsl,delay-line", &boarddata->delay_line))
+		boarddata->delay_line = 0;
+
 	return 0;
 }
 #else
diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h
index a0f5a8f9b3bc..75f70f6ac137 100644
--- a/include/linux/platform_data/mmc-esdhc-imx.h
+++ b/include/linux/platform_data/mmc-esdhc-imx.h
@@ -45,5 +45,6 @@ struct esdhc_platform_data {
 	int max_bus_width;
 	unsigned int f_max;
 	bool support_vsel;
+	unsigned int delay_line;
 };
 #endif /* __ASM_ARCH_IMX_ESDHC_H */
-- 
cgit 


From c68c7f5a88328fbcd992c68e99ebd6bf7d49e9d2 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Sun, 20 Oct 2013 06:26:02 +0200
Subject: net: fix build warnings because of net_get_random_once merge

This patch fixes the following warning:

   In file included from include/linux/skbuff.h:27:0,
                    from include/linux/netfilter.h:5,
                    from include/net/netns/netfilter.h:5,
                    from include/net/net_namespace.h:20,
                    from include/linux/init_task.h:14,
                    from init/init_task.c:1:
include/linux/net.h:243:14: warning: 'struct static_key' declared inside parameter list [enabled by default]
          struct static_key *done_key);

on x86_64 allnoconfig, um defconfig and ia64 allmodconfig and maybe others as well.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index a489705f6fa3..aca446b46754 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -24,6 +24,7 @@
 #include <linux/fcntl.h>	/* For O_CLOEXEC and O_NONBLOCK */
 #include <linux/kmemcheck.h>
 #include <linux/rcupdate.h>
+#include <linux/jump_label.h>
 #include <uapi/linux/net.h>
 
 struct poll_table_struct;
-- 
cgit 


From 0e790c64f37a1a43c147720bdfa03b7c5538e24a Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Mon, 21 Oct 2013 18:22:24 -0200
Subject: Bluetooth: Add L2CAP channel to skb private data

Adding the channel to the skb private data makes possible to us know which
channel the skb we have came from.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/bluetooth.h | 1 +
 net/bluetooth/l2cap_sock.c        | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index bf2ddffdae2d..a707a0209df4 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -282,6 +282,7 @@ struct bt_skb_cb {
 	__u8 incoming;
 	__u16 expect;
 	__u8 force_active;
+	struct l2cap_chan *chan;
 	struct l2cap_ctrl control;
 	struct hci_req_ctrl req;
 	bdaddr_t bdaddr;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a159b0e05202..cba3162dc33d 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1174,6 +1174,8 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan,
 	if (!skb)
 		return ERR_PTR(err);
 
+	bt_cb(skb)->chan = chan;
+
 	return skb;
 }
 
-- 
cgit 


From d78a32a8fcf775111ccc9ba611a08ca5c29784b6 Mon Sep 17 00:00:00 2001
From: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date: Mon, 21 Oct 2013 18:22:26 -0200
Subject: Bluetooth: Remove sk member from struct l2cap_chan

There is no access to chan->sk in L2CAP core now. This change marks the
end of the task of splitting L2CAP between Core and Socket, thus sk is now
gone from struct l2cap_chan.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 2 --
 net/bluetooth/l2cap_sock.c    | 2 --
 2 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 3d922b938141..51329905bfaa 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -435,8 +435,6 @@ struct l2cap_seq_list {
 #define L2CAP_SEQ_LIST_TAIL	0x8000
 
 struct l2cap_chan {
-	struct sock *sk;
-
 	struct l2cap_conn	*conn;
 	struct hci_conn		*hs_hcon;
 	struct hci_chan		*hs_hchan;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index cba3162dc33d..7cc24d263caa 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1374,8 +1374,6 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock,
 
 	l2cap_chan_hold(chan);
 
-	chan->sk = sk;
-
 	l2cap_pi(sk)->chan = chan;
 
 	return sk;
-- 
cgit 


From 5eccdfaabcf44f71702ba033d9c24821111749e1 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 19 Oct 2013 22:05:31 -0700
Subject: nf_tables*.h: Remove extern from function prototypes

There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_tables.h      | 55 ++++++++++++++++------------------
 include/net/netfilter/nf_tables_core.h | 28 ++++++++---------
 2 files changed, 40 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 54c4a5cafb64..5a91abfc0c30 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -91,13 +91,11 @@ struct nft_data_desc {
 	unsigned int			len;
 };
 
-extern int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
-			 struct nft_data_desc *desc, const struct nlattr *nla);
-extern void nft_data_uninit(const struct nft_data *data,
-			    enum nft_data_types type);
-extern int nft_data_dump(struct sk_buff *skb, int attr,
-			 const struct nft_data *data,
-			 enum nft_data_types type, unsigned int len);
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
+		  struct nft_data_desc *desc, const struct nlattr *nla);
+void nft_data_uninit(const struct nft_data *data, enum nft_data_types type);
+int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
+		  enum nft_data_types type, unsigned int len);
 
 static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg)
 {
@@ -109,12 +107,11 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
 	return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1;
 }
 
-extern int nft_validate_input_register(enum nft_registers reg);
-extern int nft_validate_output_register(enum nft_registers reg);
-extern int nft_validate_data_load(const struct nft_ctx *ctx,
-				  enum nft_registers reg,
-				  const struct nft_data *data,
-				  enum nft_data_types type);
+int nft_validate_input_register(enum nft_registers reg);
+int nft_validate_output_register(enum nft_registers reg);
+int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg,
+			   const struct nft_data *data,
+			   enum nft_data_types type);
 
 /**
  *	struct nft_set_elem - generic representation of set elements
@@ -183,8 +180,8 @@ struct nft_set_ops {
 	u32				features;
 };
 
-extern int nft_register_set(struct nft_set_ops *ops);
-extern void nft_unregister_set(struct nft_set_ops *ops);
+int nft_register_set(struct nft_set_ops *ops);
+void nft_unregister_set(struct nft_set_ops *ops);
 
 /**
  * 	struct nft_set - nf_tables set instance
@@ -220,8 +217,8 @@ static inline void *nft_set_priv(const struct nft_set *set)
 	return (void *)set->data;
 }
 
-extern struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
-					    const struct nlattr *nla);
+struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
+				     const struct nlattr *nla);
 
 /**
  *	struct nft_set_binding - nf_tables set binding
@@ -237,10 +234,10 @@ struct nft_set_binding {
 	const struct nft_chain		*chain;
 };
 
-extern int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
-			      struct nft_set_binding *binding);
-extern void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
-				 struct nft_set_binding *binding);
+int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
+		       struct nft_set_binding *binding);
+void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+			  struct nft_set_binding *binding);
 
 
 /**
@@ -446,8 +443,8 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai
 	return container_of(chain, struct nft_base_chain, chain);
 }
 
-extern unsigned int nft_do_chain_pktinfo(struct nft_pktinfo *pkt,
-					 const struct nf_hook_ops *ops);
+unsigned int nft_do_chain_pktinfo(struct nft_pktinfo *pkt,
+				  const struct nf_hook_ops *ops);
 
 /**
  *	struct nft_table - nf_tables table
@@ -489,8 +486,8 @@ struct nft_af_info {
 	nf_hookfn			*hooks[NF_MAX_HOOKS];
 };
 
-extern int nft_register_afinfo(struct net *, struct nft_af_info *);
-extern void nft_unregister_afinfo(struct nft_af_info *);
+int nft_register_afinfo(struct net *, struct nft_af_info *);
+void nft_unregister_afinfo(struct nft_af_info *);
 
 struct nf_chain_type {
 	unsigned int		hook_mask;
@@ -501,11 +498,11 @@ struct nf_chain_type {
 	int			family;
 };
 
-extern int nft_register_chain_type(struct nf_chain_type *);
-extern void nft_unregister_chain_type(struct nf_chain_type *);
+int nft_register_chain_type(struct nf_chain_type *);
+void nft_unregister_chain_type(struct nf_chain_type *);
 
-extern int nft_register_expr(struct nft_expr_type *);
-extern void nft_unregister_expr(struct nft_expr_type *);
+int nft_register_expr(struct nft_expr_type *);
+void nft_unregister_expr(struct nft_expr_type *);
 
 #define MODULE_ALIAS_NFT_FAMILY(family)	\
 	MODULE_ALIAS("nft-afinfo-" __stringify(family))
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index fe7b16206a4e..cf2b7ae2b9d8 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -1,11 +1,11 @@
 #ifndef _NET_NF_TABLES_CORE_H
 #define _NET_NF_TABLES_CORE_H
 
-extern int nf_tables_core_module_init(void);
-extern void nf_tables_core_module_exit(void);
+int nf_tables_core_module_init(void);
+void nf_tables_core_module_exit(void);
 
-extern int nft_immediate_module_init(void);
-extern void nft_immediate_module_exit(void);
+int nft_immediate_module_init(void);
+void nft_immediate_module_exit(void);
 
 struct nft_cmp_fast_expr {
 	u32			data;
@@ -15,17 +15,17 @@ struct nft_cmp_fast_expr {
 
 extern const struct nft_expr_ops nft_cmp_fast_ops;
 
-extern int nft_cmp_module_init(void);
-extern void nft_cmp_module_exit(void);
+int nft_cmp_module_init(void);
+void nft_cmp_module_exit(void);
 
-extern int nft_lookup_module_init(void);
-extern void nft_lookup_module_exit(void);
+int nft_lookup_module_init(void);
+void nft_lookup_module_exit(void);
 
-extern int nft_bitwise_module_init(void);
-extern void nft_bitwise_module_exit(void);
+int nft_bitwise_module_init(void);
+void nft_bitwise_module_exit(void);
 
-extern int nft_byteorder_module_init(void);
-extern void nft_byteorder_module_exit(void);
+int nft_byteorder_module_init(void);
+void nft_byteorder_module_exit(void);
 
 struct nft_payload {
 	enum nft_payload_bases	base:8;
@@ -36,7 +36,7 @@ struct nft_payload {
 
 extern const struct nft_expr_ops nft_payload_fast_ops;
 
-extern int nft_payload_module_init(void);
-extern void nft_payload_module_exit(void);
+int nft_payload_module_init(void);
+void nft_payload_module_exit(void);
 
 #endif /* _NET_NF_TABLES_CORE_H */
-- 
cgit 


From 88f074f4871a8c212b212b725e4dcdcdb09613c1 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 18 Oct 2013 14:28:59 -0700
Subject: ACPI, CPER: Update cper info

We have a lot of confusing names of functions and data structures in
amongs the the error reporting code.  In particular the "apei" prefix
has been applied to many objects that are not part of APEI.  Since we
will be using these routines for extended error log reporting it will
be clearer if we fix up the names first.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/acpi/apei/apei-internal.h | 12 ++++----
 drivers/acpi/apei/cper.c          | 58 +++++++++++++++++++--------------------
 drivers/acpi/apei/ghes.c          | 54 ++++++++++++++++++------------------
 include/acpi/actbl1.h             | 14 +++++-----
 include/acpi/ghes.h               |  2 +-
 include/linux/cper.h              |  2 +-
 6 files changed, 71 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h
index f220d642136e..21ba34a73883 100644
--- a/drivers/acpi/apei/apei-internal.h
+++ b/drivers/acpi/apei/apei-internal.h
@@ -122,11 +122,11 @@ struct dentry;
 struct dentry *apei_get_debugfs_dir(void);
 
 #define apei_estatus_for_each_section(estatus, section)			\
-	for (section = (struct acpi_hest_generic_data *)(estatus + 1);	\
+	for (section = (struct acpi_generic_data *)(estatus + 1);	\
 	     (void *)section - (void *)estatus < estatus->data_length;	\
 	     section = (void *)(section+1) + section->error_data_length)
 
-static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus)
+static inline u32 cper_estatus_len(struct acpi_generic_status *estatus)
 {
 	if (estatus->raw_data_length)
 		return estatus->raw_data_offset + \
@@ -135,10 +135,10 @@ static inline u32 apei_estatus_len(struct acpi_hest_generic_status *estatus)
 		return sizeof(*estatus) + estatus->data_length;
 }
 
-void apei_estatus_print(const char *pfx,
-			const struct acpi_hest_generic_status *estatus);
-int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus);
-int apei_estatus_check(const struct acpi_hest_generic_status *estatus);
+void cper_estatus_print(const char *pfx,
+			const struct acpi_generic_status *estatus);
+int cper_estatus_check_header(const struct acpi_generic_status *estatus);
+int cper_estatus_check(const struct acpi_generic_status *estatus);
 
 int apei_osc_setup(void);
 #endif
diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
index f827f02bfbe8..eb5f6d6d7dbc 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -5,7 +5,7 @@
  *	Author: Huang Ying <ying.huang@intel.com>
  *
  * CPER is the format used to describe platform hardware error by
- * various APEI tables, such as ERST, BERT and HEST etc.
+ * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
  * Specification version 2.3.
@@ -73,7 +73,7 @@ static const char *cper_severity_str(unsigned int severity)
  * printed, with @pfx is printed at the beginning of each line.
  */
 void cper_print_bits(const char *pfx, unsigned int bits,
-		     const char *strs[], unsigned int strs_size)
+		     const char * const strs[], unsigned int strs_size)
 {
 	int i, len = 0;
 	const char *str;
@@ -98,32 +98,32 @@ void cper_print_bits(const char *pfx, unsigned int bits,
 		printk("%s\n", buf);
 }
 
-static const char *cper_proc_type_strs[] = {
+static const char * const cper_proc_type_strs[] = {
 	"IA32/X64",
 	"IA64",
 };
 
-static const char *cper_proc_isa_strs[] = {
+static const char * const cper_proc_isa_strs[] = {
 	"IA32",
 	"IA64",
 	"X64",
 };
 
-static const char *cper_proc_error_type_strs[] = {
+static const char * const cper_proc_error_type_strs[] = {
 	"cache error",
 	"TLB error",
 	"bus error",
 	"micro-architectural error",
 };
 
-static const char *cper_proc_op_strs[] = {
+static const char * const cper_proc_op_strs[] = {
 	"unknown or generic",
 	"data read",
 	"data write",
 	"instruction execution",
 };
 
-static const char *cper_proc_flag_strs[] = {
+static const char * const cper_proc_flag_strs[] = {
 	"restartable",
 	"precise IP",
 	"overflow",
@@ -248,7 +248,7 @@ static const char *cper_pcie_port_type_strs[] = {
 };
 
 static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
-			    const struct acpi_hest_generic_data *gdata)
+			    const struct acpi_generic_data *gdata)
 {
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
@@ -283,17 +283,17 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 }
 
-static const char *apei_estatus_section_flag_strs[] = {
+static const char * const cper_estatus_section_flag_strs[] = {
 	"primary",
 	"containment warning",
 	"reset",
-	"threshold exceeded",
+	"error threshold exceeded",
 	"resource not accessible",
 	"latent error",
 };
 
-static void apei_estatus_print_section(
-	const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+static void cper_estatus_print_section(
+	const char *pfx, const struct acpi_generic_data *gdata, int sec_no)
 {
 	uuid_le *sec_type = (uuid_le *)gdata->section_type;
 	__u16 severity;
@@ -302,8 +302,8 @@ static void apei_estatus_print_section(
 	printk("%s""section: %d, severity: %d, %s\n", pfx, sec_no, severity,
 	       cper_severity_str(severity));
 	printk("%s""flags: 0x%02x\n", pfx, gdata->flags);
-	cper_print_bits(pfx, gdata->flags, apei_estatus_section_flag_strs,
-			ARRAY_SIZE(apei_estatus_section_flag_strs));
+	cper_print_bits(pfx, gdata->flags, cper_estatus_section_flag_strs,
+			ARRAY_SIZE(cper_estatus_section_flag_strs));
 	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
 		printk("%s""fru_id: %pUl\n", pfx, (uuid_le *)gdata->fru_id);
 	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
@@ -339,34 +339,34 @@ err_section_too_small:
 	pr_err(FW_WARN "error section length is too small\n");
 }
 
-void apei_estatus_print(const char *pfx,
-			const struct acpi_hest_generic_status *estatus)
+void cper_estatus_print(const char *pfx,
+			const struct acpi_generic_status *estatus)
 {
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 	unsigned int data_len, gedata_len;
 	int sec_no = 0;
 	__u16 severity;
 
-	printk("%s""APEI generic hardware error status\n", pfx);
+	printk("%s""Generic Hardware Error Status\n", pfx);
 	severity = estatus->error_severity;
 	printk("%s""severity: %d, %s\n", pfx, severity,
 	       cper_severity_str(severity));
 	data_len = estatus->data_length;
-	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	gdata = (struct acpi_generic_data *)(estatus + 1);
 	while (data_len >= sizeof(*gdata)) {
 		gedata_len = gdata->error_data_length;
-		apei_estatus_print_section(pfx, gdata, sec_no);
+		cper_estatus_print_section(pfx, gdata, sec_no);
 		data_len -= gedata_len + sizeof(*gdata);
 		gdata = (void *)(gdata + 1) + gedata_len;
 		sec_no++;
 	}
 }
-EXPORT_SYMBOL_GPL(apei_estatus_print);
+EXPORT_SYMBOL_GPL(cper_estatus_print);
 
-int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus)
+int cper_estatus_check_header(const struct acpi_generic_status *estatus)
 {
 	if (estatus->data_length &&
-	    estatus->data_length < sizeof(struct acpi_hest_generic_data))
+	    estatus->data_length < sizeof(struct acpi_generic_data))
 		return -EINVAL;
 	if (estatus->raw_data_length &&
 	    estatus->raw_data_offset < sizeof(*estatus) + estatus->data_length)
@@ -374,19 +374,19 @@ int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(apei_estatus_check_header);
+EXPORT_SYMBOL_GPL(cper_estatus_check_header);
 
-int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
+int cper_estatus_check(const struct acpi_generic_status *estatus)
 {
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 	unsigned int data_len, gedata_len;
 	int rc;
 
-	rc = apei_estatus_check_header(estatus);
+	rc = cper_estatus_check_header(estatus);
 	if (rc)
 		return rc;
 	data_len = estatus->data_length;
-	gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+	gdata = (struct acpi_generic_data *)(estatus + 1);
 	while (data_len >= sizeof(*gdata)) {
 		gedata_len = gdata->error_data_length;
 		if (gedata_len > data_len - sizeof(*gdata))
@@ -399,4 +399,4 @@ int apei_estatus_check(const struct acpi_hest_generic_status *estatus)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(apei_estatus_check);
+EXPORT_SYMBOL_GPL(cper_estatus_check);
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 8ec37bbdd699..0db6e4ff6501 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -75,13 +75,13 @@
 #define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
 	(sizeof(struct ghes_estatus_cache) + (estatus_len))
 #define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
-	((struct acpi_hest_generic_status *)			\
+	((struct acpi_generic_status *)				\
 	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))
 
 #define GHES_ESTATUS_NODE_LEN(estatus_len)			\
 	(sizeof(struct ghes_estatus_node) + (estatus_len))
-#define GHES_ESTATUS_FROM_NODE(estatus_node)				\
-	((struct acpi_hest_generic_status *)				\
+#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
+	((struct acpi_generic_status *)				\
 	 ((struct ghes_estatus_node *)(estatus_node) + 1))
 
 bool ghes_disable;
@@ -378,17 +378,17 @@ static int ghes_read_estatus(struct ghes *ghes, int silent)
 	ghes->flags |= GHES_TO_CLEAR;
 
 	rc = -EIO;
-	len = apei_estatus_len(ghes->estatus);
+	len = cper_estatus_len(ghes->estatus);
 	if (len < sizeof(*ghes->estatus))
 		goto err_read_block;
 	if (len > ghes->generic->error_block_length)
 		goto err_read_block;
-	if (apei_estatus_check_header(ghes->estatus))
+	if (cper_estatus_check_header(ghes->estatus))
 		goto err_read_block;
 	ghes_copy_tofrom_phys(ghes->estatus + 1,
 			      buf_paddr + sizeof(*ghes->estatus),
 			      len - sizeof(*ghes->estatus), 1);
-	if (apei_estatus_check(ghes->estatus))
+	if (cper_estatus_check(ghes->estatus))
 		goto err_read_block;
 	rc = 0;
 
@@ -409,7 +409,7 @@ static void ghes_clear_estatus(struct ghes *ghes)
 	ghes->flags &= ~GHES_TO_CLEAR;
 }
 
-static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int sev)
+static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 {
 #ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
 	unsigned long pfn;
@@ -438,10 +438,10 @@ static void ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, int
 }
 
 static void ghes_do_proc(struct ghes *ghes,
-			 const struct acpi_hest_generic_status *estatus)
+			 const struct acpi_generic_status *estatus)
 {
 	int sev, sec_sev;
-	struct acpi_hest_generic_data *gdata;
+	struct acpi_generic_data *gdata;
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -496,7 +496,7 @@ static void ghes_do_proc(struct ghes *ghes,
 
 static void __ghes_print_estatus(const char *pfx,
 				 const struct acpi_hest_generic *generic,
-				 const struct acpi_hest_generic_status *estatus)
+				 const struct acpi_generic_status *estatus)
 {
 	static atomic_t seqno;
 	unsigned int curr_seqno;
@@ -513,12 +513,12 @@ static void __ghes_print_estatus(const char *pfx,
 	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno);
 	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
 	       pfx_seq, generic->header.source_id);
-	apei_estatus_print(pfx_seq, estatus);
+	cper_estatus_print(pfx_seq, estatus);
 }
 
 static int ghes_print_estatus(const char *pfx,
 			      const struct acpi_hest_generic *generic,
-			      const struct acpi_hest_generic_status *estatus)
+			      const struct acpi_generic_status *estatus)
 {
 	/* Not more than 2 messages every 5 seconds */
 	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
@@ -540,15 +540,15 @@ static int ghes_print_estatus(const char *pfx,
  * GHES error status reporting throttle, to report more kinds of
  * errors, instead of just most frequently occurred errors.
  */
-static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
+static int ghes_estatus_cached(struct acpi_generic_status *estatus)
 {
 	u32 len;
 	int i, cached = 0;
 	unsigned long long now;
 	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
+	struct acpi_generic_status *cache_estatus;
 
-	len = apei_estatus_len(estatus);
+	len = cper_estatus_len(estatus);
 	rcu_read_lock();
 	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
 		cache = rcu_dereference(ghes_estatus_caches[i]);
@@ -571,19 +571,19 @@ static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
 
 static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
 	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
+	struct acpi_generic_status *estatus)
 {
 	int alloced;
 	u32 len, cache_len;
 	struct ghes_estatus_cache *cache;
-	struct acpi_hest_generic_status *cache_estatus;
+	struct acpi_generic_status *cache_estatus;
 
 	alloced = atomic_add_return(1, &ghes_estatus_cache_alloced);
 	if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {
 		atomic_dec(&ghes_estatus_cache_alloced);
 		return NULL;
 	}
-	len = apei_estatus_len(estatus);
+	len = cper_estatus_len(estatus);
 	cache_len = GHES_ESTATUS_CACHE_LEN(len);
 	cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len);
 	if (!cache) {
@@ -603,7 +603,7 @@ static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache)
 {
 	u32 len;
 
-	len = apei_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
+	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
 	len = GHES_ESTATUS_CACHE_LEN(len);
 	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
 	atomic_dec(&ghes_estatus_cache_alloced);
@@ -619,7 +619,7 @@ static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
 
 static void ghes_estatus_cache_add(
 	struct acpi_hest_generic *generic,
-	struct acpi_hest_generic_status *estatus)
+	struct acpi_generic_status *estatus)
 {
 	int i, slot = -1, count;
 	unsigned long long now, duration, period, max_period = 0;
@@ -751,7 +751,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct llist_node *llnode, *next;
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u32 len, node_len;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
@@ -765,7 +765,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
 					   llnode);
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-		len = apei_estatus_len(estatus);
+		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		ghes_do_proc(estatus_node->ghes, estatus);
 		if (!ghes_estatus_cached(estatus)) {
@@ -784,7 +784,7 @@ static void ghes_print_queued_estatus(void)
 	struct llist_node *llnode;
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u32 len, node_len;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
@@ -797,7 +797,7 @@ static void ghes_print_queued_estatus(void)
 		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
 					   llnode);
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-		len = apei_estatus_len(estatus);
+		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		generic = estatus_node->generic;
 		ghes_print_estatus(NULL, generic, estatus);
@@ -843,7 +843,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 		u32 len, node_len;
 		struct ghes_estatus_node *estatus_node;
-		struct acpi_hest_generic_status *estatus;
+		struct acpi_generic_status *estatus;
 #endif
 		if (!(ghes->flags & GHES_TO_CLEAR))
 			continue;
@@ -851,7 +851,7 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		if (ghes_estatus_cached(ghes->estatus))
 			goto next;
 		/* Save estatus for further processing in IRQ context */
-		len = apei_estatus_len(ghes->estatus);
+		len = cper_estatus_len(ghes->estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
 		estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool,
 						      node_len);
@@ -923,7 +923,7 @@ static int ghes_probe(struct platform_device *ghes_dev)
 
 	rc = -EIO;
 	if (generic->error_block_length <
-	    sizeof(struct acpi_hest_generic_status)) {
+	    sizeof(struct acpi_generic_status)) {
 		pr_warning(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
 			   generic->error_block_length,
 			   generic->header.source_id);
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 0bd750ebeb49..556c83ee6b42 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -596,7 +596,7 @@ struct acpi_hest_generic {
 
 /* Generic Error Status block */
 
-struct acpi_hest_generic_status {
+struct acpi_generic_status {
 	u32 block_status;
 	u32 raw_data_offset;
 	u32 raw_data_length;
@@ -606,15 +606,15 @@ struct acpi_hest_generic_status {
 
 /* Values for block_status flags above */
 
-#define ACPI_HEST_UNCORRECTABLE             (1)
-#define ACPI_HEST_CORRECTABLE               (1<<1)
-#define ACPI_HEST_MULTIPLE_UNCORRECTABLE    (1<<2)
-#define ACPI_HEST_MULTIPLE_CORRECTABLE      (1<<3)
-#define ACPI_HEST_ERROR_ENTRY_COUNT         (0xFF<<4)	/* 8 bits, error count */
+#define ACPI_GEN_ERR_UC			BIT(0)
+#define ACPI_GEN_ERR_CE			BIT(1)
+#define ACPI_GEN_ERR_MULTI_UC		BIT(2)
+#define ACPI_GEN_ERR_MULTI_CE		BIT(3)
+#define ACPI_GEN_ERR_COUNT_SHIFT	(0xFF<<4) /* 8 bits, error count */
 
 /* Generic Error Data entry */
 
-struct acpi_hest_generic_data {
+struct acpi_generic_data {
 	u8 section_type[16];
 	u32 error_severity;
 	u16 revision;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 720446cb243e..dfd60d0bfd27 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -14,7 +14,7 @@
 
 struct ghes {
 	struct acpi_hest_generic *generic;
-	struct acpi_hest_generic_status *estatus;
+	struct acpi_generic_status *estatus;
 	u64 buffer_paddr;
 	unsigned long flags;
 	union {
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c23049496531..09ebe2113641 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -389,6 +389,6 @@ struct cper_sec_pcie {
 
 u64 cper_next_record_id(void);
 void cper_print_bits(const char *prefix, unsigned int bits,
-		     const char *strs[], unsigned int strs_size);
+		     const char * const strs[], unsigned int strs_size);
 
 #endif
-- 
cgit 


From 10ef6b0dffe404bcc54e94cb2ca1a5b18445a66b Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 18 Oct 2013 14:29:07 -0700
Subject: bitops: Introduce a more generic BITMASK macro

GENMASK is used to create a contiguous bitmask([hi:lo]). It is
implemented twice in current kernel. One is in EDAC driver, the other
is in SiS/XGI FB driver. Move it to a more generic place for other
usage.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Winischhofer <thomas@winischhofer.net>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/edac/amd64_edac.c | 46 ++++++++++++++++++++++++----------------------
 drivers/edac/amd64_edac.h |  8 --------
 drivers/edac/sb_edac.c    |  2 +-
 drivers/video/sis/init.c  |  5 ++---
 include/linux/bitops.h    |  8 ++++++++
 5 files changed, 35 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 3c9e4e98c651..b53d0de17e15 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -339,8 +339,8 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 	if (pvt->fam == 0xf && pvt->ext_model < K8_REV_F) {
 		csbase		= pvt->csels[dct].csbases[csrow];
 		csmask		= pvt->csels[dct].csmasks[csrow];
-		base_bits	= GENMASK(21, 31) | GENMASK(9, 15);
-		mask_bits	= GENMASK(21, 29) | GENMASK(9, 15);
+		base_bits	= GENMASK_ULL(31, 21) | GENMASK_ULL(15, 9);
+		mask_bits	= GENMASK_ULL(29, 21) | GENMASK_ULL(15, 9);
 		addr_shift	= 4;
 
 	/*
@@ -352,16 +352,16 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		csbase          = pvt->csels[dct].csbases[csrow];
 		csmask          = pvt->csels[dct].csmasks[csrow >> 1];
 
-		*base  = (csbase & GENMASK(5,  15)) << 6;
-		*base |= (csbase & GENMASK(19, 30)) << 8;
+		*base  = (csbase & GENMASK_ULL(15,  5)) << 6;
+		*base |= (csbase & GENMASK_ULL(30, 19)) << 8;
 
 		*mask = ~0ULL;
 		/* poke holes for the csmask */
-		*mask &= ~((GENMASK(5, 15)  << 6) |
-			   (GENMASK(19, 30) << 8));
+		*mask &= ~((GENMASK_ULL(15, 5)  << 6) |
+			   (GENMASK_ULL(30, 19) << 8));
 
-		*mask |= (csmask & GENMASK(5, 15))  << 6;
-		*mask |= (csmask & GENMASK(19, 30)) << 8;
+		*mask |= (csmask & GENMASK_ULL(15, 5))  << 6;
+		*mask |= (csmask & GENMASK_ULL(30, 19)) << 8;
 
 		return;
 	} else {
@@ -370,9 +370,11 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 		addr_shift	= 8;
 
 		if (pvt->fam == 0x15)
-			base_bits = mask_bits = GENMASK(19,30) | GENMASK(5,13);
+			base_bits = mask_bits =
+				GENMASK_ULL(30,19) | GENMASK_ULL(13,5);
 		else
-			base_bits = mask_bits = GENMASK(19,28) | GENMASK(5,13);
+			base_bits = mask_bits =
+				GENMASK_ULL(28,19) | GENMASK_ULL(13,5);
 	}
 
 	*base  = (csbase & base_bits) << addr_shift;
@@ -561,7 +563,7 @@ static u64 sys_addr_to_dram_addr(struct mem_ctl_info *mci, u64 sys_addr)
 	 * section 3.4.2 of AMD publication 24592: AMD x86-64 Architecture
 	 * Programmer's Manual Volume 1 Application Programming.
 	 */
-	dram_addr = (sys_addr & GENMASK(0, 39)) - dram_base;
+	dram_addr = (sys_addr & GENMASK_ULL(39, 0)) - dram_base;
 
 	edac_dbg(2, "using DRAM Base register to translate SysAddr 0x%lx to DramAddr 0x%lx\n",
 		 (unsigned long)sys_addr, (unsigned long)dram_addr);
@@ -597,7 +599,7 @@ static u64 dram_addr_to_input_addr(struct mem_ctl_info *mci, u64 dram_addr)
 	 * concerning translating a DramAddr to an InputAddr.
 	 */
 	intlv_shift = num_node_interleave_bits(dram_intlv_en(pvt, 0));
-	input_addr = ((dram_addr >> intlv_shift) & GENMASK(12, 35)) +
+	input_addr = ((dram_addr >> intlv_shift) & GENMASK_ULL(35, 12)) +
 		      (dram_addr & 0xfff);
 
 	edac_dbg(2, "  Intlv Shift=%d DramAddr=0x%lx maps to InputAddr=0x%lx\n",
@@ -849,7 +851,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		end_bit   = 39;
 	}
 
-	addr = m->addr & GENMASK(start_bit, end_bit);
+	addr = m->addr & GENMASK_ULL(end_bit, start_bit);
 
 	/*
 	 * Erratum 637 workaround
@@ -861,7 +863,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		u16 mce_nid;
 		u8 intlv_en;
 
-		if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7)
+		if ((addr & GENMASK_ULL(47, 24)) >> 24 != 0x00fdf7)
 			return addr;
 
 		mce_nid	= amd_get_nb_id(m->extcpu);
@@ -871,7 +873,7 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		intlv_en = tmp >> 21 & 0x7;
 
 		/* add [47:27] + 3 trailing bits */
-		cc6_base  = (tmp & GENMASK(0, 20)) << 3;
+		cc6_base  = (tmp & GENMASK_ULL(20, 0)) << 3;
 
 		/* reverse and add DramIntlvEn */
 		cc6_base |= intlv_en ^ 0x7;
@@ -880,18 +882,18 @@ static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 		cc6_base <<= 24;
 
 		if (!intlv_en)
-			return cc6_base | (addr & GENMASK(0, 23));
+			return cc6_base | (addr & GENMASK_ULL(23, 0));
 
 		amd64_read_pci_cfg(pvt->F1, DRAM_LOCAL_NODE_BASE, &tmp);
 
 							/* faster log2 */
-		tmp_addr  = (addr & GENMASK(12, 23)) << __fls(intlv_en + 1);
+		tmp_addr  = (addr & GENMASK_ULL(23, 12)) << __fls(intlv_en + 1);
 
 		/* OR DramIntlvSel into bits [14:12] */
-		tmp_addr |= (tmp & GENMASK(21, 23)) >> 9;
+		tmp_addr |= (tmp & GENMASK_ULL(23, 21)) >> 9;
 
 		/* add remaining [11:0] bits from original MC4_ADDR */
-		tmp_addr |= addr & GENMASK(0, 11);
+		tmp_addr |= addr & GENMASK_ULL(11, 0);
 
 		return cc6_base | tmp_addr;
 	}
@@ -952,12 +954,12 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range)
 
 	amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim);
 
-	pvt->ranges[range].lim.lo &= GENMASK(0, 15);
+	pvt->ranges[range].lim.lo &= GENMASK_ULL(15, 0);
 
 				    /* {[39:27],111b} */
 	pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16;
 
-	pvt->ranges[range].lim.hi &= GENMASK(0, 7);
+	pvt->ranges[range].lim.hi &= GENMASK_ULL(7, 0);
 
 				    /* [47:40] */
 	pvt->ranges[range].lim.hi |= llim >> 13;
@@ -1330,7 +1332,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range,
 			chan_off = dram_base;
 	}
 
-	return (sys_addr & GENMASK(6,47)) - (chan_off & GENMASK(23,47));
+	return (sys_addr & GENMASK_ULL(47,6)) - (chan_off & GENMASK_ULL(47,23));
 }
 
 /*
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index d2443cfa0698..6dc1fcc25afb 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -159,14 +159,6 @@
 #define ON true
 #define OFF false
 
-/*
- * Create a contiguous bitmask starting at bit position @lo and ending at
- * position @hi. For example
- *
- * GENMASK(21, 39) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(lo, hi)			(((1ULL << ((hi) - (lo) + 1)) - 1) << (lo))
-
 /*
  * PCI-defined configuration space registers
  */
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index e04462b60756..88f60c5fecbc 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -50,7 +50,7 @@ static int probed;
  * Get a bit field at register value <v>, from bit <lo> to bit <hi>
  */
 #define GET_BITFIELD(v, lo, hi)	\
-	(((v) & ((1ULL << ((hi) - (lo) + 1)) - 1) << (lo)) >> (lo))
+	(((v) & GENMASK_ULL(hi, lo)) >> (lo))
 
 /*
  * sbridge Memory Controller Registers
diff --git a/drivers/video/sis/init.c b/drivers/video/sis/init.c
index f082ae55c0c9..4f26bc28e60b 100644
--- a/drivers/video/sis/init.c
+++ b/drivers/video/sis/init.c
@@ -3320,9 +3320,8 @@ SiSSetMode(struct SiS_Private *SiS_Pr, unsigned short ModeNo)
 }
 
 #ifndef GETBITSTR
-#define BITMASK(h,l)    	(((unsigned)(1U << ((h)-(l)+1))-1)<<(l))
-#define GENMASK(mask)   	BITMASK(1?mask,0?mask)
-#define GETBITS(var,mask)   	(((var) & GENMASK(mask)) >> (0?mask))
+#define GENBITSMASK(mask)   	GENMASK(1?mask,0?mask)
+#define GETBITS(var,mask)   	(((var) & GENBITSMASK(mask)) >> (0?mask))
 #define GETBITSTR(val,from,to)  ((GETBITS(val,from)) << (0?to))
 #endif
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3b6b82108b9..bd0c4598d03b 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -10,6 +10,14 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
 extern unsigned int __sw_hweight32(unsigned int w);
-- 
cgit 


From cd91cce620907eb3c5b3e8b4d62aadf0a19baba9 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 19 Oct 2013 16:24:02 -0700
Subject: tcp_memcontrol: Remove tcp_max_memory

This function is never called. Remove it.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp_memcontrol.h |  1 -
 net/ipv4/tcp_memcontrol.c    | 13 -------------
 2 files changed, 14 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
index 7df18bc43a97..88cdd1cb992e 100644
--- a/include/net/tcp_memcontrol.h
+++ b/include/net/tcp_memcontrol.h
@@ -14,6 +14,5 @@ struct tcp_memcontrol {
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
 void tcp_destroy_cgroup(struct mem_cgroup *memcg);
-unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
 void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
 #endif /* _TCP_MEMCG_H */
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 559d4ae6ebf4..82985d1dc9af 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -226,19 +226,6 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 	return 0;
 }
 
-unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
-{
-	struct tcp_memcontrol *tcp;
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
-	if (!cg_proto)
-		return 0;
-
-	tcp = tcp_from_cgproto(cg_proto);
-	return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
-}
-
 void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
 {
 	struct tcp_memcontrol *tcp;
-- 
cgit 


From f594d63199688ad568fb69f6a790b11d6d6d1ba5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 19 Oct 2013 16:24:52 -0700
Subject: tcp_memcontrol: Remove setting cgroup settings via sysctl

The code is broken and does not constrain sysctl_tcp_mem as
tcp_update_limit does.  With the result that it allows the cgroup tcp
memory limits to be bypassed.

The semantics are broken as the settings are not per netns and are in a
per netns table, and instead looks at current.

Since the code is broken in both design and implementation and does not
implement the functionality for which it was written remove it.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp_memcontrol.h |  1 -
 net/ipv4/sysctl_net_ipv4.c   | 39 ++-------------------------------------
 net/ipv4/tcp_memcontrol.c    | 14 --------------
 3 files changed, 2 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
index 88cdd1cb992e..af0c0680a873 100644
--- a/include/net/tcp_memcontrol.h
+++ b/include/net/tcp_memcontrol.h
@@ -14,5 +14,4 @@ struct tcp_memcontrol {
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
 void tcp_destroy_cgroup(struct mem_cgroup *memcg);
-void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
 #endif /* _TCP_MEMCG_H */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4b161d5aba0b..8457f7bc4d89 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -204,43 +204,8 @@ static int ipv4_tcp_mem(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp,
 			   loff_t *ppos)
 {
-	int ret;
-	unsigned long vec[3];
-	struct net *net = current->nsproxy->net_ns;
-#ifdef CONFIG_MEMCG_KMEM
-	struct mem_cgroup *memcg;
-#endif
-
-	struct ctl_table tmp = {
-		.data = &vec,
-		.maxlen = sizeof(vec),
-		.mode = ctl->mode,
-	};
-
-	if (!write) {
-		ctl->data = &net->ipv4.sysctl_tcp_mem;
-		return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
-	}
-
-	ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
-	if (ret)
-		return ret;
-
-#ifdef CONFIG_MEMCG_KMEM
-	rcu_read_lock();
-	memcg = mem_cgroup_from_task(current);
-
-	tcp_prot_mem(memcg, vec[0], 0);
-	tcp_prot_mem(memcg, vec[1], 1);
-	tcp_prot_mem(memcg, vec[2], 2);
-	rcu_read_unlock();
-#endif
-
-	net->ipv4.sysctl_tcp_mem[0] = vec[0];
-	net->ipv4.sysctl_tcp_mem[1] = vec[1];
-	net->ipv4.sysctl_tcp_mem[2] = vec[2];
-
-	return 0;
+	ctl->data = &current->nsproxy->net_ns->ipv4.sysctl_tcp_mem;
+	return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
 }
 
 static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 82985d1dc9af..e7c01fcf5716 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -226,20 +226,6 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 	return 0;
 }
 
-void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
-{
-	struct tcp_memcontrol *tcp;
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return;
-
-	tcp = tcp_from_cgproto(cg_proto);
-
-	tcp->tcp_prot_mem[idx] = val;
-}
-
 static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.limit_in_bytes",
-- 
cgit 


From a4fe34bf902b8f709c635ab37f1f39de0b86cff2 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 19 Oct 2013 16:25:36 -0700
Subject: tcp_memcontrol: Remove the per netns control.

The code that is implemented is per memory cgroup not per netns, and
having per netns bits is just confusing.  Remove the per netns bits to
make it easier to see what is really going on.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  1 -
 include/net/tcp.h          |  3 +--
 net/ipv4/af_inet.c         |  2 --
 net/ipv4/sysctl_net_ipv4.c | 23 +++++++----------------
 net/ipv4/tcp.c             | 12 +++++++-----
 net/ipv4/tcp_ipv4.c        |  1 +
 net/ipv4/tcp_memcontrol.c  | 10 ++++------
 net/ipv6/af_inet6.c        |  2 --
 net/ipv6/tcp_ipv6.c        |  1 +
 9 files changed, 21 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 5dbd232e12ff..ee520cba2ec2 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -71,7 +71,6 @@ struct netns_ipv4 {
 	int sysctl_tcp_ecn;
 
 	kgid_t sysctl_ping_group_range[2];
-	long sysctl_tcp_mem[3];
 
 	atomic_t dev_addr_genid;
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b12e29a76590..2d7b4bdc972f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -259,6 +259,7 @@ extern int sysctl_tcp_max_orphans;
 extern int sysctl_tcp_fack;
 extern int sysctl_tcp_reordering;
 extern int sysctl_tcp_dsack;
+extern long sysctl_tcp_mem[3];
 extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
@@ -348,8 +349,6 @@ extern struct proto tcp_prot;
 #define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
 #define TCP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val)
 
-void tcp_init_mem(struct net *net);
-
 void tcp_tasklet_init(void);
 
 void tcp_v4_err(struct sk_buff *skb, u32);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9433a6186f54..24a53fc275b0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1697,8 +1697,6 @@ static int __init inet_init(void)
 	ip_static_sysctl_init();
 #endif
 
-	tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
-
 	/*
 	 *	Add all the base protocols.
 	 */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 8457f7bc4d89..69c6a8dbe09d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -200,14 +200,6 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
 	return ret;
 }
 
-static int ipv4_tcp_mem(struct ctl_table *ctl, int write,
-			   void __user *buffer, size_t *lenp,
-			   loff_t *ppos)
-{
-	ctl->data = &current->nsproxy->net_ns->ipv4.sysctl_tcp_mem;
-	return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
-}
-
 static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos)
@@ -521,6 +513,13 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tcp_mem",
+		.maxlen		= sizeof(sysctl_tcp_mem),
+		.data		= &sysctl_tcp_mem,
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{
 		.procname	= "tcp_wmem",
 		.data		= &sysctl_tcp_wmem,
@@ -830,12 +829,6 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
-	{
-		.procname	= "tcp_mem",
-		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_mem),
-		.mode		= 0644,
-		.proc_handler	= ipv4_tcp_mem,
-	},
 	{ }
 };
 
@@ -887,8 +880,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	net->ipv4.sysctl_local_ports.range[0] =  32768;
 	net->ipv4.sysctl_local_ports.range[1] =  61000;
 
-	tcp_init_mem(net);
-
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index be4b161802e8..8e8529d3c8c9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -288,9 +288,11 @@ int sysctl_tcp_min_tso_segs __read_mostly = 2;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
+long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
+EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
@@ -3097,13 +3099,13 @@ static int __init set_thash_entries(char *str)
 }
 __setup("thash_entries=", set_thash_entries);
 
-void tcp_init_mem(struct net *net)
+static void tcp_init_mem(void)
 {
 	unsigned long limit = nr_free_buffer_pages() / 8;
 	limit = max(limit, 128UL);
-	net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
-	net->ipv4.sysctl_tcp_mem[1] = limit;
-	net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+	sysctl_tcp_mem[0] = limit / 4 * 3;
+	sysctl_tcp_mem[1] = limit;
+	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
 }
 
 void __init tcp_init(void)
@@ -3165,7 +3167,7 @@ void __init tcp_init(void)
 	sysctl_tcp_max_orphans = cnt / 2;
 	sysctl_max_syn_backlog = max(128, cnt / 256);
 
-	tcp_init_mem(&init_net);
+	tcp_init_mem();
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
 	limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
 	max_wshare = min(4UL*1024*1024, limit);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 114d1b748cbb..300ab2c93f29 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2749,6 +2749,7 @@ struct proto tcp_prot = {
 	.orphan_count		= &tcp_orphan_count,
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
+	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index e7c01fcf5716..86feaa0d6d70 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -29,7 +29,6 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 	struct cg_proto *cg_proto, *parent_cg;
 	struct tcp_memcontrol *tcp;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
-	struct net *net = current->nsproxy->net_ns;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -37,9 +36,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	tcp = tcp_from_cgproto(cg_proto);
 
-	tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
-	tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
-	tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
+	tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0];
+	tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1];
+	tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2];
 	tcp->tcp_memory_pressure = 0;
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
@@ -76,7 +75,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup);
 
 static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 {
-	struct net *net = current->nsproxy->net_ns;
 	struct tcp_memcontrol *tcp;
 	struct cg_proto *cg_proto;
 	u64 old_lim;
@@ -99,7 +97,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 
 	for (i = 0; i < 3; i++)
 		tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
-					     net->ipv4.sysctl_tcp_mem[i]);
+					     sysctl_tcp_mem[i]);
 
 	if (val == RES_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 20af1fb81c83..6468bda1f2b9 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -865,8 +865,6 @@ static int __init inet6_init(void)
 	if (err)
 		goto out_sock_register_fail;
 
-	tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
-
 	/*
 	 *	ipngwg API draft makes clear that the correct semantics
 	 *	for TCP and UDP is to consider one TCP and UDP instance
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b996ee2005a9..0740f93a114a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1929,6 +1929,7 @@ struct proto tcpv6_prot = {
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
 	.orphan_count		= &tcp_orphan_count,
+	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
-- 
cgit 


From 2e685cad57906e19add7189b5ff49dfb6aaa21d3 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sat, 19 Oct 2013 16:26:19 -0700
Subject: tcp_memcontrol: Kill struct tcp_memcontrol

Replace the pointers in struct cg_proto with actual data fields and kill
struct tcp_memcontrol as it is not fully redundant.

This removes a confusing, unnecessary layer of abstraction.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h           | 28 ++++++++++----------
 include/net/tcp_memcontrol.h | 10 --------
 mm/memcontrol.c              |  6 ++---
 net/ipv4/tcp_memcontrol.c    | 61 +++++++++++++-------------------------------
 4 files changed, 35 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7e50df5c71d4..86bb0668c581 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1036,10 +1036,10 @@ enum cg_proto_flags {
 
 struct cg_proto {
 	void			(*enter_memory_pressure)(struct sock *sk);
-	struct res_counter	*memory_allocated;	/* Current allocated memory. */
-	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
-	int			*memory_pressure;
-	long			*sysctl_mem;
+	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
+	int			memory_pressure;
+	long			sysctl_mem[3];
 	unsigned long		flags;
 	/*
 	 * memcg field is used to find which memcg we belong directly
@@ -1135,9 +1135,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 		return false;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return !!*sk->sk_cgrp->memory_pressure;
+		return !!sk->sk_cgrp->memory_pressure;
 
-	return !!*sk->sk_prot->memory_pressure;
+	return !!sk->sk_prot->memory_pressure;
 }
 
 static inline void sk_leave_memory_pressure(struct sock *sk)
@@ -1155,8 +1155,8 @@ static inline void sk_leave_memory_pressure(struct sock *sk)
 		struct proto *prot = sk->sk_prot;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			if (*cg_proto->memory_pressure)
-				*cg_proto->memory_pressure = 0;
+			if (cg_proto->memory_pressure)
+				cg_proto->memory_pressure = 0;
 	}
 
 }
@@ -1192,7 +1192,7 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 	struct res_counter *fail;
 	int ret;
 
-	ret = res_counter_charge_nofail(prot->memory_allocated,
+	ret = res_counter_charge_nofail(&prot->memory_allocated,
 					amt << PAGE_SHIFT, &fail);
 	if (ret < 0)
 		*parent_status = OVER_LIMIT;
@@ -1201,13 +1201,13 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
 }
 
 static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
 {
 	u64 ret;
-	ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
+	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
 	return ret >> PAGE_SHIFT;
 }
 
@@ -1255,7 +1255,7 @@ static inline void sk_sockets_allocated_dec(struct sock *sk)
 		struct cg_proto *cg_proto = sk->sk_cgrp;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			percpu_counter_dec(cg_proto->sockets_allocated);
+			percpu_counter_dec(&cg_proto->sockets_allocated);
 	}
 
 	percpu_counter_dec(prot->sockets_allocated);
@@ -1269,7 +1269,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk)
 		struct cg_proto *cg_proto = sk->sk_cgrp;
 
 		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
-			percpu_counter_inc(cg_proto->sockets_allocated);
+			percpu_counter_inc(&cg_proto->sockets_allocated);
 	}
 
 	percpu_counter_inc(prot->sockets_allocated);
@@ -1281,7 +1281,7 @@ sk_sockets_allocated_read_positive(struct sock *sk)
 	struct proto *prot = sk->sk_prot;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return percpu_counter_read_positive(sk->sk_cgrp->sockets_allocated);
+		return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated);
 
 	return percpu_counter_read_positive(prot->sockets_allocated);
 }
diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
index af0c0680a873..05b94d9453de 100644
--- a/include/net/tcp_memcontrol.h
+++ b/include/net/tcp_memcontrol.h
@@ -1,16 +1,6 @@
 #ifndef _TCP_MEMCG_H
 #define _TCP_MEMCG_H
 
-struct tcp_memcontrol {
-	struct cg_proto cg_proto;
-	/* per-cgroup tcp memory pressure knobs */
-	struct res_counter tcp_memory_allocated;
-	struct percpu_counter tcp_sockets_allocated;
-	/* those two are read-mostly, leave them at the end */
-	long tcp_prot_mem[3];
-	int tcp_memory_pressure;
-};
-
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
 void tcp_destroy_cgroup(struct mem_cgroup *memcg);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1c52ddbc839b..28243f7d9c23 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -311,7 +311,7 @@ struct mem_cgroup {
 
 	atomic_t	dead_count;
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct tcp_memcontrol tcp_mem;
+	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
 	/* analogous to slab_common's slab_caches list. per-memcg */
@@ -550,13 +550,13 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 	if (!memcg || mem_cgroup_is_root(memcg))
 		return NULL;
 
-	return &memcg->tcp_mem.cg_proto;
+	return &memcg->tcp_mem;
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 
 static void disarm_sock_keys(struct mem_cgroup *memcg)
 {
-	if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
+	if (!memcg_proto_activated(&memcg->tcp_mem))
 		return;
 	static_key_slow_dec(&memcg_socket_limit_enabled);
 }
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 86feaa0d6d70..03e9154f7e68 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -6,15 +6,10 @@
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
-static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
-{
-	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
-}
-
 static void memcg_tcp_enter_memory_pressure(struct sock *sk)
 {
 	if (sk->sk_cgrp->memory_pressure)
-		*sk->sk_cgrp->memory_pressure = 1;
+		sk->sk_cgrp->memory_pressure = 1;
 }
 EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
 
@@ -27,33 +22,24 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 	 */
 	struct res_counter *res_parent = NULL;
 	struct cg_proto *cg_proto, *parent_cg;
-	struct tcp_memcontrol *tcp;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
 		return 0;
 
-	tcp = tcp_from_cgproto(cg_proto);
-
-	tcp->tcp_prot_mem[0] = sysctl_tcp_mem[0];
-	tcp->tcp_prot_mem[1] = sysctl_tcp_mem[1];
-	tcp->tcp_prot_mem[2] = sysctl_tcp_mem[2];
-	tcp->tcp_memory_pressure = 0;
+	cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0];
+	cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1];
+	cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2];
+	cg_proto->memory_pressure = 0;
+	cg_proto->memcg = memcg;
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = parent_cg->memory_allocated;
-
-	res_counter_init(&tcp->tcp_memory_allocated, res_parent);
-	percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
+		res_parent = &parent_cg->memory_allocated;
 
-	cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
-	cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
-	cg_proto->sysctl_mem = tcp->tcp_prot_mem;
-	cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
-	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
-	cg_proto->memcg = memcg;
+	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	percpu_counter_init(&cg_proto->sockets_allocated, 0);
 
 	return 0;
 }
@@ -62,20 +48,17 @@ EXPORT_SYMBOL(tcp_init_cgroup);
 void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 {
 	struct cg_proto *cg_proto;
-	struct tcp_memcontrol *tcp;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
 		return;
 
-	tcp = tcp_from_cgproto(cg_proto);
-	percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+	percpu_counter_destroy(&cg_proto->sockets_allocated);
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
 static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 {
-	struct tcp_memcontrol *tcp;
 	struct cg_proto *cg_proto;
 	u64 old_lim;
 	int i;
@@ -88,16 +71,14 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (val > RES_COUNTER_MAX)
 		val = RES_COUNTER_MAX;
 
-	tcp = tcp_from_cgproto(cg_proto);
-
-	old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
-	ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
+	old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT);
+	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
-					     sysctl_tcp_mem[i]);
+		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+						sysctl_tcp_mem[i]);
 
 	if (val == RES_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
@@ -154,28 +135,24 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 
 static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
 {
-	struct tcp_memcontrol *tcp;
 	struct cg_proto *cg_proto;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
 		return default_val;
 
-	tcp = tcp_from_cgproto(cg_proto);
-	return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
+	return res_counter_read_u64(&cg_proto->memory_allocated, type);
 }
 
 static u64 tcp_read_usage(struct mem_cgroup *memcg)
 {
-	struct tcp_memcontrol *tcp;
 	struct cg_proto *cg_proto;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
 		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
 
-	tcp = tcp_from_cgproto(cg_proto);
-	return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
 }
 
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -203,21 +180,19 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 {
 	struct mem_cgroup *memcg;
-	struct tcp_memcontrol *tcp;
 	struct cg_proto *cg_proto;
 
 	memcg = mem_cgroup_from_css(css);
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
 		return 0;
-	tcp = tcp_from_cgproto(cg_proto);
 
 	switch (event) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&tcp->tcp_memory_allocated);
+		res_counter_reset_max(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&tcp->tcp_memory_allocated);
+		res_counter_reset_failcnt(&cg_proto->memory_allocated);
 		break;
 	}
 
-- 
cgit 


From 61c1db7fae21ed33c614356a43bf6580c5e53118 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 20 Oct 2013 20:47:30 -0700
Subject: ipv6: sit: add GSO/TSO support

Now ipv6_gso_segment() is stackable, its relatively easy to
implement GSO/TSO support for SIT tunnels

Performance results, when segmentation is done after tunnel
device (as no NIC is yet enabled for TSO SIT support) :

Before patch :

lpq84:~# ./netperf -H 2002:af6:1153:: -Cc
MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:1153:: () port 0 AF_INET6
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      3168.31   4.81     4.64     2.988   2.877

After patch :

lpq84:~# ./netperf -H 2002:af6:1153:: -Cc
MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to 2002:af6:1153:: () port 0 AF_INET6
Recv   Send    Send                          Utilization       Service Demand
Socket Socket  Message  Elapsed              Send     Recv     Send    Recv
Size   Size    Size     Time     Throughput  local    remote   local   remote
bytes  bytes   bytes    secs.    10^6bits/s  % S      % S      us/KB   us/KB

 87380  16384  16384    10.00      5525.00   7.76     5.17     2.763   1.840

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h |  2 ++
 include/linux/skbuff.h          |  6 ++++--
 net/core/ethtool.c              |  1 +
 net/ipv4/af_inet.c              |  1 +
 net/ipv4/tcp_offload.c          |  1 +
 net/ipv6/ip6_offload.c          | 11 +++++++++++
 net/ipv6/sit.c                  | 28 +++++++++++++++++++---------
 net/ipv6/udp_offload.c          |  1 +
 8 files changed, 40 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 8dad68cede1c..b05a4b501ab5 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -43,6 +43,7 @@ enum {
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
 	NETIF_F_GSO_IPIP_BIT,		/* ... IPIP tunnel with TSO */
+	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
@@ -109,6 +110,7 @@ enum {
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
 #define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
+#define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 60729134d253..2c154976394b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -320,9 +320,11 @@ enum {
 
 	SKB_GSO_IPIP = 1 << 7,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 8,
+	SKB_GSO_SIT = 1 << 8,
 
-	SKB_GSO_MPLS = 1 << 9,
+	SKB_GSO_UDP_TUNNEL = 1 << 9,
+
+	SKB_GSO_MPLS = 1 << 10,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 8cab7744790e..862989898f61 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -82,6 +82,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
+	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_MPLS_BIT] =	 "tx-mpls-segmentation",
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 24a53fc275b0..f4a159e705c0 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1265,6 +1265,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
 		       SKB_GSO_IPIP |
+		       SKB_GSO_SIT |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index dfc96b00673e..a7a5583eab04 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -57,6 +57,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
 			       SKB_GSO_IPIP |
+			       SKB_GSO_SIT |
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
 			       0) ||
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index f9b33d82bb9d..4b851692b1f6 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -98,6 +98,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
 		       SKB_GSO_IPIP |
+		       SKB_GSO_SIT |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
@@ -276,6 +277,13 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 	},
 };
 
+static const struct net_offload sit_offload = {
+	.callbacks = {
+		.gso_send_check = ipv6_gso_send_check,
+		.gso_segment	= ipv6_gso_segment,
+	},
+};
+
 static int __init ipv6_offload_init(void)
 {
 
@@ -287,6 +295,9 @@ static int __init ipv6_offload_init(void)
 		pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);
 
 	dev_add_offload(&ipv6_packet_offload);
+
+	inet_add_offload(&sit_offload, IPPROTO_IPV6);
+
 	return 0;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 19269453a8ea..3a9038dd818d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -933,10 +933,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ttl = iph6->hop_limit;
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
+	if (IS_ERR(skb))
+		goto out;
 
 	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
 			    ttl, df, !net_eq(tunnel->net, dev_net(dev)));
@@ -946,8 +945,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 tx_error_icmp:
 	dst_link_failure(skb);
 tx_error:
-	dev->stats.tx_errors++;
 	dev_kfree_skb(skb);
+out:
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -956,13 +956,15 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto out;
 
 	ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
 	return NETDEV_TX_OK;
+out:
+	dev->stats.tx_errors++;
+	return NETDEV_TX_OK;
 }
 
 static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
@@ -1292,6 +1294,12 @@ static void ipip6_dev_free(struct net_device *dev)
 	free_netdev(dev);
 }
 
+#define SIT_FEATURES (NETIF_F_SG	   | \
+		      NETIF_F_FRAGLIST	   | \
+		      NETIF_F_HIGHDMA	   | \
+		      NETIF_F_GSO_SOFTWARE | \
+		      NETIF_F_HW_CSUM)
+
 static void ipip6_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipip6_netdev_ops;
@@ -1305,6 +1313,8 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_LLTX;
+	dev->features		|= SIT_FEATURES;
+	dev->hw_features	|= SIT_FEATURES;
 }
 
 static int ipip6_tunnel_init(struct net_device *dev)
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index f63780ff3732..08e23b0bf302 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -65,6 +65,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 				      SKB_GSO_UDP_TUNNEL |
 				      SKB_GSO_GRE |
 				      SKB_GSO_IPIP |
+				      SKB_GSO_SIT |
 				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
-- 
cgit 


From 93302880d8a3e5dc6b7da3f9825beb839152c940 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Fri, 18 Oct 2013 11:41:55 +0200
Subject: netfilter: ipset: Use netlink callback dump args only

Instead of cb->data, use callback dump args only and introduce symbolic
names instead of plain numbers at accessing the argument members.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h  | 10 +++++
 net/netfilter/ipset/ip_set_bitmap_gen.h | 11 +++---
 net/netfilter/ipset/ip_set_core.c       | 70 ++++++++++++++++-----------------
 net/netfilter/ipset/ip_set_hash_gen.h   | 20 +++++-----
 net/netfilter/ipset/ip_set_list_set.c   | 11 +++---
 5 files changed, 68 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 7967516adc0d..c7174b816674 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -316,6 +316,16 @@ ip_set_init_counter(struct ip_set_counter *counter,
 		atomic64_set(&(counter)->packets, (long long)(ext->packets));
 }
 
+/* Netlink CB args */
+enum {
+	IPSET_CB_NET = 0,
+	IPSET_CB_DUMP,
+	IPSET_CB_INDEX,
+	IPSET_CB_ARG0,
+	IPSET_CB_ARG1,
+	IPSET_CB_ARG2,
+};
+
 /* register and unregister set references */
 extern ip_set_id_t ip_set_get_byname(struct net *net,
 				     const char *name, struct ip_set **set);
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index a13e15be7911..f2c7d83dc23f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -198,13 +198,14 @@ mtype_list(const struct ip_set *set,
 	struct mtype *map = set->data;
 	struct nlattr *adt, *nested;
 	void *x;
-	u32 id, first = cb->args[2];
+	u32 id, first = cb->args[IPSET_CB_ARG0];
 
 	adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
 	if (!adt)
 		return -EMSGSIZE;
-	for (; cb->args[2] < map->elements; cb->args[2]++) {
-		id = cb->args[2];
+	for (; cb->args[IPSET_CB_ARG0] < map->elements;
+	     cb->args[IPSET_CB_ARG0]++) {
+		id = cb->args[IPSET_CB_ARG0];
 		x = get_ext(set, map, id);
 		if (!test_bit(id, map->members) ||
 		    (SET_WITH_TIMEOUT(set) &&
@@ -231,14 +232,14 @@ mtype_list(const struct ip_set *set,
 	ipset_nest_end(skb, adt);
 
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 
 	return 0;
 
 nla_put_failure:
 	nla_nest_cancel(skb, nested);
 	if (unlikely(id == first)) {
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, adt);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index dc9284bdd2dd..bac7e01df67f 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1182,10 +1182,12 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
 static int
 ip_set_dump_done(struct netlink_callback *cb)
 {
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
-	if (cb->args[2]) {
-		pr_debug("release set %s\n", nfnl_set(inst, cb->args[1])->name);
-		__ip_set_put_byindex(inst, (ip_set_id_t) cb->args[1]);
+	struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET];
+	if (cb->args[IPSET_CB_ARG0]) {
+		pr_debug("release set %s\n",
+			 nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name);
+		__ip_set_put_byindex(inst,
+			(ip_set_id_t) cb->args[IPSET_CB_INDEX]);
 	}
 	return 0;
 }
@@ -1203,7 +1205,7 @@ dump_attrs(struct nlmsghdr *nlh)
 }
 
 static int
-dump_init(struct netlink_callback *cb)
+dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
 	int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
@@ -1211,15 +1213,15 @@ dump_init(struct netlink_callback *cb)
 	struct nlattr *attr = (void *)nlh + min_len;
 	u32 dump_type;
 	ip_set_id_t index;
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
 	/* Second pass, so parser can't fail */
 	nla_parse(cda, IPSET_ATTR_CMD_MAX,
 		  attr, nlh->nlmsg_len - min_len, ip_set_setname_policy);
 
-	/* cb->args[0] : dump single set/all sets
-	 *         [1] : set index
-	 *         [..]: type specific
+	/* cb->args[IPSET_CB_NET]:	net namespace
+	 *         [IPSET_CB_DUMP]:	dump single set/all sets
+	 *         [IPSET_CB_INDEX]: 	set index
+	 *         [IPSET_CB_ARG0]:	type specific
 	 */
 
 	if (cda[IPSET_ATTR_SETNAME]) {
@@ -1231,7 +1233,7 @@ dump_init(struct netlink_callback *cb)
 			return -ENOENT;
 
 		dump_type = DUMP_ONE;
-		cb->args[1] = index;
+		cb->args[IPSET_CB_INDEX] = index;
 	} else
 		dump_type = DUMP_ALL;
 
@@ -1239,7 +1241,8 @@ dump_init(struct netlink_callback *cb)
 		u32 f = ip_set_get_h32(cda[IPSET_ATTR_FLAGS]);
 		dump_type |= (f << 16);
 	}
-	cb->args[0] = dump_type;
+	cb->args[IPSET_CB_NET] = (unsigned long)inst;
+	cb->args[IPSET_CB_DUMP] = dump_type;
 
 	return 0;
 }
@@ -1251,12 +1254,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	struct ip_set *set = NULL;
 	struct nlmsghdr *nlh = NULL;
 	unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0;
+	struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk));
 	u32 dump_type, dump_flags;
 	int ret = 0;
-	struct ip_set_net *inst = (struct ip_set_net *)cb->data;
 
-	if (!cb->args[0]) {
-		ret = dump_init(cb);
+	if (!cb->args[IPSET_CB_DUMP]) {
+		ret = dump_init(cb, inst);
 		if (ret < 0) {
 			nlh = nlmsg_hdr(cb->skb);
 			/* We have to create and send the error message
@@ -1267,17 +1270,18 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 
-	if (cb->args[1] >= inst->ip_set_max)
+	if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max)
 		goto out;
 
-	dump_type = DUMP_TYPE(cb->args[0]);
-	dump_flags = DUMP_FLAGS(cb->args[0]);
-	max = dump_type == DUMP_ONE ? cb->args[1] + 1 : inst->ip_set_max;
+	dump_type = DUMP_TYPE(cb->args[IPSET_CB_DUMP]);
+	dump_flags = DUMP_FLAGS(cb->args[IPSET_CB_DUMP]);
+	max = dump_type == DUMP_ONE ? cb->args[IPSET_CB_INDEX] + 1
+				    : inst->ip_set_max;
 dump_last:
-	pr_debug("args[0]: %u %u args[1]: %ld\n",
-		 dump_type, dump_flags, cb->args[1]);
-	for (; cb->args[1] < max; cb->args[1]++) {
-		index = (ip_set_id_t) cb->args[1];
+	pr_debug("dump type, flag: %u %u index: %ld\n",
+		 dump_type, dump_flags, cb->args[IPSET_CB_INDEX]);
+	for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) {
+		index = (ip_set_id_t) cb->args[IPSET_CB_INDEX];
 		set = nfnl_set(inst, index);
 		if (set == NULL) {
 			if (dump_type == DUMP_ONE) {
@@ -1294,7 +1298,7 @@ dump_last:
 		     !!(set->type->features & IPSET_DUMP_LAST)))
 			continue;
 		pr_debug("List set: %s\n", set->name);
-		if (!cb->args[2]) {
+		if (!cb->args[IPSET_CB_ARG0]) {
 			/* Start listing: make sure set won't be destroyed */
 			pr_debug("reference set\n");
 			__ip_set_get(set);
@@ -1311,7 +1315,7 @@ dump_last:
 			goto nla_put_failure;
 		if (dump_flags & IPSET_FLAG_LIST_SETNAME)
 			goto next_set;
-		switch (cb->args[2]) {
+		switch (cb->args[IPSET_CB_ARG0]) {
 		case 0:
 			/* Core header data */
 			if (nla_put_string(skb, IPSET_ATTR_TYPENAME,
@@ -1331,7 +1335,7 @@ dump_last:
 			read_lock_bh(&set->lock);
 			ret = set->variant->list(set, skb, cb);
 			read_unlock_bh(&set->lock);
-			if (!cb->args[2])
+			if (!cb->args[IPSET_CB_ARG0])
 				/* Set is done, proceed with next one */
 				goto next_set;
 			goto release_refcount;
@@ -1340,8 +1344,8 @@ dump_last:
 	/* If we dump all sets, continue with dumping last ones */
 	if (dump_type == DUMP_ALL) {
 		dump_type = DUMP_LAST;
-		cb->args[0] = dump_type | (dump_flags << 16);
-		cb->args[1] = 0;
+		cb->args[IPSET_CB_DUMP] = dump_type | (dump_flags << 16);
+		cb->args[IPSET_CB_INDEX] = 0;
 		goto dump_last;
 	}
 	goto out;
@@ -1350,15 +1354,15 @@ nla_put_failure:
 	ret = -EFAULT;
 next_set:
 	if (dump_type == DUMP_ONE)
-		cb->args[1] = IPSET_INVALID_ID;
+		cb->args[IPSET_CB_INDEX] = IPSET_INVALID_ID;
 	else
-		cb->args[1]++;
+		cb->args[IPSET_CB_INDEX]++;
 release_refcount:
 	/* If there was an error or set is done, release set */
-	if (ret || !cb->args[2]) {
+	if (ret || !cb->args[IPSET_CB_ARG0]) {
 		pr_debug("release set %s\n", nfnl_set(inst, index)->name);
 		__ip_set_put_byindex(inst, index);
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 	}
 out:
 	if (nlh) {
@@ -1375,8 +1379,6 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 	    const struct nlmsghdr *nlh,
 	    const struct nlattr * const attr[])
 {
-	struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
-
 	if (unlikely(protocol_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
@@ -1384,7 +1386,6 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
 		struct netlink_dump_control c = {
 			.dump = ip_set_dump_start,
 			.done = ip_set_dump_done,
-			.data = (void *)inst
 		};
 		return netlink_dump_start(ctnl, skb, nlh, &c);
 	}
@@ -1961,7 +1962,6 @@ static int __net_init
 ip_set_net_init(struct net *net)
 {
 	struct ip_set_net *inst = ip_set_pernet(net);
-
 	struct ip_set **list;
 
 	inst->ip_set_max = max_sets ? max_sets : CONFIG_IP_SET_MAX;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 6a80dbd30df7..2f80c74c871f 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -931,7 +931,7 @@ mtype_list(const struct ip_set *set,
 	struct nlattr *atd, *nested;
 	const struct hbucket *n;
 	const struct mtype_elem *e;
-	u32 first = cb->args[2];
+	u32 first = cb->args[IPSET_CB_ARG0];
 	/* We assume that one hash bucket fills into one page */
 	void *incomplete;
 	int i;
@@ -940,20 +940,22 @@ mtype_list(const struct ip_set *set,
 	if (!atd)
 		return -EMSGSIZE;
 	pr_debug("list hash set %s\n", set->name);
-	for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) {
+	for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits);
+	     cb->args[IPSET_CB_ARG0]++) {
 		incomplete = skb_tail_pointer(skb);
-		n = hbucket(t, cb->args[2]);
-		pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n);
+		n = hbucket(t, cb->args[IPSET_CB_ARG0]);
+		pr_debug("cb->arg bucket: %lu, t %p n %p\n",
+			 cb->args[IPSET_CB_ARG0], t, n);
 		for (i = 0; i < n->pos; i++) {
 			e = ahash_data(n, i, set->dsize);
 			if (SET_WITH_TIMEOUT(set) &&
 			    ip_set_timeout_expired(ext_timeout(e, set)))
 				continue;
 			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
-				 cb->args[2], n, i, e);
+				 cb->args[IPSET_CB_ARG0], n, i, e);
 			nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 			if (!nested) {
-				if (cb->args[2] == first) {
+				if (cb->args[IPSET_CB_ARG0] == first) {
 					nla_nest_cancel(skb, atd);
 					return -EMSGSIZE;
 				} else
@@ -968,16 +970,16 @@ mtype_list(const struct ip_set *set,
 	}
 	ipset_nest_end(skb, atd);
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 
 	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, incomplete);
-	if (unlikely(first == cb->args[2])) {
+	if (unlikely(first == cb->args[IPSET_CB_ARG0])) {
 		pr_warning("Can't list set %s: one bucket does not fit into "
 			   "a message. Please report it!\n", set->name);
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, atd);
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index ec6f6d15dded..3e2317f3cf68 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -490,14 +490,15 @@ list_set_list(const struct ip_set *set,
 {
 	const struct list_set *map = set->data;
 	struct nlattr *atd, *nested;
-	u32 i, first = cb->args[2];
+	u32 i, first = cb->args[IPSET_CB_ARG0];
 	const struct set_elem *e;
 
 	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
 	if (!atd)
 		return -EMSGSIZE;
-	for (; cb->args[2] < map->size; cb->args[2]++) {
-		i = cb->args[2];
+	for (; cb->args[IPSET_CB_ARG0] < map->size;
+	     cb->args[IPSET_CB_ARG0]++) {
+		i = cb->args[IPSET_CB_ARG0];
 		e = list_set_elem(set, map, i);
 		if (e->id == IPSET_INVALID_ID)
 			goto finish;
@@ -522,13 +523,13 @@ list_set_list(const struct ip_set *set,
 finish:
 	ipset_nest_end(skb, atd);
 	/* Set listing finished */
-	cb->args[2] = 0;
+	cb->args[IPSET_CB_ARG0] = 0;
 	return 0;
 
 nla_put_failure:
 	nla_nest_cancel(skb, nested);
 	if (unlikely(i == first)) {
-		cb->args[2] = 0;
+		cb->args[IPSET_CB_ARG0] = 0;
 		return -EMSGSIZE;
 	}
 	ipset_nest_end(skb, atd);
-- 
cgit 


From 5bdebb183c9702a8c57a01dff09337be3de337a6 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 11 Oct 2013 14:07:25 +1000
Subject: drm/sysfs: sort out minor and connector device object lifetimes.

So drm was abusing device lifetimes, by having embedded device structures
in the minor and connector it meant that the lifetime of the internal drm
objects (drm_minor and drm_connector) were tied to the lifetime of the device
files in sysfs, so if something kept those files opened the current code
would kfree the objects and things would go downhill from there.

Now in reality there is no need for these lifetimes to be so intertwined,
especailly with hotplugging of devices where we wish to remove the sysfs
and userspace facing pieces before we can unwind the internal objects due
to open userspace files or mmaps, so split the objects out so the struct
device is no longer embedded and do what fbdev does and just allocate
and remove the sysfs inodes separately.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_sysfs.c                     | 94 +++++++++----------------
 drivers/gpu/drm/gma500/cdv_intel_dp.c           |  2 +-
 drivers/gpu/drm/i915/i915_irq.c                 |  8 +--
 drivers/gpu/drm/i915/i915_sysfs.c               | 28 ++++----
 drivers/gpu/drm/i915/intel_dp.c                 |  2 +-
 drivers/gpu/drm/i915/intel_panel.c              |  2 +-
 drivers/gpu/drm/nouveau/nouveau_backlight.c     |  4 +-
 drivers/gpu/drm/radeon/atombios_encoders.c      |  2 +-
 drivers/gpu/drm/radeon/radeon_legacy_encoders.c |  2 +-
 include/drm/drmP.h                              |  2 +-
 include/drm/drm_crtc.h                          |  2 +-
 11 files changed, 61 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 2290b3b73832..dae42c79154f 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -22,8 +22,8 @@
 #include <drm/drm_core.h>
 #include <drm/drmP.h>
 
-#define to_drm_minor(d) container_of(d, struct drm_minor, kdev)
-#define to_drm_connector(d) container_of(d, struct drm_connector, kdev)
+#define to_drm_minor(d) dev_get_drvdata(d)
+#define to_drm_connector(d) dev_get_drvdata(d)
 
 static struct device_type drm_sysfs_device_minor = {
 	.name = "drm_minor"
@@ -162,20 +162,6 @@ void drm_sysfs_destroy(void)
 	drm_class = NULL;
 }
 
-/**
- * drm_sysfs_device_release - do nothing
- * @dev: Linux device
- *
- * Normally, this would free the DRM device associated with @dev, along
- * with cleaning up any other stuff.  But we do that in the DRM core, so
- * this function can just return and hope that the core does its job.
- */
-static void drm_sysfs_device_release(struct device *dev)
-{
-	memset(dev, 0, sizeof(struct device));
-	return;
-}
-
 /*
  * Connector properties
  */
@@ -394,29 +380,26 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 	int i;
 	int ret;
 
-	/* We shouldn't get called more than once for the same connector */
-	BUG_ON(device_is_registered(&connector->kdev));
-
-	connector->kdev.parent = &dev->primary->kdev;
-	connector->kdev.class = drm_class;
-	connector->kdev.release = drm_sysfs_device_release;
+	if (connector->kdev)
+		return 0;
 
+	/* We shouldn't get called more than once for the same connector */
+	connector->kdev = device_create(drm_class, dev->primary->kdev,
+					0, connector, "card%d-%s",
+					dev->primary->index, drm_get_connector_name(connector));
 	DRM_DEBUG("adding \"%s\" to sysfs\n",
 		  drm_get_connector_name(connector));
 
-	dev_set_name(&connector->kdev, "card%d-%s",
-		     dev->primary->index, drm_get_connector_name(connector));
-	ret = device_register(&connector->kdev);
-
-	if (ret) {
-		DRM_ERROR("failed to register connector device: %d\n", ret);
+	if (IS_ERR(connector->kdev)) {
+		DRM_ERROR("failed to register connector device: %ld\n", PTR_ERR(connector->kdev));
+		ret = PTR_ERR(connector->kdev);
 		goto out;
 	}
 
 	/* Standard attributes */
 
 	for (attr_cnt = 0; attr_cnt < ARRAY_SIZE(connector_attrs); attr_cnt++) {
-		ret = device_create_file(&connector->kdev, &connector_attrs[attr_cnt]);
+		ret = device_create_file(connector->kdev, &connector_attrs[attr_cnt]);
 		if (ret)
 			goto err_out_files;
 	}
@@ -433,7 +416,7 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 		case DRM_MODE_CONNECTOR_Component:
 		case DRM_MODE_CONNECTOR_TV:
 			for (opt_cnt = 0; opt_cnt < ARRAY_SIZE(connector_attrs_opt1); opt_cnt++) {
-				ret = device_create_file(&connector->kdev, &connector_attrs_opt1[opt_cnt]);
+				ret = device_create_file(connector->kdev, &connector_attrs_opt1[opt_cnt]);
 				if (ret)
 					goto err_out_files;
 			}
@@ -442,7 +425,7 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 			break;
 	}
 
-	ret = sysfs_create_bin_file(&connector->kdev.kobj, &edid_attr);
+	ret = sysfs_create_bin_file(&connector->kdev->kobj, &edid_attr);
 	if (ret)
 		goto err_out_files;
 
@@ -453,10 +436,11 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 
 err_out_files:
 	for (i = 0; i < opt_cnt; i++)
-		device_remove_file(&connector->kdev, &connector_attrs_opt1[i]);
+		device_remove_file(connector->kdev, &connector_attrs_opt1[i]);
 	for (i = 0; i < attr_cnt; i++)
-		device_remove_file(&connector->kdev, &connector_attrs[i]);
-	device_unregister(&connector->kdev);
+		device_remove_file(connector->kdev, &connector_attrs[i]);
+	put_device(connector->kdev);
+	device_unregister(connector->kdev);
 
 out:
 	return ret;
@@ -480,16 +464,17 @@ void drm_sysfs_connector_remove(struct drm_connector *connector)
 {
 	int i;
 
-	if (!connector->kdev.parent)
+	if (!connector->kdev)
 		return;
 	DRM_DEBUG("removing \"%s\" from sysfs\n",
 		  drm_get_connector_name(connector));
 
 	for (i = 0; i < ARRAY_SIZE(connector_attrs); i++)
-		device_remove_file(&connector->kdev, &connector_attrs[i]);
-	sysfs_remove_bin_file(&connector->kdev.kobj, &edid_attr);
-	device_unregister(&connector->kdev);
-	connector->kdev.parent = NULL;
+		device_remove_file(connector->kdev, &connector_attrs[i]);
+	sysfs_remove_bin_file(&connector->kdev->kobj, &edid_attr);
+	put_device(connector->kdev);
+	device_unregister(connector->kdev);
+	connector->kdev = NULL;
 }
 EXPORT_SYMBOL(drm_sysfs_connector_remove);
 
@@ -508,7 +493,7 @@ void drm_sysfs_hotplug_event(struct drm_device *dev)
 
 	DRM_DEBUG("generating hotplug event\n");
 
-	kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, envp);
+	kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp);
 }
 EXPORT_SYMBOL(drm_sysfs_hotplug_event);
 
@@ -523,15 +508,8 @@ EXPORT_SYMBOL(drm_sysfs_hotplug_event);
  */
 int drm_sysfs_device_add(struct drm_minor *minor)
 {
-	int err;
 	char *minor_str;
 
-	minor->kdev.parent = minor->dev->dev;
-
-	minor->kdev.class = drm_class;
-	minor->kdev.release = drm_sysfs_device_release;
-	minor->kdev.devt = minor->device;
-	minor->kdev.type = &drm_sysfs_device_minor;
 	if (minor->type == DRM_MINOR_CONTROL)
 		minor_str = "controlD%d";
         else if (minor->type == DRM_MINOR_RENDER)
@@ -539,18 +517,14 @@ int drm_sysfs_device_add(struct drm_minor *minor)
         else
                 minor_str = "card%d";
 
-	dev_set_name(&minor->kdev, minor_str, minor->index);
-
-	err = device_register(&minor->kdev);
-	if (err) {
-		DRM_ERROR("device add failed: %d\n", err);
-		goto err_out;
+	minor->kdev = device_create(drm_class, minor->dev->dev,
+				    MKDEV(DRM_MAJOR, minor->index),
+				    minor, minor_str, minor->index);
+	if (IS_ERR(minor->kdev)) {
+		DRM_ERROR("device create failed %ld\n", PTR_ERR(minor->kdev));
+		return PTR_ERR(minor->kdev);
 	}
-
 	return 0;
-
-err_out:
-	return err;
 }
 
 /**
@@ -562,9 +536,9 @@ err_out:
  */
 void drm_sysfs_device_remove(struct drm_minor *minor)
 {
-	if (minor->kdev.parent)
-		device_unregister(&minor->kdev);
-	minor->kdev.parent = NULL;
+	if (minor->kdev)
+		device_destroy(drm_class, MKDEV(DRM_MAJOR, minor->index));
+	minor->kdev = NULL;
 }
 
 
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index f4eb43573cad..f88a1815d87c 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -666,7 +666,7 @@ cdv_intel_dp_i2c_init(struct gma_connector *connector,
 	strncpy (intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
-	intel_dp->adapter.dev.parent = &connector->base.kdev;
+	intel_dp->adapter.dev.parent = connector->base.kdev;
 
 	if (is_edp(encoder))
 		cdv_intel_edp_panel_vdd_on(encoder);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 418ad642c742..d1739d3bdae9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -942,7 +942,7 @@ static void ivybridge_parity_work(struct work_struct *work)
 		parity_event[4] = kasprintf(GFP_KERNEL, "SLICE=%d", slice);
 		parity_event[5] = NULL;
 
-		kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
+		kobject_uevent_env(&dev_priv->dev->primary->kdev->kobj,
 				   KOBJ_CHANGE, parity_event);
 
 		DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n",
@@ -1539,7 +1539,7 @@ static void i915_error_work_func(struct work_struct *work)
 	char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL };
 	int ret;
 
-	kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event);
+	kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, error_event);
 
 	/*
 	 * Note that there's only one work item which does gpu resets, so we
@@ -1553,7 +1553,7 @@ static void i915_error_work_func(struct work_struct *work)
 	 */
 	if (i915_reset_in_progress(error) && !i915_terminally_wedged(error)) {
 		DRM_DEBUG_DRIVER("resetting chip\n");
-		kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE,
+		kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE,
 				   reset_event);
 
 		/*
@@ -1580,7 +1580,7 @@ static void i915_error_work_func(struct work_struct *work)
 			smp_mb__before_atomic_inc();
 			atomic_inc(&dev_priv->gpu_error.reset_counter);
 
-			kobject_uevent_env(&dev->primary->kdev.kobj,
+			kobject_uevent_env(&dev->primary->kdev->kobj,
 					   KOBJ_CHANGE, reset_done_event);
 		} else {
 			atomic_set(&error->reset_counter, I915_WEDGED);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 3ae47951c1bd..1beec51b8e26 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -32,7 +32,7 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-#define dev_to_drm_minor(d) container_of((d), struct drm_minor, kdev)
+#define dev_to_drm_minor(d) dev_get_drvdata((d))
 
 #ifdef CONFIG_PM
 static u32 calc_residency(struct drm_device *dev, const u32 reg)
@@ -75,7 +75,7 @@ show_rc6_mask(struct device *kdev, struct device_attribute *attr, char *buf)
 static ssize_t
 show_rc6_ms(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	struct drm_minor *dminor = dev_to_drm_minor(kdev);
+	struct drm_minor *dminor = dev_get_drvdata(kdev);
 	u32 rc6_residency = calc_residency(dminor->dev, GEN6_GT_GFX_RC6);
 	return snprintf(buf, PAGE_SIZE, "%u\n", rc6_residency);
 }
@@ -543,19 +543,19 @@ void i915_setup_sysfs(struct drm_device *dev)
 
 #ifdef CONFIG_PM
 	if (INTEL_INFO(dev)->gen >= 6) {
-		ret = sysfs_merge_group(&dev->primary->kdev.kobj,
+		ret = sysfs_merge_group(&dev->primary->kdev->kobj,
 					&rc6_attr_group);
 		if (ret)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
 	if (HAS_L3_DPF(dev)) {
-		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
+		ret = device_create_bin_file(dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
 
 		if (NUM_L3_SLICES(dev) > 1) {
-			ret = device_create_bin_file(&dev->primary->kdev,
+			ret = device_create_bin_file(dev->primary->kdev,
 						     &dpf_attrs_1);
 			if (ret)
 				DRM_ERROR("l3 parity slice 1 setup failed\n");
@@ -564,13 +564,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 
 	ret = 0;
 	if (IS_VALLEYVIEW(dev))
-		ret = sysfs_create_files(&dev->primary->kdev.kobj, vlv_attrs);
+		ret = sysfs_create_files(&dev->primary->kdev->kobj, vlv_attrs);
 	else if (INTEL_INFO(dev)->gen >= 6)
-		ret = sysfs_create_files(&dev->primary->kdev.kobj, gen6_attrs);
+		ret = sysfs_create_files(&dev->primary->kdev->kobj, gen6_attrs);
 	if (ret)
 		DRM_ERROR("RPS sysfs setup failed\n");
 
-	ret = sysfs_create_bin_file(&dev->primary->kdev.kobj,
+	ret = sysfs_create_bin_file(&dev->primary->kdev->kobj,
 				    &error_state_attr);
 	if (ret)
 		DRM_ERROR("error_state sysfs setup failed\n");
@@ -578,14 +578,14 @@ void i915_setup_sysfs(struct drm_device *dev)
 
 void i915_teardown_sysfs(struct drm_device *dev)
 {
-	sysfs_remove_bin_file(&dev->primary->kdev.kobj, &error_state_attr);
+	sysfs_remove_bin_file(&dev->primary->kdev->kobj, &error_state_attr);
 	if (IS_VALLEYVIEW(dev))
-		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
+		sysfs_remove_files(&dev->primary->kdev->kobj, vlv_attrs);
 	else
-		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
-	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
-	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
+		sysfs_remove_files(&dev->primary->kdev->kobj, gen6_attrs);
+	device_remove_bin_file(dev->primary->kdev,  &dpf_attrs_1);
+	device_remove_bin_file(dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
-	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
+	sysfs_unmerge_group(&dev->primary->kdev->kobj, &rc6_attr_group);
 #endif
 }
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 4f52ec75b39f..d5bd349105e5 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -737,7 +737,7 @@ intel_dp_i2c_init(struct intel_dp *intel_dp,
 	strncpy(intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
-	intel_dp->adapter.dev.parent = &intel_connector->base.kdev;
+	intel_dp->adapter.dev.parent = intel_connector->base.kdev;
 
 	ironlake_edp_panel_vdd_on(intel_dp);
 	ret = i2c_dp_aux_add_bus(&intel_dp->adapter);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 54684168de1e..c81020923ee4 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -722,7 +722,7 @@ int intel_panel_setup_backlight(struct drm_connector *connector)
 	}
 	dev_priv->backlight.device =
 		backlight_device_register("intel_backlight",
-					  &connector->kdev, dev,
+					  connector->kdev, dev,
 					  &intel_panel_bl_ops, &props);
 
 	if (IS_ERR(dev_priv->backlight.device)) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 2ffad2176b7f..630f6e84fc01 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -82,7 +82,7 @@ nv40_backlight_init(struct drm_connector *connector)
 	memset(&props, 0, sizeof(struct backlight_properties));
 	props.type = BACKLIGHT_RAW;
 	props.max_brightness = 31;
-	bd = backlight_device_register("nv_backlight", &connector->kdev, drm,
+	bd = backlight_device_register("nv_backlight", connector->kdev, drm,
 				       &nv40_bl_ops, &props);
 	if (IS_ERR(bd))
 		return PTR_ERR(bd);
@@ -204,7 +204,7 @@ nv50_backlight_init(struct drm_connector *connector)
 	memset(&props, 0, sizeof(struct backlight_properties));
 	props.type = BACKLIGHT_RAW;
 	props.max_brightness = 100;
-	bd = backlight_device_register("nv_backlight", &connector->kdev,
+	bd = backlight_device_register("nv_backlight", connector->kdev,
 				       nv_encoder, ops, &props);
 	if (IS_ERR(bd))
 		return PTR_ERR(bd);
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 32923d2f6002..28e2dc48e015 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -213,7 +213,7 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	props.type = BACKLIGHT_RAW;
 	snprintf(bl_name, sizeof(bl_name),
 		 "radeon_bl%d", dev->primary->index);
-	bd = backlight_device_register(bl_name, &drm_connector->kdev,
+	bd = backlight_device_register(bl_name, drm_connector->kdev,
 				       pdata, &radeon_atom_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index 62cd512f5c8d..c89971d904c3 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -392,7 +392,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 	props.type = BACKLIGHT_RAW;
 	snprintf(bl_name, sizeof(bl_name),
 		 "radeon_bl%d", dev->primary->index);
-	bd = backlight_device_register(bl_name, &drm_connector->kdev,
+	bd = backlight_device_register(bl_name, drm_connector->kdev,
 				       pdata, &radeon_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2b954adf5bd4..7062307a4a2d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1046,7 +1046,7 @@ struct drm_minor {
 	int index;			/**< Minor device number */
 	int type;                       /**< Control or render */
 	dev_t device;			/**< Device number for mknod */
-	struct device kdev;		/**< Linux device */
+	struct device *kdev;		/**< Linux device */
 	struct drm_device *dev;
 
 	struct dentry *debugfs_root;
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index ba407f6b4f1f..755dd2532612 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -595,7 +595,7 @@ enum drm_connector_force {
  */
 struct drm_connector {
 	struct drm_device *dev;
-	struct device kdev;
+	struct device *kdev;
 	struct device_attribute *attr;
 	struct list_head head;
 
-- 
cgit 


From 1bd7116f1cb833c998cddb6b188df463342069d8 Mon Sep 17 00:00:00 2001
From: Andy Zhou <azhou@nicira.com>
Date: Tue, 22 Oct 2013 10:42:46 -0700
Subject: openvswitch: collect mega flow mask stats

Collect mega flow mask stats. ovs-dpctl show command can be used to
display them for debugging and performance tuning.

Signed-off-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/uapi/linux/openvswitch.h | 17 ++++++++++++++---
 net/openvswitch/datapath.c       | 38 +++++++++++++++++++++++++++++++-------
 net/openvswitch/datapath.h       |  4 ++++
 net/openvswitch/flow_table.c     | 16 +++++++++++++++-
 net/openvswitch/flow_table.h     |  4 +++-
 5 files changed, 67 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a74d375b439b..2cc4644f68ef 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -63,15 +63,18 @@ enum ovs_datapath_cmd {
  * not be sent.
  * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the
  * datapath.  Always present in notifications.
+ * @OVS_DP_ATTR_MEGAFLOW_STATS: Statistics about mega flow masks usage for the
+ * datapath. Always present in notifications.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_DP_* commands.
  */
 enum ovs_datapath_attr {
 	OVS_DP_ATTR_UNSPEC,
-	OVS_DP_ATTR_NAME,       /* name of dp_ifindex netdev */
-	OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */
-	OVS_DP_ATTR_STATS,      /* struct ovs_dp_stats */
+	OVS_DP_ATTR_NAME,		/* name of dp_ifindex netdev */
+	OVS_DP_ATTR_UPCALL_PID,		/* Netlink PID to receive upcalls */
+	OVS_DP_ATTR_STATS,		/* struct ovs_dp_stats */
+	OVS_DP_ATTR_MEGAFLOW_STATS,	/* struct ovs_dp_megaflow_stats */
 	__OVS_DP_ATTR_MAX
 };
 
@@ -84,6 +87,14 @@ struct ovs_dp_stats {
 	__u64 n_flows;           /* Number of flows present */
 };
 
+struct ovs_dp_megaflow_stats {
+	__u64 n_mask_hit;	 /* Number of masks used for flow lookups. */
+	__u32 n_masks;		 /* Number of masks for the datapath. */
+	__u32 pad0;		 /* Pad for future expension. */
+	__u64 pad1;		 /* Pad for future expension. */
+	__u64 pad2;		 /* Pad for future expension. */
+};
+
 struct ovs_vport_stats {
 	__u64   rx_packets;		/* total packets received       */
 	__u64   tx_packets;		/* total packets transmitted    */
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index cf270973095d..5bc5a4e64758 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -221,6 +221,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 	struct dp_stats_percpu *stats;
 	struct sw_flow_key key;
 	u64 *stats_counter;
+	u32 n_mask_hit;
 	int error;
 
 	stats = this_cpu_ptr(dp->stats_percpu);
@@ -233,7 +234,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 	}
 
 	/* Look up flow. */
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
+	flow = ovs_flow_tbl_lookup(&dp->table, &key, &n_mask_hit);
 	if (unlikely(!flow)) {
 		struct dp_upcall_info upcall;
 
@@ -258,6 +259,7 @@ out:
 	/* Update datapath statistics. */
 	u64_stats_update_begin(&stats->sync);
 	(*stats_counter)++;
+	stats->n_mask_hit += n_mask_hit;
 	u64_stats_update_end(&stats->sync);
 }
 
@@ -563,13 +565,18 @@ static struct genl_ops dp_packet_genl_ops[] = {
 	}
 };
 
-static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
+static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
+			 struct ovs_dp_megaflow_stats *mega_stats)
 {
 	int i;
 
+	memset(mega_stats, 0, sizeof(*mega_stats));
+
 	stats->n_flows = ovs_flow_tbl_count(&dp->table);
+	mega_stats->n_masks = ovs_flow_tbl_num_masks(&dp->table);
 
 	stats->n_hit = stats->n_missed = stats->n_lost = 0;
+
 	for_each_possible_cpu(i) {
 		const struct dp_stats_percpu *percpu_stats;
 		struct dp_stats_percpu local_stats;
@@ -585,6 +592,7 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
 		stats->n_hit += local_stats.n_hit;
 		stats->n_missed += local_stats.n_missed;
 		stats->n_lost += local_stats.n_lost;
+		mega_stats->n_mask_hit += local_stats.n_mask_hit;
 	}
 }
 
@@ -743,6 +751,14 @@ static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
 	return skb;
 }
 
+static struct sw_flow *__ovs_flow_tbl_lookup(struct flow_table *tbl,
+					      const struct sw_flow_key *key)
+{
+	u32 __always_unused n_mask_hit;
+
+	return ovs_flow_tbl_lookup(tbl, key, &n_mask_hit);
+}
+
 static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
@@ -793,7 +809,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_ovs;
 
 	/* Check if this is a duplicate flow */
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
+	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
 	if (!flow) {
 		/* Bail out if we're not allowed to create a new flow. */
 		error = -ENOENT;
@@ -905,7 +921,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
+	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
 	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
 		err = -ENOENT;
 		goto unlock;
@@ -953,7 +969,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto unlock;
 
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
+	flow = __ovs_flow_tbl_lookup(&dp->table, &key);
 	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
 		err = -ENOENT;
 		goto unlock;
@@ -1067,6 +1083,7 @@ static size_t ovs_dp_cmd_msg_size(void)
 
 	msgsize += nla_total_size(IFNAMSIZ);
 	msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
+	msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
 
 	return msgsize;
 }
@@ -1076,6 +1093,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 {
 	struct ovs_header *ovs_header;
 	struct ovs_dp_stats dp_stats;
+	struct ovs_dp_megaflow_stats dp_megaflow_stats;
 	int err;
 
 	ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family,
@@ -1091,8 +1109,14 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 	if (err)
 		goto nla_put_failure;
 
-	get_dp_stats(dp, &dp_stats);
-	if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats))
+	get_dp_stats(dp, &dp_stats, &dp_megaflow_stats);
+	if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats),
+			&dp_stats))
+		goto nla_put_failure;
+
+	if (nla_put(skb, OVS_DP_ATTR_MEGAFLOW_STATS,
+			sizeof(struct ovs_dp_megaflow_stats),
+			&dp_megaflow_stats))
 		goto nla_put_failure;
 
 	return genlmsg_end(skb, ovs_header);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index acfd4af8ca3a..d3d14a58aa91 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -46,11 +46,15 @@
  * @n_lost: Number of received packets that had no matching flow in the flow
  * table that could not be sent to userspace (normally due to an overflow in
  * one of the datapath's queues).
+ * @n_mask_hit: Number of masks looked up for flow match.
+ *   @n_mask_hit / (@n_hit + @n_missed)  will be the average masks looked
+ *   up per packet.
  */
 struct dp_stats_percpu {
 	u64 n_hit;
 	u64 n_missed;
 	u64 n_lost;
+	u64 n_mask_hit;
 	struct u64_stats_sync sync;
 };
 
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 036e019f8c3c..536b4d2a42e2 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -430,13 +430,16 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 }
 
 struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
-				    const struct sw_flow_key *key)
+				    const struct sw_flow_key *key,
+				    u32 *n_mask_hit)
 {
 	struct table_instance *ti = rcu_dereference(tbl->ti);
 	struct sw_flow_mask *mask;
 	struct sw_flow *flow;
 
+	*n_mask_hit = 0;
 	list_for_each_entry_rcu(mask, &tbl->mask_list, list) {
+		(*n_mask_hit)++;
 		flow = masked_flow_lookup(ti, key, mask);
 		if (flow)  /* Found */
 			return flow;
@@ -444,6 +447,17 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	return NULL;
 }
 
+int ovs_flow_tbl_num_masks(const struct flow_table *table)
+{
+	struct sw_flow_mask *mask;
+	int num = 0;
+
+	list_for_each_entry(mask, &table->mask_list, list)
+		num++;
+
+	return num;
+}
+
 static struct table_instance *table_instance_expand(struct table_instance *ti)
 {
 	return table_instance_rehash(ti, ti->n_buckets * 2);
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 4db5f78b6f81..fbe45d5ad07d 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -66,10 +66,12 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table);
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
 			struct sw_flow_mask *mask);
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+int  ovs_flow_tbl_num_masks(const struct flow_table *table);
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
 				       u32 *bucket, u32 *idx);
 struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
-				    const struct sw_flow_key *);
+				    const struct sw_flow_key *,
+				    u32 *n_mask_hit);
 
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
-- 
cgit 


From f65f0a1a9836abbfbe5c9b8fa0452e4d8eb7bf00 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sun, 15 Sep 2013 03:50:17 -0700
Subject: leds: lp55xx: enable setting default trigger

This enables setting a default trigger on an LP55xx channel,
either from platform data or device tree. This mechanism is
identical to the mechanism for GPIO LEDs and references the
common LEDs device tree bindings.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Milo Kim <milo.kim@ti.com>
Acked-by: Milo Kim <milo.kim@ti.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 Documentation/devicetree/bindings/leds/leds-lp55xx.txt | 10 +++++++---
 drivers/leds/leds-lp55xx-common.c                      |  3 +++
 include/linux/platform_data/leds-lp55xx.h              |  1 +
 3 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
index a61727f9a6d1..d221e75d90fa 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
@@ -17,12 +17,15 @@ Optional properties:
          2: D1~6 with VOUT, D7~9 with VDD
          3: D1~9 are connected to VOUT
 
-Alternatively, each child can have specific channel name
-- chan-name: Name of each channel name
+Alternatively, each child can have a specific channel name and trigger:
+- chan-name (optional): name of channel
+- linux,default-trigger (optional): see
+  Documentation/devicetree/bindings/leds/common.txt
 
 example 1) LP5521
 3 LED channels, external clock used. Channel names are 'lp5521_pri:channel0',
-'lp5521_pri:channel1' and 'lp5521_pri:channel2'
+'lp5521_pri:channel1' and 'lp5521_pri:channel2', with a heartbeat trigger
+on channel 0.
 
 lp5521@32 {
 	compatible = "national,lp5521";
@@ -33,6 +36,7 @@ lp5521@32 {
 	chan0 {
 		led-cur = /bits/ 8 <0x2f>;
 		max-cur = /bits/ 8 <0x5f>;
+		linux,default-trigger = "heartbeat";
 	};
 
 	chan1 {
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 351825b96f16..075acf5b9fab 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -165,6 +165,7 @@ static int lp55xx_init_led(struct lp55xx_led *led,
 	led->led_current = pdata->led_config[chan].led_current;
 	led->max_current = pdata->led_config[chan].max_current;
 	led->chan_nr = pdata->led_config[chan].chan_nr;
+	led->cdev.default_trigger = pdata->led_config[chan].default_trigger;
 
 	if (led->chan_nr >= max_channel) {
 		dev_err(dev, "Use channel numbers between 0 and %d\n",
@@ -586,6 +587,8 @@ int lp55xx_of_populate_pdata(struct device *dev, struct device_node *np)
 		of_property_read_string(child, "chan-name", &cfg[i].name);
 		of_property_read_u8(child, "led-cur", &cfg[i].led_current);
 		of_property_read_u8(child, "max-cur", &cfg[i].max_current);
+		cfg[i].default_trigger =
+			of_get_property(child, "linux,default-trigger", NULL);
 
 		i++;
 	}
diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h
index 51a2ff579d60..c32de4dcec54 100644
--- a/include/linux/platform_data/leds-lp55xx.h
+++ b/include/linux/platform_data/leds-lp55xx.h
@@ -22,6 +22,7 @@
 
 struct lp55xx_led_config {
 	const char *name;
+	const char *default_trigger;
 	u8 chan_nr;
 	u8 led_current; /* mA x10, 0 if led is not connected */
 	u8 max_current;
-- 
cgit 


From bb6febdc90efe7f664328075c204eed8e9af7ec9 Mon Sep 17 00:00:00 2001
From: Maximilian Güntner <maximilian.guentner@gmail.com>
Date: Wed, 16 Oct 2013 18:09:17 -0700
Subject: leds: Added driver for the NXP PCA9685 I2C chip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The NXP PCA9685 supports 16 channels/leds using a 12-bit PWM (4095
levels of brightness)
This driver supports configuration using platform_data.

Signed-off-by: Maximilian Güntner <maximilian.guentner@gmail.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/Kconfig                       |  10 ++
 drivers/leds/Makefile                      |   1 +
 drivers/leds/leds-pca9685.c                | 213 +++++++++++++++++++++++++++++
 include/linux/platform_data/leds-pca9685.h |  35 +++++
 4 files changed, 259 insertions(+)
 create mode 100644 drivers/leds/leds-pca9685.c
 create mode 100644 include/linux/platform_data/leds-pca9685.h

(limited to 'include')

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 875bbe4c962e..72156c123033 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -300,6 +300,16 @@ config LEDS_PCA963X
 	  LED driver chip accessed via the I2C bus. Supported
 	  devices include PCA9633 and PCA9634
 
+config LEDS_PCA9685
+	tristate "LED support for PCA9685 I2C chip"
+	depends on LEDS_CLASS
+	depends on I2C
+	help
+	  This option enables support for LEDs connected to the PCA9685
+	  LED driver chip accessed via the I2C bus.
+	  The PCA9685 offers 12-bit PWM (4095 levels of brightness) on
+	  16 individual channels.
+
 config LEDS_WM831X_STATUS
 	tristate "LED support for status LEDs on WM831x PMICs"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 8979b0b2c85e..3cd76dbd9be2 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_LEDS_OT200)		+= leds-ot200.o
 obj-$(CONFIG_LEDS_FSG)			+= leds-fsg.o
 obj-$(CONFIG_LEDS_PCA955X)		+= leds-pca955x.o
 obj-$(CONFIG_LEDS_PCA963X)		+= leds-pca963x.o
+obj-$(CONFIG_LEDS_PCA9685)		+= leds-pca9685.o
 obj-$(CONFIG_LEDS_DA903X)		+= leds-da903x.o
 obj-$(CONFIG_LEDS_DA9052)		+= leds-da9052.o
 obj-$(CONFIG_LEDS_WM831X_STATUS)	+= leds-wm831x-status.o
diff --git a/drivers/leds/leds-pca9685.c b/drivers/leds/leds-pca9685.c
new file mode 100644
index 000000000000..6e1ef3a9d6ef
--- /dev/null
+++ b/drivers/leds/leds-pca9685.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright 2013 Maximilian Güntner <maximilian.guentner@gmail.com>
+ *
+ * This file is subject to the terms and conditions of version 2 of
+ * the GNU General Public License.  See the file COPYING in the main
+ * directory of this archive for more details.
+ *
+ * Based on leds-pca963x.c driver by
+ * Peter Meerwald <p.meerwald@bct-electronic.com>
+ *
+ * Driver for the NXP PCA9685 12-Bit PWM LED driver chip.
+ *
+ */
+
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/workqueue.h>
+
+#include <linux/platform_data/leds-pca9685.h>
+
+/* Register Addresses */
+#define PCA9685_MODE1 0x00
+#define PCA9685_MODE2 0x01
+#define PCA9685_LED0_ON_L 0x06
+#define PCA9685_ALL_LED_ON_L 0xFA
+
+/* MODE1 Register */
+#define PCA9685_ALLCALL 0x00
+#define PCA9685_SLEEP   0x04
+#define PCA9685_AI      0x05
+
+/* MODE2 Register */
+#define PCA9685_INVRT   0x04
+#define PCA9685_OUTDRV  0x02
+
+static const struct i2c_device_id pca9685_id[] = {
+	{ "pca9685", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, pca9685_id);
+
+struct pca9685_led {
+	struct i2c_client *client;
+	struct work_struct work;
+	u16 brightness;
+	struct led_classdev led_cdev;
+	int led_num; /* 0-15 */
+	char name[32];
+};
+
+static void pca9685_write_msg(struct i2c_client *client, u8 *buf, u8 len)
+{
+	struct i2c_msg msg = {
+		.addr = client->addr,
+		.flags = 0x00,
+		.len = len,
+		.buf = buf
+	};
+	i2c_transfer(client->adapter, &msg, 1);
+}
+
+static void pca9685_all_off(struct i2c_client *client)
+{
+	u8 i2c_buffer[5] = {PCA9685_ALL_LED_ON_L, 0x00, 0x00, 0x00, 0x10};
+	pca9685_write_msg(client, i2c_buffer, 5);
+}
+
+static void pca9685_led_work(struct work_struct *work)
+{
+	struct pca9685_led *pca9685;
+	u8 i2c_buffer[5];
+
+	pca9685 = container_of(work, struct pca9685_led, work);
+	i2c_buffer[0] = PCA9685_LED0_ON_L + 4 * pca9685->led_num;
+	/*
+	 * 4095 is the maximum brightness, so we set the ON time to 0x1000
+	 * which disables the PWM generator for that LED
+	 */
+	if (pca9685->brightness == 4095)
+		*((__le16 *)(i2c_buffer+1)) = cpu_to_le16(0x1000);
+	else
+		*((__le16 *)(i2c_buffer+1)) = 0x0000;
+
+	if (pca9685->brightness == 0)
+		*((__le16 *)(i2c_buffer+3)) = cpu_to_le16(0x1000);
+	else if (pca9685->brightness == 4095)
+		*((__le16 *)(i2c_buffer+3)) = 0x0000;
+	else
+		*((__le16 *)(i2c_buffer+3)) = cpu_to_le16(pca9685->brightness);
+
+	pca9685_write_msg(pca9685->client, i2c_buffer, 5);
+}
+
+static void pca9685_led_set(struct led_classdev *led_cdev,
+		enum led_brightness value)
+{
+	struct pca9685_led *pca9685;
+	pca9685 = container_of(led_cdev, struct pca9685_led, led_cdev);
+	pca9685->brightness = value;
+
+	schedule_work(&pca9685->work);
+}
+
+static int pca9685_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	struct pca9685_led *pca9685;
+	struct pca9685_platform_data *pdata;
+	int err;
+	u8 i;
+
+	pdata = dev_get_platdata(&client->dev);
+	if (pdata) {
+		if (pdata->leds.num_leds < 1 || pdata->leds.num_leds > 15) {
+			dev_err(&client->dev, "board info must claim 1-16 LEDs");
+			return -EINVAL;
+		}
+	}
+
+	pca9685 = devm_kzalloc(&client->dev, 16 * sizeof(*pca9685), GFP_KERNEL);
+	if (!pca9685)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, pca9685);
+	pca9685_all_off(client);
+
+	for (i = 0; i < 16; i++) {
+		pca9685[i].client = client;
+		pca9685[i].led_num = i;
+		pca9685[i].name[0] = '\0';
+		if (pdata && i < pdata->leds.num_leds) {
+			if (pdata->leds.leds[i].name)
+				strncpy(pca9685[i].name,
+					pdata->leds.leds[i].name,
+					sizeof(pca9685[i].name)-1);
+			if (pdata->leds.leds[i].default_trigger)
+				pca9685[i].led_cdev.default_trigger =
+					pdata->leds.leds[i].default_trigger;
+		}
+		if (strlen(pca9685[i].name) == 0) {
+			/*
+			 * Write adapter and address to the name as well.
+			 * Otherwise multiple chips attached to one host would
+			 * not work.
+			 */
+			snprintf(pca9685[i].name, sizeof(pca9685[i].name),
+					"pca9685:%d:x%.2x:%d",
+					client->adapter->nr, client->addr, i);
+		}
+		pca9685[i].led_cdev.name = pca9685[i].name;
+		pca9685[i].led_cdev.max_brightness = 0xfff;
+		pca9685[i].led_cdev.brightness_set = pca9685_led_set;
+
+		INIT_WORK(&pca9685[i].work, pca9685_led_work);
+		err = led_classdev_register(&client->dev, &pca9685[i].led_cdev);
+		if (err < 0)
+			goto exit;
+	}
+
+	if (pdata)
+		i2c_smbus_write_byte_data(client, PCA9685_MODE2,
+			pdata->outdrv << PCA9685_OUTDRV |
+			pdata->inverted << PCA9685_INVRT);
+	else
+		i2c_smbus_write_byte_data(client, PCA9685_MODE2,
+			PCA9685_TOTEM_POLE << PCA9685_OUTDRV);
+	/* Enable Auto-Increment, enable oscillator, ALLCALL/SUBADDR disabled */
+	i2c_smbus_write_byte_data(client, PCA9685_MODE1, BIT(PCA9685_AI));
+
+	return 0;
+
+exit:
+	while (i--) {
+		led_classdev_unregister(&pca9685[i].led_cdev);
+		cancel_work_sync(&pca9685[i].work);
+	}
+	return err;
+}
+
+static int pca9685_remove(struct i2c_client *client)
+{
+	struct pca9685_led *pca9685 = i2c_get_clientdata(client);
+	u8 i;
+
+	for (i = 0; i < 16; i++) {
+		led_classdev_unregister(&pca9685[i].led_cdev);
+		cancel_work_sync(&pca9685[i].work);
+	}
+	pca9685_all_off(client);
+	return 0;
+}
+
+static struct i2c_driver pca9685_driver = {
+	.driver = {
+		.name = "leds-pca9685",
+		.owner = THIS_MODULE,
+	},
+	.probe = pca9685_probe,
+	.remove = pca9685_remove,
+	.id_table = pca9685_id,
+};
+
+module_i2c_driver(pca9685_driver);
+
+MODULE_AUTHOR("Maximilian Güntner <maximilian.guentner@gmail.com>");
+MODULE_DESCRIPTION("PCA9685 LED Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/platform_data/leds-pca9685.h b/include/linux/platform_data/leds-pca9685.h
new file mode 100644
index 000000000000..778e9e4249cc
--- /dev/null
+++ b/include/linux/platform_data/leds-pca9685.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright 2013 Maximilian Güntner <maximilian.guentner@gmail.com>
+ *
+ * This file is subject to the terms and conditions of version 2 of
+ * the GNU General Public License.  See the file COPYING in the main
+ * directory of this archive for more details.
+ *
+ * Based on leds-pca963x.h by Peter Meerwald <p.meerwald@bct-electronic.com>
+ *
+ * LED driver for the NXP PCA9685 PWM chip
+ *
+ */
+
+#ifndef __LINUX_PCA9685_H
+#define __LINUX_PCA9685_H
+
+#include <linux/leds.h>
+
+enum pca9685_outdrv {
+	PCA9685_OPEN_DRAIN,
+	PCA9685_TOTEM_POLE,
+};
+
+enum pca9685_inverted {
+	PCA9685_NOT_INVERTED,
+	PCA9685_INVERTED,
+};
+
+struct pca9685_platform_data {
+	struct led_platform_data leds;
+	enum pca9685_outdrv outdrv;
+	enum pca9685_inverted inverted;
+};
+
+#endif /* __LINUX_PCA9685_H */
-- 
cgit 


From 0a6957e7d47096bbeedda4e1d926359eb487dcfc Mon Sep 17 00:00:00 2001
From: ZHAO Gang <gamerh2o@gmail.com>
Date: Tue, 22 Oct 2013 16:23:38 +0800
Subject: net: remove function sk_reset_txq()

What sk_reset_txq() does is just calls function sk_tx_queue_reset(),
and sk_reset_txq() is used only in sock.h, by dst_negative_advice().
Let dst_negative_advice() calls sk_tx_queue_reset() directly so we
can remove unneeded sk_reset_txq().

Signed-off-by: ZHAO Gang <gamerh2o@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 4 +---
 net/core/sock.c    | 6 ------
 2 files changed, 1 insertion(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 86bb0668c581..c93542f92420 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1746,8 +1746,6 @@ sk_dst_get(struct sock *sk)
 	return dst;
 }
 
-void sk_reset_txq(struct sock *sk);
-
 static inline void dst_negative_advice(struct sock *sk)
 {
 	struct dst_entry *ndst, *dst = __sk_dst_get(sk);
@@ -1757,7 +1755,7 @@ static inline void dst_negative_advice(struct sock *sk)
 
 		if (ndst != dst) {
 			rcu_assign_pointer(sk->sk_dst_cache, ndst);
-			sk_reset_txq(sk);
+			sk_tx_queue_clear(sk);
 		}
 	}
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 440afdca1e8f..ab20ed9b0f31 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -475,12 +475,6 @@ discard_and_relse:
 }
 EXPORT_SYMBOL(sk_receive_skb);
 
-void sk_reset_txq(struct sock *sk)
-{
-	sk_tx_queue_clear(sk);
-}
-EXPORT_SYMBOL(sk_reset_txq);
-
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
 {
 	struct dst_entry *dst = __sk_dst_get(sk);
-- 
cgit 


From 7fcd427465e710d0c4e2737d2f02b2ffa14b9bb3 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 15 Oct 2013 20:14:21 +0100
Subject: mfd: Allow mapping regulator supplies to MFD device from children

Occasionally, it is useful to map supplies from a child device onto the
MFD device. A typical usecase for this would be if the MFD device is
represented as a single node in device tree. All supplies will be
defined in device tree as existing on the MFD device. When a child
depends on frameworks which might have no knowledge of MFD to lookup
supplies on its behalf the supply will not be found.

This patch adds a list of supplies that should be looked up on the
parent rather than the child as part of the mfd_cell structure.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/mfd/mfd-core.c   | 22 +++++++++++++++++-----
 include/linux/mfd/core.h |  6 ++++++
 2 files changed, 23 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index f421586f29fb..adc8ea36e7c4 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/irqdomain.h>
 #include <linux/of.h>
+#include <linux/regulator/consumer.h>
 
 static struct device_type mfd_dev_type = {
 	.name	= "mfd_device",
@@ -99,6 +100,13 @@ static int mfd_add_device(struct device *parent, int id,
 	pdev->dev.dma_mask = parent->dma_mask;
 	pdev->dev.dma_parms = parent->dma_parms;
 
+	ret = devm_regulator_bulk_register_supply_alias(
+			&pdev->dev, cell->parent_supplies,
+			parent, cell->parent_supplies,
+			cell->num_parent_supplies);
+	if (ret < 0)
+		goto fail_res;
+
 	if (parent->of_node && cell->of_compatible) {
 		for_each_child_of_node(parent->of_node, np) {
 			if (of_device_is_compatible(np, cell->of_compatible)) {
@@ -112,12 +120,12 @@ static int mfd_add_device(struct device *parent, int id,
 		ret = platform_device_add_data(pdev,
 					cell->platform_data, cell->pdata_size);
 		if (ret)
-			goto fail_res;
+			goto fail_alias;
 	}
 
 	ret = mfd_platform_add_cell(pdev, cell);
 	if (ret)
-		goto fail_res;
+		goto fail_alias;
 
 	for (r = 0; r < cell->num_resources; r++) {
 		res[r].name = cell->resources[r].name;
@@ -152,17 +160,17 @@ static int mfd_add_device(struct device *parent, int id,
 		if (!cell->ignore_resource_conflicts) {
 			ret = acpi_check_resource_conflict(&res[r]);
 			if (ret)
-				goto fail_res;
+				goto fail_alias;
 		}
 	}
 
 	ret = platform_device_add_resources(pdev, res, cell->num_resources);
 	if (ret)
-		goto fail_res;
+		goto fail_alias;
 
 	ret = platform_device_add(pdev);
 	if (ret)
-		goto fail_res;
+		goto fail_alias;
 
 	if (cell->pm_runtime_no_callbacks)
 		pm_runtime_no_callbacks(&pdev->dev);
@@ -171,6 +179,10 @@ static int mfd_add_device(struct device *parent, int id,
 
 	return 0;
 
+fail_alias:
+	devm_regulator_bulk_unregister_supply_alias(&pdev->dev,
+						    cell->parent_supplies,
+						    cell->num_parent_supplies);
 fail_res:
 	kfree(res);
 fail_device:
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index cebe97ee98b8..7314fc4e6d25 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -59,6 +59,12 @@ struct mfd_cell {
 	 * pm_runtime_no_callbacks().
 	 */
 	bool			pm_runtime_no_callbacks;
+
+	/* A list of regulator supplies that should be mapped to the MFD
+	 * device rather than the child device when requested
+	 */
+	const char		**parent_supplies;
+	int			num_parent_supplies;
 };
 
 /*
-- 
cgit 


From 92ec11809565cf6429c75204e99e0f583b5c9d7c Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@gmail.com>
Date: Wed, 23 Oct 2013 13:40:55 +0200
Subject: sched/wait: Fix build breakage

The wait_event_interruptible_lock_irq() macro is missing a
semi-colon which causes a build failure in the i915 DRM driver.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1382528455-29911-1-git-send-email-treding@nvidia.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index ec099b03e11b..3b23afa04d6b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -732,7 +732,7 @@ do {									\
 	int __ret = 0;							\
 	if (!(condition))						\
 		__ret = __wait_event_interruptible_lock_irq(wq,		\
-						condition, lock,)	\
+						condition, lock,);	\
 	__ret;								\
 })
 
-- 
cgit 


From b8206d3916c15a2939b85f21673bdf39e4c8d023 Mon Sep 17 00:00:00 2001
From: Marc-André Lureau <marcandre.lureau@gmail.com>
Date: Fri, 18 Oct 2013 16:11:28 +0200
Subject: drm: return if changed in drm_helper_hpd_irq_event()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The caller may want to know whether the configuration was changed, and
if an hotplug event was sent.

Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_crtc_helper.c | 6 ++++--
 include/drm/drm_crtc_helper.h     | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 5fcb9d487672..55ea4ac6fd50 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -1131,14 +1131,14 @@ void drm_kms_helper_poll_fini(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_kms_helper_poll_fini);
 
-void drm_helper_hpd_irq_event(struct drm_device *dev)
+bool drm_helper_hpd_irq_event(struct drm_device *dev)
 {
 	struct drm_connector *connector;
 	enum drm_connector_status old_status;
 	bool changed = false;
 
 	if (!dev->mode_config.poll_enabled)
-		return;
+		return false;
 
 	mutex_lock(&dev->mode_config.mutex);
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
@@ -1163,5 +1163,7 @@ void drm_helper_hpd_irq_event(struct drm_device *dev)
 
 	if (changed)
 		drm_kms_helper_hotplug_event(dev);
+
+	return changed;
 }
 EXPORT_SYMBOL(drm_helper_hpd_irq_event);
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index f43d556bf40b..ef6ad3a8e58e 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -163,7 +163,7 @@ static inline void drm_connector_helper_add(struct drm_connector *connector,
 extern int drm_helper_resume_force_mode(struct drm_device *dev);
 extern void drm_kms_helper_poll_init(struct drm_device *dev);
 extern void drm_kms_helper_poll_fini(struct drm_device *dev);
-extern void drm_helper_hpd_irq_event(struct drm_device *dev);
+extern bool drm_helper_hpd_irq_event(struct drm_device *dev);
 extern void drm_kms_helper_hotplug_event(struct drm_device *dev);
 
 extern void drm_kms_helper_poll_disable(struct drm_device *dev);
-- 
cgit 


From 43e30f23b589642a7eaff005bc30444a5247976c Mon Sep 17 00:00:00 2001
From: David Jander <david@protonic.nl>
Date: Mon, 2 Sep 2013 09:46:11 +0200
Subject: mfd: da9052: Avoid multiwrite mode due to silicon errata

DA9053 (up to revision bc) can corrupt internal registers when multi-write
mode is enabled and power is removed or during shutdown.

Signed-off-by: David Jander <david@protonic.nl>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/da9052-i2c.c          | 12 ++++++++----
 include/linux/mfd/da9052/da9052.h | 20 ++++++++++++++------
 2 files changed, 22 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 6a9fec40d018..c319c4ef5d49 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -86,7 +86,11 @@ static int da9052_i2c_fix(struct da9052 *da9052, unsigned char reg)
 	return 0;
 }
 
-static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
+/*
+ * According to errata item 24, multiwrite mode should be avoided
+ * in order to prevent register data corruption after power-down.
+ */
+static int da9052_i2c_disable_multiwrite(struct da9052 *da9052)
 {
 	int reg_val, ret;
 
@@ -94,8 +98,8 @@ static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
 	if (ret < 0)
 		return ret;
 
-	if (reg_val & DA9052_CONTROL_B_WRITEMODE) {
-		reg_val &= ~DA9052_CONTROL_B_WRITEMODE;
+	if (!(reg_val & DA9052_CONTROL_B_WRITEMODE)) {
+		reg_val |= DA9052_CONTROL_B_WRITEMODE;
 		ret = regmap_write(da9052->regmap, DA9052_CONTROL_B_REG,
 				   reg_val);
 		if (ret < 0)
@@ -154,7 +158,7 @@ static int da9052_i2c_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	ret = da9052_i2c_enable_multiwrite(da9052);
+	ret = da9052_i2c_disable_multiwrite(da9052);
 	if (ret < 0)
 		return ret;
 
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 786d02eb79d2..21e21b81cc75 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -148,10 +148,15 @@ static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg,
 				     unsigned reg_cnt, unsigned char *val)
 {
 	int ret;
+	unsigned int tmp;
+	int i;
 
-	ret = regmap_bulk_read(da9052->regmap, reg, val, reg_cnt);
-	if (ret < 0)
-		return ret;
+	for (i = 0; i < reg_cnt; i++) {
+		ret = regmap_read(da9052->regmap, reg + i, &tmp);
+		val[i] = (unsigned char)tmp;
+		if (ret < 0)
+			return ret;
+	}
 
 	if (da9052->fix_io) {
 		ret = da9052->fix_io(da9052, reg);
@@ -166,10 +171,13 @@ static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg,
 				      unsigned reg_cnt, unsigned char *val)
 {
 	int ret;
+	int i;
 
-	ret = regmap_raw_write(da9052->regmap, reg, val, reg_cnt);
-	if (ret < 0)
-		return ret;
+	for (i = 0; i < reg_cnt; i++) {
+		ret = regmap_write(da9052->regmap, reg + i, val[i]);
+		if (ret < 0)
+			return ret;
+	}
 
 	if (da9052->fix_io) {
 		ret = da9052->fix_io(da9052, reg);
-- 
cgit 


From b5f90240e1ef0568a8c666da3c3be4c6a682c5a6 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Fri, 6 Sep 2013 16:14:28 +0100
Subject: mfd: wm8994: Inline register I/O functions

Since the register I/O functions are all simple wrappers for the regmap
equivalents inline them to provide a small code size saving and an example
of good practice.

Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/wm8994-core.c       | 78 -----------------------------------------
 include/linux/mfd/wm8994/core.h | 45 +++++++++++++++++++-----
 2 files changed, 36 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index e1c283e6d4e5..030827511667 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -33,84 +33,6 @@
 
 #include "wm8994.h"
 
-/**
- * wm8994_reg_read: Read a single WM8994 register.
- *
- * @wm8994: Device to read from.
- * @reg: Register to read.
- */
-int wm8994_reg_read(struct wm8994 *wm8994, unsigned short reg)
-{
-	unsigned int val;
-	int ret;
-
-	ret = regmap_read(wm8994->regmap, reg, &val);
-
-	if (ret < 0)
-		return ret;
-	else
-		return val;
-}
-EXPORT_SYMBOL_GPL(wm8994_reg_read);
-
-/**
- * wm8994_bulk_read: Read multiple WM8994 registers
- *
- * @wm8994: Device to read from
- * @reg: First register
- * @count: Number of registers
- * @buf: Buffer to fill.  The data will be returned big endian.
- */
-int wm8994_bulk_read(struct wm8994 *wm8994, unsigned short reg,
-		     int count, u16 *buf)
-{
-	return regmap_bulk_read(wm8994->regmap, reg, buf, count);
-}
-
-/**
- * wm8994_reg_write: Write a single WM8994 register.
- *
- * @wm8994: Device to write to.
- * @reg: Register to write to.
- * @val: Value to write.
- */
-int wm8994_reg_write(struct wm8994 *wm8994, unsigned short reg,
-		     unsigned short val)
-{
-	return regmap_write(wm8994->regmap, reg, val);
-}
-EXPORT_SYMBOL_GPL(wm8994_reg_write);
-
-/**
- * wm8994_bulk_write: Write multiple WM8994 registers
- *
- * @wm8994: Device to write to
- * @reg: First register
- * @count: Number of registers
- * @buf: Buffer to write from.  Data must be big-endian formatted.
- */
-int wm8994_bulk_write(struct wm8994 *wm8994, unsigned short reg,
-		      int count, const u16 *buf)
-{
-	return regmap_raw_write(wm8994->regmap, reg, buf, count * sizeof(u16));
-}
-EXPORT_SYMBOL_GPL(wm8994_bulk_write);
-
-/**
- * wm8994_set_bits: Set the value of a bitfield in a WM8994 register
- *
- * @wm8994: Device to write to.
- * @reg: Register to write to.
- * @mask: Mask of bits to set.
- * @val: Value to set (unshifted)
- */
-int wm8994_set_bits(struct wm8994 *wm8994, unsigned short reg,
-		    unsigned short mask, unsigned short val)
-{
-	return regmap_update_bits(wm8994->regmap, reg, mask, val);
-}
-EXPORT_SYMBOL_GPL(wm8994_set_bits);
-
 static struct mfd_cell wm8994_regulator_devs[] = {
 	{
 		.name = "wm8994-ldo",
diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 40854ac0ba3d..3fbcf3d4a0fe 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -85,16 +85,43 @@ struct wm8994 {
 };
 
 /* Device I/O API */
-int wm8994_reg_read(struct wm8994 *wm8994, unsigned short reg);
-int wm8994_reg_write(struct wm8994 *wm8994, unsigned short reg,
-		 unsigned short val);
-int wm8994_set_bits(struct wm8994 *wm8994, unsigned short reg,
-		    unsigned short mask, unsigned short val);
-int wm8994_bulk_read(struct wm8994 *wm8994, unsigned short reg,
-		     int count, u16 *buf);
-int wm8994_bulk_write(struct wm8994 *wm8994, unsigned short reg,
-		     int count, const u16 *buf);
 
+static inline int wm8994_reg_read(struct wm8994 *wm8994, unsigned short reg)
+{
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(wm8994->regmap, reg, &val);
+
+	if (ret < 0)
+		return ret;
+	else
+		return val;
+}
+
+static inline int wm8994_reg_write(struct wm8994 *wm8994, unsigned short reg,
+				   unsigned short val)
+{
+	return regmap_write(wm8994->regmap, reg, val);
+}
+
+static inline int wm8994_bulk_read(struct wm8994 *wm8994, unsigned short reg,
+				   int count, u16 *buf)
+{
+	return regmap_bulk_read(wm8994->regmap, reg, buf, count);
+}
+
+static inline int wm8994_bulk_write(struct wm8994 *wm8994, unsigned short reg,
+				    int count, const u16 *buf)
+{
+	return regmap_raw_write(wm8994->regmap, reg, buf, count * sizeof(u16));
+}
+
+static inline int wm8994_set_bits(struct wm8994 *wm8994, unsigned short reg,
+		    unsigned short mask, unsigned short val)
+{
+	return regmap_update_bits(wm8994->regmap, reg, mask, val);
+}
 
 /* Helper to save on boilerplate */
 static inline int wm8994_request_irq(struct wm8994 *wm8994, int irq,
-- 
cgit 


From dae188c6092a3f085bf7fc335b6c0e0420d3dd8f Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Fri, 6 Sep 2013 17:48:35 +0100
Subject: mfd: wm8994: Remove unused irq_lock

Since the conversion to regmap-irq irq_lock has been unused.

Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/wm8994/core.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 3fbcf3d4a0fe..eefafa62d304 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -56,8 +56,6 @@ struct irq_domain;
 #define WM8994_IRQ_GPIO(x) (x + WM8994_IRQ_TEMP_WARN)
 
 struct wm8994 {
-	struct mutex irq_lock;
-
 	struct wm8994_pdata pdata;
 
 	enum wm8994_type type;
-- 
cgit 


From 1a54b7dabf8f20df2894aed9683155ff89fc20e8 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <matthias.list@kaehlcke.net>
Date: Tue, 10 Sep 2013 23:02:18 +0200
Subject: mfd: ti_am335x_tscadc: Fix idle timeout value

The old timeout value was based on the assumption that the minimum values are
used for the open and sample delay and no averaging is done. In fact the ADC
and touchscreen driver both use an open delay of 152 cycles and averaging over
16 samples. This patch adjusts the timeout value accordingly

Signed-off-by: Matthias Kaehlcke <matthias@kaehlcke.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/ti_am335x_tscadc.h | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index 25f2c611ab01..4befdb85dd9c 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -125,13 +125,18 @@
 #define TOTAL_CHANNELS		8
 
 /*
-* ADC runs at 3MHz, and it takes
-* 15 cycles to latch one data output.
-* Hence the idle time for ADC to
-* process one sample data would be
-* around 5 micro seconds.
-*/
-#define IDLE_TIMEOUT 5 /* microsec */
+ * time in us for processing a single channel, calculated as follows:
+ *
+ * num cycles = open delay + (sample delay + conv time) * averaging
+ *
+ * num cycles: 152 + (1 + 13) * 16 = 376
+ *
+ * clock frequency: 26MHz / 8 = 3.25MHz
+ * clock period: 1 / 3.25MHz = 308ns
+ *
+ * processing time: 376 * 308ns = 116us
+ */
+#define IDLE_TIMEOUT 116 /* microsec */
 
 #define TSCADC_CELLS		2
 
-- 
cgit 


From 26b818511c6562ce372566c219a2ef1afea35fe6 Mon Sep 17 00:00:00 2001
From: Wei WANG <wei_wang@realsil.com.cn>
Date: Fri, 13 Sep 2013 17:45:43 +0800
Subject: mfd: rtsx: Modify rts5249_optimize_phy

In some platforms, specially Thinkpad series, rts5249 won't be
initialized properly. So we need adjust some phy parameters to
improve the compatibility issue.

It is a little different between simulation and real chip. We have
no idea about which configuration is better before tape-out. We set
default settings according to simulation, but need to tune these
parameters after getting the real chip.

I can't explain every change in detail here. The below information is
just a rough description:

PHY_REG_REV: Disable internal clkreq_tx, enable rx_pwst
PHY_BPCR: No change, just turn the magic number to macro definitions
PHY_PCR: Change OOBS sensitivity, from 60mV to 90mV
PHY_RCR2: Control charge-pump current automatically
PHY_FLD4: Use TX cmu reference clock
PHY_RDR: Change RXDSEL from 30nF to 1.9nF
PHY_RCR1: Change the duration between adp_st and asserting cp_en from
0.32 us to 0.64us
PHY_FLD3: Adjust internal timers
PHY_TUNE: Fine tune the regulator12 output voltage

Signed-off-by: Wei WANG <wei_wang@realsil.com.cn>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/rts5249.c        | 48 +++++++++++++++++++++++++++++++++++++--
 include/linux/mfd/rtsx_pci.h | 53 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/rts5249.c b/drivers/mfd/rts5249.c
index 3b835f593e35..573de7bfcced 100644
--- a/drivers/mfd/rts5249.c
+++ b/drivers/mfd/rts5249.c
@@ -130,13 +130,57 @@ static int rts5249_optimize_phy(struct rtsx_pcr *pcr)
 {
 	int err;
 
-	err = rtsx_pci_write_phy_register(pcr, PHY_REG_REV, 0xFE46);
+	err = rtsx_pci_write_phy_register(pcr, PHY_REG_REV,
+			PHY_REG_REV_RESV | PHY_REG_REV_RXIDLE_LATCHED |
+			PHY_REG_REV_P1_EN | PHY_REG_REV_RXIDLE_EN |
+			PHY_REG_REV_RX_PWST | PHY_REG_REV_CLKREQ_DLY_TIMER_1_0 |
+			PHY_REG_REV_STOP_CLKRD | PHY_REG_REV_STOP_CLKWR);
 	if (err < 0)
 		return err;
 
 	msleep(1);
 
-	return rtsx_pci_write_phy_register(pcr, PHY_BPCR, 0x05C0);
+	err = rtsx_pci_write_phy_register(pcr, PHY_BPCR,
+			PHY_BPCR_IBRXSEL | PHY_BPCR_IBTXSEL |
+			PHY_BPCR_IB_FILTER | PHY_BPCR_CMIRROR_EN);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_PCR,
+			PHY_PCR_FORCE_CODE | PHY_PCR_OOBS_CALI_50 |
+			PHY_PCR_OOBS_VCM_08 | PHY_PCR_OOBS_SEN_90 |
+			PHY_PCR_RSSI_EN);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_RCR2,
+			PHY_RCR2_EMPHASE_EN | PHY_RCR2_NADJR |
+			PHY_RCR2_CDR_CP_10 | PHY_RCR2_CDR_SR_2 |
+			PHY_RCR2_FREQSEL_12 | PHY_RCR2_CPADJEN |
+			PHY_RCR2_CDR_SC_8 | PHY_RCR2_CALIB_LATE);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_FLD4,
+			PHY_FLD4_FLDEN_SEL | PHY_FLD4_REQ_REF |
+			PHY_FLD4_RXAMP_OFF | PHY_FLD4_REQ_ADDA |
+			PHY_FLD4_BER_COUNT | PHY_FLD4_BER_TIMER |
+			PHY_FLD4_BER_CHK_EN);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_RDR, PHY_RDR_RXDSEL_1_9);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_RCR1,
+			PHY_RCR1_ADP_TIME | PHY_RCR1_VCO_COARSE);
+	if (err < 0)
+		return err;
+	err = rtsx_pci_write_phy_register(pcr, PHY_FLD3,
+			PHY_FLD3_TIMER_4 | PHY_FLD3_TIMER_6 |
+			PHY_FLD3_RXDELINK);
+	if (err < 0)
+		return err;
+	return rtsx_pci_write_phy_register(pcr, PHY_TUNE,
+			PHY_TUNE_TUNEREF_1_0 | PHY_TUNE_VBGSEL_1252 |
+			PHY_TUNE_SDBUS_33 | PHY_TUNE_TUNED18 |
+			PHY_TUNE_TUNED12);
 }
 
 static int rts5249_turn_on_led(struct rtsx_pcr *pcr)
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index d1382dfbeff0..0ce772105508 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -756,6 +756,59 @@
 #define PCR_SETTING_REG2		0x814
 #define PCR_SETTING_REG3		0x747
 
+/* Phy bits */
+#define PHY_PCR_FORCE_CODE			0xB000
+#define PHY_PCR_OOBS_CALI_50			0x0800
+#define PHY_PCR_OOBS_VCM_08			0x0200
+#define PHY_PCR_OOBS_SEN_90			0x0040
+#define PHY_PCR_RSSI_EN				0x0002
+
+#define PHY_RCR1_ADP_TIME			0x0100
+#define PHY_RCR1_VCO_COARSE			0x001F
+
+#define PHY_RCR2_EMPHASE_EN			0x8000
+#define PHY_RCR2_NADJR				0x4000
+#define PHY_RCR2_CDR_CP_10			0x0400
+#define PHY_RCR2_CDR_SR_2			0x0100
+#define PHY_RCR2_FREQSEL_12			0x0040
+#define PHY_RCR2_CPADJEN			0x0020
+#define PHY_RCR2_CDR_SC_8			0x0008
+#define PHY_RCR2_CALIB_LATE			0x0002
+
+#define PHY_RDR_RXDSEL_1_9			0x4000
+
+#define PHY_TUNE_TUNEREF_1_0			0x4000
+#define PHY_TUNE_VBGSEL_1252			0x0C00
+#define PHY_TUNE_SDBUS_33			0x0200
+#define PHY_TUNE_TUNED18			0x01C0
+#define PHY_TUNE_TUNED12			0X0020
+
+#define PHY_BPCR_IBRXSEL			0x0400
+#define PHY_BPCR_IBTXSEL			0x0100
+#define PHY_BPCR_IB_FILTER			0x0080
+#define PHY_BPCR_CMIRROR_EN			0x0040
+
+#define PHY_REG_REV_RESV			0xE000
+#define PHY_REG_REV_RXIDLE_LATCHED		0x1000
+#define PHY_REG_REV_P1_EN			0x0800
+#define PHY_REG_REV_RXIDLE_EN			0x0400
+#define PHY_REG_REV_CLKREQ_DLY_TIMER_1_0	0x0040
+#define PHY_REG_REV_STOP_CLKRD			0x0020
+#define PHY_REG_REV_RX_PWST			0x0008
+#define PHY_REG_REV_STOP_CLKWR			0x0004
+
+#define PHY_FLD3_TIMER_4			0x7800
+#define PHY_FLD3_TIMER_6			0x00E0
+#define PHY_FLD3_RXDELINK			0x0004
+
+#define PHY_FLD4_FLDEN_SEL			0x4000
+#define PHY_FLD4_REQ_REF			0x2000
+#define PHY_FLD4_RXAMP_OFF			0x1000
+#define PHY_FLD4_REQ_ADDA			0x0800
+#define PHY_FLD4_BER_COUNT			0x00E0
+#define PHY_FLD4_BER_TIMER			0x000A
+#define PHY_FLD4_BER_CHK_EN			0x0001
+
 #define rtsx_pci_init_cmd(pcr)		((pcr)->ci = 0)
 
 struct rtsx_pcr;
-- 
cgit 


From ca13ce3701900c5b64c2c477a9cfea396c6e79c3 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Sat, 21 Sep 2013 11:02:04 +0100
Subject: mfd: arizona: Correct register definition for FLL2_SYNC_BW

We had specified the mask twice for FLL2_SYNC_BW change the first mask
definition in a bit definition to match the other fields.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/arizona/registers.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index 4706d3d46e56..cb49417f8ba9 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -1908,7 +1908,7 @@
 #define ARIZONA_FLL2_SYNC_GAIN_MASK              0x003c  /* FLL2_SYNC_GAIN */
 #define ARIZONA_FLL2_SYNC_GAIN_SHIFT                  2  /* FLL2_SYNC_GAIN */
 #define ARIZONA_FLL2_SYNC_GAIN_WIDTH                  4  /* FLL2_SYNC_GAIN */
-#define ARIZONA_FLL2_SYNC_BW_MASK                0x0001  /* FLL2_SYNC_BW */
+#define ARIZONA_FLL2_SYNC_BW                     0x0001  /* FLL2_SYNC_BW */
 #define ARIZONA_FLL2_SYNC_BW_MASK                0x0001  /* FLL2_SYNC_BW */
 #define ARIZONA_FLL2_SYNC_BW_SHIFT                    0  /* FLL2_SYNC_BW */
 #define ARIZONA_FLL2_SYNC_BW_WIDTH                    1  /* FLL2_SYNC_BW */
-- 
cgit 


From 60013b94d9530346db963474f7fde8aecabaff25 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sun, 22 Sep 2013 21:49:18 +0200
Subject: mfd: Add STw481x driver

This adds a driver for the STw481x PMICs found in the Nomadik
family of platforms. This one uses pure device tree probing.
Print some of the OTP registers on boot and register a regulator
MFD child.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig         |  10 ++
 drivers/mfd/Makefile        |   1 +
 drivers/mfd/stw481x.c       | 250 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/stw481x.h |  56 ++++++++++
 4 files changed, 317 insertions(+)
 create mode 100644 drivers/mfd/stw481x.c
 create mode 100644 include/linux/mfd/stw481x.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 914c3d142f78..d078fe4a82ef 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1151,6 +1151,16 @@ config MFD_WM8994
 	  core support for the WM8994, in order to use the actual
 	  functionaltiy of the device other drivers must be enabled.
 
+config MFD_STW481X
+	bool "Support for ST Microelectronics STw481x"
+	depends on I2C && ARCH_NOMADIK
+	select REGMAP_I2C
+	select MFD_CORE
+	help
+	  Select this option to enable the STw481x chip driver used
+	  in various ST Microelectronics and ST-Ericsson embedded
+	  Nomadik series.
+
 endmenu
 endif
 
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 15b905c6553c..656cec90a1e5 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -162,3 +162,4 @@ obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
 obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o vexpress-sysreg.o
 obj-$(CONFIG_MFD_RETU)		+= retu-mfd.o
 obj-$(CONFIG_MFD_AS3711)	+= as3711.o
+obj-$(CONFIG_MFD_STW481X)	+= stw481x.o
diff --git a/drivers/mfd/stw481x.c b/drivers/mfd/stw481x.c
new file mode 100644
index 000000000000..1243d5c6a448
--- /dev/null
+++ b/drivers/mfd/stw481x.c
@@ -0,0 +1,250 @@
+/*
+ * Core driver for STw4810/STw4811
+ *
+ * Copyright (C) 2013 ST-Ericsson SA
+ * Written on behalf of Linaro for ST-Ericsson
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/stw481x.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+
+/*
+ * This driver can only access the non-USB portions of STw4811, the register
+ * range 0x00-0x10 dealing with USB is bound to the two special I2C pins used
+ * for USB control.
+ */
+
+/* Registers inside the power control address space */
+#define STW_PC_VCORE_SEL	0x05U
+#define STW_PC_VAUX_SEL		0x06U
+#define STW_PC_VPLL_SEL		0x07U
+
+/**
+ * stw481x_get_pctl_reg() - get a power control register
+ * @stw481x: handle to the stw481x chip
+ * @reg: power control register to fetch
+ *
+ * The power control registers is a set of one-time-programmable registers
+ * in its own register space, accessed by writing addess bits to these
+ * two registers: bits 7,6,5 of PCTL_REG_LO corresponds to the 3 LSBs of
+ * the address and bits 8,9 of PCTL_REG_HI corresponds to the 2 MSBs of
+ * the address, forming an address space of 5 bits, i.e. 32 registers
+ * 0x00 ... 0x1f can be obtained.
+ */
+static int stw481x_get_pctl_reg(struct stw481x *stw481x, u8 reg)
+{
+	u8 msb = (reg >> 3) & 0x03;
+	u8 lsb = (reg << 5) & 0xe0;
+	unsigned int val;
+	u8 vrfy;
+	int ret;
+
+	ret = regmap_write(stw481x->map, STW_PCTL_REG_HI, msb);
+	if (ret)
+		return ret;
+	ret = regmap_write(stw481x->map, STW_PCTL_REG_LO, lsb);
+	if (ret)
+		return ret;
+	ret = regmap_read(stw481x->map, STW_PCTL_REG_HI, &val);
+	if (ret)
+		return ret;
+	vrfy = (val & 0x03) << 3;
+	ret = regmap_read(stw481x->map, STW_PCTL_REG_LO, &val);
+	if (ret)
+		return ret;
+	vrfy |= ((val >> 5) & 0x07);
+	if (vrfy != reg)
+		return -EIO;
+	return (val >> 1) & 0x0f;
+}
+
+static int stw481x_startup(struct stw481x *stw481x)
+{
+	/* Voltages multiplied by 100 */
+	u8 vcore_val[] = { 100, 105, 110, 115, 120, 122, 124, 126, 128,
+			   130, 132, 134, 136, 138, 140, 145 };
+	u8 vpll_val[] = { 105, 120, 130, 180 };
+	u8 vaux_val[] = { 15, 18, 25, 28 };
+	u8 vcore;
+	u8 vcore_slp;
+	u8 vpll;
+	u8 vaux;
+	bool vaux_en;
+	bool it_warn;
+	int ret;
+	unsigned int val;
+
+	ret = regmap_read(stw481x->map, STW_CONF1, &val);
+	if (ret)
+		return ret;
+	vaux_en = !!(val & STW_CONF1_PDN_VAUX);
+	it_warn = !!(val & STW_CONF1_IT_WARN);
+
+	dev_info(&stw481x->client->dev, "voltages %s\n",
+		(val & STW_CONF1_V_MONITORING) ? "OK" : "LOW");
+	dev_info(&stw481x->client->dev, "MMC level shifter %s\n",
+		(val & STW_CONF1_MMC_LS_STATUS) ? "high impedance" : "ON");
+	dev_info(&stw481x->client->dev, "VMMC: %s\n",
+		(val & STW_CONF1_PDN_VMMC) ? "ON" : "disabled");
+
+	dev_info(&stw481x->client->dev, "STw481x power control registers:\n");
+
+	ret = stw481x_get_pctl_reg(stw481x, STW_PC_VCORE_SEL);
+	if (ret < 0)
+		return ret;
+	vcore = ret & 0x0f;
+
+	ret = stw481x_get_pctl_reg(stw481x, STW_PC_VAUX_SEL);
+	if (ret < 0)
+		return ret;
+	vaux = (ret >> 2) & 3;
+	vpll = (ret >> 4) & 1; /* Save bit 4 */
+
+	ret = stw481x_get_pctl_reg(stw481x, STW_PC_VPLL_SEL);
+	if (ret < 0)
+		return ret;
+	vpll |= (ret >> 1) & 2;
+
+	dev_info(&stw481x->client->dev, "VCORE: %u.%uV %s\n",
+		vcore_val[vcore] / 100, vcore_val[vcore] % 100,
+		(ret & 4) ? "ON" : "OFF");
+
+	dev_info(&stw481x->client->dev, "VPLL:  %u.%uV %s\n",
+		vpll_val[vpll] / 100, vpll_val[vpll] % 100,
+		(ret & 0x10) ? "ON" : "OFF");
+
+	dev_info(&stw481x->client->dev, "VAUX:  %u.%uV %s\n",
+		vaux_val[vaux] / 10, vaux_val[vaux] % 10,
+		vaux_en ? "ON" : "OFF");
+
+	ret = regmap_read(stw481x->map, STW_CONF2, &val);
+	if (ret)
+		return ret;
+
+	dev_info(&stw481x->client->dev, "TWARN: %s threshold, %s\n",
+		it_warn ? "below" : "above",
+		(val & STW_CONF2_MASK_TWARN) ?
+		 "enabled" : "mask through VDDOK");
+	dev_info(&stw481x->client->dev, "VMMC: %s\n",
+		(val & STW_CONF2_VMMC_EXT) ? "internal" : "external");
+	dev_info(&stw481x->client->dev, "IT WAKE UP: %s\n",
+		(val & STW_CONF2_MASK_IT_WAKE_UP) ? "enabled" : "masked");
+	dev_info(&stw481x->client->dev, "GPO1: %s\n",
+		(val & STW_CONF2_GPO1) ? "low" : "high impedance");
+	dev_info(&stw481x->client->dev, "GPO2: %s\n",
+		(val & STW_CONF2_GPO2) ? "low" : "high impedance");
+
+	ret = regmap_read(stw481x->map, STW_VCORE_SLEEP, &val);
+	if (ret)
+		return ret;
+	vcore_slp = val & 0x0f;
+	dev_info(&stw481x->client->dev, "VCORE SLEEP: %u.%uV\n",
+		vcore_val[vcore_slp] / 100, vcore_val[vcore_slp] % 100);
+
+	return 0;
+}
+
+/*
+ * MFD cells - we have one cell which is selected operation
+ * mode, and we always have a GPIO cell.
+ */
+static struct mfd_cell stw481x_cells[] = {
+	{
+		.of_compatible = "st,stw481x-vmmc",
+		.name = "stw481x-vmmc-regulator",
+		.id = -1,
+	},
+};
+
+const struct regmap_config stw481x_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static int stw481x_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct stw481x			*stw481x;
+	int ret;
+	int i;
+
+	stw481x = devm_kzalloc(&client->dev, sizeof(*stw481x), GFP_KERNEL);
+	if (!stw481x)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, stw481x);
+	stw481x->client = client;
+	stw481x->map = devm_regmap_init_i2c(client, &stw481x_regmap_config);
+
+	ret = stw481x_startup(stw481x);
+	if (ret) {
+		dev_err(&client->dev, "chip initialization failed\n");
+		return ret;
+	}
+
+	/* Set up and register the platform devices. */
+	for (i = 0; i < ARRAY_SIZE(stw481x_cells); i++) {
+		/* One state holder for all drivers, this is simple */
+		stw481x_cells[i].platform_data = stw481x;
+		stw481x_cells[i].pdata_size = sizeof(*stw481x);
+	}
+
+	ret = mfd_add_devices(&client->dev, 0, stw481x_cells,
+			ARRAY_SIZE(stw481x_cells), NULL, 0, NULL);
+	if (ret)
+		return ret;
+
+	dev_info(&client->dev, "initialized STw481x device\n");
+
+	return ret;
+}
+
+static int stw481x_remove(struct i2c_client *client)
+{
+	mfd_remove_devices(&client->dev);
+	return 0;
+}
+
+/*
+ * This ID table is completely unused, as this is a pure
+ * device-tree probed driver, but it has to be here due to
+ * the structure of the I2C core.
+ */
+static const struct i2c_device_id stw481x_id[] = {
+	{ "stw481x", 0 },
+	{ },
+};
+
+static const struct of_device_id stw481x_match[] = {
+	{ .compatible = "st,stw4810", },
+	{ .compatible = "st,stw4811", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, stw481x_match);
+
+static struct i2c_driver stw481x_driver = {
+	.driver = {
+		.name	= "stw481x",
+		.of_match_table = stw481x_match,
+	},
+	.probe		= stw481x_probe,
+	.remove		= stw481x_remove,
+	.id_table	= stw481x_id,
+};
+
+module_i2c_driver(stw481x_driver);
+
+MODULE_AUTHOR("Linus Walleij");
+MODULE_DESCRIPTION("STw481x PMIC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/stw481x.h b/include/linux/mfd/stw481x.h
new file mode 100644
index 000000000000..eda121556e5d
--- /dev/null
+++ b/include/linux/mfd/stw481x.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2011 ST-Ericsson SA
+ * Written on behalf of Linaro for ST-Ericsson
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+#ifndef MFD_STW481X_H
+#define MFD_STW481X_H
+
+#include <linux/i2c.h>
+#include <linux/regulator/machine.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+
+/* These registers are accessed from more than one driver */
+#define STW_CONF1			0x11U
+#define STW_CONF1_PDN_VMMC		0x01U
+#define STW_CONF1_VMMC_MASK		0x0eU
+#define STW_CONF1_VMMC_1_8V		0x02U
+#define STW_CONF1_VMMC_2_85V		0x04U
+#define STW_CONF1_VMMC_3V		0x06U
+#define STW_CONF1_VMMC_1_85V		0x08U
+#define STW_CONF1_VMMC_2_6V		0x0aU
+#define STW_CONF1_VMMC_2_7V		0x0cU
+#define STW_CONF1_VMMC_3_3V		0x0eU
+#define STW_CONF1_MMC_LS_STATUS		0x10U
+#define STW_PCTL_REG_LO			0x1eU
+#define STW_PCTL_REG_HI			0x1fU
+#define STW_CONF1_V_MONITORING		0x20U
+#define STW_CONF1_IT_WARN		0x40U
+#define STW_CONF1_PDN_VAUX		0x80U
+#define STW_CONF2			0x20U
+#define STW_CONF2_MASK_TWARN		0x01U
+#define STW_CONF2_VMMC_EXT		0x02U
+#define STW_CONF2_MASK_IT_WAKE_UP	0x04U
+#define STW_CONF2_GPO1			0x08U
+#define STW_CONF2_GPO2			0x10U
+#define STW_VCORE_SLEEP			0x21U
+
+/**
+ * struct stw481x - state holder for the Stw481x drivers
+ * @mutex: mutex to serialize I2C accesses
+ * @i2c_client: corresponding I2C client
+ * @regulator: regulator device for regulator children
+ * @map: regmap handle to access device registers
+ */
+struct stw481x {
+	struct mutex		lock;
+	struct i2c_client	*client;
+	struct regulator_dev	*vmmc_regulator;
+	struct regmap		*map;
+};
+
+#endif
-- 
cgit 


From e90f875419967589d75d1a3e2b89c5f2720e794e Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <matthias.list@kaehlcke.net>
Date: Mon, 23 Sep 2013 22:43:29 +0200
Subject: mfd: ti_am335x_tscadc: Restore clock divider on resume

The ADC clock divider needs to be restored on resume as the register content
is lost when the ADC is powered down

Signed-off-by: Matthias Kaehlcke <matthias@kaehlcke.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/ti_am335x_tscadc.c       | 10 ++++++----
 include/linux/mfd/ti_am335x_tscadc.h |  1 +
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index baaf5a8123bb..a3685d6ef674 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -95,7 +95,7 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	const __be32            *cur;
 	u32			val;
 	int			err, ctrl;
-	int			clk_value, clock_rate;
+	int			clock_rate;
 	int			tsc_wires = 0, adc_channels = 0, total_channels;
 	int			readouts = 0;
 
@@ -196,11 +196,11 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	}
 	clock_rate = clk_get_rate(clk);
 	clk_put(clk);
-	clk_value = clock_rate / ADC_CLK;
+	tscadc->clk_div = clock_rate / ADC_CLK;
 
 	/* TSCADC_CLKDIV needs to be configured to the value minus 1 */
-	clk_value = clk_value - 1;
-	tscadc_writel(tscadc, REG_CLKDIV, clk_value);
+	tscadc->clk_div--;
+	tscadc_writel(tscadc, REG_CLKDIV, tscadc->clk_div);
 
 	/* Set the control register bits */
 	ctrl = CNTRLREG_STEPCONFIGWRT |
@@ -303,6 +303,8 @@ static int tscadc_resume(struct device *dev)
 	tscadc_writel(tscadc_dev, REG_CTRL,
 			(restore | CNTRLREG_TSCSSENB));
 
+	tscadc_writel(tscadc_dev, REG_CLKDIV, tscadc_dev->clk_div);
+
 	return 0;
 }
 
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index 4befdb85dd9c..7b68a061cd60 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -151,6 +151,7 @@ struct ti_tscadc_dev {
 	struct mfd_cell cells[TSCADC_CELLS];
 	u32 reg_se_cache;
 	spinlock_t reg_lock;
+	unsigned int clk_div;
 
 	/* tsc device */
 	struct titsc *tsc;
-- 
cgit 


From 0248b4bfe56f0545c051e6230939ca8b95f1b037 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Mon, 23 Sep 2013 19:14:32 +0100
Subject: mfd: mc13xxx: Move SPI erratum workaround into SPI I/O function

Move the workaround for double sending AUDIO_CODEC and AUDIO_DAC writes
into the SPI core, aiding refactoring to eliminate the ASoC custom I/O
functions and avoiding the extra writes for I2C.

Signed-off-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/mc13xxx-spi.c   | 5 +++++
 include/linux/mfd/mc13xxx.h | 7 +++++++
 sound/soc/codecs/mc13783.c  | 4 ----
 3 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/mc13xxx-spi.c b/drivers/mfd/mc13xxx-spi.c
index 77189daadf1e..5f14ef6693c2 100644
--- a/drivers/mfd/mc13xxx-spi.c
+++ b/drivers/mfd/mc13xxx-spi.c
@@ -94,10 +94,15 @@ static int mc13xxx_spi_write(void *context, const void *data, size_t count)
 {
 	struct device *dev = context;
 	struct spi_device *spi = to_spi_device(dev);
+	const char *reg = data;
 
 	if (count != 4)
 		return -ENOTSUPP;
 
+	/* include errata fix for spi audio problems */
+	if (*reg == MC13783_AUDIO_CODEC || *reg == MC13783_AUDIO_DAC)
+		spi_write(spi, data, count);
+
 	return spi_write(spi, data, count);
 }
 
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index 41ed59276c00..67c17b5a6f44 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -41,6 +41,13 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx,
 		unsigned int mode, unsigned int channel,
 		u8 ato, bool atox, unsigned int *sample);
 
+#define MC13783_AUDIO_RX0	36
+#define MC13783_AUDIO_RX1	37
+#define MC13783_AUDIO_TX	38
+#define MC13783_SSI_NETWORK	39
+#define MC13783_AUDIO_CODEC	40
+#define MC13783_AUDIO_DAC	41
+
 #define MC13XXX_IRQ_ADCDONE	0
 #define MC13XXX_IRQ_ADCBISDONE	1
 #define MC13XXX_IRQ_TS		2
diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c
index ea141e1d6f28..4d3c8fd8c5db 100644
--- a/sound/soc/codecs/mc13783.c
+++ b/sound/soc/codecs/mc13783.c
@@ -125,10 +125,6 @@ static int mc13783_write(struct snd_soc_codec *codec,
 
 	ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
 
-	/* include errata fix for spi audio problems */
-	if (reg == MC13783_AUDIO_CODEC || reg == MC13783_AUDIO_DAC)
-		ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
-
 	mc13xxx_unlock(priv->mc13xxx);
 
 	return ret;
-- 
cgit 


From 4233a0aafb72985a4692a9e6af5c528811226ac1 Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <a.hajda@samsung.com>
Date: Wed, 21 Aug 2013 18:53:33 +0200
Subject: mfd: max77693: Remove device wakeup from driver

The patch removes wakeup related code from the driver and plaftorm
data - it is already handled by i2c core using I2C_CLIENT_WAKE flag
from struct i2c_board_info. As a result MFD itself do not requires
platform data.

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/max77693.c               | 10 ----------
 include/linux/mfd/max77693-private.h |  1 -
 include/linux/mfd/max77693.h         |  2 --
 3 files changed, 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index c04723efc707..27f5da3bc63a 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -110,15 +110,9 @@ static int max77693_i2c_probe(struct i2c_client *i2c,
 			      const struct i2c_device_id *id)
 {
 	struct max77693_dev *max77693;
-	struct max77693_platform_data *pdata = dev_get_platdata(&i2c->dev);
 	u8 reg_data;
 	int ret = 0;
 
-	if (!pdata) {
-		dev_err(&i2c->dev, "No platform data found.\n");
-		return -EINVAL;
-	}
-
 	max77693 = devm_kzalloc(&i2c->dev,
 			sizeof(struct max77693_dev), GFP_KERNEL);
 	if (max77693 == NULL)
@@ -138,8 +132,6 @@ static int max77693_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
-	max77693->wakeup = pdata->wakeup;
-
 	ret = max77693_read_reg(max77693->regmap, MAX77693_PMIC_REG_PMIC_ID2,
 				&reg_data);
 	if (ret < 0) {
@@ -179,8 +171,6 @@ static int max77693_i2c_probe(struct i2c_client *i2c,
 	if (ret < 0)
 		goto err_mfd;
 
-	device_init_wakeup(max77693->dev, pdata->wakeup);
-
 	return ret;
 
 err_mfd:
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 244fb0d51589..3e050b933dd0 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -323,7 +323,6 @@ struct max77693_dev {
 
 	int irq;
 	int irq_gpio;
-	bool wakeup;
 	struct mutex irqlock;
 	int irq_masks_cur[MAX77693_IRQ_GROUP_NR];
 	int irq_masks_cache[MAX77693_IRQ_GROUP_NR];
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index 676f0f388992..3f3dc45f93ee 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -64,8 +64,6 @@ struct max77693_muic_platform_data {
 };
 
 struct max77693_platform_data {
-	int wakeup;
-
 	/* regulator data */
 	struct max77693_regulator_data *regulators;
 	int num_regulators;
-- 
cgit 


From d460a6f3d67a8558fb58299518077888b7dbf5f3 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan <ldewangan@nvidia.com>
Date: Tue, 22 Oct 2013 13:08:46 +0530
Subject: mfd: Add support for ams AS3722 PMIC

The ams AS3722 is a compact system PMU suitable for mobile phones,
tablets etc. It has 4 DC/DC step-down regulators, 3 DC/DC step-down
controller, 11 LDOs, RTC, automatic battery, temperature and
over-current monitoring, 8 GPIOs, ADC and a watchdog.

Add MFD core driver for the AS3722 to support core functionality.

Acked-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Florian Lobmaier <florian.lobmaier@ams.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 Documentation/devicetree/bindings/mfd/as3722.txt | 194 ++++++++++
 drivers/mfd/Kconfig                              |  12 +
 drivers/mfd/Makefile                             |   1 +
 drivers/mfd/as3722.c                             | 449 +++++++++++++++++++++++
 include/dt-bindings/mfd/as3722.h                 |  52 +++
 include/linux/mfd/as3722.h                       | 423 +++++++++++++++++++++
 6 files changed, 1131 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mfd/as3722.txt
 create mode 100644 drivers/mfd/as3722.c
 create mode 100644 include/dt-bindings/mfd/as3722.h
 create mode 100644 include/linux/mfd/as3722.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mfd/as3722.txt b/Documentation/devicetree/bindings/mfd/as3722.txt
new file mode 100644
index 000000000000..fc2191ecfd6b
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/as3722.txt
@@ -0,0 +1,194 @@
+* ams AS3722 Power management IC.
+
+Required properties:
+-------------------
+- compatible: Must be "ams,as3722".
+- reg: I2C device address.
+- interrupt-controller: AS3722 has internal interrupt controller which takes the
+  interrupt request from internal sub-blocks like RTC, regulators, GPIOs as well
+  as external input.
+- #interrupt-cells: Should be set to 2 for IRQ number and flags.
+  The first cell is the IRQ number. IRQ numbers for different interrupt source
+  of AS3722 are defined at dt-bindings/mfd/as3722.h
+  The second cell is the flags, encoded as the trigger masks from binding document
+	interrupts.txt, using dt-bindings/irq.
+
+Optional submodule and their properties:
+=======================================
+
+Pinmux and GPIO:
+===============
+Device has 8 GPIO pins which can be configured as GPIO as well as the special IO
+functions.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+Following are properties which is needed if GPIO and pinmux functionality
+is required:
+    Required properties:
+    -------------------
+	- gpio-controller: Marks the device node as a GPIO controller.
+	- #gpio-cells: Number of GPIO cells. Refer to binding document
+			gpio/gpio.txt
+
+    Optional properties:
+    --------------------
+	Following properties are require if pin control setting is required
+	at boot.
+	- pinctrl-names: A pinctrl state named "default" be defined, using the
+		bindings in pinctrl/pinctrl-binding.txt.
+	- pinctrl[0...n]: Properties to contain the phandle that refer to
+		different nodes of pin control settings. These nodes represents
+		the pin control setting of state 0 to state n. Each of these
+		nodes contains different subnodes to represents some desired
+		configuration for a list of pins. This configuration can
+		include the mux function to select on those pin(s), and
+		various pin configuration parameters, such as pull-up,
+		open drain.
+
+		Each subnode have following properties:
+		Required properties:
+		    - pins: List of pins. Valid values of pins properties are:
+				gpio0, gpio1, gpio2, gpio3, gpio4, gpio5,
+				gpio6, gpio7
+
+		Optional properties:
+			function, bias-disable, bias-pull-up, bias-pull-down,
+			bias-high-impedance, drive-open-drain.
+
+			Valid values for function properties are:
+				gpio, interrupt-out, gpio-in-interrupt,
+				vsup-vbat-low-undebounce-out,
+				vsup-vbat-low-debounce-out,
+				voltage-in-standby, oc-pg-sd0, oc-pg-sd6,
+				powergood-out, pwm-in, pwm-out, clk32k-out,
+				watchdog-in, soft-reset-in
+
+Regulators:
+===========
+Device has multiple DCDC and LDOs. The node "regulators" is require if regulator
+functionality is needed.
+
+Following are properties of regulator subnode.
+
+    Optional properties:
+    -------------------
+	The input supply of regulators are the optional properties on the
+	regulator node. The input supply of these regulators are provided
+	through following properties:
+		vsup-sd2-supply: Input supply for SD2.
+		vsup-sd3-supply: Input supply for SD3.
+		vsup-sd4-supply: Input supply for SD4.
+		vsup-sd5-supply: Input supply for SD5.
+		vin-ldo0-supply: Input supply for LDO0.
+		vin-ldo1-6-supply: Input supply for LDO1 and LDO6.
+		vin-ldo2-5-7-supply: Input supply for LDO2, LDO5 and LDO7.
+		vin-ldo3-4-supply: Input supply for LDO3 and LDO4.
+		vin-ldo9-10-supply: Input supply for LDO9 and LDO10.
+		vin-ldo11-supply: Input supply for LDO11.
+
+    Optional sub nodes for regulators:
+    ---------------------------------
+	The subnodes name is the name of regulator and it must be one of:
+	sd[0-6], ldo[0-7], ldo[9-11]
+
+	Each sub-node should contain the constraints and initialization
+	information for that regulator. See regulator.txt for a description
+	of standard properties for these sub-nodes.
+	Additional optional custom properties  are listed below.
+		ams,ext-control: External control of the rail. The option of
+			this properties will tell which external input is
+			controlling this rail. Valid values are 0, 1, 2 ad 3.
+			0: There is no external control of this rail.
+			1: Rail is controlled by ENABLE1 input pin.
+			2: Rail is controlled by ENABLE2 input pin.
+			3: Rail is controlled by ENABLE3 input pin.
+			Missing this property on DT will be assume as no
+			external control. The external control pin macros
+			are defined @dt-bindings/mfd/as3722.h
+
+		ams,enable-tracking: Enable tracking with SD1, only supported
+			by LDO3.
+
+Example:
+--------
+#include <dt-bindings/mfd/as3722.h>
+...
+ams3722 {
+	compatible = "ams,as3722";
+	reg = <0x48>;
+
+	interrupt-parent = <&intc>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+
+	gpio-controller;
+	#gpio-cells = <2>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&as3722_default>;
+
+	as3722_default: pinmux {
+			gpio0 {
+				pins = "gpio0";
+				function = "gpio";
+				bias-pull-down;
+			};
+
+			gpio1_2_4_7 {
+				pins = "gpio1", "gpio2", "gpio4", "gpio7";
+				function = "gpio";
+				bias-pull-up;
+			};
+
+			gpio5 {
+				pins = "gpio5";
+				function = "clk32k_out";
+			};
+	}
+
+	regulators {
+			vsup-sd2-supply = <...>;
+			...
+
+			sd0 {
+				regulator-name = "vdd_cpu";
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-always-on;
+				ams,ext-control = <2>;
+			};
+
+			sd1 {
+				regulator-name = "vdd_core";
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-always-on;
+				ams,ext-control = <1>;
+			};
+
+			sd2 {
+				regulator-name = "vddio_ddr";
+				regulator-min-microvolt = <1350000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+			};
+
+			sd4 {
+				regulator-name = "avdd-hdmi-pex";
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-always-on;
+			};
+
+			sd5 {
+				regulator-name = "vdd-1v8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+			....
+	};
+};
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d078fe4a82ef..b7c74a73d371 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -27,6 +27,18 @@ config MFD_AS3711
 	help
 	  Support for the AS3711 PMIC from AMS
 
+config MFD_AS3722
+	bool "ams AS3722 Power Management IC"
+	select MFD_CORE
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	depends on I2C && OF
+	help
+	  The ams AS3722 is a compact system PMU suitable for mobile phones,
+	  tablets etc. It has 4 DC/DC step-down regulators, 3 DC/DC step-down
+	  controllers, 11 LDOs, RTC, automatic battery, temperature and
+	  over current monitoring, GPIOs, ADC and a watchdog.
+
 config PMIC_ADP5520
 	bool "Analog Devices ADP5520/01 MFD PMIC Core Support"
 	depends on I2C=y
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 656cec90a1e5..8a28dc90fe78 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -162,4 +162,5 @@ obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
 obj-$(CONFIG_VEXPRESS_CONFIG)	+= vexpress-config.o vexpress-sysreg.o
 obj-$(CONFIG_MFD_RETU)		+= retu-mfd.o
 obj-$(CONFIG_MFD_AS3711)	+= as3711.o
+obj-$(CONFIG_MFD_AS3722)	+= as3722.o
 obj-$(CONFIG_MFD_STW481X)	+= stw481x.o
diff --git a/drivers/mfd/as3722.c b/drivers/mfd/as3722.c
new file mode 100644
index 000000000000..cd8ee593cfa8
--- /dev/null
+++ b/drivers/mfd/as3722.c
@@ -0,0 +1,449 @@
+/*
+ * Core driver for ams AS3722 PMICs
+ *
+ * Copyright (C) 2013 AMS AG
+ * Copyright (c) 2013, NVIDIA Corporation. All rights reserved.
+ *
+ * Author: Florian Lobmaier <florian.lobmaier@ams.com>
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/as3722.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#define AS3722_DEVICE_ID	0x0C
+
+static const struct resource as3722_rtc_resource[] = {
+	{
+		.name = "as3722-rtc-alarm",
+		.start = AS3722_IRQ_RTC_ALARM,
+		.end = AS3722_IRQ_RTC_ALARM,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static const struct resource as3722_adc_resource[] = {
+	{
+		.name = "as3722-adc",
+		.start = AS3722_IRQ_ADC,
+		.end = AS3722_IRQ_ADC,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct mfd_cell as3722_devs[] = {
+	{
+		.name = "as3722-pinctrl",
+	},
+	{
+		.name = "as3722-regulator",
+	},
+	{
+		.name = "as3722-rtc",
+		.num_resources = ARRAY_SIZE(as3722_rtc_resource),
+		.resources = as3722_rtc_resource,
+	},
+	{
+		.name = "as3722-adc",
+		.num_resources = ARRAY_SIZE(as3722_adc_resource),
+		.resources = as3722_adc_resource,
+	},
+	{
+		.name = "as3722-power-off",
+	},
+};
+
+static const struct regmap_irq as3722_irqs[] = {
+	/* INT1 IRQs */
+	[AS3722_IRQ_LID] = {
+		.mask = AS3722_INTERRUPT_MASK1_LID,
+	},
+	[AS3722_IRQ_ACOK] = {
+		.mask = AS3722_INTERRUPT_MASK1_ACOK,
+	},
+	[AS3722_IRQ_ENABLE1] = {
+		.mask = AS3722_INTERRUPT_MASK1_ENABLE1,
+	},
+	[AS3722_IRQ_OCCUR_ALARM_SD0] = {
+		.mask = AS3722_INTERRUPT_MASK1_OCURR_ALARM_SD0,
+	},
+	[AS3722_IRQ_ONKEY_LONG_PRESS] = {
+		.mask = AS3722_INTERRUPT_MASK1_ONKEY_LONG,
+	},
+	[AS3722_IRQ_ONKEY] = {
+		.mask = AS3722_INTERRUPT_MASK1_ONKEY,
+	},
+	[AS3722_IRQ_OVTMP] = {
+		.mask = AS3722_INTERRUPT_MASK1_OVTMP,
+	},
+	[AS3722_IRQ_LOWBAT] = {
+		.mask = AS3722_INTERRUPT_MASK1_LOWBAT,
+	},
+
+	/* INT2 IRQs */
+	[AS3722_IRQ_SD0_LV] = {
+		.mask = AS3722_INTERRUPT_MASK2_SD0_LV,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_SD1_LV] = {
+		.mask = AS3722_INTERRUPT_MASK2_SD1_LV,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_SD2_LV] = {
+		.mask = AS3722_INTERRUPT_MASK2_SD2345_LV,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_PWM1_OV_PROT] = {
+		.mask = AS3722_INTERRUPT_MASK2_PWM1_OV_PROT,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_PWM2_OV_PROT] = {
+		.mask = AS3722_INTERRUPT_MASK2_PWM2_OV_PROT,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_ENABLE2] = {
+		.mask = AS3722_INTERRUPT_MASK2_ENABLE2,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_SD6_LV] = {
+		.mask = AS3722_INTERRUPT_MASK2_SD6_LV,
+		.reg_offset = 1,
+	},
+	[AS3722_IRQ_RTC_REP] = {
+		.mask = AS3722_INTERRUPT_MASK2_RTC_REP,
+		.reg_offset = 1,
+	},
+
+	/* INT3 IRQs */
+	[AS3722_IRQ_RTC_ALARM] = {
+		.mask = AS3722_INTERRUPT_MASK3_RTC_ALARM,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_GPIO1] = {
+		.mask = AS3722_INTERRUPT_MASK3_GPIO1,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_GPIO2] = {
+		.mask = AS3722_INTERRUPT_MASK3_GPIO2,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_GPIO3] = {
+		.mask = AS3722_INTERRUPT_MASK3_GPIO3,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_GPIO4] = {
+		.mask = AS3722_INTERRUPT_MASK3_GPIO4,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_GPIO5] = {
+		.mask = AS3722_INTERRUPT_MASK3_GPIO5,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_WATCHDOG] = {
+		.mask = AS3722_INTERRUPT_MASK3_WATCHDOG,
+		.reg_offset = 2,
+	},
+	[AS3722_IRQ_ENABLE3] = {
+		.mask = AS3722_INTERRUPT_MASK3_ENABLE3,
+		.reg_offset = 2,
+	},
+
+	/* INT4 IRQs */
+	[AS3722_IRQ_TEMP_SD0_SHUTDOWN] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD0_SHUTDOWN,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_TEMP_SD1_SHUTDOWN] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD1_SHUTDOWN,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_TEMP_SD2_SHUTDOWN] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD6_SHUTDOWN,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_TEMP_SD0_ALARM] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD0_ALARM,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_TEMP_SD1_ALARM] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD1_ALARM,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_TEMP_SD6_ALARM] = {
+		.mask = AS3722_INTERRUPT_MASK4_TEMP_SD6_ALARM,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_OCCUR_ALARM_SD6] = {
+		.mask = AS3722_INTERRUPT_MASK4_OCCUR_ALARM_SD6,
+		.reg_offset = 3,
+	},
+	[AS3722_IRQ_ADC] = {
+		.mask = AS3722_INTERRUPT_MASK4_ADC,
+		.reg_offset = 3,
+	},
+};
+
+static const struct regmap_irq_chip as3722_irq_chip = {
+	.name = "as3722",
+	.irqs = as3722_irqs,
+	.num_irqs = ARRAY_SIZE(as3722_irqs),
+	.num_regs = 4,
+	.status_base = AS3722_INTERRUPT_STATUS1_REG,
+	.mask_base = AS3722_INTERRUPT_MASK1_REG,
+};
+
+static int as3722_check_device_id(struct as3722 *as3722)
+{
+	u32 val;
+	int ret;
+
+	/* Check that this is actually a AS3722 */
+	ret = as3722_read(as3722, AS3722_ASIC_ID1_REG, &val);
+	if (ret < 0) {
+		dev_err(as3722->dev, "ASIC_ID1 read failed: %d\n", ret);
+		return ret;
+	}
+
+	if (val != AS3722_DEVICE_ID) {
+		dev_err(as3722->dev, "Device is not AS3722, ID is 0x%x\n", val);
+		return -ENODEV;
+	}
+
+	ret = as3722_read(as3722, AS3722_ASIC_ID2_REG, &val);
+	if (ret < 0) {
+		dev_err(as3722->dev, "ASIC_ID2 read failed: %d\n", ret);
+		return ret;
+	}
+
+	dev_info(as3722->dev, "AS3722 with revision 0x%x found\n", val);
+	return 0;
+}
+
+static int as3722_configure_pullups(struct as3722 *as3722)
+{
+	int ret;
+	u32 val = 0;
+
+	if (as3722->en_intern_int_pullup)
+		val |= AS3722_INT_PULL_UP;
+	if (as3722->en_intern_i2c_pullup)
+		val |= AS3722_I2C_PULL_UP;
+
+	ret = as3722_update_bits(as3722, AS3722_IOVOLTAGE_REG,
+			AS3722_INT_PULL_UP | AS3722_I2C_PULL_UP, val);
+	if (ret < 0)
+		dev_err(as3722->dev, "IOVOLTAGE_REG update failed: %d\n", ret);
+	return ret;
+}
+
+static const struct regmap_range as3722_readable_ranges[] = {
+	regmap_reg_range(AS3722_SD0_VOLTAGE_REG, AS3722_SD6_VOLTAGE_REG),
+	regmap_reg_range(AS3722_GPIO0_CONTROL_REG, AS3722_LDO7_VOLTAGE_REG),
+	regmap_reg_range(AS3722_LDO9_VOLTAGE_REG, AS3722_REG_SEQU_MOD3_REG),
+	regmap_reg_range(AS3722_SD_PHSW_CTRL_REG, AS3722_PWM_CONTROL_H_REG),
+	regmap_reg_range(AS3722_WATCHDOG_TIMER_REG, AS3722_WATCHDOG_TIMER_REG),
+	regmap_reg_range(AS3722_WATCHDOG_SOFTWARE_SIGNAL_REG,
+					AS3722_BATTERY_VOLTAGE_MONITOR2_REG),
+	regmap_reg_range(AS3722_SD_CONTROL_REG, AS3722_PWM_VCONTROL4_REG),
+	regmap_reg_range(AS3722_BB_CHARGER_REG, AS3722_SRAM_REG),
+	regmap_reg_range(AS3722_RTC_ACCESS_REG, AS3722_RTC_ACCESS_REG),
+	regmap_reg_range(AS3722_RTC_STATUS_REG, AS3722_TEMP_STATUS_REG),
+	regmap_reg_range(AS3722_ADC0_CONTROL_REG, AS3722_ADC_CONFIGURATION_REG),
+	regmap_reg_range(AS3722_ASIC_ID1_REG, AS3722_ASIC_ID2_REG),
+	regmap_reg_range(AS3722_LOCK_REG, AS3722_LOCK_REG),
+};
+
+static const struct regmap_access_table as3722_readable_table = {
+	.yes_ranges = as3722_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(as3722_readable_ranges),
+};
+
+static const struct regmap_range as3722_writable_ranges[] = {
+	regmap_reg_range(AS3722_SD0_VOLTAGE_REG, AS3722_SD6_VOLTAGE_REG),
+	regmap_reg_range(AS3722_GPIO0_CONTROL_REG, AS3722_LDO7_VOLTAGE_REG),
+	regmap_reg_range(AS3722_LDO9_VOLTAGE_REG, AS3722_GPIO_SIGNAL_OUT_REG),
+	regmap_reg_range(AS3722_REG_SEQU_MOD1_REG, AS3722_REG_SEQU_MOD3_REG),
+	regmap_reg_range(AS3722_SD_PHSW_CTRL_REG, AS3722_PWM_CONTROL_H_REG),
+	regmap_reg_range(AS3722_WATCHDOG_TIMER_REG, AS3722_WATCHDOG_TIMER_REG),
+	regmap_reg_range(AS3722_WATCHDOG_SOFTWARE_SIGNAL_REG,
+					AS3722_BATTERY_VOLTAGE_MONITOR2_REG),
+	regmap_reg_range(AS3722_SD_CONTROL_REG, AS3722_PWM_VCONTROL4_REG),
+	regmap_reg_range(AS3722_BB_CHARGER_REG, AS3722_SRAM_REG),
+	regmap_reg_range(AS3722_INTERRUPT_MASK1_REG, AS3722_TEMP_STATUS_REG),
+	regmap_reg_range(AS3722_ADC0_CONTROL_REG, AS3722_ADC1_CONTROL_REG),
+	regmap_reg_range(AS3722_ADC1_THRESHOLD_HI_MSB_REG,
+					AS3722_ADC_CONFIGURATION_REG),
+	regmap_reg_range(AS3722_LOCK_REG, AS3722_LOCK_REG),
+};
+
+static const struct regmap_access_table as3722_writable_table = {
+	.yes_ranges = as3722_writable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(as3722_writable_ranges),
+};
+
+static const struct regmap_range as3722_cacheable_ranges[] = {
+	regmap_reg_range(AS3722_SD0_VOLTAGE_REG, AS3722_LDO11_VOLTAGE_REG),
+	regmap_reg_range(AS3722_SD_CONTROL_REG, AS3722_LDOCONTROL1_REG),
+};
+
+static const struct regmap_access_table as3722_volatile_table = {
+	.no_ranges = as3722_cacheable_ranges,
+	.n_no_ranges = ARRAY_SIZE(as3722_cacheable_ranges),
+};
+
+const struct regmap_config as3722_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = AS3722_MAX_REGISTER,
+	.cache_type = REGCACHE_RBTREE,
+	.rd_table = &as3722_readable_table,
+	.wr_table = &as3722_writable_table,
+	.volatile_table = &as3722_volatile_table,
+};
+
+static int as3722_i2c_of_probe(struct i2c_client *i2c,
+			struct as3722 *as3722)
+{
+	struct device_node *np = i2c->dev.of_node;
+	struct irq_data *irq_data;
+
+	if (!np) {
+		dev_err(&i2c->dev, "Device Tree not found\n");
+		return -EINVAL;
+	}
+
+	irq_data = irq_get_irq_data(i2c->irq);
+	if (!irq_data) {
+		dev_err(&i2c->dev, "Invalid IRQ: %d\n", i2c->irq);
+		return -EINVAL;
+	}
+
+	as3722->en_intern_int_pullup = of_property_read_bool(np,
+					"ams,enable-internal-int-pullup");
+	as3722->en_intern_i2c_pullup = of_property_read_bool(np,
+					"ams,enable-internal-i2c-pullup");
+	as3722->irq_flags = irqd_get_trigger_type(irq_data);
+	dev_dbg(&i2c->dev, "IRQ flags are 0x%08lx\n", as3722->irq_flags);
+	return 0;
+}
+
+static int as3722_i2c_probe(struct i2c_client *i2c,
+			const struct i2c_device_id *id)
+{
+	struct as3722 *as3722;
+	unsigned long irq_flags;
+	int ret;
+
+	as3722 = devm_kzalloc(&i2c->dev, sizeof(struct as3722), GFP_KERNEL);
+	if (!as3722)
+		return -ENOMEM;
+
+	as3722->dev = &i2c->dev;
+	as3722->chip_irq = i2c->irq;
+	i2c_set_clientdata(i2c, as3722);
+
+	ret = as3722_i2c_of_probe(i2c, as3722);
+	if (ret < 0)
+		return ret;
+
+	as3722->regmap = devm_regmap_init_i2c(i2c, &as3722_regmap_config);
+	if (IS_ERR(as3722->regmap)) {
+		ret = PTR_ERR(as3722->regmap);
+		dev_err(&i2c->dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = as3722_check_device_id(as3722);
+	if (ret < 0)
+		return ret;
+
+	irq_flags = as3722->irq_flags | IRQF_ONESHOT;
+	ret = regmap_add_irq_chip(as3722->regmap, as3722->chip_irq,
+			irq_flags, -1, &as3722_irq_chip,
+			&as3722->irq_data);
+	if (ret < 0) {
+		dev_err(as3722->dev, "Failed to add regmap irq: %d\n", ret);
+		return ret;
+	}
+
+	ret = as3722_configure_pullups(as3722);
+	if (ret < 0)
+		goto scrub;
+
+	ret = mfd_add_devices(&i2c->dev, -1, as3722_devs,
+			ARRAY_SIZE(as3722_devs), NULL, 0,
+			regmap_irq_get_domain(as3722->irq_data));
+	if (ret) {
+		dev_err(as3722->dev, "Failed to add MFD devices: %d\n", ret);
+		goto scrub;
+	}
+
+	dev_dbg(as3722->dev, "AS3722 core driver initialized successfully\n");
+	return 0;
+
+scrub:
+	regmap_del_irq_chip(as3722->chip_irq, as3722->irq_data);
+	return ret;
+}
+
+static int as3722_i2c_remove(struct i2c_client *i2c)
+{
+	struct as3722 *as3722 = i2c_get_clientdata(i2c);
+
+	mfd_remove_devices(as3722->dev);
+	regmap_del_irq_chip(as3722->chip_irq, as3722->irq_data);
+	return 0;
+}
+
+static const struct of_device_id as3722_of_match[] = {
+	{ .compatible = "ams,as3722", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, as3722_of_match);
+
+static const struct i2c_device_id as3722_i2c_id[] = {
+	{ "as3722", 0 },
+	{},
+};
+MODULE_DEVICE_TABLE(i2c, as3722_i2c_id);
+
+static struct i2c_driver as3722_i2c_driver = {
+	.driver = {
+		.name = "as3722",
+		.owner = THIS_MODULE,
+		.of_match_table = as3722_of_match,
+	},
+	.probe = as3722_i2c_probe,
+	.remove = as3722_i2c_remove,
+	.id_table = as3722_i2c_id,
+};
+
+module_i2c_driver(as3722_i2c_driver);
+
+MODULE_DESCRIPTION("I2C support for AS3722 PMICs");
+MODULE_AUTHOR("Florian Lobmaier <florian.lobmaier@ams.com>");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/dt-bindings/mfd/as3722.h b/include/dt-bindings/mfd/as3722.h
new file mode 100644
index 000000000000..0e692562d77b
--- /dev/null
+++ b/include/dt-bindings/mfd/as3722.h
@@ -0,0 +1,52 @@
+/*
+ * This header provides macros for ams AS3722 device bindings.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ */
+
+#ifndef __DT_BINDINGS_AS3722_H__
+#define __DT_BINDINGS_AS3722_H__
+
+/* External control pins */
+#define AS3722_EXT_CONTROL_PIN_ENABLE1 1
+#define AS3722_EXT_CONTROL_PIN_ENABLE2 2
+#define AS3722_EXT_CONTROL_PIN_ENABLE2 3
+
+/* Interrupt numbers for AS3722 */
+#define AS3722_IRQ_LID			0
+#define AS3722_IRQ_ACOK			1
+#define AS3722_IRQ_ENABLE1		2
+#define AS3722_IRQ_OCCUR_ALARM_SD0	3
+#define AS3722_IRQ_ONKEY_LONG_PRESS	4
+#define AS3722_IRQ_ONKEY		5
+#define AS3722_IRQ_OVTMP		6
+#define AS3722_IRQ_LOWBAT		7
+#define AS3722_IRQ_SD0_LV		8
+#define AS3722_IRQ_SD1_LV		9
+#define AS3722_IRQ_SD2_LV		10
+#define AS3722_IRQ_PWM1_OV_PROT		11
+#define AS3722_IRQ_PWM2_OV_PROT		12
+#define AS3722_IRQ_ENABLE2		13
+#define AS3722_IRQ_SD6_LV		14
+#define AS3722_IRQ_RTC_REP		15
+#define AS3722_IRQ_RTC_ALARM		16
+#define AS3722_IRQ_GPIO1		17
+#define AS3722_IRQ_GPIO2		18
+#define AS3722_IRQ_GPIO3		19
+#define AS3722_IRQ_GPIO4		20
+#define AS3722_IRQ_GPIO5		21
+#define AS3722_IRQ_WATCHDOG		22
+#define AS3722_IRQ_ENABLE3		23
+#define AS3722_IRQ_TEMP_SD0_SHUTDOWN	24
+#define AS3722_IRQ_TEMP_SD1_SHUTDOWN	25
+#define AS3722_IRQ_TEMP_SD2_SHUTDOWN	26
+#define AS3722_IRQ_TEMP_SD0_ALARM	27
+#define AS3722_IRQ_TEMP_SD1_ALARM	28
+#define AS3722_IRQ_TEMP_SD6_ALARM	29
+#define AS3722_IRQ_OCCUR_ALARM_SD6	30
+#define AS3722_IRQ_ADC			31
+
+#endif /* __DT_BINDINGS_AS3722_H__ */
diff --git a/include/linux/mfd/as3722.h b/include/linux/mfd/as3722.h
new file mode 100644
index 000000000000..16bf8a0dcd97
--- /dev/null
+++ b/include/linux/mfd/as3722.h
@@ -0,0 +1,423 @@
+/*
+ * as3722 definitions
+ *
+ * Copyright (C) 2013 ams
+ * Copyright (c) 2013, NVIDIA Corporation. All rights reserved.
+ *
+ * Author: Florian Lobmaier <florian.lobmaier@ams.com>
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#ifndef __LINUX_MFD_AS3722_H__
+#define __LINUX_MFD_AS3722_H__
+
+#include <linux/regmap.h>
+
+/* AS3722 registers */
+#define AS3722_SD0_VOLTAGE_REG				0x00
+#define AS3722_SD1_VOLTAGE_REG				0x01
+#define AS3722_SD2_VOLTAGE_REG				0x02
+#define AS3722_SD3_VOLTAGE_REG				0x03
+#define AS3722_SD4_VOLTAGE_REG				0x04
+#define AS3722_SD5_VOLTAGE_REG				0x05
+#define AS3722_SD6_VOLTAGE_REG				0x06
+#define AS3722_GPIO0_CONTROL_REG			0x08
+#define AS3722_GPIO1_CONTROL_REG			0x09
+#define AS3722_GPIO2_CONTROL_REG			0x0A
+#define AS3722_GPIO3_CONTROL_REG			0x0B
+#define AS3722_GPIO4_CONTROL_REG			0x0C
+#define AS3722_GPIO5_CONTROL_REG			0x0D
+#define AS3722_GPIO6_CONTROL_REG			0x0E
+#define AS3722_GPIO7_CONTROL_REG			0x0F
+#define AS3722_LDO0_VOLTAGE_REG				0x10
+#define AS3722_LDO1_VOLTAGE_REG				0x11
+#define AS3722_LDO2_VOLTAGE_REG				0x12
+#define AS3722_LDO3_VOLTAGE_REG				0x13
+#define AS3722_LDO4_VOLTAGE_REG				0x14
+#define AS3722_LDO5_VOLTAGE_REG				0x15
+#define AS3722_LDO6_VOLTAGE_REG				0x16
+#define AS3722_LDO7_VOLTAGE_REG				0x17
+#define AS3722_LDO9_VOLTAGE_REG				0x19
+#define AS3722_LDO10_VOLTAGE_REG			0x1A
+#define AS3722_LDO11_VOLTAGE_REG			0x1B
+#define AS3722_GPIO_DEB1_REG				0x1E
+#define AS3722_GPIO_DEB2_REG				0x1F
+#define AS3722_GPIO_SIGNAL_OUT_REG			0x20
+#define AS3722_GPIO_SIGNAL_IN_REG			0x21
+#define AS3722_REG_SEQU_MOD1_REG			0x22
+#define AS3722_REG_SEQU_MOD2_REG			0x23
+#define AS3722_REG_SEQU_MOD3_REG			0x24
+#define AS3722_SD_PHSW_CTRL_REG				0x27
+#define AS3722_SD_PHSW_STATUS				0x28
+#define AS3722_SD0_CONTROL_REG				0x29
+#define AS3722_SD1_CONTROL_REG				0x2A
+#define AS3722_SDmph_CONTROL_REG			0x2B
+#define AS3722_SD23_CONTROL_REG				0x2C
+#define AS3722_SD4_CONTROL_REG				0x2D
+#define AS3722_SD5_CONTROL_REG				0x2E
+#define AS3722_SD6_CONTROL_REG				0x2F
+#define AS3722_SD_DVM_REG				0x30
+#define AS3722_RESET_REASON_REG				0x31
+#define AS3722_BATTERY_VOLTAGE_MONITOR_REG		0x32
+#define AS3722_STARTUP_CONTROL_REG			0x33
+#define AS3722_RESET_TIMER_REG				0x34
+#define AS3722_REFERENCE_CONTROL_REG			0x35
+#define AS3722_RESET_CONTROL_REG			0x36
+#define AS3722_OVER_TEMP_CONTROL_REG			0x37
+#define AS3722_WATCHDOG_CONTROL_REG			0x38
+#define AS3722_REG_STANDBY_MOD1_REG			0x39
+#define AS3722_REG_STANDBY_MOD2_REG			0x3A
+#define AS3722_REG_STANDBY_MOD3_REG			0x3B
+#define AS3722_ENABLE_CTRL1_REG				0x3C
+#define AS3722_ENABLE_CTRL2_REG				0x3D
+#define AS3722_ENABLE_CTRL3_REG				0x3E
+#define AS3722_ENABLE_CTRL4_REG				0x3F
+#define AS3722_ENABLE_CTRL5_REG				0x40
+#define AS3722_PWM_CONTROL_L_REG			0x41
+#define AS3722_PWM_CONTROL_H_REG			0x42
+#define AS3722_WATCHDOG_TIMER_REG			0x46
+#define AS3722_WATCHDOG_SOFTWARE_SIGNAL_REG		0x48
+#define AS3722_IOVOLTAGE_REG				0x49
+#define AS3722_BATTERY_VOLTAGE_MONITOR2_REG		0x4A
+#define AS3722_SD_CONTROL_REG				0x4D
+#define AS3722_LDOCONTROL0_REG				0x4E
+#define AS3722_LDOCONTROL1_REG				0x4F
+#define AS3722_SD0_PROTECT_REG				0x50
+#define AS3722_SD6_PROTECT_REG				0x51
+#define AS3722_PWM_VCONTROL1_REG			0x52
+#define AS3722_PWM_VCONTROL2_REG			0x53
+#define AS3722_PWM_VCONTROL3_REG			0x54
+#define AS3722_PWM_VCONTROL4_REG			0x55
+#define AS3722_BB_CHARGER_REG				0x57
+#define AS3722_CTRL_SEQU1_REG				0x58
+#define AS3722_CTRL_SEQU2_REG				0x59
+#define AS3722_OVCURRENT_REG				0x5A
+#define AS3722_OVCURRENT_DEB_REG			0x5B
+#define AS3722_SDLV_DEB_REG				0x5C
+#define AS3722_OC_PG_CTRL_REG				0x5D
+#define AS3722_OC_PG_CTRL2_REG				0x5E
+#define AS3722_CTRL_STATUS				0x5F
+#define AS3722_RTC_CONTROL_REG				0x60
+#define AS3722_RTC_SECOND_REG				0x61
+#define AS3722_RTC_MINUTE_REG				0x62
+#define AS3722_RTC_HOUR_REG				0x63
+#define AS3722_RTC_DAY_REG				0x64
+#define AS3722_RTC_MONTH_REG				0x65
+#define AS3722_RTC_YEAR_REG				0x66
+#define AS3722_RTC_ALARM_SECOND_REG			0x67
+#define AS3722_RTC_ALARM_MINUTE_REG			0x68
+#define AS3722_RTC_ALARM_HOUR_REG			0x69
+#define AS3722_RTC_ALARM_DAY_REG			0x6A
+#define AS3722_RTC_ALARM_MONTH_REG			0x6B
+#define AS3722_RTC_ALARM_YEAR_REG			0x6C
+#define AS3722_SRAM_REG					0x6D
+#define AS3722_RTC_ACCESS_REG				0x6F
+#define AS3722_RTC_STATUS_REG				0x73
+#define AS3722_INTERRUPT_MASK1_REG			0x74
+#define AS3722_INTERRUPT_MASK2_REG			0x75
+#define AS3722_INTERRUPT_MASK3_REG			0x76
+#define AS3722_INTERRUPT_MASK4_REG			0x77
+#define AS3722_INTERRUPT_STATUS1_REG			0x78
+#define AS3722_INTERRUPT_STATUS2_REG			0x79
+#define AS3722_INTERRUPT_STATUS3_REG			0x7A
+#define AS3722_INTERRUPT_STATUS4_REG			0x7B
+#define AS3722_TEMP_STATUS_REG				0x7D
+#define AS3722_ADC0_CONTROL_REG				0x80
+#define AS3722_ADC1_CONTROL_REG				0x81
+#define AS3722_ADC0_MSB_RESULT_REG			0x82
+#define AS3722_ADC0_LSB_RESULT_REG			0x83
+#define AS3722_ADC1_MSB_RESULT_REG			0x84
+#define AS3722_ADC1_LSB_RESULT_REG			0x85
+#define AS3722_ADC1_THRESHOLD_HI_MSB_REG		0x86
+#define AS3722_ADC1_THRESHOLD_HI_LSB_REG		0x87
+#define AS3722_ADC1_THRESHOLD_LO_MSB_REG		0x88
+#define AS3722_ADC1_THRESHOLD_LO_LSB_REG		0x89
+#define AS3722_ADC_CONFIGURATION_REG			0x8A
+#define AS3722_ASIC_ID1_REG				0x90
+#define AS3722_ASIC_ID2_REG				0x91
+#define AS3722_LOCK_REG					0x9E
+#define AS3722_MAX_REGISTER				0xF4
+
+#define AS3722_SD0_EXT_ENABLE_MASK			0x03
+#define AS3722_SD1_EXT_ENABLE_MASK			0x0C
+#define AS3722_SD2_EXT_ENABLE_MASK			0x30
+#define AS3722_SD3_EXT_ENABLE_MASK			0xC0
+#define AS3722_SD4_EXT_ENABLE_MASK			0x03
+#define AS3722_SD5_EXT_ENABLE_MASK			0x0C
+#define AS3722_SD6_EXT_ENABLE_MASK			0x30
+#define AS3722_LDO0_EXT_ENABLE_MASK			0x03
+#define AS3722_LDO1_EXT_ENABLE_MASK			0x0C
+#define AS3722_LDO2_EXT_ENABLE_MASK			0x30
+#define AS3722_LDO3_EXT_ENABLE_MASK			0xC0
+#define AS3722_LDO4_EXT_ENABLE_MASK			0x03
+#define AS3722_LDO5_EXT_ENABLE_MASK			0x0C
+#define AS3722_LDO6_EXT_ENABLE_MASK			0x30
+#define AS3722_LDO7_EXT_ENABLE_MASK			0xC0
+#define AS3722_LDO9_EXT_ENABLE_MASK			0x0C
+#define AS3722_LDO10_EXT_ENABLE_MASK			0x30
+#define AS3722_LDO11_EXT_ENABLE_MASK			0xC0
+
+#define AS3722_OVCURRENT_SD0_ALARM_MASK			0x07
+#define AS3722_OVCURRENT_SD0_ALARM_SHIFT		0x01
+#define AS3722_OVCURRENT_SD0_TRIP_MASK			0x18
+#define AS3722_OVCURRENT_SD0_TRIP_SHIFT			0x03
+#define AS3722_OVCURRENT_SD1_TRIP_MASK			0x60
+#define AS3722_OVCURRENT_SD1_TRIP_SHIFT			0x05
+
+#define AS3722_OVCURRENT_SD6_ALARM_MASK			0x07
+#define AS3722_OVCURRENT_SD6_ALARM_SHIFT		0x01
+#define AS3722_OVCURRENT_SD6_TRIP_MASK			0x18
+#define AS3722_OVCURRENT_SD6_TRIP_SHIFT			0x03
+
+/* AS3722 register bits and bit masks */
+#define AS3722_LDO_ILIMIT_MASK				BIT(7)
+#define AS3722_LDO_ILIMIT_BIT				BIT(7)
+#define AS3722_LDO0_VSEL_MASK				0x1F
+#define AS3722_LDO0_VSEL_MIN				0x01
+#define AS3722_LDO0_VSEL_MAX				0x12
+#define AS3722_LDO0_NUM_VOLT				0x12
+#define AS3722_LDO3_VSEL_MASK				0x3F
+#define AS3722_LDO3_VSEL_MIN				0x01
+#define AS3722_LDO3_VSEL_MAX				0x2D
+#define AS3722_LDO3_NUM_VOLT				0x2D
+#define AS3722_LDO_VSEL_MASK				0x7F
+#define AS3722_LDO_VSEL_MIN				0x01
+#define AS3722_LDO_VSEL_MAX				0x7F
+#define AS3722_LDO_VSEL_DNU_MIN				0x25
+#define AS3722_LDO_VSEL_DNU_MAX				0x3F
+#define AS3722_LDO_NUM_VOLT				0x80
+
+#define AS3722_LDO0_CTRL				BIT(0)
+#define AS3722_LDO1_CTRL				BIT(1)
+#define AS3722_LDO2_CTRL				BIT(2)
+#define AS3722_LDO3_CTRL				BIT(3)
+#define AS3722_LDO4_CTRL				BIT(4)
+#define AS3722_LDO5_CTRL				BIT(5)
+#define AS3722_LDO6_CTRL				BIT(6)
+#define AS3722_LDO7_CTRL				BIT(7)
+#define AS3722_LDO9_CTRL				BIT(1)
+#define AS3722_LDO10_CTRL				BIT(2)
+#define AS3722_LDO11_CTRL				BIT(3)
+
+#define AS3722_LDO3_MODE_MASK				(3 << 6)
+#define AS3722_LDO3_MODE_VAL(n)				(((n) & 0x3) << 6)
+#define AS3722_LDO3_MODE_PMOS				AS3722_LDO3_MODE_VAL(0)
+#define AS3722_LDO3_MODE_PMOS_TRACKING			AS3722_LDO3_MODE_VAL(1)
+#define AS3722_LDO3_MODE_NMOS				AS3722_LDO3_MODE_VAL(2)
+#define AS3722_LDO3_MODE_SWITCH				AS3722_LDO3_MODE_VAL(3)
+
+#define AS3722_SD_VSEL_MASK				0x7F
+#define AS3722_SD0_VSEL_MIN				0x01
+#define AS3722_SD0_VSEL_MAX				0x5A
+#define AS3722_SD2_VSEL_MIN				0x01
+#define AS3722_SD2_VSEL_MAX				0x7F
+
+#define AS3722_SDn_CTRL(n)				BIT(n)
+
+#define AS3722_SD0_MODE_FAST				BIT(4)
+#define AS3722_SD1_MODE_FAST				BIT(4)
+#define AS3722_SD2_MODE_FAST				BIT(2)
+#define AS3722_SD3_MODE_FAST				BIT(6)
+#define AS3722_SD4_MODE_FAST				BIT(2)
+#define AS3722_SD5_MODE_FAST				BIT(2)
+#define AS3722_SD6_MODE_FAST				BIT(4)
+
+#define AS3722_POWER_OFF				BIT(1)
+
+#define AS3722_INTERRUPT_MASK1_LID			BIT(0)
+#define AS3722_INTERRUPT_MASK1_ACOK			BIT(1)
+#define AS3722_INTERRUPT_MASK1_ENABLE1			BIT(2)
+#define AS3722_INTERRUPT_MASK1_OCURR_ALARM_SD0		BIT(3)
+#define AS3722_INTERRUPT_MASK1_ONKEY_LONG		BIT(4)
+#define AS3722_INTERRUPT_MASK1_ONKEY			BIT(5)
+#define AS3722_INTERRUPT_MASK1_OVTMP			BIT(6)
+#define AS3722_INTERRUPT_MASK1_LOWBAT			BIT(7)
+
+#define AS3722_INTERRUPT_MASK2_SD0_LV			BIT(0)
+#define AS3722_INTERRUPT_MASK2_SD1_LV			BIT(1)
+#define AS3722_INTERRUPT_MASK2_SD2345_LV		BIT(2)
+#define AS3722_INTERRUPT_MASK2_PWM1_OV_PROT		BIT(3)
+#define AS3722_INTERRUPT_MASK2_PWM2_OV_PROT		BIT(4)
+#define AS3722_INTERRUPT_MASK2_ENABLE2			BIT(5)
+#define AS3722_INTERRUPT_MASK2_SD6_LV			BIT(6)
+#define AS3722_INTERRUPT_MASK2_RTC_REP			BIT(7)
+
+#define AS3722_INTERRUPT_MASK3_RTC_ALARM		BIT(0)
+#define AS3722_INTERRUPT_MASK3_GPIO1			BIT(1)
+#define AS3722_INTERRUPT_MASK3_GPIO2			BIT(2)
+#define AS3722_INTERRUPT_MASK3_GPIO3			BIT(3)
+#define AS3722_INTERRUPT_MASK3_GPIO4			BIT(4)
+#define AS3722_INTERRUPT_MASK3_GPIO5			BIT(5)
+#define AS3722_INTERRUPT_MASK3_WATCHDOG			BIT(6)
+#define AS3722_INTERRUPT_MASK3_ENABLE3			BIT(7)
+
+#define AS3722_INTERRUPT_MASK4_TEMP_SD0_SHUTDOWN	BIT(0)
+#define AS3722_INTERRUPT_MASK4_TEMP_SD1_SHUTDOWN	BIT(1)
+#define AS3722_INTERRUPT_MASK4_TEMP_SD6_SHUTDOWN	BIT(2)
+#define AS3722_INTERRUPT_MASK4_TEMP_SD0_ALARM		BIT(3)
+#define AS3722_INTERRUPT_MASK4_TEMP_SD1_ALARM		BIT(4)
+#define AS3722_INTERRUPT_MASK4_TEMP_SD6_ALARM		BIT(5)
+#define AS3722_INTERRUPT_MASK4_OCCUR_ALARM_SD6		BIT(6)
+#define AS3722_INTERRUPT_MASK4_ADC			BIT(7)
+
+#define AS3722_ADC1_INTERVAL_TIME			BIT(0)
+#define AS3722_ADC1_INT_MODE_ON				BIT(1)
+#define AS3722_ADC_BUF_ON				BIT(2)
+#define AS3722_ADC1_LOW_VOLTAGE_RANGE			BIT(5)
+#define AS3722_ADC1_INTEVAL_SCAN			BIT(6)
+#define AS3722_ADC1_INT_MASK				BIT(7)
+
+#define AS3722_ADC_MSB_VAL_MASK				0x7F
+#define AS3722_ADC_LSB_VAL_MASK				0x07
+
+#define AS3722_ADC0_CONV_START				BIT(7)
+#define AS3722_ADC0_CONV_NOTREADY			BIT(7)
+#define AS3722_ADC0_SOURCE_SELECT_MASK			0x1F
+
+#define AS3722_ADC1_CONV_START				BIT(7)
+#define AS3722_ADC1_CONV_NOTREADY			BIT(7)
+#define AS3722_ADC1_SOURCE_SELECT_MASK			0x1F
+
+/* GPIO modes */
+#define AS3722_GPIO_MODE_MASK				0x07
+#define AS3722_GPIO_MODE_INPUT				0x00
+#define AS3722_GPIO_MODE_OUTPUT_VDDH			0x01
+#define AS3722_GPIO_MODE_IO_OPEN_DRAIN			0x02
+#define AS3722_GPIO_MODE_ADC_IN				0x03
+#define AS3722_GPIO_MODE_INPUT_PULL_UP			0x04
+#define AS3722_GPIO_MODE_INPUT_PULL_DOWN		0x05
+#define AS3722_GPIO_MODE_IO_OPEN_DRAIN_PULL_UP		0x06
+#define AS3722_GPIO_MODE_OUTPUT_VDDL			0x07
+#define AS3722_GPIO_MODE_VAL(n)			((n) & AS3722_GPIO_MODE_MASK)
+
+#define AS3722_GPIO_INV					BIT(7)
+#define AS3722_GPIO_IOSF_MASK				0x78
+#define AS3722_GPIO_IOSF_VAL(n)				(((n) & 0xF) << 3)
+#define AS3722_GPIO_IOSF_NORMAL				AS3722_GPIO_IOSF_VAL(0)
+#define AS3722_GPIO_IOSF_INTERRUPT_OUT			AS3722_GPIO_IOSF_VAL(1)
+#define AS3722_GPIO_IOSF_VSUP_LOW_OUT			AS3722_GPIO_IOSF_VAL(2)
+#define AS3722_GPIO_IOSF_GPIO_INTERRUPT_IN		AS3722_GPIO_IOSF_VAL(3)
+#define AS3722_GPIO_IOSF_ISINK_PWM_IN			AS3722_GPIO_IOSF_VAL(4)
+#define AS3722_GPIO_IOSF_VOLTAGE_STBY			AS3722_GPIO_IOSF_VAL(5)
+#define AS3722_GPIO_IOSF_PWR_GOOD_OUT			AS3722_GPIO_IOSF_VAL(7)
+#define AS3722_GPIO_IOSF_Q32K_OUT			AS3722_GPIO_IOSF_VAL(8)
+#define AS3722_GPIO_IOSF_WATCHDOG_IN			AS3722_GPIO_IOSF_VAL(9)
+#define AS3722_GPIO_IOSF_SOFT_RESET_IN			AS3722_GPIO_IOSF_VAL(11)
+#define AS3722_GPIO_IOSF_PWM_OUT			AS3722_GPIO_IOSF_VAL(12)
+#define AS3722_GPIO_IOSF_VSUP_LOW_DEB_OUT		AS3722_GPIO_IOSF_VAL(13)
+#define AS3722_GPIO_IOSF_SD6_LOW_VOLT_LOW		AS3722_GPIO_IOSF_VAL(14)
+
+#define AS3722_GPIOn_SIGNAL(n)				BIT(n)
+#define AS3722_GPIOn_CONTROL_REG(n)		(AS3722_GPIO0_CONTROL_REG + n)
+#define AS3722_I2C_PULL_UP				BIT(4)
+#define AS3722_INT_PULL_UP				BIT(5)
+
+#define AS3722_RTC_REP_WAKEUP_EN			BIT(0)
+#define AS3722_RTC_ALARM_WAKEUP_EN			BIT(1)
+#define AS3722_RTC_ON					BIT(2)
+#define AS3722_RTC_IRQMODE				BIT(3)
+#define AS3722_RTC_CLK32K_OUT_EN			BIT(5)
+
+#define AS3722_WATCHDOG_TIMER_MAX			0x7F
+#define AS3722_WATCHDOG_ON				BIT(0)
+#define AS3722_WATCHDOG_SW_SIG				BIT(0)
+
+#define AS3722_EXT_CONTROL_ENABLE1			0x1
+#define AS3722_EXT_CONTROL_ENABLE2			0x2
+#define AS3722_EXT_CONTROL_ENABLE3			0x3
+
+/* Interrupt IDs */
+enum as3722_irq {
+	AS3722_IRQ_LID,
+	AS3722_IRQ_ACOK,
+	AS3722_IRQ_ENABLE1,
+	AS3722_IRQ_OCCUR_ALARM_SD0,
+	AS3722_IRQ_ONKEY_LONG_PRESS,
+	AS3722_IRQ_ONKEY,
+	AS3722_IRQ_OVTMP,
+	AS3722_IRQ_LOWBAT,
+	AS3722_IRQ_SD0_LV,
+	AS3722_IRQ_SD1_LV,
+	AS3722_IRQ_SD2_LV,
+	AS3722_IRQ_PWM1_OV_PROT,
+	AS3722_IRQ_PWM2_OV_PROT,
+	AS3722_IRQ_ENABLE2,
+	AS3722_IRQ_SD6_LV,
+	AS3722_IRQ_RTC_REP,
+	AS3722_IRQ_RTC_ALARM,
+	AS3722_IRQ_GPIO1,
+	AS3722_IRQ_GPIO2,
+	AS3722_IRQ_GPIO3,
+	AS3722_IRQ_GPIO4,
+	AS3722_IRQ_GPIO5,
+	AS3722_IRQ_WATCHDOG,
+	AS3722_IRQ_ENABLE3,
+	AS3722_IRQ_TEMP_SD0_SHUTDOWN,
+	AS3722_IRQ_TEMP_SD1_SHUTDOWN,
+	AS3722_IRQ_TEMP_SD2_SHUTDOWN,
+	AS3722_IRQ_TEMP_SD0_ALARM,
+	AS3722_IRQ_TEMP_SD1_ALARM,
+	AS3722_IRQ_TEMP_SD6_ALARM,
+	AS3722_IRQ_OCCUR_ALARM_SD6,
+	AS3722_IRQ_ADC,
+	AS3722_IRQ_MAX,
+};
+
+struct as3722 {
+	struct device *dev;
+	struct regmap *regmap;
+	int chip_irq;
+	unsigned long irq_flags;
+	bool en_intern_int_pullup;
+	bool en_intern_i2c_pullup;
+	struct regmap_irq_chip_data *irq_data;
+};
+
+static inline int as3722_read(struct as3722 *as3722, u32 reg, u32 *dest)
+{
+	return regmap_read(as3722->regmap, reg, dest);
+}
+
+static inline int as3722_write(struct as3722 *as3722, u32 reg, u32 value)
+{
+	return regmap_write(as3722->regmap, reg, value);
+}
+
+static inline int as3722_block_read(struct as3722 *as3722, u32 reg,
+		int count, u8 *buf)
+{
+	return regmap_bulk_read(as3722->regmap, reg, buf, count);
+}
+
+static inline int as3722_block_write(struct as3722 *as3722, u32 reg,
+		int count, u8 *data)
+{
+	return regmap_bulk_write(as3722->regmap, reg, data, count);
+}
+
+static inline int as3722_update_bits(struct as3722 *as3722, u32 reg,
+		u32 mask, u8 val)
+{
+	return regmap_update_bits(as3722->regmap, reg, mask, val);
+}
+
+static inline int as3722_irq_get_virq(struct as3722 *as3722, int irq)
+{
+	return regmap_irq_get_virq(as3722->irq_data, irq);
+}
+#endif /* __LINUX_MFD_AS3722_H__ */
-- 
cgit 


From df73de9b0d412915384396637bf67ef9208161e9 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Tue, 22 Oct 2013 16:46:25 +0800
Subject: mfd: syscon: Return -ENOSYS if CONFIG_MFD_SYSCON is not enabled

Some platforms may not define CONFIG_MFD_SYSCON (or haven't syscon),
it can fix build error for these platforms.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/syscon.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h
index b473577f36db..8789fa3c7fd9 100644
--- a/include/linux/mfd/syscon.h
+++ b/include/linux/mfd/syscon.h
@@ -17,10 +17,35 @@
 
 struct device_node;
 
+#ifdef CONFIG_MFD_SYSCON
 extern struct regmap *syscon_node_to_regmap(struct device_node *np);
 extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s);
 extern struct regmap *syscon_regmap_lookup_by_pdevname(const char *s);
 extern struct regmap *syscon_regmap_lookup_by_phandle(
 					struct device_node *np,
 					const char *property);
+#else
+static inline struct regmap *syscon_node_to_regmap(struct device_node *np)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct regmap *syscon_regmap_lookup_by_compatible(const char *s)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct regmap *syscon_regmap_lookup_by_pdevname(const char *s)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct regmap *syscon_regmap_lookup_by_phandle(
+					struct device_node *np,
+					const char *property)
+{
+	return ERR_PTR(-ENOSYS);
+}
+#endif
+
 #endif /* __LINUX_MFD_SYSCON_H__ */
-- 
cgit 


From 4b3db708b114fc35ff1e0cd28a2bfb1490dbb5d3 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Mon, 21 Oct 2013 14:29:25 -0700
Subject: ACPI, x86: Extended error log driver for x86 platform

This H/W error log driver (a.k.a eMCA driver) is implemented based on
http://www.intel.com/content/www/us/en/architecture-and-technology/enhanced-mca-logging-xeon-paper.html

After errors are captured, more detailed platform specific information
can be got via this new enhanced H/W error log driver. Most notably we
can track memory errors back to the DIMM slot silk screen label.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/include/asm/mce.h |   1 +
 drivers/acpi/Kconfig       |  19 +++
 drivers/acpi/Makefile      |   2 +
 drivers/acpi/acpi_extlog.c | 327 +++++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/bus.c         |   3 +-
 include/linux/acpi.h       |   1 +
 6 files changed, 352 insertions(+), 1 deletion(-)
 create mode 100644 drivers/acpi/acpi_extlog.c

(limited to 'include')

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index cbe6b9e404ce..c696a8687567 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -16,6 +16,7 @@
 #define MCG_EXT_CNT_SHIFT	16
 #define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
 #define MCG_SER_P		(1ULL<<24)   /* MCA recovery/new status bits */
+#define MCG_ELOG_P		(1ULL<<26)   /* Extended error log supported */
 
 /* MCG_STATUS register defines */
 #define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 6efe2ac6902f..252f0e818a49 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -372,4 +372,23 @@ config ACPI_BGRT
 
 source "drivers/acpi/apei/Kconfig"
 
+config ACPI_EXTLOG
+	tristate "Extended Error Log support"
+	depends on X86_MCE && ACPI_APEI
+	default n
+	help
+	  Certain usages such as Predictive Failure Analysis (PFA) require
+	  more information about the error than what can be described in
+	  processor machine check banks. Most server processors log
+	  additional information about the error in processor uncore
+	  registers. Since the addresses and layout of these registers vary
+	  widely from one processor to another, system software cannot
+	  readily make use of them. To complicate matters further, some of
+	  the additional error information cannot be constructed without
+	  detailed knowledge about platform topology.
+
+	  Enhanced MCA Logging allows firmware to provide additional error
+	  information to system software, synchronous with MCE or CMCI. This
+	  driver adds support for that functionality.
+
 endif	# ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index cdaf68b58b00..bce34afadcd0 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -82,3 +82,5 @@ processor-$(CONFIG_CPU_FREQ)	+= processor_perflib.o
 obj-$(CONFIG_ACPI_PROCESSOR_AGGREGATOR) += acpi_pad.o
 
 obj-$(CONFIG_ACPI_APEI)		+= apei/
+
+obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
new file mode 100644
index 000000000000..a6869e110ce5
--- /dev/null
+++ b/drivers/acpi/acpi_extlog.c
@@ -0,0 +1,327 @@
+/*
+ * Extended Error Log driver
+ *
+ * Copyright (C) 2013 Intel Corp.
+ * Author: Chen, Gong <gong.chen@intel.com>
+ *
+ * This file is licensed under GPLv2.
+ */
+
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <acpi/acpi_bus.h>
+#include <linux/cper.h>
+#include <linux/ratelimit.h>
+#include <asm/cpu.h>
+#include <asm/mce.h>
+
+#include "apei/apei-internal.h"
+
+#define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
+
+#define EXTLOG_DSM_REV		0x0
+#define	EXTLOG_FN_QUERY		0x0
+#define	EXTLOG_FN_ADDR		0x1
+
+#define FLAG_OS_OPTIN		BIT(0)
+#define EXTLOG_QUERY_L1_EXIST	BIT(1)
+#define ELOG_ENTRY_VALID	(1ULL<<63)
+#define ELOG_ENTRY_LEN		0x1000
+
+#define EMCA_BUG \
+	"Can not request iomem region <0x%016llx-0x%016llx> - eMCA disabled\n"
+
+struct extlog_l1_head {
+	u32 ver;	/* Header Version */
+	u32 hdr_len;	/* Header Length */
+	u64 total_len;	/* entire L1 Directory length including this header */
+	u64 elog_base;	/* MCA Error Log Directory base address */
+	u64 elog_len;	/* MCA Error Log Directory length */
+	u32 flags;	/* bit 0 - OS/VMM Opt-in */
+	u8  rev0[12];
+	u32 entries;	/* Valid L1 Directory entries per logical processor */
+	u8  rev1[12];
+};
+
+static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295";
+
+/* L1 table related physical address */
+static u64 elog_base;
+static size_t elog_size;
+static u64 l1_dirbase;
+static size_t l1_size;
+
+/* L1 table related virtual address */
+static void __iomem *extlog_l1_addr;
+static void __iomem *elog_addr;
+
+static void *elog_buf;
+
+static u64 *l1_entry_base;
+static u32 l1_percpu_entry;
+
+#define ELOG_IDX(cpu, bank) \
+	(cpu_physical_id(cpu) * l1_percpu_entry + (bank))
+
+#define ELOG_ENTRY_DATA(idx) \
+	(*(l1_entry_base + (idx)))
+
+#define ELOG_ENTRY_ADDR(phyaddr) \
+	(phyaddr - elog_base + (u8 *)elog_addr)
+
+static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank)
+{
+	int idx;
+	u64 data;
+	struct acpi_generic_status *estatus;
+
+	WARN_ON(cpu < 0);
+	idx = ELOG_IDX(cpu, bank);
+	data = ELOG_ENTRY_DATA(idx);
+	if ((data & ELOG_ENTRY_VALID) == 0)
+		return NULL;
+
+	data &= EXT_ELOG_ENTRY_MASK;
+	estatus = (struct acpi_generic_status *)ELOG_ENTRY_ADDR(data);
+
+	/* if no valid data in elog entry, just return */
+	if (estatus->block_status == 0)
+		return NULL;
+
+	return estatus;
+}
+
+static void __print_extlog_rcd(const char *pfx,
+			       struct acpi_generic_status *estatus, int cpu)
+{
+	static atomic_t seqno;
+	unsigned int curr_seqno;
+	char pfx_seq[64];
+
+	if (!pfx) {
+		if (estatus->error_severity <= CPER_SEV_CORRECTED)
+			pfx = KERN_INFO;
+		else
+			pfx = KERN_ERR;
+	}
+	curr_seqno = atomic_inc_return(&seqno);
+	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}", pfx, curr_seqno);
+	printk("%s""Hardware error detected on CPU%d\n", pfx_seq, cpu);
+	cper_estatus_print(pfx_seq, estatus);
+}
+
+static int print_extlog_rcd(const char *pfx,
+			    struct acpi_generic_status *estatus, int cpu)
+{
+	/* Not more than 2 messages every 5 seconds */
+	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
+	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
+	struct ratelimit_state *ratelimit;
+
+	if (estatus->error_severity == CPER_SEV_CORRECTED ||
+	    (estatus->error_severity == CPER_SEV_INFORMATIONAL))
+		ratelimit = &ratelimit_corrected;
+	else
+		ratelimit = &ratelimit_uncorrected;
+	if (__ratelimit(ratelimit)) {
+		__print_extlog_rcd(pfx, estatus, cpu);
+		return 0;
+	}
+
+	return 1;
+}
+
+static int extlog_print(struct notifier_block *nb, unsigned long val,
+			void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	int	bank = mce->bank;
+	int	cpu = mce->extcpu;
+	struct acpi_generic_status *estatus;
+	int rc;
+
+	estatus = extlog_elog_entry_check(cpu, bank);
+	if (estatus == NULL)
+		return NOTIFY_DONE;
+
+	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
+	/* clear record status to enable BIOS to update it again */
+	estatus->block_status = 0;
+
+	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
+
+	return NOTIFY_DONE;
+}
+
+static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret)
+{
+	struct acpi_buffer buf = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct acpi_object_list input;
+	union acpi_object params[4], *obj;
+	u8 uuid[16];
+	int i;
+
+	acpi_str_to_uuid(extlog_dsm_uuid, uuid);
+	input.count = 4;
+	input.pointer = params;
+	params[0].type = ACPI_TYPE_BUFFER;
+	params[0].buffer.length = 16;
+	params[0].buffer.pointer = uuid;
+	params[1].type = ACPI_TYPE_INTEGER;
+	params[1].integer.value = rev;
+	params[2].type = ACPI_TYPE_INTEGER;
+	params[2].integer.value = func;
+	params[3].type = ACPI_TYPE_PACKAGE;
+	params[3].package.count = 0;
+	params[3].package.elements = NULL;
+
+	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DSM", &input, &buf)))
+		return -1;
+
+	*ret = 0;
+	obj = (union acpi_object *)buf.pointer;
+	if (obj->type == ACPI_TYPE_INTEGER) {
+		*ret = obj->integer.value;
+	} else if (obj->type == ACPI_TYPE_BUFFER) {
+		if (obj->buffer.length <= 8) {
+			for (i = 0; i < obj->buffer.length; i++)
+				*ret |= (obj->buffer.pointer[i] << (i * 8));
+		}
+	}
+	kfree(buf.pointer);
+
+	return 0;
+}
+
+static bool extlog_get_l1addr(void)
+{
+	acpi_handle handle;
+	u64 ret;
+
+	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
+		return false;
+
+	if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_QUERY, &ret) ||
+	    !(ret & EXTLOG_QUERY_L1_EXIST))
+		return false;
+
+	if (extlog_get_dsm(handle, EXTLOG_DSM_REV, EXTLOG_FN_ADDR, &ret))
+		return false;
+
+	l1_dirbase = ret;
+	/* Spec says L1 directory must be 4K aligned, bail out if it isn't */
+	if (l1_dirbase & ((1 << 12) - 1)) {
+		pr_warn(FW_BUG "L1 Directory is invalid at physical %llx\n",
+			l1_dirbase);
+		return false;
+	}
+
+	return true;
+}
+static struct notifier_block extlog_mce_dec = {
+	.notifier_call	= extlog_print,
+};
+
+static int __init extlog_init(void)
+{
+	struct extlog_l1_head *l1_head;
+	void __iomem *extlog_l1_hdr;
+	size_t l1_hdr_size;
+	struct resource *r;
+	u64 cap;
+	int rc;
+
+	rc = -ENODEV;
+
+	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	if (!(cap & MCG_ELOG_P))
+		return rc;
+
+	if (!extlog_get_l1addr())
+		return rc;
+
+	rc = -EINVAL;
+	/* get L1 header to fetch necessary information */
+	l1_hdr_size = sizeof(struct extlog_l1_head);
+	r = request_mem_region(l1_dirbase, l1_hdr_size, "L1 DIR HDR");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)l1_dirbase,
+			(unsigned long long)l1_dirbase + l1_hdr_size);
+		goto err;
+	}
+
+	extlog_l1_hdr = acpi_os_map_memory(l1_dirbase, l1_hdr_size);
+	l1_head = (struct extlog_l1_head *)extlog_l1_hdr;
+	l1_size = l1_head->total_len;
+	l1_percpu_entry = l1_head->entries;
+	elog_base = l1_head->elog_base;
+	elog_size = l1_head->elog_len;
+	acpi_os_unmap_memory(extlog_l1_hdr, l1_hdr_size);
+	release_mem_region(l1_dirbase, l1_hdr_size);
+
+	/* remap L1 header again based on completed information */
+	r = request_mem_region(l1_dirbase, l1_size, "L1 Table");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)l1_dirbase,
+			(unsigned long long)l1_dirbase + l1_size);
+		goto err;
+	}
+	extlog_l1_addr = acpi_os_map_memory(l1_dirbase, l1_size);
+	l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size);
+
+	/* remap elog table */
+	r = request_mem_region(elog_base, elog_size, "Elog Table");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)elog_base,
+			(unsigned long long)elog_base + elog_size);
+		goto err_release_l1_dir;
+	}
+	elog_addr = acpi_os_map_memory(elog_base, elog_size);
+
+	rc = -ENOMEM;
+	/* allocate buffer to save elog record */
+	elog_buf = kmalloc(ELOG_ENTRY_LEN, GFP_KERNEL);
+	if (elog_buf == NULL)
+		goto err_release_elog;
+
+	mce_register_decode_chain(&extlog_mce_dec);
+	/* enable OS to be involved to take over management from BIOS */
+	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
+
+	return 0;
+
+err_release_elog:
+	if (elog_addr)
+		acpi_os_unmap_memory(elog_addr, elog_size);
+	release_mem_region(elog_base, elog_size);
+err_release_l1_dir:
+	if (extlog_l1_addr)
+		acpi_os_unmap_memory(extlog_l1_addr, l1_size);
+	release_mem_region(l1_dirbase, l1_size);
+err:
+	pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n");
+	return rc;
+}
+
+static void __exit extlog_exit(void)
+{
+	mce_unregister_decode_chain(&extlog_mce_dec);
+	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
+	if (extlog_l1_addr)
+		acpi_os_unmap_memory(extlog_l1_addr, l1_size);
+	if (elog_addr)
+		acpi_os_unmap_memory(elog_addr, elog_size);
+	release_mem_region(elog_base, elog_size);
+	release_mem_region(l1_dirbase, l1_size);
+	kfree(elog_buf);
+}
+
+module_init(extlog_init);
+module_exit(extlog_exit);
+
+MODULE_AUTHOR("Chen, Gong <gong.chen@intel.com>");
+MODULE_DESCRIPTION("Extended MCA Error Log Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index b587ec8257b2..e1bd9a181117 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -174,7 +174,7 @@ static void acpi_print_osc_error(acpi_handle handle,
 	printk("\n");
 }
 
-static acpi_status acpi_str_to_uuid(char *str, u8 *uuid)
+acpi_status acpi_str_to_uuid(char *str, u8 *uuid)
 {
 	int i;
 	static int opc_map_to_uuid[16] = {6, 4, 2, 0, 11, 9, 16, 14, 19, 21,
@@ -195,6 +195,7 @@ static acpi_status acpi_str_to_uuid(char *str, u8 *uuid)
 	}
 	return AE_OK;
 }
+EXPORT_SYMBOL_GPL(acpi_str_to_uuid);
 
 acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context)
 {
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a5db4aeefa36..c30bac8503bc 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -311,6 +311,7 @@ struct acpi_osc_context {
 #define OSC_INVALID_REVISION_ERROR	8
 #define OSC_CAPABILITIES_MASK_ERROR	16
 
+acpi_status acpi_str_to_uuid(char *str, u8 *uuid);
 acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 
 /* platform-wide _OSC bits */
-- 
cgit 


From dd6dad4288cb93e79bd7abfa6c6a338c47454d1a Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 18 Oct 2013 14:29:25 -0700
Subject: DMI: Parse memory device (type 17) in SMBIOS

This patch adds a new interface to decode memory device (type 17)
to help error reporting on DIMMs.

Original-author: Tony Luck <tony.luck@intel.com>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/ia64/kernel/setup.c    |  1 +
 arch/x86/kernel/setup.c     |  1 +
 drivers/firmware/dmi_scan.c | 60 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dmi.h         |  5 ++++
 4 files changed, 67 insertions(+)

(limited to 'include')

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 4fc2e9569bb2..d86669bcdfb2 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1063,6 +1063,7 @@ check_bugs (void)
 static int __init run_dmi_scan(void)
 {
 	dmi_scan_machine();
+	dmi_memdev_walk();
 	dmi_set_dump_stack_arch_desc();
 	return 0;
 }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f0de6294b955..918d489fa53d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p)
 		efi_init();
 
 	dmi_scan_machine();
+	dmi_memdev_walk();
 	dmi_set_dump_stack_arch_desc();
 
 	/*
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index fa0affb699b4..59579a744d58 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -25,6 +25,13 @@ static int dmi_initialized;
 /* DMI system identification string used during boot */
 static char dmi_ids_string[128] __initdata;
 
+static struct dmi_memdev_info {
+	const char *device;
+	const char *bank;
+	u16 handle;
+} *dmi_memdev;
+static int dmi_memdev_nr;
+
 static const char * __init dmi_string_nosave(const struct dmi_header *dm, u8 s)
 {
 	const u8 *bp = ((u8 *) dm) + dm->length;
@@ -322,6 +329,42 @@ static void __init dmi_save_extended_devices(const struct dmi_header *dm)
 	dmi_save_one_device(*d & 0x7f, dmi_string_nosave(dm, *(d - 1)));
 }
 
+static void __init count_mem_devices(const struct dmi_header *dm, void *v)
+{
+	if (dm->type != DMI_ENTRY_MEM_DEVICE)
+		return;
+	dmi_memdev_nr++;
+}
+
+static void __init save_mem_devices(const struct dmi_header *dm, void *v)
+{
+	const char *d = (const char *)dm;
+	static int nr;
+
+	if (dm->type != DMI_ENTRY_MEM_DEVICE)
+		return;
+	if (nr >= dmi_memdev_nr) {
+		pr_warn(FW_BUG "Too many DIMM entries in SMBIOS table\n");
+		return;
+	}
+	dmi_memdev[nr].handle = dm->handle;
+	dmi_memdev[nr].device = dmi_string(dm, d[0x10]);
+	dmi_memdev[nr].bank = dmi_string(dm, d[0x11]);
+	nr++;
+}
+
+void __init dmi_memdev_walk(void)
+{
+	if (!dmi_available)
+		return;
+
+	if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) {
+		dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr);
+		if (dmi_memdev)
+			dmi_walk_early(save_mem_devices);
+	}
+}
+
 /*
  *	Process a DMI table entry. Right now all we care about are the BIOS
  *	and machine entries. For 2.5 we should pull the smbus controller info
@@ -815,3 +858,20 @@ bool dmi_match(enum dmi_field f, const char *str)
 	return !strcmp(info, str);
 }
 EXPORT_SYMBOL_GPL(dmi_match);
+
+void dmi_memdev_name(u16 handle, const char **bank, const char **device)
+{
+	int n;
+
+	if (dmi_memdev == NULL)
+		return;
+
+	for (n = 0; n < dmi_memdev_nr; n++) {
+		if (handle == dmi_memdev[n].handle) {
+			*bank = dmi_memdev[n].bank;
+			*device = dmi_memdev[n].device;
+			break;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(dmi_memdev_name);
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index b6eb7a05d58e..f820f0a336c9 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -99,6 +99,7 @@ extern const char * dmi_get_system_info(int field);
 extern const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from);
 extern void dmi_scan_machine(void);
+extern void dmi_memdev_walk(void);
 extern void dmi_set_dump_stack_arch_desc(void);
 extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
 extern int dmi_name_in_vendors(const char *str);
@@ -107,6 +108,7 @@ extern int dmi_available;
 extern int dmi_walk(void (*decode)(const struct dmi_header *, void *),
 	void *private_data);
 extern bool dmi_match(enum dmi_field f, const char *str);
+extern void dmi_memdev_name(u16 handle, const char **bank, const char **device);
 
 #else
 
@@ -115,6 +117,7 @@ static inline const char * dmi_get_system_info(int field) { return NULL; }
 static inline const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from) { return NULL; }
 static inline void dmi_scan_machine(void) { return; }
+static inline void dmi_memdev_walk(void) { }
 static inline void dmi_set_dump_stack_arch_desc(void) { }
 static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
 {
@@ -133,6 +136,8 @@ static inline int dmi_walk(void (*decode)(const struct dmi_header *, void *),
 	void *private_data) { return -1; }
 static inline bool dmi_match(enum dmi_field f, const char *str)
 	{ return false; }
+static inline void dmi_memdev_name(u16 handle, const char **bank,
+		const char **device) { }
 static inline const struct dmi_system_id *
 	dmi_first_match(const struct dmi_system_id *list) { return NULL; }
 
-- 
cgit 


From 147de14772ed897727dba7353916b02d1e0f17f4 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 18 Oct 2013 14:30:13 -0700
Subject: ACPI, APEI, CPER: Add UEFI 2.4 support for memory error

In latest UEFI spec(by now it is 2.4) memory error definition
for CPER (UEFI 2.4 Appendix N Common Platform Error Record)
adds some new fields. These fields help people to locate
memory error to an actual DIMM location.

Original-author: Tony Luck <tony.luck@intel.com>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
 drivers/acpi/apei/cper.c              |  7 ++++---
 drivers/acpi/apei/ghes.c              |  4 ++--
 drivers/edac/ghes_edac.c              |  5 ++---
 include/linux/cper.h                  | 11 +++++++++--
 5 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index cd8b166a1735..de8b60a53f69 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
 	struct mce m;
 
 	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits &
-				CPER_MEM_VALID_PHYSICAL_ADDRESS))
+	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);
diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
index eb5f6d6d7dbc..946ef520186f 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -8,7 +8,7 @@
  * various tables, such as ERST, BERT and HEST etc.
  *
  * For more information about CPER, please refer to Appendix N of UEFI
- * Specification version 2.3.
+ * Specification version 2.4.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version
@@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = {
 	"memory sparing",
 	"scrub corrected error",
 	"scrub uncorrected error",
+	"physical memory map-out event",
 };
 
 static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
 {
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)
+	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
-	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
+	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
 		printk("%s""physical_address_mask: 0x%016llx\n",
 		       pfx, mem->physical_addr_mask);
 	if (mem->validation_bits & CPER_MEM_VALID_NODE)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0db6e4ff6501..a30bc313787b 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 
 	if (sec_sev == GHES_SEV_CORRECTED &&
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
+	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		if (pfn_valid(pfn))
 			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
@@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 	}
 	if (sev == GHES_SEV_RECOVERABLE &&
 	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		pfn = mem_err->physical_addr >> PAGE_SHIFT;
 		memory_failure_queue(pfn, 0, 0);
 	}
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index bb534670ec02..0ad797b9db65 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 	}
 
 	/* Error address */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
 		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
 		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
 	}
 
 	/* Error grain */
-	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
 		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
-	}
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 09ebe2113641..2fc0ec3d89cc 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -218,8 +218,8 @@ enum {
 #define CPER_PROC_VALID_IP			0x1000
 
 #define CPER_MEM_VALID_ERROR_STATUS		0x0001
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS		0x0002
-#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK	0x0004
+#define CPER_MEM_VALID_PA			0x0002
+#define CPER_MEM_VALID_PA_MASK			0x0004
 #define CPER_MEM_VALID_NODE			0x0008
 #define CPER_MEM_VALID_CARD			0x0010
 #define CPER_MEM_VALID_MODULE			0x0020
@@ -232,6 +232,9 @@ enum {
 #define CPER_MEM_VALID_RESPONDER_ID		0x1000
 #define CPER_MEM_VALID_TARGET_ID		0x2000
 #define CPER_MEM_VALID_ERROR_TYPE		0x4000
+#define CPER_MEM_VALID_RANK_NUMBER		0x8000
+#define CPER_MEM_VALID_CARD_HANDLE		0x10000
+#define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
@@ -347,6 +350,10 @@ struct cper_sec_mem_err {
 	__u64	responder_id;
 	__u64	target_id;
 	__u8	error_type;
+	__u8	reserved;
+	__u16	rank;
+	__u16	mem_array_handle;	/* card handle in UEFI 2.4 */
+	__u16	mem_dev_handle;		/* module handle in UEFI 2.4 */
 };
 
 struct cper_sec_pcie {
-- 
cgit 


From 56507694de3453076d73e0e9813349586ee67e59 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 18 Oct 2013 14:30:38 -0700
Subject: EDAC, GHES: Update ghes error record info

In latest UEFI spec(by now it's 2.4) there are some new
fields for memory error reporting. Add these new fields for
ghes_edac interface.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Cc: Mauro Carvalho Chehab <m.chehab@samsung.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/edac/ghes_edac.c | 11 +++++++++++
 include/linux/edac.h     |  2 +-
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 0ad797b9db65..d5a98a45c062 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -314,6 +314,8 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 		p += sprintf(p, "card:%d ", mem_err->card);
 	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE)
 		p += sprintf(p, "module:%d ", mem_err->module);
+	if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
+		p += sprintf(p, "rank:%d ", mem_err->rank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
 		p += sprintf(p, "bank:%d ", mem_err->bank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_ROW)
@@ -322,6 +324,15 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
 		p += sprintf(p, "col:%d ", mem_err->column);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
 		p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);
+	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
+		const char *bank = NULL, *device = NULL;
+		dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device);
+		if (bank != NULL && device != NULL)
+			p += sprintf(p, "DIMM location:%s %s ", bank, device);
+		else
+			p += sprintf(p, "DIMM DMI handle: 0x%.4x ",
+				     mem_err->mem_dev_handle);
+	}
 	if (p > e->location)
 		*(p - 1) = '\0';
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 5c6d7fbaf89e..dbdffe8d4469 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -51,7 +51,7 @@ static inline void opstate_init(void)
 #define EDAC_MC_LABEL_LEN	31
 
 /* Maximum size of the location string */
-#define LOCATION_SIZE 80
+#define LOCATION_SIZE 256
 
 /* Defines the maximum number of labels that can be reported */
 #define EDAC_MAX_LABELS		8
-- 
cgit 


From 35b87f6c135b7ded8ab1a44e46d792f7688f3608 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <christoph.paasch@uclouvain.be>
Date: Wed, 23 Oct 2013 12:49:21 -0700
Subject: net: Dereference pointer-value of sk_prot->memory_pressure

2e685cad57 (tcp_memcontrol: Kill struct tcp_memcontrol) falsly modified
the access to memory_pressure of sk->sk_prot->memory_pressure. The patch
did modify the memory_pressure-field of struct cg_proto, but not the one
of struct proto.

So, the access to sk_prot->memory_pressure should not be changed.

Acked-by: Eric Dumazet <edumazet@google.com>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index c93542f92420..e3a18ff0c38b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1137,7 +1137,7 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
 		return !!sk->sk_cgrp->memory_pressure;
 
-	return !!sk->sk_prot->memory_pressure;
+	return !!*sk->sk_prot->memory_pressure;
 }
 
 static inline void sk_leave_memory_pressure(struct sock *sk)
-- 
cgit 


From b1190570b451fb9fd77be8c115fcdb418c5108a5 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 23 Oct 2013 11:06:56 +0200
Subject: ipv6: split inet6_hash_frag for netfilter and initialize secrets with
 net_get_random_once

Defer the fragmentation hash secret initialization for IPv6 like the
previous patch did for IPv4.

Because the netfilter logic reuses the hash secret we have to split it
first. Thus introduce a new nf_hash_frag function which takes care to
seed the hash secret.

Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h                      |  2 --
 net/ipv6/netfilter/nf_conntrack_reasm.c | 16 ++++++++++++++--
 net/ipv6/reassembly.c                   | 12 ++++++------
 3 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a35055f4f8da..dd96638ab8ff 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -805,8 +805,6 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf);
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 		  struct group_filter __user *optval, int __user *optlen);
-unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-			     const struct in6_addr *daddr, u32 rnd);
 
 #ifdef CONFIG_PROC_FS
 int ac6_proc_init(struct net *net);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index dffdc1a389c5..4a258263d8ec 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -144,12 +144,24 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
 }
 
+static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
+				 const struct in6_addr *daddr)
+{
+	u32 c;
+
+	net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
+	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
+			 (__force u32)id, nf_frags.rnd);
+	return c & (INETFRAGS_HASHSZ - 1);
+}
+
+
 static unsigned int nf_hashfn(struct inet_frag_queue *q)
 {
 	const struct frag_queue *nq;
 
 	nq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd);
+	return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
 }
 
 static void nf_skb_free(struct sk_buff *skb)
@@ -185,7 +197,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.ecn = ecn;
 
 	read_lock_bh(&nf_frags.lock);
-	hash = inet6_hash_frag(id, src, dst, nf_frags.rnd);
+	hash = nf_hash_frag(id, src, dst);
 
 	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
 	local_bh_enable();
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1aeb473b2cc6..cc85a9ba5010 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -82,24 +82,24 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
  * callers should be careful not to use the hash value outside the ipfrag_lock
  * as doing so could race with ipfrag_hash_rnd being recalculated.
  */
-unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
-			     const struct in6_addr *daddr, u32 rnd)
+static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
+				    const struct in6_addr *daddr)
 {
 	u32 c;
 
+	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
 	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			 (__force u32)id, rnd);
+			 (__force u32)id, ip6_frags.rnd);
 
 	return c & (INETFRAGS_HASHSZ - 1);
 }
-EXPORT_SYMBOL_GPL(inet6_hash_frag);
 
 static unsigned int ip6_hashfn(struct inet_frag_queue *q)
 {
 	struct frag_queue *fq;
 
 	fq = container_of(q, struct frag_queue, q);
-	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr, ip6_frags.rnd);
+	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
 }
 
 bool ip6_frag_match(struct inet_frag_queue *q, void *a)
@@ -193,7 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.ecn = ecn;
 
 	read_lock(&ip6_frags.lock);
-	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
+	hash = inet6_hash_frag(id, src, dst);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
 	if (IS_ERR_OR_NULL(q)) {
-- 
cgit 


From 7088ad74e6e710d0c80ea2cead9500f47a2a5d58 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 23 Oct 2013 11:06:57 +0200
Subject: inet: remove old fragmentation hash initializing

All fragmentation hash secrets now get initialized by their
corresponding hash function with net_get_random_once. Thus we can
eliminate the initial seeding.

Also provide a comment that hash secret seeding happens at the first
call to the corresponding hashing function.

Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h  | 4 ++++
 net/ipv4/inet_fragment.c | 3 ---
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index bfcbc0017950..6f59de98dabd 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -64,6 +64,10 @@ struct inet_frags {
 	rwlock_t		lock ____cacheline_aligned_in_smp;
 	int			secret_interval;
 	struct timer_list	secret_timer;
+
+	/* The first call to hashfn is responsible to initialize
+	 * rnd. This is best done with net_get_random_once.
+	 */
 	u32			rnd;
 	int			qsize;
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c5313a9c019b..bb075fc9a14f 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -93,9 +93,6 @@ void inet_frags_init(struct inet_frags *f)
 	}
 	rwlock_init(&f->lock);
 
-	f->rnd = (u32) ((totalram_pages ^ (totalram_pages >> 7)) ^
-				   (jiffies ^ (jiffies >> 6)));
-
 	setup_timer(&f->secret_timer, inet_frag_secret_rebuild,
 			(unsigned long)f);
 	f->secret_timer.expires = jiffies + f->secret_interval;
-- 
cgit 


From b3fde035714b83ef7ddbbd5a520a2150d990349b Mon Sep 17 00:00:00 2001
From: Thomas Glanzmann <thomas@glanzmann.de>
Date: Mon, 7 Oct 2013 23:13:02 +0200
Subject: target: Export symbol core_tpg_check_initiator_node_acl

Export symbol core_tpg_check_initiator_node_acl and move prototype from the
private drivers/target/target_core_internal.h to the public
include/target/target_core_fabric.h

Signed-off-by: Thomas Glanzmann <thomas@glanzmann.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_internal.h | 2 --
 drivers/target/target_core_tpg.c      | 1 +
 include/target/target_core_fabric.h   | 2 ++
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 579128abe3f5..889af4df8562 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -75,8 +75,6 @@ extern struct se_device *g_lun0_dev;
 
 struct se_node_acl *__core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
 		const char *);
-struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
-		unsigned char *);
 void	core_tpg_add_node_to_devs(struct se_node_acl *, struct se_portal_group *);
 void	core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *);
 struct se_lun *core_tpg_pre_addlun(struct se_portal_group *, u32);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index b9a6ec0aa5fe..ec992208dc55 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -116,6 +116,7 @@ struct se_node_acl *core_tpg_get_initiator_node_acl(
 
 	return acl;
 }
+EXPORT_SYMBOL(core_tpg_get_initiator_node_acl);
 
 /*	core_tpg_add_node_to_devs():
  *
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 882b650e32be..4cf4fda404a3 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -137,6 +137,8 @@ void	transport_generic_request_failure(struct se_cmd *, sense_reason_t);
 void	__target_execute_cmd(struct se_cmd *);
 int	transport_lookup_tmr_lun(struct se_cmd *, u32);
 
+struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg,
+		unsigned char *);
 struct se_node_acl *core_tpg_check_initiator_node_acl(struct se_portal_group *,
 		unsigned char *);
 void	core_tpg_clear_object_luns(struct se_portal_group *);
-- 
cgit 


From 055032142c42d2821c4aa617915292d6a08d56fc Mon Sep 17 00:00:00 2001
From: Nicolin Chen <b42378@freescale.com>
Date: Wed, 23 Oct 2013 11:47:43 +0800
Subject: ALSA: Add SoC on-chip internal ram support for DMA buffer allocation

Now it's quite common that an SoC contains its on-chip internal RAM.
By using this RAM space for DMA buffer during audio playback/record,
we can shutdown the voltage for external RAM to save power.

So add new DEV type with iram malloc()/free() and accordingly modify
current default mmap() for the iram circumstance.

Signed-off-by: Nicolin Chen <b42378@freescale.com>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/memalloc.h |  1 +
 sound/core/memalloc.c    | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 sound/core/pcm_native.c  |  6 ++++++
 3 files changed, 59 insertions(+)

(limited to 'include')

diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index cf15b8213df7..510aec437f72 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -52,6 +52,7 @@ struct snd_dma_device {
 #else
 #define SNDRV_DMA_TYPE_DEV_SG	SNDRV_DMA_TYPE_DEV /* no SG-buf support */
 #endif
+#define SNDRV_DMA_TYPE_DEV_IRAM		4	/* generic device iram-buffer */
 
 /*
  * info for buffer allocation
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index bdf826f4fe0c..18c1d4759ccb 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <asm/uaccess.h>
 #include <linux/dma-mapping.h>
+#include <linux/genalloc.h>
 #include <linux/moduleparam.h>
 #include <linux/mutex.h>
 #include <sound/memalloc.h>
@@ -157,6 +158,46 @@ static void snd_free_dev_pages(struct device *dev, size_t size, void *ptr,
 	dec_snd_pages(pg);
 	dma_free_coherent(dev, PAGE_SIZE << pg, ptr, dma);
 }
+
+/**
+ * snd_malloc_dev_iram - allocate memory from on-chip internal ram
+ * @dmab: buffer allocation record to store the allocated data
+ * @size: number of bytes to allocate from the iram
+ *
+ * This function requires iram phandle provided via of_node
+ */
+void snd_malloc_dev_iram(struct snd_dma_buffer *dmab, size_t size)
+{
+	struct device *dev = dmab->dev.dev;
+	struct gen_pool *pool = NULL;
+
+	if (dev->of_node)
+		pool = of_get_named_gen_pool(dev->of_node, "iram", 0);
+
+	if (!pool)
+		return;
+
+	/* Assign the pool into private_data field */
+	dmab->private_data = pool;
+
+	dmab->area = (void *)gen_pool_alloc(pool, size);
+	if (!dmab->area)
+		return;
+
+	dmab->addr = gen_pool_virt_to_phys(pool, (unsigned long)dmab->area);
+}
+
+/**
+ * snd_free_dev_iram - free allocated specific memory from on-chip internal ram
+ * @dmab: buffer allocation record to store the allocated data
+ */
+void snd_free_dev_iram(struct snd_dma_buffer *dmab)
+{
+	struct gen_pool *pool = dmab->private_data;
+
+	if (pool && dmab->area)
+		gen_pool_free(pool, (unsigned long)dmab->area, dmab->bytes);
+}
 #endif /* CONFIG_HAS_DMA */
 
 /*
@@ -197,6 +238,14 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size,
 		dmab->addr = 0;
 		break;
 #ifdef CONFIG_HAS_DMA
+	case SNDRV_DMA_TYPE_DEV_IRAM:
+		snd_malloc_dev_iram(dmab, size);
+		if (dmab->area)
+			break;
+		/* Internal memory might have limited size and no enough space,
+		 * so if we fail to malloc, try to fetch memory traditionally.
+		 */
+		dmab->dev.type = SNDRV_DMA_TYPE_DEV;
 	case SNDRV_DMA_TYPE_DEV:
 		dmab->area = snd_malloc_dev_pages(device, size, &dmab->addr);
 		break;
@@ -269,6 +318,9 @@ void snd_dma_free_pages(struct snd_dma_buffer *dmab)
 		snd_free_pages(dmab->area, dmab->bytes);
 		break;
 #ifdef CONFIG_HAS_DMA
+	case SNDRV_DMA_TYPE_DEV_IRAM:
+		snd_free_dev_iram(dmab);
+		break;
 	case SNDRV_DMA_TYPE_DEV:
 		snd_free_dev_pages(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr);
 		break;
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index a68d4c6d702c..513f0954d92e 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3199,6 +3199,12 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream,
 			     struct vm_area_struct *area)
 {
 	area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	if (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV_IRAM) {
+		area->vm_page_prot = pgprot_writecombine(area->vm_page_prot);
+		return remap_pfn_range(area, area->vm_start,
+				substream->dma_buffer.addr >> PAGE_SHIFT,
+				area->vm_end - area->vm_start, area->vm_page_prot);
+	}
 #ifdef ARCH_HAS_DMA_MMAP_COHERENT
 	if (!substream->ops->page &&
 	    substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV)
-- 
cgit 


From 0c02c8007ea5554d028f99fd3e29fc201fdeeab3 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Thu, 19 Sep 2013 11:22:36 -0500
Subject: of/irq: Rename of_irq_map_* functions to of_irq_parse_*

The OF irq handling code has been overloading the term 'map' to refer to
both parsing the data in the device tree and mapping it to the internal
linux irq system. This is probably because the device tree does have the
concept of an 'interrupt-map' function for translating interrupt
references from one node to another, but 'map' is still confusing when
the primary purpose of some of the functions are to parse the DT data.

This patch renames all the of_irq_map_* functions to of_irq_parse_*
which makes it clear that there is a difference between the parsing
phase and the mapping phase. Kernel code can make use of just the
parsing or just the mapping support as needed by the subsystem.

The patch was generated mechanically with a handful of sed commands.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Michal Simek <monstr@monstr.eu>
Acked-by: Tony Lindgren <tony@atomide.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/arm/mach-integrator/pci_v3.c              |  4 ++--
 arch/microblaze/pci/pci-common.c               |  2 +-
 arch/mips/pci/fixup-lantiq.c                   |  2 +-
 arch/mips/pci/pci-rt3883.c                     |  2 +-
 arch/powerpc/kernel/pci-common.c               |  2 +-
 arch/powerpc/platforms/cell/celleb_scc_pciex.c |  2 +-
 arch/powerpc/platforms/cell/celleb_scc_sio.c   |  2 +-
 arch/powerpc/platforms/cell/spider-pic.c       |  2 +-
 arch/powerpc/platforms/cell/spu_manage.c       |  2 +-
 arch/powerpc/platforms/fsl_uli1575.c           |  2 +-
 arch/powerpc/platforms/powermac/pic.c          |  2 +-
 arch/powerpc/platforms/pseries/event_sources.c |  2 +-
 arch/powerpc/sysdev/mpic_msi.c                 |  2 +-
 arch/x86/kernel/devicetree.c                   |  2 +-
 drivers/of/address.c                           |  4 ++--
 drivers/of/irq.c                               | 28 +++++++++++++-------------
 drivers/of/of_pci_irq.c                        | 10 ++++-----
 drivers/pci/host/pci-mvebu.c                   |  2 +-
 include/linux/of_irq.h                         |  8 ++++----
 include/linux/of_pci.h                         |  2 +-
 20 files changed, 42 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index bef100527c42..0f496cc51f36 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -840,9 +840,9 @@ static int __init pci_v3_map_irq_dt(const struct pci_dev *dev, u8 slot, u8 pin)
 	struct of_irq oirq;
 	int ret;
 
-	ret = of_irq_map_pci(dev, &oirq);
+	ret = of_irq_parse_pci(dev, &oirq);
 	if (ret) {
-		dev_err(&dev->dev, "of_irq_map_pci() %d\n", ret);
+		dev_err(&dev->dev, "of_irq_parse_pci() %d\n", ret);
 		/* Proper return code 0 == NO_IRQ */
 		return 0;
 	}
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 1b93bf0892a0..4d5b1a9cd790 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -217,7 +217,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 	memset(&oirq, 0xff, sizeof(oirq));
 #endif
 	/* Try to get a mapping from the device-tree */
-	if (of_irq_map_pci(pci_dev, &oirq)) {
+	if (of_irq_parse_pci(pci_dev, &oirq)) {
 		u8 line, pin;
 
 		/* If that fails, lets fallback to what is in the config
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index 6c829df28dc7..2e8dbfedae53 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -28,7 +28,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	struct of_irq dev_irq;
 	int irq;
 
-	if (of_irq_map_pci(dev, &dev_irq)) {
+	if (of_irq_parse_pci(dev, &dev_irq)) {
 		dev_err(&dev->dev, "trying to map irq for unknown slot:%d pin:%d\n",
 			slot, pin);
 		return 0;
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 95c9d41382e7..cae92a05ee70 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -587,7 +587,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	int err;
 	int irq;
 
-	err = of_irq_map_pci(dev, &dev_irq);
+	err = of_irq_parse_pci(dev, &dev_irq);
 	if (err) {
 		pr_err("pci %s: unable to get irq map, err=%d\n",
 		       pci_name((struct pci_dev *) dev), err);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 905a24bb7acc..2f4185425ed5 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -237,7 +237,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
 	memset(&oirq, 0xff, sizeof(oirq));
 #endif
 	/* Try to get a mapping from the device-tree */
-	if (of_irq_map_pci(pci_dev, &oirq)) {
+	if (of_irq_parse_pci(pci_dev, &oirq)) {
 		u8 line, pin;
 
 		/* If that fails, lets fallback to what is in the config
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index 14be2bd358b8..40bc371096b7 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -507,7 +507,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
 	phb->ops = &scc_pciex_pci_ops;
 
 	/* internal interrupt handler */
-	if (of_irq_map_one(node, 1, &oirq)) {
+	if (of_irq_parse_one(node, 1, &oirq)) {
 		pr_err("PCIEXC:Failed to map irq\n");
 		goto error;
 	}
diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c
index 9c339ec646f5..96388b202f4e 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_sio.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c
@@ -53,7 +53,7 @@ static int __init txx9_serial_init(void)
 			if (!(txx9_serial_bitmap & (1<<i)))
 				continue;
 
-			if (of_irq_map_one(node, i, &irq))
+			if (of_irq_parse_one(node, i, &irq))
 				continue;
 			if (of_address_to_resource(node,
 				txx9_scc_tab[i].index, &res))
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 8e299447127e..b491f406560a 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -236,7 +236,7 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	 * tree in case the device-tree is ever fixed
 	 */
 	struct of_irq oirq;
-	if (of_irq_map_one(pic->host->of_node, 0, &oirq) == 0) {
+	if (of_irq_parse_one(pic->host->of_node, 0, &oirq) == 0) {
 		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
 					     oirq.size);
 		return virq;
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index 2bb6977c0a5a..e6cdb81a0959 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -182,7 +182,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 	int i;
 
 	for (i=0; i < 3; i++) {
-		ret = of_irq_map_one(np, i, &oirq);
+		ret = of_irq_parse_one(np, i, &oirq);
 		if (ret) {
 			pr_debug("spu_new: failed to get irq %d\n", i);
 			goto err;
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index 92ac9b52b32d..ac539c1cd808 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -333,7 +333,7 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 
 	laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8);
 	laddr[1] = laddr[2] = 0;
-	of_irq_map_raw(hosenode, &pin, 1, laddr, &oirq);
+	of_irq_parse_raw(hosenode, &pin, 1, laddr, &oirq);
 	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
 				     oirq.size);
 	dev->irq = virq;
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 31036b56670e..720663e29f47 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -393,7 +393,7 @@ static void __init pmac_pic_probe_oldstyle(void)
 #endif
 }
 
-int of_irq_map_oldworld(struct device_node *device, int index,
+int of_irq_parse_oldworld(struct device_node *device, int index,
 			struct of_irq *out_irq)
 {
 	const u32 *ints = NULL;
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 2605c310166a..850c18c457ad 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -55,7 +55,7 @@ void request_event_sources_irqs(struct device_node *np,
 	/* Else use normal interrupt tree parsing */
 	else {
 		/* First try to do a proper OF tree parsing */
-		for (index = 0; of_irq_map_one(np, index, &oirq) == 0;
+		for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
 		     index++) {
 			if (count > 15)
 				break;
diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c
index bbf342c88314..463e3a7c193c 100644
--- a/arch/powerpc/sysdev/mpic_msi.c
+++ b/arch/powerpc/sysdev/mpic_msi.c
@@ -63,7 +63,7 @@ static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
 		pr_debug("mpic: mapping hwirqs for %s\n", np->full_name);
 
 		index = 0;
-		while (of_irq_map_one(np, index++, &oirq) == 0) {
+		while (of_irq_parse_one(np, index++, &oirq) == 0) {
 			ops->xlate(mpic->irqhost, NULL, oirq.specifier,
 						oirq.size, &hwirq, &flags);
 			msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, hwirq);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 376dc7873447..3ac6398e5361 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -116,7 +116,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
 	if (!pin)
 		return 0;
 
-	ret = of_irq_map_pci(dev, &oirq);
+	ret = of_irq_parse_pci(dev, &oirq);
 	if (ret)
 		return ret;
 
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 71180b91bfbe..994f293baebf 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -532,12 +532,12 @@ static u64 __of_translate_address(struct device_node *dev,
 		pbus->count_cells(dev, &pna, &pns);
 		if (!OF_CHECK_COUNTS(pna, pns)) {
 			printk(KERN_ERR "prom_parse: Bad cell count for %s\n",
-			       dev->full_name);
+			       of_node_full_name(dev));
 			break;
 		}
 
 		pr_debug("OF: parent bus is %s (na=%d, ns=%d) on %s\n",
-		    pbus->name, pna, pns, parent->full_name);
+		    pbus->name, pna, pns, of_node_full_name(parent));
 
 		/* Apply bus translation */
 		if (of_translate_one(dev, bus, pbus, addr, na, ns, pna, rprop))
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 90068f914911..410aa2415f42 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -31,14 +31,14 @@
  * @dev: Device node of the device whose interrupt is to be mapped
  * @index: Index of the interrupt to map
  *
- * This function is a wrapper that chains of_irq_map_one() and
+ * This function is a wrapper that chains of_irq_parse_one() and
  * irq_create_of_mapping() to make things easier to callers
  */
 unsigned int irq_of_parse_and_map(struct device_node *dev, int index)
 {
 	struct of_irq oirq;
 
-	if (of_irq_map_one(dev, index, &oirq))
+	if (of_irq_parse_one(dev, index, &oirq))
 		return 0;
 
 	return irq_create_of_mapping(oirq.controller, oirq.specifier,
@@ -79,7 +79,7 @@ struct device_node *of_irq_find_parent(struct device_node *child)
 }
 
 /**
- * of_irq_map_raw - Low level interrupt tree parsing
+ * of_irq_parse_raw - Low level interrupt tree parsing
  * @parent:	the device interrupt parent
  * @intspec:	interrupt specifier ("interrupts" property of the device)
  * @ointsize:   size of the passed in interrupt specifier
@@ -93,7 +93,7 @@ struct device_node *of_irq_find_parent(struct device_node *child)
  * properties, for example when resolving PCI interrupts when no device
  * node exist for the parent.
  */
-int of_irq_map_raw(struct device_node *parent, const __be32 *intspec,
+int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 		   u32 ointsize, const __be32 *addr, struct of_irq *out_irq)
 {
 	struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
@@ -101,7 +101,7 @@ int of_irq_map_raw(struct device_node *parent, const __be32 *intspec,
 	u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
 	int imaplen, match, i;
 
-	pr_debug("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
+	pr_debug("of_irq_parse_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
 		 of_node_full_name(parent), be32_to_cpup(intspec),
 		 be32_to_cpup(intspec + 1), ointsize);
 
@@ -126,7 +126,7 @@ int of_irq_map_raw(struct device_node *parent, const __be32 *intspec,
 		goto fail;
 	}
 
-	pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", of_node_full_name(ipar), intsize);
+	pr_debug("of_irq_parse_raw: ipar=%s, size=%d\n", of_node_full_name(ipar), intsize);
 
 	if (ointsize != intsize)
 		return -EINVAL;
@@ -269,29 +269,29 @@ int of_irq_map_raw(struct device_node *parent, const __be32 *intspec,
 
 	return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(of_irq_map_raw);
+EXPORT_SYMBOL_GPL(of_irq_parse_raw);
 
 /**
- * of_irq_map_one - Resolve an interrupt for a device
+ * of_irq_parse_one - Resolve an interrupt for a device
  * @device: the device whose interrupt is to be resolved
  * @index: index of the interrupt to resolve
  * @out_irq: structure of_irq filled by this function
  *
  * This function resolves an interrupt, walking the tree, for a given
- * device-tree node. It's the high level pendant to of_irq_map_raw().
+ * device-tree node. It's the high level pendant to of_irq_parse_raw().
  */
-int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq)
+int of_irq_parse_one(struct device_node *device, int index, struct of_irq *out_irq)
 {
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
 	u32 intsize, intlen;
 	int res = -EINVAL;
 
-	pr_debug("of_irq_map_one: dev=%s, index=%d\n", of_node_full_name(device), index);
+	pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index);
 
 	/* OldWorld mac stuff is "special", handle out of line */
 	if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)
-		return of_irq_map_oldworld(device, index, out_irq);
+		return of_irq_parse_oldworld(device, index, out_irq);
 
 	/* Get the interrupts property */
 	intspec = of_get_property(device, "interrupts", &intlen);
@@ -322,13 +322,13 @@ int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq
 		goto out;
 
 	/* Get new specifier and map it */
-	res = of_irq_map_raw(p, intspec + index * intsize, intsize,
+	res = of_irq_parse_raw(p, intspec + index * intsize, intsize,
 			     addr, out_irq);
  out:
 	of_node_put(p);
 	return res;
 }
-EXPORT_SYMBOL_GPL(of_irq_map_one);
+EXPORT_SYMBOL_GPL(of_irq_parse_one);
 
 /**
  * of_irq_to_resource - Decode a node's IRQ and return it as a resource
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index 677053813211..dceec1048dab 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -5,7 +5,7 @@
 #include <asm/prom.h>
 
 /**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
+ * of_irq_parse_pci - Resolve the interrupt for a PCI device
  * @pdev:       the device whose interrupt is to be resolved
  * @out_irq:    structure of_irq filled by this function
  *
@@ -15,7 +15,7 @@
  * PCI tree until an device-node is found, at which point it will finish
  * resolving using the OF tree walking.
  */
-int of_irq_map_pci(const struct pci_dev *pdev, struct of_irq *out_irq)
+int of_irq_parse_pci(const struct pci_dev *pdev, struct of_irq *out_irq)
 {
 	struct device_node *dn, *ppnode;
 	struct pci_dev *ppdev;
@@ -30,7 +30,7 @@ int of_irq_map_pci(const struct pci_dev *pdev, struct of_irq *out_irq)
 	 */
 	dn = pci_device_to_OF_node(pdev);
 	if (dn) {
-		rc = of_irq_map_one(dn, 0, out_irq);
+		rc = of_irq_parse_one(dn, 0, out_irq);
 		if (!rc)
 			return rc;
 	}
@@ -88,6 +88,6 @@ int of_irq_map_pci(const struct pci_dev *pdev, struct of_irq *out_irq)
 	lspec_be = cpu_to_be32(lspec);
 	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
 	laddr[1]  = laddr[2] = cpu_to_be32(0);
-	return of_irq_map_raw(ppnode, &lspec_be, 1, laddr, out_irq);
+	return of_irq_parse_raw(ppnode, &lspec_be, 1, laddr, out_irq);
 }
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
+EXPORT_SYMBOL_GPL(of_irq_parse_pci);
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 729d5a101d62..05f81807d05b 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -650,7 +650,7 @@ static int __init mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	struct of_irq oirq;
 	int ret;
 
-	ret = of_irq_map_pci(dev, &oirq);
+	ret = of_irq_parse_pci(dev, &oirq);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index fcd63baee5f2..a00bc71e62a3 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -35,12 +35,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
 #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 extern unsigned int of_irq_workarounds;
 extern struct device_node *of_irq_dflt_pic;
-extern int of_irq_map_oldworld(struct device_node *device, int index,
+extern int of_irq_parse_oldworld(struct device_node *device, int index,
 			       struct of_irq *out_irq);
 #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */
 #define of_irq_workarounds (0)
 #define of_irq_dflt_pic (NULL)
-static inline int of_irq_map_oldworld(struct device_node *device, int index,
+static inline int of_irq_parse_oldworld(struct device_node *device, int index,
 				      struct of_irq *out_irq)
 {
 	return -EINVAL;
@@ -48,10 +48,10 @@ static inline int of_irq_map_oldworld(struct device_node *device, int index,
 #endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */
 
 
-extern int of_irq_map_raw(struct device_node *parent, const __be32 *intspec,
+extern int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 			  u32 ointsize, const __be32 *addr,
 			  struct of_irq *out_irq);
-extern int of_irq_map_one(struct device_node *device, int index,
+extern int of_irq_parse_one(struct device_node *device, int index,
 			  struct of_irq *out_irq);
 extern unsigned int irq_create_of_mapping(struct device_node *controller,
 					  const u32 *intspec,
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index fd9c408631a0..839ba20808fe 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -6,7 +6,7 @@
 
 struct pci_dev;
 struct of_irq;
-int of_irq_map_pci(const struct pci_dev *pdev, struct of_irq *out_irq);
+int of_irq_parse_pci(const struct pci_dev *pdev, struct of_irq *out_irq);
 
 struct device_node;
 struct device_node *of_pci_find_child_device(struct device_node *parent,
-- 
cgit 


From 530210c7814e83564c7ca7bca8192515042c0b63 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Sun, 15 Sep 2013 16:39:11 +0100
Subject: of/irq: Replace of_irq with of_phandle_args

struct of_irq and struct of_phandle_args are exactly the same structure.
This patch makes the kernel use of_phandle_args everywhere. This in
itself isn't a big deal, but it makes some follow-on patches simpler.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Michal Simek <monstr@monstr.eu>
Acked-by: Tony Lindgren <tony@atomide.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/arm/mach-integrator/pci_v3.c              |  5 ++---
 arch/microblaze/pci/pci-common.c               |  9 ++++-----
 arch/mips/pci/fixup-lantiq.c                   |  5 ++---
 arch/mips/pci/pci-rt3883.c                     |  6 ++----
 arch/powerpc/kernel/pci-common.c               |  9 ++++-----
 arch/powerpc/platforms/cell/celleb_scc_pciex.c |  5 ++---
 arch/powerpc/platforms/cell/celleb_scc_sio.c   |  5 ++---
 arch/powerpc/platforms/cell/spider-pic.c       |  6 +++---
 arch/powerpc/platforms/cell/spu_manage.c       | 12 ++++++------
 arch/powerpc/platforms/fsl_uli1575.c           |  8 +++-----
 arch/powerpc/platforms/powermac/pic.c          |  8 ++++----
 arch/powerpc/platforms/pseries/event_sources.c |  7 +++----
 arch/powerpc/sysdev/mpic_msi.c                 |  6 +++---
 arch/x86/kernel/devicetree.c                   |  5 ++---
 drivers/of/irq.c                               | 15 +++++++--------
 drivers/of/of_pci_irq.c                        |  2 +-
 drivers/pci/host/pci-mvebu.c                   |  5 ++---
 include/linux/of_irq.h                         | 24 ++++--------------------
 include/linux/of_pci.h                         |  4 ++--
 19 files changed, 58 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 0f496cc51f36..2d6b4da90fb4 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -837,7 +837,7 @@ static struct hw_pci pci_v3 __initdata = {
 
 static int __init pci_v3_map_irq_dt(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	int ret;
 
 	ret = of_irq_parse_pci(dev, &oirq);
@@ -847,8 +847,7 @@ static int __init pci_v3_map_irq_dt(const struct pci_dev *dev, u8 slot, u8 pin)
 		return 0;
 	}
 
-	return irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
+	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 }
 
 static int __init pci_v3_dtprobe(struct platform_device *pdev,
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 4d5b1a9cd790..c9302c4f8a57 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -199,7 +199,7 @@ void pcibios_set_master(struct pci_dev *dev)
  */
 int pci_read_irq_line(struct pci_dev *pci_dev)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	unsigned int virq;
 
 	/* The current device-tree that iSeries generates from the HV
@@ -243,11 +243,10 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 			irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
 	} else {
 		pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
-			 oirq.size, oirq.specifier[0], oirq.specifier[1],
-			 of_node_full_name(oirq.controller));
+			 oirq.args_count, oirq.args[0], oirq.args[1],
+			 of_node_full_name(oirq.np));
 
-		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-					     oirq.size);
+		virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 	}
 	if (!virq) {
 		pr_debug(" Failed to map !\n");
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index 2e8dbfedae53..81ff0b5e6efa 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -25,7 +25,7 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 
 int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_irq dev_irq;
+	struct of_phandle_args dev_irq;
 	int irq;
 
 	if (of_irq_parse_pci(dev, &dev_irq)) {
@@ -33,8 +33,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 			slot, pin);
 		return 0;
 	}
-	irq = irq_create_of_mapping(dev_irq.controller, dev_irq.specifier,
-					dev_irq.size);
+	irq = irq_create_of_mapping(dev_irq.np, dev_irq.args, dev_irq.args_count);
 	dev_info(&dev->dev, "SLOT:%d PIN:%d IRQ:%d\n", slot, pin, irq);
 	return irq;
 }
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index cae92a05ee70..0f08a5ba0b2a 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -583,7 +583,7 @@ err_put_intc_node:
 
 int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_irq dev_irq;
+	struct of_phandle_args dev_irq;
 	int err;
 	int irq;
 
@@ -594,9 +594,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 		return 0;
 	}
 
-	irq = irq_create_of_mapping(dev_irq.controller,
-				    dev_irq.specifier,
-				    dev_irq.size);
+	irq = irq_create_of_mapping(dev_irq.np, dev_irq.args, dev_irq.args_count);
 
 	if (irq == 0)
 		pr_crit("pci %s: no irq found for pin %u\n",
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2f4185425ed5..96c46235fda2 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -228,7 +228,7 @@ int pcibios_add_platform_entries(struct pci_dev *pdev)
  */
 static int pci_read_irq_line(struct pci_dev *pci_dev)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	unsigned int virq;
 
 	pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
@@ -263,11 +263,10 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
 			irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
 	} else {
 		pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
-			 oirq.size, oirq.specifier[0], oirq.specifier[1],
-			 of_node_full_name(oirq.controller));
+			 oirq.args_count, oirq.args[0], oirq.args[1],
+			 of_node_full_name(oirq.np));
 
-		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-					     oirq.size);
+		virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 	}
 	if(virq == NO_IRQ) {
 		pr_debug(" Failed to map !\n");
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index 40bc371096b7..e8d34d1f640d 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -486,7 +486,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
 				     struct pci_controller *phb)
 {
 	struct resource	r;
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	int virq;
 
 	/* SMMIO registers; used inside this file */
@@ -511,8 +511,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
 		pr_err("PCIEXC:Failed to map irq\n");
 		goto error;
 	}
-	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
+	virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 	if (request_irq(virq, pciex_handle_internal_irq,
 			0, "pciex", (void *)phb)) {
 		pr_err("PCIEXC:Failed to request irq\n");
diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c
index 96388b202f4e..06046d512130 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_sio.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c
@@ -45,7 +45,7 @@ static int __init txx9_serial_init(void)
 	struct device_node *node;
 	int i;
 	struct uart_port req;
-	struct of_irq irq;
+	struct of_phandle_args irq;
 	struct resource res;
 
 	for_each_compatible_node(node, "serial", "toshiba,sio-scc") {
@@ -66,8 +66,7 @@ static int __init txx9_serial_init(void)
 #ifdef CONFIG_SERIAL_TXX9_CONSOLE
 			req.membase = ioremap(req.mapbase, 0x24);
 #endif
-			req.irq = irq_create_of_mapping(irq.controller,
-				irq.specifier, irq.size);
+			req.irq = irq_create_of_mapping(irq.np, irq.args, irq.args_count);
 			req.flags |= UPF_IOREMAP | UPF_BUGGY_UART
 				/*HAVE_CTS_LINE*/;
 			req.uartclk = 83300000;
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index b491f406560a..6e842fdbfcab 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -235,10 +235,10 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	/* First, we check whether we have a real "interrupts" in the device
 	 * tree in case the device-tree is ever fixed
 	 */
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	if (of_irq_parse_one(pic->host->of_node, 0, &oirq) == 0) {
-		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-					     oirq.size);
+		virq = irq_create_of_mapping(oirq.np, oirq.args,
+					     oirq.args_count);
 		return virq;
 	}
 
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index e6cdb81a0959..e9eb4f83b1d5 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -177,7 +177,7 @@ out:
 
 static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	int ret;
 	int i;
 
@@ -188,10 +188,10 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 			goto err;
 		}
 		ret = -EINVAL;
-		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.specifier[0],
-			 oirq.controller->full_name);
-		spu->irqs[i] = irq_create_of_mapping(oirq.controller,
-					oirq.specifier, oirq.size);
+		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.args[0],
+			 oirq.np->full_name);
+		spu->irqs[i] = irq_create_of_mapping(oirq.np,
+					oirq.args, oirq.args_count);
 		if (spu->irqs[i] == NO_IRQ) {
 			pr_debug("spu_new: failed to map it !\n");
 			goto err;
@@ -200,7 +200,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 	return 0;
 
 err:
-	pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier,
+	pr_debug("failed to map irq %x for spu %s\n", *oirq.args,
 		spu->name);
 	for (; i >= 0; i--) {
 		if (spu->irqs[i] != NO_IRQ)
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index ac539c1cd808..288226deffa3 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -321,8 +321,8 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct device_node *hosenode = hose ? hose->dn : NULL;
-	struct of_irq oirq;
-	int virq, pin = 2;
+	struct of_phandle_args oirq;
+	int pin = 2;
 	u32 laddr[3];
 
 	if (!machine_is(mpc86xx_hpcd))
@@ -334,9 +334,7 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 	laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8);
 	laddr[1] = laddr[2] = 0;
 	of_irq_parse_raw(hosenode, &pin, 1, laddr, &oirq);
-	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
-	dev->irq = virq;
+	dev->irq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x1575, hpcd_quirk_uli1575);
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 720663e29f47..4c24bf60d39d 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -394,7 +394,7 @@ static void __init pmac_pic_probe_oldstyle(void)
 }
 
 int of_irq_parse_oldworld(struct device_node *device, int index,
-			struct of_irq *out_irq)
+			struct of_phandle_args *out_irq)
 {
 	const u32 *ints = NULL;
 	int intlen;
@@ -422,9 +422,9 @@ int of_irq_parse_oldworld(struct device_node *device, int index,
 	if (index >= intlen)
 		return -EINVAL;
 
-	out_irq->controller = NULL;
-	out_irq->specifier[0] = ints[index];
-	out_irq->size = 1;
+	out_irq->np = NULL;
+	out_irq->args[0] = ints[index];
+	out_irq->args_count = 1;
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 850c18c457ad..6dcf9cc38ffb 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -25,7 +25,7 @@ void request_event_sources_irqs(struct device_node *np,
 				const char *name)
 {
 	int i, index, count = 0;
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	const u32 *opicprop;
 	unsigned int opicplen;
 	unsigned int virqs[16];
@@ -59,9 +59,8 @@ void request_event_sources_irqs(struct device_node *np,
 		     index++) {
 			if (count > 15)
 				break;
-			virqs[count] = irq_create_of_mapping(oirq.controller,
-							    oirq.specifier,
-							    oirq.size);
+			virqs[count] = irq_create_of_mapping(oirq.np, oirq.args,
+							    oirq.args_count);
 			if (virqs[count] == NO_IRQ) {
 				pr_err("event-sources: Unable to allocate "
 				       "interrupt number for %s\n",
diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c
index 463e3a7c193c..7dc39f35a4cc 100644
--- a/arch/powerpc/sysdev/mpic_msi.c
+++ b/arch/powerpc/sysdev/mpic_msi.c
@@ -35,7 +35,7 @@ static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
 	const struct irq_domain_ops *ops = mpic->irqhost->ops;
 	struct device_node *np;
 	int flags, index, i;
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 
 	pr_debug("mpic: found U3, guessing msi allocator setup\n");
 
@@ -64,8 +64,8 @@ static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
 
 		index = 0;
 		while (of_irq_parse_one(np, index++, &oirq) == 0) {
-			ops->xlate(mpic->irqhost, NULL, oirq.specifier,
-						oirq.size, &hwirq, &flags);
+			ops->xlate(mpic->irqhost, NULL, oirq.args,
+						oirq.args_count, &hwirq, &flags);
 			msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, hwirq);
 		}
 	}
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 3ac6398e5361..00986988a10e 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -105,7 +105,7 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
 
 static int x86_of_pci_irq_enable(struct pci_dev *dev)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	u32 virq;
 	int ret;
 	u8 pin;
@@ -120,8 +120,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
 	if (ret)
 		return ret;
 
-	virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
-			oirq.size);
+	virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 	if (virq == 0)
 		return -EINVAL;
 	dev->irq = virq;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 410aa2415f42..a7db38a63403 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -36,13 +36,12 @@
  */
 unsigned int irq_of_parse_and_map(struct device_node *dev, int index)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 
 	if (of_irq_parse_one(dev, index, &oirq))
 		return 0;
 
-	return irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
+	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 }
 EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
 
@@ -94,7 +93,7 @@ struct device_node *of_irq_find_parent(struct device_node *child)
  * node exist for the parent.
  */
 int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
-		   u32 ointsize, const __be32 *addr, struct of_irq *out_irq)
+		   u32 ointsize, const __be32 *addr, struct of_phandle_args *out_irq)
 {
 	struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
 	const __be32 *tmp, *imap, *imask;
@@ -156,10 +155,10 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 				NULL) {
 			pr_debug(" -> got it !\n");
 			for (i = 0; i < intsize; i++)
-				out_irq->specifier[i] =
+				out_irq->args[i] =
 						of_read_number(intspec +i, 1);
-			out_irq->size = intsize;
-			out_irq->controller = ipar;
+			out_irq->args_count = intsize;
+			out_irq->np = ipar;
 			of_node_put(old);
 			return 0;
 		}
@@ -280,7 +279,7 @@ EXPORT_SYMBOL_GPL(of_irq_parse_raw);
  * This function resolves an interrupt, walking the tree, for a given
  * device-tree node. It's the high level pendant to of_irq_parse_raw().
  */
-int of_irq_parse_one(struct device_node *device, int index, struct of_irq *out_irq)
+int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq)
 {
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index dceec1048dab..ee3293d4b66b 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -15,7 +15,7 @@
  * PCI tree until an device-node is found, at which point it will finish
  * resolving using the OF tree walking.
  */
-int of_irq_parse_pci(const struct pci_dev *pdev, struct of_irq *out_irq)
+int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq)
 {
 	struct device_node *dn, *ppnode;
 	struct pci_dev *ppdev;
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 05f81807d05b..c5e57f82b9af 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -647,15 +647,14 @@ static int __init mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
 
 static int __init mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_irq oirq;
+	struct of_phandle_args oirq;
 	int ret;
 
 	ret = of_irq_parse_pci(dev, &oirq);
 	if (ret)
 		return ret;
 
-	return irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
+	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
 }
 
 static struct pci_bus *mvebu_pcie_scan_bus(int nr, struct pci_sys_data *sys)
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index a00bc71e62a3..8d9f85560d48 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -8,22 +8,6 @@
 #include <linux/ioport.h>
 #include <linux/of.h>
 
-/**
- * of_irq - container for device_node/irq_specifier pair for an irq controller
- * @controller: pointer to interrupt controller device tree node
- * @size: size of interrupt specifier
- * @specifier: array of cells @size long specifing the specific interrupt
- *
- * This structure is returned when an interrupt is mapped. The controller
- * field needs to be put() after use
- */
-#define OF_MAX_IRQ_SPEC		4 /* We handle specifiers of at most 4 cells */
-struct of_irq {
-	struct device_node *controller; /* Interrupt controller node */
-	u32 size; /* Specifier size */
-	u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */
-};
-
 typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
 
 /*
@@ -36,12 +20,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *);
 extern unsigned int of_irq_workarounds;
 extern struct device_node *of_irq_dflt_pic;
 extern int of_irq_parse_oldworld(struct device_node *device, int index,
-			       struct of_irq *out_irq);
+			       struct of_phandle_args *out_irq);
 #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */
 #define of_irq_workarounds (0)
 #define of_irq_dflt_pic (NULL)
 static inline int of_irq_parse_oldworld(struct device_node *device, int index,
-				      struct of_irq *out_irq)
+				      struct of_phandle_args *out_irq)
 {
 	return -EINVAL;
 }
@@ -50,9 +34,9 @@ static inline int of_irq_parse_oldworld(struct device_node *device, int index,
 
 extern int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 			  u32 ointsize, const __be32 *addr,
-			  struct of_irq *out_irq);
+			  struct of_phandle_args *out_irq);
 extern int of_irq_parse_one(struct device_node *device, int index,
-			  struct of_irq *out_irq);
+			  struct of_phandle_args *out_irq);
 extern unsigned int irq_create_of_mapping(struct device_node *controller,
 					  const u32 *intspec,
 					  unsigned int intsize);
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index 839ba20808fe..f297237349e8 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -5,8 +5,8 @@
 #include <linux/msi.h>
 
 struct pci_dev;
-struct of_irq;
-int of_irq_parse_pci(const struct pci_dev *pdev, struct of_irq *out_irq);
+struct of_phandle_args;
+int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq);
 
 struct device_node;
 struct device_node *of_pci_find_child_device(struct device_node *parent,
-- 
cgit 


From e6d30ab1e7d1281784672c0fc2ffa385cfb7279e Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Sun, 15 Sep 2013 16:55:53 +0100
Subject: of/irq: simplify args to irq_create_of_mapping

All the callers of irq_create_of_mapping() pass the contents of a struct
of_phandle_args structure to the function. Since all the callers already
have an of_phandle_args pointer, why not pass it directly to
irq_create_of_mapping()?

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Michal Simek <monstr@monstr.eu>
Acked-by: Tony Lindgren <tony@atomide.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/arm/mach-integrator/pci_v3.c              |  2 +-
 arch/microblaze/pci/pci-common.c               |  2 +-
 arch/mips/pci/fixup-lantiq.c                   |  2 +-
 arch/mips/pci/pci-rt3883.c                     |  2 +-
 arch/powerpc/kernel/pci-common.c               |  2 +-
 arch/powerpc/platforms/cell/celleb_scc_pciex.c |  2 +-
 arch/powerpc/platforms/cell/celleb_scc_sio.c   |  2 +-
 arch/powerpc/platforms/cell/spider-pic.c       |  7 ++-----
 arch/powerpc/platforms/cell/spu_manage.c       |  3 +--
 arch/powerpc/platforms/fsl_uli1575.c           |  2 +-
 arch/powerpc/platforms/pseries/event_sources.c |  3 +--
 arch/x86/kernel/devicetree.c                   |  2 +-
 drivers/of/irq.c                               |  2 +-
 drivers/pci/host/pci-mvebu.c                   |  2 +-
 include/linux/of_irq.h                         |  4 +---
 kernel/irq/irqdomain.c                         | 13 ++++++-------
 16 files changed, 22 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 2d6b4da90fb4..bb3aeb31a54e 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -847,7 +847,7 @@ static int __init pci_v3_map_irq_dt(const struct pci_dev *dev, u8 slot, u8 pin)
 		return 0;
 	}
 
-	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	return irq_create_of_mapping(&oirq);
 }
 
 static int __init pci_v3_dtprobe(struct platform_device *pdev,
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index c9302c4f8a57..60b386c72c57 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -246,7 +246,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 			 oirq.args_count, oirq.args[0], oirq.args[1],
 			 of_node_full_name(oirq.np));
 
-		virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+		virq = irq_create_of_mapping(&oirq);
 	}
 	if (!virq) {
 		pr_debug(" Failed to map !\n");
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index 81ff0b5e6efa..aef60e75003e 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -33,7 +33,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 			slot, pin);
 		return 0;
 	}
-	irq = irq_create_of_mapping(dev_irq.np, dev_irq.args, dev_irq.args_count);
+	irq = irq_create_of_mapping(&dev_irq);
 	dev_info(&dev->dev, "SLOT:%d PIN:%d IRQ:%d\n", slot, pin, irq);
 	return irq;
 }
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 0f08a5ba0b2a..eadc4310cd36 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -594,7 +594,7 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 		return 0;
 	}
 
-	irq = irq_create_of_mapping(dev_irq.np, dev_irq.args, dev_irq.args_count);
+	irq = irq_create_of_mapping(&dev_irq);
 
 	if (irq == 0)
 		pr_crit("pci %s: no irq found for pin %u\n",
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 96c46235fda2..a1e3e40ca3fd 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -266,7 +266,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
 			 oirq.args_count, oirq.args[0], oirq.args[1],
 			 of_node_full_name(oirq.np));
 
-		virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+		virq = irq_create_of_mapping(&oirq);
 	}
 	if(virq == NO_IRQ) {
 		pr_debug(" Failed to map !\n");
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index e8d34d1f640d..b3ea96db5b06 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -511,7 +511,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
 		pr_err("PCIEXC:Failed to map irq\n");
 		goto error;
 	}
-	virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	virq = irq_create_of_mapping(&oirq);
 	if (request_irq(virq, pciex_handle_internal_irq,
 			0, "pciex", (void *)phb)) {
 		pr_err("PCIEXC:Failed to request irq\n");
diff --git a/arch/powerpc/platforms/cell/celleb_scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c
index 06046d512130..c8eb57193826 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_sio.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c
@@ -66,7 +66,7 @@ static int __init txx9_serial_init(void)
 #ifdef CONFIG_SERIAL_TXX9_CONSOLE
 			req.membase = ioremap(req.mapbase, 0x24);
 #endif
-			req.irq = irq_create_of_mapping(irq.np, irq.args, irq.args_count);
+			req.irq = irq_create_of_mapping(&irq);
 			req.flags |= UPF_IOREMAP | UPF_BUGGY_UART
 				/*HAVE_CTS_LINE*/;
 			req.uartclk = 83300000;
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 6e842fdbfcab..d20680446174 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -236,11 +236,8 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	 * tree in case the device-tree is ever fixed
 	 */
 	struct of_phandle_args oirq;
-	if (of_irq_parse_one(pic->host->of_node, 0, &oirq) == 0) {
-		virq = irq_create_of_mapping(oirq.np, oirq.args,
-					     oirq.args_count);
-		return virq;
-	}
+	if (of_irq_parse_one(pic->host->of_node, 0, &oirq) == 0)
+		return irq_create_of_mapping(&oirq);
 
 	/* Now do the horrible hacks */
 	tmp = of_get_property(pic->host->of_node, "#interrupt-cells", NULL);
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index e9eb4f83b1d5..c3327f3d8cf7 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -190,8 +190,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 		ret = -EINVAL;
 		pr_debug("  irq %d no 0x%x on %s\n", i, oirq.args[0],
 			 oirq.np->full_name);
-		spu->irqs[i] = irq_create_of_mapping(oirq.np,
-					oirq.args, oirq.args_count);
+		spu->irqs[i] = irq_create_of_mapping(&oirq);
 		if (spu->irqs[i] == NO_IRQ) {
 			pr_debug("spu_new: failed to map it !\n");
 			goto err;
diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index 288226deffa3..8904046556ad 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -334,7 +334,7 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 	laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8);
 	laddr[1] = laddr[2] = 0;
 	of_irq_parse_raw(hosenode, &pin, 1, laddr, &oirq);
-	dev->irq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	dev->irq = irq_create_of_mapping(&oirq);
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x1575, hpcd_quirk_uli1575);
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 6dcf9cc38ffb..18380e8f6dfe 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -59,8 +59,7 @@ void request_event_sources_irqs(struct device_node *np,
 		     index++) {
 			if (count > 15)
 				break;
-			virqs[count] = irq_create_of_mapping(oirq.np, oirq.args,
-							    oirq.args_count);
+			virqs[count] = irq_create_of_mapping(&oirq);
 			if (virqs[count] == NO_IRQ) {
 				pr_err("event-sources: Unable to allocate "
 				       "interrupt number for %s\n",
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 00986988a10e..d39948f654a0 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -120,7 +120,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
 	if (ret)
 		return ret;
 
-	virq = irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	virq = irq_create_of_mapping(&oirq);
 	if (virq == 0)
 		return -EINVAL;
 	dev->irq = virq;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index a7db38a63403..84184c44e8db 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -41,7 +41,7 @@ unsigned int irq_of_parse_and_map(struct device_node *dev, int index)
 	if (of_irq_parse_one(dev, index, &oirq))
 		return 0;
 
-	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	return irq_create_of_mapping(&oirq);
 }
 EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
 
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index c5e57f82b9af..3a8d01ec50f7 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -654,7 +654,7 @@ static int __init mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	if (ret)
 		return ret;
 
-	return irq_create_of_mapping(oirq.np, oirq.args, oirq.args_count);
+	return irq_create_of_mapping(&oirq);
 }
 
 static struct pci_bus *mvebu_pcie_scan_bus(int nr, struct pci_sys_data *sys)
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 8d9f85560d48..3bbba8d6adc8 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -37,9 +37,7 @@ extern int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 			  struct of_phandle_args *out_irq);
 extern int of_irq_parse_one(struct device_node *device, int index,
 			  struct of_phandle_args *out_irq);
-extern unsigned int irq_create_of_mapping(struct device_node *controller,
-					  const u32 *intspec,
-					  unsigned int intsize);
+extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data);
 extern int of_irq_to_resource(struct device_node *dev, int index,
 			      struct resource *r);
 extern int of_irq_count(struct device_node *dev);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 706724e9835d..cf68bb36fe58 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -465,27 +465,26 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base,
 }
 EXPORT_SYMBOL_GPL(irq_create_strict_mappings);
 
-unsigned int irq_create_of_mapping(struct device_node *controller,
-				   const u32 *intspec, unsigned int intsize)
+unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data)
 {
 	struct irq_domain *domain;
 	irq_hw_number_t hwirq;
 	unsigned int type = IRQ_TYPE_NONE;
 	unsigned int virq;
 
-	domain = controller ? irq_find_host(controller) : irq_default_domain;
+	domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain;
 	if (!domain) {
 		pr_warn("no irq domain found for %s !\n",
-			of_node_full_name(controller));
+			of_node_full_name(irq_data->np));
 		return 0;
 	}
 
 	/* If domain has no translation, then we assume interrupt line */
 	if (domain->ops->xlate == NULL)
-		hwirq = intspec[0];
+		hwirq = irq_data->args[0];
 	else {
-		if (domain->ops->xlate(domain, controller, intspec, intsize,
-				     &hwirq, &type))
+		if (domain->ops->xlate(domain, irq_data->np, irq_data->args,
+					irq_data->args_count, &hwirq, &type))
 			return 0;
 	}
 
-- 
cgit 


From 2361613206e66ce59cc0e08efa8d98ec15b84ed1 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Sun, 15 Sep 2013 22:32:39 +0100
Subject: of/irq: Refactor interrupt-map parsing

All the users of of_irq_parse_raw pass in a raw interrupt specifier from
the device tree and expect it to be returned (possibly modified) in an
of_phandle_args structure. However, the primary function of
of_irq_parse_raw() is to check for translations due to the presence of
one or more interrupt-map properties. The actual placing of the data
into an of_phandle_args structure is trivial. If it is refactored to
accept an of_phandle_args structure directly, then it becomes possible
to consume of_phandle_args from other sources. This is important for an
upcoming patch that allows a device to be connected to more than one
interrupt parent. It also simplifies the code a bit.

The biggest complication with this patch is that the old version works
on the interrupt specifiers in __be32 form, but the of_phandle_args
structure is intended to carry it in the cpu-native version. A bit of
churn was required to make this work. In the end it results in tighter
code, so the churn is worth it.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/fsl_uli1575.c |   6 +-
 drivers/of/irq.c                     | 108 ++++++++++++++++++-----------------
 drivers/of/of_pci_irq.c              |   7 ++-
 include/linux/of_irq.h               |   5 +-
 4 files changed, 67 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c
index 8904046556ad..b97f6f3d3c5b 100644
--- a/arch/powerpc/platforms/fsl_uli1575.c
+++ b/arch/powerpc/platforms/fsl_uli1575.c
@@ -322,7 +322,6 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct device_node *hosenode = hose ? hose->dn : NULL;
 	struct of_phandle_args oirq;
-	int pin = 2;
 	u32 laddr[3];
 
 	if (!machine_is(mpc86xx_hpcd))
@@ -331,9 +330,12 @@ static void hpcd_final_uli5288(struct pci_dev *dev)
 	if (!hosenode)
 		return;
 
+	oirq.np = hosenode;
+	oirq.args[0] = 2;
+	oirq.args_count = 1;
 	laddr[0] = (hose->first_busno << 16) | (PCI_DEVFN(31, 0) << 8);
 	laddr[1] = laddr[2] = 0;
-	of_irq_parse_raw(hosenode, &pin, 1, laddr, &oirq);
+	of_irq_parse_raw(laddr, &oirq);
 	dev->irq = irq_create_of_mapping(&oirq);
 }
 
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 84184c44e8db..0ed5ed4a5f9b 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -80,31 +80,32 @@ struct device_node *of_irq_find_parent(struct device_node *child)
 /**
  * of_irq_parse_raw - Low level interrupt tree parsing
  * @parent:	the device interrupt parent
- * @intspec:	interrupt specifier ("interrupts" property of the device)
- * @ointsize:   size of the passed in interrupt specifier
- * @addr:	address specifier (start of "reg" property of the device)
- * @out_irq:	structure of_irq filled by this function
+ * @addr:	address specifier (start of "reg" property of the device) in be32 format
+ * @out_irq:	structure of_irq updated by this function
  *
  * Returns 0 on success and a negative number on error
  *
  * This function is a low-level interrupt tree walking function. It
  * can be used to do a partial walk with synthetized reg and interrupts
  * properties, for example when resolving PCI interrupts when no device
- * node exist for the parent.
+ * node exist for the parent. It takes an interrupt specifier structure as
+ * input, walks the tree looking for any interrupt-map properties, translates
+ * the specifier for each map, and then returns the translated map.
  */
-int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
-		   u32 ointsize, const __be32 *addr, struct of_phandle_args *out_irq)
+int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 {
 	struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
-	const __be32 *tmp, *imap, *imask;
+	__be32 initial_match_array[8];
+	const __be32 *match_array = initial_match_array;
+	const __be32 *tmp, *imap, *imask, dummy_imask[] = { ~0, ~0, ~0, ~0, ~0 };
 	u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
 	int imaplen, match, i;
 
 	pr_debug("of_irq_parse_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
-		 of_node_full_name(parent), be32_to_cpup(intspec),
-		 be32_to_cpup(intspec + 1), ointsize);
+		 of_node_full_name(out_irq->np), out_irq->args[0], out_irq->args[1],
+		 out_irq->args_count);
 
-	ipar = of_node_get(parent);
+	ipar = of_node_get(out_irq->np);
 
 	/* First get the #interrupt-cells property of the current cursor
 	 * that tells us how to interpret the passed-in intspec. If there
@@ -127,7 +128,7 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 
 	pr_debug("of_irq_parse_raw: ipar=%s, size=%d\n", of_node_full_name(ipar), intsize);
 
-	if (ointsize != intsize)
+	if (out_irq->args_count != intsize)
 		return -EINVAL;
 
 	/* Look for this #address-cells. We have to implement the old linux
@@ -146,6 +147,21 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 
 	pr_debug(" -> addrsize=%d\n", addrsize);
 
+	/* If we were passed no "reg" property and we attempt to parse
+	 * an interrupt-map, then #address-cells must be 0.
+	 * Fail if it's not.
+	 */
+	if (addr == NULL && addrsize != 0) {
+		pr_debug(" -> no reg passed in when needed !\n");
+		return -EINVAL;
+	}
+
+	/* Precalculate the match array - this simplifies match loop */
+	for (i = 0; i < addrsize; i++)
+		initial_match_array[i] = addr[i];
+	for (i = 0; i < intsize; i++)
+		initial_match_array[addrsize + i] = cpu_to_be32(out_irq->args[i]);
+
 	/* Now start the actual "proper" walk of the interrupt tree */
 	while (ipar != NULL) {
 		/* Now check if cursor is an interrupt-controller and if it is
@@ -154,11 +170,6 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 		if (of_get_property(ipar, "interrupt-controller", NULL) !=
 				NULL) {
 			pr_debug(" -> got it !\n");
-			for (i = 0; i < intsize; i++)
-				out_irq->args[i] =
-						of_read_number(intspec +i, 1);
-			out_irq->args_count = intsize;
-			out_irq->np = ipar;
 			of_node_put(old);
 			return 0;
 		}
@@ -175,34 +186,16 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 
 		/* Look for a mask */
 		imask = of_get_property(ipar, "interrupt-map-mask", NULL);
-
-		/* If we were passed no "reg" property and we attempt to parse
-		 * an interrupt-map, then #address-cells must be 0.
-		 * Fail if it's not.
-		 */
-		if (addr == NULL && addrsize != 0) {
-			pr_debug(" -> no reg passed in when needed !\n");
-			goto fail;
-		}
+		if (!imask)
+			imask = dummy_imask;
 
 		/* Parse interrupt-map */
 		match = 0;
 		while (imaplen > (addrsize + intsize + 1) && !match) {
 			/* Compare specifiers */
 			match = 1;
-			for (i = 0; i < addrsize && match; ++i) {
-				__be32 mask = imask ? imask[i]
-						    : cpu_to_be32(0xffffffffu);
-				match = ((addr[i] ^ imap[i]) & mask) == 0;
-			}
-			for (; i < (addrsize + intsize) && match; ++i) {
-				__be32 mask = imask ? imask[i]
-						    : cpu_to_be32(0xffffffffu);
-				match =
-				   ((intspec[i-addrsize] ^ imap[i]) & mask) == 0;
-			}
-			imap += addrsize + intsize;
-			imaplen -= addrsize + intsize;
+			for (i = 0; i < (addrsize + intsize); i++, imaplen--)
+				match = !((match_array[i] ^ *imap++) & imask[i]);
 
 			pr_debug(" -> match=%d (imaplen=%d)\n", match, imaplen);
 
@@ -247,12 +240,18 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 		if (!match)
 			goto fail;
 
-		of_node_put(old);
-		old = of_node_get(newpar);
+		/*
+		 * Successfully parsed an interrrupt-map translation; copy new
+		 * interrupt specifier into the out_irq structure
+		 */
+		of_node_put(out_irq->np);
+		out_irq->np = of_node_get(newpar);
+
+		match_array = imap - newaddrsize - newintsize;
+		for (i = 0; i < newintsize; i++)
+			out_irq->args[i] = be32_to_cpup(imap - newintsize + i);
+		out_irq->args_count = intsize = newintsize;
 		addrsize = newaddrsize;
-		intsize = newintsize;
-		intspec = imap - intsize;
-		addr = intspec - addrsize;
 
 	skiplevel:
 		/* Iterate again with new parent */
@@ -263,7 +262,7 @@ int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
 	}
  fail:
 	of_node_put(ipar);
-	of_node_put(old);
+	of_node_put(out_irq->np);
 	of_node_put(newpar);
 
 	return -EINVAL;
@@ -276,15 +275,16 @@ EXPORT_SYMBOL_GPL(of_irq_parse_raw);
  * @index: index of the interrupt to resolve
  * @out_irq: structure of_irq filled by this function
  *
- * This function resolves an interrupt, walking the tree, for a given
- * device-tree node. It's the high level pendant to of_irq_parse_raw().
+ * This function resolves an interrupt for a node by walking the interrupt tree,
+ * finding which interrupt controller node it is attached to, and returning the
+ * interrupt specifier that can be used to retrieve a Linux IRQ number.
  */
 int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq)
 {
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
 	u32 intsize, intlen;
-	int res = -EINVAL;
+	int i, res = -EINVAL;
 
 	pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index);
 
@@ -320,9 +320,15 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	if ((index + 1) * intsize > intlen)
 		goto out;
 
-	/* Get new specifier and map it */
-	res = of_irq_parse_raw(p, intspec + index * intsize, intsize,
-			     addr, out_irq);
+	/* Copy intspec into irq structure */
+	intspec += index * intsize;
+	out_irq->np = p;
+	out_irq->args_count = intsize;
+	for (i = 0; i < intsize; i++)
+		out_irq->args[i] = be32_to_cpup(intspec++);
+
+	/* Check if there are any interrupt-map translations to process */
+	res = of_irq_parse_raw(addr, out_irq);
  out:
 	of_node_put(p);
 	return res;
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index ee3293d4b66b..303afebc247a 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -85,9 +85,12 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 		pdev = ppdev;
 	}
 
+	out_irq->np = ppnode;
+	out_irq->args_count = 1;
+	out_irq->args[0] = lspec;
 	lspec_be = cpu_to_be32(lspec);
 	laddr[0] = cpu_to_be32((pdev->bus->number << 16) | (pdev->devfn << 8));
-	laddr[1]  = laddr[2] = cpu_to_be32(0);
-	return of_irq_parse_raw(ppnode, &lspec_be, 1, laddr, out_irq);
+	laddr[1] = laddr[2] = cpu_to_be32(0);
+	return of_irq_parse_raw(laddr, out_irq);
 }
 EXPORT_SYMBOL_GPL(of_irq_parse_pci);
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 3bbba8d6adc8..c0d6dfe80895 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -31,10 +31,7 @@ static inline int of_irq_parse_oldworld(struct device_node *device, int index,
 }
 #endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */
 
-
-extern int of_irq_parse_raw(struct device_node *parent, const __be32 *intspec,
-			  u32 ointsize, const __be32 *addr,
-			  struct of_phandle_args *out_irq);
+extern int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq);
 extern int of_irq_parse_one(struct device_node *device, int index,
 			  struct of_phandle_args *out_irq);
 extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data);
-- 
cgit 


From 624cfca534f9b1ffb1326617b4e973a3d5ecff4a Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Fri, 11 Oct 2013 22:05:10 +0100
Subject: of: Add helper for printing an of_phandle_args structure

It is sometimes useful for debug to get the contents of an
of_phandle_args structure out into the kernel log.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/base.c  | 9 +++++++++
 drivers/of/irq.c   | 6 +++---
 include/linux/of.h | 1 +
 3 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3ae106d89791..021db96245e7 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1185,6 +1185,15 @@ int of_property_count_strings(struct device_node *np, const char *propname)
 }
 EXPORT_SYMBOL_GPL(of_property_count_strings);
 
+void of_print_phandle_args(const char *msg, const struct of_phandle_args *args)
+{
+	int i;
+	printk("%s %s", msg, of_node_full_name(args->np));
+	for (i = 0; i < args->args_count; i++)
+		printk(i ? ",%08x" : ":%08x", args->args[i]);
+	printk("\n");
+}
+
 static int __of_parse_phandle_with_args(const struct device_node *np,
 					const char *list_name,
 					const char *cells_name,
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 0ed5ed4a5f9b..ddea945ec29e 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -101,9 +101,9 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 	u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
 	int imaplen, match, i;
 
-	pr_debug("of_irq_parse_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
-		 of_node_full_name(out_irq->np), out_irq->args[0], out_irq->args[1],
-		 out_irq->args_count);
+#ifdef DEBUG
+	of_print_phandle_args("of_irq_parse_raw: ", out_irq);
+#endif
 
 	ipar = of_node_get(out_irq->np);
 
diff --git a/include/linux/of.h b/include/linux/of.h
index f95aee391e30..374e03536135 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -275,6 +275,7 @@ extern int of_n_size_cells(struct device_node *np);
 extern const struct of_device_id *of_match_node(
 	const struct of_device_id *matches, const struct device_node *node);
 extern int of_modalias_node(struct device_node *node, char *modalias, int len);
+extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args);
 extern struct device_node *of_parse_phandle(const struct device_node *np,
 					    const char *phandle_name,
 					    int index);
-- 
cgit 


From 16b84e5a505c790538e534ad8dfda9c288691e40 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Thu, 19 Sep 2013 16:44:55 -0500
Subject: of/irq: Create of_irq_parse_and_map_pci() to consolidate arch code.

Several architectures open code effectively the same code block for
finding and mapping PCI irqs. This patch consolidates it down to a
single function.

Signed-off-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Michal Simek <monstr@monstr.eu>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/arm/mach-integrator/pci_v3.c | 17 +----------------
 arch/mips/pci/fixup-lantiq.c      | 12 +-----------
 arch/mips/pci/pci-rt3883.c        | 22 +---------------------
 arch/x86/kernel/devicetree.c      |  7 +------
 drivers/of/of_pci_irq.c           | 25 +++++++++++++++++++++++++
 drivers/pci/host/pci-mvebu.c      | 14 +-------------
 include/linux/of_pci.h            |  1 +
 7 files changed, 31 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index bb3aeb31a54e..a87e510fe0c4 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -835,21 +835,6 @@ static struct hw_pci pci_v3 __initdata = {
 
 #ifdef CONFIG_OF
 
-static int __init pci_v3_map_irq_dt(const struct pci_dev *dev, u8 slot, u8 pin)
-{
-	struct of_phandle_args oirq;
-	int ret;
-
-	ret = of_irq_parse_pci(dev, &oirq);
-	if (ret) {
-		dev_err(&dev->dev, "of_irq_parse_pci() %d\n", ret);
-		/* Proper return code 0 == NO_IRQ */
-		return 0;
-	}
-
-	return irq_create_of_mapping(&oirq);
-}
-
 static int __init pci_v3_dtprobe(struct platform_device *pdev,
 				struct device_node *np)
 {
@@ -918,7 +903,7 @@ static int __init pci_v3_dtprobe(struct platform_device *pdev,
 		return -EINVAL;
 	}
 
-	pci_v3.map_irq = pci_v3_map_irq_dt;
+	pci_v3.map_irq = of_irq_parse_and_map_pci;
 	pci_common_init_dev(&pdev->dev, &pci_v3);
 
 	return 0;
diff --git a/arch/mips/pci/fixup-lantiq.c b/arch/mips/pci/fixup-lantiq.c
index aef60e75003e..c2ce41ea61d7 100644
--- a/arch/mips/pci/fixup-lantiq.c
+++ b/arch/mips/pci/fixup-lantiq.c
@@ -25,15 +25,5 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 
 int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_phandle_args dev_irq;
-	int irq;
-
-	if (of_irq_parse_pci(dev, &dev_irq)) {
-		dev_err(&dev->dev, "trying to map irq for unknown slot:%d pin:%d\n",
-			slot, pin);
-		return 0;
-	}
-	irq = irq_create_of_mapping(&dev_irq);
-	dev_info(&dev->dev, "SLOT:%d PIN:%d IRQ:%d\n", slot, pin, irq);
-	return irq;
+	return of_irq_parse_and_map_pci(dev, slot, pin);
 }
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index eadc4310cd36..adeff2bfe4cd 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -583,27 +583,7 @@ err_put_intc_node:
 
 int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
-	struct of_phandle_args dev_irq;
-	int err;
-	int irq;
-
-	err = of_irq_parse_pci(dev, &dev_irq);
-	if (err) {
-		pr_err("pci %s: unable to get irq map, err=%d\n",
-		       pci_name((struct pci_dev *) dev), err);
-		return 0;
-	}
-
-	irq = irq_create_of_mapping(&dev_irq);
-
-	if (irq == 0)
-		pr_crit("pci %s: no irq found for pin %u\n",
-			pci_name((struct pci_dev *) dev), pin);
-	else
-		pr_info("pci %s: using irq %d for pin %u\n",
-			pci_name((struct pci_dev *) dev), irq, pin);
-
-	return irq;
+	return of_irq_parse_and_map_pci(dev, slot, pin);
 }
 
 int pcibios_plat_dev_init(struct pci_dev *dev)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index d39948f654a0..69c826a3d07e 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -105,7 +105,6 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
 
 static int x86_of_pci_irq_enable(struct pci_dev *dev)
 {
-	struct of_phandle_args oirq;
 	u32 virq;
 	int ret;
 	u8 pin;
@@ -116,11 +115,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
 	if (!pin)
 		return 0;
 
-	ret = of_irq_parse_pci(dev, &oirq);
-	if (ret)
-		return ret;
-
-	virq = irq_create_of_mapping(&oirq);
+	virq = of_irq_parse_and_map_pci(dev, 0, 0);
 	if (virq == 0)
 		return -EINVAL;
 	dev->irq = virq;
diff --git a/drivers/of/of_pci_irq.c b/drivers/of/of_pci_irq.c
index 303afebc247a..8e92acd8253f 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -94,3 +94,28 @@ int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq
 	return of_irq_parse_raw(laddr, out_irq);
 }
 EXPORT_SYMBOL_GPL(of_irq_parse_pci);
+
+/**
+ * of_irq_parse_and_map_pci() - Decode a PCI irq from the device tree and map to a virq
+ * @dev: The pci device needing an irq
+ * @slot: PCI slot number; passed when used as map_irq callback. Unused
+ * @pin: PCI irq pin number; passed when used as map_irq callback. Unused
+ *
+ * @slot and @pin are unused, but included in the function so that this
+ * function can be used directly as the map_irq callback to pci_fixup_irqs().
+ */
+int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct of_phandle_args oirq;
+	int ret;
+
+	ret = of_irq_parse_pci(dev, &oirq);
+	if (ret) {
+		dev_err(&dev->dev, "of_irq_parse_pci() failed with rc=%d\n", ret);
+		return 0; /* Proper return code 0 == NO_IRQ */
+	}
+
+	return irq_create_of_mapping(&oirq);
+}
+EXPORT_SYMBOL_GPL(of_irq_parse_and_map_pci);
+
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 3a8d01ec50f7..07ddb3a13c6e 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -645,18 +645,6 @@ static int __init mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
 	return 1;
 }
 
-static int __init mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
-{
-	struct of_phandle_args oirq;
-	int ret;
-
-	ret = of_irq_parse_pci(dev, &oirq);
-	if (ret)
-		return ret;
-
-	return irq_create_of_mapping(&oirq);
-}
-
 static struct pci_bus *mvebu_pcie_scan_bus(int nr, struct pci_sys_data *sys)
 {
 	struct mvebu_pcie *pcie = sys_to_pcie(sys);
@@ -705,7 +693,7 @@ static void __init mvebu_pcie_enable(struct mvebu_pcie *pcie)
 	hw.private_data   = (void **)&pcie;
 	hw.setup          = mvebu_pcie_setup;
 	hw.scan           = mvebu_pcie_scan_bus;
-	hw.map_irq        = mvebu_pcie_map_irq;
+	hw.map_irq        = of_irq_parse_and_map_pci;
 	hw.ops            = &mvebu_pcie_ops;
 	hw.align_resource = mvebu_pcie_align_resource;
 
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index f297237349e8..1a1f5ffd5288 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -7,6 +7,7 @@
 struct pci_dev;
 struct of_phandle_args;
 int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq);
+int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin);
 
 struct device_node;
 struct device_node *of_pci_find_child_device(struct device_node *parent,
-- 
cgit 


From a5606f85611267047206d8ba055bc0e4ba166ad3 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 24 Oct 2013 14:25:32 +0200
Subject: ALSA: Add ifdef CONFIG_GENERIC_ALLOCATOR for SNDRV_DMA_TYPE_IRAM code

It turned out that we can't use gen_pool_*() functions on archs
without CONFIG_GENERIC_ALLOCATOR (resulting in missing symbols), since
linux/genalloc.h doesn't provide dummy functions for all.  We'd be
able to fix linux/genalloc.h size, but I take an easier path for
now...

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/memalloc.h | 4 ++++
 sound/core/memalloc.c    | 4 ++++
 sound/core/pcm_native.c  | 2 ++
 3 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index 510aec437f72..af9983970417 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -52,7 +52,11 @@ struct snd_dma_device {
 #else
 #define SNDRV_DMA_TYPE_DEV_SG	SNDRV_DMA_TYPE_DEV /* no SG-buf support */
 #endif
+#ifdef CONFIG_GENERIC_ALLOCATOR
 #define SNDRV_DMA_TYPE_DEV_IRAM		4	/* generic device iram-buffer */
+#else
+#define SNDRV_DMA_TYPE_DEV_IRAM	SNDRV_DMA_TYPE_DEV
+#endif
 
 /*
  * info for buffer allocation
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 18c1d4759ccb..51a79218815b 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -238,6 +238,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size,
 		dmab->addr = 0;
 		break;
 #ifdef CONFIG_HAS_DMA
+#ifdef CONFIG_GENERIC_ALLOCATOR
 	case SNDRV_DMA_TYPE_DEV_IRAM:
 		snd_malloc_dev_iram(dmab, size);
 		if (dmab->area)
@@ -246,6 +247,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size,
 		 * so if we fail to malloc, try to fetch memory traditionally.
 		 */
 		dmab->dev.type = SNDRV_DMA_TYPE_DEV;
+#endif /* CONFIG_GENERIC_ALLOCATOR */
 	case SNDRV_DMA_TYPE_DEV:
 		dmab->area = snd_malloc_dev_pages(device, size, &dmab->addr);
 		break;
@@ -318,9 +320,11 @@ void snd_dma_free_pages(struct snd_dma_buffer *dmab)
 		snd_free_pages(dmab->area, dmab->bytes);
 		break;
 #ifdef CONFIG_HAS_DMA
+#ifdef CONFIG_GENERIC_ALLOCATOR
 	case SNDRV_DMA_TYPE_DEV_IRAM:
 		snd_free_dev_iram(dmab);
 		break;
+#endif /* CONFIG_GENERIC_ALLOCATOR */
 	case SNDRV_DMA_TYPE_DEV:
 		snd_free_dev_pages(dmab->dev.dev, dmab->bytes, dmab->area, dmab->addr);
 		break;
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 513f0954d92e..b71be579c6ec 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3199,12 +3199,14 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream,
 			     struct vm_area_struct *area)
 {
 	area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+#ifdef CONFIG_GENERIC_ALLOCATOR
 	if (substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV_IRAM) {
 		area->vm_page_prot = pgprot_writecombine(area->vm_page_prot);
 		return remap_pfn_range(area, area->vm_start,
 				substream->dma_buffer.addr >> PAGE_SHIFT,
 				area->vm_end - area->vm_start, area->vm_page_prot);
 	}
+#endif /* CONFIG_GENERIC_ALLOCATOR */
 #ifdef ARCH_HAS_DMA_MMAP_COHERENT
 	if (!substream->ops->page &&
 	    substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV)
-- 
cgit 


From 917f4b5cba78980a527098a910d94139d3e82c8d Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Thu, 24 Oct 2013 16:37:31 +0530
Subject: ALSA: compress: fix drain calls blocking other compress functions

The drain and drain_notify callback were blocked by low level driver untill the
draining was complete. Due to this being invoked with big fat mutex held, others
ops like reading timestamp, calling pause, drop were blocked.

So to fix this we add a new snd_compr_drain_notify() API. This would be required
to be invoked by low level driver when drain or partial drain has been completed
by the DSP. Thus we make the drain and partial_drain callback as non blocking
and driver returns immediately after notifying DSP.
The waiting is done while relasing the lock so that other ops can go ahead.

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
CC: stable@vger.kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/compress_driver.h | 12 ++++++++++++
 sound/core/compress_offload.c   | 41 ++++++++++++++++++++++++++++++++++++++---
 2 files changed, 50 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 9031a26249b5..175ab3237b58 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -48,6 +48,8 @@ struct snd_compr_ops;
  *	the ring buffer
  * @total_bytes_transferred: cumulative bytes transferred by offload DSP
  * @sleep: poll sleep
+ * @wait: drain wait queue
+ * @drain_wake: condition for drain wake
  */
 struct snd_compr_runtime {
 	snd_pcm_state_t state;
@@ -59,6 +61,8 @@ struct snd_compr_runtime {
 	u64 total_bytes_available;
 	u64 total_bytes_transferred;
 	wait_queue_head_t sleep;
+	wait_queue_head_t wait;
+	unsigned int drain_wake;
 	void *private_data;
 };
 
@@ -171,4 +175,12 @@ static inline void snd_compr_fragment_elapsed(struct snd_compr_stream *stream)
 	wake_up(&stream->runtime->sleep);
 }
 
+static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
+{
+	snd_BUG_ON(!stream);
+
+	stream->runtime->drain_wake = 1;
+	wake_up(&stream->runtime->wait);
+}
+
 #endif
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index bea523a5d852..3eb47d0006a7 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -123,6 +123,7 @@ static int snd_compr_open(struct inode *inode, struct file *f)
 	}
 	runtime->state = SNDRV_PCM_STATE_OPEN;
 	init_waitqueue_head(&runtime->sleep);
+	init_waitqueue_head(&runtime->wait);
 	data->stream.runtime = runtime;
 	f->private_data = (void *)data;
 	mutex_lock(&compr->lock);
@@ -682,12 +683,34 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 	if (!retval) {
 		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
 		wake_up(&stream->runtime->sleep);
+		snd_compr_drain_notify(stream);
 		stream->runtime->total_bytes_available = 0;
 		stream->runtime->total_bytes_transferred = 0;
 	}
 	return retval;
 }
 
+static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
+{
+	/*
+	 * We are called with lock held. So drop the lock while we wait for
+	 * drain complete notfication from the driver
+	 *
+	 * It is expected that driver will notify the drain completion and then
+	 * stream will be moved to SETUP state, even if draining resulted in an
+	 * error. We can trigger next track after this.
+	 */
+	stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+	mutex_unlock(&stream->device->lock);
+
+	wait_event(stream->runtime->wait, stream->runtime->drain_wake);
+
+	wake_up(&stream->runtime->sleep);
+	mutex_lock(&stream->device->lock);
+
+	return 0;
+}
+
 static int snd_compr_drain(struct snd_compr_stream *stream)
 {
 	int retval;
@@ -695,11 +718,17 @@ static int snd_compr_drain(struct snd_compr_stream *stream)
 	if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
 			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
 		return -EPERM;
+
+	stream->runtime->drain_wake = 0;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
-	if (!retval) {
-		stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+	if (retval) {
+		pr_err("SND_COMPR_TRIGGER_DRAIN failed %d\n", retval);
 		wake_up(&stream->runtime->sleep);
+		return retval;
 	}
+
+	retval = snd_compress_wait_for_drain(stream);
+	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
 	return retval;
 }
 
@@ -735,10 +764,16 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 	if (stream->next_track == false)
 		return -EPERM;
 
+	stream->runtime->drain_wake = 0;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
+	if (retval) {
+		pr_err("Partial drain returned failure\n");
+		wake_up(&stream->runtime->sleep);
+		return retval;
+	}
 
 	stream->next_track = false;
-	return retval;
+	return snd_compress_wait_for_drain(stream);
 }
 
 static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-- 
cgit 


From 68126702b419fd26ef4946e314bb3a1f57d3a53f Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 24 Oct 2013 10:07:42 +0900
Subject: slab: overloading the RCU head over the LRU for RCU free

With build-time size checking, we can overload the RCU head over the LRU
of struct page to free pages of a slab in rcu context. This really help to
implement to overload the struct slab over the struct page and this
eventually reduce memory usage and cache footprint of the SLAB.

Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@iki.fi>
---
 include/linux/mm_types.h |  3 +++
 include/linux/slab.h     |  9 ++++++-
 mm/slab.c                | 68 +++++++++++++++++++++---------------------------
 3 files changed, 41 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index faf4b7c1ad12..959cb369b197 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -130,6 +130,9 @@ struct page {
 
 		struct list_head list;	/* slobs list of pages */
 		struct slab *slab_page; /* slab fields */
+		struct rcu_head rcu_head;	/* Used by SLAB
+						 * when destroying via RCU
+						 */
 	};
 
 	/* Remainder is not double word aligned */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 6c5cc0ea8713..caaad51fee1f 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -51,7 +51,14 @@
  *  }
  *  rcu_read_unlock();
  *
- * See also the comment on struct slab_rcu in mm/slab.c.
+ * This is useful if we need to approach a kernel structure obliquely,
+ * from its address obtained without the usual locking. We can lock
+ * the structure to stabilize it and check it's still at the given address,
+ * only if we can be sure that the memory has not been meanwhile reused
+ * for some other kind of object (which our subsystem's lock might corrupt).
+ *
+ * rcu_read_lock before reading the address, then rcu_read_unlock after
+ * taking the spinlock within the structure expected at that address.
  */
 #define SLAB_DESTROY_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
 #define SLAB_MEM_SPREAD		0x00100000UL	/* Spread some memory over cpuset */
diff --git a/mm/slab.c b/mm/slab.c
index 7e1aabe2b5d8..84c4ed62c10d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -188,25 +188,6 @@ typedef unsigned int kmem_bufctl_t;
 #define	BUFCTL_ACTIVE	(((kmem_bufctl_t)(~0U))-2)
 #define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-3)
 
-/*
- * struct slab_rcu
- *
- * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
- * arrange for kmem_freepages to be called via RCU.  This is useful if
- * we need to approach a kernel structure obliquely, from its address
- * obtained without the usual locking.  We can lock the structure to
- * stabilize it and check it's still at the given address, only if we
- * can be sure that the memory has not been meanwhile reused for some
- * other kind of object (which our subsystem's lock might corrupt).
- *
- * rcu_read_lock before reading the address, then rcu_read_unlock after
- * taking the spinlock within the structure expected at that address.
- */
-struct slab_rcu {
-	struct rcu_head head;
-	struct page *page;
-};
-
 /*
  * struct slab
  *
@@ -215,14 +196,11 @@ struct slab_rcu {
  * Slabs are chained into three list: fully used, partial, fully free slabs.
  */
 struct slab {
-	union {
-		struct {
-			struct list_head list;
-			void *s_mem;		/* including colour offset */
-			unsigned int inuse;	/* num of objs active in slab */
-			kmem_bufctl_t free;
-		};
-		struct slab_rcu __slab_cover_slab_rcu;
+	struct {
+		struct list_head list;
+		void *s_mem;		/* including colour offset */
+		unsigned int inuse;	/* num of objs active in slab */
+		kmem_bufctl_t free;
 	};
 };
 
@@ -1509,6 +1487,8 @@ void __init kmem_cache_init(void)
 {
 	int i;
 
+	BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
+					sizeof(struct rcu_head));
 	kmem_cache = &kmem_cache_boot;
 	setup_node_pointer(kmem_cache);
 
@@ -1822,12 +1802,13 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 
 static void kmem_rcu_free(struct rcu_head *head)
 {
-	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
-	struct kmem_cache *cachep = slab_rcu->page->slab_cache;
+	struct kmem_cache *cachep;
+	struct page *page;
 
-	kmem_freepages(cachep, slab_rcu->page);
-	if (OFF_SLAB(cachep))
-		kmem_cache_free(cachep->slabp_cache, slab_rcu);
+	page = container_of(head, struct page, rcu_head);
+	cachep = page->slab_cache;
+
+	kmem_freepages(cachep, page);
 }
 
 #if DEBUG
@@ -2048,16 +2029,27 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
 
 	slab_destroy_debugcheck(cachep, slabp);
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
-		struct slab_rcu *slab_rcu;
+		struct rcu_head *head;
+
+		/*
+		 * RCU free overloads the RCU head over the LRU.
+		 * slab_page has been overloeaded over the LRU,
+		 * however it is not used from now on so that
+		 * we can use it safely.
+		 */
+		head = (void *)&page->rcu_head;
+		call_rcu(head, kmem_rcu_free);
 
-		slab_rcu = (struct slab_rcu *)slabp;
-		slab_rcu->page = page;
-		call_rcu(&slab_rcu->head, kmem_rcu_free);
 	} else {
 		kmem_freepages(cachep, page);
-		if (OFF_SLAB(cachep))
-			kmem_cache_free(cachep->slabp_cache, slabp);
 	}
+
+	/*
+	 * From now on, we don't use slab management
+	 * although actual page can be freed in rcu context
+	 */
+	if (OFF_SLAB(cachep))
+		kmem_cache_free(cachep->slabp_cache, slabp);
 }
 
 /**
-- 
cgit 


From 8456a648cf44f14365f1f44de90a3da2526a4776 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 24 Oct 2013 10:07:49 +0900
Subject: slab: use struct page for slab management

Now, there are a few field in struct slab, so we can overload these
over struct page. This will save some memory and reduce cache footprint.

After this change, slabp_cache and slab_size no longer related to
a struct slab, so rename them as freelist_cache and freelist_size.

These changes are just mechanical ones and there is no functional change.

Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@iki.fi>
---
 include/linux/mm_types.h |  21 ++--
 include/linux/slab_def.h |   4 +-
 mm/slab.c                | 306 ++++++++++++++++++++++-------------------------
 3 files changed, 158 insertions(+), 173 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 959cb369b197..95bf0c5a7eb9 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -42,18 +42,22 @@ struct page {
 	/* First double word block */
 	unsigned long flags;		/* Atomic flags, some possibly
 					 * updated asynchronously */
-	struct address_space *mapping;	/* If low bit clear, points to
-					 * inode address_space, or NULL.
-					 * If page mapped as anonymous
-					 * memory, low bit is set, and
-					 * it points to anon_vma object:
-					 * see PAGE_MAPPING_ANON below.
-					 */
+	union {
+		struct address_space *mapping;	/* If low bit clear, points to
+						 * inode address_space, or NULL.
+						 * If page mapped as anonymous
+						 * memory, low bit is set, and
+						 * it points to anon_vma object:
+						 * see PAGE_MAPPING_ANON below.
+						 */
+		void *s_mem;			/* slab first object */
+	};
+
 	/* Second double word */
 	struct {
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
-			void *freelist;		/* slub/slob first free object */
+			void *freelist;		/* sl[aou]b first free object */
 			bool pfmemalloc;	/* If set by the page allocator,
 						 * ALLOC_NO_WATERMARKS was set
 						 * and the low watermark was not
@@ -109,6 +113,7 @@ struct page {
 				};
 				atomic_t _count;		/* Usage count, see below. */
 			};
+			unsigned int active;	/* SLAB */
 		};
 	};
 
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index cd401580bdd3..ca82e8ff89fa 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -41,8 +41,8 @@ struct kmem_cache {
 
 	size_t colour;			/* cache colouring range */
 	unsigned int colour_off;	/* colour offset */
-	struct kmem_cache *slabp_cache;
-	unsigned int slab_size;
+	struct kmem_cache *freelist_cache;
+	unsigned int freelist_size;
 
 	/* constructor func */
 	void (*ctor)(void *obj);
diff --git a/mm/slab.c b/mm/slab.c
index 2ec2336a1ffc..0e7f2e73e08e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -163,21 +163,6 @@
  */
 static bool pfmemalloc_active __read_mostly;
 
-/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
-	struct {
-		struct list_head list;
-		void *s_mem;		/* including colour offset */
-		unsigned int active;	/* num of objs active in slab */
-	};
-};
-
 /*
  * struct array_cache
  *
@@ -405,18 +390,10 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 	return page->slab_cache;
 }
 
-static inline struct slab *virt_to_slab(const void *obj)
-{
-	struct page *page = virt_to_head_page(obj);
-
-	VM_BUG_ON(!PageSlab(page));
-	return page->slab_page;
-}
-
-static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
+static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
 				 unsigned int idx)
 {
-	return slab->s_mem + cache->size * idx;
+	return page->s_mem + cache->size * idx;
 }
 
 /*
@@ -426,9 +403,9 @@ static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
  *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
  */
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
+					const struct page *page, void *obj)
 {
-	u32 offset = (obj - slab->s_mem);
+	u32 offset = (obj - page->s_mem);
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
@@ -590,7 +567,7 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 
 static size_t slab_mgmt_size(size_t nr_objs, size_t align)
 {
-	return ALIGN(sizeof(struct slab)+nr_objs*sizeof(unsigned int), align);
+	return ALIGN(nr_objs * sizeof(unsigned int), align);
 }
 
 /*
@@ -609,7 +586,6 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 	 * on it. For the latter case, the memory allocated for a
 	 * slab is used for:
 	 *
-	 * - The struct slab
 	 * - One unsigned int for each object
 	 * - Padding to respect alignment of @align
 	 * - @buffer_size bytes for each object
@@ -632,8 +608,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		 * into the memory allocation when taking the padding
 		 * into account.
 		 */
-		nr_objs = (slab_size - sizeof(struct slab)) /
-			  (buffer_size + sizeof(unsigned int));
+		nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
 
 		/*
 		 * This calculated number will be either the right
@@ -773,11 +748,11 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 	return nc;
 }
 
-static inline bool is_slab_pfmemalloc(struct slab *slabp)
+static inline bool is_slab_pfmemalloc(struct page *page)
 {
-	struct page *page = virt_to_page(slabp->s_mem);
+	struct page *mem_page = virt_to_page(page->s_mem);
 
-	return PageSlabPfmemalloc(page);
+	return PageSlabPfmemalloc(mem_page);
 }
 
 /* Clears pfmemalloc_active if no slabs have pfmalloc set */
@@ -785,23 +760,23 @@ static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
 						struct array_cache *ac)
 {
 	struct kmem_cache_node *n = cachep->node[numa_mem_id()];
-	struct slab *slabp;
+	struct page *page;
 	unsigned long flags;
 
 	if (!pfmemalloc_active)
 		return;
 
 	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(slabp, &n->slabs_full, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_full, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
-	list_for_each_entry(slabp, &n->slabs_partial, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_partial, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
-	list_for_each_entry(slabp, &n->slabs_free, list)
-		if (is_slab_pfmemalloc(slabp))
+	list_for_each_entry(page, &n->slabs_free, lru)
+		if (is_slab_pfmemalloc(page))
 			goto out;
 
 	pfmemalloc_active = false;
@@ -841,8 +816,8 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
 		 */
 		n = cachep->node[numa_mem_id()];
 		if (!list_empty(&n->slabs_free) && force_refill) {
-			struct slab *slabp = virt_to_slab(objp);
-			ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
+			struct page *page = virt_to_head_page(objp);
+			ClearPageSlabPfmemalloc(virt_to_head_page(page->s_mem));
 			clear_obj_pfmemalloc(&objp);
 			recheck_pfmemalloc_active(cachep, ac);
 			return objp;
@@ -874,9 +849,9 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
 {
 	if (unlikely(pfmemalloc_active)) {
 		/* Some pfmemalloc slabs exist, check if this is one */
-		struct slab *slabp = virt_to_slab(objp);
-		struct page *page = virt_to_head_page(slabp->s_mem);
-		if (PageSlabPfmemalloc(page))
+		struct page *page = virt_to_head_page(objp);
+		struct page *mem_page = virt_to_head_page(page->s_mem);
+		if (PageSlabPfmemalloc(mem_page))
 			set_obj_pfmemalloc(&objp);
 	}
 
@@ -1633,7 +1608,7 @@ static noinline void
 slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 {
 	struct kmem_cache_node *n;
-	struct slab *slabp;
+	struct page *page;
 	unsigned long flags;
 	int node;
 
@@ -1652,15 +1627,15 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 			continue;
 
 		spin_lock_irqsave(&n->list_lock, flags);
-		list_for_each_entry(slabp, &n->slabs_full, list) {
+		list_for_each_entry(page, &n->slabs_full, lru) {
 			active_objs += cachep->num;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_partial, list) {
-			active_objs += slabp->active;
+		list_for_each_entry(page, &n->slabs_partial, lru) {
+			active_objs += page->active;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_free, list)
+		list_for_each_entry(page, &n->slabs_free, lru)
 			num_slabs++;
 
 		free_objects += n->free_objects;
@@ -1746,6 +1721,8 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 	BUG_ON(!PageSlab(page));
 	__ClearPageSlabPfmemalloc(page);
 	__ClearPageSlab(page);
+	page_mapcount_reset(page);
+	page->mapping = NULL;
 
 	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
@@ -1910,19 +1887,19 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 		/* Print some data about the neighboring objects, if they
 		 * exist:
 		 */
-		struct slab *slabp = virt_to_slab(objp);
+		struct page *page = virt_to_head_page(objp);
 		unsigned int objnr;
 
-		objnr = obj_to_index(cachep, slabp, objp);
+		objnr = obj_to_index(cachep, page, objp);
 		if (objnr) {
-			objp = index_to_obj(cachep, slabp, objnr - 1);
+			objp = index_to_obj(cachep, page, objnr - 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
 			       realobj, size);
 			print_objinfo(cachep, objp, 2);
 		}
 		if (objnr + 1 < cachep->num) {
-			objp = index_to_obj(cachep, slabp, objnr + 1);
+			objp = index_to_obj(cachep, page, objnr + 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
 			       realobj, size);
@@ -1933,11 +1910,12 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 #endif
 
 #if DEBUG
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+						struct page *page)
 {
 	int i;
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slabp, i);
+		void *objp = index_to_obj(cachep, page, i);
 
 		if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -1962,7 +1940,8 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab
 	}
 }
 #else
-static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep,
+						struct page *page)
 {
 }
 #endif
@@ -1976,11 +1955,12 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slab
  * Before calling the slab must have been unlinked from the cache.  The
  * cache-lock is not held/needed.
  */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy(struct kmem_cache *cachep, struct page *page)
 {
-	struct page *page = virt_to_head_page(slabp->s_mem);
+	struct freelist *freelist;
 
-	slab_destroy_debugcheck(cachep, slabp);
+	freelist = page->freelist;
+	slab_destroy_debugcheck(cachep, page);
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
 		struct rcu_head *head;
 
@@ -1998,11 +1978,11 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
 	}
 
 	/*
-	 * From now on, we don't use slab management
+	 * From now on, we don't use freelist
 	 * although actual page can be freed in rcu context
 	 */
 	if (OFF_SLAB(cachep))
-		kmem_cache_free(cachep->slabp_cache, slabp);
+		kmem_cache_free(cachep->freelist_cache, freelist);
 }
 
 /**
@@ -2039,7 +2019,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			 * use off-slab slabs. Needed to avoid a possible
 			 * looping condition in cache_grow().
 			 */
-			offslab_limit = size - sizeof(struct slab);
+			offslab_limit = size;
 			offslab_limit /= sizeof(unsigned int);
 
  			if (num > offslab_limit)
@@ -2162,7 +2142,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 int
 __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 {
-	size_t left_over, slab_size, ralign;
+	size_t left_over, freelist_size, ralign;
 	gfp_t gfp;
 	int err;
 	size_t size = cachep->size;
@@ -2281,22 +2261,21 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (!cachep->num)
 		return -E2BIG;
 
-	slab_size = ALIGN(cachep->num * sizeof(unsigned int)
-			  + sizeof(struct slab), cachep->align);
+	freelist_size =
+		ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
 
 	/*
 	 * If the slab has been placed off-slab, and we have enough space then
 	 * move it on-slab. This is at the expense of any extra colouring.
 	 */
-	if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
+	if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) {
 		flags &= ~CFLGS_OFF_SLAB;
-		left_over -= slab_size;
+		left_over -= freelist_size;
 	}
 
 	if (flags & CFLGS_OFF_SLAB) {
 		/* really off slab. No need for manual alignment */
-		slab_size =
-		    cachep->num * sizeof(unsigned int) + sizeof(struct slab);
+		freelist_size = cachep->num * sizeof(unsigned int);
 
 #ifdef CONFIG_PAGE_POISONING
 		/* If we're going to use the generic kernel_map_pages()
@@ -2313,7 +2292,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (cachep->colour_off < cachep->align)
 		cachep->colour_off = cachep->align;
 	cachep->colour = left_over / cachep->colour_off;
-	cachep->slab_size = slab_size;
+	cachep->freelist_size = freelist_size;
 	cachep->flags = flags;
 	cachep->allocflags = __GFP_COMP;
 	if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
@@ -2322,7 +2301,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	cachep->reciprocal_buffer_size = reciprocal_value(size);
 
 	if (flags & CFLGS_OFF_SLAB) {
-		cachep->slabp_cache = kmalloc_slab(slab_size, 0u);
+		cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
 		/*
 		 * This is a possibility for one of the malloc_sizes caches.
 		 * But since we go off slab only for object size greater than
@@ -2330,7 +2309,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		 * this should not happen at all.
 		 * But leave a BUG_ON for some lucky dude.
 		 */
-		BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
+		BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
 	}
 
 	err = setup_cpu_cache(cachep, gfp);
@@ -2436,7 +2415,7 @@ static int drain_freelist(struct kmem_cache *cache,
 {
 	struct list_head *p;
 	int nr_freed;
-	struct slab *slabp;
+	struct page *page;
 
 	nr_freed = 0;
 	while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
@@ -2448,18 +2427,18 @@ static int drain_freelist(struct kmem_cache *cache,
 			goto out;
 		}
 
-		slabp = list_entry(p, struct slab, list);
+		page = list_entry(p, struct page, lru);
 #if DEBUG
-		BUG_ON(slabp->active);
+		BUG_ON(page->active);
 #endif
-		list_del(&slabp->list);
+		list_del(&page->lru);
 		/*
 		 * Safe to drop the lock. The slab is no longer linked
 		 * to the cache.
 		 */
 		n->free_objects -= cache->num;
 		spin_unlock_irq(&n->list_lock);
-		slab_destroy(cache, slabp);
+		slab_destroy(cache, page);
 		nr_freed++;
 	}
 out:
@@ -2542,18 +2521,18 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
  * descriptors in kmem_cache_create, we search through the malloc_sizes array.
  * If we are creating a malloc_sizes cache here it would not be visible to
  * kmem_find_general_cachep till the initialization is complete.
- * Hence we cannot have slabp_cache same as the original cache.
+ * Hence we cannot have freelist_cache same as the original cache.
  */
-static struct slab *alloc_slabmgmt(struct kmem_cache *cachep,
+static struct freelist *alloc_slabmgmt(struct kmem_cache *cachep,
 				   struct page *page, int colour_off,
 				   gfp_t local_flags, int nodeid)
 {
-	struct slab *slabp;
+	struct freelist *freelist;
 	void *addr = page_address(page);
 
 	if (OFF_SLAB(cachep)) {
 		/* Slab management obj is off-slab. */
-		slabp = kmem_cache_alloc_node(cachep->slabp_cache,
+		freelist = kmem_cache_alloc_node(cachep->freelist_cache,
 					      local_flags, nodeid);
 		/*
 		 * If the first object in the slab is leaked (it's allocated
@@ -2561,31 +2540,31 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep,
 		 * kmemleak does not treat the ->s_mem pointer as a reference
 		 * to the object. Otherwise we will not report the leak.
 		 */
-		kmemleak_scan_area(&slabp->list, sizeof(struct list_head),
+		kmemleak_scan_area(&page->lru, sizeof(struct list_head),
 				   local_flags);
-		if (!slabp)
+		if (!freelist)
 			return NULL;
 	} else {
-		slabp = addr + colour_off;
-		colour_off += cachep->slab_size;
+		freelist = addr + colour_off;
+		colour_off += cachep->freelist_size;
 	}
-	slabp->active = 0;
-	slabp->s_mem = addr + colour_off;
-	return slabp;
+	page->active = 0;
+	page->s_mem = addr + colour_off;
+	return freelist;
 }
 
-static inline unsigned int *slab_bufctl(struct slab *slabp)
+static inline unsigned int *slab_bufctl(struct page *page)
 {
-	return (unsigned int *) (slabp + 1);
+	return (unsigned int *)(page->freelist);
 }
 
 static void cache_init_objs(struct kmem_cache *cachep,
-			    struct slab *slabp)
+			    struct page *page)
 {
 	int i;
 
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slabp, i);
+		void *objp = index_to_obj(cachep, page, i);
 #if DEBUG
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON)
@@ -2621,7 +2600,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		if (cachep->ctor)
 			cachep->ctor(objp);
 #endif
-		slab_bufctl(slabp)[i] = i;
+		slab_bufctl(page)[i] = i;
 	}
 }
 
@@ -2635,13 +2614,13 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 	}
 }
 
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
 				int nodeid)
 {
 	void *objp;
 
-	objp = index_to_obj(cachep, slabp, slab_bufctl(slabp)[slabp->active]);
-	slabp->active++;
+	objp = index_to_obj(cachep, page, slab_bufctl(page)[page->active]);
+	page->active++;
 #if DEBUG
 	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
 #endif
@@ -2649,10 +2628,10 @@ static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
 	return objp;
 }
 
-static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
+static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
 				void *objp, int nodeid)
 {
-	unsigned int objnr = obj_to_index(cachep, slabp, objp);
+	unsigned int objnr = obj_to_index(cachep, page, objp);
 #if DEBUG
 	unsigned int i;
 
@@ -2660,16 +2639,16 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
 	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
 
 	/* Verify double free bug */
-	for (i = slabp->active; i < cachep->num; i++) {
-		if (slab_bufctl(slabp)[i] == objnr) {
+	for (i = page->active; i < cachep->num; i++) {
+		if (slab_bufctl(page)[i] == objnr) {
 			printk(KERN_ERR "slab: double free detected in cache "
 					"'%s', objp %p\n", cachep->name, objp);
 			BUG();
 		}
 	}
 #endif
-	slabp->active--;
-	slab_bufctl(slabp)[slabp->active] = objnr;
+	page->active--;
+	slab_bufctl(page)[page->active] = objnr;
 }
 
 /*
@@ -2677,11 +2656,11 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
  * for the slab allocator to be able to lookup the cache and slab of a
  * virtual address for kfree, ksize, and slab debugging.
  */
-static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
-			   struct page *page)
+static void slab_map_pages(struct kmem_cache *cache, struct page *page,
+			   struct freelist *freelist)
 {
 	page->slab_cache = cache;
-	page->slab_page = slab;
+	page->freelist = freelist;
 }
 
 /*
@@ -2691,7 +2670,7 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
 static int cache_grow(struct kmem_cache *cachep,
 		gfp_t flags, int nodeid, struct page *page)
 {
-	struct slab *slabp;
+	struct freelist *freelist;
 	size_t offset;
 	gfp_t local_flags;
 	struct kmem_cache_node *n;
@@ -2738,14 +2717,14 @@ static int cache_grow(struct kmem_cache *cachep,
 		goto failed;
 
 	/* Get slab management. */
-	slabp = alloc_slabmgmt(cachep, page, offset,
+	freelist = alloc_slabmgmt(cachep, page, offset,
 			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
-	if (!slabp)
+	if (!freelist)
 		goto opps1;
 
-	slab_map_pages(cachep, slabp, page);
+	slab_map_pages(cachep, page, freelist);
 
-	cache_init_objs(cachep, slabp);
+	cache_init_objs(cachep, page);
 
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
@@ -2753,7 +2732,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	spin_lock(&n->list_lock);
 
 	/* Make slab active. */
-	list_add_tail(&slabp->list, &(n->slabs_free));
+	list_add_tail(&page->lru, &(n->slabs_free));
 	STATS_INC_GROWN(cachep);
 	n->free_objects += cachep->num;
 	spin_unlock(&n->list_lock);
@@ -2808,13 +2787,13 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 				   unsigned long caller)
 {
 	unsigned int objnr;
-	struct slab *slabp;
+	struct page *page;
 
 	BUG_ON(virt_to_cache(objp) != cachep);
 
 	objp -= obj_offset(cachep);
 	kfree_debugcheck(objp);
-	slabp = virt_to_slab(objp);
+	page = virt_to_head_page(objp);
 
 	if (cachep->flags & SLAB_RED_ZONE) {
 		verify_redzone_free(cachep, objp);
@@ -2824,10 +2803,10 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	if (cachep->flags & SLAB_STORE_USER)
 		*dbg_userword(cachep, objp) = (void *)caller;
 
-	objnr = obj_to_index(cachep, slabp, objp);
+	objnr = obj_to_index(cachep, page, objp);
 
 	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
+	BUG_ON(objp != index_to_obj(cachep, page, objnr));
 
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -2886,7 +2865,7 @@ retry:
 
 	while (batchcount > 0) {
 		struct list_head *entry;
-		struct slab *slabp;
+		struct page *page;
 		/* Get slab alloc is to come from. */
 		entry = n->slabs_partial.next;
 		if (entry == &n->slabs_partial) {
@@ -2896,7 +2875,7 @@ retry:
 				goto must_grow;
 		}
 
-		slabp = list_entry(entry, struct slab, list);
+		page = list_entry(entry, struct page, lru);
 		check_spinlock_acquired(cachep);
 
 		/*
@@ -2904,23 +2883,23 @@ retry:
 		 * there must be at least one object available for
 		 * allocation.
 		 */
-		BUG_ON(slabp->active >= cachep->num);
+		BUG_ON(page->active >= cachep->num);
 
-		while (slabp->active < cachep->num && batchcount--) {
+		while (page->active < cachep->num && batchcount--) {
 			STATS_INC_ALLOCED(cachep);
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+			ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
 									node));
 		}
 
 		/* move slabp to correct slabp list: */
-		list_del(&slabp->list);
-		if (slabp->active == cachep->num)
-			list_add(&slabp->list, &n->slabs_full);
+		list_del(&page->lru);
+		if (page->active == cachep->num)
+			list_add(&page->list, &n->slabs_full);
 		else
-			list_add(&slabp->list, &n->slabs_partial);
+			list_add(&page->list, &n->slabs_partial);
 	}
 
 must_grow:
@@ -3175,7 +3154,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 				int nodeid)
 {
 	struct list_head *entry;
-	struct slab *slabp;
+	struct page *page;
 	struct kmem_cache_node *n;
 	void *obj;
 	int x;
@@ -3195,24 +3174,24 @@ retry:
 			goto must_grow;
 	}
 
-	slabp = list_entry(entry, struct slab, list);
+	page = list_entry(entry, struct page, lru);
 	check_spinlock_acquired_node(cachep, nodeid);
 
 	STATS_INC_NODEALLOCS(cachep);
 	STATS_INC_ACTIVE(cachep);
 	STATS_SET_HIGH(cachep);
 
-	BUG_ON(slabp->active == cachep->num);
+	BUG_ON(page->active == cachep->num);
 
-	obj = slab_get_obj(cachep, slabp, nodeid);
+	obj = slab_get_obj(cachep, page, nodeid);
 	n->free_objects--;
 	/* move slabp to correct slabp list: */
-	list_del(&slabp->list);
+	list_del(&page->lru);
 
-	if (slabp->active == cachep->num)
-		list_add(&slabp->list, &n->slabs_full);
+	if (page->active == cachep->num)
+		list_add(&page->lru, &n->slabs_full);
 	else
-		list_add(&slabp->list, &n->slabs_partial);
+		list_add(&page->lru, &n->slabs_partial);
 
 	spin_unlock(&n->list_lock);
 	goto done;
@@ -3362,21 +3341,21 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 
 	for (i = 0; i < nr_objects; i++) {
 		void *objp;
-		struct slab *slabp;
+		struct page *page;
 
 		clear_obj_pfmemalloc(&objpp[i]);
 		objp = objpp[i];
 
-		slabp = virt_to_slab(objp);
+		page = virt_to_head_page(objp);
 		n = cachep->node[node];
-		list_del(&slabp->list);
+		list_del(&page->lru);
 		check_spinlock_acquired_node(cachep, node);
-		slab_put_obj(cachep, slabp, objp, node);
+		slab_put_obj(cachep, page, objp, node);
 		STATS_DEC_ACTIVE(cachep);
 		n->free_objects++;
 
 		/* fixup slab chains */
-		if (slabp->active == 0) {
+		if (page->active == 0) {
 			if (n->free_objects > n->free_limit) {
 				n->free_objects -= cachep->num;
 				/* No need to drop any previously held
@@ -3385,16 +3364,16 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 				 * a different cache, refer to comments before
 				 * alloc_slabmgmt.
 				 */
-				slab_destroy(cachep, slabp);
+				slab_destroy(cachep, page);
 			} else {
-				list_add(&slabp->list, &n->slabs_free);
+				list_add(&page->lru, &n->slabs_free);
 			}
 		} else {
 			/* Unconditionally move a slab to the end of the
 			 * partial list on free - maximum time for the
 			 * other objects to be freed, too.
 			 */
-			list_add_tail(&slabp->list, &n->slabs_partial);
+			list_add_tail(&page->lru, &n->slabs_partial);
 		}
 	}
 }
@@ -3434,10 +3413,10 @@ free_done:
 
 		p = n->slabs_free.next;
 		while (p != &(n->slabs_free)) {
-			struct slab *slabp;
+			struct page *page;
 
-			slabp = list_entry(p, struct slab, list);
-			BUG_ON(slabp->active);
+			page = list_entry(p, struct page, lru);
+			BUG_ON(page->active);
 
 			i++;
 			p = p->next;
@@ -4041,7 +4020,7 @@ out:
 #ifdef CONFIG_SLABINFO
 void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 {
-	struct slab *slabp;
+	struct page *page;
 	unsigned long active_objs;
 	unsigned long num_objs;
 	unsigned long active_slabs = 0;
@@ -4061,22 +4040,22 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(slabp, &n->slabs_full, list) {
-			if (slabp->active != cachep->num && !error)
+		list_for_each_entry(page, &n->slabs_full, lru) {
+			if (page->active != cachep->num && !error)
 				error = "slabs_full accounting error";
 			active_objs += cachep->num;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_partial, list) {
-			if (slabp->active == cachep->num && !error)
+		list_for_each_entry(page, &n->slabs_partial, lru) {
+			if (page->active == cachep->num && !error)
 				error = "slabs_partial accounting error";
-			if (!slabp->active && !error)
+			if (!page->active && !error)
 				error = "slabs_partial accounting error";
-			active_objs += slabp->active;
+			active_objs += page->active;
 			active_slabs++;
 		}
-		list_for_each_entry(slabp, &n->slabs_free, list) {
-			if (slabp->active && !error)
+		list_for_each_entry(page, &n->slabs_free, lru) {
+			if (page->active && !error)
 				error = "slabs_free accounting error";
 			num_slabs++;
 		}
@@ -4229,19 +4208,20 @@ static inline int add_caller(unsigned long *n, unsigned long v)
 	return 1;
 }
 
-static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+static void handle_slab(unsigned long *n, struct kmem_cache *c,
+						struct page *page)
 {
 	void *p;
 	int i, j;
 
 	if (n[0] == n[1])
 		return;
-	for (i = 0, p = s->s_mem; i < c->num; i++, p += c->size) {
+	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
 		bool active = true;
 
-		for (j = s->active; j < c->num; j++) {
+		for (j = page->active; j < c->num; j++) {
 			/* Skip freed item */
-			if (slab_bufctl(s)[j] == i) {
+			if (slab_bufctl(page)[j] == i) {
 				active = false;
 				break;
 			}
@@ -4273,7 +4253,7 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 static int leaks_show(struct seq_file *m, void *p)
 {
 	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
-	struct slab *slabp;
+	struct page *page;
 	struct kmem_cache_node *n;
 	const char *name;
 	unsigned long *x = m->private;
@@ -4297,10 +4277,10 @@ static int leaks_show(struct seq_file *m, void *p)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(slabp, &n->slabs_full, list)
-			handle_slab(x, cachep, slabp);
-		list_for_each_entry(slabp, &n->slabs_partial, list)
-			handle_slab(x, cachep, slabp);
+		list_for_each_entry(page, &n->slabs_full, lru)
+			handle_slab(x, cachep, page);
+		list_for_each_entry(page, &n->slabs_partial, lru)
+			handle_slab(x, cachep, page);
 		spin_unlock_irq(&n->list_lock);
 	}
 	name = cachep->name;
-- 
cgit 


From 87dc800be2499128efb3a6f059d75dc8e1e6d503 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 16 Sep 2013 10:30:04 -0400
Subject: new helper: kfree_put_link()

duplicated to hell and back...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/cifs/cifsfs.c    |  2 +-
 fs/cifs/cifsfs.h    |  2 --
 fs/cifs/link.c      |  7 -------
 fs/ecryptfs/inode.c | 12 +-----------
 fs/gfs2/inode.c     |  9 +--------
 fs/libfs.c          | 10 ++++++++++
 fs/proc/self.c      | 10 +---------
 include/linux/fs.h  |  1 +
 8 files changed, 15 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index a16b4e58bcc6..801975c34cf9 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -860,7 +860,7 @@ const struct inode_operations cifs_file_inode_ops = {
 const struct inode_operations cifs_symlink_inode_ops = {
 	.readlink = generic_readlink,
 	.follow_link = cifs_follow_link,
-	.put_link = cifs_put_link,
+	.put_link = kfree_put_link,
 	.permission = cifs_permission,
 	/* BB add the following two eventually */
 	/* revalidate: cifs_revalidate,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 6d0b07217ac9..26a754f49ba1 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -115,8 +115,6 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path);
 
 /* Functions related to symlinks */
 extern void *cifs_follow_link(struct dentry *direntry, struct nameidata *nd);
-extern void cifs_put_link(struct dentry *direntry,
-			  struct nameidata *nd, void *);
 extern int cifs_readlink(struct dentry *direntry, char __user *buffer,
 			 int buflen);
 extern int cifs_symlink(struct inode *inode, struct dentry *direntry,
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 7e36ceba0c7a..cc0234710ddb 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -621,10 +621,3 @@ symlink_exit:
 	free_xid(xid);
 	return rc;
 }
-
-void cifs_put_link(struct dentry *direntry, struct nameidata *nd, void *cookie)
-{
-	char *p = nd_get_link(nd);
-	if (!IS_ERR(p))
-		kfree(p);
-}
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 2ca62c40c6c2..0f9b66eaa767 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -703,16 +703,6 @@ out:
 	return NULL;
 }
 
-static void
-ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr)
-{
-	char *buf = nd_get_link(nd);
-	if (!IS_ERR(buf)) {
-		/* Free the char* */
-		kfree(buf);
-	}
-}
-
 /**
  * upper_size_to_lower_size
  * @crypt_stat: Crypt_stat associated with file
@@ -1121,7 +1111,7 @@ out:
 const struct inode_operations ecryptfs_symlink_iops = {
 	.readlink = generic_readlink,
 	.follow_link = ecryptfs_follow_link,
-	.put_link = ecryptfs_put_link,
+	.put_link = kfree_put_link,
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
 	.getattr = ecryptfs_getattr_link,
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index ced3257f06e8..d2384f7c53e1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1506,13 +1506,6 @@ out:
 	return NULL;
 }
 
-static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
-{
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		kfree(s);
-}
-
 /**
  * gfs2_permission -
  * @inode: The inode
@@ -1864,7 +1857,7 @@ const struct inode_operations gfs2_dir_iops = {
 const struct inode_operations gfs2_symlink_iops = {
 	.readlink = generic_readlink,
 	.follow_link = gfs2_follow_link,
-	.put_link = gfs2_put_link,
+	.put_link = kfree_put_link,
 	.permission = gfs2_permission,
 	.setattr = gfs2_setattr,
 	.getattr = gfs2_getattr,
diff --git a/fs/libfs.c b/fs/libfs.c
index 828622a31d30..8c5018493154 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -10,6 +10,7 @@
 #include <linux/vfs.h>
 #include <linux/quotaops.h>
 #include <linux/mutex.h>
+#include <linux/namei.h>
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h> /* sync_mapping_buffers */
@@ -992,3 +993,12 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return 0;
 }
 EXPORT_SYMBOL(noop_fsync);
+
+void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
+				void *cookie)
+{
+	char *s = nd_get_link(nd);
+	if (!IS_ERR(s))
+		kfree(s);
+}
+EXPORT_SYMBOL(kfree_put_link);
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 6b6a993b5c25..ffeb202ec942 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -36,18 +36,10 @@ static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
 	return NULL;
 }
 
-static void proc_self_put_link(struct dentry *dentry, struct nameidata *nd,
-				void *cookie)
-{
-	char *s = nd_get_link(nd);
-	if (!IS_ERR(s))
-		kfree(s);
-}
-
 static const struct inode_operations proc_self_inode_operations = {
 	.readlink	= proc_self_readlink,
 	.follow_link	= proc_self_follow_link,
-	.put_link	= proc_self_put_link,
+	.put_link	= kfree_put_link,
 };
 
 static unsigned self_inum;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f40547ba191..d80c2437d624 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2502,6 +2502,7 @@ extern int __page_symlink(struct inode *inode, const char *symname, int len,
 		int nofs);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
+extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
 extern int vfs_getattr(struct path *, struct kstat *);
-- 
cgit 


From e84f9e57b90ca89664d733a7cef19aa7ccd832f3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Sep 2013 14:17:15 -0400
Subject: consolidate the reassignments of ->f_op in ->open() instances

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/char/misc.c             | 12 +++---------
 drivers/gpu/drm/drm_fops.c      | 17 ++++++-----------
 drivers/media/dvb-core/dvbdev.c | 19 ++++++-------------
 drivers/usb/core/file.c         | 16 ++++------------
 fs/char_dev.c                   |  6 ++++--
 include/linux/fs.h              | 11 +++++++++++
 sound/core/sound.c              | 22 ++++++----------------
 sound/sound_core.c              | 17 +++--------------
 8 files changed, 43 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 190d4423653f..fd0f7c4b4df9 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -114,7 +114,7 @@ static int misc_open(struct inode * inode, struct file * file)
 	int minor = iminor(inode);
 	struct miscdevice *c;
 	int err = -ENODEV;
-	const struct file_operations *old_fops, *new_fops = NULL;
+	const struct file_operations *new_fops = NULL;
 
 	mutex_lock(&misc_mtx);
 	
@@ -141,17 +141,11 @@ static int misc_open(struct inode * inode, struct file * file)
 	}
 
 	err = 0;
-	old_fops = file->f_op;
-	file->f_op = new_fops;
+	replace_fops(file, new_fops);
 	if (file->f_op->open) {
 		file->private_data = c;
-		err=file->f_op->open(inode,file);
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
+		err = file->f_op->open(inode,file);
 	}
-	fops_put(old_fops);
 fail:
 	mutex_unlock(&misc_mtx);
 	return err;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 3f84277d7036..22d14ecbd3ec 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -148,7 +148,7 @@ int drm_stub_open(struct inode *inode, struct file *filp)
 	struct drm_minor *minor;
 	int minor_id = iminor(inode);
 	int err = -ENODEV;
-	const struct file_operations *old_fops;
+	const struct file_operations *new_fops;
 
 	DRM_DEBUG("\n");
 
@@ -163,18 +163,13 @@ int drm_stub_open(struct inode *inode, struct file *filp)
 	if (drm_device_is_unplugged(dev))
 		goto out;
 
-	old_fops = filp->f_op;
-	filp->f_op = fops_get(dev->driver->fops);
-	if (filp->f_op == NULL) {
-		filp->f_op = old_fops;
+	new_fops = fops_get(dev->driver->fops);
+	if (!new_fops)
 		goto out;
-	}
-	if (filp->f_op->open && (err = filp->f_op->open(inode, filp))) {
-		fops_put(filp->f_op);
-		filp->f_op = fops_get(old_fops);
-	}
-	fops_put(old_fops);
 
+	replace_fops(filp, new_fops);
+	if (filp->f_op->open)
+		err = filp->f_op->open(inode, filp);
 out:
 	mutex_unlock(&drm_global_mutex);
 	return err;
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 401ef64f92c6..983db75de350 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -74,22 +74,15 @@ static int dvb_device_open(struct inode *inode, struct file *file)
 
 	if (dvbdev && dvbdev->fops) {
 		int err = 0;
-		const struct file_operations *old_fops;
+		const struct file_operations *new_fops;
 
-		file->private_data = dvbdev;
-		old_fops = file->f_op;
-		file->f_op = fops_get(dvbdev->fops);
-		if (file->f_op == NULL) {
-			file->f_op = old_fops;
+		new_fops = fops_get(dvbdev->fops);
+		if (!new_fops)
 			goto fail;
-		}
-		if(file->f_op->open)
+		file->private_data = dvbdev;
+		replace_fops(file, new_fops);
+		if (file->f_op->open)
 			err = file->f_op->open(inode,file);
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
-		fops_put(old_fops);
 		up_read(&minor_rwsem);
 		mutex_unlock(&dvbdev_mutex);
 		return err;
diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c
index 7421888087a3..fe0d8365411a 100644
--- a/drivers/usb/core/file.c
+++ b/drivers/usb/core/file.c
@@ -29,27 +29,19 @@ static DECLARE_RWSEM(minor_rwsem);
 
 static int usb_open(struct inode * inode, struct file * file)
 {
-	int minor = iminor(inode);
-	const struct file_operations *c;
 	int err = -ENODEV;
-	const struct file_operations *old_fops, *new_fops = NULL;
+	const struct file_operations *new_fops;
 
 	down_read(&minor_rwsem);
-	c = usb_minors[minor];
+	new_fops = fops_get(usb_minors[iminor(inode)]);
 
-	if (!c || !(new_fops = fops_get(c)))
+	if (!new_fops)
 		goto done;
 
-	old_fops = file->f_op;
-	file->f_op = new_fops;
+	replace_fops(file, new_fops);
 	/* Curiouser and curiouser... NULL ->open() as "no device" ? */
 	if (file->f_op->open)
 		err = file->f_op->open(inode,file);
-	if (err) {
-		fops_put(file->f_op);
-		file->f_op = fops_get(old_fops);
-	}
-	fops_put(old_fops);
  done:
 	up_read(&minor_rwsem);
 	return err;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index afc2bb691780..94b5f60076da 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -368,6 +368,7 @@ void cdev_put(struct cdev *p)
  */
 static int chrdev_open(struct inode *inode, struct file *filp)
 {
+	const struct file_operations *fops;
 	struct cdev *p;
 	struct cdev *new = NULL;
 	int ret = 0;
@@ -400,10 +401,11 @@ static int chrdev_open(struct inode *inode, struct file *filp)
 		return ret;
 
 	ret = -ENXIO;
-	filp->f_op = fops_get(p->ops);
-	if (!filp->f_op)
+	fops = fops_get(p->ops);
+	if (!fops)
 		goto out_cdev_put;
 
+	replace_fops(filp, fops);
 	if (filp->f_op->open) {
 		ret = filp->f_op->open(inode, filp);
 		if (ret)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d80c2437d624..b09e4e1d747a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1875,6 +1875,17 @@ extern struct dentry *mount_pseudo(struct file_system_type *, char *,
 	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
 #define fops_put(fops) \
 	do { if (fops) module_put((fops)->owner); } while(0)
+/*
+ * This one is to be used *ONLY* from ->open() instances.
+ * fops must be non-NULL, pinned down *and* module dependencies
+ * should be sufficient to pin the caller down as well.
+ */
+#define replace_fops(f, fops) \
+	do {	\
+		struct file *__file = (f); \
+		fops_put(__file->f_op); \
+		BUG_ON(!(__file->f_op = (fops))); \
+	} while(0)
 
 extern int register_filesystem(struct file_system_type *);
 extern int unregister_filesystem(struct file_system_type *);
diff --git a/sound/core/sound.c b/sound/core/sound.c
index f002bd911dae..437c25ea6403 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -153,7 +153,7 @@ static int snd_open(struct inode *inode, struct file *file)
 {
 	unsigned int minor = iminor(inode);
 	struct snd_minor *mptr = NULL;
-	const struct file_operations *old_fops;
+	const struct file_operations *new_fops;
 	int err = 0;
 
 	if (minor >= ARRAY_SIZE(snd_minors))
@@ -167,24 +167,14 @@ static int snd_open(struct inode *inode, struct file *file)
 			return -ENODEV;
 		}
 	}
-	old_fops = file->f_op;
-	file->f_op = fops_get(mptr->f_ops);
-	if (file->f_op == NULL) {
-		file->f_op = old_fops;
-		err = -ENODEV;
-	}
+	new_fops = fops_get(mptr->f_ops);
 	mutex_unlock(&sound_mutex);
-	if (err < 0)
-		return err;
+	if (!new_fops)
+		return -ENODEV;
+	replace_fops(file, new_fops);
 
-	if (file->f_op->open) {
+	if (file->f_op->open)
 		err = file->f_op->open(inode, file);
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
-	}
-	fops_put(old_fops);
 	return err;
 }
 
diff --git a/sound/sound_core.c b/sound/sound_core.c
index 45759f4cca75..11e953a1fa45 100644
--- a/sound/sound_core.c
+++ b/sound/sound_core.c
@@ -626,31 +626,20 @@ static int soundcore_open(struct inode *inode, struct file *file)
 		if (s)
 			new_fops = fops_get(s->unit_fops);
 	}
+	spin_unlock(&sound_loader_lock);
 	if (new_fops) {
 		/*
 		 * We rely upon the fact that we can't be unloaded while the
-		 * subdriver is there, so if ->open() is successful we can
-		 * safely drop the reference counter and if it is not we can
-		 * revert to old ->f_op. Ugly, indeed, but that's the cost of
-		 * switching ->f_op in the first place.
+		 * subdriver is there.
 		 */
 		int err = 0;
-		const struct file_operations *old_fops = file->f_op;
-		file->f_op = new_fops;
-		spin_unlock(&sound_loader_lock);
+		replace_fops(file, new_fops);
 
 		if (file->f_op->open)
 			err = file->f_op->open(inode,file);
 
-		if (err) {
-			fops_put(file->f_op);
-			file->f_op = fops_get(old_fops);
-		}
-
-		fops_put(old_fops);
 		return err;
 	}
-	spin_unlock(&sound_loader_lock);
 	return -ENODEV;
 }
 
-- 
cgit 


From b70a80e7a133a0c86f2fa078e7c144597c516415 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 1 Oct 2013 16:44:54 +0200
Subject: vfs: introduce d_instantiate_no_diralias()

...which just returns -EBUSY if a directory alias would be created.

This is to be used by fuse mkdir to make sure that a buggy or malicious
userspace filesystem doesn't do anything nasty.  Previously fuse used a
private mutex for this purpose, which can now go away.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/dcache.c            | 27 +++++++++++++++++++++++++++
 fs/fuse/dir.c          | 40 +++++-----------------------------------
 fs/fuse/fuse_i.h       |  3 ---
 fs/fuse/inode.c        |  2 --
 include/linux/dcache.h |  1 +
 5 files changed, 33 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index d888223a5486..c8e83d0d61ac 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1801,6 +1801,33 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 
 EXPORT_SYMBOL(d_instantiate_unique);
 
+/**
+ * d_instantiate_no_diralias - instantiate a non-aliased dentry
+ * @entry: dentry to complete
+ * @inode: inode to attach to this dentry
+ *
+ * Fill in inode information in the entry.  If a directory alias is found, then
+ * return an error (and drop inode).  Together with d_materialise_unique() this
+ * guarantees that a directory inode may never have more than one alias.
+ */
+int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
+{
+	BUG_ON(!hlist_unhashed(&entry->d_alias));
+
+	spin_lock(&inode->i_lock);
+	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
+		spin_unlock(&inode->i_lock);
+		iput(inode);
+		return -EBUSY;
+	}
+	__d_instantiate(entry, inode);
+	spin_unlock(&inode->i_lock);
+	security_d_instantiate(entry, inode);
+
+	return 0;
+}
+EXPORT_SYMBOL(d_instantiate_no_diralias);
+
 struct dentry *d_make_root(struct inode *root_inode)
 {
 	struct dentry *res = NULL;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b7989f2ab4c4..c3eb2c46c8f1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -342,24 +342,6 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 	return err;
 }
 
-static struct dentry *fuse_materialise_dentry(struct dentry *dentry,
-					      struct inode *inode)
-{
-	struct dentry *newent;
-
-	if (inode && S_ISDIR(inode->i_mode)) {
-		struct fuse_conn *fc = get_fuse_conn(inode);
-
-		mutex_lock(&fc->inst_mutex);
-		newent = d_materialise_unique(dentry, inode);
-		mutex_unlock(&fc->inst_mutex);
-	} else {
-		newent = d_materialise_unique(dentry, inode);
-	}
-
-	return newent;
-}
-
 static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 				  unsigned int flags)
 {
@@ -382,7 +364,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	if (inode && get_node_id(inode) == FUSE_ROOT_ID)
 		goto out_iput;
 
-	newent = fuse_materialise_dentry(entry, inode);
+	newent = d_materialise_unique(entry, inode);
 	err = PTR_ERR(newent);
 	if (IS_ERR(newent))
 		goto out_err;
@@ -601,21 +583,9 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
 	}
 	kfree(forget);
 
-	if (S_ISDIR(inode->i_mode)) {
-		struct dentry *alias;
-		mutex_lock(&fc->inst_mutex);
-		alias = d_find_alias(inode);
-		if (alias) {
-			/* New directory must have moved since mkdir */
-			mutex_unlock(&fc->inst_mutex);
-			dput(alias);
-			iput(inode);
-			return -EBUSY;
-		}
-		d_instantiate(entry, inode);
-		mutex_unlock(&fc->inst_mutex);
-	} else
-		d_instantiate(entry, inode);
+	err = d_instantiate_no_diralias(entry, inode);
+	if (err)
+		return err;
 
 	fuse_change_entry_timeout(entry, &outarg);
 	fuse_invalidate_attr(dir);
@@ -1284,7 +1254,7 @@ static int fuse_direntplus_link(struct file *file,
 	if (!inode)
 		goto out;
 
-	alias = fuse_materialise_dentry(dentry, inode);
+	alias = d_materialise_unique(dentry, inode);
 	err = PTR_ERR(alias);
 	if (IS_ERR(alias))
 		goto out;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 5b9e6f3b6aef..fe446c222e3f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -374,9 +374,6 @@ struct fuse_conn {
 	/** Lock protecting accessess to  members of this structure */
 	spinlock_t lock;
 
-	/** Mutex protecting against directory alias creation */
-	struct mutex inst_mutex;
-
 	/** Refcount */
 	atomic_t count;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index a8ce6dab60a0..1c15613c64f8 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -565,7 +565,6 @@ void fuse_conn_init(struct fuse_conn *fc)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
-	mutex_init(&fc->inst_mutex);
 	init_rwsem(&fc->killsb);
 	atomic_set(&fc->count, 1);
 	init_waitqueue_head(&fc->waitq);
@@ -596,7 +595,6 @@ void fuse_conn_put(struct fuse_conn *fc)
 	if (atomic_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
-		mutex_destroy(&fc->inst_mutex);
 		fc->release(fc);
 	}
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 59066e0b4ff1..716c3760ee39 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -224,6 +224,7 @@ static inline int dname_external(const struct dentry *dentry)
 extern void d_instantiate(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_materialise_unique(struct dentry *, struct inode *);
+extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-- 
cgit 


From e2fec7c35582e7bb41cccc1761faa2af4dc17627 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 4 Oct 2013 17:06:56 -0400
Subject: make freeing super_block rcu-delayed

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/super.c         | 2 +-
 include/linux/fs.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index efa6e488a95c..743bb7118053 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -149,7 +149,7 @@ static void destroy_super(struct super_block *s)
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
 	kfree(s->s_options);
-	kfree(s);
+	kfree_rcu(s, rcu);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b09e4e1d747a..2ab8a67ee054 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1330,6 +1330,7 @@ struct super_block {
 	 */
 	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
 	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
+	struct rcu_head		rcu;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
-- 
cgit 


From 1adfcb03e31ba0d6be5fddf773da4357d0792cbb Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 3 Oct 2013 13:28:06 -0400
Subject: pid_namespace: make freeing struct pid_namespace rcu-delayed

makes procfs ->premission() instances safety in RCU mode independent
from vfsmount_lock.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/pid_namespace.h | 1 +
 kernel/pid_namespace.c        | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index e2772666f004..7246ef3d4455 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -23,6 +23,7 @@ struct bsd_acct_struct;
 struct pid_namespace {
 	struct kref kref;
 	struct pidmap pidmap[PIDMAP_ENTRIES];
+	struct rcu_head rcu;
 	int last_pid;
 	unsigned int nr_hashed;
 	struct task_struct *child_reaper;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 42086551a24a..06c62de9c711 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -132,6 +132,12 @@ out:
 	return ERR_PTR(err);
 }
 
+static void delayed_free_pidns(struct rcu_head *p)
+{
+	kmem_cache_free(pid_ns_cachep,
+			container_of(p, struct pid_namespace, rcu));
+}
+
 static void destroy_pid_namespace(struct pid_namespace *ns)
 {
 	int i;
@@ -140,7 +146,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns)
 	for (i = 0; i < PIDMAP_ENTRIES; i++)
 		kfree(ns->pidmap[i].page);
 	put_user_ns(ns->user_ns);
-	kmem_cache_free(pid_ns_cachep, ns);
+	call_rcu(&ns->rcu, delayed_free_pidns);
 }
 
 struct pid_namespace *copy_pid_ns(unsigned long flags,
-- 
cgit 


From adfedd9a32e4e3490c0060576fd824881572b72a Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Wed, 16 Oct 2013 13:29:02 +0530
Subject: dmaengine: use DMA_COMPLETE for dma completion status

the DMA_SUCCESS is a misnomer as dmaengine indicates the transfer is complete and
gives no guarantee of the transfer success. Hence we should use DMA_COMPLTE
instead of DMA_SUCCESS

Acked-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/dmaengine.c   |  2 +-
 include/linux/dmaengine.h | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 9162ac80c18f..81d876528c70 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1062,7 +1062,7 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
 
 	if (!tx)
-		return DMA_SUCCESS;
+		return DMA_COMPLETE;
 
 	while (tx->cookie == -EBUSY) {
 		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 0bc727534108..120e64c96478 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -45,13 +45,13 @@ static inline int dma_submit_error(dma_cookie_t cookie)
 
 /**
  * enum dma_status - DMA transaction status
- * @DMA_SUCCESS: transaction completed successfully
+ * @DMA_COMPLETE: transaction completed
  * @DMA_IN_PROGRESS: transaction not yet processed
  * @DMA_PAUSED: transaction is paused
  * @DMA_ERROR: transaction failed
  */
 enum dma_status {
-	DMA_SUCCESS,
+	DMA_SUCCESS = 0, DMA_COMPLETE = 0,
 	DMA_IN_PROGRESS,
 	DMA_PAUSED,
 	DMA_ERROR,
@@ -979,10 +979,10 @@ static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie,
 {
 	if (last_complete <= last_used) {
 		if ((cookie <= last_complete) || (cookie > last_used))
-			return DMA_SUCCESS;
+			return DMA_COMPLETE;
 	} else {
 		if ((cookie <= last_complete) && (cookie > last_used))
-			return DMA_SUCCESS;
+			return DMA_COMPLETE;
 	}
 	return DMA_IN_PROGRESS;
 }
@@ -1013,11 +1013,11 @@ static inline struct dma_chan *dma_find_channel(enum dma_transaction_type tx_typ
 }
 static inline enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 {
-	return DMA_SUCCESS;
+	return DMA_COMPLETE;
 }
 static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 {
-	return DMA_SUCCESS;
+	return DMA_COMPLETE;
 }
 static inline void dma_issue_pending_all(void)
 {
-- 
cgit 


From 7db5f7274a0b065abdc358be2a44b4a911d75707 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Thu, 17 Oct 2013 07:29:57 +0530
Subject: dmaengine: remove unused DMA_SUCCESS

after all the users are converted

Acked-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 120e64c96478..4b460a683968 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -51,7 +51,7 @@ static inline int dma_submit_error(dma_cookie_t cookie)
  * @DMA_ERROR: transaction failed
  */
 enum dma_status {
-	DMA_SUCCESS = 0, DMA_COMPLETE = 0,
+	DMA_COMPLETE,
 	DMA_IN_PROGRESS,
 	DMA_PAUSED,
 	DMA_ERROR,
-- 
cgit 


From 26c6b8879911df991dc780c67eaeb84c7629949d Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Date: Thu, 24 Oct 2013 17:53:29 +0900
Subject: f2fs: add tracepoint for set_page_dirty

This patch adds a tracepoint for set_page_dirty.

Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 fs/f2fs/checkpoint.c        |  2 ++
 fs/f2fs/data.c              |  2 ++
 fs/f2fs/node.c              |  2 ++
 include/trace/events/f2fs.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5649a9d8e942..6526f5010621 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -167,6 +167,8 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 	struct address_space *mapping = page->mapping;
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 
+	trace_f2fs_set_page_dirty(page, META);
+
 	SetPageUptodate(page);
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 1cccf98f0e4d..c8887d847dcf 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -756,6 +756,8 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
 
+	trace_f2fs_set_page_dirty(page, DATA);
+
 	SetPageUptodate(page);
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7bac4815f1d6..304d5ced6355 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1225,6 +1225,8 @@ static int f2fs_set_node_page_dirty(struct page *page)
 	struct address_space *mapping = page->mapping;
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 
+	trace_f2fs_set_page_dirty(page, NODE);
+
 	SetPageUptodate(page);
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 52ae54828eda..ebde3afb89cd 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -36,6 +36,11 @@
 		{ CURSEG_COLD_NODE, 	"Cold NODE" },			\
 		{ NO_CHECK_TYPE, 	"No TYPE" })
 
+#define show_file_type(type)						\
+	__print_symbolic(type,						\
+		{ 0,		"FILE" },				\
+		{ 1,		"DIR" })
+
 #define show_gc_type(type)						\
 	__print_symbolic(type,						\
 		{ FG_GC,	"Foreground GC" },			\
@@ -623,6 +628,45 @@ TRACE_EVENT(f2fs_do_submit_bio,
 		__entry->size)
 );
 
+DECLARE_EVENT_CLASS(f2fs__page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int, type)
+		__field(int, dir)
+		__field(pgoff_t, index)
+		__field(int, dirty)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= page->mapping->host->i_sb->s_dev;
+		__entry->ino	= page->mapping->host->i_ino;
+		__entry->type	= type;
+		__entry->dir	= S_ISDIR(page->mapping->host->i_mode);
+		__entry->index	= page->index;
+		__entry->dirty	= PageDirty(page);
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, dirty = %d",
+		show_dev_ino(__entry),
+		show_block_type(__entry->type),
+		show_file_type(__entry->dir),
+		(unsigned long)__entry->index,
+		__entry->dirty)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 TRACE_EVENT(f2fs_submit_write_page,
 
 	TP_PROTO(struct page *page, block_t blk_addr, int type),
-- 
cgit 


From e943a10d94f6076f7bc8da91828cbdca5fbf62fc Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Date: Fri, 25 Oct 2013 14:26:31 +0900
Subject: f2fs: add tracepoint for vm_page_mkwrite

This patch adds a tracepoint for f2fs_vm_page_mkwrite.

Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 fs/f2fs/file.c              | 1 +
 include/trace/events/f2fs.h | 7 +++++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index c80faa2fff39..2d4190a4abe3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -88,6 +88,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	set_page_dirty(page);
 	SetPageUptodate(page);
 
+	trace_f2fs_vm_page_mkwrite(page, DATA);
 mapped:
 	/* fill the page */
 	wait_on_page_writeback(page);
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index ebde3afb89cd..e0dc355fa317 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -667,6 +667,13 @@ DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
 	TP_ARGS(page, type)
 );
 
+DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 TRACE_EVENT(f2fs_submit_write_page,
 
 	TP_PROTO(struct page *page, block_t blk_addr, int type),
-- 
cgit 


From 3af142fea7da55718b733b25be9d54ddb87acfcc Mon Sep 17 00:00:00 2001
From: Adheer Chandravanshi <adheer.chandravanshi@qlogic.com>
Date: Tue, 17 Sep 2013 07:54:48 -0400
Subject: [SCSI] scsi_transport_iscsi: Add support to set CHAP entries

For offload iSCSI like qla4xxx, CHAP entries are stored in adapter's
flash.
This patch adds support to add/update CHAP entries in adapter's flash
using iscsi tools, like Open-iSCSI.

Signed-off-by: Adheer Chandravanshi <adheer.chandravanshi@qlogic.com>
Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/scsi_transport_iscsi.c | 26 ++++++++++++++++++++++++++
 include/scsi/iscsi_if.h             | 17 +++++++++++++++++
 include/scsi/scsi_transport_iscsi.h |  1 +
 3 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index e4a989fa477d..63a6ca49d4e5 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2744,6 +2744,28 @@ exit_get_chap:
 	return err;
 }
 
+static int iscsi_set_chap(struct iscsi_transport *transport,
+			  struct iscsi_uevent *ev, uint32_t len)
+{
+	char *data = (char *)ev + sizeof(*ev);
+	struct Scsi_Host *shost;
+	int err = 0;
+
+	if (!transport->set_chap)
+		return -ENOSYS;
+
+	shost = scsi_host_lookup(ev->u.set_path.host_no);
+	if (!shost) {
+		pr_err("%s could not find host no %u\n",
+		       __func__, ev->u.set_path.host_no);
+		return -ENODEV;
+	}
+
+	err = transport->set_chap(shost, data, len);
+	scsi_host_put(shost);
+	return err;
+}
+
 static int iscsi_delete_chap(struct iscsi_transport *transport,
 			     struct iscsi_uevent *ev)
 {
@@ -3234,6 +3256,10 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 	case ISCSI_UEVENT_LOGOUT_FLASHNODE_SID:
 		err = iscsi_logout_flashnode_sid(transport, ev);
 		break;
+	case ISCSI_UEVENT_SET_CHAP:
+		err = iscsi_set_chap(transport, ev,
+				     nlmsg_attrlen(nlh, sizeof(*ev)));
+		break;
 	default:
 		err = -ENOSYS;
 		break;
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index 13d81c5c4ebf..5d6ed6cf12cc 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -69,6 +69,7 @@ enum iscsi_uevent_e {
 	ISCSI_UEVENT_LOGIN_FLASHNODE	= UEVENT_BASE + 28,
 	ISCSI_UEVENT_LOGOUT_FLASHNODE	= UEVENT_BASE + 29,
 	ISCSI_UEVENT_LOGOUT_FLASHNODE_SID	= UEVENT_BASE + 30,
+	ISCSI_UEVENT_SET_CHAP		= UEVENT_BASE + 31,
 
 	/* up events */
 	ISCSI_KEVENT_RECV_PDU		= KEVENT_BASE + 1,
@@ -309,8 +310,16 @@ enum iscsi_param_type {
 	ISCSI_HOST_PARAM,	/* iscsi_host_param */
 	ISCSI_NET_PARAM,	/* iscsi_net_param */
 	ISCSI_FLASHNODE_PARAM,	/* iscsi_flashnode_param */
+	ISCSI_CHAP_PARAM,	/* iscsi_chap_param */
 };
 
+/* structure for minimalist usecase */
+struct iscsi_param_info {
+	uint32_t len;		/* Actual length of the param value */
+	uint16_t param;		/* iscsi param */
+	uint8_t value[0];	/* length sized value follows */
+} __packed;
+
 struct iscsi_iface_param_info {
 	uint32_t iface_num;	/* iface number, 0 - n */
 	uint32_t len;		/* Actual length of the param */
@@ -739,6 +748,14 @@ enum chap_type_e {
 	CHAP_TYPE_IN,
 };
 
+enum iscsi_chap_param {
+	ISCSI_CHAP_PARAM_INDEX,
+	ISCSI_CHAP_PARAM_CHAP_TYPE,
+	ISCSI_CHAP_PARAM_USERNAME,
+	ISCSI_CHAP_PARAM_PASSWORD,
+	ISCSI_CHAP_PARAM_PASSWORD_LEN
+};
+
 #define ISCSI_CHAP_AUTH_NAME_MAX_LEN	256
 #define ISCSI_CHAP_AUTH_SECRET_MAX_LEN	256
 struct iscsi_chap_rec {
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index d0f1602985e7..fe7c8f3e93f8 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -152,6 +152,7 @@ struct iscsi_transport {
 	int (*get_chap) (struct Scsi_Host *shost, uint16_t chap_tbl_idx,
 			 uint32_t *num_entries, char *buf);
 	int (*delete_chap) (struct Scsi_Host *shost, uint16_t chap_tbl_idx);
+	int (*set_chap) (struct Scsi_Host *shost, void *data, int len);
 	int (*get_flashnode_param) (struct iscsi_bus_flash_session *fnode_sess,
 				    int param, char *buf);
 	int (*set_flashnode_param) (struct iscsi_bus_flash_session *fnode_sess,
-- 
cgit 


From 5953316dbf90067ebdeca626c34488bc166b73a8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 23 May 2013 12:25:08 +0200
Subject: block: make rq->cmd_flags be 64-bit

We have officially run out of flags in a 32-bit space. Extend it
to 64-bit even on 32-bit archs.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          |  4 +--
 drivers/block/floppy.c    |  4 +--
 drivers/scsi/sd.c         |  2 +-
 include/linux/blk_types.h | 66 +++++++++++++++++++++++------------------------
 include/linux/blkdev.h    |  4 +--
 5 files changed, 40 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 0a00e4ecf87c..213e9f01c627 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -174,9 +174,9 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 {
 	int bit;
 
-	printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
+	printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
 		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
-		rq->cmd_flags);
+		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
 	       (unsigned long long)blk_rq_pos(rq),
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 04ceb7e2fadd..000abe2f105c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2886,9 +2886,9 @@ static void do_fd_request(struct request_queue *q)
 		return;
 
 	if (WARN(atomic_read(&usage_count) == 0,
-		 "warning: usage count=0, current_req=%p sect=%ld type=%x flags=%x\n",
+		 "warning: usage count=0, current_req=%p sect=%ld type=%x flags=%llx\n",
 		 current_req, (long)blk_rq_pos(current_req), current_req->cmd_type,
-		 current_req->cmd_flags))
+		 (unsigned long long) current_req->cmd_flags))
 		return;
 
 	if (test_and_set_bit(0, &fdc_busy)) {
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index e62d17d41d4e..dae6133a538d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1002,7 +1002,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 		SCpnt->cmnd[0] = READ_6;
 		SCpnt->sc_data_direction = DMA_FROM_DEVICE;
 	} else {
-		scmd_printk(KERN_ERR, SCpnt, "Unknown command %x\n", rq->cmd_flags);
+		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llx\n", (unsigned long long) rq->cmd_flags);
 		goto out;
 	}
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index fa1abeb45b76..c26801e14788 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -181,16 +181,16 @@ enum rq_flag_bits {
 	__REQ_NR_BITS,		/* stops here */
 };
 
-#define REQ_WRITE		(1 << __REQ_WRITE)
-#define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
-#define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
-#define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
-#define REQ_SYNC		(1 << __REQ_SYNC)
-#define REQ_META		(1 << __REQ_META)
-#define REQ_PRIO		(1 << __REQ_PRIO)
-#define REQ_DISCARD		(1 << __REQ_DISCARD)
-#define REQ_WRITE_SAME		(1 << __REQ_WRITE_SAME)
-#define REQ_NOIDLE		(1 << __REQ_NOIDLE)
+#define REQ_WRITE		(1ULL << __REQ_WRITE)
+#define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
+#define REQ_SYNC		(1ULL << __REQ_SYNC)
+#define REQ_META		(1ULL << __REQ_META)
+#define REQ_PRIO		(1ULL << __REQ_PRIO)
+#define REQ_DISCARD		(1ULL << __REQ_DISCARD)
+#define REQ_WRITE_SAME		(1ULL << __REQ_WRITE_SAME)
+#define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -206,28 +206,28 @@ enum rq_flag_bits {
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
 
-#define REQ_RAHEAD		(1 << __REQ_RAHEAD)
-#define REQ_THROTTLED		(1 << __REQ_THROTTLED)
-
-#define REQ_SORTED		(1 << __REQ_SORTED)
-#define REQ_SOFTBARRIER		(1 << __REQ_SOFTBARRIER)
-#define REQ_FUA			(1 << __REQ_FUA)
-#define REQ_NOMERGE		(1 << __REQ_NOMERGE)
-#define REQ_STARTED		(1 << __REQ_STARTED)
-#define REQ_DONTPREP		(1 << __REQ_DONTPREP)
-#define REQ_QUEUED		(1 << __REQ_QUEUED)
-#define REQ_ELVPRIV		(1 << __REQ_ELVPRIV)
-#define REQ_FAILED		(1 << __REQ_FAILED)
-#define REQ_QUIET		(1 << __REQ_QUIET)
-#define REQ_PREEMPT		(1 << __REQ_PREEMPT)
-#define REQ_ALLOCED		(1 << __REQ_ALLOCED)
-#define REQ_COPY_USER		(1 << __REQ_COPY_USER)
-#define REQ_FLUSH		(1 << __REQ_FLUSH)
-#define REQ_FLUSH_SEQ		(1 << __REQ_FLUSH_SEQ)
-#define REQ_IO_STAT		(1 << __REQ_IO_STAT)
-#define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
-#define REQ_SECURE		(1 << __REQ_SECURE)
-#define REQ_KERNEL		(1 << __REQ_KERNEL)
-#define REQ_PM			(1 << __REQ_PM)
+#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
+#define REQ_THROTTLED		(1ULL << __REQ_THROTTLED)
+
+#define REQ_SORTED		(1ULL << __REQ_SORTED)
+#define REQ_SOFTBARRIER		(1ULL << __REQ_SOFTBARRIER)
+#define REQ_FUA			(1ULL << __REQ_FUA)
+#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
+#define REQ_STARTED		(1ULL << __REQ_STARTED)
+#define REQ_DONTPREP		(1ULL << __REQ_DONTPREP)
+#define REQ_QUEUED		(1ULL << __REQ_QUEUED)
+#define REQ_ELVPRIV		(1ULL << __REQ_ELVPRIV)
+#define REQ_FAILED		(1ULL << __REQ_FAILED)
+#define REQ_QUIET		(1ULL << __REQ_QUIET)
+#define REQ_PREEMPT		(1ULL << __REQ_PREEMPT)
+#define REQ_ALLOCED		(1ULL << __REQ_ALLOCED)
+#define REQ_COPY_USER		(1ULL << __REQ_COPY_USER)
+#define REQ_FLUSH		(1ULL << __REQ_FLUSH)
+#define REQ_FLUSH_SEQ		(1ULL << __REQ_FLUSH_SEQ)
+#define REQ_IO_STAT		(1ULL << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE		(1ULL << __REQ_MIXED_MERGE)
+#define REQ_SECURE		(1ULL << __REQ_SECURE)
+#define REQ_KERNEL		(1ULL << __REQ_KERNEL)
+#define REQ_PM			(1ULL << __REQ_PM)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0e6f765aa1f5..f5c7596c93dd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -99,7 +99,7 @@ struct request {
 
 	struct request_queue *q;
 
-	unsigned int cmd_flags;
+	u64 cmd_flags;
 	enum rq_cmd_type_bits cmd_type;
 	unsigned long atomic_flags;
 
@@ -570,7 +570,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq)		((rq)->cmd_flags & 1)
+#define rq_data_dir(rq)		(((rq)->cmd_flags & 1) != 0)
 
 static inline unsigned int blk_queue_cluster(struct request_queue *q)
 {
-- 
cgit 


From 71fe07d040626de7b72244bf6de889c2e0f5aea3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Fri, 4 Oct 2013 06:49:11 -0700
Subject: block: remove request ref_count

This reference count has been around since before git history, but the only
place where it's used is in blk_execute_rq, and ther it is entirely useless
as it is incremented before submitting the request and decremented in the
end_io handler before waking up the submitter thread.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 3 ---
 block/blk-exec.c       | 7 -------
 include/linux/blkdev.h | 2 --
 3 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 213e9f01c627..18faa7e81d3b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -145,7 +145,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->cmd = rq->__cmd;
 	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
-	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
@@ -1272,8 +1271,6 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 {
 	if (unlikely(!q))
 		return;
-	if (unlikely(--req->ref_count))
-		return;
 
 	blk_pm_put_request(req);
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index ae4f27d7944e..6b18d82d91c5 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -24,7 +24,6 @@ static void blk_end_sync_rq(struct request *rq, int error)
 	struct completion *waiting = rq->end_io_data;
 
 	rq->end_io_data = NULL;
-	__blk_put_request(rq->q, rq);
 
 	/*
 	 * complete last, if this is a stack request the process (and thus
@@ -103,12 +102,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	int err = 0;
 	unsigned long hang_check;
 
-	/*
-	 * we need an extra reference to the request, so we can look at
-	 * it after io completion
-	 */
-	rq->ref_count++;
-
 	if (!rq->sense) {
 		memset(sense, 0, sizeof(sense));
 		rq->sense = sense;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f5c7596c93dd..0a8da96274c3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -160,8 +160,6 @@ struct request {
 
 	unsigned short ioprio;
 
-	int ref_count;
-
 	void *special;		/* opaque pointer available for LLD use */
 	char *buffer;		/* kaddr of the current segment if available */
 
-- 
cgit 


From e26b53d0b287056646a0dffce8bc6b0f053f3823 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@kernel.org>
Date: Tue, 15 Oct 2013 09:05:01 +0800
Subject: percpu_ida: make percpu_ida percpu size/batch configurable

Make percpu_ida percpu size/batch configurable. The block-mq-tag will
use it.

After block-mq uses percpu_ida to manage tags, performance is improved.
My test is done in a 2 sockets machine, 12 process cross the 2 sockets.
So if there is lock contention or ipi, should be stressed heavily.
Testing is done for null-blk.

hw_queue_depth	nopatch iops	patch iops
64		~800k/s		~1470k/s
2048		~4470k/s	~4340k/s

Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/percpu_ida.h | 18 +++++++++++++++++-
 lib/percpu_ida.c           | 28 +++++++++++-----------------
 2 files changed, 28 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 0b23edbee309..56c14033e7e7 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -16,6 +16,8 @@ struct percpu_ida {
 	 * percpu_ida_init()
 	 */
 	unsigned			nr_tags;
+	unsigned			percpu_max_size;
+	unsigned			percpu_batch_size;
 
 	struct percpu_ida_cpu __percpu	*tag_cpu;
 
@@ -51,10 +53,24 @@ struct percpu_ida {
 	} ____cacheline_aligned_in_smp;
 };
 
+/*
+ * Number of tags we move between the percpu freelist and the global freelist at
+ * a time
+ */
+#define IDA_DEFAULT_PCPU_BATCH_MOVE	32U
+/* Max size of percpu freelist, */
+#define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
+
 int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
 void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
 
 void percpu_ida_destroy(struct percpu_ida *pool);
-int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags);
+int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
+	unsigned long max_size, unsigned long batch_size);
+static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+{
+	return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE,
+		IDA_DEFAULT_PCPU_BATCH_MOVE);
+}
 
 #endif /* __PERCPU_IDA_H__ */
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index bab1ba2a4c71..a601d4259e13 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -30,15 +30,6 @@
 #include <linux/spinlock.h>
 #include <linux/percpu_ida.h>
 
-/*
- * Number of tags we move between the percpu freelist and the global freelist at
- * a time
- */
-#define IDA_PCPU_BATCH_MOVE	32U
-
-/* Max size of percpu freelist, */
-#define IDA_PCPU_SIZE		((IDA_PCPU_BATCH_MOVE * 3) / 2)
-
 struct percpu_ida_cpu {
 	/*
 	 * Even though this is percpu, we need a lock for tag stealing by remote
@@ -78,7 +69,7 @@ static inline void steal_tags(struct percpu_ida *pool,
 	struct percpu_ida_cpu *remote;
 
 	for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
-	     cpus_have_tags * IDA_PCPU_SIZE > pool->nr_tags / 2;
+	     cpus_have_tags * pool->percpu_max_size > pool->nr_tags / 2;
 	     cpus_have_tags--) {
 		cpu = cpumask_next(cpu, &pool->cpus_have_tags);
 
@@ -123,7 +114,7 @@ static inline void alloc_global_tags(struct percpu_ida *pool,
 {
 	move_tags(tags->freelist, &tags->nr_free,
 		  pool->freelist, &pool->nr_free,
-		  min(pool->nr_free, IDA_PCPU_BATCH_MOVE));
+		  min(pool->nr_free, pool->percpu_batch_size));
 }
 
 static inline unsigned alloc_local_tag(struct percpu_ida *pool,
@@ -245,17 +236,17 @@ void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
 		wake_up(&pool->wait);
 	}
 
-	if (nr_free == IDA_PCPU_SIZE) {
+	if (nr_free == pool->percpu_max_size) {
 		spin_lock(&pool->lock);
 
 		/*
 		 * Global lock held and irqs disabled, don't need percpu
 		 * lock
 		 */
-		if (tags->nr_free == IDA_PCPU_SIZE) {
+		if (tags->nr_free == pool->percpu_max_size) {
 			move_tags(pool->freelist, &pool->nr_free,
 				  tags->freelist, &tags->nr_free,
-				  IDA_PCPU_BATCH_MOVE);
+				  pool->percpu_batch_size);
 
 			wake_up(&pool->wait);
 		}
@@ -292,7 +283,8 @@ EXPORT_SYMBOL_GPL(percpu_ida_destroy);
  * Allocation is percpu, but sharding is limited by nr_tags - for best
  * performance, the workload should not span more cpus than nr_tags / 128.
  */
-int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
+	unsigned long max_size, unsigned long batch_size)
 {
 	unsigned i, cpu, order;
 
@@ -301,6 +293,8 @@ int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
 	init_waitqueue_head(&pool->wait);
 	spin_lock_init(&pool->lock);
 	pool->nr_tags = nr_tags;
+	pool->percpu_max_size = max_size;
+	pool->percpu_batch_size = batch_size;
 
 	/* Guard against overflow */
 	if (nr_tags > (unsigned) INT_MAX + 1) {
@@ -319,7 +313,7 @@ int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
 	pool->nr_free = nr_tags;
 
 	pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
-				       IDA_PCPU_SIZE * sizeof(unsigned),
+				       pool->percpu_max_size * sizeof(unsigned),
 				       sizeof(unsigned));
 	if (!pool->tag_cpu)
 		goto err;
@@ -332,4 +326,4 @@ err:
 	percpu_ida_destroy(pool);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL_GPL(percpu_ida_init);
+EXPORT_SYMBOL_GPL(__percpu_ida_init);
-- 
cgit 


From 7fc2ba17e8bf9f218cac10cc2a3de613d9d9086d Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@kernel.org>
Date: Tue, 15 Oct 2013 09:05:02 +0800
Subject: percpu_ida: add percpu_ida_for_each_free

Add a new API to iterate free ids. blk-mq-tag will use it.

Note, this doesn't guarantee to iterate all free ids restrictly. Caller
should be aware of this. blk-mq uses it to do sanity check for request
timedout, so can tolerate the limitation.

Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/percpu_ida.h |  4 ++++
 lib/percpu_ida.c           | 44 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

(limited to 'include')

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 56c14033e7e7..63510ae6f933 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -73,4 +73,8 @@ static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags
 		IDA_DEFAULT_PCPU_BATCH_MOVE);
 }
 
+typedef int (*percpu_ida_cb)(unsigned, void *);
+int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
+	void *data);
+
 #endif /* __PERCPU_IDA_H__ */
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index a601d4259e13..0f51c1b556cf 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -327,3 +327,47 @@ err:
 	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(__percpu_ida_init);
+
+/**
+ * percpu_ida_for_each_free - iterate free ids of a pool
+ * @pool: pool to iterate
+ * @fn: interate callback function
+ * @data: parameter for @fn
+ *
+ * Note, this doesn't guarantee to iterate all free ids restrictly. Some free
+ * ids might be missed, some might be iterated duplicated, and some might
+ * be iterated and not free soon.
+ */
+int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
+	void *data)
+{
+	unsigned long flags;
+	struct percpu_ida_cpu *remote;
+	unsigned cpu, i, err = 0;
+
+	local_irq_save(flags);
+	for_each_possible_cpu(cpu) {
+		remote = per_cpu_ptr(pool->tag_cpu, cpu);
+		spin_lock(&remote->lock);
+		for (i = 0; i < remote->nr_free; i++) {
+			err = fn(remote->freelist[i], data);
+			if (err)
+				break;
+		}
+		spin_unlock(&remote->lock);
+		if (err)
+			goto out;
+	}
+
+	spin_lock(&pool->lock);
+	for (i = 0; i < pool->nr_free; i++) {
+		err = fn(pool->freelist[i], data);
+		if (err)
+			break;
+	}
+	spin_unlock(&pool->lock);
+out:
+	local_irq_restore(flags);
+	return err;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
-- 
cgit 


From 1dddc01af0d42b21058e0cb9c1ca9e8d5204d9b0 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@kernel.org>
Date: Tue, 15 Oct 2013 09:05:03 +0800
Subject: percpu_ida: add an API to return free tags

Add an API to return free tags, blk-mq-tag will use it.

Note, this just returns a snapshot of free tags number. blk-mq-tag has
two usages of it. One is for info output for diagnosis. The other is to
quickly check if there are free tags for request dispatch checking.
Neither requires very precise.

Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/percpu_ida.h |  1 +
 lib/percpu_ida.c           | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 63510ae6f933..1900bd0fa639 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -77,4 +77,5 @@ typedef int (*percpu_ida_cb)(unsigned, void *);
 int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
 	void *data);
 
+unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu);
 #endif /* __PERCPU_IDA_H__ */
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
index 0f51c1b556cf..b0698ea972c6 100644
--- a/lib/percpu_ida.c
+++ b/lib/percpu_ida.c
@@ -371,3 +371,20 @@ out:
 	return err;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
+
+/**
+ * percpu_ida_free_tags - return free tags number of a specific cpu or global pool
+ * @pool: pool related
+ * @cpu: specific cpu or global pool if @cpu == nr_cpu_ids
+ *
+ * Note: this just returns a snapshot of free tags number.
+ */
+unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu)
+{
+	struct percpu_ida_cpu *remote;
+	if (cpu == nr_cpu_ids)
+		return pool->nr_free;
+	remote = per_cpu_ptr(pool->tag_cpu, cpu);
+	return remote->nr_free;
+}
+EXPORT_SYMBOL_GPL(percpu_ida_free_tags);
-- 
cgit 


From 320ae51feed5c2f13664aa05a76bec198967e04d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 24 Oct 2013 09:20:05 +0100
Subject: blk-mq: new multi-queue block IO queueing mechanism

Linux currently has two models for block devices:

- The classic request_fn based approach, where drivers use struct
  request units for IO. The block layer provides various helper
  functionalities to let drivers share code, things like tag
  management, timeout handling, queueing, etc.

- The "stacked" approach, where a driver squeezes in between the
  block layer and IO submitter. Since this bypasses the IO stack,
  driver generally have to manage everything themselves.

With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.

The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.

This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.

blk-mq provides various helper functions, which include:

- Scalable support for request tagging. Most devices need to
  be able to uniquely identify a request both in the driver and
  to the hardware. The tagging uses per-cpu caches for freed
  tags, to enable cache hot reuse.

- Timeout handling without tracking request on a per-device
  basis. Basically the driver should be able to get a notification,
  if a request happens to fail.

- Optional support for non 1:1 mappings between issue and
  submission queues. blk-mq can redirect IO completions to the
  desired location.

- Support for per-request payloads. Drivers almost always need
  to associate a request structure with some driver private
  command structure. Drivers can tell blk-mq this at init time,
  and then any request handed to the driver will have the
  required size of memory associated with it.

- Support for merging of IO, and plugging. The stacked model
  gets neither of these. Even for high IOPS devices, merging
  sequential IO reduces per-command overhead and thus
  increases bandwidth.

For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).

Contributions in this patch from the following people:

Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Makefile            |    5 +-
 block/blk-core.c          |  142 +++--
 block/blk-exec.c          |    7 +
 block/blk-flush.c         |  154 ++++-
 block/blk-mq-cpu.c        |   93 +++
 block/blk-mq-cpumap.c     |  108 ++++
 block/blk-mq-sysfs.c      |  384 ++++++++++++
 block/blk-mq-tag.c        |  204 +++++++
 block/blk-mq-tag.h        |   27 +
 block/blk-mq.c            | 1480 +++++++++++++++++++++++++++++++++++++++++++++
 block/blk-mq.h            |   52 ++
 block/blk-sysfs.c         |   13 +
 block/blk-timeout.c       |   73 ++-
 block/blk.h               |   17 +
 include/linux/bio.h       |    2 +
 include/linux/blk-mq.h    |  182 ++++++
 include/linux/blk_types.h |    2 +
 include/linux/blkdev.h    |   54 +-
 18 files changed, 2890 insertions(+), 109 deletions(-)
 create mode 100644 block/blk-mq-cpu.c
 create mode 100644 block/blk-mq-cpumap.c
 create mode 100644 block/blk-mq-sysfs.c
 create mode 100644 block/blk-mq-tag.c
 create mode 100644 block/blk-mq-tag.h
 create mode 100644 block/blk-mq.c
 create mode 100644 block/blk-mq.h
 create mode 100644 include/linux/blk-mq.h

(limited to 'include')

diff --git a/block/Makefile b/block/Makefile
index 671a83d063a5..20645e88fb57 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,8 +5,9 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o \
-			partition-generic.o partitions/
+			blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \
+			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
+			genhd.o scsi_ioctl.o partition-generic.o partitions/
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 18faa7e81d3b..3bb9e9f7f87e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -16,6 +16,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/kernel_stat.h>
@@ -48,7 +49,7 @@ DEFINE_IDA(blk_queue_ida);
 /*
  * For the allocated request tables
  */
-static struct kmem_cache *request_cachep;
+struct kmem_cache *request_cachep = NULL;
 
 /*
  * For queue allocation
@@ -60,42 +61,6 @@ struct kmem_cache *blk_requestq_cachep;
  */
 static struct workqueue_struct *kblockd_workqueue;
 
-static void drive_stat_acct(struct request *rq, int new_io)
-{
-	struct hd_struct *part;
-	int rw = rq_data_dir(rq);
-	int cpu;
-
-	if (!blk_do_io_stat(rq))
-		return;
-
-	cpu = part_stat_lock();
-
-	if (!new_io) {
-		part = rq->part;
-		part_stat_inc(cpu, part, merges[rw]);
-	} else {
-		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
-		if (!hd_struct_try_get(part)) {
-			/*
-			 * The partition is already being removed,
-			 * the request will be accounted on the disk only
-			 *
-			 * We take a reference on disk->part0 although that
-			 * partition will never be deleted, so we can treat
-			 * it as any other partition.
-			 */
-			part = &rq->rq_disk->part0;
-			hd_struct_get(part);
-		}
-		part_round_stats(cpu, part);
-		part_inc_in_flight(part, rw);
-		rq->part = part;
-	}
-
-	part_stat_unlock();
-}
-
 void blk_queue_congestion_threshold(struct request_queue *q)
 {
 	int nr;
@@ -594,9 +559,12 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q)
 		return NULL;
 
+	if (percpu_counter_init(&q->mq_usage_counter, 0))
+		goto fail_q;
+
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
 	if (q->id < 0)
-		goto fail_q;
+		goto fail_c;
 
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
@@ -643,6 +611,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	q->bypass_depth = 1;
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
+	init_waitqueue_head(&q->mq_freeze_wq);
+
 	if (blkcg_init_queue(q))
 		goto fail_id;
 
@@ -650,6 +620,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
+fail_c:
+	percpu_counter_destroy(&q->mq_usage_counter);
 fail_q:
 	kmem_cache_free(blk_requestq_cachep, q);
 	return NULL;
@@ -1108,7 +1080,8 @@ retry:
 	goto retry;
 }
 
-struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+static struct request *blk_old_get_request(struct request_queue *q, int rw,
+		gfp_t gfp_mask)
 {
 	struct request *rq;
 
@@ -1125,6 +1098,14 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 
 	return rq;
 }
+
+struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+{
+	if (q->mq_ops)
+		return blk_mq_alloc_request(q, rw, gfp_mask);
+	else
+		return blk_old_get_request(q, rw, gfp_mask);
+}
 EXPORT_SYMBOL(blk_get_request);
 
 /**
@@ -1210,7 +1191,7 @@ EXPORT_SYMBOL(blk_requeue_request);
 static void add_acct_request(struct request_queue *q, struct request *rq,
 			     int where)
 {
-	drive_stat_acct(rq, 1);
+	blk_account_io_start(rq, true);
 	__elv_add_request(q, rq, where);
 }
 
@@ -1299,12 +1280,17 @@ EXPORT_SYMBOL_GPL(__blk_put_request);
 
 void blk_put_request(struct request *req)
 {
-	unsigned long flags;
 	struct request_queue *q = req->q;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_put_request(q, req);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	if (q->mq_ops)
+		blk_mq_free_request(req);
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		__blk_put_request(q, req);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
 }
 EXPORT_SYMBOL(blk_put_request);
 
@@ -1340,8 +1326,8 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 }
 EXPORT_SYMBOL_GPL(blk_add_request_payload);
 
-static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
-				   struct bio *bio)
+bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
+			    struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
@@ -1358,12 +1344,12 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 	req->__data_len += bio->bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
-	drive_stat_acct(req, 0);
+	blk_account_io_start(req, false);
 	return true;
 }
 
-static bool bio_attempt_front_merge(struct request_queue *q,
-				    struct request *req, struct bio *bio)
+bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
+			     struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
@@ -1388,12 +1374,12 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	req->__data_len += bio->bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
-	drive_stat_acct(req, 0);
+	blk_account_io_start(req, false);
 	return true;
 }
 
 /**
- * attempt_plug_merge - try to merge with %current's plugged list
+ * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
  * @bio: new bio being queued
  * @request_count: out parameter for number of traversed plugged requests
@@ -1409,8 +1395,8 @@ static bool bio_attempt_front_merge(struct request_queue *q,
  * reliable access to the elevator outside queue lock.  Only check basic
  * merging parameters without querying the elevator.
  */
-static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			       unsigned int *request_count)
+bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+			    unsigned int *request_count)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1489,7 +1475,7 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (attempt_plug_merge(q, bio, &request_count))
+	if (blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1557,7 +1543,7 @@ get_rq:
 			}
 		}
 		list_add_tail(&req->queuelist, &plug->list);
-		drive_stat_acct(req, 1);
+		blk_account_io_start(req, true);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
@@ -2011,7 +1997,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-static void blk_account_io_completion(struct request *req, unsigned int bytes)
+void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
 		const int rw = rq_data_dir(req);
@@ -2025,7 +2011,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 	}
 }
 
-static void blk_account_io_done(struct request *req)
+void blk_account_io_done(struct request *req)
 {
 	/*
 	 * Account IO completion.  flush_rq isn't accounted as a
@@ -2073,6 +2059,42 @@ static inline struct request *blk_pm_peek_request(struct request_queue *q,
 }
 #endif
 
+void blk_account_io_start(struct request *rq, bool new_io)
+{
+	struct hd_struct *part;
+	int rw = rq_data_dir(rq);
+	int cpu;
+
+	if (!blk_do_io_stat(rq))
+		return;
+
+	cpu = part_stat_lock();
+
+	if (!new_io) {
+		part = rq->part;
+		part_stat_inc(cpu, part, merges[rw]);
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+		if (!hd_struct_try_get(part)) {
+			/*
+			 * The partition is already being removed,
+			 * the request will be accounted on the disk only
+			 *
+			 * We take a reference on disk->part0 although that
+			 * partition will never be deleted, so we can treat
+			 * it as any other partition.
+			 */
+			part = &rq->rq_disk->part0;
+			hd_struct_get(part);
+		}
+		part_round_stats(cpu, part);
+		part_inc_in_flight(part, rw);
+		rq->part = part;
+	}
+
+	part_stat_unlock();
+}
+
 /**
  * blk_peek_request - peek at the top of a request queue
  * @q: request queue to peek at
@@ -2448,7 +2470,6 @@ static void blk_finish_request(struct request *req, int error)
 	if (req->cmd_flags & REQ_DONTPREP)
 		blk_unprep_request(req);
 
-
 	blk_account_io_done(req);
 
 	if (req->end_io)
@@ -2870,6 +2891,7 @@ void blk_start_plug(struct blk_plug *plug)
 
 	plug->magic = PLUG_MAGIC;
 	INIT_LIST_HEAD(&plug->list);
+	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
 
 	/*
@@ -2967,6 +2989,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	BUG_ON(plug->magic != PLUG_MAGIC);
 
 	flush_plug_callbacks(plug, from_schedule);
+
+	if (!list_empty(&plug->mq_list))
+		blk_mq_flush_plug_list(plug, from_schedule);
+
 	if (list_empty(&plug->list))
 		return;
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 6b18d82d91c5..c3edf9dff566 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
@@ -58,6 +59,12 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
+
+	if (q->mq_ops) {
+		blk_mq_insert_request(q, rq, true);
+		return;
+	}
+
 	/*
 	 * need to check this before __blk_run_queue(), because rq can
 	 * be freed before that returns.
diff --git a/block/blk-flush.c b/block/blk-flush.c
index cc2b827a853c..3e4cc9c7890a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -69,8 +69,10 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/gfp.h>
+#include <linux/blk-mq.h>
 
 #include "blk.h"
+#include "blk-mq.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -124,6 +126,24 @@ static void blk_flush_restore_request(struct request *rq)
 	/* make @rq a normal request */
 	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
 	rq->end_io = rq->flush.saved_end_io;
+
+	blk_clear_rq_complete(rq);
+}
+
+static void mq_flush_data_run(struct work_struct *work)
+{
+	struct request *rq;
+
+	rq = container_of(work, struct request, mq_flush_data);
+
+	memset(&rq->csd, 0, sizeof(rq->csd));
+	blk_mq_run_request(rq, true, false);
+}
+
+static void blk_mq_flush_data_insert(struct request *rq)
+{
+	INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
+	kblockd_schedule_work(rq->q, &rq->mq_flush_data);
 }
 
 /**
@@ -136,7 +156,7 @@ static void blk_flush_restore_request(struct request *rq)
  * completion and trigger the next step.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock)
+ * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
  *
  * RETURNS:
  * %true if requests were added to the dispatch queue, %false otherwise.
@@ -146,7 +166,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 {
 	struct request_queue *q = rq->q;
 	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
-	bool queued = false;
+	bool queued = false, kicked;
 
 	BUG_ON(rq->flush.seq & seq);
 	rq->flush.seq |= seq;
@@ -167,8 +187,12 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		list_add(&rq->queuelist, &q->queue_head);
-		queued = true;
+		if (q->mq_ops)
+			blk_mq_flush_data_insert(rq);
+		else {
+			list_add(&rq->queuelist, &q->queue_head);
+			queued = true;
+		}
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -181,28 +205,43 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 		BUG_ON(!list_empty(&rq->queuelist));
 		list_del_init(&rq->flush.list);
 		blk_flush_restore_request(rq);
-		__blk_end_request_all(rq, error);
+		if (q->mq_ops)
+			blk_mq_end_io(rq, error);
+		else
+			__blk_end_request_all(rq, error);
 		break;
 
 	default:
 		BUG();
 	}
 
-	return blk_kick_flush(q) | queued;
+	kicked = blk_kick_flush(q);
+	/* blk_mq_run_flush will run queue */
+	if (q->mq_ops)
+		return queued;
+	return kicked | queued;
 }
 
 static void flush_end_io(struct request *flush_rq, int error)
 {
 	struct request_queue *q = flush_rq->q;
-	struct list_head *running = &q->flush_queue[q->flush_running_idx];
+	struct list_head *running;
 	bool queued = false;
 	struct request *rq, *n;
+	unsigned long flags = 0;
 
+	if (q->mq_ops) {
+		blk_mq_free_request(flush_rq);
+		spin_lock_irqsave(&q->mq_flush_lock, flags);
+	}
+	running = &q->flush_queue[q->flush_running_idx];
 	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
 
 	/* account completion of the flush request */
 	q->flush_running_idx ^= 1;
-	elv_completed_request(q, flush_rq);
+
+	if (!q->mq_ops)
+		elv_completed_request(q, flush_rq);
 
 	/* and push the waiting requests to the next stage */
 	list_for_each_entry_safe(rq, n, running, flush.list) {
@@ -223,9 +262,48 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * directly into request_fn may confuse the driver.  Always use
 	 * kblockd.
 	 */
-	if (queued || q->flush_queue_delayed)
-		blk_run_queue_async(q);
+	if (queued || q->flush_queue_delayed) {
+		if (!q->mq_ops)
+			blk_run_queue_async(q);
+		else
+		/*
+		 * This can be optimized to only run queues with requests
+		 * queued if necessary.
+		 */
+			blk_mq_run_queues(q, true);
+	}
 	q->flush_queue_delayed = 0;
+	if (q->mq_ops)
+		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+}
+
+static void mq_flush_work(struct work_struct *work)
+{
+	struct request_queue *q;
+	struct request *rq;
+
+	q = container_of(work, struct request_queue, mq_flush_work);
+
+	/* We don't need set REQ_FLUSH_SEQ, it's for consistency */
+	rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
+		__GFP_WAIT|GFP_ATOMIC);
+	rq->cmd_type = REQ_TYPE_FS;
+	rq->end_io = flush_end_io;
+
+	blk_mq_run_request(rq, true, false);
+}
+
+/*
+ * We can't directly use q->flush_rq, because it doesn't have tag and is not in
+ * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
+ * so offload the work to workqueue.
+ *
+ * Note: we assume a flush request finished in any hardware queue will flush
+ * the whole disk cache.
+ */
+static void mq_run_flush(struct request_queue *q)
+{
+	kblockd_schedule_work(q, &q->mq_flush_work);
 }
 
 /**
@@ -236,7 +314,7 @@ static void flush_end_io(struct request *flush_rq, int error)
  * Please read the comment at the top of this file for more info.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock)
+ * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
  *
  * RETURNS:
  * %true if flush was issued, %false otherwise.
@@ -261,13 +339,18 @@ static bool blk_kick_flush(struct request_queue *q)
 	 * Issue flush and toggle pending_idx.  This makes pending_idx
 	 * different from running_idx, which means flush is in flight.
 	 */
+	q->flush_pending_idx ^= 1;
+	if (q->mq_ops) {
+		mq_run_flush(q);
+		return true;
+	}
+
 	blk_rq_init(q, &q->flush_rq);
 	q->flush_rq.cmd_type = REQ_TYPE_FS;
 	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
 	q->flush_rq.rq_disk = first_rq->rq_disk;
 	q->flush_rq.end_io = flush_end_io;
 
-	q->flush_pending_idx ^= 1;
 	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
 	return true;
 }
@@ -284,16 +367,37 @@ static void flush_data_end_io(struct request *rq, int error)
 		blk_run_queue_async(q);
 }
 
+static void mq_flush_data_end_io(struct request *rq, int error)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	unsigned long flags;
+
+	ctx = rq->mq_ctx;
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	/*
+	 * After populating an empty queue, kick it to avoid stall.  Read
+	 * the comment in flush_end_io().
+	 */
+	spin_lock_irqsave(&q->mq_flush_lock, flags);
+	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
+		blk_mq_run_hw_queue(hctx, true);
+	spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+}
+
 /**
  * blk_insert_flush - insert a new FLUSH/FUA request
  * @rq: request to insert
  *
  * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions.
+ * or __blk_mq_run_hw_queue() to dispatch request.
  * @rq is being submitted.  Analyze what needs to be done and put it on the
  * right queue.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock)
+ * spin_lock_irq(q->queue_lock) in !mq case
  */
 void blk_insert_flush(struct request *rq)
 {
@@ -316,7 +420,10 @@ void blk_insert_flush(struct request *rq)
 	 * complete the request.
 	 */
 	if (!policy) {
-		__blk_end_bidi_request(rq, 0, 0, 0);
+		if (q->mq_ops)
+			blk_mq_end_io(rq, 0);
+		else
+			__blk_end_bidi_request(rq, 0, 0, 0);
 		return;
 	}
 
@@ -329,7 +436,10 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		list_add_tail(&rq->queuelist, &q->queue_head);
+		if (q->mq_ops) {
+			blk_mq_run_request(rq, false, true);
+		} else
+			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
 
@@ -341,6 +451,14 @@ void blk_insert_flush(struct request *rq)
 	INIT_LIST_HEAD(&rq->flush.list);
 	rq->cmd_flags |= REQ_FLUSH_SEQ;
 	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
+	if (q->mq_ops) {
+		rq->end_io = mq_flush_data_end_io;
+
+		spin_lock_irq(&q->mq_flush_lock);
+		blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
+		spin_unlock_irq(&q->mq_flush_lock);
+		return;
+	}
 	rq->end_io = flush_data_end_io;
 
 	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
@@ -453,3 +571,9 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
+
+void blk_mq_init_flush(struct request_queue *q)
+{
+	spin_lock_init(&q->mq_flush_lock);
+	INIT_WORK(&q->mq_flush_work, mq_flush_work);
+}
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
new file mode 100644
index 000000000000..f8ea39d7ae54
--- /dev/null
+++ b/block/blk-mq-cpu.c
@@ -0,0 +1,93 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/list.h>
+#include <linux/llist.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
+
+static LIST_HEAD(blk_mq_cpu_notify_list);
+static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+
+static int __cpuinit blk_mq_main_cpu_notify(struct notifier_block *self,
+					    unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long) hcpu;
+	struct blk_mq_cpu_notifier *notify;
+
+	spin_lock(&blk_mq_cpu_notify_lock);
+
+	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
+		notify->notify(notify->data, action, cpu);
+
+	spin_unlock(&blk_mq_cpu_notify_lock);
+	return NOTIFY_OK;
+}
+
+static void __cpuinit blk_mq_cpu_notify(void *data, unsigned long action,
+					unsigned int cpu)
+{
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		/*
+		 * If the CPU goes away, ensure that we run any pending
+		 * completions.
+		 */
+		struct llist_node *node;
+		struct request *rq;
+
+		local_irq_disable();
+
+		node = llist_del_all(&per_cpu(ipi_lists, cpu));
+		while (node) {
+			struct llist_node *next = node->next;
+
+			rq = llist_entry(node, struct request, ll_list);
+			__blk_mq_end_io(rq, rq->errors);
+			node = next;
+		}
+
+		local_irq_enable();
+	}
+}
+
+static struct notifier_block __cpuinitdata blk_mq_main_cpu_notifier = {
+	.notifier_call	= blk_mq_main_cpu_notify,
+};
+
+void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
+{
+	BUG_ON(!notifier->notify);
+
+	spin_lock(&blk_mq_cpu_notify_lock);
+	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
+	spin_unlock(&blk_mq_cpu_notify_lock);
+}
+
+void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
+{
+	spin_lock(&blk_mq_cpu_notify_lock);
+	list_del(&notifier->list);
+	spin_unlock(&blk_mq_cpu_notify_lock);
+}
+
+void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
+			      void (*fn)(void *, unsigned long, unsigned int),
+			      void *data)
+{
+	notifier->notify = fn;
+	notifier->data = data;
+}
+
+static struct blk_mq_cpu_notifier __cpuinitdata cpu_notifier = {
+	.notify = blk_mq_cpu_notify,
+};
+
+void __init blk_mq_cpu_init(void)
+{
+	register_hotcpu_notifier(&blk_mq_main_cpu_notifier);
+	blk_mq_register_cpu_notifier(&cpu_notifier);
+}
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
new file mode 100644
index 000000000000..f8721278601c
--- /dev/null
+++ b/block/blk-mq-cpumap.c
@@ -0,0 +1,108 @@
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+
+#include <linux/blk-mq.h>
+#include "blk.h"
+#include "blk-mq.h"
+
+static void show_map(unsigned int *map, unsigned int nr)
+{
+	int i;
+
+	pr_info("blk-mq: CPU -> queue map\n");
+	for_each_online_cpu(i)
+		pr_info("  CPU%2u -> Queue %u\n", i, map[i]);
+}
+
+static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
+			      const int cpu)
+{
+	return cpu / ((nr_cpus + nr_queues - 1) / nr_queues);
+}
+
+static int get_first_sibling(unsigned int cpu)
+{
+	unsigned int ret;
+
+	ret = cpumask_first(topology_thread_cpumask(cpu));
+	if (ret < nr_cpu_ids)
+		return ret;
+
+	return cpu;
+}
+
+int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
+{
+	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
+	cpumask_var_t cpus;
+
+	if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
+		return 1;
+
+	cpumask_clear(cpus);
+	nr_cpus = nr_uniq_cpus = 0;
+	for_each_online_cpu(i) {
+		nr_cpus++;
+		first_sibling = get_first_sibling(i);
+		if (!cpumask_test_cpu(first_sibling, cpus))
+			nr_uniq_cpus++;
+		cpumask_set_cpu(i, cpus);
+	}
+
+	queue = 0;
+	for_each_possible_cpu(i) {
+		if (!cpu_online(i)) {
+			map[i] = 0;
+			continue;
+		}
+
+		/*
+		 * Easy case - we have equal or more hardware queues. Or
+		 * there are no thread siblings to take into account. Do
+		 * 1:1 if enough, or sequential mapping if less.
+		 */
+		if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
+			map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
+			queue++;
+			continue;
+		}
+
+		/*
+		 * Less then nr_cpus queues, and we have some number of
+		 * threads per cores. Map sibling threads to the same
+		 * queue.
+		 */
+		first_sibling = get_first_sibling(i);
+		if (first_sibling == i) {
+			map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
+							queue);
+			queue++;
+		} else
+			map[i] = map[first_sibling];
+	}
+
+	show_map(map, nr_cpus);
+	free_cpumask_var(cpus);
+	return 0;
+}
+
+unsigned int *blk_mq_make_queue_map(struct blk_mq_reg *reg)
+{
+	unsigned int *map;
+
+	/* If cpus are offline, map them to first hctx */
+	map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL,
+				reg->numa_node);
+	if (!map)
+		return NULL;
+
+	if (!blk_mq_update_queue_map(map, reg->nr_hw_queues))
+		return map;
+
+	kfree(map);
+	return NULL;
+}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
new file mode 100644
index 000000000000..ba6cf8e9aa0a
--- /dev/null
+++ b/block/blk-mq-sysfs.c
@@ -0,0 +1,384 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/smp.h>
+
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+static void blk_mq_sysfs_release(struct kobject *kobj)
+{
+}
+
+struct blk_mq_ctx_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_mq_ctx *, char *);
+	ssize_t (*store)(struct blk_mq_ctx *, const char *, size_t);
+};
+
+struct blk_mq_hw_ctx_sysfs_entry {
+	struct attribute attr;
+	ssize_t (*show)(struct blk_mq_hw_ctx *, char *);
+	ssize_t (*store)(struct blk_mq_hw_ctx *, const char *, size_t);
+};
+
+static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
+				 char *page)
+{
+	struct blk_mq_ctx_sysfs_entry *entry;
+	struct blk_mq_ctx *ctx;
+	struct request_queue *q;
+	ssize_t res;
+
+	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
+	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
+	q = ctx->queue;
+
+	if (!entry->show)
+		return -EIO;
+
+	res = -ENOENT;
+	mutex_lock(&q->sysfs_lock);
+	if (!blk_queue_dying(q))
+		res = entry->show(ctx, page);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
+				  const char *page, size_t length)
+{
+	struct blk_mq_ctx_sysfs_entry *entry;
+	struct blk_mq_ctx *ctx;
+	struct request_queue *q;
+	ssize_t res;
+
+	entry = container_of(attr, struct blk_mq_ctx_sysfs_entry, attr);
+	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
+	q = ctx->queue;
+
+	if (!entry->store)
+		return -EIO;
+
+	res = -ENOENT;
+	mutex_lock(&q->sysfs_lock);
+	if (!blk_queue_dying(q))
+		res = entry->store(ctx, page, length);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
+				    struct attribute *attr, char *page)
+{
+	struct blk_mq_hw_ctx_sysfs_entry *entry;
+	struct blk_mq_hw_ctx *hctx;
+	struct request_queue *q;
+	ssize_t res;
+
+	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
+	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
+	q = hctx->queue;
+
+	if (!entry->show)
+		return -EIO;
+
+	res = -ENOENT;
+	mutex_lock(&q->sysfs_lock);
+	if (!blk_queue_dying(q))
+		res = entry->show(hctx, page);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
+				     struct attribute *attr, const char *page,
+				     size_t length)
+{
+	struct blk_mq_hw_ctx_sysfs_entry *entry;
+	struct blk_mq_hw_ctx *hctx;
+	struct request_queue *q;
+	ssize_t res;
+
+	entry = container_of(attr, struct blk_mq_hw_ctx_sysfs_entry, attr);
+	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
+	q = hctx->queue;
+
+	if (!entry->store)
+		return -EIO;
+
+	res = -ENOENT;
+	mutex_lock(&q->sysfs_lock);
+	if (!blk_queue_dying(q))
+		res = entry->store(hctx, page, length);
+	mutex_unlock(&q->sysfs_lock);
+	return res;
+}
+
+static ssize_t blk_mq_sysfs_dispatched_show(struct blk_mq_ctx *ctx, char *page)
+{
+	return sprintf(page, "%lu %lu\n", ctx->rq_dispatched[1],
+				ctx->rq_dispatched[0]);
+}
+
+static ssize_t blk_mq_sysfs_merged_show(struct blk_mq_ctx *ctx, char *page)
+{
+	return sprintf(page, "%lu\n", ctx->rq_merged);
+}
+
+static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
+{
+	return sprintf(page, "%lu %lu\n", ctx->rq_completed[1],
+				ctx->rq_completed[0]);
+}
+
+static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
+{
+	char *start_page = page;
+	struct request *rq;
+
+	page += sprintf(page, "%s:\n", msg);
+
+	list_for_each_entry(rq, list, queuelist)
+		page += sprintf(page, "\t%p\n", rq);
+
+	return page - start_page;
+}
+
+static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
+{
+	ssize_t ret;
+
+	spin_lock(&ctx->lock);
+	ret = sysfs_list_show(page, &ctx->rq_list, "CTX pending");
+	spin_unlock(&ctx->lock);
+
+	return ret;
+}
+
+static ssize_t blk_mq_hw_sysfs_queued_show(struct blk_mq_hw_ctx *hctx,
+					   char *page)
+{
+	return sprintf(page, "%lu\n", hctx->queued);
+}
+
+static ssize_t blk_mq_hw_sysfs_run_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	return sprintf(page, "%lu\n", hctx->run);
+}
+
+static ssize_t blk_mq_hw_sysfs_dispatched_show(struct blk_mq_hw_ctx *hctx,
+					       char *page)
+{
+	char *start_page = page;
+	int i;
+
+	page += sprintf(page, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
+
+	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER; i++) {
+		unsigned long d = 1U << (i - 1);
+
+		page += sprintf(page, "%8lu\t%lu\n", d, hctx->dispatched[i]);
+	}
+
+	return page - start_page;
+}
+
+static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
+					    char *page)
+{
+	ssize_t ret;
+
+	spin_lock(&hctx->lock);
+	ret = sysfs_list_show(page, &hctx->dispatch, "HCTX pending");
+	spin_unlock(&hctx->lock);
+
+	return ret;
+}
+
+static ssize_t blk_mq_hw_sysfs_ipi_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	ssize_t ret;
+
+	spin_lock(&hctx->lock);
+	ret = sprintf(page, "%u\n", !!(hctx->flags & BLK_MQ_F_SHOULD_IPI));
+	spin_unlock(&hctx->lock);
+
+	return ret;
+}
+
+static ssize_t blk_mq_hw_sysfs_ipi_store(struct blk_mq_hw_ctx *hctx,
+					 const char *page, size_t len)
+{
+	struct blk_mq_ctx *ctx;
+	unsigned long ret;
+	unsigned int i;
+
+	if (kstrtoul(page, 10, &ret)) {
+		pr_err("blk-mq-sysfs: invalid input '%s'\n", page);
+		return -EINVAL;
+	}
+
+	spin_lock(&hctx->lock);
+	if (ret)
+		hctx->flags |= BLK_MQ_F_SHOULD_IPI;
+	else
+		hctx->flags &= ~BLK_MQ_F_SHOULD_IPI;
+	spin_unlock(&hctx->lock);
+
+	hctx_for_each_ctx(hctx, ctx, i)
+		ctx->ipi_redirect = !!ret;
+
+	return len;
+}
+
+static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	return blk_mq_tag_sysfs_show(hctx->tags, page);
+}
+
+static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
+	.attr = {.name = "dispatched", .mode = S_IRUGO },
+	.show = blk_mq_sysfs_dispatched_show,
+};
+static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_merged = {
+	.attr = {.name = "merged", .mode = S_IRUGO },
+	.show = blk_mq_sysfs_merged_show,
+};
+static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_completed = {
+	.attr = {.name = "completed", .mode = S_IRUGO },
+	.show = blk_mq_sysfs_completed_show,
+};
+static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_rq_list = {
+	.attr = {.name = "rq_list", .mode = S_IRUGO },
+	.show = blk_mq_sysfs_rq_list_show,
+};
+
+static struct attribute *default_ctx_attrs[] = {
+	&blk_mq_sysfs_dispatched.attr,
+	&blk_mq_sysfs_merged.attr,
+	&blk_mq_sysfs_completed.attr,
+	&blk_mq_sysfs_rq_list.attr,
+	NULL,
+};
+
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_queued = {
+	.attr = {.name = "queued", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_queued_show,
+};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_run = {
+	.attr = {.name = "run", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_run_show,
+};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_dispatched = {
+	.attr = {.name = "dispatched", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_dispatched_show,
+};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
+	.attr = {.name = "pending", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_rq_list_show,
+};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_ipi = {
+	.attr = {.name = "ipi_redirect", .mode = S_IRUGO | S_IWUSR},
+	.show = blk_mq_hw_sysfs_ipi_show,
+	.store = blk_mq_hw_sysfs_ipi_store,
+};
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
+	.attr = {.name = "tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_tags_show,
+};
+
+static struct attribute *default_hw_ctx_attrs[] = {
+	&blk_mq_hw_sysfs_queued.attr,
+	&blk_mq_hw_sysfs_run.attr,
+	&blk_mq_hw_sysfs_dispatched.attr,
+	&blk_mq_hw_sysfs_pending.attr,
+	&blk_mq_hw_sysfs_ipi.attr,
+	&blk_mq_hw_sysfs_tags.attr,
+	NULL,
+};
+
+static const struct sysfs_ops blk_mq_sysfs_ops = {
+	.show	= blk_mq_sysfs_show,
+	.store	= blk_mq_sysfs_store,
+};
+
+static const struct sysfs_ops blk_mq_hw_sysfs_ops = {
+	.show	= blk_mq_hw_sysfs_show,
+	.store	= blk_mq_hw_sysfs_store,
+};
+
+static struct kobj_type blk_mq_ktype = {
+	.sysfs_ops	= &blk_mq_sysfs_ops,
+	.release	= blk_mq_sysfs_release,
+};
+
+static struct kobj_type blk_mq_ctx_ktype = {
+	.sysfs_ops	= &blk_mq_sysfs_ops,
+	.default_attrs	= default_ctx_attrs,
+	.release	= blk_mq_sysfs_release,
+};
+
+static struct kobj_type blk_mq_hw_ktype = {
+	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
+	.default_attrs	= default_hw_ctx_attrs,
+	.release	= blk_mq_sysfs_release,
+};
+
+void blk_mq_unregister_disk(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+
+	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(&q->mq_kobj);
+
+	kobject_put(&disk_to_dev(disk)->kobj);
+}
+
+int blk_mq_register_disk(struct gendisk *disk)
+{
+	struct device *dev = disk_to_dev(disk);
+	struct request_queue *q = disk->queue;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	int ret, i, j;
+
+	kobject_init(&q->mq_kobj, &blk_mq_ktype);
+
+	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
+	if (ret < 0)
+		return ret;
+
+	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		kobject_init(&hctx->kobj, &blk_mq_hw_ktype);
+		ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", i);
+		if (ret)
+			break;
+
+		if (!hctx->nr_ctx)
+			continue;
+
+		hctx_for_each_ctx(hctx, ctx, j) {
+			kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
+			ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu);
+			if (ret)
+				break;
+		}
+	}
+
+	if (ret) {
+		blk_mq_unregister_disk(disk);
+		return ret;
+	}
+
+	return 0;
+}
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
new file mode 100644
index 000000000000..d64a02fb1f73
--- /dev/null
+++ b/block/blk-mq-tag.c
@@ -0,0 +1,204 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu_ida.h>
+
+#include <linux/blk-mq.h>
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+/*
+ * Per tagged queue (tag address space) map
+ */
+struct blk_mq_tags {
+	unsigned int nr_tags;
+	unsigned int nr_reserved_tags;
+	unsigned int nr_batch_move;
+	unsigned int nr_max_cache;
+
+	struct percpu_ida free_tags;
+	struct percpu_ida reserved_tags;
+};
+
+void blk_mq_wait_for_tags(struct blk_mq_tags *tags)
+{
+	int tag = blk_mq_get_tag(tags, __GFP_WAIT, false);
+	blk_mq_put_tag(tags, tag);
+}
+
+bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
+{
+	return !tags ||
+		percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids) != 0;
+}
+
+static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
+{
+	int tag;
+
+	tag = percpu_ida_alloc(&tags->free_tags, gfp);
+	if (tag < 0)
+		return BLK_MQ_TAG_FAIL;
+	return tag + tags->nr_reserved_tags;
+}
+
+static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
+					      gfp_t gfp)
+{
+	int tag;
+
+	if (unlikely(!tags->nr_reserved_tags)) {
+		WARN_ON_ONCE(1);
+		return BLK_MQ_TAG_FAIL;
+	}
+
+	tag = percpu_ida_alloc(&tags->reserved_tags, gfp);
+	if (tag < 0)
+		return BLK_MQ_TAG_FAIL;
+	return tag;
+}
+
+unsigned int blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp, bool reserved)
+{
+	if (!reserved)
+		return __blk_mq_get_tag(tags, gfp);
+
+	return __blk_mq_get_reserved_tag(tags, gfp);
+}
+
+static void __blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
+{
+	BUG_ON(tag >= tags->nr_tags);
+
+	percpu_ida_free(&tags->free_tags, tag - tags->nr_reserved_tags);
+}
+
+static void __blk_mq_put_reserved_tag(struct blk_mq_tags *tags,
+				      unsigned int tag)
+{
+	BUG_ON(tag >= tags->nr_reserved_tags);
+
+	percpu_ida_free(&tags->reserved_tags, tag);
+}
+
+void blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag)
+{
+	if (tag >= tags->nr_reserved_tags)
+		__blk_mq_put_tag(tags, tag);
+	else
+		__blk_mq_put_reserved_tag(tags, tag);
+}
+
+static int __blk_mq_tag_iter(unsigned id, void *data)
+{
+	unsigned long *tag_map = data;
+	__set_bit(id, tag_map);
+	return 0;
+}
+
+void blk_mq_tag_busy_iter(struct blk_mq_tags *tags,
+			  void (*fn)(void *, unsigned long *), void *data)
+{
+	unsigned long *tag_map;
+	size_t map_size;
+
+	map_size = ALIGN(tags->nr_tags, BITS_PER_LONG) / BITS_PER_LONG;
+	tag_map = kzalloc(map_size * sizeof(unsigned long), GFP_ATOMIC);
+	if (!tag_map)
+		return;
+
+	percpu_ida_for_each_free(&tags->free_tags, __blk_mq_tag_iter, tag_map);
+	if (tags->nr_reserved_tags)
+		percpu_ida_for_each_free(&tags->reserved_tags, __blk_mq_tag_iter,
+			tag_map);
+
+	fn(data, tag_map);
+	kfree(tag_map);
+}
+
+struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
+				     unsigned int reserved_tags, int node)
+{
+	unsigned int nr_tags, nr_cache;
+	struct blk_mq_tags *tags;
+	int ret;
+
+	if (total_tags > BLK_MQ_TAG_MAX) {
+		pr_err("blk-mq: tag depth too large\n");
+		return NULL;
+	}
+
+	tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);
+	if (!tags)
+		return NULL;
+
+	nr_tags = total_tags - reserved_tags;
+	nr_cache = nr_tags / num_possible_cpus();
+
+	if (nr_cache < BLK_MQ_TAG_CACHE_MIN)
+		nr_cache = BLK_MQ_TAG_CACHE_MIN;
+	else if (nr_cache > BLK_MQ_TAG_CACHE_MAX)
+		nr_cache = BLK_MQ_TAG_CACHE_MAX;
+
+	tags->nr_tags = total_tags;
+	tags->nr_reserved_tags = reserved_tags;
+	tags->nr_max_cache = nr_cache;
+	tags->nr_batch_move = max(1u, nr_cache / 2);
+
+	ret = __percpu_ida_init(&tags->free_tags, tags->nr_tags -
+				tags->nr_reserved_tags,
+				tags->nr_max_cache,
+				tags->nr_batch_move);
+	if (ret)
+		goto err_free_tags;
+
+	if (reserved_tags) {
+		/*
+		 * With max_cahe and batch set to 1, the allocator fallbacks to
+		 * no cached. It's fine reserved tags allocation is slow.
+		 */
+		ret = __percpu_ida_init(&tags->reserved_tags, reserved_tags,
+				1, 1);
+		if (ret)
+			goto err_reserved_tags;
+	}
+
+	return tags;
+
+err_reserved_tags:
+	percpu_ida_destroy(&tags->free_tags);
+err_free_tags:
+	kfree(tags);
+	return NULL;
+}
+
+void blk_mq_free_tags(struct blk_mq_tags *tags)
+{
+	percpu_ida_destroy(&tags->free_tags);
+	percpu_ida_destroy(&tags->reserved_tags);
+	kfree(tags);
+}
+
+ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
+{
+	char *orig_page = page;
+	int cpu;
+
+	if (!tags)
+		return 0;
+
+	page += sprintf(page, "nr_tags=%u, reserved_tags=%u, batch_move=%u,"
+			" max_cache=%u\n", tags->nr_tags, tags->nr_reserved_tags,
+			tags->nr_batch_move, tags->nr_max_cache);
+
+	page += sprintf(page, "nr_free=%u, nr_reserved=%u\n",
+			percpu_ida_free_tags(&tags->free_tags, nr_cpu_ids),
+			percpu_ida_free_tags(&tags->reserved_tags, nr_cpu_ids));
+
+	for_each_possible_cpu(cpu) {
+		page += sprintf(page, "  cpu%02u: nr_free=%u\n", cpu,
+				percpu_ida_free_tags(&tags->free_tags, cpu));
+	}
+
+	return page - orig_page;
+}
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
new file mode 100644
index 000000000000..947ba2c6148e
--- /dev/null
+++ b/block/blk-mq-tag.h
@@ -0,0 +1,27 @@
+#ifndef INT_BLK_MQ_TAG_H
+#define INT_BLK_MQ_TAG_H
+
+struct blk_mq_tags;
+
+extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node);
+extern void blk_mq_free_tags(struct blk_mq_tags *tags);
+
+extern unsigned int blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp, bool reserved);
+extern void blk_mq_wait_for_tags(struct blk_mq_tags *tags);
+extern void blk_mq_put_tag(struct blk_mq_tags *tags, unsigned int tag);
+extern void blk_mq_tag_busy_iter(struct blk_mq_tags *tags, void (*fn)(void *data, unsigned long *), void *data);
+extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
+extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
+
+enum {
+	BLK_MQ_TAG_CACHE_MIN	= 1,
+	BLK_MQ_TAG_CACHE_MAX	= 64,
+};
+
+enum {
+	BLK_MQ_TAG_FAIL		= -1U,
+	BLK_MQ_TAG_MIN		= BLK_MQ_TAG_CACHE_MIN,
+	BLK_MQ_TAG_MAX		= BLK_MQ_TAG_FAIL - 1,
+};
+
+#endif
diff --git a/block/blk-mq.c b/block/blk-mq.c
new file mode 100644
index 000000000000..f21ec964e411
--- /dev/null
+++ b/block/blk-mq.c
@@ -0,0 +1,1480 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/smp.h>
+#include <linux/llist.h>
+#include <linux/list_sort.h>
+#include <linux/cpu.h>
+#include <linux/cache.h>
+#include <linux/sched/sysctl.h>
+#include <linux/delay.h>
+
+#include <trace/events/block.h>
+
+#include <linux/blk-mq.h>
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+static DEFINE_MUTEX(all_q_mutex);
+static LIST_HEAD(all_q_list);
+
+static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
+
+DEFINE_PER_CPU(struct llist_head, ipi_lists);
+
+static struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
+					   unsigned int cpu)
+{
+	return per_cpu_ptr(q->queue_ctx, cpu);
+}
+
+/*
+ * This assumes per-cpu software queueing queues. They could be per-node
+ * as well, for instance. For now this is hardcoded as-is. Note that we don't
+ * care about preemption, since we know the ctx's are persistent. This does
+ * mean that we can't rely on ctx always matching the currently running CPU.
+ */
+static struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
+{
+	return __blk_mq_get_ctx(q, get_cpu());
+}
+
+static void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
+{
+	put_cpu();
+}
+
+/*
+ * Check if any of the ctx's have pending work in this hardware queue
+ */
+static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
+{
+	unsigned int i;
+
+	for (i = 0; i < hctx->nr_ctx_map; i++)
+		if (hctx->ctx_map[i])
+			return true;
+
+	return false;
+}
+
+/*
+ * Mark this ctx as having pending work in this hardware queue
+ */
+static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
+				     struct blk_mq_ctx *ctx)
+{
+	if (!test_bit(ctx->index_hw, hctx->ctx_map))
+		set_bit(ctx->index_hw, hctx->ctx_map);
+}
+
+static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
+				       bool reserved)
+{
+	struct request *rq;
+	unsigned int tag;
+
+	tag = blk_mq_get_tag(hctx->tags, gfp, reserved);
+	if (tag != BLK_MQ_TAG_FAIL) {
+		rq = hctx->rqs[tag];
+		rq->tag = tag;
+
+		return rq;
+	}
+
+	return NULL;
+}
+
+static int blk_mq_queue_enter(struct request_queue *q)
+{
+	int ret;
+
+	__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
+	smp_wmb();
+	/* we have problems to freeze the queue if it's initializing */
+	if (!blk_queue_bypass(q) || !blk_queue_init_done(q))
+		return 0;
+
+	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
+
+	spin_lock_irq(q->queue_lock);
+	ret = wait_event_interruptible_lock_irq(q->mq_freeze_wq,
+		!blk_queue_bypass(q), *q->queue_lock);
+	/* inc usage with lock hold to avoid freeze_queue runs here */
+	if (!ret)
+		__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
+static void blk_mq_queue_exit(struct request_queue *q)
+{
+	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
+}
+
+/*
+ * Guarantee no request is in use, so we can change any data structure of
+ * the queue afterward.
+ */
+static void blk_mq_freeze_queue(struct request_queue *q)
+{
+	bool drain;
+
+	spin_lock_irq(q->queue_lock);
+	drain = !q->bypass_depth++;
+	queue_flag_set(QUEUE_FLAG_BYPASS, q);
+	spin_unlock_irq(q->queue_lock);
+
+	if (!drain)
+		return;
+
+	while (true) {
+		s64 count;
+
+		spin_lock_irq(q->queue_lock);
+		count = percpu_counter_sum(&q->mq_usage_counter);
+		spin_unlock_irq(q->queue_lock);
+
+		if (count == 0)
+			break;
+		blk_mq_run_queues(q, false);
+		msleep(10);
+	}
+}
+
+static void blk_mq_unfreeze_queue(struct request_queue *q)
+{
+	bool wake = false;
+
+	spin_lock_irq(q->queue_lock);
+	if (!--q->bypass_depth) {
+		queue_flag_clear(QUEUE_FLAG_BYPASS, q);
+		wake = true;
+	}
+	WARN_ON_ONCE(q->bypass_depth < 0);
+	spin_unlock_irq(q->queue_lock);
+	if (wake)
+		wake_up_all(&q->mq_freeze_wq);
+}
+
+bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
+{
+	return blk_mq_has_free_tags(hctx->tags);
+}
+EXPORT_SYMBOL(blk_mq_can_queue);
+
+static void blk_mq_rq_ctx_init(struct blk_mq_ctx *ctx, struct request *rq,
+			       unsigned int rw_flags)
+{
+	rq->mq_ctx = ctx;
+	rq->cmd_flags = rw_flags;
+	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
+}
+
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+					      gfp_t gfp, bool reserved)
+{
+	return blk_mq_alloc_rq(hctx, gfp, reserved);
+}
+
+static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
+						   int rw, gfp_t gfp,
+						   bool reserved)
+{
+	struct request *rq;
+
+	do {
+		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+		struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+		rq = __blk_mq_alloc_request(hctx, gfp & ~__GFP_WAIT, reserved);
+		if (rq) {
+			blk_mq_rq_ctx_init(ctx, rq, rw);
+			break;
+		} else if (!(gfp & __GFP_WAIT))
+			break;
+
+		blk_mq_put_ctx(ctx);
+		__blk_mq_run_hw_queue(hctx);
+		blk_mq_wait_for_tags(hctx->tags);
+	} while (1);
+
+	return rq;
+}
+
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
+{
+	struct request *rq;
+
+	if (blk_mq_queue_enter(q))
+		return NULL;
+
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
+	blk_mq_put_ctx(rq->mq_ctx);
+	return rq;
+}
+
+struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw,
+					      gfp_t gfp)
+{
+	struct request *rq;
+
+	if (blk_mq_queue_enter(q))
+		return NULL;
+
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, true);
+	blk_mq_put_ctx(rq->mq_ctx);
+	return rq;
+}
+EXPORT_SYMBOL(blk_mq_alloc_reserved_request);
+
+/*
+ * Re-init and set pdu, if we have it
+ */
+static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	blk_rq_init(hctx->queue, rq);
+
+	if (hctx->cmd_size)
+		rq->special = blk_mq_rq_to_pdu(rq);
+}
+
+static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
+				  struct blk_mq_ctx *ctx, struct request *rq)
+{
+	const int tag = rq->tag;
+	struct request_queue *q = rq->q;
+
+	blk_mq_rq_init(hctx, rq);
+	blk_mq_put_tag(hctx->tags, tag);
+
+	blk_mq_queue_exit(q);
+}
+
+void blk_mq_free_request(struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx;
+	struct request_queue *q = rq->q;
+
+	ctx->rq_completed[rq_is_sync(rq)]++;
+
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	__blk_mq_free_request(hctx, ctx, rq);
+}
+
+static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
+{
+	if (error)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = -EIO;
+
+	if (unlikely(rq->cmd_flags & REQ_QUIET))
+		set_bit(BIO_QUIET, &bio->bi_flags);
+
+	/* don't actually finish bio if it's part of flush sequence */
+	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
+		bio_endio(bio, error);
+}
+
+void blk_mq_complete_request(struct request *rq, int error)
+{
+	struct bio *bio = rq->bio;
+	unsigned int bytes = 0;
+
+	trace_block_rq_complete(rq->q, rq);
+
+	while (bio) {
+		struct bio *next = bio->bi_next;
+
+		bio->bi_next = NULL;
+		bytes += bio->bi_size;
+		blk_mq_bio_endio(rq, bio, error);
+		bio = next;
+	}
+
+	blk_account_io_completion(rq, bytes);
+
+	if (rq->end_io)
+		rq->end_io(rq, error);
+	else
+		blk_mq_free_request(rq);
+
+	blk_account_io_done(rq);
+}
+
+void __blk_mq_end_io(struct request *rq, int error)
+{
+	if (!blk_mark_rq_complete(rq))
+		blk_mq_complete_request(rq, error);
+}
+
+#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+
+/*
+ * Called with interrupts disabled.
+ */
+static void ipi_end_io(void *data)
+{
+	struct llist_head *list = &per_cpu(ipi_lists, smp_processor_id());
+	struct llist_node *entry, *next;
+	struct request *rq;
+
+	entry = llist_del_all(list);
+
+	while (entry) {
+		next = entry->next;
+		rq = llist_entry(entry, struct request, ll_list);
+		__blk_mq_end_io(rq, rq->errors);
+		entry = next;
+	}
+}
+
+static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
+			  struct request *rq, const int error)
+{
+	struct call_single_data *data = &rq->csd;
+
+	rq->errors = error;
+	rq->ll_list.next = NULL;
+
+	/*
+	 * If the list is non-empty, an existing IPI must already
+	 * be "in flight". If that is the case, we need not schedule
+	 * a new one.
+	 */
+	if (llist_add(&rq->ll_list, &per_cpu(ipi_lists, ctx->cpu))) {
+		data->func = ipi_end_io;
+		data->flags = 0;
+		__smp_call_function_single(ctx->cpu, data, 0);
+	}
+
+	return true;
+}
+#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
+			  struct request *rq, const int error)
+{
+	return false;
+}
+#endif
+
+/*
+ * End IO on this request on a multiqueue enabled driver. We'll either do
+ * it directly inline, or punt to a local IPI handler on the matching
+ * remote CPU.
+ */
+void blk_mq_end_io(struct request *rq, int error)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	int cpu;
+
+	if (!ctx->ipi_redirect)
+		return __blk_mq_end_io(rq, error);
+
+	cpu = get_cpu();
+
+	if (cpu == ctx->cpu || !cpu_online(ctx->cpu) ||
+	    !ipi_remote_cpu(ctx, cpu, rq, error))
+		__blk_mq_end_io(rq, error);
+
+	put_cpu();
+}
+EXPORT_SYMBOL(blk_mq_end_io);
+
+static void blk_mq_start_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	trace_block_rq_issue(q, rq);
+
+	/*
+	 * Just mark start time and set the started bit. Due to memory
+	 * ordering, we know we'll see the correct deadline as long as
+	 * REQ_ATOMIC_STARTED is seen.
+	 */
+	rq->deadline = jiffies + q->rq_timeout;
+	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+}
+
+static void blk_mq_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+
+	trace_block_rq_requeue(q, rq);
+	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+}
+
+struct blk_mq_timeout_data {
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long *next;
+	unsigned int *next_set;
+};
+
+static void blk_mq_timeout_check(void *__data, unsigned long *free_tags)
+{
+	struct blk_mq_timeout_data *data = __data;
+	struct blk_mq_hw_ctx *hctx = data->hctx;
+	unsigned int tag;
+
+	 /* It may not be in flight yet (this is where
+	 * the REQ_ATOMIC_STARTED flag comes in). The requests are
+	 * statically allocated, so we know it's always safe to access the
+	 * memory associated with a bit offset into ->rqs[].
+	 */
+	tag = 0;
+	do {
+		struct request *rq;
+
+		tag = find_next_zero_bit(free_tags, hctx->queue_depth, tag);
+		if (tag >= hctx->queue_depth)
+			break;
+
+		rq = hctx->rqs[tag++];
+
+		if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+			continue;
+
+		blk_rq_check_expired(rq, data->next, data->next_set);
+	} while (1);
+}
+
+static void blk_mq_hw_ctx_check_timeout(struct blk_mq_hw_ctx *hctx,
+					unsigned long *next,
+					unsigned int *next_set)
+{
+	struct blk_mq_timeout_data data = {
+		.hctx		= hctx,
+		.next		= next,
+		.next_set	= next_set,
+	};
+
+	/*
+	 * Ask the tagging code to iterate busy requests, so we can
+	 * check them for timeout.
+	 */
+	blk_mq_tag_busy_iter(hctx->tags, blk_mq_timeout_check, &data);
+}
+
+static void blk_mq_rq_timer(unsigned long data)
+{
+	struct request_queue *q = (struct request_queue *) data;
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long next = 0;
+	int i, next_set = 0;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_hw_ctx_check_timeout(hctx, &next, &next_set);
+
+	if (next_set)
+		mod_timer(&q->timeout, round_jiffies_up(next));
+}
+
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+				 struct blk_mq_ctx *ctx, struct bio *bio)
+{
+	struct request *rq;
+	int checked = 8;
+
+	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+		int el_ret;
+
+		if (!checked--)
+			break;
+
+		if (!blk_rq_merge_ok(rq, bio))
+			continue;
+
+		el_ret = blk_try_merge(rq, bio);
+		if (el_ret == ELEVATOR_BACK_MERGE) {
+			if (bio_attempt_back_merge(q, rq, bio)) {
+				ctx->rq_merged++;
+				return true;
+			}
+			break;
+		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+			if (bio_attempt_front_merge(q, rq, bio)) {
+				ctx->rq_merged++;
+				return true;
+			}
+			break;
+		}
+	}
+
+	return false;
+}
+
+void blk_mq_add_timer(struct request *rq)
+{
+	__blk_add_timer(rq, NULL);
+}
+
+/*
+ * Run this hardware queue, pulling any software queues mapped to it in.
+ * Note that this function currently has various problems around ordering
+ * of IO. In particular, we'd like FIFO behaviour on handling existing
+ * items on the hctx->dispatch list. Ignore that for now.
+ */
+static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+	LIST_HEAD(rq_list);
+	int bit, queued;
+
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+		return;
+
+	hctx->run++;
+
+	/*
+	 * Touch any software queue that has pending entries.
+	 */
+	for_each_set_bit(bit, hctx->ctx_map, hctx->nr_ctx) {
+		clear_bit(bit, hctx->ctx_map);
+		ctx = hctx->ctxs[bit];
+		BUG_ON(bit != ctx->index_hw);
+
+		spin_lock(&ctx->lock);
+		list_splice_tail_init(&ctx->rq_list, &rq_list);
+		spin_unlock(&ctx->lock);
+	}
+
+	/*
+	 * If we have previous entries on our dispatch list, grab them
+	 * and stuff them at the front for more fair dispatch.
+	 */
+	if (!list_empty_careful(&hctx->dispatch)) {
+		spin_lock(&hctx->lock);
+		if (!list_empty(&hctx->dispatch))
+			list_splice_init(&hctx->dispatch, &rq_list);
+		spin_unlock(&hctx->lock);
+	}
+
+	/*
+	 * Delete and return all entries from our dispatch list
+	 */
+	queued = 0;
+
+	/*
+	 * Now process all the entries, sending them to the driver.
+	 */
+	while (!list_empty(&rq_list)) {
+		int ret;
+
+		rq = list_first_entry(&rq_list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_mq_start_request(rq);
+
+		/*
+		 * Last request in the series. Flag it as such, this
+		 * enables drivers to know when IO should be kicked off,
+		 * if they don't do it on a per-request basis.
+		 *
+		 * Note: the flag isn't the only condition drivers
+		 * should do kick off. If drive is busy, the last
+		 * request might not have the bit set.
+		 */
+		if (list_empty(&rq_list))
+			rq->cmd_flags |= REQ_END;
+
+		ret = q->mq_ops->queue_rq(hctx, rq);
+		switch (ret) {
+		case BLK_MQ_RQ_QUEUE_OK:
+			queued++;
+			continue;
+		case BLK_MQ_RQ_QUEUE_BUSY:
+			/*
+			 * FIXME: we should have a mechanism to stop the queue
+			 * like blk_stop_queue, otherwise we will waste cpu
+			 * time
+			 */
+			list_add(&rq->queuelist, &rq_list);
+			blk_mq_requeue_request(rq);
+			break;
+		default:
+			pr_err("blk-mq: bad return on queue: %d\n", ret);
+			rq->errors = -EIO;
+		case BLK_MQ_RQ_QUEUE_ERROR:
+			blk_mq_end_io(rq, rq->errors);
+			break;
+		}
+
+		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
+			break;
+	}
+
+	if (!queued)
+		hctx->dispatched[0]++;
+	else if (queued < (1 << (BLK_MQ_MAX_DISPATCH_ORDER - 1)))
+		hctx->dispatched[ilog2(queued) + 1]++;
+
+	/*
+	 * Any items that need requeuing? Stuff them into hctx->dispatch,
+	 * that is where we will continue on next queue run.
+	 */
+	if (!list_empty(&rq_list)) {
+		spin_lock(&hctx->lock);
+		list_splice(&rq_list, &hctx->dispatch);
+		spin_unlock(&hctx->lock);
+	}
+}
+
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+		return;
+
+	if (!async)
+		__blk_mq_run_hw_queue(hctx);
+	else {
+		struct request_queue *q = hctx->queue;
+
+		kblockd_schedule_delayed_work(q, &hctx->delayed_work, 0);
+	}
+}
+
+void blk_mq_run_queues(struct request_queue *q, bool async)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if ((!blk_mq_hctx_has_pending(hctx) &&
+		    list_empty_careful(&hctx->dispatch)) ||
+		    test_bit(BLK_MQ_S_STOPPED, &hctx->flags))
+			continue;
+
+		blk_mq_run_hw_queue(hctx, async);
+	}
+}
+EXPORT_SYMBOL(blk_mq_run_queues);
+
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	cancel_delayed_work(&hctx->delayed_work);
+	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
+}
+EXPORT_SYMBOL(blk_mq_stop_hw_queue);
+
+void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
+{
+	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	__blk_mq_run_hw_queue(hctx);
+}
+EXPORT_SYMBOL(blk_mq_start_hw_queue);
+
+void blk_mq_start_stopped_hw_queues(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!test_bit(BLK_MQ_S_STOPPED, &hctx->state))
+			continue;
+
+		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+		blk_mq_run_hw_queue(hctx, true);
+	}
+}
+EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues);
+
+static void blk_mq_work_fn(struct work_struct *work)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	hctx = container_of(work, struct blk_mq_hw_ctx, delayed_work.work);
+	__blk_mq_run_hw_queue(hctx);
+}
+
+static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
+				    struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+
+	list_add_tail(&rq->queuelist, &ctx->rq_list);
+	blk_mq_hctx_mark_pending(hctx, ctx);
+
+	/*
+	 * We do this early, to ensure we are on the right CPU.
+	 */
+	blk_mq_add_timer(rq);
+}
+
+void blk_mq_insert_request(struct request_queue *q, struct request *rq,
+			   bool run_queue)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx, *current_ctx;
+
+	ctx = rq->mq_ctx;
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+		blk_insert_flush(rq);
+	} else {
+		current_ctx = blk_mq_get_ctx(q);
+
+		if (!cpu_online(ctx->cpu)) {
+			ctx = current_ctx;
+			hctx = q->mq_ops->map_queue(q, ctx->cpu);
+			rq->mq_ctx = ctx;
+		}
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq);
+		spin_unlock(&ctx->lock);
+
+		blk_mq_put_ctx(current_ctx);
+	}
+
+	if (run_queue)
+		__blk_mq_run_hw_queue(hctx);
+}
+EXPORT_SYMBOL(blk_mq_insert_request);
+
+/*
+ * This is a special version of blk_mq_insert_request to bypass FLUSH request
+ * check. Should only be used internally.
+ */
+void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
+{
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx, *current_ctx;
+
+	current_ctx = blk_mq_get_ctx(q);
+
+	ctx = rq->mq_ctx;
+	if (!cpu_online(ctx->cpu)) {
+		ctx = current_ctx;
+		rq->mq_ctx = ctx;
+	}
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	/* ctx->cpu might be offline */
+	spin_lock(&ctx->lock);
+	__blk_mq_insert_request(hctx, rq);
+	spin_unlock(&ctx->lock);
+
+	blk_mq_put_ctx(current_ctx);
+
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, async);
+}
+
+static void blk_mq_insert_requests(struct request_queue *q,
+				     struct blk_mq_ctx *ctx,
+				     struct list_head *list,
+				     int depth,
+				     bool from_schedule)
+
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *current_ctx;
+
+	trace_block_unplug(q, depth, !from_schedule);
+
+	current_ctx = blk_mq_get_ctx(q);
+
+	if (!cpu_online(ctx->cpu))
+		ctx = current_ctx;
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	/*
+	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
+	 * offline now
+	 */
+	spin_lock(&ctx->lock);
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		rq->mq_ctx = ctx;
+		__blk_mq_insert_request(hctx, rq);
+	}
+	spin_unlock(&ctx->lock);
+
+	blk_mq_put_ctx(current_ctx);
+
+	blk_mq_run_hw_queue(hctx, from_schedule);
+}
+
+static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct request *rqa = container_of(a, struct request, queuelist);
+	struct request *rqb = container_of(b, struct request, queuelist);
+
+	return !(rqa->mq_ctx < rqb->mq_ctx ||
+		 (rqa->mq_ctx == rqb->mq_ctx &&
+		  blk_rq_pos(rqa) < blk_rq_pos(rqb)));
+}
+
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+{
+	struct blk_mq_ctx *this_ctx;
+	struct request_queue *this_q;
+	struct request *rq;
+	LIST_HEAD(list);
+	LIST_HEAD(ctx_list);
+	unsigned int depth;
+
+	list_splice_init(&plug->mq_list, &list);
+
+	list_sort(NULL, &list, plug_ctx_cmp);
+
+	this_q = NULL;
+	this_ctx = NULL;
+	depth = 0;
+
+	while (!list_empty(&list)) {
+		rq = list_entry_rq(list.next);
+		list_del_init(&rq->queuelist);
+		BUG_ON(!rq->q);
+		if (rq->mq_ctx != this_ctx) {
+			if (this_ctx) {
+				blk_mq_insert_requests(this_q, this_ctx,
+							&ctx_list, depth,
+							from_schedule);
+			}
+
+			this_ctx = rq->mq_ctx;
+			this_q = rq->q;
+			depth = 0;
+		}
+
+		depth++;
+		list_add_tail(&rq->queuelist, &ctx_list);
+	}
+
+	/*
+	 * If 'this_ctx' is set, we know we have entries to complete
+	 * on 'ctx_list'. Do those.
+	 */
+	if (this_ctx) {
+		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
+				       from_schedule);
+	}
+}
+
+static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
+{
+	init_request_from_bio(rq, bio);
+	blk_account_io_start(rq, 1);
+}
+
+static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	const int is_sync = rw_is_sync(bio->bi_rw);
+	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	int rw = bio_data_dir(bio);
+	struct request *rq;
+	unsigned int use_plug, request_count = 0;
+
+	/*
+	 * If we have multiple hardware queues, just go directly to
+	 * one of those for sync IO.
+	 */
+	use_plug = !is_flush_fua && ((q->nr_hw_queues == 1) || !is_sync);
+
+	blk_queue_bounce(q, &bio);
+
+	if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
+		return;
+
+	if (blk_mq_queue_enter(q)) {
+		bio_endio(bio, -EIO);
+		return;
+	}
+
+	ctx = blk_mq_get_ctx(q);
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	trace_block_getrq(q, bio, rw);
+	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
+	if (likely(rq))
+		blk_mq_rq_ctx_init(ctx, rq, rw);
+	else {
+		blk_mq_put_ctx(ctx);
+		trace_block_sleeprq(q, bio, rw);
+		rq = blk_mq_alloc_request_pinned(q, rw, __GFP_WAIT|GFP_ATOMIC,
+							false);
+		ctx = rq->mq_ctx;
+		hctx = q->mq_ops->map_queue(q, ctx->cpu);
+	}
+
+	hctx->queued++;
+
+	if (unlikely(is_flush_fua)) {
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_put_ctx(ctx);
+		blk_insert_flush(rq);
+		goto run_queue;
+	}
+
+	/*
+	 * A task plug currently exists. Since this is completely lockless,
+	 * utilize that to temporarily store requests until the task is
+	 * either done or scheduled away.
+	 */
+	if (use_plug) {
+		struct blk_plug *plug = current->plug;
+
+		if (plug) {
+			blk_mq_bio_to_request(rq, bio);
+			if (list_empty(&plug->list))
+				trace_block_plug(q);
+			else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+				blk_flush_plug_list(plug, false);
+				trace_block_plug(q);
+			}
+			list_add_tail(&rq->queuelist, &plug->mq_list);
+			blk_mq_put_ctx(ctx);
+			return;
+		}
+	}
+
+	spin_lock(&ctx->lock);
+
+	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+	    blk_mq_attempt_merge(q, ctx, bio))
+		__blk_mq_free_request(hctx, ctx, rq);
+	else {
+		blk_mq_bio_to_request(rq, bio);
+		__blk_mq_insert_request(hctx, rq);
+	}
+
+	spin_unlock(&ctx->lock);
+	blk_mq_put_ctx(ctx);
+
+	/*
+	 * For a SYNC request, send it to the hardware immediately. For an
+	 * ASYNC request, just ensure that we run it later on. The latter
+	 * allows for merging opportunities and more efficient dispatching.
+	 */
+run_queue:
+	blk_mq_run_hw_queue(hctx, !is_sync || is_flush_fua);
+}
+
+/*
+ * Default mapping to a software queue, since we use one per CPU.
+ */
+struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, const int cpu)
+{
+	return q->queue_hw_ctx[q->mq_map[cpu]];
+}
+EXPORT_SYMBOL(blk_mq_map_queue);
+
+struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *reg,
+						   unsigned int hctx_index)
+{
+	return kmalloc_node(sizeof(struct blk_mq_hw_ctx),
+				GFP_KERNEL | __GFP_ZERO, reg->numa_node);
+}
+EXPORT_SYMBOL(blk_mq_alloc_single_hw_queue);
+
+void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *hctx,
+				 unsigned int hctx_index)
+{
+	kfree(hctx);
+}
+EXPORT_SYMBOL(blk_mq_free_single_hw_queue);
+
+static void blk_mq_hctx_notify(void *data, unsigned long action,
+			       unsigned int cpu)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+	struct blk_mq_ctx *ctx;
+	LIST_HEAD(tmp);
+
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
+		return;
+
+	/*
+	 * Move ctx entries to new CPU, if this one is going away.
+	 */
+	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
+
+	spin_lock(&ctx->lock);
+	if (!list_empty(&ctx->rq_list)) {
+		list_splice_init(&ctx->rq_list, &tmp);
+		clear_bit(ctx->index_hw, hctx->ctx_map);
+	}
+	spin_unlock(&ctx->lock);
+
+	if (list_empty(&tmp))
+		return;
+
+	ctx = blk_mq_get_ctx(hctx->queue);
+	spin_lock(&ctx->lock);
+
+	while (!list_empty(&tmp)) {
+		struct request *rq;
+
+		rq = list_first_entry(&tmp, struct request, queuelist);
+		rq->mq_ctx = ctx;
+		list_move_tail(&rq->queuelist, &ctx->rq_list);
+	}
+
+	blk_mq_hctx_mark_pending(hctx, ctx);
+
+	spin_unlock(&ctx->lock);
+	blk_mq_put_ctx(ctx);
+}
+
+static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
+				    void (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+				    void *data)
+{
+	unsigned int i;
+
+	for (i = 0; i < hctx->queue_depth; i++) {
+		struct request *rq = hctx->rqs[i];
+
+		init(data, hctx, rq, i);
+	}
+}
+
+void blk_mq_init_commands(struct request_queue *q,
+			  void (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+			  void *data)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_init_hw_commands(hctx, init, data);
+}
+EXPORT_SYMBOL(blk_mq_init_commands);
+
+static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
+{
+	struct page *page;
+
+	while (!list_empty(&hctx->page_list)) {
+		page = list_first_entry(&hctx->page_list, struct page, list);
+		list_del_init(&page->list);
+		__free_pages(page, page->private);
+	}
+
+	kfree(hctx->rqs);
+
+	if (hctx->tags)
+		blk_mq_free_tags(hctx->tags);
+}
+
+static size_t order_to_size(unsigned int order)
+{
+	size_t ret = PAGE_SIZE;
+
+	while (order--)
+		ret *= 2;
+
+	return ret;
+}
+
+static int blk_mq_init_rq_map(struct blk_mq_hw_ctx *hctx,
+			      unsigned int reserved_tags, int node)
+{
+	unsigned int i, j, entries_per_page, max_order = 4;
+	size_t rq_size, left;
+
+	INIT_LIST_HEAD(&hctx->page_list);
+
+	hctx->rqs = kmalloc_node(hctx->queue_depth * sizeof(struct request *),
+					GFP_KERNEL, node);
+	if (!hctx->rqs)
+		return -ENOMEM;
+
+	/*
+	 * rq_size is the size of the request plus driver payload, rounded
+	 * to the cacheline size
+	 */
+	rq_size = round_up(sizeof(struct request) + hctx->cmd_size,
+				cache_line_size());
+	left = rq_size * hctx->queue_depth;
+
+	for (i = 0; i < hctx->queue_depth;) {
+		int this_order = max_order;
+		struct page *page;
+		int to_do;
+		void *p;
+
+		while (left < order_to_size(this_order - 1) && this_order)
+			this_order--;
+
+		do {
+			page = alloc_pages_node(node, GFP_KERNEL, this_order);
+			if (page)
+				break;
+			if (!this_order--)
+				break;
+			if (order_to_size(this_order) < rq_size)
+				break;
+		} while (1);
+
+		if (!page)
+			break;
+
+		page->private = this_order;
+		list_add_tail(&page->list, &hctx->page_list);
+
+		p = page_address(page);
+		entries_per_page = order_to_size(this_order) / rq_size;
+		to_do = min(entries_per_page, hctx->queue_depth - i);
+		left -= to_do * rq_size;
+		for (j = 0; j < to_do; j++) {
+			hctx->rqs[i] = p;
+			blk_mq_rq_init(hctx, hctx->rqs[i]);
+			p += rq_size;
+			i++;
+		}
+	}
+
+	if (i < (reserved_tags + BLK_MQ_TAG_MIN))
+		goto err_rq_map;
+	else if (i != hctx->queue_depth) {
+		hctx->queue_depth = i;
+		pr_warn("%s: queue depth set to %u because of low memory\n",
+					__func__, i);
+	}
+
+	hctx->tags = blk_mq_init_tags(hctx->queue_depth, reserved_tags, node);
+	if (!hctx->tags) {
+err_rq_map:
+		blk_mq_free_rq_map(hctx);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int blk_mq_init_hw_queues(struct request_queue *q,
+				 struct blk_mq_reg *reg, void *driver_data)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i, j;
+
+	/*
+	 * Initialize hardware queues
+	 */
+	queue_for_each_hw_ctx(q, hctx, i) {
+		unsigned int num_maps;
+		int node;
+
+		node = hctx->numa_node;
+		if (node == NUMA_NO_NODE)
+			node = hctx->numa_node = reg->numa_node;
+
+		INIT_DELAYED_WORK(&hctx->delayed_work, blk_mq_work_fn);
+		spin_lock_init(&hctx->lock);
+		INIT_LIST_HEAD(&hctx->dispatch);
+		hctx->queue = q;
+		hctx->queue_num = i;
+		hctx->flags = reg->flags;
+		hctx->queue_depth = reg->queue_depth;
+		hctx->cmd_size = reg->cmd_size;
+
+		blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
+						blk_mq_hctx_notify, hctx);
+		blk_mq_register_cpu_notifier(&hctx->cpu_notifier);
+
+		if (blk_mq_init_rq_map(hctx, reg->reserved_tags, node))
+			break;
+
+		/*
+		 * Allocate space for all possible cpus to avoid allocation in
+		 * runtime
+		 */
+		hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
+						GFP_KERNEL, node);
+		if (!hctx->ctxs)
+			break;
+
+		num_maps = ALIGN(nr_cpu_ids, BITS_PER_LONG) / BITS_PER_LONG;
+		hctx->ctx_map = kzalloc_node(num_maps * sizeof(unsigned long),
+						GFP_KERNEL, node);
+		if (!hctx->ctx_map)
+			break;
+
+		hctx->nr_ctx_map = num_maps;
+		hctx->nr_ctx = 0;
+
+		if (reg->ops->init_hctx &&
+		    reg->ops->init_hctx(hctx, driver_data, i))
+			break;
+	}
+
+	if (i == q->nr_hw_queues)
+		return 0;
+
+	/*
+	 * Init failed
+	 */
+	queue_for_each_hw_ctx(q, hctx, j) {
+		if (i == j)
+			break;
+
+		if (reg->ops->exit_hctx)
+			reg->ops->exit_hctx(hctx, j);
+
+		blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+		blk_mq_free_rq_map(hctx);
+		kfree(hctx->ctxs);
+	}
+
+	return 1;
+}
+
+static void blk_mq_init_cpu_queues(struct request_queue *q,
+				   unsigned int nr_hw_queues)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i) {
+		struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
+		struct blk_mq_hw_ctx *hctx;
+
+		memset(__ctx, 0, sizeof(*__ctx));
+		__ctx->cpu = i;
+		spin_lock_init(&__ctx->lock);
+		INIT_LIST_HEAD(&__ctx->rq_list);
+		__ctx->queue = q;
+
+		/* If the cpu isn't online, the cpu is mapped to first hctx */
+		hctx = q->mq_ops->map_queue(q, i);
+		hctx->nr_ctx++;
+
+		if (!cpu_online(i))
+			continue;
+
+		/*
+		 * Set local node, IFF we have more than one hw queue. If
+		 * not, we remain on the home node of the device
+		 */
+		if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
+			hctx->numa_node = cpu_to_node(i);
+	}
+}
+
+static void blk_mq_map_swqueue(struct request_queue *q)
+{
+	unsigned int i;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->nr_ctx = 0;
+	}
+
+	/*
+	 * Map software to hardware queues
+	 */
+	queue_for_each_ctx(q, ctx, i) {
+		/* If the cpu isn't online, the cpu is mapped to first hctx */
+		hctx = q->mq_ops->map_queue(q, i);
+		ctx->index_hw = hctx->nr_ctx;
+		hctx->ctxs[hctx->nr_ctx++] = ctx;
+	}
+}
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
+					void *driver_data)
+{
+	struct blk_mq_hw_ctx **hctxs;
+	struct blk_mq_ctx *ctx;
+	struct request_queue *q;
+	int i;
+
+	if (!reg->nr_hw_queues ||
+	    !reg->ops->queue_rq || !reg->ops->map_queue ||
+	    !reg->ops->alloc_hctx || !reg->ops->free_hctx)
+		return ERR_PTR(-EINVAL);
+
+	if (!reg->queue_depth)
+		reg->queue_depth = BLK_MQ_MAX_DEPTH;
+	else if (reg->queue_depth > BLK_MQ_MAX_DEPTH) {
+		pr_err("blk-mq: queuedepth too large (%u)\n", reg->queue_depth);
+		reg->queue_depth = BLK_MQ_MAX_DEPTH;
+	}
+
+	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
+		return ERR_PTR(-EINVAL);
+
+	ctx = alloc_percpu(struct blk_mq_ctx);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	hctxs = kmalloc_node(reg->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
+			reg->numa_node);
+
+	if (!hctxs)
+		goto err_percpu;
+
+	for (i = 0; i < reg->nr_hw_queues; i++) {
+		hctxs[i] = reg->ops->alloc_hctx(reg, i);
+		if (!hctxs[i])
+			goto err_hctxs;
+
+		hctxs[i]->numa_node = NUMA_NO_NODE;
+		hctxs[i]->queue_num = i;
+	}
+
+	q = blk_alloc_queue_node(GFP_KERNEL, reg->numa_node);
+	if (!q)
+		goto err_hctxs;
+
+	q->mq_map = blk_mq_make_queue_map(reg);
+	if (!q->mq_map)
+		goto err_map;
+
+	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
+	blk_queue_rq_timeout(q, 30000);
+
+	q->nr_queues = nr_cpu_ids;
+	q->nr_hw_queues = reg->nr_hw_queues;
+
+	q->queue_ctx = ctx;
+	q->queue_hw_ctx = hctxs;
+
+	q->mq_ops = reg->ops;
+
+	blk_queue_make_request(q, blk_mq_make_request);
+	blk_queue_rq_timed_out(q, reg->ops->timeout);
+	if (reg->timeout)
+		blk_queue_rq_timeout(q, reg->timeout);
+
+	blk_mq_init_flush(q);
+	blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
+
+	if (blk_mq_init_hw_queues(q, reg, driver_data))
+		goto err_hw;
+
+	blk_mq_map_swqueue(q);
+
+	mutex_lock(&all_q_mutex);
+	list_add_tail(&q->all_q_node, &all_q_list);
+	mutex_unlock(&all_q_mutex);
+
+	return q;
+err_hw:
+	kfree(q->mq_map);
+err_map:
+	blk_cleanup_queue(q);
+err_hctxs:
+	for (i = 0; i < reg->nr_hw_queues; i++) {
+		if (!hctxs[i])
+			break;
+		reg->ops->free_hctx(hctxs[i], i);
+	}
+	kfree(hctxs);
+err_percpu:
+	free_percpu(ctx);
+	return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL(blk_mq_init_queue);
+
+void blk_mq_free_queue(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		cancel_delayed_work_sync(&hctx->delayed_work);
+		kfree(hctx->ctx_map);
+		kfree(hctx->ctxs);
+		blk_mq_free_rq_map(hctx);
+		blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+		if (q->mq_ops->exit_hctx)
+			q->mq_ops->exit_hctx(hctx, i);
+		q->mq_ops->free_hctx(hctx, i);
+	}
+
+	free_percpu(q->queue_ctx);
+	kfree(q->queue_hw_ctx);
+	kfree(q->mq_map);
+
+	q->queue_ctx = NULL;
+	q->queue_hw_ctx = NULL;
+	q->mq_map = NULL;
+
+	mutex_lock(&all_q_mutex);
+	list_del_init(&q->all_q_node);
+	mutex_unlock(&all_q_mutex);
+}
+EXPORT_SYMBOL(blk_mq_free_queue);
+
+/* Basically redo blk_mq_init_queue with queue frozen */
+static void __cpuinit blk_mq_queue_reinit(struct request_queue *q)
+{
+	blk_mq_freeze_queue(q);
+
+	blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues);
+
+	/*
+	 * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
+	 * we should change hctx numa_node according to new topology (this
+	 * involves free and re-allocate memory, worthy doing?)
+	 */
+
+	blk_mq_map_swqueue(q);
+
+	blk_mq_unfreeze_queue(q);
+}
+
+static int __cpuinit blk_mq_queue_reinit_notify(struct notifier_block *nb,
+		unsigned long action, void *hcpu)
+{
+	struct request_queue *q;
+
+	/*
+	 * Before new mapping is established, hotadded cpu might already start
+	 * handling requests. This doesn't break anything as we map offline
+	 * CPUs to first hardware queue. We will re-init queue below to get
+	 * optimal settings.
+	 */
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN &&
+	    action != CPU_ONLINE && action != CPU_ONLINE_FROZEN)
+		return NOTIFY_OK;
+
+	mutex_lock(&all_q_mutex);
+	list_for_each_entry(q, &all_q_list, all_q_node)
+		blk_mq_queue_reinit(q);
+	mutex_unlock(&all_q_mutex);
+	return NOTIFY_OK;
+}
+
+static int __init blk_mq_init(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		init_llist_head(&per_cpu(ipi_lists, i));
+
+	blk_mq_cpu_init();
+
+	/* Must be called after percpu_counter_hotcpu_callback() */
+	hotcpu_notifier(blk_mq_queue_reinit_notify, -10);
+
+	return 0;
+}
+subsys_initcall(blk_mq_init);
diff --git a/block/blk-mq.h b/block/blk-mq.h
new file mode 100644
index 000000000000..52bf1f96a2c2
--- /dev/null
+++ b/block/blk-mq.h
@@ -0,0 +1,52 @@
+#ifndef INT_BLK_MQ_H
+#define INT_BLK_MQ_H
+
+struct blk_mq_ctx {
+	struct {
+		spinlock_t		lock;
+		struct list_head	rq_list;
+	}  ____cacheline_aligned_in_smp;
+
+	unsigned int		cpu;
+	unsigned int		index_hw;
+	unsigned int		ipi_redirect;
+
+	/* incremented at dispatch time */
+	unsigned long		rq_dispatched[2];
+	unsigned long		rq_merged;
+
+	/* incremented at completion time */
+	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
+
+	struct request_queue	*queue;
+	struct kobject		kobj;
+};
+
+void __blk_mq_end_io(struct request *rq, int error);
+void blk_mq_complete_request(struct request *rq, int error);
+void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
+void blk_mq_init_flush(struct request_queue *q);
+
+/*
+ * CPU hotplug helpers
+ */
+struct blk_mq_cpu_notifier;
+void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
+			      void (*fn)(void *, unsigned long, unsigned int),
+			      void *data);
+void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
+void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
+void blk_mq_cpu_init(void);
+DECLARE_PER_CPU(struct llist_head, ipi_lists);
+
+/*
+ * CPU -> queue mappings
+ */
+struct blk_mq_reg;
+extern unsigned int *blk_mq_make_queue_map(struct blk_mq_reg *reg);
+extern int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues);
+
+void blk_mq_add_timer(struct request *rq);
+
+#endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3aa5b195f4dd..4f8c4d90ec73 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -7,6 +7,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/blktrace_api.h>
+#include <linux/blk-mq.h>
 
 #include "blk.h"
 #include "blk-cgroup.h"
@@ -542,6 +543,11 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
+	percpu_counter_destroy(&q->mq_usage_counter);
+
+	if (q->mq_ops)
+		blk_mq_free_queue(q);
+
 	blk_trace_shutdown(q);
 
 	bdi_destroy(&q->backing_dev_info);
@@ -575,6 +581,7 @@ int blk_register_queue(struct gendisk *disk)
 	 * bypass from queue allocation.
 	 */
 	blk_queue_bypass_end(q);
+	queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
 
 	ret = blk_trace_init_sysfs(dev);
 	if (ret)
@@ -588,6 +595,9 @@ int blk_register_queue(struct gendisk *disk)
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
+	if (q->mq_ops)
+		blk_mq_register_disk(disk);
+
 	if (!q->request_fn)
 		return 0;
 
@@ -610,6 +620,9 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
+	if (q->mq_ops)
+		blk_mq_unregister_disk(disk);
+
 	if (q->request_fn)
 		elv_unregister_queue(q);
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 65f103563969..22846cf3595a 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -7,6 +7,7 @@
 #include <linux/fault-inject.h>
 
 #include "blk.h"
+#include "blk-mq.h"
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
 
@@ -88,11 +89,18 @@ static void blk_rq_timed_out(struct request *req)
 		ret = q->rq_timed_out_fn(req);
 	switch (ret) {
 	case BLK_EH_HANDLED:
-		__blk_complete_request(req);
+		/* Can we use req->errors here? */
+		if (q->mq_ops)
+			blk_mq_complete_request(req, req->errors);
+		else
+			__blk_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:
 		blk_clear_rq_complete(req);
-		blk_add_timer(req);
+		if (q->mq_ops)
+			blk_mq_add_timer(req);
+		else
+			blk_add_timer(req);
 		break;
 	case BLK_EH_NOT_HANDLED:
 		/*
@@ -108,6 +116,23 @@ static void blk_rq_timed_out(struct request *req)
 	}
 }
 
+void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
+			  unsigned int *next_set)
+{
+	if (time_after_eq(jiffies, rq->deadline)) {
+		list_del_init(&rq->timeout_list);
+
+		/*
+		 * Check if we raced with end io completion
+		 */
+		if (!blk_mark_rq_complete(rq))
+			blk_rq_timed_out(rq);
+	} else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
+		*next_timeout = rq->deadline;
+		*next_set = 1;
+	}
+}
+
 void blk_rq_timed_out_timer(unsigned long data)
 {
 	struct request_queue *q = (struct request_queue *) data;
@@ -117,21 +142,8 @@ void blk_rq_timed_out_timer(unsigned long data)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
-	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) {
-		if (time_after_eq(jiffies, rq->deadline)) {
-			list_del_init(&rq->timeout_list);
-
-			/*
-			 * Check if we raced with end io completion
-			 */
-			if (blk_mark_rq_complete(rq))
-				continue;
-			blk_rq_timed_out(rq);
-		} else if (!next_set || time_after(next, rq->deadline)) {
-			next = rq->deadline;
-			next_set = 1;
-		}
-	}
+	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
+		blk_rq_check_expired(rq, &next, &next_set);
 
 	if (next_set)
 		mod_timer(&q->timeout, round_jiffies_up(next));
@@ -157,15 +169,7 @@ void blk_abort_request(struct request *req)
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
-/**
- * blk_add_timer - Start timeout timer for a single request
- * @req:	request that is about to start running.
- *
- * Notes:
- *    Each request has its own timer, and as it is added to the queue, we
- *    set up the timer. When the request completes, we cancel the timer.
- */
-void blk_add_timer(struct request *req)
+void __blk_add_timer(struct request *req, struct list_head *timeout_list)
 {
 	struct request_queue *q = req->q;
 	unsigned long expiry;
@@ -184,7 +188,8 @@ void blk_add_timer(struct request *req)
 		req->timeout = q->rq_timeout;
 
 	req->deadline = jiffies + req->timeout;
-	list_add_tail(&req->timeout_list, &q->timeout_list);
+	if (timeout_list)
+		list_add_tail(&req->timeout_list, timeout_list);
 
 	/*
 	 * If the timer isn't already pending or this timeout is earlier
@@ -196,5 +201,19 @@ void blk_add_timer(struct request *req)
 	if (!timer_pending(&q->timeout) ||
 	    time_before(expiry, q->timeout.expires))
 		mod_timer(&q->timeout, expiry);
+
+}
+
+/**
+ * blk_add_timer - Start timeout timer for a single request
+ * @req:	request that is about to start running.
+ *
+ * Notes:
+ *    Each request has its own timer, and as it is added to the queue, we
+ *    set up the timer. When the request completes, we cancel the timer.
+ */
+void blk_add_timer(struct request *req)
+{
+	__blk_add_timer(req, &req->q->timeout_list);
 }
 
diff --git a/block/blk.h b/block/blk.h
index e837b8f619b7..c90e1d8f7a2b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -10,6 +10,7 @@
 #define BLK_BATCH_REQ	32
 
 extern struct kmem_cache *blk_requestq_cachep;
+extern struct kmem_cache *request_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
@@ -34,14 +35,30 @@ bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
 
 void blk_rq_timed_out_timer(unsigned long data);
+void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
+			  unsigned int *next_set);
+void __blk_add_timer(struct request *req, struct list_head *timeout_list);
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
 
+
+bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
+			     struct bio *bio);
+bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
+			    struct bio *bio);
+bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+			    unsigned int *request_count);
+
+void blk_account_io_start(struct request *req, bool new_io);
+void blk_account_io_completion(struct request *req, unsigned int bytes);
+void blk_account_io_done(struct request *req);
+
 /*
  * Internal atomic flags for request handling
  */
 enum rq_atomic_flags {
 	REQ_ATOM_COMPLETE = 0,
+	REQ_ATOM_STARTED,
 };
 
 /*
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec48bac5b039..4c2775443dcf 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -419,6 +419,8 @@ static inline void bio_list_init(struct bio_list *bl)
 	bl->head = bl->tail = NULL;
 }
 
+#define BIO_EMPTY_LIST	{ NULL, NULL }
+
 #define bio_list_for_each(bio, bl) \
 	for (bio = (bl)->head; bio; bio = bio->bi_next)
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
new file mode 100644
index 000000000000..746042ff321a
--- /dev/null
+++ b/include/linux/blk-mq.h
@@ -0,0 +1,182 @@
+#ifndef BLK_MQ_H
+#define BLK_MQ_H
+
+#include <linux/blkdev.h>
+
+struct blk_mq_tags;
+
+struct blk_mq_cpu_notifier {
+	struct list_head list;
+	void *data;
+	void (*notify)(void *data, unsigned long action, unsigned int cpu);
+};
+
+struct blk_mq_hw_ctx {
+	struct {
+		spinlock_t		lock;
+		struct list_head	dispatch;
+	} ____cacheline_aligned_in_smp;
+
+	unsigned long		state;		/* BLK_MQ_S_* flags */
+	struct delayed_work	delayed_work;
+
+	unsigned long		flags;		/* BLK_MQ_F_* flags */
+
+	struct request_queue	*queue;
+	unsigned int		queue_num;
+
+	void			*driver_data;
+
+	unsigned int		nr_ctx;
+	struct blk_mq_ctx	**ctxs;
+	unsigned int 		nr_ctx_map;
+	unsigned long		*ctx_map;
+
+	struct request		**rqs;
+	struct list_head	page_list;
+	struct blk_mq_tags	*tags;
+
+	unsigned long		queued;
+	unsigned long		run;
+#define BLK_MQ_MAX_DISPATCH_ORDER	10
+	unsigned long		dispatched[BLK_MQ_MAX_DISPATCH_ORDER];
+
+	unsigned int		queue_depth;
+	unsigned int		numa_node;
+	unsigned int		cmd_size;	/* per-request extra data */
+
+	struct blk_mq_cpu_notifier	cpu_notifier;
+	struct kobject		kobj;
+};
+
+struct blk_mq_reg {
+	struct blk_mq_ops	*ops;
+	unsigned int		nr_hw_queues;
+	unsigned int		queue_depth;
+	unsigned int		reserved_tags;
+	unsigned int		cmd_size;	/* per-request extra data */
+	int			numa_node;
+	unsigned int		timeout;
+	unsigned int		flags;		/* BLK_MQ_F_* */
+};
+
+typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *);
+typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
+typedef struct blk_mq_hw_ctx *(alloc_hctx_fn)(struct blk_mq_reg *,unsigned int);
+typedef void (free_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
+typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
+typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
+
+struct blk_mq_ops {
+	/*
+	 * Queue request
+	 */
+	queue_rq_fn		*queue_rq;
+
+	/*
+	 * Map to specific hardware queue
+	 */
+	map_queue_fn		*map_queue;
+
+	/*
+	 * Called on request timeout
+	 */
+	rq_timed_out_fn		*timeout;
+
+	/*
+	 * Override for hctx allocations (should probably go)
+	 */
+	alloc_hctx_fn		*alloc_hctx;
+	free_hctx_fn		*free_hctx;
+
+	/*
+	 * Called when the block layer side of a hardware queue has been
+	 * set up, allowing the driver to allocate/init matching structures.
+	 * Ditto for exit/teardown.
+	 */
+	init_hctx_fn		*init_hctx;
+	exit_hctx_fn		*exit_hctx;
+};
+
+enum {
+	BLK_MQ_RQ_QUEUE_OK	= 0,	/* queued fine */
+	BLK_MQ_RQ_QUEUE_BUSY	= 1,	/* requeue IO for later */
+	BLK_MQ_RQ_QUEUE_ERROR	= 2,	/* end IO with error */
+
+	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
+	BLK_MQ_F_SHOULD_SORT	= 1 << 1,
+	BLK_MQ_F_SHOULD_IPI	= 1 << 2,
+
+	BLK_MQ_S_STOPPED	= 1 << 0,
+
+	BLK_MQ_MAX_DEPTH	= 2048,
+};
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_reg *, void *);
+void blk_mq_free_queue(struct request_queue *);
+int blk_mq_register_disk(struct gendisk *);
+void blk_mq_unregister_disk(struct gendisk *);
+void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data);
+
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
+
+void blk_mq_insert_request(struct request_queue *, struct request *, bool);
+void blk_mq_run_queues(struct request_queue *q, bool async);
+void blk_mq_free_request(struct request *rq);
+bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp);
+struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp);
+struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag);
+
+struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
+struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_reg *, unsigned int);
+void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int);
+
+void blk_mq_end_io(struct request *rq, int error);
+
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
+void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
+void blk_mq_start_stopped_hw_queues(struct request_queue *q);
+
+/*
+ * Driver command data is immediately after the request. So subtract request
+ * size to get back to the original request.
+ */
+static inline struct request *blk_mq_rq_from_pdu(void *pdu)
+{
+	return pdu - sizeof(struct request);
+}
+static inline void *blk_mq_rq_to_pdu(struct request *rq)
+{
+	return (void *) rq + sizeof(*rq);
+}
+
+static inline struct request *blk_mq_tag_to_rq(struct blk_mq_hw_ctx *hctx,
+					       unsigned int tag)
+{
+	return hctx->rqs[tag];
+}
+
+#define queue_for_each_hw_ctx(q, hctx, i)				\
+	for ((i) = 0, hctx = (q)->queue_hw_ctx[0];			\
+	     (i) < (q)->nr_hw_queues; (i)++, hctx = (q)->queue_hw_ctx[i])
+
+#define queue_for_each_ctx(q, ctx, i)					\
+	for ((i) = 0, ctx = per_cpu_ptr((q)->queue_ctx, 0);		\
+	     (i) < (q)->nr_queues; (i)++, ctx = per_cpu_ptr(q->queue_ctx, (i)))
+
+#define hctx_for_each_ctx(hctx, ctx, i)					\
+	for ((i) = 0, ctx = (hctx)->ctxs[0];				\
+	     (i) < (hctx)->nr_ctx; (i)++, ctx = (hctx)->ctxs[(i)])
+
+#define blk_ctx_sum(q, sum)						\
+({									\
+	struct blk_mq_ctx *__x;						\
+	unsigned int __ret = 0, __i;					\
+									\
+	queue_for_each_ctx((q), __x, __i)				\
+		__ret += sum;						\
+	__ret;								\
+})
+
+#endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index c26801e14788..238ef0ed62f8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -178,6 +178,7 @@ enum rq_flag_bits {
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
+	__REQ_END,		/* last of chain of requests */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -229,5 +230,6 @@ enum rq_flag_bits {
 #define REQ_SECURE		(1ULL << __REQ_SECURE)
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
+#define REQ_END			(1ULL << __REQ_END)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0a8da96274c3..f26ec20f6354 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -8,6 +8,7 @@
 #include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/pagemap.h>
@@ -94,10 +95,17 @@ enum rq_cmd_type_bits {
  * as well!
  */
 struct request {
-	struct list_head queuelist;
-	struct call_single_data csd;
+	union {
+		struct list_head queuelist;
+		struct llist_node ll_list;
+	};
+	union {
+		struct call_single_data csd;
+		struct work_struct mq_flush_data;
+	};
 
 	struct request_queue *q;
+	struct blk_mq_ctx *mq_ctx;
 
 	u64 cmd_flags;
 	enum rq_cmd_type_bits cmd_type;
@@ -213,6 +221,8 @@ struct request_pm_state
 
 #include <linux/elevator.h>
 
+struct blk_queue_ctx;
+
 typedef void (request_fn_proc) (struct request_queue *q);
 typedef void (make_request_fn) (struct request_queue *q, struct bio *bio);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
@@ -311,6 +321,18 @@ struct request_queue {
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
 
+	struct blk_mq_ops	*mq_ops;
+
+	unsigned int		*mq_map;
+
+	/* sw queues */
+	struct blk_mq_ctx	*queue_ctx;
+	unsigned int		nr_queues;
+
+	/* hw dispatch queues */
+	struct blk_mq_hw_ctx	**queue_hw_ctx;
+	unsigned int		nr_hw_queues;
+
 	/*
 	 * Dispatch queue sorting
 	 */
@@ -359,6 +381,11 @@ struct request_queue {
 	 */
 	struct kobject kobj;
 
+	/*
+	 * mq queue kobject
+	 */
+	struct kobject mq_kobj;
+
 #ifdef CONFIG_PM_RUNTIME
 	struct device		*dev;
 	int			rpm_status;
@@ -423,7 +450,13 @@ struct request_queue {
 	unsigned long		flush_pending_since;
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
-	struct request		flush_rq;
+	union {
+		struct request	flush_rq;
+		struct {
+			spinlock_t mq_flush_lock;
+			struct work_struct mq_flush_work;
+		};
+	};
 
 	struct mutex		sysfs_lock;
 
@@ -435,14 +468,14 @@ struct request_queue {
 	struct bsg_class_device bsg_dev;
 #endif
 
-#ifdef CONFIG_BLK_CGROUP
-	struct list_head	all_q_node;
-#endif
 #ifdef CONFIG_BLK_DEV_THROTTLING
 	/* Throttle data */
 	struct throtl_data *td;
 #endif
 	struct rcu_head		rcu_head;
+	wait_queue_head_t	mq_freeze_wq;
+	struct percpu_counter	mq_usage_counter;
+	struct list_head	all_q_node;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -465,6 +498,7 @@ struct request_queue {
 #define QUEUE_FLAG_SECDISCARD  17	/* supports SECDISCARD */
 #define QUEUE_FLAG_SAME_FORCE  18	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
+#define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -537,6 +571,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_bypass(q)	test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags)
+#define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
@@ -1011,6 +1046,7 @@ static inline void blk_post_runtime_resume(struct request_queue *q, int err) {}
 struct blk_plug {
 	unsigned long magic; /* detect uninitialized use-cases */
 	struct list_head list; /* requests */
+	struct list_head mq_list; /* blk-mq requests */
 	struct list_head cb_list; /* md requires an unplug callback */
 };
 #define BLK_MAX_REQUEST_COUNT 16
@@ -1048,7 +1084,10 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 {
 	struct blk_plug *plug = tsk->plug;
 
-	return plug && (!list_empty(&plug->list) || !list_empty(&plug->cb_list));
+	return plug &&
+		(!list_empty(&plug->list) ||
+		 !list_empty(&plug->mq_list) ||
+		 !list_empty(&plug->cb_list));
 }
 
 /*
@@ -1323,6 +1362,7 @@ static inline void put_dev_sector(Sector p)
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
+int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
 /*
-- 
cgit 


From 6b1e5a45d4eaa75e28f2d170ea43ab8fc6dd34d8 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 23 Oct 2013 10:51:20 +0200
Subject: [SCSI] remove check for 'resetting'

Field is now unused, so this is dead code.

[jejb: remove resetting and last_reset from Scsi_Host]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/scsi.c      | 28 ----------------------------
 include/scsi/scsi_host.h |  2 --
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index eaa808e6ba91..fe0bcb18fb26 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -78,11 +78,6 @@ static void scsi_done(struct scsi_cmnd *cmd);
  * Definitions and constants.
  */
 
-#define MIN_RESET_DELAY (2*HZ)
-
-/* Do not call reset on error if we just did a reset within 15 sec. */
-#define MIN_RESET_PERIOD (15*HZ)
-
 /*
  * Note - the initial logging level can be set here to log events at boot time.
  * After the system is up, you may enable logging via the /proc interface.
@@ -658,7 +653,6 @@ EXPORT_SYMBOL(scsi_cmd_get_serial);
 int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *host = cmd->device->host;
-	unsigned long timeout;
 	int rtn = 0;
 
 	atomic_inc(&cmd->device->iorequest_cnt);
@@ -704,28 +698,6 @@ int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 			       (cmd->device->lun << 5 & 0xe0);
 	}
 
-	/*
-	 * We will wait MIN_RESET_DELAY clock ticks after the last reset so
-	 * we can avoid the drive not being ready.
-	 */
-	timeout = host->last_reset + MIN_RESET_DELAY;
-
-	if (host->resetting && time_before(jiffies, timeout)) {
-		int ticks_remaining = timeout - jiffies;
-		/*
-		 * NOTE: This may be executed from within an interrupt
-		 * handler!  This is bad, but for now, it'll do.  The irq
-		 * level of the interrupt handler has been masked out by the
-		 * platform dependent interrupt handling code already, so the
-		 * sti() here will not cause another call to the SCSI host's
-		 * interrupt handler (assuming there is one irq-level per
-		 * host).
-		 */
-		while (--ticks_remaining >= 0)
-			mdelay(1 + 999 / HZ);
-		host->resetting = 0;
-	}
-
 	scsi_log_send(cmd);
 
 	/*
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 755243572219..a74b7d9afe8e 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -598,8 +598,6 @@ struct Scsi_Host {
 	unsigned int host_eh_scheduled;    /* EH scheduled without command */
     
 	unsigned int host_no;  /* Used for IOCTL_GET_IDLUN, /proc/scsi et al. */
-	int resetting; /* if set, it means that last_reset is a valid value */
-	unsigned long last_reset;
 
 	/*
 	 * These three parameters can be used to allow for wide scsi,
-- 
cgit 


From b45620229dd67ff1daffa8adce57f37b37860f78 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 23 Oct 2013 10:51:21 +0200
Subject: [SCSI] Add 'eh_deadline' to limit SCSI EH runtime

This patchs adds an 'eh_deadline' sysfs attribute to the scsi
host which limits the overall runtime of the SCSI EH.
The 'eh_deadline' value is stored in the now obsolete field
'resetting'.
When a command is failed the start time of the EH is stored
in 'last_reset'. If the overall runtime of the SCSI EH is longer
than last_reset + eh_deadline, the EH is short-circuited and
falls through to issue a host reset only.

[jejb: add comments in Scsi_Host about new fields]
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/hosts.c      |   7 +++
 drivers/scsi/scsi_error.c | 130 +++++++++++++++++++++++++++++++++++++++++++---
 drivers/scsi/scsi_sysfs.c |  37 +++++++++++++
 include/scsi/scsi_host.h  |   5 ++
 4 files changed, 173 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index df0c3c71ea43..f334859024c0 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -316,6 +316,12 @@ static void scsi_host_dev_release(struct device *dev)
 	kfree(shost);
 }
 
+static unsigned int shost_eh_deadline;
+
+module_param_named(eh_deadline, shost_eh_deadline, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(eh_deadline,
+		 "SCSI EH timeout in seconds (should be between 1 and 2^32-1)");
+
 static struct device_type scsi_host_type = {
 	.name =		"scsi_host",
 	.release =	scsi_host_dev_release,
@@ -388,6 +394,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->use_clustering = sht->use_clustering;
 	shost->ordered_tag = sht->ordered_tag;
+	shost->eh_deadline = shost_eh_deadline * HZ;
 
 	if (sht->supported_mode == MODE_UNKNOWN)
 		/* means we didn't set it ... default to INITIATOR */
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 83e591b60193..edae9e20f886 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -87,6 +87,18 @@ void scsi_schedule_eh(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL_GPL(scsi_schedule_eh);
 
+static int scsi_host_eh_past_deadline(struct Scsi_Host *shost)
+{
+	if (!shost->last_reset || !shost->eh_deadline)
+		return 0;
+
+	if (time_before(jiffies,
+			shost->last_reset + shost->eh_deadline))
+		return 0;
+
+	return 1;
+}
+
 /**
  * scsi_eh_scmd_add - add scsi cmd to error handling.
  * @scmd:	scmd to run eh on.
@@ -109,6 +121,9 @@ int scsi_eh_scmd_add(struct scsi_cmnd *scmd, int eh_flag)
 		if (scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY))
 			goto out_unlock;
 
+	if (shost->eh_deadline && !shost->last_reset)
+		shost->last_reset = jiffies;
+
 	ret = 1;
 	scmd->eh_eflags |= eh_flag;
 	list_add_tail(&scmd->eh_entry, &shost->eh_cmd_q);
@@ -138,6 +153,9 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 	trace_scsi_dispatch_cmd_timeout(scmd);
 	scsi_log_completion(scmd, TIMEOUT_ERROR);
 
+	if (host->eh_deadline && !host->last_reset)
+		host->last_reset = jiffies;
+
 	if (host->transportt->eh_timed_out)
 		rtn = host->transportt->eh_timed_out(scmd);
 	else if (host->hostt->eh_timed_out)
@@ -990,13 +1008,26 @@ int scsi_eh_get_sense(struct list_head *work_q,
 		      struct list_head *done_q)
 {
 	struct scsi_cmnd *scmd, *next;
+	struct Scsi_Host *shost;
 	int rtn;
+	unsigned long flags;
 
 	list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
 		if ((scmd->eh_eflags & SCSI_EH_CANCEL_CMD) ||
 		    SCSI_SENSE_VALID(scmd))
 			continue;
 
+		shost = scmd->device->host;
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			break;
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
 		SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd,
 						  "%s: requesting sense\n",
 						  current->comm));
@@ -1082,11 +1113,28 @@ static int scsi_eh_test_devices(struct list_head *cmd_list,
 	struct scsi_cmnd *scmd, *next;
 	struct scsi_device *sdev;
 	int finish_cmds;
+	unsigned long flags;
 
 	while (!list_empty(cmd_list)) {
 		scmd = list_entry(cmd_list->next, struct scsi_cmnd, eh_entry);
 		sdev = scmd->device;
 
+		if (!try_stu) {
+			spin_lock_irqsave(sdev->host->host_lock, flags);
+			if (scsi_host_eh_past_deadline(sdev->host)) {
+				/* Push items back onto work_q */
+				list_splice_init(cmd_list, work_q);
+				spin_unlock_irqrestore(sdev->host->host_lock,
+						       flags);
+				SCSI_LOG_ERROR_RECOVERY(3,
+					shost_printk(KERN_INFO, sdev->host,
+						     "skip %s, past eh deadline",
+						     __func__));
+				break;
+			}
+			spin_unlock_irqrestore(sdev->host->host_lock, flags);
+		}
+
 		finish_cmds = !scsi_device_online(scmd->device) ||
 			(try_stu && !scsi_eh_try_stu(scmd) &&
 			 !scsi_eh_tur(scmd)) ||
@@ -1122,14 +1170,28 @@ static int scsi_eh_abort_cmds(struct list_head *work_q,
 	struct scsi_cmnd *scmd, *next;
 	LIST_HEAD(check_list);
 	int rtn;
+	struct Scsi_Host *shost;
+	unsigned long flags;
 
 	list_for_each_entry_safe(scmd, next, work_q, eh_entry) {
 		if (!(scmd->eh_eflags & SCSI_EH_CANCEL_CMD))
 			continue;
+		shost = scmd->device->host;
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			list_splice_init(&check_list, work_q);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			return list_empty(work_q);
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
 		SCSI_LOG_ERROR_RECOVERY(3, printk("%s: aborting cmd:"
 						  "0x%p\n", current->comm,
 						  scmd));
-		rtn = scsi_try_to_abort_cmd(scmd->device->host->hostt, scmd);
+		rtn = scsi_try_to_abort_cmd(shost->hostt, scmd);
 		if (rtn == SUCCESS || rtn == FAST_IO_FAIL) {
 			scmd->eh_eflags &= ~SCSI_EH_CANCEL_CMD;
 			if (rtn == FAST_IO_FAIL)
@@ -1187,8 +1249,19 @@ static int scsi_eh_stu(struct Scsi_Host *shost,
 {
 	struct scsi_cmnd *scmd, *stu_scmd, *next;
 	struct scsi_device *sdev;
+	unsigned long flags;
 
 	shost_for_each_device(sdev, shost) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			break;
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
 		stu_scmd = NULL;
 		list_for_each_entry(scmd, work_q, eh_entry)
 			if (scmd->device == sdev && SCSI_SENSE_VALID(scmd) &&
@@ -1241,9 +1314,20 @@ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost,
 {
 	struct scsi_cmnd *scmd, *bdr_scmd, *next;
 	struct scsi_device *sdev;
+	unsigned long flags;
 	int rtn;
 
 	shost_for_each_device(sdev, shost) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			break;
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
 		bdr_scmd = NULL;
 		list_for_each_entry(scmd, work_q, eh_entry)
 			if (scmd->device == sdev) {
@@ -1303,6 +1387,21 @@ static int scsi_eh_target_reset(struct Scsi_Host *shost,
 		struct scsi_cmnd *next, *scmd;
 		int rtn;
 		unsigned int id;
+		unsigned long flags;
+
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			/* push back on work queue for further processing */
+			list_splice_init(&check_list, work_q);
+			list_splice_init(&tmp_list, work_q);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			return list_empty(work_q);
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
 
 		scmd = list_entry(tmp_list.next, struct scsi_cmnd, eh_entry);
 		id = scmd_id(scmd);
@@ -1347,6 +1446,7 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost,
 	LIST_HEAD(check_list);
 	unsigned int channel;
 	int rtn;
+	unsigned long flags;
 
 	/*
 	 * we really want to loop over the various channels, and do this on
@@ -1356,6 +1456,18 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost,
 	 */
 
 	for (channel = 0; channel <= shost->max_channel; channel++) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_eh_past_deadline(shost)) {
+			spin_unlock_irqrestore(shost->host_lock, flags);
+			list_splice_init(&check_list, work_q);
+			SCSI_LOG_ERROR_RECOVERY(3,
+				shost_printk(KERN_INFO, shost,
+					    "skip %s, past eh deadline\n",
+					     __func__));
+			return list_empty(work_q);
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
+
 		chan_scmd = NULL;
 		list_for_each_entry(scmd, work_q, eh_entry) {
 			if (channel == scmd_channel(scmd)) {
@@ -1755,8 +1867,9 @@ static void scsi_restart_operations(struct Scsi_Host *shost)
 	 * will be requests for character device operations, and also for
 	 * ioctls to queued block devices.
 	 */
-	SCSI_LOG_ERROR_RECOVERY(3, printk("%s: waking up host to restart\n",
-					  __func__));
+	SCSI_LOG_ERROR_RECOVERY(3,
+		printk("scsi_eh_%d waking up host to restart\n",
+		       shost->host_no));
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (scsi_host_set_state(shost, SHOST_RUNNING))
@@ -1883,6 +1996,10 @@ static void scsi_unjam_host(struct Scsi_Host *shost)
 		if (!scsi_eh_abort_cmds(&eh_work_q, &eh_done_q))
 			scsi_eh_ready_devs(shost, &eh_work_q, &eh_done_q);
 
+	spin_lock_irqsave(shost->host_lock, flags);
+	if (shost->eh_deadline)
+		shost->last_reset = 0;
+	spin_unlock_irqrestore(shost->host_lock, flags);
 	scsi_eh_flush_done_q(&eh_done_q);
 }
 
@@ -1909,7 +2026,7 @@ int scsi_error_handler(void *data)
 		if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
 		    shost->host_failed != shost->host_busy) {
 			SCSI_LOG_ERROR_RECOVERY(1,
-				printk("Error handler scsi_eh_%d sleeping\n",
+				printk("scsi_eh_%d: sleeping\n",
 					shost->host_no));
 			schedule();
 			continue;
@@ -1917,8 +2034,9 @@ int scsi_error_handler(void *data)
 
 		__set_current_state(TASK_RUNNING);
 		SCSI_LOG_ERROR_RECOVERY(1,
-			printk("Error handler scsi_eh_%d waking up\n",
-				shost->host_no));
+			printk("scsi_eh_%d: waking up %d/%d/%d\n",
+			       shost->host_no, shost->host_eh_scheduled,
+			       shost->host_failed, shost->host_busy));
 
 		/*
 		 * We have a host that is failing for some reason.  Figure out
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index a73471074a02..8ff62c26a41c 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -281,6 +281,42 @@ exit_store_host_reset:
 
 static DEVICE_ATTR(host_reset, S_IWUSR, NULL, store_host_reset);
 
+static ssize_t
+show_shost_eh_deadline(struct device *dev,
+		      struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+
+	return sprintf(buf, "%d\n", shost->eh_deadline / HZ);
+}
+
+static ssize_t
+store_shost_eh_deadline(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	int ret = -EINVAL;
+	int deadline;
+	unsigned long flags;
+
+	if (shost->transportt && shost->transportt->eh_strategy_handler)
+		return ret;
+
+	if (sscanf(buf, "%d\n", &deadline) == 1) {
+		spin_lock_irqsave(shost->host_lock, flags);
+		if (scsi_host_in_recovery(shost))
+			ret = -EBUSY;
+		else {
+			shost->eh_deadline = deadline * HZ;
+			ret = count;
+		}
+		spin_unlock_irqrestore(shost->host_lock, flags);
+	}
+	return ret;
+}
+
+static DEVICE_ATTR(eh_deadline, S_IRUGO | S_IWUSR, show_shost_eh_deadline, store_shost_eh_deadline);
+
 shost_rd_attr(unique_id, "%u\n");
 shost_rd_attr(host_busy, "%hu\n");
 shost_rd_attr(cmd_per_lun, "%hd\n");
@@ -308,6 +344,7 @@ static struct attribute *scsi_sysfs_shost_attrs[] = {
 	&dev_attr_prot_capabilities.attr,
 	&dev_attr_prot_guard_type.attr,
 	&dev_attr_host_reset.attr,
+	&dev_attr_eh_deadline.attr,
 	NULL
 };
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index a74b7d9afe8e..546084964d55 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -599,6 +599,11 @@ struct Scsi_Host {
     
 	unsigned int host_no;  /* Used for IOCTL_GET_IDLUN, /proc/scsi et al. */
 
+	/* next two fields are used to bound the time spent in error handling */
+	int eh_deadline;
+	unsigned long last_reset;
+
+
 	/*
 	 * These three parameters can be used to allow for wide scsi,
 	 * and for host adapters that support multiple busses
-- 
cgit 


From 280d45f6c35d8d7a0fe20c36caf426e3ac139cf9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Oct 2013 14:45:58 +0100
Subject: blk-mq: add blk_mq_stop_hw_queues

Add a helper to iterate over all hw queues and stop them.  This is useful
for driver that implement PM suspend functionality.

Signed-off-by: Christoph Hellwig <hch@lst.de>

Modified to just call blk_mq_stop_hw_queue() by Jens.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         | 10 ++++++++++
 include/linux/blk-mq.h |  1 +
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f21ec964e411..ac804c635040 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -672,6 +672,16 @@ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
 
+void blk_mq_stop_hw_queues(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_stop_hw_queue(hctx);
+}
+EXPORT_SYMBOL(blk_mq_stop_hw_queues);
+
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 746042ff321a..3368b97bee73 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -136,6 +136,7 @@ void blk_mq_end_io(struct request *rq, int error);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
+void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q);
 
 /*
-- 
cgit 


From 6dd17757927ba9d23c604fee6fe72b4755c7ea7f Mon Sep 17 00:00:00 2001
From: Brian Austin <brian.austin@cirrus.com>
Date: Fri, 25 Oct 2013 10:01:14 -0500
Subject: ASoC: cs42l52: Add platform data for reset gpio

This patch adds platform data support for a reset GPIO.
Also uses reset_gpio to toggle reset of the CODEC

Signed-off-by: Brian Austin <brian.austin@cirrus.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/sound/cs42l52.h    |  2 ++
 sound/soc/codecs/cs42l52.c | 21 +++++++++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/cs42l52.h b/include/sound/cs42l52.h
index 4c68955f7330..7c2be4a51894 100644
--- a/include/sound/cs42l52.h
+++ b/include/sound/cs42l52.h
@@ -31,6 +31,8 @@ struct cs42l52_platform_data {
 	/* Charge Pump Freq. Check datasheet Pg73 */
 	unsigned int chgfreq;
 
+	/* Reset GPIO */
+	unsigned int reset_gpio;
 };
 
 #endif /* __CS42L52_H */
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index be2ba1b6fe4a..8367f3c571eb 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
 #include <linux/pm.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
@@ -1205,6 +1206,7 @@ static int cs42l52_i2c_probe(struct i2c_client *i2c_client,
 			     const struct i2c_device_id *id)
 {
 	struct cs42l52_private *cs42l52;
+	struct cs42l52_platform_data *pdata = dev_get_platdata(&i2c_client->dev);
 	int ret;
 	unsigned int devid = 0;
 	unsigned int reg;
@@ -1222,11 +1224,22 @@ static int cs42l52_i2c_probe(struct i2c_client *i2c_client,
 		return ret;
 	}
 
-	i2c_set_clientdata(i2c_client, cs42l52);
+	if (pdata)
+		cs42l52->pdata = *pdata;
 
-	if (dev_get_platdata(&i2c_client->dev))
-		memcpy(&cs42l52->pdata, dev_get_platdata(&i2c_client->dev),
-		       sizeof(cs42l52->pdata));
+	if (cs42l52->pdata.reset_gpio) {
+		ret = gpio_request_one(cs42l52->pdata.reset_gpio,
+				       GPIOF_OUT_INIT_HIGH, "CS42L52 /RST");
+		if (ret < 0) {
+			dev_err(&i2c_client->dev, "Failed to request /RST %d: %d\n",
+				cs42l52->pdata.reset_gpio, ret);
+			return ret;
+		}
+		gpio_set_value_cansleep(cs42l52->pdata.reset_gpio, 0);
+		gpio_set_value_cansleep(cs42l52->pdata.reset_gpio, 1);
+	}
+
+	i2c_set_clientdata(i2c_client, cs42l52);
 
 	ret = regmap_register_patch(cs42l52->regmap, cs42l52_threshold_patch,
 				    ARRAY_SIZE(cs42l52_threshold_patch));
-- 
cgit 


From 954e04b9491adea99e4590bc73937fdd8774ab3c Mon Sep 17 00:00:00 2001
From: Bryan Wu <cooloney@gmail.com>
Date: Tue, 24 Sep 2013 10:38:26 -0700
Subject: of: introduce of_get_available_child_count

Some drivers keep counting available child by themselves. So
introduce a new simple API like of_get_child_count() but for
available childs.

Cc: Josh Wu <josh.wu@atmel.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
Acked-by: Rob Herring <rob.herring@calxeda.com>
---
 include/linux/of.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index f95aee391e30..54c25606a997 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -226,6 +226,17 @@ static inline int of_get_child_count(const struct device_node *np)
 	return num;
 }
 
+static inline int of_get_available_child_count(const struct device_node *np)
+{
+	struct device_node *child;
+	int num = 0;
+
+	for_each_available_child_of_node(np, child)
+		num++;
+
+	return num;
+}
+
 extern struct device_node *of_find_node_with_property(
 	struct device_node *from, const char *prop_name);
 #define for_each_node_with_property(dn, prop_name) \
@@ -376,6 +387,11 @@ static inline int of_get_child_count(const struct device_node *np)
 	return 0;
 }
 
+static inline int of_get_available_child_count(const struct device_node *np)
+{
+	return 0;
+}
+
 static inline int of_device_is_compatible(const struct device_node *device,
 					  const char *name)
 {
-- 
cgit 


From 30dae2f98612d7c8cd855861b9de205ebd9ef4fa Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@debian.org>
Date: Tue, 22 Oct 2013 11:02:56 -0700
Subject: leds: lp55xx: handle enable pin in driver

This patch moves the handling of the chip's enable pin from the board
code into the driver. It also updates all board-code files using the
driver to incorporate this change.

This is needed for device tree support of the enable pin.

Signed-off-by: Sebastian Reichel <sre@debian.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 .../devicetree/bindings/leds/leds-lp55xx.txt       |  1 +
 arch/arm/mach-omap2/board-rx51-peripherals.c       | 20 +----------------
 arch/arm/mach-ux500/board-mop500.c                 |  2 ++
 drivers/leds/leds-lp55xx-common.c                  | 25 +++++++++++-----------
 include/linux/platform_data/leds-lp55xx.h          |  6 ++----
 5 files changed, 19 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
index d221e75d90fa..c55b8c016a9e 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
@@ -10,6 +10,7 @@ Each child has own specific current settings
 - max-cur: Maximun current at each led channel.
 
 Optional properties:
+- enable-gpio: GPIO attached to the chip's enable pin
 - label: Used for naming LEDs
 - pwr-sel: LP8501 specific property. Power selection for output channels.
          0: D1~9 are connected to VDD
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index f6fe388af989..68dc998fa34b 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -211,29 +211,11 @@ static struct lp55xx_led_config rx51_lp5523_led_config[] = {
 	}
 };
 
-static int rx51_lp5523_setup(void)
-{
-	return gpio_request_one(RX51_LP5523_CHIP_EN_GPIO, GPIOF_DIR_OUT,
-			"lp5523_enable");
-}
-
-static void rx51_lp5523_release(void)
-{
-	gpio_free(RX51_LP5523_CHIP_EN_GPIO);
-}
-
-static void rx51_lp5523_enable(bool state)
-{
-	gpio_set_value(RX51_LP5523_CHIP_EN_GPIO, !!state);
-}
-
 static struct lp55xx_platform_data rx51_lp5523_platform_data = {
 	.led_config		= rx51_lp5523_led_config,
 	.num_channels		= ARRAY_SIZE(rx51_lp5523_led_config),
 	.clock_mode		= LP55XX_CLOCK_AUTO,
-	.setup_resources	= rx51_lp5523_setup,
-	.release_resources	= rx51_lp5523_release,
-	.enable			= rx51_lp5523_enable,
+	.enable_gpio		= RX51_LP5523_CHIP_EN_GPIO,
 };
 #endif
 
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index ad0806eff762..703dec2b7d8d 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -297,6 +297,7 @@ static struct lp55xx_platform_data __initdata lp5521_pri_data = {
        .led_config     = &lp5521_pri_led[0],
        .num_channels   = 3,
        .clock_mode     = LP55XX_CLOCK_EXT,
+       .enable_gpio    = -1,
 };
 
 static struct lp55xx_led_config lp5521_sec_led[] = {
@@ -322,6 +323,7 @@ static struct lp55xx_platform_data __initdata lp5521_sec_data = {
        .led_config     = &lp5521_sec_led[0],
        .num_channels   = 3,
        .clock_mode     = LP55XX_CLOCK_EXT,
+       .enable_gpio    = -1,
 };
 
 /* I2C0 devices only available on the first HREF/MOP500 */
diff --git a/drivers/leds/leds-lp55xx-common.c b/drivers/leds/leds-lp55xx-common.c
index 075acf5b9fab..9acc6bb7deef 100644
--- a/drivers/leds/leds-lp55xx-common.c
+++ b/drivers/leds/leds-lp55xx-common.c
@@ -20,6 +20,8 @@
 #include <linux/module.h>
 #include <linux/platform_data/leds-lp55xx.h>
 #include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
 
 #include "leds-lp55xx-common.h"
 
@@ -407,18 +409,18 @@ int lp55xx_init_device(struct lp55xx_chip *chip)
 	if (!pdata || !cfg)
 		return -EINVAL;
 
-	if (pdata->setup_resources) {
-		ret = pdata->setup_resources();
+	if (gpio_is_valid(pdata->enable_gpio)) {
+		ret = devm_gpio_request_one(dev, pdata->enable_gpio,
+					    GPIOF_DIR_OUT, "lp5523_enable");
 		if (ret < 0) {
-			dev_err(dev, "setup resoure err: %d\n", ret);
+			dev_err(dev, "could not acquire enable gpio (err=%d)\n",
+				ret);
 			goto err;
 		}
-	}
 
-	if (pdata->enable) {
-		pdata->enable(0);
+		gpio_set_value(pdata->enable_gpio, 0);
 		usleep_range(1000, 2000); /* Keep enable down at least 1ms */
-		pdata->enable(1);
+		gpio_set_value(pdata->enable_gpio, 1);
 		usleep_range(1000, 2000); /* 500us abs min. */
 	}
 
@@ -459,11 +461,8 @@ void lp55xx_deinit_device(struct lp55xx_chip *chip)
 	if (chip->clk)
 		clk_disable_unprepare(chip->clk);
 
-	if (pdata->enable)
-		pdata->enable(0);
-
-	if (pdata->release_resources)
-		pdata->release_resources();
+	if (gpio_is_valid(pdata->enable_gpio))
+		gpio_set_value(pdata->enable_gpio, 0);
 }
 EXPORT_SYMBOL_GPL(lp55xx_deinit_device);
 
@@ -596,6 +595,8 @@ int lp55xx_of_populate_pdata(struct device *dev, struct device_node *np)
 	of_property_read_string(np, "label", &pdata->label);
 	of_property_read_u8(np, "clock-mode", &pdata->clock_mode);
 
+	pdata->enable_gpio = of_get_named_gpio(np, "enable-gpio", 0);
+
 	/* LP8501 specific */
 	of_property_read_u8(np, "pwr-sel", (u8 *)&pdata->pwr_sel);
 
diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h
index c32de4dcec54..624ff9edad6f 100644
--- a/include/linux/platform_data/leds-lp55xx.h
+++ b/include/linux/platform_data/leds-lp55xx.h
@@ -67,10 +67,8 @@ struct lp55xx_platform_data {
 	/* Clock configuration */
 	u8 clock_mode;
 
-	/* Platform specific functions */
-	int (*setup_resources)(void);
-	void (*release_resources)(void);
-	void (*enable)(bool state);
+	/* optional enable GPIO */
+	int enable_gpio;
 
 	/* Predefined pattern data */
 	struct lp55xx_predef_pattern *patterns;
-- 
cgit 


From 5d4879cda67b09f086807821cf594ee079d6dfbe Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Thu, 19 Sep 2013 16:03:50 -0500
Subject: PM / OPP: rename functions to dev_pm_opp*

Since Operating Performance Points (OPP) functions are specific to
device specific power management, be specific and rename opp_*
accessors in OPP library with dev_pm_opp_* equivalent.

Affected functions are:
 opp_get_voltage
 opp_get_freq
 opp_get_opp_count
 opp_find_freq_exact
 opp_find_freq_floor
 opp_find_freq_ceil
 opp_add
 opp_enable
 opp_disable
 opp_get_notifier
 opp_init_cpufreq_table
 opp_free_cpufreq_table

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Nishanth Menon <nm@ti.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/opp.txt             | 102 ++++++++++++++++----------------
 arch/arm/mach-imx/mach-imx6q.c          |   2 +-
 arch/arm/mach-omap2/board-omap3beagle.c |   8 +--
 arch/arm/mach-omap2/opp.c               |   4 +-
 arch/arm/mach-omap2/pm.c                |   4 +-
 drivers/base/power/opp.c                |  82 ++++++++++++-------------
 drivers/cpufreq/arm_big_little.c        |   6 +-
 drivers/cpufreq/cpufreq-cpu0.c          |  18 +++---
 drivers/cpufreq/exynos5440-cpufreq.c    |  13 ++--
 drivers/cpufreq/imx6q-cpufreq.c         |  20 +++----
 drivers/cpufreq/omap-cpufreq.c          |   8 +--
 drivers/devfreq/devfreq.c               |  14 ++---
 drivers/devfreq/exynos/exynos4_bus.c    |  21 +++----
 drivers/devfreq/exynos/exynos5_bus.c    |  18 +++---
 include/linux/opp.h                     |  50 ++++++++--------
 15 files changed, 187 insertions(+), 183 deletions(-)

(limited to 'include')

diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index 425c51d56aef..185367b1848f 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -71,14 +71,14 @@ operations until that OPP could be re-enabled if possible.
 
 OPP library facilitates this concept in it's implementation. The following
 operational functions operate only on available opps:
-opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
-and opp_init_cpufreq_table
+opp_find_freq_{ceil, floor}, dev_pm_opp_get_voltage, dev_pm_opp_get_freq, dev_pm_opp_get_opp_count
+and dev_pm_opp_init_cpufreq_table
 
-opp_find_freq_exact is meant to be used to find the opp pointer which can then
-be used for opp_enable/disable functions to make an opp available as required.
+dev_pm_opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for dev_pm_opp_enable/disable functions to make an opp available as required.
 
 WARNING: Users of OPP library should refresh their availability count using
-get_opp_count if opp_enable/disable functions are invoked for a device, the
+get_opp_count if dev_pm_opp_enable/disable functions are invoked for a device, the
 exact mechanism to trigger these or the notification mechanism to other
 dependent subsystems such as cpufreq are left to the discretion of the SoC
 specific framework which uses the OPP library. Similar care needs to be taken
@@ -96,24 +96,24 @@ using RCU read locks. The opp_find_freq_{exact,ceil,floor},
 opp_get_{voltage, freq, opp_count} fall into this category.
 
 opp_{add,enable,disable} are updaters which use mutex and implement it's own
-RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+RCU locking mechanisms. dev_pm_opp_init_cpufreq_table acts as an updater and uses
 mutex to implment RCU updater strategy. These functions should *NOT* be called
 under RCU locks and other contexts that prevent blocking functions in RCU or
 mutex operations from working.
 
 2. Initial OPP List Registration
 ================================
-The SoC implementation calls opp_add function iteratively to add OPPs per
+The SoC implementation calls dev_pm_opp_add function iteratively to add OPPs per
 device. It is expected that the SoC framework will register the OPP entries
 optimally- typical numbers range to be less than 5. The list generated by
 registering the OPPs is maintained by OPP library throughout the device
 operation. The SoC framework can subsequently control the availability of the
-OPPs dynamically using the opp_enable / disable functions.
+OPPs dynamically using the dev_pm_opp_enable / disable functions.
 
-opp_add - Add a new OPP for a specific domain represented by the device pointer.
+dev_pm_opp_add - Add a new OPP for a specific domain represented by the device pointer.
 	The OPP is defined using the frequency and voltage. Once added, the OPP
 	is assumed to be available and control of it's availability can be done
-	with the opp_enable/disable functions. OPP library internally stores
+	with the dev_pm_opp_enable/disable functions. OPP library internally stores
 	and manages this information in the opp struct. This function may be
 	used by SoC framework to define a optimal list as per the demands of
 	SoC usage environment.
@@ -124,7 +124,7 @@ opp_add - Add a new OPP for a specific domain represented by the device pointer.
 	 soc_pm_init()
 	 {
 		/* Do things */
-		r = opp_add(mpu_dev, 1000000, 900000);
+		r = dev_pm_opp_add(mpu_dev, 1000000, 900000);
 		if (!r) {
 			pr_err("%s: unable to register mpu opp(%d)\n", r);
 			goto no_cpufreq;
@@ -143,44 +143,44 @@ functions return the matching pointer representing the opp if a match is
 found, else returns error. These errors are expected to be handled by standard
 error checks such as IS_ERR() and appropriate actions taken by the caller.
 
-opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+dev_pm_opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
 	availability. This function is especially useful to enable an OPP which
 	is not available by default.
 	Example: In a case when SoC framework detects a situation where a
 	higher frequency could be made available, it can use this function to
-	find the OPP prior to call the opp_enable to actually make it available.
+	find the OPP prior to call the dev_pm_opp_enable to actually make it available.
 	 rcu_read_lock();
-	 opp = opp_find_freq_exact(dev, 1000000000, false);
+	 opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
 	 rcu_read_unlock();
 	 /* dont operate on the pointer.. just do a sanity check.. */
 	 if (IS_ERR(opp)) {
 		pr_err("frequency not disabled!\n");
 		/* trigger appropriate actions.. */
 	 } else {
-		opp_enable(dev,1000000000);
+		dev_pm_opp_enable(dev,1000000000);
 	 }
 
 	NOTE: This is the only search function that operates on OPPs which are
 	not available.
 
-opp_find_freq_floor - Search for an available OPP which is *at most* the
+dev_pm_opp_find_freq_floor - Search for an available OPP which is *at most* the
 	provided frequency. This function is useful while searching for a lesser
 	match OR operating on OPP information in the order of decreasing
 	frequency.
 	Example: To find the highest opp for a device:
 	 freq = ULONG_MAX;
 	 rcu_read_lock();
-	 opp_find_freq_floor(dev, &freq);
+	 dev_pm_opp_find_freq_floor(dev, &freq);
 	 rcu_read_unlock();
 
-opp_find_freq_ceil - Search for an available OPP which is *at least* the
+dev_pm_opp_find_freq_ceil - Search for an available OPP which is *at least* the
 	provided frequency. This function is useful while searching for a
 	higher match OR operating on OPP information in the order of increasing
 	frequency.
 	Example 1: To find the lowest opp for a device:
 	 freq = 0;
 	 rcu_read_lock();
-	 opp_find_freq_ceil(dev, &freq);
+	 dev_pm_opp_find_freq_ceil(dev, &freq);
 	 rcu_read_unlock();
 	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
 	 soc_cpufreq_target(..)
@@ -188,7 +188,7 @@ opp_find_freq_ceil - Search for an available OPP which is *at least* the
 		/* Do stuff like policy checks etc. */
 		/* Find the best frequency match for the req */
 		rcu_read_lock();
-		opp = opp_find_freq_ceil(dev, &freq);
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		rcu_read_unlock();
 		if (!IS_ERR(opp))
 			soc_switch_to_freq_voltage(freq);
@@ -208,34 +208,34 @@ as thermal considerations (e.g. don't use OPPx until the temperature drops).
 
 WARNING: Do not use these functions in interrupt context.
 
-opp_enable - Make a OPP available for operation.
+dev_pm_opp_enable - Make a OPP available for operation.
 	Example: Lets say that 1GHz OPP is to be made available only if the
 	SoC temperature is lower than a certain threshold. The SoC framework
 	implementation might choose to do something as follows:
 	 if (cur_temp < temp_low_thresh) {
 		/* Enable 1GHz if it was disabled */
 		rcu_read_lock();
-		opp = opp_find_freq_exact(dev, 1000000000, false);
+		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
 		rcu_read_unlock();
 		/* just error check */
 		if (!IS_ERR(opp))
-			ret = opp_enable(dev, 1000000000);
+			ret = dev_pm_opp_enable(dev, 1000000000);
 		else
 			goto try_something_else;
 	 }
 
-opp_disable - Make an OPP to be not available for operation
+dev_pm_opp_disable - Make an OPP to be not available for operation
 	Example: Lets say that 1GHz OPP is to be disabled if the temperature
 	exceeds a threshold value. The SoC framework implementation might
 	choose to do something as follows:
 	 if (cur_temp > temp_high_thresh) {
 		/* Disable 1GHz if it was enabled */
 		rcu_read_lock();
-		opp = opp_find_freq_exact(dev, 1000000000, true);
+		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, true);
 		rcu_read_unlock();
 		/* just error check */
 		if (!IS_ERR(opp))
-			ret = opp_disable(dev, 1000000000);
+			ret = dev_pm_opp_disable(dev, 1000000000);
 		else
 			goto try_something_else;
 	 }
@@ -247,7 +247,7 @@ information from the OPP structure is necessary. Once an OPP pointer is
 retrieved using the search functions, the following functions can be used by SoC
 framework to retrieve the information represented inside the OPP layer.
 
-opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+dev_pm_opp_get_voltage - Retrieve the voltage represented by the opp pointer.
 	Example: At a cpufreq transition to a different frequency, SoC
 	framework requires to set the voltage represented by the OPP using
 	the regulator framework to the Power Management chip providing the
@@ -256,15 +256,15 @@ opp_get_voltage - Retrieve the voltage represented by the opp pointer.
 	 {
 		/* do things */
 		rcu_read_lock();
-		opp = opp_find_freq_ceil(dev, &freq);
-		v = opp_get_voltage(opp);
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+		v = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 		if (v)
 			regulator_set_voltage(.., v);
 		/* do other things */
 	 }
 
-opp_get_freq - Retrieve the freq represented by the opp pointer.
+dev_pm_opp_get_freq - Retrieve the freq represented by the opp pointer.
 	Example: Lets say the SoC framework uses a couple of helper functions
 	we could pass opp pointers instead of doing additional parameters to
 	handle quiet a bit of data parameters.
@@ -273,8 +273,8 @@ opp_get_freq - Retrieve the freq represented by the opp pointer.
 		/* do things.. */
 		 max_freq = ULONG_MAX;
 		 rcu_read_lock();
-		 max_opp = opp_find_freq_floor(dev,&max_freq);
-		 requested_opp = opp_find_freq_ceil(dev,&freq);
+		 max_opp = dev_pm_opp_find_freq_floor(dev,&max_freq);
+		 requested_opp = dev_pm_opp_find_freq_ceil(dev,&freq);
 		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
 			r = soc_test_validity(max_opp, requested_opp);
 		 rcu_read_unlock();
@@ -282,25 +282,25 @@ opp_get_freq - Retrieve the freq represented by the opp pointer.
 	 }
 	 soc_test_validity(..)
 	 {
-		 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+		 if(dev_pm_opp_get_voltage(max_opp) < dev_pm_opp_get_voltage(requested_opp))
 			 return -EINVAL;
-		 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+		 if(dev_pm_opp_get_freq(max_opp) < dev_pm_opp_get_freq(requested_opp))
 			 return -EINVAL;
 		/* do things.. */
 	 }
 
-opp_get_opp_count - Retrieve the number of available opps for a device
+dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 	Example: Lets say a co-processor in the SoC needs to know the available
 	frequencies in a table, the main processor can notify as following:
 	 soc_notify_coproc_available_frequencies()
 	 {
 		/* Do things */
 		rcu_read_lock();
-		num_available = opp_get_opp_count(dev);
+		num_available = dev_pm_opp_get_opp_count(dev);
 		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
 		/* populate the table in increasing order */
 		freq = 0;
-		while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+		while (!IS_ERR(opp = dev_pm_opp_find_freq_ceil(dev, &freq))) {
 			speeds[i] = freq;
 			freq++;
 			i++;
@@ -313,7 +313,7 @@ opp_get_opp_count - Retrieve the number of available opps for a device
 
 6. Cpufreq Table Generation
 ===========================
-opp_init_cpufreq_table - cpufreq framework typically is initialized with
+dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with
 	cpufreq_frequency_table_cpuinfo which is provided with the list of
 	frequencies that are available for operation. This function provides
 	a ready to use conversion routine to translate the OPP layer's internal
@@ -326,7 +326,7 @@ opp_init_cpufreq_table - cpufreq framework typically is initialized with
 	 soc_pm_init()
 	 {
 		/* Do things */
-		r = opp_init_cpufreq_table(dev, &freq_table);
+		r = dev_pm_opp_init_cpufreq_table(dev, &freq_table);
 		if (!r)
 			cpufreq_frequency_table_cpuinfo(policy, freq_table);
 		/* Do other things */
@@ -336,7 +336,7 @@ opp_init_cpufreq_table - cpufreq framework typically is initialized with
 	addition to CONFIG_PM as power management feature is required to
 	dynamically scale voltage and frequency in a system.
 
-opp_free_cpufreq_table - Free up the table allocated by opp_init_cpufreq_table
+dev_pm_opp_free_cpufreq_table - Free up the table allocated by dev_pm_opp_init_cpufreq_table
 
 7. Data Structures
 ==================
@@ -366,8 +366,8 @@ struct opp - The internal data structure of OPP library which is used to
 	identifier for OPP in the interactions with OPP layer.
 
 	WARNING: The struct opp pointer should not be parsed or modified by the
-	users. The defaults of for an instance is populated by opp_add, but the
-	availability of the OPP can be modified by opp_enable/disable functions.
+	users. The defaults of for an instance is populated by dev_pm_opp_add, but the
+	availability of the OPP can be modified by dev_pm_opp_enable/disable functions.
 
 struct device - This is used to identify a domain to the OPP layer. The
 	nature of the device and it's implementation is left to the user of
@@ -377,19 +377,19 @@ Overall, in a simplistic view, the data structure operations is represented as
 following:
 
 Initialization / modification:
-            +-----+        /- opp_enable
-opp_add --> | opp | <-------
-  |         +-----+        \- opp_disable
+            +-----+        /- dev_pm_opp_enable
+dev_pm_opp_add --> | opp | <-------
+  |         +-----+        \- dev_pm_opp_disable
   \-------> domain_info(device)
 
 Search functions:
-             /-- opp_find_freq_ceil  ---\   +-----+
-domain_info<---- opp_find_freq_exact -----> | opp |
-             \-- opp_find_freq_floor ---/   +-----+
+             /-- dev_pm_opp_find_freq_ceil  ---\   +-----+
+domain_info<---- dev_pm_opp_find_freq_exact -----> | opp |
+             \-- dev_pm_opp_find_freq_floor ---/   +-----+
 
 Retrieval functions:
-+-----+     /- opp_get_voltage
++-----+     /- dev_pm_opp_get_voltage
 | opp | <---
-+-----+     \- opp_get_freq
++-----+     \- dev_pm_opp_get_freq
 
-domain_info <- opp_get_opp_count
+domain_info <- dev_pm_opp_get_opp_count
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 90372a21087f..d7ecc90e6bba 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -226,7 +226,7 @@ static void __init imx6q_opp_check_1p2ghz(struct device *cpu_dev)
 	val = readl_relaxed(base + OCOTP_CFG3);
 	val >>= OCOTP_CFG3_SPEED_SHIFT;
 	if ((val & 0x3) != OCOTP_CFG3_SPEED_1P2GHZ)
-		if (opp_disable(cpu_dev, 1200000000))
+		if (dev_pm_opp_disable(cpu_dev, 1200000000))
 			pr_warn("failed to disable 1.2 GHz OPP\n");
 
 put_node:
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index f26918467efc..33969e5a149f 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -522,11 +522,11 @@ static int __init beagle_opp_init(void)
 			return -ENODEV;
 		}
 		/* Enable MPU 1GHz and lower opps */
-		r = opp_enable(mpu_dev, 800000000);
+		r = dev_pm_opp_enable(mpu_dev, 800000000);
 		/* TODO: MPU 1GHz needs SR and ABB */
 
 		/* Enable IVA 800MHz and lower opps */
-		r |= opp_enable(iva_dev, 660000000);
+		r |= dev_pm_opp_enable(iva_dev, 660000000);
 		/* TODO: DSP 800MHz needs SR and ABB */
 		if (r) {
 			pr_err("%s: failed to enable higher opp %d\n",
@@ -535,8 +535,8 @@ static int __init beagle_opp_init(void)
 			 * Cleanup - disable the higher freqs - we dont care
 			 * about the results
 			 */
-			opp_disable(mpu_dev, 800000000);
-			opp_disable(iva_dev, 660000000);
+			dev_pm_opp_disable(mpu_dev, 800000000);
+			dev_pm_opp_disable(iva_dev, 660000000);
 		}
 	}
 	return 0;
diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c
index bd41d59a7cab..7b04637b13cb 100644
--- a/arch/arm/mach-omap2/opp.c
+++ b/arch/arm/mach-omap2/opp.c
@@ -81,14 +81,14 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 			dev = &oh->od->pdev->dev;
 		}
 
-		r = opp_add(dev, opp_def->freq, opp_def->u_volt);
+		r = dev_pm_opp_add(dev, opp_def->freq, opp_def->u_volt);
 		if (r) {
 			dev_err(dev, "%s: add OPP %ld failed for %s [%d] result=%d\n",
 				__func__, opp_def->freq,
 				opp_def->hwmod_name, i, r);
 		} else {
 			if (!opp_def->default_available)
-				r = opp_disable(dev, opp_def->freq);
+				r = dev_pm_opp_disable(dev, opp_def->freq);
 			if (r)
 				dev_err(dev, "%s: disable %ld failed for %s [%d] result=%d\n",
 					__func__, opp_def->freq,
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index e742118fcfd2..937744c3679d 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -172,7 +172,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
 	clk_put(clk);
 
 	rcu_read_lock();
-	opp = opp_find_freq_ceil(dev, &freq);
+	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 	if (IS_ERR(opp)) {
 		rcu_read_unlock();
 		pr_err("%s: unable to find boot up OPP for vdd_%s\n",
@@ -180,7 +180,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
 		goto exit;
 	}
 
-	bootup_volt = opp_get_voltage(opp);
+	bootup_volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 	if (!bootup_volt) {
 		pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n",
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index ef89897c6043..00c6a449cdeb 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -136,7 +136,7 @@ static struct device_opp *find_device_opp(struct device *dev)
 }
 
 /**
- * opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an available opp
  * @opp:	opp for which voltage has to be returned for
  *
  * Return voltage in micro volt corresponding to the opp, else
@@ -150,7 +150,7 @@ static struct device_opp *find_device_opp(struct device *dev)
  * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
  * pointer.
  */
-unsigned long opp_get_voltage(struct opp *opp)
+unsigned long dev_pm_opp_get_voltage(struct opp *opp)
 {
 	struct opp *tmp_opp;
 	unsigned long v = 0;
@@ -163,10 +163,10 @@ unsigned long opp_get_voltage(struct opp *opp)
 
 	return v;
 }
-EXPORT_SYMBOL_GPL(opp_get_voltage);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
 /**
- * opp_get_freq() - Gets the frequency corresponding to an available opp
+ * dev_pm_opp_get_freq() - Gets the frequency corresponding to an available opp
  * @opp:	opp for which frequency has to be returned for
  *
  * Return frequency in hertz corresponding to the opp, else
@@ -180,7 +180,7 @@ EXPORT_SYMBOL_GPL(opp_get_voltage);
  * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
  * pointer.
  */
-unsigned long opp_get_freq(struct opp *opp)
+unsigned long dev_pm_opp_get_freq(struct opp *opp)
 {
 	struct opp *tmp_opp;
 	unsigned long f = 0;
@@ -193,10 +193,10 @@ unsigned long opp_get_freq(struct opp *opp)
 
 	return f;
 }
-EXPORT_SYMBOL_GPL(opp_get_freq);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
 /**
- * opp_get_opp_count() - Get number of opps available in the opp list
+ * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
  *
  * This function returns the number of available opps if there are any,
@@ -206,7 +206,7 @@ EXPORT_SYMBOL_GPL(opp_get_freq);
  * internally references two RCU protected structures: device_opp and opp which
  * are safe as long as we are under a common RCU locked section.
  */
-int opp_get_opp_count(struct device *dev)
+int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	struct device_opp *dev_opp;
 	struct opp *temp_opp;
@@ -226,10 +226,10 @@ int opp_get_opp_count(struct device *dev)
 
 	return count;
 }
-EXPORT_SYMBOL_GPL(opp_get_opp_count);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
 
 /**
- * opp_find_freq_exact() - search for an exact frequency
+ * dev_pm_opp_find_freq_exact() - search for an exact frequency
  * @dev:		device for which we do this operation
  * @freq:		frequency to search for
  * @available:		true/false - match for available opp
@@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(opp_get_opp_count);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+struct opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq,
 				bool available)
 {
 	struct device_opp *dev_opp;
@@ -277,10 +277,10 @@ struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
 
 	return opp;
 }
-EXPORT_SYMBOL_GPL(opp_find_freq_exact);
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 
 /**
- * opp_find_freq_ceil() - Search for an rounded ceil freq
+ * dev_pm_opp_find_freq_ceil() - Search for an rounded ceil freq
  * @dev:	device for which we do this operation
  * @freq:	Start frequency
  *
@@ -300,7 +300,7 @@ EXPORT_SYMBOL_GPL(opp_find_freq_exact);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+struct opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq)
 {
 	struct device_opp *dev_opp;
 	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
@@ -324,10 +324,10 @@ struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq)
 
 	return opp;
 }
-EXPORT_SYMBOL_GPL(opp_find_freq_ceil);
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
 /**
- * opp_find_freq_floor() - Search for a rounded floor freq
+ * dev_pm_opp_find_freq_floor() - Search for a rounded floor freq
  * @dev:	device for which we do this operation
  * @freq:	Start frequency
  *
@@ -347,7 +347,7 @@ EXPORT_SYMBOL_GPL(opp_find_freq_ceil);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
+struct opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq)
 {
 	struct device_opp *dev_opp;
 	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
@@ -375,17 +375,17 @@ struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq)
 
 	return opp;
 }
-EXPORT_SYMBOL_GPL(opp_find_freq_floor);
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
 /**
- * opp_add()  - Add an OPP table from a table definitions
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
  *
  * This function adds an opp definition to the opp list and returns status.
  * The opp is made available by default and it can be controlled using
- * opp_enable/disable functions.
+ * dev_pm_opp_enable/disable functions.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -393,7 +393,7 @@ EXPORT_SYMBOL_GPL(opp_find_freq_floor);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
 	struct device_opp *dev_opp = NULL;
 	struct opp *opp, *new_opp;
@@ -460,7 +460,7 @@ int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 	srcu_notifier_call_chain(&dev_opp->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(opp_add);
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * opp_set_availability() - helper to set the availability of an opp
@@ -552,13 +552,13 @@ unlock:
 }
 
 /**
- * opp_enable() - Enable a specific OPP
+ * dev_pm_opp_enable() - Enable a specific OPP
  * @dev:	device for which we do this operation
  * @freq:	OPP frequency to enable
  *
  * Enables a provided opp. If the operation is valid, this returns 0, else the
  * corresponding error value. It is meant to be used for users an OPP available
- * after being temporarily made unavailable with opp_disable.
+ * after being temporarily made unavailable with dev_pm_opp_disable.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU and mutex locks to keep the
@@ -566,21 +566,21 @@ unlock:
  * this function is *NOT* called under RCU protection or in contexts where
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  */
-int opp_enable(struct device *dev, unsigned long freq)
+int dev_pm_opp_enable(struct device *dev, unsigned long freq)
 {
 	return opp_set_availability(dev, freq, true);
 }
-EXPORT_SYMBOL_GPL(opp_enable);
+EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
 
 /**
- * opp_disable() - Disable a specific OPP
+ * dev_pm_opp_disable() - Disable a specific OPP
  * @dev:	device for which we do this operation
  * @freq:	OPP frequency to disable
  *
  * Disables a provided opp. If the operation is valid, this returns
  * 0, else the corresponding error value. It is meant to be a temporary
  * control by users to make this OPP not available until the circumstances are
- * right to make it available again (with a call to opp_enable).
+ * right to make it available again (with a call to dev_pm_opp_enable).
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly uses RCU and mutex locks to keep the
@@ -588,15 +588,15 @@ EXPORT_SYMBOL_GPL(opp_enable);
  * this function is *NOT* called under RCU protection or in contexts where
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  */
-int opp_disable(struct device *dev, unsigned long freq)
+int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 {
 	return opp_set_availability(dev, freq, false);
 }
-EXPORT_SYMBOL_GPL(opp_disable);
+EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
 #ifdef CONFIG_CPU_FREQ
 /**
- * opp_init_cpufreq_table() - create a cpufreq table for a device
+ * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
  * @dev:	device for which we do this operation
  * @table:	Cpufreq table returned back to caller
  *
@@ -619,7 +619,7 @@ EXPORT_SYMBOL_GPL(opp_disable);
  * Callers should ensure that this function is *NOT* called under RCU protection
  * or in contexts where mutex locking cannot be used.
  */
-int opp_init_cpufreq_table(struct device *dev,
+int dev_pm_opp_init_cpufreq_table(struct device *dev,
 			    struct cpufreq_frequency_table **table)
 {
 	struct device_opp *dev_opp;
@@ -639,7 +639,7 @@ int opp_init_cpufreq_table(struct device *dev,
 	}
 
 	freq_table = kzalloc(sizeof(struct cpufreq_frequency_table) *
-			     (opp_get_opp_count(dev) + 1), GFP_KERNEL);
+			     (dev_pm_opp_get_opp_count(dev) + 1), GFP_KERNEL);
 	if (!freq_table) {
 		mutex_unlock(&dev_opp_list_lock);
 		dev_warn(dev, "%s: Unable to allocate frequency table\n",
@@ -663,16 +663,16 @@ int opp_init_cpufreq_table(struct device *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(opp_init_cpufreq_table);
+EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
 
 /**
- * opp_free_cpufreq_table() - free the cpufreq table
+ * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
  * @dev:	device for which we do this operation
  * @table:	table to free
  *
- * Free up the table allocated by opp_init_cpufreq_table
+ * Free up the table allocated by dev_pm_opp_init_cpufreq_table
  */
-void opp_free_cpufreq_table(struct device *dev,
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
 				struct cpufreq_frequency_table **table)
 {
 	if (!table)
@@ -681,14 +681,14 @@ void opp_free_cpufreq_table(struct device *dev,
 	kfree(*table);
 	*table = NULL;
 }
-EXPORT_SYMBOL_GPL(opp_free_cpufreq_table);
+EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
 #endif		/* CONFIG_CPU_FREQ */
 
 /**
- * opp_get_notifier() - find notifier_head of the device with opp
+ * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
  * @dev:	device pointer used to lookup device OPPs.
  */
-struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
 {
 	struct device_opp *dev_opp = find_device_opp(dev);
 
@@ -732,7 +732,7 @@ int of_init_opp_table(struct device *dev)
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (opp_add(dev, freq, volt)) {
+		if (dev_pm_opp_add(dev, freq, volt)) {
 			dev_warn(dev, "%s: Failed to add OPP %ld\n",
 				 __func__, freq);
 			continue;
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 3549f0784af1..9e82a9d5df77 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -98,7 +98,7 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 
 	if (!atomic_dec_return(&cluster_usage[cluster])) {
 		clk_put(clk[cluster]);
-		opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+		dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
 		dev_dbg(cpu_dev, "%s: cluster: %d\n", __func__, cluster);
 	}
 }
@@ -119,7 +119,7 @@ static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		goto atomic_dec;
 	}
 
-	ret = opp_init_cpufreq_table(cpu_dev, &freq_table[cluster]);
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table[cluster]);
 	if (ret) {
 		dev_err(cpu_dev, "%s: failed to init cpufreq table, cpu: %d, err: %d\n",
 				__func__, cpu_dev->id, ret);
@@ -138,7 +138,7 @@ static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
 	dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d, cluster: %d\n",
 			__func__, cpu_dev->id, cluster);
 	ret = PTR_ERR(clk[cluster]);
-	opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table[cluster]);
 
 atomic_dec:
 	atomic_dec(&cluster_usage[cluster]);
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index c522a95c0e16..af951a9cea78 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -72,7 +72,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 
 	if (!IS_ERR(cpu_reg)) {
 		rcu_read_lock();
-		opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
+		opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz);
 		if (IS_ERR(opp)) {
 			rcu_read_unlock();
 			pr_err("failed to find OPP for %ld\n", freq_Hz);
@@ -80,7 +80,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 			ret = PTR_ERR(opp);
 			goto post_notify;
 		}
-		volt = opp_get_voltage(opp);
+		volt = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 		tol = volt * voltage_tolerance / 100;
 		volt_old = regulator_get_voltage(cpu_reg);
@@ -218,7 +218,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		goto out_put_node;
 	}
 
-	ret = opp_init_cpufreq_table(cpu_dev, &freq_table);
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		pr_err("failed to init cpufreq table: %d\n", ret);
 		goto out_put_node;
@@ -242,12 +242,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
 			;
 		rcu_read_lock();
-		opp = opp_find_freq_exact(cpu_dev,
+		opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				freq_table[0].frequency * 1000, true);
-		min_uV = opp_get_voltage(opp);
-		opp = opp_find_freq_exact(cpu_dev,
+		min_uV = dev_pm_opp_get_voltage(opp);
+		opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				freq_table[i-1].frequency * 1000, true);
-		max_uV = opp_get_voltage(opp);
+		max_uV = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
 		if (ret > 0)
@@ -264,7 +264,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 
 out_free_table:
-	opp_free_cpufreq_table(cpu_dev, &freq_table);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_put_node:
 	of_node_put(np);
 	return ret;
@@ -273,7 +273,7 @@ out_put_node:
 static int cpu0_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&cpu0_cpufreq_driver);
-	opp_free_cpufreq_table(cpu_dev, &freq_table);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index be5380ecdcd4..444eca74d3c2 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -123,7 +123,7 @@ static int init_div_table(void)
 	rcu_read_lock();
 	for (i = 0; freq_tbl[i].frequency != CPUFREQ_TABLE_END; i++) {
 
-		opp = opp_find_freq_exact(dvfs_info->dev,
+		opp = dev_pm_opp_find_freq_exact(dvfs_info->dev,
 					freq_tbl[i].frequency * 1000, true);
 		if (IS_ERR(opp)) {
 			rcu_read_unlock();
@@ -142,7 +142,7 @@ static int init_div_table(void)
 					<< P0_7_CSCLKDEV_SHIFT;
 
 		/* Calculate EMA */
-		volt_id = opp_get_voltage(opp);
+		volt_id = dev_pm_opp_get_voltage(opp);
 		volt_id = (MAX_VOLTAGE - volt_id) / VOLTAGE_STEP;
 		if (volt_id < PMIC_HIGH_VOLT) {
 			ema_div = (CPUEMA_HIGH << P0_7_CPUEMA_SHIFT) |
@@ -399,13 +399,14 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 		goto err_put_node;
 	}
 
-	ret = opp_init_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
+	ret = dev_pm_opp_init_cpufreq_table(dvfs_info->dev,
+					    &dvfs_info->freq_table);
 	if (ret) {
 		dev_err(dvfs_info->dev,
 			"failed to init cpufreq table: %d\n", ret);
 		goto err_put_node;
 	}
-	dvfs_info->freq_count = opp_get_opp_count(dvfs_info->dev);
+	dvfs_info->freq_count = dev_pm_opp_get_opp_count(dvfs_info->dev);
 	exynos_sort_descend_freq_table();
 
 	if (of_property_read_u32(np, "clock-latency", &dvfs_info->latency))
@@ -454,7 +455,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 
 err_free_table:
-	opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
+	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 err_put_node:
 	of_node_put(np);
 	dev_err(&pdev->dev, "%s: failed initialization\n", __func__);
@@ -464,7 +465,7 @@ err_put_node:
 static int exynos_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&exynos_driver);
-	opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
+	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index c3fd2a101ca0..b360549e7715 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -70,14 +70,14 @@ static int imx6q_set_target(struct cpufreq_policy *policy,
 		return 0;
 
 	rcu_read_lock();
-	opp = opp_find_freq_ceil(cpu_dev, &freq_hz);
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
 		rcu_read_unlock();
 		dev_err(cpu_dev, "failed to find OPP for %ld\n", freq_hz);
 		return PTR_ERR(opp);
 	}
 
-	volt = opp_get_voltage(opp);
+	volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 	volt_old = regulator_get_voltage(arm_reg);
 
@@ -237,14 +237,14 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	/* We expect an OPP table supplied by platform */
-	num = opp_get_opp_count(cpu_dev);
+	num = dev_pm_opp_get_opp_count(cpu_dev);
 	if (num < 0) {
 		ret = num;
 		dev_err(cpu_dev, "no OPP table is found: %d\n", ret);
 		goto put_node;
 	}
 
-	ret = opp_init_cpufreq_table(cpu_dev, &freq_table);
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
 		goto put_node;
@@ -259,12 +259,12 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	 * same order.
 	 */
 	rcu_read_lock();
-	opp = opp_find_freq_exact(cpu_dev,
+	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[0].frequency * 1000, true);
-	min_volt = opp_get_voltage(opp);
-	opp = opp_find_freq_exact(cpu_dev,
+	min_volt = dev_pm_opp_get_voltage(opp);
+	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[--num].frequency * 1000, true);
-	max_volt = opp_get_voltage(opp);
+	max_volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 	ret = regulator_set_voltage_time(arm_reg, min_volt, max_volt);
 	if (ret > 0)
@@ -292,7 +292,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 
 free_freq_table:
-	opp_free_cpufreq_table(cpu_dev, &freq_table);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 put_node:
 	of_node_put(np);
 	return ret;
@@ -301,7 +301,7 @@ put_node:
 static int imx6q_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
-	opp_free_cpufreq_table(cpu_dev, &freq_table);
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index f31fcfcad514..c5e31d296607 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -105,14 +105,14 @@ static int omap_target(struct cpufreq_policy *policy,
 
 	if (mpu_reg) {
 		rcu_read_lock();
-		opp = opp_find_freq_ceil(mpu_dev, &freq);
+		opp = dev_pm_opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
 			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, freqs.new);
 			return -EINVAL;
 		}
-		volt = opp_get_voltage(opp);
+		volt = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
@@ -162,7 +162,7 @@ done:
 static inline void freq_table_free(void)
 {
 	if (atomic_dec_and_test(&freq_table_users))
-		opp_free_cpufreq_table(mpu_dev, &freq_table);
+		dev_pm_opp_free_cpufreq_table(mpu_dev, &freq_table);
 }
 
 static int omap_cpu_init(struct cpufreq_policy *policy)
@@ -181,7 +181,7 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 	policy->cur = omap_getspeed(policy->cpu);
 
 	if (!freq_table)
-		result = opp_init_cpufreq_table(mpu_dev, &freq_table);
+		result = dev_pm_opp_init_cpufreq_table(mpu_dev, &freq_table);
 
 	if (result) {
 		dev_err(mpu_dev, "%s: cpu%d: failed creating freq table[%d]\n",
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index c99c00d35d34..f798edcb910d 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -908,7 +908,7 @@ static ssize_t available_frequencies_show(struct device *d,
 
 	rcu_read_lock();
 	do {
-		opp = opp_find_freq_ceil(dev, &freq);
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		if (IS_ERR(opp))
 			break;
 
@@ -1036,18 +1036,18 @@ struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq,
 
 	if (flags & DEVFREQ_FLAG_LEAST_UPPER_BOUND) {
 		/* The freq is an upper bound. opp should be lower */
-		opp = opp_find_freq_floor(dev, freq);
+		opp = dev_pm_opp_find_freq_floor(dev, freq);
 
 		/* If not available, use the closest opp */
 		if (opp == ERR_PTR(-ERANGE))
-			opp = opp_find_freq_ceil(dev, freq);
+			opp = dev_pm_opp_find_freq_ceil(dev, freq);
 	} else {
 		/* The freq is an lower bound. opp should be higher */
-		opp = opp_find_freq_ceil(dev, freq);
+		opp = dev_pm_opp_find_freq_ceil(dev, freq);
 
 		/* If not available, use the closest opp */
 		if (opp == ERR_PTR(-ERANGE))
-			opp = opp_find_freq_floor(dev, freq);
+			opp = dev_pm_opp_find_freq_floor(dev, freq);
 	}
 
 	return opp;
@@ -1066,7 +1066,7 @@ int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
 	int ret = 0;
 
 	rcu_read_lock();
-	nh = opp_get_notifier(dev);
+	nh = dev_pm_opp_get_notifier(dev);
 	if (IS_ERR(nh))
 		ret = PTR_ERR(nh);
 	rcu_read_unlock();
@@ -1092,7 +1092,7 @@ int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
 	int ret = 0;
 
 	rcu_read_lock();
-	nh = opp_get_notifier(dev);
+	nh = dev_pm_opp_get_notifier(dev);
 	if (IS_ERR(nh))
 		ret = PTR_ERR(nh);
 	rcu_read_unlock();
diff --git a/drivers/devfreq/exynos/exynos4_bus.c b/drivers/devfreq/exynos/exynos4_bus.c
index c5f86d8caca3..33c0e05a5ff1 100644
--- a/drivers/devfreq/exynos/exynos4_bus.c
+++ b/drivers/devfreq/exynos/exynos4_bus.c
@@ -650,8 +650,8 @@ static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
 		rcu_read_unlock();
 		return PTR_ERR(opp);
 	}
-	new_oppinfo.rate = opp_get_freq(opp);
-	new_oppinfo.volt = opp_get_voltage(opp);
+	new_oppinfo.rate = dev_pm_opp_get_freq(opp);
+	new_oppinfo.volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 	freq = new_oppinfo.rate;
 
@@ -873,7 +873,7 @@ static int exynos4210_init_tables(struct busfreq_data *data)
 		exynos4210_busclk_table[i].volt = exynos4210_asv_volt[mgrp][i];
 
 	for (i = LV_0; i < EX4210_LV_NUM; i++) {
-		err = opp_add(data->dev, exynos4210_busclk_table[i].clk,
+		err = dev_pm_opp_add(data->dev, exynos4210_busclk_table[i].clk,
 			      exynos4210_busclk_table[i].volt);
 		if (err) {
 			dev_err(data->dev, "Cannot add opp entries.\n");
@@ -940,7 +940,7 @@ static int exynos4x12_init_tables(struct busfreq_data *data)
 	}
 
 	for (i = 0; i < EX4x12_LV_NUM; i++) {
-		ret = opp_add(data->dev, exynos4x12_mifclk_table[i].clk,
+		ret = dev_pm_opp_add(data->dev, exynos4x12_mifclk_table[i].clk,
 			      exynos4x12_mifclk_table[i].volt);
 		if (ret) {
 			dev_err(data->dev, "Fail to add opp entries.\n");
@@ -969,7 +969,7 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
 		data->disabled = true;
 
 		rcu_read_lock();
-		opp = opp_find_freq_floor(data->dev, &maxfreq);
+		opp = dev_pm_opp_find_freq_floor(data->dev, &maxfreq);
 		if (IS_ERR(opp)) {
 			rcu_read_unlock();
 			dev_err(data->dev, "%s: unable to find a min freq\n",
@@ -977,8 +977,8 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
 			mutex_unlock(&data->lock);
 			return PTR_ERR(opp);
 		}
-		new_oppinfo.rate = opp_get_freq(opp);
-		new_oppinfo.volt = opp_get_voltage(opp);
+		new_oppinfo.rate = dev_pm_opp_get_freq(opp);
+		new_oppinfo.volt = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 
 		err = exynos4_bus_setvolt(data, &new_oppinfo,
@@ -1065,15 +1065,16 @@ static int exynos4_busfreq_probe(struct platform_device *pdev)
 	}
 
 	rcu_read_lock();
-	opp = opp_find_freq_floor(dev, &exynos4_devfreq_profile.initial_freq);
+	opp = dev_pm_opp_find_freq_floor(dev,
+					 &exynos4_devfreq_profile.initial_freq);
 	if (IS_ERR(opp)) {
 		rcu_read_unlock();
 		dev_err(dev, "Invalid initial frequency %lu kHz.\n",
 			exynos4_devfreq_profile.initial_freq);
 		return PTR_ERR(opp);
 	}
-	data->curr_oppinfo.rate = opp_get_freq(opp);
-	data->curr_oppinfo.volt = opp_get_voltage(opp);
+	data->curr_oppinfo.rate = dev_pm_opp_get_freq(opp);
+	data->curr_oppinfo.volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 
 	platform_set_drvdata(pdev, data);
diff --git a/drivers/devfreq/exynos/exynos5_bus.c b/drivers/devfreq/exynos/exynos5_bus.c
index 574b16b59be5..b0e45925505b 100644
--- a/drivers/devfreq/exynos/exynos5_bus.c
+++ b/drivers/devfreq/exynos/exynos5_bus.c
@@ -144,8 +144,8 @@ static int exynos5_busfreq_int_target(struct device *dev, unsigned long *_freq,
 		return PTR_ERR(opp);
 	}
 
-	freq = opp_get_freq(opp);
-	volt = opp_get_voltage(opp);
+	freq = dev_pm_opp_get_freq(opp);
+	volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 
 	old_freq = data->curr_freq;
@@ -246,7 +246,7 @@ static int exynos5250_init_int_tables(struct busfreq_data_int *data)
 	int i, err = 0;
 
 	for (i = LV_0; i < _LV_END; i++) {
-		err = opp_add(data->dev, exynos5_int_opp_table[i].clk,
+		err = dev_pm_opp_add(data->dev, exynos5_int_opp_table[i].clk,
 				exynos5_int_opp_table[i].volt);
 		if (err) {
 			dev_err(data->dev, "Cannot add opp entries.\n");
@@ -276,14 +276,14 @@ static int exynos5_busfreq_int_pm_notifier_event(struct notifier_block *this,
 		data->disabled = true;
 
 		rcu_read_lock();
-		opp = opp_find_freq_floor(data->dev, &maxfreq);
+		opp = dev_pm_opp_find_freq_floor(data->dev, &maxfreq);
 		if (IS_ERR(opp)) {
 			rcu_read_unlock();
 			err = PTR_ERR(opp);
 			goto unlock;
 		}
-		freq = opp_get_freq(opp);
-		volt = opp_get_voltage(opp);
+		freq = dev_pm_opp_get_freq(opp);
+		volt = dev_pm_opp_get_voltage(opp);
 		rcu_read_unlock();
 
 		err = exynos5_int_setvolt(data, volt);
@@ -368,7 +368,7 @@ static int exynos5_busfreq_int_probe(struct platform_device *pdev)
 	}
 
 	rcu_read_lock();
-	opp = opp_find_freq_floor(dev,
+	opp = dev_pm_opp_find_freq_floor(dev,
 			&exynos5_devfreq_int_profile.initial_freq);
 	if (IS_ERR(opp)) {
 		rcu_read_unlock();
@@ -377,8 +377,8 @@ static int exynos5_busfreq_int_probe(struct platform_device *pdev)
 		err = PTR_ERR(opp);
 		goto err_opp_add;
 	}
-	initial_freq = opp_get_freq(opp);
-	initial_volt = opp_get_voltage(opp);
+	initial_freq = dev_pm_opp_get_freq(opp);
+	initial_volt = dev_pm_opp_get_voltage(opp);
 	rcu_read_unlock();
 	data->curr_freq = initial_freq;
 
diff --git a/include/linux/opp.h b/include/linux/opp.h
index 3aca2b8def33..2066ae5880c6 100644
--- a/include/linux/opp.h
+++ b/include/linux/opp.h
@@ -27,77 +27,79 @@ enum opp_event {
 
 #if defined(CONFIG_PM_OPP)
 
-unsigned long opp_get_voltage(struct opp *opp);
+unsigned long dev_pm_opp_get_voltage(struct opp *opp);
 
-unsigned long opp_get_freq(struct opp *opp);
+unsigned long dev_pm_opp_get_freq(struct opp *opp);
 
-int opp_get_opp_count(struct device *dev);
+int dev_pm_opp_get_opp_count(struct device *dev);
 
-struct opp *opp_find_freq_exact(struct device *dev, unsigned long freq,
+struct opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq,
 				bool available);
 
-struct opp *opp_find_freq_floor(struct device *dev, unsigned long *freq);
+struct opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq);
 
-struct opp *opp_find_freq_ceil(struct device *dev, unsigned long *freq);
+struct opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq);
 
-int opp_add(struct device *dev, unsigned long freq, unsigned long u_volt);
+int dev_pm_opp_add(struct device *dev, unsigned long freq,
+		   unsigned long u_volt);
 
-int opp_enable(struct device *dev, unsigned long freq);
+int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
-int opp_disable(struct device *dev, unsigned long freq);
+int dev_pm_opp_disable(struct device *dev, unsigned long freq);
 
-struct srcu_notifier_head *opp_get_notifier(struct device *dev);
+struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
 #else
-static inline unsigned long opp_get_voltage(struct opp *opp)
+static inline unsigned long dev_pm_opp_get_voltage(struct opp *opp)
 {
 	return 0;
 }
 
-static inline unsigned long opp_get_freq(struct opp *opp)
+static inline unsigned long dev_pm_opp_get_freq(struct opp *opp)
 {
 	return 0;
 }
 
-static inline int opp_get_opp_count(struct device *dev)
+static inline int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	return 0;
 }
 
-static inline struct opp *opp_find_freq_exact(struct device *dev,
+static inline struct opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					unsigned long freq, bool available)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct opp *opp_find_freq_floor(struct device *dev,
+static inline struct opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					unsigned long *freq)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct opp *opp_find_freq_ceil(struct device *dev,
+static inline struct opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					unsigned long *freq)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline int opp_add(struct device *dev, unsigned long freq,
+static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
 					unsigned long u_volt)
 {
 	return -EINVAL;
 }
 
-static inline int opp_enable(struct device *dev, unsigned long freq)
+static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
 {
 	return 0;
 }
 
-static inline int opp_disable(struct device *dev, unsigned long freq)
+static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 {
 	return 0;
 }
 
-static inline struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
+							struct device *dev)
 {
 	return ERR_PTR(-EINVAL);
 }
@@ -113,19 +115,19 @@ static inline int of_init_opp_table(struct device *dev)
 #endif
 
 #if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
-int opp_init_cpufreq_table(struct device *dev,
+int dev_pm_opp_init_cpufreq_table(struct device *dev,
 			    struct cpufreq_frequency_table **table);
-void opp_free_cpufreq_table(struct device *dev,
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
 				struct cpufreq_frequency_table **table);
 #else
-static inline int opp_init_cpufreq_table(struct device *dev,
+static inline int dev_pm_opp_init_cpufreq_table(struct device *dev,
 			    struct cpufreq_frequency_table **table)
 {
 	return -EINVAL;
 }
 
 static inline
-void opp_free_cpufreq_table(struct device *dev,
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
 				struct cpufreq_frequency_table **table)
 {
 }
-- 
cgit 


From 47d43ba73eb98d8ba731208735c899129d9849e1 Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Thu, 19 Sep 2013 16:03:51 -0500
Subject: PM / OPP: rename data structures to dev_pm equivalents

Since Operating Performance Points (OPP) data structures are specific
to device specific power management, be specific and rename opp_* data
structures in OPP library with dev_pm_opp_* equivalent.

Affected structures are:
 struct opp
 enum opp_event

Minor checkpatch warning resulting of this change was fixed as well.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/opp.txt          |  4 ++--
 arch/arm/mach-omap2/pm.c             |  2 +-
 drivers/base/power/opp.c             | 41 +++++++++++++++++++-----------------
 drivers/cpufreq/cpufreq-cpu0.c       |  4 ++--
 drivers/cpufreq/exynos5440-cpufreq.c |  2 +-
 drivers/cpufreq/imx6q-cpufreq.c      |  4 ++--
 drivers/cpufreq/omap-cpufreq.c       |  2 +-
 drivers/devfreq/devfreq.c            |  9 ++++----
 drivers/devfreq/exynos/exynos4_bus.c |  6 +++---
 drivers/devfreq/exynos/exynos5_bus.c |  6 +++---
 include/linux/devfreq.h              |  4 ++--
 include/linux/opp.h                  | 29 +++++++++++++------------
 12 files changed, 60 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index 185367b1848f..7f67e3d2c530 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -358,14 +358,14 @@ accessed by various functions as described above. However, the structures
 representing the actual OPPs and domains are internal to the OPP library itself
 to allow for suitable abstraction reusable across systems.
 
-struct opp - The internal data structure of OPP library which is used to
+struct dev_pm_opp - The internal data structure of OPP library which is used to
 	represent an OPP. In addition to the freq, voltage, availability
 	information, it also contains internal book keeping information required
 	for the OPP library to operate on.  Pointer to this structure is
 	provided back to the users such as SoC framework to be used as a
 	identifier for OPP in the interactions with OPP layer.
 
-	WARNING: The struct opp pointer should not be parsed or modified by the
+	WARNING: The struct dev_pm_opp pointer should not be parsed or modified by the
 	users. The defaults of for an instance is populated by dev_pm_opp_add, but the
 	availability of the OPP can be modified by dev_pm_opp_enable/disable functions.
 
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 937744c3679d..92901bd41490 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -131,7 +131,7 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
 {
 	struct voltagedomain *voltdm;
 	struct clk *clk;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long freq, bootup_volt;
 	struct device *dev;
 
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 00c6a449cdeb..693e14a24914 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -42,7 +42,7 @@
  */
 
 /**
- * struct opp - Generic OPP description structure
+ * struct dev_pm_opp - Generic OPP description structure
  * @node:	opp list node. The nodes are maintained throughout the lifetime
  *		of boot. It is expected only an optimal set of OPPs are
  *		added to the library by the SoC framework.
@@ -59,7 +59,7 @@
  *
  * This structure stores the OPP information for a given device.
  */
-struct opp {
+struct dev_pm_opp {
 	struct list_head node;
 
 	bool available;
@@ -150,9 +150,9 @@ static struct device_opp *find_device_opp(struct device *dev)
  * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
  * pointer.
  */
-unsigned long dev_pm_opp_get_voltage(struct opp *opp)
+unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
-	struct opp *tmp_opp;
+	struct dev_pm_opp *tmp_opp;
 	unsigned long v = 0;
 
 	tmp_opp = rcu_dereference(opp);
@@ -180,9 +180,9 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
  * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
  * pointer.
  */
-unsigned long dev_pm_opp_get_freq(struct opp *opp)
+unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
-	struct opp *tmp_opp;
+	struct dev_pm_opp *tmp_opp;
 	unsigned long f = 0;
 
 	tmp_opp = rcu_dereference(opp);
@@ -209,7 +209,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	struct device_opp *dev_opp;
-	struct opp *temp_opp;
+	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
 	dev_opp = find_device_opp(dev);
@@ -254,11 +254,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq,
-				bool available)
+struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					      unsigned long freq,
+					      bool available)
 {
 	struct device_opp *dev_opp;
-	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	dev_opp = find_device_opp(dev);
 	if (IS_ERR(dev_opp)) {
@@ -300,10 +301,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq)
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+					     unsigned long *freq)
 {
 	struct device_opp *dev_opp;
-	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
@@ -347,10 +349,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq)
+struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
+					      unsigned long *freq)
 {
 	struct device_opp *dev_opp;
-	struct opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
@@ -396,11 +399,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
 	struct device_opp *dev_opp = NULL;
-	struct opp *opp, *new_opp;
+	struct dev_pm_opp *opp, *new_opp;
 	struct list_head *head;
 
 	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(struct opp), GFP_KERNEL);
+	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
 	if (!new_opp) {
 		dev_warn(dev, "%s: Unable to create new OPP node\n", __func__);
 		return -ENOMEM;
@@ -485,11 +488,11 @@ static int opp_set_availability(struct device *dev, unsigned long freq,
 		bool availability_req)
 {
 	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
-	struct opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
 	int r = 0;
 
 	/* keep the node allocated */
-	new_opp = kmalloc(sizeof(struct opp), GFP_KERNEL);
+	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
 	if (!new_opp) {
 		dev_warn(dev, "%s: Unable to create OPP\n", __func__);
 		return -ENOMEM;
@@ -623,7 +626,7 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 			    struct cpufreq_frequency_table **table)
 {
 	struct device_opp *dev_opp;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	struct cpufreq_frequency_table *freq_table;
 	int i = 0;
 
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index af951a9cea78..d73107894fee 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -44,7 +44,7 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 			   unsigned int target_freq, unsigned int relation)
 {
 	struct cpufreq_freqs freqs;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long volt = 0, volt_old = 0, tol = 0;
 	long freq_Hz, freq_exact;
 	unsigned int index;
@@ -230,7 +230,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
-		struct opp *opp;
+		struct dev_pm_opp *opp;
 		unsigned long min_uV, max_uV;
 		int i;
 
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 444eca74d3c2..c8b3d3950f9e 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -118,7 +118,7 @@ static int init_div_table(void)
 	struct cpufreq_frequency_table *freq_tbl = dvfs_info->freq_table;
 	unsigned int tmp, clk_div, ema_div, freq, volt_id;
 	int i = 0;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 
 	rcu_read_lock();
 	for (i = 0; freq_tbl[i].frequency != CPUFREQ_TABLE_END; i++) {
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index b360549e7715..84e993dfb305 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -49,7 +49,7 @@ static int imx6q_set_target(struct cpufreq_policy *policy,
 			    unsigned int target_freq, unsigned int relation)
 {
 	struct cpufreq_freqs freqs;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long freq_hz, volt, volt_old;
 	unsigned int index;
 	int ret;
@@ -199,7 +199,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
 static int imx6q_cpufreq_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long min_volt, max_volt;
 	int num, ret;
 
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index c5e31d296607..f057d423020c 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -65,7 +65,7 @@ static int omap_target(struct cpufreq_policy *policy,
 	unsigned int i;
 	int r, ret = 0;
 	struct cpufreq_freqs freqs;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long freq, volt = 0, volt_old = 0, tol = 0;
 
 	if (!freq_table) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index f798edcb910d..03530a0a8042 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -902,7 +902,7 @@ static ssize_t available_frequencies_show(struct device *d,
 {
 	struct devfreq *df = to_devfreq(d);
 	struct device *dev = df->dev.parent;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	ssize_t count = 0;
 	unsigned long freq = 0;
 
@@ -1029,10 +1029,11 @@ module_exit(devfreq_exit);
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
-struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq,
-				    u32 flags)
+struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
+					   unsigned long *freq,
+					   u32 flags)
 {
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 
 	if (flags & DEVFREQ_FLAG_LEAST_UPPER_BOUND) {
 		/* The freq is an upper bound. opp should be lower */
diff --git a/drivers/devfreq/exynos/exynos4_bus.c b/drivers/devfreq/exynos/exynos4_bus.c
index 33c0e05a5ff1..891becd46513 100644
--- a/drivers/devfreq/exynos/exynos4_bus.c
+++ b/drivers/devfreq/exynos/exynos4_bus.c
@@ -639,7 +639,7 @@ static int exynos4_bus_target(struct device *dev, unsigned long *_freq,
 	struct platform_device *pdev = container_of(dev, struct platform_device,
 						    dev);
 	struct busfreq_data *data = platform_get_drvdata(pdev);
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long freq;
 	unsigned long old_freq = data->curr_oppinfo.rate;
 	struct busfreq_opp_info	new_oppinfo;
@@ -956,7 +956,7 @@ static int exynos4_busfreq_pm_notifier_event(struct notifier_block *this,
 {
 	struct busfreq_data *data = container_of(this, struct busfreq_data,
 						 pm_notifier);
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	struct busfreq_opp_info	new_oppinfo;
 	unsigned long maxfreq = ULONG_MAX;
 	int err = 0;
@@ -1020,7 +1020,7 @@ unlock:
 static int exynos4_busfreq_probe(struct platform_device *pdev)
 {
 	struct busfreq_data *data;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	struct device *dev = &pdev->dev;
 	int err = 0;
 
diff --git a/drivers/devfreq/exynos/exynos5_bus.c b/drivers/devfreq/exynos/exynos5_bus.c
index b0e45925505b..d06232aa0738 100644
--- a/drivers/devfreq/exynos/exynos5_bus.c
+++ b/drivers/devfreq/exynos/exynos5_bus.c
@@ -132,7 +132,7 @@ static int exynos5_busfreq_int_target(struct device *dev, unsigned long *_freq,
 	struct platform_device *pdev = container_of(dev, struct platform_device,
 						    dev);
 	struct busfreq_data_int *data = platform_get_drvdata(pdev);
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long old_freq, freq;
 	unsigned long volt;
 
@@ -262,7 +262,7 @@ static int exynos5_busfreq_int_pm_notifier_event(struct notifier_block *this,
 {
 	struct busfreq_data_int *data = container_of(this,
 					struct busfreq_data_int, pm_notifier);
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	unsigned long maxfreq = ULONG_MAX;
 	unsigned long freq;
 	unsigned long volt;
@@ -316,7 +316,7 @@ unlock:
 static int exynos5_busfreq_int_probe(struct platform_device *pdev)
 {
 	struct busfreq_data_int *data;
-	struct opp *opp;
+	struct dev_pm_opp *opp;
 	struct device *dev = &pdev->dev;
 	struct device_node *np;
 	unsigned long initial_freq;
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 5f1ab92107e6..c8c995325ca8 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -187,7 +187,7 @@ extern int devfreq_suspend_device(struct devfreq *devfreq);
 extern int devfreq_resume_device(struct devfreq *devfreq);
 
 /* Helper functions for devfreq user device driver with OPP. */
-extern struct opp *devfreq_recommended_opp(struct device *dev,
+extern struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq, u32 flags);
 extern int devfreq_register_opp_notifier(struct device *dev,
 					 struct devfreq *devfreq);
@@ -238,7 +238,7 @@ static inline int devfreq_resume_device(struct devfreq *devfreq)
 	return 0;
 }
 
-static inline struct opp *devfreq_recommended_opp(struct device *dev,
+static inline struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq, u32 flags)
 {
 	return ERR_PTR(-EINVAL);
diff --git a/include/linux/opp.h b/include/linux/opp.h
index 2066ae5880c6..5151b0059585 100644
--- a/include/linux/opp.h
+++ b/include/linux/opp.h
@@ -18,27 +18,30 @@
 #include <linux/cpufreq.h>
 #include <linux/notifier.h>
 
-struct opp;
+struct dev_pm_opp;
 struct device;
 
-enum opp_event {
+enum dev_pm_opp_event {
 	OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
 };
 
 #if defined(CONFIG_PM_OPP)
 
-unsigned long dev_pm_opp_get_voltage(struct opp *opp);
+unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
 
-unsigned long dev_pm_opp_get_freq(struct opp *opp);
+unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
 
 int dev_pm_opp_get_opp_count(struct device *dev);
 
-struct opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq,
-				bool available);
+struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					      unsigned long freq,
+					      bool available);
 
-struct opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq);
+struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
+					      unsigned long *freq);
 
-struct opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq);
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+					     unsigned long *freq);
 
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
 		   unsigned long u_volt);
@@ -49,12 +52,12 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq);
 
 struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
 #else
-static inline unsigned long dev_pm_opp_get_voltage(struct opp *opp)
+static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
 	return 0;
 }
 
-static inline unsigned long dev_pm_opp_get_freq(struct opp *opp)
+static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
 	return 0;
 }
@@ -64,19 +67,19 @@ static inline int dev_pm_opp_get_opp_count(struct device *dev)
 	return 0;
 }
 
-static inline struct opp *dev_pm_opp_find_freq_exact(struct device *dev,
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					unsigned long freq, bool available)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct opp *dev_pm_opp_find_freq_floor(struct device *dev,
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					unsigned long *freq)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline struct opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					unsigned long *freq)
 {
 	return ERR_PTR(-EINVAL);
-- 
cgit 


From e4db1c7439b31993a4886b273bb9235a8eea82bf Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Thu, 19 Sep 2013 16:03:52 -0500
Subject: PM / OPP: rename header to linux/pm_opp.h

Since Operating Performance Points (OPP) functions are specific
to device specific power management, be specific and rename opp.h
to pm_opp.h

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/opp.txt             |   2 +-
 arch/arm/mach-imx/mach-imx6q.c          |   2 +-
 arch/arm/mach-omap2/board-omap3beagle.c |   2 +-
 arch/arm/mach-omap2/omap-pm.h           |   2 +-
 arch/arm/mach-omap2/opp.c               |   2 +-
 arch/arm/mach-omap2/pm.c                |   2 +-
 drivers/base/power/opp.c                |   2 +-
 drivers/cpufreq/arm_big_little.c        |   2 +-
 drivers/cpufreq/arm_big_little_dt.c     |   2 +-
 drivers/cpufreq/cpufreq-cpu0.c          |   2 +-
 drivers/cpufreq/exynos5440-cpufreq.c    |   2 +-
 drivers/cpufreq/imx6q-cpufreq.c         |   2 +-
 drivers/cpufreq/omap-cpufreq.c          |   2 +-
 drivers/devfreq/devfreq.c               |   2 +-
 drivers/devfreq/exynos/exynos4_bus.c    |   2 +-
 drivers/devfreq/exynos/exynos5_bus.c    |   4 +-
 include/linux/devfreq.h                 |   2 +-
 include/linux/opp.h                     | 139 --------------------------------
 include/linux/pm_opp.h                  | 139 ++++++++++++++++++++++++++++++++
 19 files changed, 157 insertions(+), 157 deletions(-)
 delete mode 100644 include/linux/opp.h
 create mode 100644 include/linux/pm_opp.h

(limited to 'include')

diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index 7f67e3d2c530..b8a907dc0169 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -42,7 +42,7 @@ We can represent these as three OPPs as the following {Hz, uV} tuples:
 
 OPP library provides a set of helper functions to organize and query the OPP
 information. The library is located in drivers/base/power/opp.c and the header
-is located in include/linux/opp.h. OPP library can be enabled by enabling
+is located in include/linux/pm_opp.h. OPP library can be enabled by enabling
 CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
 CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
 optionally boot at a certain OPP without needing cpufreq.
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index d7ecc90e6bba..699aabe296e1 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -25,7 +25,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/phy.h>
 #include <linux/reboot.h>
 #include <linux/regmap.h>
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 33969e5a149f..6432ab8d9207 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -25,7 +25,7 @@
 #include <linux/gpio.h>
 #include <linux/input.h>
 #include <linux/gpio_keys.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/cpu.h>
 
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-omap2/omap-pm.h b/arch/arm/mach-omap2/omap-pm.h
index 67faa7b8fe92..1d777e63e05c 100644
--- a/arch/arm/mach-omap2/omap-pm.h
+++ b/arch/arm/mach-omap2/omap-pm.h
@@ -17,7 +17,7 @@
 #include <linux/device.h>
 #include <linux/cpufreq.h>
 #include <linux/clk.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 
 /*
  * agent_id values for use with omap_pm_set_min_bus_tput():
diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c
index 7b04637b13cb..ec21e6eb03e1 100644
--- a/arch/arm/mach-omap2/opp.c
+++ b/arch/arm/mach-omap2/opp.c
@@ -17,7 +17,7 @@
  * GNU General Public License for more details.
  */
 #include <linux/module.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/cpu.h>
 
 #include "omap_device.h"
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 92901bd41490..2f569b3c3092 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/err.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/cpu.h>
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 693e14a24914..fa4187418440 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -21,7 +21,7 @@
 #include <linux/list.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/of.h>
 #include <linux/export.h>
 
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 9e82a9d5df77..e010fb722c6b 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -25,7 +25,7 @@
 #include <linux/cpumask.h>
 #include <linux/export.h>
 #include <linux/of_platform.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
diff --git a/drivers/cpufreq/arm_big_little_dt.c b/drivers/cpufreq/arm_big_little_dt.c
index 480c0bd0468d..8d9d59108906 100644
--- a/drivers/cpufreq/arm_big_little_dt.c
+++ b/drivers/cpufreq/arm_big_little_dt.c
@@ -24,7 +24,7 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/types.h>
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index d73107894fee..242d4900de47 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -17,7 +17,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index c8b3d3950f9e..d41e77769d1a 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -20,7 +20,7 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 84e993dfb305..e4c914066601 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -13,7 +13,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index f057d423020c..20190f56594f 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -22,7 +22,7 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 03530a0a8042..2e23b12c350b 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -18,7 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/workqueue.h>
 #include <linux/platform_device.h>
diff --git a/drivers/devfreq/exynos/exynos4_bus.c b/drivers/devfreq/exynos/exynos4_bus.c
index 891becd46513..cede6f71cd63 100644
--- a/drivers/devfreq/exynos/exynos4_bus.c
+++ b/drivers/devfreq/exynos/exynos4_bus.c
@@ -19,7 +19,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/suspend.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
diff --git a/drivers/devfreq/exynos/exynos5_bus.c b/drivers/devfreq/exynos/exynos5_bus.c
index d06232aa0738..52835f12ac98 100644
--- a/drivers/devfreq/exynos/exynos5_bus.c
+++ b/drivers/devfreq/exynos/exynos5_bus.c
@@ -15,10 +15,10 @@
 #include <linux/module.h>
 #include <linux/devfreq.h>
 #include <linux/io.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index c8c995325ca8..7a7cc74d7f27 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -15,7 +15,7 @@
 
 #include <linux/device.h>
 #include <linux/notifier.h>
-#include <linux/opp.h>
+#include <linux/pm_opp.h>
 
 #define DEVFREQ_NAME_LEN 16
 
diff --git a/include/linux/opp.h b/include/linux/opp.h
deleted file mode 100644
index 5151b0059585..000000000000
--- a/include/linux/opp.h
+++ /dev/null
@@ -1,139 +0,0 @@
-/*
- * Generic OPP Interface
- *
- * Copyright (C) 2009-2010 Texas Instruments Incorporated.
- *	Nishanth Menon
- *	Romit Dasgupta
- *	Kevin Hilman
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __LINUX_OPP_H__
-#define __LINUX_OPP_H__
-
-#include <linux/err.h>
-#include <linux/cpufreq.h>
-#include <linux/notifier.h>
-
-struct dev_pm_opp;
-struct device;
-
-enum dev_pm_opp_event {
-	OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
-};
-
-#if defined(CONFIG_PM_OPP)
-
-unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
-
-unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
-
-int dev_pm_opp_get_opp_count(struct device *dev);
-
-struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
-					      unsigned long freq,
-					      bool available);
-
-struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
-					      unsigned long *freq);
-
-struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
-					     unsigned long *freq);
-
-int dev_pm_opp_add(struct device *dev, unsigned long freq,
-		   unsigned long u_volt);
-
-int dev_pm_opp_enable(struct device *dev, unsigned long freq);
-
-int dev_pm_opp_disable(struct device *dev, unsigned long freq);
-
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
-#else
-static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
-{
-	return 0;
-}
-
-static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
-{
-	return 0;
-}
-
-static inline int dev_pm_opp_get_opp_count(struct device *dev)
-{
-	return 0;
-}
-
-static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
-					unsigned long freq, bool available)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
-					unsigned long *freq)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
-					unsigned long *freq)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
-					unsigned long u_volt)
-{
-	return -EINVAL;
-}
-
-static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
-{
-	return 0;
-}
-
-static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq)
-{
-	return 0;
-}
-
-static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
-							struct device *dev)
-{
-	return ERR_PTR(-EINVAL);
-}
-#endif		/* CONFIG_PM_OPP */
-
-#if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
-int of_init_opp_table(struct device *dev);
-#else
-static inline int of_init_opp_table(struct device *dev)
-{
-	return -EINVAL;
-}
-#endif
-
-#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
-int dev_pm_opp_init_cpufreq_table(struct device *dev,
-			    struct cpufreq_frequency_table **table);
-void dev_pm_opp_free_cpufreq_table(struct device *dev,
-				struct cpufreq_frequency_table **table);
-#else
-static inline int dev_pm_opp_init_cpufreq_table(struct device *dev,
-			    struct cpufreq_frequency_table **table)
-{
-	return -EINVAL;
-}
-
-static inline
-void dev_pm_opp_free_cpufreq_table(struct device *dev,
-				struct cpufreq_frequency_table **table)
-{
-}
-#endif		/* CONFIG_CPU_FREQ */
-
-#endif		/* __LINUX_OPP_H__ */
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
new file mode 100644
index 000000000000..5151b0059585
--- /dev/null
+++ b/include/linux/pm_opp.h
@@ -0,0 +1,139 @@
+/*
+ * Generic OPP Interface
+ *
+ * Copyright (C) 2009-2010 Texas Instruments Incorporated.
+ *	Nishanth Menon
+ *	Romit Dasgupta
+ *	Kevin Hilman
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_OPP_H__
+#define __LINUX_OPP_H__
+
+#include <linux/err.h>
+#include <linux/cpufreq.h>
+#include <linux/notifier.h>
+
+struct dev_pm_opp;
+struct device;
+
+enum dev_pm_opp_event {
+	OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
+};
+
+#if defined(CONFIG_PM_OPP)
+
+unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
+
+unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
+
+int dev_pm_opp_get_opp_count(struct device *dev);
+
+struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					      unsigned long freq,
+					      bool available);
+
+struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
+					      unsigned long *freq);
+
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+					     unsigned long *freq);
+
+int dev_pm_opp_add(struct device *dev, unsigned long freq,
+		   unsigned long u_volt);
+
+int dev_pm_opp_enable(struct device *dev, unsigned long freq);
+
+int dev_pm_opp_disable(struct device *dev, unsigned long freq);
+
+struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
+#else
+static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
+{
+	return 0;
+}
+
+static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
+{
+	return 0;
+}
+
+static inline int dev_pm_opp_get_opp_count(struct device *dev)
+{
+	return 0;
+}
+
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
+					unsigned long freq, bool available)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
+					unsigned long *freq)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
+					unsigned long u_volt)
+{
+	return -EINVAL;
+}
+
+static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+
+static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq)
+{
+	return 0;
+}
+
+static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
+							struct device *dev)
+{
+	return ERR_PTR(-EINVAL);
+}
+#endif		/* CONFIG_PM_OPP */
+
+#if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
+int of_init_opp_table(struct device *dev);
+#else
+static inline int of_init_opp_table(struct device *dev)
+{
+	return -EINVAL;
+}
+#endif
+
+#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
+int dev_pm_opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table);
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
+				struct cpufreq_frequency_table **table);
+#else
+static inline int dev_pm_opp_init_cpufreq_table(struct device *dev,
+			    struct cpufreq_frequency_table **table)
+{
+	return -EINVAL;
+}
+
+static inline
+void dev_pm_opp_free_cpufreq_table(struct device *dev,
+				struct cpufreq_frequency_table **table)
+{
+}
+#endif		/* CONFIG_CPU_FREQ */
+
+#endif		/* __LINUX_OPP_H__ */
-- 
cgit 


From 9c0ebcf78fde0ffa348a95a544c6d3f2dac5af65 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 25 Oct 2013 19:45:48 +0530
Subject: cpufreq: Implement light weight ->target_index() routine

Currently, the prototype of cpufreq_drivers target routines is:

int target(struct cpufreq_policy *policy, unsigned int target_freq,
		unsigned int relation);

And most of the drivers call cpufreq_frequency_table_target() to get a valid
index of their frequency table which is closest to the target_freq. And they
don't use target_freq and relation after that.

So, it makes sense to just do this work in cpufreq core before calling
cpufreq_frequency_table_target() and simply pass index instead. But this can be
done only with drivers which expose their frequency table with cpufreq core. For
others we need to stick with the old prototype of target() until those drivers
are converted to expose frequency tables.

This patch implements the new light weight prototype for target_index() routine.
It looks like this:

int target_index(struct cpufreq_policy *policy, unsigned int index);

CPUFreq core will call cpufreq_frequency_table_target() before calling this
routine and pass index to it. Because CPUFreq core now requires to call routines
present in freq_table.c CONFIG_CPU_FREQ_TABLE must be enabled all the time.

This also marks target() interface as deprecated. So, that new drivers avoid
using it. And Documentation is updated accordingly.

It also converts existing .target() to newly defined light weight
.target_index() routine for many driver.

Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Russell King <linux@arm.linux.org.uk>
Acked-by: David S. Miller <davem@davemloft.net>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
---
 Documentation/cpu-freq/cpu-drivers.txt | 27 ++++++++++------
 Documentation/cpu-freq/governors.txt   |  4 +--
 arch/arm/mach-sa1100/generic.c         | 20 ------------
 arch/arm/mach-sa1100/generic.h         |  2 --
 drivers/cpufreq/acpi-cpufreq.c         | 21 ++++---------
 drivers/cpufreq/arm_big_little.c       | 17 +++-------
 drivers/cpufreq/at32ap-cpufreq.c       | 23 +++-----------
 drivers/cpufreq/blackfin-cpufreq.c     | 17 +++-------
 drivers/cpufreq/cpufreq-cpu0.c         | 17 ++--------
 drivers/cpufreq/cpufreq.c              | 57 +++++++++++++++++++++++++++-------
 drivers/cpufreq/cris-artpec3-cpufreq.c | 18 ++---------
 drivers/cpufreq/cris-etraxfs-cpufreq.c | 17 ++--------
 drivers/cpufreq/davinci-cpufreq.c      | 16 ++--------
 drivers/cpufreq/dbx500-cpufreq.c       | 16 ++--------
 drivers/cpufreq/e_powersaver.c         | 17 ++--------
 drivers/cpufreq/elanfreq.c             | 34 ++------------------
 drivers/cpufreq/exynos-cpufreq.c       | 21 ++-----------
 drivers/cpufreq/exynos5440-cpufreq.c   | 21 +++----------
 drivers/cpufreq/ia64-acpi-cpufreq.c    | 21 ++-----------
 drivers/cpufreq/imx6q-cpufreq.c        | 17 ++--------
 drivers/cpufreq/kirkwood-cpufreq.c     | 19 ++----------
 drivers/cpufreq/longhaul.c             | 13 ++------
 drivers/cpufreq/loongson2_cpufreq.c    | 21 +++----------
 drivers/cpufreq/maple-cpufreq.c        | 16 +++-------
 drivers/cpufreq/omap-cpufreq.c         | 31 ++----------------
 drivers/cpufreq/p4-clockmod.c          | 18 +++--------
 drivers/cpufreq/pasemi-cpufreq.c       | 12 ++-----
 drivers/cpufreq/pmac32-cpufreq.c       | 12 ++-----
 drivers/cpufreq/pmac64-cpufreq.c       | 17 +++-------
 drivers/cpufreq/powernow-k6.c          | 35 +++------------------
 drivers/cpufreq/powernow-k7.c          | 22 +++----------
 drivers/cpufreq/powernow-k8.c          | 24 +++++---------
 drivers/cpufreq/ppc-corenet-cpufreq.c  | 15 +++------
 drivers/cpufreq/ppc_cbe_cpufreq.c      | 12 ++-----
 drivers/cpufreq/pxa2xx-cpufreq.c       | 13 ++------
 drivers/cpufreq/pxa3xx-cpufreq.c       | 17 ++--------
 drivers/cpufreq/s3c2416-cpufreq.c      | 17 +++-------
 drivers/cpufreq/s3c64xx-cpufreq.c      | 18 +++--------
 drivers/cpufreq/s5pv210-cpufreq.c      | 54 +++++++++-----------------------
 drivers/cpufreq/sa1100-cpufreq.c       | 24 +++-----------
 drivers/cpufreq/sa1110-cpufreq.c       | 26 +++-------------
 drivers/cpufreq/sc520_freq.c           | 19 ++----------
 drivers/cpufreq/sparc-us2e-cpufreq.c   | 21 ++-----------
 drivers/cpufreq/sparc-us3-cpufreq.c    | 23 ++------------
 drivers/cpufreq/spear-cpufreq.c        | 12 +++----
 drivers/cpufreq/speedstep-centrino.c   | 27 +++++-----------
 drivers/cpufreq/speedstep-ich.c        | 24 ++++----------
 drivers/cpufreq/speedstep-smi.c        | 20 +++---------
 drivers/cpufreq/tegra-cpufreq.c        | 12 ++-----
 include/linux/cpufreq.h                |  4 ++-
 50 files changed, 242 insertions(+), 759 deletions(-)

(limited to 'include')

diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 40282e617913..8b1a4451422e 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -23,8 +23,8 @@ Contents:
 1.1  Initialization
 1.2  Per-CPU Initialization
 1.3  verify
-1.4  target or setpolicy?
-1.5  target
+1.4  target/target_index or setpolicy?
+1.5  target/target_index
 1.6  setpolicy
 2.   Frequency Table Helpers
 
@@ -56,7 +56,8 @@ cpufreq_driver.init -		A pointer to the per-CPU initialization
 cpufreq_driver.verify -		A pointer to a "verification" function.
 
 cpufreq_driver.setpolicy _or_ 
-cpufreq_driver.target -		See below on the differences.
+cpufreq_driver.target/
+target_index		-	See below on the differences.
 
 And optionally
 
@@ -66,7 +67,7 @@ cpufreq_driver.resume -		A pointer to a per-CPU resume function
 				which is called with interrupts disabled
 				and _before_ the pre-suspend frequency
 				and/or policy is restored by a call to
-				->target or ->setpolicy.
+				->target/target_index or ->setpolicy.
 
 cpufreq_driver.attr -		A pointer to a NULL-terminated list of
 				"struct freq_attr" which allow to
@@ -103,8 +104,8 @@ policy->governor		must contain the "default policy" for
 				this CPU. A few moments later,
 				cpufreq_driver.verify and either
 				cpufreq_driver.setpolicy or
-				cpufreq_driver.target is called with
-				these values.
+				cpufreq_driver.target/target_index is called
+				with these values.
 
 For setting some of these values (cpuinfo.min[max]_freq, policy->min[max]), the
 frequency table helpers might be helpful. See the section 2 for more information
@@ -133,20 +134,28 @@ range) is within policy->min and policy->max. If necessary, increase
 policy->max first, and only if this is no solution, decrease policy->min.
 
 
-1.4 target or setpolicy?
+1.4 target/target_index or setpolicy?
 ----------------------------
 
 Most cpufreq drivers or even most cpu frequency scaling algorithms 
 only allow the CPU to be set to one frequency. For these, you use the
-->target call.
+->target/target_index call.
 
 Some cpufreq-capable processors switch the frequency between certain
 limits on their own. These shall use the ->setpolicy call
 
 
-1.4. target
+1.4. target/target_index
 -------------
 
+The target_index call has two arguments: struct cpufreq_policy *policy,
+and unsigned int index (into the exposed frequency table).
+
+The CPUfreq driver must set the new frequency when called here. The
+actual frequency must be determined by freq_table[index].frequency.
+
+Deprecated:
+----------
 The target call has three arguments: struct cpufreq_policy *policy,
 unsigned int target_frequency, unsigned int relation.
 
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index 219970ba54b7..77ec21574fb1 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -40,7 +40,7 @@ Most cpufreq drivers (in fact, all except one, longrun) or even most
 cpu frequency scaling algorithms only offer the CPU to be set to one
 frequency. In order to offer dynamic frequency scaling, the cpufreq
 core must be able to tell these drivers of a "target frequency". So
-these specific drivers will be transformed to offer a "->target"
+these specific drivers will be transformed to offer a "->target/target_index"
 call instead of the existing "->setpolicy" call. For "longrun", all
 stays the same, though.
 
@@ -71,7 +71,7 @@ CPU can be set to switch independently	 |	   CPU can only be set
 		    /			       the limits of policy->{min,max}
 		   /			            \
 		  /				     \
-	Using the ->setpolicy call,		 Using the ->target call,
+	Using the ->setpolicy call,		 Using the ->target/target_index call,
 	    the limits and the			  the frequency closest
 	     "policy" is set.			  to target_freq is set.
 						  It is assured that it
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index cb4b2ca3cf6b..d4ea142c4edd 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -62,26 +62,6 @@ struct cpufreq_frequency_table sa11x0_freq_table[NR_FREQS+1] = {
 	{ .frequency = CPUFREQ_TABLE_END, },
 };
 
-/* rounds up(!)  */
-unsigned int sa11x0_freq_to_ppcr(unsigned int khz)
-{
-	int i;
-
-	for (i = 0; i < NR_FREQS; i++)
-		if (sa11x0_freq_table[i].frequency >= khz)
-			break;
-
-	return i;
-}
-
-unsigned int sa11x0_ppcr_to_freq(unsigned int idx)
-{
-	unsigned int freq = 0;
-	if (idx < NR_FREQS)
-		freq = sa11x0_freq_table[idx].frequency;
-	return freq;
-}
-
 unsigned int sa11x0_getspeed(unsigned int cpu)
 {
 	if (cpu)
diff --git a/arch/arm/mach-sa1100/generic.h b/arch/arm/mach-sa1100/generic.h
index cbdfae744dc5..0d92e119b36b 100644
--- a/arch/arm/mach-sa1100/generic.h
+++ b/arch/arm/mach-sa1100/generic.h
@@ -21,9 +21,7 @@ extern void sa1110_mb_enable(void);
 extern void sa1110_mb_disable(void);
 
 extern struct cpufreq_frequency_table sa11x0_freq_table[];
-extern unsigned int sa11x0_freq_to_ppcr(unsigned int khz);
 extern unsigned int sa11x0_getspeed(unsigned int cpu);
-extern unsigned int sa11x0_ppcr_to_freq(unsigned int idx);
 
 struct flash_platform_data;
 struct resource;
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index a1717d7367c1..889cec0a9022 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -424,17 +424,17 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 }
 
 static int acpi_cpufreq_target(struct cpufreq_policy *policy,
-			       unsigned int target_freq, unsigned int relation)
+			       unsigned int index)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 	struct acpi_processor_performance *perf;
 	struct cpufreq_freqs freqs;
 	struct drv_cmd cmd;
-	unsigned int next_state = 0; /* Index into freq_table */
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
-	pr_debug("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
+	pr_debug("acpi_cpufreq_target %d (%d)\n",
+			data->freq_table[index].frequency, policy->cpu);
 
 	if (unlikely(data == NULL ||
 	     data->acpi_data == NULL || data->freq_table == NULL)) {
@@ -442,16 +442,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	}
 
 	perf = data->acpi_data;
-	result = cpufreq_frequency_table_target(policy,
-						data->freq_table,
-						target_freq,
-						relation, &next_state);
-	if (unlikely(result)) {
-		result = -ENODEV;
-		goto out;
-	}
-
-	next_perf_state = data->freq_table[next_state].driver_data;
+	next_perf_state = data->freq_table[index].driver_data;
 	if (perf->state == next_perf_state) {
 		if (unlikely(data->resume)) {
 			pr_debug("Called after resume, resetting to P%d\n",
@@ -493,7 +484,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		cmd.mask = cpumask_of(policy->cpu);
 
 	freqs.old = perf->states[perf->state].core_frequency * 1000;
-	freqs.new = data->freq_table[next_state].frequency;
+	freqs.new = data->freq_table[index].frequency;
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	drv_write(&cmd);
@@ -923,7 +914,7 @@ static struct freq_attr *acpi_cpufreq_attr[] = {
 
 static struct cpufreq_driver acpi_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= acpi_cpufreq_target,
+	.target_index	= acpi_cpufreq_target,
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 086f7c17ff58..163e3378fe17 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -49,28 +49,21 @@ static unsigned int bL_cpufreq_get(unsigned int cpu)
 
 /* Set clock frequency */
 static int bL_cpufreq_set_target(struct cpufreq_policy *policy,
-		unsigned int target_freq, unsigned int relation)
+		unsigned int index)
 {
 	struct cpufreq_freqs freqs;
-	u32 cpu = policy->cpu, freq_tab_idx, cur_cluster;
+	u32 cpu = policy->cpu, cur_cluster;
 	int ret = 0;
 
 	cur_cluster = cpu_to_cluster(policy->cpu);
 
 	freqs.old = bL_cpufreq_get(policy->cpu);
-
-	/* Determine valid target frequency using freq_table */
-	cpufreq_frequency_table_target(policy, freq_table[cur_cluster],
-			target_freq, relation, &freq_tab_idx);
-	freqs.new = freq_table[cur_cluster][freq_tab_idx].frequency;
+	freqs.new = freq_table[cur_cluster][index].frequency;
 
 	pr_debug("%s: cpu: %d, cluster: %d, oldfreq: %d, target freq: %d, new freq: %d\n",
-			__func__, cpu, cur_cluster, freqs.old, target_freq,
+			__func__, cpu, cur_cluster, freqs.old, freqs.new,
 			freqs.new);
 
-	if (freqs.old == freqs.new)
-		return 0;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	ret = clk_set_rate(clk[cur_cluster], freqs.new * 1000);
@@ -200,7 +193,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.flags			= CPUFREQ_STICKY |
 					CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
 	.verify			= cpufreq_generic_frequency_table_verify,
-	.target			= bL_cpufreq_set_target,
+	.target_index		= bL_cpufreq_set_target,
 	.get			= bL_cpufreq_get,
 	.init			= bL_cpufreq_init,
 	.exit			= bL_cpufreq_exit,
diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c
index 7439deddd5cf..81d07527bde6 100644
--- a/drivers/cpufreq/at32ap-cpufreq.c
+++ b/drivers/cpufreq/at32ap-cpufreq.c
@@ -35,25 +35,12 @@ static unsigned int at32_get_speed(unsigned int cpu)
 static unsigned int	ref_freq;
 static unsigned long	loops_per_jiffy_ref;
 
-static int at32_set_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int at32_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct cpufreq_freqs freqs;
-	long freq;
-
-	/* Convert target_freq from kHz to Hz */
-	freq = clk_round_rate(cpuclk, target_freq * 1000);
-
-	/* Check if policy->min <= new_freq <= policy->max */
-	if(freq < (policy->min * 1000) || freq > (policy->max * 1000))
-		return -EINVAL;
-
-	pr_debug("cpufreq: requested frequency %u Hz\n", target_freq * 1000);
 
 	freqs.old = at32_get_speed(0);
-	freqs.new = (freq + 500) / 1000;
-	freqs.flags = 0;
+	freqs.new = freq_table[index].frequency;
 
 	if (!ref_freq) {
 		ref_freq = freqs.old;
@@ -64,13 +51,13 @@ static int at32_set_target(struct cpufreq_policy *policy,
 	if (freqs.old < freqs.new)
 		boot_cpu_data.loops_per_jiffy = cpufreq_scale(
 				loops_per_jiffy_ref, ref_freq, freqs.new);
-	clk_set_rate(cpuclk, freq);
+	clk_set_rate(cpuclk, freqs.new * 1000);
 	if (freqs.new < freqs.old)
 		boot_cpu_data.loops_per_jiffy = cpufreq_scale(
 				loops_per_jiffy_ref, ref_freq, freqs.new);
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
-	pr_debug("cpufreq: set frequency %lu Hz\n", freq);
+	pr_debug("cpufreq: set frequency %u Hz\n", freqs.new * 1000);
 
 	return 0;
 }
@@ -139,7 +126,7 @@ static struct cpufreq_driver at32_driver = {
 	.name		= "at32ap",
 	.init		= at32_cpufreq_driver_init,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= at32_set_target,
+	.target_index	= at32_set_target,
 	.get		= at32_get_speed,
 	.flags		= CPUFREQ_STICKY,
 };
diff --git a/drivers/cpufreq/blackfin-cpufreq.c b/drivers/cpufreq/blackfin-cpufreq.c
index 0bc9e8c2c79b..12528b28d45d 100644
--- a/drivers/cpufreq/blackfin-cpufreq.c
+++ b/drivers/cpufreq/blackfin-cpufreq.c
@@ -127,14 +127,11 @@ unsigned long cpu_set_cclk(int cpu, unsigned long new)
 }
 #endif
 
-static int bfin_target(struct cpufreq_policy *policy,
-			unsigned int target_freq, unsigned int relation)
+static int bfin_target(struct cpufreq_policy *policy, unsigned int index)
 {
 #ifndef CONFIG_BF60x
 	unsigned int plldiv;
 #endif
-	unsigned int index;
-	unsigned long cclk_hz;
 	struct cpufreq_freqs freqs;
 	static unsigned long lpj_ref;
 	static unsigned int  lpj_ref_freq;
@@ -144,17 +141,11 @@ static int bfin_target(struct cpufreq_policy *policy,
 	cycles_t cycles;
 #endif
 
-	if (cpufreq_frequency_table_target(policy, bfin_freq_table, target_freq,
-				relation, &index))
-		return -EINVAL;
-
-	cclk_hz = bfin_freq_table[index].frequency;
-
 	freqs.old = bfin_getfreq_khz(0);
-	freqs.new = cclk_hz;
+	freqs.new = bfin_freq_table[index].frequency;
 
 	pr_debug("cpufreq: changing cclk to %lu; target = %u, oldfreq = %u\n",
-			cclk_hz, target_freq, freqs.old);
+			freqs.new, freqs.new, freqs.old);
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 #ifndef CONFIG_BF60x
@@ -209,7 +200,7 @@ static int __bfin_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver bfin_driver = {
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = bfin_target,
+	.target_index = bfin_target,
 	.get = bfin_getfreq_khz,
 	.init = __bfin_cpu_init,
 	.exit = cpufreq_generic_exit,
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 33ab6504c447..4dbe7efd86e5 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -35,24 +35,14 @@ static unsigned int cpu0_get_speed(unsigned int cpu)
 	return clk_get_rate(cpu_clk) / 1000;
 }
 
-static int cpu0_set_target(struct cpufreq_policy *policy,
-			   unsigned int target_freq, unsigned int relation)
+static int cpu0_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct cpufreq_freqs freqs;
 	struct dev_pm_opp *opp;
 	unsigned long volt = 0, volt_old = 0, tol = 0;
 	long freq_Hz, freq_exact;
-	unsigned int index;
 	int ret;
 
-	ret = cpufreq_frequency_table_target(policy, freq_table, target_freq,
-					     relation, &index);
-	if (ret) {
-		pr_err("failed to match target freqency %d: %d\n",
-		       target_freq, ret);
-		return ret;
-	}
-
 	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
 	if (freq_Hz < 0)
 		freq_Hz = freq_table[index].frequency * 1000;
@@ -60,9 +50,6 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 	freqs.new = freq_Hz / 1000;
 	freqs.old = clk_get_rate(cpu_clk) / 1000;
 
-	if (freqs.old == freqs.new)
-		return 0;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	if (!IS_ERR(cpu_reg)) {
@@ -128,7 +115,7 @@ static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver cpu0_cpufreq_driver = {
 	.flags = CPUFREQ_STICKY,
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = cpu0_set_target,
+	.target_index = cpu0_set_target,
 	.get = cpu0_get_speed,
 	.init = cpu0_cpufreq_init,
 	.exit = cpufreq_generic_exit,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ec391d7f010b..87ed83a6c894 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -47,6 +47,11 @@ static LIST_HEAD(cpufreq_policy_list);
 static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 #endif
 
+static inline bool has_target(void)
+{
+	return cpufreq_driver->target_index || cpufreq_driver->target;
+}
+
 /*
  * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
  * all cpufreq/hotplug/workqueue/etc related lock issues.
@@ -392,7 +397,7 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 			*policy = CPUFREQ_POLICY_POWERSAVE;
 			err = 0;
 		}
-	} else if (cpufreq_driver->target) {
+	} else if (has_target()) {
 		struct cpufreq_governor *t;
 
 		mutex_lock(&cpufreq_governor_mutex);
@@ -550,7 +555,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
 	ssize_t i = 0;
 	struct cpufreq_governor *t;
 
-	if (!cpufreq_driver->target) {
+	if (!has_target()) {
 		i += sprintf(buf, "performance powersave");
 		goto out;
 	}
@@ -835,7 +840,7 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 		if (ret)
 			goto err_out_kobj_put;
 	}
-	if (cpufreq_driver->target) {
+	if (has_target()) {
 		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
 		if (ret)
 			goto err_out_kobj_put;
@@ -884,10 +889,10 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 				  unsigned int cpu, struct device *dev,
 				  bool frozen)
 {
-	int ret = 0, has_target = !!cpufreq_driver->target;
+	int ret = 0;
 	unsigned long flags;
 
-	if (has_target) {
+	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			pr_err("%s: Failed to stop governor\n", __func__);
@@ -905,7 +910,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 
 	unlock_policy_rwsem_write(policy->cpu);
 
-	if (has_target) {
+	if (has_target()) {
 		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
 			(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
 			pr_err("%s: Failed to start governor\n", __func__);
@@ -1215,7 +1220,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 		return -EINVAL;
 	}
 
-	if (cpufreq_driver->target) {
+	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			pr_err("%s: Failed to stop governor\n", __func__);
@@ -1280,7 +1285,7 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target) {
+		if (has_target()) {
 			ret = __cpufreq_governor(policy,
 					CPUFREQ_GOV_POLICY_EXIT);
 			if (ret) {
@@ -1323,7 +1328,7 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		if (!frozen)
 			cpufreq_policy_free(policy);
 	} else {
-		if (cpufreq_driver->target) {
+		if (has_target()) {
 			if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
 					(ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))) {
 				pr_err("%s: Failed to start governor\n",
@@ -1694,12 +1699,41 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
 			policy->cpu, target_freq, relation, old_target_freq);
 
+	/*
+	 * This might look like a redundant call as we are checking it again
+	 * after finding index. But it is left intentionally for cases where
+	 * exactly same freq is called again and so we can save on few function
+	 * calls.
+	 */
 	if (target_freq == policy->cur)
 		return 0;
 
 	if (cpufreq_driver->target)
 		retval = cpufreq_driver->target(policy, target_freq, relation);
+	else if (cpufreq_driver->target_index) {
+		struct cpufreq_frequency_table *freq_table;
+		int index;
 
+		freq_table = cpufreq_frequency_get_table(policy->cpu);
+		if (unlikely(!freq_table)) {
+			pr_err("%s: Unable to find freq_table\n", __func__);
+			goto out;
+		}
+
+		retval = cpufreq_frequency_table_target(policy, freq_table,
+				target_freq, relation, &index);
+		if (unlikely(retval)) {
+			pr_err("%s: Unable to find matching freq\n", __func__);
+			goto out;
+		}
+
+		if (freq_table[index].frequency == policy->cur)
+			retval = 0;
+		else
+			retval = cpufreq_driver->target_index(policy, index);
+	}
+
+out:
 	return retval;
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
@@ -2025,7 +2059,7 @@ int cpufreq_update_policy(unsigned int cpu)
 			pr_debug("Driver did not initialize current freq");
 			policy->cur = new_policy.cur;
 		} else {
-			if (policy->cur != new_policy.cur && cpufreq_driver->target)
+			if (policy->cur != new_policy.cur && has_target())
 				cpufreq_out_of_sync(cpu, policy->cur,
 								new_policy.cur);
 		}
@@ -2103,7 +2137,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		return -ENODEV;
 
 	if (!driver_data || !driver_data->verify || !driver_data->init ||
-	    ((!driver_data->setpolicy) && (!driver_data->target)))
+	    !(driver_data->setpolicy || driver_data->target_index ||
+		    driver_data->target))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
diff --git a/drivers/cpufreq/cris-artpec3-cpufreq.c b/drivers/cpufreq/cris-artpec3-cpufreq.c
index 05fdc7e40257..841857cf1562 100644
--- a/drivers/cpufreq/cris-artpec3-cpufreq.c
+++ b/drivers/cpufreq/cris-artpec3-cpufreq.c
@@ -27,8 +27,7 @@ static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)
 	return clk_ctrl.pll ? 200000 : 6000;
 }
 
-static void cris_freq_set_cpu_state(struct cpufreq_policy *policy,
-		unsigned int state)
+static int cris_freq_target(struct cpufreq_policy *policy, unsigned int state)
 {
 	struct cpufreq_freqs freqs;
 	reg_clkgen_rw_clk_ctrl clk_ctrl;
@@ -52,19 +51,6 @@ static void cris_freq_set_cpu_state(struct cpufreq_policy *policy,
 	local_irq_enable();
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-};
-
-static int cris_freq_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
-{
-	unsigned int newstate = 0;
-
-	if (cpufreq_frequency_table_target(policy, cris_freq_table,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	cris_freq_set_cpu_state(policy, newstate);
 
 	return 0;
 }
@@ -77,7 +63,7 @@ static int cris_freq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver cris_freq_driver = {
 	.get	= cris_freq_get_cpu_frequency,
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= cris_freq_target,
+	.target_index = cris_freq_target,
 	.init	= cris_freq_cpu_init,
 	.exit	= cpufreq_generic_exit,
 	.name	= "cris_freq",
diff --git a/drivers/cpufreq/cris-etraxfs-cpufreq.c b/drivers/cpufreq/cris-etraxfs-cpufreq.c
index fac2b26932dd..c58811abd961 100644
--- a/drivers/cpufreq/cris-etraxfs-cpufreq.c
+++ b/drivers/cpufreq/cris-etraxfs-cpufreq.c
@@ -27,8 +27,7 @@ static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)
 	return clk_ctrl.pll ? 200000 : 6000;
 }
 
-static void cris_freq_set_cpu_state(struct cpufreq_policy *policy,
-		unsigned int state)
+static int cris_freq_target(struct cpufreq_policy *policy, unsigned int state)
 {
 	struct cpufreq_freqs freqs;
 	reg_config_rw_clk_ctrl clk_ctrl;
@@ -52,18 +51,6 @@ static void cris_freq_set_cpu_state(struct cpufreq_policy *policy,
 	local_irq_enable();
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-};
-
-static int cris_freq_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq, unsigned int relation)
-{
-	unsigned int newstate = 0;
-
-	if (cpufreq_frequency_table_target
-	    (policy, cris_freq_table, target_freq, relation, &newstate))
-		return -EINVAL;
-
-	cris_freq_set_cpu_state(policy, newstate);
 
 	return 0;
 }
@@ -76,7 +63,7 @@ static int cris_freq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver cris_freq_driver = {
 	.get = cris_freq_get_cpu_frequency,
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = cris_freq_target,
+	.target_index = cris_freq_target,
 	.init = cris_freq_cpu_init,
 	.exit = cpufreq_generic_exit,
 	.name = "cris_freq",
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 972583baf9e8..1f5d8a569c77 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -66,28 +66,18 @@ static unsigned int davinci_getspeed(unsigned int cpu)
 	return clk_get_rate(cpufreq.armclk) / 1000;
 }
 
-static int davinci_target(struct cpufreq_policy *policy,
-				unsigned int target_freq, unsigned int relation)
+static int davinci_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	int ret = 0;
-	unsigned int idx;
 	struct cpufreq_freqs freqs;
 	struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data;
 	struct clk *armclk = cpufreq.armclk;
 
 	freqs.old = davinci_getspeed(0);
-	freqs.new = clk_round_rate(armclk, target_freq * 1000) / 1000;
-
-	if (freqs.old == freqs.new)
-		return ret;
+	freqs.new = pdata->freq_table[idx].frequency;
 
 	dev_dbg(cpufreq.dev, "transition: %u --> %u\n", freqs.old, freqs.new);
 
-	ret = cpufreq_frequency_table_target(policy, pdata->freq_table,
-						freqs.new, relation, &idx);
-	if (ret)
-		return -EINVAL;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	/* if moving to higher frequency, up the voltage beforehand */
@@ -148,7 +138,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver davinci_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= davinci_verify_speed,
-	.target		= davinci_target,
+	.target_index	= davinci_target,
 	.get		= davinci_getspeed,
 	.init		= davinci_cpu_init,
 	.exit		= cpufreq_generic_exit,
diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c
index a60f7693c18e..238b16976be1 100644
--- a/drivers/cpufreq/dbx500-cpufreq.c
+++ b/drivers/cpufreq/dbx500-cpufreq.c
@@ -20,23 +20,13 @@ static struct cpufreq_frequency_table *freq_table;
 static struct clk *armss_clk;
 
 static int dbx500_cpufreq_target(struct cpufreq_policy *policy,
-				unsigned int target_freq,
-				unsigned int relation)
+				unsigned int index)
 {
 	struct cpufreq_freqs freqs;
-	unsigned int idx;
 	int ret;
 
-	/* Lookup the next frequency */
-	if (cpufreq_frequency_table_target(policy, freq_table, target_freq,
-					relation, &idx))
-		return -EINVAL;
-
 	freqs.old = policy->cur;
-	freqs.new = freq_table[idx].frequency;
-
-	if (freqs.old == freqs.new)
-		return 0;
+	freqs.new = freq_table[index].frequency;
 
 	/* pre-change notification */
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
@@ -80,7 +70,7 @@ static int dbx500_cpufreq_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver dbx500_cpufreq_driver = {
 	.flags  = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS,
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = dbx500_cpufreq_target,
+	.target_index = dbx500_cpufreq_target,
 	.get    = dbx500_cpufreq_getspeed,
 	.init   = dbx500_cpufreq_init,
 	.name   = "DBX500",
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 2c11ce3c67bd..b39c4ef60a7a 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -168,12 +168,9 @@ postchange:
 	return err;
 }
 
-static int eps_target(struct cpufreq_policy *policy,
-			       unsigned int target_freq,
-			       unsigned int relation)
+static int eps_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct eps_cpu_data *centaur;
-	unsigned int newstate = 0;
 	unsigned int cpu = policy->cpu;
 	unsigned int dest_state;
 	int ret;
@@ -182,16 +179,8 @@ static int eps_target(struct cpufreq_policy *policy,
 		return -ENODEV;
 	centaur = eps_cpu[cpu];
 
-	if (unlikely(cpufreq_frequency_table_target(policy,
-			&eps_cpu[cpu]->freq_table[0],
-			target_freq,
-			relation,
-			&newstate))) {
-		return -EINVAL;
-	}
-
 	/* Make frequency transition */
-	dest_state = centaur->freq_table[newstate].driver_data & 0xffff;
+	dest_state = centaur->freq_table[index].driver_data & 0xffff;
 	ret = eps_set_state(centaur, policy, dest_state);
 	if (ret)
 		printk(KERN_ERR "eps: Timeout!\n");
@@ -418,7 +407,7 @@ static int eps_cpu_exit(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver eps_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= eps_target,
+	.target_index	= eps_target,
 	.init		= eps_cpu_init,
 	.exit		= eps_cpu_exit,
 	.get		= eps_get,
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index d91a645a27ae..4ab41539514f 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -105,20 +105,8 @@ static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu)
 }
 
 
-/**
- *	elanfreq_set_cpu_frequency: Change the CPU core frequency
- *	@cpu: cpu number
- *	@freq: frequency in kHz
- *
- *	This function takes a frequency value and changes the CPU frequency
- *	according to this. Note that the frequency has to be checked by
- *	elanfreq_validatespeed() for correctness!
- *
- *	There is no return value.
- */
-
-static void elanfreq_set_cpu_state(struct cpufreq_policy *policy,
-		unsigned int state)
+static int elanfreq_target(struct cpufreq_policy *policy,
+			    unsigned int state)
 {
 	struct cpufreq_freqs    freqs;
 
@@ -162,25 +150,9 @@ static void elanfreq_set_cpu_state(struct cpufreq_policy *policy,
 	local_irq_enable();
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-};
-
-
-static int elanfreq_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
-{
-	unsigned int newstate = 0;
-
-	if (cpufreq_frequency_table_target(policy, &elanfreq_table[0],
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
-	elanfreq_set_cpu_state(policy, newstate);
 
 	return 0;
 }
-
-
 /*
  *	Module init and exit code
  */
@@ -237,7 +209,7 @@ __setup("elanfreq=", elanfreq_setup);
 static struct cpufreq_driver elanfreq_driver = {
 	.get		= elanfreq_get_cpu_frequency,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= elanfreq_target,
+	.target_index	= elanfreq_target,
 	.init		= elanfreq_cpu_init,
 	.exit		= cpufreq_generic_exit,
 	.name		= "elanfreq",
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 3e4af676f43d..9982fcb82257 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -65,9 +65,6 @@ static int exynos_cpufreq_scale(unsigned int target_freq)
 	freqs.old = policy->cur;
 	freqs.new = target_freq;
 
-	if (freqs.new == freqs.old)
-		goto out;
-
 	/*
 	 * The policy max have been changed so that we cannot get proper
 	 * old_index with cpufreq_frequency_table_target(). Thus, ignore
@@ -151,13 +148,9 @@ out:
 	return ret;
 }
 
-static int exynos_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int exynos_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct cpufreq_frequency_table *freq_table = exynos_info->freq_table;
-	unsigned int index;
-	unsigned int new_freq;
 	int ret = 0;
 
 	mutex_lock(&cpufreq_lock);
@@ -165,15 +158,7 @@ static int exynos_target(struct cpufreq_policy *policy,
 	if (frequency_locked)
 		goto out;
 
-	if (cpufreq_frequency_table_target(policy, freq_table,
-					   target_freq, relation, &index)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	new_freq = freq_table[index].frequency;
-
-	ret = exynos_cpufreq_scale(new_freq);
+	ret = exynos_cpufreq_scale(freq_table[index].frequency);
 
 out:
 	mutex_unlock(&cpufreq_lock);
@@ -247,7 +232,7 @@ static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver exynos_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= exynos_target,
+	.target_index	= exynos_target,
 	.get		= exynos_getspeed,
 	.init		= exynos_cpufreq_cpu_init,
 	.exit		= cpufreq_generic_exit,
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 8ae5e2925bf1..1bf9b060d522 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -214,27 +214,17 @@ static unsigned int exynos_getspeed(unsigned int cpu)
 	return dvfs_info->cur_frequency;
 }
 
-static int exynos_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int exynos_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int index, tmp;
-	int ret = 0, i;
+	unsigned int tmp;
+	int i;
 	struct cpufreq_frequency_table *freq_table = dvfs_info->freq_table;
 
 	mutex_lock(&cpufreq_lock);
 
-	ret = cpufreq_frequency_table_target(policy, freq_table,
-					   target_freq, relation, &index);
-	if (ret)
-		goto out;
-
 	freqs.old = dvfs_info->cur_frequency;
 	freqs.new = freq_table[index].frequency;
 
-	if (freqs.old == freqs.new)
-		goto out;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	/* Set the target frequency in all C0_3_PSTATE register */
@@ -245,9 +235,8 @@ static int exynos_target(struct cpufreq_policy *policy,
 
 		__raw_writel(tmp, dvfs_info->base + XMU_C0_3_PSTATE + i * 4);
 	}
-out:
 	mutex_unlock(&cpufreq_lock);
-	return ret;
+	return 0;
 }
 
 static void exynos_cpufreq_work(struct work_struct *work)
@@ -325,7 +314,7 @@ static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver exynos_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= exynos_target,
+	.target_index	= exynos_target,
 	.get		= exynos_getspeed,
 	.init		= exynos_cpufreq_cpu_init,
 	.exit		= cpufreq_generic_exit,
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 90c6598415fd..4695fa22406a 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -227,26 +227,11 @@ acpi_cpufreq_get (
 static int
 acpi_cpufreq_target (
 	struct cpufreq_policy   *policy,
-	unsigned int target_freq,
-	unsigned int relation)
+	unsigned int index)
 {
-	struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu];
-	unsigned int next_state = 0;
-	unsigned int result = 0;
-
-	pr_debug("acpi_cpufreq_setpolicy\n");
-
-	result = cpufreq_frequency_table_target(policy,
-			data->freq_table, target_freq, relation, &next_state);
-	if (result)
-		return (result);
-
-	result = processor_set_freq(data, policy, next_state);
-
-	return (result);
+	return processor_set_freq(acpi_io_data[policy->cpu], policy, index);
 }
 
-
 static int
 acpi_cpufreq_cpu_init (
 	struct cpufreq_policy   *policy)
@@ -379,7 +364,7 @@ acpi_cpufreq_cpu_exit (
 
 static struct cpufreq_driver acpi_cpufreq_driver = {
 	.verify 	= cpufreq_generic_frequency_table_verify,
-	.target 	= acpi_cpufreq_target,
+	.target_index	= acpi_cpufreq_target,
 	.get 		= acpi_cpufreq_get,
 	.init		= acpi_cpufreq_cpu_init,
 	.exit		= acpi_cpufreq_cpu_exit,
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index be23892282e3..07af3b0de069 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -40,30 +40,17 @@ static unsigned int imx6q_get_speed(unsigned int cpu)
 	return clk_get_rate(arm_clk) / 1000;
 }
 
-static int imx6q_set_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq, unsigned int relation)
+static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct cpufreq_freqs freqs;
 	struct dev_pm_opp *opp;
 	unsigned long freq_hz, volt, volt_old;
-	unsigned int index;
 	int ret;
 
-	ret = cpufreq_frequency_table_target(policy, freq_table, target_freq,
-					     relation, &index);
-	if (ret) {
-		dev_err(cpu_dev, "failed to match target frequency %d: %d\n",
-			target_freq, ret);
-		return ret;
-	}
-
 	freqs.new = freq_table[index].frequency;
 	freq_hz = freqs.new * 1000;
 	freqs.old = clk_get_rate(arm_clk) / 1000;
 
-	if (freqs.old == freqs.new)
-		return 0;
-
 	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
@@ -159,7 +146,7 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = imx6q_set_target,
+	.target_index = imx6q_set_target,
 	.get = imx6q_get_speed,
 	.init = imx6q_cpufreq_init,
 	.exit = cpufreq_generic_exit,
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index fff8653c8e9b..0ae4dd7e1f2d 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -55,8 +55,8 @@ static unsigned int kirkwood_cpufreq_get_cpu_frequency(unsigned int cpu)
 	return kirkwood_freq_table[0].frequency;
 }
 
-static void kirkwood_cpufreq_set_cpu_state(struct cpufreq_policy *policy,
-		unsigned int index)
+static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
+			    unsigned int index)
 {
 	struct cpufreq_freqs freqs;
 	unsigned int state = kirkwood_freq_table[index].driver_data;
@@ -100,19 +100,6 @@ static void kirkwood_cpufreq_set_cpu_state(struct cpufreq_policy *policy,
 		local_irq_enable();
 	}
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-};
-
-static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
-{
-	unsigned int index = 0;
-
-	if (cpufreq_frequency_table_target(policy, kirkwood_freq_table,
-				target_freq, relation, &index))
-		return -EINVAL;
-
-	kirkwood_cpufreq_set_cpu_state(policy, index);
 
 	return 0;
 }
@@ -126,7 +113,7 @@ static int kirkwood_cpufreq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver kirkwood_cpufreq_driver = {
 	.get	= kirkwood_cpufreq_get_cpu_frequency,
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= kirkwood_cpufreq_target,
+	.target_index = kirkwood_cpufreq_target,
 	.init	= kirkwood_cpufreq_cpu_init,
 	.exit	= cpufreq_generic_exit,
 	.name	= "kirkwood-cpufreq",
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 14df4974fb45..45bafddfd8ea 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -626,21 +626,12 @@ static void longhaul_setup_voltagescaling(void)
 
 
 static int longhaul_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq, unsigned int relation)
+			    unsigned int table_index)
 {
-	unsigned int table_index = 0;
 	unsigned int i;
 	unsigned int dir = 0;
 	u8 vid, current_vid;
 
-	if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq,
-				relation, &table_index))
-		return -EINVAL;
-
-	/* Don't set same frequency again */
-	if (longhaul_index == table_index)
-		return 0;
-
 	if (!can_scale_voltage)
 		longhaul_setstate(policy, table_index);
 	else {
@@ -919,7 +910,7 @@ static int longhaul_cpu_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver longhaul_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= longhaul_target,
+	.target_index = longhaul_target,
 	.get	= longhaul_get,
 	.init	= longhaul_cpu_init,
 	.exit	= cpufreq_generic_exit,
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index 2c8ec8e06449..41a8e2cdf940 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -53,11 +53,9 @@ static unsigned int loongson2_cpufreq_get(unsigned int cpu)
  * Here we notify other drivers of the proposed change and the final change.
  */
 static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
-				     unsigned int target_freq,
-				     unsigned int relation)
+				     unsigned int index)
 {
 	unsigned int cpu = policy->cpu;
-	unsigned int newstate = 0;
 	cpumask_t cpus_allowed;
 	struct cpufreq_freqs freqs;
 	unsigned int freq;
@@ -65,26 +63,17 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
 	cpus_allowed = current->cpus_allowed;
 	set_cpus_allowed_ptr(current, cpumask_of(cpu));
 
-	if (cpufreq_frequency_table_target
-	    (policy, &loongson2_clockmod_table[0], target_freq, relation,
-	     &newstate))
-		return -EINVAL;
-
 	freq =
 	    ((cpu_clock_freq / 1000) *
-	     loongson2_clockmod_table[newstate].driver_data) / 8;
-	if (freq < policy->min || freq > policy->max)
-		return -EINVAL;
+	     loongson2_clockmod_table[index].driver_data) / 8;
 
-	pr_debug("cpufreq: requested frequency %u Hz\n", target_freq * 1000);
+	pr_debug("cpufreq: requested frequency %u Hz\n",
+			loongson2_clockmod_table[index].frequency * 1000);
 
 	freqs.old = loongson2_cpufreq_get(cpu);
 	freqs.new = freq;
 	freqs.flags = 0;
 
-	if (freqs.new == freqs.old)
-		return 0;
-
 	/* notifiers */
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
@@ -145,7 +134,7 @@ static struct cpufreq_driver loongson2_cpufreq_driver = {
 	.name = "loongson2",
 	.init = loongson2_cpufreq_cpu_init,
 	.verify = cpufreq_generic_frequency_table_verify,
-	.target = loongson2_cpufreq_target,
+	.target_index = loongson2_cpufreq_target,
 	.get = loongson2_cpufreq_get,
 	.exit = loongson2_cpufreq_exit,
 	.attr = cpufreq_generic_attr,
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index eb1e1766baed..4e2da0874bfb 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -131,26 +131,18 @@ static int maple_scom_query_freq(void)
  */
 
 static int maple_cpufreq_target(struct cpufreq_policy *policy,
-	unsigned int target_freq, unsigned int relation)
+	unsigned int index)
 {
-	unsigned int newstate = 0;
 	struct cpufreq_freqs freqs;
 	int rc;
 
-	if (cpufreq_frequency_table_target(policy, maple_cpu_freqs,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	if (maple_pmode_cur == newstate)
-		return 0;
-
 	mutex_lock(&maple_switch_mutex);
 
 	freqs.old = maple_cpu_freqs[maple_pmode_cur].frequency;
-	freqs.new = maple_cpu_freqs[newstate].frequency;
+	freqs.new = maple_cpu_freqs[index].frequency;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	rc = maple_scom_switch_freq(newstate);
+	rc = maple_scom_switch_freq(index);
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
 	mutex_unlock(&maple_switch_mutex);
@@ -173,7 +165,7 @@ static struct cpufreq_driver maple_cpufreq_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= maple_cpufreq_cpu_init,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= maple_cpufreq_target,
+	.target_index	= maple_cpufreq_target,
 	.get		= maple_cpufreq_get_speed,
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index ac552d090463..b5512712298f 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -51,40 +51,15 @@ static unsigned int omap_getspeed(unsigned int cpu)
 	return rate;
 }
 
-static int omap_target(struct cpufreq_policy *policy,
-		       unsigned int target_freq,
-		       unsigned int relation)
+static int omap_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int i;
 	int r, ret = 0;
 	struct cpufreq_freqs freqs;
 	struct dev_pm_opp *opp;
 	unsigned long freq, volt = 0, volt_old = 0, tol = 0;
 
-	if (!freq_table) {
-		dev_err(mpu_dev, "%s: cpu%d: no freq table!\n", __func__,
-				policy->cpu);
-		return -EINVAL;
-	}
-
-	ret = cpufreq_frequency_table_target(policy, freq_table, target_freq,
-			relation, &i);
-	if (ret) {
-		dev_dbg(mpu_dev, "%s: cpu%d: no freq match for %d(ret=%d)\n",
-			__func__, policy->cpu, target_freq, ret);
-		return ret;
-	}
-	freqs.new = freq_table[i].frequency;
-	if (!freqs.new) {
-		dev_err(mpu_dev, "%s: cpu%d: no match for freq %d\n", __func__,
-			policy->cpu, target_freq);
-		return -EINVAL;
-	}
-
 	freqs.old = omap_getspeed(policy->cpu);
-
-	if (freqs.old == freqs.new && policy->cur == freqs.new)
-		return ret;
+	freqs.new = freq_table[index].frequency;
 
 	freq = freqs.new * 1000;
 	ret = clk_round_rate(mpu_clk, freq);
@@ -200,7 +175,7 @@ static int omap_cpu_exit(struct cpufreq_policy *policy)
 static struct cpufreq_driver omap_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= omap_target,
+	.target_index	= omap_target,
 	.get		= omap_getspeed,
 	.init		= omap_cpu_init,
 	.exit		= omap_cpu_exit,
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 6164c1cca504..3c23053afdfd 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -105,23 +105,13 @@ static struct cpufreq_frequency_table p4clockmod_table[] = {
 };
 
 
-static int cpufreq_p4_target(struct cpufreq_policy *policy,
-			     unsigned int target_freq,
-			     unsigned int relation)
+static int cpufreq_p4_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int    newstate = DC_RESV;
 	struct cpufreq_freqs freqs;
 	int i;
 
-	if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0],
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
 	freqs.old = cpufreq_p4_get(policy->cpu);
-	freqs.new = stock_freq * p4clockmod_table[newstate].driver_data / 8;
-
-	if (freqs.new == freqs.old)
-		return 0;
+	freqs.new = stock_freq * p4clockmod_table[index].driver_data / 8;
 
 	/* notifiers */
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
@@ -131,7 +121,7 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy,
 	 * Developer's Manual, Volume 3
 	 */
 	for_each_cpu(i, policy->cpus)
-		cpufreq_p4_setdc(i, p4clockmod_table[newstate].driver_data);
+		cpufreq_p4_setdc(i, p4clockmod_table[index].driver_data);
 
 	/* notifiers */
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
@@ -255,7 +245,7 @@ static unsigned int cpufreq_p4_get(unsigned int cpu)
 
 static struct cpufreq_driver p4clockmod_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= cpufreq_p4_target,
+	.target_index	= cpufreq_p4_target,
 	.init		= cpufreq_p4_cpu_init,
 	.exit		= cpufreq_generic_exit,
 	.get		= cpufreq_p4_get,
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 1cca332728c3..17424ddc7f67 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -240,19 +240,11 @@ static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 }
 
 static int pas_cpufreq_target(struct cpufreq_policy *policy,
-			      unsigned int target_freq,
-			      unsigned int relation)
+			      unsigned int pas_astate_new)
 {
 	struct cpufreq_freqs freqs;
-	int pas_astate_new;
 	int i;
 
-	cpufreq_frequency_table_target(policy,
-				       pas_freqs,
-				       target_freq,
-				       relation,
-				       &pas_astate_new);
-
 	freqs.old = policy->cur;
 	freqs.new = pas_freqs[pas_astate_new].frequency;
 
@@ -282,7 +274,7 @@ static struct cpufreq_driver pas_cpufreq_driver = {
 	.init		= pas_cpufreq_cpu_init,
 	.exit		= pas_cpufreq_cpu_exit,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= pas_cpufreq_target,
+	.target_index	= pas_cpufreq_target,
 	.attr		= cpufreq_generic_attr,
 };
 
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 6eac1e230078..05f705e1b7a2 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -374,17 +374,11 @@ static unsigned int pmac_cpufreq_get_speed(unsigned int cpu)
 }
 
 static int pmac_cpufreq_target(	struct cpufreq_policy *policy,
-					unsigned int target_freq,
-					unsigned int relation)
+					unsigned int index)
 {
-	unsigned int    newstate = 0;
 	int		rc;
 
-	if (cpufreq_frequency_table_target(policy, pmac_cpu_freqs,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	rc = do_set_cpu_speed(policy, newstate, 1);
+	rc = do_set_cpu_speed(policy, index, 1);
 
 	ppc_proc_freq = cur_freq * 1000ul;
 	return rc;
@@ -453,7 +447,7 @@ static int pmac_cpufreq_resume(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver pmac_cpufreq_driver = {
 	.verify 	= cpufreq_generic_frequency_table_verify,
-	.target 	= pmac_cpufreq_target,
+	.target_index	= pmac_cpufreq_target,
 	.get		= pmac_cpufreq_get_speed,
 	.init		= pmac_cpufreq_cpu_init,
 	.suspend	= pmac_cpufreq_suspend,
diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c
index 5261b92d768b..234b598ce416 100644
--- a/drivers/cpufreq/pmac64-cpufreq.c
+++ b/drivers/cpufreq/pmac64-cpufreq.c
@@ -312,27 +312,18 @@ static int g5_pfunc_query_freq(void)
  * Common interface to the cpufreq core
  */
 
-static int g5_cpufreq_target(struct cpufreq_policy *policy,
-	unsigned int target_freq, unsigned int relation)
+static int g5_cpufreq_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int newstate = 0;
 	struct cpufreq_freqs freqs;
 	int rc;
 
-	if (cpufreq_frequency_table_target(policy, g5_cpu_freqs,
-			target_freq, relation, &newstate))
-		return -EINVAL;
-
-	if (g5_pmode_cur == newstate)
-		return 0;
-
 	mutex_lock(&g5_switch_mutex);
 
 	freqs.old = g5_cpu_freqs[g5_pmode_cur].frequency;
-	freqs.new = g5_cpu_freqs[newstate].frequency;
+	freqs.new = g5_cpu_freqs[index].frequency;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	rc = g5_switch_freq(newstate);
+	rc = g5_switch_freq(index);
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
 	mutex_unlock(&g5_switch_mutex);
@@ -355,7 +346,7 @@ static struct cpufreq_driver g5_cpufreq_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.init		= g5_cpufreq_cpu_init,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= g5_cpufreq_target,
+	.target_index	= g5_cpufreq_target,
 	.get		= g5_cpufreq_get_speed,
 	.attr 		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index eda17024a34a..643e7952cad3 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -63,12 +63,12 @@ static int powernow_k6_get_cpu_multiplier(void)
 
 
 /**
- * powernow_k6_set_state - set the PowerNow! multiplier
+ * powernow_k6_target - set the PowerNow! multiplier
  * @best_i: clock_ratio[best_i] is the target multiplier
  *
  *   Tries to change the PowerNow! multiplier
  */
-static void powernow_k6_set_state(struct cpufreq_policy *policy,
+static int powernow_k6_target(struct cpufreq_policy *policy,
 		unsigned int best_i)
 {
 	unsigned long outvalue = 0, invalue = 0;
@@ -77,7 +77,7 @@ static void powernow_k6_set_state(struct cpufreq_policy *policy,
 
 	if (clock_ratio[best_i].driver_data > max_multiplier) {
 		printk(KERN_ERR PFX "invalid target frequency\n");
-		return;
+		return -EINVAL;
 	}
 
 	freqs.old = busfreq * powernow_k6_get_cpu_multiplier();
@@ -100,31 +100,6 @@ static void powernow_k6_set_state(struct cpufreq_policy *policy,
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
-	return;
-}
-
-
-/**
- * powernow_k6_setpolicy - sets a new CPUFreq policy
- * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- *  (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
- *
- * sets a new CPUFreq policy
- */
-static int powernow_k6_target(struct cpufreq_policy *policy,
-			       unsigned int target_freq,
-			       unsigned int relation)
-{
-	unsigned int newstate = 0;
-
-	if (cpufreq_frequency_table_target(policy, &clock_ratio[0],
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
-	powernow_k6_set_state(policy, newstate);
-
 	return 0;
 }
 
@@ -161,7 +136,7 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy)
 	unsigned int i;
 	for (i = 0; i < 8; i++) {
 		if (i == max_multiplier)
-			powernow_k6_set_state(policy, i);
+			powernow_k6_target(policy, i);
 	}
 	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
@@ -176,7 +151,7 @@ static unsigned int powernow_k6_get(unsigned int cpu)
 
 static struct cpufreq_driver powernow_k6_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= powernow_k6_target,
+	.target_index	= powernow_k6_target,
 	.init		= powernow_k6_cpu_init,
 	.exit		= powernow_k6_cpu_exit,
 	.get		= powernow_k6_get,
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 44d345bad6fb..946708a1d745 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -248,7 +248,7 @@ static void change_VID(int vid)
 }
 
 
-static void change_speed(struct cpufreq_policy *policy, unsigned int index)
+static int powernow_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	u8 fid, vid;
 	struct cpufreq_freqs freqs;
@@ -291,6 +291,8 @@ static void change_speed(struct cpufreq_policy *policy, unsigned int index)
 		local_irq_enable();
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
+
+	return 0;
 }
 
 
@@ -533,22 +535,6 @@ static int powernow_decode_bios(int maxfid, int startvid)
 }
 
 
-static int powernow_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
-{
-	unsigned int newstate;
-
-	if (cpufreq_frequency_table_target(policy, powernow_table, target_freq,
-				relation, &newstate))
-		return -EINVAL;
-
-	change_speed(policy, newstate);
-
-	return 0;
-}
-
-
 /*
  * We use the fact that the bus frequency is somehow
  * a multiple of 100000/3 khz, then we compute sgtc according
@@ -694,7 +680,7 @@ static int powernow_cpu_exit(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver powernow_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= powernow_target,
+	.target_index	= powernow_target,
 	.get		= powernow_get,
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
 	.bios_limit	= acpi_processor_get_bios_limit,
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 298beb742ebb..62a1ce47d3df 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -977,20 +977,17 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 
 struct powernowk8_target_arg {
 	struct cpufreq_policy		*pol;
-	unsigned			targfreq;
-	unsigned			relation;
+	unsigned			newstate;
 };
 
 static long powernowk8_target_fn(void *arg)
 {
 	struct powernowk8_target_arg *pta = arg;
 	struct cpufreq_policy *pol = pta->pol;
-	unsigned targfreq = pta->targfreq;
-	unsigned relation = pta->relation;
+	unsigned newstate = pta->newstate;
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 	u32 checkfid;
 	u32 checkvid;
-	unsigned int newstate;
 	int ret;
 
 	if (!data)
@@ -1004,8 +1001,9 @@ static long powernowk8_target_fn(void *arg)
 		return -EIO;
 	}
 
-	pr_debug("targ: cpu %d, %d kHz, min %d, max %d, relation %d\n",
-		pol->cpu, targfreq, pol->min, pol->max, relation);
+	pr_debug("targ: cpu %d, %d kHz, min %d, max %d\n",
+		pol->cpu, data->powernow_table[newstate].frequency, pol->min,
+		pol->max);
 
 	if (query_current_values_with_pending_wait(data))
 		return -EIO;
@@ -1021,10 +1019,6 @@ static long powernowk8_target_fn(void *arg)
 		       checkvid, data->currvid);
 	}
 
-	if (cpufreq_frequency_table_target(pol, data->powernow_table,
-				targfreq, relation, &newstate))
-		return -EIO;
-
 	mutex_lock(&fidvid_mutex);
 
 	powernow_k8_acpi_pst_values(data, newstate);
@@ -1044,11 +1038,9 @@ static long powernowk8_target_fn(void *arg)
 }
 
 /* Driver entry point to switch to the target frequency */
-static int powernowk8_target(struct cpufreq_policy *pol,
-		unsigned targfreq, unsigned relation)
+static int powernowk8_target(struct cpufreq_policy *pol, unsigned index)
 {
-	struct powernowk8_target_arg pta = { .pol = pol, .targfreq = targfreq,
-					     .relation = relation };
+	struct powernowk8_target_arg pta = { .pol = pol, .newstate = index };
 
 	return work_on_cpu(pol->cpu, powernowk8_target_fn, &pta);
 }
@@ -1213,7 +1205,7 @@ out:
 
 static struct cpufreq_driver cpufreq_amd64_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= powernowk8_target,
+	.target_index	= powernowk8_target,
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= powernowk8_cpu_init,
 	.exit		= powernowk8_cpu_exit,
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index a0f562ca292d..79d8e9c46b6d 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -251,27 +251,20 @@ static int __exit corenet_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 }
 
 static int corenet_cpufreq_target(struct cpufreq_policy *policy,
-		unsigned int target_freq, unsigned int relation)
+		unsigned int index)
 {
 	struct cpufreq_freqs freqs;
-	unsigned int new;
 	struct clk *parent;
 	int ret;
 	struct cpu_data *data = per_cpu(cpu_data, policy->cpu);
 
-	cpufreq_frequency_table_target(policy, data->table,
-			target_freq, relation, &new);
-
-	if (policy->cur == data->table[new].frequency)
-		return 0;
-
 	freqs.old = policy->cur;
-	freqs.new = data->table[new].frequency;
+	freqs.new = data->table[index].frequency;
 
 	mutex_lock(&cpufreq_lock);
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	parent = of_clk_get(data->parent, data->table[new].driver_data);
+	parent = of_clk_get(data->parent, data->table[index].driver_data);
 	ret = clk_set_parent(data->clk, parent);
 	if (ret)
 		freqs.new = freqs.old;
@@ -288,7 +281,7 @@ static struct cpufreq_driver ppc_corenet_cpufreq_driver = {
 	.init		= corenet_cpufreq_cpu_init,
 	.exit		= __exit_p(corenet_cpufreq_cpu_exit),
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= corenet_cpufreq_target,
+	.target_index	= corenet_cpufreq_target,
 	.get		= corenet_cpufreq_get_speed,
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index 38540d1f5939..52f707d5f458 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -129,18 +129,10 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 }
 
 static int cbe_cpufreq_target(struct cpufreq_policy *policy,
-			      unsigned int target_freq,
-			      unsigned int relation)
+			      unsigned int cbe_pmode_new)
 {
 	int rc;
 	struct cpufreq_freqs freqs;
-	unsigned int cbe_pmode_new;
-
-	cpufreq_frequency_table_target(policy,
-				       cbe_freqs,
-				       target_freq,
-				       relation,
-				       &cbe_pmode_new);
 
 	freqs.old = policy->cur;
 	freqs.new = cbe_freqs[cbe_pmode_new].frequency;
@@ -164,7 +156,7 @@ static int cbe_cpufreq_target(struct cpufreq_policy *policy,
 
 static struct cpufreq_driver cbe_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= cbe_cpufreq_target,
+	.target_index	= cbe_cpufreq_target,
 	.init		= cbe_cpufreq_cpu_init,
 	.exit		= cpufreq_generic_exit,
 	.name		= "cbe-cpufreq",
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index 29aca574317b..183bc13f13e5 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -267,14 +267,11 @@ static unsigned int pxa_cpufreq_get(unsigned int cpu)
 	return get_clk_frequency_khz(0);
 }
 
-static int pxa_set_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int pxa_set_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	struct cpufreq_frequency_table *pxa_freqs_table;
 	pxa_freqs_t *pxa_freq_settings;
 	struct cpufreq_freqs freqs;
-	unsigned int idx;
 	unsigned long flags;
 	unsigned int new_freq_cpu, new_freq_mem;
 	unsigned int unused, preset_mdrefr, postset_mdrefr, cclkcfg;
@@ -283,12 +280,6 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	/* Get the current policy */
 	find_freq_tables(&pxa_freqs_table, &pxa_freq_settings);
 
-	/* Lookup the next frequency */
-	if (cpufreq_frequency_table_target(policy, pxa_freqs_table,
-					   target_freq, relation, &idx)) {
-		return -EINVAL;
-	}
-
 	new_freq_cpu = pxa_freq_settings[idx].khz;
 	new_freq_mem = pxa_freq_settings[idx].membus;
 	freqs.old = policy->cur;
@@ -448,7 +439,7 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver pxa_cpufreq_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= pxa_set_target,
+	.target_index = pxa_set_target,
 	.init	= pxa_cpufreq_init,
 	.exit	= cpufreq_generic_exit,
 	.get	= pxa_cpufreq_get,
diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c
index 47fbee49d6e5..132e37d578c2 100644
--- a/drivers/cpufreq/pxa3xx-cpufreq.c
+++ b/drivers/cpufreq/pxa3xx-cpufreq.c
@@ -155,24 +155,16 @@ static unsigned int pxa3xx_cpufreq_get(unsigned int cpu)
 	return pxa3xx_get_clk_frequency_khz(0);
 }
 
-static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy,
-			      unsigned int target_freq,
-			      unsigned int relation)
+static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct pxa3xx_freq_info *next;
 	struct cpufreq_freqs freqs;
 	unsigned long flags;
-	int idx;
 
 	if (policy->cpu != 0)
 		return -EINVAL;
 
-	/* Lookup the next frequency */
-	if (cpufreq_frequency_table_target(policy, pxa3xx_freqs_table,
-				target_freq, relation, &idx))
-		return -EINVAL;
-
-	next = &pxa3xx_freqs[idx];
+	next = &pxa3xx_freqs[index];
 
 	freqs.old = policy->cur;
 	freqs.new = next->cpufreq_mhz * 1000;
@@ -181,9 +173,6 @@ static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy,
 			freqs.old / 1000, freqs.new / 1000,
 			(freqs.old == freqs.new) ? " (skipped)" : "");
 
-	if (freqs.old == target_freq)
-		return 0;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	local_irq_save(flags);
@@ -225,7 +214,7 @@ static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver pxa3xx_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= pxa3xx_cpufreq_set,
+	.target_index	= pxa3xx_cpufreq_set,
 	.init		= pxa3xx_cpufreq_init,
 	.exit		= cpufreq_generic_exit,
 	.get		= pxa3xx_cpufreq_get,
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index 26a35d137157..4188accd34ab 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -217,24 +217,15 @@ static int s3c2416_cpufreq_leave_dvs(struct s3c2416_data *s3c_freq, int idx)
 }
 
 static int s3c2416_cpufreq_set_target(struct cpufreq_policy *policy,
-				      unsigned int target_freq,
-				      unsigned int relation)
+				      unsigned int index)
 {
 	struct s3c2416_data *s3c_freq = &s3c2416_cpufreq;
 	struct cpufreq_freqs freqs;
 	int idx, ret, to_dvs = 0;
-	unsigned int i;
 
 	mutex_lock(&cpufreq_lock);
 
-	pr_debug("cpufreq: to %dKHz, relation %d\n", target_freq, relation);
-
-	ret = cpufreq_frequency_table_target(policy, s3c_freq->freq_table,
-					     target_freq, relation, &i);
-	if (ret != 0)
-		goto out;
-
-	idx = s3c_freq->freq_table[i].driver_data;
+	idx = s3c_freq->freq_table[index].driver_data;
 
 	if (idx == SOURCE_HCLK)
 		to_dvs = 1;
@@ -256,7 +247,7 @@ static int s3c2416_cpufreq_set_target(struct cpufreq_policy *policy,
 	 */
 	freqs.new = (s3c_freq->is_dvs && !to_dvs)
 				? clk_get_rate(s3c_freq->hclk) / 1000
-				: s3c_freq->freq_table[i].frequency;
+				: s3c_freq->freq_table[index].frequency;
 
 	pr_debug("cpufreq: Transition %d-%dkHz\n", freqs.old, freqs.new);
 
@@ -505,7 +496,7 @@ err_hclk:
 static struct cpufreq_driver s3c2416_cpufreq_driver = {
 	.flags          = 0,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= s3c2416_cpufreq_set_target,
+	.target_index	= s3c2416_cpufreq_set_target,
 	.get		= s3c2416_cpufreq_get_speed,
 	.init		= s3c2416_cpufreq_driver_init,
 	.name		= "s3c2416",
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index 461617332033..8bdcf32a4418 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -63,26 +63,16 @@ static unsigned int s3c64xx_cpufreq_get_speed(unsigned int cpu)
 }
 
 static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy,
-				      unsigned int target_freq,
-				      unsigned int relation)
+				      unsigned int index)
 {
 	int ret;
-	unsigned int i;
 	struct cpufreq_freqs freqs;
 	struct s3c64xx_dvfs *dvfs;
 
-	ret = cpufreq_frequency_table_target(policy, s3c64xx_freq_table,
-					     target_freq, relation, &i);
-	if (ret != 0)
-		return ret;
-
 	freqs.old = clk_get_rate(armclk) / 1000;
-	freqs.new = s3c64xx_freq_table[i].frequency;
+	freqs.new = s3c64xx_freq_table[index].frequency;
 	freqs.flags = 0;
-	dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[i].driver_data];
-
-	if (freqs.old == freqs.new)
-		return 0;
+	dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data];
 
 	pr_debug("Transition %d-%dkHz\n", freqs.old, freqs.new);
 
@@ -254,7 +244,7 @@ static int s3c64xx_cpufreq_driver_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver s3c64xx_cpufreq_driver = {
 	.flags          = 0,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= s3c64xx_cpufreq_set_target,
+	.target_index	= s3c64xx_cpufreq_set_target,
 	.get		= s3c64xx_cpufreq_get_speed,
 	.init		= s3c64xx_cpufreq_driver_init,
 	.name		= "s3c",
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 600b4f472e28..5978b94e0340 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -36,16 +36,7 @@ static DEFINE_MUTEX(set_freq_lock);
 /* Use 800MHz when entering sleep mode */
 #define SLEEP_FREQ	(800 * 1000)
 
-/*
- * relation has an additional symantics other than the standard of cpufreq
- * DISALBE_FURTHER_CPUFREQ: disable further access to target
- * ENABLE_FURTUER_CPUFREQ: enable access to target
- */
-enum cpufreq_access {
-	DISABLE_FURTHER_CPUFREQ = 0x10,
-	ENABLE_FURTHER_CPUFREQ = 0x20,
-};
-
+/* Tracks if cpu freqency can be updated anymore */
 static bool no_cpufreq_access;
 
 /*
@@ -182,12 +173,10 @@ static unsigned int s5pv210_getspeed(unsigned int cpu)
 	return clk_get_rate(cpu_clk) / 1000;
 }
 
-static int s5pv210_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned long reg;
-	unsigned int index, priv_index;
+	unsigned int priv_index;
 	unsigned int pll_changing = 0;
 	unsigned int bus_speed_changing = 0;
 	int arm_volt, int_volt;
@@ -195,9 +184,6 @@ static int s5pv210_target(struct cpufreq_policy *policy,
 
 	mutex_lock(&set_freq_lock);
 
-	if (relation & ENABLE_FURTHER_CPUFREQ)
-		no_cpufreq_access = false;
-
 	if (no_cpufreq_access) {
 #ifdef CONFIG_PM_VERBOSE
 		pr_err("%s:%d denied access to %s as it is disabled"
@@ -207,27 +193,13 @@ static int s5pv210_target(struct cpufreq_policy *policy,
 		goto exit;
 	}
 
-	if (relation & DISABLE_FURTHER_CPUFREQ)
-		no_cpufreq_access = true;
-
-	relation &= ~(ENABLE_FURTHER_CPUFREQ | DISABLE_FURTHER_CPUFREQ);
-
 	freqs.old = s5pv210_getspeed(0);
-
-	if (cpufreq_frequency_table_target(policy, s5pv210_freq_table,
-					   target_freq, relation, &index)) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
 	freqs.new = s5pv210_freq_table[index].frequency;
 
-	if (freqs.new == freqs.old)
-		goto exit;
-
 	/* Finding current running level index */
 	if (cpufreq_frequency_table_target(policy, s5pv210_freq_table,
-					   freqs.old, relation, &priv_index)) {
+					   freqs.old, CPUFREQ_RELATION_H,
+					   &priv_index)) {
 		ret = -EINVAL;
 		goto exit;
 	}
@@ -559,16 +531,18 @@ static int s5pv210_cpufreq_notifier_event(struct notifier_block *this,
 
 	switch (event) {
 	case PM_SUSPEND_PREPARE:
-		ret = cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ,
-					    DISABLE_FURTHER_CPUFREQ);
+		ret = cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ, 0);
 		if (ret < 0)
 			return NOTIFY_BAD;
 
+		/* Disable updation of cpu frequency */
+		no_cpufreq_access = true;
 		return NOTIFY_OK;
 	case PM_POST_RESTORE:
 	case PM_POST_SUSPEND:
-		cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ,
-				      ENABLE_FURTHER_CPUFREQ);
+		/* Enable updation of cpu frequency */
+		no_cpufreq_access = false;
+		cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ, 0);
 
 		return NOTIFY_OK;
 	}
@@ -581,18 +555,18 @@ static int s5pv210_cpufreq_reboot_notifier_event(struct notifier_block *this,
 {
 	int ret;
 
-	ret = cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ,
-				    DISABLE_FURTHER_CPUFREQ);
+	ret = cpufreq_driver_target(cpufreq_cpu_get(0), SLEEP_FREQ, 0);
 	if (ret < 0)
 		return NOTIFY_BAD;
 
+	no_cpufreq_access = true;
 	return NOTIFY_DONE;
 }
 
 static struct cpufreq_driver s5pv210_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= s5pv210_target,
+	.target_index	= s5pv210_target,
 	.get		= s5pv210_getspeed,
 	.init		= s5pv210_cpu_init,
 	.name		= "s5pv210",
diff --git a/drivers/cpufreq/sa1100-cpufreq.c b/drivers/cpufreq/sa1100-cpufreq.c
index b282cea47e62..b0da1fe40b1d 100644
--- a/drivers/cpufreq/sa1100-cpufreq.c
+++ b/drivers/cpufreq/sa1100-cpufreq.c
@@ -177,36 +177,20 @@ static void sa1100_update_dram_timings(int current_speed, int new_speed)
 	}
 }
 
-static int sa1100_target(struct cpufreq_policy *policy,
-			 unsigned int target_freq,
-			 unsigned int relation)
+static int sa1100_target(struct cpufreq_policy *policy, unsigned int ppcr)
 {
 	unsigned int cur = sa11x0_getspeed(0);
-	unsigned int new_ppcr;
 	struct cpufreq_freqs freqs;
 
-	new_ppcr = sa11x0_freq_to_ppcr(target_freq);
-	switch (relation) {
-	case CPUFREQ_RELATION_L:
-		if (sa11x0_ppcr_to_freq(new_ppcr) > policy->max)
-			new_ppcr--;
-		break;
-	case CPUFREQ_RELATION_H:
-		if ((sa11x0_ppcr_to_freq(new_ppcr) > target_freq) &&
-		    (sa11x0_ppcr_to_freq(new_ppcr - 1) >= policy->min))
-			new_ppcr--;
-		break;
-	}
-
 	freqs.old = cur;
-	freqs.new = sa11x0_ppcr_to_freq(new_ppcr);
+	freqs.new = sa11x0_freq_table[ppcr].frequency;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
 	if (freqs.new > cur)
 		sa1100_update_dram_timings(cur, freqs.new);
 
-	PPCR = new_ppcr;
+	PPCR = ppcr;
 
 	if (freqs.new < cur)
 		sa1100_update_dram_timings(cur, freqs.new);
@@ -224,7 +208,7 @@ static int __init sa1100_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver sa1100_driver __refdata = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= sa1100_target,
+	.target_index	= sa1100_target,
 	.get		= sa11x0_getspeed,
 	.init		= sa1100_cpu_init,
 	.name		= "sa1100",
diff --git a/drivers/cpufreq/sa1110-cpufreq.c b/drivers/cpufreq/sa1110-cpufreq.c
index bca04c0b4a73..55b1818c3e49 100644
--- a/drivers/cpufreq/sa1110-cpufreq.c
+++ b/drivers/cpufreq/sa1110-cpufreq.c
@@ -229,34 +229,16 @@ sdram_update_refresh(u_int cpu_khz, struct sdram_params *sdram)
 /*
  * Ok, set the CPU frequency.
  */
-static int sa1110_target(struct cpufreq_policy *policy,
-			 unsigned int target_freq,
-			 unsigned int relation)
+static int sa1110_target(struct cpufreq_policy *policy, unsigned int ppcr)
 {
 	struct sdram_params *sdram = &sdram_params;
 	struct cpufreq_freqs freqs;
 	struct sdram_info sd;
 	unsigned long flags;
-	unsigned int ppcr, unused;
-
-	switch (relation) {
-	case CPUFREQ_RELATION_L:
-		ppcr = sa11x0_freq_to_ppcr(target_freq);
-		if (sa11x0_ppcr_to_freq(ppcr) > policy->max)
-			ppcr--;
-		break;
-	case CPUFREQ_RELATION_H:
-		ppcr = sa11x0_freq_to_ppcr(target_freq);
-		if (ppcr && (sa11x0_ppcr_to_freq(ppcr) > target_freq) &&
-		    (sa11x0_ppcr_to_freq(ppcr-1) >= policy->min))
-			ppcr--;
-		break;
-	default:
-		return -EINVAL;
-	}
+	unsigned int unused;
 
 	freqs.old = sa11x0_getspeed(0);
-	freqs.new = sa11x0_ppcr_to_freq(ppcr);
+	freqs.new = sa11x0_freq_table[ppcr].frequency;
 
 	sdram_calculate_timing(&sd, freqs.new, sdram);
 
@@ -340,7 +322,7 @@ static int __init sa1110_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver sa1110_driver __refdata = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= sa1110_target,
+	.target_index	= sa1110_target,
 	.get		= sa11x0_getspeed,
 	.init		= sa1110_cpu_init,
 	.name		= "sa1110",
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 9047ab1ca014..6c86452e1737 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -53,8 +53,7 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
 	}
 }
 
-static void sc520_freq_set_cpu_state(struct cpufreq_policy *policy,
-		unsigned int state)
+static int sc520_freq_target(struct cpufreq_policy *policy, unsigned int state)
 {
 
 	struct cpufreq_freqs	freqs;
@@ -76,24 +75,10 @@ static void sc520_freq_set_cpu_state(struct cpufreq_policy *policy,
 	local_irq_enable();
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
-};
-
-static int sc520_freq_target(struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
-{
-	unsigned int newstate = 0;
-
-	if (cpufreq_frequency_table_target(policy, sc520_freq_table,
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
-	sc520_freq_set_cpu_state(policy, newstate);
 
 	return 0;
 }
 
-
 /*
  *	Module init and exit code
  */
@@ -117,7 +102,7 @@ static int sc520_freq_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver sc520_freq_driver = {
 	.get	= sc520_freq_get_cpu_frequency,
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= sc520_freq_target,
+	.target_index = sc520_freq_target,
 	.init	= sc520_freq_cpu_init,
 	.exit	= cpufreq_generic_exit,
 	.name	= "sc520_freq",
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index 291688c1da9a..3bf5b8f03661 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -245,8 +245,7 @@ static unsigned int us2e_freq_get(unsigned int cpu)
 	return clock_tick / estar_to_divisor(estar);
 }
 
-static void us2e_set_cpu_divider_index(struct cpufreq_policy *policy,
-		unsigned int index)
+static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned int cpu = policy->cpu;
 	unsigned long new_bits, new_freq;
@@ -277,20 +276,6 @@ static void us2e_set_cpu_divider_index(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
 	set_cpus_allowed_ptr(current, &cpus_allowed);
-}
-
-static int us2e_freq_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
-{
-	unsigned int new_index = 0;
-
-	if (cpufreq_frequency_table_target(policy,
-					   &us2e_freq_table[policy->cpu].table[0],
-					   target_freq, relation, &new_index))
-		return -EINVAL;
-
-	us2e_set_cpu_divider_index(policy, new_index);
 
 	return 0;
 }
@@ -325,7 +310,7 @@ static int us2e_freq_cpu_exit(struct cpufreq_policy *policy)
 {
 	if (cpufreq_us2e_driver) {
 		cpufreq_frequency_table_put_attr(policy->cpu);
-		us2e_set_cpu_divider_index(policy, 0);
+		us2e_freq_target(policy, 0);
 	}
 
 	return 0;
@@ -358,7 +343,7 @@ static int __init us2e_freq_init(void)
 
 		driver->init = us2e_freq_cpu_init;
 		driver->verify = cpufreq_generic_frequency_table_verify;
-		driver->target = us2e_freq_target;
+		driver->target_index = us2e_freq_target;
 		driver->get = us2e_freq_get;
 		driver->exit = us2e_freq_cpu_exit;
 		strcpy(driver->name, "UltraSPARC-IIe");
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index 9b3dbd31362e..2e54d55915df 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -93,8 +93,7 @@ static unsigned int us3_freq_get(unsigned int cpu)
 	return ret;
 }
 
-static void us3_set_cpu_divider_index(struct cpufreq_policy *policy,
-		unsigned int index)
+static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned int cpu = policy->cpu;
 	unsigned long new_bits, new_freq, reg;
@@ -136,22 +135,6 @@ static void us3_set_cpu_divider_index(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
 	set_cpus_allowed_ptr(current, &cpus_allowed);
-}
-
-static int us3_freq_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
-{
-	unsigned int new_index = 0;
-
-	if (cpufreq_frequency_table_target(policy,
-					   &us3_freq_table[policy->cpu].table[0],
-					   target_freq,
-					   relation,
-					   &new_index))
-		return -EINVAL;
-
-	us3_set_cpu_divider_index(policy, new_index);
 
 	return 0;
 }
@@ -182,7 +165,7 @@ static int us3_freq_cpu_exit(struct cpufreq_policy *policy)
 {
 	if (cpufreq_us3_driver) {
 		cpufreq_frequency_table_put_attr(policy->cpu);
-		us3_set_cpu_divider_index(policy, 0);
+		us3_freq_target(policy, 0);
 	}
 
 	return 0;
@@ -219,7 +202,7 @@ static int __init us3_freq_init(void)
 
 		driver->init = us3_freq_cpu_init;
 		driver->verify = cpufreq_generic_frequency_table_verify;
-		driver->target = us3_freq_target;
+		driver->target_index = us3_freq_target;
 		driver->get = us3_freq_get;
 		driver->exit = us3_freq_cpu_exit;
 		strcpy(driver->name, "UltraSPARC-III");
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
index 8841366a2068..11a65be3fd76 100644
--- a/drivers/cpufreq/spear-cpufreq.c
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -105,20 +105,16 @@ static int spear1340_set_cpu_rate(struct clk *sys_pclk, unsigned long newfreq)
 }
 
 static int spear_cpufreq_target(struct cpufreq_policy *policy,
-		unsigned int target_freq, unsigned int relation)
+		unsigned int index)
 {
 	struct cpufreq_freqs freqs;
 	long newfreq;
 	struct clk *srcclk;
-	int index, ret, mult = 1;
-
-	if (cpufreq_frequency_table_target(policy, spear_cpufreq.freq_tbl,
-				target_freq, relation, &index))
-		return -EINVAL;
+	int ret, mult = 1;
 
 	freqs.old = spear_cpufreq_get(0);
-
 	newfreq = spear_cpufreq.freq_tbl[index].frequency * 1000;
+
 	if (of_machine_is_compatible("st,spear1340")) {
 		/*
 		 * SPEAr1340 is special in the sense that due to the possibility
@@ -179,7 +175,7 @@ static struct cpufreq_driver spear_cpufreq_driver = {
 	.name		= "cpufreq-spear",
 	.flags		= CPUFREQ_STICKY,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= spear_cpufreq_target,
+	.target_index	= spear_cpufreq_target,
 	.get		= spear_cpufreq_get,
 	.init		= spear_cpufreq_init,
 	.exit		= cpufreq_generic_exit,
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 25e45f89acac..c51ec8c0e3a8 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -416,21 +416,17 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy)
 /**
  * centrino_setpolicy - set a new CPUFreq policy
  * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- *	(CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
+ * @index: index of target frequency
  *
  * Sets a new CPUFreq policy.
  */
-static int centrino_target (struct cpufreq_policy *policy,
-			    unsigned int target_freq,
-			    unsigned int relation)
+static int centrino_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int    newstate = 0;
 	unsigned int	msr, oldmsr = 0, h = 0, cpu = policy->cpu;
 	struct cpufreq_freqs	freqs;
 	int			retval = 0;
 	unsigned int		j, first_cpu, tmp;
+	struct cpufreq_frequency_table *op_points;
 	cpumask_var_t covered_cpus;
 
 	if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL)))
@@ -441,16 +437,8 @@ static int centrino_target (struct cpufreq_policy *policy,
 		goto out;
 	}
 
-	if (unlikely(cpufreq_frequency_table_target(policy,
-			per_cpu(centrino_model, cpu)->op_points,
-			target_freq,
-			relation,
-			&newstate))) {
-		retval = -EINVAL;
-		goto out;
-	}
-
 	first_cpu = 1;
+	op_points = &per_cpu(centrino_model, cpu)->op_points[index];
 	for_each_cpu(j, policy->cpus) {
 		int good_cpu;
 
@@ -474,7 +462,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 			break;
 		}
 
-		msr = per_cpu(centrino_model, cpu)->op_points[newstate].driver_data;
+		msr = op_points->driver_data;
 
 		if (first_cpu) {
 			rdmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, &oldmsr, &h);
@@ -489,7 +477,8 @@ static int centrino_target (struct cpufreq_policy *policy,
 			freqs.new = extract_clock(msr, cpu, 0);
 
 			pr_debug("target=%dkHz old=%d new=%d msr=%04x\n",
-				target_freq, freqs.old, freqs.new, msr);
+				op_points->frequency, freqs.old, freqs.new,
+				msr);
 
 			cpufreq_notify_transition(policy, &freqs,
 					CPUFREQ_PRECHANGE);
@@ -540,7 +529,7 @@ static struct cpufreq_driver centrino_driver = {
 	.init		= centrino_cpu_init,
 	.exit		= centrino_cpu_exit,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= centrino_target,
+	.target_index	= centrino_target,
 	.get		= get_cur_freq,
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 1a8b01bd0fec..707721ebb853 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -251,36 +251,24 @@ static unsigned int speedstep_get(unsigned int cpu)
 /**
  * speedstep_target - set a new CPUFreq policy
  * @policy: new policy
- * @target_freq: the target frequency
- * @relation: how that frequency relates to achieved frequency
- *	(CPUFREQ_RELATION_L or CPUFREQ_RELATION_H)
+ * @index: index of target frequency
  *
  * Sets a new CPUFreq policy.
  */
-static int speedstep_target(struct cpufreq_policy *policy,
-			     unsigned int target_freq,
-			     unsigned int relation)
+static int speedstep_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int newstate = 0, policy_cpu;
+	unsigned int policy_cpu;
 	struct cpufreq_freqs freqs;
 
-	if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0],
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
 	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 	freqs.old = speedstep_get(policy_cpu);
-	freqs.new = speedstep_freqs[newstate].frequency;
+	freqs.new = speedstep_freqs[index].frequency;
 
 	pr_debug("transiting from %u to %u kHz\n", freqs.old, freqs.new);
 
-	/* no transition necessary */
-	if (freqs.old == freqs.new)
-		return 0;
-
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
 
-	smp_call_function_single(policy_cpu, _speedstep_set_state, &newstate,
+	smp_call_function_single(policy_cpu, _speedstep_set_state, &index,
 				 true);
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
@@ -330,7 +318,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 static struct cpufreq_driver speedstep_driver = {
 	.name	= "speedstep-ich",
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.target	= speedstep_target,
+	.target_index = speedstep_target,
 	.init	= speedstep_cpu_init,
 	.exit	= cpufreq_generic_exit,
 	.get	= speedstep_get,
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index a02b649c9647..19446e479ccc 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -235,29 +235,19 @@ static void speedstep_set_state(unsigned int state)
 /**
  * speedstep_target - set a new CPUFreq policy
  * @policy: new policy
- * @target_freq: new freq
- * @relation:
+ * @index: index of new freq
  *
  * Sets a new CPUFreq policy/freq.
  */
-static int speedstep_target(struct cpufreq_policy *policy,
-			unsigned int target_freq, unsigned int relation)
+static int speedstep_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int newstate = 0;
 	struct cpufreq_freqs freqs;
 
-	if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0],
-				target_freq, relation, &newstate))
-		return -EINVAL;
-
 	freqs.old = speedstep_freqs[speedstep_get_state()].frequency;
-	freqs.new = speedstep_freqs[newstate].frequency;
-
-	if (freqs.old == freqs.new)
-		return 0;
+	freqs.new = speedstep_freqs[index].frequency;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	speedstep_set_state(newstate);
+	speedstep_set_state(index);
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
 
 	return 0;
@@ -327,7 +317,7 @@ static int speedstep_resume(struct cpufreq_policy *policy)
 static struct cpufreq_driver speedstep_driver = {
 	.name		= "speedstep-smi",
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= speedstep_target,
+	.target_index	= speedstep_target,
 	.init		= speedstep_cpu_init,
 	.exit		= cpufreq_generic_exit,
 	.get		= speedstep_get,
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c
index 32483ef63d53..bd7d89c013a5 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra-cpufreq.c
@@ -150,11 +150,8 @@ static unsigned long tegra_cpu_highest_speed(void)
 	return rate;
 }
 
-static int tegra_target(struct cpufreq_policy *policy,
-		       unsigned int target_freq,
-		       unsigned int relation)
+static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned int idx;
 	unsigned int freq;
 	int ret = 0;
 
@@ -165,10 +162,7 @@ static int tegra_target(struct cpufreq_policy *policy,
 		goto out;
 	}
 
-	cpufreq_frequency_table_target(policy, freq_table, target_freq,
-		relation, &idx);
-
-	freq = freq_table[idx].frequency;
+	freq = freq_table[index].frequency;
 
 	target_cpu_speed[policy->cpu] = freq;
 
@@ -238,7 +232,7 @@ static int tegra_cpu_exit(struct cpufreq_policy *policy)
 
 static struct cpufreq_driver tegra_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.target		= tegra_target,
+	.target_index	= tegra_target,
 	.get		= tegra_getspeed,
 	.init		= tegra_cpu_init,
 	.exit		= tegra_cpu_exit,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 0aba2a6cadaf..e8c77d330479 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -187,9 +187,11 @@ struct cpufreq_driver {
 
 	/* define one out of two */
 	int	(*setpolicy)	(struct cpufreq_policy *policy);
-	int	(*target)	(struct cpufreq_policy *policy,
+	int	(*target)	(struct cpufreq_policy *policy,	/* Deprecated */
 				 unsigned int target_freq,
 				 unsigned int relation);
+	int	(*target_index)	(struct cpufreq_policy *policy,
+				 unsigned int index);
 
 	/* should be defined, if possible */
 	unsigned int	(*get)	(unsigned int cpu);
-- 
cgit 


From ee08997fee16f10be23c9748d609dbdf3baab8e4 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Mon, 6 May 2013 15:40:01 +0300
Subject: crypto: provide single place for hash algo information

This patch provides a single place for information about hash algorithms,
such as hash sizes and kernel driver names, which will be used by IMA
and the public key code.

Changelog:
- Fix sparse and checkpatch warnings
- Move hash algo enums to uapi for userspace signing functions.

Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/Kconfig                 |  3 +++
 crypto/Makefile                |  1 +
 crypto/hash_info.c             | 56 ++++++++++++++++++++++++++++++++++++++++++
 include/crypto/hash_info.h     | 40 ++++++++++++++++++++++++++++++
 include/uapi/linux/hash_info.h | 37 ++++++++++++++++++++++++++++
 5 files changed, 137 insertions(+)
 create mode 100644 crypto/hash_info.c
 create mode 100644 include/crypto/hash_info.h
 create mode 100644 include/uapi/linux/hash_info.h

(limited to 'include')

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 69ce573f1224..ba061b091d9f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1386,6 +1386,9 @@ config CRYPTO_USER_API_SKCIPHER
 	  This option enables the user-spaces interface for symmetric
 	  key cipher algorithms.
 
+config CRYPTO_HASH_INFO
+	bool
+
 source "drivers/crypto/Kconfig"
 source crypto/asymmetric_keys/Kconfig
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 80019ba8da3a..b3a7e807e08b 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -104,3 +104,4 @@ obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 obj-$(CONFIG_XOR_BLOCKS) += xor.o
 obj-$(CONFIG_ASYNC_CORE) += async_tx/
 obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_HASH_INFO) += hash_info.o
diff --git a/crypto/hash_info.c b/crypto/hash_info.c
new file mode 100644
index 000000000000..3e7ff46f26e8
--- /dev/null
+++ b/crypto/hash_info.c
@@ -0,0 +1,56 @@
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <linux/export.h>
+#include <crypto/hash_info.h>
+
+const char *const hash_algo_name[HASH_ALGO__LAST] = {
+	[HASH_ALGO_MD4]		= "md4",
+	[HASH_ALGO_MD5]		= "md5",
+	[HASH_ALGO_SHA1]	= "sha1",
+	[HASH_ALGO_RIPE_MD_160]	= "rmd160",
+	[HASH_ALGO_SHA256]	= "sha256",
+	[HASH_ALGO_SHA384]	= "sha384",
+	[HASH_ALGO_SHA512]	= "sha512",
+	[HASH_ALGO_SHA224]	= "sha224",
+	[HASH_ALGO_RIPE_MD_128]	= "rmd128",
+	[HASH_ALGO_RIPE_MD_256]	= "rmd256",
+	[HASH_ALGO_RIPE_MD_320]	= "rmd320",
+	[HASH_ALGO_WP_256]	= "wp256",
+	[HASH_ALGO_WP_384]	= "wp384",
+	[HASH_ALGO_WP_512]	= "wp512",
+	[HASH_ALGO_TGR_128]	= "tgr128",
+	[HASH_ALGO_TGR_160]	= "tgr160",
+	[HASH_ALGO_TGR_192]	= "tgr192",
+};
+EXPORT_SYMBOL_GPL(hash_algo_name);
+
+const int hash_digest_size[HASH_ALGO__LAST] = {
+	[HASH_ALGO_MD4]		= MD5_DIGEST_SIZE,
+	[HASH_ALGO_MD5]		= MD5_DIGEST_SIZE,
+	[HASH_ALGO_SHA1]	= SHA1_DIGEST_SIZE,
+	[HASH_ALGO_RIPE_MD_160]	= RMD160_DIGEST_SIZE,
+	[HASH_ALGO_SHA256]	= SHA256_DIGEST_SIZE,
+	[HASH_ALGO_SHA384]	= SHA384_DIGEST_SIZE,
+	[HASH_ALGO_SHA512]	= SHA512_DIGEST_SIZE,
+	[HASH_ALGO_SHA224]	= SHA224_DIGEST_SIZE,
+	[HASH_ALGO_RIPE_MD_128]	= RMD128_DIGEST_SIZE,
+	[HASH_ALGO_RIPE_MD_256]	= RMD256_DIGEST_SIZE,
+	[HASH_ALGO_RIPE_MD_320]	= RMD320_DIGEST_SIZE,
+	[HASH_ALGO_WP_256]	= WP256_DIGEST_SIZE,
+	[HASH_ALGO_WP_384]	= WP384_DIGEST_SIZE,
+	[HASH_ALGO_WP_512]	= WP512_DIGEST_SIZE,
+	[HASH_ALGO_TGR_128]	= TGR128_DIGEST_SIZE,
+	[HASH_ALGO_TGR_160]	= TGR160_DIGEST_SIZE,
+	[HASH_ALGO_TGR_192]	= TGR192_DIGEST_SIZE,
+};
+EXPORT_SYMBOL_GPL(hash_digest_size);
diff --git a/include/crypto/hash_info.h b/include/crypto/hash_info.h
new file mode 100644
index 000000000000..e1e5a3e5dd1b
--- /dev/null
+++ b/include/crypto/hash_info.h
@@ -0,0 +1,40 @@
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _CRYPTO_HASH_INFO_H
+#define _CRYPTO_HASH_INFO_H
+
+#include <crypto/sha.h>
+#include <crypto/md5.h>
+
+#include <uapi/linux/hash_info.h>
+
+/* not defined in include/crypto/ */
+#define RMD128_DIGEST_SIZE      16
+#define RMD160_DIGEST_SIZE	20
+#define RMD256_DIGEST_SIZE      32
+#define RMD320_DIGEST_SIZE      40
+
+/* not defined in include/crypto/ */
+#define WP512_DIGEST_SIZE	64
+#define WP384_DIGEST_SIZE	48
+#define WP256_DIGEST_SIZE	32
+
+/* not defined in include/crypto/ */
+#define TGR128_DIGEST_SIZE 16
+#define TGR160_DIGEST_SIZE 20
+#define TGR192_DIGEST_SIZE 24
+
+extern const char *const hash_algo_name[HASH_ALGO__LAST];
+extern const int hash_digest_size[HASH_ALGO__LAST];
+
+#endif /* _CRYPTO_HASH_INFO_H */
diff --git a/include/uapi/linux/hash_info.h b/include/uapi/linux/hash_info.h
new file mode 100644
index 000000000000..ca18c45f8304
--- /dev/null
+++ b/include/uapi/linux/hash_info.h
@@ -0,0 +1,37 @@
+/*
+ * Hash Info: Hash algorithms information
+ *
+ * Copyright (c) 2013 Dmitry Kasatkin <d.kasatkin@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _UAPI_LINUX_HASH_INFO_H
+#define _UAPI_LINUX_HASH_INFO_H
+
+enum hash_algo {
+	HASH_ALGO_MD4,
+	HASH_ALGO_MD5,
+	HASH_ALGO_SHA1,
+	HASH_ALGO_RIPE_MD_160,
+	HASH_ALGO_SHA256,
+	HASH_ALGO_SHA384,
+	HASH_ALGO_SHA512,
+	HASH_ALGO_SHA224,
+	HASH_ALGO_RIPE_MD_128,
+	HASH_ALGO_RIPE_MD_256,
+	HASH_ALGO_RIPE_MD_320,
+	HASH_ALGO_WP_256,
+	HASH_ALGO_WP_384,
+	HASH_ALGO_WP_512,
+	HASH_ALGO_TGR_128,
+	HASH_ALGO_TGR_160,
+	HASH_ALGO_TGR_192,
+	HASH_ALGO__LAST
+};
+
+#endif /* _UAPI_LINUX_HASH_INFO_H */
-- 
cgit 


From 3fe78ca2fb1d61ea598e63fcbf38aec76b36b3a8 Mon Sep 17 00:00:00 2001
From: Dmitry Kasatkin <d.kasatkin@samsung.com>
Date: Mon, 6 May 2013 15:58:15 +0300
Subject: keys: change asymmetric keys to use common hash definitions

This patch makes use of the newly defined common hash algorithm info,
replacing, for example, PKEY_HASH with HASH_ALGO.

Changelog:
- Lindent fixes - Mimi

CC: David Howells <dhowells@redhat.com>
Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 crypto/asymmetric_keys/Kconfig            |  1 +
 crypto/asymmetric_keys/public_key.c       | 12 ------------
 crypto/asymmetric_keys/rsa.c              | 14 +++++++-------
 crypto/asymmetric_keys/x509_cert_parser.c | 12 ++++++------
 crypto/asymmetric_keys/x509_parser.h      |  2 ++
 crypto/asymmetric_keys/x509_public_key.c  |  9 ++++-----
 include/crypto/public_key.h               | 18 ++++--------------
 kernel/module_signing.c                   |  8 ++++----
 8 files changed, 28 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig
index 862b01fe6172..82e7d6b0c276 100644
--- a/crypto/asymmetric_keys/Kconfig
+++ b/crypto/asymmetric_keys/Kconfig
@@ -13,6 +13,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE
 	tristate "Asymmetric public-key crypto algorithm subtype"
 	select MPILIB
 	select PUBLIC_KEY_ALGO_RSA
+	select CRYPTO_HASH_INFO
 	help
 	  This option provides support for asymmetric public key type handling.
 	  If signature generation and/or verification are to be used,
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index 49ac8d848ed1..97eb001960b9 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -36,18 +36,6 @@ const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST] = {
 };
 EXPORT_SYMBOL_GPL(pkey_algo);
 
-const char *const pkey_hash_algo_name[PKEY_HASH__LAST] = {
-	[PKEY_HASH_MD4]		= "md4",
-	[PKEY_HASH_MD5]		= "md5",
-	[PKEY_HASH_SHA1]	= "sha1",
-	[PKEY_HASH_RIPE_MD_160]	= "rmd160",
-	[PKEY_HASH_SHA256]	= "sha256",
-	[PKEY_HASH_SHA384]	= "sha384",
-	[PKEY_HASH_SHA512]	= "sha512",
-	[PKEY_HASH_SHA224]	= "sha224",
-};
-EXPORT_SYMBOL_GPL(pkey_hash_algo_name);
-
 const char *const pkey_id_type_name[PKEY_ID_TYPE__LAST] = {
 	[PKEY_ID_PGP]		= "PGP",
 	[PKEY_ID_X509]		= "X509",
diff --git a/crypto/asymmetric_keys/rsa.c b/crypto/asymmetric_keys/rsa.c
index 4a6a0696f8a3..90a17f59ba28 100644
--- a/crypto/asymmetric_keys/rsa.c
+++ b/crypto/asymmetric_keys/rsa.c
@@ -73,13 +73,13 @@ static const struct {
 	size_t size;
 } RSA_ASN1_templates[PKEY_HASH__LAST] = {
 #define _(X) { RSA_digest_info_##X, sizeof(RSA_digest_info_##X) }
-	[PKEY_HASH_MD5]		= _(MD5),
-	[PKEY_HASH_SHA1]	= _(SHA1),
-	[PKEY_HASH_RIPE_MD_160]	= _(RIPE_MD_160),
-	[PKEY_HASH_SHA256]	= _(SHA256),
-	[PKEY_HASH_SHA384]	= _(SHA384),
-	[PKEY_HASH_SHA512]	= _(SHA512),
-	[PKEY_HASH_SHA224]	= _(SHA224),
+	[HASH_ALGO_MD5]		= _(MD5),
+	[HASH_ALGO_SHA1]	= _(SHA1),
+	[HASH_ALGO_RIPE_MD_160]	= _(RIPE_MD_160),
+	[HASH_ALGO_SHA256]	= _(SHA256),
+	[HASH_ALGO_SHA384]	= _(SHA384),
+	[HASH_ALGO_SHA512]	= _(SHA512),
+	[HASH_ALGO_SHA224]	= _(SHA224),
 #undef _
 };
 
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 144201ccba0c..29893162497c 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -154,32 +154,32 @@ int x509_note_pkey_algo(void *context, size_t hdrlen,
 		return -ENOPKG; /* Unsupported combination */
 
 	case OID_md4WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_MD5;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_MD5;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 
 	case OID_sha1WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_SHA1;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA1;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 
 	case OID_sha256WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_SHA256;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA256;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 
 	case OID_sha384WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_SHA384;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA384;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 
 	case OID_sha512WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_SHA512;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA512;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 
 	case OID_sha224WithRSAEncryption:
-		ctx->cert->sig.pkey_hash_algo = PKEY_HASH_SHA224;
+		ctx->cert->sig.pkey_hash_algo = HASH_ALGO_SHA224;
 		ctx->cert->sig.pkey_algo = PKEY_ALGO_RSA;
 		break;
 	}
diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index 87d9cc26f630..04c81bd0f3f2 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -21,6 +21,8 @@ struct x509_certificate {
 	char		*authority;		/* Authority key fingerprint as hex */
 	struct tm	valid_from;
 	struct tm	valid_to;
+	enum pkey_algo	pkey_algo : 8;		/* Public key algorithm */
+	enum hash_algo sig_hash_algo : 8;	/* Signature hash algorithm */
 	const void	*tbs;			/* Signed data */
 	unsigned	tbs_size;		/* Size of signed data */
 	unsigned	raw_sig_size;		/* Size of sigature */
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 6abc27f2e8a5..0a6bfad54916 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -96,7 +96,7 @@ int x509_get_sig_params(struct x509_certificate *cert)
 	/* Allocate the hashing algorithm we're going to need and find out how
 	 * big the hash operational data will be.
 	 */
-	tfm = crypto_alloc_shash(pkey_hash_algo_name[cert->sig.pkey_hash_algo], 0, 0);
+	tfm = crypto_alloc_shash(hash_algo_name[cert->sig.pkey_hash_algo], 0, 0);
 	if (IS_ERR(tfm))
 		return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm);
 
@@ -199,7 +199,7 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 	    cert->sig.pkey_hash_algo >= PKEY_HASH__LAST ||
 	    !pkey_algo[cert->pub->pkey_algo] ||
 	    !pkey_algo[cert->sig.pkey_algo] ||
-	    !pkey_hash_algo_name[cert->sig.pkey_hash_algo]) {
+	    !hash_algo_name[cert->sig.pkey_hash_algo]) {
 		ret = -ENOPKG;
 		goto error_free_cert;
 	}
@@ -213,9 +213,8 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		 cert->valid_to.tm_year + 1900, cert->valid_to.tm_mon + 1,
 		 cert->valid_to.tm_mday, cert->valid_to.tm_hour,
 		 cert->valid_to.tm_min,  cert->valid_to.tm_sec);
-	pr_devel("Cert Signature: %s + %s\n",
-		 pkey_algo_name[cert->sig.pkey_algo],
-		 pkey_hash_algo_name[cert->sig.pkey_hash_algo]);
+	pr_devel("Cert Signature: %s\n",
+		 hash_algo_name[cert->sig.pkey_hash_algo]);
 
 	if (!cert->fingerprint) {
 		pr_warn("Cert for '%s' must have a SubjKeyId extension\n",
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index b34fda4dcabf..fc09732613ad 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -15,6 +15,7 @@
 #define _LINUX_PUBLIC_KEY_H
 
 #include <linux/mpi.h>
+#include <crypto/hash_info.h>
 
 enum pkey_algo {
 	PKEY_ALGO_DSA,
@@ -25,19 +26,8 @@ enum pkey_algo {
 extern const char *const pkey_algo_name[PKEY_ALGO__LAST];
 extern const struct public_key_algorithm *pkey_algo[PKEY_ALGO__LAST];
 
-enum pkey_hash_algo {
-	PKEY_HASH_MD4,
-	PKEY_HASH_MD5,
-	PKEY_HASH_SHA1,
-	PKEY_HASH_RIPE_MD_160,
-	PKEY_HASH_SHA256,
-	PKEY_HASH_SHA384,
-	PKEY_HASH_SHA512,
-	PKEY_HASH_SHA224,
-	PKEY_HASH__LAST
-};
-
-extern const char *const pkey_hash_algo_name[PKEY_HASH__LAST];
+/* asymmetric key implementation supports only up to SHA224 */
+#define PKEY_HASH__LAST		(HASH_ALGO_SHA224 + 1)
 
 enum pkey_id_type {
 	PKEY_ID_PGP,		/* OpenPGP generated key ID */
@@ -91,7 +81,7 @@ struct public_key_signature {
 	u8 digest_size;			/* Number of bytes in digest */
 	u8 nr_mpi;			/* Occupancy of mpi[] */
 	enum pkey_algo pkey_algo : 8;
-	enum pkey_hash_algo pkey_hash_algo : 8;
+	enum hash_algo pkey_hash_algo : 8;
 	union {
 		MPI mpi[2];
 		struct {
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index 0b6b870dc5e4..be5b8fac4bd0 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -29,7 +29,7 @@
  */
 struct module_signature {
 	u8	algo;		/* Public-key crypto algorithm [enum pkey_algo] */
-	u8	hash;		/* Digest algorithm [enum pkey_hash_algo] */
+	u8	hash;		/* Digest algorithm [enum hash_algo] */
 	u8	id_type;	/* Key identifier type [enum pkey_id_type] */
 	u8	signer_len;	/* Length of signer's name */
 	u8	key_id_len;	/* Length of key identifier */
@@ -40,7 +40,7 @@ struct module_signature {
 /*
  * Digest the module contents.
  */
-static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
+static struct public_key_signature *mod_make_digest(enum hash_algo hash,
 						    const void *mod,
 						    unsigned long modlen)
 {
@@ -55,7 +55,7 @@ static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
 	/* Allocate the hashing algorithm we're going to need and find out how
 	 * big the hash operational data will be.
 	 */
-	tfm = crypto_alloc_shash(pkey_hash_algo_name[hash], 0, 0);
+	tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0);
 	if (IS_ERR(tfm))
 		return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm);
 
@@ -218,7 +218,7 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
 		return -ENOPKG;
 
 	if (ms.hash >= PKEY_HASH__LAST ||
-	    !pkey_hash_algo_name[ms.hash])
+	    !hash_algo_name[ms.hash])
 		return -ENOPKG;
 
 	key = request_asymmetric_key(sig, ms.signer_len,
-- 
cgit 


From ad7722dab7292dbc1c4586d701ac226b68122d39 Mon Sep 17 00:00:00 2001
From: viresh kumar <viresh.kumar@linaro.org>
Date: Fri, 18 Oct 2013 19:10:15 +0530
Subject: cpufreq: create per policy rwsem instead of per CPU cpu_policy_rwsem

We have per-CPU cpu_policy_rwsem for cpufreq core, but we never use
all of them. We always use rwsem of policy->cpu and so we can
actually make this rwsem per policy instead.

This patch does this change. With this change other tricky situations
are also avoided now, like which lock to take while we are changing
policy->cpu, etc.

Suggested-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 110 +++++++++++++---------------------------------
 include/linux/cpufreq.h   |  14 ++++++
 2 files changed, 45 insertions(+), 79 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 87ed83a6c894..6c9cbb9ebd1f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -52,47 +52,6 @@ static inline bool has_target(void)
 	return cpufreq_driver->target_index || cpufreq_driver->target;
 }
 
-/*
- * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
- * all cpufreq/hotplug/workqueue/etc related lock issues.
- *
- * The rules for this semaphore:
- * - Any routine that wants to read from the policy structure will
- *   do a down_read on this semaphore.
- * - Any routine that will write to the policy structure and/or may take away
- *   the policy altogether (eg. CPU hotplug), will hold this lock in write
- *   mode before doing so.
- *
- * Additional rules:
- * - Governor routines that can be called in cpufreq hotplug path should not
- *   take this sem as top level hotplug notifier handler takes this.
- * - Lock should not be held across
- *     __cpufreq_governor(data, CPUFREQ_GOV_STOP);
- */
-static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
-
-#define lock_policy_rwsem(mode, cpu)					\
-static void lock_policy_rwsem_##mode(int cpu)				\
-{									\
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
-	BUG_ON(!policy);						\
-	down_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
-}
-
-lock_policy_rwsem(read, cpu);
-lock_policy_rwsem(write, cpu);
-
-#define unlock_policy_rwsem(mode, cpu)					\
-static void unlock_policy_rwsem_##mode(int cpu)				\
-{									\
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);	\
-	BUG_ON(!policy);						\
-	up_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu));		\
-}
-
-unlock_policy_rwsem(read, cpu);
-unlock_policy_rwsem(write, cpu);
-
 /*
  * rwsem to guarantee that cpufreq driver module doesn't unload during critical
  * sections
@@ -688,14 +647,14 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return -EINVAL;
 
-	lock_policy_rwsem_read(policy->cpu);
+	down_read(&policy->rwsem);
 
 	if (fattr->show)
 		ret = fattr->show(policy, buf);
 	else
 		ret = -EIO;
 
-	unlock_policy_rwsem_read(policy->cpu);
+	up_read(&policy->rwsem);
 	up_read(&cpufreq_rwsem);
 
 	return ret;
@@ -716,14 +675,14 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	if (!down_read_trylock(&cpufreq_rwsem))
 		goto unlock;
 
-	lock_policy_rwsem_write(policy->cpu);
+	down_write(&policy->rwsem);
 
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
 	else
 		ret = -EIO;
 
-	unlock_policy_rwsem_write(policy->cpu);
+	up_write(&policy->rwsem);
 
 	up_read(&cpufreq_rwsem);
 unlock:
@@ -900,7 +859,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 		}
 	}
 
-	lock_policy_rwsem_write(policy->cpu);
+	down_write(&policy->rwsem);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
@@ -908,7 +867,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	per_cpu(cpufreq_cpu_data, cpu) = policy;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	unlock_policy_rwsem_write(policy->cpu);
+	up_write(&policy->rwsem);
 
 	if (has_target()) {
 		if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) ||
@@ -955,6 +914,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 		goto err_free_cpumask;
 
 	INIT_LIST_HEAD(&policy->policy_list);
+	init_rwsem(&policy->rwsem);
+
 	return policy;
 
 err_free_cpumask:
@@ -977,19 +938,12 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 	if (WARN_ON(cpu == policy->cpu))
 		return;
 
-	/*
-	 * Take direct locks as lock_policy_rwsem_write wouldn't work here.
-	 * Also lock for last cpu is enough here as contention will happen only
-	 * after policy->cpu is changed and after it is changed, other threads
-	 * will try to acquire lock for new cpu. And policy is already updated
-	 * by then.
-	 */
-	down_write(&per_cpu(cpu_policy_rwsem, policy->cpu));
+	down_write(&policy->rwsem);
 
 	policy->last_cpu = policy->cpu;
 	policy->cpu = cpu;
 
-	up_write(&per_cpu(cpu_policy_rwsem, policy->last_cpu));
+	up_write(&policy->rwsem);
 
 	cpufreq_frequency_table_update_policy_cpu(policy);
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
@@ -1181,9 +1135,9 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
 	if (ret) {
 		pr_err("%s: Failed to move kobj: %d", __func__, ret);
 
-		lock_policy_rwsem_write(old_cpu);
+		down_write(&policy->rwsem);
 		cpumask_set_cpu(old_cpu, policy->cpus);
-		unlock_policy_rwsem_write(old_cpu);
+		up_write(&policy->rwsem);
 
 		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
 					"cpufreq");
@@ -1234,9 +1188,9 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 			policy->governor->name, CPUFREQ_NAME_LEN);
 #endif
 
-	lock_policy_rwsem_read(cpu);
+	down_read(&policy->rwsem);
 	cpus = cpumask_weight(policy->cpus);
-	unlock_policy_rwsem_read(cpu);
+	up_read(&policy->rwsem);
 
 	if (cpu != policy->cpu) {
 		if (!frozen)
@@ -1276,12 +1230,12 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		return -EINVAL;
 	}
 
-	lock_policy_rwsem_write(cpu);
+	down_write(&policy->rwsem);
 	cpus = cpumask_weight(policy->cpus);
 
 	if (cpus > 1)
 		cpumask_clear_cpu(cpu, policy->cpus);
-	unlock_policy_rwsem_write(cpu);
+	up_write(&policy->rwsem);
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
@@ -1296,10 +1250,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
 		}
 
 		if (!frozen) {
-			lock_policy_rwsem_read(cpu);
+			down_read(&policy->rwsem);
 			kobj = &policy->kobj;
 			cmp = &policy->kobj_unregister;
-			unlock_policy_rwsem_read(cpu);
+			up_read(&policy->rwsem);
 			kobject_put(kobj);
 
 			/*
@@ -1479,19 +1433,22 @@ static unsigned int __cpufreq_get(unsigned int cpu)
  */
 unsigned int cpufreq_get(unsigned int cpu)
 {
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 	unsigned int ret_freq = 0;
 
 	if (cpufreq_disabled() || !cpufreq_driver)
 		return -ENOENT;
 
+	BUG_ON(!policy);
+
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
 
-	lock_policy_rwsem_read(cpu);
+	down_read(&policy->rwsem);
 
 	ret_freq = __cpufreq_get(cpu);
 
-	unlock_policy_rwsem_read(cpu);
+	up_read(&policy->rwsem);
 	up_read(&cpufreq_rwsem);
 
 	return ret_freq;
@@ -1744,11 +1701,11 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 {
 	int ret = -EINVAL;
 
-	lock_policy_rwsem_write(policy->cpu);
+	down_write(&policy->rwsem);
 
 	ret = __cpufreq_driver_target(policy, target_freq, relation);
 
-	unlock_policy_rwsem_write(policy->cpu);
+	up_write(&policy->rwsem);
 
 	return ret;
 }
@@ -1979,10 +1936,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			/* end old governor */
 			if (policy->governor) {
 				__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-				unlock_policy_rwsem_write(new_policy->cpu);
+				up_write(&policy->rwsem);
 				__cpufreq_governor(policy,
 						CPUFREQ_GOV_POLICY_EXIT);
-				lock_policy_rwsem_write(new_policy->cpu);
+				down_write(&policy->rwsem);
 			}
 
 			/* start new governor */
@@ -1991,10 +1948,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 				if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) {
 					failed = 0;
 				} else {
-					unlock_policy_rwsem_write(new_policy->cpu);
+					up_write(&policy->rwsem);
 					__cpufreq_governor(policy,
 							CPUFREQ_GOV_POLICY_EXIT);
-					lock_policy_rwsem_write(new_policy->cpu);
+					down_write(&policy->rwsem);
 				}
 			}
 
@@ -2040,7 +1997,7 @@ int cpufreq_update_policy(unsigned int cpu)
 		goto no_policy;
 	}
 
-	lock_policy_rwsem_write(cpu);
+	down_write(&policy->rwsem);
 
 	pr_debug("updating policy for CPU %u\n", cpu);
 	memcpy(&new_policy, policy, sizeof(*policy));
@@ -2067,7 +2024,7 @@ int cpufreq_update_policy(unsigned int cpu)
 
 	ret = cpufreq_set_policy(policy, &new_policy);
 
-	unlock_policy_rwsem_write(cpu);
+	up_write(&policy->rwsem);
 
 	cpufreq_cpu_put(policy);
 no_policy:
@@ -2225,14 +2182,9 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
 
 static int __init cpufreq_core_init(void)
 {
-	int cpu;
-
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	for_each_possible_cpu(cpu)
-		init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
-
 	cpufreq_global_kobject = kobject_create();
 	BUG_ON(!cpufreq_global_kobject);
 	register_syscore_ops(&cpufreq_syscore_ops);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index e8c77d330479..93a8c34d6c7f 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -85,6 +85,20 @@ struct cpufreq_policy {
 	struct list_head        policy_list;
 	struct kobject		kobj;
 	struct completion	kobj_unregister;
+
+	/*
+	 * The rules for this semaphore:
+	 * - Any routine that wants to read from the policy structure will
+	 *   do a down_read on this semaphore.
+	 * - Any routine that will write to the policy structure and/or may take away
+	 *   the policy altogether (eg. CPU hotplug), will hold this lock in write
+	 *   mode before doing so.
+	 *
+	 * Additional rules:
+	 * - Lock should not be held across
+	 *     __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+	 */
+	struct rw_semaphore	rwsem;
 };
 
 /* Only for ACPI */
-- 
cgit 


From ce77399226313a72578b5b0d67e289d3f165b8ba Mon Sep 17 00:00:00 2001
From: Darbha Sriharsha <dsriharsha@nvidia.com>
Date: Fri, 11 Oct 2013 17:15:43 -0400
Subject: power_supply: Add support for bq24735 charger

Adds support for the bq24735 charger chipset. The bq24735 is a
high-efficiency, synchronous battery charger.

It allows control of the charging current, input current, and the charger
voltage DAC's through SMBus.

Signed-off-by: Darbha Sriharsha <dsriharsha@nvidia.com>
Signed-off-by: Rhyland Klein <rklein@nvidia.com>
Thanks-to: Stephen Warren <swarren@wwwdotorg.org>
Thanks-to: Thierry Reding <thierry.reding@gmail.com>
Thanks-to: Manish Badarkhe <badarkhe.manish@gmail.com>
Signed-off-by: Anton Vorontsov <anton@enomsg.org>
---
 .../bindings/power_supply/ti,bq24735.txt           |  32 ++
 drivers/power/Kconfig                              |   6 +
 drivers/power/Makefile                             |   1 +
 drivers/power/bq24735-charger.c                    | 419 +++++++++++++++++++++
 include/linux/power/bq24735-charger.h              |  39 ++
 5 files changed, 497 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/power_supply/ti,bq24735.txt
 create mode 100644 drivers/power/bq24735-charger.c
 create mode 100644 include/linux/power/bq24735-charger.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power_supply/ti,bq24735.txt b/Documentation/devicetree/bindings/power_supply/ti,bq24735.txt
new file mode 100644
index 000000000000..4f6a550184d0
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/ti,bq24735.txt
@@ -0,0 +1,32 @@
+TI BQ24735 Charge Controller
+~~~~~~~~~~
+
+Required properties :
+ - compatible : "ti,bq24735"
+
+Optional properties :
+ - interrupts : Specify the interrupt to be used to trigger when the AC
+   adapter is either plugged in or removed.
+ - ti,ac-detect-gpios : This GPIO is optionally used to read the AC adapter
+   presence. This is a Host GPIO that is configured as an input and
+   connected to the bq24735.
+ - ti,charge-current : Used to control and set the charging current. This value
+   must be between 128mA and 8.128A with a 64mA step resolution. The POR value
+   is 0x0000h. This number is in mA (e.g. 8192), see spec for more information
+   about the ChargeCurrent (0x14h) register.
+ - ti,charge-voltage : Used to control and set the charging voltage. This value
+   must be between 1.024V and 19.2V with a 16mV step resolution. The POR value
+   is 0x0000h. This number is in mV (e.g. 19200), see spec for more information
+   about the ChargeVoltage (0x15h) register.
+ - ti,input-current : Used to control and set the charger input current. This
+   value must be between 128mA and 8.064A with a 128mA step resolution. The
+   POR value is 0x1000h. This number is in mA (e.g. 8064), see the spec for
+   more information about the InputCurrent (0x3fh) register.
+
+Example:
+
+	bq24735@9 {
+		compatible = "ti,bq24735";
+		reg = <0x9>;
+		ti,ac-detect-gpios = <&gpio 72 0x1>;
+	}
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index e6f92b450913..5e2054afe840 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -346,6 +346,12 @@ config CHARGER_BQ24190
 	help
 	  Say Y to enable support for the TI BQ24190 battery charger.
 
+config CHARGER_BQ24735
+	tristate "TI BQ24735 battery charger support"
+	depends on I2C && GPIOLIB
+	help
+	  Say Y to enable support for the TI BQ24735 battery charger.
+
 config CHARGER_SMB347
 	tristate "Summit Microelectronics SMB347 Battery Charger"
 	depends on I2C
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index a4b74177706f..372b4e8ab598 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_CHARGER_MAX8997)	+= max8997_charger.o
 obj-$(CONFIG_CHARGER_MAX8998)	+= max8998_charger.o
 obj-$(CONFIG_CHARGER_BQ2415X)	+= bq2415x_charger.o
 obj-$(CONFIG_CHARGER_BQ24190)	+= bq24190_charger.o
+obj-$(CONFIG_CHARGER_BQ24735)	+= bq24735-charger.o
 obj-$(CONFIG_POWER_AVS)		+= avs/
 obj-$(CONFIG_CHARGER_SMB347)	+= smb347-charger.o
 obj-$(CONFIG_CHARGER_TPS65090)	+= tps65090-charger.o
diff --git a/drivers/power/bq24735-charger.c b/drivers/power/bq24735-charger.c
new file mode 100644
index 000000000000..d022b823305b
--- /dev/null
+++ b/drivers/power/bq24735-charger.c
@@ -0,0 +1,419 @@
+/*
+ * Battery charger driver for TI BQ24735
+ *
+ * Copyright (c) 2013, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation;
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/power_supply.h>
+#include <linux/slab.h>
+
+#include <linux/power/bq24735-charger.h>
+
+#define BQ24735_CHG_OPT			0x12
+#define BQ24735_CHG_OPT_CHARGE_DISABLE	(1 << 0)
+#define BQ24735_CHG_OPT_AC_PRESENT	(1 << 4)
+#define BQ24735_CHARGE_CURRENT		0x14
+#define BQ24735_CHARGE_CURRENT_MASK	0x1fc0
+#define BQ24735_CHARGE_VOLTAGE		0x15
+#define BQ24735_CHARGE_VOLTAGE_MASK	0x7ff0
+#define BQ24735_INPUT_CURRENT		0x3f
+#define BQ24735_INPUT_CURRENT_MASK	0x1f80
+#define BQ24735_MANUFACTURER_ID		0xfe
+#define BQ24735_DEVICE_ID		0xff
+
+struct bq24735 {
+	struct power_supply	charger;
+	struct i2c_client	*client;
+	struct bq24735_platform	*pdata;
+};
+
+static inline struct bq24735 *to_bq24735(struct power_supply *psy)
+{
+	return container_of(psy, struct bq24735, charger);
+}
+
+static enum power_supply_property bq24735_charger_properties[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+};
+
+static inline int bq24735_write_word(struct i2c_client *client, u8 reg,
+				     u16 value)
+{
+	return i2c_smbus_write_word_data(client, reg, le16_to_cpu(value));
+}
+
+static inline int bq24735_read_word(struct i2c_client *client, u8 reg)
+{
+	s32 ret = i2c_smbus_read_word_data(client, reg);
+
+	return ret < 0 ? ret : le16_to_cpu(ret);
+}
+
+static int bq24735_update_word(struct i2c_client *client, u8 reg,
+			       u16 mask, u16 value)
+{
+	unsigned int tmp;
+	int ret;
+
+	ret = bq24735_read_word(client, reg);
+	if (ret < 0)
+		return ret;
+
+	tmp = ret & ~mask;
+	tmp |= value & mask;
+
+	return bq24735_write_word(client, reg, tmp);
+}
+
+static inline int bq24735_enable_charging(struct bq24735 *charger)
+{
+	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE,
+				   ~BQ24735_CHG_OPT_CHARGE_DISABLE);
+}
+
+static inline int bq24735_disable_charging(struct bq24735 *charger)
+{
+	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE);
+}
+
+static int bq24735_config_charger(struct bq24735 *charger)
+{
+	struct bq24735_platform *pdata = charger->pdata;
+	int ret;
+	u16 value;
+
+	if (pdata->charge_current) {
+		value = pdata->charge_current & BQ24735_CHARGE_CURRENT_MASK;
+
+		ret = bq24735_write_word(charger->client,
+					 BQ24735_CHARGE_CURRENT, value);
+		if (ret < 0) {
+			dev_err(&charger->client->dev,
+				"Failed to write charger current : %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	if (pdata->charge_voltage) {
+		value = pdata->charge_voltage & BQ24735_CHARGE_VOLTAGE_MASK;
+
+		ret = bq24735_write_word(charger->client,
+					 BQ24735_CHARGE_VOLTAGE, value);
+		if (ret < 0) {
+			dev_err(&charger->client->dev,
+				"Failed to write charger voltage : %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	if (pdata->input_current) {
+		value = pdata->input_current & BQ24735_INPUT_CURRENT_MASK;
+
+		ret = bq24735_write_word(charger->client,
+					 BQ24735_INPUT_CURRENT, value);
+		if (ret < 0) {
+			dev_err(&charger->client->dev,
+				"Failed to write input current : %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static bool bq24735_charger_is_present(struct bq24735 *charger)
+{
+	struct bq24735_platform *pdata = charger->pdata;
+	int ret;
+
+	if (pdata->status_gpio_valid) {
+		ret = gpio_get_value_cansleep(pdata->status_gpio);
+		return ret ^= pdata->status_gpio_active_low == 0;
+	} else {
+		int ac = 0;
+
+		ac = bq24735_read_word(charger->client, BQ24735_CHG_OPT);
+		if (ac < 0) {
+			dev_err(&charger->client->dev,
+				"Failed to read charger options : %d\n",
+				ac);
+			return false;
+		}
+		return (ac & BQ24735_CHG_OPT_AC_PRESENT) ? true : false;
+	}
+
+	return false;
+}
+
+static irqreturn_t bq24735_charger_isr(int irq, void *devid)
+{
+	struct power_supply *psy = devid;
+	struct bq24735 *charger = to_bq24735(psy);
+
+	if (bq24735_charger_is_present(charger))
+		bq24735_enable_charging(charger);
+	else
+		bq24735_disable_charging(charger);
+
+	power_supply_changed(psy);
+
+	return IRQ_HANDLED;
+}
+
+static int bq24735_charger_get_property(struct power_supply *psy,
+					enum power_supply_property psp,
+					union power_supply_propval *val)
+{
+	struct bq24735 *charger;
+
+	charger = container_of(psy, struct bq24735, charger);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = bq24735_charger_is_present(charger) ? 1 : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct bq24735_platform *bq24735_parse_dt_data(struct i2c_client *client)
+{
+	struct bq24735_platform *pdata;
+	struct device_node *np = client->dev.of_node;
+	u32 val;
+	int ret;
+	enum of_gpio_flags flags;
+
+	pdata = devm_kzalloc(&client->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_err(&client->dev,
+			"Memory alloc for bq24735 pdata failed\n");
+		return NULL;
+	}
+
+	pdata->status_gpio = of_get_named_gpio_flags(np, "ti,ac-detect-gpios",
+						     0, &flags);
+
+	if (flags & OF_GPIO_ACTIVE_LOW)
+		pdata->status_gpio_active_low = 1;
+
+	ret = of_property_read_u32(np, "ti,charge-current", &val);
+	if (!ret)
+		pdata->charge_current = val;
+
+	ret = of_property_read_u32(np, "ti,charge-voltage", &val);
+	if (!ret)
+		pdata->charge_voltage = val;
+
+	ret = of_property_read_u32(np, "ti,input-current", &val);
+	if (!ret)
+		pdata->input_current = val;
+
+	return pdata;
+}
+
+static int bq24735_charger_probe(struct i2c_client *client,
+				 const struct i2c_device_id *id)
+{
+	int ret;
+	struct bq24735 *charger;
+	struct power_supply *supply;
+	char *name;
+
+	charger = devm_kzalloc(&client->dev, sizeof(*charger), GFP_KERNEL);
+	if (!charger)
+		return -ENOMEM;
+
+	charger->pdata = client->dev.platform_data;
+
+	if (IS_ENABLED(CONFIG_OF) && !charger->pdata && client->dev.of_node)
+		charger->pdata = bq24735_parse_dt_data(client);
+
+	if (!charger->pdata) {
+		dev_err(&client->dev, "no platform data provided\n");
+		return -EINVAL;
+	}
+
+	name = (char *)charger->pdata->name;
+	if (!name) {
+		name = kasprintf(GFP_KERNEL, "bq24735@%s",
+				 dev_name(&client->dev));
+		if (!name) {
+			dev_err(&client->dev, "Failed to alloc device name\n");
+			return -ENOMEM;
+		}
+	}
+
+	charger->client = client;
+
+	supply = &charger->charger;
+
+	supply->name = name;
+	supply->type = POWER_SUPPLY_TYPE_MAINS;
+	supply->properties = bq24735_charger_properties;
+	supply->num_properties = ARRAY_SIZE(bq24735_charger_properties);
+	supply->get_property = bq24735_charger_get_property;
+	supply->supplied_to = charger->pdata->supplied_to;
+	supply->num_supplicants = charger->pdata->num_supplicants;
+	supply->of_node = client->dev.of_node;
+
+	i2c_set_clientdata(client, charger);
+
+	ret = bq24735_read_word(client, BQ24735_MANUFACTURER_ID);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failed to read manufacturer id : %d\n",
+			ret);
+		goto err_free_name;
+	} else if (ret != 0x0040) {
+		dev_err(&client->dev,
+			"manufacturer id mismatch. 0x0040 != 0x%04x\n", ret);
+		ret = -ENODEV;
+		goto err_free_name;
+	}
+
+	ret = bq24735_read_word(client, BQ24735_DEVICE_ID);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failed to read device id : %d\n", ret);
+		goto err_free_name;
+	} else if (ret != 0x000B) {
+		dev_err(&client->dev,
+			"device id mismatch. 0x000b != 0x%04x\n", ret);
+		ret = -ENODEV;
+		goto err_free_name;
+	}
+
+	if (gpio_is_valid(charger->pdata->status_gpio)) {
+		ret = devm_gpio_request(&client->dev,
+					charger->pdata->status_gpio,
+					name);
+		if (ret) {
+			dev_err(&client->dev,
+				"Failed GPIO request for GPIO %d: %d\n",
+				charger->pdata->status_gpio, ret);
+		}
+
+		charger->pdata->status_gpio_valid = !ret;
+	}
+
+	ret = bq24735_config_charger(charger);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed in configuring charger");
+		goto err_free_name;
+	}
+
+	/* check for AC adapter presence */
+	if (bq24735_charger_is_present(charger)) {
+		ret = bq24735_enable_charging(charger);
+		if (ret < 0) {
+			dev_err(&client->dev, "Failed to enable charging\n");
+			goto err_free_name;
+		}
+	}
+
+	ret = power_supply_register(&client->dev, supply);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failed to register power supply: %d\n",
+			ret);
+		goto err_free_name;
+	}
+
+	if (client->irq) {
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+						NULL, bq24735_charger_isr,
+						IRQF_TRIGGER_RISING |
+						IRQF_TRIGGER_FALLING |
+						IRQF_ONESHOT,
+						supply->name, supply);
+		if (ret) {
+			dev_err(&client->dev,
+				"Unable to register IRQ %d err %d\n",
+				client->irq, ret);
+			goto err_unregister_supply;
+		}
+	}
+
+	return 0;
+err_unregister_supply:
+	power_supply_unregister(supply);
+err_free_name:
+	if (name != charger->pdata->name)
+		kfree(name);
+
+	return ret;
+}
+
+static int bq24735_charger_remove(struct i2c_client *client)
+{
+	struct bq24735 *charger = i2c_get_clientdata(client);
+
+	if (charger->client->irq)
+		devm_free_irq(&charger->client->dev, charger->client->irq,
+			      &charger->charger);
+
+	power_supply_unregister(&charger->charger);
+
+	if (charger->charger.name != charger->pdata->name)
+		kfree(charger->charger.name);
+
+	return 0;
+}
+
+static const struct i2c_device_id bq24735_charger_id[] = {
+	{ "bq24735-charger", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, bq24735_charger_id);
+
+static const struct of_device_id bq24735_match_ids[] = {
+	{ .compatible = "ti,bq24735", },
+	{ /* end */ }
+};
+MODULE_DEVICE_TABLE(of, bq24735_match_ids);
+
+static struct i2c_driver bq24735_charger_driver = {
+	.driver = {
+		.name = "bq24735-charger",
+		.owner = THIS_MODULE,
+		.of_match_table = bq24735_match_ids,
+	},
+	.probe = bq24735_charger_probe,
+	.remove = bq24735_charger_remove,
+	.id_table = bq24735_charger_id,
+};
+
+module_i2c_driver(bq24735_charger_driver);
+
+MODULE_DESCRIPTION("bq24735 battery charging driver");
+MODULE_AUTHOR("Darbha Sriharsha <dsriharsha@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/power/bq24735-charger.h b/include/linux/power/bq24735-charger.h
new file mode 100644
index 000000000000..f536164a6069
--- /dev/null
+++ b/include/linux/power/bq24735-charger.h
@@ -0,0 +1,39 @@
+/*
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __CHARGER_BQ24735_H_
+#define __CHARGER_BQ24735_H_
+
+#include <linux/types.h>
+#include <linux/power_supply.h>
+
+struct bq24735_platform {
+	uint32_t charge_current;
+	uint32_t charge_voltage;
+	uint32_t input_current;
+
+	const char *name;
+
+	int status_gpio;
+	int status_gpio_active_low;
+	bool status_gpio_valid;
+
+	char **supplied_to;
+	size_t num_supplicants;
+};
+
+#endif /* __CHARGER_BQ24735_H_ */
-- 
cgit 


From f84be2bd96a108b09c8440263fa3adb3fb225fa3 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 23 Oct 2013 20:05:27 +0200
Subject: net: make net_get_random_once irq safe

I initial build non irq safe version of net_get_random_once because I
would liked to have the freedom to defer even the extraction process of
get_random_bytes until the nonblocking pool is fully seeded.

I don't think this is a good idea anymore and thus this patch makes
net_get_random_once irq safe. Now someone using net_get_random_once does
not need to care from where it is called.

Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h | 1 -
 net/core/utils.c    | 7 ++++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index aca446b46754..b292a0435571 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -250,7 +250,6 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 #define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
 #endif /* HAVE_JUMP_LABEL */
 
-/* BE CAREFUL: this function is not interrupt safe */
 #define net_get_random_once(buf, nbytes)				\
 	({								\
 		bool ___ret = false;					\
diff --git a/net/core/utils.c b/net/core/utils.c
index bf09371e19b1..2f737bf90b3f 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -370,16 +370,17 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 			   struct static_key *done_key)
 {
 	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
 
-	spin_lock_bh(&lock);
+	spin_lock_irqsave(&lock, flags);
 	if (*done) {
-		spin_unlock_bh(&lock);
+		spin_unlock_irqrestore(&lock, flags);
 		return false;
 	}
 
 	get_random_bytes(buf, nbytes);
 	*done = true;
-	spin_unlock_bh(&lock);
+	spin_unlock_irqrestore(&lock, flags);
 
 	__net_random_once_disable_jump(done_key);
 
-- 
cgit 


From 7f29405403d7c17f539c099987972b862e7e5255 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Wed, 23 Oct 2013 16:02:42 -0700
Subject: net: fix rtnl notification in atomic context

commit 991fb3f74c "dev: always advertise rx_flags changes via netlink"
introduced rtnl notification from __dev_set_promiscuity(),
which can be called in atomic context.

Steps to reproduce:
ip tuntap add dev tap1 mode tap
ifconfig tap1 up
tcpdump -nei tap1 &
ip tuntap del dev tap1 mode tap

[  271.627994] device tap1 left promiscuous mode
[  271.639897] BUG: sleeping function called from invalid context at mm/slub.c:940
[  271.664491] in_atomic(): 1, irqs_disabled(): 0, pid: 3394, name: ip
[  271.677525] INFO: lockdep is turned off.
[  271.690503] CPU: 0 PID: 3394 Comm: ip Tainted: G        W    3.12.0-rc3+ #73
[  271.703996] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012
[  271.731254]  ffffffff81a58506 ffff8807f0d57a58 ffffffff817544e5 ffff88082fa0f428
[  271.760261]  ffff8808071f5f40 ffff8807f0d57a88 ffffffff8108bad1 ffffffff81110ff8
[  271.790683]  0000000000000010 00000000000000d0 00000000000000d0 ffff8807f0d57af8
[  271.822332] Call Trace:
[  271.838234]  [<ffffffff817544e5>] dump_stack+0x55/0x76
[  271.854446]  [<ffffffff8108bad1>] __might_sleep+0x181/0x240
[  271.870836]  [<ffffffff81110ff8>] ? rcu_irq_exit+0x68/0xb0
[  271.887076]  [<ffffffff811a80be>] kmem_cache_alloc_node+0x4e/0x2a0
[  271.903368]  [<ffffffff810b4ddc>] ? vprintk_emit+0x1dc/0x5a0
[  271.919716]  [<ffffffff81614d67>] ? __alloc_skb+0x57/0x2a0
[  271.936088]  [<ffffffff810b4de0>] ? vprintk_emit+0x1e0/0x5a0
[  271.952504]  [<ffffffff81614d67>] __alloc_skb+0x57/0x2a0
[  271.968902]  [<ffffffff8163a0b2>] rtmsg_ifinfo+0x52/0x100
[  271.985302]  [<ffffffff8162ac6d>] __dev_notify_flags+0xad/0xc0
[  272.001642]  [<ffffffff8162ad0c>] __dev_set_promiscuity+0x8c/0x1c0
[  272.017917]  [<ffffffff81731ea5>] ? packet_notifier+0x5/0x380
[  272.033961]  [<ffffffff8162b109>] dev_set_promiscuity+0x29/0x50
[  272.049855]  [<ffffffff8172e937>] packet_dev_mc+0x87/0xc0
[  272.065494]  [<ffffffff81732052>] packet_notifier+0x1b2/0x380
[  272.080915]  [<ffffffff81731ea5>] ? packet_notifier+0x5/0x380
[  272.096009]  [<ffffffff81761c66>] notifier_call_chain+0x66/0x150
[  272.110803]  [<ffffffff8108503e>] __raw_notifier_call_chain+0xe/0x10
[  272.125468]  [<ffffffff81085056>] raw_notifier_call_chain+0x16/0x20
[  272.139984]  [<ffffffff81620190>] call_netdevice_notifiers_info+0x40/0x70
[  272.154523]  [<ffffffff816201d6>] call_netdevice_notifiers+0x16/0x20
[  272.168552]  [<ffffffff816224c5>] rollback_registered_many+0x145/0x240
[  272.182263]  [<ffffffff81622641>] rollback_registered+0x31/0x40
[  272.195369]  [<ffffffff816229c8>] unregister_netdevice_queue+0x58/0x90
[  272.208230]  [<ffffffff81547ca0>] __tun_detach+0x140/0x340
[  272.220686]  [<ffffffff81547ed6>] tun_chr_close+0x36/0x60

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c |  4 ++--
 include/linux/rtnetlink.h       |  2 +-
 net/core/dev.c                  | 16 ++++++++--------
 net/core/rtnetlink.c            |  9 +++++----
 4 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2daa066c6cdd..a141f406cb98 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1213,7 +1213,7 @@ static int bond_master_upper_dev_link(struct net_device *bond_dev,
 	if (err)
 		return err;
 	slave_dev->flags |= IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE);
+	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
 
@@ -1222,7 +1222,7 @@ static void bond_upper_dev_unlink(struct net_device *bond_dev,
 {
 	netdev_upper_dev_unlink(slave_dev, bond_dev);
 	slave_dev->flags &= ~IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE);
+	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 }
 
 /* enslave device <slave> to bond device <master> */
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index f28544b2f9af..939428ad25ac 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -15,7 +15,7 @@ extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics);
 extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
 			      u32 id, long expires, u32 error);
 
-extern void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change);
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
 
 /* RTNL is used as a global lock for all changes to network configuration  */
 extern void rtnl_lock(void);
diff --git a/net/core/dev.c b/net/core/dev.c
index bdffd654edc4..0054c8c75f50 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1203,7 +1203,7 @@ void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
 		call_netdevice_notifiers(NETDEV_CHANGE, dev);
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
 EXPORT_SYMBOL(netdev_state_change);
@@ -1293,7 +1293,7 @@ int dev_open(struct net_device *dev)
 	if (ret < 0)
 		return ret;
 
-	rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+	rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
 	call_netdevice_notifiers(NETDEV_UP, dev);
 
 	return ret;
@@ -1371,7 +1371,7 @@ static int dev_close_many(struct list_head *head)
 	__dev_close_many(head);
 
 	list_for_each_entry_safe(dev, tmp, head, close_list) {
-		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL);
 		call_netdevice_notifiers(NETDEV_DOWN, dev);
 		list_del_init(&dev->close_list);
 	}
@@ -5258,7 +5258,7 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
 	unsigned int changes = dev->flags ^ old_flags;
 
 	if (gchanges)
-		rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC);
 
 	if (changes & IFF_UP) {
 		if (dev->flags & IFF_UP)
@@ -5490,7 +5490,7 @@ static void rollback_registered_many(struct list_head *head)
 
 		if (!dev->rtnl_link_ops ||
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
+			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
 
 		/*
 		 *	Flush the unicast and multicast chains
@@ -5889,7 +5889,7 @@ int register_netdevice(struct net_device *dev)
 	 */
 	if (!dev->rtnl_link_ops ||
 	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
 
 out:
 	return ret;
@@ -6501,7 +6501,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	rcu_barrier();
 	call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
-	rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
+	rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
 
 	/*
 	 *	Flush the unicast and multicast chains
@@ -6540,7 +6540,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	 *	Prevent userspace races by waiting until the network
 	 *	device is fully setup before sending notifications.
 	 */
-	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL);
 
 	synchronize_net();
 	err = 0;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4aedf03da052..cf67144d3e3c 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1984,14 +1984,15 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+		  gfp_t flags)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 	size_t if_info_size;
 
-	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL);
+	skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags);
 	if (skb == NULL)
 		goto errout;
 
@@ -2002,7 +2003,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
 		kfree_skb(skb);
 		goto errout;
 	}
-	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL);
+	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
 	return;
 errout:
 	if (err < 0)
@@ -2716,7 +2717,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_JOIN:
 		break;
 	default:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
+		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 		break;
 	}
 	return NOTIFY_DONE;
-- 
cgit 


From 8fb479a47c869820966e7298f38038aa334d889c Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@meshcoding.com>
Date: Wed, 23 Oct 2013 23:36:30 +0200
Subject: netpoll: fix rx_hook() interface by passing the skb

Right now skb->data is passed to rx_hook() even if the skb
has not been linearised and without giving rx_hook() a way
to linearise it.

Change the rx_hook() interface and make it accept the skb
and the offset to the UDP payload as arguments. rx_hook() is
also renamed to rx_skb_hook() to ensure that out of the tree
users notice the API change.

In this way any rx_skb_hook() implementation can perform all
the needed operations to properly (and safely) access the
skb data.

Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h |  5 +++--
 net/core/netpoll.c      | 31 ++++++++++++++++++-------------
 2 files changed, 21 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index f3c7c24bec1c..fbfdb9d8d3a7 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -24,7 +24,8 @@ struct netpoll {
 	struct net_device *dev;
 	char dev_name[IFNAMSIZ];
 	const char *name;
-	void (*rx_hook)(struct netpoll *, int, char *, int);
+	void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb,
+			    int offset, int len);
 
 	union inet_addr local_ip, remote_ip;
 	bool ipv6;
@@ -41,7 +42,7 @@ struct netpoll_info {
 	unsigned long rx_flags;
 	spinlock_t rx_lock;
 	struct semaphore dev_lock;
-	struct list_head rx_np; /* netpolls that registered an rx_hook */
+	struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
 
 	struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */
 	struct sk_buff_head txq;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index fc75c9e461b8..8f971990677c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -636,8 +636,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 
 			netpoll_send_skb(np, send_skb);
 
-			/* If there are several rx_hooks for the same address,
-			   we're fine by sending a single reply */
+			/* If there are several rx_skb_hooks for the same
+			 * address we're fine by sending a single reply
+			 */
 			break;
 		}
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -719,8 +720,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 
 			netpoll_send_skb(np, send_skb);
 
-			/* If there are several rx_hooks for the same address,
-			   we're fine by sending a single reply */
+			/* If there are several rx_skb_hooks for the same
+			 * address, we're fine by sending a single reply
+			 */
 			break;
 		}
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
@@ -756,11 +758,12 @@ static bool pkt_is_ns(struct sk_buff *skb)
 
 int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 {
-	int proto, len, ulen;
-	int hits = 0;
+	int proto, len, ulen, data_len;
+	int hits = 0, offset;
 	const struct iphdr *iph;
 	struct udphdr *uh;
 	struct netpoll *np, *tmp;
+	uint16_t source;
 
 	if (list_empty(&npinfo->rx_np))
 		goto out;
@@ -820,7 +823,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 
 		len -= iph->ihl*4;
 		uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
+		offset = (unsigned char *)(uh + 1) - skb->data;
 		ulen = ntohs(uh->len);
+		data_len = skb->len - offset;
+		source = ntohs(uh->source);
 
 		if (ulen != len)
 			goto out;
@@ -834,9 +840,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 			if (np->local_port && np->local_port != ntohs(uh->dest))
 				continue;
 
-			np->rx_hook(np, ntohs(uh->source),
-				       (char *)(uh+1),
-				       ulen - sizeof(struct udphdr));
+			np->rx_skb_hook(np, source, skb, offset, data_len);
 			hits++;
 		}
 	} else {
@@ -859,7 +863,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 			goto out;
 		uh = udp_hdr(skb);
+		offset = (unsigned char *)(uh + 1) - skb->data;
 		ulen = ntohs(uh->len);
+		data_len = skb->len - offset;
+		source = ntohs(uh->source);
 		if (ulen != skb->len)
 			goto out;
 		if (udp6_csum_init(skb, uh, IPPROTO_UDP))
@@ -872,9 +879,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 			if (np->local_port && np->local_port != ntohs(uh->dest))
 				continue;
 
-			np->rx_hook(np, ntohs(uh->source),
-				       (char *)(uh+1),
-				       ulen - sizeof(struct udphdr));
+			np->rx_skb_hook(np, source, skb, offset, data_len);
 			hits++;
 		}
 #endif
@@ -1062,7 +1067,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	npinfo->netpoll = np;
 
-	if (np->rx_hook) {
+	if (np->rx_skb_hook) {
 		spin_lock_irqsave(&npinfo->rx_lock, flags);
 		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
 		list_add_tail(&np->rx, &npinfo->rx_np);
-- 
cgit 


From 01ba16d6ec85a1ec4669c75513a76b61ec53ee50 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 24 Oct 2013 10:14:27 +0200
Subject: ipv6: reset dst.expires value when clearing expire flag

On receiving a packet too big icmp error we update the expire value by
calling rt6_update_expires. This function uses dst_set_expires which is
implemented that it can only reduce the expiration value of the dst entry.

If we insert new routing non-expiry information into the ipv6 fib where
we already have a matching rt6_info we only clear the RTF_EXPIRES flag
in rt6i_flags and leave the dst.expires value as is.

When new mtu information arrives for that cached dst_entry we again
call dst_set_expires. This time it won't update the dst.expire value
because we left the dst.expire value intact from the last update. So
dst_set_expires won't touch dst.expires.

Fix this by resetting dst.expires when clearing the RTF_EXPIRE flag.
dst_set_expires checks for a zero expiration and updates the
dst.expires.

In the past this (not updating dst.expires) was necessary because
dst.expire was placed in a union with the dst_entry *from reference
and rt6_clean_expires did assign NULL to it. This split happend in
ecd9883724b78cc72ed92c98bcb1a46c764fff21 ("ipv6: fix race condition
regarding dst->expires and dst->from").

Reported-by: Steinar H. Gunderson <sgunderson@bigfoot.com>
Reported-by: Valentijn Sessink <valentyn@blub.net>
Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Tested-by: Valentijn Sessink <valentyn@blub.net>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 48ec25a7fcb6..5e661a979694 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -165,6 +165,7 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
 static inline void rt6_clean_expires(struct rt6_info *rt)
 {
 	rt->rt6i_flags &= ~RTF_EXPIRES;
+	rt->dst.expires = 0;
 }
 
 static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
-- 
cgit 


From 3915c3b5b10cd127198c1f9e2aefff7808500d92 Mon Sep 17 00:00:00 2001
From: Robert Hancock <hancockrwd@gmail.com>
Date: Mon, 21 Oct 2013 19:26:30 -0600
Subject: libata: Add some missing command descriptions

Add some missing command enumerations from the ATA-8 ACS-3 spec into
include/linux/ata.h, and add the corresponding human-readable command
descriptions in libata-eh.c.

Signed-off-by: Robert Hancock <hancockrwd@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-eh.c | 8 ++++++++
 include/linux/ata.h     | 7 +++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c69fcce505c0..ca88c48d08b8 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2293,6 +2293,7 @@ const char *ata_get_cmd_descript(u8 command)
 		{ ATA_CMD_IDLE, 		"IDLE" },
 		{ ATA_CMD_EDD, 			"EXECUTE DEVICE DIAGNOSTIC" },
 		{ ATA_CMD_DOWNLOAD_MICRO,   	"DOWNLOAD MICROCODE" },
+		{ ATA_CMD_DOWNLOAD_MICRO_DMA,	"DOWNLOAD MICROCODE DMA" },
 		{ ATA_CMD_NOP,			"NOP" },
 		{ ATA_CMD_FLUSH, 		"FLUSH CACHE" },
 		{ ATA_CMD_FLUSH_EXT, 		"FLUSH CACHE EXT" },
@@ -2313,6 +2314,8 @@ const char *ata_get_cmd_descript(u8 command)
 		{ ATA_CMD_WRITE_QUEUED_FUA_EXT, "WRITE DMA QUEUED FUA EXT" },
 		{ ATA_CMD_FPDMA_READ,		"READ FPDMA QUEUED" },
 		{ ATA_CMD_FPDMA_WRITE,		"WRITE FPDMA QUEUED" },
+		{ ATA_CMD_FPDMA_SEND,		"SEND FPDMA QUEUED" },
+		{ ATA_CMD_FPDMA_RECV,		"RECEIVE FPDMA QUEUED" },
 		{ ATA_CMD_PIO_READ,		"READ SECTOR(S)" },
 		{ ATA_CMD_PIO_READ_EXT,		"READ SECTOR(S) EXT" },
 		{ ATA_CMD_PIO_WRITE,		"WRITE SECTOR(S)" },
@@ -2339,12 +2342,15 @@ const char *ata_get_cmd_descript(u8 command)
 		{ ATA_CMD_WRITE_LOG_EXT,	"WRITE LOG EXT" },
 		{ ATA_CMD_READ_LOG_DMA_EXT,	"READ LOG DMA EXT" },
 		{ ATA_CMD_WRITE_LOG_DMA_EXT, 	"WRITE LOG DMA EXT" },
+		{ ATA_CMD_TRUSTED_NONDATA,	"TRUSTED NON-DATA" },
 		{ ATA_CMD_TRUSTED_RCV,		"TRUSTED RECEIVE" },
 		{ ATA_CMD_TRUSTED_RCV_DMA, 	"TRUSTED RECEIVE DMA" },
 		{ ATA_CMD_TRUSTED_SND,		"TRUSTED SEND" },
 		{ ATA_CMD_TRUSTED_SND_DMA, 	"TRUSTED SEND DMA" },
 		{ ATA_CMD_PMP_READ,		"READ BUFFER" },
+		{ ATA_CMD_PMP_READ_DMA,		"READ BUFFER DMA" },
 		{ ATA_CMD_PMP_WRITE,		"WRITE BUFFER" },
+		{ ATA_CMD_PMP_WRITE_DMA,	"WRITE BUFFER DMA" },
 		{ ATA_CMD_CONF_OVERLAY,		"DEVICE CONFIGURATION OVERLAY" },
 		{ ATA_CMD_SEC_SET_PASS,		"SECURITY SET PASSWORD" },
 		{ ATA_CMD_SEC_UNLOCK,		"SECURITY UNLOCK" },
@@ -2363,6 +2369,8 @@ const char *ata_get_cmd_descript(u8 command)
 		{ ATA_CMD_CFA_TRANS_SECT,	"CFA TRANSLATE SECTOR" },
 		{ ATA_CMD_CFA_ERASE,		"CFA ERASE SECTORS" },
 		{ ATA_CMD_CFA_WRITE_MULT_NE, 	"CFA WRITE MULTIPLE WITHOUT ERASE" },
+		{ ATA_CMD_REQ_SENSE_DATA,	"REQUEST SENSE DATA EXT" },
+		{ ATA_CMD_SANITIZE_DEVICE,	"SANITIZE DEVICE" },
 		{ ATA_CMD_READ_LONG,		"READ LONG (with retries)" },
 		{ ATA_CMD_READ_LONG_ONCE,	"READ LONG (without retries)" },
 		{ ATA_CMD_WRITE_LONG,		"WRITE LONG (with retries)" },
diff --git a/include/linux/ata.h b/include/linux/ata.h
index bf4c69ca76df..f2f4d8da97c0 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -219,6 +219,7 @@ enum {
 	ATA_CMD_IDLE		= 0xE3, /* place in idle power mode */
 	ATA_CMD_EDD		= 0x90,	/* execute device diagnostic */
 	ATA_CMD_DOWNLOAD_MICRO  = 0x92,
+	ATA_CMD_DOWNLOAD_MICRO_DMA = 0x93,
 	ATA_CMD_NOP		= 0x00,
 	ATA_CMD_FLUSH		= 0xE7,
 	ATA_CMD_FLUSH_EXT	= 0xEA,
@@ -268,12 +269,15 @@ enum {
 	ATA_CMD_WRITE_LOG_EXT	= 0x3F,
 	ATA_CMD_READ_LOG_DMA_EXT = 0x47,
 	ATA_CMD_WRITE_LOG_DMA_EXT = 0x57,
+	ATA_CMD_TRUSTED_NONDATA	= 0x5B,
 	ATA_CMD_TRUSTED_RCV	= 0x5C,
 	ATA_CMD_TRUSTED_RCV_DMA = 0x5D,
 	ATA_CMD_TRUSTED_SND	= 0x5E,
 	ATA_CMD_TRUSTED_SND_DMA = 0x5F,
 	ATA_CMD_PMP_READ	= 0xE4,
+	ATA_CMD_PMP_READ_DMA	= 0xE9,
 	ATA_CMD_PMP_WRITE	= 0xE8,
+	ATA_CMD_PMP_WRITE_DMA	= 0xEB,
 	ATA_CMD_CONF_OVERLAY	= 0xB1,
 	ATA_CMD_SEC_SET_PASS	= 0xF1,
 	ATA_CMD_SEC_UNLOCK	= 0xF2,
@@ -292,6 +296,9 @@ enum {
 	ATA_CMD_CFA_TRANS_SECT	= 0x87,
 	ATA_CMD_CFA_ERASE	= 0xC0,
 	ATA_CMD_CFA_WRITE_MULT_NE = 0xCD,
+	ATA_CMD_REQ_SENSE_DATA  = 0x0B,
+	ATA_CMD_SANITIZE_DEVICE = 0xB4,
+
 	/* marked obsolete in the ATA/ATAPI-7 spec */
 	ATA_CMD_RESTORE		= 0x10,
 
-- 
cgit 


From 84292b29475bc7bb6b04ae5360595bd816ca4efb Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 21 Oct 2013 13:25:36 +0200
Subject: percpu: remove this_cpu_xor() implementation

There is not a single user in the whole kernel.
Besides that this_cpu_xor() is broken anyway since it gets
translated to this_cpu_or() (see __pcpu_size_call() line).

So instead of fixing an unused definition just remove it.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/percpu.h | 32 --------------------------------
 1 file changed, 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index cc88172c7d9a..fd6ffe459aae 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -375,22 +375,6 @@ do {									\
 # define this_cpu_or(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
 #endif
 
-#ifndef this_cpu_xor
-# ifndef this_cpu_xor_1
-#  define this_cpu_xor_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef this_cpu_xor_2
-#  define this_cpu_xor_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef this_cpu_xor_4
-#  define this_cpu_xor_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef this_cpu_xor_8
-#  define this_cpu_xor_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# define this_cpu_xor(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
-#endif
-
 #define _this_cpu_generic_add_return(pcp, val)				\
 ({									\
 	typeof(pcp) ret__;						\
@@ -629,22 +613,6 @@ do {									\
 # define __this_cpu_or(pcp, val)	__pcpu_size_call(__this_cpu_or_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_xor
-# ifndef __this_cpu_xor_1
-#  define __this_cpu_xor_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef __this_cpu_xor_2
-#  define __this_cpu_xor_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef __this_cpu_xor_4
-#  define __this_cpu_xor_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef __this_cpu_xor_8
-#  define __this_cpu_xor_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# define __this_cpu_xor(pcp, val)	__pcpu_size_call(__this_cpu_xor_, (pcp), (val))
-#endif
-
 #define __this_cpu_generic_add_return(pcp, val)				\
 ({									\
 	__this_cpu_add(pcp, val);					\
-- 
cgit 


From a6eaa2ae7820f0cca742917f85f34ef1eed2c95d Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Date: Mon, 2 Sep 2013 23:37:53 -0300
Subject: of_mtd: Add no-op stubs to support CONFIG_OF=n

Just like the rest of the subsystems, let's add the required no-op
functions to implement stubs when CONFIG_OF=n.

This prevents MTD drivers from having ugly ifdefs in their code,
and instead hide the ifdef monster in the header closet (far away
from people's sight).

Signed-off-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/of_mtd.h | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/of_mtd.h b/include/linux/of_mtd.h
index ed7f267e6389..6f10e938ff7e 100644
--- a/include/linux/of_mtd.h
+++ b/include/linux/of_mtd.h
@@ -10,10 +10,29 @@
 #define __LINUX_OF_NET_H
 
 #ifdef CONFIG_OF_MTD
+
 #include <linux/of.h>
 int of_get_nand_ecc_mode(struct device_node *np);
 int of_get_nand_bus_width(struct device_node *np);
 bool of_get_nand_on_flash_bbt(struct device_node *np);
-#endif
+
+#else /* CONFIG_OF_MTD */
+
+static inline int of_get_nand_ecc_mode(struct device_node *np)
+{
+	return -ENOSYS;
+}
+
+static inline int of_get_nand_bus_width(struct device_node *np)
+{
+	return -ENOSYS;
+}
+
+static inline bool of_get_nand_on_flash_bbt(struct device_node *np)
+{
+	return false;
+}
+
+#endif /* CONFIG_OF_MTD */
 
 #endif /* __LINUX_OF_MTD_H */
-- 
cgit 


From aaadd9819a128fb7ad988b6808581e3175859e2f Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Fri, 23 Aug 2013 23:24:47 -0700
Subject: mtd: nand: remove obsolete 'ecclayout' field

This field is never used, except to print it out.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/fsl_elbc_nand.c | 2 --
 drivers/mtd/nand/fsl_ifc_nand.c  | 2 --
 include/linux/mtd/nand.h         | 2 --
 3 files changed, 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 20657209a472..c6ef9f1c7a82 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -650,8 +650,6 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 	        chip->page_shift);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->phys_erase_shift = %d\n",
 	        chip->phys_erase_shift);
-	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecclayout = %p\n",
-	        chip->ecclayout);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.mode = %d\n",
 	        chip->ecc.mode);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.steps = %d\n",
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 317a771f1587..47acda6c4e92 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -718,8 +718,6 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
 							chip->page_shift);
 	dev_dbg(priv->dev, "%s: nand->phys_erase_shift = %d\n", __func__,
 							chip->phys_erase_shift);
-	dev_dbg(priv->dev, "%s: nand->ecclayout = %p\n", __func__,
-							chip->ecclayout);
 	dev_dbg(priv->dev, "%s: nand->ecc.mode = %d\n", __func__,
 							chip->ecc.mode);
 	dev_dbg(priv->dev, "%s: nand->ecc.steps = %d\n", __func__,
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index ac8e89d5a792..129548169400 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -498,7 +498,6 @@ struct nand_buffers {
  *			supported, 0 otherwise.
  * @onfi_set_features:	[REPLACEABLE] set the features for ONFI nand
  * @onfi_get_features:	[REPLACEABLE] get the features for ONFI nand
- * @ecclayout:		[REPLACEABLE] the default ECC placement scheme
  * @bbt:		[INTERN] bad block table pointer
  * @bbt_td:		[REPLACEABLE] bad block table descriptor for flash
  *			lookup.
@@ -572,7 +571,6 @@ struct nand_chip {
 
 	uint8_t *oob_poi;
 	struct nand_hw_control *controller;
-	struct nand_ecclayout *ecclayout;
 
 	struct nand_ecc_ctrl ecc;
 	struct nand_buffers *buffers;
-- 
cgit 


From 1d0ed69ddd714b6e2a974f42896463366923ded6 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Wed, 25 Sep 2013 14:58:10 +0800
Subject: mtd: nand: add a helper to check the SLC/MLC nand chip

Add a helper to check if a nand chip is SLC or MLC.
This helper makes the code more readable.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/denali.c    |  2 +-
 drivers/mtd/nand/nand_base.c | 14 ++++++--------
 include/linux/mtd/nand.h     |  9 +++++++++
 3 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 154b033b4e8e..370b9dd7a278 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1520,7 +1520,7 @@ int denali_init(struct denali_nand_info *denali)
 	 * so just let controller do 15bit ECC for MLC and 8bit ECC for
 	 * SLC if possible.
 	 * */
-	if (denali->nand.cellinfo & NAND_CI_CELLTYPE_MSK &&
+	if (!nand_is_slc(&denali->nand) &&
 			(denali->mtd.oobsize > (denali->bbtskipbytes +
 			ECC_15BITS * (denali->mtd.writesize /
 			ECC_SECTOR_SIZE)))) {
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 0b39d0c03f1e..6ea66270dbf5 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3108,8 +3108,7 @@ static void nand_decode_ext_id(struct mtd_info *mtd, struct nand_chip *chip,
 	 * ID to decide what to do.
 	 */
 	if (id_len == 6 && id_data[0] == NAND_MFR_SAMSUNG &&
-			(chip->cellinfo & NAND_CI_CELLTYPE_MSK) &&
-			id_data[5] != 0x00) {
+			!nand_is_slc(chip) && id_data[5] != 0x00) {
 		/* Calc pagesize */
 		mtd->writesize = 2048 << (extid & 0x03);
 		extid >>= 2;
@@ -3141,7 +3140,7 @@ static void nand_decode_ext_id(struct mtd_info *mtd, struct nand_chip *chip,
 			(((extid >> 1) & 0x04) | (extid & 0x03));
 		*busw = 0;
 	} else if (id_len == 6 && id_data[0] == NAND_MFR_HYNIX &&
-			(chip->cellinfo & NAND_CI_CELLTYPE_MSK)) {
+			!nand_is_slc(chip)) {
 		unsigned int tmp;
 
 		/* Calc pagesize */
@@ -3204,7 +3203,7 @@ static void nand_decode_ext_id(struct mtd_info *mtd, struct nand_chip *chip,
 		 * - ID byte 5, bit[7]:    1 -> BENAND, 0 -> raw SLC
 		 */
 		if (id_len >= 6 && id_data[0] == NAND_MFR_TOSHIBA &&
-				!(chip->cellinfo & NAND_CI_CELLTYPE_MSK) &&
+				nand_is_slc(chip) &&
 				(id_data[5] & 0x7) == 0x6 /* 24nm */ &&
 				!(id_data[4] & 0x80) /* !BENAND */) {
 			mtd->oobsize = 32 * mtd->writesize >> 9;
@@ -3265,11 +3264,11 @@ static void nand_decode_bbm_options(struct mtd_info *mtd,
 	 * Micron devices with 2KiB pages and on SLC Samsung, Hynix, Toshiba,
 	 * AMD/Spansion, and Macronix.  All others scan only the first page.
 	 */
-	if ((chip->cellinfo & NAND_CI_CELLTYPE_MSK) &&
+	if (!nand_is_slc(chip) &&
 			(maf_id == NAND_MFR_SAMSUNG ||
 			 maf_id == NAND_MFR_HYNIX))
 		chip->bbt_options |= NAND_BBT_SCANLASTPAGE;
-	else if ((!(chip->cellinfo & NAND_CI_CELLTYPE_MSK) &&
+	else if ((nand_is_slc(chip) &&
 				(maf_id == NAND_MFR_SAMSUNG ||
 				 maf_id == NAND_MFR_HYNIX ||
 				 maf_id == NAND_MFR_TOSHIBA ||
@@ -3745,8 +3744,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 	chip->ecc.total = chip->ecc.steps * chip->ecc.bytes;
 
 	/* Allow subpage writes up to ecc.steps. Not possible for MLC flash */
-	if (!(chip->options & NAND_NO_SUBPAGE_WRITE) &&
-	    !(chip->cellinfo & NAND_CI_CELLTYPE_MSK)) {
+	if (!(chip->options & NAND_NO_SUBPAGE_WRITE) && nand_is_slc(chip)) {
 		switch (chip->ecc.steps) {
 		case 2:
 			mtd->subpage_sft = 1;
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 129548169400..5c05bab0ad89 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -795,4 +795,13 @@ static inline int onfi_get_sync_timing_mode(struct nand_chip *chip)
 	return le16_to_cpu(chip->onfi_params.src_sync_timing_mode);
 }
 
+/*
+ * Check if it is a SLC nand.
+ * The !nand_is_slc() can be used to check the MLC/TLC nand chips.
+ * We do not distinguish the MLC and TLC now.
+ */
+static inline bool nand_is_slc(struct nand_chip *chip)
+{
+	return !(chip->cellinfo & NAND_CI_CELLTYPE_MSK);
+}
 #endif /* __LINUX_MTD_NAND_H */
-- 
cgit 


From 7db906b79f69b6ed936a1ef1d788f02e3ad42462 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Wed, 25 Sep 2013 14:58:11 +0800
Subject: mtd: nand: rename the cellinfo to bits_per_cell

The @cellinfo fields contains unused information, such as write caching,
internal chip numbering, etc. But we only use it to check the SLC or MLC.

This patch tries to make it more clear and simple, renames the @cellinfo
to @bits_per_cell.

In order to avoiding the bisect issue, this patch also does the following
changes:
  (0) add a macro NAND_CI_CELLTYPE_SHIFT to avoid the hardcode.

  (1) add a helper to parse out the cell type : nand_get_bits_per_cell()

  (2) parse out the cell type for extended-ID chips and the full-id nand chips.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/nand_base.c | 14 ++++++++++++--
 include/linux/mtd/nand.h     |  7 ++++---
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 6ea66270dbf5..5fb00957fd25 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3082,6 +3082,16 @@ static int nand_id_len(u8 *id_data, int arrlen)
 	return arrlen;
 }
 
+/* Extract the bits of per cell from the 3rd byte of the extended ID */
+static int nand_get_bits_per_cell(u8 cellinfo)
+{
+	int bits;
+
+	bits = cellinfo & NAND_CI_CELLTYPE_MSK;
+	bits >>= NAND_CI_CELLTYPE_SHIFT;
+	return bits + 1;
+}
+
 /*
  * Many new NAND share similar device ID codes, which represent the size of the
  * chip. The rest of the parameters must be decoded according to generic or
@@ -3092,7 +3102,7 @@ static void nand_decode_ext_id(struct mtd_info *mtd, struct nand_chip *chip,
 {
 	int extid, id_len;
 	/* The 3rd id byte holds MLC / multichip data */
-	chip->cellinfo = id_data[2];
+	chip->bits_per_cell = nand_get_bits_per_cell(id_data[2]);
 	/* The 4th id byte is the important one */
 	extid = id_data[3];
 
@@ -3292,7 +3302,7 @@ static bool find_full_id_nand(struct mtd_info *mtd, struct nand_chip *chip,
 		mtd->erasesize = type->erasesize;
 		mtd->oobsize = type->oobsize;
 
-		chip->cellinfo = id_data[2];
+		chip->bits_per_cell = nand_get_bits_per_cell(id_data[2]);
 		chip->chipsize = (uint64_t)type->chipsize << 20;
 		chip->options |= type->options;
 		chip->ecc_strength_ds = NAND_ECC_STRENGTH(type);
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 5c05bab0ad89..9e6c8f9f306e 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -198,6 +198,7 @@ typedef enum {
 /* Cell info constants */
 #define NAND_CI_CHIPNR_MSK	0x03
 #define NAND_CI_CELLTYPE_MSK	0x0C
+#define NAND_CI_CELLTYPE_SHIFT	2
 
 /* Keep gcc happy */
 struct nand_chip;
@@ -477,7 +478,7 @@ struct nand_buffers {
  * @badblockbits:	[INTERN] minimum number of set bits in a good block's
  *			bad block marker position; i.e., BBM == 11110111b is
  *			not bad when badblockbits == 7
- * @cellinfo:		[INTERN] MLC/multichip data from chip ident
+ * @bits_per_cell:	[INTERN] number of bits per cell. i.e., 1 means SLC.
  * @ecc_strength_ds:	[INTERN] ECC correctability from the datasheet.
  *			Minimum amount of bit errors per @ecc_step_ds guaranteed
  *			to be correctable. If unknown, set to zero.
@@ -558,7 +559,7 @@ struct nand_chip {
 	int pagebuf;
 	unsigned int pagebuf_bitflips;
 	int subpagesize;
-	uint8_t cellinfo;
+	uint8_t bits_per_cell;
 	uint16_t ecc_strength_ds;
 	uint16_t ecc_step_ds;
 	int badblockpos;
@@ -802,6 +803,6 @@ static inline int onfi_get_sync_timing_mode(struct nand_chip *chip)
  */
 static inline bool nand_is_slc(struct nand_chip *chip)
 {
-	return !(chip->cellinfo & NAND_CI_CELLTYPE_MSK);
+	return chip->bits_per_cell == 1;
 }
 #endif /* __LINUX_MTD_NAND_H */
-- 
cgit 


From fda5b0e24dca3d52671e5a6543a285d4e86c55e1 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Wed, 25 Sep 2013 14:58:16 +0800
Subject: mtd: nand: add more comment for MTD_NANDFLASH/MTD_MLCNANDFLASH

In current code, the MTD_NANDFLASH is used to represent both the SLC and
MLC. It is confusing to us.

By adding an explicit comment about these two macros, this patch makes it
clear that:
	MTD_NANDFLASH    : stands for SLC NAND,
	MTD_MLCNANDFLASH : stands for MLC NAND (including TLC).

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/uapi/mtd/mtd-abi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h
index 36eace03b2ac..e89b096856f8 100644
--- a/include/uapi/mtd/mtd-abi.h
+++ b/include/uapi/mtd/mtd-abi.h
@@ -94,10 +94,10 @@ struct mtd_write_req {
 #define MTD_RAM			1
 #define MTD_ROM			2
 #define MTD_NORFLASH		3
-#define MTD_NANDFLASH		4
+#define MTD_NANDFLASH		4	/* SLC NAND */
 #define MTD_DATAFLASH		6
 #define MTD_UBIVOLUME		7
-#define MTD_MLCNANDFLASH	8
+#define MTD_MLCNANDFLASH	8	/* MLC NAND (including TLC) */
 
 #define MTD_WRITEABLE		0x400	/* Device is writeable */
 #define MTD_BIT_WRITEABLE	0x800	/* Single bits can be flipped */
-- 
cgit 


From 818b97392932ac4cecc36ab839957258367004a9 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Wed, 25 Sep 2013 14:58:17 +0800
Subject: mtd: nand: add a helper to detect the nand type

This helper detects that whether the mtd's type is nand type.

Now, it's clear that the MTD_NANDFLASH stands for SLC nand only.
So use the mtd_type_is_nand() to replace the old check method
to do the nand type (include the SLC and MLC) check.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/inftlcore.c         | 2 +-
 drivers/mtd/nftlcore.c          | 2 +-
 drivers/mtd/ssfdc.c             | 2 +-
 drivers/mtd/tests/nandbiterrs.c | 2 +-
 drivers/mtd/tests/oobtest.c     | 2 +-
 drivers/mtd/tests/pagetest.c    | 2 +-
 drivers/mtd/tests/subpagetest.c | 2 +-
 include/linux/mtd/mtd.h         | 5 +++++
 8 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/inftlcore.c b/drivers/mtd/inftlcore.c
index 3af351484098..b66b541877f0 100644
--- a/drivers/mtd/inftlcore.c
+++ b/drivers/mtd/inftlcore.c
@@ -50,7 +50,7 @@ static void inftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	struct INFTLrecord *inftl;
 	unsigned long temp;
 
-	if (mtd->type != MTD_NANDFLASH || mtd->size > UINT_MAX)
+	if (!mtd_type_is_nand(mtd) || mtd->size > UINT_MAX)
 		return;
 	/* OK, this is moderately ugly.  But probably safe.  Alternatives? */
 	if (memcmp(mtd->name, "DiskOnChip", 10))
diff --git a/drivers/mtd/nftlcore.c b/drivers/mtd/nftlcore.c
index c5f4ebf4b384..46f27de018c3 100644
--- a/drivers/mtd/nftlcore.c
+++ b/drivers/mtd/nftlcore.c
@@ -50,7 +50,7 @@ static void nftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	struct NFTLrecord *nftl;
 	unsigned long temp;
 
-	if (mtd->type != MTD_NANDFLASH || mtd->size > UINT_MAX)
+	if (!mtd_type_is_nand(mtd) || mtd->size > UINT_MAX)
 		return;
 	/* OK, this is moderately ugly.  But probably safe.  Alternatives? */
 	if (memcmp(mtd->name, "DiskOnChip", 10))
diff --git a/drivers/mtd/ssfdc.c b/drivers/mtd/ssfdc.c
index ab2a52a039c3..daf82ba7aba0 100644
--- a/drivers/mtd/ssfdc.c
+++ b/drivers/mtd/ssfdc.c
@@ -290,7 +290,7 @@ static void ssfdcr_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	int cis_sector;
 
 	/* Check for small page NAND flash */
-	if (mtd->type != MTD_NANDFLASH || mtd->oobsize != OOB_SIZE ||
+	if (!mtd_type_is_nand(mtd) || mtd->oobsize != OOB_SIZE ||
 	    mtd->size > UINT_MAX)
 		return;
 
diff --git a/drivers/mtd/tests/nandbiterrs.c b/drivers/mtd/tests/nandbiterrs.c
index 3cd3aabbe1cd..6f976159611f 100644
--- a/drivers/mtd/tests/nandbiterrs.c
+++ b/drivers/mtd/tests/nandbiterrs.c
@@ -349,7 +349,7 @@ static int __init mtd_nandbiterrs_init(void)
 		goto exit_mtddev;
 	}
 
-	if (mtd->type != MTD_NANDFLASH) {
+	if (!mtd_type_is_nand(mtd)) {
 		pr_info("this test requires NAND flash\n");
 		err = -ENODEV;
 		goto exit_nand;
diff --git a/drivers/mtd/tests/oobtest.c b/drivers/mtd/tests/oobtest.c
index ff35c465bfee..2e9e2d11f204 100644
--- a/drivers/mtd/tests/oobtest.c
+++ b/drivers/mtd/tests/oobtest.c
@@ -289,7 +289,7 @@ static int __init mtd_oobtest_init(void)
 		return err;
 	}
 
-	if (mtd->type != MTD_NANDFLASH) {
+	if (!mtd_type_is_nand(mtd)) {
 		pr_info("this test requires NAND flash\n");
 		goto out;
 	}
diff --git a/drivers/mtd/tests/pagetest.c b/drivers/mtd/tests/pagetest.c
index 44b96e999ad4..ed2d3f656fd2 100644
--- a/drivers/mtd/tests/pagetest.c
+++ b/drivers/mtd/tests/pagetest.c
@@ -353,7 +353,7 @@ static int __init mtd_pagetest_init(void)
 		return err;
 	}
 
-	if (mtd->type != MTD_NANDFLASH) {
+	if (!mtd_type_is_nand(mtd)) {
 		pr_info("this test requires NAND flash\n");
 		goto out;
 	}
diff --git a/drivers/mtd/tests/subpagetest.c b/drivers/mtd/tests/subpagetest.c
index e2c0adf24cfc..a876371ad410 100644
--- a/drivers/mtd/tests/subpagetest.c
+++ b/drivers/mtd/tests/subpagetest.c
@@ -299,7 +299,7 @@ static int __init mtd_subpagetest_init(void)
 		return err;
 	}
 
-	if (mtd->type != MTD_NANDFLASH) {
+	if (!mtd_type_is_nand(mtd)) {
 		pr_info("this test requires NAND flash\n");
 		goto out;
 	}
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index f9bfe526d310..88409b813418 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -354,6 +354,11 @@ static inline int mtd_has_oob(const struct mtd_info *mtd)
 	return mtd->_read_oob && mtd->_write_oob;
 }
 
+static inline int mtd_type_is_nand(const struct mtd_info *mtd)
+{
+	return mtd->type == MTD_NANDFLASH || mtd->type == MTD_MLCNANDFLASH;
+}
+
 static inline int mtd_can_have_bb(const struct mtd_info *mtd)
 {
 	return !!mtd->_block_isbad;
-- 
cgit 


From 4f8a3ba700b882f61d4cea2d68a8f83fa93c6dfd Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Wed, 25 Sep 2013 14:58:18 +0800
Subject: mtd: mtd-abi: add a helper to detect the nand type

The helper is for user applications, and it is just a copy of
the kernel helper: mtd_type_is_nand();

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/uapi/mtd/mtd-abi.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h
index e89b096856f8..e272ea060e38 100644
--- a/include/uapi/mtd/mtd-abi.h
+++ b/include/uapi/mtd/mtd-abi.h
@@ -275,4 +275,9 @@ enum mtd_file_modes {
 	MTD_FILE_MODE_RAW,
 };
 
+static inline int mtd_type_is_nand_user(const struct mtd_info_user *mtd)
+{
+	return mtd->type == MTD_NANDFLASH || mtd->type == MTD_MLCNANDFLASH;
+}
+
 #endif /* __MTD_ABI_H__ */
-- 
cgit 


From 5336fa88e8ac6b666a3db9902a4797d94d86a702 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <simon.wunderlich@s2003.tu-chemnitz.de>
Date: Mon, 7 Oct 2013 18:41:05 +0200
Subject: nl80211/cfg80211: enable DFS for IBSS mode

To use DFS in IBSS mode, userspace is required to react to radar events.
It can inform nl80211 that it is capable of doing so by adding a
NL80211_ATTR_HANDLE_DFS attribute when joining the IBSS.

This attribute is supplied to let the kernelspace know that the
userspace application can and will handle radar events, e.g. by
intiating channel switches to a valid channel. DFS channels may
only be used if this attribute is supplied and the driver supports
it. Driver support will be checked even if a channel without DFS
will be initially joined, as a DFS channel may be chosen later.

Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de>
[fix attribute name in commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  6 ++++++
 include/uapi/linux/nl80211.h |  9 +++++++++
 net/wireless/chan.c          |  3 ++-
 net/wireless/ibss.c          | 24 ++++++++++++++++++++----
 net/wireless/nl80211.c       |  8 ++++++--
 net/wireless/util.c          | 14 ++++++++++----
 6 files changed, 53 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5db5fe24eff6..b1acf36e5f45 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1664,6 +1664,9 @@ struct cfg80211_disassoc_request {
  *	sets/clears %NL80211_STA_FLAG_AUTHORIZED. If true, the driver is
  *	required to assume that the port is unauthorized until authorized by
  *	user space. Otherwise, port is marked authorized by default.
+ * @userspace_handles_dfs: whether user space controls DFS operation, i.e.
+ *	changes the channel when a radar is detected. This is required
+ *	to operate on DFS channels.
  * @basic_rates: bitmap of basic rates to use when creating the IBSS
  * @mcast_rate: per-band multicast rate index + 1 (0: disabled)
  * @ht_capa:  HT Capabilities over-rides.  Values set in ht_capa_mask
@@ -1681,6 +1684,7 @@ struct cfg80211_ibss_params {
 	bool channel_fixed;
 	bool privacy;
 	bool control_port;
+	bool userspace_handles_dfs;
 	int mcast_rate[IEEE80211_NUM_BANDS];
 	struct ieee80211_ht_cap ht_capa;
 	struct ieee80211_ht_cap ht_capa_mask;
@@ -3061,6 +3065,7 @@ struct cfg80211_cached_keys;
  * @conn: (private) cfg80211 software SME connection state machine data
  * @connect_keys: (private) keys to set after connection is established
  * @ibss_fixed: (private) IBSS is using fixed BSSID
+ * @ibss_dfs_possible: (private) IBSS may change to a DFS channel
  * @event_list: (private) list for internal event processing
  * @event_lock: (private) lock for event list
  */
@@ -3099,6 +3104,7 @@ struct wireless_dev {
 	struct ieee80211_channel *channel;
 
 	bool ibss_fixed;
+	bool ibss_dfs_possible;
 
 	bool ps;
 	int ps_timeout;
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f2aef2a7a570..f752e9821e71 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1501,6 +1501,13 @@ enum nl80211_commands {
  * @NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES: array of supported
  *      supported operating classes.
  *
+ * @NL80211_ATTR_HANDLE_DFS: A flag indicating whether user space
+ *	controls DFS operation in IBSS mode. If the flag is included in
+ *	%NL80211_CMD_JOIN_IBSS request, the driver will allow use of DFS
+ *	channels and reports radar events to userspace. Userspace is required
+ *	to react to radar events, e.g. initiate a channel switch or leave the
+ *	IBSS network.
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1815,6 +1822,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES,
 
+	NL80211_ATTR_HANDLE_DFS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 16f3c3a7b2c1..9b8cc877eb19 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -504,7 +504,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 	case NL80211_IFTYPE_ADHOC:
 		if (wdev->current_bss) {
 			*chan = wdev->current_bss->pub.channel;
-			*chanmode = wdev->ibss_fixed
+			*chanmode = (wdev->ibss_fixed &&
+				     !wdev->ibss_dfs_possible)
 				  ? CHAN_MODE_SHARED
 				  : CHAN_MODE_EXCLUSIVE;
 			return;
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 39bff7d36768..fa7461b6ba39 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -83,6 +83,8 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 			 struct cfg80211_cached_keys *connkeys)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct ieee80211_channel *check_chan;
+	u8 radar_detect_width = 0;
 	int err;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -114,14 +116,28 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 	wdev->connect_keys = connkeys;
 
 	wdev->ibss_fixed = params->channel_fixed;
+	wdev->ibss_dfs_possible = params->userspace_handles_dfs;
 #ifdef CONFIG_CFG80211_WEXT
 	wdev->wext.ibss.chandef = params->chandef;
 #endif
+	check_chan = params->chandef.chan;
+	if (params->userspace_handles_dfs) {
+		/* use channel NULL to check for radar even if the current
+		 * channel is not a radar channel - it might decide to change
+		 * to DFS channel later.
+		 */
+		radar_detect_width = BIT(params->chandef.width);
+		check_chan = NULL;
+	}
+
+	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
+					   check_chan,
+					   (params->channel_fixed &&
+					    !radar_detect_width)
+					   ? CHAN_MODE_SHARED
+					   : CHAN_MODE_EXCLUSIVE,
+					   radar_detect_width);
 
-	err = cfg80211_can_use_chan(rdev, wdev, params->chandef.chan,
-				    params->channel_fixed
-				    ? CHAN_MODE_SHARED
-				    : CHAN_MODE_EXCLUSIVE);
 	if (err) {
 		wdev->connect_keys = NULL;
 		return err;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 460638ac2d73..7502d33a3a70 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -356,6 +356,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_U16 },
 	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
+	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -5768,9 +5769,9 @@ skip_beacons:
 	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
 		return -EINVAL;
 
-	/* DFS channels are only supported for AP/P2P GO ... for now. */
 	if (dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
-	    dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) {
+	    dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO ||
+	    dev->ieee80211_ptr->iftype == NL80211_IFTYPE_ADHOC) {
 		err = cfg80211_chandef_dfs_required(wdev->wiphy,
 						    &params.chandef);
 		if (err < 0) {
@@ -6602,6 +6603,9 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	ibss.control_port =
 		nla_get_flag(info->attrs[NL80211_ATTR_CONTROL_PORT]);
 
+	ibss.userspace_handles_dfs =
+		nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS]);
+
 	err = cfg80211_join_ibss(rdev, dev, &ibss, connkeys);
 	if (err)
 		kfree(connkeys);
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 3c8be6104ba4..935dea9485da 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1249,7 +1249,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 	enum cfg80211_chan_mode chmode;
 	int num_different_channels = 0;
 	int total = 1;
-	bool radar_required;
+	bool radar_required = false;
 	int i, j;
 
 	ASSERT_RTNL();
@@ -1264,14 +1264,20 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 	case NL80211_IFTYPE_MESH_POINT:
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_WDS:
-		radar_required = !!(chan &&
-				    (chan->flags & IEEE80211_CHAN_RADAR));
+		/* if the interface could potentially choose a DFS channel,
+		 * then mark DFS as required.
+		 */
+		if (!chan) {
+			if (chanmode != CHAN_MODE_UNDEFINED && radar_detect)
+				radar_required = true;
+			break;
+		}
+		radar_required = !!(chan->flags & IEEE80211_CHAN_RADAR);
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_DEVICE:
 	case NL80211_IFTYPE_MONITOR:
-		radar_required = false;
 		break;
 	case NUM_NL80211_IFTYPES:
 	case NL80211_IFTYPE_UNSPECIFIED:
-- 
cgit 


From 919be62b97e43e48c97a35ff82add1719d56553e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 14 Oct 2013 10:05:16 +0200
Subject: mac80211: add missing IEEE80211_HW_SUPPORTS_HT_CCK_RATES docs

Document the IEEE80211_HW_SUPPORTS_HT_CCK_RATES flag.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index f386c480e134..ecba8a10acf4 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1503,6 +1503,10 @@ struct ieee80211_tx_control {
  * @IEEE80211_HW_TIMING_BEACON_ONLY: Use sync timing from beacon frames
  *	only, to allow getting TBTT of a DTIM beacon.
  *
+ * @IEEE80211_HW_SUPPORTS_HT_CCK_RATES: Hardware supports mixing HT/CCK rates
+ *	and can cope with CCK rates in an aggregation session (e.g. by not
+ *	using aggregation for such frames.)
+ *
  * @IEEE80211_HW_CHANCTX_STA_CSA: Support 802.11h based channel-switch (CSA)
  *	for a single active channel while using channel contexts. When support
  *	is not enabled the default action is to disconnect when getting the
-- 
cgit 


From 034c6d6e675f84ef5e67445150522b2517d963c9 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@do-not-panic.com>
Date: Mon, 14 Oct 2013 17:42:06 -0700
Subject: cfg80211: export reg_initiator_name()

Drivers can now use this to parse the regulatory request and
be more verbose when needed.

Signed-off-by: Luis R. Rodriguez <mcgrof@do-not-panic.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  9 +++++++++
 net/wireless/reg.c     | 26 ++++++++++++++++----------
 2 files changed, 25 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b1acf36e5f45..3eae46cb1acf 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3497,6 +3497,15 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
 const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 					       u32 center_freq);
 
+/**
+ * reg_initiator_name - map regulatory request initiator enum to name
+ * @initiator: the regulatory request initiator
+ *
+ * You can use this to map the regulatory request initiator enum to a
+ * proper string representation.
+ */
+const char *reg_initiator_name(enum nl80211_reg_initiator initiator);
+
 /*
  * callbacks for asynchronous cfg80211 methods, notification
  * functions and BSS handling helpers
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index edb2ba4e2a18..7da67fd0b418 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -768,24 +768,25 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(freq_reg_info);
 
-#ifdef CONFIG_CFG80211_REG_DEBUG
-static const char *reg_initiator_name(enum nl80211_reg_initiator initiator)
+const char *reg_initiator_name(enum nl80211_reg_initiator initiator)
 {
 	switch (initiator) {
 	case NL80211_REGDOM_SET_BY_CORE:
-		return "Set by core";
+		return "core";
 	case NL80211_REGDOM_SET_BY_USER:
-		return "Set by user";
+		return "user";
 	case NL80211_REGDOM_SET_BY_DRIVER:
-		return "Set by driver";
+		return "driver";
 	case NL80211_REGDOM_SET_BY_COUNTRY_IE:
-		return "Set by country IE";
+		return "country IE";
 	default:
 		WARN_ON(1);
-		return "Set by bug";
+		return "bug";
 	}
 }
+EXPORT_SYMBOL(reg_initiator_name);
 
+#ifdef CONFIG_CFG80211_REG_DEBUG
 static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan,
 				    const struct ieee80211_reg_rule *reg_rule)
 {
@@ -986,14 +987,17 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 	struct regulatory_request *lr = get_last_request();
 
 	if (!lr) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since last_request is not set\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since last_request is not set\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
 
 	if (initiator == NL80211_REGDOM_SET_BY_CORE &&
 	    wiphy->flags & WIPHY_FLAG_CUSTOM_REGULATORY) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since the driver uses its own custom regulatory domain\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since the driver uses its own custom "
+			      "regulatory domain\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
@@ -1005,7 +1009,9 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 	if (wiphy_strict_alpha2_regd(wiphy) && !wiphy->regd &&
 	    initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE &&
 	    !is_world_regdom(lr->alpha2)) {
-		REG_DBG_PRINT("Ignoring regulatory request %s since the driver requires its own regulatory domain to be set first\n",
+		REG_DBG_PRINT("Ignoring regulatory request set by %s "
+			      "since the driver requires its own regulatory "
+			      "domain to be set first\n",
 			      reg_initiator_name(initiator));
 		return true;
 	}
-- 
cgit 


From 06be6b149f7e406bcf16098567f5a6c9f042bced Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Mon, 14 Oct 2013 18:01:00 +0200
Subject: mac80211: add ieee80211_tx_prepare_skb() helper function

This can be used by a driver to prepare skbs for transmission, which were
obtained via functions such as ieee80211_probereq_get or
ieee80211_nullfunc_get.

This is useful for drivers that want to send those frames directly, but
need rate control information to be prepared first.

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 14 ++++++++++++++
 net/mac80211/tx.c      | 29 +++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ecba8a10acf4..7ceed99a05bc 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4571,4 +4571,18 @@ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif,
 				    struct cfg80211_wowlan_wakeup *wakeup,
 				    gfp_t gfp);
 
+/**
+ * ieee80211_tx_prepare_skb - prepare an 802.11 skb for transmission
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @vif: virtual interface
+ * @skb: frame to be sent from within the driver
+ * @band: the band to transmit on
+ * @sta: optional pointer to get the station to send the frame to
+ *
+ * Note: must be called under RCU lock
+ */
+bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif, struct sk_buff *skb,
+			      int band, struct ieee80211_sta **sta);
+
 #endif /* MAC80211_H */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 4fcbf634b548..acd9b61fbc07 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1366,6 +1366,35 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx)
 	return 0;
 }
 
+bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif, struct sk_buff *skb,
+			      int band, struct ieee80211_sta **sta)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_data tx;
+
+	if (ieee80211_tx_prepare(sdata, &tx, skb) == TX_DROP)
+		return false;
+
+	info->band = band;
+	info->control.vif = vif;
+	info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)];
+
+	if (invoke_tx_handlers(&tx))
+		return false;
+
+	if (sta) {
+		if (tx.sta)
+			*sta = &tx.sta->sta;
+		else
+			*sta = NULL;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(ieee80211_tx_prepare_skb);
+
 /*
  * Returns false if the frame couldn't be transmitted but was queued instead.
  */
-- 
cgit 


From 8f2535b92d685c68db4bc699dd78462a646f6ef9 Mon Sep 17 00:00:00 2001
From: Chun-Yeow Yeoh <yeohchunyeow@cozybit.com>
Date: Mon, 14 Oct 2013 19:08:27 -0700
Subject: mac80211: process the CSA frame for mesh accordingly

Process the CSA frame according to the procedures define in IEEE Std
802.11-2012 section 10.9.8.4.3 as follow:
* The mesh channel switch parameters element (MCSP) must be availabe.
* If the MCSP's TTL is 1, drop the frame but still process the CSA.
* If the MCSP's precedence value is less than or equal to the current
  precedence value, drop the frame and do not process the CSA.
* The CSA frame is forwarded after TTL is decremented by 1 and the
  initiator field is set to 0. Transmit restrict field and others
  are maintained as is.
* No beacon or probe response frame are handled here.

Also, introduce the debug message used for mesh CSA purpose.

Signed-off-by: Chun-Yeow Yeoh <yeohchunyeow@cozybit.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 20 +++++++++++
 net/mac80211/Kconfig       | 11 ++++++
 net/mac80211/debug.h       | 10 ++++++
 net/mac80211/ieee80211_i.h |  4 +++
 net/mac80211/mesh.c        | 83 ++++++++++++++++++++++++++++++++++++++++++++--
 net/mac80211/util.c        |  9 +++++
 6 files changed, 134 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 7c1e1ebc0e23..8c3b26a21574 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -696,6 +696,18 @@ struct ieee80211_sec_chan_offs_ie {
 	u8 sec_chan_offs;
 } __packed;
 
+/**
+ * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE
+ *
+ * This structure represents the "Mesh Channel Switch Paramters element"
+ */
+struct ieee80211_mesh_chansw_params_ie {
+	u8 mesh_ttl;
+	u8 mesh_flags;
+	__le16 mesh_reason;
+	__le16 mesh_pre_value;
+} __packed;
+
 /**
  * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE
  */
@@ -750,6 +762,14 @@ enum mesh_config_capab_flags {
 	IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL	= 0x40,
 };
 
+/**
+ * mesh channel switch parameters element's flag indicator
+ *
+ */
+#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0)
+#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1)
+#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2)
+
 /**
  * struct ieee80211_rann_ie
  *
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index dc31ec3db404..97b5dcad5025 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -259,6 +259,17 @@ config MAC80211_MESH_SYNC_DEBUG
 
 	  Do not select this option.
 
+config MAC80211_MESH_CSA_DEBUG
+	bool "Verbose mesh channel switch debugging"
+	depends on MAC80211_DEBUG_MENU
+	depends on MAC80211_MESH
+	---help---
+	  Selecting this option causes mac80211 to print out very verbose mesh
+	  channel switch debugging messages (when mac80211 is taking part in a
+	  mesh network).
+
+	  Do not select this option.
+
 config MAC80211_MESH_PS_DEBUG
 	bool "Verbose mesh powersave debugging"
 	depends on MAC80211_DEBUG_MENU
diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index 4ccc5ed6237d..493d68061f0c 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -44,6 +44,12 @@
 #define MAC80211_MESH_SYNC_DEBUG 0
 #endif
 
+#ifdef CONFIG_MAC80211_MESH_CSA_DEBUG
+#define MAC80211_MESH_CSA_DEBUG 1
+#else
+#define MAC80211_MESH_CSA_DEBUG 0
+#endif
+
 #ifdef CONFIG_MAC80211_MESH_PS_DEBUG
 #define MAC80211_MESH_PS_DEBUG 1
 #else
@@ -157,6 +163,10 @@ do {									\
 	_sdata_dbg(MAC80211_MESH_SYNC_DEBUG,				\
 		   sdata, fmt, ##__VA_ARGS__)
 
+#define mcsa_dbg(sdata, fmt, ...)					\
+	_sdata_dbg(MAC80211_MESH_CSA_DEBUG,				\
+		   sdata, fmt, ##__VA_ARGS__)
+
 #define mps_dbg(sdata, fmt, ...)					\
 	_sdata_dbg(MAC80211_MESH_PS_DEBUG,				\
 		   sdata, fmt, ##__VA_ARGS__)
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index cbaea32bccf1..4ebbcc6f67e0 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -603,6 +603,9 @@ struct ieee80211_if_mesh {
 	int ps_peers_light_sleep;
 	int ps_peers_deep_sleep;
 	struct ps_data ps;
+	/* Channel Switching Support */
+	bool chsw_init;
+	u16 pre_value;
 };
 
 #ifdef CONFIG_MAC80211_MESH
@@ -1252,6 +1255,7 @@ struct ieee802_11_elems {
 	const struct ieee80211_timeout_interval_ie *timeout_int;
 	const u8 *opmode_notif;
 	const struct ieee80211_sec_chan_offs_ie *sec_chan_offs;
+	const struct ieee80211_mesh_chansw_params_ie *mesh_chansw_params_ie;
 
 	/* length of them, respectively */
 	u8 ssid_len;
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 707ac61d63e5..0a3ccaa275f9 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -920,6 +920,82 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
 			stype, mgmt, &elems, rx_status);
 }
 
+static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata,
+			       struct ieee80211_mgmt *mgmt, size_t len)
+{
+	struct ieee80211_mgmt *mgmt_fwd;
+	struct sk_buff *skb;
+	struct ieee80211_local *local = sdata->local;
+	u8 *pos = mgmt->u.action.u.chan_switch.variable;
+	size_t offset_ttl;
+
+	skb = dev_alloc_skb(local->tx_headroom + len);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, local->tx_headroom);
+	mgmt_fwd = (struct ieee80211_mgmt *) skb_put(skb, len);
+
+	/* offset_ttl is based on whether the secondary channel
+	 * offset is available or not. Substract 1 from the mesh TTL
+	 * and disable the initiator flag before forwarding.
+	 */
+	offset_ttl = (len < 42) ? 7 : 10;
+	*(pos + offset_ttl) -= 1;
+	*(pos + offset_ttl + 1) &= ~WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR;
+
+	memcpy(mgmt_fwd, mgmt, len);
+	eth_broadcast_addr(mgmt_fwd->da);
+	memcpy(mgmt_fwd->sa, sdata->vif.addr, ETH_ALEN);
+	memcpy(mgmt_fwd->bssid, sdata->vif.addr, ETH_ALEN);
+
+	ieee80211_tx_skb(sdata, skb);
+	return 0;
+}
+
+static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
+			      struct ieee80211_mgmt *mgmt, size_t len)
+{
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	struct ieee802_11_elems elems;
+	u16 pre_value;
+	bool block_tx, fwd_csa = true;
+	size_t baselen;
+	u8 *pos, ttl;
+
+	if (mgmt->u.action.u.measurement.action_code !=
+	    WLAN_ACTION_SPCT_CHL_SWITCH)
+		return;
+
+	pos = mgmt->u.action.u.chan_switch.variable;
+	baselen = offsetof(struct ieee80211_mgmt,
+			   u.action.u.chan_switch.variable);
+	ieee802_11_parse_elems(pos, len - baselen, false, &elems);
+
+	ttl = elems.mesh_chansw_params_ie->mesh_ttl;
+	if (!--ttl)
+		fwd_csa = false;
+
+	pre_value = le16_to_cpu(elems.mesh_chansw_params_ie->mesh_pre_value);
+	if (ifmsh->pre_value >= pre_value)
+		return;
+
+	ifmsh->pre_value = pre_value;
+
+	/* forward or re-broadcast the CSA frame */
+	if (fwd_csa) {
+		if (mesh_fwd_csa_frame(sdata, mgmt, len) < 0)
+			mcsa_dbg(sdata, "Failed to forward the CSA frame");
+	}
+
+	/* block the Tx only after forwarding the CSA frame if required */
+	block_tx = elems.mesh_chansw_params_ie->mesh_flags &
+		   WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT;
+	if (block_tx)
+		ieee80211_stop_queues_by_reason(&sdata->local->hw,
+				IEEE80211_MAX_QUEUE_MAP,
+				IEEE80211_QUEUE_STOP_REASON_CSA);
+}
+
 static void ieee80211_mesh_rx_mgmt_action(struct ieee80211_sub_if_data *sdata,
 					  struct ieee80211_mgmt *mgmt,
 					  size_t len,
@@ -939,6 +1015,9 @@ static void ieee80211_mesh_rx_mgmt_action(struct ieee80211_sub_if_data *sdata,
 		if (mesh_action_is_path_sel(mgmt))
 			mesh_rx_path_sel_frame(sdata, mgmt, len);
 		break;
+	case WLAN_CATEGORY_SPECTRUM_MGMT:
+		mesh_rx_csa_frame(sdata, mgmt, len);
+		break;
 	}
 }
 
@@ -1056,13 +1135,11 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata)
 		    (unsigned long) sdata);
 
 	ifmsh->accepting_plinks = true;
-	ifmsh->preq_id = 0;
-	ifmsh->sn = 0;
-	ifmsh->num_gates = 0;
 	atomic_set(&ifmsh->mpaths, 0);
 	mesh_rmc_init(sdata);
 	ifmsh->last_preq = jiffies;
 	ifmsh->next_perr = jiffies;
+	ifmsh->chsw_init = false;
 	/* Allocate all mesh structures when creating the first mesh interface. */
 	if (!mesh_allocated)
 		ieee80211s_init();
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 65ebe0c5e835..523783cedf6e 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -740,6 +740,7 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_TIMEOUT_INTERVAL:
 		case WLAN_EID_SECONDARY_CHANNEL_OFFSET:
 		case WLAN_EID_WIDE_BW_CHANNEL_SWITCH:
+		case WLAN_EID_CHAN_SWITCH_PARAM:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -905,6 +906,14 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			}
 			elems->sec_chan_offs = (void *)pos;
 			break;
+		case WLAN_EID_CHAN_SWITCH_PARAM:
+			if (elen !=
+			    sizeof(*elems->mesh_chansw_params_ie)) {
+				elem_parse_failed = true;
+				break;
+			}
+			elems->mesh_chansw_params_ie = (void *)pos;
+			break;
 		case WLAN_EID_WIDE_BW_CHANNEL_SWITCH:
 			if (!action ||
 			    elen != sizeof(*elems->wide_bw_chansw_ie)) {
-- 
cgit 


From 4571912743ac6a04a6644e5a292bb9876bb5329b Mon Sep 17 00:00:00 2001
From: Archit Taneja <archit@ti.com>
Date: Wed, 16 Oct 2013 02:36:47 -0300
Subject: [media] v4l: ti-vpe: Add VPE mem to mem driver

VPE is a block which consists of a single memory to memory path which
can perform chrominance up/down sampling, de-interlacing, scaling, and
color space conversion of raster or tiled YUV420 coplanar, YUV422
coplanar or YUV422 interleaved video formats.

We create a mem2mem driver based primarily on the mem2mem-testdev
example. The de-interlacer, scaler and color space converter are all
bypassed for now to keep the driver simple. Chroma up/down sampler
blocks are implemented, so conversion beteen different YUV formats is
possible.

Each mem2mem context allocates a buffer for VPE MMR values which it will
use when it gets access to the VPE HW via the mem2mem queue, it also
allocates a VPDMA descriptor list to which configuration and data
descriptors are added.

Based on the information received via v4l2 ioctls for the source and
destination queues, the driver configures the values for the MMRs, and
stores them in the buffer. There are also some VPDMA parameters like
frame start and line mode which needs to be configured, these are
configured by direct register writes via the VPDMA helper functions.

The driver's device_run() mem2mem op will add each descriptor based on
how the source and destination queues are set up for the given ctx, once
the list is prepared, it's submitted to VPDMA, these descriptors when
parsed by VPDMA will upload MMR registers, start DMA of video buffers on
the various input and output clients/ports.

When the list is parsed completely(and the DMAs on all the output ports
done), an interrupt is generated which we use to notify that the source
and destination buffers are done. The rest of the driver is quite
similar to other mem2mem drivers, we use the multiplane v4l2 ioctls as
the HW support coplanar formats.

Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Kamil Debski <k.debski@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/Kconfig           |   16 +
 drivers/media/platform/Makefile          |    2 +
 drivers/media/platform/ti-vpe/Makefile   |    5 +
 drivers/media/platform/ti-vpe/vpe.c      | 1775 ++++++++++++++++++++++++++++++
 drivers/media/platform/ti-vpe/vpe_regs.h |  496 +++++++++
 include/uapi/linux/v4l2-controls.h       |    4 +
 6 files changed, 2298 insertions(+)
 create mode 100644 drivers/media/platform/ti-vpe/Makefile
 create mode 100644 drivers/media/platform/ti-vpe/vpe.c
 create mode 100644 drivers/media/platform/ti-vpe/vpe_regs.h

(limited to 'include')

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 29acc2d2aee6..2405ef7c6604 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -220,6 +220,22 @@ config VIDEO_RENESAS_VSP1
 	  To compile this driver as a module, choose M here: the module
 	  will be called vsp1.
 
+config VIDEO_TI_VPE
+	tristate "TI VPE (Video Processing Engine) driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && SOC_DRA7XX
+	select VIDEOBUF2_DMA_CONTIG
+	select V4L2_MEM2MEM_DEV
+	default n
+	---help---
+	  Support for the TI VPE(Video Processing Engine) block
+	  found on DRA7XX SoC.
+
+config VIDEO_TI_VPE_DEBUG
+	bool "VPE debug messages"
+	depends on VIDEO_TI_VPE
+	---help---
+	  Enable debug messages on VPE driver.
+
 endif # V4L_MEM2MEM_DRIVERS
 
 menuconfig V4L_TEST_DRIVERS
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 4e4da482c522..1348ba1faf92 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -22,6 +22,8 @@ obj-$(CONFIG_VIDEO_VIVI) += vivi.o
 
 obj-$(CONFIG_VIDEO_MEM2MEM_TESTDEV) += mem2mem_testdev.o
 
+obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
+
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP)		+= mx2_emmaprp.o
 obj-$(CONFIG_VIDEO_CODA) 		+= coda.o
 
diff --git a/drivers/media/platform/ti-vpe/Makefile b/drivers/media/platform/ti-vpe/Makefile
new file mode 100644
index 000000000000..cbf0a806ba1d
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_VIDEO_TI_VPE) += ti-vpe.o
+
+ti-vpe-y := vpe.o vpdma.o
+
+ccflags-$(CONFIG_VIDEO_TI_VPE_DEBUG) += -DDEBUG
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
new file mode 100644
index 000000000000..3bd9ca658b54
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -0,0 +1,1775 @@
+/*
+ * TI VPE mem2mem driver, based on the virtual v4l2-mem2mem example driver
+ *
+ * Copyright (c) 2013 Texas Instruments Inc.
+ * David Griego, <dagriego@biglakesoftware.com>
+ * Dale Farnsworth, <dale@farnsworth.org>
+ * Archit Taneja, <archit@ti.com>
+ *
+ * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
+ * Pawel Osciak, <pawel@osciak.com>
+ * Marek Szyprowski, <m.szyprowski@samsung.com>
+ *
+ * Based on the virtual v4l2-mem2mem example device
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioctl.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "vpdma.h"
+#include "vpe_regs.h"
+
+#define VPE_MODULE_NAME "vpe"
+
+/* minimum and maximum frame sizes */
+#define MIN_W		128
+#define MIN_H		128
+#define MAX_W		1920
+#define MAX_H		1080
+
+/* required alignments */
+#define S_ALIGN		0	/* multiple of 1 */
+#define H_ALIGN		1	/* multiple of 2 */
+#define W_ALIGN		1	/* multiple of 2 */
+
+/* multiple of 128 bits, line stride, 16 bytes */
+#define L_ALIGN		4
+
+/* flags that indicate a format can be used for capture/output */
+#define VPE_FMT_TYPE_CAPTURE	(1 << 0)
+#define VPE_FMT_TYPE_OUTPUT	(1 << 1)
+
+/* used as plane indices */
+#define VPE_MAX_PLANES	2
+#define VPE_LUMA	0
+#define VPE_CHROMA	1
+
+/* per m2m context info */
+#define VPE_DEF_BUFS_PER_JOB	1	/* default one buffer per batch job */
+
+/*
+ * each VPE context can need up to 3 config desciptors, 7 input descriptors,
+ * 3 output descriptors, and 10 control descriptors
+ */
+#define VPE_DESC_LIST_SIZE	(10 * VPDMA_DTD_DESC_SIZE +	\
+					13 * VPDMA_CFD_CTD_DESC_SIZE)
+
+#define vpe_dbg(vpedev, fmt, arg...)	\
+		dev_dbg((vpedev)->v4l2_dev.dev, fmt, ##arg)
+#define vpe_err(vpedev, fmt, arg...)	\
+		dev_err((vpedev)->v4l2_dev.dev, fmt, ##arg)
+
+struct vpe_us_coeffs {
+	unsigned short	anchor_fid0_c0;
+	unsigned short	anchor_fid0_c1;
+	unsigned short	anchor_fid0_c2;
+	unsigned short	anchor_fid0_c3;
+	unsigned short	interp_fid0_c0;
+	unsigned short	interp_fid0_c1;
+	unsigned short	interp_fid0_c2;
+	unsigned short	interp_fid0_c3;
+	unsigned short	anchor_fid1_c0;
+	unsigned short	anchor_fid1_c1;
+	unsigned short	anchor_fid1_c2;
+	unsigned short	anchor_fid1_c3;
+	unsigned short	interp_fid1_c0;
+	unsigned short	interp_fid1_c1;
+	unsigned short	interp_fid1_c2;
+	unsigned short	interp_fid1_c3;
+};
+
+/*
+ * Default upsampler coefficients
+ */
+static const struct vpe_us_coeffs us_coeffs[] = {
+	{
+		/* Coefficients for progressive input */
+		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
+		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
+	},
+};
+
+/*
+ * The port_data structure contains per-port data.
+ */
+struct vpe_port_data {
+	enum vpdma_channel channel;	/* VPDMA channel */
+	u8	vb_part;		/* plane index for co-panar formats */
+};
+
+/*
+ * Define indices into the port_data tables
+ */
+#define VPE_PORT_LUMA1_IN	0
+#define VPE_PORT_CHROMA1_IN	1
+#define VPE_PORT_LUMA_OUT	8
+#define VPE_PORT_CHROMA_OUT	9
+#define VPE_PORT_RGB_OUT	10
+
+static const struct vpe_port_data port_data[11] = {
+	[VPE_PORT_LUMA1_IN] = {
+		.channel	= VPE_CHAN_LUMA1_IN,
+		.vb_part	= VPE_LUMA,
+	},
+	[VPE_PORT_CHROMA1_IN] = {
+		.channel	= VPE_CHAN_CHROMA1_IN,
+		.vb_part	= VPE_CHROMA,
+	},
+	[VPE_PORT_LUMA_OUT] = {
+		.channel	= VPE_CHAN_LUMA_OUT,
+		.vb_part	= VPE_LUMA,
+	},
+	[VPE_PORT_CHROMA_OUT] = {
+		.channel	= VPE_CHAN_CHROMA_OUT,
+		.vb_part	= VPE_CHROMA,
+	},
+	[VPE_PORT_RGB_OUT] = {
+		.channel	= VPE_CHAN_RGB_OUT,
+		.vb_part	= VPE_LUMA,
+	},
+};
+
+
+/* driver info for each of the supported video formats */
+struct vpe_fmt {
+	char	*name;			/* human-readable name */
+	u32	fourcc;			/* standard format identifier */
+	u8	types;			/* CAPTURE and/or OUTPUT */
+	u8	coplanar;		/* set for unpacked Luma and Chroma */
+	/* vpdma format info for each plane */
+	struct vpdma_data_format const *vpdma_fmt[VPE_MAX_PLANES];
+};
+
+static struct vpe_fmt vpe_formats[] = {
+	{
+		.name		= "YUV 422 co-planar",
+		.fourcc		= V4L2_PIX_FMT_NV16,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 1,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y444],
+				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C444],
+				  },
+	},
+	{
+		.name		= "YUV 420 co-planar",
+		.fourcc		= V4L2_PIX_FMT_NV12,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 1,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
+				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C420],
+				  },
+	},
+	{
+		.name		= "YUYV 422 packed",
+		.fourcc		= V4L2_PIX_FMT_YUYV,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_YC422],
+				  },
+	},
+	{
+		.name		= "UYVY 422 packed",
+		.fourcc		= V4L2_PIX_FMT_UYVY,
+		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
+		.coplanar	= 0,
+		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CY422],
+				  },
+	},
+};
+
+/*
+ * per-queue, driver-specific private data.
+ * there is one source queue and one destination queue for each m2m context.
+ */
+struct vpe_q_data {
+	unsigned int		width;				/* frame width */
+	unsigned int		height;				/* frame height */
+	unsigned int		bytesperline[VPE_MAX_PLANES];	/* bytes per line in memory */
+	enum v4l2_colorspace	colorspace;
+	unsigned int		flags;
+	unsigned int		sizeimage[VPE_MAX_PLANES];	/* image size in memory */
+	struct v4l2_rect	c_rect;				/* crop/compose rectangle */
+	struct vpe_fmt		*fmt;				/* format info */
+};
+
+/* vpe_q_data flag bits */
+#define	Q_DATA_FRAME_1D		(1 << 0)
+#define	Q_DATA_MODE_TILED	(1 << 1)
+
+enum {
+	Q_DATA_SRC = 0,
+	Q_DATA_DST = 1,
+};
+
+/* find our format description corresponding to the passed v4l2_format */
+static struct vpe_fmt *find_format(struct v4l2_format *f)
+{
+	struct vpe_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) {
+		fmt = &vpe_formats[k];
+		if (fmt->fourcc == f->fmt.pix.pixelformat)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+/*
+ * there is one vpe_dev structure in the driver, it is shared by
+ * all instances.
+ */
+struct vpe_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	vfd;
+	struct v4l2_m2m_dev	*m2m_dev;
+
+	atomic_t		num_instances;	/* count of driver instances */
+	dma_addr_t		loaded_mmrs;	/* shadow mmrs in device */
+	struct mutex		dev_mutex;
+	spinlock_t		lock;
+
+	int			irq;
+	void __iomem		*base;
+
+	struct vb2_alloc_ctx	*alloc_ctx;
+	struct vpdma_data	*vpdma;		/* vpdma data handle */
+};
+
+/*
+ * There is one vpe_ctx structure for each m2m context.
+ */
+struct vpe_ctx {
+	struct v4l2_fh		fh;
+	struct vpe_dev		*dev;
+	struct v4l2_m2m_ctx	*m2m_ctx;
+	struct v4l2_ctrl_handler hdl;
+
+	unsigned int		sequence;		/* current frame/field seq */
+	unsigned int		aborting;		/* abort after next irq */
+
+	unsigned int		bufs_per_job;		/* input buffers per batch */
+	unsigned int		bufs_completed;		/* bufs done in this batch */
+
+	struct vpe_q_data	q_data[2];		/* src & dst queue data */
+	struct vb2_buffer	*src_vb;
+	struct vb2_buffer	*dst_vb;
+
+	struct vpdma_buf	mmr_adb;		/* shadow reg addr/data block */
+	struct vpdma_desc_list	desc_list;		/* DMA descriptor list */
+
+	bool			load_mmrs;		/* have new shadow reg values */
+};
+
+
+/*
+ * M2M devices get 2 queues.
+ * Return the queue given the type.
+ */
+static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx,
+				     enum v4l2_buf_type type)
+{
+	switch (type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		return &ctx->q_data[Q_DATA_SRC];
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		return &ctx->q_data[Q_DATA_DST];
+	default:
+		BUG();
+	}
+	return NULL;
+}
+
+static u32 read_reg(struct vpe_dev *dev, int offset)
+{
+	return ioread32(dev->base + offset);
+}
+
+static void write_reg(struct vpe_dev *dev, int offset, u32 value)
+{
+	iowrite32(value, dev->base + offset);
+}
+
+/* register field read/write helpers */
+static int get_field(u32 value, u32 mask, int shift)
+{
+	return (value & (mask << shift)) >> shift;
+}
+
+static int read_field_reg(struct vpe_dev *dev, int offset, u32 mask, int shift)
+{
+	return get_field(read_reg(dev, offset), mask, shift);
+}
+
+static void write_field(u32 *valp, u32 field, u32 mask, int shift)
+{
+	u32 val = *valp;
+
+	val &= ~(mask << shift);
+	val |= (field & mask) << shift;
+	*valp = val;
+}
+
+static void write_field_reg(struct vpe_dev *dev, int offset, u32 field,
+		u32 mask, int shift)
+{
+	u32 val = read_reg(dev, offset);
+
+	write_field(&val, field, mask, shift);
+
+	write_reg(dev, offset, val);
+}
+
+/*
+ * DMA address/data block for the shadow registers
+ */
+struct vpe_mmr_adb {
+	struct vpdma_adb_hdr	out_fmt_hdr;
+	u32			out_fmt_reg[1];
+	u32			out_fmt_pad[3];
+	struct vpdma_adb_hdr	us1_hdr;
+	u32			us1_regs[8];
+	struct vpdma_adb_hdr	us2_hdr;
+	u32			us2_regs[8];
+	struct vpdma_adb_hdr	us3_hdr;
+	u32			us3_regs[8];
+	struct vpdma_adb_hdr	dei_hdr;
+	u32			dei_regs[1];
+	u32			dei_pad[3];
+	struct vpdma_adb_hdr	sc_hdr;
+	u32			sc_regs[1];
+	u32			sc_pad[3];
+	struct vpdma_adb_hdr	csc_hdr;
+	u32			csc_regs[6];
+	u32			csc_pad[2];
+};
+
+#define VPE_SET_MMR_ADB_HDR(ctx, hdr, regs, offset_a)	\
+	VPDMA_SET_MMR_ADB_HDR(ctx->mmr_adb, vpe_mmr_adb, hdr, regs, offset_a)
+/*
+ * Set the headers for all of the address/data block structures.
+ */
+static void init_adb_hdrs(struct vpe_ctx *ctx)
+{
+	VPE_SET_MMR_ADB_HDR(ctx, out_fmt_hdr, out_fmt_reg, VPE_CLK_FORMAT_SELECT);
+	VPE_SET_MMR_ADB_HDR(ctx, us1_hdr, us1_regs, VPE_US1_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, us2_hdr, us2_regs, VPE_US2_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, us3_hdr, us3_regs, VPE_US3_R0);
+	VPE_SET_MMR_ADB_HDR(ctx, dei_hdr, dei_regs, VPE_DEI_FRAME_SIZE);
+	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr, sc_regs, VPE_SC_MP_SC0);
+	VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs, VPE_CSC_CSC00);
+};
+
+/*
+ * Enable or disable the VPE clocks
+ */
+static void vpe_set_clock_enable(struct vpe_dev *dev, bool on)
+{
+	u32 val = 0;
+
+	if (on)
+		val = VPE_DATA_PATH_CLK_ENABLE | VPE_VPEDMA_CLK_ENABLE;
+	write_reg(dev, VPE_CLK_ENABLE, val);
+}
+
+static void vpe_top_reset(struct vpe_dev *dev)
+{
+
+	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_DATA_PATH_CLK_RESET_MASK,
+		VPE_DATA_PATH_CLK_RESET_SHIFT);
+
+	usleep_range(100, 150);
+
+	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_DATA_PATH_CLK_RESET_MASK,
+		VPE_DATA_PATH_CLK_RESET_SHIFT);
+}
+
+static void vpe_top_vpdma_reset(struct vpe_dev *dev)
+{
+	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_VPDMA_CLK_RESET_MASK,
+		VPE_VPDMA_CLK_RESET_SHIFT);
+
+	usleep_range(100, 150);
+
+	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_VPDMA_CLK_RESET_MASK,
+		VPE_VPDMA_CLK_RESET_SHIFT);
+}
+
+/*
+ * Load the correct of upsampler coefficients into the shadow MMRs
+ */
+static void set_us_coefficients(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *us1_reg = &mmr_adb->us1_regs[0];
+	u32 *us2_reg = &mmr_adb->us2_regs[0];
+	u32 *us3_reg = &mmr_adb->us3_regs[0];
+	const unsigned short *cp, *end_cp;
+
+	cp = &us_coeffs[0].anchor_fid0_c0;
+
+	end_cp = cp + sizeof(us_coeffs[0]) / sizeof(*cp);
+
+	while (cp < end_cp) {
+		write_field(us1_reg, *cp++, VPE_US_C0_MASK, VPE_US_C0_SHIFT);
+		write_field(us1_reg, *cp++, VPE_US_C1_MASK, VPE_US_C1_SHIFT);
+		*us2_reg++ = *us1_reg;
+		*us3_reg++ = *us1_reg++;
+	}
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the upsampler config mode and the VPDMA line mode in the shadow MMRs.
+ */
+static void set_cfg_and_line_modes(struct vpe_ctx *ctx)
+{
+	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *us1_reg0 = &mmr_adb->us1_regs[0];
+	u32 *us2_reg0 = &mmr_adb->us2_regs[0];
+	u32 *us3_reg0 = &mmr_adb->us3_regs[0];
+	int line_mode = 1;
+	int cfg_mode = 1;
+
+	/*
+	 * Cfg Mode 0: YUV420 source, enable upsampler, DEI is de-interlacing.
+	 * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing.
+	 */
+
+	if (fmt->fourcc == V4L2_PIX_FMT_NV12) {
+		cfg_mode = 0;
+		line_mode = 0;		/* double lines to line buffer */
+	}
+
+	write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+	write_field(us2_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+	write_field(us3_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
+
+	/* regs for now */
+	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA1_IN);
+
+	/* frame start for input luma */
+	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
+		VPE_CHAN_LUMA1_IN);
+
+	/* frame start for input chroma */
+	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
+		VPE_CHAN_CHROMA1_IN);
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the shadow registers that are modified when the source
+ * format changes.
+ */
+static void set_src_registers(struct vpe_ctx *ctx)
+{
+	set_us_coefficients(ctx);
+}
+
+/*
+ * Set the shadow registers that are modified when the destination
+ * format changes.
+ */
+static void set_dst_registers(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt;
+	u32 val = 0;
+
+	/* select RGB path when color space conversion is supported in future */
+	if (fmt->fourcc == V4L2_PIX_FMT_RGB24)
+		val |= VPE_RGB_OUT_SELECT | VPE_CSC_SRC_DEI_SCALER;
+	else if (fmt->fourcc == V4L2_PIX_FMT_NV16)
+		val |= VPE_COLOR_SEPARATE_422;
+
+	/* The source of CHR_DS is always the scaler, whether it's used or not */
+	val |= VPE_DS_SRC_DEI_SCALER;
+
+	if (fmt->fourcc != V4L2_PIX_FMT_NV12)
+		val |= VPE_DS_BYPASS;
+
+	mmr_adb->out_fmt_reg[0] = val;
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the de-interlacer shadow register values
+ */
+static void set_dei_regs_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
+	unsigned int src_h = s_q_data->c_rect.height;
+	unsigned int src_w = s_q_data->c_rect.width;
+	u32 *dei_mmr0 = &mmr_adb->dei_regs[0];
+	u32 val = 0;
+
+	/*
+	 * according to TRM, we should set DEI in progressive bypass mode when
+	 * the input content is progressive, however, DEI is bypassed correctly
+	 * for both progressive and interlace content in interlace bypass mode.
+	 * It has been recommended not to use progressive bypass mode.
+	 */
+	val = VPE_DEI_INTERLACE_BYPASS;
+
+	val |= (src_h << VPE_DEI_HEIGHT_SHIFT) |
+		(src_w << VPE_DEI_WIDTH_SHIFT) |
+		VPE_DEI_FIELD_FLUSH;
+
+	*dei_mmr0 = val;
+
+	ctx->load_mmrs = true;
+}
+
+static void set_csc_coeff_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *shadow_csc_reg5 = &mmr_adb->csc_regs[5];
+
+	*shadow_csc_reg5 |= VPE_CSC_BYPASS;
+
+	ctx->load_mmrs = true;
+}
+
+static void set_sc_regs_bypass(struct vpe_ctx *ctx)
+{
+	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
+	u32 *sc_reg0 = &mmr_adb->sc_regs[0];
+	u32 val = 0;
+
+	val |= VPE_SC_BYPASS;
+	*sc_reg0 = val;
+
+	ctx->load_mmrs = true;
+}
+
+/*
+ * Set the shadow registers whose values are modified when either the
+ * source or destination format is changed.
+ */
+static int set_srcdst_params(struct vpe_ctx *ctx)
+{
+	ctx->sequence = 0;
+
+	set_cfg_and_line_modes(ctx);
+	set_dei_regs_bypass(ctx);
+	set_csc_coeff_bypass(ctx);
+	set_sc_regs_bypass(ctx);
+
+	return 0;
+}
+
+/*
+ * Return the vpe_ctx structure for a given struct file
+ */
+static struct vpe_ctx *file2ctx(struct file *file)
+{
+	return container_of(file->private_data, struct vpe_ctx, fh);
+}
+
+/*
+ * mem2mem callbacks
+ */
+
+/**
+ * job_ready() - check whether an instance is ready to be scheduled to run
+ */
+static int job_ready(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	int needed = ctx->bufs_per_job;
+
+	if (v4l2_m2m_num_src_bufs_ready(ctx->m2m_ctx) < needed)
+		return 0;
+
+	return 1;
+}
+
+static void job_abort(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+
+	/* Will cancel the transaction in the next interrupt handler */
+	ctx->aborting = 1;
+}
+
+/*
+ * Lock access to the device
+ */
+static void vpe_lock(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_dev *dev = ctx->dev;
+	mutex_lock(&dev->dev_mutex);
+}
+
+static void vpe_unlock(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_dev *dev = ctx->dev;
+	mutex_unlock(&dev->dev_mutex);
+}
+
+static void vpe_dump_regs(struct vpe_dev *dev)
+{
+#define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))
+
+	vpe_dbg(dev, "VPE Registers:\n");
+
+	DUMPREG(PID);
+	DUMPREG(SYSCONFIG);
+	DUMPREG(INT0_STATUS0_RAW);
+	DUMPREG(INT0_STATUS0);
+	DUMPREG(INT0_ENABLE0);
+	DUMPREG(INT0_STATUS1_RAW);
+	DUMPREG(INT0_STATUS1);
+	DUMPREG(INT0_ENABLE1);
+	DUMPREG(CLK_ENABLE);
+	DUMPREG(CLK_RESET);
+	DUMPREG(CLK_FORMAT_SELECT);
+	DUMPREG(CLK_RANGE_MAP);
+	DUMPREG(US1_R0);
+	DUMPREG(US1_R1);
+	DUMPREG(US1_R2);
+	DUMPREG(US1_R3);
+	DUMPREG(US1_R4);
+	DUMPREG(US1_R5);
+	DUMPREG(US1_R6);
+	DUMPREG(US1_R7);
+	DUMPREG(US2_R0);
+	DUMPREG(US2_R1);
+	DUMPREG(US2_R2);
+	DUMPREG(US2_R3);
+	DUMPREG(US2_R4);
+	DUMPREG(US2_R5);
+	DUMPREG(US2_R6);
+	DUMPREG(US2_R7);
+	DUMPREG(US3_R0);
+	DUMPREG(US3_R1);
+	DUMPREG(US3_R2);
+	DUMPREG(US3_R3);
+	DUMPREG(US3_R4);
+	DUMPREG(US3_R5);
+	DUMPREG(US3_R6);
+	DUMPREG(US3_R7);
+	DUMPREG(DEI_FRAME_SIZE);
+	DUMPREG(MDT_BYPASS);
+	DUMPREG(MDT_SF_THRESHOLD);
+	DUMPREG(EDI_CONFIG);
+	DUMPREG(DEI_EDI_LUT_R0);
+	DUMPREG(DEI_EDI_LUT_R1);
+	DUMPREG(DEI_EDI_LUT_R2);
+	DUMPREG(DEI_EDI_LUT_R3);
+	DUMPREG(DEI_FMD_WINDOW_R0);
+	DUMPREG(DEI_FMD_WINDOW_R1);
+	DUMPREG(DEI_FMD_CONTROL_R0);
+	DUMPREG(DEI_FMD_CONTROL_R1);
+	DUMPREG(DEI_FMD_STATUS_R0);
+	DUMPREG(DEI_FMD_STATUS_R1);
+	DUMPREG(DEI_FMD_STATUS_R2);
+	DUMPREG(SC_MP_SC0);
+	DUMPREG(SC_MP_SC1);
+	DUMPREG(SC_MP_SC2);
+	DUMPREG(SC_MP_SC3);
+	DUMPREG(SC_MP_SC4);
+	DUMPREG(SC_MP_SC5);
+	DUMPREG(SC_MP_SC6);
+	DUMPREG(SC_MP_SC8);
+	DUMPREG(SC_MP_SC9);
+	DUMPREG(SC_MP_SC10);
+	DUMPREG(SC_MP_SC11);
+	DUMPREG(SC_MP_SC12);
+	DUMPREG(SC_MP_SC13);
+	DUMPREG(SC_MP_SC17);
+	DUMPREG(SC_MP_SC18);
+	DUMPREG(SC_MP_SC19);
+	DUMPREG(SC_MP_SC20);
+	DUMPREG(SC_MP_SC21);
+	DUMPREG(SC_MP_SC22);
+	DUMPREG(SC_MP_SC23);
+	DUMPREG(SC_MP_SC24);
+	DUMPREG(SC_MP_SC25);
+	DUMPREG(CSC_CSC00);
+	DUMPREG(CSC_CSC01);
+	DUMPREG(CSC_CSC02);
+	DUMPREG(CSC_CSC03);
+	DUMPREG(CSC_CSC04);
+	DUMPREG(CSC_CSC05);
+#undef DUMPREG
+}
+
+static void add_out_dtd(struct vpe_ctx *ctx, int port)
+{
+	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_DST];
+	const struct vpe_port_data *p_data = &port_data[port];
+	struct vb2_buffer *vb = ctx->dst_vb;
+	struct v4l2_rect *c_rect = &q_data->c_rect;
+	struct vpe_fmt *fmt = q_data->fmt;
+	const struct vpdma_data_format *vpdma_fmt;
+	int plane = fmt->coplanar ? p_data->vb_part : 0;
+	dma_addr_t dma_addr;
+	u32 flags = 0;
+
+	vpdma_fmt = fmt->vpdma_fmt[plane];
+	dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
+	if (!dma_addr) {
+		vpe_err(ctx->dev,
+			"acquiring output buffer(%d) dma_addr failed\n",
+			port);
+		return;
+	}
+
+	if (q_data->flags & Q_DATA_FRAME_1D)
+		flags |= VPDMA_DATA_FRAME_1D;
+	if (q_data->flags & Q_DATA_MODE_TILED)
+		flags |= VPDMA_DATA_MODE_TILED;
+
+	vpdma_add_out_dtd(&ctx->desc_list, c_rect, vpdma_fmt, dma_addr,
+		p_data->channel, flags);
+}
+
+static void add_in_dtd(struct vpe_ctx *ctx, int port)
+{
+	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_SRC];
+	const struct vpe_port_data *p_data = &port_data[port];
+	struct vb2_buffer *vb = ctx->src_vb;
+	struct v4l2_rect *c_rect = &q_data->c_rect;
+	struct vpe_fmt *fmt = q_data->fmt;
+	const struct vpdma_data_format *vpdma_fmt;
+	int plane = fmt->coplanar ? p_data->vb_part : 0;
+	int field = 0;
+	dma_addr_t dma_addr;
+	u32 flags = 0;
+
+	vpdma_fmt = fmt->vpdma_fmt[plane];
+
+	dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
+	if (!dma_addr) {
+		vpe_err(ctx->dev,
+			"acquiring input buffer(%d) dma_addr failed\n",
+			port);
+		return;
+	}
+
+	if (q_data->flags & Q_DATA_FRAME_1D)
+		flags |= VPDMA_DATA_FRAME_1D;
+	if (q_data->flags & Q_DATA_MODE_TILED)
+		flags |= VPDMA_DATA_MODE_TILED;
+
+	vpdma_add_in_dtd(&ctx->desc_list, q_data->width, q_data->height,
+		c_rect, vpdma_fmt, dma_addr, p_data->channel, field, flags);
+}
+
+/*
+ * Enable the expected IRQ sources
+ */
+static void enable_irqs(struct vpe_ctx *ctx)
+{
+	write_reg(ctx->dev, VPE_INT0_ENABLE0_SET, VPE_INT0_LIST0_COMPLETE);
+	write_reg(ctx->dev, VPE_INT0_ENABLE1_SET, VPE_DS1_UV_ERROR_INT);
+
+	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, true);
+}
+
+static void disable_irqs(struct vpe_ctx *ctx)
+{
+	write_reg(ctx->dev, VPE_INT0_ENABLE0_CLR, 0xffffffff);
+	write_reg(ctx->dev, VPE_INT0_ENABLE1_CLR, 0xffffffff);
+
+	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, false);
+}
+
+/* device_run() - prepares and starts the device
+ *
+ * This function is only called when both the source and destination
+ * buffers are in place.
+ */
+static void device_run(void *priv)
+{
+	struct vpe_ctx *ctx = priv;
+	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
+
+	ctx->src_vb = v4l2_m2m_src_buf_remove(ctx->m2m_ctx);
+	WARN_ON(ctx->src_vb == NULL);
+	ctx->dst_vb = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
+	WARN_ON(ctx->dst_vb == NULL);
+
+	/* config descriptors */
+	if (ctx->dev->loaded_mmrs != ctx->mmr_adb.dma_addr || ctx->load_mmrs) {
+		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->mmr_adb);
+		vpdma_add_cfd_adb(&ctx->desc_list, CFD_MMR_CLIENT, &ctx->mmr_adb);
+		ctx->dev->loaded_mmrs = ctx->mmr_adb.dma_addr;
+		ctx->load_mmrs = false;
+	}
+
+	add_out_dtd(ctx, VPE_PORT_LUMA_OUT);
+	if (d_q_data->fmt->coplanar)
+		add_out_dtd(ctx, VPE_PORT_CHROMA_OUT);
+
+	add_in_dtd(ctx, VPE_PORT_LUMA1_IN);
+	add_in_dtd(ctx, VPE_PORT_CHROMA1_IN);
+
+	/* sync on channel control descriptors for input ports */
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA1_IN);
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA1_IN);
+
+	/* sync on channel control descriptors for output ports */
+	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA_OUT);
+	if (d_q_data->fmt->coplanar)
+		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA_OUT);
+
+	enable_irqs(ctx);
+
+	vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->desc_list.buf);
+	vpdma_submit_descs(ctx->dev->vpdma, &ctx->desc_list);
+}
+
+static void ds1_uv_error(struct vpe_ctx *ctx)
+{
+	dev_warn(ctx->dev->v4l2_dev.dev,
+		"received downsampler error interrupt\n");
+}
+
+static irqreturn_t vpe_irq(int irq_vpe, void *data)
+{
+	struct vpe_dev *dev = (struct vpe_dev *)data;
+	struct vpe_ctx *ctx;
+	struct vb2_buffer *s_vb, *d_vb;
+	struct v4l2_buffer *s_buf, *d_buf;
+	unsigned long flags;
+	u32 irqst0, irqst1;
+
+	irqst0 = read_reg(dev, VPE_INT0_STATUS0);
+	if (irqst0) {
+		write_reg(dev, VPE_INT0_STATUS0_CLR, irqst0);
+		vpe_dbg(dev, "INT0_STATUS0 = 0x%08x\n", irqst0);
+	}
+
+	irqst1 = read_reg(dev, VPE_INT0_STATUS1);
+	if (irqst1) {
+		write_reg(dev, VPE_INT0_STATUS1_CLR, irqst1);
+		vpe_dbg(dev, "INT0_STATUS1 = 0x%08x\n", irqst1);
+	}
+
+	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
+	if (!ctx) {
+		vpe_err(dev, "instance released before end of transaction\n");
+		goto handled;
+	}
+
+	if (irqst1 & VPE_DS1_UV_ERROR_INT) {
+		irqst1 &= ~VPE_DS1_UV_ERROR_INT;
+		ds1_uv_error(ctx);
+	}
+
+	if (irqst0) {
+		if (irqst0 & VPE_INT0_LIST0_COMPLETE)
+			vpdma_clear_list_stat(ctx->dev->vpdma);
+
+		irqst0 &= ~(VPE_INT0_LIST0_COMPLETE);
+	}
+
+	if (irqst0 | irqst1) {
+		dev_warn(dev->v4l2_dev.dev, "Unexpected interrupt: "
+			"INT0_STATUS0 = 0x%08x, INT0_STATUS1 = 0x%08x\n",
+			irqst0, irqst1);
+	}
+
+	disable_irqs(ctx);
+
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
+	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
+
+	vpdma_reset_desc_list(&ctx->desc_list);
+
+	if (ctx->aborting)
+		goto finished;
+
+	s_vb = ctx->src_vb;
+	d_vb = ctx->dst_vb;
+	s_buf = &s_vb->v4l2_buf;
+	d_buf = &d_vb->v4l2_buf;
+
+	d_buf->timestamp = s_buf->timestamp;
+	if (s_buf->flags & V4L2_BUF_FLAG_TIMECODE) {
+		d_buf->flags |= V4L2_BUF_FLAG_TIMECODE;
+		d_buf->timecode = s_buf->timecode;
+	}
+
+	d_buf->sequence = ctx->sequence;
+
+	ctx->sequence++;
+
+	spin_lock_irqsave(&dev->lock, flags);
+	v4l2_m2m_buf_done(s_vb, VB2_BUF_STATE_DONE);
+	v4l2_m2m_buf_done(d_vb, VB2_BUF_STATE_DONE);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	ctx->bufs_completed++;
+	if (ctx->bufs_completed < ctx->bufs_per_job) {
+		device_run(ctx);
+		goto handled;
+	}
+
+finished:
+	vpe_dbg(ctx->dev, "finishing transaction\n");
+	ctx->bufs_completed = 0;
+	v4l2_m2m_job_finish(dev->m2m_dev, ctx->m2m_ctx);
+handled:
+	return IRQ_HANDLED;
+}
+
+/*
+ * video ioctls
+ */
+static int vpe_querycap(struct file *file, void *priv,
+			struct v4l2_capability *cap)
+{
+	strncpy(cap->driver, VPE_MODULE_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, VPE_MODULE_NAME, sizeof(cap->card) - 1);
+	strlcpy(cap->bus_info, VPE_MODULE_NAME, sizeof(cap->bus_info));
+	cap->device_caps  = V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int __enum_fmt(struct v4l2_fmtdesc *f, u32 type)
+{
+	int i, index;
+	struct vpe_fmt *fmt = NULL;
+
+	index = 0;
+	for (i = 0; i < ARRAY_SIZE(vpe_formats); ++i) {
+		if (vpe_formats[i].types & type) {
+			if (index == f->index) {
+				fmt = &vpe_formats[i];
+				break;
+			}
+			index++;
+		}
+	}
+
+	if (!fmt)
+		return -EINVAL;
+
+	strncpy(f->description, fmt->name, sizeof(f->description) - 1);
+	f->pixelformat = fmt->fourcc;
+	return 0;
+}
+
+static int vpe_enum_fmt(struct file *file, void *priv,
+				struct v4l2_fmtdesc *f)
+{
+	if (V4L2_TYPE_IS_OUTPUT(f->type))
+		return __enum_fmt(f, VPE_FMT_TYPE_OUTPUT);
+
+	return __enum_fmt(f, VPE_FMT_TYPE_CAPTURE);
+}
+
+static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vb2_queue *vq;
+	struct vpe_q_data *q_data;
+	int i;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+
+	pix->width = q_data->width;
+	pix->height = q_data->height;
+	pix->pixelformat = q_data->fmt->fourcc;
+
+	if (V4L2_TYPE_IS_OUTPUT(f->type)) {
+		pix->colorspace = q_data->colorspace;
+	} else {
+		struct vpe_q_data *s_q_data;
+
+		/* get colorspace from the source queue */
+		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+
+		pix->colorspace = s_q_data->colorspace;
+	}
+
+	pix->num_planes = q_data->fmt->coplanar ? 2 : 1;
+
+	for (i = 0; i < pix->num_planes; i++) {
+		pix->plane_fmt[i].bytesperline = q_data->bytesperline[i];
+		pix->plane_fmt[i].sizeimage = q_data->sizeimage[i];
+	}
+
+	return 0;
+}
+
+static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
+		       struct vpe_fmt *fmt, int type)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct v4l2_plane_pix_format *plane_fmt;
+	int i;
+
+	if (!fmt || !(fmt->types & type)) {
+		vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
+			pix->pixelformat);
+		return -EINVAL;
+	}
+
+	pix->field = V4L2_FIELD_NONE;
+
+	v4l_bound_align_image(&pix->width, MIN_W, MAX_W, W_ALIGN,
+			      &pix->height, MIN_H, MAX_H, H_ALIGN,
+			      S_ALIGN);
+
+	pix->num_planes = fmt->coplanar ? 2 : 1;
+	pix->pixelformat = fmt->fourcc;
+
+	if (type == VPE_FMT_TYPE_CAPTURE) {
+		struct vpe_q_data *s_q_data;
+
+		/* get colorspace from the source queue */
+		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+
+		pix->colorspace = s_q_data->colorspace;
+	} else {
+		if (!pix->colorspace)
+			pix->colorspace = V4L2_COLORSPACE_SMPTE240M;
+	}
+
+	for (i = 0; i < pix->num_planes; i++) {
+		int depth;
+
+		plane_fmt = &pix->plane_fmt[i];
+		depth = fmt->vpdma_fmt[i]->depth;
+
+		if (i == VPE_LUMA)
+			plane_fmt->bytesperline =
+					round_up((pix->width * depth) >> 3,
+						1 << L_ALIGN);
+		else
+			plane_fmt->bytesperline = pix->width;
+
+		plane_fmt->sizeimage =
+				(pix->height * pix->width * depth) >> 3;
+	}
+
+	return 0;
+}
+
+static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_fmt *fmt = find_format(f);
+
+	if (V4L2_TYPE_IS_OUTPUT(f->type))
+		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_OUTPUT);
+	else
+		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_CAPTURE);
+}
+
+static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
+	struct v4l2_plane_pix_format *plane_fmt;
+	struct vpe_q_data *q_data;
+	struct vb2_queue *vq;
+	int i;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	if (vb2_is_busy(vq)) {
+		vpe_err(ctx->dev, "queue busy\n");
+		return -EBUSY;
+	}
+
+	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
+
+	q_data->fmt		= find_format(f);
+	q_data->width		= pix->width;
+	q_data->height		= pix->height;
+	q_data->colorspace	= pix->colorspace;
+
+	for (i = 0; i < pix->num_planes; i++) {
+		plane_fmt = &pix->plane_fmt[i];
+
+		q_data->bytesperline[i]	= plane_fmt->bytesperline;
+		q_data->sizeimage[i]	= plane_fmt->sizeimage;
+	}
+
+	q_data->c_rect.left	= 0;
+	q_data->c_rect.top	= 0;
+	q_data->c_rect.width	= q_data->width;
+	q_data->c_rect.height	= q_data->height;
+
+	vpe_dbg(ctx->dev, "Setting format for type %d, wxh: %dx%d, fmt: %d bpl_y %d",
+		f->type, q_data->width, q_data->height, q_data->fmt->fourcc,
+		q_data->bytesperline[VPE_LUMA]);
+	if (q_data->fmt->coplanar)
+		vpe_dbg(ctx->dev, " bpl_uv %d\n",
+			q_data->bytesperline[VPE_CHROMA]);
+
+	return 0;
+}
+
+static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
+{
+	int ret;
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	ret = vpe_try_fmt(file, priv, f);
+	if (ret)
+		return ret;
+
+	ret = __vpe_s_fmt(ctx, f);
+	if (ret)
+		return ret;
+
+	if (V4L2_TYPE_IS_OUTPUT(f->type))
+		set_src_registers(ctx);
+	else
+		set_dst_registers(ctx);
+
+	return set_srcdst_params(ctx);
+}
+
+static int vpe_reqbufs(struct file *file, void *priv,
+		       struct v4l2_requestbuffers *reqbufs)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	return v4l2_m2m_reqbufs(file, ctx->m2m_ctx, reqbufs);
+}
+
+static int vpe_querybuf(struct file *file, void *priv, struct v4l2_buffer *buf)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	return v4l2_m2m_querybuf(file, ctx->m2m_ctx, buf);
+}
+
+static int vpe_qbuf(struct file *file, void *priv, struct v4l2_buffer *buf)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	return v4l2_m2m_qbuf(file, ctx->m2m_ctx, buf);
+}
+
+static int vpe_dqbuf(struct file *file, void *priv, struct v4l2_buffer *buf)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	return v4l2_m2m_dqbuf(file, ctx->m2m_ctx, buf);
+}
+
+static int vpe_streamon(struct file *file, void *priv, enum v4l2_buf_type type)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	return v4l2_m2m_streamon(file, ctx->m2m_ctx, type);
+}
+
+static int vpe_streamoff(struct file *file, void *priv, enum v4l2_buf_type type)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	vpe_dump_regs(ctx->dev);
+	vpdma_dump_regs(ctx->dev->vpdma);
+
+	return v4l2_m2m_streamoff(file, ctx->m2m_ctx, type);
+}
+
+/*
+ * defines number of buffers/frames a context can process with VPE before
+ * switching to a different context. default value is 1 buffer per context
+ */
+#define V4L2_CID_VPE_BUFS_PER_JOB		(V4L2_CID_USER_TI_VPE_BASE + 0)
+
+static int vpe_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vpe_ctx *ctx =
+		container_of(ctrl->handler, struct vpe_ctx, hdl);
+
+	switch (ctrl->id) {
+	case V4L2_CID_VPE_BUFS_PER_JOB:
+		ctx->bufs_per_job = ctrl->val;
+		break;
+
+	default:
+		vpe_err(ctx->dev, "Invalid control\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vpe_ctrl_ops = {
+	.s_ctrl = vpe_s_ctrl,
+};
+
+static const struct v4l2_ioctl_ops vpe_ioctl_ops = {
+	.vidioc_querycap	= vpe_querycap,
+
+	.vidioc_enum_fmt_vid_cap_mplane = vpe_enum_fmt,
+	.vidioc_g_fmt_vid_cap_mplane	= vpe_g_fmt,
+	.vidioc_try_fmt_vid_cap_mplane	= vpe_try_fmt,
+	.vidioc_s_fmt_vid_cap_mplane	= vpe_s_fmt,
+
+	.vidioc_enum_fmt_vid_out_mplane = vpe_enum_fmt,
+	.vidioc_g_fmt_vid_out_mplane	= vpe_g_fmt,
+	.vidioc_try_fmt_vid_out_mplane	= vpe_try_fmt,
+	.vidioc_s_fmt_vid_out_mplane	= vpe_s_fmt,
+
+	.vidioc_reqbufs		= vpe_reqbufs,
+	.vidioc_querybuf	= vpe_querybuf,
+
+	.vidioc_qbuf		= vpe_qbuf,
+	.vidioc_dqbuf		= vpe_dqbuf,
+
+	.vidioc_streamon	= vpe_streamon,
+	.vidioc_streamoff	= vpe_streamoff,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+/*
+ * Queue operations
+ */
+static int vpe_queue_setup(struct vb2_queue *vq,
+			   const struct v4l2_format *fmt,
+			   unsigned int *nbuffers, unsigned int *nplanes,
+			   unsigned int sizes[], void *alloc_ctxs[])
+{
+	int i;
+	struct vpe_ctx *ctx = vb2_get_drv_priv(vq);
+	struct vpe_q_data *q_data;
+
+	q_data = get_q_data(ctx, vq->type);
+
+	*nplanes = q_data->fmt->coplanar ? 2 : 1;
+
+	for (i = 0; i < *nplanes; i++) {
+		sizes[i] = q_data->sizeimage[i];
+		alloc_ctxs[i] = ctx->dev->alloc_ctx;
+	}
+
+	vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers,
+		sizes[VPE_LUMA]);
+	if (q_data->fmt->coplanar)
+		vpe_dbg(ctx->dev, " and %d\n", sizes[VPE_CHROMA]);
+
+	return 0;
+}
+
+static int vpe_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct vpe_q_data *q_data;
+	int i, num_planes;
+
+	vpe_dbg(ctx->dev, "type: %d\n", vb->vb2_queue->type);
+
+	q_data = get_q_data(ctx, vb->vb2_queue->type);
+	num_planes = q_data->fmt->coplanar ? 2 : 1;
+
+	for (i = 0; i < num_planes; i++) {
+		if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) {
+			vpe_err(ctx->dev,
+				"data will not fit into plane (%lu < %lu)\n",
+				vb2_plane_size(vb, i),
+				(long) q_data->sizeimage[i]);
+			return -EINVAL;
+		}
+	}
+
+	for (i = 0; i < num_planes; i++)
+		vb2_set_plane_payload(vb, i, q_data->sizeimage[i]);
+
+	return 0;
+}
+
+static void vpe_buf_queue(struct vb2_buffer *vb)
+{
+	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	v4l2_m2m_buf_queue(ctx->m2m_ctx, vb);
+}
+
+static void vpe_wait_prepare(struct vb2_queue *q)
+{
+	struct vpe_ctx *ctx = vb2_get_drv_priv(q);
+	vpe_unlock(ctx);
+}
+
+static void vpe_wait_finish(struct vb2_queue *q)
+{
+	struct vpe_ctx *ctx = vb2_get_drv_priv(q);
+	vpe_lock(ctx);
+}
+
+static struct vb2_ops vpe_qops = {
+	.queue_setup	 = vpe_queue_setup,
+	.buf_prepare	 = vpe_buf_prepare,
+	.buf_queue	 = vpe_buf_queue,
+	.wait_prepare	 = vpe_wait_prepare,
+	.wait_finish	 = vpe_wait_finish,
+};
+
+static int queue_init(void *priv, struct vb2_queue *src_vq,
+		      struct vb2_queue *dst_vq)
+{
+	struct vpe_ctx *ctx = priv;
+	int ret;
+
+	memset(src_vq, 0, sizeof(*src_vq));
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
+	src_vq->io_modes = VB2_MMAP;
+	src_vq->drv_priv = ctx;
+	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	src_vq->ops = &vpe_qops;
+	src_vq->mem_ops = &vb2_dma_contig_memops;
+	src_vq->timestamp_type = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	memset(dst_vq, 0, sizeof(*dst_vq));
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	dst_vq->io_modes = VB2_MMAP;
+	dst_vq->drv_priv = ctx;
+	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->ops = &vpe_qops;
+	dst_vq->mem_ops = &vb2_dma_contig_memops;
+	dst_vq->timestamp_type = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+
+	return vb2_queue_init(dst_vq);
+}
+
+static const struct v4l2_ctrl_config vpe_bufs_per_job = {
+	.ops = &vpe_ctrl_ops,
+	.id = V4L2_CID_VPE_BUFS_PER_JOB,
+	.name = "Buffers Per Transaction",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.def = VPE_DEF_BUFS_PER_JOB,
+	.min = 1,
+	.max = VIDEO_MAX_FRAME,
+	.step = 1,
+};
+
+/*
+ * File operations
+ */
+static int vpe_open(struct file *file)
+{
+	struct vpe_dev *dev = video_drvdata(file);
+	struct vpe_ctx *ctx = NULL;
+	struct vpe_q_data *s_q_data;
+	struct v4l2_ctrl_handler *hdl;
+	int ret;
+
+	vpe_dbg(dev, "vpe_open\n");
+
+	if (!dev->vpdma->ready) {
+		vpe_err(dev, "vpdma firmware not loaded\n");
+		return -ENODEV;
+	}
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->dev = dev;
+
+	if (mutex_lock_interruptible(&dev->dev_mutex)) {
+		ret = -ERESTARTSYS;
+		goto free_ctx;
+	}
+
+	ret = vpdma_create_desc_list(&ctx->desc_list, VPE_DESC_LIST_SIZE,
+			VPDMA_LIST_TYPE_NORMAL);
+	if (ret != 0)
+		goto unlock;
+
+	ret = vpdma_alloc_desc_buf(&ctx->mmr_adb, sizeof(struct vpe_mmr_adb));
+	if (ret != 0)
+		goto free_desc_list;
+
+	init_adb_hdrs(ctx);
+
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+
+	hdl = &ctx->hdl;
+	v4l2_ctrl_handler_init(hdl, 1);
+	v4l2_ctrl_new_custom(hdl, &vpe_bufs_per_job, NULL);
+	if (hdl->error) {
+		ret = hdl->error;
+		goto exit_fh;
+	}
+	ctx->fh.ctrl_handler = hdl;
+	v4l2_ctrl_handler_setup(hdl);
+
+	s_q_data = &ctx->q_data[Q_DATA_SRC];
+	s_q_data->fmt = &vpe_formats[2];
+	s_q_data->width = 1920;
+	s_q_data->height = 1080;
+	s_q_data->sizeimage[VPE_LUMA] = (s_q_data->width * s_q_data->height *
+			s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
+	s_q_data->colorspace = V4L2_COLORSPACE_SMPTE240M;
+	s_q_data->c_rect.left = 0;
+	s_q_data->c_rect.top = 0;
+	s_q_data->c_rect.width = s_q_data->width;
+	s_q_data->c_rect.height = s_q_data->height;
+	s_q_data->flags = 0;
+
+	ctx->q_data[Q_DATA_DST] = *s_q_data;
+
+	set_src_registers(ctx);
+	set_dst_registers(ctx);
+	ret = set_srcdst_params(ctx);
+	if (ret)
+		goto exit_fh;
+
+	ctx->m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx, &queue_init);
+
+	if (IS_ERR(ctx->m2m_ctx)) {
+		ret = PTR_ERR(ctx->m2m_ctx);
+		goto exit_fh;
+	}
+
+	v4l2_fh_add(&ctx->fh);
+
+	/*
+	 * for now, just report the creation of the first instance, we can later
+	 * optimize the driver to enable or disable clocks when the first
+	 * instance is created or the last instance released
+	 */
+	if (atomic_inc_return(&dev->num_instances) == 1)
+		vpe_dbg(dev, "first instance created\n");
+
+	ctx->bufs_per_job = VPE_DEF_BUFS_PER_JOB;
+
+	ctx->load_mmrs = true;
+
+	vpe_dbg(dev, "created instance %p, m2m_ctx: %p\n",
+		ctx, ctx->m2m_ctx);
+
+	mutex_unlock(&dev->dev_mutex);
+
+	return 0;
+exit_fh:
+	v4l2_ctrl_handler_free(hdl);
+	v4l2_fh_exit(&ctx->fh);
+	vpdma_free_desc_buf(&ctx->mmr_adb);
+free_desc_list:
+	vpdma_free_desc_list(&ctx->desc_list);
+unlock:
+	mutex_unlock(&dev->dev_mutex);
+free_ctx:
+	kfree(ctx);
+	return ret;
+}
+
+static int vpe_release(struct file *file)
+{
+	struct vpe_dev *dev = video_drvdata(file);
+	struct vpe_ctx *ctx = file2ctx(file);
+
+	vpe_dbg(dev, "releasing instance %p\n", ctx);
+
+	mutex_lock(&dev->dev_mutex);
+	vpdma_free_desc_list(&ctx->desc_list);
+	vpdma_free_desc_buf(&ctx->mmr_adb);
+
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	v4l2_ctrl_handler_free(&ctx->hdl);
+	v4l2_m2m_ctx_release(ctx->m2m_ctx);
+
+	kfree(ctx);
+
+	/*
+	 * for now, just report the release of the last instance, we can later
+	 * optimize the driver to enable or disable clocks when the first
+	 * instance is created or the last instance released
+	 */
+	if (atomic_dec_return(&dev->num_instances) == 0)
+		vpe_dbg(dev, "last instance released\n");
+
+	mutex_unlock(&dev->dev_mutex);
+
+	return 0;
+}
+
+static unsigned int vpe_poll(struct file *file,
+			     struct poll_table_struct *wait)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_dev *dev = ctx->dev;
+	int ret;
+
+	mutex_lock(&dev->dev_mutex);
+	ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait);
+	mutex_unlock(&dev->dev_mutex);
+	return ret;
+}
+
+static int vpe_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct vpe_ctx *ctx = file2ctx(file);
+	struct vpe_dev *dev = ctx->dev;
+	int ret;
+
+	if (mutex_lock_interruptible(&dev->dev_mutex))
+		return -ERESTARTSYS;
+	ret = v4l2_m2m_mmap(file, ctx->m2m_ctx, vma);
+	mutex_unlock(&dev->dev_mutex);
+	return ret;
+}
+
+static const struct v4l2_file_operations vpe_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vpe_open,
+	.release	= vpe_release,
+	.poll		= vpe_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= vpe_mmap,
+};
+
+static struct video_device vpe_videodev = {
+	.name		= VPE_MODULE_NAME,
+	.fops		= &vpe_fops,
+	.ioctl_ops	= &vpe_ioctl_ops,
+	.minor		= -1,
+	.release	= video_device_release,
+	.vfl_dir	= VFL_DIR_M2M,
+};
+
+static struct v4l2_m2m_ops m2m_ops = {
+	.device_run	= device_run,
+	.job_ready	= job_ready,
+	.job_abort	= job_abort,
+	.lock		= vpe_lock,
+	.unlock		= vpe_unlock,
+};
+
+static int vpe_runtime_get(struct platform_device *pdev)
+{
+	int r;
+
+	dev_dbg(&pdev->dev, "vpe_runtime_get\n");
+
+	r = pm_runtime_get_sync(&pdev->dev);
+	WARN_ON(r < 0);
+	return r < 0 ? r : 0;
+}
+
+static void vpe_runtime_put(struct platform_device *pdev)
+{
+
+	int r;
+
+	dev_dbg(&pdev->dev, "vpe_runtime_put\n");
+
+	r = pm_runtime_put_sync(&pdev->dev);
+	WARN_ON(r < 0 && r != -ENOSYS);
+}
+
+static int vpe_probe(struct platform_device *pdev)
+{
+	struct vpe_dev *dev;
+	struct video_device *vfd;
+	struct resource *res;
+	int ret, irq, func;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
+
+	spin_lock_init(&dev->lock);
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret)
+		return ret;
+
+	atomic_set(&dev->num_instances, 0);
+	mutex_init(&dev->dev_mutex);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpe_top");
+	/*
+	 * HACK: we get resource info from device tree in the form of a list of
+	 * VPE sub blocks, the driver currently uses only the base of vpe_top
+	 * for register access, the driver should be changed later to access
+	 * registers based on the sub block base addresses
+	 */
+	dev->base = devm_ioremap(&pdev->dev, res->start, SZ_32K);
+	if (IS_ERR(dev->base)) {
+		ret = PTR_ERR(dev->base);
+		goto v4l2_dev_unreg;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(&pdev->dev, irq, vpe_irq, 0, VPE_MODULE_NAME,
+			dev);
+	if (ret)
+		goto v4l2_dev_unreg;
+
+	platform_set_drvdata(pdev, dev);
+
+	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
+	if (IS_ERR(dev->alloc_ctx)) {
+		vpe_err(dev, "Failed to alloc vb2 context\n");
+		ret = PTR_ERR(dev->alloc_ctx);
+		goto v4l2_dev_unreg;
+	}
+
+	dev->m2m_dev = v4l2_m2m_init(&m2m_ops);
+	if (IS_ERR(dev->m2m_dev)) {
+		vpe_err(dev, "Failed to init mem2mem device\n");
+		ret = PTR_ERR(dev->m2m_dev);
+		goto rel_ctx;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = vpe_runtime_get(pdev);
+	if (ret)
+		goto rel_m2m;
+
+	/* Perform clk enable followed by reset */
+	vpe_set_clock_enable(dev, 1);
+
+	vpe_top_reset(dev);
+
+	func = read_field_reg(dev, VPE_PID, VPE_PID_FUNC_MASK,
+		VPE_PID_FUNC_SHIFT);
+	vpe_dbg(dev, "VPE PID function %x\n", func);
+
+	vpe_top_vpdma_reset(dev);
+
+	dev->vpdma = vpdma_create(pdev);
+	if (IS_ERR(dev->vpdma))
+		goto runtime_put;
+
+	vfd = &dev->vfd;
+	*vfd = vpe_videodev;
+	vfd->lock = &dev->dev_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		vpe_err(dev, "Failed to register video device\n");
+		goto runtime_put;
+	}
+
+	video_set_drvdata(vfd, dev);
+	snprintf(vfd->name, sizeof(vfd->name), "%s", vpe_videodev.name);
+	dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n",
+		vfd->num);
+
+	return 0;
+
+runtime_put:
+	vpe_runtime_put(pdev);
+rel_m2m:
+	pm_runtime_disable(&pdev->dev);
+	v4l2_m2m_release(dev->m2m_dev);
+rel_ctx:
+	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+v4l2_dev_unreg:
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return ret;
+}
+
+static int vpe_remove(struct platform_device *pdev)
+{
+	struct vpe_dev *dev =
+		(struct vpe_dev *) platform_get_drvdata(pdev);
+
+	v4l2_info(&dev->v4l2_dev, "Removing " VPE_MODULE_NAME);
+
+	v4l2_m2m_release(dev->m2m_dev);
+	video_unregister_device(&dev->vfd);
+	v4l2_device_unregister(&dev->v4l2_dev);
+	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+
+	vpe_set_clock_enable(dev, 0);
+	vpe_runtime_put(pdev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#if defined(CONFIG_OF)
+static const struct of_device_id vpe_of_match[] = {
+	{
+		.compatible = "ti,vpe",
+	},
+	{},
+};
+#else
+#define vpe_of_match NULL
+#endif
+
+static struct platform_driver vpe_pdrv = {
+	.probe		= vpe_probe,
+	.remove		= vpe_remove,
+	.driver		= {
+		.name	= VPE_MODULE_NAME,
+		.owner	= THIS_MODULE,
+		.of_match_table = vpe_of_match,
+	},
+};
+
+static void __exit vpe_exit(void)
+{
+	platform_driver_unregister(&vpe_pdrv);
+}
+
+static int __init vpe_init(void)
+{
+	return platform_driver_register(&vpe_pdrv);
+}
+
+module_init(vpe_init);
+module_exit(vpe_exit);
+
+MODULE_DESCRIPTION("TI VPE driver");
+MODULE_AUTHOR("Dale Farnsworth, <dale@farnsworth.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/ti-vpe/vpe_regs.h b/drivers/media/platform/ti-vpe/vpe_regs.h
new file mode 100644
index 000000000000..ed214e828398
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/vpe_regs.h
@@ -0,0 +1,496 @@
+/*
+ * Copyright (c) 2013 Texas Instruments Inc.
+ *
+ * David Griego, <dagriego@biglakesoftware.com>
+ * Dale Farnsworth, <dale@farnsworth.org>
+ * Archit Taneja, <archit@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef __TI_VPE_REGS_H
+#define __TI_VPE_REGS_H
+
+/* VPE register offsets and field selectors */
+
+/* VPE top level regs */
+#define VPE_PID				0x0000
+#define VPE_PID_MINOR_MASK		0x3f
+#define VPE_PID_MINOR_SHIFT		0
+#define VPE_PID_CUSTOM_MASK		0x03
+#define VPE_PID_CUSTOM_SHIFT		6
+#define VPE_PID_MAJOR_MASK		0x07
+#define VPE_PID_MAJOR_SHIFT		8
+#define VPE_PID_RTL_MASK		0x1f
+#define VPE_PID_RTL_SHIFT		11
+#define VPE_PID_FUNC_MASK		0xfff
+#define VPE_PID_FUNC_SHIFT		16
+#define VPE_PID_SCHEME_MASK		0x03
+#define VPE_PID_SCHEME_SHIFT		30
+
+#define VPE_SYSCONFIG			0x0010
+#define VPE_SYSCONFIG_IDLE_MASK		0x03
+#define VPE_SYSCONFIG_IDLE_SHIFT	2
+#define VPE_SYSCONFIG_STANDBY_MASK	0x03
+#define VPE_SYSCONFIG_STANDBY_SHIFT	4
+#define VPE_FORCE_IDLE_MODE		0
+#define VPE_NO_IDLE_MODE		1
+#define VPE_SMART_IDLE_MODE		2
+#define VPE_SMART_IDLE_WAKEUP_MODE	3
+#define VPE_FORCE_STANDBY_MODE		0
+#define VPE_NO_STANDBY_MODE		1
+#define VPE_SMART_STANDBY_MODE		2
+#define VPE_SMART_STANDBY_WAKEUP_MODE	3
+
+#define VPE_INT0_STATUS0_RAW_SET	0x0020
+#define VPE_INT0_STATUS0_RAW		VPE_INT0_STATUS0_RAW_SET
+#define VPE_INT0_STATUS0_CLR		0x0028
+#define VPE_INT0_STATUS0		VPE_INT0_STATUS0_CLR
+#define VPE_INT0_ENABLE0_SET		0x0030
+#define VPE_INT0_ENABLE0		VPE_INT0_ENABLE0_SET
+#define VPE_INT0_ENABLE0_CLR		0x0038
+#define VPE_INT0_LIST0_COMPLETE		(1 << 0)
+#define VPE_INT0_LIST0_NOTIFY		(1 << 1)
+#define VPE_INT0_LIST1_COMPLETE		(1 << 2)
+#define VPE_INT0_LIST1_NOTIFY		(1 << 3)
+#define VPE_INT0_LIST2_COMPLETE		(1 << 4)
+#define VPE_INT0_LIST2_NOTIFY		(1 << 5)
+#define VPE_INT0_LIST3_COMPLETE		(1 << 6)
+#define VPE_INT0_LIST3_NOTIFY		(1 << 7)
+#define VPE_INT0_LIST4_COMPLETE		(1 << 8)
+#define VPE_INT0_LIST4_NOTIFY		(1 << 9)
+#define VPE_INT0_LIST5_COMPLETE		(1 << 10)
+#define VPE_INT0_LIST5_NOTIFY		(1 << 11)
+#define VPE_INT0_LIST6_COMPLETE		(1 << 12)
+#define VPE_INT0_LIST6_NOTIFY		(1 << 13)
+#define VPE_INT0_LIST7_COMPLETE		(1 << 14)
+#define VPE_INT0_LIST7_NOTIFY		(1 << 15)
+#define VPE_INT0_DESCRIPTOR		(1 << 16)
+#define VPE_DEI_FMD_INT			(1 << 18)
+
+#define VPE_INT0_STATUS1_RAW_SET	0x0024
+#define VPE_INT0_STATUS1_RAW		VPE_INT0_STATUS1_RAW_SET
+#define VPE_INT0_STATUS1_CLR		0x002c
+#define VPE_INT0_STATUS1		VPE_INT0_STATUS1_CLR
+#define VPE_INT0_ENABLE1_SET		0x0034
+#define VPE_INT0_ENABLE1		VPE_INT0_ENABLE1_SET
+#define VPE_INT0_ENABLE1_CLR		0x003c
+#define VPE_INT0_CHANNEL_GROUP0		(1 << 0)
+#define VPE_INT0_CHANNEL_GROUP1		(1 << 1)
+#define VPE_INT0_CHANNEL_GROUP2		(1 << 2)
+#define VPE_INT0_CHANNEL_GROUP3		(1 << 3)
+#define VPE_INT0_CHANNEL_GROUP4		(1 << 4)
+#define VPE_INT0_CHANNEL_GROUP5		(1 << 5)
+#define VPE_INT0_CLIENT			(1 << 7)
+#define VPE_DEI_ERROR_INT		(1 << 16)
+#define VPE_DS1_UV_ERROR_INT		(1 << 22)
+
+#define VPE_INTC_EOI			0x00a0
+
+#define VPE_CLK_ENABLE			0x0100
+#define VPE_VPEDMA_CLK_ENABLE		(1 << 0)
+#define VPE_DATA_PATH_CLK_ENABLE	(1 << 1)
+
+#define VPE_CLK_RESET			0x0104
+#define VPE_VPDMA_CLK_RESET_MASK	0x1
+#define VPE_VPDMA_CLK_RESET_SHIFT	0
+#define VPE_DATA_PATH_CLK_RESET_MASK	0x1
+#define VPE_DATA_PATH_CLK_RESET_SHIFT	1
+#define VPE_MAIN_RESET_MASK		0x1
+#define VPE_MAIN_RESET_SHIFT		31
+
+#define VPE_CLK_FORMAT_SELECT		0x010c
+#define VPE_CSC_SRC_SELECT_MASK		0x03
+#define VPE_CSC_SRC_SELECT_SHIFT	0
+#define VPE_RGB_OUT_SELECT		(1 << 8)
+#define VPE_DS_SRC_SELECT_MASK		0x07
+#define VPE_DS_SRC_SELECT_SHIFT		9
+#define VPE_DS_BYPASS			(1 << 16)
+#define VPE_COLOR_SEPARATE_422		(1 << 18)
+
+#define VPE_DS_SRC_DEI_SCALER		(5 << VPE_DS_SRC_SELECT_SHIFT)
+#define VPE_CSC_SRC_DEI_SCALER		(3 << VPE_CSC_SRC_SELECT_SHIFT)
+
+#define VPE_CLK_RANGE_MAP		0x011c
+#define VPE_RANGE_RANGE_MAP_Y_MASK	0x07
+#define VPE_RANGE_RANGE_MAP_Y_SHIFT	0
+#define VPE_RANGE_RANGE_MAP_UV_MASK	0x07
+#define VPE_RANGE_RANGE_MAP_UV_SHIFT	3
+#define VPE_RANGE_MAP_ON		(1 << 6)
+#define VPE_RANGE_REDUCTION_ON		(1 << 28)
+
+/* VPE chrominance upsampler regs */
+#define VPE_US1_R0			0x0304
+#define VPE_US2_R0			0x0404
+#define VPE_US3_R0			0x0504
+#define VPE_US_C1_MASK			0x3fff
+#define VPE_US_C1_SHIFT			2
+#define VPE_US_C0_MASK			0x3fff
+#define VPE_US_C0_SHIFT			18
+#define VPE_US_MODE_MASK		0x03
+#define VPE_US_MODE_SHIFT		16
+#define VPE_ANCHOR_FID0_C1_MASK		0x3fff
+#define VPE_ANCHOR_FID0_C1_SHIFT	2
+#define VPE_ANCHOR_FID0_C0_MASK		0x3fff
+#define VPE_ANCHOR_FID0_C0_SHIFT	18
+
+#define VPE_US1_R1			0x0308
+#define VPE_US2_R1			0x0408
+#define VPE_US3_R1			0x0508
+#define VPE_ANCHOR_FID0_C3_MASK		0x3fff
+#define VPE_ANCHOR_FID0_C3_SHIFT	2
+#define VPE_ANCHOR_FID0_C2_MASK		0x3fff
+#define VPE_ANCHOR_FID0_C2_SHIFT	18
+
+#define VPE_US1_R2			0x030c
+#define VPE_US2_R2			0x040c
+#define VPE_US3_R2			0x050c
+#define VPE_INTERP_FID0_C1_MASK		0x3fff
+#define VPE_INTERP_FID0_C1_SHIFT	2
+#define VPE_INTERP_FID0_C0_MASK		0x3fff
+#define VPE_INTERP_FID0_C0_SHIFT	18
+
+#define VPE_US1_R3			0x0310
+#define VPE_US2_R3			0x0410
+#define VPE_US3_R3			0x0510
+#define VPE_INTERP_FID0_C3_MASK		0x3fff
+#define VPE_INTERP_FID0_C3_SHIFT	2
+#define VPE_INTERP_FID0_C2_MASK		0x3fff
+#define VPE_INTERP_FID0_C2_SHIFT	18
+
+#define VPE_US1_R4			0x0314
+#define VPE_US2_R4			0x0414
+#define VPE_US3_R4			0x0514
+#define VPE_ANCHOR_FID1_C1_MASK		0x3fff
+#define VPE_ANCHOR_FID1_C1_SHIFT	2
+#define VPE_ANCHOR_FID1_C0_MASK		0x3fff
+#define VPE_ANCHOR_FID1_C0_SHIFT	18
+
+#define VPE_US1_R5			0x0318
+#define VPE_US2_R5			0x0418
+#define VPE_US3_R5			0x0518
+#define VPE_ANCHOR_FID1_C3_MASK		0x3fff
+#define VPE_ANCHOR_FID1_C3_SHIFT	2
+#define VPE_ANCHOR_FID1_C2_MASK		0x3fff
+#define VPE_ANCHOR_FID1_C2_SHIFT	18
+
+#define VPE_US1_R6			0x031c
+#define VPE_US2_R6			0x041c
+#define VPE_US3_R6			0x051c
+#define VPE_INTERP_FID1_C1_MASK		0x3fff
+#define VPE_INTERP_FID1_C1_SHIFT	2
+#define VPE_INTERP_FID1_C0_MASK		0x3fff
+#define VPE_INTERP_FID1_C0_SHIFT	18
+
+#define VPE_US1_R7			0x0320
+#define VPE_US2_R7			0x0420
+#define VPE_US3_R7			0x0520
+#define VPE_INTERP_FID0_C3_MASK		0x3fff
+#define VPE_INTERP_FID0_C3_SHIFT	2
+#define VPE_INTERP_FID0_C2_MASK		0x3fff
+#define VPE_INTERP_FID0_C2_SHIFT	18
+
+/* VPE de-interlacer regs */
+#define VPE_DEI_FRAME_SIZE		0x0600
+#define VPE_DEI_WIDTH_MASK		0x07ff
+#define VPE_DEI_WIDTH_SHIFT		0
+#define VPE_DEI_HEIGHT_MASK		0x07ff
+#define VPE_DEI_HEIGHT_SHIFT		16
+#define VPE_DEI_INTERLACE_BYPASS	(1 << 29)
+#define VPE_DEI_FIELD_FLUSH		(1 << 30)
+#define VPE_DEI_PROGRESSIVE		(1 << 31)
+
+#define VPE_MDT_BYPASS			0x0604
+#define VPE_MDT_TEMPMAX_BYPASS		(1 << 0)
+#define VPE_MDT_SPATMAX_BYPASS		(1 << 1)
+
+#define VPE_MDT_SF_THRESHOLD		0x0608
+#define VPE_MDT_SF_SC_THR1_MASK		0xff
+#define VPE_MDT_SF_SC_THR1_SHIFT	0
+#define VPE_MDT_SF_SC_THR2_MASK		0xff
+#define VPE_MDT_SF_SC_THR2_SHIFT	0
+#define VPE_MDT_SF_SC_THR3_MASK		0xff
+#define VPE_MDT_SF_SC_THR3_SHIFT	0
+
+#define VPE_EDI_CONFIG			0x060c
+#define VPE_EDI_INP_MODE_MASK		0x03
+#define VPE_EDI_INP_MODE_SHIFT		0
+#define VPE_EDI_ENABLE_3D		(1 << 2)
+#define VPE_EDI_ENABLE_CHROMA_3D	(1 << 3)
+#define VPE_EDI_CHROMA3D_COR_THR_MASK	0xff
+#define VPE_EDI_CHROMA3D_COR_THR_SHIFT	8
+#define VPE_EDI_DIR_COR_LOWER_THR_MASK	0xff
+#define VPE_EDI_DIR_COR_LOWER_THR_SHIFT	16
+#define VPE_EDI_COR_SCALE_FACTOR_MASK	0xff
+#define VPE_EDI_COR_SCALE_FACTOR_SHIFT	23
+
+#define VPE_DEI_EDI_LUT_R0		0x0610
+#define VPE_EDI_LUT0_MASK		0x1f
+#define VPE_EDI_LUT0_SHIFT		0
+#define VPE_EDI_LUT1_MASK		0x1f
+#define VPE_EDI_LUT1_SHIFT		8
+#define VPE_EDI_LUT2_MASK		0x1f
+#define VPE_EDI_LUT2_SHIFT		16
+#define VPE_EDI_LUT3_MASK		0x1f
+#define VPE_EDI_LUT3_SHIFT		24
+
+#define VPE_DEI_EDI_LUT_R1		0x0614
+#define VPE_EDI_LUT0_MASK		0x1f
+#define VPE_EDI_LUT0_SHIFT		0
+#define VPE_EDI_LUT1_MASK		0x1f
+#define VPE_EDI_LUT1_SHIFT		8
+#define VPE_EDI_LUT2_MASK		0x1f
+#define VPE_EDI_LUT2_SHIFT		16
+#define VPE_EDI_LUT3_MASK		0x1f
+#define VPE_EDI_LUT3_SHIFT		24
+
+#define VPE_DEI_EDI_LUT_R2		0x0618
+#define VPE_EDI_LUT4_MASK		0x1f
+#define VPE_EDI_LUT4_SHIFT		0
+#define VPE_EDI_LUT5_MASK		0x1f
+#define VPE_EDI_LUT5_SHIFT		8
+#define VPE_EDI_LUT6_MASK		0x1f
+#define VPE_EDI_LUT6_SHIFT		16
+#define VPE_EDI_LUT7_MASK		0x1f
+#define VPE_EDI_LUT7_SHIFT		24
+
+#define VPE_DEI_EDI_LUT_R3		0x061c
+#define VPE_EDI_LUT8_MASK		0x1f
+#define VPE_EDI_LUT8_SHIFT		0
+#define VPE_EDI_LUT9_MASK		0x1f
+#define VPE_EDI_LUT9_SHIFT		8
+#define VPE_EDI_LUT10_MASK		0x1f
+#define VPE_EDI_LUT10_SHIFT		16
+#define VPE_EDI_LUT11_MASK		0x1f
+#define VPE_EDI_LUT11_SHIFT		24
+
+#define VPE_DEI_FMD_WINDOW_R0		0x0620
+#define VPE_FMD_WINDOW_MINX_MASK	0x07ff
+#define VPE_FMD_WINDOW_MINX_SHIFT	0
+#define VPE_FMD_WINDOW_MAXX_MASK	0x07ff
+#define VPE_FMD_WINDOW_MAXX_SHIFT	16
+#define VPE_FMD_WINDOW_ENABLE		(1 << 31)
+
+#define VPE_DEI_FMD_WINDOW_R1		0x0624
+#define VPE_FMD_WINDOW_MINY_MASK	0x07ff
+#define VPE_FMD_WINDOW_MINY_SHIFT	0
+#define VPE_FMD_WINDOW_MAXY_MASK	0x07ff
+#define VPE_FMD_WINDOW_MAXY_SHIFT	16
+
+#define VPE_DEI_FMD_CONTROL_R0		0x0628
+#define VPE_FMD_ENABLE			(1 << 0)
+#define VPE_FMD_LOCK			(1 << 1)
+#define VPE_FMD_JAM_DIR			(1 << 2)
+#define VPE_FMD_BED_ENABLE		(1 << 3)
+#define VPE_FMD_CAF_FIELD_THR_MASK	0xff
+#define VPE_FMD_CAF_FIELD_THR_SHIFT	16
+#define VPE_FMD_CAF_LINE_THR_MASK	0xff
+#define VPE_FMD_CAF_LINE_THR_SHIFT	24
+
+#define VPE_DEI_FMD_CONTROL_R1		0x062c
+#define VPE_FMD_CAF_THR_MASK		0x000fffff
+#define VPE_FMD_CAF_THR_SHIFT		0
+
+#define VPE_DEI_FMD_STATUS_R0		0x0630
+#define VPE_FMD_CAF_MASK		0x000fffff
+#define VPE_FMD_CAF_SHIFT		0
+#define VPE_FMD_RESET			(1 << 24)
+
+#define VPE_DEI_FMD_STATUS_R1		0x0634
+#define VPE_FMD_FIELD_DIFF_MASK		0x0fffffff
+#define VPE_FMD_FIELD_DIFF_SHIFT	0
+
+#define VPE_DEI_FMD_STATUS_R2		0x0638
+#define VPE_FMD_FRAME_DIFF_MASK		0x000fffff
+#define VPE_FMD_FRAME_DIFF_SHIFT	0
+
+/* VPE scaler regs */
+#define VPE_SC_MP_SC0			0x0700
+#define VPE_INTERLACE_O			(1 << 0)
+#define VPE_LINEAR			(1 << 1)
+#define VPE_SC_BYPASS			(1 << 2)
+#define VPE_INVT_FID			(1 << 3)
+#define VPE_USE_RAV			(1 << 4)
+#define VPE_ENABLE_EV			(1 << 5)
+#define VPE_AUTO_HS			(1 << 6)
+#define VPE_DCM_2X			(1 << 7)
+#define VPE_DCM_4X			(1 << 8)
+#define VPE_HP_BYPASS			(1 << 9)
+#define VPE_INTERLACE_I			(1 << 10)
+#define VPE_ENABLE_SIN2_VER_INTP	(1 << 11)
+#define VPE_Y_PK_EN			(1 << 14)
+#define VPE_TRIM			(1 << 15)
+#define VPE_SELFGEN_FID			(1 << 16)
+
+#define VPE_SC_MP_SC1			0x0704
+#define VPE_ROW_ACC_INC_MASK		0x07ffffff
+#define VPE_ROW_ACC_INC_SHIFT		0
+
+#define VPE_SC_MP_SC2			0x0708
+#define VPE_ROW_ACC_OFFSET_MASK		0x0fffffff
+#define VPE_ROW_ACC_OFFSET_SHIFT	0
+
+#define VPE_SC_MP_SC3			0x070c
+#define VPE_ROW_ACC_OFFSET_B_MASK	0x0fffffff
+#define VPE_ROW_ACC_OFFSET_B_SHIFT	0
+
+#define VPE_SC_MP_SC4			0x0710
+#define VPE_TAR_H_MASK			0x07ff
+#define VPE_TAR_H_SHIFT			0
+#define VPE_TAR_W_MASK			0x07ff
+#define VPE_TAR_W_SHIFT			12
+#define VPE_LIN_ACC_INC_U_MASK		0x07
+#define VPE_LIN_ACC_INC_U_SHIFT		24
+#define VPE_NLIN_ACC_INIT_U_MASK	0x07
+#define VPE_NLIN_ACC_INIT_U_SHIFT	28
+
+#define VPE_SC_MP_SC5			0x0714
+#define VPE_SRC_H_MASK			0x07ff
+#define VPE_SRC_H_SHIFT			0
+#define VPE_SRC_W_MASK			0x07ff
+#define VPE_SRC_W_SHIFT			12
+#define VPE_NLIN_ACC_INC_U_MASK		0x07
+#define VPE_NLIN_ACC_INC_U_SHIFT	24
+
+#define VPE_SC_MP_SC6			0x0718
+#define VPE_ROW_ACC_INIT_RAV_MASK	0x03ff
+#define VPE_ROW_ACC_INIT_RAV_SHIFT	0
+#define VPE_ROW_ACC_INIT_RAV_B_MASK	0x03ff
+#define VPE_ROW_ACC_INIT_RAV_B_SHIFT	10
+
+#define VPE_SC_MP_SC8			0x0720
+#define VPE_NLIN_LEFT_MASK		0x07ff
+#define VPE_NLIN_LEFT_SHIFT		0
+#define VPE_NLIN_RIGHT_MASK		0x07ff
+#define VPE_NLIN_RIGHT_SHIFT		12
+
+#define VPE_SC_MP_SC9			0x0724
+#define VPE_LIN_ACC_INC			VPE_SC_MP_SC9
+
+#define VPE_SC_MP_SC10			0x0728
+#define VPE_NLIN_ACC_INIT		VPE_SC_MP_SC10
+
+#define VPE_SC_MP_SC11			0x072c
+#define VPE_NLIN_ACC_INC		VPE_SC_MP_SC11
+
+#define VPE_SC_MP_SC12			0x0730
+#define VPE_COL_ACC_OFFSET_MASK		0x01ffffff
+#define VPE_COL_ACC_OFFSET_SHIFT	0
+
+#define VPE_SC_MP_SC13			0x0734
+#define VPE_SC_FACTOR_RAV_MASK		0x03ff
+#define VPE_SC_FACTOR_RAV_SHIFT		0
+#define VPE_CHROMA_INTP_THR_MASK	0x03ff
+#define VPE_CHROMA_INTP_THR_SHIFT	12
+#define VPE_DELTA_CHROMA_THR_MASK	0x0f
+#define VPE_DELTA_CHROMA_THR_SHIFT	24
+
+#define VPE_SC_MP_SC17			0x0744
+#define VPE_EV_THR_MASK			0x03ff
+#define VPE_EV_THR_SHIFT		12
+#define VPE_DELTA_LUMA_THR_MASK		0x0f
+#define VPE_DELTA_LUMA_THR_SHIFT	24
+#define VPE_DELTA_EV_THR_MASK		0x0f
+#define VPE_DELTA_EV_THR_SHIFT		28
+
+#define VPE_SC_MP_SC18			0x0748
+#define VPE_HS_FACTOR_MASK		0x03ff
+#define VPE_HS_FACTOR_SHIFT		0
+#define VPE_CONF_DEFAULT_MASK		0x01ff
+#define VPE_CONF_DEFAULT_SHIFT		16
+
+#define VPE_SC_MP_SC19			0x074c
+#define VPE_HPF_COEFF0_MASK		0xff
+#define VPE_HPF_COEFF0_SHIFT		0
+#define VPE_HPF_COEFF1_MASK		0xff
+#define VPE_HPF_COEFF1_SHIFT		8
+#define VPE_HPF_COEFF2_MASK		0xff
+#define VPE_HPF_COEFF2_SHIFT		16
+#define VPE_HPF_COEFF3_MASK		0xff
+#define VPE_HPF_COEFF3_SHIFT		23
+
+#define VPE_SC_MP_SC20			0x0750
+#define VPE_HPF_COEFF4_MASK		0xff
+#define VPE_HPF_COEFF4_SHIFT		0
+#define VPE_HPF_COEFF5_MASK		0xff
+#define VPE_HPF_COEFF5_SHIFT		8
+#define VPE_HPF_NORM_SHIFT_MASK		0x07
+#define VPE_HPF_NORM_SHIFT_SHIFT	16
+#define VPE_NL_LIMIT_MASK		0x1ff
+#define VPE_NL_LIMIT_SHIFT		20
+
+#define VPE_SC_MP_SC21			0x0754
+#define VPE_NL_LO_THR_MASK		0x01ff
+#define VPE_NL_LO_THR_SHIFT		0
+#define VPE_NL_LO_SLOPE_MASK		0xff
+#define VPE_NL_LO_SLOPE_SHIFT		16
+
+#define VPE_SC_MP_SC22			0x0758
+#define VPE_NL_HI_THR_MASK		0x01ff
+#define VPE_NL_HI_THR_SHIFT		0
+#define VPE_NL_HI_SLOPE_SH_MASK		0x07
+#define VPE_NL_HI_SLOPE_SH_SHIFT	16
+
+#define VPE_SC_MP_SC23			0x075c
+#define VPE_GRADIENT_THR_MASK		0x07ff
+#define VPE_GRADIENT_THR_SHIFT		0
+#define VPE_GRADIENT_THR_RANGE_MASK	0x0f
+#define VPE_GRADIENT_THR_RANGE_SHIFT	12
+#define VPE_MIN_GY_THR_MASK		0xff
+#define VPE_MIN_GY_THR_SHIFT		16
+#define VPE_MIN_GY_THR_RANGE_MASK	0x0f
+#define VPE_MIN_GY_THR_RANGE_SHIFT	28
+
+#define VPE_SC_MP_SC24			0x0760
+#define VPE_ORG_H_MASK			0x07ff
+#define VPE_ORG_H_SHIFT			0
+#define VPE_ORG_W_MASK			0x07ff
+#define VPE_ORG_W_SHIFT			16
+
+#define VPE_SC_MP_SC25			0x0764
+#define VPE_OFF_H_MASK			0x07ff
+#define VPE_OFF_H_SHIFT			0
+#define VPE_OFF_W_MASK			0x07ff
+#define VPE_OFF_W_SHIFT			16
+
+/* VPE color space converter regs */
+#define VPE_CSC_CSC00			0x5700
+#define VPE_CSC_A0_MASK			0x1fff
+#define VPE_CSC_A0_SHIFT		0
+#define VPE_CSC_B0_MASK			0x1fff
+#define VPE_CSC_B0_SHIFT		16
+
+#define VPE_CSC_CSC01			0x5704
+#define VPE_CSC_C0_MASK			0x1fff
+#define VPE_CSC_C0_SHIFT		0
+#define VPE_CSC_A1_MASK			0x1fff
+#define VPE_CSC_A1_SHIFT		16
+
+#define VPE_CSC_CSC02			0x5708
+#define VPE_CSC_B1_MASK			0x1fff
+#define VPE_CSC_B1_SHIFT		0
+#define VPE_CSC_C1_MASK			0x1fff
+#define VPE_CSC_C1_SHIFT		16
+
+#define VPE_CSC_CSC03			0x570c
+#define VPE_CSC_A2_MASK			0x1fff
+#define VPE_CSC_A2_SHIFT		0
+#define VPE_CSC_B2_MASK			0x1fff
+#define VPE_CSC_B2_SHIFT		16
+
+#define VPE_CSC_CSC04			0x5710
+#define VPE_CSC_C2_MASK			0x1fff
+#define VPE_CSC_C2_SHIFT		0
+#define VPE_CSC_D0_MASK			0x0fff
+#define VPE_CSC_D0_SHIFT		16
+
+#define VPE_CSC_CSC05			0x5714
+#define VPE_CSC_D1_MASK			0x0fff
+#define VPE_CSC_D1_SHIFT		0
+#define VPE_CSC_D2_MASK			0x0fff
+#define VPE_CSC_D2_SHIFT		16
+#define VPE_CSC_BYPASS			(1 << 28)
+
+#endif
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 083bb5a5aae2..1666aabbbb86 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -160,6 +160,10 @@ enum v4l2_colorfx {
  * of controls. Total of 16 controls is reserved for this driver */
 #define V4L2_CID_USER_SI476X_BASE		(V4L2_CID_USER_BASE + 0x1040)
 
+/* The base for the TI VPE driver controls. Total of 16 controls is reserved for
+ * this driver */
+#define V4L2_CID_USER_TI_VPE_BASE		(V4L2_CID_USER_BASE + 0x1050)
+
 /* MPEG-class control IDs */
 /* The MPEG controls are applicable to all codec controls
  * and the 'MPEG' part of the define is historical */
-- 
cgit 


From 40b00b6b17c412ff9ff28631250d32ee29ff0006 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Thu, 17 Oct 2013 14:12:23 -0400
Subject: SUNRPC: Add a helper to switch the transport of an rpc_clnt

Add an RPC client API to redirect an rpc_clnt's transport from a
source server to a destination server during a migration event.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
[ cel: forward ported to 3.12 ]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/sunrpc/clnt.h |   4 ++
 net/sunrpc/clnt.c           | 107 +++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 104 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 943ee895f2d1..8af2804bab16 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -136,6 +136,10 @@ void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt);
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
 struct rpc_clnt *rpc_clone_client_set_auth(struct rpc_clnt *,
 				rpc_authflavor_t);
+int		rpc_switch_client_transport(struct rpc_clnt *,
+				struct xprt_create *,
+				const struct rpc_timeout *);
+
 void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
 void		rpc_task_release_client(struct rpc_task *);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 587f31e0577e..f167d9c8d7dd 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -25,6 +25,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
 #include <linux/in.h>
@@ -264,6 +265,25 @@ void rpc_clients_notifier_unregister(void)
 	return rpc_pipefs_notifier_unregister(&rpc_clients_block);
 }
 
+static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt,
+		struct rpc_xprt *xprt,
+		const struct rpc_timeout *timeout)
+{
+	struct rpc_xprt *old;
+
+	spin_lock(&clnt->cl_lock);
+	old = clnt->cl_xprt;
+
+	if (!xprt_bound(xprt))
+		clnt->cl_autobind = 1;
+
+	clnt->cl_timeout = timeout;
+	rcu_assign_pointer(clnt->cl_xprt, xprt);
+	spin_unlock(&clnt->cl_lock);
+
+	return old;
+}
+
 static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename)
 {
 	clnt->cl_nodelen = strlen(nodename);
@@ -338,7 +358,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 {
 	const struct rpc_program *program = args->program;
 	const struct rpc_version *version;
-	struct rpc_clnt		*clnt = NULL;
+	struct rpc_clnt *clnt = NULL;
+	const struct rpc_timeout *timeout;
 	int err;
 
 	/* sanity check the name before trying to print it */
@@ -366,7 +387,6 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 	if (err)
 		goto out_no_clid;
 
-	rcu_assign_pointer(clnt->cl_xprt, xprt);
 	clnt->cl_procinfo = version->procs;
 	clnt->cl_maxproc  = version->nrprocs;
 	clnt->cl_prog     = args->prognumber ? : program->number;
@@ -381,16 +401,15 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args,
 	INIT_LIST_HEAD(&clnt->cl_tasks);
 	spin_lock_init(&clnt->cl_lock);
 
-	if (!xprt_bound(xprt))
-		clnt->cl_autobind = 1;
-
-	clnt->cl_timeout = xprt->timeout;
+	timeout = xprt->timeout;
 	if (args->timeout != NULL) {
 		memcpy(&clnt->cl_timeout_default, args->timeout,
 				sizeof(clnt->cl_timeout_default));
-		clnt->cl_timeout = &clnt->cl_timeout_default;
+		timeout = &clnt->cl_timeout_default;
 	}
 
+	rpc_clnt_set_transport(clnt, xprt, timeout);
+
 	clnt->cl_rtt = &clnt->cl_rtt_default;
 	rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval);
 
@@ -601,6 +620,80 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 }
 EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth);
 
+/**
+ * rpc_switch_client_transport: switch the RPC transport on the fly
+ * @clnt: pointer to a struct rpc_clnt
+ * @args: pointer to the new transport arguments
+ * @timeout: pointer to the new timeout parameters
+ *
+ * This function allows the caller to switch the RPC transport for the
+ * rpc_clnt structure 'clnt' to allow it to connect to a mirrored NFS
+ * server, for instance.  It assumes that the caller has ensured that
+ * there are no active RPC tasks by using some form of locking.
+ *
+ * Returns zero if "clnt" is now using the new xprt.  Otherwise a
+ * negative errno is returned, and "clnt" continues to use the old
+ * xprt.
+ */
+int rpc_switch_client_transport(struct rpc_clnt *clnt,
+		struct xprt_create *args,
+		const struct rpc_timeout *timeout)
+{
+	const struct rpc_timeout *old_timeo;
+	rpc_authflavor_t pseudoflavor;
+	struct rpc_xprt *xprt, *old;
+	struct rpc_clnt *parent;
+	int err;
+
+	xprt = xprt_create_transport(args);
+	if (IS_ERR(xprt)) {
+		dprintk("RPC:       failed to create new xprt for clnt %p\n",
+			clnt);
+		return PTR_ERR(xprt);
+	}
+
+	pseudoflavor = clnt->cl_auth->au_flavor;
+
+	old_timeo = clnt->cl_timeout;
+	old = rpc_clnt_set_transport(clnt, xprt, timeout);
+
+	rpc_unregister_client(clnt);
+	__rpc_clnt_remove_pipedir(clnt);
+
+	/*
+	 * A new transport was created.  "clnt" therefore
+	 * becomes the root of a new cl_parent tree.  clnt's
+	 * children, if it has any, still point to the old xprt.
+	 */
+	parent = clnt->cl_parent;
+	clnt->cl_parent = clnt;
+
+	/*
+	 * The old rpc_auth cache cannot be re-used.  GSS
+	 * contexts in particular are between a single
+	 * client and server.
+	 */
+	err = rpc_client_register(clnt, pseudoflavor, NULL);
+	if (err)
+		goto out_revert;
+
+	synchronize_rcu();
+	if (parent != clnt)
+		rpc_release_client(parent);
+	xprt_put(old);
+	dprintk("RPC:       replaced xprt for clnt %p\n", clnt);
+	return 0;
+
+out_revert:
+	rpc_clnt_set_transport(clnt, old, old_timeo);
+	clnt->cl_parent = parent;
+	rpc_client_register(clnt, pseudoflavor, NULL);
+	xprt_put(xprt);
+	dprintk("RPC:       failed to switch xprt for clnt %p\n", clnt);
+	return err;
+}
+EXPORT_SYMBOL_GPL(rpc_switch_client_transport);
+
 /*
  * Kill all tasks for the given client.
  * XXX: kill their descendants as well?
-- 
cgit 


From b03d735b4ca2375d2251195cd848713bc55e7d79 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2013 14:12:50 -0400
Subject: NFS: Add method to retrieve fs_locations during migration recovery

The nfs4_proc_fs_locations() function is invoked during referral
processing to perform a GETATTR(fs_locations) on an object's parent
directory in order to discover the target of the referral.  It
performs a LOOKUP in the compound, so the client needs to know the
parent's file handle a priori.

Unfortunately this function is not adequate for handling migration
recovery.  We need to probe fs_locations information on an FSID, but
there's no parent directory available for many operations that
can return NFS4ERR_MOVED.

Another subtlety: recovering from NFS4ERR_LEASE_MOVED is a process
of walking over a list of known FSIDs that reside on the server, and
probing whether they have migrated.  Once the server has detected
that the client has probed all migrated file systems, it stops
returning NFS4ERR_LEASE_MOVED.

A minor version zero server needs to know what client ID is
requesting fs_locations information so it can clear the flag that
forces it to continue returning NFS4ERR_LEASE_MOVED.  This flag is
set per client ID and per FSID.  However, the client ID is not an
argument of either the PUTFH or GETATTR operations.  Later minor
versions have client ID information embedded in the compound's
SEQUENCE operation.

Therefore, by convention, minor version zero clients send a RENEW
operation in the same compound as the GETATTR(fs_locations), since
RENEW's one argument is a clientid4.  This allows a minor version
zero server to identify correctly the client that is probing for a
migration.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h        |   4 ++
 fs/nfs/nfs4proc.c       | 153 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4xdr.c        |  46 +++++++++++----
 include/linux/nfs_xdr.h |   4 ++
 4 files changed, 196 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4f48000b2b97..e59d3b4c7944 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -205,6 +205,8 @@ struct nfs4_state_maintenance_ops {
 };
 
 struct nfs4_mig_recovery_ops {
+	int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
+		struct page *, struct rpc_cred *);
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
@@ -237,6 +239,8 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
 				  struct nfs4_fs_locations *, struct page *);
+extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
+		struct page *page, struct rpc_cred *);
 extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2aacd1357dc5..c71c16e0ac22 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5984,6 +5984,157 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
 	return err;
 }
 
+/*
+ * This operation also signals the server that this client is
+ * performing migration recovery.  The server can stop returning
+ * NFS4ERR_LEASE_MOVED to this client.  A RENEW operation is
+ * appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_get_locations(struct inode *inode,
+				     struct nfs4_fs_locations *locations,
+				     struct page *page, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct rpc_clnt *clnt = server->client;
+	u32 bitmask[2] = {
+		[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
+	};
+	struct nfs4_fs_locations_arg args = {
+		.clientid	= server->nfs_client->cl_clientid,
+		.fh		= NFS_FH(inode),
+		.page		= page,
+		.bitmask	= bitmask,
+		.migration	= 1,		/* skip LOOKUP */
+		.renew		= 1,		/* append RENEW */
+	};
+	struct nfs4_fs_locations_res res = {
+		.fs_locations	= locations,
+		.migration	= 1,
+		.renew		= 1,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	unsigned long now = jiffies;
+	int status;
+
+	nfs_fattr_init(&locations->fattr);
+	locations->server = server;
+	locations->nlocations = 0;
+
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+					&args.seq_args, &res.seq_res);
+	if (status)
+		return status;
+
+	renew_lease(server, now);
+	return 0;
+}
+
+#ifdef CONFIG_NFS_V4_1
+
+/*
+ * This operation also signals the server that this client is
+ * performing migration recovery.  The server can stop asserting
+ * SEQ4_STATUS_LEASE_MOVED for this client.  The client ID
+ * performing this operation is identified in the SEQUENCE
+ * operation in this compound.
+ *
+ * When the client supports GETATTR(fs_locations_info), it can
+ * be plumbed in here.
+ */
+static int _nfs41_proc_get_locations(struct inode *inode,
+				     struct nfs4_fs_locations *locations,
+				     struct page *page, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct rpc_clnt *clnt = server->client;
+	u32 bitmask[2] = {
+		[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
+	};
+	struct nfs4_fs_locations_arg args = {
+		.fh		= NFS_FH(inode),
+		.page		= page,
+		.bitmask	= bitmask,
+		.migration	= 1,		/* skip LOOKUP */
+	};
+	struct nfs4_fs_locations_res res = {
+		.fs_locations	= locations,
+		.migration	= 1,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	int status;
+
+	nfs_fattr_init(&locations->fattr);
+	locations->server = server;
+	locations->nlocations = 0;
+
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+					&args.seq_args, &res.seq_res);
+	if (status == NFS4_OK &&
+	    res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED)
+		status = -NFS4ERR_LEASE_MOVED;
+	return status;
+}
+
+#endif	/* CONFIG_NFS_V4_1 */
+
+/**
+ * nfs4_proc_get_locations - discover locations for a migrated FSID
+ * @inode: inode on FSID that is migrating
+ * @locations: result of query
+ * @page: buffer
+ * @cred: credential to use for this operation
+ *
+ * Returns NFS4_OK on success, a negative NFS4ERR status code if the
+ * operation failed, or a negative errno if a local error occurred.
+ *
+ * On success, "locations" is filled in, but if the server has
+ * no locations information, NFS_ATTR_FATTR_V4_LOCATIONS is not
+ * asserted.
+ *
+ * -NFS4ERR_LEASE_MOVED is returned if the server still has leases
+ * from this client that require migration recovery.
+ */
+int nfs4_proc_get_locations(struct inode *inode,
+			    struct nfs4_fs_locations *locations,
+			    struct page *page, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = server->nfs_client;
+	const struct nfs4_mig_recovery_ops *ops =
+					clp->cl_mvops->mig_recovery_ops;
+	struct nfs4_exception exception = { };
+	int status;
+
+	dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
+		(unsigned long long)server->fsid.major,
+		(unsigned long long)server->fsid.minor,
+		clp->cl_hostname);
+	nfs_display_fhandle(NFS_FH(inode), __func__);
+
+	do {
+		status = ops->get_locations(inode, locations, page, cred);
+		if (status != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, status, &exception);
+	} while (exception.retry);
+	return status;
+}
+
 /**
  * If 'use_integrity' is true and the state managment nfs_client
  * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient
@@ -7882,10 +8033,12 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
 #endif
 
 static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
+	.get_locations = _nfs40_proc_get_locations,
 };
 
 #if defined(CONFIG_NFS_V4_1)
 static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = {
+	.get_locations = _nfs41_proc_get_locations,
 };
 #endif	/* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 79210d23f607..1854b04f828f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -736,13 +736,15 @@ static int nfs4_stat_to_errno(int);
 				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
 				 encode_lookup_maxsz + \
-				 encode_fs_locations_maxsz)
+				 encode_fs_locations_maxsz + \
+				 encode_renew_maxsz)
 #define NFS4_dec_fs_locations_sz \
 				(compound_decode_hdr_maxsz + \
 				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_lookup_maxsz + \
-				 decode_fs_locations_maxsz)
+				 decode_fs_locations_maxsz + \
+				 decode_renew_maxsz)
 #define NFS4_enc_secinfo_sz 	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
@@ -2687,11 +2689,20 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
-	encode_putfh(xdr, args->dir_fh, &hdr);
-	encode_lookup(xdr, args->name, &hdr);
-	replen = hdr.replen;	/* get the attribute into args->page */
-	encode_fs_locations(xdr, args->bitmask, &hdr);
+	if (args->migration) {
+		encode_putfh(xdr, args->fh, &hdr);
+		replen = hdr.replen;
+		encode_fs_locations(xdr, args->bitmask, &hdr);
+		if (args->renew)
+			encode_renew(xdr, args->clientid, &hdr);
+	} else {
+		encode_putfh(xdr, args->dir_fh, &hdr);
+		encode_lookup(xdr, args->name, &hdr);
+		replen = hdr.replen;
+		encode_fs_locations(xdr, args->bitmask, &hdr);
+	}
 
+	/* Set up reply kvec to capture returned fs_locations array. */
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page,
 			0, PAGE_SIZE);
 	encode_nops(&hdr);
@@ -6824,13 +6835,26 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_lookup(xdr);
-	if (status)
-		goto out;
-	xdr_enter_page(xdr, PAGE_SIZE);
-	status = decode_getfattr_generic(xdr, &res->fs_locations->fattr,
+	if (res->migration) {
+		xdr_enter_page(xdr, PAGE_SIZE);
+		status = decode_getfattr_generic(xdr,
+					&res->fs_locations->fattr,
 					 NULL, res->fs_locations,
 					 NULL, res->fs_locations->server);
+		if (status)
+			goto out;
+		if (res->renew)
+			status = decode_renew(xdr);
+	} else {
+		status = decode_lookup(xdr);
+		if (status)
+			goto out;
+		xdr_enter_page(xdr, PAGE_SIZE);
+		status = decode_getfattr_generic(xdr,
+					&res->fs_locations->fattr,
+					 NULL, res->fs_locations,
+					 NULL, res->fs_locations->server);
+	}
 out:
 	return status;
 }
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 49f52c8f4422..405dfadcbc3b 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1053,14 +1053,18 @@ struct nfs4_fs_locations {
 struct nfs4_fs_locations_arg {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *dir_fh;
+	const struct nfs_fh *fh;
 	const struct qstr *name;
 	struct page *page;
 	const u32 *bitmask;
+	clientid4 clientid;
+	unsigned char migration:1, renew:1;
 };
 
 struct nfs4_fs_locations_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs4_fs_locations       *fs_locations;
+	unsigned char			migration:1, renew:1;
 };
 
 struct nfs4_secinfo4 {
-- 
cgit 


From ce6cda1845cf2332d2c411a5c72cd166256b21da Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2013 14:12:56 -0400
Subject: NFS: Add a super_block backpointer to the nfs_server struct

NFS_SB() returns the pointer to an nfs_server struct, given a
pointer to a super_block.  But we have no way to go back the other
way.

Add a super_block backpointer field so that, given an nfs_server
struct, it is easy to get to the filesystem's root dentry.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/super.c            | 1 +
 include/linux/nfs_fs_sb.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3f5a7a85c9c2..e26647be69ce 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2534,6 +2534,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 			mntroot = ERR_PTR(error);
 			goto error_splat_bdi;
 		}
+		server->super = s;
 	}
 
 	if (!s->s_root) {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index f9c0a6cb41e9..46b0cb4bee09 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -148,6 +148,7 @@ struct nfs_server {
 	__u64			maxfilesize;	/* maximum file size */
 	struct timespec		time_delta;	/* smallest time granularity */
 	unsigned long		mount_time;	/* when this fs was mounted */
+	struct super_block	*super;		/* VFS super block */
 	dev_t			s_dev;		/* superblock dev numbers */
 
 #ifdef CONFIG_NFS_FSCACHE
-- 
cgit 


From c9fdeb280b8cc511c6730db9ab3973331ea344e0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2013 14:13:02 -0400
Subject: NFS: Add basic migration support to state manager thread

Migration recovery and state recovery must be serialized, so handle
both in the state manager thread.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h          |   2 +
 fs/nfs/nfs4client.c       |   1 +
 fs/nfs/nfs4state.c        | 161 +++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/nfs_fs_sb.h |   7 ++
 4 files changed, 168 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e59d3b4c7944..94e783ffcf08 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -29,6 +29,7 @@ enum nfs4_client_state {
 	NFS4CLNT_SERVER_SCOPE_MISMATCH,
 	NFS4CLNT_PURGE_STATE,
 	NFS4CLNT_BIND_CONN_TO_SESSION,
+	NFS4CLNT_MOVED,
 };
 
 #define NFS4_RENEW_TIMEOUT		0x01
@@ -421,6 +422,7 @@ extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
 extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
+extern int nfs4_schedule_migration_recovery(const struct nfs_server *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_server_scope(struct nfs_client *,
 				      struct nfs41_server_scope **);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index a2cba66f8345..0cde95e9bd6a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -197,6 +197,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
 	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
+	clp->cl_mig_gen = 1;
 	return clp;
 
 error:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index fa2706a4225a..ba0db18b5f67 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -239,8 +239,6 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 	}
 }
 
-#if defined(CONFIG_NFS_V4_1)
-
 static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
 {
 	set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
@@ -270,6 +268,8 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
 	return nfs4_drain_slot_tbl(&ses->fc_slot_table);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
 static int nfs41_setup_state_renewal(struct nfs_client *clp)
 {
 	int status;
@@ -1197,6 +1197,42 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
 
+/**
+ * nfs4_schedule_migration_recovery - trigger migration recovery
+ *
+ * @server: FSID that is migrating
+ *
+ * Returns zero if recovery has started, otherwise a negative NFS4ERR
+ * value is returned.
+ */
+int nfs4_schedule_migration_recovery(const struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	if (server->fh_expire_type != NFS4_FH_PERSISTENT) {
+		pr_err("NFS: volatile file handles not supported (server %s)\n",
+				clp->cl_hostname);
+		return -NFS4ERR_IO;
+	}
+
+	if (test_bit(NFS_MIG_FAILED, &server->mig_status))
+		return -NFS4ERR_IO;
+
+	dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n",
+			__func__,
+			(unsigned long long)server->fsid.major,
+			(unsigned long long)server->fsid.minor,
+			clp->cl_hostname);
+
+	set_bit(NFS_MIG_IN_TRANSITION,
+			&((struct nfs_server *)server)->mig_status);
+	set_bit(NFS4CLNT_MOVED, &clp->cl_state);
+
+	nfs4_schedule_state_manager(clp);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery);
+
 int nfs4_wait_clnt_recover(struct nfs_client *clp)
 {
 	int res;
@@ -1826,6 +1862,119 @@ static int nfs4_purge_lease(struct nfs_client *clp)
 	return 0;
 }
 
+/*
+ * Try remote migration of one FSID from a source server to a
+ * destination server.  The source server provides a list of
+ * potential destinations.
+ *
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_fs_locations *locations = NULL;
+	struct inode *inode;
+	struct page *page;
+	int status, result;
+
+	dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__,
+			(unsigned long long)server->fsid.major,
+			(unsigned long long)server->fsid.minor,
+			clp->cl_hostname);
+
+	result = 0;
+	page = alloc_page(GFP_KERNEL);
+	locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
+	if (page == NULL || locations == NULL) {
+		dprintk("<-- %s: no memory\n", __func__);
+		goto out;
+	}
+
+	inode = server->super->s_root->d_inode;
+	result = nfs4_proc_get_locations(inode, locations, page, cred);
+	if (result) {
+		dprintk("<-- %s: failed to retrieve fs_locations: %d\n",
+			__func__, result);
+		goto out;
+	}
+
+	result = -NFS4ERR_NXIO;
+	if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
+		dprintk("<-- %s: No fs_locations data, migration skipped\n",
+			__func__);
+		goto out;
+	}
+
+	nfs4_begin_drain_session(clp);
+
+	status = nfs4_replace_transport(server, locations);
+	if (status != 0) {
+		dprintk("<-- %s: failed to replace transport: %d\n",
+			__func__, status);
+		goto out;
+	}
+
+	result = 0;
+	dprintk("<-- %s: migration succeeded\n", __func__);
+
+out:
+	if (page != NULL)
+		__free_page(page);
+	kfree(locations);
+	if (result) {
+		pr_err("NFS: migration recovery failed (server %s)\n",
+				clp->cl_hostname);
+		set_bit(NFS_MIG_FAILED, &server->mig_status);
+	}
+	return result;
+}
+
+/*
+ * Returns zero or a negative NFS4ERR status code.
+ */
+static int nfs4_handle_migration(struct nfs_client *clp)
+{
+	const struct nfs4_state_maintenance_ops *ops =
+				clp->cl_mvops->state_renewal_ops;
+	struct nfs_server *server;
+	struct rpc_cred *cred;
+
+	dprintk("%s: migration reported on \"%s\"\n", __func__,
+			clp->cl_hostname);
+
+	spin_lock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred_locked(clp);
+	spin_unlock(&clp->cl_lock);
+	if (cred == NULL)
+		return -NFS4ERR_NOENT;
+
+	clp->cl_mig_gen++;
+restart:
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		int status;
+
+		if (server->mig_gen == clp->cl_mig_gen)
+			continue;
+		server->mig_gen = clp->cl_mig_gen;
+
+		if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION,
+						&server->mig_status))
+			continue;
+
+		rcu_read_unlock();
+		status = nfs4_try_migration(server, cred);
+		if (status < 0) {
+			put_rpccred(cred);
+			return status;
+		}
+		goto restart;
+	}
+	rcu_read_unlock();
+	put_rpccred(cred);
+	return 0;
+}
+
 /**
  * nfs4_discover_server_trunking - Detect server IP address trunking
  *
@@ -2154,7 +2303,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
-			continue;
+		}
+
+		if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
+			section = "migration";
+			status = nfs4_handle_migration(clp);
+			if (status < 0)
+				goto out_error;
 		}
 
 		/* First recover reboot state... */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 46b0cb4bee09..186ec4969313 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -79,6 +79,7 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
 	const struct nfs4_minor_version_ops *cl_mvops;
+	unsigned long		cl_mig_gen;
 
 	/* NFSv4.0 transport blocking */
 	struct nfs4_slot_table	*cl_slot_tbl;
@@ -189,6 +190,12 @@ struct nfs_server {
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
+
+	unsigned long		mig_gen;
+	unsigned long		mig_status;
+#define NFS_MIG_IN_TRANSITION		(1)
+#define NFS_MIG_FAILED			(2)
+
 	void (*destroy)(struct nfs_server *);
 
 	atomic_t active; /* Keep trace of any activity to this server */
-- 
cgit 


From 44c9993384e9311cd56acf6ead3baffab616ae50 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 17 Oct 2013 14:13:30 -0400
Subject: NFS: Add method to detect whether an FSID is still on the server

Introduce a mechanism for probing a server to determine if an FSID
is present or absent.

The on-the-wire compound is different between minor version 0 and 1.
Minor version 0 appends a RENEW operation to identify which client
ID is probing.  Minor version 1 has a SEQUENCE operation in the
compound which effectively carries the same information.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4_fs.h        |   2 +
 fs/nfs/nfs4proc.c       | 128 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4xdr.c        |  67 ++++++++++++++++++++++++-
 include/linux/nfs4.h    |   1 +
 include/linux/nfs_xdr.h |  13 +++++
 5 files changed, 209 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 94e783ffcf08..2f0f8c216441 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -208,6 +208,7 @@ struct nfs4_state_maintenance_ops {
 struct nfs4_mig_recovery_ops {
 	int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
 		struct page *, struct rpc_cred *);
+	int (*fsid_present)(struct inode *, struct rpc_cred *);
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
@@ -242,6 +243,7 @@ extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struc
 				  struct nfs4_fs_locations *, struct page *);
 extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
 		struct page *page, struct rpc_cred *);
+extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *);
 extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 552e4f7a8225..01b90bd341bb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6153,6 +6153,132 @@ int nfs4_proc_get_locations(struct inode *inode,
 	return status;
 }
 
+/*
+ * This operation also signals the server that this client is
+ * performing "lease moved" recovery.  The server can stop
+ * returning NFS4ERR_LEASE_MOVED to this client.  A RENEW operation
+ * is appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct rpc_clnt *clnt = server->client;
+	struct nfs4_fsid_present_arg args = {
+		.fh		= NFS_FH(inode),
+		.clientid	= clp->cl_clientid,
+		.renew		= 1,		/* append RENEW */
+	};
+	struct nfs4_fsid_present_res res = {
+		.renew		= 1,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	unsigned long now = jiffies;
+	int status;
+
+	res.fh = nfs_alloc_fhandle();
+	if (res.fh == NULL)
+		return -ENOMEM;
+
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+						&args.seq_args, &res.seq_res);
+	nfs_free_fhandle(res.fh);
+	if (status)
+		return status;
+
+	do_renew_lease(clp, now);
+	return 0;
+}
+
+#ifdef CONFIG_NFS_V4_1
+
+/*
+ * This operation also signals the server that this client is
+ * performing "lease moved" recovery.  The server can stop asserting
+ * SEQ4_STATUS_LEASE_MOVED for this client.  The client ID performing
+ * this operation is identified in the SEQUENCE operation in this
+ * compound.
+ */
+static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct rpc_clnt *clnt = server->client;
+	struct nfs4_fsid_present_arg args = {
+		.fh		= NFS_FH(inode),
+	};
+	struct nfs4_fsid_present_res res = {
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	int status;
+
+	res.fh = nfs_alloc_fhandle();
+	if (res.fh == NULL)
+		return -ENOMEM;
+
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+						&args.seq_args, &res.seq_res);
+	nfs_free_fhandle(res.fh);
+	if (status == NFS4_OK &&
+	    res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED)
+		status = -NFS4ERR_LEASE_MOVED;
+	return status;
+}
+
+#endif	/* CONFIG_NFS_V4_1 */
+
+/**
+ * nfs4_proc_fsid_present - Is this FSID present or absent on server?
+ * @inode: inode on FSID to check
+ * @cred: credential to use for this operation
+ *
+ * Server indicates whether the FSID is present, moved, or not
+ * recognized.  This operation is necessary to clear a LEASE_MOVED
+ * condition for this client ID.
+ *
+ * Returns NFS4_OK if the FSID is present on this server,
+ * -NFS4ERR_MOVED if the FSID is no longer present, a negative
+ *  NFS4ERR code if some error occurred on the server, or a
+ *  negative errno if a local failure occurred.
+ */
+int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = server->nfs_client;
+	const struct nfs4_mig_recovery_ops *ops =
+					clp->cl_mvops->mig_recovery_ops;
+	struct nfs4_exception exception = { };
+	int status;
+
+	dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__,
+		(unsigned long long)server->fsid.major,
+		(unsigned long long)server->fsid.minor,
+		clp->cl_hostname);
+	nfs_display_fhandle(NFS_FH(inode), __func__);
+
+	do {
+		status = ops->fsid_present(inode, cred);
+		if (status != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, status, &exception);
+	} while (exception.retry);
+	return status;
+}
+
 /**
  * If 'use_integrity' is true and the state managment nfs_client
  * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient
@@ -8052,11 +8178,13 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
 
 static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
 	.get_locations = _nfs40_proc_get_locations,
+	.fsid_present = _nfs40_proc_fsid_present,
 };
 
 #if defined(CONFIG_NFS_V4_1)
 static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = {
 	.get_locations = _nfs41_proc_get_locations,
+	.fsid_present = _nfs41_proc_fsid_present,
 };
 #endif	/* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1854b04f828f..f903389d90f1 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -595,11 +595,13 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_enc_getattr_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
-				encode_getattr_maxsz)
+				encode_getattr_maxsz + \
+				encode_renew_maxsz)
 #define NFS4_dec_getattr_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				decode_getattr_maxsz)
+				decode_getattr_maxsz + \
+				decode_renew_maxsz)
 #define NFS4_enc_lookup_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
@@ -753,6 +755,18 @@ static int nfs4_stat_to_errno(int);
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_secinfo_maxsz)
+#define NFS4_enc_fsid_present_sz \
+				(compound_encode_hdr_maxsz + \
+				 encode_sequence_maxsz + \
+				 encode_putfh_maxsz + \
+				 encode_getfh_maxsz + \
+				 encode_renew_maxsz)
+#define NFS4_dec_fsid_present_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
+				 decode_putfh_maxsz + \
+				 decode_getfh_maxsz + \
+				 decode_renew_maxsz)
 #if defined(CONFIG_NFS_V4_1)
 #define NFS4_enc_bind_conn_to_session_sz \
 				(compound_encode_hdr_maxsz + \
@@ -2726,6 +2740,26 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode FSID_PRESENT request
+ */
+static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req,
+				      struct xdr_stream *xdr,
+				      struct nfs4_fsid_present_arg *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_getfh(xdr, &hdr);
+	if (args->renew)
+		encode_renew(xdr, args->clientid, &hdr);
+	encode_nops(&hdr);
+}
+
 #if defined(CONFIG_NFS_V4_1)
 /*
  * BIND_CONN_TO_SESSION request
@@ -6883,6 +6917,34 @@ out:
 	return status;
 }
 
+/*
+ * Decode FSID_PRESENT response
+ */
+static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs4_fsid_present_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_getfh(xdr, res->fh);
+	if (status)
+		goto out;
+	if (res->renew)
+		status = decode_renew(xdr);
+out:
+	return status;
+}
+
 #if defined(CONFIG_NFS_V4_1)
 /*
  * Decode BIND_CONN_TO_SESSION response
@@ -7397,6 +7459,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(FS_LOCATIONS,	enc_fs_locations,	dec_fs_locations),
 	PROC(RELEASE_LOCKOWNER,	enc_release_lockowner,	dec_release_lockowner),
 	PROC(SECINFO,		enc_secinfo,		dec_secinfo),
+	PROC(FSID_PRESENT,	enc_fsid_present,	dec_fsid_present),
 #if defined(CONFIG_NFS_V4_1)
 	PROC(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
 	PROC(CREATE_SESSION,	enc_create_session,	dec_create_session),
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e36dee52f224..c56fa8fedce9 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -460,6 +460,7 @@ enum {
 	NFSPROC4_CLNT_FS_LOCATIONS,
 	NFSPROC4_CLNT_RELEASE_LOCKOWNER,
 	NFSPROC4_CLNT_SECINFO,
+	NFSPROC4_CLNT_FSID_PRESENT,
 
 	/* nfs41 */
 	NFSPROC4_CLNT_EXCHANGE_ID,
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 405dfadcbc3b..8fe5b940c5f2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1088,6 +1088,19 @@ struct nfs4_secinfo_res {
 	struct nfs4_secinfo_flavors	*flavors;
 };
 
+struct nfs4_fsid_present_arg {
+	struct nfs4_sequence_args	seq_args;
+	const struct nfs_fh		*fh;
+	clientid4			clientid;
+	unsigned char			renew:1;
+};
+
+struct nfs4_fsid_present_res {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs_fh			*fh;
+	unsigned char			renew:1;
+};
+
 #endif /* CONFIG_NFS_V4 */
 
 struct nfstime4 {
-- 
cgit 


From 3228f48be2d19b2dd90db96ec16a40187a2946f3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 28 Oct 2013 13:33:58 -0600
Subject: blk-mq: fix for flush deadlock

The flush state machine takes in a struct request, which then is
submitted multiple times to the underling driver.  The old block code
requeses the same request for each of those, so it does not have an
issue with tapping into the request pool.  The new one on the other hand
allocates a new request for each of the actualy steps of the flush
sequence. If have already allocated all of the tags for IO, we will
fail allocating the flush request.

Set aside a reserved request just for flushes.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       |  2 +-
 block/blk-flush.c      |  2 +-
 block/blk-mq.c         | 14 ++++++++++++--
 include/linux/blk-mq.h |  2 +-
 4 files changed, 15 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 3bb9e9f7f87e..9677c6525ed8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1102,7 +1102,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw, gfp_mask);
+		return blk_mq_alloc_request(q, rw, gfp_mask, false);
 	else
 		return blk_old_get_request(q, rw, gfp_mask);
 }
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3e4cc9c7890a..331e627301ea 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -286,7 +286,7 @@ static void mq_flush_work(struct work_struct *work)
 
 	/* We don't need set REQ_FLUSH_SEQ, it's for consistency */
 	rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
-		__GFP_WAIT|GFP_ATOMIC);
+		__GFP_WAIT|GFP_ATOMIC, true);
 	rq->cmd_type = REQ_TYPE_FS;
 	rq->end_io = flush_end_io;
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ac804c635040..2dc8de86d0d2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -210,14 +210,15 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+		gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 
 	if (blk_mq_queue_enter(q))
 		return NULL;
 
-	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
 	blk_mq_put_ctx(rq->mq_ctx);
 	return rq;
 }
@@ -1327,6 +1328,15 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 		reg->queue_depth = BLK_MQ_MAX_DEPTH;
 	}
 
+	/*
+	 * Set aside a tag for flush requests.  It will only be used while
+	 * another flush request is in progress but outside the driver.
+	 *
+	 * TODO: only allocate if flushes are supported
+	 */
+	reg->queue_depth++;
+	reg->reserved_tags++;
+
 	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
 		return ERR_PTR(-EINVAL);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 3368b97bee73..ab0e9b2025b3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -124,7 +124,7 @@ void blk_mq_insert_request(struct request_queue *, struct request *, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp);
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved);
 struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp);
 struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag);
 
-- 
cgit 


From a3f73c27afff9590a4432879b7145289cb89cf0a Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@netapp.com>
Date: Fri, 18 Oct 2013 15:15:16 -0400
Subject: NFS: separate passed security flavs from selected

When filling parsed_mount_data, store the parsed sec= mount option in
the new struct nfs_auth_info and the chosen flavor in selected_flavor.

This patch lays the groundwork for supporting multiple sec= options.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/client.c         |  3 ++-
 fs/nfs/internal.h       |  4 ++--
 fs/nfs/nfs4client.c     | 16 +++++++++-------
 fs/nfs/super.c          | 47 ++++++++++++++++++++++-------------------------
 include/linux/nfs_xdr.h |  6 ++++++
 5 files changed, 41 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 692fd0e9362f..f5a7f7f9cd59 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -787,7 +787,8 @@ static int nfs_init_server(struct nfs_server *server,
 
 	server->port = data->nfs_server.port;
 
-	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
+	error = nfs_init_server_rpcclient(server, &timeparms,
+					  data->selected_flavor);
 	if (error < 0)
 		goto error;
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e5a6bd12562a..c8cd044f0982 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -88,8 +88,8 @@ struct nfs_parsed_mount_data {
 	unsigned int		namlen;
 	unsigned int		options;
 	unsigned int		bsize;
-	unsigned int		auth_flavor_len;
-	rpc_authflavor_t	auth_flavors[1];
+	struct nfs_auth_info	auth_info;
+	rpc_authflavor_t	selected_flavor;
 	char			*client_address;
 	unsigned int		version;
 	unsigned int		minorversion;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 0cde95e9bd6a..d65090e5d00f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -949,9 +949,8 @@ out:
  * Create a version 4 volume record
  */
 static int nfs4_init_server(struct nfs_server *server,
-		const struct nfs_parsed_mount_data *data)
+		struct nfs_parsed_mount_data *data)
 {
-	rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
 	struct rpc_timeout timeparms;
 	int error;
 
@@ -964,8 +963,10 @@ static int nfs4_init_server(struct nfs_server *server,
 	server->flags = data->flags;
 	server->options = data->options;
 
-	if (data->auth_flavor_len >= 1)
-		pseudoflavor = data->auth_flavors[0];
+	if (data->auth_info.flavor_len >= 1)
+		data->selected_flavor = data->auth_info.flavors[0];
+	else
+		data->selected_flavor = RPC_AUTH_UNIX;
 
 	/* Get a client record */
 	error = nfs4_set_client(server,
@@ -973,7 +974,7 @@ static int nfs4_init_server(struct nfs_server *server,
 			(const struct sockaddr *)&data->nfs_server.address,
 			data->nfs_server.addrlen,
 			data->client_address,
-			pseudoflavor,
+			data->selected_flavor,
 			data->nfs_server.protocol,
 			&timeparms,
 			data->minorversion,
@@ -993,7 +994,8 @@ static int nfs4_init_server(struct nfs_server *server,
 
 	server->port = data->nfs_server.port;
 
-	error = nfs_init_server_rpcclient(server, &timeparms, pseudoflavor);
+	error = nfs_init_server_rpcclient(server, &timeparms,
+					  data->selected_flavor);
 
 error:
 	/* Done */
@@ -1020,7 +1022,7 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
 	if (!server)
 		return ERR_PTR(-ENOMEM);
 
-	auth_probe = mount_info->parsed->auth_flavor_len < 1;
+	auth_probe = mount_info->parsed->auth_info.flavor_len < 1;
 
 	/* set up the general RPC client */
 	error = nfs4_init_server(server, mount_info->parsed);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e26647be69ce..b87744fb9dcd 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -923,8 +923,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
 		data->mount_server.port	= NFS_UNSPEC_PORT;
 		data->nfs_server.port	= NFS_UNSPEC_PORT;
 		data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
-		data->auth_flavors[0]	= RPC_AUTH_MAXFLAVOR;
-		data->auth_flavor_len	= 0;
+		data->selected_flavor	= RPC_AUTH_MAXFLAVOR;
 		data->minorversion	= 0;
 		data->need_mount	= true;
 		data->net		= current->nsproxy->net_ns;
@@ -1019,13 +1018,6 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
 	}
 }
 
-static void nfs_set_auth_parsed_mount_data(struct nfs_parsed_mount_data *data,
-		rpc_authflavor_t pseudoflavor)
-{
-	data->auth_flavors[0] = pseudoflavor;
-	data->auth_flavor_len = 1;
-}
-
 /*
  * Parse the value of the 'sec=' option.
  */
@@ -1076,7 +1068,8 @@ static int nfs_parse_security_flavors(char *value,
 	}
 
 	mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-	nfs_set_auth_parsed_mount_data(mnt, pseudoflavor);
+	mnt->auth_info.flavors[0] = pseudoflavor;
+	mnt->auth_info.flavor_len = 1;
 	return 1;
 }
 
@@ -1623,7 +1616,7 @@ out_security_failure:
 }
 
 /*
- * Ensure that the specified authtype in args->auth_flavors[0] is supported by
+ * Ensure that the specified authtype in args->auth_info is supported by
  * the server. Returns 0 if it's ok, and -EACCES if not.
  */
 static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args,
@@ -1640,17 +1633,18 @@ static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args,
 	 * can be used.
 	 */
 	for (i = 0; i < count; i++) {
-		if (args->auth_flavors[0] == server_authlist[i] ||
+		if (args->auth_info.flavors[0] == server_authlist[i] ||
 		    server_authlist[i] == RPC_AUTH_NULL)
 			goto out;
 	}
 
 	dfprintk(MOUNT, "NFS: auth flavor %u not supported by server\n",
-		args->auth_flavors[0]);
+		args->auth_info.flavors[0]);
 	return -EACCES;
 
 out:
-	dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]);
+	args->selected_flavor = args->auth_info.flavors[0];
+	dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor);
 	return 0;
 }
 
@@ -1738,9 +1732,10 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf
 	 * Was a sec= authflavor specified in the options? First, verify
 	 * whether the server supports it, and then just try to use it if so.
 	 */
-	if (args->auth_flavor_len > 0) {
+	if (args->auth_info.flavor_len > 0) {
 		status = nfs_verify_authflavor(args, authlist, authlist_len);
-		dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]);
+		dfprintk(MOUNT, "NFS: using auth flavor %u\n",
+			 args->selected_flavor);
 		if (status)
 			return ERR_PTR(status);
 		return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
@@ -1769,7 +1764,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf
 			/* Fallthrough */
 		}
 		dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor);
-		nfs_set_auth_parsed_mount_data(args, flavor);
+		args->selected_flavor = flavor;
 		server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
 		if (!IS_ERR(server))
 			return server;
@@ -1785,7 +1780,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf
 
 	/* Last chance! Try AUTH_UNIX */
 	dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX);
-	nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX);
+	args->selected_flavor = RPC_AUTH_UNIX;
 	return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
 }
 
@@ -1972,9 +1967,9 @@ static int nfs23_validate_mount_data(void *options,
 		args->bsize		= data->bsize;
 
 		if (data->flags & NFS_MOUNT_SECFLAVOUR)
-			nfs_set_auth_parsed_mount_data(args, data->pseudoflavor);
+			args->selected_flavor = data->pseudoflavor;
 		else
-			nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX);
+			args->selected_flavor = RPC_AUTH_UNIX;
 		if (!args->nfs_server.hostname)
 			goto out_nomem;
 
@@ -2108,7 +2103,7 @@ static int nfs_validate_text_mount_data(void *options,
 
 	nfs_set_port(sap, &args->nfs_server.port, port);
 
-	if (args->auth_flavor_len > 1)
+	if (args->auth_info.flavor_len > 1)
 		goto out_bad_auth;
 
 	return nfs_parse_devname(dev_name,
@@ -2146,7 +2141,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	    data->version != nfss->nfs_client->rpc_ops->version ||
 	    data->minorversion != nfss->nfs_client->cl_minorversion ||
 	    data->retrans != nfss->client->cl_timeout->to_retries ||
-	    data->auth_flavors[0] != nfss->client->cl_auth->au_flavor ||
+	    data->selected_flavor != nfss->client->cl_auth->au_flavor ||
 	    data->acregmin != nfss->acregmin / HZ ||
 	    data->acregmax != nfss->acregmax / HZ ||
 	    data->acdirmin != nfss->acdirmin / HZ ||
@@ -2191,7 +2186,9 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->rsize = nfss->rsize;
 	data->wsize = nfss->wsize;
 	data->retrans = nfss->client->cl_timeout->to_retries;
-	nfs_set_auth_parsed_mount_data(data, nfss->client->cl_auth->au_flavor);
+	data->selected_flavor = nfss->client->cl_auth->au_flavor;
+	data->auth_info.flavors[0] = nfss->client->cl_auth->au_flavor;
+	data->auth_info.flavor_len = 1;
 	data->acregmin = nfss->acregmin / HZ;
 	data->acregmax = nfss->acregmax / HZ;
 	data->acdirmin = nfss->acdirmin / HZ;
@@ -2718,9 +2715,9 @@ static int nfs4_validate_mount_data(void *options,
 					   data->auth_flavours,
 					   sizeof(pseudoflavor)))
 				return -EFAULT;
-			nfs_set_auth_parsed_mount_data(args, pseudoflavor);
+			args->selected_flavor = pseudoflavor;
 		} else
-			nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX);
+			args->selected_flavor = RPC_AUTH_UNIX;
 
 		c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN);
 		if (IS_ERR(c))
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 8fe5b940c5f2..658104acf13b 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -591,6 +591,12 @@ struct nfs_renameres {
 	struct nfs_fattr		*new_fattr;
 };
 
+/* parsed sec= options */
+struct nfs_auth_info {
+	unsigned int            flavor_len;
+	rpc_authflavor_t        flavors[1];
+};
+
 /*
  * Argument struct for decode_entry function
  */
-- 
cgit 


From 0f5f49b8b3593309fd3c3a2080a5fd465afdbe16 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@netapp.com>
Date: Fri, 18 Oct 2013 15:15:17 -0400
Subject: NFS: cache parsed auth_info in nfs_server

Cache the auth_info structure in nfs_server and pass these values to submounts.

This lays the groundwork for supporting multiple sec= options.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/client.c           | 2 ++
 fs/nfs/nfs4client.c       | 1 +
 fs/nfs/super.c            | 3 +--
 include/linux/nfs_fs_sb.h | 1 +
 4 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f5a7f7f9cd59..1d09289c8f0e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -786,6 +786,7 @@ static int nfs_init_server(struct nfs_server *server,
 		goto error;
 
 	server->port = data->nfs_server.port;
+	server->auth_info = data->auth_info;
 
 	error = nfs_init_server_rpcclient(server, &timeparms,
 					  data->selected_flavor);
@@ -929,6 +930,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->acdirmax = source->acdirmax;
 	target->caps = source->caps;
 	target->options = source->options;
+	target->auth_info = source->auth_info;
 }
 EXPORT_SYMBOL_GPL(nfs_server_copy_userdata);
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index d65090e5d00f..04131c837f27 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -962,6 +962,7 @@ static int nfs4_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
 	server->options = data->options;
+	server->auth_info = data->auth_info;
 
 	if (data->auth_info.flavor_len >= 1)
 		data->selected_flavor = data->auth_info.flavors[0];
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index b87744fb9dcd..de1e5e89c93d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2187,8 +2187,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->wsize = nfss->wsize;
 	data->retrans = nfss->client->cl_timeout->to_retries;
 	data->selected_flavor = nfss->client->cl_auth->au_flavor;
-	data->auth_info.flavors[0] = nfss->client->cl_auth->au_flavor;
-	data->auth_info.flavor_len = 1;
+	data->auth_info = nfss->auth_info;
 	data->acregmin = nfss->acregmin / HZ;
 	data->acregmax = nfss->acregmax / HZ;
 	data->acdirmin = nfss->acdirmin / HZ;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 186ec4969313..1150ea41b626 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -151,6 +151,7 @@ struct nfs_server {
 	unsigned long		mount_time;	/* when this fs was mounted */
 	struct super_block	*super;		/* VFS super block */
 	dev_t			s_dev;		/* superblock dev numbers */
+	struct nfs_auth_info	auth_info;	/* parsed auth flavors */
 
 #ifdef CONFIG_NFS_FSCACHE
 	struct nfs_fscache_key	*fscache_key;	/* unique key for superblock */
-- 
cgit 


From 5837f6dfcb00f764976ddc178933e612702cbf54 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@netapp.com>
Date: Fri, 18 Oct 2013 15:15:18 -0400
Subject: NFS: stop using NFS_MOUNT_SECFLAVOUR server flag

Since the parsed sec= flavor is now stored in nfs_server->auth_info,
we no longer need an nfs_server flag to determine if a sec= option was
used.

This flag has not been completely removed because it is still needed for
the (old but still supported) non-text parsed mount options ABI
compatability.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4client.c            | 6 ++++--
 fs/nfs/nfs4namespace.c         | 2 +-
 fs/nfs/nfs4proc.c              | 4 ++--
 fs/nfs/super.c                 | 3 +--
 include/uapi/linux/nfs_mount.h | 2 +-
 5 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 04131c837f27..f6cc77c7d802 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1051,6 +1051,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 {
 	struct nfs_client *parent_client;
 	struct nfs_server *server, *parent_server;
+	bool auth_probe;
 	int error;
 
 	dprintk("--> nfs4_create_referral_server()\n");
@@ -1083,8 +1084,9 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	if (error < 0)
 		goto error;
 
-	error = nfs4_server_common_setup(server, mntfh,
-			!(parent_server->flags & NFS_MOUNT_SECFLAVOUR));
+	auth_probe = parent_server->auth_info.flavor_len < 1;
+
+	error = nfs4_server_common_setup(server, mntfh, auth_probe);
 	if (error < 0)
 		goto error;
 
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4ec0eea68fdf..b947054f0ca1 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -390,7 +390,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
 
 	if (client->cl_auth->au_flavor != flavor)
 		flavor = client->cl_auth->au_flavor;
-	else if (!(server->flags & NFS_MOUNT_SECFLAVOUR)) {
+	else if (server->auth_info.flavor_len == 0) {
 		rpc_authflavor_t new = nfs4_negotiate_security(dir, name);
 		if ((int)new >= 0)
 			flavor = new;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1463c71b0862..0eb8dc5792da 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2920,7 +2920,7 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 		if (status != -NFS4ERR_WRONGSEC)
 			break;
 		/* Did user force a 'sec=' mount option? */
-		if (server->flags & NFS_MOUNT_SECFLAVOUR)
+		if (server->auth_info.flavor_len > 0)
 			break;
 	default:
 		status = nfs4_do_find_root_sec(server, fhandle, info);
@@ -3180,7 +3180,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
 			if (client != *clnt)
 				goto out;
 			/* No security negotiation if the user specified 'sec=' */
-			if (NFS_SERVER(dir)->flags & NFS_MOUNT_SECFLAVOUR)
+			if (NFS_SERVER(dir)->auth_info.flavor_len > 0)
 				goto out;
 			client = nfs4_create_sec_client(client, dir, name);
 			if (IS_ERR(client))
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index de1e5e89c93d..3a4f8bf5e5a5 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1067,7 +1067,6 @@ static int nfs_parse_security_flavors(char *value,
 		return 0;
 	}
 
-	mnt->flags |= NFS_MOUNT_SECFLAVOUR;
 	mnt->auth_info.flavors[0] = pseudoflavor;
 	mnt->auth_info.flavor_len = 1;
 	return 1;
@@ -2332,7 +2331,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n
 		goto Ebusy;
 	if (a->acdirmax != b->acdirmax)
 		goto Ebusy;
-	if (b->flags & NFS_MOUNT_SECFLAVOUR &&
+	if (b->auth_info.flavor_len > 0 &&
 	   clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor)
 		goto Ebusy;
 	return 1;
diff --git a/include/uapi/linux/nfs_mount.h b/include/uapi/linux/nfs_mount.h
index 576bddd72e04..64b0f22f5c4c 100644
--- a/include/uapi/linux/nfs_mount.h
+++ b/include/uapi/linux/nfs_mount.h
@@ -60,7 +60,7 @@ struct nfs_mount_data {
 #define NFS_MOUNT_BROKEN_SUID	0x0400	/* 4 */
 #define NFS_MOUNT_NOACL		0x0800	/* 4 */
 #define NFS_MOUNT_STRICTLOCK	0x1000	/* reserved for NFSv4 */
-#define NFS_MOUNT_SECFLAVOUR	0x2000	/* 5 */
+#define NFS_MOUNT_SECFLAVOUR	0x2000	/* 5 non-text parsed mount data only */
 #define NFS_MOUNT_NORDIRPLUS	0x4000	/* 5 */
 #define NFS_MOUNT_UNSHARED	0x8000	/* 5 */
 #define NFS_MOUNT_FLAGMASK	0xFFFF
-- 
cgit 


From 4d4b69dd847a098cdca341c45326f6c6f61b8691 Mon Sep 17 00:00:00 2001
From: Weston Andros Adamson <dros@netapp.com>
Date: Fri, 18 Oct 2013 15:15:19 -0400
Subject: NFS: add support for multiple sec= mount options

This patch adds support for multiple security options which can be
specified using a colon-delimited list of security flavors (the same
syntax as nfsd's exports file).

This is useful, for instance, when NFSv4.x mounts cross SECINFO
boundaries. With this patch a user can use "sec=krb5i,krb5p"
to mount a remote filesystem using krb5i, but can still cross
into krb5p-only exports.

New mounts will try all security options before failing.  NFSv4.x
SECINFO results will be compared against the sec= flavors to
find the first flavor in both lists or if no match is found will
return -EPERM.

Signed-off-by: Weston Andros Adamson <dros@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h       |   1 +
 fs/nfs/nfs4client.c     |   3 +
 fs/nfs/nfs4namespace.c  |  17 +++--
 fs/nfs/nfs4proc.c       |  32 ++++++----
 fs/nfs/super.c          | 160 +++++++++++++++++++++++++++++++-----------------
 include/linux/nfs_xdr.h |   3 +-
 6 files changed, 145 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index c8cd044f0982..bca6a3e3c49c 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -326,6 +326,7 @@ extern struct file_system_type nfs_xdev_fs_type;
 extern struct file_system_type nfs4_xdev_fs_type;
 extern struct file_system_type nfs4_referral_fs_type;
 #endif
+bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
 struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *,
 			struct nfs_subversion *);
 void nfs_initialise_sb(struct super_block *);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index f6cc77c7d802..b4a160a405ce 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -964,6 +964,9 @@ static int nfs4_init_server(struct nfs_server *server,
 	server->options = data->options;
 	server->auth_info = data->auth_info;
 
+	/* Use the first specified auth flavor. If this flavor isn't
+	 * allowed by the server, use the SECINFO path to try the
+	 * other specified flavors */
 	if (data->auth_info.flavor_len >= 1)
 		data->selected_flavor = data->auth_info.flavors[0];
 	else
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index b947054f0ca1..c08cbf40c59e 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -137,6 +137,7 @@ static size_t nfs_parse_server_name(char *string, size_t len,
 
 /**
  * nfs_find_best_sec - Find a security mechanism supported locally
+ * @server: NFS server struct
  * @flavors: List of security tuples returned by SECINFO procedure
  *
  * Return the pseudoflavor of the first security mechanism in
@@ -145,7 +146,8 @@ static size_t nfs_parse_server_name(char *string, size_t len,
  * is searched in the order returned from the server, per RFC 3530
  * recommendation.
  */
-static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
+static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server,
+					  struct nfs4_secinfo_flavors *flavors)
 {
 	rpc_authflavor_t pseudoflavor;
 	struct nfs4_secinfo4 *secinfo;
@@ -160,12 +162,19 @@ static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
 		case RPC_AUTH_GSS:
 			pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor,
 							&secinfo->flavor_info);
-			if (pseudoflavor != RPC_AUTH_MAXFLAVOR)
+			/* make sure pseudoflavor matches sec= mount opt */
+			if (pseudoflavor != RPC_AUTH_MAXFLAVOR &&
+			    nfs_auth_info_match(&server->auth_info,
+						pseudoflavor))
 				return pseudoflavor;
 			break;
 		}
 	}
 
+	/* if there were any sec= options then nothing matched */
+	if (server->auth_info.flavor_len > 0)
+		return -EPERM;
+
 	return RPC_AUTH_UNIX;
 }
 
@@ -187,7 +196,7 @@ static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr
 		goto out;
 	}
 
-	flavor = nfs_find_best_sec(flavors);
+	flavor = nfs_find_best_sec(NFS_SERVER(inode), flavors);
 
 out:
 	put_page(page);
@@ -390,7 +399,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
 
 	if (client->cl_auth->au_flavor != flavor)
 		flavor = client->cl_auth->au_flavor;
-	else if (server->auth_info.flavor_len == 0) {
+	else {
 		rpc_authflavor_t new = nfs4_negotiate_security(dir, name);
 		if ((int)new >= 0)
 			flavor = new;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0eb8dc5792da..b02c4cc7b0a9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2873,11 +2873,24 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	int status = -EPERM;
 	size_t i;
 
-	for (i = 0; i < ARRAY_SIZE(flav_array); i++) {
-		status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]);
-		if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
-			continue;
-		break;
+	if (server->auth_info.flavor_len > 0) {
+		/* try each flavor specified by user */
+		for (i = 0; i < server->auth_info.flavor_len; i++) {
+			status = nfs4_lookup_root_sec(server, fhandle, info,
+						server->auth_info.flavors[i]);
+			if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
+				continue;
+			break;
+		}
+	} else {
+		/* no flavors specified by user, try default list */
+		for (i = 0; i < ARRAY_SIZE(flav_array); i++) {
+			status = nfs4_lookup_root_sec(server, fhandle, info,
+						      flav_array[i]);
+			if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
+				continue;
+			break;
+		}
 	}
 
 	/*
@@ -2919,9 +2932,6 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 		status = nfs4_lookup_root(server, fhandle, info);
 		if (status != -NFS4ERR_WRONGSEC)
 			break;
-		/* Did user force a 'sec=' mount option? */
-		if (server->auth_info.flavor_len > 0)
-			break;
 	default:
 		status = nfs4_do_find_root_sec(server, fhandle, info);
 	}
@@ -3179,9 +3189,6 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
 			err = -EPERM;
 			if (client != *clnt)
 				goto out;
-			/* No security negotiation if the user specified 'sec=' */
-			if (NFS_SERVER(dir)->auth_info.flavor_len > 0)
-				goto out;
 			client = nfs4_create_sec_client(client, dir, name);
 			if (IS_ERR(client))
 				return PTR_ERR(client);
@@ -7942,6 +7949,9 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 			break;
 		}
 
+		if (!nfs_auth_info_match(&server->auth_info, flavor))
+			flavor = RPC_AUTH_MAXFLAVOR;
+
 		if (flavor != RPC_AUTH_MAXFLAVOR) {
 			err = nfs4_lookup_root_sec(server, fhandle,
 						   info, flavor);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3a4f8bf5e5a5..317d6fc2160e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -497,7 +497,8 @@ static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
 	static const struct {
 		rpc_authflavor_t flavour;
 		const char *str;
-	} sec_flavours[] = {
+	} sec_flavours[NFS_AUTH_INFO_MAX_FLAVORS] = {
+		/* update NFS_AUTH_INFO_MAX_FLAVORS when this list changes! */
 		{ RPC_AUTH_NULL, "null" },
 		{ RPC_AUTH_UNIX, "sys" },
 		{ RPC_AUTH_GSS_KRB5, "krb5" },
@@ -1018,6 +1019,52 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
 	}
 }
 
+/*
+ * Add 'flavor' to 'auth_info' if not already present.
+ * Returns true if 'flavor' ends up in the list, false otherwise
+ */
+static bool nfs_auth_info_add(struct nfs_auth_info *auth_info,
+			      rpc_authflavor_t flavor)
+{
+	unsigned int i;
+	unsigned int max_flavor_len = (sizeof(auth_info->flavors) /
+				       sizeof(auth_info->flavors[0]));
+
+	/* make sure this flavor isn't already in the list */
+	for (i = 0; i < auth_info->flavor_len; i++) {
+		if (flavor == auth_info->flavors[i])
+			return true;
+	}
+
+	if (auth_info->flavor_len + 1 >= max_flavor_len) {
+		dfprintk(MOUNT, "NFS: too many sec= flavors\n");
+		return false;
+	}
+
+	auth_info->flavors[auth_info->flavor_len++] = flavor;
+	return true;
+}
+
+/*
+ * Return true if 'match' is in auth_info or auth_info is empty.
+ * Return false otherwise.
+ */
+bool nfs_auth_info_match(const struct nfs_auth_info *auth_info,
+			 rpc_authflavor_t match)
+{
+	int i;
+
+	if (!auth_info->flavor_len)
+		return true;
+
+	for (i = 0; i < auth_info->flavor_len; i++) {
+		if (auth_info->flavors[i] == match)
+			return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(nfs_auth_info_match);
+
 /*
  * Parse the value of the 'sec=' option.
  */
@@ -1026,49 +1073,55 @@ static int nfs_parse_security_flavors(char *value,
 {
 	substring_t args[MAX_OPT_ARGS];
 	rpc_authflavor_t pseudoflavor;
+	char *p;
 
 	dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value);
 
-	switch (match_token(value, nfs_secflavor_tokens, args)) {
-	case Opt_sec_none:
-		pseudoflavor = RPC_AUTH_NULL;
-		break;
-	case Opt_sec_sys:
-		pseudoflavor = RPC_AUTH_UNIX;
-		break;
-	case Opt_sec_krb5:
-		pseudoflavor = RPC_AUTH_GSS_KRB5;
-		break;
-	case Opt_sec_krb5i:
-		pseudoflavor = RPC_AUTH_GSS_KRB5I;
-		break;
-	case Opt_sec_krb5p:
-		pseudoflavor = RPC_AUTH_GSS_KRB5P;
-		break;
-	case Opt_sec_lkey:
-		pseudoflavor = RPC_AUTH_GSS_LKEY;
-		break;
-	case Opt_sec_lkeyi:
-		pseudoflavor = RPC_AUTH_GSS_LKEYI;
-		break;
-	case Opt_sec_lkeyp:
-		pseudoflavor = RPC_AUTH_GSS_LKEYP;
-		break;
-	case Opt_sec_spkm:
-		pseudoflavor = RPC_AUTH_GSS_SPKM;
-		break;
-	case Opt_sec_spkmi:
-		pseudoflavor = RPC_AUTH_GSS_SPKMI;
-		break;
-	case Opt_sec_spkmp:
-		pseudoflavor = RPC_AUTH_GSS_SPKMP;
-		break;
-	default:
-		return 0;
+	while ((p = strsep(&value, ":")) != NULL) {
+		switch (match_token(p, nfs_secflavor_tokens, args)) {
+		case Opt_sec_none:
+			pseudoflavor = RPC_AUTH_NULL;
+			break;
+		case Opt_sec_sys:
+			pseudoflavor = RPC_AUTH_UNIX;
+			break;
+		case Opt_sec_krb5:
+			pseudoflavor = RPC_AUTH_GSS_KRB5;
+			break;
+		case Opt_sec_krb5i:
+			pseudoflavor = RPC_AUTH_GSS_KRB5I;
+			break;
+		case Opt_sec_krb5p:
+			pseudoflavor = RPC_AUTH_GSS_KRB5P;
+			break;
+		case Opt_sec_lkey:
+			pseudoflavor = RPC_AUTH_GSS_LKEY;
+			break;
+		case Opt_sec_lkeyi:
+			pseudoflavor = RPC_AUTH_GSS_LKEYI;
+			break;
+		case Opt_sec_lkeyp:
+			pseudoflavor = RPC_AUTH_GSS_LKEYP;
+			break;
+		case Opt_sec_spkm:
+			pseudoflavor = RPC_AUTH_GSS_SPKM;
+			break;
+		case Opt_sec_spkmi:
+			pseudoflavor = RPC_AUTH_GSS_SPKMI;
+			break;
+		case Opt_sec_spkmp:
+			pseudoflavor = RPC_AUTH_GSS_SPKMP;
+			break;
+		default:
+			dfprintk(MOUNT,
+				 "NFS: sec= option '%s' not recognized\n", p);
+			return 0;
+		}
+
+		if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor))
+			return 0;
 	}
 
-	mnt->auth_info.flavors[0] = pseudoflavor;
-	mnt->auth_info.flavor_len = 1;
 	return 1;
 }
 
@@ -1615,12 +1668,14 @@ out_security_failure:
 }
 
 /*
- * Ensure that the specified authtype in args->auth_info is supported by
- * the server. Returns 0 if it's ok, and -EACCES if not.
+ * Ensure that a specified authtype in args->auth_info is supported by
+ * the server. Returns 0 and sets args->selected_flavor if it's ok, and
+ * -EACCES if not.
  */
-static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args,
+static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args,
 			rpc_authflavor_t *server_authlist, unsigned int count)
 {
+	rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR;
 	unsigned int i;
 
 	/*
@@ -1632,17 +1687,19 @@ static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args,
 	 * can be used.
 	 */
 	for (i = 0; i < count; i++) {
-		if (args->auth_info.flavors[0] == server_authlist[i] ||
-		    server_authlist[i] == RPC_AUTH_NULL)
+		flavor = server_authlist[i];
+
+		if (nfs_auth_info_match(&args->auth_info, flavor) ||
+		    flavor == RPC_AUTH_NULL)
 			goto out;
 	}
 
-	dfprintk(MOUNT, "NFS: auth flavor %u not supported by server\n",
-		args->auth_info.flavors[0]);
+	dfprintk(MOUNT,
+		 "NFS: specified auth flavors not supported by server\n");
 	return -EACCES;
 
 out:
-	args->selected_flavor = args->auth_info.flavors[0];
+	args->selected_flavor = flavor;
 	dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor);
 	return 0;
 }
@@ -1732,7 +1789,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf
 	 * whether the server supports it, and then just try to use it if so.
 	 */
 	if (args->auth_info.flavor_len > 0) {
-		status = nfs_verify_authflavor(args, authlist, authlist_len);
+		status = nfs_verify_authflavors(args, authlist, authlist_len);
 		dfprintk(MOUNT, "NFS: using auth flavor %u\n",
 			 args->selected_flavor);
 		if (status)
@@ -2102,9 +2159,6 @@ static int nfs_validate_text_mount_data(void *options,
 
 	nfs_set_port(sap, &args->nfs_server.port, port);
 
-	if (args->auth_info.flavor_len > 1)
-		goto out_bad_auth;
-
 	return nfs_parse_devname(dev_name,
 				   &args->nfs_server.hostname,
 				   max_namelen,
@@ -2124,10 +2178,6 @@ out_invalid_transport_udp:
 out_no_address:
 	dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n");
 	return -EINVAL;
-
-out_bad_auth:
-	dfprintk(MOUNT, "NFS: Too many RPC auth flavours specified\n");
-	return -EINVAL;
 }
 
 static int
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 658104acf13b..3ccfcecf8999 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -592,9 +592,10 @@ struct nfs_renameres {
 };
 
 /* parsed sec= options */
+#define NFS_AUTH_INFO_MAX_FLAVORS 12 /* see fs/nfs/super.c */
 struct nfs_auth_info {
 	unsigned int            flavor_len;
-	rpc_authflavor_t        flavors[1];
+	rpc_authflavor_t        flavors[NFS_AUTH_INFO_MAX_FLAVORS];
 };
 
 /*
-- 
cgit 


From a01779f89fc8a2225cb82dca0fc7b8451851cb7b Mon Sep 17 00:00:00 2001
From: Josh Cartwright <joshc@codeaurora.org>
Date: Mon, 28 Oct 2013 13:12:35 -0500
Subject: regmap: add SPMI support

Add basic support for the System Power Management Interface (SPMI) bus.
This is a simple implementation which only implements register accesses
via the Extended Register Read/Write Long commands.

Signed-off-by: Josh Cartwright <joshc@codeaurora.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/Kconfig       |  5 ++-
 drivers/base/regmap/Makefile      |  1 +
 drivers/base/regmap/regmap-spmi.c | 90 +++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h            |  5 +++
 4 files changed, 100 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/regmap/regmap-spmi.c

(limited to 'include')

diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index f0d30543fcce..4251570610c9 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -3,7 +3,7 @@
 # subsystems should select the appropriate symbols.
 
 config REGMAP
-	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_MMIO || REGMAP_IRQ)
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_MMIO || REGMAP_IRQ)
 	select LZO_COMPRESS
 	select LZO_DECOMPRESS
 	select IRQ_DOMAIN if REGMAP_IRQ
@@ -15,6 +15,9 @@ config REGMAP_I2C
 config REGMAP_SPI
 	tristate
 
+config REGMAP_SPMI
+	tristate
+
 config REGMAP_MMIO
 	tristate
 
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index cf129980abd0..a7c670b4123a 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -3,5 +3,6 @@ obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o regcache-flat.o
 obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o
 obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o
 obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o
+obj-$(CONFIG_REGMAP_SPMI) += regmap-spmi.o
 obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c
new file mode 100644
index 000000000000..ac2391013db1
--- /dev/null
+++ b/drivers/base/regmap/regmap-spmi.c
@@ -0,0 +1,90 @@
+/*
+ * Register map access API - SPMI support
+ *
+ * Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
+ *
+ * Based on regmap-i2c.c:
+ * Copyright 2011 Wolfson Microelectronics plc
+ * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/regmap.h>
+#include <linux/spmi.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+static int regmap_spmi_read(void *context,
+			    const void *reg, size_t reg_size,
+			    void *val, size_t val_size)
+{
+	BUG_ON(reg_size != 2);
+	return spmi_ext_register_readl(context, *(u16 *)reg,
+				       val, val_size);
+}
+
+static int regmap_spmi_gather_write(void *context,
+				    const void *reg, size_t reg_size,
+				    const void *val, size_t val_size)
+{
+	BUG_ON(reg_size != 2);
+	return spmi_ext_register_writel(context, *(u16 *)reg, val, val_size);
+}
+
+static int regmap_spmi_write(void *context, const void *data,
+			     size_t count)
+{
+	BUG_ON(count < 2);
+	return regmap_spmi_gather_write(context, data, 2, data + 2, count - 2);
+}
+
+static struct regmap_bus regmap_spmi = {
+	.read				= regmap_spmi_read,
+	.write				= regmap_spmi_write,
+	.gather_write			= regmap_spmi_gather_write,
+	.reg_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+};
+
+/**
+ * regmap_init_spmi(): Initialize register map
+ *
+ * @sdev: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_spmi(struct spmi_device *sdev,
+				const struct regmap_config *config)
+{
+	return regmap_init(&sdev->dev, &regmap_spmi, sdev, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_spmi);
+
+/**
+ * devm_regmap_init_spmi(): Initialise managed register map
+ *
+ * @sdev: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_spmi(struct spmi_device *sdev,
+				     const struct regmap_config *config)
+{
+	return devm_regmap_init(&sdev->dev, &regmap_spmi, sdev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_spmi);
+
+MODULE_LICENSE("GPL");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index a10380bfbeac..3f5abc86b6b5 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -23,6 +23,7 @@ struct device;
 struct i2c_client;
 struct irq_domain;
 struct spi_device;
+struct spmi_device;
 struct regmap;
 struct regmap_range_cfg;
 struct regmap_field;
@@ -318,6 +319,8 @@ struct regmap *regmap_init_i2c(struct i2c_client *i2c,
 			       const struct regmap_config *config);
 struct regmap *regmap_init_spi(struct spi_device *dev,
 			       const struct regmap_config *config);
+struct regmap *regmap_init_spmi(struct spmi_device *dev,
+			       const struct regmap_config *config);
 struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 				    void __iomem *regs,
 				    const struct regmap_config *config);
@@ -330,6 +333,8 @@ struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c,
 				    const struct regmap_config *config);
 struct regmap *devm_regmap_init_spi(struct spi_device *dev,
 				    const struct regmap_config *config);
+struct regmap *devm_regmap_init_spmi(struct spmi_device *dev,
+				     const struct regmap_config *config);
 struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 					 void __iomem *regs,
 					 const struct regmap_config *config);
-- 
cgit 


From e0f244c63fc9d192dfd399cc2677bbdca61994b1 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 23 Oct 2013 10:57:58 +1030
Subject: asmlinkage, module: Make ksymtab and kcrctab symbols and
 __this_module __visible

Make the ksymtab symbols for EXPORT_SYMBOL visible.
This prevents the LTO compiler from adding a .NUMBER prefix,
which avoids various problems in later export processing.

Cc: rusty@rustcorp.com.au
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/export.h | 4 ++--
 scripts/mod/modpost.c  | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/export.h b/include/linux/export.h
index 412cd509effe..3f2793d51899 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -43,7 +43,7 @@ extern struct module __this_module;
 /* Mark the CRC weak since genksyms apparently decides not to
  * generate a checksums for some symbols */
 #define __CRC_SYMBOL(sym, sec)					\
-	extern void *__crc_##sym __attribute__((weak));		\
+	extern __visible void *__crc_##sym __attribute__((weak));		\
 	static const unsigned long __kcrctab_##sym		\
 	__used							\
 	__attribute__((section("___kcrctab" sec "+" #sym), unused))	\
@@ -59,7 +59,7 @@ extern struct module __this_module;
 	static const char __kstrtab_##sym[]			\
 	__attribute__((section("__ksymtab_strings"), aligned(1))) \
 	= VMLINUX_SYMBOL_STR(sym);				\
-	static const struct kernel_symbol __ksymtab_##sym	\
+	__visible const struct kernel_symbol __ksymtab_##sym	\
 	__used							\
 	__attribute__((section("___ksymtab" sec "+" #sym), unused))	\
 	= { (unsigned long)&sym, __kstrtab_##sym }
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 393706b37774..9b873ac6ed7b 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1861,7 +1861,7 @@ static void add_header(struct buffer *b, struct module *mod)
 	buf_printf(b, "\n");
 	buf_printf(b, "MODULE_INFO(vermagic, VERMAGIC_STRING);\n");
 	buf_printf(b, "\n");
-	buf_printf(b, "struct module __this_module\n");
+	buf_printf(b, "__visible struct module __this_module\n");
 	buf_printf(b, "__attribute__((section(\".gnu.linkonce.this_module\"))) = {\n");
 	buf_printf(b, "\t.name = KBUILD_MODNAME,\n");
 	if (mod->has_init)
-- 
cgit 


From 5d9efa7ee99eed58388f186c13cf2e2a87e9ceb4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 28 Oct 2013 20:07:50 -0400
Subject: ipv6: Remove privacy config option.

The code for privacy extentions is very mature, and making it
configurable only gives marginal memory/code savings in exchange
for obfuscation and hard to read code via CPP ifdef'ery.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h   |  2 --
 include/net/if_inet6.h |  5 +----
 net/ipv6/Kconfig       | 18 ------------------
 net/ipv6/addrconf.c    | 41 +++--------------------------------------
 4 files changed, 4 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a80a63cfb70c..5d89d1b808a6 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -21,13 +21,11 @@ struct ipv6_devconf {
 	__s32		force_mld_version;
 	__s32		mldv1_unsolicited_report_interval;
 	__s32		mldv2_unsolicited_report_interval;
-#ifdef CONFIG_IPV6_PRIVACY
 	__s32		use_tempaddr;
 	__s32		temp_valid_lft;
 	__s32		temp_prefered_lft;
 	__s32		regen_max_retry;
 	__s32		max_desync_factor;
-#endif
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
 	__s32		accept_ra_pinfo;
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 02ef7727bb55..76d54270f2e2 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -66,11 +66,10 @@ struct inet6_ifaddr {
 	struct hlist_node	addr_lst;
 	struct list_head	if_list;
 
-#ifdef CONFIG_IPV6_PRIVACY
 	struct list_head	tmp_list;
 	struct inet6_ifaddr	*ifpub;
 	int			regen_count;
-#endif
+
 	bool			tokenized;
 
 	struct rcu_head		rcu;
@@ -192,11 +191,9 @@ struct inet6_dev {
 	__u32			if_flags;
 	int			dead;
 
-#ifdef CONFIG_IPV6_PRIVACY
 	u8			rndid[8];
 	struct timer_list	regen_timer;
 	struct list_head	tempaddr_list;
-#endif
 
 	struct in6_addr		token;
 
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index e1a8d903e366..d92e5586783e 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -21,24 +21,6 @@ menuconfig IPV6
 
 if IPV6
 
-config IPV6_PRIVACY
-	bool "IPv6: Privacy Extensions (RFC 3041) support"
-	---help---
-	  Privacy Extensions for Stateless Address Autoconfiguration in IPv6
-	  support.  With this option, additional periodically-altered
-	  pseudo-random global-scope unicast address(es) will be assigned to
-	  your interface(s).
-	
-	  We use our standard pseudo-random algorithm to generate the
-          randomized interface identifier, instead of one described in RFC 3041.
-
-	  By default the kernel does not generate temporary addresses.
-	  To use temporary addresses, do
-	
-	        echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr 
-
-	  See <file:Documentation/networking/ip-sysctl.txt> for details.
-
 config IPV6_ROUTER_PREF
 	bool "IPv6: Router Preference (RFC 4191) support"
 	---help---
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cd3fb301da38..542d09561ed6 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -83,11 +83,7 @@
 #include <linux/if_tunnel.h>
 #include <linux/rtnetlink.h>
 #include <linux/netconf.h>
-
-#ifdef CONFIG_IPV6_PRIVACY
 #include <linux/random.h>
-#endif
-
 #include <linux/uaccess.h>
 #include <asm/unaligned.h>
 
@@ -124,11 +120,9 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
 }
 #endif
 
-#ifdef CONFIG_IPV6_PRIVACY
 static void __ipv6_regen_rndid(struct inet6_dev *idev);
 static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
 static void ipv6_regen_rndid(unsigned long data);
-#endif
 
 static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
 static int ipv6_count_addresses(struct inet6_dev *idev);
@@ -183,13 +177,11 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.rtr_solicits		= MAX_RTR_SOLICITATIONS,
 	.rtr_solicit_interval	= RTR_SOLICITATION_INTERVAL,
 	.rtr_solicit_delay	= MAX_RTR_SOLICITATION_DELAY,
-#ifdef CONFIG_IPV6_PRIVACY
 	.use_tempaddr 		= 0,
 	.temp_valid_lft		= TEMP_VALID_LIFETIME,
 	.temp_prefered_lft	= TEMP_PREFERRED_LIFETIME,
 	.regen_max_retry	= REGEN_MAX_RETRY,
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
-#endif
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
 	.accept_ra_pinfo	= 1,
@@ -221,13 +213,11 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.rtr_solicits		= MAX_RTR_SOLICITATIONS,
 	.rtr_solicit_interval	= RTR_SOLICITATION_INTERVAL,
 	.rtr_solicit_delay	= MAX_RTR_SOLICITATION_DELAY,
-#ifdef CONFIG_IPV6_PRIVACY
 	.use_tempaddr		= 0,
 	.temp_valid_lft		= TEMP_VALID_LIFETIME,
 	.temp_prefered_lft	= TEMP_PREFERRED_LIFETIME,
 	.regen_max_retry	= REGEN_MAX_RETRY,
 	.max_desync_factor	= MAX_DESYNC_FACTOR,
-#endif
 	.max_addresses		= IPV6_MAX_ADDRESSES,
 	.accept_ra_defrtr	= 1,
 	.accept_ra_pinfo	= 1,
@@ -371,7 +361,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	}
 #endif
 
-#ifdef CONFIG_IPV6_PRIVACY
 	INIT_LIST_HEAD(&ndev->tempaddr_list);
 	setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev);
 	if ((dev->flags&IFF_LOOPBACK) ||
@@ -384,7 +373,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 		in6_dev_hold(ndev);
 		ipv6_regen_rndid((unsigned long) ndev);
 	}
-#endif
+
 	ndev->token = in6addr_any;
 
 	if (netif_running(dev) && addrconf_qdisc_ok(dev))
@@ -865,12 +854,10 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	/* Add to inet6_dev unicast addr list. */
 	ipv6_link_dev_addr(idev, ifa);
 
-#ifdef CONFIG_IPV6_PRIVACY
 	if (ifa->flags&IFA_F_TEMPORARY) {
 		list_add(&ifa->tmp_list, &idev->tempaddr_list);
 		in6_ifa_hold(ifa);
 	}
-#endif
 
 	in6_ifa_hold(ifa);
 	write_unlock(&idev->lock);
@@ -913,7 +900,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	spin_unlock_bh(&addrconf_hash_lock);
 
 	write_lock_bh(&idev->lock);
-#ifdef CONFIG_IPV6_PRIVACY
+
 	if (ifp->flags&IFA_F_TEMPORARY) {
 		list_del(&ifp->tmp_list);
 		if (ifp->ifpub) {
@@ -922,7 +909,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 		}
 		__in6_ifa_put(ifp);
 	}
-#endif
 
 	list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) {
 		if (ifa == ifp) {
@@ -1013,7 +999,6 @@ out:
 	in6_ifa_put(ifp);
 }
 
-#ifdef CONFIG_IPV6_PRIVACY
 static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift)
 {
 	struct inet6_dev *idev = ifp->idev;
@@ -1116,7 +1101,6 @@ retry:
 out:
 	return ret;
 }
-#endif
 
 /*
  *	Choose an appropriate source address (RFC3484)
@@ -1131,9 +1115,7 @@ enum {
 #endif
 	IPV6_SADDR_RULE_OIF,
 	IPV6_SADDR_RULE_LABEL,
-#ifdef CONFIG_IPV6_PRIVACY
 	IPV6_SADDR_RULE_PRIVACY,
-#endif
 	IPV6_SADDR_RULE_ORCHID,
 	IPV6_SADDR_RULE_PREFIX,
 	IPV6_SADDR_RULE_MAX
@@ -1247,7 +1229,6 @@ static int ipv6_get_saddr_eval(struct net *net,
 				      &score->ifa->addr, score->addr_type,
 				      score->ifa->idev->dev->ifindex) == dst->label;
 		break;
-#ifdef CONFIG_IPV6_PRIVACY
 	case IPV6_SADDR_RULE_PRIVACY:
 	    {
 		/* Rule 7: Prefer public address
@@ -1259,7 +1240,6 @@ static int ipv6_get_saddr_eval(struct net *net,
 		ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp;
 		break;
 	    }
-#endif
 	case IPV6_SADDR_RULE_ORCHID:
 		/* Rule 8-: Prefer ORCHID vs ORCHID or
 		 *	    non-ORCHID vs non-ORCHID
@@ -1588,7 +1568,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 		if (dad_failed)
 			ipv6_ifa_notify(0, ifp);
 		in6_ifa_put(ifp);
-#ifdef CONFIG_IPV6_PRIVACY
 	} else if (ifp->flags&IFA_F_TEMPORARY) {
 		struct inet6_ifaddr *ifpub;
 		spin_lock_bh(&ifp->lock);
@@ -1602,7 +1581,6 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 			spin_unlock_bh(&ifp->lock);
 		}
 		ipv6_del_addr(ifp);
-#endif
 	} else
 		ipv6_del_addr(ifp);
 }
@@ -1851,7 +1829,6 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
 	return err;
 }
 
-#ifdef CONFIG_IPV6_PRIVACY
 /* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
 static void __ipv6_regen_rndid(struct inet6_dev *idev)
 {
@@ -1919,7 +1896,6 @@ static void  __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmp
 	if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
 		__ipv6_regen_rndid(idev);
 }
-#endif
 
 /*
  *	Add prefix route.
@@ -2207,9 +2183,7 @@ ok:
 		if (ifp) {
 			int flags;
 			unsigned long now;
-#ifdef CONFIG_IPV6_PRIVACY
 			struct inet6_ifaddr *ift;
-#endif
 			u32 stored_lft;
 
 			/* update lifetime (RFC2462 5.5.3 e) */
@@ -2250,7 +2224,6 @@ ok:
 			} else
 				spin_unlock(&ifp->lock);
 
-#ifdef CONFIG_IPV6_PRIVACY
 			read_lock_bh(&in6_dev->lock);
 			/* update all temporary addresses in the list */
 			list_for_each_entry(ift, &in6_dev->tempaddr_list,
@@ -2315,7 +2288,7 @@ ok:
 			} else {
 				read_unlock_bh(&in6_dev->lock);
 			}
-#endif
+
 			in6_ifa_put(ifp);
 			addrconf_verify(0);
 		}
@@ -2995,7 +2968,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	if (!how)
 		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
 
-#ifdef CONFIG_IPV6_PRIVACY
 	if (how && del_timer(&idev->regen_timer))
 		in6_dev_put(idev);
 
@@ -3015,7 +2987,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		in6_ifa_put(ifa);
 		write_lock_bh(&idev->lock);
 	}
-#endif
 
 	while (!list_empty(&idev->addr_list)) {
 		ifa = list_first_entry(&idev->addr_list,
@@ -3528,7 +3499,6 @@ restart:
 					in6_ifa_put(ifp);
 					goto restart;
 				}
-#ifdef CONFIG_IPV6_PRIVACY
 			} else if ((ifp->flags&IFA_F_TEMPORARY) &&
 				   !(ifp->flags&IFA_F_TENTATIVE)) {
 				unsigned long regen_advance = ifp->idev->cnf.regen_max_retry *
@@ -3556,7 +3526,6 @@ restart:
 				} else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next))
 					next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ;
 				spin_unlock(&ifp->lock);
-#endif
 			} else {
 				/* ifp->prefered_lft <= ifp->valid_lft */
 				if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next))
@@ -4128,13 +4097,11 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 		jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval);
 	array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] =
 		jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval);
-#ifdef CONFIG_IPV6_PRIVACY
 	array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr;
 	array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft;
 	array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft;
 	array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry;
 	array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor;
-#endif
 	array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses;
 	array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr;
 	array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo;
@@ -4828,7 +4795,6 @@ static struct addrconf_sysctl_table
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_ms_jiffies,
 		},
-#ifdef CONFIG_IPV6_PRIVACY
 		{
 			.procname	= "use_tempaddr",
 			.data		= &ipv6_devconf.use_tempaddr,
@@ -4864,7 +4830,6 @@ static struct addrconf_sysctl_table
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-#endif
 		{
 			.procname	= "max_addresses",
 			.data		= &ipv6_devconf.max_addresses,
-- 
cgit 


From 46f9c2b925ac12e5ad8b8b7c90c71dacc9d5db37 Mon Sep 17 00:00:00 2001
From: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Date: Tue, 29 Oct 2013 09:38:50 +1030
Subject: virtio_ring: change host notification API

Currently a host kick error is silently ignored and not reflected in
the virtqueue of a particular virtio device.

Changing the notify API for guest->host notification seems to be one
prerequisite in order to be able to handle such errors in the context
where the kick is triggered.

This patch changes the notify API. The notify function must return a
bool return value. It returns false if the host notification failed.

Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/lguest/lguest_device.c         |  3 ++-
 drivers/remoteproc/remoteproc_virtio.c |  3 ++-
 drivers/s390/kvm/kvm_virtio.c          |  8 ++++++--
 drivers/s390/kvm/virtio_ccw.c          |  5 ++++-
 drivers/virtio/virtio_mmio.c           |  3 ++-
 drivers/virtio/virtio_pci.c            |  3 ++-
 drivers/virtio/virtio_ring.c           |  4 ++--
 include/linux/virtio_ring.h            |  2 +-
 tools/virtio/virtio_test.c             |  3 ++-
 tools/virtio/vringh_test.c             | 13 +++++++++----
 10 files changed, 32 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index b3256ff0d426..d0a1d8a45c81 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -229,7 +229,7 @@ struct lguest_vq_info {
  * make a hypercall.  We hand the physical address of the virtqueue so the Host
  * knows which virtqueue we're talking about.
  */
-static void lg_notify(struct virtqueue *vq)
+static bool lg_notify(struct virtqueue *vq)
 {
 	/*
 	 * We store our virtqueue information in the "priv" pointer of the
@@ -238,6 +238,7 @@ static void lg_notify(struct virtqueue *vq)
 	struct lguest_vq_info *lvq = vq->priv;
 
 	hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0, 0);
+	return true;
 }
 
 /* An extern declaration inside a C file is bad form.  Don't do it. */
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index b09c75c21b60..a34b50690b4e 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -30,7 +30,7 @@
 #include "remoteproc_internal.h"
 
 /* kick the remote processor, and let it know which virtqueue to poke at */
-static void rproc_virtio_notify(struct virtqueue *vq)
+static bool rproc_virtio_notify(struct virtqueue *vq)
 {
 	struct rproc_vring *rvring = vq->priv;
 	struct rproc *rproc = rvring->rvdev->rproc;
@@ -39,6 +39,7 @@ static void rproc_virtio_notify(struct virtqueue *vq)
 	dev_dbg(&rproc->dev, "kicking vq index: %d\n", notifyid);
 
 	rproc->ops->kick(rproc, notifyid);
+	return true;
 }
 
 /**
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index af2166fa5159..1abd0db29915 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -166,11 +166,15 @@ static void kvm_reset(struct virtio_device *vdev)
  * make a hypercall.  We hand the address  of the virtqueue so the Host
  * knows which virtqueue we're talking about.
  */
-static void kvm_notify(struct virtqueue *vq)
+static bool kvm_notify(struct virtqueue *vq)
 {
+	long rc;
 	struct kvm_vqconfig *config = vq->priv;
 
-	kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
+	rc = kvm_hypercall1(KVM_S390_VIRTIO_NOTIFY, config->address);
+	if (rc < 0)
+		return false;
+	return true;
 }
 
 /*
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index 779dc5136291..d6297176ab85 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -162,7 +162,7 @@ static inline long do_kvm_notify(struct subchannel_id schid,
 	return __rc;
 }
 
-static void virtio_ccw_kvm_notify(struct virtqueue *vq)
+static bool virtio_ccw_kvm_notify(struct virtqueue *vq)
 {
 	struct virtio_ccw_vq_info *info = vq->priv;
 	struct virtio_ccw_device *vcdev;
@@ -171,6 +171,9 @@ static void virtio_ccw_kvm_notify(struct virtqueue *vq)
 	vcdev = to_vc_device(info->vq->vdev);
 	ccw_device_get_schid(vcdev->cdev, &schid);
 	info->cookie = do_kvm_notify(schid, vq->index, info->cookie);
+	if (info->cookie < 0)
+		return false;
+	return true;
 }
 
 static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev,
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 1ba0d6831015..e9fdeb861992 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -219,13 +219,14 @@ static void vm_reset(struct virtio_device *vdev)
 /* Transport interface */
 
 /* the notify function used when creating a virt queue */
-static void vm_notify(struct virtqueue *vq)
+static bool vm_notify(struct virtqueue *vq)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 
 	/* We write the queue's selector into the notification register to
 	 * signal the other end */
 	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	return true;
 }
 
 /* Notify all virtqueues on an interrupt. */
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 98917fc872a4..a37c69941d30 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -197,13 +197,14 @@ static void vp_reset(struct virtio_device *vdev)
 }
 
 /* the notify function used when creating a virt queue */
-static void vp_notify(struct virtqueue *vq)
+static bool vp_notify(struct virtqueue *vq)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 
 	/* we write the queue's selector into the notification register to
 	 * signal the other end */
 	iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	return true;
 }
 
 /* Handle a configuration change: Tell driver if it wants to know. */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 6547d46171b3..97dd51619b55 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -81,7 +81,7 @@ struct vring_virtqueue
 	u16 last_used_idx;
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
-	void (*notify)(struct virtqueue *vq);
+	bool (*notify)(struct virtqueue *vq);
 
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
@@ -744,7 +744,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
 				      void *pages,
-				      void (*notify)(struct virtqueue *),
+				      bool (*notify)(struct virtqueue *),
 				      void (*callback)(struct virtqueue *),
 				      const char *name)
 {
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index b300787af8e0..67e06fe18c03 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -71,7 +71,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
 				      void *pages,
-				      void (*notify)(struct virtqueue *vq),
+				      bool (*notify)(struct virtqueue *vq),
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name);
 void vring_del_virtqueue(struct virtqueue *vq);
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index da7a19558281..059cb723f6a7 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -41,13 +41,14 @@ struct vdev_info {
 	struct vhost_memory *mem;
 };
 
-void vq_notify(struct virtqueue *vq)
+bool vq_notify(struct virtqueue *vq)
 {
 	struct vq_info *info = vq->priv;
 	unsigned long long v = 1;
 	int r;
 	r = write(info->kick, &v, sizeof v);
 	assert(r == sizeof v);
+	return true;
 }
 
 void vq_callback(struct virtqueue *vq)
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
index d053ea40c001..14a4f4cab5b9 100644
--- a/tools/virtio/vringh_test.c
+++ b/tools/virtio/vringh_test.c
@@ -22,7 +22,7 @@ static u64 user_addr_offset;
 #define RINGSIZE 256
 #define ALIGN 4096
 
-static void never_notify_host(struct virtqueue *vq)
+static bool never_notify_host(struct virtqueue *vq)
 {
 	abort();
 }
@@ -65,17 +65,22 @@ struct guest_virtio_device {
 	unsigned long notifies;
 };
 
-static void parallel_notify_host(struct virtqueue *vq)
+static bool parallel_notify_host(struct virtqueue *vq)
 {
+	int rc;
 	struct guest_virtio_device *gvdev;
 
 	gvdev = container_of(vq->vdev, struct guest_virtio_device, vdev);
-	write(gvdev->to_host_fd, "", 1);
+	rc = write(gvdev->to_host_fd, "", 1);
+	if (rc < 0)
+		return false;
 	gvdev->notifies++;
+	return true;
 }
 
-static void no_notify_host(struct virtqueue *vq)
+static bool no_notify_host(struct virtqueue *vq)
 {
+	return true;
 }
 
 #define NUM_XFERS (10000000)
-- 
cgit 


From 5b1bf7cb673ade0ab5c75f200dce911d9fb91c21 Mon Sep 17 00:00:00 2001
From: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Date: Tue, 29 Oct 2013 09:39:48 +1030
Subject: virtio_ring: let virtqueue_{kick()/notify()} return a bool

virtqueue_{kick()/notify()} should exploit the new host notification API.
If the notify call returned with a negative value the host kick failed
(e.g. a kick triggered after a device was hot-unplugged). In this case
the virtqueue is set to 'broken' and false is returned, otherwise true.

Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio_ring.c | 20 ++++++++++++++++----
 include/linux/virtio.h       |  4 ++--
 2 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 97dd51619b55..b47142723119 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -430,13 +430,22 @@ EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
  * @vq: the struct virtqueue
  *
  * This does not need to be serialized.
+ *
+ * Returns false if host notify failed or queue is broken, otherwise true.
  */
-void virtqueue_notify(struct virtqueue *_vq)
+bool virtqueue_notify(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
+	if (unlikely(vq->broken))
+		return false;
+
 	/* Prod other side to tell it about changes. */
-	vq->notify(_vq);
+	if (vq->notify(_vq) < 0) {
+		vq->broken = true;
+		return false;
+	}
+	return true;
 }
 EXPORT_SYMBOL_GPL(virtqueue_notify);
 
@@ -449,11 +458,14 @@ EXPORT_SYMBOL_GPL(virtqueue_notify);
  *
  * Caller must ensure we don't call this with other virtqueue
  * operations at the same time (except where noted).
+ *
+ * Returns false if kick failed, otherwise true.
  */
-void virtqueue_kick(struct virtqueue *vq)
+bool virtqueue_kick(struct virtqueue *vq)
 {
 	if (virtqueue_kick_prepare(vq))
-		virtqueue_notify(vq);
+		return virtqueue_notify(vq);
+	return true;
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 36d36cc89329..9b4de15fcb2f 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -51,11 +51,11 @@ int virtqueue_add_sgs(struct virtqueue *vq,
 		      void *data,
 		      gfp_t gfp);
 
-void virtqueue_kick(struct virtqueue *vq);
+bool virtqueue_kick(struct virtqueue *vq);
 
 bool virtqueue_kick_prepare(struct virtqueue *vq);
 
-void virtqueue_notify(struct virtqueue *vq);
+bool virtqueue_notify(struct virtqueue *vq);
 
 void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
 
-- 
cgit 


From b3b32c94133621c9ba7e4c8f29ec7533f2f4d8ec Mon Sep 17 00:00:00 2001
From: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Date: Tue, 29 Oct 2013 09:40:19 +1030
Subject: virtio_ring: add new function virtqueue_is_broken()

Add new function virtqueue_is_broken(). Callers of virtqueue_get_buf()
should check for a broken queue.

Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/virtio/virtio_ring.c | 8 ++++++++
 include/linux/virtio.h       | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b47142723119..f47777582ce5 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -851,4 +851,12 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
 
+bool virtqueue_is_broken(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->broken;
+}
+EXPORT_SYMBOL_GPL(virtqueue_is_broken);
+
 MODULE_LICENSE("GPL");
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 9b4de15fcb2f..e4abb84199be 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -73,6 +73,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
+bool virtqueue_is_broken(struct virtqueue *vq);
+
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
-- 
cgit 


From 123b0d1ba0a98ef12550d82b79ccb8d89090f871 Mon Sep 17 00:00:00 2001
From: Mathias Krause <mathias.krause@secunet.com>
Date: Fri, 18 Oct 2013 12:09:04 +0200
Subject: net: esp{4,6}: remove padlen from struct esp_data

The padlen member of struct esp_data is always zero. Get rid of it.

Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/esp.h | 3 ---
 net/ipv4/esp4.c   | 9 +--------
 net/ipv6/esp6.c   | 9 +--------
 3 files changed, 2 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/esp.h b/include/net/esp.h
index 1356dda00d22..706b740d7057 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -6,9 +6,6 @@
 struct crypto_aead;
 
 struct esp_data {
-	/* 0..255 */
-	int padlen;
-
 	/* Confidentiality & Integrity */
 	struct crypto_aead *aead;
 };
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 109ee89f123e..8b5386a6cb88 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -154,8 +154,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	}
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	clen = ALIGN(skb->len + 2 + tfclen, blksize);
-	if (esp->padlen)
-		clen = ALIGN(clen, esp->padlen);
 	plen = clen - skb->len - tfclen;
 
 	err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
@@ -461,7 +459,6 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 {
 	struct esp_data *esp = x->data;
 	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
-	u32 align = max_t(u32, blksize, esp->padlen);
 	unsigned int net_adj;
 
 	switch (x->props.mode) {
@@ -477,7 +474,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 	}
 
 	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
-		 net_adj) & ~(align - 1)) + net_adj - 2;
+		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
 static void esp4_err(struct sk_buff *skb, u32 info)
@@ -659,8 +656,6 @@ static int esp_init_state(struct xfrm_state *x)
 
 	aead = esp->aead;
 
-	esp->padlen = 0;
-
 	x->props.header_len = sizeof(struct ip_esp_hdr) +
 			      crypto_aead_ivsize(aead);
 	if (x->props.mode == XFRM_MODE_TUNNEL)
@@ -683,8 +678,6 @@ static int esp_init_state(struct xfrm_state *x)
 	}
 
 	align = ALIGN(crypto_aead_blocksize(aead), 4);
-	if (esp->padlen)
-		align = max_t(u32, align, esp->padlen);
 	x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead);
 
 error:
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index d3618a78fcac..0073cd096984 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -181,8 +181,6 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	}
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	clen = ALIGN(skb->len + 2 + tfclen, blksize);
-	if (esp->padlen)
-		clen = ALIGN(clen, esp->padlen);
 	plen = clen - skb->len - tfclen;
 
 	err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
@@ -416,7 +414,6 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 {
 	struct esp_data *esp = x->data;
 	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
-	u32 align = max_t(u32, blksize, esp->padlen);
 	unsigned int net_adj;
 
 	if (x->props.mode != XFRM_MODE_TUNNEL)
@@ -425,7 +422,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 		net_adj = 0;
 
 	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
-		 net_adj) & ~(align - 1)) + net_adj - 2;
+		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
 static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
@@ -606,8 +603,6 @@ static int esp6_init_state(struct xfrm_state *x)
 
 	aead = esp->aead;
 
-	esp->padlen = 0;
-
 	x->props.header_len = sizeof(struct ip_esp_hdr) +
 			      crypto_aead_ivsize(aead);
 	switch (x->props.mode) {
@@ -626,8 +621,6 @@ static int esp6_init_state(struct xfrm_state *x)
 	}
 
 	align = ALIGN(crypto_aead_blocksize(aead), 4);
-	if (esp->padlen)
-		align = max_t(u32, align, esp->padlen);
 	x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead);
 
 error:
-- 
cgit 


From 1c5ad13f7c2b2afe30e43858d04fff979dc9d243 Mon Sep 17 00:00:00 2001
From: Mathias Krause <mathias.krause@secunet.com>
Date: Fri, 18 Oct 2013 12:09:05 +0200
Subject: net: esp{4,6}: get rid of struct esp_data

struct esp_data consists of a single pointer, vanishing the need for it
to be a structure. Fold the pointer into 'data' direcly, removing one
level of pointer indirection.

Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/esp.h |  7 -------
 net/ipv4/esp4.c   | 40 ++++++++++++++--------------------------
 net/ipv6/esp6.c   | 39 ++++++++++++++-------------------------
 3 files changed, 28 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/net/esp.h b/include/net/esp.h
index 706b740d7057..c92213c38312 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -3,13 +3,6 @@
 
 #include <linux/skbuff.h>
 
-struct crypto_aead;
-
-struct esp_data {
-	/* Confidentiality & Integrity */
-	struct crypto_aead *aead;
-};
-
 void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
 
 struct ip_esp_hdr;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 8b5386a6cb88..7785b28061ac 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -121,7 +121,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	struct aead_givcrypt_request *req;
 	struct scatterlist *sg;
 	struct scatterlist *asg;
-	struct esp_data *esp;
 	struct sk_buff *trailer;
 	void *tmp;
 	u8 *iv;
@@ -139,8 +138,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	/* skb is pure payload to encrypt */
 
-	esp = x->data;
-	aead = esp->aead;
+	aead = x->data;
 	alen = crypto_aead_authsize(aead);
 
 	tfclen = 0;
@@ -278,8 +276,7 @@ static int esp_input_done2(struct sk_buff *skb, int err)
 {
 	const struct iphdr *iph;
 	struct xfrm_state *x = xfrm_input_state(skb);
-	struct esp_data *esp = x->data;
-	struct crypto_aead *aead = esp->aead;
+	struct crypto_aead *aead = x->data;
 	int alen = crypto_aead_authsize(aead);
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
 	int elen = skb->len - hlen;
@@ -374,8 +371,7 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct ip_esp_hdr *esph;
-	struct esp_data *esp = x->data;
-	struct crypto_aead *aead = esp->aead;
+	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
 	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
@@ -457,8 +453,8 @@ out:
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 {
-	struct esp_data *esp = x->data;
-	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
+	struct crypto_aead *aead = x->data;
+	u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	unsigned int net_adj;
 
 	switch (x->props.mode) {
@@ -473,7 +469,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
 		BUG();
 	}
 
-	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
+	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
@@ -508,18 +504,16 @@ static void esp4_err(struct sk_buff *skb, u32 info)
 
 static void esp_destroy(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
+	struct crypto_aead *aead = x->data;
 
-	if (!esp)
+	if (!aead)
 		return;
 
-	crypto_free_aead(esp->aead);
-	kfree(esp);
+	crypto_free_aead(aead);
 }
 
 static int esp_init_aead(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
 	struct crypto_aead *aead;
 	int err;
 
@@ -528,7 +522,7 @@ static int esp_init_aead(struct xfrm_state *x)
 	if (IS_ERR(aead))
 		goto error;
 
-	esp->aead = aead;
+	x->data = aead;
 
 	err = crypto_aead_setkey(aead, x->aead->alg_key,
 				 (x->aead->alg_key_len + 7) / 8);
@@ -545,7 +539,6 @@ error:
 
 static int esp_init_authenc(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
 	struct crypto_aead *aead;
 	struct crypto_authenc_key_param *param;
 	struct rtattr *rta;
@@ -580,7 +573,7 @@ static int esp_init_authenc(struct xfrm_state *x)
 	if (IS_ERR(aead))
 		goto error;
 
-	esp->aead = aead;
+	x->data = aead;
 
 	keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) +
 		 (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param));
@@ -635,16 +628,11 @@ error:
 
 static int esp_init_state(struct xfrm_state *x)
 {
-	struct esp_data *esp;
 	struct crypto_aead *aead;
 	u32 align;
 	int err;
 
-	esp = kzalloc(sizeof(*esp), GFP_KERNEL);
-	if (esp == NULL)
-		return -ENOMEM;
-
-	x->data = esp;
+	x->data = NULL;
 
 	if (x->aead)
 		err = esp_init_aead(x);
@@ -654,7 +642,7 @@ static int esp_init_state(struct xfrm_state *x)
 	if (err)
 		goto error;
 
-	aead = esp->aead;
+	aead = x->data;
 
 	x->props.header_len = sizeof(struct ip_esp_hdr) +
 			      crypto_aead_ivsize(aead);
@@ -678,7 +666,7 @@ static int esp_init_state(struct xfrm_state *x)
 	}
 
 	align = ALIGN(crypto_aead_blocksize(aead), 4);
-	x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead);
+	x->props.trailer_len = align + 1 + crypto_aead_authsize(aead);
 
 error:
 	return err;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 0073cd096984..87eb79e65e49 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -164,10 +164,9 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	u8 *iv;
 	u8 *tail;
 	__be32 *seqhi;
-	struct esp_data *esp = x->data;
 
 	/* skb is pure payload to encrypt */
-	aead = esp->aead;
+	aead = x->data;
 	alen = crypto_aead_authsize(aead);
 
 	tfclen = 0;
@@ -269,8 +268,7 @@ error:
 static int esp_input_done2(struct sk_buff *skb, int err)
 {
 	struct xfrm_state *x = xfrm_input_state(skb);
-	struct esp_data *esp = x->data;
-	struct crypto_aead *aead = esp->aead;
+	struct crypto_aead *aead = x->data;
 	int alen = crypto_aead_authsize(aead);
 	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
 	int elen = skb->len - hlen;
@@ -323,8 +321,7 @@ static void esp_input_done(struct crypto_async_request *base, int err)
 static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct ip_esp_hdr *esph;
-	struct esp_data *esp = x->data;
-	struct crypto_aead *aead = esp->aead;
+	struct crypto_aead *aead = x->data;
 	struct aead_request *req;
 	struct sk_buff *trailer;
 	int elen = skb->len - sizeof(*esph) - crypto_aead_ivsize(aead);
@@ -412,8 +409,8 @@ out:
 
 static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 {
-	struct esp_data *esp = x->data;
-	u32 blksize = ALIGN(crypto_aead_blocksize(esp->aead), 4);
+	struct crypto_aead *aead = x->data;
+	u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	unsigned int net_adj;
 
 	if (x->props.mode != XFRM_MODE_TUNNEL)
@@ -421,7 +418,7 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
 	else
 		net_adj = 0;
 
-	return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
+	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
 		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
 
@@ -452,18 +449,16 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 static void esp6_destroy(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
+	struct crypto_aead *aead = x->data;
 
-	if (!esp)
+	if (!aead)
 		return;
 
-	crypto_free_aead(esp->aead);
-	kfree(esp);
+	crypto_free_aead(aead);
 }
 
 static int esp_init_aead(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
 	struct crypto_aead *aead;
 	int err;
 
@@ -472,7 +467,7 @@ static int esp_init_aead(struct xfrm_state *x)
 	if (IS_ERR(aead))
 		goto error;
 
-	esp->aead = aead;
+	x->data = aead;
 
 	err = crypto_aead_setkey(aead, x->aead->alg_key,
 				 (x->aead->alg_key_len + 7) / 8);
@@ -489,7 +484,6 @@ error:
 
 static int esp_init_authenc(struct xfrm_state *x)
 {
-	struct esp_data *esp = x->data;
 	struct crypto_aead *aead;
 	struct crypto_authenc_key_param *param;
 	struct rtattr *rta;
@@ -524,7 +518,7 @@ static int esp_init_authenc(struct xfrm_state *x)
 	if (IS_ERR(aead))
 		goto error;
 
-	esp->aead = aead;
+	x->data = aead;
 
 	keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) +
 		 (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param));
@@ -579,7 +573,6 @@ error:
 
 static int esp6_init_state(struct xfrm_state *x)
 {
-	struct esp_data *esp;
 	struct crypto_aead *aead;
 	u32 align;
 	int err;
@@ -587,11 +580,7 @@ static int esp6_init_state(struct xfrm_state *x)
 	if (x->encap)
 		return -EINVAL;
 
-	esp = kzalloc(sizeof(*esp), GFP_KERNEL);
-	if (esp == NULL)
-		return -ENOMEM;
-
-	x->data = esp;
+	x->data = NULL;
 
 	if (x->aead)
 		err = esp_init_aead(x);
@@ -601,7 +590,7 @@ static int esp6_init_state(struct xfrm_state *x)
 	if (err)
 		goto error;
 
-	aead = esp->aead;
+	aead = x->data;
 
 	x->props.header_len = sizeof(struct ip_esp_hdr) +
 			      crypto_aead_ivsize(aead);
@@ -621,7 +610,7 @@ static int esp6_init_state(struct xfrm_state *x)
 	}
 
 	align = ALIGN(crypto_aead_blocksize(aead), 4);
-	x->props.trailer_len = align + 1 + crypto_aead_authsize(esp->aead);
+	x->props.trailer_len = align + 1 + crypto_aead_authsize(aead);
 
 error:
 	return err;
-- 
cgit 


From e6cd988c27bb5918630db67b3526c9e78e786818 Mon Sep 17 00:00:00 2001
From: Joseph Gasparakis <joseph.gasparakis@intel.com>
Date: Thu, 24 Oct 2013 06:27:10 +0000
Subject: vxlan: Have the NIC drivers do less work for offloads

This patch removes the burden from the NIC drivers to check if the
vxlan driver is enabled in the kernel and also makes available
the vxlan headrooms to them.

Signed-off-by: Joseph Gasparakis <joseph.gasparakis@intel.com>
Tested-by: Kavindya Deegala <kavindya.s.deegala@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/vxlan.c |  4 ----
 include/net/vxlan.h | 11 +++++++++++
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 75a3a740ce19..24260ced86d2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -60,10 +60,6 @@
 
 #define VXLAN_N_VID	(1u << 24)
 #define VXLAN_VID_MASK	(VXLAN_N_VID - 1)
-/* IP header + UDP + VXLAN + Ethernet header */
-#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
-/* IPv6 header + UDP + VXLAN + Ethernet header */
-#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
 #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
 
 #define VXLAN_FLAGS 0x08000000	/* struct vxlanhdr.vx_flags required value. */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 2d64d3cd4999..6b6d180fb91a 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -36,5 +36,16 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 
 __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb);
 
+/* IP header + UDP + VXLAN + Ethernet header */
+#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
+/* IPv6 header + UDP + VXLAN + Ethernet header */
+#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
+
+#if IS_ENABLED(CONFIG_VXLAN)
 void vxlan_get_rx_port(struct net_device *netdev);
+#else
+static inline void vxlan_get_rx_port(struct net_device *netdev)
+{
+}
+#endif
 #endif
-- 
cgit 


From 80c33ddd31d0e801953e02b7b003f395c1920e4e Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Sat, 21 Sep 2013 05:05:39 +0000
Subject: net: add might_sleep() call to napi_disable

napi_disable uses an msleep() call to wait for outstanding napi work to be
finished after setting the disable bit. It does not always sleep incase there
was no outstanding work. This resulted in a rare bug in ixgbe_down operation
where a napi_disable call took place inside of a local_bh_disable()d context.
In order to enable easier detection of future sleep while atomic BUGs, this
patch adds a might_sleep() call, so that every use of napi_disable during
atomic context will be visible.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: Alexander Duyck <alexander.duyck@intel.com>
Cc: Hyong-Youb Kim <hykim@myri.com>
Cc: Amir Vadai <amirv@mellanox.com>
Cc: Dmitry Kravkov <dmitry@broadcom.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 27f62f746621..cb1d918ecdf1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -483,6 +483,7 @@ void napi_hash_del(struct napi_struct *napi);
  */
 static inline void napi_disable(struct napi_struct *n)
 {
+	might_sleep();
 	set_bit(NAPI_STATE_DISABLE, &n->state);
 	while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
 		msleep(1);
-- 
cgit 


From f51a07d05c5142e73f781d878f411d63d3548a49 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 19 Sep 2013 18:35:54 -0700
Subject: framebuffer: Add fb_<level> convenience logging macros

Add fb_<level> convenience macros for emitting the
"fb%d: ", struct fb_info->node value.

Neatens and shortens the code a bit.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/linux/fb.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/fb.h b/include/linux/fb.h
index ffac70aab3e9..70c4836e4a9f 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -792,4 +792,16 @@ extern int fb_find_mode(struct fb_var_screeninfo *var,
 			const struct fb_videomode *default_mode,
 			unsigned int default_bpp);
 
+/* Convenience logging macros */
+#define fb_err(fb_info, fmt, ...)					\
+	pr_err("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+#define fb_notice(info, fmt, ...)					\
+	pr_notice("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+#define fb_warn(fb_info, fmt, ...)					\
+	pr_warn("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+#define fb_info(fb_info, fmt, ...)					\
+	pr_info("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+#define fb_dbg(fb_info, fmt, ...)					\
+	pr_debug("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+
 #endif /* _LINUX_FB_H */
-- 
cgit 


From e12483e0f3dbc32dad8fa1dc97efac22b6aee94f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 29 Oct 2013 16:37:11 +0100
Subject: ALSA: ak4114: Fix wrong register array size

The size of the register cache array is actually 6 instead of 7,
as it caches up to AK4114_REG_INT1_MASK.  This resulted in unexpected
access out of array range, although most of them aren't so serious
(just reading one more byte on the stack at snd_ak4114_create()).

Also, the check of cache size was wrongly done by checking with
sizeof() instead of ARRAY_SIZE().  Fixed this together.

(And yes, hardcoded numbers are bad, but I keep the coding style as is
 for making it clear what this patch actually does.)

Spotted by coverity among several CIDs, e.g. 711621.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ak4114.h   | 4 ++--
 sound/i2c/other/ak4114.c | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 3ce69fd92523..52f02a60dba7 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -170,7 +170,7 @@ struct ak4114 {
 	void * private_data;
 	unsigned int init: 1;
 	spinlock_t lock;
-	unsigned char regmap[7];
+	unsigned char regmap[6];
 	unsigned char txcsb[5];
 	struct snd_kcontrol *kctls[AK4114_CONTROLS];
 	struct snd_pcm_substream *playback_substream;
@@ -189,7 +189,7 @@ struct ak4114 {
 
 int snd_ak4114_create(struct snd_card *card,
 		      ak4114_read_t *read, ak4114_write_t *write,
-		      const unsigned char pgm[7], const unsigned char txcsb[5],
+		      const unsigned char pgm[6], const unsigned char txcsb[5],
 		      void *private_data, struct ak4114 **r_ak4114);
 void snd_ak4114_reg_write(struct ak4114 *ak4114, unsigned char reg, unsigned char mask, unsigned char val);
 void snd_ak4114_reinit(struct ak4114 *ak4114);
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index 5bf4fca19e48..15ae0250eace 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -60,7 +60,7 @@ static void reg_dump(struct ak4114 *ak4114)
 
 	printk(KERN_DEBUG "AK4114 REG DUMP:\n");
 	for (i = 0; i < 0x20; i++)
-		printk(KERN_DEBUG "reg[%02x] = %02x (%02x)\n", i, reg_read(ak4114, i), i < sizeof(ak4114->regmap) ? ak4114->regmap[i] : 0);
+		printk(KERN_DEBUG "reg[%02x] = %02x (%02x)\n", i, reg_read(ak4114, i), i < ARRAY_SIZE(ak4114->regmap) ? ak4114->regmap[i] : 0);
 }
 #endif
 
@@ -81,7 +81,7 @@ static int snd_ak4114_dev_free(struct snd_device *device)
 
 int snd_ak4114_create(struct snd_card *card,
 		      ak4114_read_t *read, ak4114_write_t *write,
-		      const unsigned char pgm[7], const unsigned char txcsb[5],
+		      const unsigned char pgm[6], const unsigned char txcsb[5],
 		      void *private_data, struct ak4114 **r_ak4114)
 {
 	struct ak4114 *chip;
@@ -101,7 +101,7 @@ int snd_ak4114_create(struct snd_card *card,
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
 
-	for (reg = 0; reg < 7; reg++)
+	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
 	for (reg = 0; reg < 5; reg++)
 		chip->txcsb[reg] = txcsb[reg];
@@ -142,7 +142,7 @@ static void ak4114_init_regs(struct ak4114 *chip)
 	/* release reset, but leave powerdown */
 	reg_write(chip, AK4114_REG_PWRDN, (old | AK4114_RST) & ~AK4114_PWN);
 	udelay(200);
-	for (reg = 1; reg < 7; reg++)
+	for (reg = 1; reg < 6; reg++)
 		reg_write(chip, reg, chip->regmap[reg]);
 	for (reg = 0; reg < 5; reg++)
 		reg_write(chip, reg + AK4114_REG_TXCSB0, chip->txcsb[reg]);
-- 
cgit 


From c2d3f25dda016d9697c5416810d4528770f0a281 Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Wed, 9 Oct 2013 14:08:09 +0200
Subject: uprobes: Remove the wrong __weak attribute

linux/uprobes.h declares arch_uprobe_skip_sstep() as a weak function.
But as there is no definition of generic version so when trying to build
uprobes for an architecture that doesn't yet have a arch_uprobe_skip_sstep()
implementation, the vmlinux will try to call arch_uprobe_skip_sstep()
somehwere in Stupidhistan leading to a system crash.  We rather want a
proper link error so remove arch_uprobe_skip_sstep().

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/uprobes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 06f28beed7c2..e6fba627ea45 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -123,7 +123,7 @@ extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
 extern bool uprobe_deny_signal(void);
-extern bool __weak arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs);
+extern bool arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void uprobe_clear_state(struct mm_struct *mm);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
-- 
cgit 


From 3ab679661721b1ec2aaad99a801870ed59ab1110 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 16 Oct 2013 19:39:37 +0200
Subject: uprobes: Teach uprobe_copy_process() to handle CLONE_VFORK

uprobe_copy_process() does nothing if the child shares ->mm with
the forking process, but there is a special case: CLONE_VFORK.
In this case it would be more correct to do dup_utask() but avoid
dup_xol(). This is not that important, the child should not unwind
its stack too much, this can corrupt the parent's stack, but at
least we need this to allow to ret-probe __vfork() itself.

Note: in theory, it would be better to check task_pt_regs(p)->sp
instead of CLONE_VFORK, we need to dup_utask() if and only if the
child can return from the function called by the parent. But this
needs the arch-dependant helper, and I think that nobody actually
does clone(same_stack, CLONE_VM).

Reported-by: Martin Cermak <mcermak@redhat.com>
Reported-by: David Smith <dsmith@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/uprobes.h |  4 ++--
 kernel/events/uprobes.c | 10 ++++++++--
 kernel/fork.c           |  2 +-
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index e6fba627ea45..9e0d5a6fe7a8 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -117,7 +117,7 @@ extern void uprobe_start_dup_mmap(void);
 extern void uprobe_end_dup_mmap(void);
 extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
-extern void uprobe_copy_process(struct task_struct *t);
+extern void uprobe_copy_process(struct task_struct *t, unsigned long flags);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
@@ -174,7 +174,7 @@ static inline unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
 static inline void uprobe_free_utask(struct task_struct *t)
 {
 }
-static inline void uprobe_copy_process(struct task_struct *t)
+static inline void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 }
 static inline void uprobe_clear_state(struct mm_struct *mm)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 9f282e14925d..ae9e1d2ef256 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1415,7 +1415,7 @@ static void dup_xol_work(struct callback_head *work)
 /*
  * Called in context of a new clone/fork from copy_process.
  */
-void uprobe_copy_process(struct task_struct *t)
+void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 	struct uprobe_task *utask = current->utask;
 	struct mm_struct *mm = current->mm;
@@ -1424,7 +1424,10 @@ void uprobe_copy_process(struct task_struct *t)
 
 	t->utask = NULL;
 
-	if (mm == t->mm || !utask || !utask->return_instances)
+	if (!utask || !utask->return_instances)
+		return;
+
+	if (mm == t->mm && !(flags & CLONE_VFORK))
 		return;
 
 	if (dup_utask(t, utask))
@@ -1435,6 +1438,9 @@ void uprobe_copy_process(struct task_struct *t)
 	if (!area)
 		return uprobe_warn(t, "dup xol area");
 
+	if (mm == t->mm)
+		return;
+
 	/* TODO: move it into the union in uprobe_task */
 	work = kmalloc(sizeof(*work), GFP_KERNEL);
 	if (!work)
diff --git a/kernel/fork.c b/kernel/fork.c
index d3603b81246b..8531609b6a82 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1489,7 +1489,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
-	uprobe_copy_process(p);
+	uprobe_copy_process(p, clone_flags);
 
 	return p;
 
-- 
cgit 


From 7d1d65cb84e1cfacba3f54c5934194785259e0d8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 28 Oct 2013 16:43:02 +0100
Subject: net: sched: cls_bpf: add BPF-based classifier

This work contains a lightweight BPF-based traffic classifier that can
serve as a flexible alternative to ematch-based tree classification, i.e.
now that BPF filter engine can also be JITed in the kernel. Naturally, tc
actions and policies are supported as well with cls_bpf. Multiple BPF
programs/filter can be attached for a class, or they can just as well be
written within a single BPF program, that's really up to the user how he
wishes to run/optimize the code, e.g. also for inversion of verdicts etc.
The notion of a BPF program's return/exit codes is being kept as follows:

     0: No match
    -1: Select classid given in "tc filter ..." command
  else: flowid, overwrite the default one

As a minimal usage example with iproute2, we use a 3 band prio root qdisc
on a router with sfq each as leave, and assign ssh and icmp bpf-based
filters to band 1, http traffic to band 2 and the rest to band 3. For the
first two bands we load the bytecode from a file, in the 2nd we load it
inline as an example:

echo 1 > /proc/sys/net/core/bpf_jit_enable

tc qdisc del dev em1 root
tc qdisc add dev em1 root handle 1: prio bands 3 priomap 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1

tc qdisc add dev em1 parent 1:1 sfq perturb 16
tc qdisc add dev em1 parent 1:2 sfq perturb 16
tc qdisc add dev em1 parent 1:3 sfq perturb 16

tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/ssh.bpf flowid 1:1
tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/icmp.bpf flowid 1:1
tc filter add dev em1 parent 1: bpf run bytecode-file /etc/tc/http.bpf flowid 1:2
tc filter add dev em1 parent 1: bpf run bytecode "`bpfc -f tc -i misc.ops`" flowid 1:3

BPF programs can be easily created and passed to tc, either as inline
'bytecode' or 'bytecode-file'. There are a couple of front-ends that can
compile opcodes, for example:

1) People familiar with tcpdump-like filters:

   tcpdump -iem1 -ddd port 22 | tr '\n' ',' > /etc/tc/ssh.bpf

2) People that want to low-level program their filters or use BPF
   extensions that lack support by libpcap's compiler:

   bpfc -f tc -i ssh.ops > /etc/tc/ssh.bpf

   ssh.ops example code:
   ldh [12]
   jne #0x800, drop
   ldb [23]
   jneq #6, drop
   ldh [20]
   jset #0x1fff, drop
   ldxb 4 * ([14] & 0xf)
   ldh [%x + 14]
   jeq #0x16, pass
   ldh [%x + 16]
   jne #0x16, drop
   pass: ret #-1
   drop: ret #0

It was chosen to load bytecode into tc, since the reverse operation,
tc filter list dev em1, is then able to show the exact commands again.
Possible follow-up work could also include a small expression compiler
for iproute2. Tested with the help of bmon. This idea came up during
the Netfilter Workshop 2013 in Copenhagen. Also thanks to feedback from
Eric Dumazet!

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  14 ++
 net/sched/Kconfig            |  10 ++
 net/sched/Makefile           |   1 +
 net/sched/cls_bpf.c          | 385 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 410 insertions(+)
 create mode 100644 net/sched/cls_bpf.c

(limited to 'include')

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 082eafaf026b..25731dfb3fcc 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -388,6 +388,20 @@ enum {
 
 #define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
 
+/* BPF classifier */
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
 /* Extended Matches */
 
 struct tcf_ematch_tree_hdr {
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index c03a32a0418e..ad1f1d819203 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -443,6 +443,16 @@ config NET_CLS_CGROUP
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_cgroup.
 
+config NET_CLS_BPF
+	tristate "BPF-based classifier"
+	select NET_CLS
+	---help---
+	  If you say Y here, you will be able to classify packets based on
+	  programmable BPF (JIT'ed) filters as an alternative to ematches.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called cls_bpf.
+
 config NET_EMATCH
 	bool "Extended Matches"
 	select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index e5f9abe9a5db..35fa47a494ab 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_NET_CLS_RSVP6)	+= cls_rsvp6.o
 obj-$(CONFIG_NET_CLS_BASIC)	+= cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)	+= cls_flow.o
 obj-$(CONFIG_NET_CLS_CGROUP)	+= cls_cgroup.o
+obj-$(CONFIG_NET_CLS_BPF)	+= cls_bpf.o
 obj-$(CONFIG_NET_EMATCH)	+= ematch.o
 obj-$(CONFIG_NET_EMATCH_CMP)	+= em_cmp.o
 obj-$(CONFIG_NET_EMATCH_NBYTE)	+= em_nbyte.o
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
new file mode 100644
index 000000000000..1002a8226281
--- /dev/null
+++ b/net/sched/cls_bpf.c
@@ -0,0 +1,385 @@
+/*
+ * Berkeley Packet Filter based traffic classifier
+ *
+ * Might be used to classify traffic through flexible, user-defined and
+ * possibly JIT-ed BPF filters for traffic control as an alternative to
+ * ematches.
+ *
+ * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_DESCRIPTION("TC BPF based classifier");
+
+struct cls_bpf_head {
+	struct list_head plist;
+	u32 hgen;
+};
+
+struct cls_bpf_prog {
+	struct sk_filter *filter;
+	struct sock_filter *bpf_ops;
+	struct tcf_exts exts;
+	struct tcf_result res;
+	struct list_head link;
+	u32 handle;
+	u16 bpf_len;
+};
+
+static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
+	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static const struct tcf_ext_map bpf_ext_map = {
+	.action = TCA_BPF_ACT,
+	.police = TCA_BPF_POLICE,
+};
+
+static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+			    struct tcf_result *res)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+	int ret;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		int filter_res = SK_RUN_FILTER(prog->filter, skb);
+
+		if (filter_res == 0)
+			continue;
+
+		*res = prog->res;
+		if (filter_res != -1)
+			res->classid = filter_res;
+
+		ret = tcf_exts_exec(skb, &prog->exts, res);
+		if (ret < 0)
+			continue;
+
+		return ret;
+	}
+
+	return -1;
+}
+
+static int cls_bpf_init(struct tcf_proto *tp)
+{
+	struct cls_bpf_head *head;
+
+	head = kzalloc(sizeof(*head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	INIT_LIST_HEAD(&head->plist);
+	tp->root = head;
+
+	return 0;
+}
+
+static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
+{
+	tcf_unbind_filter(tp, &prog->res);
+	tcf_exts_destroy(tp, &prog->exts);
+
+	sk_unattached_filter_destroy(prog->filter);
+
+	kfree(prog->bpf_ops);
+	kfree(prog);
+}
+
+static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (prog == todel) {
+			tcf_tree_lock(tp);
+			list_del(&prog->link);
+			tcf_tree_unlock(tp);
+
+			cls_bpf_delete_prog(tp, prog);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+static void cls_bpf_destroy(struct tcf_proto *tp)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog, *tmp;
+
+	list_for_each_entry_safe(prog, tmp, &head->plist, link) {
+		list_del(&prog->link);
+		cls_bpf_delete_prog(tp, prog);
+	}
+
+	kfree(head);
+}
+
+static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+	unsigned long ret = 0UL;
+
+	if (head == NULL)
+		return 0UL;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (prog->handle == handle) {
+			ret = (unsigned long) prog;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
+{
+}
+
+static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
+				   struct cls_bpf_prog *prog,
+				   unsigned long base, struct nlattr **tb,
+				   struct nlattr *est)
+{
+	struct sock_filter *bpf_ops, *bpf_old;
+	struct tcf_exts exts;
+	struct sock_fprog tmp;
+	struct sk_filter *fp, *fp_old;
+	u16 bpf_size, bpf_len;
+	u32 classid;
+	int ret;
+
+	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
+		return -EINVAL;
+
+	ret = tcf_exts_validate(net, tp, tb, est, &exts, &bpf_ext_map);
+	if (ret < 0)
+		return ret;
+
+	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+	bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
+	if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
+		ret = -EINVAL;
+		goto errout;
+	}
+
+	bpf_size = bpf_len * sizeof(*bpf_ops);
+	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL) {
+		ret = -ENOMEM;
+		goto errout;
+	}
+
+	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
+
+	tmp.len = bpf_len;
+	tmp.filter = (struct sock_filter __user *) bpf_ops;
+
+	ret = sk_unattached_filter_create(&fp, &tmp);
+	if (ret)
+		goto errout_free;
+
+	tcf_tree_lock(tp);
+	fp_old = prog->filter;
+	bpf_old = prog->bpf_ops;
+
+	prog->bpf_len = bpf_len;
+	prog->bpf_ops = bpf_ops;
+	prog->filter = fp;
+	prog->res.classid = classid;
+	tcf_tree_unlock(tp);
+
+	tcf_bind_filter(tp, &prog->res, base);
+	tcf_exts_change(tp, &prog->exts, &exts);
+
+	if (fp_old)
+		sk_unattached_filter_destroy(fp_old);
+	if (bpf_old)
+		kfree(bpf_old);
+
+	return 0;
+
+errout_free:
+	kfree(bpf_ops);
+errout:
+	tcf_exts_destroy(tp, &exts);
+	return ret;
+}
+
+static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
+				   struct cls_bpf_head *head)
+{
+	unsigned int i = 0x80000000;
+
+	do {
+		if (++head->hgen == 0x7FFFFFFF)
+			head->hgen = 1;
+	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
+	if (i == 0)
+		pr_err("Insufficient number of handles\n");
+
+	return i;
+}
+
+static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
+			  struct tcf_proto *tp, unsigned long base,
+			  u32 handle, struct nlattr **tca,
+			  unsigned long *arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
+	struct nlattr *tb[TCA_BPF_MAX + 1];
+	int ret;
+
+	if (tca[TCA_OPTIONS] == NULL)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy);
+	if (ret < 0)
+		return ret;
+
+	if (prog != NULL) {
+		if (handle && prog->handle != handle)
+			return -EINVAL;
+		return cls_bpf_modify_existing(net, tp, prog, base, tb,
+					       tca[TCA_RATE]);
+	}
+
+	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
+	if (prog == NULL)
+		return -ENOBUFS;
+
+	if (handle == 0)
+		prog->handle = cls_bpf_grab_new_handle(tp, head);
+	else
+		prog->handle = handle;
+	if (prog->handle == 0) {
+		ret = -EINVAL;
+		goto errout;
+	}
+
+	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE]);
+	if (ret < 0)
+		goto errout;
+
+	tcf_tree_lock(tp);
+	list_add(&prog->link, &head->plist);
+	tcf_tree_unlock(tp);
+
+	*arg = (unsigned long) prog;
+
+	return 0;
+errout:
+	if (*arg == 0UL && prog)
+		kfree(prog);
+
+	return ret;
+}
+
+static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh,
+			struct sk_buff *skb, struct tcmsg *tm)
+{
+	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
+	struct nlattr *nest, *nla;
+
+	if (prog == NULL)
+		return skb->len;
+
+	tm->tcm_handle = prog->handle;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
+		goto nla_put_failure;
+	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
+		goto nla_put_failure;
+
+	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		goto nla_put_failure;
+
+        memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0)
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &prog->exts, &bpf_ext_map) < 0)
+		goto nla_put_failure;
+
+	return skb->len;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (arg->count < arg->skip)
+			goto skip;
+		if (arg->fn(tp, (unsigned long) prog, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+skip:
+		arg->count++;
+	}
+}
+
+static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
+	.kind		=	"bpf",
+	.owner		=	THIS_MODULE,
+	.classify	=	cls_bpf_classify,
+	.init		=	cls_bpf_init,
+	.destroy	=	cls_bpf_destroy,
+	.get		=	cls_bpf_get,
+	.put		=	cls_bpf_put,
+	.change		=	cls_bpf_change,
+	.delete		=	cls_bpf_delete,
+	.walk		=	cls_bpf_walk,
+	.dump		=	cls_bpf_dump,
+};
+
+static int __init cls_bpf_init_mod(void)
+{
+	return register_tcf_proto_ops(&cls_bpf_ops);
+}
+
+static void __exit cls_bpf_exit_mod(void)
+{
+	unregister_tcf_proto_ops(&cls_bpf_ops);
+}
+
+module_init(cls_bpf_init_mod);
+module_exit(cls_bpf_exit_mod);
-- 
cgit 


From 34411a69a4925dd6de8e1069956f59d758da3ce9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 30 Oct 2013 00:00:30 +0100
Subject: ACPI / processor: Do not request ACPI cpufreq module directly

Function acpi_processor_load_module() used by the ACPI processor
driver can only really work if the acpi-cpufreq module is available
when acpi_processor_start() is executed which usually is not the case
for systems loading the processor driver module from an initramfs.

Moreover, that used to be a hackish workaround for module autoloading
issues, but udev loads acpi-cpufreq just fine nowadays, so that
function isn't really necessary any more.  For this reason, drop
acpi_processor_load_module() entirely.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/processor_driver.c  |  1 -
 drivers/acpi/processor_perflib.c | 22 ----------------------
 include/acpi/processor.h         |  1 -
 3 files changed, 24 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 40fc773ab6e0..146ab7e2b81d 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -171,7 +171,6 @@ static int __acpi_processor_start(struct acpi_device *device)
 
 #ifdef CONFIG_CPU_FREQ
 	acpi_processor_ppc_has_changed(pr, 0);
-	acpi_processor_load_module(pr);
 #endif
 	acpi_processor_get_throttling_info(pr);
 
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 51d7948611da..60a7c28fc167 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -235,28 +235,6 @@ void acpi_processor_ppc_exit(void)
 	acpi_processor_ppc_status &= ~PPC_REGISTERED;
 }
 
-/*
- * Do a quick check if the systems looks like it should use ACPI
- * cpufreq. We look at a _PCT method being available, but don't
- * do a whole lot of sanity checks.
- */
-void acpi_processor_load_module(struct acpi_processor *pr)
-{
-	static int requested;
-	acpi_status status = 0;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-
-	if (!arch_has_acpi_pdc() || requested)
-		return;
-	status = acpi_evaluate_object(pr->handle, "_PCT", NULL, &buffer);
-	if (!ACPI_FAILURE(status)) {
-		printk(KERN_INFO PREFIX "Requesting acpi_cpufreq\n");
-		request_module_nowait("acpi_cpufreq");
-		requested = 1;
-	}
-	kfree(buffer.pointer);
-}
-
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
 {
 	int result = 0;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 7816e45f5d5a..6eb1d3cb5104 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -225,7 +225,6 @@ struct acpi_processor_errata {
 	} piix4;
 };
 
-extern void acpi_processor_load_module(struct acpi_processor *pr);
 extern int acpi_processor_preregister_performance(struct
 						  acpi_processor_performance
 						  __percpu *performance);
-- 
cgit 


From 3eae13671716492f3bcde270115407185e9c69fd Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 24 Oct 2013 15:42:33 -0600
Subject: device: Make dev_WARN/dev_WARN_ONCE print device as well as driver
 name

dev_WARN() and dev_WARN_ONCE() are annoying because (1) they include
only the driver name, not the device name, and (2) they print a spurious
newline in the middle.  This results in messages like this that are less
useful than they should be:

  [   40.094995] Device pcieport
  disabling already-disabled device

This patch makes them work more like dev_printk().

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index 5e44cff5bced..b025925df7f7 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1170,16 +1170,15 @@ do {									\
 #endif
 
 /*
- * dev_WARN*() acts like dev_printk(), but with the key difference
- * of using a WARN/WARN_ON to get the message out, including the
- * file/line information and a backtrace.
+ * dev_WARN*() acts like dev_printk(), but with the key difference of
+ * using WARN/WARN_ONCE to include file/line information and a backtrace.
  */
 #define dev_WARN(dev, format, arg...) \
-	WARN(1, "Device: %s\n" format, dev_driver_string(dev), ## arg);
+	WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg);
 
 #define dev_WARN_ONCE(dev, condition, format, arg...) \
-	WARN_ONCE(condition, "Device %s\n" format, \
-			dev_driver_string(dev), ## arg)
+	WARN_ONCE(condition, "%s %s: " format, \
+			dev_driver_string(dev), dev_name(dev), ## arg)
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
-- 
cgit 


From 29fc2bc75393864bbc9b90a7a13a0d0e11c6f41e Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 26 Oct 2013 20:41:53 -0700
Subject: printk: pr_debug_ratelimited: check state first to reduce "callbacks
 suppressed" messages

pr_debug_ratelimited should be coded similarly to dev_dbg_ratelimited
to reduce the "callbacks suppressed" messages.

Add #include <linux/dynamic_debug.h> to printk.h. Unfortunately, this
new #include must be after the prototype/declaration of function printk.

It may be better to split out these _ratelimited declarations into
a separate file one day.

Any use of these pr_<foo>_ratelimited functions must also have another
specific #include <ratelimited.h>.  Most users have this done indirectly
via #include <linux/kernel.h>

printk.h may not #include <linux/ratelimit.h> as it causes circular
dependencies and compilation failures.

Signed-off-by: Joe Perches <joe@perches.com>
Tested-by: Krzysztof Mazur <krzysiek@podlesie.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/printk.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index e6131a782481..694925837a16 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -233,6 +233,8 @@ extern asmlinkage void dump_stack(void) __cold;
 	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
+#include <linux/dynamic_debug.h>
+
 /* If you are writing a driver, please use dev_dbg instead */
 #if defined(CONFIG_DYNAMIC_DEBUG)
 /* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */
@@ -343,7 +345,19 @@ extern asmlinkage void dump_stack(void) __cold;
 #endif
 
 /* If you are writing a driver, please use dev_dbg instead */
-#if defined(DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG)
+/* descriptor check is first to prevent flooding with "callbacks suppressed" */
+#define pr_debug_ratelimited(fmt, ...)					\
+do {									\
+	static DEFINE_RATELIMIT_STATE(_rs,				\
+				      DEFAULT_RATELIMIT_INTERVAL,	\
+				      DEFAULT_RATELIMIT_BURST);		\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) &&	\
+	    __ratelimit(&_rs))						\
+		__dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__);	\
+} while (0)
+#elif defined(DEBUG)
 #define pr_debug_ratelimited(fmt, ...)					\
 	printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #else
-- 
cgit 


From 6587fca23001c33813d56309faf41188b5fbdb70 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 3 Oct 2013 21:26:40 +0530
Subject: cpuidle: fix indentation of cpumask

Use tabs for cpumask indentation in struct cpuidle_driver.

[rjw: Changelog]
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpuidle.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 781addc66f03..c082425757f4 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -114,7 +114,7 @@ struct cpuidle_driver {
 	int			safe_state_index;
 
 	/* the driver handles the cpus in cpumask */
-	struct cpumask       *cpumask;
+	struct cpumask		*cpumask;
 };
 
 #ifdef CONFIG_CPU_IDLE
-- 
cgit 


From f60e230f6be5672241e48434a6c2a417d9674d42 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 3 Oct 2013 21:26:55 +0530
Subject: cpuidle: remove cpuidle_unregister_governor()

cpuidle_unregister_governor() and cpuidle_replace_governor() aren't
used anymore and can be removed. They were used by cpufreq governors
earlier, but since the governors can't be compiled as modules any
more, these two functions aren't necessary.

Suggested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/cpuidle/governor.txt |  1 -
 drivers/cpuidle/governor.c         | 43 --------------------------------------
 include/linux/cpuidle.h            |  6 ------
 3 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/Documentation/cpuidle/governor.txt b/Documentation/cpuidle/governor.txt
index 12c6bd50c9f6..d9020f5e847b 100644
--- a/Documentation/cpuidle/governor.txt
+++ b/Documentation/cpuidle/governor.txt
@@ -25,5 +25,4 @@ kernel configuration and platform will be selected by cpuidle.
 
 Interfaces:
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
-extern void cpuidle_unregister_governor(struct cpuidle_governor *gov);
 struct cpuidle_governor
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index ea2f8e7aa24a..ca89412f5122 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -96,46 +96,3 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
 
 	return ret;
 }
-
-/**
- * cpuidle_replace_governor - find a replacement governor
- * @exclude_rating: the rating that will be skipped while looking for
- * new governor.
- */
-static struct cpuidle_governor *cpuidle_replace_governor(int exclude_rating)
-{
-	struct cpuidle_governor *gov;
-	struct cpuidle_governor *ret_gov = NULL;
-	unsigned int max_rating = 0;
-
-	list_for_each_entry(gov, &cpuidle_governors, governor_list) {
-		if (gov->rating == exclude_rating)
-			continue;
-		if (gov->rating > max_rating) {
-			max_rating = gov->rating;
-			ret_gov = gov;
-		}
-	}
-
-	return ret_gov;
-}
-
-/**
- * cpuidle_unregister_governor - unregisters a governor
- * @gov: the governor
- */
-void cpuidle_unregister_governor(struct cpuidle_governor *gov)
-{
-	if (!gov)
-		return;
-
-	mutex_lock(&cpuidle_lock);
-	if (gov == cpuidle_curr_governor) {
-		struct cpuidle_governor *new_gov;
-		new_gov = cpuidle_replace_governor(gov->rating);
-		cpuidle_switch_governor(new_gov);
-	}
-	list_del(&gov->governor_list);
-	mutex_unlock(&cpuidle_lock);
-}
-
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index c082425757f4..50fcbb0ac4e7 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -195,16 +195,10 @@ struct cpuidle_governor {
 };
 
 #ifdef CONFIG_CPU_IDLE
-
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
-extern void cpuidle_unregister_governor(struct cpuidle_governor *gov);
-
 #else
-
 static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
 {return 0;}
-static inline void cpuidle_unregister_governor(struct cpuidle_governor *gov) { }
-
 #endif
 
 #ifdef CONFIG_ARCH_HAS_CPU_RELAX
-- 
cgit 


From 403c1d0be5ccbd750d25c59d8358843a81e52e3b Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 25 Oct 2013 12:59:05 +0200
Subject: gpio: provide stubs for devres gpio functions

commit 6b3d8145dcfdbbb43f13544e16f44f4574f941dd
"gpiolib: make GPIO_DEVRES depend on GPIOLIB"
breaks builds when device drivers are using devm_gpio*
devres functions without enabling GPIOLIB, relying on
the devres code to be compiled anyway.

Provide stubs so that we get these if we're using the
devres functions without GPIOLIB.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio.h | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index c691df044458..0c56b9e9c209 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -77,6 +77,15 @@ static inline int irq_to_gpio(unsigned int irq)
 
 #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */
 
+/* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */
+
+struct device;
+
+int devm_gpio_request(struct device *dev, unsigned gpio, const char *label);
+int devm_gpio_request_one(struct device *dev, unsigned gpio,
+			  unsigned long flags, const char *label);
+void devm_gpio_free(struct device *dev, unsigned int gpio);
+
 #else /* ! CONFIG_GPIOLIB */
 
 #include <linux/kernel.h>
@@ -241,14 +250,25 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip)
 	WARN_ON(1);
 }
 
-#endif /* ! CONFIG_GPIOLIB */
+static inline int devm_gpio_request(struct device *dev, unsigned gpio,
+				    const char *label)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
 
-struct device;
+static inline int devm_gpio_request_one(struct device *dev, unsigned gpio,
+					unsigned long flags, const char *label)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
 
-/* bindings for managed devices that want to request gpios */
-int devm_gpio_request(struct device *dev, unsigned gpio, const char *label);
-int devm_gpio_request_one(struct device *dev, unsigned gpio,
-			  unsigned long flags, const char *label);
-void devm_gpio_free(struct device *dev, unsigned int gpio);
+static inline void devm_gpio_free(struct device *dev, unsigned int gpio)
+{
+	WARN_ON(1);
+}
+
+#endif /* ! CONFIG_GPIOLIB */
 
 #endif /* __LINUX_GPIO_H */
-- 
cgit 


From 335d7a7d63aa3a6da4d4903ef6e64de4a88f27da Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 29 Oct 2013 20:10:13 +1100
Subject: gpiolib: include gpio/consumer.h in of_gpio.h for desc_to_gpio()

Fixes this build error on sparc:

In file included from drivers/spi/spi.c:33:0:
include/linux/of_gpio.h: In function 'of_get_named_gpio_flags':
include/linux/of_gpio.h:93:3: error: implicit declaration of function 'desc_to_gpio' [-Werror=implicit-function-declaration]

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/of_gpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h
index d71f2cc141ae..f14123a5a9df 100644
--- a/include/linux/of_gpio.h
+++ b/include/linux/of_gpio.h
@@ -19,9 +19,9 @@
 #include <linux/errno.h>
 #include <linux/gpio.h>
 #include <linux/of.h>
+#include <linux/gpio/consumer.h>
 
 struct device_node;
-struct gpio_desc;
 
 /*
  * This is Linux-specific flags. By default controllers' and Linux' mapping
-- 
cgit 


From f3ed0b66482fa2a0403280174a998487e9054867 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 29 Oct 2013 01:06:23 +1100
Subject: gpiolib: provide a declaration of seq_file in gpio/driver.h

Fixes this build error:

In file included from include/asm-generic/gpio.h:13:0,
                 from include/linux/gpio.h:51,
                 from include/linux/of_gpio.h:20,
                 from arch/powerpc/sysdev/ppc4xx_gpio.c:29:
include/linux/gpio/driver.h:85:14: error: 'struct seq_file' declared inside=
 parameter list [-Werror]
include/linux/gpio/driver.h:85:14: error: its scope is only this definition=
 or declaration, which is probably not what you want [-Werror]

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/driver.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index cd9da3885d79..656a27efb2c8 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -5,6 +5,7 @@
 
 struct device;
 struct gpio_desc;
+struct seq_file;
 
 /**
  * struct gpio_chip - abstract a GPIO controller
-- 
cgit 


From c26f3c908091294e5909f5459b6682e10922c824 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:29:16 +0800
Subject: ACPICA: Fix a macro for the hardware-reduced case

This fix repairs a version of a macro that is used for the hardware
reduced case only. It adds a return statement to the macro definition
so that the translation into the Linux kernel source will not completely
delete the second line of the macro because it thinks that it is an empty
block. It actually clarifies the use of the macro anyway.

Reported-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index c7b1475422b3..ebab0d89c70b 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -106,7 +106,7 @@ extern u8 acpi_gbl_disable_ssdt_table_load;
 	static ACPI_INLINE prototype {return(AE_OK);}
 
 #define ACPI_HW_DEPENDENT_RETURN_VOID(prototype) \
-	static ACPI_INLINE prototype {}
+	static ACPI_INLINE prototype {return;}
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
-- 
cgit 


From b3c86c30efd83ebfa7010c5890e2ebf2678e49f8 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:29:27 +0800
Subject: ACPICA: Cleanup memory allocation macros and configurability.

In the common case, the ACPI_ALLOCATE and related macros now resolve
directly to their respective acpi_os* OSL interfaces. Two options:
1) The ACPI_ALLOCATE_ZEROED macro defaults to a simple local implementation
   by default, unless overridden by the USE_NATIVE_ALLOCATE_ZEROED define.
2) For ACPI execution simulation environment (AcpiExec) which is not
   shipped with the Linux kernel, the macros can optionally be resolved to
   the local interfaces that track each allocation (used to immediately
   detect memory leaks).

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acmacros.h  |  31 -----------
 drivers/acpi/acpica/acutils.h   |   6 ---
 drivers/acpi/acpica/utalloc.c   | 113 ++++++++++++----------------------------
 drivers/acpi/acpica/uttrack.c   |  29 +++++++++--
 include/acpi/acpiosxf.h         |   2 +
 include/acpi/acpixf.h           |   9 ----
 include/acpi/actypes.h          |  27 ++++++++++
 include/acpi/platform/aclinux.h |  15 ++++--
 8 files changed, 100 insertions(+), 132 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index 530a2f8c1252..2a86c65d873b 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -409,37 +409,6 @@
 #define ACPI_DEBUGGER_EXEC(a)
 #endif
 
-/*
- * Memory allocation tracking (DEBUG ONLY)
- */
-#define ACPI_MEM_PARAMETERS         _COMPONENT, _acpi_module_name, __LINE__
-
-#ifndef ACPI_DBG_TRACK_ALLOCATIONS
-
-/* Memory allocation */
-
-#ifndef ACPI_ALLOCATE
-#define ACPI_ALLOCATE(a)            acpi_ut_allocate((acpi_size) (a), ACPI_MEM_PARAMETERS)
-#endif
-#ifndef ACPI_ALLOCATE_ZEROED
-#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed((acpi_size) (a), ACPI_MEM_PARAMETERS)
-#endif
-#ifndef ACPI_FREE
-#define ACPI_FREE(a)                acpi_os_free(a)
-#endif
-#define ACPI_MEM_TRACKING(a)
-
-#else
-
-/* Memory allocation */
-
-#define ACPI_ALLOCATE(a)            acpi_ut_allocate_and_track((acpi_size) (a), ACPI_MEM_PARAMETERS)
-#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed_and_track((acpi_size) (a), ACPI_MEM_PARAMETERS)
-#define ACPI_FREE(a)                acpi_ut_free_and_track(a, ACPI_MEM_PARAMETERS)
-#define ACPI_MEM_TRACKING(a)        a
-
-#endif				/* ACPI_DBG_TRACK_ALLOCATIONS */
-
 /*
  * Macros used for ACPICA utilities only
  */
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 4f25e8f0cd5f..be8180c17d7e 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -663,12 +663,6 @@ acpi_status
 acpi_ut_initialize_buffer(struct acpi_buffer *buffer,
 			  acpi_size required_length);
 
-void *acpi_ut_allocate(acpi_size size,
-		       u32 component, const char *module, u32 line);
-
-void *acpi_ut_allocate_zeroed(acpi_size size,
-			      u32 component, const char *module, u32 line);
-
 #ifdef ACPI_DBG_TRACK_ALLOCATIONS
 void *acpi_ut_allocate_and_track(acpi_size size,
 				 u32 component, const char *module, u32 line);
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index e0ffb580f4b0..d84479610971 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -48,6 +48,39 @@
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utalloc")
 
+#if !defined (USE_NATIVE_ALLOCATE_ZEROED)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_os_allocate_zeroed
+ *
+ * PARAMETERS:  size                - Size of the allocation
+ *
+ * RETURN:      Address of the allocated memory on success, NULL on failure.
+ *
+ * DESCRIPTION: Subsystem equivalent of calloc. Allocate and zero memory.
+ *              This is the default implementation. Can be overridden via the
+ *              USE_NATIVE_ALLOCATE_ZEROED flag.
+ *
+ ******************************************************************************/
+void *acpi_os_allocate_zeroed(acpi_size size)
+{
+	void *allocation;
+
+	ACPI_FUNCTION_ENTRY();
+
+	allocation = acpi_os_allocate(size);
+	if (allocation) {
+
+		/* Clear the memory block */
+
+		ACPI_MEMSET(allocation, 0, size);
+	}
+
+	return (allocation);
+}
+
+#endif				/* !USE_NATIVE_ALLOCATE_ZEROED */
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_create_caches
@@ -59,6 +92,7 @@ ACPI_MODULE_NAME("utalloc")
  * DESCRIPTION: Create all local caches
  *
  ******************************************************************************/
+
 acpi_status acpi_ut_create_caches(void)
 {
 	acpi_status status;
@@ -302,82 +336,3 @@ acpi_ut_initialize_buffer(struct acpi_buffer * buffer,
 	ACPI_MEMSET(buffer->pointer, 0, required_length);
 	return (AE_OK);
 }
-
-#ifdef NOT_USED_BY_LINUX
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_allocate
- *
- * PARAMETERS:  size                - Size of the allocation
- *              component           - Component type of caller
- *              module              - Source file name of caller
- *              line                - Line number of caller
- *
- * RETURN:      Address of the allocated memory on success, NULL on failure.
- *
- * DESCRIPTION: Subsystem equivalent of malloc.
- *
- ******************************************************************************/
-
-void *acpi_ut_allocate(acpi_size size,
-		       u32 component, const char *module, u32 line)
-{
-	void *allocation;
-
-	ACPI_FUNCTION_TRACE_U32(ut_allocate, size);
-
-	/* Check for an inadvertent size of zero bytes */
-
-	if (!size) {
-		ACPI_WARNING((module, line,
-			      "Attempt to allocate zero bytes, allocating 1 byte"));
-		size = 1;
-	}
-
-	allocation = acpi_os_allocate(size);
-	if (!allocation) {
-
-		/* Report allocation error */
-
-		ACPI_WARNING((module, line,
-			      "Could not allocate size %u", (u32) size));
-
-		return_PTR(NULL);
-	}
-
-	return_PTR(allocation);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ut_allocate_zeroed
- *
- * PARAMETERS:  size                - Size of the allocation
- *              component           - Component type of caller
- *              module              - Source file name of caller
- *              line                - Line number of caller
- *
- * RETURN:      Address of the allocated memory on success, NULL on failure.
- *
- * DESCRIPTION: Subsystem equivalent of calloc. Allocate and zero memory.
- *
- ******************************************************************************/
-
-void *acpi_ut_allocate_zeroed(acpi_size size,
-			      u32 component, const char *module, u32 line)
-{
-	void *allocation;
-
-	ACPI_FUNCTION_ENTRY();
-
-	allocation = acpi_ut_allocate(size, component, module, line);
-	if (allocation) {
-
-		/* Clear the memory block */
-
-		ACPI_MEMSET(allocation, 0, size);
-	}
-
-	return (allocation);
-}
-#endif
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index 160f13f4aab5..77e3eb7d7c04 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -130,10 +130,23 @@ void *acpi_ut_allocate_and_track(acpi_size size,
 	struct acpi_debug_mem_block *allocation;
 	acpi_status status;
 
+	/* Check for an inadvertent size of zero bytes */
+
+	if (!size) {
+		ACPI_WARNING((module, line,
+			      "Attempt to allocate zero bytes, allocating 1 byte"));
+		size = 1;
+	}
+
 	allocation =
-	    acpi_ut_allocate(size + sizeof(struct acpi_debug_mem_header),
-			     component, module, line);
+	    acpi_os_allocate(size + sizeof(struct acpi_debug_mem_header));
 	if (!allocation) {
+
+		/* Report allocation error */
+
+		ACPI_WARNING((module, line,
+			      "Could not allocate size %u", (u32)size));
+
 		return (NULL);
 	}
 
@@ -179,9 +192,17 @@ void *acpi_ut_allocate_zeroed_and_track(acpi_size size,
 	struct acpi_debug_mem_block *allocation;
 	acpi_status status;
 
+	/* Check for an inadvertent size of zero bytes */
+
+	if (!size) {
+		ACPI_WARNING((module, line,
+			      "Attempt to allocate zero bytes, allocating 1 byte"));
+		size = 1;
+	}
+
 	allocation =
-	    acpi_ut_allocate_zeroed(size + sizeof(struct acpi_debug_mem_header),
-				    component, module, line);
+	    acpi_os_allocate_zeroed(size +
+				    sizeof(struct acpi_debug_mem_header));
 	if (!allocation) {
 
 		/* Report allocation error */
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 64b8c7639520..7f95215e7754 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -146,6 +146,8 @@ void acpi_os_release_mutex(acpi_mutex handle);
  */
 void *acpi_os_allocate(acpi_size size);
 
+void *acpi_os_allocate_zeroed(acpi_size size);
+
 void acpi_os_free(void *memory);
 
 void __iomem *acpi_os_map_memory(acpi_physical_address where,
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index ebab0d89c70b..ddde61b43041 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -158,15 +158,6 @@ acpi_status
 acpi_decode_pld_buffer(u8 *in_buffer,
 		       acpi_size length, struct acpi_pld_info **return_buffer);
 
-/*
- * ACPI Memory management
- */
-void *acpi_allocate(u32 size);
-
-void *acpi_callocate(u32 size);
-
-void acpi_free(void *address);
-
 /*
  * ACPI table load/unload interfaces
  */
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index f6abf23ad0a7..fed5af2bcb93 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -306,6 +306,33 @@ typedef u32 acpi_physical_address;
 #define ACPI_EXPORT_SYMBOL(symbol)
 #endif
 
+/*******************************************************************************
+ *
+ * Configuration
+ *
+ ******************************************************************************/
+
+#ifdef ACPI_DBG_TRACK_ALLOCATIONS
+/*
+ * Memory allocation tracking (used by acpi_exec to detect memory leaks)
+ */
+#define ACPI_MEM_PARAMETERS             _COMPONENT, _acpi_module_name, __LINE__
+#define ACPI_ALLOCATE(a)                acpi_ut_allocate_and_track ((acpi_size) (a), ACPI_MEM_PARAMETERS)
+#define ACPI_ALLOCATE_ZEROED(a)         acpi_ut_allocate_zeroed_and_track ((acpi_size) (a), ACPI_MEM_PARAMETERS)
+#define ACPI_FREE(a)                    acpi_ut_free_and_track (a, ACPI_MEM_PARAMETERS)
+#define ACPI_MEM_TRACKING(a)            a
+
+#else
+/*
+ * Normal memory allocation directly via the OS services layer
+ */
+#define ACPI_ALLOCATE(a)                acpi_os_allocate ((acpi_size) (a))
+#define ACPI_ALLOCATE_ZEROED(a)         acpi_os_allocate_zeroed ((acpi_size) (a))
+#define ACPI_FREE(a)                    acpi_os_free (a)
+#define ACPI_MEM_TRACKING(a)
+
+#endif				/* ACPI_DBG_TRACK_ALLOCATIONS */
+
 /******************************************************************************
  *
  * ACPI Specification constants (Do not change unless the specification changes)
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index fda0f3e35c03..7346a9235a4c 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -118,6 +118,14 @@ static inline acpi_thread_id acpi_os_get_thread_id(void)
 	return (acpi_thread_id)(unsigned long)current;
 }
 
+/*
+ * Memory allocation/deallocation
+ */
+
+/* Use native linux version of acpi_os_allocate_zeroed */
+
+#define USE_NATIVE_ALLOCATE_ZEROED
+
 /*
  * The irqs_disabled() check is for resume from RAM.
  * Interrupts are off during resume, just like they are for boot.
@@ -140,9 +148,10 @@ static inline void *acpi_os_acquire_object(acpi_cache_t * cache)
 		irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
 }
 
-#define ACPI_ALLOCATE(a)        acpi_os_allocate(a)
-#define ACPI_ALLOCATE_ZEROED(a) acpi_os_allocate_zeroed(a)
-#define ACPI_FREE(a)            kfree(a)
+static inline void acpi_os_free(void *a)
+{
+	kfree(a);
+}
 
 #ifndef CONFIG_PREEMPT
 /*
-- 
cgit 


From bf4994aca7c62b62b0a85a28476ef3a69ea8970f Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:29:34 +0800
Subject: ACPICA: Predefine name macros: Sort list.

Sort the method names in acnames.h.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acnames.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index ce08ef7d969c..1f36777e26fe 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -46,25 +46,25 @@
 
 /* Method names - these methods can appear anywhere in the namespace */
 
-#define METHOD_NAME__SB_        "_SB_"
-#define METHOD_NAME__HID        "_HID"
-#define METHOD_NAME__CID        "_CID"
-#define METHOD_NAME__UID        "_UID"
-#define METHOD_NAME__SUB        "_SUB"
 #define METHOD_NAME__ADR        "_ADR"
-#define METHOD_NAME__INI        "_INI"
-#define METHOD_NAME__STA        "_STA"
-#define METHOD_NAME__REG        "_REG"
-#define METHOD_NAME__SEG        "_SEG"
+#define METHOD_NAME__AEI        "_AEI"
 #define METHOD_NAME__BBN        "_BBN"
-#define METHOD_NAME__PRT        "_PRT"
+#define METHOD_NAME__CBA        "_CBA"
+#define METHOD_NAME__CID        "_CID"
 #define METHOD_NAME__CRS        "_CRS"
+#define METHOD_NAME__HID        "_HID"
+#define METHOD_NAME__INI        "_INI"
+#define METHOD_NAME__PLD        "_PLD"
 #define METHOD_NAME__PRS        "_PRS"
-#define METHOD_NAME__AEI        "_AEI"
+#define METHOD_NAME__PRT        "_PRT"
 #define METHOD_NAME__PRW        "_PRW"
+#define METHOD_NAME__REG        "_REG"
+#define METHOD_NAME__SB_        "_SB_"
+#define METHOD_NAME__SEG        "_SEG"
 #define METHOD_NAME__SRS        "_SRS"
-#define METHOD_NAME__CBA        "_CBA"
-#define METHOD_NAME__PLD        "_PLD"
+#define METHOD_NAME__STA        "_STA"
+#define METHOD_NAME__SUB        "_SUB"
+#define METHOD_NAME__UID        "_UID"
 
 /* Method names - these methods must appear at the namespace root */
 
-- 
cgit 


From e07fcfd89f9bbbc5f655b85b70e6f9b0bb626bac Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:29:45 +0800
Subject: ACPICA: Hardcode access width for the reset register.

The ACPI spec requires the reset register width to be 8, so we
now hardcode it and ignore the FADT value. This provides/maintains
compatibility with other ACPI implementations that have allowed
BIOS code with bad register width values to go unnoticed.
Matthew Garett, Bob Moore, Lv Zheng.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/hwxface.c | 10 ++++++++--
 include/acpi/actypes.h        |  1 +
 2 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index f81fb068d20e..d3682c2ae0d1 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -83,11 +83,17 @@ acpi_status acpi_reset(void)
 		 * For I/O space, write directly to the OSL. This bypasses the port
 		 * validation mechanism, which may block a valid write to the reset
 		 * register.
-		 * Spec section 4.7.3.6 requires register width to be 8.
+		 *
+		 * NOTE:
+		 * The ACPI spec requires the reset register width to be 8, so we
+		 * hardcode it here and ignore the FADT value. This maintains
+		 * compatibility with other ACPI implementations that have allowed
+		 * BIOS code with bad register width values to go unnoticed.
 		 */
 		status =
 		    acpi_os_write_port((acpi_io_address) reset_reg->address,
-				       acpi_gbl_FADT.reset_value, 8);
+				       acpi_gbl_FADT.reset_value,
+				       ACPI_RESET_REGISTER_WIDTH);
 	} else {
 		/* Write the reset value to the reset register */
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index fed5af2bcb93..63909d9c2f7a 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -349,6 +349,7 @@ typedef u32 acpi_physical_address;
 #define ACPI_PM1_REGISTER_WIDTH         16
 #define ACPI_PM2_REGISTER_WIDTH         8
 #define ACPI_PM_TIMER_WIDTH             32
+#define ACPI_RESET_REGISTER_WIDTH       8
 
 /* Names within the namespace are 4 bytes long */
 
-- 
cgit 


From db60d8da8f643586c95f8fc3e383954f8c57f1f3 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Wed, 30 Oct 2013 18:22:30 +0530
Subject: dmanengine: fix edma driver to not define DMA_COMPLETE

edma header defines DMA_COMPLETE, this causes issues as commit adfedd9a32e4 move
DMA_SUCCESS to DMA_COMPLETE. edma should properly namespace its defines and
needs a future fix

Reported-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 arch/arm/common/edma.c             | 4 ++--
 drivers/dma/edma.c                 | 4 ++--
 include/linux/platform_data/edma.h | 8 ++++----
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 8e1a0245907f..41bca32409fc 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -404,7 +404,7 @@ static irqreturn_t dma_irq_handler(int irq, void *data)
 					BIT(slot));
 			if (edma_cc[ctlr]->intr_data[channel].callback)
 				edma_cc[ctlr]->intr_data[channel].callback(
-					channel, DMA_COMPLETE,
+					channel, EDMA_DMA_COMPLETE,
 					edma_cc[ctlr]->intr_data[channel].data);
 		}
 	} while (sh_ipr);
@@ -459,7 +459,7 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data)
 								callback) {
 						edma_cc[ctlr]->intr_data[k].
 						callback(k,
-						DMA_CC_ERROR,
+						EDMA_DMA_CC_ERROR,
 						edma_cc[ctlr]->intr_data
 						[k].data);
 					}
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 29fa35807f09..cb69f3a674e0 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -407,7 +407,7 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 	edma_pause(echan->ch_num);
 
 	switch (ch_status) {
-	case DMA_COMPLETE:
+	case EDMA_DMA_COMPLETE:
 		spin_lock_irqsave(&echan->vchan.lock, flags);
 
 		edesc = echan->edesc;
@@ -426,7 +426,7 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
 		spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 		break;
-	case DMA_CC_ERROR:
+	case EDMA_DMA_CC_ERROR:
 		spin_lock_irqsave(&echan->vchan.lock, flags);
 
 		edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p);
diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h
index 179fb91bb5f2..f50821cb64be 100644
--- a/include/linux/platform_data/edma.h
+++ b/include/linux/platform_data/edma.h
@@ -67,10 +67,10 @@ struct edmacc_param {
 #define ITCCHEN		BIT(23)
 
 /*ch_status paramater of callback function possible values*/
-#define DMA_COMPLETE 1
-#define DMA_CC_ERROR 2
-#define DMA_TC1_ERROR 3
-#define DMA_TC2_ERROR 4
+#define EDMA_DMA_COMPLETE 1
+#define EDMA_DMA_CC_ERROR 2
+#define EDMA_DMA_TC1_ERROR 3
+#define EDMA_DMA_TC2_ERROR 4
 
 enum address_mode {
 	INCR = 0,
-- 
cgit 


From 9c15bb1d0a8411f9bb3395d21d5309bde7da0c1c Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sun, 22 Sep 2013 16:44:50 +0200
Subject: kvm: Add KVM_GET_EMULATED_CPUID

Add a kvm ioctl which states which system functionality kvm emulates.
The format used is that of CPUID and we return the corresponding CPUID
bits set for which we do emulate functionality.

Make sure ->padding is being passed on clean from userspace so that we
can use it for something in the future, after the ioctl gets cast in
stone.

s/kvm_dev_ioctl_get_supported_cpuid/kvm_dev_ioctl_get_cpuid/ while at
it.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 77 +++++++++++++++++++++++++++++++++++++--
 arch/x86/include/uapi/asm/kvm.h   |  6 +--
 arch/x86/kvm/cpuid.c              | 57 ++++++++++++++++++++++++++---
 arch/x86/kvm/cpuid.h              |  5 ++-
 arch/x86/kvm/x86.c                |  9 +++--
 include/uapi/linux/kvm.h          |  2 +
 6 files changed, 139 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a89a5ee0b940..488964414f04 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1122,9 +1122,9 @@ struct kvm_cpuid2 {
 	struct kvm_cpuid_entry2 entries[0];
 };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
 struct kvm_cpuid_entry2 {
 	__u32 function;
@@ -2684,6 +2684,77 @@ and usually define the validity of a groups of registers. (e.g. one bit
 };
 
 
+4.81 KVM_GET_EMULATED_CPUID
+
+Capability: KVM_CAP_EXT_EMUL_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 flags;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+The member 'flags' is used for passing flags from userspace.
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are emulated by
+kvm.Userspace can use the information returned by this ioctl to query
+which features are emulated by kvm instead of being present natively.
+
+Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
+structure with the 'nent' field indicating the number of entries in
+the variable-size array 'entries'. If the number of entries is too low
+to describe the cpu capabilities, an error (E2BIG) is returned. If the
+number is too high, the 'nent' field is adjusted and an error (ENOMEM)
+is returned. If the number is just right, the 'nent' field is adjusted
+to the number of valid entries in the 'entries' array, which is then
+filled.
+
+The entries returned are the set CPUID bits of the respective features
+which kvm emulates, as returned by the CPUID instruction, with unknown
+or unsupported feature bits cleared.
+
+Features like x2apic, for example, may not be present in the host cpu
+but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
+emulated efficiently and thus not included here.
+
+The fields in each entry are defined as follows:
+
+  function: the eax value used to obtain the entry
+  index: the ecx value used to obtain the entry (for entries that are
+         affected by ecx)
+  flags: an OR of zero or more of the following:
+        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+           if the index field is valid
+        KVM_CPUID_FLAG_STATEFUL_FUNC:
+           if cpuid for this function returns different values for successive
+           invocations; there will be several entries with the same function,
+           all with this flag set
+        KVM_CPUID_FLAG_STATE_READ_NEXT:
+           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+           the first entry to be read by a cpu
+   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+         this function/index combination
+
+
 6. Capabilities that can be enabled
 -----------------------------------
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 5d9a3033b3d7..d3a87780c70b 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 {
 	__u32 padding[3];
 };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
 /* for KVM_SET_CPUID2 */
 struct kvm_cpuid2 {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0a1e3b8b964d..78a4439bfdc5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -219,8 +219,14 @@ static bool supported_xcr0_bit(unsigned bit)
 
 #define F(x) bit(X86_FEATURE_##x)
 
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-			 u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+				   u32 func, u32 index, int *nent, int maxnent)
+{
+	return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+				 u32 index, int *nent, int maxnent)
 {
 	int r;
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -515,6 +521,15 @@ out:
 	return r;
 }
 
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+			u32 idx, int *nent, int maxnent, unsigned int type)
+{
+	if (type == KVM_GET_EMULATED_CPUID)
+		return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+	return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
 #undef F
 
 struct kvm_cpuid_param {
@@ -529,8 +544,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
 	return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
 }
 
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+				 __u32 num_entries, unsigned int ioctl_type)
+{
+	int i;
+
+	if (ioctl_type != KVM_GET_EMULATED_CPUID)
+		return false;
+
+	/*
+	 * We want to make sure that ->padding is being passed clean from
+	 * userspace in case we want to use it for something in the future.
+	 *
+	 * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+	 * have to give ourselves satisfied only with the emulated side. /me
+	 * sheds a tear.
+	 */
+	for (i = 0; i < num_entries; i++) {
+		if (entries[i].padding[0] ||
+		    entries[i].padding[1] ||
+		    entries[i].padding[2])
+			return true;
+	}
+	return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type)
 {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG, i;
@@ -547,6 +588,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		goto out;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+	if (sanity_check_entries(entries, cpuid->nent, type))
+		return -EINVAL;
+
 	r = -ENOMEM;
 	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
 	if (!cpuid_entries)
@@ -560,7 +605,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 			continue;
 
 		r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
-				&nent, cpuid->nent);
+				&nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
@@ -571,7 +616,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		limit = cpuid_entries[nent - 1].eax;
 		for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
 			r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
-				     &nent, cpuid->nent);
+				     &nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd07984888..f1e4895174b2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
 void kvm_update_cpuid(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type);
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid *cpuid,
 			     struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edf2a07df3a3..3d1e3ee8b39e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2564,6 +2564,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
@@ -2673,15 +2674,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
-	case KVM_GET_SUPPORTED_CPUID: {
+	case KVM_GET_SUPPORTED_CPUID:
+	case KVM_GET_EMULATED_CPUID: {
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
-		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-						      cpuid_arg->entries);
+
+		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+					    ioctl);
 		if (r)
 			goto out;
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e32e776f20c0..32c60b98ddf8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -541,6 +541,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 
 /*
  * Extension capability list.
@@ -668,6 +669,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQ_XICS 92
 #define KVM_CAP_ARM_EL1_32BIT 93
 #define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit 


From ec53500fae421e07c5d035918ca454a429732ef4 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 30 Oct 2013 11:02:17 -0600
Subject: kvm: Add VFIO device

So far we've succeeded at making KVM and VFIO mostly unaware of each
other, but areas are cropping up where a connection beyond eventfds
and irqfds needs to be made.  This patch introduces a KVM-VFIO device
that is meant to be a gateway for such interaction.  The user creates
the device and can add and remove VFIO groups to it via file
descriptors.  When a group is added, KVM verifies the group is valid
and gets a reference to it via the VFIO external user interface.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/devices/vfio.txt |  22 +++
 arch/x86/kvm/Kconfig                       |   1 +
 arch/x86/kvm/Makefile                      |   2 +-
 include/linux/kvm_host.h                   |   1 +
 include/uapi/linux/kvm.h                   |   4 +
 virt/kvm/Kconfig                           |   3 +
 virt/kvm/kvm_main.c                        |   5 +
 virt/kvm/vfio.c                            | 220 +++++++++++++++++++++++++++++
 8 files changed, 257 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/virtual/kvm/devices/vfio.txt
 create mode 100644 virt/kvm/vfio.c

(limited to 'include')

diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
new file mode 100644
index 000000000000..ef51740c67ca
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -0,0 +1,22 @@
+VFIO virtual device
+===================
+
+Device types supported:
+  KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM.  The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM.  As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence.  When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+  KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+  KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+  KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+
+For each, kvm_device_attr.addr points to an int32_t file descriptor
+for the VFIO group.
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e54b964..b89c5db2b832 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -38,6 +38,7 @@ config KVM
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select KVM_VFIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index bf4fb04d0112..25d22b2d6509 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -9,7 +9,7 @@ KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/ioapic.o \
 				$(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c9d4236ab442..7beddbd38ac7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1058,6 +1058,7 @@ struct kvm_device *kvm_device_from_filp(struct file *filp);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
+extern struct kvm_device_ops kvm_vfio_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 32c60b98ddf8..509cfbfe9658 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -845,6 +845,10 @@ struct kvm_device_attr {
 #define KVM_DEV_TYPE_FSL_MPIC_20	1
 #define KVM_DEV_TYPE_FSL_MPIC_42	2
 #define KVM_DEV_TYPE_XICS		3
+#define KVM_DEV_TYPE_VFIO		4
+#define  KVM_DEV_VFIO_GROUP			1
+#define   KVM_DEV_VFIO_GROUP_ADD			1
+#define   KVM_DEV_VFIO_GROUP_DEL			2
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 779262f59e25..fbe1a48bd629 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -27,3 +27,6 @@ config HAVE_KVM_MSI
 
 config HAVE_KVM_CPU_RELAX_INTERCEPT
        bool
+
+config KVM_VFIO
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9ca014da134d..82c4047aa0e3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2270,6 +2270,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	case KVM_DEV_TYPE_XICS:
 		ops = &kvm_xics_ops;
 		break;
+#endif
+#ifdef CONFIG_KVM_VFIO
+	case KVM_DEV_TYPE_VFIO:
+		ops = &kvm_vfio_ops;
+		break;
 #endif
 	default:
 		return -ENODEV;
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 000000000000..597c258245ea
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,220 @@
+/*
+ * VFIO-KVM bridge pseudo device
+ *
+ * Copyright (C) 2013 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+struct kvm_vfio_group {
+	struct list_head node;
+	struct vfio_group *vfio_group;
+};
+
+struct kvm_vfio {
+	struct list_head group_list;
+	struct mutex lock;
+};
+
+static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *vfio_group;
+	struct vfio_group *(*fn)(struct file *);
+
+	fn = symbol_get(vfio_group_get_external_user);
+	if (!fn)
+		return ERR_PTR(-EINVAL);
+
+	vfio_group = fn(filep);
+
+	symbol_put(vfio_group_get_external_user);
+
+	return vfio_group;
+}
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+	void (*fn)(struct vfio_group *);
+
+	fn = symbol_get(vfio_group_put_external_user);
+	if (!fn)
+		return;
+
+	fn(vfio_group);
+
+	symbol_put(vfio_group_put_external_user);
+}
+
+static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct vfio_group *vfio_group;
+	struct kvm_vfio_group *kvg;
+	void __user *argp = (void __user *)arg;
+	struct fd f;
+	int32_t fd;
+	int ret;
+
+	switch (attr) {
+	case KVM_DEV_VFIO_GROUP_ADD:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group == vfio_group) {
+				mutex_unlock(&kv->lock);
+				kvm_vfio_group_put_external_user(vfio_group);
+				return -EEXIST;
+			}
+		}
+
+		kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
+		if (!kvg) {
+			mutex_unlock(&kv->lock);
+			kvm_vfio_group_put_external_user(vfio_group);
+			return -ENOMEM;
+		}
+
+		list_add_tail(&kvg->node, &kv->group_list);
+		kvg->vfio_group = vfio_group;
+
+		mutex_unlock(&kv->lock);
+
+		return 0;
+
+	case KVM_DEV_VFIO_GROUP_DEL:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			list_del(&kvg->node);
+			kvm_vfio_group_put_external_user(kvg->vfio_group);
+			kfree(kvg);
+			ret = 0;
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_set_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		return kvm_vfio_set_group(dev, attr->attr, attr->addr);
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_has_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		switch (attr->attr) {
+		case KVM_DEV_VFIO_GROUP_ADD:
+		case KVM_DEV_VFIO_GROUP_DEL:
+			return 0;
+		}
+
+		break;
+	}
+
+	return -ENXIO;
+}
+
+static void kvm_vfio_destroy(struct kvm_device *dev)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct kvm_vfio_group *kvg, *tmp;
+
+	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+		kvm_vfio_group_put_external_user(kvg->vfio_group);
+		list_del(&kvg->node);
+		kfree(kvg);
+	}
+
+	kfree(kv);
+	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+}
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type)
+{
+	struct kvm_device *tmp;
+	struct kvm_vfio *kv;
+
+	/* Only one VFIO "device" per VM */
+	list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
+		if (tmp->ops == &kvm_vfio_ops)
+			return -EBUSY;
+
+	kv = kzalloc(sizeof(*kv), GFP_KERNEL);
+	if (!kv)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&kv->group_list);
+	mutex_init(&kv->lock);
+
+	dev->private = kv;
+
+	return 0;
+}
+
+struct kvm_device_ops kvm_vfio_ops = {
+	.name = "kvm-vfio",
+	.create = kvm_vfio_create,
+	.destroy = kvm_vfio_destroy,
+	.set_attr = kvm_vfio_set_attr,
+	.has_attr = kvm_vfio_has_attr,
+};
-- 
cgit 


From d96eb2c6f480769bff32054e78b964860dae4d56 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 30 Oct 2013 11:02:23 -0600
Subject: kvm/x86: Convert iommu_flags to iommu_noncoherent

Default to operating in coherent mode.  This simplifies the logic when
we switch to a model of registering and unregistering noncoherent I/O
with KVM.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/ia64/include/asm/kvm_host.h |  2 +-
 arch/x86/include/asm/kvm_host.h  |  2 +-
 arch/x86/kvm/vmx.c               |  2 +-
 arch/x86/kvm/x86.c               |  2 +-
 include/linux/kvm_host.h         |  3 ---
 virt/kvm/iommu.c                 | 16 ++++++++--------
 6 files changed, 12 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 95a3ff93777c..db95f570705f 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -476,7 +476,7 @@ struct kvm_arch {
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
-	int iommu_flags;
+	bool iommu_noncoherent;
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5cbf3166257c..91b35e4005d3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -564,7 +564,7 @@ struct kvm_arch {
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
-	int iommu_flags;
+	bool iommu_noncoherent;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6850b0f1d52b..727a5e980c43 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7446,7 +7446,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	if (is_mmio)
 		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
 	else if (vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY))
+		 vcpu->kvm->arch.iommu_noncoherent)
 		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
 		      VMX_EPT_MT_EPTE_SHIFT;
 	else
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 15f9540a2b1f..92ad83e5b132 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2719,7 +2719,7 @@ static void wbinvd_ipi(void *garbage)
 static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY);
+	       vcpu->kvm->arch.iommu_noncoherent;
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7beddbd38ac7..ed64880e4915 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -746,9 +746,6 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
-/* For vcpu->arch.iommu_flags */
-#define KVM_IOMMU_CACHE_COHERENCY	0x1
-
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot);
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index a3b14109049b..d32d156a423a 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -79,7 +79,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	flags = IOMMU_READ;
 	if (!(slot->flags & KVM_MEM_READONLY))
 		flags |= IOMMU_WRITE;
-	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
+	if (!kvm->arch.iommu_noncoherent)
 		flags |= IOMMU_CACHE;
 
 
@@ -158,7 +158,8 @@ int kvm_assign_device(struct kvm *kvm,
 {
 	struct pci_dev *pdev = NULL;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int r, last_flags;
+	int r;
+	bool noncoherent;
 
 	/* check if iommu exists and in use */
 	if (!domain)
@@ -174,15 +175,13 @@ int kvm_assign_device(struct kvm *kvm,
 		return r;
 	}
 
-	last_flags = kvm->arch.iommu_flags;
-	if (iommu_domain_has_cap(kvm->arch.iommu_domain,
-				 IOMMU_CAP_CACHE_COHERENCY))
-		kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY;
+	noncoherent = !iommu_domain_has_cap(kvm->arch.iommu_domain,
+					    IOMMU_CAP_CACHE_COHERENCY);
 
 	/* Check if need to update IOMMU page table for guest memory */
-	if ((last_flags ^ kvm->arch.iommu_flags) ==
-			KVM_IOMMU_CACHE_COHERENCY) {
+	if (noncoherent != kvm->arch.iommu_noncoherent) {
 		kvm_iommu_unmap_memslots(kvm);
+		kvm->arch.iommu_noncoherent = noncoherent;
 		r = kvm_iommu_map_memslots(kvm);
 		if (r)
 			goto out_unmap;
@@ -342,6 +341,7 @@ int kvm_iommu_unmap_guest(struct kvm *kvm)
 	mutex_lock(&kvm->slots_lock);
 	kvm_iommu_unmap_memslots(kvm);
 	kvm->arch.iommu_domain = NULL;
+	kvm->arch.iommu_noncoherent = false;
 	mutex_unlock(&kvm->slots_lock);
 
 	iommu_domain_free(domain);
-- 
cgit 


From e0f0bbc527f6e9c0261f1d16b2a0b47612b7f235 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 30 Oct 2013 11:02:30 -0600
Subject: kvm: Create non-coherent DMA registeration

We currently use some ad-hoc arch variables tied to legacy KVM device
assignment to manage emulation of instructions that depend on whether
non-coherent DMA is present.  Create an interface for this, adapting
legacy KVM device assignment and adding VFIO via the KVM-VFIO device.
For now we assume that non-coherent DMA is possible any time we have a
VFIO group.  Eventually an interface can be developed as part of the
VFIO external user interface to query the coherency of a group.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/vmx.c              |  3 +--
 arch/x86/kvm/x86.c              | 22 +++++++++++++++++++--
 include/linux/kvm_host.h        | 19 ++++++++++++++++++
 virt/kvm/iommu.c                |  6 ++++++
 virt/kvm/vfio.c                 | 44 +++++++++++++++++++++++++++++++++++++++++
 6 files changed, 92 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 91b35e4005d3..de388c55e7ec 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -565,6 +565,8 @@ struct kvm_arch {
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
 	bool iommu_noncoherent;
+#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
+	atomic_t noncoherent_dma_count;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 727a5e980c43..fabf7421ec18 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7445,8 +7445,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	 */
 	if (is_mmio)
 		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (vcpu->kvm->arch.iommu_domain &&
-		 vcpu->kvm->arch.iommu_noncoherent)
+	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
 		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
 		      VMX_EPT_MT_EPTE_SHIFT;
 	else
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 92ad83e5b132..ec35d09937da 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2718,8 +2718,7 @@ static void wbinvd_ipi(void *garbage)
 
 static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
-	return vcpu->kvm->arch.iommu_domain &&
-	       vcpu->kvm->arch.iommu_noncoherent;
+	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -6998,6 +6997,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
+	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
@@ -7437,6 +7437,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma);
+
+void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma);
+
+bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ed64880e4915..92aae88756db 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -670,6 +670,25 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
+#ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
+void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
+void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
+bool kvm_arch_has_noncoherent_dma(struct kvm *kvm);
+#else
+static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
+{
+}
+
+static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
+{
+}
+
+static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index d32d156a423a..c7d9ce122529 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -140,6 +140,9 @@ static int kvm_iommu_map_memslots(struct kvm *kvm)
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 
+	if (kvm->arch.iommu_noncoherent)
+		kvm_arch_register_noncoherent_dma(kvm);
+
 	idx = srcu_read_lock(&kvm->srcu);
 	slots = kvm_memslots(kvm);
 
@@ -327,6 +330,9 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm)
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
+	if (kvm->arch.iommu_noncoherent)
+		kvm_arch_unregister_noncoherent_dma(kvm);
+
 	return 0;
 }
 
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 597c258245ea..ca4260e35037 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -27,6 +27,7 @@ struct kvm_vfio_group {
 struct kvm_vfio {
 	struct list_head group_list;
 	struct mutex lock;
+	bool noncoherent;
 };
 
 static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
@@ -58,6 +59,43 @@ static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
 	symbol_put(vfio_group_put_external_user);
 }
 
+/*
+ * Groups can use the same or different IOMMU domains.  If the same then
+ * adding a new group may change the coherency of groups we've previously
+ * been told about.  We don't want to care about any of that so we retest
+ * each group and bail as soon as we find one that's noncoherent.  This
+ * means we only ever [un]register_noncoherent_dma once for the whole device.
+ */
+static void kvm_vfio_update_coherency(struct kvm_device *dev)
+{
+	struct kvm_vfio *kv = dev->private;
+	bool noncoherent = false;
+	struct kvm_vfio_group *kvg;
+
+	mutex_lock(&kv->lock);
+
+	list_for_each_entry(kvg, &kv->group_list, node) {
+		/*
+		 * TODO: We need an interface to check the coherency of
+		 * the IOMMU domain this group is using.  For now, assume
+		 * it's always noncoherent.
+		 */
+		noncoherent = true;
+		break;
+	}
+
+	if (noncoherent != kv->noncoherent) {
+		kv->noncoherent = noncoherent;
+
+		if (kv->noncoherent)
+			kvm_arch_register_noncoherent_dma(dev->kvm);
+		else
+			kvm_arch_unregister_noncoherent_dma(dev->kvm);
+	}
+
+	mutex_unlock(&kv->lock);
+}
+
 static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 {
 	struct kvm_vfio *kv = dev->private;
@@ -105,6 +143,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		mutex_unlock(&kv->lock);
 
+		kvm_vfio_update_coherency(dev);
+
 		return 0;
 
 	case KVM_DEV_VFIO_GROUP_DEL:
@@ -140,6 +180,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
 
 		kvm_vfio_group_put_external_user(vfio_group);
 
+		kvm_vfio_update_coherency(dev);
+
 		return ret;
 	}
 
@@ -185,6 +227,8 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 		kfree(kvg);
 	}
 
+	kvm_vfio_update_coherency(dev);
+
 	kfree(kv);
 	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
 }
-- 
cgit 


From 8217d146ab98a1790349d79c436176658e311e3c Mon Sep 17 00:00:00 2001
From: Anna Schumaker <bjschuma@netapp.com>
Date: Wed, 30 Oct 2013 13:38:13 -0400
Subject: NFSD: Add support for NFS v4.2 operation checking

The server does allow NFS over v4.2, even if it doesn't add any new
operations yet.

I also switch to using constants to represent the last operation for
each minor version since this makes the code cleaner and easier to
understand at a quick glance.

Signed-off-by: Anna Schumaker <bjschuma@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4xdr.c    | 8 +++++---
 include/linux/nfs4.h | 3 +++
 2 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 99bebea20668..83db5a742aa9 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1585,11 +1585,13 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 static inline bool
 nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op)
 {
-	if (op->opnum < FIRST_NFS4_OP || op->opnum > LAST_NFS4_OP)
+	if (op->opnum < FIRST_NFS4_OP)
 		return false;
-	else if (argp->minorversion == 0 && op->opnum > OP_RELEASE_LOCKOWNER)
+	else if (argp->minorversion == 0 && op->opnum > LAST_NFS40_OP)
 		return false;
-	else if (argp->minorversion == 1 && op->opnum > OP_RECLAIM_COMPLETE)
+	else if (argp->minorversion == 1 && op->opnum > LAST_NFS41_OP)
+		return false;
+	else if (argp->minorversion == 2 && op->opnum > LAST_NFS42_OP)
 		return false;
 	return true;
 }
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index e36dee52f224..737e40e4c554 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -118,6 +118,9 @@ Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
 #define LAST_NFS4_OP 	OP_RECLAIM_COMPLETE
+#define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
+#define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
+#define LAST_NFS42_OP	OP_RECLAIM_COMPLETE
 
 enum nfsstat4 {
 	NFS4_OK = 0,
-- 
cgit 


From 7dbf694db6ac7c759599316d50d7050efcbd512a Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 29 Oct 2013 18:56:06 +0530
Subject: cpufreq: distinguish drivers that do asynchronous notifications

There are few special cases like exynos5440 which doesn't send POSTCHANGE
notification from their ->target() routine and call some kind of bottom halves
for doing this work, work/tasklet/etc.. From which they finally send POSTCHANGE
notification.

Its better if we distinguish them from other cpufreq drivers in some way so that
core can handle them specially. So this patch introduces another flag:
CPUFREQ_ASYNC_NOTIFICATION, which will be set by such drivers.

This also changes exynos5440-cpufreq.c and powernow-k8 in order to set this
flag.

Acked-by: Amit Daniel Kachhap <amit.daniel@samsung.com>
Acked-by: Kukjin Kim <kgene.kim@samsung.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/exynos5440-cpufreq.c | 2 +-
 drivers/cpufreq/powernow-k8.c        | 1 +
 include/linux/cpufreq.h              | 7 +++++++
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 1bf9b060d522..76bef8b078cb 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -312,7 +312,7 @@ static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver exynos_driver = {
-	.flags		= CPUFREQ_STICKY,
+	.flags		= CPUFREQ_STICKY | CPUFREQ_ASYNC_NOTIFICATION,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= exynos_target,
 	.get		= exynos_getspeed,
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 62a1ce47d3df..0023c7d40a51 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1204,6 +1204,7 @@ out:
 }
 
 static struct cpufreq_driver cpufreq_amd64_driver = {
+	.flags		= CPUFREQ_ASYNC_NOTIFICATION,
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= powernowk8_target,
 	.bios_limit	= acpi_processor_get_bios_limit,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 93a8c34d6c7f..5bd6ab9b0c27 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -237,6 +237,13 @@ struct cpufreq_driver {
  */
 #define CPUFREQ_HAVE_GOVERNOR_PER_POLICY (1 << 3)
 
+/*
+ * Driver will do POSTCHANGE notifications from outside of their ->target()
+ * routine and so must set cpufreq_driver->flags with this flag, so that core
+ * can handle them specially.
+ */
+#define CPUFREQ_ASYNC_NOTIFICATION  (1 << 4)
+
 int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
-- 
cgit 


From 878e200bbb1fbde9f21582decab95b178e5a3b83 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 9 Sep 2013 11:57:57 +0200
Subject: mmc: core: Do not poll for busy with status cmd for all switch cmds

Some switch operations like poweroff notify, shall according to the
spec not be followed by any other new commands. For these cases and
when the host does'nt support MMC_CAP_WAIT_WHILE_BUSY, we must not
send status commands to poll for busy detection. Instead wait for
the stated timeout from the EXT_CSD before completing the request.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Jaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/core.c    |  2 +-
 drivers/mmc/core/mmc.c     |  6 +++---
 drivers/mmc/core/mmc_ops.c | 23 ++++++++++++++++++-----
 include/linux/mmc/core.h   |  3 ++-
 4 files changed, 24 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 006ead2fb701..0292ad448b07 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -301,7 +301,7 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 	}
 
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			EXT_CSD_BKOPS_START, 1, timeout, use_busy_signal);
+			EXT_CSD_BKOPS_START, 1, timeout, use_busy_signal, true);
 	if (err) {
 		pr_warn("%s: Error %d starting bkops\n",
 			mmc_hostname(card->host), err);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 6d02012a1d0b..8f0c51686849 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1404,9 +1404,9 @@ static int mmc_poweroff_notify(struct mmc_card *card, unsigned int notify_type)
 	if (notify_type == EXT_CSD_POWER_OFF_LONG)
 		timeout = card->ext_csd.power_off_longtime;
 
-	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			 EXT_CSD_POWER_OFF_NOTIFICATION,
-			 notify_type, timeout);
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			EXT_CSD_POWER_OFF_NOTIFICATION,
+			notify_type, timeout, true, false);
 	if (err)
 		pr_err("%s: Power Off Notification timed out, %u\n",
 		       mmc_hostname(card->host), timeout);
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 37f7d7059ab7..aae8d8b45549 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -404,11 +404,12 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc)
  *	@timeout_ms: timeout (ms) for operation performed by register write,
  *                   timeout of zero implies maximum possible timeout
  *	@use_busy_signal: use the busy signal as response type
+ *	@send_status: send status cmd to poll for busy
  *
  *	Modifies the EXT_CSD register for selected card.
  */
 int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
-	       unsigned int timeout_ms, bool use_busy_signal)
+		unsigned int timeout_ms, bool use_busy_signal, bool send_status)
 {
 	int err;
 	struct mmc_command cmd = {0};
@@ -454,14 +455,26 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 
 	timeout = jiffies + msecs_to_jiffies(MMC_OPS_TIMEOUT_MS);
 	do {
-		err = __mmc_send_status(card, &status, ignore_crc);
-		if (err)
-			return err;
+		if (send_status) {
+			err = __mmc_send_status(card, &status, ignore_crc);
+			if (err)
+				return err;
+		}
 		if (card->host->caps & MMC_CAP_WAIT_WHILE_BUSY)
 			break;
 		if (mmc_host_is_spi(card->host))
 			break;
 
+		/*
+		 * We are not allowed to issue a status command and the host
+		 * does'nt support MMC_CAP_WAIT_WHILE_BUSY, then we can only
+		 * rely on waiting for the stated timeout to be sufficient.
+		 */
+		if (!send_status) {
+			mmc_delay(timeout_ms);
+			return 0;
+		}
+
 		/* Timeout if the device never leaves the program state. */
 		if (time_after(jiffies, timeout)) {
 			pr_err("%s: Card stuck in programming state! %s\n",
@@ -488,7 +501,7 @@ EXPORT_SYMBOL_GPL(__mmc_switch);
 int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		unsigned int timeout_ms)
 {
-	return __mmc_switch(card, set, index, value, timeout_ms, true);
+	return __mmc_switch(card, set, index, value, timeout_ms, true, true);
 }
 EXPORT_SYMBOL_GPL(mmc_switch);
 
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index a00fc49c8434..87079fc38011 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -151,7 +151,8 @@ extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *);
 extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
 	struct mmc_command *, int);
 extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
-extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool);
+extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
+			bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
 extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd);
 
-- 
cgit 


From 6904115095ad60ced638eb1e36e0e4e5e7de00b0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 13 Sep 2013 11:31:33 +0200
Subject: mmc: core: Move cached value of the negotiated ocr mask to card
 struct

The negotiated ocr mask is directly related to the card. Once a card
gets removed, the mask shall be dropped. By moving the cache of the ocr
mask from the host struct to the card struct we have accomplished this.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/core.c  |  7 ++++---
 drivers/mmc/core/mmc.c   | 19 ++++++++++---------
 drivers/mmc/core/sd.c    | 22 ++++++++++++----------
 drivers/mmc/core/sdio.c  | 26 ++++++++++++++------------
 include/linux/mmc/card.h |  1 +
 include/linux/mmc/host.h |  1 -
 6 files changed, 41 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 5909ba46b8f2..529d2eff6095 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1574,9 +1574,10 @@ void mmc_power_off(struct mmc_host *host)
 
 	/*
 	 * Reset ocr mask to be the highest possible voltage supported for
-	 * this mmc host. This value will be used at next power up.
+	 * this card. This value will be used at next power up.
 	 */
-	host->ocr = 1 << (fls(host->ocr_avail) - 1);
+	if (host->card)
+		host->card->ocr = 1 << (fls(host->ocr_avail) - 1);
 
 	if (!mmc_host_is_spi(host)) {
 		host->ios.bus_mode = MMC_BUSMODE_OPENDRAIN;
@@ -2550,7 +2551,7 @@ int mmc_power_restore_host(struct mmc_host *host)
 		return -EINVAL;
 	}
 
-	mmc_power_up(host, host->ocr);
+	mmc_power_up(host, host->card->ocr);
 	ret = host->bus_ops->power_restore(host);
 
 	mmc_bus_put(host);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 75c66f975e24..eb7161c11587 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -934,6 +934,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			goto err;
 		}
 
+		card->ocr = ocr;
 		card->type = MMC_TYPE_MMC;
 		card->rca = 1;
 		memcpy(card->raw_cid, cid, sizeof(card->raw_cid));
@@ -1533,9 +1534,9 @@ static int mmc_resume(struct mmc_host *host)
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
-	mmc_power_up(host, host->ocr);
-	mmc_select_voltage(host, host->ocr);
-	err = mmc_init_card(host, host->ocr, host->card);
+	mmc_power_up(host, host->card->ocr);
+	mmc_select_voltage(host, host->card->ocr);
+	err = mmc_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
 
 	return err;
@@ -1579,7 +1580,7 @@ static int mmc_runtime_resume(struct mmc_host *host)
 
 	mmc_claim_host(host);
 
-	mmc_power_up(host, host->ocr);
+	mmc_power_up(host, host->card->ocr);
 	err = mmc_resume(host);
 	if (err)
 		pr_err("%s: error %d doing aggessive resume\n",
@@ -1595,7 +1596,7 @@ static int mmc_power_restore(struct mmc_host *host)
 
 	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
 	mmc_claim_host(host);
-	ret = mmc_init_card(host, host->ocr, host->card);
+	ret = mmc_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
 
 	return ret;
@@ -1640,7 +1641,7 @@ static void mmc_attach_bus_ops(struct mmc_host *host)
 int mmc_attach_mmc(struct mmc_host *host)
 {
 	int err;
-	u32 ocr;
+	u32 ocr, rocr;
 
 	BUG_ON(!host);
 	WARN_ON(!host->claimed);
@@ -1677,12 +1678,12 @@ int mmc_attach_mmc(struct mmc_host *host)
 		ocr &= ~0x7F;
 	}
 
-	host->ocr = mmc_select_voltage(host, ocr);
+	rocr = mmc_select_voltage(host, ocr);
 
 	/*
 	 * Can we support the voltage of the card?
 	 */
-	if (!host->ocr) {
+	if (!rocr) {
 		err = -EINVAL;
 		goto err;
 	}
@@ -1690,7 +1691,7 @@ int mmc_attach_mmc(struct mmc_host *host)
 	/*
 	 * Detect and init the card.
 	 */
-	err = mmc_init_card(host, host->ocr, NULL);
+	err = mmc_init_card(host, rocr, NULL);
 	if (err)
 		goto err;
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 5818887fffb3..398065c57edf 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -721,6 +721,7 @@ int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr)
 	int err;
 	u32 max_current;
 	int retries = 10;
+	u32 pocr = ocr;
 
 try_again:
 	if (!retries) {
@@ -774,7 +775,7 @@ try_again:
 	if (!mmc_host_is_spi(host) && rocr &&
 	   ((*rocr & 0x41000000) == 0x41000000)) {
 		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180,
-					host->ocr);
+					pocr);
 		if (err == -EAGAIN) {
 			retries--;
 			goto try_again;
@@ -936,6 +937,7 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr,
 		if (IS_ERR(card))
 			return PTR_ERR(card);
 
+		card->ocr = ocr;
 		card->type = MMC_TYPE_SD;
 		memcpy(card->raw_cid, cid, sizeof(card->raw_cid));
 	}
@@ -1100,9 +1102,9 @@ static int mmc_sd_resume(struct mmc_host *host)
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
-	mmc_power_up(host, host->ocr);
-	mmc_select_voltage(host, host->ocr);
-	err = mmc_sd_init_card(host, host->ocr, host->card);
+	mmc_power_up(host, host->card->ocr);
+	mmc_select_voltage(host, host->card->ocr);
+	err = mmc_sd_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
 
 	return err;
@@ -1145,7 +1147,7 @@ static int mmc_sd_runtime_resume(struct mmc_host *host)
 
 	mmc_claim_host(host);
 
-	mmc_power_up(host, host->ocr);
+	mmc_power_up(host, host->card->ocr);
 	err = mmc_sd_resume(host);
 	if (err)
 		pr_err("%s: error %d doing aggessive resume\n",
@@ -1161,7 +1163,7 @@ static int mmc_sd_power_restore(struct mmc_host *host)
 
 	host->card->state &= ~MMC_STATE_HIGHSPEED;
 	mmc_claim_host(host);
-	ret = mmc_sd_init_card(host, host->ocr, host->card);
+	ret = mmc_sd_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
 
 	return ret;
@@ -1206,7 +1208,7 @@ static void mmc_sd_attach_bus_ops(struct mmc_host *host)
 int mmc_attach_sd(struct mmc_host *host)
 {
 	int err;
-	u32 ocr;
+	u32 ocr, rocr;
 
 	BUG_ON(!host);
 	WARN_ON(!host->claimed);
@@ -1249,12 +1251,12 @@ int mmc_attach_sd(struct mmc_host *host)
 		ocr &= ~MMC_VDD_165_195;
 	}
 
-	host->ocr = mmc_select_voltage(host, ocr);
+	rocr = mmc_select_voltage(host, ocr);
 
 	/*
 	 * Can we support the voltage(s) of the card(s)?
 	 */
-	if (!host->ocr) {
+	if (!rocr) {
 		err = -EINVAL;
 		goto err;
 	}
@@ -1262,7 +1264,7 @@ int mmc_attach_sd(struct mmc_host *host)
 	/*
 	 * Detect and init the card.
 	 */
-	err = mmc_sd_init_card(host, host->ocr, NULL);
+	err = mmc_sd_init_card(host, rocr, NULL);
 	if (err)
 		goto err;
 
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 9587d9f8cf1c..e0a135a635f5 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -594,6 +594,7 @@ static int mmc_sdio_init_card(struct mmc_host *host, u32 ocr,
 	int err;
 	int retries = 10;
 	u32 rocr = 0;
+	u32 ocr_card = ocr;
 
 	BUG_ON(!host);
 	WARN_ON(!host->claimed);
@@ -762,6 +763,7 @@ try_again:
 
 		card = oldcard;
 	}
+	card->ocr = ocr_card;
 	mmc_fixup_device(card, NULL);
 
 	if (card->type == MMC_TYPE_SD_COMBO) {
@@ -984,8 +986,8 @@ static int mmc_sdio_resume(struct mmc_host *host)
 
 	/* Restore power if needed */
 	if (!mmc_card_keep_power(host)) {
-		mmc_power_up(host, host->ocr);
-		mmc_select_voltage(host, host->ocr);
+		mmc_power_up(host, host->card->ocr);
+		mmc_select_voltage(host, host->card->ocr);
 		/*
 		 * Tell runtime PM core we just powered up the card,
 		 * since it still believes the card is powered off.
@@ -1003,7 +1005,7 @@ static int mmc_sdio_resume(struct mmc_host *host)
 	if (mmc_card_is_removable(host) || !mmc_card_keep_power(host)) {
 		sdio_reset(host);
 		mmc_go_idle(host);
-		err = mmc_sdio_init_card(host, host->ocr, host->card,
+		err = mmc_sdio_init_card(host, host->card->ocr, host->card,
 					mmc_card_keep_power(host));
 	} else if (mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host)) {
 		/* We may have switched to 1-bit mode during suspend */
@@ -1043,7 +1045,7 @@ static int mmc_sdio_resume(struct mmc_host *host)
 static int mmc_sdio_power_restore(struct mmc_host *host)
 {
 	int ret;
-	u32 ocr;
+	u32 ocr, rocr;
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
@@ -1080,13 +1082,13 @@ static int mmc_sdio_power_restore(struct mmc_host *host)
 	if (host->ocr_avail_sdio)
 		host->ocr_avail = host->ocr_avail_sdio;
 
-	host->ocr = mmc_select_voltage(host, ocr & ~0x7F);
-	if (!host->ocr) {
+	rocr = mmc_select_voltage(host, ocr & ~0x7F);
+	if (!rocr) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	ret = mmc_sdio_init_card(host, host->ocr, host->card,
+	ret = mmc_sdio_init_card(host, rocr, host->card,
 				mmc_card_keep_power(host));
 	if (!ret && host->sdio_irqs)
 		mmc_signal_sdio_irq(host);
@@ -1107,7 +1109,7 @@ static int mmc_sdio_runtime_suspend(struct mmc_host *host)
 static int mmc_sdio_runtime_resume(struct mmc_host *host)
 {
 	/* Restore power and re-initialize. */
-	mmc_power_up(host, host->ocr);
+	mmc_power_up(host, host->card->ocr);
 	return mmc_sdio_power_restore(host);
 }
 
@@ -1130,7 +1132,7 @@ static const struct mmc_bus_ops mmc_sdio_ops = {
 int mmc_attach_sdio(struct mmc_host *host)
 {
 	int err, i, funcs;
-	u32 ocr;
+	u32 ocr, rocr;
 	struct mmc_card *card;
 
 	BUG_ON(!host);
@@ -1155,12 +1157,12 @@ int mmc_attach_sdio(struct mmc_host *host)
 		ocr &= ~0x7F;
 	}
 
-	host->ocr = mmc_select_voltage(host, ocr);
+	rocr = mmc_select_voltage(host, ocr);
 
 	/*
 	 * Can we support the voltage(s) of the card(s)?
 	 */
-	if (!host->ocr) {
+	if (!rocr) {
 		err = -EINVAL;
 		goto err;
 	}
@@ -1168,7 +1170,7 @@ int mmc_attach_sdio(struct mmc_host *host)
 	/*
 	 * Detect and init the card.
 	 */
-	err = mmc_sdio_init_card(host, host->ocr, NULL, 0);
+	err = mmc_sdio_init_card(host, rocr, NULL, 0);
 	if (err)
 		goto err;
 
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index f42cdbd8ac21..33d9a74f92e6 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -240,6 +240,7 @@ struct mmc_part {
 struct mmc_card {
 	struct mmc_host		*host;		/* the host this device belongs to */
 	struct device		dev;		/* the device */
+	u32			ocr;		/* the current OCR setting */
 	unsigned int		rca;		/* relative card address of device */
 	unsigned int		type;		/* card type */
 #define MMC_TYPE_MMC		0		/* MMC card */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 3b0c33ae13e1..1c91bbbb01c3 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -309,7 +309,6 @@ struct mmc_host {
 	spinlock_t		lock;		/* lock for claim and bus ops */
 
 	struct mmc_ios		ios;		/* current io bus settings */
-	u32			ocr;		/* the current OCR setting */
 
 	/* group bitfields together to minimize padding */
 	unsigned int		use_spi_crc:1;
-- 
cgit 


From 3c0d22e8180b98eea412b84aa0f0c42c16159679 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 26 Sep 2013 11:01:18 +0200
Subject: mmc: core: Remove deprecated mmc_suspend|resume_host APIs

The are no more users of the deprecated mmc_suspend|resume_host API,
so let's remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/core.c  | 22 ----------------------
 include/linux/mmc/host.h |  3 ---
 2 files changed, 25 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 49dfafa99cc1..57a2b403bf8e 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2641,28 +2641,6 @@ EXPORT_SYMBOL(mmc_cache_ctrl);
 
 #ifdef CONFIG_PM
 
-/**
- *	mmc_suspend_host - suspend a host
- *	@host: mmc host
- */
-int mmc_suspend_host(struct mmc_host *host)
-{
-	/* This function is deprecated */
-	return 0;
-}
-EXPORT_SYMBOL(mmc_suspend_host);
-
-/**
- *	mmc_resume_host - resume a previously suspended host
- *	@host: mmc host
- */
-int mmc_resume_host(struct mmc_host *host)
-{
-	/* This function is deprecated */
-	return 0;
-}
-EXPORT_SYMBOL(mmc_resume_host);
-
 /* Do the card removal on suspend if card is assumed removeable
  * Do that in pm notifier while userspace isn't yet frozen, so we will be able
    to sync the card.
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 1c91bbbb01c3..f18669e15d4d 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -381,9 +381,6 @@ static inline void *mmc_priv(struct mmc_host *host)
 #define mmc_classdev(x)	(&(x)->class_dev)
 #define mmc_hostname(x)	(dev_name(&(x)->class_dev))
 
-int mmc_suspend_host(struct mmc_host *);
-int mmc_resume_host(struct mmc_host *);
-
 int mmc_power_save_host(struct mmc_host *host);
 int mmc_power_restore_host(struct mmc_host *host);
 
-- 
cgit 


From 9ec775f7efd6d17084b4f361804d2030d50fca0e Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 2 Oct 2013 17:37:09 +0200
Subject: mmc: Don't force card to active state when entering suspend/shutdown

By adding a card state that records if it is suspended or resumed, we
can accept asyncronus suspend/resume requests for the mmc and sd
bus_ops.

MMC_CAP_AGGRESSIVE_PM, will at request inactivity through the runtime
bus_ops callbacks, execute a suspend of the the card. In the state were
this has been done, we can receive a suspend request for the mmc bus,
which for sd and mmc forced the card to active state by a
pm_runtime_get_sync. In other words, the card was resumed and then
immediately suspended again, completely unnecessary.

Since the suspend/resume bus_ops callbacks for sd and mmc are now
capable of handling asynchronous requests, we no longer need to force
the card to active state before executing suspend. Evidently preventing
the above sequence for MMC_CAP_AGGRESSIVE_PM.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/card/block.c |  2 --
 drivers/mmc/core/mmc.c   | 45 ++++++++++++++++++++++++++++++++++-----------
 drivers/mmc/core/sd.c    | 21 +++++++++++++++++----
 include/linux/mmc/card.h |  4 ++++
 4 files changed, 55 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 1a3163f1407e..29d5d988a51c 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -2448,7 +2448,6 @@ static int _mmc_blk_suspend(struct mmc_card *card)
 	struct mmc_blk_data *md = mmc_get_drvdata(card);
 
 	if (md) {
-		pm_runtime_get_sync(&card->dev);
 		mmc_queue_suspend(&md->queue);
 		list_for_each_entry(part_md, &md->part, part) {
 			mmc_queue_suspend(&part_md->queue);
@@ -2483,7 +2482,6 @@ static int mmc_blk_resume(struct mmc_card *card)
 		list_for_each_entry(part_md, &md->part, part) {
 			mmc_queue_resume(&part_md->queue);
 		}
-		pm_runtime_put(&card->dev);
 	}
 	return 0;
 }
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 0d060227cfc1..84d8694cf369 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1478,6 +1478,9 @@ static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
 
 	mmc_claim_host(host);
 
+	if (mmc_card_suspended(host->card))
+		goto out;
+
 	if (mmc_card_doing_bkops(host->card)) {
 		err = mmc_stop_bkops(host->card);
 		if (err)
@@ -1497,8 +1500,10 @@ static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
 		err = mmc_deselect_cards(host);
 	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
 
-	if (!err)
+	if (!err) {
 		mmc_power_off(host);
+		mmc_card_set_suspended(host->card);
+	}
 out:
 	mmc_release_host(host);
 	return err;
@@ -1512,14 +1517,6 @@ static int mmc_suspend(struct mmc_host *host)
 	return _mmc_suspend(host, true);
 }
 
-/*
- * Shutdown callback
- */
-static int mmc_shutdown(struct mmc_host *host)
-{
-	return _mmc_suspend(host, false);
-}
-
 /*
  * Resume callback from host.
  *
@@ -1528,19 +1525,45 @@ static int mmc_shutdown(struct mmc_host *host)
  */
 static int mmc_resume(struct mmc_host *host)
 {
-	int err;
+	int err = 0;
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
+
+	if (!mmc_card_suspended(host->card))
+		goto out;
+
 	mmc_power_up(host, host->card->ocr);
 	err = mmc_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
+	mmc_card_clr_suspended(host->card);
 
+out:
+	mmc_release_host(host);
 	return err;
 }
 
+/*
+ * Shutdown callback
+ */
+static int mmc_shutdown(struct mmc_host *host)
+{
+	int err = 0;
+
+	/*
+	 * In a specific case for poweroff notify, we need to resume the card
+	 * before we can shutdown it properly.
+	 */
+	if (mmc_can_poweroff_notify(host->card) &&
+		!(host->caps2 & MMC_CAP2_FULL_PWR_CYCLE))
+		err = mmc_resume(host);
+
+	if (!err)
+		err = _mmc_suspend(host, false);
+
+	return err;
+}
 
 /*
  * Callback for runtime_suspend.
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 6ef84d0ca178..685796560f8b 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1078,13 +1078,20 @@ static int mmc_sd_suspend(struct mmc_host *host)
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
+
+	if (mmc_card_suspended(host->card))
+		goto out;
+
 	if (!mmc_host_is_spi(host))
 		err = mmc_deselect_cards(host);
 	host->card->state &= ~MMC_STATE_HIGHSPEED;
-	if (!err)
+	if (!err) {
 		mmc_power_off(host);
-	mmc_release_host(host);
+		mmc_card_set_suspended(host->card);
+	}
 
+out:
+	mmc_release_host(host);
 	return err;
 }
 
@@ -1096,16 +1103,22 @@ static int mmc_sd_suspend(struct mmc_host *host)
  */
 static int mmc_sd_resume(struct mmc_host *host)
 {
-	int err;
+	int err = 0;
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
+
+	if (!mmc_card_suspended(host->card))
+		goto out;
+
 	mmc_power_up(host, host->card->ocr);
 	err = mmc_sd_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
+	mmc_card_clr_suspended(host->card);
 
+out:
+	mmc_release_host(host);
 	return err;
 }
 
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 33d9a74f92e6..176fdf824b14 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -258,6 +258,7 @@ struct mmc_card {
 #define MMC_CARD_REMOVED	(1<<7)		/* card has been removed */
 #define MMC_STATE_HIGHSPEED_200	(1<<8)		/* card is in HS200 mode */
 #define MMC_STATE_DOING_BKOPS	(1<<10)		/* card is doing BKOPS */
+#define MMC_STATE_SUSPENDED	(1<<11)		/* card is suspended */
 	unsigned int		quirks; 	/* card quirks */
 #define MMC_QUIRK_LENIENT_FN0	(1<<0)		/* allow SDIO FN0 writes outside of the VS CCCR range */
 #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1)	/* use func->cur_blksize */
@@ -424,6 +425,7 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
 #define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
 #define mmc_card_doing_bkops(c)	((c)->state & MMC_STATE_DOING_BKOPS)
+#define mmc_card_suspended(c)	((c)->state & MMC_STATE_SUSPENDED)
 
 #define mmc_card_set_present(c)	((c)->state |= MMC_STATE_PRESENT)
 #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY)
@@ -436,6 +438,8 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
 #define mmc_card_set_doing_bkops(c)	((c)->state |= MMC_STATE_DOING_BKOPS)
 #define mmc_card_clr_doing_bkops(c)	((c)->state &= ~MMC_STATE_DOING_BKOPS)
+#define mmc_card_set_suspended(c) ((c)->state |= MMC_STATE_SUSPENDED)
+#define mmc_card_clr_suspended(c) ((c)->state &= ~MMC_STATE_SUSPENDED)
 
 /*
  * Quirk add/remove for MMC products.
-- 
cgit 


From 4d22378221bd0ed69c2e99408d31c108d72aeb80 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 10 Oct 2013 17:22:23 +0200
Subject: mmc: core: Add MMC_CAP_RUNTIME_RESUME to resume at runtime_resume

In some environments it is to prefer to postpone the resume of the card
device until runtime_resume is being carried out, since it will mean a
signficant decrease of the total system resume time.

The reason of the decreased resume time is simply because of the actual
re-initalization of the card, which typically takes hundreds of
milliseconds, is performed outside the resume sequence and wont thus
affect it.

For removable card, the detect work tries to re-detect the card to make
sure it is still present, as a part of that sequence the card will also
be runtime_resumed and thus also fully resumed.

For a non-removable card, typically a mmc blk request will trigger a
runtime_resume and thus fully resume the card. This also means the
first request will likely suffer from an inital latency since the
re-initialization of the card needs to be performed.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <cjb@laptop.org>
---
 drivers/mmc/core/mmc.c   | 12 +++++++-----
 drivers/mmc/core/sd.c    | 12 +++++++-----
 include/linux/mmc/host.h |  1 +
 3 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 7f5dc26865de..f631f5a9bf79 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1577,11 +1577,13 @@ static int mmc_shutdown(struct mmc_host *host)
  */
 static int mmc_resume(struct mmc_host *host)
 {
-	int err;
+	int err = 0;
 
-	err = _mmc_resume(host);
-	pm_runtime_set_active(&host->card->dev);
-	pm_runtime_mark_last_busy(&host->card->dev);
+	if (!(host->caps & MMC_CAP_RUNTIME_RESUME)) {
+		err = _mmc_resume(host);
+		pm_runtime_set_active(&host->card->dev);
+		pm_runtime_mark_last_busy(&host->card->dev);
+	}
 	pm_runtime_enable(&host->card->dev);
 
 	return err;
@@ -1612,7 +1614,7 @@ static int mmc_runtime_resume(struct mmc_host *host)
 {
 	int err;
 
-	if (!(host->caps & MMC_CAP_AGGRESSIVE_PM))
+	if (!(host->caps & (MMC_CAP_AGGRESSIVE_PM | MMC_CAP_RUNTIME_RESUME)))
 		return 0;
 
 	err = _mmc_resume(host);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 447fa8e9f322..6f42050b7ccc 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1139,11 +1139,13 @@ out:
  */
 static int mmc_sd_resume(struct mmc_host *host)
 {
-	int err;
+	int err = 0;
 
-	err = _mmc_sd_resume(host);
-	pm_runtime_set_active(&host->card->dev);
-	pm_runtime_mark_last_busy(&host->card->dev);
+	if (!(host->caps & MMC_CAP_RUNTIME_RESUME)) {
+		err = _mmc_sd_resume(host);
+		pm_runtime_set_active(&host->card->dev);
+		pm_runtime_mark_last_busy(&host->card->dev);
+	}
 	pm_runtime_enable(&host->card->dev);
 
 	return err;
@@ -1174,7 +1176,7 @@ static int mmc_sd_runtime_resume(struct mmc_host *host)
 {
 	int err;
 
-	if (!(host->caps & MMC_CAP_AGGRESSIVE_PM))
+	if (!(host->caps & (MMC_CAP_AGGRESSIVE_PM | MMC_CAP_RUNTIME_RESUME)))
 		return 0;
 
 	err = _mmc_sd_resume(host);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index f18669e15d4d..99f5709ac343 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -254,6 +254,7 @@ struct mmc_host {
 #define MMC_CAP_UHS_SDR50	(1 << 17)	/* Host supports UHS SDR50 mode */
 #define MMC_CAP_UHS_SDR104	(1 << 18)	/* Host supports UHS SDR104 mode */
 #define MMC_CAP_UHS_DDR50	(1 << 19)	/* Host supports UHS DDR50 mode */
+#define MMC_CAP_RUNTIME_RESUME	(1 << 20)	/* Resume at runtime_resume. */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
-- 
cgit 


From a3e31b4588443f37d82195096c6b30dff1c152c2 Mon Sep 17 00:00:00 2001
From: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
Date: Wed, 18 Sep 2013 11:53:05 +0100
Subject: of: Move definition of of_find_next_cache_node into common code.

Since the definition of_find_next_cache_node is architecture independent,
the existing definition in powerpc can be moved to driver/of/base.c

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/prom.h |  3 ---
 arch/powerpc/kernel/prom.c      | 31 -------------------------------
 drivers/of/base.c               | 31 +++++++++++++++++++++++++++++++
 include/linux/of.h              |  2 ++
 4 files changed, 33 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 7d0c7f3a7171..bf09e5a065b8 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -44,9 +44,6 @@ void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
 
 extern void kdump_move_device_tree(void);
 
-/* cache lookup */
-struct device_node *of_find_next_cache_node(struct device_node *np);
-
 #ifdef CONFIG_NUMA
 extern int of_node_to_nid(struct device_node *device);
 #else
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 09be2759c314..4432fd86a6d2 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -760,37 +760,6 @@ void __init early_init_devtree(void *params)
  *
  *******/
 
-/**
- *	of_find_next_cache_node - Find a node's subsidiary cache
- *	@np:	node of type "cpu" or "cache"
- *
- *	Returns a node pointer with refcount incremented, use
- *	of_node_put() on it when done.  Caller should hold a reference
- *	to np.
- */
-struct device_node *of_find_next_cache_node(struct device_node *np)
-{
-	struct device_node *child;
-	const phandle *handle;
-
-	handle = of_get_property(np, "l2-cache", NULL);
-	if (!handle)
-		handle = of_get_property(np, "next-level-cache", NULL);
-
-	if (handle)
-		return of_find_node_by_phandle(be32_to_cpup(handle));
-
-	/* OF on pmac has nodes instead of properties named "l2-cache"
-	 * beneath CPU nodes.
-	 */
-	if (!strcmp(np->type, "cpu"))
-		for_each_child_of_node(np, child)
-			if (!strcmp(child->type, "cache"))
-				return child;
-
-	return NULL;
-}
-
 /**
  * of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
  * @np: device node of the device
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 865d3f66c86b..b2cee3db5ceb 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1884,3 +1884,34 @@ int of_device_is_stdout_path(struct device_node *dn)
 	return of_stdout == dn;
 }
 EXPORT_SYMBOL_GPL(of_device_is_stdout_path);
+
+/**
+ *	of_find_next_cache_node - Find a node's subsidiary cache
+ *	@np:	node of type "cpu" or "cache"
+ *
+ *	Returns a node pointer with refcount incremented, use
+ *	of_node_put() on it when done.  Caller should hold a reference
+ *	to np.
+ */
+struct device_node *of_find_next_cache_node(const struct device_node *np)
+{
+	struct device_node *child;
+	const phandle *handle;
+
+	handle = of_get_property(np, "l2-cache", NULL);
+	if (!handle)
+		handle = of_get_property(np, "next-level-cache", NULL);
+
+	if (handle)
+		return of_find_node_by_phandle(be32_to_cpup(handle));
+
+	/* OF on pmac has nodes instead of properties named "l2-cache"
+	 * beneath CPU nodes.
+	 */
+	if (!strcmp(np->type, "cpu"))
+		for_each_child_of_node(np, child)
+			if (!strcmp(child->type, "cache"))
+				return child;
+
+	return NULL;
+}
diff --git a/include/linux/of.h b/include/linux/of.h
index f95aee391e30..c08c07e249b3 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -226,6 +226,8 @@ static inline int of_get_child_count(const struct device_node *np)
 	return num;
 }
 
+/* cache lookup */
+extern struct device_node *of_find_next_cache_node(const struct device_node *);
 extern struct device_node *of_find_node_with_property(
 	struct device_node *from, const char *prop_name);
 #define for_each_node_with_property(dn, prop_name) \
-- 
cgit 


From 1bfa6e0d1f7f42ea52c79051f027dbcf8f123e41 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Thu, 18 Apr 2013 18:35:22 -0300
Subject: [media] V4L2: (cosmetic) remove redundant use of unlikely()

BUG*() and WARN*() macros specify their conditions as unlikely, using
BUG_ON(unlikely(condition)) is redundant, remove it.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-subdev.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index bfda0fe9aeb0..46768eed7464 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -622,8 +622,8 @@ struct v4l2_subdev_fh {
 	v4l2_subdev_get_try_##fun_name(struct v4l2_subdev_fh *fh,	\
 				       unsigned int pad)		\
 	{								\
-		BUG_ON(unlikely(pad >= vdev_to_v4l2_subdev(		\
-					fh->vfh.vdev)->entity.num_pads)); \
+		BUG_ON(pad >= vdev_to_v4l2_subdev(			\
+					fh->vfh.vdev)->entity.num_pads); \
 		return &fh->pad[pad].field_name;			\
 	}
 
-- 
cgit 


From b1cbab05d9adbd8d6d7afc822b809c5d47c46f94 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Thu, 18 Apr 2013 18:35:27 -0300
Subject: [media] V4L2: add a common V4L2 subdevice platform data type

This struct shall be used by subdevice drivers to pass per-subdevice data,
e.g. power supplies, to generic V4L2 methods, at the same time allowing
optional host-specific extensions via the host_priv pointer. To avoid
having to pass two pointers to those methods, add a pointer to this new
struct to struct v4l2_subdev.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-subdev.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 46768eed7464..27b28506f749 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -559,6 +559,17 @@ struct v4l2_subdev_internal_ops {
 /* Set this flag if this subdev generates events. */
 #define V4L2_SUBDEV_FL_HAS_EVENTS		(1U << 3)
 
+struct regulator_bulk_data;
+
+struct v4l2_subdev_platform_data {
+	/* Optional regulators uset to power on/off the subdevice */
+	struct regulator_bulk_data *regulators;
+	int num_regulators;
+
+	/* Per-subdevice data, specific for a certain video host device */
+	void *host_priv;
+};
+
 /* Each instance of a subdev driver should create this struct, either
    stand-alone or embedded in a larger struct.
  */
@@ -592,6 +603,8 @@ struct v4l2_subdev {
 	struct v4l2_async_subdev *asd;
 	/* Pointer to the managing notifier. */
 	struct v4l2_async_notifier *notifier;
+	/* common part of subdevice platform data */
+	struct v4l2_subdev_platform_data *pdata;
 };
 
 #define media_entity_to_v4l2_subdev(ent) \
-- 
cgit 


From d3f884a70938b1776ba44c7b6c82f3c3fd54ccbd Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Thu, 18 Apr 2013 18:35:28 -0300
Subject: [media] soc-camera: switch to using the new struct
 v4l2_subdev_platform_data

This prepares soc-camera to use struct v4l2_subdev_platform_data for its
subdevice-facing API, which would allow subdevice driver re-use.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/soc_camera/soc_camera.c | 24 ++++++++++++------------
 include/media/soc_camera.h                     | 17 +++++++++--------
 2 files changed, 21 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index 387a232d95a4..e201d48de70e 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -76,8 +76,8 @@ int soc_camera_power_on(struct device *dev, struct soc_camera_subdev_desc *ssdd,
 		dev_err(dev, "Cannot enable clock: %d\n", ret);
 		return ret;
 	}
-	ret = regulator_bulk_enable(ssdd->num_regulators,
-					ssdd->regulators);
+	ret = regulator_bulk_enable(ssdd->sd_pdata.num_regulators,
+				    ssdd->sd_pdata.regulators);
 	if (ret < 0) {
 		dev_err(dev, "Cannot enable regulators\n");
 		goto eregenable;
@@ -95,8 +95,8 @@ int soc_camera_power_on(struct device *dev, struct soc_camera_subdev_desc *ssdd,
 	return 0;
 
 epwron:
-	regulator_bulk_disable(ssdd->num_regulators,
-			       ssdd->regulators);
+	regulator_bulk_disable(ssdd->sd_pdata.num_regulators,
+			       ssdd->sd_pdata.regulators);
 eregenable:
 	if (clk)
 		v4l2_clk_disable(clk);
@@ -120,8 +120,8 @@ int soc_camera_power_off(struct device *dev, struct soc_camera_subdev_desc *ssdd
 		}
 	}
 
-	err = regulator_bulk_disable(ssdd->num_regulators,
-				     ssdd->regulators);
+	err = regulator_bulk_disable(ssdd->sd_pdata.num_regulators,
+				     ssdd->sd_pdata.regulators);
 	if (err < 0) {
 		dev_err(dev, "Cannot disable regulators\n");
 		ret = ret ? : err;
@@ -137,8 +137,8 @@ EXPORT_SYMBOL(soc_camera_power_off);
 int soc_camera_power_init(struct device *dev, struct soc_camera_subdev_desc *ssdd)
 {
 	/* Should not have any effect in synchronous case */
-	return devm_regulator_bulk_get(dev, ssdd->num_regulators,
-				       ssdd->regulators);
+	return devm_regulator_bulk_get(dev, ssdd->sd_pdata.num_regulators,
+				       ssdd->sd_pdata.regulators);
 }
 EXPORT_SYMBOL(soc_camera_power_init);
 
@@ -1346,8 +1346,8 @@ static int soc_camera_i2c_init(struct soc_camera_device *icd,
 	 * soc_camera_pdrv_probe(), make sure the subdevice driver doesn't try
 	 * to allocate them again.
 	 */
-	ssdd->num_regulators = 0;
-	ssdd->regulators = NULL;
+	ssdd->sd_pdata.num_regulators = 0;
+	ssdd->sd_pdata.regulators = NULL;
 	shd->board_info->platform_data = ssdd;
 
 	snprintf(clk_name, sizeof(clk_name), "%d-%04x",
@@ -2020,8 +2020,8 @@ static int soc_camera_pdrv_probe(struct platform_device *pdev)
 	 * that case regulators are attached to the I2C device and not to the
 	 * camera platform device.
 	 */
-	ret = devm_regulator_bulk_get(&pdev->dev, ssdd->num_regulators,
-				      ssdd->regulators);
+	ret = devm_regulator_bulk_get(&pdev->dev, ssdd->sd_pdata.num_regulators,
+				      ssdd->sd_pdata.regulators);
 	if (ret < 0)
 		return ret;
 
diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h
index 34d2414f2b8c..2bb418346b1f 100644
--- a/include/media/soc_camera.h
+++ b/include/media/soc_camera.h
@@ -146,10 +146,6 @@ struct soc_camera_subdev_desc {
 	/* sensor driver private platform data */
 	void *drv_priv;
 
-	/* Optional regulators that have to be managed on power on/off events */
-	struct regulator_bulk_data *regulators;
-	int num_regulators;
-
 	/* Optional callbacks to power on or off and reset the sensor */
 	int (*power)(struct device *, int);
 	int (*reset)(struct device *);
@@ -162,6 +158,9 @@ struct soc_camera_subdev_desc {
 	int (*set_bus_param)(struct soc_camera_subdev_desc *, unsigned long flags);
 	unsigned long (*query_bus_param)(struct soc_camera_subdev_desc *);
 	void (*free_bus)(struct soc_camera_subdev_desc *);
+
+	/* Optional regulators that have to be managed on power on/off events */
+	struct v4l2_subdev_platform_data sd_pdata;
 };
 
 struct soc_camera_host_desc {
@@ -202,10 +201,6 @@ struct soc_camera_link {
 
 	void *priv;
 
-	/* Optional regulators that have to be managed on power on/off events */
-	struct regulator_bulk_data *regulators;
-	int num_regulators;
-
 	/* Optional callbacks to power on or off and reset the sensor */
 	int (*power)(struct device *, int);
 	int (*reset)(struct device *);
@@ -218,6 +213,12 @@ struct soc_camera_link {
 	unsigned long (*query_bus_param)(struct soc_camera_link *);
 	void (*free_bus)(struct soc_camera_link *);
 
+	/* Optional regulators that have to be managed on power on/off events */
+	struct regulator_bulk_data *regulators;
+	int num_regulators;
+
+	void *host_priv;
+
 	/*
 	 * Host part - keep at bottom and compatible to
 	 * struct soc_camera_host_desc
-- 
cgit 


From cf326dfebe612bf56c83d8fca7a7c1d1584c061f Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Wed, 28 Aug 2013 10:28:26 -0300
Subject: [media] V4L2: add v4l2-clock helpers to register and unregister a
 fixed-rate clock

Many bridges and video host controllers supply fixed rate always on clocks
to their I2C devices. This patch adds two simple helpers to register and
unregister such a clock.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/v4l2-core/v4l2-clk.c | 39 ++++++++++++++++++++++++++++++++++++++
 include/media/v4l2-clk.h           | 14 ++++++++++++++
 2 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-clk.c b/drivers/media/v4l2-core/v4l2-clk.c
index b67de8642b5a..e18cc0469cf8 100644
--- a/drivers/media/v4l2-core/v4l2-clk.c
+++ b/drivers/media/v4l2-core/v4l2-clk.c
@@ -240,3 +240,42 @@ void v4l2_clk_unregister(struct v4l2_clk *clk)
 	kfree(clk);
 }
 EXPORT_SYMBOL(v4l2_clk_unregister);
+
+struct v4l2_clk_fixed {
+	unsigned long rate;
+	struct v4l2_clk_ops ops;
+};
+
+static unsigned long fixed_get_rate(struct v4l2_clk *clk)
+{
+	struct v4l2_clk_fixed *priv = clk->priv;
+	return priv->rate;
+}
+
+struct v4l2_clk *__v4l2_clk_register_fixed(const char *dev_id,
+		const char *id, unsigned long rate, struct module *owner)
+{
+	struct v4l2_clk *clk;
+	struct v4l2_clk_fixed *priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	priv->rate = rate;
+	priv->ops.get_rate = fixed_get_rate;
+	priv->ops.owner = owner;
+
+	clk = v4l2_clk_register(&priv->ops, dev_id, id, priv);
+	if (IS_ERR(clk))
+		kfree(priv);
+
+	return clk;
+}
+EXPORT_SYMBOL(__v4l2_clk_register_fixed);
+
+void v4l2_clk_unregister_fixed(struct v4l2_clk *clk)
+{
+	kfree(clk->priv);
+	v4l2_clk_unregister(clk);
+}
+EXPORT_SYMBOL(v4l2_clk_unregister_fixed);
diff --git a/include/media/v4l2-clk.h b/include/media/v4l2-clk.h
index 0503a90b48bb..a354a9d6456e 100644
--- a/include/media/v4l2-clk.h
+++ b/include/media/v4l2-clk.h
@@ -15,6 +15,7 @@
 #define MEDIA_V4L2_CLK_H
 
 #include <linux/atomic.h>
+#include <linux/export.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 
@@ -51,4 +52,17 @@ void v4l2_clk_disable(struct v4l2_clk *clk);
 unsigned long v4l2_clk_get_rate(struct v4l2_clk *clk);
 int v4l2_clk_set_rate(struct v4l2_clk *clk, unsigned long rate);
 
+struct module;
+
+struct v4l2_clk *__v4l2_clk_register_fixed(const char *dev_id,
+		const char *id, unsigned long rate, struct module *owner);
+void v4l2_clk_unregister_fixed(struct v4l2_clk *clk);
+
+static inline struct v4l2_clk *v4l2_clk_register_fixed(const char *dev_id,
+							const char *id,
+							unsigned long rate)
+{
+	return __v4l2_clk_register_fixed(dev_id, id, rate, THIS_MODULE);
+}
+
 #endif
-- 
cgit 


From 774cc4c289152bfb77806ccae722a9ae2d29dd02 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Wed, 28 Aug 2013 10:28:27 -0300
Subject: [media] V4L2: add a v4l2-clk helper macro to produce an I2C device ID

To obtain a clock reference consumers supply their device object to the
V4L2 clock framework. The latter then uses the consumer device name to
find a matching clock. For that to work V4L2 clock providers have to
provide the same device name, when registering clocks. This patch adds
a helper macro to generate a suitable device name for I2C devices.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-clk.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-clk.h b/include/media/v4l2-clk.h
index a354a9d6456e..0b36cc138304 100644
--- a/include/media/v4l2-clk.h
+++ b/include/media/v4l2-clk.h
@@ -65,4 +65,7 @@ static inline struct v4l2_clk *v4l2_clk_register_fixed(const char *dev_id,
 	return __v4l2_clk_register_fixed(dev_id, id, rate, THIS_MODULE);
 }
 
+#define v4l2_clk_name_i2c(name, size, adap, client) snprintf(name, size, \
+			  "%d-%04x", adap, client)
+
 #endif
-- 
cgit 


From 40f075330adfa497cc2894f9c6a32bb99c5cd5b8 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Mon, 21 Oct 2013 06:28:02 -0300
Subject: [media] V4L2: soc-camera: work around unbalanced calls to .s_power()

Some non soc-camera drivers, e.g. em28xx, use subdevice drivers, originally
written for soc-camera, which use soc_camera_power_on() and
soc_camera_power_off() helpers to implement their .s_power() methods. Those
helpers in turn can enable and disable a clock, if it is supplied to them
as a parameter. This works well when camera host drivers balance their
calls to subdevices' .s_power() methods. However, some such drivers fail to
do that, which leads to unbalanced calls to v4l2_clk_enable() /
v4l2_clk_disable(), which then in turn produce kernel warnings. Such
behaviour is wrong and should be fixed, however, sometimes it is difficult,
because some of those drivers are rather old and use lots of subdevices,
which all should be tested after such a fix. To support such drivers this
patch adds a work-around, allowing host drivers or platforms to set a flag,
in which case soc-camera helpers will only enable the clock, if it is
disabled, and disable it only once on the first call to .s_power(0).

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/platform/soc_camera/soc_camera.c | 22 ++++++++++++++++------
 include/media/soc_camera.h                     | 14 ++++++++++++++
 2 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index e201d48de70e..4b8c024fc487 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -71,11 +71,21 @@ static int video_dev_create(struct soc_camera_device *icd);
 int soc_camera_power_on(struct device *dev, struct soc_camera_subdev_desc *ssdd,
 			struct v4l2_clk *clk)
 {
-	int ret = clk ? v4l2_clk_enable(clk) : 0;
-	if (ret < 0) {
-		dev_err(dev, "Cannot enable clock: %d\n", ret);
-		return ret;
+	int ret;
+	bool clock_toggle;
+
+	if (clk && (!ssdd->unbalanced_power ||
+		    !test_and_set_bit(0, &ssdd->clock_state))) {
+		ret = v4l2_clk_enable(clk);
+		if (ret < 0) {
+			dev_err(dev, "Cannot enable clock: %d\n", ret);
+			return ret;
+		}
+		clock_toggle = true;
+	} else {
+		clock_toggle = false;
 	}
+
 	ret = regulator_bulk_enable(ssdd->sd_pdata.num_regulators,
 				    ssdd->sd_pdata.regulators);
 	if (ret < 0) {
@@ -98,7 +108,7 @@ epwron:
 	regulator_bulk_disable(ssdd->sd_pdata.num_regulators,
 			       ssdd->sd_pdata.regulators);
 eregenable:
-	if (clk)
+	if (clock_toggle)
 		v4l2_clk_disable(clk);
 
 	return ret;
@@ -127,7 +137,7 @@ int soc_camera_power_off(struct device *dev, struct soc_camera_subdev_desc *ssdd
 		ret = ret ? : err;
 	}
 
-	if (clk)
+	if (clk && (!ssdd->unbalanced_power || test_and_clear_bit(0, &ssdd->clock_state)))
 		v4l2_clk_disable(clk);
 
 	return ret;
diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h
index 2bb418346b1f..865246b00127 100644
--- a/include/media/soc_camera.h
+++ b/include/media/soc_camera.h
@@ -146,6 +146,15 @@ struct soc_camera_subdev_desc {
 	/* sensor driver private platform data */
 	void *drv_priv;
 
+	/*
+	 * Set unbalanced_power to true to deal with legacy drivers, failing to
+	 * balance their calls to subdevice's .s_power() method. clock_state is
+	 * then used internally by helper functions, it shouldn't be touched by
+	 * drivers or the platform code.
+	 */
+	bool unbalanced_power;
+	unsigned long clock_state;
+
 	/* Optional callbacks to power on or off and reset the sensor */
 	int (*power)(struct device *, int);
 	int (*reset)(struct device *);
@@ -201,6 +210,11 @@ struct soc_camera_link {
 
 	void *priv;
 
+	/* Set by platforms to handle misbehaving drivers */
+	bool unbalanced_power;
+	/* Used by soc-camera helper functions */
+	unsigned long clock_state;
+
 	/* Optional callbacks to power on or off and reset the sensor */
 	int (*power)(struct device *, int);
 	int (*reset)(struct device *);
-- 
cgit 


From e1e906448d2fc6f5a69e1967e00868f0cbfbb566 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 24 Sep 2013 13:59:01 +0200
Subject: gpu: host1x: Make host1x header file public

In preparation to support host1x clients other than DRM, move this
header into a public location.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 MAINTAINERS                        |  1 +
 drivers/gpu/host1x/drm/drm.h       |  6 +++---
 drivers/gpu/host1x/drm/gr2d.c      |  1 -
 drivers/gpu/host1x/host1x.h        | 30 ------------------------------
 drivers/gpu/host1x/hw/channel_hw.c |  3 ++-
 include/linux/host1x.h             | 28 ++++++++++++++++++++++++++++
 6 files changed, 34 insertions(+), 35 deletions(-)
 delete mode 100644 drivers/gpu/host1x/host1x.h
 create mode 100644 include/linux/host1x.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 284969fa2896..89f347ae077f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2817,6 +2817,7 @@ L:	linux-tegra@vger.kernel.org
 T:	git git://anongit.freedesktop.org/tegra/linux.git
 S:	Maintained
 F:	drivers/gpu/host1x/
+F:	include/linux/host1x.h
 F:	include/uapi/drm/tegra_drm.h
 F:	Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
 
diff --git a/drivers/gpu/host1x/drm/drm.h b/drivers/gpu/host1x/drm/drm.h
index dd6b98b18640..78754f6a9153 100644
--- a/drivers/gpu/host1x/drm/drm.h
+++ b/drivers/gpu/host1x/drm/drm.h
@@ -10,14 +10,14 @@
 #ifndef HOST1X_DRM_H
 #define HOST1X_DRM_H 1
 
+#include <uapi/drm/tegra_drm.h>
+#include <linux/host1x.h>
+
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fixed.h>
-#include <uapi/drm/tegra_drm.h>
-
-#include "host1x.h"
 
 struct tegra_fb {
 	struct drm_framebuffer base;
diff --git a/drivers/gpu/host1x/drm/gr2d.c b/drivers/gpu/host1x/drm/gr2d.c
index f045f7c0a91c..2691e333e0e2 100644
--- a/drivers/gpu/host1x/drm/gr2d.c
+++ b/drivers/gpu/host1x/drm/gr2d.c
@@ -20,7 +20,6 @@
 #include "drm.h"
 #include "gem.h"
 #include "job.h"
-#include "host1x.h"
 #include "host1x_bo.h"
 #include "host1x_client.h"
 #include "syncpt.h"
diff --git a/drivers/gpu/host1x/host1x.h b/drivers/gpu/host1x/host1x.h
deleted file mode 100644
index a2bc1e65e972..000000000000
--- a/drivers/gpu/host1x/host1x.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Tegra host1x driver
- *
- * Copyright (c) 2009-2013, NVIDIA Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- */
-
-#ifndef __LINUX_HOST1X_H
-#define __LINUX_HOST1X_H
-
-enum host1x_class {
-	HOST1X_CLASS_HOST1X	= 0x1,
-	HOST1X_CLASS_GR2D	= 0x51,
-	HOST1X_CLASS_GR2D_SB    = 0x52
-};
-
-#endif
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index ee199623e365..c950bc655ade 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -16,10 +16,11 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/host1x.h>
 #include <linux/slab.h>
+
 #include <trace/events/host1x.h>
 
-#include "host1x.h"
 #include "host1x_bo.h"
 #include "channel.h"
 #include "dev.h"
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
new file mode 100644
index 000000000000..fe09939800bc
--- /dev/null
+++ b/include/linux/host1x.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (c) 2009-2013, NVIDIA Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef __LINUX_HOST1X_H
+#define __LINUX_HOST1X_H
+
+enum host1x_class {
+	HOST1X_CLASS_HOST1X = 0x1,
+	HOST1X_CLASS_GR2D = 0x51,
+	HOST1X_CLASS_GR2D_SB = 0x52,
+};
+
+#endif
-- 
cgit 


From 53fa7f7204c97dc0c86b99ff8365ad6a7b2ebd78 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 24 Sep 2013 15:35:40 +0200
Subject: drm/tegra: Introduce tegra_drm_client structure

This structure derives from host1x_client. DRM-specific fields are moved
from host1x_client to this structure, so that host1x_client can remain
agnostic of DRM.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/drm/dc.c   | 35 ++++++++++++++++++-----------------
 drivers/gpu/host1x/drm/drm.c  | 30 +++++++++++++++++++-----------
 drivers/gpu/host1x/drm/drm.h  | 37 +++++++++++++++++--------------------
 drivers/gpu/host1x/drm/gr2d.c | 42 +++++++++++++++++++++++-------------------
 drivers/gpu/host1x/drm/hdmi.c | 33 +++++++++++++++++----------------
 include/linux/host1x.h        | 20 ++++++++++++++++++++
 6 files changed, 114 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/host1x/drm/dc.c b/drivers/gpu/host1x/drm/dc.c
index e11aec779a15..5106df08f046 100644
--- a/drivers/gpu/host1x/drm/dc.c
+++ b/drivers/gpu/host1x/drm/dc.c
@@ -1038,30 +1038,30 @@ static int tegra_dc_debugfs_exit(struct tegra_dc *dc)
 	return 0;
 }
 
-static int tegra_dc_drm_init(struct host1x_client *client,
-			     struct drm_device *drm)
+static int tegra_dc_init(struct host1x_client *client)
 {
-	struct tegra_dc *dc = host1x_client_to_dc(client);
+	struct tegra_drm_client *drm = to_tegra_drm_client(client);
+	struct tegra_dc *dc = tegra_drm_client_to_dc(drm);
 	int err;
 
-	dc->pipe = drm->mode_config.num_crtc;
+	dc->pipe = drm->drm->mode_config.num_crtc;
 
-	drm_crtc_init(drm, &dc->base, &tegra_crtc_funcs);
+	drm_crtc_init(drm->drm, &dc->base, &tegra_crtc_funcs);
 	drm_mode_crtc_set_gamma_size(&dc->base, 256);
 	drm_crtc_helper_add(&dc->base, &tegra_crtc_helper_funcs);
 
-	err = tegra_dc_rgb_init(drm, dc);
+	err = tegra_dc_rgb_init(drm->drm, dc);
 	if (err < 0 && err != -ENODEV) {
 		dev_err(dc->dev, "failed to initialize RGB output: %d\n", err);
 		return err;
 	}
 
-	err = tegra_dc_add_planes(drm, dc);
+	err = tegra_dc_add_planes(drm->drm, dc);
 	if (err < 0)
 		return err;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_dc_debugfs_init(dc, drm->primary);
+		err = tegra_dc_debugfs_init(dc, drm->drm->primary);
 		if (err < 0)
 			dev_err(dc->dev, "debugfs setup failed: %d\n", err);
 	}
@@ -1077,9 +1077,10 @@ static int tegra_dc_drm_init(struct host1x_client *client,
 	return 0;
 }
 
-static int tegra_dc_drm_exit(struct host1x_client *client)
+static int tegra_dc_exit(struct host1x_client *client)
 {
-	struct tegra_dc *dc = host1x_client_to_dc(client);
+	struct tegra_drm_client *drm = to_tegra_drm_client(client);
+	struct tegra_dc *dc = tegra_drm_client_to_dc(drm);
 	int err;
 
 	devm_free_irq(dc->dev, dc->irq, dc);
@@ -1100,8 +1101,8 @@ static int tegra_dc_drm_exit(struct host1x_client *client)
 }
 
 static const struct host1x_client_ops dc_client_ops = {
-	.drm_init = tegra_dc_drm_init,
-	.drm_exit = tegra_dc_drm_exit,
+	.init = tegra_dc_init,
+	.exit = tegra_dc_exit,
 };
 
 static int tegra_dc_probe(struct platform_device *pdev)
@@ -1140,9 +1141,9 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	INIT_LIST_HEAD(&dc->client.list);
-	dc->client.ops = &dc_client_ops;
-	dc->client.dev = &pdev->dev;
+	INIT_LIST_HEAD(&dc->client.base.list);
+	dc->client.base.ops = &dc_client_ops;
+	dc->client.base.dev = &pdev->dev;
 
 	err = tegra_dc_rgb_probe(dc);
 	if (err < 0 && err != -ENODEV) {
@@ -1150,7 +1151,7 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = host1x_register_client(tegra, &dc->client);
+	err = host1x_register_client(tegra, &dc->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
@@ -1168,7 +1169,7 @@ static int tegra_dc_remove(struct platform_device *pdev)
 	struct tegra_dc *dc = platform_get_drvdata(pdev);
 	int err;
 
-	err = host1x_unregister_client(tegra, &dc->client);
+	err = host1x_unregister_client(tegra, &dc->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
diff --git a/drivers/gpu/host1x/drm/drm.c b/drivers/gpu/host1x/drm/drm.c
index 4e503613536b..33d966145293 100644
--- a/drivers/gpu/host1x/drm/drm.c
+++ b/drivers/gpu/host1x/drm/drm.c
@@ -131,12 +131,18 @@ int tegra_drm_alloc(struct platform_device *pdev)
 int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm)
 {
 	struct host1x_client *client;
+	int err;
 
 	mutex_lock(&tegra->clients_lock);
 
 	list_for_each_entry(client, &tegra->clients, list) {
-		if (client->ops && client->ops->drm_init) {
-			int err = client->ops->drm_init(client, drm);
+		struct tegra_drm_client *tdc = to_tegra_drm_client(client);
+
+		/* associate client with DRM device */
+		tdc->drm = drm;
+
+		if (client->ops && client->ops->init) {
+			err = client->ops->init(client);
 			if (err < 0) {
 				dev_err(tegra->dev,
 					"DRM setup failed for %s: %d\n",
@@ -154,8 +160,9 @@ int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm)
 
 int tegra_drm_exit(struct tegra_drm *tegra)
 {
-	struct platform_device *pdev = to_platform_device(tegra->dev);
 	struct host1x_client *client;
+	struct platform_device *pdev;
+	int err;
 
 	if (!tegra->drm)
 		return 0;
@@ -163,8 +170,8 @@ int tegra_drm_exit(struct tegra_drm *tegra)
 	mutex_lock(&tegra->clients_lock);
 
 	list_for_each_entry_reverse(client, &tegra->clients, list) {
-		if (client->ops && client->ops->drm_exit) {
-			int err = client->ops->drm_exit(client);
+		if (client->ops && client->ops->exit) {
+			err = client->ops->exit(client);
 			if (err < 0) {
 				dev_err(tegra->dev,
 					"DRM cleanup failed for %s: %d\n",
@@ -177,6 +184,7 @@ int tegra_drm_exit(struct tegra_drm *tegra)
 
 	mutex_unlock(&tegra->clients_lock);
 
+	pdev = to_platform_device(tegra->dev);
 	drm_platform_exit(&tegra_drm_driver, pdev);
 	tegra->drm = NULL;
 
@@ -409,22 +417,22 @@ static int tegra_open_channel(struct drm_device *drm, void *data,
 	struct tegra_drm *tegra = drm->dev_private;
 	struct drm_tegra_open_channel *args = data;
 	struct tegra_drm_context *context;
-	struct host1x_client *client;
+	struct tegra_drm_client *client;
 	int err = -ENODEV;
 
 	context = kzalloc(sizeof(*context), GFP_KERNEL);
 	if (!context)
 		return -ENOMEM;
 
-	list_for_each_entry(client, &tegra->clients, list)
-		if (client->class == args->client) {
+	list_for_each_entry(client, &tegra->clients, base.list)
+		if (client->base.class == args->client) {
 			err = client->ops->open_channel(client, context);
 			if (err)
 				break;
 
-			context->client = client;
 			list_add(&context->list, &fpriv->contexts);
 			args->context = (uintptr_t)context;
+			context->client = client;
 			return 0;
 		}
 
@@ -463,10 +471,10 @@ static int tegra_get_syncpt(struct drm_device *drm, void *data,
 	if (!tegra_drm_file_owns_context(fpriv, context))
 		return -ENODEV;
 
-	if (args->index >= context->client->num_syncpts)
+	if (args->index >= context->client->base.num_syncpts)
 		return -EINVAL;
 
-	syncpt = context->client->syncpts[args->index];
+	syncpt = context->client->base.syncpts[args->index];
 	args->id = host1x_syncpt_id(syncpt);
 
 	return 0;
diff --git a/drivers/gpu/host1x/drm/drm.h b/drivers/gpu/host1x/drm/drm.h
index 78754f6a9153..8c26c6b1f5e1 100644
--- a/drivers/gpu/host1x/drm/drm.h
+++ b/drivers/gpu/host1x/drm/drm.h
@@ -44,18 +44,16 @@ struct tegra_drm {
 	struct tegra_fbdev *fbdev;
 };
 
-struct host1x_client;
+struct tegra_drm_client;
 
 struct tegra_drm_context {
-	struct host1x_client *client;
+	struct tegra_drm_client *client;
 	struct host1x_channel *channel;
 	struct list_head list;
 };
 
-struct host1x_client_ops {
-	int (*drm_init)(struct host1x_client *client, struct drm_device *drm);
-	int (*drm_exit)(struct host1x_client *client);
-	int (*open_channel)(struct host1x_client *client,
+struct tegra_drm_client_ops {
+	int (*open_channel)(struct tegra_drm_client *client,
 			    struct tegra_drm_context *context);
 	void (*close_channel)(struct tegra_drm_context *context);
 	int (*submit)(struct tegra_drm_context *context,
@@ -63,21 +61,19 @@ struct host1x_client_ops {
 		      struct drm_file *file);
 };
 
-struct host1x_client {
-	struct tegra_drm *tegra;
-	struct device *dev;
-
-	const struct host1x_client_ops *ops;
-
-	enum host1x_class class;
-	struct host1x_channel *channel;
-
-	struct host1x_syncpt **syncpts;
-	unsigned int num_syncpts;
+struct tegra_drm_client {
+	struct host1x_client base;
+	struct drm_device *drm;
 
-	struct list_head list;
+	const struct tegra_drm_client_ops *ops;
 };
 
+static inline struct tegra_drm_client *
+to_tegra_drm_client(struct host1x_client *client)
+{
+	return container_of(client, struct tegra_drm_client, base);
+}
+
 extern int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm);
 extern int tegra_drm_exit(struct tegra_drm *tegra);
 
@@ -89,7 +85,7 @@ extern int host1x_unregister_client(struct tegra_drm *tegra,
 struct tegra_output;
 
 struct tegra_dc {
-	struct host1x_client client;
+	struct tegra_drm_client client;
 	struct device *dev;
 	spinlock_t lock;
 
@@ -112,7 +108,8 @@ struct tegra_dc {
 	struct drm_pending_vblank_event *event;
 };
 
-static inline struct tegra_dc *host1x_client_to_dc(struct host1x_client *client)
+static inline struct tegra_dc *
+tegra_drm_client_to_dc(struct tegra_drm_client *client)
 {
 	return container_of(client, struct tegra_dc, client);
 }
diff --git a/drivers/gpu/host1x/drm/gr2d.c b/drivers/gpu/host1x/drm/gr2d.c
index 2691e333e0e2..a7edc794c5ce 100644
--- a/drivers/gpu/host1x/drm/gr2d.c
+++ b/drivers/gpu/host1x/drm/gr2d.c
@@ -27,20 +27,19 @@
 #define GR2D_NUM_REGS 0x4d
 
 struct gr2d {
-	struct host1x_client client;
+	struct tegra_drm_client client;
 	struct host1x_channel *channel;
 	struct clk *clk;
 
 	DECLARE_BITMAP(addr_regs, GR2D_NUM_REGS);
 };
 
-static inline struct gr2d *to_gr2d(struct host1x_client *client)
+static inline struct gr2d *to_gr2d(struct tegra_drm_client *client)
 {
 	return container_of(client, struct gr2d, client);
 }
 
-static int gr2d_client_init(struct host1x_client *client,
-			    struct drm_device *drm)
+static int gr2d_client_init(struct host1x_client *client)
 {
 	return 0;
 }
@@ -50,7 +49,12 @@ static int gr2d_client_exit(struct host1x_client *client)
 	return 0;
 }
 
-static int gr2d_open_channel(struct host1x_client *client,
+static const struct host1x_client_ops gr2d_client_ops = {
+	.init = gr2d_client_init,
+	.exit = gr2d_client_exit,
+};
+
+static int gr2d_open_channel(struct tegra_drm_client *client,
 			     struct tegra_drm_context *context)
 {
 	struct gr2d *gr2d = to_gr2d(client);
@@ -140,7 +144,7 @@ static int gr2d_submit(struct tegra_drm_context *context,
 	job->num_relocs = args->num_relocs;
 	job->num_waitchk = args->num_waitchks;
 	job->client = (u32)args->context;
-	job->class = context->client->class;
+	job->class = context->client->base.class;
 	job->serialize = true;
 
 	while (num_cmdbufs) {
@@ -201,7 +205,7 @@ static int gr2d_submit(struct tegra_drm_context *context,
 	if (args->timeout && args->timeout < 10000)
 		job->timeout = args->timeout;
 
-	err = host1x_job_pin(job, context->client->dev);
+	err = host1x_job_pin(job, context->client->base.dev);
 	if (err)
 		goto fail;
 
@@ -221,9 +225,7 @@ fail:
 	return err;
 }
 
-static struct host1x_client_ops gr2d_client_ops = {
-	.drm_init = gr2d_client_init,
-	.drm_exit = gr2d_client_exit,
+static const struct tegra_drm_client_ops gr2d_ops = {
 	.open_channel = gr2d_open_channel,
 	.close_channel = gr2d_close_channel,
 	.submit = gr2d_submit,
@@ -279,13 +281,15 @@ static int gr2d_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	gr2d->client.ops = &gr2d_client_ops;
-	gr2d->client.dev = dev;
-	gr2d->client.class = HOST1X_CLASS_GR2D;
-	gr2d->client.syncpts = syncpts;
-	gr2d->client.num_syncpts = 1;
+	INIT_LIST_HEAD(&gr2d->client.base.list);
+	gr2d->client.base.ops = &gr2d_client_ops;
+	gr2d->client.base.dev = dev;
+	gr2d->client.base.class = HOST1X_CLASS_GR2D;
+	gr2d->client.base.syncpts = syncpts;
+	gr2d->client.base.num_syncpts = 1;
+	gr2d->client.ops = &gr2d_ops;
 
-	err = host1x_register_client(tegra, &gr2d->client);
+	err = host1x_register_client(tegra, &gr2d->client.base);
 	if (err < 0) {
 		dev_err(dev, "failed to register host1x client: %d\n", err);
 		return err;
@@ -307,15 +311,15 @@ static int gr2d_remove(struct platform_device *pdev)
 	unsigned int i;
 	int err;
 
-	err = host1x_unregister_client(tegra, &gr2d->client);
+	err = host1x_unregister_client(tegra, &gr2d->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
 		return err;
 	}
 
-	for (i = 0; i < gr2d->client.num_syncpts; i++)
-		host1x_syncpt_free(gr2d->client.syncpts[i]);
+	for (i = 0; i < gr2d->client.base.num_syncpts; i++)
+		host1x_syncpt_free(gr2d->client.base.syncpts[i]);
 
 	host1x_channel_free(gr2d->channel);
 	clk_disable_unprepare(gr2d->clk);
diff --git a/drivers/gpu/host1x/drm/hdmi.c b/drivers/gpu/host1x/drm/hdmi.c
index 5d8c41cf4f58..30ac9e872b0d 100644
--- a/drivers/gpu/host1x/drm/hdmi.c
+++ b/drivers/gpu/host1x/drm/hdmi.c
@@ -19,7 +19,7 @@
 #include "host1x_client.h"
 
 struct tegra_hdmi {
-	struct host1x_client client;
+	struct tegra_drm_client client;
 	struct tegra_output output;
 	struct device *dev;
 
@@ -43,7 +43,7 @@ struct tegra_hdmi {
 };
 
 static inline struct tegra_hdmi *
-host1x_client_to_hdmi(struct host1x_client *client)
+tegra_drm_client_to_hdmi(struct tegra_drm_client *client)
 {
 	return container_of(client, struct tegra_hdmi, client);
 }
@@ -1116,24 +1116,24 @@ static int tegra_hdmi_debugfs_exit(struct tegra_hdmi *hdmi)
 	return 0;
 }
 
-static int tegra_hdmi_drm_init(struct host1x_client *client,
-			       struct drm_device *drm)
+static int tegra_hdmi_init(struct host1x_client *client)
 {
-	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
+	struct tegra_drm_client *drm = to_tegra_drm_client(client);
+	struct tegra_hdmi *hdmi = tegra_drm_client_to_hdmi(drm);
 	int err;
 
 	hdmi->output.type = TEGRA_OUTPUT_HDMI;
 	hdmi->output.dev = client->dev;
 	hdmi->output.ops = &hdmi_ops;
 
-	err = tegra_output_init(drm, &hdmi->output);
+	err = tegra_output_init(drm->drm, &hdmi->output);
 	if (err < 0) {
 		dev_err(client->dev, "output setup failed: %d\n", err);
 		return err;
 	}
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_hdmi_debugfs_init(hdmi, drm->primary);
+		err = tegra_hdmi_debugfs_init(hdmi, drm->drm->primary);
 		if (err < 0)
 			dev_err(client->dev, "debugfs setup failed: %d\n", err);
 	}
@@ -1141,9 +1141,10 @@ static int tegra_hdmi_drm_init(struct host1x_client *client,
 	return 0;
 }
 
-static int tegra_hdmi_drm_exit(struct host1x_client *client)
+static int tegra_hdmi_exit(struct host1x_client *client)
 {
-	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
+	struct tegra_drm_client *drm = to_tegra_drm_client(client);
+	struct tegra_hdmi *hdmi = tegra_drm_client_to_hdmi(drm);
 	int err;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
@@ -1169,8 +1170,8 @@ static int tegra_hdmi_drm_exit(struct host1x_client *client)
 }
 
 static const struct host1x_client_ops hdmi_client_ops = {
-	.drm_init = tegra_hdmi_drm_init,
-	.drm_exit = tegra_hdmi_drm_exit,
+	.init = tegra_hdmi_init,
+	.exit = tegra_hdmi_exit,
 };
 
 static int tegra_hdmi_probe(struct platform_device *pdev)
@@ -1246,11 +1247,11 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 
 	hdmi->irq = err;
 
-	hdmi->client.ops = &hdmi_client_ops;
-	INIT_LIST_HEAD(&hdmi->client.list);
-	hdmi->client.dev = &pdev->dev;
+	INIT_LIST_HEAD(&hdmi->client.base.list);
+	hdmi->client.base.ops = &hdmi_client_ops;
+	hdmi->client.base.dev = &pdev->dev;
 
-	err = host1x_register_client(tegra, &hdmi->client);
+	err = host1x_register_client(tegra, &hdmi->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
@@ -1268,7 +1269,7 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 	struct tegra_hdmi *hdmi = platform_get_drvdata(pdev);
 	int err;
 
-	err = host1x_unregister_client(tegra, &hdmi->client);
+	err = host1x_unregister_client(tegra, &hdmi->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index fe09939800bc..d429a938ba13 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -25,4 +25,24 @@ enum host1x_class {
 	HOST1X_CLASS_GR2D_SB = 0x52,
 };
 
+struct host1x_client;
+
+struct host1x_client_ops {
+	int (*init)(struct host1x_client *client);
+	int (*exit)(struct host1x_client *client);
+};
+
+struct host1x_client {
+	struct list_head list;
+	struct device *dev;
+
+	const struct host1x_client_ops *ops;
+
+	enum host1x_class class;
+	struct host1x_channel *channel;
+
+	struct host1x_syncpt **syncpts;
+	unsigned int num_syncpts;
+};
+
 #endif
-- 
cgit 


From 35d747a81d7eb824bd0c3476cd0c564b52ad5353 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 24 Sep 2013 16:30:32 +0200
Subject: gpu: host1x: Expose syncpt and channel functionality

Expose the buffer objects, syncpoint and channel functionality in the
public public header so that drivers can use them.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/cdma.c          |   2 +-
 drivers/gpu/host1x/channel.h       |   6 --
 drivers/gpu/host1x/drm/drm.c       |   2 -
 drivers/gpu/host1x/drm/gem.h       |   4 +-
 drivers/gpu/host1x/drm/gr2d.c      |   6 +-
 drivers/gpu/host1x/drm/hdmi.c      |   2 +-
 drivers/gpu/host1x/host1x_bo.h     |  87 -----------------
 drivers/gpu/host1x/hw/channel_hw.c |   1 -
 drivers/gpu/host1x/hw/debug_hw.c   |   1 -
 drivers/gpu/host1x/job.c           |   2 +-
 drivers/gpu/host1x/job.h           | 108 ----------------------
 drivers/gpu/host1x/syncpt.c        |  19 ++++
 drivers/gpu/host1x/syncpt.h        |  40 +-------
 include/linux/host1x.h             | 185 +++++++++++++++++++++++++++++++++++++
 14 files changed, 211 insertions(+), 254 deletions(-)
 delete mode 100644 drivers/gpu/host1x/host1x_bo.h

(limited to 'include')

diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index de72172d3b5f..3995255b16c7 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -20,6 +20,7 @@
 #include <asm/cacheflush.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/host1x.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/kfifo.h>
@@ -30,7 +31,6 @@
 #include "channel.h"
 #include "dev.h"
 #include "debug.h"
-#include "host1x_bo.h"
 #include "job.h"
 
 /*
diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h
index 48723b8eea42..df767cf90d51 100644
--- a/drivers/gpu/host1x/channel.h
+++ b/drivers/gpu/host1x/channel.h
@@ -40,12 +40,6 @@ struct host1x_channel {
 /* channel list operations */
 int host1x_channel_list_init(struct host1x *host);
 
-struct host1x_channel *host1x_channel_request(struct device *dev);
-void host1x_channel_free(struct host1x_channel *channel);
-struct host1x_channel *host1x_channel_get(struct host1x_channel *channel);
-void host1x_channel_put(struct host1x_channel *channel);
-int host1x_job_submit(struct host1x_job *job);
-
 #define host1x_for_each_channel(host, channel)				\
 	list_for_each_entry(channel, &host->chlist.list, list)
 
diff --git a/drivers/gpu/host1x/drm/drm.c b/drivers/gpu/host1x/drm/drm.c
index 33d966145293..1abcdbc7f4cd 100644
--- a/drivers/gpu/host1x/drm/drm.c
+++ b/drivers/gpu/host1x/drm/drm.c
@@ -8,10 +8,8 @@
  */
 
 #include "host1x_client.h"
-#include "dev.h"
 #include "drm.h"
 #include "gem.h"
-#include "syncpt.h"
 
 #define DRIVER_NAME "tegra"
 #define DRIVER_DESC "NVIDIA Tegra graphics"
diff --git a/drivers/gpu/host1x/drm/gem.h b/drivers/gpu/host1x/drm/gem.h
index 492533a2dacb..2b54f1425d5e 100644
--- a/drivers/gpu/host1x/drm/gem.h
+++ b/drivers/gpu/host1x/drm/gem.h
@@ -19,11 +19,11 @@
 #ifndef __HOST1X_GEM_H
 #define __HOST1X_GEM_H
 
+#include <linux/host1x.h>
+
 #include <drm/drm.h>
 #include <drm/drmP.h>
 
-#include "host1x_bo.h"
-
 struct tegra_bo {
 	struct drm_gem_object gem;
 	struct host1x_bo base;
diff --git a/drivers/gpu/host1x/drm/gr2d.c b/drivers/gpu/host1x/drm/gr2d.c
index a7edc794c5ce..dfb822428ca0 100644
--- a/drivers/gpu/host1x/drm/gr2d.c
+++ b/drivers/gpu/host1x/drm/gr2d.c
@@ -16,13 +16,9 @@
 
 #include <linux/clk.h>
 
-#include "channel.h"
+#include "host1x_client.h"
 #include "drm.h"
 #include "gem.h"
-#include "job.h"
-#include "host1x_bo.h"
-#include "host1x_client.h"
-#include "syncpt.h"
 
 #define GR2D_NUM_REGS 0x4d
 
diff --git a/drivers/gpu/host1x/drm/hdmi.c b/drivers/gpu/host1x/drm/hdmi.c
index 30ac9e872b0d..a2370045993c 100644
--- a/drivers/gpu/host1x/drm/hdmi.c
+++ b/drivers/gpu/host1x/drm/hdmi.c
@@ -13,10 +13,10 @@
 #include <linux/hdmi.h>
 #include <linux/regulator/consumer.h>
 
+#include "host1x_client.h"
 #include "hdmi.h"
 #include "drm.h"
 #include "dc.h"
-#include "host1x_client.h"
 
 struct tegra_hdmi {
 	struct tegra_drm_client client;
diff --git a/drivers/gpu/host1x/host1x_bo.h b/drivers/gpu/host1x/host1x_bo.h
deleted file mode 100644
index 4c1f10bd773d..000000000000
--- a/drivers/gpu/host1x/host1x_bo.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * Tegra host1x Memory Management Abstraction header
- *
- * Copyright (c) 2012-2013, NVIDIA Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _HOST1X_BO_H
-#define _HOST1X_BO_H
-
-struct host1x_bo;
-
-struct host1x_bo_ops {
-	struct host1x_bo *(*get)(struct host1x_bo *bo);
-	void (*put)(struct host1x_bo *bo);
-	dma_addr_t (*pin)(struct host1x_bo *bo, struct sg_table **sgt);
-	void (*unpin)(struct host1x_bo *bo, struct sg_table *sgt);
-	void *(*mmap)(struct host1x_bo *bo);
-	void (*munmap)(struct host1x_bo *bo, void *addr);
-	void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum);
-	void (*kunmap)(struct host1x_bo *bo, unsigned int pagenum, void *addr);
-};
-
-struct host1x_bo {
-	const struct host1x_bo_ops *ops;
-};
-
-static inline void host1x_bo_init(struct host1x_bo *bo,
-				  const struct host1x_bo_ops *ops)
-{
-	bo->ops = ops;
-}
-
-static inline struct host1x_bo *host1x_bo_get(struct host1x_bo *bo)
-{
-	return bo->ops->get(bo);
-}
-
-static inline void host1x_bo_put(struct host1x_bo *bo)
-{
-	bo->ops->put(bo);
-}
-
-static inline dma_addr_t host1x_bo_pin(struct host1x_bo *bo,
-				       struct sg_table **sgt)
-{
-	return bo->ops->pin(bo, sgt);
-}
-
-static inline void host1x_bo_unpin(struct host1x_bo *bo, struct sg_table *sgt)
-{
-	bo->ops->unpin(bo, sgt);
-}
-
-static inline void *host1x_bo_mmap(struct host1x_bo *bo)
-{
-	return bo->ops->mmap(bo);
-}
-
-static inline void host1x_bo_munmap(struct host1x_bo *bo, void *addr)
-{
-	bo->ops->munmap(bo, addr);
-}
-
-static inline void *host1x_bo_kmap(struct host1x_bo *bo, unsigned int pagenum)
-{
-	return bo->ops->kmap(bo, pagenum);
-}
-
-static inline void host1x_bo_kunmap(struct host1x_bo *bo,
-				    unsigned int pagenum, void *addr)
-{
-	bo->ops->kunmap(bo, pagenum, addr);
-}
-
-#endif
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index c950bc655ade..aa9bdf331139 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -21,7 +21,6 @@
 
 #include <trace/events/host1x.h>
 
-#include "host1x_bo.h"
 #include "channel.h"
 #include "dev.h"
 #include "intr.h"
diff --git a/drivers/gpu/host1x/hw/debug_hw.c b/drivers/gpu/host1x/hw/debug_hw.c
index dfad66312286..788fe7179d8f 100644
--- a/drivers/gpu/host1x/hw/debug_hw.c
+++ b/drivers/gpu/host1x/hw/debug_hw.c
@@ -19,7 +19,6 @@
 #include "debug.h"
 #include "cdma.h"
 #include "channel.h"
-#include "host1x_bo.h"
 
 #define HOST1X_DEBUG_MAX_PAGE_OFFSET 102400
 
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index d1b72f4c744d..de5ec333ce1a 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -18,6 +18,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
+#include <linux/host1x.h>
 #include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
@@ -27,7 +28,6 @@
 
 #include "channel.h"
 #include "dev.h"
-#include "host1x_bo.h"
 #include "job.h"
 #include "syncpt.h"
 
diff --git a/drivers/gpu/host1x/job.h b/drivers/gpu/host1x/job.h
index fba45f20458e..33a697d6dcef 100644
--- a/drivers/gpu/host1x/job.h
+++ b/drivers/gpu/host1x/job.h
@@ -34,15 +34,6 @@ struct host1x_cmdbuf {
 	u32 pad;
 };
 
-struct host1x_reloc {
-	struct host1x_bo *cmdbuf;
-	u32 cmdbuf_offset;
-	struct host1x_bo *target;
-	u32 target_offset;
-	u32 shift;
-	u32 pad;
-};
-
 struct host1x_waitchk {
 	struct host1x_bo *bo;
 	u32 offset;
@@ -55,105 +46,6 @@ struct host1x_job_unpin_data {
 	struct sg_table *sgt;
 };
 
-/*
- * Each submit is tracked as a host1x_job.
- */
-struct host1x_job {
-	/* When refcount goes to zero, job can be freed */
-	struct kref ref;
-
-	/* List entry */
-	struct list_head list;
-
-	/* Channel where job is submitted to */
-	struct host1x_channel *channel;
-
-	u32 client;
-
-	/* Gathers and their memory */
-	struct host1x_job_gather *gathers;
-	unsigned int num_gathers;
-
-	/* Wait checks to be processed at submit time */
-	struct host1x_waitchk *waitchk;
-	unsigned int num_waitchk;
-	u32 waitchk_mask;
-
-	/* Array of handles to be pinned & unpinned */
-	struct host1x_reloc *relocarray;
-	unsigned int num_relocs;
-	struct host1x_job_unpin_data *unpins;
-	unsigned int num_unpins;
-
-	dma_addr_t *addr_phys;
-	dma_addr_t *gather_addr_phys;
-	dma_addr_t *reloc_addr_phys;
-
-	/* Sync point id, number of increments and end related to the submit */
-	u32 syncpt_id;
-	u32 syncpt_incrs;
-	u32 syncpt_end;
-
-	/* Maximum time to wait for this job */
-	unsigned int timeout;
-
-	/* Index and number of slots used in the push buffer */
-	unsigned int first_get;
-	unsigned int num_slots;
-
-	/* Copy of gathers */
-	size_t gather_copy_size;
-	dma_addr_t gather_copy;
-	u8 *gather_copy_mapped;
-
-	/* Check if register is marked as an address reg */
-	int (*is_addr_reg)(struct device *dev, u32 reg, u32 class);
-
-	/* Request a SETCLASS to this class */
-	u32 class;
-
-	/* Add a channel wait for previous ops to complete */
-	bool serialize;
-};
-/*
- * Allocate memory for a job. Just enough memory will be allocated to
- * accomodate the submit.
- */
-struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
-				    u32 num_cmdbufs, u32 num_relocs,
-				    u32 num_waitchks);
-
-/*
- * Add a gather to a job.
- */
-void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *mem_id,
-			   u32 words, u32 offset);
-
-/*
- * Increment reference going to host1x_job.
- */
-struct host1x_job *host1x_job_get(struct host1x_job *job);
-
-/*
- * Decrement reference job, free if goes to zero.
- */
-void host1x_job_put(struct host1x_job *job);
-
-/*
- * Pin memory related to job. This handles relocation of addresses to the
- * host1x address space. Handles both the gather memory and any other memory
- * referred to from the gather buffers.
- *
- * Handles also patching out host waits that would wait for an expired sync
- * point value.
- */
-int host1x_job_pin(struct host1x_job *job, struct device *dev);
-
-/*
- * Unpin memory related to job.
- */
-void host1x_job_unpin(struct host1x_job *job);
-
 /*
  * Dump contents of job to debug output.
  */
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index 409745b949db..03cf2922e469 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -354,6 +354,25 @@ void host1x_syncpt_deinit(struct host1x *host)
 		kfree(sp->name);
 }
 
+/*
+ * Read max. It indicates how many operations there are in queue, either in
+ * channel or in a software thread.
+ * */
+u32 host1x_syncpt_read_max(struct host1x_syncpt *sp)
+{
+	smp_rmb();
+	return (u32)atomic_read(&sp->max_val);
+}
+
+/*
+ * Read min, which is a shadow of the current sync point value in hardware.
+ */
+u32 host1x_syncpt_read_min(struct host1x_syncpt *sp)
+{
+	smp_rmb();
+	return (u32)atomic_read(&sp->min_val);
+}
+
 int host1x_syncpt_nb_pts(struct host1x *host)
 {
 	return host->info->nb_pts;
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index 267c0b9d3647..4eb933a497fd 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -20,6 +20,7 @@
 #define __HOST1X_SYNCPT_H
 
 #include <linux/atomic.h>
+#include <linux/host1x.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 
@@ -50,25 +51,6 @@ int host1x_syncpt_init(struct host1x *host);
 /*  Free sync point array */
 void host1x_syncpt_deinit(struct host1x *host);
 
-/*
- * Read max. It indicates how many operations there are in queue, either in
- * channel or in a software thread.
- * */
-static inline u32 host1x_syncpt_read_max(struct host1x_syncpt *sp)
-{
-	smp_rmb();
-	return (u32)atomic_read(&sp->max_val);
-}
-
-/*
- * Read min, which is a shadow of the current sync point value in hardware.
- */
-static inline u32 host1x_syncpt_read_min(struct host1x_syncpt *sp)
-{
-	smp_rmb();
-	return (u32)atomic_read(&sp->min_val);
-}
-
 /* Return number of sync point supported. */
 int host1x_syncpt_nb_pts(struct host1x *host);
 
@@ -112,9 +94,6 @@ static inline bool host1x_syncpt_idle(struct host1x_syncpt *sp)
 	return (min == max);
 }
 
-/* Return pointer to struct denoting sync point id. */
-struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, u32 id);
-
 /* Load current value from hardware to the shadow register. */
 u32 host1x_syncpt_load(struct host1x_syncpt *sp);
 
@@ -130,16 +109,9 @@ void host1x_syncpt_restore(struct host1x *host);
 /* Read current wait base value into shadow register and return it. */
 u32 host1x_syncpt_load_wait_base(struct host1x_syncpt *sp);
 
-/* Request incrementing a sync point. */
-int host1x_syncpt_incr(struct host1x_syncpt *sp);
-
 /* Indicate future operations by incrementing the sync point max. */
 u32 host1x_syncpt_incr_max(struct host1x_syncpt *sp, u32 incrs);
 
-/* Wait until sync point reaches a threshold value, or a timeout. */
-int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh,
-			long timeout, u32 *value);
-
 /* Check if sync point id is valid. */
 static inline int host1x_syncpt_is_valid(struct host1x_syncpt *sp)
 {
@@ -149,14 +121,4 @@ static inline int host1x_syncpt_is_valid(struct host1x_syncpt *sp)
 /* Patch a wait by replacing it with a wait for syncpt 0 value 0 */
 int host1x_syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr);
 
-/* Return id of the sync point */
-u32 host1x_syncpt_id(struct host1x_syncpt *sp);
-
-/* Allocate a sync point for a device. */
-struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
-					    bool client_managed);
-
-/* Free a sync point. */
-void host1x_syncpt_free(struct host1x_syncpt *sp);
-
 #endif
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index d429a938ba13..7442f2a57039 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -19,6 +19,9 @@
 #ifndef __LINUX_HOST1X_H
 #define __LINUX_HOST1X_H
 
+#include <linux/kref.h>
+#include <linux/types.h>
+
 enum host1x_class {
 	HOST1X_CLASS_HOST1X = 0x1,
 	HOST1X_CLASS_GR2D = 0x51,
@@ -45,4 +48,186 @@ struct host1x_client {
 	unsigned int num_syncpts;
 };
 
+/*
+ * host1x buffer objects
+ */
+
+struct host1x_bo;
+struct sg_table;
+
+struct host1x_bo_ops {
+	struct host1x_bo *(*get)(struct host1x_bo *bo);
+	void (*put)(struct host1x_bo *bo);
+	dma_addr_t (*pin)(struct host1x_bo *bo, struct sg_table **sgt);
+	void (*unpin)(struct host1x_bo *bo, struct sg_table *sgt);
+	void *(*mmap)(struct host1x_bo *bo);
+	void (*munmap)(struct host1x_bo *bo, void *addr);
+	void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum);
+	void (*kunmap)(struct host1x_bo *bo, unsigned int pagenum, void *addr);
+};
+
+struct host1x_bo {
+	const struct host1x_bo_ops *ops;
+};
+
+static inline void host1x_bo_init(struct host1x_bo *bo,
+				  const struct host1x_bo_ops *ops)
+{
+	bo->ops = ops;
+}
+
+static inline struct host1x_bo *host1x_bo_get(struct host1x_bo *bo)
+{
+	return bo->ops->get(bo);
+}
+
+static inline void host1x_bo_put(struct host1x_bo *bo)
+{
+	bo->ops->put(bo);
+}
+
+static inline dma_addr_t host1x_bo_pin(struct host1x_bo *bo,
+				       struct sg_table **sgt)
+{
+	return bo->ops->pin(bo, sgt);
+}
+
+static inline void host1x_bo_unpin(struct host1x_bo *bo, struct sg_table *sgt)
+{
+	bo->ops->unpin(bo, sgt);
+}
+
+static inline void *host1x_bo_mmap(struct host1x_bo *bo)
+{
+	return bo->ops->mmap(bo);
+}
+
+static inline void host1x_bo_munmap(struct host1x_bo *bo, void *addr)
+{
+	bo->ops->munmap(bo, addr);
+}
+
+static inline void *host1x_bo_kmap(struct host1x_bo *bo, unsigned int pagenum)
+{
+	return bo->ops->kmap(bo, pagenum);
+}
+
+static inline void host1x_bo_kunmap(struct host1x_bo *bo,
+				    unsigned int pagenum, void *addr)
+{
+	bo->ops->kunmap(bo, pagenum, addr);
+}
+
+/*
+ * host1x syncpoints
+ */
+
+struct host1x_syncpt;
+struct host1x;
+
+struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, u32 id);
+u32 host1x_syncpt_id(struct host1x_syncpt *sp);
+u32 host1x_syncpt_read_min(struct host1x_syncpt *sp);
+u32 host1x_syncpt_read_max(struct host1x_syncpt *sp);
+int host1x_syncpt_incr(struct host1x_syncpt *sp);
+int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
+		       u32 *value);
+struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
+					    bool client_managed);
+void host1x_syncpt_free(struct host1x_syncpt *sp);
+
+/*
+ * host1x channel
+ */
+
+struct host1x_channel;
+struct host1x_job;
+
+struct host1x_channel *host1x_channel_request(struct device *dev);
+void host1x_channel_free(struct host1x_channel *channel);
+struct host1x_channel *host1x_channel_get(struct host1x_channel *channel);
+void host1x_channel_put(struct host1x_channel *channel);
+int host1x_job_submit(struct host1x_job *job);
+
+/*
+ * host1x job
+ */
+
+struct host1x_reloc {
+	struct host1x_bo *cmdbuf;
+	u32 cmdbuf_offset;
+	struct host1x_bo *target;
+	u32 target_offset;
+	u32 shift;
+	u32 pad;
+};
+
+struct host1x_job {
+	/* When refcount goes to zero, job can be freed */
+	struct kref ref;
+
+	/* List entry */
+	struct list_head list;
+
+	/* Channel where job is submitted to */
+	struct host1x_channel *channel;
+
+	u32 client;
+
+	/* Gathers and their memory */
+	struct host1x_job_gather *gathers;
+	unsigned int num_gathers;
+
+	/* Wait checks to be processed at submit time */
+	struct host1x_waitchk *waitchk;
+	unsigned int num_waitchk;
+	u32 waitchk_mask;
+
+	/* Array of handles to be pinned & unpinned */
+	struct host1x_reloc *relocarray;
+	unsigned int num_relocs;
+	struct host1x_job_unpin_data *unpins;
+	unsigned int num_unpins;
+
+	dma_addr_t *addr_phys;
+	dma_addr_t *gather_addr_phys;
+	dma_addr_t *reloc_addr_phys;
+
+	/* Sync point id, number of increments and end related to the submit */
+	u32 syncpt_id;
+	u32 syncpt_incrs;
+	u32 syncpt_end;
+
+	/* Maximum time to wait for this job */
+	unsigned int timeout;
+
+	/* Index and number of slots used in the push buffer */
+	unsigned int first_get;
+	unsigned int num_slots;
+
+	/* Copy of gathers */
+	size_t gather_copy_size;
+	dma_addr_t gather_copy;
+	u8 *gather_copy_mapped;
+
+	/* Check if register is marked as an address reg */
+	int (*is_addr_reg)(struct device *dev, u32 reg, u32 class);
+
+	/* Request a SETCLASS to this class */
+	u32 class;
+
+	/* Add a channel wait for previous ops to complete */
+	bool serialize;
+};
+
+struct host1x_job *host1x_job_alloc(struct host1x_channel *ch,
+				    u32 num_cmdbufs, u32 num_relocs,
+				    u32 num_waitchks);
+void host1x_job_add_gather(struct host1x_job *job, struct host1x_bo *mem_id,
+			   u32 words, u32 offset);
+struct host1x_job *host1x_job_get(struct host1x_job *job);
+void host1x_job_put(struct host1x_job *job);
+int host1x_job_pin(struct host1x_job *job, struct device *dev);
+void host1x_job_unpin(struct host1x_job *job);
+
 #endif
-- 
cgit 


From 7f6b11a18c30743a7099d6e3110e45bd1b2cf54c Mon Sep 17 00:00:00 2001
From: Daniel Jeong <gshark.jeong@gmail.com>
Date: Wed, 16 Oct 2013 04:12:19 -0300
Subject: [media] media: i2c: add driver for dual LED Flash, lm3560

Adds the driver for the LM3560, dual LED Flash The LM3560 has two 1A
constant current driver for high current white LEDs.

It is controlled via an I2C compatible interface(up to 400kHz).

Each flash brightness, torch  brightness and enable/disable can be
controlled independantly, but flash timeout and operation mode are shared.

Signed-off-by: Daniel Jeong <gshark.jeong@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 drivers/media/i2c/Kconfig  |   9 +
 drivers/media/i2c/Makefile |   1 +
 drivers/media/i2c/lm3560.c | 488 +++++++++++++++++++++++++++++++++++++++++++++
 include/media/lm3560.h     |  97 +++++++++
 4 files changed, 595 insertions(+)
 create mode 100644 drivers/media/i2c/lm3560.c
 create mode 100644 include/media/lm3560.h

(limited to 'include')

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index d18be19c96cd..75c8a035539a 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -621,6 +621,15 @@ config VIDEO_AS3645A
 	  This is a driver for the AS3645A and LM3555 flash controllers. It has
 	  build in control for flash, torch and indicator LEDs.
 
+config VIDEO_LM3560
+	tristate "LM3560 dual flash driver support"
+	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on MEDIA_CAMERA_SUPPORT
+	select REGMAP_I2C
+	---help---
+	  This is a driver for the lm3560 dual flash controllers. It controls
+	  flash, torch LEDs.
+
 comment "Video improvement chips"
 
 config VIDEO_UPD64031A
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 9f462df77b4a..e03f1776f4f4 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_VIDEO_S5K4ECGX)	+= s5k4ecgx.o
 obj-$(CONFIG_VIDEO_S5C73M3)	+= s5c73m3/
 obj-$(CONFIG_VIDEO_ADP1653)	+= adp1653.o
 obj-$(CONFIG_VIDEO_AS3645A)	+= as3645a.o
+obj-$(CONFIG_VIDEO_LM3560)	+= lm3560.o
 obj-$(CONFIG_VIDEO_SMIAPP_PLL)	+= smiapp-pll.o
 obj-$(CONFIG_VIDEO_AK881X)		+= ak881x.o
 obj-$(CONFIG_VIDEO_IR_I2C)  += ir-kbd-i2c.o
diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c
new file mode 100644
index 000000000000..3317a9ae3961
--- /dev/null
+++ b/drivers/media/i2c/lm3560.c
@@ -0,0 +1,488 @@
+/*
+ * drivers/media/i2c/lm3560.c
+ * General device driver for TI lm3560, FLASH LED Driver
+ *
+ * Copyright (C) 2013 Texas Instruments
+ *
+ * Contact: Daniel Jeong <gshark.jeong@gmail.com>
+ *			Ldd-Mlp <ldd-mlp@list.ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/videodev2.h>
+#include <media/lm3560.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+/* registers definitions */
+#define REG_ENABLE		0x10
+#define REG_TORCH_BR	0xa0
+#define REG_FLASH_BR	0xb0
+#define REG_FLASH_TOUT	0xc0
+#define REG_FLAG		0xd0
+#define REG_CONFIG1		0xe0
+
+/* Fault Mask */
+#define FAULT_TIMEOUT	(1<<0)
+#define FAULT_OVERTEMP	(1<<1)
+#define FAULT_SHORT_CIRCUIT	(1<<2)
+
+enum led_enable {
+	MODE_SHDN = 0x0,
+	MODE_TORCH = 0x2,
+	MODE_FLASH = 0x3,
+};
+
+/* struct lm3560_flash
+ *
+ * @pdata: platform data
+ * @regmap: reg. map for i2c
+ * @lock: muxtex for serial access.
+ * @led_mode: V4L2 LED mode
+ * @ctrls_led: V4L2 contols
+ * @subdev_led: V4L2 subdev
+ */
+struct lm3560_flash {
+	struct device *dev;
+	struct lm3560_platform_data *pdata;
+	struct regmap *regmap;
+	struct mutex lock;
+
+	enum v4l2_flash_led_mode led_mode;
+	struct v4l2_ctrl_handler ctrls_led[LM3560_LED_MAX];
+	struct v4l2_subdev subdev_led[LM3560_LED_MAX];
+};
+
+#define to_lm3560_flash(_ctrl, _no)	\
+	container_of(_ctrl->handler, struct lm3560_flash, ctrls_led[_no])
+
+/* enable mode control */
+static int lm3560_mode_ctrl(struct lm3560_flash *flash)
+{
+	int rval = -EINVAL;
+
+	switch (flash->led_mode) {
+	case V4L2_FLASH_LED_MODE_NONE:
+		rval = regmap_update_bits(flash->regmap,
+					  REG_ENABLE, 0x03, MODE_SHDN);
+		break;
+	case V4L2_FLASH_LED_MODE_TORCH:
+		rval = regmap_update_bits(flash->regmap,
+					  REG_ENABLE, 0x03, MODE_TORCH);
+		break;
+	case V4L2_FLASH_LED_MODE_FLASH:
+		rval = regmap_update_bits(flash->regmap,
+					  REG_ENABLE, 0x03, MODE_FLASH);
+		break;
+	}
+	return rval;
+}
+
+/* led1/2  enable/disable */
+static int lm3560_enable_ctrl(struct lm3560_flash *flash,
+			      enum lm3560_led_id led_no, bool on)
+{
+	int rval;
+
+	if (led_no == LM3560_LED0) {
+		if (on == true)
+			rval = regmap_update_bits(flash->regmap,
+						  REG_ENABLE, 0x08, 0x08);
+		else
+			rval = regmap_update_bits(flash->regmap,
+						  REG_ENABLE, 0x08, 0x00);
+	} else {
+		if (on == true)
+			rval = regmap_update_bits(flash->regmap,
+						  REG_ENABLE, 0x10, 0x10);
+		else
+			rval = regmap_update_bits(flash->regmap,
+						  REG_ENABLE, 0x10, 0x00);
+	}
+	return rval;
+}
+
+/* torch1/2 brightness control */
+static int lm3560_torch_brt_ctrl(struct lm3560_flash *flash,
+				 enum lm3560_led_id led_no, unsigned int brt)
+{
+	int rval;
+	u8 br_bits;
+
+	if (brt < LM3560_TORCH_BRT_MIN)
+		return lm3560_enable_ctrl(flash, led_no, false);
+	else
+		rval = lm3560_enable_ctrl(flash, led_no, true);
+
+	br_bits = LM3560_TORCH_BRT_uA_TO_REG(brt);
+	if (led_no == LM3560_LED0)
+		rval = regmap_update_bits(flash->regmap,
+					  REG_TORCH_BR, 0x07, br_bits);
+	else
+		rval = regmap_update_bits(flash->regmap,
+					  REG_TORCH_BR, 0x38, br_bits << 3);
+
+	return rval;
+}
+
+/* flash1/2 brightness control */
+static int lm3560_flash_brt_ctrl(struct lm3560_flash *flash,
+				 enum lm3560_led_id led_no, unsigned int brt)
+{
+	int rval;
+	u8 br_bits;
+
+	if (brt < LM3560_FLASH_BRT_MIN)
+		return lm3560_enable_ctrl(flash, led_no, false);
+	else
+		rval = lm3560_enable_ctrl(flash, led_no, true);
+
+	br_bits = LM3560_FLASH_BRT_uA_TO_REG(brt);
+	if (led_no == LM3560_LED0)
+		rval = regmap_update_bits(flash->regmap,
+					  REG_FLASH_BR, 0x0f, br_bits);
+	else
+		rval = regmap_update_bits(flash->regmap,
+					  REG_FLASH_BR, 0xf0, br_bits << 4);
+
+	return rval;
+}
+
+/* V4L2 controls  */
+static int lm3560_get_ctrl(struct v4l2_ctrl *ctrl, enum lm3560_led_id led_no)
+{
+	struct lm3560_flash *flash = to_lm3560_flash(ctrl, led_no);
+
+	mutex_lock(&flash->lock);
+
+	if (ctrl->id == V4L2_CID_FLASH_FAULT) {
+		int rval;
+		s32 fault = 0;
+		unsigned int reg_val;
+		rval = regmap_read(flash->regmap, REG_FLAG, &reg_val);
+		if (rval < 0)
+			return rval;
+		if (rval & FAULT_SHORT_CIRCUIT)
+			fault |= V4L2_FLASH_FAULT_SHORT_CIRCUIT;
+		if (rval & FAULT_OVERTEMP)
+			fault |= V4L2_FLASH_FAULT_OVER_TEMPERATURE;
+		if (rval & FAULT_TIMEOUT)
+			fault |= V4L2_FLASH_FAULT_TIMEOUT;
+		ctrl->cur.val = fault;
+		return 0;
+	}
+
+	mutex_unlock(&flash->lock);
+	return -EINVAL;
+}
+
+static int lm3560_set_ctrl(struct v4l2_ctrl *ctrl, enum lm3560_led_id led_no)
+{
+	struct lm3560_flash *flash = to_lm3560_flash(ctrl, led_no);
+	u8 tout_bits;
+	int rval = -EINVAL;
+
+	mutex_lock(&flash->lock);
+
+	switch (ctrl->id) {
+	case V4L2_CID_FLASH_LED_MODE:
+		flash->led_mode = ctrl->val;
+		if (flash->led_mode != V4L2_FLASH_LED_MODE_FLASH)
+			rval = lm3560_mode_ctrl(flash);
+		break;
+
+	case V4L2_CID_FLASH_STROBE_SOURCE:
+		rval = regmap_update_bits(flash->regmap,
+					  REG_CONFIG1, 0x04, (ctrl->val) << 2);
+		if (rval < 0)
+			goto err_out;
+		break;
+
+	case V4L2_CID_FLASH_STROBE:
+		if (flash->led_mode != V4L2_FLASH_LED_MODE_FLASH)
+			return -EBUSY;
+		flash->led_mode = V4L2_FLASH_LED_MODE_FLASH;
+		rval = lm3560_mode_ctrl(flash);
+		break;
+
+	case V4L2_CID_FLASH_STROBE_STOP:
+		if (flash->led_mode != V4L2_FLASH_LED_MODE_FLASH)
+			return -EBUSY;
+		flash->led_mode = V4L2_FLASH_LED_MODE_NONE;
+		rval = lm3560_mode_ctrl(flash);
+		break;
+
+	case V4L2_CID_FLASH_TIMEOUT:
+		tout_bits = LM3560_FLASH_TOUT_ms_TO_REG(ctrl->val);
+		rval = regmap_update_bits(flash->regmap,
+					  REG_FLASH_TOUT, 0x1f, tout_bits);
+		break;
+
+	case V4L2_CID_FLASH_INTENSITY:
+		rval = lm3560_flash_brt_ctrl(flash, led_no, ctrl->val);
+		break;
+
+	case V4L2_CID_FLASH_TORCH_INTENSITY:
+		rval = lm3560_torch_brt_ctrl(flash, led_no, ctrl->val);
+		break;
+	}
+
+	mutex_unlock(&flash->lock);
+err_out:
+	return rval;
+}
+
+static int lm3560_led1_get_ctrl(struct v4l2_ctrl *ctrl)
+{
+	return lm3560_get_ctrl(ctrl, LM3560_LED1);
+}
+
+static int lm3560_led1_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	return lm3560_set_ctrl(ctrl, LM3560_LED1);
+}
+
+static int lm3560_led0_get_ctrl(struct v4l2_ctrl *ctrl)
+{
+	return lm3560_get_ctrl(ctrl, LM3560_LED0);
+}
+
+static int lm3560_led0_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	return lm3560_set_ctrl(ctrl, LM3560_LED0);
+}
+
+static const struct v4l2_ctrl_ops lm3560_led_ctrl_ops[LM3560_LED_MAX] = {
+	[LM3560_LED0] = {
+			 .g_volatile_ctrl = lm3560_led0_get_ctrl,
+			 .s_ctrl = lm3560_led0_set_ctrl,
+			 },
+	[LM3560_LED1] = {
+			 .g_volatile_ctrl = lm3560_led1_get_ctrl,
+			 .s_ctrl = lm3560_led1_set_ctrl,
+			 }
+};
+
+static int lm3560_init_controls(struct lm3560_flash *flash,
+				enum lm3560_led_id led_no)
+{
+	struct v4l2_ctrl *fault;
+	u32 max_flash_brt = flash->pdata->max_flash_brt[led_no];
+	u32 max_torch_brt = flash->pdata->max_torch_brt[led_no];
+	struct v4l2_ctrl_handler *hdl = &flash->ctrls_led[led_no];
+	const struct v4l2_ctrl_ops *ops = &lm3560_led_ctrl_ops[led_no];
+
+	v4l2_ctrl_handler_init(hdl, 8);
+	/* flash mode */
+	v4l2_ctrl_new_std_menu(hdl, ops, V4L2_CID_FLASH_LED_MODE,
+			       V4L2_FLASH_LED_MODE_TORCH, ~0x7,
+			       V4L2_FLASH_LED_MODE_NONE);
+	flash->led_mode = V4L2_FLASH_LED_MODE_NONE;
+
+	/* flash source */
+	v4l2_ctrl_new_std_menu(hdl, ops, V4L2_CID_FLASH_STROBE_SOURCE,
+			       0x1, ~0x3, V4L2_FLASH_STROBE_SOURCE_SOFTWARE);
+
+	/* flash strobe */
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_STROBE, 0, 0, 0, 0);
+	/* flash strobe stop */
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_STROBE_STOP, 0, 0, 0, 0);
+
+	/* flash strobe timeout */
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_TIMEOUT,
+			  LM3560_FLASH_TOUT_MIN,
+			  flash->pdata->max_flash_timeout,
+			  LM3560_FLASH_TOUT_STEP,
+			  flash->pdata->max_flash_timeout);
+
+	/* flash brt */
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_INTENSITY,
+			  LM3560_FLASH_BRT_MIN, max_flash_brt,
+			  LM3560_FLASH_BRT_STEP, max_flash_brt);
+
+	/* torch brt */
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_TORCH_INTENSITY,
+			  LM3560_TORCH_BRT_MIN, max_torch_brt,
+			  LM3560_TORCH_BRT_STEP, max_torch_brt);
+
+	/* fault */
+	fault = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FLASH_FAULT, 0,
+				  V4L2_FLASH_FAULT_OVER_VOLTAGE
+				  | V4L2_FLASH_FAULT_OVER_TEMPERATURE
+				  | V4L2_FLASH_FAULT_SHORT_CIRCUIT
+				  | V4L2_FLASH_FAULT_TIMEOUT, 0, 0);
+	if (fault != NULL)
+		fault->flags |= V4L2_CTRL_FLAG_VOLATILE;
+
+	if (hdl->error)
+		return hdl->error;
+
+	flash->subdev_led[led_no].ctrl_handler = hdl;
+	return 0;
+}
+
+/* initialize device */
+static const struct v4l2_subdev_ops lm3560_ops = {
+	.core = NULL,
+};
+
+static const struct regmap_config lm3560_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0xFF,
+};
+
+static int lm3560_subdev_init(struct lm3560_flash *flash,
+			      enum lm3560_led_id led_no, char *led_name)
+{
+	struct i2c_client *client = to_i2c_client(flash->dev);
+	int rval;
+
+	v4l2_i2c_subdev_init(&flash->subdev_led[led_no], client, &lm3560_ops);
+	flash->subdev_led[led_no].flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	strcpy(flash->subdev_led[led_no].name, led_name);
+	rval = lm3560_init_controls(flash, led_no);
+	if (rval)
+		goto err_out;
+	rval = media_entity_init(&flash->subdev_led[led_no].entity, 0, NULL, 0);
+	if (rval < 0)
+		goto err_out;
+	flash->subdev_led[led_no].entity.type = MEDIA_ENT_T_V4L2_SUBDEV_FLASH;
+
+	return rval;
+
+err_out:
+	v4l2_ctrl_handler_free(&flash->ctrls_led[led_no]);
+	return rval;
+}
+
+static int lm3560_init_device(struct lm3560_flash *flash)
+{
+	int rval;
+	unsigned int reg_val;
+
+	/* set peak current */
+	rval = regmap_update_bits(flash->regmap,
+				  REG_FLASH_TOUT, 0x60, flash->pdata->peak);
+	if (rval < 0)
+		return rval;
+	/* output disable */
+	flash->led_mode = V4L2_FLASH_LED_MODE_NONE;
+	rval = lm3560_mode_ctrl(flash);
+	if (rval < 0)
+		return rval;
+	/* Reset faults */
+	rval = regmap_read(flash->regmap, REG_FLAG, &reg_val);
+	return rval;
+}
+
+static int lm3560_probe(struct i2c_client *client,
+			const struct i2c_device_id *devid)
+{
+	struct lm3560_flash *flash;
+	struct lm3560_platform_data *pdata = dev_get_platdata(&client->dev);
+	int rval;
+
+	flash = devm_kzalloc(&client->dev, sizeof(*flash), GFP_KERNEL);
+	if (flash == NULL)
+		return -ENOMEM;
+
+	flash->regmap = devm_regmap_init_i2c(client, &lm3560_regmap);
+	if (IS_ERR(flash->regmap)) {
+		rval = PTR_ERR(flash->regmap);
+		return rval;
+	}
+
+	/* if there is no platform data, use chip default value */
+	if (pdata == NULL) {
+		pdata =
+		    kzalloc(sizeof(struct lm3560_platform_data), GFP_KERNEL);
+		if (pdata == NULL)
+			return -ENODEV;
+		pdata->peak = LM3560_PEAK_3600mA;
+		pdata->max_flash_timeout = LM3560_FLASH_TOUT_MAX;
+		/* led 1 */
+		pdata->max_flash_brt[LM3560_LED0] = LM3560_FLASH_BRT_MAX;
+		pdata->max_torch_brt[LM3560_LED0] = LM3560_TORCH_BRT_MAX;
+		/* led 2 */
+		pdata->max_flash_brt[LM3560_LED1] = LM3560_FLASH_BRT_MAX;
+		pdata->max_torch_brt[LM3560_LED1] = LM3560_TORCH_BRT_MAX;
+	}
+	flash->pdata = pdata;
+	flash->dev = &client->dev;
+	mutex_init(&flash->lock);
+
+	rval = lm3560_subdev_init(flash, LM3560_LED0, "lm3560-led0");
+	if (rval < 0)
+		return rval;
+
+	rval = lm3560_subdev_init(flash, LM3560_LED1, "lm3560-led1");
+	if (rval < 0)
+		return rval;
+
+	rval = lm3560_init_device(flash);
+	if (rval < 0)
+		return rval;
+
+	return 0;
+}
+
+static int lm3560_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *subdev = i2c_get_clientdata(client);
+	struct lm3560_flash *flash = container_of(subdev, struct lm3560_flash,
+						  subdev_led[LM3560_LED_MAX]);
+	unsigned int i;
+
+	for (i = LM3560_LED0; i < LM3560_LED_MAX; i++) {
+		v4l2_device_unregister_subdev(&flash->subdev_led[i]);
+		v4l2_ctrl_handler_free(&flash->ctrls_led[i]);
+		media_entity_cleanup(&flash->subdev_led[i].entity);
+	}
+
+	return 0;
+}
+
+static const struct i2c_device_id lm3560_id_table[] = {
+	{LM3560_NAME, 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, lm3560_id_table);
+
+static struct i2c_driver lm3560_i2c_driver = {
+	.driver = {
+		   .name = LM3560_NAME,
+		   .pm = NULL,
+		   },
+	.probe = lm3560_probe,
+	.remove = lm3560_remove,
+	.id_table = lm3560_id_table,
+};
+
+module_i2c_driver(lm3560_i2c_driver);
+
+MODULE_AUTHOR("Daniel Jeong <gshark.jeong@gmail.com>");
+MODULE_AUTHOR("Ldd Mlp <ldd-mlp@list.ti.com>");
+MODULE_DESCRIPTION("Texas Instruments LM3560 LED flash driver");
+MODULE_LICENSE("GPL");
diff --git a/include/media/lm3560.h b/include/media/lm3560.h
new file mode 100644
index 000000000000..46670706d6f8
--- /dev/null
+++ b/include/media/lm3560.h
@@ -0,0 +1,97 @@
+/*
+ * include/media/lm3560.h
+ *
+ * Copyright (C) 2013 Texas Instruments
+ *
+ * Contact: Daniel Jeong <gshark.jeong@gmail.com>
+ *			Ldd-Mlp <ldd-mlp@list.ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#ifndef __LM3560_H__
+#define __LM3560_H__
+
+#include <media/v4l2-subdev.h>
+
+#define LM3560_NAME	"lm3560"
+#define LM3560_I2C_ADDR	(0x53)
+
+/*  FLASH Brightness
+ *	min 62500uA, step 62500uA, max 1000000uA
+ */
+#define LM3560_FLASH_BRT_MIN 62500
+#define LM3560_FLASH_BRT_STEP 62500
+#define LM3560_FLASH_BRT_MAX 1000000
+#define LM3560_FLASH_BRT_uA_TO_REG(a)	\
+	((a) < LM3560_FLASH_BRT_MIN ? 0 :	\
+	 (((a) - LM3560_FLASH_BRT_MIN) / LM3560_FLASH_BRT_STEP))
+#define LM3560_FLASH_BRT_REG_TO_uA(a)		\
+	((a) * LM3560_FLASH_BRT_STEP + LM3560_FLASH_BRT_MIN)
+
+/*  FLASH TIMEOUT DURATION
+ *	min 32ms, step 32ms, max 1024ms
+ */
+#define LM3560_FLASH_TOUT_MIN 32
+#define LM3560_FLASH_TOUT_STEP 32
+#define LM3560_FLASH_TOUT_MAX 1024
+#define LM3560_FLASH_TOUT_ms_TO_REG(a)	\
+	((a) < LM3560_FLASH_TOUT_MIN ? 0 :	\
+	 (((a) - LM3560_FLASH_TOUT_MIN) / LM3560_FLASH_TOUT_STEP))
+#define LM3560_FLASH_TOUT_REG_TO_ms(a)		\
+	((a) * LM3560_FLASH_TOUT_STEP + LM3560_FLASH_TOUT_MIN)
+
+/*  TORCH BRT
+ *	min 31250uA, step 31250uA, max 250000uA
+ */
+#define LM3560_TORCH_BRT_MIN 31250
+#define LM3560_TORCH_BRT_STEP 31250
+#define LM3560_TORCH_BRT_MAX 250000
+#define LM3560_TORCH_BRT_uA_TO_REG(a)	\
+	((a) < LM3560_TORCH_BRT_MIN ? 0 :	\
+	 (((a) - LM3560_TORCH_BRT_MIN) / LM3560_TORCH_BRT_STEP))
+#define LM3560_TORCH_BRT_REG_TO_uA(a)		\
+	((a) * LM3560_TORCH_BRT_STEP + LM3560_TORCH_BRT_MIN)
+
+enum lm3560_led_id {
+	LM3560_LED0 = 0,
+	LM3560_LED1,
+	LM3560_LED_MAX
+};
+
+enum lm3560_peak_current {
+	LM3560_PEAK_1600mA = 0x00,
+	LM3560_PEAK_2300mA = 0x20,
+	LM3560_PEAK_3000mA = 0x40,
+	LM3560_PEAK_3600mA = 0x60
+};
+
+/* struct lm3560_platform_data
+ *
+ * @peak :  peak current
+ * @max_flash_timeout: flash timeout
+ * @max_flash_brt: flash mode led brightness
+ * @max_torch_brt: torch mode led brightness
+ */
+struct lm3560_platform_data {
+	enum lm3560_peak_current peak;
+
+	u32 max_flash_timeout;
+	u32 max_flash_brt[LM3560_LED_MAX];
+	u32 max_torch_brt[LM3560_LED_MAX];
+};
+
+#endif /* __LM3560_H__ */
-- 
cgit 


From 776dc38403676f499a73d32e2e7c61eb5b42f736 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 14 Oct 2013 14:43:22 +0200
Subject: drm/tegra: Move subdevice infrastructure to host1x

The Tegra DRM driver currently uses some infrastructure to defer the DRM
core initialization until all required devices have registered. The same
infrastructure can potentially be used by any other driver that requires
more than a single sub-device of the host1x module.

Make the infrastructure more generic and keep only the DRM specific code
in the DRM part of the driver. Eventually this will make it easy to move
the DRM driver part back to the DRM subsystem.

Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/Makefile        |   2 +
 drivers/gpu/host1x/bus.c           | 550 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/host1x/bus.h           |  29 ++
 drivers/gpu/host1x/dev.c           |  60 ++--
 drivers/gpu/host1x/dev.h           |   9 +-
 drivers/gpu/host1x/drm/bus.c       |  76 +++++
 drivers/gpu/host1x/drm/dc.c        |  30 +-
 drivers/gpu/host1x/drm/drm.c       | 347 ++++++++---------------
 drivers/gpu/host1x/drm/drm.h       |  31 ++-
 drivers/gpu/host1x/drm/gr2d.c      |  60 ++--
 drivers/gpu/host1x/drm/hdmi.c      |  28 +-
 drivers/gpu/host1x/host1x_client.h |  35 ---
 include/drm/drmP.h                 |   1 +
 include/linux/host1x.h             |  45 ++-
 14 files changed, 918 insertions(+), 385 deletions(-)
 create mode 100644 drivers/gpu/host1x/bus.c
 create mode 100644 drivers/gpu/host1x/bus.h
 create mode 100644 drivers/gpu/host1x/drm/bus.c
 delete mode 100644 drivers/gpu/host1x/host1x_client.h

(limited to 'include')

diff --git a/drivers/gpu/host1x/Makefile b/drivers/gpu/host1x/Makefile
index 3b037b6e0298..7b781920c58a 100644
--- a/drivers/gpu/host1x/Makefile
+++ b/drivers/gpu/host1x/Makefile
@@ -1,6 +1,7 @@
 ccflags-y = -Idrivers/gpu/host1x
 
 host1x-y = \
+	bus.o \
 	syncpt.o \
 	dev.o \
 	intr.o \
@@ -17,4 +18,5 @@ host1x-$(CONFIG_DRM_TEGRA) += drm/drm.o drm/fb.o drm/dc.o
 host1x-$(CONFIG_DRM_TEGRA) += drm/output.o drm/rgb.o drm/hdmi.o
 host1x-$(CONFIG_DRM_TEGRA) += drm/gem.o
 host1x-$(CONFIG_DRM_TEGRA) += drm/gr2d.o
+host1x-$(CONFIG_DRM_TEGRA) += drm/bus.o
 obj-$(CONFIG_TEGRA_HOST1X) += host1x.o
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
new file mode 100644
index 000000000000..509383f8be03
--- /dev/null
+++ b/drivers/gpu/host1x/bus.c
@@ -0,0 +1,550 @@
+/*
+ * Copyright (C) 2012 Avionic Design GmbH
+ * Copyright (C) 2012-2013, NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/host1x.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include "dev.h"
+
+static DEFINE_MUTEX(clients_lock);
+static LIST_HEAD(clients);
+
+static DEFINE_MUTEX(drivers_lock);
+static LIST_HEAD(drivers);
+
+static DEFINE_MUTEX(devices_lock);
+static LIST_HEAD(devices);
+
+struct host1x_subdev {
+	struct host1x_client *client;
+	struct device_node *np;
+	struct list_head list;
+};
+
+/**
+ * host1x_subdev_add() - add a new subdevice with an associated device node
+ */
+static int host1x_subdev_add(struct host1x_device *device,
+			     struct device_node *np)
+{
+	struct host1x_subdev *subdev;
+
+	subdev = kzalloc(sizeof(*subdev), GFP_KERNEL);
+	if (!subdev)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&subdev->list);
+	subdev->np = of_node_get(np);
+
+	mutex_lock(&device->subdevs_lock);
+	list_add_tail(&subdev->list, &device->subdevs);
+	mutex_unlock(&device->subdevs_lock);
+
+	return 0;
+}
+
+/**
+ * host1x_subdev_del() - remove subdevice
+ */
+static void host1x_subdev_del(struct host1x_subdev *subdev)
+{
+	list_del(&subdev->list);
+	of_node_put(subdev->np);
+	kfree(subdev);
+}
+
+/**
+ * host1x_device_parse_dt() - scan device tree and add matching subdevices
+ */
+static int host1x_device_parse_dt(struct host1x_device *device)
+{
+	struct device_node *np;
+	int err;
+
+	for_each_child_of_node(device->dev.parent->of_node, np) {
+		if (of_match_node(device->driver->subdevs, np) &&
+		    of_device_is_available(np)) {
+			err = host1x_subdev_add(device, np);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static void host1x_subdev_register(struct host1x_device *device,
+				   struct host1x_subdev *subdev,
+				   struct host1x_client *client)
+{
+	int err;
+
+	/*
+	 * Move the subdevice to the list of active (registered) subdevices
+	 * and associate it with a client. At the same time, associate the
+	 * client with its parent device.
+	 */
+	mutex_lock(&device->subdevs_lock);
+	mutex_lock(&device->clients_lock);
+	list_move_tail(&client->list, &device->clients);
+	list_move_tail(&subdev->list, &device->active);
+	client->parent = &device->dev;
+	subdev->client = client;
+	mutex_unlock(&device->clients_lock);
+	mutex_unlock(&device->subdevs_lock);
+
+	/*
+	 * When all subdevices have been registered, the composite device is
+	 * ready to be probed.
+	 */
+	if (list_empty(&device->subdevs)) {
+		err = device->driver->probe(device);
+		if (err < 0)
+			dev_err(&device->dev, "probe failed: %d\n", err);
+	}
+}
+
+static void __host1x_subdev_unregister(struct host1x_device *device,
+				       struct host1x_subdev *subdev)
+{
+	struct host1x_client *client = subdev->client;
+	int err;
+
+	/*
+	 * If all subdevices have been activated, we're about to remove the
+	 * first active subdevice, so unload the driver first.
+	 */
+	if (list_empty(&device->subdevs)) {
+		err = device->driver->remove(device);
+		if (err < 0)
+			dev_err(&device->dev, "remove failed: %d\n", err);
+	}
+
+	/*
+	 * Move the subdevice back to the list of idle subdevices and remove
+	 * it from list of clients.
+	 */
+	mutex_lock(&device->clients_lock);
+	subdev->client = NULL;
+	client->parent = NULL;
+	list_move_tail(&subdev->list, &device->subdevs);
+	/*
+	 * XXX: Perhaps don't do this here, but rather explicitly remove it
+	 * when the device is about to be deleted.
+	 *
+	 * This is somewhat complicated by the fact that this function is
+	 * used to remove the subdevice when a client is unregistered but
+	 * also when the composite device is about to be removed.
+	 */
+	list_del_init(&client->list);
+	mutex_unlock(&device->clients_lock);
+}
+
+static void host1x_subdev_unregister(struct host1x_device *device,
+				     struct host1x_subdev *subdev)
+{
+	mutex_lock(&device->subdevs_lock);
+	__host1x_subdev_unregister(device, subdev);
+	mutex_unlock(&device->subdevs_lock);
+}
+
+int host1x_device_init(struct host1x_device *device)
+{
+	struct host1x_client *client;
+	int err;
+
+	mutex_lock(&device->clients_lock);
+
+	list_for_each_entry(client, &device->clients, list) {
+		if (client->ops && client->ops->init) {
+			err = client->ops->init(client);
+			if (err < 0) {
+				dev_err(&device->dev,
+					"failed to initialize %s: %d\n",
+					dev_name(client->dev), err);
+				mutex_unlock(&device->clients_lock);
+				return err;
+			}
+		}
+	}
+
+	mutex_unlock(&device->clients_lock);
+
+	return 0;
+}
+
+int host1x_device_exit(struct host1x_device *device)
+{
+	struct host1x_client *client;
+	int err;
+
+	mutex_lock(&device->clients_lock);
+
+	list_for_each_entry_reverse(client, &device->clients, list) {
+		if (client->ops && client->ops->exit) {
+			err = client->ops->exit(client);
+			if (err < 0) {
+				dev_err(&device->dev,
+					"failed to cleanup %s: %d\n",
+					dev_name(client->dev), err);
+				mutex_unlock(&device->clients_lock);
+				return err;
+			}
+		}
+	}
+
+	mutex_unlock(&device->clients_lock);
+
+	return 0;
+}
+
+static int host1x_register_client(struct host1x *host1x,
+				  struct host1x_client *client)
+{
+	struct host1x_device *device;
+	struct host1x_subdev *subdev;
+
+	mutex_lock(&host1x->devices_lock);
+
+	list_for_each_entry(device, &host1x->devices, list) {
+		list_for_each_entry(subdev, &device->subdevs, list) {
+			if (subdev->np == client->dev->of_node) {
+				host1x_subdev_register(device, subdev, client);
+				mutex_unlock(&host1x->devices_lock);
+				return 0;
+			}
+		}
+	}
+
+	mutex_unlock(&host1x->devices_lock);
+	return -ENODEV;
+}
+
+static int host1x_unregister_client(struct host1x *host1x,
+				    struct host1x_client *client)
+{
+	struct host1x_device *device, *dt;
+	struct host1x_subdev *subdev;
+
+	mutex_lock(&host1x->devices_lock);
+
+	list_for_each_entry_safe(device, dt, &host1x->devices, list) {
+		list_for_each_entry(subdev, &device->active, list) {
+			if (subdev->client == client) {
+				host1x_subdev_unregister(device, subdev);
+				mutex_unlock(&host1x->devices_lock);
+				return 0;
+			}
+		}
+	}
+
+	mutex_unlock(&host1x->devices_lock);
+	return -ENODEV;
+}
+
+struct bus_type host1x_bus_type = {
+	.name = "host1x",
+};
+
+int host1x_bus_init(void)
+{
+	return bus_register(&host1x_bus_type);
+}
+
+void host1x_bus_exit(void)
+{
+	bus_unregister(&host1x_bus_type);
+}
+
+static void host1x_device_release(struct device *dev)
+{
+	struct host1x_device *device = to_host1x_device(dev);
+
+	kfree(device);
+}
+
+static int host1x_device_add(struct host1x *host1x,
+			     struct host1x_driver *driver)
+{
+	struct host1x_client *client, *tmp;
+	struct host1x_subdev *subdev;
+	struct host1x_device *device;
+	int err;
+
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device)
+		return -ENOMEM;
+
+	mutex_init(&device->subdevs_lock);
+	INIT_LIST_HEAD(&device->subdevs);
+	INIT_LIST_HEAD(&device->active);
+	mutex_init(&device->clients_lock);
+	INIT_LIST_HEAD(&device->clients);
+	INIT_LIST_HEAD(&device->list);
+	device->driver = driver;
+
+	device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask;
+	device->dev.dma_mask = &device->dev.coherent_dma_mask;
+	device->dev.release = host1x_device_release;
+	dev_set_name(&device->dev, driver->name);
+	device->dev.bus = &host1x_bus_type;
+	device->dev.parent = host1x->dev;
+
+	err = device_register(&device->dev);
+	if (err < 0)
+		return err;
+
+	err = host1x_device_parse_dt(device);
+	if (err < 0) {
+		device_unregister(&device->dev);
+		return err;
+	}
+
+	mutex_lock(&host1x->devices_lock);
+	list_add_tail(&device->list, &host1x->devices);
+	mutex_unlock(&host1x->devices_lock);
+
+	mutex_lock(&clients_lock);
+
+	list_for_each_entry_safe(client, tmp, &clients, list) {
+		list_for_each_entry(subdev, &device->subdevs, list) {
+			if (subdev->np == client->dev->of_node) {
+				host1x_subdev_register(device, subdev, client);
+				break;
+			}
+		}
+	}
+
+	mutex_unlock(&clients_lock);
+
+	return 0;
+}
+
+/*
+ * Removes a device by first unregistering any subdevices and then removing
+ * itself from the list of devices.
+ *
+ * This function must be called with the host1x->devices_lock held.
+ */
+static void host1x_device_del(struct host1x *host1x,
+			      struct host1x_device *device)
+{
+	struct host1x_subdev *subdev, *sd;
+	struct host1x_client *client, *cl;
+
+	mutex_lock(&device->subdevs_lock);
+
+	/* unregister subdevices */
+	list_for_each_entry_safe(subdev, sd, &device->active, list) {
+		/*
+		 * host1x_subdev_unregister() will remove the client from
+		 * any lists, so we'll need to manually add it back to the
+		 * list of idle clients.
+		 *
+		 * XXX: Alternatively, perhaps don't remove the client from
+		 * any lists in host1x_subdev_unregister() and instead do
+		 * that explicitly from host1x_unregister_client()?
+		 */
+		client = subdev->client;
+
+		__host1x_subdev_unregister(device, subdev);
+
+		/* add the client to the list of idle clients */
+		mutex_lock(&clients_lock);
+		list_add_tail(&client->list, &clients);
+		mutex_unlock(&clients_lock);
+	}
+
+	/* remove subdevices */
+	list_for_each_entry_safe(subdev, sd, &device->subdevs, list)
+		host1x_subdev_del(subdev);
+
+	mutex_unlock(&device->subdevs_lock);
+
+	/* move clients to idle list */
+	mutex_lock(&clients_lock);
+	mutex_lock(&device->clients_lock);
+
+	list_for_each_entry_safe(client, cl, &device->clients, list)
+		list_move_tail(&client->list, &clients);
+
+	mutex_unlock(&device->clients_lock);
+	mutex_unlock(&clients_lock);
+
+	/* finally remove the device */
+	list_del_init(&device->list);
+	device_unregister(&device->dev);
+}
+
+static void host1x_attach_driver(struct host1x *host1x,
+				 struct host1x_driver *driver)
+{
+	struct host1x_device *device;
+	int err;
+
+	mutex_lock(&host1x->devices_lock);
+
+	list_for_each_entry(device, &host1x->devices, list) {
+		if (device->driver == driver) {
+			mutex_unlock(&host1x->devices_lock);
+			return;
+		}
+	}
+
+	mutex_unlock(&host1x->devices_lock);
+
+	err = host1x_device_add(host1x, driver);
+	if (err < 0)
+		dev_err(host1x->dev, "failed to allocate device: %d\n", err);
+}
+
+static void host1x_detach_driver(struct host1x *host1x,
+				 struct host1x_driver *driver)
+{
+	struct host1x_device *device, *tmp;
+
+	mutex_lock(&host1x->devices_lock);
+
+	list_for_each_entry_safe(device, tmp, &host1x->devices, list)
+		if (device->driver == driver)
+			host1x_device_del(host1x, device);
+
+	mutex_unlock(&host1x->devices_lock);
+}
+
+int host1x_register(struct host1x *host1x)
+{
+	struct host1x_driver *driver;
+
+	mutex_lock(&devices_lock);
+	list_add_tail(&host1x->list, &devices);
+	mutex_unlock(&devices_lock);
+
+	mutex_lock(&drivers_lock);
+
+	list_for_each_entry(driver, &drivers, list)
+		host1x_attach_driver(host1x, driver);
+
+	mutex_unlock(&drivers_lock);
+
+	return 0;
+}
+
+int host1x_unregister(struct host1x *host1x)
+{
+	struct host1x_driver *driver;
+
+	mutex_lock(&drivers_lock);
+
+	list_for_each_entry(driver, &drivers, list)
+		host1x_detach_driver(host1x, driver);
+
+	mutex_unlock(&drivers_lock);
+
+	mutex_lock(&devices_lock);
+	list_del_init(&host1x->list);
+	mutex_unlock(&devices_lock);
+
+	return 0;
+}
+
+int host1x_driver_register(struct host1x_driver *driver)
+{
+	struct host1x *host1x;
+
+	INIT_LIST_HEAD(&driver->list);
+
+	mutex_lock(&drivers_lock);
+	list_add_tail(&driver->list, &drivers);
+	mutex_unlock(&drivers_lock);
+
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list)
+		host1x_attach_driver(host1x, driver);
+
+	mutex_unlock(&devices_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(host1x_driver_register);
+
+void host1x_driver_unregister(struct host1x_driver *driver)
+{
+	mutex_lock(&drivers_lock);
+	list_del_init(&driver->list);
+	mutex_unlock(&drivers_lock);
+}
+EXPORT_SYMBOL(host1x_driver_unregister);
+
+int host1x_client_register(struct host1x_client *client)
+{
+	struct host1x *host1x;
+	int err;
+
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list) {
+		err = host1x_register_client(host1x, client);
+		if (!err) {
+			mutex_unlock(&devices_lock);
+			return 0;
+		}
+	}
+
+	mutex_unlock(&devices_lock);
+
+	mutex_lock(&clients_lock);
+	list_add_tail(&client->list, &clients);
+	mutex_unlock(&clients_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(host1x_client_register);
+
+int host1x_client_unregister(struct host1x_client *client)
+{
+	struct host1x_client *c;
+	struct host1x *host1x;
+	int err;
+
+	mutex_lock(&devices_lock);
+
+	list_for_each_entry(host1x, &devices, list) {
+		err = host1x_unregister_client(host1x, client);
+		if (!err) {
+			mutex_unlock(&devices_lock);
+			return 0;
+		}
+	}
+
+	mutex_unlock(&devices_lock);
+	mutex_lock(&clients_lock);
+
+	list_for_each_entry(c, &clients, list) {
+		if (c == client) {
+			list_del_init(&c->list);
+			break;
+		}
+	}
+
+	mutex_unlock(&clients_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(host1x_client_unregister);
diff --git a/drivers/gpu/host1x/bus.h b/drivers/gpu/host1x/bus.h
new file mode 100644
index 000000000000..4099e99212c8
--- /dev/null
+++ b/drivers/gpu/host1x/bus.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2012 Avionic Design GmbH
+ * Copyright (C) 2012-2013, NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef HOST1X_BUS_H
+#define HOST1X_BUS_H
+
+struct host1x;
+
+int host1x_bus_init(void);
+void host1x_bus_exit(void);
+
+int host1x_register(struct host1x *host1x);
+int host1x_unregister(struct host1x *host1x);
+
+#endif
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 105aa4ed665a..de0fd552710d 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -27,24 +27,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/host1x.h>
 
+#include "bus.h"
 #include "dev.h"
 #include "intr.h"
 #include "channel.h"
 #include "debug.h"
 #include "hw/host1x01.h"
-#include "host1x_client.h"
-
-void host1x_set_drm_data(struct device *dev, void *data)
-{
-	struct host1x *host1x = dev_get_drvdata(dev);
-	host1x->drm_data = data;
-}
-
-void *host1x_get_drm_data(struct device *dev)
-{
-	struct host1x *host1x = dev_get_drvdata(dev);
-	return host1x ? host1x->drm_data : NULL;
-}
 
 void host1x_sync_writel(struct host1x *host1x, u32 v, u32 r)
 {
@@ -114,6 +102,9 @@ static int host1x_probe(struct platform_device *pdev)
 	if (!host)
 		return -ENOMEM;
 
+	mutex_init(&host->devices_lock);
+	INIT_LIST_HEAD(&host->devices);
+	INIT_LIST_HEAD(&host->list);
 	host->dev = &pdev->dev;
 	host->info = id->data;
 
@@ -163,10 +154,14 @@ static int host1x_probe(struct platform_device *pdev)
 
 	host1x_debug_init(host);
 
-	tegra_drm_alloc(pdev);
+	err = host1x_register(host);
+	if (err < 0)
+		goto fail_deinit_intr;
 
 	return 0;
 
+fail_deinit_intr:
+	host1x_intr_deinit(host);
 fail_deinit_syncpt:
 	host1x_syncpt_deinit(host);
 	return err;
@@ -176,6 +171,7 @@ static int host1x_remove(struct platform_device *pdev)
 {
 	struct host1x *host = platform_get_drvdata(pdev);
 
+	host1x_unregister(host);
 	host1x_intr_deinit(host);
 	host1x_syncpt_deinit(host);
 	clk_disable_unprepare(host->clk);
@@ -196,46 +192,24 @@ static int __init tegra_host1x_init(void)
 {
 	int err;
 
-	err = platform_driver_register(&tegra_host1x_driver);
+	err = host1x_bus_init();
 	if (err < 0)
 		return err;
 
-#ifdef CONFIG_DRM_TEGRA
-	err = platform_driver_register(&tegra_dc_driver);
-	if (err < 0)
-		goto unregister_host1x;
-
-	err = platform_driver_register(&tegra_hdmi_driver);
-	if (err < 0)
-		goto unregister_dc;
-
-	err = platform_driver_register(&tegra_gr2d_driver);
-	if (err < 0)
-		goto unregister_hdmi;
-#endif
+	err = platform_driver_register(&tegra_host1x_driver);
+	if (err < 0) {
+		host1x_bus_exit();
+		return err;
+	}
 
 	return 0;
-
-#ifdef CONFIG_DRM_TEGRA
-unregister_hdmi:
-	platform_driver_unregister(&tegra_hdmi_driver);
-unregister_dc:
-	platform_driver_unregister(&tegra_dc_driver);
-unregister_host1x:
-	platform_driver_unregister(&tegra_host1x_driver);
-	return err;
-#endif
 }
 module_init(tegra_host1x_init);
 
 static void __exit tegra_host1x_exit(void)
 {
-#ifdef CONFIG_DRM_TEGRA
-	platform_driver_unregister(&tegra_gr2d_driver);
-	platform_driver_unregister(&tegra_hdmi_driver);
-	platform_driver_unregister(&tegra_dc_driver);
-#endif
 	platform_driver_unregister(&tegra_host1x_driver);
+	host1x_bus_exit();
 }
 module_exit(tegra_host1x_exit);
 
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index bed90a8131be..6cf689b9e17b 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -125,7 +125,10 @@ struct host1x {
 
 	struct dentry *debugfs;
 
-	void *drm_data;
+	struct mutex devices_lock;
+	struct list_head devices;
+
+	struct list_head list;
 };
 
 void host1x_sync_writel(struct host1x *host1x, u32 r, u32 v);
@@ -301,8 +304,4 @@ static inline void host1x_hw_show_mlocks(struct host1x *host, struct output *o)
 	host->debug_op->show_mlocks(host, o);
 }
 
-extern struct platform_driver tegra_dc_driver;
-extern struct platform_driver tegra_hdmi_driver;
-extern struct platform_driver tegra_gr2d_driver;
-
 #endif
diff --git a/drivers/gpu/host1x/drm/bus.c b/drivers/gpu/host1x/drm/bus.c
new file mode 100644
index 000000000000..565f8f7b9a47
--- /dev/null
+++ b/drivers/gpu/host1x/drm/bus.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright (C) 2013 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "drm.h"
+
+static int drm_host1x_set_busid(struct drm_device *dev,
+				struct drm_master *master)
+{
+	const char *device = dev_name(dev->dev);
+	const char *driver = dev->driver->name;
+	const char *bus = dev->dev->bus->name;
+	int length;
+
+	master->unique_len = strlen(bus) + 1 + strlen(device);
+	master->unique_size = master->unique_len;
+
+	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
+	if (!master->unique)
+		return -ENOMEM;
+
+	snprintf(master->unique, master->unique_len + 1, "%s:%s", bus, device);
+
+	length = strlen(driver) + 1 + master->unique_len;
+
+	dev->devname = kmalloc(length + 1, GFP_KERNEL);
+	if (!dev->devname)
+		return -ENOMEM;
+
+	snprintf(dev->devname, length + 1, "%s@%s", driver, master->unique);
+
+	return 0;
+}
+
+static struct drm_bus drm_host1x_bus = {
+	.bus_type = DRIVER_BUS_HOST1X,
+	.set_busid = drm_host1x_set_busid,
+};
+
+int drm_host1x_init(struct drm_driver *driver, struct host1x_device *device)
+{
+	struct drm_device *drm;
+	int ret;
+
+	INIT_LIST_HEAD(&driver->device_list);
+	driver->bus = &drm_host1x_bus;
+
+	drm = drm_dev_alloc(driver, &device->dev);
+	if (!drm)
+		return -ENOMEM;
+
+	ret = drm_dev_register(drm, 0);
+	if (ret)
+		goto err_free;
+
+	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", driver->name,
+		 driver->major, driver->minor, driver->patchlevel,
+		 driver->date, drm->primary->index);
+
+	return 0;
+
+err_free:
+	drm_dev_free(drm);
+	return ret;
+}
+
+void drm_host1x_exit(struct drm_driver *driver, struct host1x_device *device)
+{
+	struct tegra_drm *tegra = dev_get_drvdata(&device->dev);
+
+	drm_put_dev(tegra->drm);
+}
diff --git a/drivers/gpu/host1x/drm/dc.c b/drivers/gpu/host1x/drm/dc.c
index 5106df08f046..588d4ba0d8cf 100644
--- a/drivers/gpu/host1x/drm/dc.c
+++ b/drivers/gpu/host1x/drm/dc.c
@@ -11,7 +11,6 @@
 #include <linux/clk/tegra.h>
 #include <linux/debugfs.h>
 
-#include "host1x_client.h"
 #include "dc.h"
 #include "drm.h"
 #include "gem.h"
@@ -1040,28 +1039,28 @@ static int tegra_dc_debugfs_exit(struct tegra_dc *dc)
 
 static int tegra_dc_init(struct host1x_client *client)
 {
-	struct tegra_drm_client *drm = to_tegra_drm_client(client);
-	struct tegra_dc *dc = tegra_drm_client_to_dc(drm);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct tegra_dc *dc = host1x_client_to_dc(client);
 	int err;
 
-	dc->pipe = drm->drm->mode_config.num_crtc;
+	dc->pipe = tegra->drm->mode_config.num_crtc;
 
-	drm_crtc_init(drm->drm, &dc->base, &tegra_crtc_funcs);
+	drm_crtc_init(tegra->drm, &dc->base, &tegra_crtc_funcs);
 	drm_mode_crtc_set_gamma_size(&dc->base, 256);
 	drm_crtc_helper_add(&dc->base, &tegra_crtc_helper_funcs);
 
-	err = tegra_dc_rgb_init(drm->drm, dc);
+	err = tegra_dc_rgb_init(tegra->drm, dc);
 	if (err < 0 && err != -ENODEV) {
 		dev_err(dc->dev, "failed to initialize RGB output: %d\n", err);
 		return err;
 	}
 
-	err = tegra_dc_add_planes(drm->drm, dc);
+	err = tegra_dc_add_planes(tegra->drm, dc);
 	if (err < 0)
 		return err;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_dc_debugfs_init(dc, drm->drm->primary);
+		err = tegra_dc_debugfs_init(dc, tegra->drm->primary);
 		if (err < 0)
 			dev_err(dc->dev, "debugfs setup failed: %d\n", err);
 	}
@@ -1079,8 +1078,7 @@ static int tegra_dc_init(struct host1x_client *client)
 
 static int tegra_dc_exit(struct host1x_client *client)
 {
-	struct tegra_drm_client *drm = to_tegra_drm_client(client);
-	struct tegra_dc *dc = tegra_drm_client_to_dc(drm);
+	struct tegra_dc *dc = host1x_client_to_dc(client);
 	int err;
 
 	devm_free_irq(dc->dev, dc->irq, dc);
@@ -1107,7 +1105,6 @@ static const struct host1x_client_ops dc_client_ops = {
 
 static int tegra_dc_probe(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct resource *regs;
 	struct tegra_dc *dc;
 	int err;
@@ -1141,9 +1138,9 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	INIT_LIST_HEAD(&dc->client.base.list);
-	dc->client.base.ops = &dc_client_ops;
-	dc->client.base.dev = &pdev->dev;
+	INIT_LIST_HEAD(&dc->client.list);
+	dc->client.ops = &dc_client_ops;
+	dc->client.dev = &pdev->dev;
 
 	err = tegra_dc_rgb_probe(dc);
 	if (err < 0 && err != -ENODEV) {
@@ -1151,7 +1148,7 @@ static int tegra_dc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = host1x_register_client(tegra, &dc->client.base);
+	err = host1x_client_register(&dc->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
@@ -1165,11 +1162,10 @@ static int tegra_dc_probe(struct platform_device *pdev)
 
 static int tegra_dc_remove(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct tegra_dc *dc = platform_get_drvdata(pdev);
 	int err;
 
-	err = host1x_unregister_client(tegra, &dc->client.base);
+	err = host1x_client_unregister(&dc->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
diff --git a/drivers/gpu/host1x/drm/drm.c b/drivers/gpu/host1x/drm/drm.c
index 1abcdbc7f4cd..c2db409bbd63 100644
--- a/drivers/gpu/host1x/drm/drm.c
+++ b/drivers/gpu/host1x/drm/drm.c
@@ -7,7 +7,8 @@
  * published by the Free Software Foundation.
  */
 
-#include "host1x_client.h"
+#include <linux/host1x.h>
+
 #include "drm.h"
 #include "gem.h"
 
@@ -22,239 +23,25 @@ struct tegra_drm_file {
 	struct list_head contexts;
 };
 
-struct host1x_subdev {
-	struct host1x_client *client;
-	struct device_node *np;
-	struct list_head list;
-};
-
-static int host1x_subdev_add(struct tegra_drm *tegra, struct device_node *np)
-{
-	struct host1x_subdev *subdev;
-
-	subdev = kzalloc(sizeof(*subdev), GFP_KERNEL);
-	if (!subdev)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&subdev->list);
-	subdev->np = of_node_get(np);
-
-	list_add_tail(&subdev->list, &tegra->subdevs);
-
-	return 0;
-}
-
-static int host1x_subdev_register(struct tegra_drm *tegra,
-				  struct host1x_subdev *subdev,
-				  struct host1x_client *client)
-{
-	mutex_lock(&tegra->subdevs_lock);
-	list_del_init(&subdev->list);
-	list_add_tail(&subdev->list, &tegra->active);
-	subdev->client = client;
-	mutex_unlock(&tegra->subdevs_lock);
-
-	return 0;
-}
-
-static int host1x_subdev_unregister(struct tegra_drm *tegra,
-				    struct host1x_subdev *subdev)
-{
-	mutex_lock(&tegra->subdevs_lock);
-	list_del_init(&subdev->list);
-	mutex_unlock(&tegra->subdevs_lock);
-
-	of_node_put(subdev->np);
-	kfree(subdev);
-
-	return 0;
-}
-
-static int tegra_parse_dt(struct tegra_drm *tegra)
-{
-	static const char * const compat[] = {
-		"nvidia,tegra20-dc",
-		"nvidia,tegra20-hdmi",
-		"nvidia,tegra20-gr2d",
-		"nvidia,tegra30-dc",
-		"nvidia,tegra30-hdmi",
-		"nvidia,tegra30-gr2d",
-	};
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < ARRAY_SIZE(compat); i++) {
-		struct device_node *np;
-
-		for_each_child_of_node(tegra->dev->of_node, np) {
-			if (of_device_is_compatible(np, compat[i]) &&
-			    of_device_is_available(np)) {
-				err = host1x_subdev_add(tegra, np);
-				if (err < 0)
-					return err;
-			}
-		}
-	}
-
-	return 0;
-}
-
-int tegra_drm_alloc(struct platform_device *pdev)
+static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 {
+	struct host1x_device *device = to_host1x_device(drm->dev);
 	struct tegra_drm *tegra;
 	int err;
 
-	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
+	tegra = kzalloc(sizeof(*tegra), GFP_KERNEL);
 	if (!tegra)
 		return -ENOMEM;
 
-	mutex_init(&tegra->subdevs_lock);
-	INIT_LIST_HEAD(&tegra->subdevs);
-	INIT_LIST_HEAD(&tegra->active);
+	dev_set_drvdata(drm->dev, tegra);
 	mutex_init(&tegra->clients_lock);
 	INIT_LIST_HEAD(&tegra->clients);
-	tegra->dev = &pdev->dev;
-
-	err = tegra_parse_dt(tegra);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to parse DT: %d\n", err);
-		return err;
-	}
-
-	host1x_set_drm_data(&pdev->dev, tegra);
-
-	return 0;
-}
-
-int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm)
-{
-	struct host1x_client *client;
-	int err;
-
-	mutex_lock(&tegra->clients_lock);
-
-	list_for_each_entry(client, &tegra->clients, list) {
-		struct tegra_drm_client *tdc = to_tegra_drm_client(client);
-
-		/* associate client with DRM device */
-		tdc->drm = drm;
-
-		if (client->ops && client->ops->init) {
-			err = client->ops->init(client);
-			if (err < 0) {
-				dev_err(tegra->dev,
-					"DRM setup failed for %s: %d\n",
-					dev_name(client->dev), err);
-				mutex_unlock(&tegra->clients_lock);
-				return err;
-			}
-		}
-	}
-
-	mutex_unlock(&tegra->clients_lock);
-
-	return 0;
-}
-
-int tegra_drm_exit(struct tegra_drm *tegra)
-{
-	struct host1x_client *client;
-	struct platform_device *pdev;
-	int err;
-
-	if (!tegra->drm)
-		return 0;
-
-	mutex_lock(&tegra->clients_lock);
-
-	list_for_each_entry_reverse(client, &tegra->clients, list) {
-		if (client->ops && client->ops->exit) {
-			err = client->ops->exit(client);
-			if (err < 0) {
-				dev_err(tegra->dev,
-					"DRM cleanup failed for %s: %d\n",
-					dev_name(client->dev), err);
-				mutex_unlock(&tegra->clients_lock);
-				return err;
-			}
-		}
-	}
-
-	mutex_unlock(&tegra->clients_lock);
-
-	pdev = to_platform_device(tegra->dev);
-	drm_platform_exit(&tegra_drm_driver, pdev);
-	tegra->drm = NULL;
-
-	return 0;
-}
-
-int host1x_register_client(struct tegra_drm *tegra,
-			   struct host1x_client *client)
-{
-	struct host1x_subdev *subdev, *tmp;
-	int err;
-
-	mutex_lock(&tegra->clients_lock);
-	list_add_tail(&client->list, &tegra->clients);
-	mutex_unlock(&tegra->clients_lock);
-
-	list_for_each_entry_safe(subdev, tmp, &tegra->subdevs, list)
-		if (subdev->np == client->dev->of_node)
-			host1x_subdev_register(tegra, subdev, client);
-
-	if (list_empty(&tegra->subdevs)) {
-		struct platform_device *pdev = to_platform_device(tegra->dev);
-
-		err = drm_platform_init(&tegra_drm_driver, pdev);
-		if (err < 0) {
-			dev_err(tegra->dev, "drm_platform_init(): %d\n", err);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-int host1x_unregister_client(struct tegra_drm *tegra,
-			     struct host1x_client *client)
-{
-	struct host1x_subdev *subdev, *tmp;
-	int err;
-
-	list_for_each_entry_safe(subdev, tmp, &tegra->active, list) {
-		if (subdev->client == client) {
-			err = tegra_drm_exit(tegra);
-			if (err < 0) {
-				dev_err(tegra->dev, "tegra_drm_exit(): %d\n",
-					err);
-				return err;
-			}
-
-			host1x_subdev_unregister(tegra, subdev);
-			break;
-		}
-	}
-
-	mutex_lock(&tegra->clients_lock);
-	list_del_init(&client->list);
-	mutex_unlock(&tegra->clients_lock);
-
-	return 0;
-}
-
-static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
-{
-	struct tegra_drm *tegra;
-	int err;
-
-	tegra = host1x_get_drm_data(drm->dev);
 	drm->dev_private = tegra;
 	tegra->drm = drm;
 
 	drm_mode_config_init(drm);
 
-	err = tegra_drm_init(tegra, drm);
+	err = host1x_device_init(device);
 	if (err < 0)
 		return err;
 
@@ -280,9 +67,16 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 
 static int tegra_drm_unload(struct drm_device *drm)
 {
+	struct host1x_device *device = to_host1x_device(drm->dev);
+	int err;
+
 	drm_kms_helper_poll_fini(drm);
 	tegra_drm_fb_exit(drm);
 
+	err = host1x_device_exit(device);
+	if (err < 0)
+		return err;
+
 	drm_mode_config_cleanup(drm);
 
 	return 0;
@@ -370,10 +164,11 @@ static int tegra_gem_mmap(struct drm_device *drm, void *data,
 static int tegra_syncpt_read(struct drm_device *drm, void *data,
 			     struct drm_file *file)
 {
+	struct host1x *host = dev_get_drvdata(drm->dev->parent);
 	struct drm_tegra_syncpt_read *args = data;
-	struct host1x *host = dev_get_drvdata(drm->dev);
-	struct host1x_syncpt *sp = host1x_syncpt_get(host, args->id);
+	struct host1x_syncpt *sp;
 
+	sp = host1x_syncpt_get(host, args->id);
 	if (!sp)
 		return -EINVAL;
 
@@ -384,10 +179,11 @@ static int tegra_syncpt_read(struct drm_device *drm, void *data,
 static int tegra_syncpt_incr(struct drm_device *drm, void *data,
 			     struct drm_file *file)
 {
+	struct host1x *host1x = dev_get_drvdata(drm->dev->parent);
 	struct drm_tegra_syncpt_incr *args = data;
-	struct host1x *host = dev_get_drvdata(drm->dev);
-	struct host1x_syncpt *sp = host1x_syncpt_get(host, args->id);
+	struct host1x_syncpt *sp;
 
+	sp = host1x_syncpt_get(host1x, args->id);
 	if (!sp)
 		return -EINVAL;
 
@@ -397,10 +193,11 @@ static int tegra_syncpt_incr(struct drm_device *drm, void *data,
 static int tegra_syncpt_wait(struct drm_device *drm, void *data,
 			     struct drm_file *file)
 {
+	struct host1x *host1x = dev_get_drvdata(drm->dev->parent);
 	struct drm_tegra_syncpt_wait *args = data;
-	struct host1x *host = dev_get_drvdata(drm->dev);
-	struct host1x_syncpt *sp = host1x_syncpt_get(host, args->id);
+	struct host1x_syncpt *sp;
 
+	sp = host1x_syncpt_get(host1x, args->id);
 	if (!sp)
 		return -EINVAL;
 
@@ -422,7 +219,7 @@ static int tegra_open_channel(struct drm_device *drm, void *data,
 	if (!context)
 		return -ENOMEM;
 
-	list_for_each_entry(client, &tegra->clients, base.list)
+	list_for_each_entry(client, &tegra->clients, list)
 		if (client->base.class == args->client) {
 			err = client->ops->open_channel(client, context);
 			if (err)
@@ -441,8 +238,8 @@ static int tegra_open_channel(struct drm_device *drm, void *data,
 static int tegra_close_channel(struct drm_device *drm, void *data,
 			       struct drm_file *file)
 {
-	struct drm_tegra_close_channel *args = data;
 	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_close_channel *args = data;
 	struct tegra_drm_context *context;
 
 	context = tegra_drm_get_context(args->context);
@@ -652,3 +449,97 @@ struct drm_driver tegra_drm_driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
+
+int tegra_drm_register_client(struct tegra_drm *tegra,
+			      struct tegra_drm_client *client)
+{
+	mutex_lock(&tegra->clients_lock);
+	list_add_tail(&client->list, &tegra->clients);
+	mutex_unlock(&tegra->clients_lock);
+
+	return 0;
+}
+
+int tegra_drm_unregister_client(struct tegra_drm *tegra,
+				struct tegra_drm_client *client)
+{
+	mutex_lock(&tegra->clients_lock);
+	list_del_init(&client->list);
+	mutex_unlock(&tegra->clients_lock);
+
+	return 0;
+}
+
+static int host1x_drm_probe(struct host1x_device *device)
+{
+	return drm_host1x_init(&tegra_drm_driver, device);
+}
+
+static int host1x_drm_remove(struct host1x_device *device)
+{
+	drm_host1x_exit(&tegra_drm_driver, device);
+
+	return 0;
+}
+
+static const struct of_device_id host1x_drm_subdevs[] = {
+	{ .compatible = "nvidia,tegra20-dc", },
+	{ .compatible = "nvidia,tegra20-hdmi", },
+	{ .compatible = "nvidia,tegra20-gr2d", },
+	{ .compatible = "nvidia,tegra30-dc", },
+	{ .compatible = "nvidia,tegra30-hdmi", },
+	{ .compatible = "nvidia,tegra30-gr2d", },
+	{ /* sentinel */ }
+};
+
+static struct host1x_driver host1x_drm_driver = {
+	.name = "drm",
+	.probe = host1x_drm_probe,
+	.remove = host1x_drm_remove,
+	.subdevs = host1x_drm_subdevs,
+};
+
+static int __init host1x_drm_init(void)
+{
+	int err;
+
+	err = host1x_driver_register(&host1x_drm_driver);
+	if (err < 0)
+		return err;
+
+	err = platform_driver_register(&tegra_dc_driver);
+	if (err < 0)
+		goto unregister_host1x;
+
+	err = platform_driver_register(&tegra_hdmi_driver);
+	if (err < 0)
+		goto unregister_dc;
+
+	err = platform_driver_register(&tegra_gr2d_driver);
+	if (err < 0)
+		goto unregister_hdmi;
+
+	return 0;
+
+unregister_hdmi:
+	platform_driver_unregister(&tegra_hdmi_driver);
+unregister_dc:
+	platform_driver_unregister(&tegra_dc_driver);
+unregister_host1x:
+	host1x_driver_unregister(&host1x_drm_driver);
+	return err;
+}
+module_init(host1x_drm_init);
+
+static void __exit host1x_drm_exit(void)
+{
+	platform_driver_unregister(&tegra_gr2d_driver);
+	platform_driver_unregister(&tegra_hdmi_driver);
+	platform_driver_unregister(&tegra_dc_driver);
+	host1x_driver_unregister(&host1x_drm_driver);
+}
+module_exit(host1x_drm_exit);
+
+MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
+MODULE_DESCRIPTION("NVIDIA Tegra DRM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/host1x/drm/drm.h b/drivers/gpu/host1x/drm/drm.h
index 8c26c6b1f5e1..25522e23c7b8 100644
--- a/drivers/gpu/host1x/drm/drm.h
+++ b/drivers/gpu/host1x/drm/drm.h
@@ -32,11 +32,6 @@ struct tegra_fbdev {
 
 struct tegra_drm {
 	struct drm_device *drm;
-	struct device *dev;
-
-	struct mutex subdevs_lock;
-	struct list_head subdevs;
-	struct list_head active;
 
 	struct mutex clients_lock;
 	struct list_head clients;
@@ -63,29 +58,29 @@ struct tegra_drm_client_ops {
 
 struct tegra_drm_client {
 	struct host1x_client base;
-	struct drm_device *drm;
+	struct list_head list;
 
 	const struct tegra_drm_client_ops *ops;
 };
 
 static inline struct tegra_drm_client *
-to_tegra_drm_client(struct host1x_client *client)
+host1x_to_drm_client(struct host1x_client *client)
 {
 	return container_of(client, struct tegra_drm_client, base);
 }
 
+extern int tegra_drm_register_client(struct tegra_drm *tegra,
+				     struct tegra_drm_client *client);
+extern int tegra_drm_unregister_client(struct tegra_drm *tegra,
+				       struct tegra_drm_client *client);
+
 extern int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm);
 extern int tegra_drm_exit(struct tegra_drm *tegra);
 
-extern int host1x_register_client(struct tegra_drm *tegra,
-				  struct host1x_client *client);
-extern int host1x_unregister_client(struct tegra_drm *tegra,
-				    struct host1x_client *client);
-
 struct tegra_output;
 
 struct tegra_dc {
-	struct tegra_drm_client client;
+	struct host1x_client client;
 	struct device *dev;
 	spinlock_t lock;
 
@@ -109,7 +104,7 @@ struct tegra_dc {
 };
 
 static inline struct tegra_dc *
-tegra_drm_client_to_dc(struct tegra_drm_client *client)
+host1x_client_to_dc(struct host1x_client *client)
 {
 	return container_of(client, struct tegra_dc, client);
 }
@@ -235,6 +230,10 @@ static inline int tegra_output_check_mode(struct tegra_output *output,
 	return output ? -ENOSYS : -EINVAL;
 }
 
+/* from bus.c */
+int drm_host1x_init(struct drm_driver *driver, struct host1x_device *device);
+void drm_host1x_exit(struct drm_driver *driver, struct host1x_device *device);
+
 /* from rgb.c */
 extern int tegra_dc_rgb_probe(struct tegra_dc *dc);
 extern int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc);
@@ -252,6 +251,8 @@ extern int tegra_drm_fb_init(struct drm_device *drm);
 extern void tegra_drm_fb_exit(struct drm_device *drm);
 extern void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev);
 
-extern struct drm_driver tegra_drm_driver;
+extern struct platform_driver tegra_dc_driver;
+extern struct platform_driver tegra_hdmi_driver;
+extern struct platform_driver tegra_gr2d_driver;
 
 #endif /* HOST1X_DRM_H */
diff --git a/drivers/gpu/host1x/drm/gr2d.c b/drivers/gpu/host1x/drm/gr2d.c
index dfb822428ca0..4e407e30da1c 100644
--- a/drivers/gpu/host1x/drm/gr2d.c
+++ b/drivers/gpu/host1x/drm/gr2d.c
@@ -16,7 +16,6 @@
 
 #include <linux/clk.h>
 
-#include "host1x_client.h"
 #include "drm.h"
 #include "gem.h"
 
@@ -35,19 +34,45 @@ static inline struct gr2d *to_gr2d(struct tegra_drm_client *client)
 	return container_of(client, struct gr2d, client);
 }
 
-static int gr2d_client_init(struct host1x_client *client)
+static int gr2d_init(struct host1x_client *client)
 {
-	return 0;
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct gr2d *gr2d = to_gr2d(drm);
+
+	gr2d->channel = host1x_channel_request(client->dev);
+	if (!gr2d->channel)
+		return -ENOMEM;
+
+	client->syncpts[0] = host1x_syncpt_request(client->dev, false);
+	if (!client->syncpts[0]) {
+		host1x_channel_free(gr2d->channel);
+		return -ENOMEM;
+	}
+
+	return tegra_drm_register_client(tegra, drm);
 }
 
-static int gr2d_client_exit(struct host1x_client *client)
+static int gr2d_exit(struct host1x_client *client)
 {
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct gr2d *gr2d = to_gr2d(drm);
+	int err;
+
+	err = tegra_drm_unregister_client(tegra, drm);
+	if (err < 0)
+		return err;
+
+	host1x_syncpt_free(client->syncpts[0]);
+	host1x_channel_free(gr2d->channel);
+
 	return 0;
 }
 
 static const struct host1x_client_ops gr2d_client_ops = {
-	.init = gr2d_client_init,
-	.exit = gr2d_client_exit,
+	.init = gr2d_init,
+	.exit = gr2d_exit,
 };
 
 static int gr2d_open_channel(struct tegra_drm_client *client,
@@ -240,7 +265,6 @@ static const u32 gr2d_addr_regs[] = {
 
 static int gr2d_probe(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct device *dev = &pdev->dev;
 	struct host1x_syncpt **syncpts;
 	struct gr2d *gr2d;
@@ -267,25 +291,17 @@ static int gr2d_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	gr2d->channel = host1x_channel_request(dev);
-	if (!gr2d->channel)
-		return -ENOMEM;
-
-	*syncpts = host1x_syncpt_request(dev, false);
-	if (!(*syncpts)) {
-		host1x_channel_free(gr2d->channel);
-		return -ENOMEM;
-	}
-
 	INIT_LIST_HEAD(&gr2d->client.base.list);
 	gr2d->client.base.ops = &gr2d_client_ops;
 	gr2d->client.base.dev = dev;
 	gr2d->client.base.class = HOST1X_CLASS_GR2D;
 	gr2d->client.base.syncpts = syncpts;
 	gr2d->client.base.num_syncpts = 1;
+
+	INIT_LIST_HEAD(&gr2d->client.list);
 	gr2d->client.ops = &gr2d_ops;
 
-	err = host1x_register_client(tegra, &gr2d->client.base);
+	err = host1x_client_register(&gr2d->client.base);
 	if (err < 0) {
 		dev_err(dev, "failed to register host1x client: %d\n", err);
 		return err;
@@ -302,22 +318,16 @@ static int gr2d_probe(struct platform_device *pdev)
 
 static int gr2d_remove(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct gr2d *gr2d = platform_get_drvdata(pdev);
-	unsigned int i;
 	int err;
 
-	err = host1x_unregister_client(tegra, &gr2d->client.base);
+	err = host1x_client_unregister(&gr2d->client.base);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
 		return err;
 	}
 
-	for (i = 0; i < gr2d->client.base.num_syncpts; i++)
-		host1x_syncpt_free(gr2d->client.base.syncpts[i]);
-
-	host1x_channel_free(gr2d->channel);
 	clk_disable_unprepare(gr2d->clk);
 
 	return 0;
diff --git a/drivers/gpu/host1x/drm/hdmi.c b/drivers/gpu/host1x/drm/hdmi.c
index a2370045993c..f5663d15670b 100644
--- a/drivers/gpu/host1x/drm/hdmi.c
+++ b/drivers/gpu/host1x/drm/hdmi.c
@@ -13,13 +13,12 @@
 #include <linux/hdmi.h>
 #include <linux/regulator/consumer.h>
 
-#include "host1x_client.h"
 #include "hdmi.h"
 #include "drm.h"
 #include "dc.h"
 
 struct tegra_hdmi {
-	struct tegra_drm_client client;
+	struct host1x_client client;
 	struct tegra_output output;
 	struct device *dev;
 
@@ -43,7 +42,7 @@ struct tegra_hdmi {
 };
 
 static inline struct tegra_hdmi *
-tegra_drm_client_to_hdmi(struct tegra_drm_client *client)
+host1x_client_to_hdmi(struct host1x_client *client)
 {
 	return container_of(client, struct tegra_hdmi, client);
 }
@@ -1118,22 +1117,22 @@ static int tegra_hdmi_debugfs_exit(struct tegra_hdmi *hdmi)
 
 static int tegra_hdmi_init(struct host1x_client *client)
 {
-	struct tegra_drm_client *drm = to_tegra_drm_client(client);
-	struct tegra_hdmi *hdmi = tegra_drm_client_to_hdmi(drm);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
 	int err;
 
 	hdmi->output.type = TEGRA_OUTPUT_HDMI;
 	hdmi->output.dev = client->dev;
 	hdmi->output.ops = &hdmi_ops;
 
-	err = tegra_output_init(drm->drm, &hdmi->output);
+	err = tegra_output_init(tegra->drm, &hdmi->output);
 	if (err < 0) {
 		dev_err(client->dev, "output setup failed: %d\n", err);
 		return err;
 	}
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_hdmi_debugfs_init(hdmi, drm->drm->primary);
+		err = tegra_hdmi_debugfs_init(hdmi, tegra->drm->primary);
 		if (err < 0)
 			dev_err(client->dev, "debugfs setup failed: %d\n", err);
 	}
@@ -1143,8 +1142,7 @@ static int tegra_hdmi_init(struct host1x_client *client)
 
 static int tegra_hdmi_exit(struct host1x_client *client)
 {
-	struct tegra_drm_client *drm = to_tegra_drm_client(client);
-	struct tegra_hdmi *hdmi = tegra_drm_client_to_hdmi(drm);
+	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
 	int err;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
@@ -1176,7 +1174,6 @@ static const struct host1x_client_ops hdmi_client_ops = {
 
 static int tegra_hdmi_probe(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct tegra_hdmi *hdmi;
 	struct resource *regs;
 	int err;
@@ -1247,11 +1244,11 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 
 	hdmi->irq = err;
 
-	INIT_LIST_HEAD(&hdmi->client.base.list);
-	hdmi->client.base.ops = &hdmi_client_ops;
-	hdmi->client.base.dev = &pdev->dev;
+	INIT_LIST_HEAD(&hdmi->client.list);
+	hdmi->client.ops = &hdmi_client_ops;
+	hdmi->client.dev = &pdev->dev;
 
-	err = host1x_register_client(tegra, &hdmi->client.base);
+	err = host1x_client_register(&hdmi->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
 			err);
@@ -1265,11 +1262,10 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 
 static int tegra_hdmi_remove(struct platform_device *pdev)
 {
-	struct tegra_drm *tegra = host1x_get_drm_data(pdev->dev.parent);
 	struct tegra_hdmi *hdmi = platform_get_drvdata(pdev);
 	int err;
 
-	err = host1x_unregister_client(tegra, &hdmi->client.base);
+	err = host1x_client_unregister(&hdmi->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
 			err);
diff --git a/drivers/gpu/host1x/host1x_client.h b/drivers/gpu/host1x/host1x_client.h
deleted file mode 100644
index 6a0bd0268042..000000000000
--- a/drivers/gpu/host1x/host1x_client.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (c) 2013, NVIDIA Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef HOST1X_CLIENT_H
-#define HOST1X_CLIENT_H
-
-struct device;
-struct platform_device;
-
-#ifdef CONFIG_DRM_TEGRA
-int tegra_drm_alloc(struct platform_device *pdev);
-#else
-static inline int tegra_drm_alloc(struct platform_device *pdev)
-{
-	return 0;
-}
-#endif
-
-void host1x_set_drm_data(struct device *dev, void *data);
-void *host1x_get_drm_data(struct device *dev);
-
-#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 2b954adf5bd4..ffd8ad92cdf9 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -150,6 +150,7 @@ int drm_err(const char *func, const char *format, ...);
 #define DRIVER_BUS_PCI 0x1
 #define DRIVER_BUS_PLATFORM 0x2
 #define DRIVER_BUS_USB 0x3
+#define DRIVER_BUS_HOST1X 0x4
 
 /***********************************************************************/
 /** \name Begin the DRM... */
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 7442f2a57039..e62c61a4afa9 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -19,7 +19,7 @@
 #ifndef __LINUX_HOST1X_H
 #define __LINUX_HOST1X_H
 
-#include <linux/kref.h>
+#include <linux/device.h>
 #include <linux/types.h>
 
 enum host1x_class {
@@ -37,6 +37,7 @@ struct host1x_client_ops {
 
 struct host1x_client {
 	struct list_head list;
+	struct device *parent;
 	struct device *dev;
 
 	const struct host1x_client_ops *ops;
@@ -230,4 +231,46 @@ void host1x_job_put(struct host1x_job *job);
 int host1x_job_pin(struct host1x_job *job, struct device *dev);
 void host1x_job_unpin(struct host1x_job *job);
 
+/*
+ * subdevice probe infrastructure
+ */
+
+struct host1x_device;
+
+struct host1x_driver {
+	const struct of_device_id *subdevs;
+	struct list_head list;
+	const char *name;
+
+	int (*probe)(struct host1x_device *device);
+	int (*remove)(struct host1x_device *device);
+};
+
+int host1x_driver_register(struct host1x_driver *driver);
+void host1x_driver_unregister(struct host1x_driver *driver);
+
+struct host1x_device {
+	struct host1x_driver *driver;
+	struct list_head list;
+	struct device dev;
+
+	struct mutex subdevs_lock;
+	struct list_head subdevs;
+	struct list_head active;
+
+	struct mutex clients_lock;
+	struct list_head clients;
+};
+
+static inline struct host1x_device *to_host1x_device(struct device *dev)
+{
+	return container_of(dev, struct host1x_device, dev);
+}
+
+int host1x_device_init(struct host1x_device *device);
+int host1x_device_exit(struct host1x_device *device);
+
+int host1x_client_register(struct host1x_client *client);
+int host1x_client_unregister(struct host1x_client *client);
+
 #endif
-- 
cgit 


From 5f60ed0d840d53e9d65aa54e1a5365af8ce2769e Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@avionic-design.de>
Date: Thu, 28 Feb 2013 08:08:01 +0100
Subject: drm/tegra: Add 3D support

Initialize and power the 3D unit on Tegra20, Tegra30 and Tegra114 and
register a channel with the Tegra DRM driver so that the unit can be
used from userspace.

Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/Makefile |   3 +-
 drivers/gpu/drm/tegra/drm.c    |  10 ++
 drivers/gpu/drm/tegra/drm.h    |   1 +
 drivers/gpu/drm/tegra/gr3d.c   | 337 +++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/tegra/gr3d.h   |  27 ++++
 include/linux/host1x.h         |   1 +
 6 files changed, 378 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/tegra/gr3d.c
 create mode 100644 drivers/gpu/drm/tegra/gr3d.h

(limited to 'include')

diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile
index e1cdf1da2778..edc76abd58bb 100644
--- a/drivers/gpu/drm/tegra/Makefile
+++ b/drivers/gpu/drm/tegra/Makefile
@@ -9,6 +9,7 @@ tegra-drm-y := \
 	output.o \
 	rgb.o \
 	hdmi.o \
-	gr2d.o
+	gr2d.o \
+	gr3d.o
 
 obj-$(CONFIG_DRM_TEGRA) += tegra-drm.o
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 6f42f1692f29..26a2903879d8 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -615,10 +615,13 @@ static const struct of_device_id host1x_drm_subdevs[] = {
 	{ .compatible = "nvidia,tegra20-dc", },
 	{ .compatible = "nvidia,tegra20-hdmi", },
 	{ .compatible = "nvidia,tegra20-gr2d", },
+	{ .compatible = "nvidia,tegra20-gr3d", },
 	{ .compatible = "nvidia,tegra30-dc", },
 	{ .compatible = "nvidia,tegra30-hdmi", },
 	{ .compatible = "nvidia,tegra30-gr2d", },
+	{ .compatible = "nvidia,tegra30-gr3d", },
 	{ .compatible = "nvidia,tegra114-hdmi", },
+	{ .compatible = "nvidia,tegra114-gr3d", },
 	{ /* sentinel */ }
 };
 
@@ -649,8 +652,14 @@ static int __init host1x_drm_init(void)
 	if (err < 0)
 		goto unregister_hdmi;
 
+	err = platform_driver_register(&tegra_gr3d_driver);
+	if (err < 0)
+		goto unregister_gr2d;
+
 	return 0;
 
+unregister_gr2d:
+	platform_driver_unregister(&tegra_gr2d_driver);
 unregister_hdmi:
 	platform_driver_unregister(&tegra_hdmi_driver);
 unregister_dc:
@@ -663,6 +672,7 @@ module_init(host1x_drm_init);
 
 static void __exit host1x_drm_exit(void)
 {
+	platform_driver_unregister(&tegra_gr3d_driver);
 	platform_driver_unregister(&tegra_gr2d_driver);
 	platform_driver_unregister(&tegra_hdmi_driver);
 	platform_driver_unregister(&tegra_dc_driver);
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index e3cd3ed438d5..b599fd4650ad 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -261,5 +261,6 @@ extern void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev);
 extern struct platform_driver tegra_dc_driver;
 extern struct platform_driver tegra_hdmi_driver;
 extern struct platform_driver tegra_gr2d_driver;
+extern struct platform_driver tegra_gr3d_driver;
 
 #endif /* HOST1X_DRM_H */
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
new file mode 100644
index 000000000000..dc0f222d1323
--- /dev/null
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2013 Avionic Design GmbH
+ * Copyright (C) 2013 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/host1x.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/tegra-powergate.h>
+
+#include "drm.h"
+#include "gem.h"
+#include "gr3d.h"
+
+struct gr3d {
+	struct tegra_drm_client client;
+	struct host1x_channel *channel;
+	struct clk *clk_secondary;
+	struct clk *clk;
+
+	DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS);
+};
+
+static inline struct gr3d *to_gr3d(struct tegra_drm_client *client)
+{
+	return container_of(client, struct gr3d, client);
+}
+
+static int gr3d_init(struct host1x_client *client)
+{
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct gr3d *gr3d = to_gr3d(drm);
+
+	gr3d->channel = host1x_channel_request(client->dev);
+	if (!gr3d->channel)
+		return -ENOMEM;
+
+	client->syncpts[0] = host1x_syncpt_request(client->dev, 0);
+	if (!client->syncpts[0]) {
+		host1x_channel_free(gr3d->channel);
+		return -ENOMEM;
+	}
+
+	return tegra_drm_register_client(tegra, drm);
+}
+
+static int gr3d_exit(struct host1x_client *client)
+{
+	struct tegra_drm_client *drm = host1x_to_drm_client(client);
+	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct gr3d *gr3d = to_gr3d(drm);
+	int err;
+
+	err = tegra_drm_unregister_client(tegra, drm);
+	if (err < 0)
+		return err;
+
+	host1x_syncpt_free(client->syncpts[0]);
+	host1x_channel_free(gr3d->channel);
+
+	return 0;
+}
+
+static const struct host1x_client_ops gr3d_client_ops = {
+	.init = gr3d_init,
+	.exit = gr3d_exit,
+};
+
+static int gr3d_open_channel(struct tegra_drm_client *client,
+			     struct tegra_drm_context *context)
+{
+	struct gr3d *gr3d = to_gr3d(client);
+
+	context->channel = host1x_channel_get(gr3d->channel);
+	if (!context->channel)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void gr3d_close_channel(struct tegra_drm_context *context)
+{
+	host1x_channel_put(context->channel);
+}
+
+static int gr3d_is_addr_reg(struct device *dev, u32 class, u32 offset)
+{
+	struct gr3d *gr3d = dev_get_drvdata(dev);
+
+	switch (class) {
+	case HOST1X_CLASS_HOST1X:
+		if (offset == 0x2b)
+			return 1;
+
+		break;
+
+	case HOST1X_CLASS_GR3D:
+		if (offset >= GR3D_NUM_REGS)
+			break;
+
+		if (test_bit(offset, gr3d->addr_regs))
+			return 1;
+
+		break;
+	}
+
+	return 0;
+}
+
+static const struct tegra_drm_client_ops gr3d_ops = {
+	.open_channel = gr3d_open_channel,
+	.close_channel = gr3d_close_channel,
+	.is_addr_reg = gr3d_is_addr_reg,
+	.submit = tegra_drm_submit,
+};
+
+static const struct of_device_id tegra_gr3d_match[] = {
+	{ .compatible = "nvidia,tegra114-gr3d" },
+	{ .compatible = "nvidia,tegra30-gr3d" },
+	{ .compatible = "nvidia,tegra20-gr3d" },
+	{ }
+};
+
+static const u32 gr3d_addr_regs[] = {
+	GR3D_IDX_ATTRIBUTE( 0),
+	GR3D_IDX_ATTRIBUTE( 1),
+	GR3D_IDX_ATTRIBUTE( 2),
+	GR3D_IDX_ATTRIBUTE( 3),
+	GR3D_IDX_ATTRIBUTE( 4),
+	GR3D_IDX_ATTRIBUTE( 5),
+	GR3D_IDX_ATTRIBUTE( 6),
+	GR3D_IDX_ATTRIBUTE( 7),
+	GR3D_IDX_ATTRIBUTE( 8),
+	GR3D_IDX_ATTRIBUTE( 9),
+	GR3D_IDX_ATTRIBUTE(10),
+	GR3D_IDX_ATTRIBUTE(11),
+	GR3D_IDX_ATTRIBUTE(12),
+	GR3D_IDX_ATTRIBUTE(13),
+	GR3D_IDX_ATTRIBUTE(14),
+	GR3D_IDX_ATTRIBUTE(15),
+	GR3D_IDX_INDEX_BASE,
+	GR3D_QR_ZTAG_ADDR,
+	GR3D_QR_CTAG_ADDR,
+	GR3D_QR_CZ_ADDR,
+	GR3D_TEX_TEX_ADDR( 0),
+	GR3D_TEX_TEX_ADDR( 1),
+	GR3D_TEX_TEX_ADDR( 2),
+	GR3D_TEX_TEX_ADDR( 3),
+	GR3D_TEX_TEX_ADDR( 4),
+	GR3D_TEX_TEX_ADDR( 5),
+	GR3D_TEX_TEX_ADDR( 6),
+	GR3D_TEX_TEX_ADDR( 7),
+	GR3D_TEX_TEX_ADDR( 8),
+	GR3D_TEX_TEX_ADDR( 9),
+	GR3D_TEX_TEX_ADDR(10),
+	GR3D_TEX_TEX_ADDR(11),
+	GR3D_TEX_TEX_ADDR(12),
+	GR3D_TEX_TEX_ADDR(13),
+	GR3D_TEX_TEX_ADDR(14),
+	GR3D_TEX_TEX_ADDR(15),
+	GR3D_DW_MEMORY_OUTPUT_ADDRESS,
+	GR3D_GLOBAL_SURFADDR( 0),
+	GR3D_GLOBAL_SURFADDR( 1),
+	GR3D_GLOBAL_SURFADDR( 2),
+	GR3D_GLOBAL_SURFADDR( 3),
+	GR3D_GLOBAL_SURFADDR( 4),
+	GR3D_GLOBAL_SURFADDR( 5),
+	GR3D_GLOBAL_SURFADDR( 6),
+	GR3D_GLOBAL_SURFADDR( 7),
+	GR3D_GLOBAL_SURFADDR( 8),
+	GR3D_GLOBAL_SURFADDR( 9),
+	GR3D_GLOBAL_SURFADDR(10),
+	GR3D_GLOBAL_SURFADDR(11),
+	GR3D_GLOBAL_SURFADDR(12),
+	GR3D_GLOBAL_SURFADDR(13),
+	GR3D_GLOBAL_SURFADDR(14),
+	GR3D_GLOBAL_SURFADDR(15),
+	GR3D_GLOBAL_SPILLSURFADDR,
+	GR3D_GLOBAL_SURFOVERADDR( 0),
+	GR3D_GLOBAL_SURFOVERADDR( 1),
+	GR3D_GLOBAL_SURFOVERADDR( 2),
+	GR3D_GLOBAL_SURFOVERADDR( 3),
+	GR3D_GLOBAL_SURFOVERADDR( 4),
+	GR3D_GLOBAL_SURFOVERADDR( 5),
+	GR3D_GLOBAL_SURFOVERADDR( 6),
+	GR3D_GLOBAL_SURFOVERADDR( 7),
+	GR3D_GLOBAL_SURFOVERADDR( 8),
+	GR3D_GLOBAL_SURFOVERADDR( 9),
+	GR3D_GLOBAL_SURFOVERADDR(10),
+	GR3D_GLOBAL_SURFOVERADDR(11),
+	GR3D_GLOBAL_SURFOVERADDR(12),
+	GR3D_GLOBAL_SURFOVERADDR(13),
+	GR3D_GLOBAL_SURFOVERADDR(14),
+	GR3D_GLOBAL_SURFOVERADDR(15),
+	GR3D_GLOBAL_SAMP01SURFADDR( 0),
+	GR3D_GLOBAL_SAMP01SURFADDR( 1),
+	GR3D_GLOBAL_SAMP01SURFADDR( 2),
+	GR3D_GLOBAL_SAMP01SURFADDR( 3),
+	GR3D_GLOBAL_SAMP01SURFADDR( 4),
+	GR3D_GLOBAL_SAMP01SURFADDR( 5),
+	GR3D_GLOBAL_SAMP01SURFADDR( 6),
+	GR3D_GLOBAL_SAMP01SURFADDR( 7),
+	GR3D_GLOBAL_SAMP01SURFADDR( 8),
+	GR3D_GLOBAL_SAMP01SURFADDR( 9),
+	GR3D_GLOBAL_SAMP01SURFADDR(10),
+	GR3D_GLOBAL_SAMP01SURFADDR(11),
+	GR3D_GLOBAL_SAMP01SURFADDR(12),
+	GR3D_GLOBAL_SAMP01SURFADDR(13),
+	GR3D_GLOBAL_SAMP01SURFADDR(14),
+	GR3D_GLOBAL_SAMP01SURFADDR(15),
+	GR3D_GLOBAL_SAMP23SURFADDR( 0),
+	GR3D_GLOBAL_SAMP23SURFADDR( 1),
+	GR3D_GLOBAL_SAMP23SURFADDR( 2),
+	GR3D_GLOBAL_SAMP23SURFADDR( 3),
+	GR3D_GLOBAL_SAMP23SURFADDR( 4),
+	GR3D_GLOBAL_SAMP23SURFADDR( 5),
+	GR3D_GLOBAL_SAMP23SURFADDR( 6),
+	GR3D_GLOBAL_SAMP23SURFADDR( 7),
+	GR3D_GLOBAL_SAMP23SURFADDR( 8),
+	GR3D_GLOBAL_SAMP23SURFADDR( 9),
+	GR3D_GLOBAL_SAMP23SURFADDR(10),
+	GR3D_GLOBAL_SAMP23SURFADDR(11),
+	GR3D_GLOBAL_SAMP23SURFADDR(12),
+	GR3D_GLOBAL_SAMP23SURFADDR(13),
+	GR3D_GLOBAL_SAMP23SURFADDR(14),
+	GR3D_GLOBAL_SAMP23SURFADDR(15),
+};
+
+static int gr3d_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct host1x_syncpt **syncpts;
+	struct gr3d *gr3d;
+	unsigned int i;
+	int err;
+
+	gr3d = devm_kzalloc(&pdev->dev, sizeof(*gr3d), GFP_KERNEL);
+	if (!gr3d)
+		return -ENOMEM;
+
+	syncpts = devm_kzalloc(&pdev->dev, sizeof(*syncpts), GFP_KERNEL);
+	if (!syncpts)
+		return -ENOMEM;
+
+	gr3d->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(gr3d->clk)) {
+		dev_err(&pdev->dev, "cannot get clock\n");
+		return PTR_ERR(gr3d->clk);
+	}
+
+	if (of_device_is_compatible(np, "nvidia,tegra30-gr3d")) {
+		gr3d->clk_secondary = devm_clk_get(&pdev->dev, "3d2");
+		if (IS_ERR(gr3d->clk)) {
+			dev_err(&pdev->dev, "cannot get secondary clock\n");
+			return PTR_ERR(gr3d->clk);
+		}
+	}
+
+	err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D, gr3d->clk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to power up 3D unit\n");
+		return err;
+	}
+
+	if (gr3d->clk_secondary) {
+		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D1,
+							gr3d->clk_secondary);
+		if (err < 0) {
+			dev_err(&pdev->dev,
+				"failed to power up secondary 3D unit\n");
+			return err;
+		}
+	}
+
+	INIT_LIST_HEAD(&gr3d->client.base.list);
+	gr3d->client.base.ops = &gr3d_client_ops;
+	gr3d->client.base.dev = &pdev->dev;
+	gr3d->client.base.class = HOST1X_CLASS_GR3D;
+	gr3d->client.base.syncpts = syncpts;
+	gr3d->client.base.num_syncpts = 1;
+
+	INIT_LIST_HEAD(&gr3d->client.list);
+	gr3d->client.ops = &gr3d_ops;
+
+	err = host1x_client_register(&gr3d->client.base);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
+			err);
+		return err;
+	}
+
+	/* initialize address register map */
+	for (i = 0; i < ARRAY_SIZE(gr3d_addr_regs); i++)
+		set_bit(gr3d_addr_regs[i], gr3d->addr_regs);
+
+	platform_set_drvdata(pdev, gr3d);
+
+	return 0;
+}
+
+static int gr3d_remove(struct platform_device *pdev)
+{
+	struct gr3d *gr3d = platform_get_drvdata(pdev);
+	int err;
+
+	err = host1x_client_unregister(&gr3d->client.base);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to unregister host1x client: %d\n",
+			err);
+		return err;
+	}
+
+	if (gr3d->clk_secondary) {
+		tegra_powergate_power_off(TEGRA_POWERGATE_3D1);
+		clk_disable_unprepare(gr3d->clk_secondary);
+	}
+
+	tegra_powergate_power_off(TEGRA_POWERGATE_3D);
+	clk_disable_unprepare(gr3d->clk);
+
+	return 0;
+}
+
+struct platform_driver tegra_gr3d_driver = {
+	.driver = {
+		.name = "tegra-gr3d",
+		.of_match_table = tegra_gr3d_match,
+	},
+	.probe = gr3d_probe,
+	.remove = gr3d_remove,
+};
diff --git a/drivers/gpu/drm/tegra/gr3d.h b/drivers/gpu/drm/tegra/gr3d.h
new file mode 100644
index 000000000000..0c30a1351c83
--- /dev/null
+++ b/drivers/gpu/drm/tegra/gr3d.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2013 NVIDIA Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef TEGRA_GR3D_H
+#define TEGRA_GR3D_H
+
+#define GR3D_IDX_ATTRIBUTE(x)		(0x100 + (x) * 2)
+#define GR3D_IDX_INDEX_BASE		0x121
+#define GR3D_QR_ZTAG_ADDR		0x415
+#define GR3D_QR_CTAG_ADDR		0x417
+#define GR3D_QR_CZ_ADDR			0x419
+#define GR3D_TEX_TEX_ADDR(x)		(0x710 + (x))
+#define GR3D_DW_MEMORY_OUTPUT_ADDRESS	0x904
+#define GR3D_GLOBAL_SURFADDR(x)		(0xe00 + (x))
+#define GR3D_GLOBAL_SPILLSURFADDR	0xe2a
+#define GR3D_GLOBAL_SURFOVERADDR(x)	(0xe30 + (x))
+#define GR3D_GLOBAL_SAMP01SURFADDR(x)	(0xe50 + (x))
+#define GR3D_GLOBAL_SAMP23SURFADDR(x)	(0xe60 + (x))
+
+#define GR3D_NUM_REGS			0xe88
+
+#endif
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index e62c61a4afa9..f5dd56fbdc3e 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -26,6 +26,7 @@ enum host1x_class {
 	HOST1X_CLASS_HOST1X = 0x1,
 	HOST1X_CLASS_GR2D = 0x51,
 	HOST1X_CLASS_GR2D_SB = 0x52,
+	HOST1X_CLASS_GR3D = 0x60,
 };
 
 struct host1x_client;
-- 
cgit 


From 773af77fc479fd454c3f6836f86bf63996545cf4 Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@avionic-design.de>
Date: Fri, 4 Oct 2013 22:34:01 +0200
Subject: drm/tegra: Add support for tiled buffer objects

The gr2d and gr3d engines work more efficiently on buffers with a tiled
memory layout. Allow created buffers to be marked as tiled so that the
display controller can scan them out properly.

Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dc.c   | 21 +++++++++++++++++++++
 drivers/gpu/drm/tegra/dc.h   |  4 ++++
 drivers/gpu/drm/tegra/drm.c  |  2 +-
 drivers/gpu/drm/tegra/drm.h  |  2 ++
 drivers/gpu/drm/tegra/fb.c   | 12 +++++++++++-
 drivers/gpu/drm/tegra/gem.c  | 13 ++++++++++---
 drivers/gpu/drm/tegra/gem.h  | 13 +++++++++----
 include/uapi/drm/tegra_drm.h |  2 ++
 8 files changed, 60 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 054ca1b6bd31..c51aaf7555f5 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -47,6 +47,7 @@ static int tegra_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	window.dst.h = crtc_h;
 	window.format = tegra_dc_format(fb->pixel_format);
 	window.bits_per_pixel = fb->bits_per_pixel;
+	window.tiled = tegra_fb_is_tiled(fb);
 
 	for (i = 0; i < drm_format_num_planes(fb->pixel_format); i++) {
 		struct tegra_bo *bo = tegra_fb_get_plane(fb, i);
@@ -157,6 +158,16 @@ static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 	tegra_dc_writel(dc, fb->pitches[0], DC_WIN_LINE_STRIDE);
 	tegra_dc_writel(dc, format, DC_WIN_COLOR_DEPTH);
 
+	if (tegra_fb_is_tiled(fb)) {
+		value = DC_WIN_BUFFER_ADDR_MODE_TILE_UV |
+			DC_WIN_BUFFER_ADDR_MODE_TILE;
+	} else {
+		value = DC_WIN_BUFFER_ADDR_MODE_LINEAR_UV |
+			DC_WIN_BUFFER_ADDR_MODE_LINEAR;
+	}
+
+	tegra_dc_writel(dc, value, DC_WIN_BUFFER_ADDR_MODE);
+
 	value = GENERAL_UPDATE | WIN_A_UPDATE;
 	tegra_dc_writel(dc, value, DC_CMD_STATE_CONTROL);
 
@@ -509,6 +520,16 @@ int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
 	tegra_dc_writel(dc, h_offset, DC_WINBUF_ADDR_H_OFFSET);
 	tegra_dc_writel(dc, v_offset, DC_WINBUF_ADDR_V_OFFSET);
 
+	if (window->tiled) {
+		value = DC_WIN_BUFFER_ADDR_MODE_TILE_UV |
+			DC_WIN_BUFFER_ADDR_MODE_TILE;
+	} else {
+		value = DC_WIN_BUFFER_ADDR_MODE_LINEAR_UV |
+			DC_WIN_BUFFER_ADDR_MODE_LINEAR;
+	}
+
+	tegra_dc_writel(dc, value, DC_WIN_BUFFER_ADDR_MODE);
+
 	value = WIN_ENABLE;
 
 	if (yuv) {
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index 79eaec9aac77..e0b94c26bb86 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -365,6 +365,10 @@
 #define DC_WIN_BUF_STRIDE			0x70b
 #define DC_WIN_UV_BUF_STRIDE			0x70c
 #define DC_WIN_BUFFER_ADDR_MODE			0x70d
+#define DC_WIN_BUFFER_ADDR_MODE_LINEAR		(0 <<  0)
+#define DC_WIN_BUFFER_ADDR_MODE_TILE		(1 <<  0)
+#define DC_WIN_BUFFER_ADDR_MODE_LINEAR_UV	(0 << 16)
+#define DC_WIN_BUFFER_ADDR_MODE_TILE_UV		(1 << 16)
 #define DC_WIN_DV_CONTROL			0x70e
 
 #define DC_WIN_BLEND_NOKEY			0x70f
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 26a2903879d8..ecb6ec735ef1 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -262,7 +262,7 @@ static int tegra_gem_create(struct drm_device *drm, void *data,
 	struct drm_tegra_gem_create *args = data;
 	struct tegra_bo *bo;
 
-	bo = tegra_bo_create_with_handle(file, drm, args->size,
+	bo = tegra_bo_create_with_handle(file, drm, args->size, args->flags,
 					 &args->handle);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index b599fd4650ad..e07a10eedae6 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -148,6 +148,7 @@ struct tegra_dc_window {
 	unsigned int format;
 	unsigned int stride[2];
 	unsigned long base[3];
+	bool tiled;
 };
 
 /* from dc.c */
@@ -254,6 +255,7 @@ extern int tegra_output_exit(struct tegra_output *output);
 /* from fb.c */
 struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 				    unsigned int index);
+bool tegra_fb_is_tiled(struct drm_framebuffer *framebuffer);
 extern int tegra_drm_fb_init(struct drm_device *drm);
 extern void tegra_drm_fb_exit(struct drm_device *drm);
 extern void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev);
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index 1fd4e196b934..fdb00e040046 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -34,6 +34,16 @@ struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 	return fb->planes[index];
 }
 
+bool tegra_fb_is_tiled(struct drm_framebuffer *framebuffer)
+{
+	struct tegra_fb *fb = to_tegra_fb(framebuffer);
+
+	if (fb->planes[0]->flags & TEGRA_BO_TILED)
+		return true;
+
+	return false;
+}
+
 static void tegra_fb_destroy(struct drm_framebuffer *framebuffer)
 {
 	struct tegra_fb *fb = to_tegra_fb(framebuffer);
@@ -188,7 +198,7 @@ static int tegra_fbdev_probe(struct drm_fb_helper *helper,
 
 	size = cmd.pitches[0] * cmd.height;
 
-	bo = tegra_bo_create(drm, size);
+	bo = tegra_bo_create(drm, size, 0);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 267c0c21e5cc..d851ec106cf4 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -18,6 +18,8 @@
  * GNU General Public License for more details.
  */
 
+#include <drm/tegra_drm.h>
+
 #include "gem.h"
 
 static inline struct tegra_bo *host1x_to_tegra_bo(struct host1x_bo *bo)
@@ -97,7 +99,8 @@ static void tegra_bo_destroy(struct drm_device *drm, struct tegra_bo *bo)
 	dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr, bo->paddr);
 }
 
-struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size)
+struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size,
+				 unsigned long flags)
 {
 	struct tegra_bo *bo;
 	int err;
@@ -126,6 +129,9 @@ struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size)
 	if (err)
 		goto err_mmap;
 
+	if (flags & DRM_TEGRA_GEM_CREATE_TILED)
+		bo->flags |= TEGRA_BO_TILED;
+
 	return bo;
 
 err_mmap:
@@ -142,12 +148,13 @@ err_dma:
 struct tegra_bo *tegra_bo_create_with_handle(struct drm_file *file,
 					     struct drm_device *drm,
 					     unsigned int size,
+					     unsigned long flags,
 					     unsigned int *handle)
 {
 	struct tegra_bo *bo;
 	int ret;
 
-	bo = tegra_bo_create(drm, size);
+	bo = tegra_bo_create(drm, size, flags);
 	if (IS_ERR(bo))
 		return bo;
 
@@ -187,7 +194,7 @@ int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 	if (args->size < args->pitch * args->height)
 		args->size = args->pitch * args->height;
 
-	bo = tegra_bo_create_with_handle(file, drm, args->size,
+	bo = tegra_bo_create_with_handle(file, drm, args->size, 0,
 					 &args->handle);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h
index 2b54f1425d5e..c4993fc2c3bd 100644
--- a/drivers/gpu/drm/tegra/gem.h
+++ b/drivers/gpu/drm/tegra/gem.h
@@ -24,9 +24,12 @@
 #include <drm/drm.h>
 #include <drm/drmP.h>
 
+#define TEGRA_BO_TILED (1 << 0)
+
 struct tegra_bo {
 	struct drm_gem_object gem;
 	struct host1x_bo base;
+	unsigned long flags;
 	dma_addr_t paddr;
 	void *vaddr;
 };
@@ -38,11 +41,13 @@ static inline struct tegra_bo *to_tegra_bo(struct drm_gem_object *gem)
 
 extern const struct host1x_bo_ops tegra_bo_ops;
 
-struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size);
+struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size,
+				 unsigned long flags);
 struct tegra_bo *tegra_bo_create_with_handle(struct drm_file *file,
-					    struct drm_device *drm,
-					    unsigned int size,
-					    unsigned int *handle);
+					     struct drm_device *drm,
+					     unsigned int size,
+					     unsigned long flags,
+					     unsigned int *handle);
 void tegra_bo_free_object(struct drm_gem_object *gem);
 int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm,
 			 struct drm_mode_create_dumb *args);
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 73bde4eaf16c..6b420029a645 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -19,6 +19,8 @@
 
 #include <drm/drm.h>
 
+#define DRM_TEGRA_GEM_CREATE_TILED (1 << 0)
+
 struct drm_tegra_gem_create {
 	__u64 size;
 	__u32 flags;
-- 
cgit 


From db7fbdfd25ee009165b6c3b80a9d1c6d8534ad94 Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@avionic-design.de>
Date: Mon, 7 Oct 2013 09:47:58 +0200
Subject: drm/tegra: Support bottom-up buffer objects

The gr3d engine renders images bottom-up. Allow buffers that are used
for 3D content to be marked as such and implement support in the display
controller to present them properly.

Signed-off-by: Thierry Reding <thierry.reding@avionic-design.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/dc.c   | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/tegra/dc.h   |  1 +
 drivers/gpu/drm/tegra/drm.h  |  2 ++
 drivers/gpu/drm/tegra/fb.c   | 10 ++++++++++
 drivers/gpu/drm/tegra/gem.c  |  3 +++
 drivers/gpu/drm/tegra/gem.h  |  3 ++-
 include/uapi/drm/tegra_drm.h |  3 ++-
 7 files changed, 44 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c51aaf7555f5..ae1cb31ead7e 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -47,6 +47,7 @@ static int tegra_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	window.dst.h = crtc_h;
 	window.format = tegra_dc_format(fb->pixel_format);
 	window.bits_per_pixel = fb->bits_per_pixel;
+	window.bottom_up = tegra_fb_is_bottom_up(fb);
 	window.tiled = tegra_fb_is_tiled(fb);
 
 	for (i = 0; i < drm_format_num_planes(fb->pixel_format); i++) {
@@ -147,6 +148,7 @@ static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 {
 	unsigned int format = tegra_dc_format(fb->pixel_format);
 	struct tegra_bo *bo = tegra_fb_get_plane(fb, 0);
+	unsigned int h_offset = 0, v_offset = 0;
 	unsigned long value;
 
 	tegra_dc_writel(dc, WINDOW_A_SELECT, DC_CMD_DISPLAY_WINDOW_HEADER);
@@ -168,6 +170,22 @@ static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 
 	tegra_dc_writel(dc, value, DC_WIN_BUFFER_ADDR_MODE);
 
+	/* make sure bottom-up buffers are properly displayed */
+	if (tegra_fb_is_bottom_up(fb)) {
+		value = tegra_dc_readl(dc, DC_WIN_WIN_OPTIONS);
+		value |= INVERT_V;
+		tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
+
+		v_offset += fb->height - 1;
+	} else {
+		value = tegra_dc_readl(dc, DC_WIN_WIN_OPTIONS);
+		value &= ~INVERT_V;
+		tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
+	}
+
+	tegra_dc_writel(dc, h_offset, DC_WINBUF_ADDR_H_OFFSET);
+	tegra_dc_writel(dc, v_offset, DC_WINBUF_ADDR_V_OFFSET);
+
 	value = GENERAL_UPDATE | WIN_A_UPDATE;
 	tegra_dc_writel(dc, value, DC_CMD_STATE_CONTROL);
 
@@ -517,6 +535,9 @@ int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
 		tegra_dc_writel(dc, window->stride[0], DC_WIN_LINE_STRIDE);
 	}
 
+	if (window->bottom_up)
+		v_offset += window->src.h - 1;
+
 	tegra_dc_writel(dc, h_offset, DC_WINBUF_ADDR_H_OFFSET);
 	tegra_dc_writel(dc, v_offset, DC_WINBUF_ADDR_V_OFFSET);
 
@@ -548,6 +569,9 @@ int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
 		value |= COLOR_EXPAND;
 	}
 
+	if (window->bottom_up)
+		value |= INVERT_V;
+
 	tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
 
 	/*
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index e0b94c26bb86..91bbda291470 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -302,6 +302,7 @@
 #define DC_WIN_CSC_KVB				0x618
 
 #define DC_WIN_WIN_OPTIONS			0x700
+#define INVERT_V     (1 <<  2)
 #define COLOR_EXPAND (1 <<  6)
 #define CSC_ENABLE   (1 << 18)
 #define WIN_ENABLE   (1 << 30)
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index e07a10eedae6..fdfe259ed7f8 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -148,6 +148,7 @@ struct tegra_dc_window {
 	unsigned int format;
 	unsigned int stride[2];
 	unsigned long base[3];
+	bool bottom_up;
 	bool tiled;
 };
 
@@ -255,6 +256,7 @@ extern int tegra_output_exit(struct tegra_output *output);
 /* from fb.c */
 struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 				    unsigned int index);
+bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer);
 bool tegra_fb_is_tiled(struct drm_framebuffer *framebuffer);
 extern int tegra_drm_fb_init(struct drm_device *drm);
 extern void tegra_drm_fb_exit(struct drm_device *drm);
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index fdb00e040046..490f7719e317 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -34,6 +34,16 @@ struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 	return fb->planes[index];
 }
 
+bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer)
+{
+	struct tegra_fb *fb = to_tegra_fb(framebuffer);
+
+	if (fb->planes[0]->flags & TEGRA_BO_BOTTOM_UP)
+		return true;
+
+	return false;
+}
+
 bool tegra_fb_is_tiled(struct drm_framebuffer *framebuffer)
 {
 	struct tegra_fb *fb = to_tegra_fb(framebuffer);
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index d851ec106cf4..28a9cbc07ab9 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -132,6 +132,9 @@ struct tegra_bo *tegra_bo_create(struct drm_device *drm, unsigned int size,
 	if (flags & DRM_TEGRA_GEM_CREATE_TILED)
 		bo->flags |= TEGRA_BO_TILED;
 
+	if (flags & DRM_TEGRA_GEM_CREATE_BOTTOM_UP)
+		bo->flags |= TEGRA_BO_BOTTOM_UP;
+
 	return bo;
 
 err_mmap:
diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h
index c4993fc2c3bd..7674000bf47d 100644
--- a/drivers/gpu/drm/tegra/gem.h
+++ b/drivers/gpu/drm/tegra/gem.h
@@ -24,7 +24,8 @@
 #include <drm/drm.h>
 #include <drm/drmP.h>
 
-#define TEGRA_BO_TILED (1 << 0)
+#define TEGRA_BO_TILED     (1 << 0)
+#define TEGRA_BO_BOTTOM_UP (1 << 1)
 
 struct tegra_bo {
 	struct drm_gem_object gem;
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 6b420029a645..0f8575f58db8 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -19,7 +19,8 @@
 
 #include <drm/drm.h>
 
-#define DRM_TEGRA_GEM_CREATE_TILED (1 << 0)
+#define DRM_TEGRA_GEM_CREATE_TILED     (1 << 0)
+#define DRM_TEGRA_GEM_CREATE_BOTTOM_UP (1 << 1)
 
 struct drm_tegra_gem_create {
 	__u64 size;
-- 
cgit 


From 8736fe81532182ba0086a371fae0708ea42a2cdf Mon Sep 17 00:00:00 2001
From: Arto Merilainen <amerilainen@nvidia.com>
Date: Mon, 14 Oct 2013 15:21:52 +0300
Subject: gpu: host1x: Add 'flags' field to syncpt request

Functions host1x_syncpt_request() and _host1x_syncpt_alloc() have
been taking a separate boolean flag ('client_managed') for indicating
if the syncpoint value should be tracked by the host1x driver.

This patch converts the field into generic 'flags' field so that
we can easily add more information while requesting a syncpoint.
Clients are adapted to use the new interface accordingly.

Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/gr2d.c |  2 +-
 drivers/gpu/host1x/syncpt.c  | 18 +++++++++++-------
 include/linux/host1x.h       |  4 +++-
 3 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
index 7f4eb110aa85..3a04b97b54a2 100644
--- a/drivers/gpu/drm/tegra/gr2d.c
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -43,7 +43,7 @@ static int gr2d_init(struct host1x_client *client)
 	if (!gr2d->channel)
 		return -ENOMEM;
 
-	client->syncpts[0] = host1x_syncpt_request(client->dev, false);
+	client->syncpts[0] = host1x_syncpt_request(client->dev, 0);
 	if (!client->syncpts[0]) {
 		host1x_channel_free(gr2d->channel);
 		return -ENOMEM;
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index 03cf2922e469..5b88ba4c974e 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -30,9 +30,9 @@
 #define SYNCPT_CHECK_PERIOD (2 * HZ)
 #define MAX_STUCK_CHECK_COUNT 15
 
-static struct host1x_syncpt *_host1x_syncpt_alloc(struct host1x *host,
-						  struct device *dev,
-						  bool client_managed)
+static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
+						 struct device *dev,
+						 unsigned long flags)
 {
 	int i;
 	struct host1x_syncpt *sp = host->syncpt;
@@ -51,7 +51,11 @@ static struct host1x_syncpt *_host1x_syncpt_alloc(struct host1x *host,
 
 	sp->dev = dev;
 	sp->name = name;
-	sp->client_managed = client_managed;
+
+	if (flags & HOST1X_SYNCPT_CLIENT_MANAGED)
+		sp->client_managed = true;
+	else
+		sp->client_managed = false;
 
 	return sp;
 }
@@ -321,7 +325,7 @@ int host1x_syncpt_init(struct host1x *host)
 	host1x_syncpt_restore(host);
 
 	/* Allocate sync point to use for clearing waits for expired fences */
-	host->nop_sp = _host1x_syncpt_alloc(host, NULL, false);
+	host->nop_sp = host1x_syncpt_alloc(host, NULL, 0);
 	if (!host->nop_sp)
 		return -ENOMEM;
 
@@ -329,10 +333,10 @@ int host1x_syncpt_init(struct host1x *host)
 }
 
 struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
-					    bool client_managed)
+					    unsigned long flags)
 {
 	struct host1x *host = dev_get_drvdata(dev->parent);
-	return _host1x_syncpt_alloc(host, dev, client_managed);
+	return host1x_syncpt_alloc(host, dev, flags);
 }
 
 void host1x_syncpt_free(struct host1x_syncpt *sp)
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index f5dd56fbdc3e..eb713dbbae29 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -124,6 +124,8 @@ static inline void host1x_bo_kunmap(struct host1x_bo *bo,
  * host1x syncpoints
  */
 
+#define HOST1X_SYNCPT_CLIENT_MANAGED	(1 << 0)
+
 struct host1x_syncpt;
 struct host1x;
 
@@ -135,7 +137,7 @@ int host1x_syncpt_incr(struct host1x_syncpt *sp);
 int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 		       u32 *value);
 struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
-					    bool client_managed);
+					    unsigned long flags);
 void host1x_syncpt_free(struct host1x_syncpt *sp);
 
 /*
-- 
cgit 


From f5a954fed9b3eb04973ede72c50c66157fa9e15b Mon Sep 17 00:00:00 2001
From: Arto Merilainen <amerilainen@nvidia.com>
Date: Mon, 14 Oct 2013 15:21:53 +0300
Subject: gpu: host1x: Add syncpoint base support

This patch adds support for hardware syncpoint bases. This creates
a simple mechanism to stall the command FIFO until an operation is
completed.

Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/dev.h                   |  2 ++
 drivers/gpu/host1x/hw/channel_hw.c         | 20 +++++++++++
 drivers/gpu/host1x/hw/hw_host1x01_uclass.h |  6 ++++
 drivers/gpu/host1x/syncpt.c                | 55 ++++++++++++++++++++++++++++--
 drivers/gpu/host1x/syncpt.h                |  6 ++++
 include/linux/host1x.h                     |  5 +++
 6 files changed, 92 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 6cf689b9e17b..a61a976e7a42 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -27,6 +27,7 @@
 #include "job.h"
 
 struct host1x_syncpt;
+struct host1x_syncpt_base;
 struct host1x_channel;
 struct host1x_cdma;
 struct host1x_job;
@@ -102,6 +103,7 @@ struct host1x {
 
 	void __iomem *regs;
 	struct host1x_syncpt *syncpt;
+	struct host1x_syncpt_base *bases;
 	struct device *dev;
 	struct clk *clk;
 
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 3be0cd296d3a..4608257ab656 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -67,6 +67,22 @@ static void submit_gathers(struct host1x_job *job)
 	}
 }
 
+static inline void synchronize_syncpt_base(struct host1x_job *job)
+{
+	struct host1x *host = dev_get_drvdata(job->channel->dev->parent);
+	struct host1x_syncpt *sp = host->syncpt + job->syncpt_id;
+	u32 id, value;
+
+	value = host1x_syncpt_read_max(sp);
+	id = sp->base->id;
+
+	host1x_cdma_push(&job->channel->cdma,
+			 host1x_opcode_setclass(HOST1X_CLASS_HOST1X,
+				HOST1X_UCLASS_LOAD_SYNCPT_BASE, 1),
+			 HOST1X_UCLASS_LOAD_SYNCPT_BASE_BASE_INDX_F(id) |
+			 HOST1X_UCLASS_LOAD_SYNCPT_BASE_VALUE_F(value));
+}
+
 static int channel_submit(struct host1x_job *job)
 {
 	struct host1x_channel *ch = job->channel;
@@ -118,6 +134,10 @@ static int channel_submit(struct host1x_job *job)
 					host1x_syncpt_read_max(sp)));
 	}
 
+	/* Synchronize base register to allow using it for relative waiting */
+	if (sp->base)
+		synchronize_syncpt_base(job);
+
 	syncval = host1x_syncpt_incr_max(sp, user_syncpt_incrs);
 
 	job->syncpt_end = syncval;
diff --git a/drivers/gpu/host1x/hw/hw_host1x01_uclass.h b/drivers/gpu/host1x/hw/hw_host1x01_uclass.h
index 42f3ce19ca32..f7553599ee27 100644
--- a/drivers/gpu/host1x/hw/hw_host1x01_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x01_uclass.h
@@ -111,6 +111,12 @@ static inline u32 host1x_uclass_wait_syncpt_base_offset_f(u32 v)
 }
 #define HOST1X_UCLASS_WAIT_SYNCPT_BASE_OFFSET_F(v) \
 	host1x_uclass_wait_syncpt_base_offset_f(v)
+static inline u32 host1x_uclass_load_syncpt_base_r(void)
+{
+	return 0xb;
+}
+#define HOST1X_UCLASS_LOAD_SYNCPT_BASE \
+	host1x_uclass_load_syncpt_base_r()
 static inline u32 host1x_uclass_load_syncpt_base_base_indx_f(u32 v)
 {
 	return (v & 0xff) << 24;
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index 5b88ba4c974e..159c479829c9 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -30,6 +30,29 @@
 #define SYNCPT_CHECK_PERIOD (2 * HZ)
 #define MAX_STUCK_CHECK_COUNT 15
 
+static struct host1x_syncpt_base *
+host1x_syncpt_base_request(struct host1x *host)
+{
+	struct host1x_syncpt_base *bases = host->bases;
+	unsigned int i;
+
+	for (i = 0; i < host->info->nb_bases; i++)
+		if (!bases[i].requested)
+			break;
+
+	if (i >= host->info->nb_bases)
+		return NULL;
+
+	bases[i].requested = true;
+	return &bases[i];
+}
+
+static void host1x_syncpt_base_free(struct host1x_syncpt_base *base)
+{
+	if (base)
+		base->requested = false;
+}
+
 static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
 						 struct device *dev,
 						 unsigned long flags)
@@ -44,6 +67,12 @@ static struct host1x_syncpt *host1x_syncpt_alloc(struct host1x *host,
 	if (i >= host->info->nb_pts)
 		return NULL;
 
+	if (flags & HOST1X_SYNCPT_HAS_BASE) {
+		sp->base = host1x_syncpt_base_request(host);
+		if (!sp->base)
+			return NULL;
+	}
+
 	name = kasprintf(GFP_KERNEL, "%02d-%s", sp->id,
 			dev ? dev_name(dev) : NULL);
 	if (!name)
@@ -307,20 +336,30 @@ int host1x_syncpt_patch_wait(struct host1x_syncpt *sp, void *patch_addr)
 
 int host1x_syncpt_init(struct host1x *host)
 {
+	struct host1x_syncpt_base *bases;
 	struct host1x_syncpt *syncpt;
 	int i;
 
 	syncpt = devm_kzalloc(host->dev, sizeof(*syncpt) * host->info->nb_pts,
-		GFP_KERNEL);
+			      GFP_KERNEL);
 	if (!syncpt)
 		return -ENOMEM;
 
-	for (i = 0; i < host->info->nb_pts; ++i) {
+	bases = devm_kzalloc(host->dev, sizeof(*bases) * host->info->nb_bases,
+			     GFP_KERNEL);
+	if (!bases)
+		return -ENOMEM;
+
+	for (i = 0; i < host->info->nb_pts; i++) {
 		syncpt[i].id = i;
 		syncpt[i].host = host;
 	}
 
+	for (i = 0; i < host->info->nb_bases; i++)
+		bases[i].id = i;
+
 	host->syncpt = syncpt;
+	host->bases = bases;
 
 	host1x_syncpt_restore(host);
 
@@ -344,7 +383,9 @@ void host1x_syncpt_free(struct host1x_syncpt *sp)
 	if (!sp)
 		return;
 
+	host1x_syncpt_base_free(sp->base);
 	kfree(sp->name);
+	sp->base = NULL;
 	sp->dev = NULL;
 	sp->name = NULL;
 	sp->client_managed = false;
@@ -398,3 +439,13 @@ struct host1x_syncpt *host1x_syncpt_get(struct host1x *host, u32 id)
 		return NULL;
 	return host->syncpt + id;
 }
+
+struct host1x_syncpt_base *host1x_syncpt_get_base(struct host1x_syncpt *sp)
+{
+	return sp ? sp->base : NULL;
+}
+
+u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base)
+{
+	return base->id;
+}
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index 4eb933a497fd..9056465ecd3f 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -31,6 +31,11 @@ struct host1x;
 /* Reserved for replacing an expired wait with a NOP */
 #define HOST1X_SYNCPT_RESERVED			0
 
+struct host1x_syncpt_base {
+	unsigned int id;
+	bool requested;
+};
+
 struct host1x_syncpt {
 	int id;
 	atomic_t min_val;
@@ -40,6 +45,7 @@ struct host1x_syncpt {
 	bool client_managed;
 	struct host1x *host;
 	struct device *dev;
+	struct host1x_syncpt_base *base;
 
 	/* interrupt data */
 	struct host1x_syncpt_intr intr;
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index eb713dbbae29..f5b9b87ac9a9 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -125,7 +125,9 @@ static inline void host1x_bo_kunmap(struct host1x_bo *bo,
  */
 
 #define HOST1X_SYNCPT_CLIENT_MANAGED	(1 << 0)
+#define HOST1X_SYNCPT_HAS_BASE		(1 << 1)
 
+struct host1x_syncpt_base;
 struct host1x_syncpt;
 struct host1x;
 
@@ -140,6 +142,9 @@ struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
 					    unsigned long flags);
 void host1x_syncpt_free(struct host1x_syncpt *sp);
 
+struct host1x_syncpt_base *host1x_syncpt_get_base(struct host1x_syncpt *sp);
+u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base);
+
 /*
  * host1x channel
  */
-- 
cgit 


From c54a169b528d0ac2a5d3a7bf91f8534323bda83d Mon Sep 17 00:00:00 2001
From: Arto Merilainen <amerilainen@nvidia.com>
Date: Mon, 14 Oct 2013 15:21:54 +0300
Subject: drm/tegra: Deliver syncpoint base to user space

This patch adds a separate ioctl for delivering syncpoint base number
to user space. If the syncpoint does not have an associated base, the
function returns -ENXIO.

Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/drm/tegra/drm.c  | 29 +++++++++++++++++++++++++++++
 include/uapi/drm/tegra_drm.h | 26 +++++++++++++++++---------
 2 files changed, 46 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index ecb6ec735ef1..28e178137718 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -418,6 +418,34 @@ static int tegra_submit(struct drm_device *drm, void *data,
 
 	return context->client->ops->submit(context, args, drm, file);
 }
+
+static int tegra_get_syncpt_base(struct drm_device *drm, void *data,
+				 struct drm_file *file)
+{
+	struct tegra_drm_file *fpriv = file->driver_priv;
+	struct drm_tegra_get_syncpt_base *args = data;
+	struct tegra_drm_context *context;
+	struct host1x_syncpt_base *base;
+	struct host1x_syncpt *syncpt;
+
+	context = tegra_drm_get_context(args->context);
+
+	if (!tegra_drm_file_owns_context(fpriv, context))
+		return -ENODEV;
+
+	if (args->syncpt >= context->client->base.num_syncpts)
+		return -EINVAL;
+
+	syncpt = context->client->base.syncpts[args->syncpt];
+
+	base = host1x_syncpt_get_base(syncpt);
+	if (!base)
+		return -ENXIO;
+
+	args->id = host1x_syncpt_base_id(base);
+
+	return 0;
+}
 #endif
 
 static const struct drm_ioctl_desc tegra_drm_ioctls[] = {
@@ -431,6 +459,7 @@ static const struct drm_ioctl_desc tegra_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(TEGRA_CLOSE_CHANNEL, tegra_close_channel, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(TEGRA_GET_SYNCPT, tegra_get_syncpt, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(TEGRA_SUBMIT, tegra_submit, DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(TEGRA_GET_SYNCPT_BASE, tegra_get_syncpt_base, DRM_UNLOCKED),
 #endif
 };
 
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 0f8575f58db8..5e1ab552cbed 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -68,6 +68,12 @@ struct drm_tegra_get_syncpt {
 	__u32 id;
 };
 
+struct drm_tegra_get_syncpt_base {
+	__u64 context;
+	__u32 syncpt;
+	__u32 id;
+};
+
 struct drm_tegra_syncpt {
 	__u32 id;
 	__u32 incrs;
@@ -118,15 +124,16 @@ struct drm_tegra_submit {
 	__u32 reserved[5];	/* future expansion */
 };
 
-#define DRM_TEGRA_GEM_CREATE	0x00
-#define DRM_TEGRA_GEM_MMAP	0x01
-#define DRM_TEGRA_SYNCPT_READ	0x02
-#define DRM_TEGRA_SYNCPT_INCR	0x03
-#define DRM_TEGRA_SYNCPT_WAIT	0x04
-#define DRM_TEGRA_OPEN_CHANNEL	0x05
-#define DRM_TEGRA_CLOSE_CHANNEL	0x06
-#define DRM_TEGRA_GET_SYNCPT	0x07
-#define DRM_TEGRA_SUBMIT	0x08
+#define DRM_TEGRA_GEM_CREATE		0x00
+#define DRM_TEGRA_GEM_MMAP		0x01
+#define DRM_TEGRA_SYNCPT_READ		0x02
+#define DRM_TEGRA_SYNCPT_INCR		0x03
+#define DRM_TEGRA_SYNCPT_WAIT		0x04
+#define DRM_TEGRA_OPEN_CHANNEL		0x05
+#define DRM_TEGRA_CLOSE_CHANNEL		0x06
+#define DRM_TEGRA_GET_SYNCPT		0x07
+#define DRM_TEGRA_SUBMIT		0x08
+#define DRM_TEGRA_GET_SYNCPT_BASE	0x09
 
 #define DRM_IOCTL_TEGRA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_CREATE, struct drm_tegra_gem_create)
 #define DRM_IOCTL_TEGRA_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_MMAP, struct drm_tegra_gem_mmap)
@@ -137,5 +144,6 @@ struct drm_tegra_submit {
 #define DRM_IOCTL_TEGRA_CLOSE_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_CLOSE_CHANNEL, struct drm_tegra_open_channel)
 #define DRM_IOCTL_TEGRA_GET_SYNCPT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT, struct drm_tegra_get_syncpt)
 #define DRM_IOCTL_TEGRA_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SUBMIT, struct drm_tegra_submit)
+#define DRM_IOCTL_TEGRA_GET_SYNCPT_BASE DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT_BASE, struct drm_tegra_get_syncpt_base)
 
 #endif
-- 
cgit 


From 769980dea10c0b6edb1903119fe0a93ab1bf8194 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 26 Aug 2013 06:17:51 -0300
Subject: [media] v4l: Fix typo in v4l2_subdev_get_try_crop()

The helper function is defined by a macro that is erroneously called
with the compose rectangle instead of the crop rectangle. Fix it.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Sakari Ailus <sakari.ailus@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
---
 include/media/v4l2-subdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 27b28506f749..d67210a37ef3 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -641,7 +641,7 @@ struct v4l2_subdev_fh {
 	}
 
 __V4L2_SUBDEV_MK_GET_TRY(v4l2_mbus_framefmt, format, try_fmt)
-__V4L2_SUBDEV_MK_GET_TRY(v4l2_rect, crop, try_compose)
+__V4L2_SUBDEV_MK_GET_TRY(v4l2_rect, crop, try_crop)
 __V4L2_SUBDEV_MK_GET_TRY(v4l2_rect, compose, try_compose)
 #endif
 
-- 
cgit 


From 6a716c90a51338009c3bc1f460829afaed8f922d Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sat, 19 Oct 2013 18:18:28 +0200
Subject: hung_task debugging: Add tracepoint to report the hang

Currently check_hung_task() prints a warning if it detects the
problem, but it is not convenient to watch the system logs if
user-space wants to be notified about the hang.

Add the new trace_sched_process_hang() into check_hung_task(),
this way a user-space monitor can easily wait for the hang and
potentially resolve a problem.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Dave Sullivan <dsulliva@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20131019161828.GA7439@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/trace/events/sched.h | 19 +++++++++++++++++++
 kernel/hung_task.c           |  4 ++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 2e7d9947a10d..2a652d124fbb 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -424,6 +424,25 @@ TRACE_EVENT(sched_pi_setprio,
 			__entry->oldprio, __entry->newprio)
 );
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+TRACE_EVENT(sched_process_hang,
+	TP_PROTO(struct task_struct *tsk),
+	TP_ARGS(tsk),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid = tsk->pid;
+	),
+
+	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
+);
+#endif /* CONFIG_DETECT_HUNG_TASK */
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 042252383fd2..8807061ca004 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/sysctl.h>
 #include <linux/utsname.h>
+#include <trace/events/sched.h>
 
 /*
  * The number of tasks checked:
@@ -92,6 +93,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 		t->last_switch_count = switch_count;
 		return;
 	}
+
+	trace_sched_process_hang(t);
+
 	if (!sysctl_hung_task_warnings)
 		return;
 	sysctl_hung_task_warnings--;
-- 
cgit 


From 8623ec220b9c9d873ef82d41c9adbac7eec53174 Mon Sep 17 00:00:00 2001
From: Marek Belisko <marek@goldelico.com>
Date: Tue, 29 Oct 2013 23:25:40 +0100
Subject: omapdss: Add new panel driver for Topolly td028ttec1 LCD.

Signed-off-by: Marek Belisko <marek@goldelico.com>
Signed-off-by: H. Nikolaus Schaller <hns@goldelico.com>
[tomi.valkeinen@ti.com: made a few funcs static]
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/omap2/displays-new/Kconfig           |   6 +
 drivers/video/omap2/displays-new/Makefile          |   1 +
 .../omap2/displays-new/panel-tpo-td028ttec1.c      | 480 +++++++++++++++++++++
 include/video/omap-panel-data.h                    |  13 +
 4 files changed, 500 insertions(+)
 create mode 100644 drivers/video/omap2/displays-new/panel-tpo-td028ttec1.c

(limited to 'include')

diff --git a/drivers/video/omap2/displays-new/Kconfig b/drivers/video/omap2/displays-new/Kconfig
index 6c90885b0940..1054249b16a5 100644
--- a/drivers/video/omap2/displays-new/Kconfig
+++ b/drivers/video/omap2/displays-new/Kconfig
@@ -56,6 +56,12 @@ config DISPLAY_PANEL_SHARP_LS037V7DW01
         help
           LCD Panel used in TI's SDP3430 and EVM boards
 
+config DISPLAY_PANEL_TPO_TD028TTEC1
+        tristate "TPO TD028TTEC1 LCD Panel"
+        depends on SPI
+        help
+          LCD panel used in Openmoko.
+
 config DISPLAY_PANEL_TPO_TD043MTEA1
         tristate "TPO TD043MTEA1 LCD Panel"
         depends on SPI
diff --git a/drivers/video/omap2/displays-new/Makefile b/drivers/video/omap2/displays-new/Makefile
index 5aeb11b8fcd5..0323a8a1c682 100644
--- a/drivers/video/omap2/displays-new/Makefile
+++ b/drivers/video/omap2/displays-new/Makefile
@@ -8,5 +8,6 @@ obj-$(CONFIG_DISPLAY_PANEL_DSI_CM) += panel-dsi-cm.o
 obj-$(CONFIG_DISPLAY_PANEL_SONY_ACX565AKM) += panel-sony-acx565akm.o
 obj-$(CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02) += panel-lgphilips-lb035q02.o
 obj-$(CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01) += panel-sharp-ls037v7dw01.o
+obj-$(CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1) += panel-tpo-td028ttec1.o
 obj-$(CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o
 obj-$(CONFIG_DISPLAY_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o
diff --git a/drivers/video/omap2/displays-new/panel-tpo-td028ttec1.c b/drivers/video/omap2/displays-new/panel-tpo-td028ttec1.c
new file mode 100644
index 000000000000..9a08908fe998
--- /dev/null
+++ b/drivers/video/omap2/displays-new/panel-tpo-td028ttec1.c
@@ -0,0 +1,480 @@
+/*
+ * Toppoly TD028TTEC1 panel support
+ *
+ * Copyright (C) 2008 Nokia Corporation
+ * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ *
+ * Neo 1973 code (jbt6k74.c):
+ * Copyright (C) 2006-2007 by OpenMoko, Inc.
+ * Author: Harald Welte <laforge@openmoko.org>
+ *
+ * Ported and adapted from Neo 1973 U-Boot by:
+ * H. Nikolaus Schaller <hns@goldelico.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/spi/spi.h>
+#include <linux/gpio.h>
+#include <video/omapdss.h>
+#include <video/omap-panel-data.h>
+
+struct panel_drv_data {
+	struct omap_dss_device dssdev;
+	struct omap_dss_device *in;
+
+	int data_lines;
+
+	struct omap_video_timings videomode;
+
+	struct spi_device *spi_dev;
+};
+
+static struct omap_video_timings td028ttec1_panel_timings = {
+	.x_res		= 480,
+	.y_res		= 640,
+	.pixel_clock	= 22153,
+	.hfp		= 24,
+	.hsw		= 8,
+	.hbp		= 8,
+	.vfp		= 4,
+	.vsw		= 2,
+	.vbp		= 2,
+
+	.vsync_level	= OMAPDSS_SIG_ACTIVE_LOW,
+	.hsync_level	= OMAPDSS_SIG_ACTIVE_LOW,
+
+	.data_pclk_edge	= OMAPDSS_DRIVE_SIG_FALLING_EDGE,
+	.de_level	= OMAPDSS_SIG_ACTIVE_HIGH,
+	.sync_pclk_edge	= OMAPDSS_DRIVE_SIG_OPPOSITE_EDGES,
+};
+
+#define JBT_COMMAND	0x000
+#define JBT_DATA	0x100
+
+static int jbt_ret_write_0(struct panel_drv_data *ddata, u8 reg)
+{
+	int rc;
+	u16 tx_buf = JBT_COMMAND | reg;
+
+	rc = spi_write(ddata->spi_dev, (u8 *)&tx_buf,
+			1*sizeof(u16));
+	if (rc != 0)
+		dev_err(&ddata->spi_dev->dev,
+			"jbt_ret_write_0 spi_write ret %d\n", rc);
+
+	return rc;
+}
+
+static int jbt_reg_write_1(struct panel_drv_data *ddata, u8 reg, u8 data)
+{
+	int rc;
+	u16 tx_buf[2];
+
+	tx_buf[0] = JBT_COMMAND | reg;
+	tx_buf[1] = JBT_DATA | data;
+	rc = spi_write(ddata->spi_dev, (u8 *)tx_buf,
+			2*sizeof(u16));
+	if (rc != 0)
+		dev_err(&ddata->spi_dev->dev,
+			"jbt_reg_write_1 spi_write ret %d\n", rc);
+
+	return rc;
+}
+
+static int jbt_reg_write_2(struct panel_drv_data *ddata, u8 reg, u16 data)
+{
+	int rc;
+	u16 tx_buf[3];
+
+	tx_buf[0] = JBT_COMMAND | reg;
+	tx_buf[1] = JBT_DATA | (data >> 8);
+	tx_buf[2] = JBT_DATA | (data & 0xff);
+
+	rc = spi_write(ddata->spi_dev, (u8 *)tx_buf,
+			3*sizeof(u16));
+
+	if (rc != 0)
+		dev_err(&ddata->spi_dev->dev,
+			"jbt_reg_write_2 spi_write ret %d\n", rc);
+
+	return rc;
+}
+
+enum jbt_register {
+	JBT_REG_SLEEP_IN		= 0x10,
+	JBT_REG_SLEEP_OUT		= 0x11,
+
+	JBT_REG_DISPLAY_OFF		= 0x28,
+	JBT_REG_DISPLAY_ON		= 0x29,
+
+	JBT_REG_RGB_FORMAT		= 0x3a,
+	JBT_REG_QUAD_RATE		= 0x3b,
+
+	JBT_REG_POWER_ON_OFF		= 0xb0,
+	JBT_REG_BOOSTER_OP		= 0xb1,
+	JBT_REG_BOOSTER_MODE		= 0xb2,
+	JBT_REG_BOOSTER_FREQ		= 0xb3,
+	JBT_REG_OPAMP_SYSCLK		= 0xb4,
+	JBT_REG_VSC_VOLTAGE		= 0xb5,
+	JBT_REG_VCOM_VOLTAGE		= 0xb6,
+	JBT_REG_EXT_DISPL		= 0xb7,
+	JBT_REG_OUTPUT_CONTROL		= 0xb8,
+	JBT_REG_DCCLK_DCEV		= 0xb9,
+	JBT_REG_DISPLAY_MODE1		= 0xba,
+	JBT_REG_DISPLAY_MODE2		= 0xbb,
+	JBT_REG_DISPLAY_MODE		= 0xbc,
+	JBT_REG_ASW_SLEW		= 0xbd,
+	JBT_REG_DUMMY_DISPLAY		= 0xbe,
+	JBT_REG_DRIVE_SYSTEM		= 0xbf,
+
+	JBT_REG_SLEEP_OUT_FR_A		= 0xc0,
+	JBT_REG_SLEEP_OUT_FR_B		= 0xc1,
+	JBT_REG_SLEEP_OUT_FR_C		= 0xc2,
+	JBT_REG_SLEEP_IN_LCCNT_D	= 0xc3,
+	JBT_REG_SLEEP_IN_LCCNT_E	= 0xc4,
+	JBT_REG_SLEEP_IN_LCCNT_F	= 0xc5,
+	JBT_REG_SLEEP_IN_LCCNT_G	= 0xc6,
+
+	JBT_REG_GAMMA1_FINE_1		= 0xc7,
+	JBT_REG_GAMMA1_FINE_2		= 0xc8,
+	JBT_REG_GAMMA1_INCLINATION	= 0xc9,
+	JBT_REG_GAMMA1_BLUE_OFFSET	= 0xca,
+
+	JBT_REG_BLANK_CONTROL		= 0xcf,
+	JBT_REG_BLANK_TH_TV		= 0xd0,
+	JBT_REG_CKV_ON_OFF		= 0xd1,
+	JBT_REG_CKV_1_2			= 0xd2,
+	JBT_REG_OEV_TIMING		= 0xd3,
+	JBT_REG_ASW_TIMING_1		= 0xd4,
+	JBT_REG_ASW_TIMING_2		= 0xd5,
+
+	JBT_REG_HCLOCK_VGA		= 0xec,
+	JBT_REG_HCLOCK_QVGA		= 0xed,
+};
+
+#define to_panel_data(p) container_of(p, struct panel_drv_data, dssdev)
+
+static int td028ttec1_panel_connect(struct omap_dss_device *dssdev)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+	int r;
+
+	if (omapdss_device_is_connected(dssdev))
+		return 0;
+
+	r = in->ops.dpi->connect(in, dssdev);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+static void td028ttec1_panel_disconnect(struct omap_dss_device *dssdev)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+
+	if (!omapdss_device_is_connected(dssdev))
+		return;
+
+	in->ops.dpi->disconnect(in, dssdev);
+}
+
+static int td028ttec1_panel_enable(struct omap_dss_device *dssdev)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+	int r;
+
+	if (!omapdss_device_is_connected(dssdev))
+		return -ENODEV;
+
+	if (omapdss_device_is_enabled(dssdev))
+		return 0;
+
+	in->ops.dpi->set_data_lines(in, ddata->data_lines);
+	in->ops.dpi->set_timings(in, &ddata->videomode);
+
+	r = in->ops.dpi->enable(in);
+	if (r)
+		return r;
+
+	dev_dbg(dssdev->dev, "td028ttec1_panel_enable() - state %d\n",
+		dssdev->state);
+
+	/* three times command zero */
+	r |= jbt_ret_write_0(ddata, 0x00);
+	usleep_range(1000, 2000);
+	r |= jbt_ret_write_0(ddata, 0x00);
+	usleep_range(1000, 2000);
+	r |= jbt_ret_write_0(ddata, 0x00);
+	usleep_range(1000, 2000);
+
+	if (r) {
+		dev_warn(dssdev->dev, "transfer error\n");
+		goto transfer_err;
+	}
+
+	/* deep standby out */
+	r |= jbt_reg_write_1(ddata, JBT_REG_POWER_ON_OFF, 0x17);
+
+	/* RGB I/F on, RAM write off, QVGA through, SIGCON enable */
+	r |= jbt_reg_write_1(ddata, JBT_REG_DISPLAY_MODE, 0x80);
+
+	/* Quad mode off */
+	r |= jbt_reg_write_1(ddata, JBT_REG_QUAD_RATE, 0x00);
+
+	/* AVDD on, XVDD on */
+	r |= jbt_reg_write_1(ddata, JBT_REG_POWER_ON_OFF, 0x16);
+
+	/* Output control */
+	r |= jbt_reg_write_2(ddata, JBT_REG_OUTPUT_CONTROL, 0xfff9);
+
+	/* Sleep mode off */
+	r |= jbt_ret_write_0(ddata, JBT_REG_SLEEP_OUT);
+
+	/* at this point we have like 50% grey */
+
+	/* initialize register set */
+	r |= jbt_reg_write_1(ddata, JBT_REG_DISPLAY_MODE1, 0x01);
+	r |= jbt_reg_write_1(ddata, JBT_REG_DISPLAY_MODE2, 0x00);
+	r |= jbt_reg_write_1(ddata, JBT_REG_RGB_FORMAT, 0x60);
+	r |= jbt_reg_write_1(ddata, JBT_REG_DRIVE_SYSTEM, 0x10);
+	r |= jbt_reg_write_1(ddata, JBT_REG_BOOSTER_OP, 0x56);
+	r |= jbt_reg_write_1(ddata, JBT_REG_BOOSTER_MODE, 0x33);
+	r |= jbt_reg_write_1(ddata, JBT_REG_BOOSTER_FREQ, 0x11);
+	r |= jbt_reg_write_1(ddata, JBT_REG_BOOSTER_FREQ, 0x11);
+	r |= jbt_reg_write_1(ddata, JBT_REG_OPAMP_SYSCLK, 0x02);
+	r |= jbt_reg_write_1(ddata, JBT_REG_VSC_VOLTAGE, 0x2b);
+	r |= jbt_reg_write_1(ddata, JBT_REG_VCOM_VOLTAGE, 0x40);
+	r |= jbt_reg_write_1(ddata, JBT_REG_EXT_DISPL, 0x03);
+	r |= jbt_reg_write_1(ddata, JBT_REG_DCCLK_DCEV, 0x04);
+	/*
+	 * default of 0x02 in JBT_REG_ASW_SLEW responsible for 72Hz requirement
+	 * to avoid red / blue flicker
+	 */
+	r |= jbt_reg_write_1(ddata, JBT_REG_ASW_SLEW, 0x04);
+	r |= jbt_reg_write_1(ddata, JBT_REG_DUMMY_DISPLAY, 0x00);
+
+	r |= jbt_reg_write_1(ddata, JBT_REG_SLEEP_OUT_FR_A, 0x11);
+	r |= jbt_reg_write_1(ddata, JBT_REG_SLEEP_OUT_FR_B, 0x11);
+	r |= jbt_reg_write_1(ddata, JBT_REG_SLEEP_OUT_FR_C, 0x11);
+	r |= jbt_reg_write_2(ddata, JBT_REG_SLEEP_IN_LCCNT_D, 0x2040);
+	r |= jbt_reg_write_2(ddata, JBT_REG_SLEEP_IN_LCCNT_E, 0x60c0);
+	r |= jbt_reg_write_2(ddata, JBT_REG_SLEEP_IN_LCCNT_F, 0x1020);
+	r |= jbt_reg_write_2(ddata, JBT_REG_SLEEP_IN_LCCNT_G, 0x60c0);
+
+	r |= jbt_reg_write_2(ddata, JBT_REG_GAMMA1_FINE_1, 0x5533);
+	r |= jbt_reg_write_1(ddata, JBT_REG_GAMMA1_FINE_2, 0x00);
+	r |= jbt_reg_write_1(ddata, JBT_REG_GAMMA1_INCLINATION, 0x00);
+	r |= jbt_reg_write_1(ddata, JBT_REG_GAMMA1_BLUE_OFFSET, 0x00);
+
+	r |= jbt_reg_write_2(ddata, JBT_REG_HCLOCK_VGA, 0x1f0);
+	r |= jbt_reg_write_1(ddata, JBT_REG_BLANK_CONTROL, 0x02);
+	r |= jbt_reg_write_2(ddata, JBT_REG_BLANK_TH_TV, 0x0804);
+
+	r |= jbt_reg_write_1(ddata, JBT_REG_CKV_ON_OFF, 0x01);
+	r |= jbt_reg_write_2(ddata, JBT_REG_CKV_1_2, 0x0000);
+
+	r |= jbt_reg_write_2(ddata, JBT_REG_OEV_TIMING, 0x0d0e);
+	r |= jbt_reg_write_2(ddata, JBT_REG_ASW_TIMING_1, 0x11a4);
+	r |= jbt_reg_write_1(ddata, JBT_REG_ASW_TIMING_2, 0x0e);
+
+	r |= jbt_ret_write_0(ddata, JBT_REG_DISPLAY_ON);
+
+	dssdev->state = OMAP_DSS_DISPLAY_ACTIVE;
+
+transfer_err:
+
+	return r ? -EIO : 0;
+}
+
+static void td028ttec1_panel_disable(struct omap_dss_device *dssdev)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+
+	if (!omapdss_device_is_enabled(dssdev))
+		return;
+
+	dev_dbg(dssdev->dev, "td028ttec1_panel_disable()\n");
+
+	jbt_ret_write_0(ddata, JBT_REG_DISPLAY_OFF);
+	jbt_reg_write_2(ddata, JBT_REG_OUTPUT_CONTROL, 0x8002);
+	jbt_ret_write_0(ddata, JBT_REG_SLEEP_IN);
+	jbt_reg_write_1(ddata, JBT_REG_POWER_ON_OFF, 0x00);
+
+	in->ops.dpi->disable(in);
+
+	dssdev->state = OMAP_DSS_DISPLAY_DISABLED;
+}
+
+static void td028ttec1_panel_set_timings(struct omap_dss_device *dssdev,
+		struct omap_video_timings *timings)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+
+	ddata->videomode = *timings;
+	dssdev->panel.timings = *timings;
+
+	in->ops.dpi->set_timings(in, timings);
+}
+
+static void td028ttec1_panel_get_timings(struct omap_dss_device *dssdev,
+		struct omap_video_timings *timings)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+
+	*timings = ddata->videomode;
+}
+
+static int td028ttec1_panel_check_timings(struct omap_dss_device *dssdev,
+		struct omap_video_timings *timings)
+{
+	struct panel_drv_data *ddata = to_panel_data(dssdev);
+	struct omap_dss_device *in = ddata->in;
+
+	return in->ops.dpi->check_timings(in, timings);
+}
+
+static struct omap_dss_driver td028ttec1_ops = {
+	.connect	= td028ttec1_panel_connect,
+	.disconnect	= td028ttec1_panel_disconnect,
+
+	.enable		= td028ttec1_panel_enable,
+	.disable	= td028ttec1_panel_disable,
+
+	.set_timings	= td028ttec1_panel_set_timings,
+	.get_timings	= td028ttec1_panel_get_timings,
+	.check_timings	= td028ttec1_panel_check_timings,
+};
+
+static int td028ttec1_panel_probe_pdata(struct spi_device *spi)
+{
+	const struct panel_tpo_td028ttec1_platform_data *pdata;
+	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
+	struct omap_dss_device *dssdev, *in;
+
+	pdata = dev_get_platdata(&spi->dev);
+
+	in = omap_dss_find_output(pdata->source);
+	if (in == NULL) {
+		dev_err(&spi->dev, "failed to find video source '%s'\n",
+				pdata->source);
+		return -EPROBE_DEFER;
+	}
+
+	ddata->in = in;
+
+	ddata->data_lines = pdata->data_lines;
+
+	dssdev = &ddata->dssdev;
+	dssdev->name = pdata->name;
+
+	return 0;
+}
+
+static int td028ttec1_panel_probe(struct spi_device *spi)
+{
+	struct panel_drv_data *ddata;
+	struct omap_dss_device *dssdev;
+	int r;
+
+	dev_dbg(&spi->dev, "%s\n", __func__);
+
+	spi->bits_per_word = 9;
+	spi->mode = SPI_MODE_3;
+
+	r = spi_setup(spi);
+	if (r < 0) {
+		dev_err(&spi->dev, "spi_setup failed: %d\n", r);
+		return r;
+	}
+
+	ddata = devm_kzalloc(&spi->dev, sizeof(*ddata), GFP_KERNEL);
+	if (ddata == NULL)
+		return -ENOMEM;
+
+	dev_set_drvdata(&spi->dev, ddata);
+
+	ddata->spi_dev = spi;
+
+	if (dev_get_platdata(&spi->dev)) {
+		r = td028ttec1_panel_probe_pdata(spi);
+		if (r)
+			return r;
+	} else {
+		return -ENODEV;
+	}
+
+	ddata->videomode = td028ttec1_panel_timings;
+
+	dssdev = &ddata->dssdev;
+	dssdev->dev = &spi->dev;
+	dssdev->driver = &td028ttec1_ops;
+	dssdev->type = OMAP_DISPLAY_TYPE_DPI;
+	dssdev->owner = THIS_MODULE;
+	dssdev->panel.timings = ddata->videomode;
+	dssdev->phy.dpi.data_lines = ddata->data_lines;
+
+	r = omapdss_register_display(dssdev);
+	if (r) {
+		dev_err(&spi->dev, "Failed to register panel\n");
+		goto err_reg;
+	}
+
+	return 0;
+
+err_reg:
+	omap_dss_put_device(ddata->in);
+	return r;
+}
+
+static int td028ttec1_panel_remove(struct spi_device *spi)
+{
+	struct panel_drv_data *ddata = dev_get_drvdata(&spi->dev);
+	struct omap_dss_device *dssdev = &ddata->dssdev;
+	struct omap_dss_device *in = ddata->in;
+
+	dev_dbg(&ddata->spi_dev->dev, "%s\n", __func__);
+
+	omapdss_unregister_display(dssdev);
+
+	td028ttec1_panel_disable(dssdev);
+	td028ttec1_panel_disconnect(dssdev);
+
+	omap_dss_put_device(in);
+
+	return 0;
+}
+
+static struct spi_driver td028ttec1_spi_driver = {
+	.probe		= td028ttec1_panel_probe,
+	.remove		= td028ttec1_panel_remove,
+
+	.driver         = {
+		.name   = "panel-tpo-td028ttec1",
+		.owner  = THIS_MODULE,
+	},
+};
+
+module_spi_driver(td028ttec1_spi_driver);
+
+MODULE_AUTHOR("H. Nikolaus Schaller <hns@goldelico.com>");
+MODULE_DESCRIPTION("Toppoly TD028TTEC1 panel driver");
+MODULE_LICENSE("GPL");
diff --git a/include/video/omap-panel-data.h b/include/video/omap-panel-data.h
index f7ac8d972af0..69279c013ac4 100644
--- a/include/video/omap-panel-data.h
+++ b/include/video/omap-panel-data.h
@@ -238,4 +238,17 @@ struct panel_nec_nl8048hl11_platform_data {
 	int qvga_gpio;
 };
 
+/**
+ * panel-tpo-td028ttec1 platform data
+ * @name: name for display entity
+ * @source: name of the display entity used as a video source
+ * @data_lines: number of DPI datalines
+ */
+struct panel_tpo_td028ttec1_platform_data {
+	const char *name;
+	const char *source;
+
+	int data_lines;
+};
+
 #endif /* __OMAP_PANEL_DATA_H */
-- 
cgit 


From 839e928f5bbb695c31ddc23cf3fae3cf1c9e9f20 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:29:51 +0800
Subject: ACPICA: Add EXPORT_ACPI_INTERFACES macro to external interface
 modules.

For Linux, there are no functional changes/binary generation differences
introduced by this patch.

This change adds a new macro to all files that contain external ACPICA
interfaces. It can be detected and used by the host (via the host-specific
header) for any special processing required for such modules. Lv Zheng.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/evxface.c   |  3 ++-
 drivers/acpi/acpica/evxfevnt.c  |  3 ++-
 drivers/acpi/acpica/evxfgpe.c   |  3 ++-
 drivers/acpi/acpica/evxfregn.c  |  3 ++-
 drivers/acpi/acpica/hwtimer.c   |  3 ++-
 drivers/acpi/acpica/hwxface.c   |  3 ++-
 drivers/acpi/acpica/hwxfsleep.c |  3 ++-
 drivers/acpi/acpica/nsxfeval.c  |  3 ++-
 drivers/acpi/acpica/nsxfname.c  |  3 ++-
 drivers/acpi/acpica/nsxfobj.c   |  3 ++-
 drivers/acpi/acpica/rsxface.c   |  3 ++-
 drivers/acpi/acpica/tbxface.c   |  3 ++-
 drivers/acpi/acpica/tbxfload.c  |  3 ++-
 drivers/acpi/acpica/utdebug.c   |  3 ++-
 drivers/acpi/acpica/utdecode.c  |  1 -
 drivers/acpi/acpica/utexcep.c   |  3 ++-
 drivers/acpi/acpica/utglobal.c  |  2 +-
 drivers/acpi/acpica/utxface.c   |  3 ++-
 drivers/acpi/acpica/utxferror.c |  3 ++-
 drivers/acpi/acpica/utxfinit.c  |  3 ++-
 include/acpi/platform/aclinux.h | 12 ++++++++----
 21 files changed, 45 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 6f56146a6f88..6d88b1368088 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index 7039606a0ba8..39d06af5e347 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "actables.h"
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 7662f1a42ff6..fab40d9b3bd6 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acevents.h"
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index 80cecf838591..1bd3225be468 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -42,7 +42,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 2d7d22ebc782..3c498dc1636e 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index d3682c2ae0d1..b1568481463a 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index f2e669db8b65..4895fca102dd 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index 481a6b4a9b2f..a6e3bca48567 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -42,7 +42,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 83c164434580..3a6d78a3f64e 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -42,7 +42,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index c0853ef294e4..94e961cf6294 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -42,7 +42,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 94e3517554f9..01e476988aae 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acresrc.h"
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index ad11162482ff..2ad853275e39 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "actables.h"
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 0ba9e328d5d7..2620dbe96cfa 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index ffd0db509d34..1a67b3944b3b 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 11e2e02e1618..b3f31dd89a45 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -41,7 +41,6 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acnamesp.h"
diff --git a/drivers/acpi/acpica/utexcep.c b/drivers/acpi/acpica/utexcep.c
index ff6d9e8aa842..3cf7b597edb9 100644
--- a/drivers/acpi/acpica/utexcep.c
+++ b/drivers/acpi/acpica/utexcep.c
@@ -41,8 +41,9 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
+#define EXPORT_ACPI_INTERFACES
+
 #define ACPI_DEFINE_EXCEPTION_TABLE
-#include <linux/export.h>
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 046d5b059c07..4f59784b397d 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -41,9 +41,9 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
+#define EXPORT_ACPI_INTERFACES
 #define DEFINE_ACPI_GLOBALS
 
-#include <linux/export.h>
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 03a211e6e26a..2178da8af1a7 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acdebug.h"
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index e966a2e47b76..f7edb88f6054 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 41ebaaf8bb1a..dda18e622a93 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -41,7 +41,8 @@
  * POSSIBILITY OF SUCH DAMAGES.
  */
 
-#include <linux/export.h>
+#define EXPORT_ACPI_INTERFACES
+
 #include <acpi/acpi.h>
 #include "accommon.h"
 #include "acevents.h"
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 7346a9235a4c..0e6e73c04dcb 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -74,7 +74,7 @@
 #define acpi_spinlock                       spinlock_t *
 #define acpi_cpu_flags                      unsigned long
 
-#else /* !__KERNEL__ */
+#else				/* !__KERNEL__ */
 
 #include <stdarg.h>
 #include <string.h>
@@ -102,7 +102,7 @@
 #define __cdecl
 #endif
 
-#endif /* __KERNEL__ */
+#endif				/* __KERNEL__ */
 
 /* Linux uses GCC */
 
@@ -183,6 +183,10 @@ static inline void acpi_os_free(void *a)
 	lock ? AE_OK : AE_NO_MEMORY;				\
 })
 
-#endif /* __KERNEL__ */
+#ifdef EXPORT_ACPI_INTERFACES
+#include <linux/export.h>
+#endif
+
+#endif				/* __KERNEL__ */
 
-#endif /* __ACLINUX_H__ */
+#endif				/* __ACLINUX_H__ */
-- 
cgit 


From bb1cab3d52375b5007645ca55d2b55167e5f757b Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:29:57 +0800
Subject: ACPICA: Clarify ACPI_FREE_BUFFER usage.

Add a comment to clarify reason for using ACPI_FREE_BUFFER directly
instead of ACPI_FREE.

In addition to that, change one instance in which ACPI_FREE_BUFFER()
should be used instead of ACPI_FREE().

[rjw: Subject and changelog]
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/nsxfeval.c |  2 +-
 include/acpi/actypes.h         | 10 +++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index a6e3bca48567..ce2a84575a36 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -139,7 +139,7 @@ acpi_evaluate_object_typed(acpi_handle handle,
 
 		/* Caller used ACPI_ALLOCATE_BUFFER, free the return buffer */
 
-		ACPI_FREE(return_buffer->pointer);
+		ACPI_FREE_BUFFER(*return_buffer);
 		return_buffer->pointer = NULL;
 	}
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 63909d9c2f7a..0bb23e6bce43 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -919,9 +919,13 @@ struct acpi_buffer {
 	void *pointer;		/* pointer to buffer */
 };
 
-/* Free a buffer created in an struct acpi_buffer via ACPI_ALLOCATE_LOCAL_BUFFER */
-
-#define ACPI_FREE_BUFFER(b)         ACPI_FREE(b.pointer)
+/*
+ * Free a buffer created in an struct acpi_buffer via ACPI_ALLOCATE_BUFFER.
+ * Note: We use acpi_os_free here because acpi_os_allocate was used to allocate
+ * the buffer. This purposefully bypasses the internal allocation tracking
+ * mechanism (if it is enabled).
+ */
+#define ACPI_FREE_BUFFER(b)         acpi_os_free((b).pointer)
 
 /*
  * name_type for acpi_get_name
-- 
cgit 


From d21f600b0e4d5a694a338688e61d95f08dbf0afb Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:30:10 +0800
Subject: ACPICA: Deploy ACPI_EXPORT_SYMBOL_INIT for main ACPICA initialization
 interfaces.

This changes can reduce source code differences between Linux and ACPICA
upstream to help improving the release automation.

The side effect of applying this patch in Linux is:
1. Some ACPICA initialization/termination APIs are no longer exported in
   Linux, these include:
    acpi_load_tables
    acpi_initialize_subsystem
    acpi_enable_subsystem
    acpi_initialize_objects
    acpi_terminate
2. This patch does not affect the following APIs as they are currently not
   marked with ACPI_EXPORT_SYMBOL in Linux:
    acpi_reallocate_root_table
    acpi_initialize_tables
Such functions should not be exported as they are internal to ACPI
subsystem in Linux, and will only be invoked inside of ACPI subsystem's
initialization routines marked with __init and termination routines marked
with __exit.  While on other OSPMs, such functions may still need to be
exported.

Thus this patch adds the configurability for ACPICA, so that it leaves
OSPMs to determine if the __init/__exit marked functions should be exported
or not.  Lv Zheng.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/tbxface.c  |  7 ++++++-
 drivers/acpi/acpica/tbxfload.c |  2 +-
 drivers/acpi/acpica/utxface.c  |  2 +-
 drivers/acpi/acpica/utxfinit.c |  9 ++++++---
 include/acpi/actypes.h         | 13 +++++++++++--
 5 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index bbaad5c4e2cd..7e63090742dc 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -148,6 +148,8 @@ acpi_initialize_tables(struct acpi_table_desc * initial_table_array,
 	return_ACPI_STATUS(status);
 }
 
+ACPI_EXPORT_SYMBOL_INIT(acpi_initialize_tables)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_reallocate_root_table
@@ -182,6 +184,8 @@ acpi_status acpi_reallocate_root_table(void)
 	return_ACPI_STATUS(status);
 }
 
+ACPI_EXPORT_SYMBOL_INIT(acpi_reallocate_root_table)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_get_table_header
@@ -357,6 +361,7 @@ acpi_get_table_with_size(char *signature,
 
 	return (AE_NOT_FOUND);
 }
+
 ACPI_EXPORT_SYMBOL(acpi_get_table_with_size)
 
 acpi_status
@@ -368,6 +373,7 @@ acpi_get_table(char *signature,
 	return acpi_get_table_with_size(signature,
 		       instance, out_table, &tbl_size);
 }
+
 ACPI_EXPORT_SYMBOL(acpi_get_table)
 
 /*******************************************************************************
@@ -425,7 +431,6 @@ acpi_get_table_by_index(u32 table_index, struct acpi_table_header **table)
 
 ACPI_EXPORT_SYMBOL(acpi_get_table_by_index)
 
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_table_handler
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 5a2202495b0f..b1e1edd5703a 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -83,7 +83,7 @@ acpi_status acpi_load_tables(void)
 	return_ACPI_STATUS(status);
 }
 
-ACPI_EXPORT_SYMBOL(acpi_load_tables)
+ACPI_EXPORT_SYMBOL_INIT(acpi_load_tables)
 
 /*******************************************************************************
  *
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 2178da8af1a7..891a37b69d3c 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -105,7 +105,7 @@ acpi_status acpi_terminate(void)
 	return_ACPI_STATUS(status);
 }
 
-ACPI_EXPORT_SYMBOL(acpi_terminate)
+ACPI_EXPORT_SYMBOL_INIT(acpi_terminate)
 
 #ifndef ACPI_ASL_COMPILER
 #ifdef ACPI_FUTURE_USAGE
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index dda18e622a93..ff6f4d194136 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -125,7 +125,8 @@ acpi_status acpi_initialize_subsystem(void)
 	ACPI_DEBUGGER_EXEC(status = acpi_db_initialize());
 	return_ACPI_STATUS(status);
 }
-ACPI_EXPORT_SYMBOL(acpi_initialize_subsystem)
+
+ACPI_EXPORT_SYMBOL_INIT(acpi_initialize_subsystem)
 
 /*******************************************************************************
  *
@@ -229,7 +230,8 @@ acpi_status acpi_enable_subsystem(u32 flags)
 
 	return_ACPI_STATUS(status);
 }
-ACPI_EXPORT_SYMBOL(acpi_enable_subsystem)
+
+ACPI_EXPORT_SYMBOL_INIT(acpi_enable_subsystem)
 
 /*******************************************************************************
  *
@@ -315,4 +317,5 @@ acpi_status acpi_initialize_objects(u32 flags)
 	acpi_gbl_startup_flags |= ACPI_INITIALIZED_OK;
 	return_ACPI_STATUS(status);
 }
-ACPI_EXPORT_SYMBOL(acpi_initialize_objects)
+
+ACPI_EXPORT_SYMBOL_INIT(acpi_initialize_objects)
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 0bb23e6bce43..8614bc139113 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -299,9 +299,18 @@ typedef u32 acpi_physical_address;
 #endif
 
 /*
- * All ACPICA functions that are available to the rest of the kernel are
- * tagged with this macro which can be defined as appropriate for the host.
+ * All ACPICA external functions that are available to the rest of the kernel
+ * are tagged with thes macros which can be defined as appropriate for the host.
+ *
+ * Notes:
+ * ACPI_EXPORT_SYMBOL_INIT is used for initialization and termination
+ * interfaces that may need special processing.
+ * ACPI_EXPORT_SYMBOL is used for all other public external functions.
  */
+#ifndef ACPI_EXPORT_SYMBOL_INIT
+#define ACPI_EXPORT_SYMBOL_INIT(symbol)
+#endif
+
 #ifndef ACPI_EXPORT_SYMBOL
 #define ACPI_EXPORT_SYMBOL(symbol)
 #endif
-- 
cgit 


From 4506bf2329cab39d41f027cdccb1cf455de2bf79 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:30:16 +0800
Subject: ACPICA: Prevent possible build issues for use of ACPI_PRINTF_LIKE
 macro

The following build error:
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   CC      arch/x86/kernel/setup.o
 In file included from include/acpi/acpi.h:64:0,
                  from include/linux/iscsi_ibft.h:24,
                  from arch/x86/kernel/setup.c:43:
 include/acpi/acpixf.h:543:1: error: expected ',' or ';' before '{' token
 include/acpi/acpixf.h:540:1: warning: 'acpi_error' declared 'static' but never defined [-Wunused-function]
 make[2]: *** [arch/x86/kernel/setup.o] Error 1
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
can be triggerred by the following stub function (if implemented):
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 static inline void ACPI_INTERNAL_VAR_XFACE
 acpi_error(const char *module_name,
 	   u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3)
 {
 }
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This patch changes the position of ACPI_PRINTF_LIKE(x) to follow the
style of __printf(x, x+1) used in Linux to prevent such issues from
happening.  Lv Zheng.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index ddde61b43041..9759bd5f4777 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -530,50 +530,53 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 /*
  * Error/Warning output
  */
+ACPI_PRINTF_LIKE(3)
 void ACPI_INTERNAL_VAR_XFACE
-acpi_error(const char *module_name,
-	   u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3);
+acpi_error(const char *module_name, u32 line_number, const char *format, ...);
 
+ACPI_PRINTF_LIKE(4)
 void ACPI_INTERNAL_VAR_XFACE
 acpi_exception(const char *module_name,
-	       u32 line_number,
-	       acpi_status status, const char *format, ...) ACPI_PRINTF_LIKE(4);
+	       u32 line_number, acpi_status status, const char *format, ...);
 
+ACPI_PRINTF_LIKE(3)
 void ACPI_INTERNAL_VAR_XFACE
-acpi_warning(const char *module_name,
-	     u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3);
+acpi_warning(const char *module_name, u32 line_number, const char *format, ...);
 
+ACPI_PRINTF_LIKE(3)
 void ACPI_INTERNAL_VAR_XFACE
-acpi_info(const char *module_name,
-	  u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3);
+acpi_info(const char *module_name, u32 line_number, const char *format, ...);
 
+ACPI_PRINTF_LIKE(3)
 void ACPI_INTERNAL_VAR_XFACE
 acpi_bios_error(const char *module_name,
-		u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3);
+		u32 line_number, const char *format, ...);
 
+ACPI_PRINTF_LIKE(3)
 void ACPI_INTERNAL_VAR_XFACE
 acpi_bios_warning(const char *module_name,
-		  u32 line_number, const char *format, ...) ACPI_PRINTF_LIKE(3);
+		  u32 line_number, const char *format, ...);
 
 /*
  * Debug output
  */
 #ifdef ACPI_DEBUG_OUTPUT
 
+ACPI_PRINTF_LIKE(6)
 void ACPI_INTERNAL_VAR_XFACE
 acpi_debug_print(u32 requested_debug_level,
 		 u32 line_number,
 		 const char *function_name,
 		 const char *module_name,
-		 u32 component_id, const char *format, ...) ACPI_PRINTF_LIKE(6);
+		 u32 component_id, const char *format, ...);
 
+ACPI_PRINTF_LIKE(6)
 void ACPI_INTERNAL_VAR_XFACE
 acpi_debug_print_raw(u32 requested_debug_level,
 		     u32 line_number,
 		     const char *function_name,
 		     const char *module_name,
-		     u32 component_id,
-		     const char *format, ...) ACPI_PRINTF_LIKE(6);
+		     u32 component_id, const char *format, ...);
 #endif
 
 #endif				/* __ACXFACE_H__ */
-- 
cgit 


From cd27d79f56e77924b6c66fa4a48306209b93605f Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:30:22 +0800
Subject: ACPICA: Fix indentation issues for macro invocations.

During the automatic translation of the upstream ACPICA source code
into Linux kernel source code some extra white spaces are added by
the "indent" program at the beginning of each line which is an
invocation of a macro and there is no ";" at the end of the line.

For this reason, a new mode has been added to the translation scripts
to remove the extra spaces inserted before invoking such macros and add
an empty line between the invocations of such macros (like the other
function declarations).  This new mode is executed after executing
"indent" during the Linux release process.  Consequently, some
existing ACPICA source code in the Linux kernel tree needs to be
adjusted to allow the new scripts to work correctly.

The affected macros and files are:
 1. ACPI_HW_DEPENDENT_RETURN (acpixf.h/acdebug.h/acevents.h):
    This macro is used as a wrapper for hardware dependent APIs to offer
    a stub when the reduced hardware is configured during compilation.
 2. ACPI_EXPORT_SYMBOL (utglobal.c):
    This macro is used by Linux to export symbols to be found by Linux
    modules.  All such invocations are well formatted except those
    exported as global variables.

This can help to reduce the source code differences between Linux
and upstream ACPICA, and also help to automate the release process.
No functional or binary generation changes should result from it.
Lv Zheng.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acdebug.h  |  3 ++-
 drivers/acpi/acpica/acevents.h |  3 ++-
 drivers/acpi/acpica/utcache.c  |  2 +-
 drivers/acpi/acpica/utglobal.c |  3 +++
 include/acpi/acpixf.h          | 22 +++++++++++++++++-----
 5 files changed, 25 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 57cdc770fba8..a9fd0b872062 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -113,7 +113,8 @@ void acpi_db_display_handlers(void);
 ACPI_HW_DEPENDENT_RETURN_VOID(void
 			      acpi_db_generate_gpe(char *gpe_arg,
 						   char *block_arg))
- ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_generate_sci(void))
+
+ACPI_HW_DEPENDENT_RETURN_VOID(void acpi_db_generate_sci(void))
 
 /*
  * dbconvert - miscellaneous conversion routines
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 3ae5fd02ae64..41abe552c7a3 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -71,7 +71,8 @@ acpi_status acpi_ev_init_global_lock_handler(void);
 
 ACPI_HW_DEPENDENT_RETURN_OK(acpi_status
 			    acpi_ev_acquire_global_lock(u16 timeout))
- ACPI_HW_DEPENDENT_RETURN_OK(acpi_status acpi_ev_release_global_lock(void))
+
+ACPI_HW_DEPENDENT_RETURN_OK(acpi_status acpi_ev_release_global_lock(void))
  acpi_status acpi_ev_remove_global_lock_handler(void);
 
 /*
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index a877a9647fd9..366bfec4b770 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -65,7 +65,7 @@ ACPI_MODULE_NAME("utcache")
 acpi_status
 acpi_os_create_cache(char *cache_name,
 		     u16 object_size,
-		     u16 max_depth, struct acpi_memory_list ** return_cache)
+		     u16 max_depth, struct acpi_memory_list **return_cache)
 {
 	struct acpi_memory_list *cache;
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 4f59784b397d..77caa4fbcdee 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -378,6 +378,9 @@ acpi_status acpi_ut_init_globals(void)
 /* Public globals */
 
 ACPI_EXPORT_SYMBOL(acpi_gbl_FADT)
+
 ACPI_EXPORT_SYMBOL(acpi_dbg_level)
+
 ACPI_EXPORT_SYMBOL(acpi_dbg_layer)
+
 ACPI_EXPORT_SYMBOL(acpi_current_gpe_count)
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 9759bd5f4777..cb2e74443f35 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -54,6 +54,7 @@
 #include <acpi/acbuffer.h>
 
 extern u8 acpi_gbl_permanent_mmap;
+extern u32 acpi_rsdt_forced;
 
 /*
  * Globals that are publically available
@@ -110,7 +111,6 @@ extern u8 acpi_gbl_disable_ssdt_table_load;
 
 #endif				/* !ACPI_REDUCED_HARDWARE */
 
-extern u32 acpi_rsdt_forced;
 /*
  * Initialization
  */
@@ -130,9 +130,10 @@ acpi_status acpi_terminate(void);
  * Miscellaneous global interfaces
  */
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable(void))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable(void))
 #ifdef ACPI_FUTURE_USAGE
-acpi_status acpi_subsystem_status(void);
+ acpi_status acpi_subsystem_status(void);
 #endif
 
 #ifdef ACPI_FUTURE_USAGE
@@ -172,7 +173,7 @@ acpi_status acpi_load_tables(void);
  */
 acpi_status acpi_reallocate_root_table(void);
 
-acpi_status acpi_find_root_pointer(acpi_size *rsdp_address);
+acpi_status acpi_find_root_pointer(acpi_size * rsdp_address);
 
 acpi_status acpi_unload_table_id(acpi_owner_id id);
 
@@ -184,6 +185,7 @@ acpi_status
 acpi_get_table_with_size(acpi_string signature,
 	       u32 instance, struct acpi_table_header **out_table,
 	       acpi_size *tbl_size);
+
 acpi_status
 acpi_get_table(acpi_string signature,
 	       u32 instance, struct acpi_table_header **out_table);
@@ -274,13 +276,16 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_install_sci_handler(acpi_sci_handler
 							 address,
 							 void *context))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_remove_sci_handler(acpi_sci_handler
 							 address))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_install_global_event_handler
 				 (acpi_gbl_event_handler handler,
 				  void *context))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_install_fixed_event_handler(u32
 								  acpi_event,
@@ -288,10 +293,12 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 								  handler,
 								  void
 								  *context))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_remove_fixed_event_handler(u32 acpi_event,
 								 acpi_event_handler
 								 handler))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_install_gpe_handler(acpi_handle
 							  gpe_device,
@@ -300,6 +307,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 							  acpi_gpe_handler
 							  address,
 							  void *context))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_remove_gpe_handler(acpi_handle gpe_device,
 							 u32 gpe_number,
@@ -336,6 +344,7 @@ acpi_status acpi_install_interface_handler(acpi_interface_handler handler);
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_acquire_global_lock(u16 timeout,
 							 u32 *handle))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_release_global_lock(u32 handle))
 
@@ -362,6 +371,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_get_event_status(u32 event,
 						      acpi_event_status
 						      *event_status))
+
 /*
  * General Purpose Event (GPE) Interfaces
  */
@@ -392,10 +402,12 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 							parent_device,
 							acpi_handle gpe_device,
 							u32 gpe_number))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_set_gpe_wake_mask(acpi_handle gpe_device,
 							u32 gpe_number,
 							u8 action))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_get_gpe_status(acpi_handle gpe_device,
 						     u32 gpe_number,
@@ -417,6 +429,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 						       *gpe_block_address,
 						       u32 register_count,
 						       u32 interrupt_number))
+
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_remove_gpe_block(acpi_handle gpe_device))
 
@@ -491,7 +504,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
  * Sleep/Wake interfaces
  */
 acpi_status
-acpi_get_sleep_type_data(u8 sleep_state, u8 * slp_typ_a, u8 * slp_typ_b);
+acpi_get_sleep_type_data(u8 sleep_state, u8 *slp_typ_a, u8 *slp_typ_b);
 
 acpi_status acpi_enter_sleep_state_prep(u8 sleep_state);
 
@@ -506,7 +519,6 @@ acpi_status acpi_leave_sleep_state(u8 sleep_state);
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_set_firmware_waking_vector(u32
 								physical_address))
-
 #if ACPI_MACHINE_WIDTH == 64
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_set_firmware_waking_vector64(u64
-- 
cgit 


From c0144dc0e43ed97d60ce34c900a4326bb087bf11 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:30:29 +0800
Subject: ACPICA: Simplify configuration of global ACPI_REDUCED_HARDWARE macro.

Surround definition of this with a #ifndef so that the kernel
can define it elsewhere if desired.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acconfig.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 1c16f821434f..d98c67001840 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -100,7 +100,9 @@
  *      ACPI PM timer
  *      FACS table (Waking vectors and Global Lock)
  */
+#ifndef ACPI_REDUCED_HARDWARE
 #define ACPI_REDUCED_HARDWARE           FALSE
+#endif
 
 /******************************************************************************
  *
-- 
cgit 


From 7e94632fc530d990de3110e6c53425d6e28dd238 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:30:35 +0800
Subject: ACPICA: Add support to allow host OS to redefine individual OSL
 prototypes.

This change enables the host OS to redefine OSL prototypes found in the
acpiosxf.h file. This allows the host OS to implement OSL interfaces with
a macro or inlined function. Further, it allows the host OS to add any
additional required modifiers such as __iomem, __init, __exit, etc.,
as necessary on a per-interface basis. Enables maximum flexibility
for the OSL interfaces. Lv Zheng.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpiosxf.h         | 139 +++++++++++++++++++++++++++++++++++++++-
 include/acpi/platform/aclinux.h |   1 +
 2 files changed, 137 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 7f95215e7754..55165fcd77d7 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -77,54 +77,80 @@ struct acpi_signal_fatal_info {
 /*
  * OSL Initialization and shutdown primitives
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize
 acpi_status __init acpi_os_initialize(void);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate
 acpi_status acpi_os_terminate(void);
+#endif
 
 /*
  * ACPI Table interfaces
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_root_pointer
 acpi_physical_address acpi_os_get_root_pointer(void);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_predefined_override
 acpi_status
 acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
 			    acpi_string * new_val);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_table_override
 acpi_status
 acpi_os_table_override(struct acpi_table_header *existing_table,
 		       struct acpi_table_header **new_table);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_physical_table_override
 acpi_status
 acpi_os_physical_table_override(struct acpi_table_header *existing_table,
 				acpi_physical_address * new_address,
 				u32 *new_table_length);
+#endif
 
 /*
  * Spinlock primitives
  */
-#ifndef acpi_os_create_lock
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
 acpi_status acpi_os_create_lock(acpi_spinlock * out_handle);
 #endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_lock
 void acpi_os_delete_lock(acpi_spinlock handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_lock
 acpi_cpu_flags acpi_os_acquire_lock(acpi_spinlock handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_lock
 void acpi_os_release_lock(acpi_spinlock handle, acpi_cpu_flags flags);
+#endif
 
 /*
  * Semaphore primitives
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_semaphore
 acpi_status
 acpi_os_create_semaphore(u32 max_units,
 			 u32 initial_units, acpi_semaphore * out_handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_semaphore
 acpi_status acpi_os_delete_semaphore(acpi_semaphore handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_wait_semaphore
 acpi_status
 acpi_os_wait_semaphore(acpi_semaphore handle, u32 units, u16 timeout);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_signal_semaphore
 acpi_status acpi_os_signal_semaphore(acpi_semaphore handle, u32 units);
+#endif
 
 /*
  * Mutex primitives. May be configured to use semaphores instead via
@@ -132,63 +158,98 @@ acpi_status acpi_os_signal_semaphore(acpi_semaphore handle, u32 units);
  */
 #if (ACPI_MUTEX_TYPE != ACPI_BINARY_SEMAPHORE)
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_mutex
 acpi_status acpi_os_create_mutex(acpi_mutex * out_handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_mutex
 void acpi_os_delete_mutex(acpi_mutex handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_mutex
 acpi_status acpi_os_acquire_mutex(acpi_mutex handle, u16 timeout);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_mutex
 void acpi_os_release_mutex(acpi_mutex handle);
 #endif
 
+#endif
+
 /*
  * Memory allocation and mapping
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_allocate
 void *acpi_os_allocate(acpi_size size);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_allocate_zeroed
 void *acpi_os_allocate_zeroed(acpi_size size);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_free
 void acpi_os_free(void *memory);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_map_memory
 void __iomem *acpi_os_map_memory(acpi_physical_address where,
 				acpi_size length);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_unmap_memory
 void acpi_os_unmap_memory(void __iomem * logical_address, acpi_size size);
+#endif
 void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
 
 #ifdef ACPI_FUTURE_USAGE
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_physical_address
 acpi_status
 acpi_os_get_physical_address(void *logical_address,
 			     acpi_physical_address * physical_address);
 #endif
+#endif
 
 /*
  * Memory/Object Cache
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_cache
 acpi_status
 acpi_os_create_cache(char *cache_name,
 		     u16 object_size,
 		     u16 max_depth, acpi_cache_t ** return_cache);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_delete_cache
 acpi_status acpi_os_delete_cache(acpi_cache_t * cache);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_purge_cache
 acpi_status acpi_os_purge_cache(acpi_cache_t * cache);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_object
 void *acpi_os_acquire_object(acpi_cache_t * cache);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_release_object
 acpi_status acpi_os_release_object(acpi_cache_t * cache, void *object);
+#endif
 
 /*
  * Interrupt handlers
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_install_interrupt_handler
 acpi_status
 acpi_os_install_interrupt_handler(u32 interrupt_number,
 				  acpi_osd_handler service_routine,
 				  void *context);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_remove_interrupt_handler
 acpi_status
 acpi_os_remove_interrupt_handler(u32 interrupt_number,
 				 acpi_osd_handler service_routine);
+#endif
 
 void acpi_os_gpe_count(u32 gpe_number);
 void acpi_os_fixed_event_count(u32 fixed_event_number);
@@ -196,86 +257,158 @@ void acpi_os_fixed_event_count(u32 fixed_event_number);
 /*
  * Threads and Scheduling
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
 acpi_thread_id acpi_os_get_thread_id(void);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_execute
 acpi_status
 acpi_os_execute(acpi_execute_type type,
 		acpi_osd_exec_callback function, void *context);
+#endif
 
 acpi_status
 acpi_os_hotplug_execute(acpi_osd_exec_callback function, void *context);
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_wait_events_complete
 void acpi_os_wait_events_complete(void);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_sleep
 void acpi_os_sleep(u64 milliseconds);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_stall
 void acpi_os_stall(u32 microseconds);
+#endif
 
 /*
  * Platform and hardware-independent I/O interfaces
  */
-acpi_status acpi_os_read_port(acpi_io_address address, u32 * value, u32 width);
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_read_port
+acpi_status acpi_os_read_port(acpi_io_address address, u32 *value, u32 width);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_write_port
 acpi_status acpi_os_write_port(acpi_io_address address, u32 value, u32 width);
+#endif
 
 /*
  * Platform and hardware-independent physical memory interfaces
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_read_memory
 acpi_status
 acpi_os_read_memory(acpi_physical_address address, u64 *value, u32 width);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_write_memory
 acpi_status
 acpi_os_write_memory(acpi_physical_address address, u64 value, u32 width);
+#endif
 
 /*
  * Platform and hardware-independent PCI configuration space access
  * Note: Can't use "Register" as a parameter, changed to "Reg" --
  * certain compilers complain.
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_read_pci_configuration
 acpi_status
 acpi_os_read_pci_configuration(struct acpi_pci_id *pci_id,
 			       u32 reg, u64 *value, u32 width);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_write_pci_configuration
 acpi_status
 acpi_os_write_pci_configuration(struct acpi_pci_id *pci_id,
 				u32 reg, u64 value, u32 width);
+#endif
 
 /*
  * Miscellaneous
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_readable
+u8 acpi_os_readable(void *pointer, acpi_size length);
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_writable
+u8 acpi_os_writable(void *pointer, acpi_size length);
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_timer
 u64 acpi_os_get_timer(void);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_signal
 acpi_status acpi_os_signal(u32 function, void *info);
+#endif
 
 /*
  * Debug print routines
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_printf
 void ACPI_INTERNAL_VAR_XFACE acpi_os_printf(const char *format, ...);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_vprintf
 void acpi_os_vprintf(const char *format, va_list args);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_redirect_output
 void acpi_os_redirect_output(void *destination);
+#endif
 
 #ifdef ACPI_FUTURE_USAGE
 /*
  * Debug input
  */
-u32 acpi_os_get_line(char *buffer);
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_line
+acpi_status acpi_os_get_line(char *buffer, u32 buffer_length, u32 *bytes_read);
+#endif
+#endif
+
+/*
+ * Obtain ACPI table(s)
+ */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_name
+acpi_status
+acpi_os_get_table_by_name(char *signature,
+			  u32 instance,
+			  struct acpi_table_header **table,
+			  acpi_physical_address * address);
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_index
+acpi_status
+acpi_os_get_table_by_index(u32 index,
+			   struct acpi_table_header **table,
+			   u32 *instance, acpi_physical_address * address);
+#endif
+
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_address
+acpi_status
+acpi_os_get_table_by_address(acpi_physical_address address,
+			     struct acpi_table_header **table);
 #endif
 
 /*
  * Directory manipulation
  */
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_open_directory
 void *acpi_os_open_directory(char *pathname,
 			     char *wildcard_spec, char requested_file_type);
+#endif
 
 /* requeste_file_type values */
 
 #define REQUEST_FILE_ONLY                   0
 #define REQUEST_DIR_ONLY                    1
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_next_filename
 char *acpi_os_get_next_filename(void *dir_handle);
+#endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_close_directory
 void acpi_os_close_directory(void *dir_handle);
+#endif
 
 #endif				/* __ACPIOSXF_H__ */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 0e6e73c04dcb..04e87a3b8086 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -182,6 +182,7 @@ static inline void acpi_os_free(void *a)
 	}							\
 	lock ? AE_OK : AE_NO_MEMORY;				\
 })
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
 
 #ifdef EXPORT_ACPI_INTERFACES
 #include <linux/export.h>
-- 
cgit 


From 93220587f76b8a4eca89cb655fc0cc04e9da663d Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Tue, 29 Oct 2013 09:30:41 +0800
Subject: ACPICA: Update aclinux.h for new OSL override mechanism.

The new ACPICA OSL override mechanism is used to solve these issues
for the Linux OSL:
 1. Linux can implement OSL using a macro.
 2. Linux can implement OSL using an inlined function.
 3. Linux can leave OSL not implemented for __KERNEL__ undefined code
    fragments.
 4. Linux can add sparse declarators (__iomem) to OSL.
 5. Linux can add memory tuning declarators (__init/__exit) to OSL.
This patch also moves Linux specific OSL to aclinux.h which has not been
maintained in the ACPICA code base.  Lv Zheng.

Known issue:

 From ACPICA's perspective, actypes.h should be included after inclusion
 of acenv.h.  But currently in Linux, aclinux.h included by acenv.h has
 included actypes.h to find ACPICA types for inline functions.  This is a
 known and existing issue and currently there is no real problem caused
 by this issue for Linux kernel build.  Thus this issue is not covered by
 this cleanup commit.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpiosxf.h         |  18 +-----
 include/acpi/platform/aclinux.h | 118 ++++++++++++++++++++++++++++++----------
 2 files changed, 91 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 55165fcd77d7..01e6c6d8b7e1 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -78,7 +78,7 @@ struct acpi_signal_fatal_info {
  * OSL Initialization and shutdown primitives
  */
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize
-acpi_status __init acpi_os_initialize(void);
+acpi_status acpi_os_initialize(void);
 #endif
 
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate
@@ -192,22 +192,18 @@ void acpi_os_free(void *memory);
 #endif
 
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_map_memory
-void __iomem *acpi_os_map_memory(acpi_physical_address where,
-				acpi_size length);
+void *acpi_os_map_memory(acpi_physical_address where, acpi_size length);
 #endif
 
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_unmap_memory
-void acpi_os_unmap_memory(void __iomem * logical_address, acpi_size size);
+void acpi_os_unmap_memory(void *logical_address, acpi_size size);
 #endif
-void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
 
-#ifdef ACPI_FUTURE_USAGE
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_physical_address
 acpi_status
 acpi_os_get_physical_address(void *logical_address,
 			     acpi_physical_address * physical_address);
 #endif
-#endif
 
 /*
  * Memory/Object Cache
@@ -251,9 +247,6 @@ acpi_os_remove_interrupt_handler(u32 interrupt_number,
 				 acpi_osd_handler service_routine);
 #endif
 
-void acpi_os_gpe_count(u32 gpe_number);
-void acpi_os_fixed_event_count(u32 fixed_event_number);
-
 /*
  * Threads and Scheduling
  */
@@ -267,9 +260,6 @@ acpi_os_execute(acpi_execute_type type,
 		acpi_osd_exec_callback function, void *context);
 #endif
 
-acpi_status
-acpi_os_hotplug_execute(acpi_osd_exec_callback function, void *context);
-
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_wait_events_complete
 void acpi_os_wait_events_complete(void);
 #endif
@@ -357,14 +347,12 @@ void acpi_os_vprintf(const char *format, va_list args);
 void acpi_os_redirect_output(void *destination);
 #endif
 
-#ifdef ACPI_FUTURE_USAGE
 /*
  * Debug input
  */
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_line
 acpi_status acpi_os_get_line(char *buffer, u32 buffer_length, u32 *bytes_read);
 #endif
-#endif
 
 /*
  * Obtain ACPI table(s)
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 04e87a3b8086..ab57930794a5 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -50,7 +50,6 @@
 #define ACPI_USE_DO_WHILE_0
 #define ACPI_MUTEX_TYPE             ACPI_BINARY_SEMAPHORE
 
-
 #ifdef __KERNEL__
 
 #include <linux/string.h>
@@ -58,11 +57,13 @@
 #include <linux/ctype.h>
 #include <linux/sched.h>
 #include <linux/atomic.h>
-#include <asm/div64.h>
-#include <asm/acpi.h>
+#include <linux/math64.h>
 #include <linux/slab.h>
 #include <linux/spinlock_types.h>
-#include <asm/current.h>
+#ifdef EXPORT_ACPI_INTERFACES
+#include <linux/export.h>
+#endif
+#include <asm/acpi.h>
 
 /* Host-dependent types and defines for in-kernel ACPICA */
 
@@ -109,23 +110,29 @@
 #include <acpi/platform/acgcc.h>
 
 #ifdef __KERNEL__
+
+/*
+ * FIXME: Inclusion of actypes.h
+ * Linux kernel need this before defining inline OSL interfaces as
+ * actypes.h need to be included to find ACPICA type definitions.
+ * Since from ACPICA's perspective, the actypes.h should be included after
+ * acenv.h (aclinux.h), this leads to a inclusion mis-ordering issue.
+ */
 #include <acpi/actypes.h>
+
 /*
  * Overrides for in-kernel ACPICA
  */
-static inline acpi_thread_id acpi_os_get_thread_id(void)
-{
-	return (acpi_thread_id)(unsigned long)current;
-}
+acpi_status __init acpi_os_initialize(void);
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize
+
+acpi_status acpi_os_terminate(void);
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate
 
 /*
  * Memory allocation/deallocation
  */
 
-/* Use native linux version of acpi_os_allocate_zeroed */
-
-#define USE_NATIVE_ALLOCATE_ZEROED
-
 /*
  * The irqs_disabled() check is for resume from RAM.
  * Interrupts are off during resume, just like they are for boot.
@@ -134,26 +141,45 @@ static inline acpi_thread_id acpi_os_get_thread_id(void)
  */
 static inline void *acpi_os_allocate(acpi_size size)
 {
-	return kmalloc(size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
+	return kmalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
 }
 
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_allocate
+
+/* Use native linux version of acpi_os_allocate_zeroed */
+
 static inline void *acpi_os_allocate_zeroed(acpi_size size)
 {
-	return kzalloc(size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
+	return kzalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
+}
+
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_allocate_zeroed
+#define USE_NATIVE_ALLOCATE_ZEROED
+
+static inline void acpi_os_free(void *memory)
+{
+	kfree(memory);
 }
 
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_free
+
 static inline void *acpi_os_acquire_object(acpi_cache_t * cache)
 {
 	return kmem_cache_zalloc(cache,
-		irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
+				 irqs_disabled()? GFP_ATOMIC : GFP_KERNEL);
 }
 
-static inline void acpi_os_free(void *a)
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_acquire_object
+
+static inline acpi_thread_id acpi_os_get_thread_id(void)
 {
-	kfree(a);
+	return (acpi_thread_id) (unsigned long)current;
 }
 
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
+
 #ifndef CONFIG_PREEMPT
+
 /*
  * Used within ACPICA to show where it is safe to preempt execution
  * when CONFIG_PREEMPT=n
@@ -163,6 +189,7 @@ static inline void acpi_os_free(void *a)
 		if (!irqs_disabled()) \
 			cond_resched(); \
 	} while (0)
+
 #endif
 
 /*
@@ -172,21 +199,52 @@ static inline void acpi_os_free(void *a)
  * all locks to the name of the argument of acpi_os_create_lock(), which
  * prevents lockdep from reporting false positives for ACPICA locks.
  */
-#define acpi_os_create_lock(__handle)				\
-({								\
-	spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock));	\
-								\
-	if (lock) {						\
-		*(__handle) = lock;				\
-		spin_lock_init(*(__handle));			\
-	}							\
-	lock ? AE_OK : AE_NO_MEMORY;				\
-})
+#define acpi_os_create_lock(__handle) \
+	({ \
+		spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
+		if (lock) { \
+			*(__handle) = lock; \
+			spin_lock_init(*(__handle)); \
+		} \
+		lock ? AE_OK : AE_NO_MEMORY; \
+	})
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
 
-#ifdef EXPORT_ACPI_INTERFACES
-#include <linux/export.h>
-#endif
+void __iomem *acpi_os_map_memory(acpi_physical_address where, acpi_size length);
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_map_memory
+
+void acpi_os_unmap_memory(void __iomem * logical_address, acpi_size size);
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_unmap_memory
+
+/*
+ * OSL interfaces used by debugger/disassembler
+ */
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_readable
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_writable
+
+/*
+ * OSL interfaces used by utilities
+ */
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_redirect_output
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_line
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_name
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_index
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_table_by_address
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_open_directory
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_next_filename
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_close_directory
+
+/*
+ * OSL interfaces added by Linux
+ */
+void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
+
+void acpi_os_gpe_count(u32 gpe_number);
+
+void acpi_os_fixed_event_count(u32 fixed_event_number);
+
+acpi_status
+acpi_os_hotplug_execute(acpi_osd_exec_callback function, void *context);
 
 #endif				/* __KERNEL__ */
 
-- 
cgit 


From affffae367c7ee1003232201c52db1fd7dd4f472 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Tue, 29 Oct 2013 09:30:48 +0800
Subject: ACPICA: Update version to 20130927.

Version 20130927.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index cb2e74443f35..b2dcab0438c6 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20130823
+#define ACPI_CA_VERSION                 0x20130927
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit 


From 09b8b1fce7688958f44884135b83fb857eb6e1b6 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:30:16 +0800
Subject: ACPICA: Update RSDP table definitions.

This patch updates RSDP table header definitions as such enhancement
has been made in ACPICA upstream already.  It ports that change to
the Linux source to reduce source code differences between Linux and
ACPICA upstream.

This patch does not affect the generation of the Linux kernel binary.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl.h | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 9b58a8f43771..94970880126f 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -146,7 +146,24 @@ struct acpi_table_rsdp {
 	u8 reserved[3];		/* Reserved, must be zero */
 };
 
-#define ACPI_RSDP_REV0_SIZE     20	/* Size of original ACPI 1.0 RSDP */
+/* Standalone struct for the ACPI 1.0 RSDP */
+
+struct acpi_rsdp_common {
+	char signature[8];
+	u8 checksum;
+	char oem_id[ACPI_OEM_ID_SIZE];
+	u8 revision;
+	u32 rsdt_physical_address;
+};
+
+/* Standalone struct for the extended part of the RSDP (ACPI 2.0+) */
+
+struct acpi_rsdp_extension {
+	u32 length;
+	u64 xsdt_physical_address;
+	u8 extended_checksum;
+	u8 reserved[3];
+};
 
 /*******************************************************************************
  *
-- 
cgit 


From fa5f508f942faaf73ae5020db7a4189d5ca88d2a Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:30:22 +0800
Subject: ACPICA: Update DMAR table definitions.

This patch updates DMAR table header definitions as such enhancement
has been made in ACPICA upstream already.  It ports that change to
the Linux source to reduce source code differences between Linux and
ACPICA upstream.

Build test done on x86-64 machine with the following configs enabled:
  CONFIG_DMAR_TABLE
  CONFIG_IRQ_REMAP
  CONFIG_INTEL_IOMMU

This patch does not affect the generation of the Linux kernel binary.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/iommu/dmar.c                | 4 ++--
 drivers/iommu/intel_irq_remapping.c | 8 ++++----
 include/acpi/actbl2.h               | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 785675a56a10..900946950230 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -88,7 +88,7 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 			pr_warn("Device scope bus [%d] not found\n", scope->bus);
 			break;
 		}
-		pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn));
+		pdev = pci_get_slot(bus, PCI_DEVFN(path->device, path->function));
 		if (!pdev) {
 			/* warning will be printed below */
 			break;
@@ -99,7 +99,7 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 	}
 	if (!pdev) {
 		pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n",
-			segment, scope->bus, path->dev, path->fn);
+			segment, scope->bus, path->device, path->function);
 		*dev = NULL;
 		return 0;
 	}
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index f71673dbb23d..ab86902fd9ff 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -686,12 +686,12 @@ static void ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
 		 * Access PCI directly due to the PCI
 		 * subsystem isn't initialized yet.
 		 */
-		bus = read_pci_config_byte(bus, path->dev, path->fn,
+		bus = read_pci_config_byte(bus, path->device, path->function,
 					   PCI_SECONDARY_BUS);
 		path++;
 	}
 	ir_hpet[ir_hpet_num].bus   = bus;
-	ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_hpet[ir_hpet_num].devfn = PCI_DEVFN(path->device, path->function);
 	ir_hpet[ir_hpet_num].iommu = iommu;
 	ir_hpet[ir_hpet_num].id    = scope->enumeration_id;
 	ir_hpet_num++;
@@ -714,13 +714,13 @@ static void ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
 		 * Access PCI directly due to the PCI
 		 * subsystem isn't initialized yet.
 		 */
-		bus = read_pci_config_byte(bus, path->dev, path->fn,
+		bus = read_pci_config_byte(bus, path->device, path->function,
 					   PCI_SECONDARY_BUS);
 		path++;
 	}
 
 	ir_ioapic[ir_ioapic_num].bus   = bus;
-	ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->dev, path->fn);
+	ir_ioapic[ir_ioapic_num].devfn = PCI_DEVFN(path->device, path->function);
 	ir_ioapic[ir_ioapic_num].iommu = iommu;
 	ir_ioapic[ir_ioapic_num].id    = scope->enumeration_id;
 	ir_ioapic_num++;
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index ffaac0e7e0c6..40f7ed115452 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -444,8 +444,8 @@ enum acpi_dmar_scope_type {
 };
 
 struct acpi_dmar_pci_path {
-	u8 dev;
-	u8 fn;
+	u8 device;
+	u8 function;
 };
 
 /*
-- 
cgit 


From 9187a415fd119c1d89a5ad2fd05513cd43699ebf Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:30:28 +0800
Subject: ACPICA: Add new statistics interface.

This patch ports new counters and statistics interface, already
implemented in ACPICA upstream, to Linux.  That helps to reduce
source code differences between Linux and ACPICA upstream.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acglobal.h |  2 ++
 drivers/acpi/acpica/dsmethod.c |  1 +
 drivers/acpi/acpica/evsci.c    |  1 +
 drivers/acpi/acpica/utglobal.c | 12 ++++++++++++
 drivers/acpi/acpica/utxface.c  | 38 ++++++++++++++++++++++++++++++++++++++
 include/acpi/acpixf.h          |  2 ++
 include/acpi/actypes.h         | 10 ++++++++++
 7 files changed, 66 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 0fba431f4fcb..e9f1fc7f99c7 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -406,7 +406,9 @@ extern u32 acpi_gbl_nesting_level;
 
 /* Event counters */
 
+ACPI_EXTERN u32 acpi_method_count;
 ACPI_EXTERN u32 acpi_gpe_count;
+ACPI_EXTERN u32 acpi_sci_count;
 ACPI_EXTERN u32 acpi_fixed_event_count[ACPI_NUM_FIXED_EVENTS];
 
 /* Support for dynamic control method tracing mechanism */
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index df3ea125507f..81a78ba84311 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -292,6 +292,7 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node,
 	 * reentered one more time (even if it is the same thread)
 	 */
 	obj_desc->method.thread_count++;
+	acpi_method_count++;
 	return_ACPI_STATUS(status);
 
 cleanup:
diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index 94d9ebddf575..9e9e3454d893 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -137,6 +137,7 @@ static u32 ACPI_SYSTEM_XFACE acpi_ev_sci_xrupt_handler(void *context)
 
 	interrupt_handled |= acpi_ev_sci_dispatch();
 
+	acpi_sci_count++;
 	return_UINT32(interrupt_handled);
 }
 
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 77caa4fbcdee..81f9a9584451 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -289,6 +289,16 @@ acpi_status acpi_ut_init_globals(void)
 
 	acpi_gbl_owner_id_mask[ACPI_NUM_OWNERID_MASKS - 1] = 0x80000000;
 
+	/* Event counters */
+
+	acpi_method_count = 0;
+	acpi_sci_count = 0;
+	acpi_gpe_count = 0;
+
+	for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) {
+		acpi_fixed_event_count[i] = 0;
+	}
+
 #if (!ACPI_REDUCED_HARDWARE)
 
 	/* GPE/SCI support */
@@ -383,4 +393,6 @@ ACPI_EXPORT_SYMBOL(acpi_dbg_level)
 
 ACPI_EXPORT_SYMBOL(acpi_dbg_layer)
 
+ACPI_EXPORT_SYMBOL(acpi_gpe_count)
+
 ACPI_EXPORT_SYMBOL(acpi_current_gpe_count)
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 891a37b69d3c..39869022a417 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -208,6 +208,44 @@ acpi_status acpi_get_system_info(struct acpi_buffer * out_buffer)
 
 ACPI_EXPORT_SYMBOL(acpi_get_system_info)
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_get_statistics
+ *
+ * PARAMETERS:  stats           - Where the statistics are returned
+ *
+ * RETURN:      status          - the status of the call
+ *
+ * DESCRIPTION: Get the contents of the various system counters
+ *
+ ******************************************************************************/
+acpi_status acpi_get_statistics(struct acpi_statistics *stats)
+{
+	ACPI_FUNCTION_TRACE(acpi_get_statistics);
+
+	/* Parameter validation */
+
+	if (!stats) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	/* Various interrupt-based event counters */
+
+	stats->sci_count = acpi_sci_count;
+	stats->gpe_count = acpi_gpe_count;
+
+	ACPI_MEMCPY(stats->fixed_event_count, acpi_fixed_event_count,
+		    sizeof(acpi_fixed_event_count));
+
+	/* Other counters */
+
+	stats->method_count = acpi_method_count;
+
+	return_ACPI_STATUS(AE_OK);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_get_statistics)
+
 /*****************************************************************************
  *
  * FUNCTION:    acpi_install_initialization_handler
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index b2dcab0438c6..7def8cabfaba 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -140,6 +140,8 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable(void))
 acpi_status acpi_get_system_info(struct acpi_buffer *ret_buffer);
 #endif
 
+acpi_status acpi_get_statistics(struct acpi_statistics *stats);
+
 const char *acpi_format_exception(acpi_status exception);
 
 acpi_status acpi_purge_cached_objects(void);
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 8614bc139113..0e32b6cab6e6 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -973,6 +973,16 @@ struct acpi_system_info {
 	u32 debug_layer;
 };
 
+/*
+ * System statistics returned by acpi_get_statistics()
+ */
+struct acpi_statistics {
+	u32 sci_count;
+	u32 gpe_count;
+	u32 fixed_event_count[ACPI_NUM_FIXED_EVENTS];
+	u32 method_count;
+};
+
 /* Table Event Types */
 
 #define ACPI_TABLE_EVENT_LOAD           0x0
-- 
cgit 


From a4fb614ad01506aa45f894f0f1c912e99cc7fdf1 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:31:06 +0800
Subject: ACPICA: Update compilation environment settings.

This patch updates architecture specific environment settings to reduce
source differences between Linux and ACPICA upstream.

This patch does not affect the generation of the Linux kernel binary.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/platform/acenv.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index ef04b36ca6ed..9b3966c35b33 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -147,6 +147,9 @@
 #if defined(_LINUX) || defined(__linux__)
 #include <acpi/platform/aclinux.h>
 
+#elif defined(_APPLE) || defined(__APPLE__)
+#include "acmacosx.h"
+
 #elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
 #include "acfreebsd.h"
 
-- 
cgit 


From efb835429fff1488e4718138cdf5bc855a6762a4 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:31:12 +0800
Subject: ACPICA: Update acpidump related header file changes.

This patch updates header files used by acpidump to reduce the
source code differences between Linux and ACPICA upstream.

This patch does not affect the generation of the Linux kernel binary.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actypes.h        | 8 ++++++++
 include/acpi/platform/acenv.h | 5 +++--
 2 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 0e32b6cab6e6..809b1a0fee7f 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -315,6 +315,14 @@ typedef u32 acpi_physical_address;
 #define ACPI_EXPORT_SYMBOL(symbol)
 #endif
 
+/*
+ * Compiler/Clibrary-dependent debug initialization. Used for ACPICA
+ * utilities only.
+ */
+#ifndef ACPI_DEBUG_INITIALIZE
+#define ACPI_DEBUG_INITIALIZE()
+#endif
+
 /*******************************************************************************
  *
  * Configuration
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 9b3966c35b33..974d3ef7c141 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -96,10 +96,11 @@
 #endif
 
 /*
- * acpi_bin/acpi_help/acpi_src configuration. All single threaded, with
- * no debug output.
+ * acpi_bin/acpi_dump/acpi_src/acpi_xtract configuration. All single
+ * threaded, with no debug output.
  */
 #if (defined ACPI_BIN_APP)   || \
+	(defined ACPI_DUMP_APP)  || \
 	(defined ACPI_SRC_APP)   || \
 	(defined ACPI_XTRACT_APP)
 #define ACPI_APPLICATION
-- 
cgit 


From 40bce100cafb945f1fb5475a70628b4379c74f38 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:31:18 +0800
Subject: ACPICA: Cleanup asmlinkage for ACPICA APIs.

Add an asmlinkage wrapper around acpi_enter_sleep_state() to prevent
an empty stub from being called by assmebly code for ACPI_REDUCED_HARDWARE
set.

As arch/x86/kernel/acpi/wakeup_xx.S is only compiled when CONFIG_ACPI=y
and there are no users of ACPI_HARDWARE_REDUCED, currently this is in
fact not a real issue, but a cleanup to reduce source code differences
between Linux and ACPICA upstream.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/acpi/sleep.c     | 11 +++++++++++
 arch/x86/kernel/acpi/sleep.h     |  2 ++
 arch/x86/kernel/acpi/wakeup_32.S |  2 +-
 arch/x86/kernel/acpi/wakeup_64.S |  2 +-
 drivers/acpi/acpica/hwxfsleep.c  |  4 ++--
 include/acpi/acpixf.h            |  4 ++--
 6 files changed, 19 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 33120100ff5e..3a2ae4c88948 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -25,6 +25,17 @@ unsigned long acpi_realmode_flags;
 static char temp_stack[4096];
 #endif
 
+/**
+ * x86_acpi_enter_sleep_state - enter sleep state
+ * @state: Sleep state to enter.
+ *
+ * Wrapper around acpi_enter_sleep_state() to be called by assmebly.
+ */
+acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state)
+{
+	return acpi_enter_sleep_state(state);
+}
+
 /**
  * x86_acpi_suspend_lowlevel - save kernel state
  *
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index c9c2c982d5e4..65c7b606b606 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -17,3 +17,5 @@ extern void wakeup_long64(void);
 extern void do_suspend_lowlevel(void);
 
 extern int x86_acpi_suspend_lowlevel(void);
+
+acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state);
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index d1daa66ab162..665c6b7d2ea9 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
 	pushl	$3
-	call	acpi_enter_sleep_state
+	call	x86_acpi_enter_sleep_state
 	addl	$4, %esp
 
 #	In case of S3 failure, we'll emerge here.  Jump
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8ea5164cbd04..ae693b51ed8e 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -73,7 +73,7 @@ ENTRY(do_suspend_lowlevel)
 	addq	$8, %rsp
 	movl	$3, %edi
 	xorl	%eax, %eax
-	call	acpi_enter_sleep_state
+	call	x86_acpi_enter_sleep_state
 	/* in case something went wrong, restore the machine status and go on */
 	jmp	resume_point
 
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 4895fca102dd..15dddc10fc9b 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -167,7 +167,7 @@ ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector64)
  *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
  *
  ******************************************************************************/
-acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void)
+acpi_status acpi_enter_sleep_state_s4bios(void)
 {
 	u32 in_value;
 	acpi_status status;
@@ -361,7 +361,7 @@ ACPI_EXPORT_SYMBOL(acpi_enter_sleep_state_prep)
  *              THIS FUNCTION MUST BE CALLED WITH INTERRUPTS DISABLED
  *
  ******************************************************************************/
-acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state)
+acpi_status acpi_enter_sleep_state(u8 sleep_state)
 {
 	acpi_status status;
 
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 7def8cabfaba..00725f44ac89 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -510,9 +510,9 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 *slp_typ_a, u8 *slp_typ_b);
 
 acpi_status acpi_enter_sleep_state_prep(u8 sleep_state);
 
-acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state);
+acpi_status acpi_enter_sleep_state(u8 sleep_state);
 
-ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enter_sleep_state_s4bios(void))
 
 acpi_status acpi_leave_sleep_state_prep(u8 sleep_state);
 
-- 
cgit 


From 45c9f78b25ad9ce6cdf259ac4b652e6783adcb23 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 31 Oct 2013 09:31:24 +0800
Subject: ACPICA: Add __init for ACPICA initializers/finalizers.

This patch adds __init to the ACPICA documented initializers:
  acpi_initialize_tables()
  acpi_initialize_subsystem()
  acpi_load_tables()
  acpi_enable_subsystem()
  acpi_initialize_objects()
and to acpi_reallocate_root_table(), acpi_find_root_pointer() which
are also meant to be called only during initialization.

This patch adds __init to the ACPICA documented finalizer:
  acpi_terminate()
as this finalizer is only called in __init function now.

This change helps to reduce source code differences between
ACPICA upstream and Linux.

[rjw: Changelog]
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/tbutils.c  |  3 +--
 drivers/acpi/acpica/tbxface.c  |  2 +-
 drivers/acpi/acpica/tbxfload.c |  2 +-
 drivers/acpi/acpica/tbxfroot.c |  2 +-
 drivers/acpi/acpica/utxface.c  |  2 +-
 drivers/acpi/acpica/utxfinit.c |  6 +++---
 include/acpi/acpixf.h          | 14 +++++++-------
 7 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 43ffe21c7b26..3d6bb83aa7e7 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -430,8 +430,7 @@ acpi_tb_get_root_table_entry(u8 *table_entry, u32 table_entry_size)
  *
  ******************************************************************************/
 
-acpi_status __init
-acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
+acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 {
 	struct acpi_table_rsdp *rsdp;
 	u32 table_entry_size;
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 7e63090742dc..db826eaadd1c 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -164,7 +164,7 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_initialize_tables)
  *              kernel.
  *
  ******************************************************************************/
-acpi_status acpi_reallocate_root_table(void)
+acpi_status __init acpi_reallocate_root_table(void)
 {
 	acpi_status status;
 
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index b1e1edd5703a..60b5a871833c 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -66,7 +66,7 @@ static acpi_status acpi_tb_load_namespace(void);
  *
  ******************************************************************************/
 
-acpi_status acpi_load_tables(void)
+acpi_status __init acpi_load_tables(void)
 {
 	acpi_status status;
 
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 1c95fabbe6a4..e4e1468877c3 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -111,7 +111,7 @@ acpi_status acpi_tb_validate_rsdp(struct acpi_table_rsdp *rsdp)
  *
  ******************************************************************************/
 
-acpi_status acpi_find_root_pointer(acpi_size *table_address)
+acpi_status __init acpi_find_root_pointer(acpi_size *table_address)
 {
 	u8 *table_ptr;
 	u8 *mem_rover;
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 39869022a417..be322c83643a 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -61,7 +61,7 @@ ACPI_MODULE_NAME("utxface")
  * DESCRIPTION: Shutdown the ACPICA subsystem and release all resources.
  *
  ******************************************************************************/
-acpi_status acpi_terminate(void)
+acpi_status __init acpi_terminate(void)
 {
 	acpi_status status;
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index ff6f4d194136..75efea0539c1 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -65,7 +65,7 @@ ACPI_MODULE_NAME("utxfinit")
  *              called, so any early initialization belongs here.
  *
  ******************************************************************************/
-acpi_status acpi_initialize_subsystem(void)
+acpi_status __init acpi_initialize_subsystem(void)
 {
 	acpi_status status;
 
@@ -140,7 +140,7 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_initialize_subsystem)
  *              Puts system into ACPI mode if it isn't already.
  *
  ******************************************************************************/
-acpi_status acpi_enable_subsystem(u32 flags)
+acpi_status __init acpi_enable_subsystem(u32 flags)
 {
 	acpi_status status = AE_OK;
 
@@ -245,7 +245,7 @@ ACPI_EXPORT_SYMBOL_INIT(acpi_enable_subsystem)
  *              objects and executing AML code for Regions, buffers, etc.
  *
  ******************************************************************************/
-acpi_status acpi_initialize_objects(u32 flags)
+acpi_status __init acpi_initialize_objects(u32 flags)
 {
 	acpi_status status = AE_OK;
 
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 00725f44ac89..d8f9457755b4 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -114,17 +114,17 @@ extern u8 acpi_gbl_disable_ssdt_table_load;
 /*
  * Initialization
  */
-acpi_status
+acpi_status __init
 acpi_initialize_tables(struct acpi_table_desc *initial_storage,
 		       u32 initial_table_count, u8 allow_resize);
 
 acpi_status __init acpi_initialize_subsystem(void);
 
-acpi_status acpi_enable_subsystem(u32 flags);
+acpi_status __init acpi_enable_subsystem(u32 flags);
 
-acpi_status acpi_initialize_objects(u32 flags);
+acpi_status __init acpi_initialize_objects(u32 flags);
 
-acpi_status acpi_terminate(void);
+acpi_status __init acpi_terminate(void);
 
 /*
  * Miscellaneous global interfaces
@@ -168,14 +168,14 @@ acpi_status acpi_load_table(struct acpi_table_header *table);
 
 acpi_status acpi_unload_parent_table(acpi_handle object);
 
-acpi_status acpi_load_tables(void);
+acpi_status __init acpi_load_tables(void);
 
 /*
  * ACPI table manipulation interfaces
  */
-acpi_status acpi_reallocate_root_table(void);
+acpi_status __init acpi_reallocate_root_table(void);
 
-acpi_status acpi_find_root_pointer(acpi_size * rsdp_address);
+acpi_status __init acpi_find_root_pointer(acpi_size *rsdp_address);
 
 acpi_status acpi_unload_table_id(acpi_owner_id id);
 
-- 
cgit 


From 446b2a9380b64b9d7410d86ee8226031e03645cf Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Thu, 27 Jun 2013 10:25:33 +0100
Subject: DMA-API: amba: get rid of separate dma_mask

AMBA Primecell devices always treat streaming and coherent DMA exactly
the same, so there's no point in having the masks separated.

Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/amba/bus.c       | 6 +-----
 drivers/of/platform.c    | 3 ---
 include/linux/amba/bus.h | 2 --
 3 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index c6707278a6bb..c4876ac9151a 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -552,7 +552,6 @@ amba_aphb_device_add(struct device *parent, const char *name,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->dma_mask = dma_mask;
 	dev->dev.coherent_dma_mask = dma_mask;
 	dev->irq[0] = irq1;
 	dev->irq[1] = irq2;
@@ -619,7 +618,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name)
 		dev_set_name(&dev->dev, "%s", name);
 	dev->dev.release = amba_device_release;
 	dev->dev.bus = &amba_bustype;
-	dev->dev.dma_mask = &dev->dma_mask;
+	dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->res.name = dev_name(&dev->dev);
 }
 
@@ -663,9 +662,6 @@ int amba_device_register(struct amba_device *dev, struct resource *parent)
 	amba_device_initialize(dev, dev->dev.init_name);
 	dev->dev.init_name = NULL;
 
-	if (!dev->dev.coherent_dma_mask && dev->dma_mask)
-		dev_warn(&dev->dev, "coherent dma mask is unset\n");
-
 	return amba_device_add(dev, parent);
 }
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 9b439ac63d8e..54382ba4a6e9 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -284,9 +284,6 @@ static struct amba_device *of_amba_device_create(struct device_node *node,
 	else
 		of_device_make_bus_id(&dev->dev);
 
-	/* setup amba-specific device info */
-	dev->dma_mask = ~0;
-
 	/* Allow the HW Peripheral ID to be overridden */
 	prop = of_get_property(node, "arm,primecell-periphid", NULL);
 	if (prop)
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 43ec7e247a80..682df0e1954a 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -30,7 +30,6 @@ struct amba_device {
 	struct device		dev;
 	struct resource		res;
 	struct clk		*pclk;
-	u64			dma_mask;
 	unsigned int		periphid;
 	unsigned int		irq[AMBA_NR_IRQS];
 };
@@ -131,7 +130,6 @@ struct amba_device name##_device = {				\
 struct amba_device name##_device = {				\
 	.dev = __AMBA_DEV(busid, data, ~0ULL),			\
 	.res = DEFINE_RES_MEM(base, SZ_4K),			\
-	.dma_mask = ~0ULL,					\
 	.irq = irqs,						\
 	.periphid = id,						\
 }
-- 
cgit 


From fa6a8d6d65b19ab44e5244ea499bcd553cc72343 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Thu, 27 Jun 2013 12:21:45 +0100
Subject: DMA-API: provide a helper to setup DMA masks

Many drivers contain code such as:

	dev->dma_mask = &dev->coherent_dma_mask;
	dev->coherent_dma_mask = MASK;

Let's move this pattern out of drivers and have the DMA API provide a
helper for it.  This helper uses dma_set_mask_and_coherent() to allow
platform issues to be properly dealt with via dma_set_mask()/
dma_is_supported().

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/dma-mapping.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index ec951f98e3d9..27d1421ad42c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -111,6 +111,16 @@ static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask)
 	return rc;
 }
 
+/*
+ * Similar to the above, except it deals with the case where the device
+ * does not have dev->dma_mask appropriately setup.
+ */
+static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
+{
+	dev->dma_mask = &dev->coherent_dma_mask;
+	return dma_set_mask_and_coherent(dev, mask);
+}
+
 extern u64 dma_get_required_mask(struct device *dev);
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
-- 
cgit 


From 00c8f1623658947a97345ecb86b71232ff540d0d Mon Sep 17 00:00:00 2001
From: Santosh Shilimkar <santosh.shilimkar@ti.com>
Date: Mon, 29 Jul 2013 14:18:48 +0100
Subject: ARM: 7795/1: mm: dma-mapping: Add dma_max_pfn(dev) helper function

Most of the kernel assumes that PFN0 is the start of the physical
memory (RAM). This assumptions is not true on most of the ARM SOCs
and hence and if one try to update the ARM port to follow the assumptions,
we end of breaking the dma bounce limit for few block layer drivers.
One such example is trying to unify the meaning of max*_pfn on ARM
as the bootmem layer expects, breaks few block layer driver dma
bounce limit.

To fix this problem, we introduce dma_max_pfn(dev) generic helper with
a possibility of override from the architecture code. The helper converts
a DMA bitmask of bits to a block PFN number. In all the generic cases,
it is just  "dev->dma_mask >> PAGE_SHIFT" and hence default behavior
is maintained as is.

Subsequent patches will make use of the helper. No functional change.

Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/dma-mapping.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 27d1421ad42c..fd4aee29ad10 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -153,6 +153,13 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 		return -EIO;
 }
 
+#ifndef dma_max_pfn
+static inline unsigned long dma_max_pfn(struct device *dev)
+{
+	return *dev->dma_mask >> PAGE_SHIFT;
+}
+#endif
+
 static inline void *dma_zalloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flag)
 {
-- 
cgit 


From c6d81bd7237b5785080087bcf796ce456ef69557 Mon Sep 17 00:00:00 2001
From: Heiko Stübner <heiko@sntech.de>
Date: Thu, 31 Oct 2013 01:25:32 -0700
Subject: Input: add driver for Neonode zForce based touchscreens

This adds a driver for touchscreens using the zforce infrared
technology from Neonode connected via i2c to the host system.

It supports multitouch with up to two fingers and tracking of the
contacts in hardware.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig       |  13 +
 drivers/input/touchscreen/Makefile      |   1 +
 drivers/input/touchscreen/zforce_ts.c   | 836 ++++++++++++++++++++++++++++++++
 include/linux/platform_data/zforce_ts.h |  26 +
 4 files changed, 876 insertions(+)
 create mode 100644 drivers/input/touchscreen/zforce_ts.c
 create mode 100644 include/linux/platform_data/zforce_ts.h

(limited to 'include')

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index e09ec67957a3..00d1e547b211 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -919,4 +919,17 @@ config TOUCHSCREEN_TPS6507X
 	  To compile this driver as a module, choose M here: the
 	  module will be called tps6507x_ts.
 
+config TOUCHSCREEN_ZFORCE
+	tristate "Neonode zForce infrared touchscreens"
+	depends on I2C
+	depends on GPIOLIB
+	help
+	  Say Y here if you have a touchscreen using the zforce
+	  infraread technology from Neonode.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called zforce_ts.
+
 endif
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index f5216c1bf53e..7587883b8d38 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -75,3 +75,4 @@ obj-$(CONFIG_TOUCHSCREEN_WM97XX_MAINSTONE)	+= mainstone-wm97xx.o
 obj-$(CONFIG_TOUCHSCREEN_WM97XX_ZYLONITE)	+= zylonite-wm97xx.o
 obj-$(CONFIG_TOUCHSCREEN_W90X900)	+= w90p910_ts.o
 obj-$(CONFIG_TOUCHSCREEN_TPS6507X)	+= tps6507x-ts.o
+obj-$(CONFIG_TOUCHSCREEN_ZFORCE)	+= zforce_ts.o
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
new file mode 100644
index 000000000000..75762d6ff3ba
--- /dev/null
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -0,0 +1,836 @@
+/*
+ * Copyright (C) 2012-2013 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * based in parts on Nook zforce driver
+ *
+ * Copyright (C) 2010 Barnes & Noble, Inc.
+ * Author: Pieter Truter<ptruter@intrinsyc.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/hrtimer.h>
+#include <linux/slab.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/i2c.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+#include <linux/input/mt.h>
+#include <linux/platform_data/zforce_ts.h>
+
+#define WAIT_TIMEOUT		msecs_to_jiffies(1000)
+
+#define FRAME_START		0xee
+
+/* Offsets of the different parts of the payload the controller sends */
+#define PAYLOAD_HEADER		0
+#define PAYLOAD_LENGTH		1
+#define PAYLOAD_BODY		2
+
+/* Response offsets */
+#define RESPONSE_ID		0
+#define RESPONSE_DATA		1
+
+/* Commands */
+#define COMMAND_DEACTIVATE	0x00
+#define COMMAND_INITIALIZE	0x01
+#define COMMAND_RESOLUTION	0x02
+#define COMMAND_SETCONFIG	0x03
+#define COMMAND_DATAREQUEST	0x04
+#define COMMAND_SCANFREQ	0x08
+#define COMMAND_STATUS		0X1e
+
+/*
+ * Responses the controller sends as a result of
+ * command requests
+ */
+#define RESPONSE_DEACTIVATE	0x00
+#define RESPONSE_INITIALIZE	0x01
+#define RESPONSE_RESOLUTION	0x02
+#define RESPONSE_SETCONFIG	0x03
+#define RESPONSE_SCANFREQ	0x08
+#define RESPONSE_STATUS		0X1e
+
+/*
+ * Notifications are send by the touch controller without
+ * being requested by the driver and include for example
+ * touch indications
+ */
+#define NOTIFICATION_TOUCH		0x04
+#define NOTIFICATION_BOOTCOMPLETE	0x07
+#define NOTIFICATION_OVERRUN		0x25
+#define NOTIFICATION_PROXIMITY		0x26
+#define NOTIFICATION_INVALID_COMMAND	0xfe
+
+#define ZFORCE_REPORT_POINTS		2
+#define ZFORCE_MAX_AREA			0xff
+
+#define STATE_DOWN			0
+#define STATE_MOVE			1
+#define STATE_UP			2
+
+#define SETCONFIG_DUALTOUCH		(1 << 0)
+
+struct zforce_point {
+	int coord_x;
+	int coord_y;
+	int state;
+	int id;
+	int area_major;
+	int area_minor;
+	int orientation;
+	int pressure;
+	int prblty;
+};
+
+/*
+ * @client		the i2c_client
+ * @input		the input device
+ * @suspending		in the process of going to suspend (don't emit wakeup
+ *			events for commands executed to suspend the device)
+ * @suspended		device suspended
+ * @access_mutex	serialize i2c-access, to keep multipart reads together
+ * @command_done	completion to wait for the command result
+ * @command_mutex	serialize commands send to the ic
+ * @command_waiting	the id of the command that that is currently waiting
+ *			for a result
+ * @command_result	returned result of the command
+ */
+struct zforce_ts {
+	struct i2c_client	*client;
+	struct input_dev	*input;
+	const struct zforce_ts_platdata *pdata;
+	char			phys[32];
+
+	bool			suspending;
+	bool			suspended;
+	bool			boot_complete;
+
+	/* Firmware version information */
+	u16			version_major;
+	u16			version_minor;
+	u16			version_build;
+	u16			version_rev;
+
+	struct mutex		access_mutex;
+
+	struct completion	command_done;
+	struct mutex		command_mutex;
+	int			command_waiting;
+	int			command_result;
+};
+
+static int zforce_command(struct zforce_ts *ts, u8 cmd)
+{
+	struct i2c_client *client = ts->client;
+	char buf[3];
+	int ret;
+
+	dev_dbg(&client->dev, "%s: 0x%x\n", __func__, cmd);
+
+	buf[0] = FRAME_START;
+	buf[1] = 1; /* data size, command only */
+	buf[2] = cmd;
+
+	mutex_lock(&ts->access_mutex);
+	ret = i2c_master_send(client, &buf[0], ARRAY_SIZE(buf));
+	mutex_unlock(&ts->access_mutex);
+	if (ret < 0) {
+		dev_err(&client->dev, "i2c send data request error: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int zforce_send_wait(struct zforce_ts *ts, const char *buf, int len)
+{
+	struct i2c_client *client = ts->client;
+	int ret;
+
+	ret = mutex_trylock(&ts->command_mutex);
+	if (!ret) {
+		dev_err(&client->dev, "already waiting for a command\n");
+		return -EBUSY;
+	}
+
+	dev_dbg(&client->dev, "sending %d bytes for command 0x%x\n",
+		buf[1], buf[2]);
+
+	ts->command_waiting = buf[2];
+
+	mutex_lock(&ts->access_mutex);
+	ret = i2c_master_send(client, buf, len);
+	mutex_unlock(&ts->access_mutex);
+	if (ret < 0) {
+		dev_err(&client->dev, "i2c send data request error: %d\n", ret);
+		goto unlock;
+	}
+
+	dev_dbg(&client->dev, "waiting for result for command 0x%x\n", buf[2]);
+
+	if (wait_for_completion_timeout(&ts->command_done, WAIT_TIMEOUT) == 0) {
+		ret = -ETIME;
+		goto unlock;
+	}
+
+	ret = ts->command_result;
+
+unlock:
+	mutex_unlock(&ts->command_mutex);
+	return ret;
+}
+
+static int zforce_command_wait(struct zforce_ts *ts, u8 cmd)
+{
+	struct i2c_client *client = ts->client;
+	char buf[3];
+	int ret;
+
+	dev_dbg(&client->dev, "%s: 0x%x\n", __func__, cmd);
+
+	buf[0] = FRAME_START;
+	buf[1] = 1; /* data size, command only */
+	buf[2] = cmd;
+
+	ret = zforce_send_wait(ts, &buf[0], ARRAY_SIZE(buf));
+	if (ret < 0) {
+		dev_err(&client->dev, "i2c send data request error: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int zforce_resolution(struct zforce_ts *ts, u16 x, u16 y)
+{
+	struct i2c_client *client = ts->client;
+	char buf[7] = { FRAME_START, 5, COMMAND_RESOLUTION,
+			(x & 0xff), ((x >> 8) & 0xff),
+			(y & 0xff), ((y >> 8) & 0xff) };
+
+	dev_dbg(&client->dev, "set resolution to (%d,%d)\n", x, y);
+
+	return zforce_send_wait(ts, &buf[0], ARRAY_SIZE(buf));
+}
+
+static int zforce_scan_frequency(struct zforce_ts *ts, u16 idle, u16 finger,
+				 u16 stylus)
+{
+	struct i2c_client *client = ts->client;
+	char buf[9] = { FRAME_START, 7, COMMAND_SCANFREQ,
+			(idle & 0xff), ((idle >> 8) & 0xff),
+			(finger & 0xff), ((finger >> 8) & 0xff),
+			(stylus & 0xff), ((stylus >> 8) & 0xff) };
+
+	dev_dbg(&client->dev, "set scan frequency to (idle: %d, finger: %d, stylus: %d)\n",
+		idle, finger, stylus);
+
+	return zforce_send_wait(ts, &buf[0], ARRAY_SIZE(buf));
+}
+
+static int zforce_setconfig(struct zforce_ts *ts, char b1)
+{
+	struct i2c_client *client = ts->client;
+	char buf[7] = { FRAME_START, 5, COMMAND_SETCONFIG,
+			b1, 0, 0, 0 };
+
+	dev_dbg(&client->dev, "set config to (%d)\n", b1);
+
+	return zforce_send_wait(ts, &buf[0], ARRAY_SIZE(buf));
+}
+
+static int zforce_start(struct zforce_ts *ts)
+{
+	struct i2c_client *client = ts->client;
+	const struct zforce_ts_platdata *pdata = dev_get_platdata(&client->dev);
+	int ret;
+
+	dev_dbg(&client->dev, "starting device\n");
+
+	ret = zforce_command_wait(ts, COMMAND_INITIALIZE);
+	if (ret) {
+		dev_err(&client->dev, "Unable to initialize, %d\n", ret);
+		return ret;
+	}
+
+	ret = zforce_resolution(ts, pdata->x_max, pdata->y_max);
+	if (ret) {
+		dev_err(&client->dev, "Unable to set resolution, %d\n", ret);
+		goto error;
+	}
+
+	ret = zforce_scan_frequency(ts, 10, 50, 50);
+	if (ret) {
+		dev_err(&client->dev, "Unable to set scan frequency, %d\n",
+			ret);
+		goto error;
+	}
+
+	if (zforce_setconfig(ts, SETCONFIG_DUALTOUCH)) {
+		dev_err(&client->dev, "Unable to set config\n");
+		goto error;
+	}
+
+	/* start sending touch events */
+	ret = zforce_command(ts, COMMAND_DATAREQUEST);
+	if (ret) {
+		dev_err(&client->dev, "Unable to request data\n");
+		goto error;
+	}
+
+	/*
+	 * Per NN, initial cal. take max. of 200msec.
+	 * Allow time to complete this calibration
+	 */
+	msleep(200);
+
+	return 0;
+
+error:
+	zforce_command_wait(ts, COMMAND_DEACTIVATE);
+	return ret;
+}
+
+static int zforce_stop(struct zforce_ts *ts)
+{
+	struct i2c_client *client = ts->client;
+	int ret;
+
+	dev_dbg(&client->dev, "stopping device\n");
+
+	/* Deactivates touch sensing and puts the device into sleep. */
+	ret = zforce_command_wait(ts, COMMAND_DEACTIVATE);
+	if (ret != 0) {
+		dev_err(&client->dev, "could not deactivate device, %d\n",
+			ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int zforce_touch_event(struct zforce_ts *ts, u8 *payload)
+{
+	struct i2c_client *client = ts->client;
+	const struct zforce_ts_platdata *pdata = dev_get_platdata(&client->dev);
+	struct zforce_point point;
+	int count, i, num = 0;
+
+	count = payload[0];
+	if (count > ZFORCE_REPORT_POINTS) {
+		dev_warn(&client->dev, "to many coordinates %d, expected max %d\n",
+			 count, ZFORCE_REPORT_POINTS);
+		count = ZFORCE_REPORT_POINTS;
+	}
+
+	for (i = 0; i < count; i++) {
+		point.coord_x =
+			payload[9 * i + 2] << 8 | payload[9 * i + 1];
+		point.coord_y =
+			payload[9 * i + 4] << 8 | payload[9 * i + 3];
+
+		if (point.coord_x > pdata->x_max ||
+		    point.coord_y > pdata->y_max) {
+			dev_warn(&client->dev, "coordinates (%d,%d) invalid\n",
+				point.coord_x, point.coord_y);
+			point.coord_x = point.coord_y = 0;
+		}
+
+		point.state = payload[9 * i + 5] & 0x03;
+		point.id = (payload[9 * i + 5] & 0xfc) >> 2;
+
+		/* determine touch major, minor and orientation */
+		point.area_major = max(payload[9 * i + 6],
+					  payload[9 * i + 7]);
+		point.area_minor = min(payload[9 * i + 6],
+					  payload[9 * i + 7]);
+		point.orientation = payload[9 * i + 6] > payload[9 * i + 7];
+
+		point.pressure = payload[9 * i + 8];
+		point.prblty = payload[9 * i + 9];
+
+		dev_dbg(&client->dev,
+			"point %d/%d: state %d, id %d, pressure %d, prblty %d, x %d, y %d, amajor %d, aminor %d, ori %d\n",
+			i, count, point.state, point.id,
+			point.pressure, point.prblty,
+			point.coord_x, point.coord_y,
+			point.area_major, point.area_minor,
+			point.orientation);
+
+		/* the zforce id starts with "1", so needs to be decreased */
+		input_mt_slot(ts->input, point.id - 1);
+
+		input_mt_report_slot_state(ts->input, MT_TOOL_FINGER,
+						point.state != STATE_UP);
+
+		if (point.state != STATE_UP) {
+			input_report_abs(ts->input, ABS_MT_POSITION_X,
+					 point.coord_x);
+			input_report_abs(ts->input, ABS_MT_POSITION_Y,
+					 point.coord_y);
+			input_report_abs(ts->input, ABS_MT_TOUCH_MAJOR,
+					 point.area_major);
+			input_report_abs(ts->input, ABS_MT_TOUCH_MINOR,
+					 point.area_minor);
+			input_report_abs(ts->input, ABS_MT_ORIENTATION,
+					 point.orientation);
+			num++;
+		}
+	}
+
+	input_mt_sync_frame(ts->input);
+
+	input_mt_report_finger_count(ts->input, num);
+
+	input_sync(ts->input);
+
+	return 0;
+}
+
+static int zforce_read_packet(struct zforce_ts *ts, u8 *buf)
+{
+	struct i2c_client *client = ts->client;
+	int ret;
+
+	mutex_lock(&ts->access_mutex);
+
+	/* read 2 byte message header */
+	ret = i2c_master_recv(client, buf, 2);
+	if (ret < 0) {
+		dev_err(&client->dev, "error reading header: %d\n", ret);
+		goto unlock;
+	}
+
+	if (buf[PAYLOAD_HEADER] != FRAME_START) {
+		dev_err(&client->dev, "invalid frame start: %d\n", buf[0]);
+		ret = -EIO;
+		goto unlock;
+	}
+
+	if (buf[PAYLOAD_LENGTH] <= 0 || buf[PAYLOAD_LENGTH] > 255) {
+		dev_err(&client->dev, "invalid payload length: %d\n",
+			buf[PAYLOAD_LENGTH]);
+		ret = -EIO;
+		goto unlock;
+	}
+
+	/* read the message */
+	ret = i2c_master_recv(client, &buf[PAYLOAD_BODY], buf[PAYLOAD_LENGTH]);
+	if (ret < 0) {
+		dev_err(&client->dev, "error reading payload: %d\n", ret);
+		goto unlock;
+	}
+
+	dev_dbg(&client->dev, "read %d bytes for response command 0x%x\n",
+		buf[PAYLOAD_LENGTH], buf[PAYLOAD_BODY]);
+
+unlock:
+	mutex_unlock(&ts->access_mutex);
+	return ret;
+}
+
+static void zforce_complete(struct zforce_ts *ts, int cmd, int result)
+{
+	struct i2c_client *client = ts->client;
+
+	if (ts->command_waiting == cmd) {
+		dev_dbg(&client->dev, "completing command 0x%x\n", cmd);
+		ts->command_result = result;
+		complete(&ts->command_done);
+	} else {
+		dev_dbg(&client->dev, "command %d not for us\n", cmd);
+	}
+}
+
+static irqreturn_t zforce_interrupt(int irq, void *dev_id)
+{
+	struct zforce_ts *ts = dev_id;
+	struct i2c_client *client = ts->client;
+	const struct zforce_ts_platdata *pdata = dev_get_platdata(&client->dev);
+	int ret;
+	u8 payload_buffer[512];
+	u8 *payload;
+
+	/*
+	 * When suspended, emit a wakeup signal if necessary and return.
+	 * Due to the level-interrupt we will get re-triggered later.
+	 */
+	if (ts->suspended) {
+		if (device_may_wakeup(&client->dev))
+			pm_wakeup_event(&client->dev, 500);
+		msleep(20);
+		return IRQ_HANDLED;
+	}
+
+	dev_dbg(&client->dev, "handling interrupt\n");
+
+	/* Don't emit wakeup events from commands run by zforce_suspend */
+	if (!ts->suspending && device_may_wakeup(&client->dev))
+		pm_stay_awake(&client->dev);
+
+	while (!gpio_get_value(pdata->gpio_int)) {
+		ret = zforce_read_packet(ts, payload_buffer);
+		if (ret < 0) {
+			dev_err(&client->dev, "could not read packet, ret: %d\n",
+				ret);
+			break;
+		}
+
+		payload =  &payload_buffer[PAYLOAD_BODY];
+
+		switch (payload[RESPONSE_ID]) {
+		case NOTIFICATION_TOUCH:
+			/*
+			 * Always report touch-events received while
+			 * suspending, when being a wakeup source
+			 */
+			if (ts->suspending && device_may_wakeup(&client->dev))
+				pm_wakeup_event(&client->dev, 500);
+			zforce_touch_event(ts, &payload[RESPONSE_DATA]);
+			break;
+
+		case NOTIFICATION_BOOTCOMPLETE:
+			ts->boot_complete = payload[RESPONSE_DATA];
+			zforce_complete(ts, payload[RESPONSE_ID], 0);
+			break;
+
+		case RESPONSE_INITIALIZE:
+		case RESPONSE_DEACTIVATE:
+		case RESPONSE_SETCONFIG:
+		case RESPONSE_RESOLUTION:
+		case RESPONSE_SCANFREQ:
+			zforce_complete(ts, payload[RESPONSE_ID],
+					payload[RESPONSE_DATA]);
+			break;
+
+		case RESPONSE_STATUS:
+			/*
+			 * Version Payload Results
+			 * [2:major] [2:minor] [2:build] [2:rev]
+			 */
+			ts->version_major = (payload[RESPONSE_DATA + 1] << 8) |
+						payload[RESPONSE_DATA];
+			ts->version_minor = (payload[RESPONSE_DATA + 3] << 8) |
+						payload[RESPONSE_DATA + 2];
+			ts->version_build = (payload[RESPONSE_DATA + 5] << 8) |
+						payload[RESPONSE_DATA + 4];
+			ts->version_rev   = (payload[RESPONSE_DATA + 7] << 8) |
+						payload[RESPONSE_DATA + 6];
+			dev_dbg(&ts->client->dev, "Firmware Version %04x:%04x %04x:%04x\n",
+				ts->version_major, ts->version_minor,
+				ts->version_build, ts->version_rev);
+
+			zforce_complete(ts, payload[RESPONSE_ID], 0);
+			break;
+
+		case NOTIFICATION_INVALID_COMMAND:
+			dev_err(&ts->client->dev, "invalid command: 0x%x\n",
+				payload[RESPONSE_DATA]);
+			break;
+
+		default:
+			dev_err(&ts->client->dev, "unrecognized response id: 0x%x\n",
+				payload[RESPONSE_ID]);
+			break;
+		}
+	}
+
+	if (!ts->suspending && device_may_wakeup(&client->dev))
+		pm_relax(&client->dev);
+
+	dev_dbg(&client->dev, "finished interrupt\n");
+
+	return IRQ_HANDLED;
+}
+
+static int zforce_input_open(struct input_dev *dev)
+{
+	struct zforce_ts *ts = input_get_drvdata(dev);
+	int ret;
+
+	ret = zforce_start(ts);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void zforce_input_close(struct input_dev *dev)
+{
+	struct zforce_ts *ts = input_get_drvdata(dev);
+	struct i2c_client *client = ts->client;
+	int ret;
+
+	ret = zforce_stop(ts);
+	if (ret)
+		dev_warn(&client->dev, "stopping zforce failed\n");
+
+	return;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int zforce_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct zforce_ts *ts = i2c_get_clientdata(client);
+	struct input_dev *input = ts->input;
+	int ret = 0;
+
+	mutex_lock(&input->mutex);
+	ts->suspending = true;
+
+	/*
+	 * When configured as a wakeup source device should always wake
+	 * the system, therefore start device if necessary.
+	 */
+	if (device_may_wakeup(&client->dev)) {
+		dev_dbg(&client->dev, "suspend while being a wakeup source\n");
+
+		/* Need to start device, if not open, to be a wakeup source. */
+		if (!input->users) {
+			ret = zforce_start(ts);
+			if (ret)
+				goto unlock;
+		}
+
+		enable_irq_wake(client->irq);
+	} else if (input->users) {
+		dev_dbg(&client->dev, "suspend without being a wakeup source\n");
+
+		ret = zforce_stop(ts);
+		if (ret)
+			goto unlock;
+
+		disable_irq(client->irq);
+	}
+
+	ts->suspended = true;
+
+unlock:
+	ts->suspending = false;
+	mutex_unlock(&input->mutex);
+
+	return ret;
+}
+
+static int zforce_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct zforce_ts *ts = i2c_get_clientdata(client);
+	struct input_dev *input = ts->input;
+	int ret = 0;
+
+	mutex_lock(&input->mutex);
+
+	ts->suspended = false;
+
+	if (device_may_wakeup(&client->dev)) {
+		dev_dbg(&client->dev, "resume from being a wakeup source\n");
+
+		disable_irq_wake(client->irq);
+
+		/* need to stop device if it was not open on suspend */
+		if (!input->users) {
+			ret = zforce_stop(ts);
+			if (ret)
+				goto unlock;
+		}
+	} else if (input->users) {
+		dev_dbg(&client->dev, "resume without being a wakeup source\n");
+
+		enable_irq(client->irq);
+
+		ret = zforce_start(ts);
+		if (ret < 0)
+			goto unlock;
+	}
+
+unlock:
+	mutex_unlock(&input->mutex);
+
+	return ret;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(zforce_pm_ops, zforce_suspend, zforce_resume);
+
+static void zforce_reset(void *data)
+{
+	struct zforce_ts *ts = data;
+
+	gpio_set_value(ts->pdata->gpio_rst, 0);
+}
+
+static int zforce_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	const struct zforce_ts_platdata *pdata = dev_get_platdata(&client->dev);
+	struct zforce_ts *ts;
+	struct input_dev *input_dev;
+	int ret;
+
+	if (!pdata)
+		return -EINVAL;
+
+	ts = devm_kzalloc(&client->dev, sizeof(struct zforce_ts), GFP_KERNEL);
+	if (!ts)
+		return -ENOMEM;
+
+	ret = devm_gpio_request_one(&client->dev, pdata->gpio_int, GPIOF_IN,
+				    "zforce_ts_int");
+	if (ret) {
+		dev_err(&client->dev, "request of gpio %d failed, %d\n",
+			pdata->gpio_int, ret);
+		return ret;
+	}
+
+	ret = devm_gpio_request_one(&client->dev, pdata->gpio_rst,
+				    GPIOF_OUT_INIT_LOW, "zforce_ts_rst");
+	if (ret) {
+		dev_err(&client->dev, "request of gpio %d failed, %d\n",
+			pdata->gpio_rst, ret);
+		return ret;
+	}
+
+	ret = devm_add_action(&client->dev, zforce_reset, ts);
+	if (ret) {
+		dev_err(&client->dev, "failed to register reset action, %d\n",
+			ret);
+		return ret;
+	}
+
+	snprintf(ts->phys, sizeof(ts->phys),
+		 "%s/input0", dev_name(&client->dev));
+
+	input_dev = devm_input_allocate_device(&client->dev);
+	if (!input_dev) {
+		dev_err(&client->dev, "could not allocate input device\n");
+		return -ENOMEM;
+	}
+
+	mutex_init(&ts->access_mutex);
+	mutex_init(&ts->command_mutex);
+
+	ts->pdata = pdata;
+	ts->client = client;
+	ts->input = input_dev;
+
+	input_dev->name = "Neonode zForce touchscreen";
+	input_dev->phys = ts->phys;
+	input_dev->id.bustype = BUS_I2C;
+
+	input_dev->open = zforce_input_open;
+	input_dev->close = zforce_input_close;
+
+	__set_bit(EV_KEY, input_dev->evbit);
+	__set_bit(EV_SYN, input_dev->evbit);
+	__set_bit(EV_ABS, input_dev->evbit);
+
+	/* For multi touch */
+	input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0,
+			     pdata->x_max, 0, 0);
+	input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
+			     pdata->y_max, 0, 0);
+
+	input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0,
+			     ZFORCE_MAX_AREA, 0, 0);
+	input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0,
+			     ZFORCE_MAX_AREA, 0, 0);
+	input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
+	input_mt_init_slots(input_dev, ZFORCE_REPORT_POINTS, INPUT_MT_DIRECT);
+
+	input_set_drvdata(ts->input, ts);
+
+	init_completion(&ts->command_done);
+
+	/*
+	 * The zforce pulls the interrupt low when it has data ready.
+	 * After it is triggered the isr thread runs until all the available
+	 * packets have been read and the interrupt is high again.
+	 * Therefore we can trigger the interrupt anytime it is low and do
+	 * not need to limit it to the interrupt edge.
+	 */
+	ret = devm_request_threaded_irq(&client->dev, client->irq, NULL,
+					zforce_interrupt,
+					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+					input_dev->name, ts);
+	if (ret) {
+		dev_err(&client->dev, "irq %d request failed\n", client->irq);
+		return ret;
+	}
+
+	i2c_set_clientdata(client, ts);
+
+	/* let the controller boot */
+	gpio_set_value(pdata->gpio_rst, 1);
+
+	ts->command_waiting = NOTIFICATION_BOOTCOMPLETE;
+	if (wait_for_completion_timeout(&ts->command_done, WAIT_TIMEOUT) == 0)
+		dev_warn(&client->dev, "bootcomplete timed out\n");
+
+	/* need to start device to get version information */
+	ret = zforce_command_wait(ts, COMMAND_INITIALIZE);
+	if (ret) {
+		dev_err(&client->dev, "unable to initialize, %d\n", ret);
+		return ret;
+	}
+
+	/* this gets the firmware version among other informations */
+	ret = zforce_command_wait(ts, COMMAND_STATUS);
+	if (ret < 0) {
+		dev_err(&client->dev, "couldn't get status, %d\n", ret);
+		zforce_stop(ts);
+		return ret;
+	}
+
+	/* stop device and put it into sleep until it is opened */
+	ret = zforce_stop(ts);
+	if (ret < 0)
+		return ret;
+
+	device_set_wakeup_capable(&client->dev, true);
+
+	ret = input_register_device(input_dev);
+	if (ret) {
+		dev_err(&client->dev, "could not register input device, %d\n",
+			ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct i2c_device_id zforce_idtable[] = {
+	{ "zforce-ts", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, zforce_idtable);
+
+static struct i2c_driver zforce_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "zforce-ts",
+		.pm	= &zforce_pm_ops,
+	},
+	.probe		= zforce_probe,
+	.id_table	= zforce_idtable,
+};
+
+module_i2c_driver(zforce_driver);
+
+MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
+MODULE_DESCRIPTION("zForce TouchScreen Driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/zforce_ts.h b/include/linux/platform_data/zforce_ts.h
new file mode 100644
index 000000000000..0472ab2f6ede
--- /dev/null
+++ b/include/linux/platform_data/zforce_ts.h
@@ -0,0 +1,26 @@
+/* drivers/input/touchscreen/zforce.c
+ *
+ * Copyright (C) 2012-2013 MundoReader S.L.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_INPUT_ZFORCE_TS_H
+#define _LINUX_INPUT_ZFORCE_TS_H
+
+struct zforce_ts_platdata {
+	int gpio_int;
+	int gpio_rst;
+
+	unsigned int x_max;
+	unsigned int y_max;
+};
+
+#endif /* _LINUX_INPUT_ZFORCE_TS_H */
-- 
cgit 


From 81e87e26796782e014fd1f2bb9cd8fb6ce4021a8 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Wed, 30 Oct 2013 21:43:01 +0200
Subject: kvm_host: typo fix

fix up typo in comment.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 92aae88756db..9bb1048d010e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -804,7 +804,7 @@ static inline void kvm_guest_enter(void)
 
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
-	 * is very similar to exiting to userspase from rcu point of view. In
+	 * is very similar to exiting to userspace from rcu point of view. In
 	 * addition CPU may stay in a guest mode for quite a long time (up to
 	 * one time slice). Lets treat guest mode as quiescent state, just like
 	 * we do with user-mode execution.
-- 
cgit 


From 7d716456a0ee4e9bd63be9234f886d20382ac950 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 31 Oct 2013 12:48:14 +0100
Subject: sched/wait: Fix __wait_event_interruptible_lock_irq_timeout()

__wait_event_interruptible_lock_irq_timeout() needs the timeout
parameter passed instead of "ret".

This magically compiled since the only user has a local ret
variable. Luckily we got a build warning:

  CC      drivers/s390/scsi/zfcp_qdio.o
  drivers/s390/scsi/zfcp_qdio.c: In function 'zfcp_qdio_sbal_get':
  include/linux/wait.h:780:15: warning: 'ret' may be used uninitialized

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20131031114814.GB5551@osiris
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3b23afa04d6b..61939ba30aa0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -739,7 +739,7 @@ do {									\
 #define __wait_event_interruptible_lock_irq_timeout(wq, condition,	\
 						    lock, timeout)	\
 	___wait_event(wq, ___wait_cond_timeout(condition),		\
-		      TASK_INTERRUPTIBLE, 0, ret,			\
+		      TASK_INTERRUPTIBLE, 0, timeout,			\
 		      spin_unlock_irq(&lock);				\
 		      __ret = schedule_timeout(__ret);			\
 		      spin_lock_irq(&lock));
-- 
cgit 


From 5eb26b156e29eadcc21f73fb5d14497f0db24b86 Mon Sep 17 00:00:00 2001
From: Jarno Rajahalme <jrajahalme@nicira.com>
Date: Wed, 23 Oct 2013 01:44:59 -0700
Subject: openvswitch: TCP flags matching support.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

    tcp_flags=flags/mask
        Bitwise  match on TCP flags.  The flags and mask are 16-bit num‐
        bers written in decimal or in hexadecimal prefixed by 0x.   Each
        1-bit  in  mask requires that the corresponding bit in port must
        match.  Each 0-bit in mask causes the corresponding  bit  to  be
        ignored.

        TCP  protocol  currently  defines  9 flag bits, and additional 3
        bits are reserved (must be transmitted as zero), see  RFCs  793,
        3168, and 3540.  The flag bits are, numbering from the least
        significant bit:

        0: FIN No more data from sender.

        1: SYN Synchronize sequence numbers.

        2: RST Reset the connection.

        3: PSH Push function.

        4: ACK Acknowledgement field significant.

        5: URG Urgent pointer field significant.

        6: ECE ECN Echo.

        7: CWR Congestion Windows Reduced.

        8: NS  Nonce Sum.

        9-11:  Reserved.

        12-15: Not matchable, must be zero.

Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/uapi/linux/openvswitch.h |  1 +
 net/openvswitch/flow.c           |  2 ++
 net/openvswitch/flow.h           |  2 ++
 net/openvswitch/flow_netlink.c   | 31 +++++++++++++++++++++++++++++--
 4 files changed, 34 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 2cc4644f68ef..d120f9fe0017 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -271,6 +271,7 @@ enum ovs_key_attr {
 	OVS_KEY_ATTR_SKB_MARK,  /* u32 skb mark */
 	OVS_KEY_ATTR_TUNNEL,    /* Nested set of ovs_tunnel attributes */
 	OVS_KEY_ATTR_SCTP,      /* struct ovs_key_sctp */
+	OVS_KEY_ATTR_TCP_FLAGS,	/* be16 TCP flags. */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_IPV4_TUNNEL,  /* struct ovs_key_ipv4_tunnel */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b73c7680a3d2..b409f5279601 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -428,6 +428,7 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				struct tcphdr *tcp = tcp_hdr(skb);
 				key->ipv4.tp.src = tcp->source;
 				key->ipv4.tp.dst = tcp->dest;
+				key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == IPPROTO_UDP) {
 			if (udphdr_ok(skb)) {
@@ -496,6 +497,7 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				struct tcphdr *tcp = tcp_hdr(skb);
 				key->ipv6.tp.src = tcp->source;
 				key->ipv6.tp.dst = tcp->dest;
+				key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == NEXTHDR_UDP) {
 			if (udphdr_ok(skb)) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 204e0ccd116d..1510f51dbf74 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -93,6 +93,7 @@ struct sw_flow_key {
 				struct {
 					__be16 src;		/* TCP/UDP/SCTP source port. */
 					__be16 dst;		/* TCP/UDP/SCTP destination port. */
+					__be16 flags;		/* TCP flags. */
 				} tp;
 				struct {
 					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
@@ -109,6 +110,7 @@ struct sw_flow_key {
 			struct {
 				__be16 src;		/* TCP/UDP/SCTP source port. */
 				__be16 dst;		/* TCP/UDP/SCTP destination port. */
+				__be16 flags;		/* TCP flags. */
 			} tp;
 			struct {
 				struct in6_addr target;	/* ND target address. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index e04649c56a96..2bc1bc1aca3b 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -114,6 +114,7 @@ static bool match_validate(const struct sw_flow_match *match,
 	mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4)
 			| (1 << OVS_KEY_ATTR_IPV6)
 			| (1 << OVS_KEY_ATTR_TCP)
+			| (1 << OVS_KEY_ATTR_TCP_FLAGS)
 			| (1 << OVS_KEY_ATTR_UDP)
 			| (1 << OVS_KEY_ATTR_SCTP)
 			| (1 << OVS_KEY_ATTR_ICMP)
@@ -154,8 +155,11 @@ static bool match_validate(const struct sw_flow_match *match,
 
 			if (match->key->ip.proto == IPPROTO_TCP) {
 				key_expected |= 1 << OVS_KEY_ATTR_TCP;
-				if (match->mask && (match->mask->key.ip.proto == 0xff))
+				key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
+				if (match->mask && (match->mask->key.ip.proto == 0xff)) {
 					mask_allowed |= 1 << OVS_KEY_ATTR_TCP;
+					mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
+				}
 			}
 
 			if (match->key->ip.proto == IPPROTO_ICMP) {
@@ -186,8 +190,11 @@ static bool match_validate(const struct sw_flow_match *match,
 
 			if (match->key->ip.proto == IPPROTO_TCP) {
 				key_expected |= 1 << OVS_KEY_ATTR_TCP;
-				if (match->mask && (match->mask->key.ip.proto == 0xff))
+				key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
+				if (match->mask && (match->mask->key.ip.proto == 0xff)) {
 					mask_allowed |= 1 << OVS_KEY_ATTR_TCP;
+					mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
+				}
 			}
 
 			if (match->key->ip.proto == IPPROTO_ICMPV6) {
@@ -235,6 +242,7 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
 	[OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
 	[OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
 	[OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
+	[OVS_KEY_ATTR_TCP_FLAGS] = sizeof(__be16),
 	[OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
 	[OVS_KEY_ATTR_SCTP] = sizeof(struct ovs_key_sctp),
 	[OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
@@ -634,6 +642,19 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  u64 attrs,
 		attrs &= ~(1 << OVS_KEY_ATTR_TCP);
 	}
 
+	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
+		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
+			SW_FLOW_KEY_PUT(match, ipv4.tp.flags,
+					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
+					is_mask);
+		} else {
+			SW_FLOW_KEY_PUT(match, ipv6.tp.flags,
+					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
+					is_mask);
+		}
+		attrs &= ~(1 << OVS_KEY_ATTR_TCP_FLAGS);
+	}
+
 	if (attrs & (1 << OVS_KEY_ATTR_UDP)) {
 		const struct ovs_key_udp *udp_key;
 
@@ -1004,9 +1025,15 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (swkey->eth.type == htons(ETH_P_IP)) {
 				tcp_key->tcp_src = output->ipv4.tp.src;
 				tcp_key->tcp_dst = output->ipv4.tp.dst;
+				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
+						 output->ipv4.tp.flags))
+					goto nla_put_failure;
 			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
 				tcp_key->tcp_src = output->ipv6.tp.src;
 				tcp_key->tcp_dst = output->ipv6.tp.dst;
+				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
+						 output->ipv6.tp.flags))
+					goto nla_put_failure;
 			}
 		} else if (swkey->ip.proto == IPPROTO_UDP) {
 			struct ovs_key_udp *udp_key;
-- 
cgit 


From f6701d5f73c5c2f4ca37634514631fb056291f89 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:39 +0100
Subject: net: cdc_ncm: add include protection to cdc_ncm.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This makes it a lot easier to test modified versions

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/usb/cdc_ncm.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index cc25b70af33c..89f0bbc2cf83 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -36,6 +36,9 @@
  * SUCH DAMAGE.
  */
 
+#ifndef __LINUX_USB_CDC_NCM_H
+#define __LINUX_USB_CDC_NCM_H
+
 #define CDC_NCM_COMM_ALTSETTING_NCM		0
 #define CDC_NCM_COMM_ALTSETTING_MBIM		1
 
@@ -133,3 +136,5 @@ extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 extern struct sk_buff *cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign);
 extern int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
 extern int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
+
+#endif /* __LINUX_USB_CDC_NCM_H */
-- 
cgit 


From 3e515665a76ad8f60a1c05968cc6a5b2f2701171 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:40 +0100
Subject: net: cdc_ncm: remove redundant "intf" field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is always a duplicate of the "control" field. It causes
confusion wrt intf_data updates and cleanups.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 4 +---
 include/linux/usb/cdc_ncm.h | 1 -
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 38566bffca98..bfab8796730f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -382,7 +382,6 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	len = intf->cur_altsetting->extralen;
 
 	ctx->udev = dev->udev;
-	ctx->intf = intf;
 
 	/* parse through descriptors associated with control interface */
 	while ((len > 0) && (buf[0] > 2) && (buf[0] <= len)) {
@@ -489,7 +488,6 @@ advance:
 
 	usb_set_intfdata(ctx->data, dev);
 	usb_set_intfdata(ctx->control, dev);
-	usb_set_intfdata(ctx->intf, dev);
 
 	if (ctx->ether_desc) {
 		temp = usbnet_get_ethernet_addr(dev, ctx->ether_desc->iMACAddress);
@@ -562,7 +560,7 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 		ctx->control = NULL;
 	}
 
-	usb_set_intfdata(ctx->intf, NULL);
+	usb_set_intfdata(intf, NULL);
 	cdc_ncm_free(ctx);
 }
 EXPORT_SYMBOL_GPL(cdc_ncm_unbind);
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 89f0bbc2cf83..c14e00fb1667 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -103,7 +103,6 @@ struct cdc_ncm_ctx {
 	struct usb_host_endpoint *in_ep;
 	struct usb_host_endpoint *out_ep;
 	struct usb_host_endpoint *status_ep;
-	struct usb_interface *intf;
 	struct usb_interface *control;
 	struct usb_interface *data;
 
-- 
cgit 


From ff1632aa8581b7103ac2af1ea3cb4a415eb9d6ad Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:41 +0100
Subject: net: cdc_ncm: remove redundant endpoint pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No need to duplicate stuff already in the common usbnet
struct.  We still need to keep our special find_endpoints
function because we need explicit control over the selected
altsetting.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 38 +++++++++++++++++++-------------------
 include/linux/usb/cdc_ncm.h |  3 ---
 2 files changed, 19 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index bfab8796730f..a989bd5290a6 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -292,9 +292,9 @@ max_dgram_err:
 }
 
 static void
-cdc_ncm_find_endpoints(struct cdc_ncm_ctx *ctx, struct usb_interface *intf)
+cdc_ncm_find_endpoints(struct usbnet *dev, struct usb_interface *intf)
 {
-	struct usb_host_endpoint *e;
+	struct usb_host_endpoint *e, *in = NULL, *out = NULL;
 	u8 ep;
 
 	for (ep = 0; ep < intf->cur_altsetting->desc.bNumEndpoints; ep++) {
@@ -303,18 +303,18 @@ cdc_ncm_find_endpoints(struct cdc_ncm_ctx *ctx, struct usb_interface *intf)
 		switch (e->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) {
 		case USB_ENDPOINT_XFER_INT:
 			if (usb_endpoint_dir_in(&e->desc)) {
-				if (ctx->status_ep == NULL)
-					ctx->status_ep = e;
+				if (!dev->status)
+					dev->status = e;
 			}
 			break;
 
 		case USB_ENDPOINT_XFER_BULK:
 			if (usb_endpoint_dir_in(&e->desc)) {
-				if (ctx->in_ep == NULL)
-					ctx->in_ep = e;
+				if (!in)
+					in = e;
 			} else {
-				if (ctx->out_ep == NULL)
-					ctx->out_ep = e;
+				if (!out)
+					out = e;
 			}
 			break;
 
@@ -322,6 +322,14 @@ cdc_ncm_find_endpoints(struct cdc_ncm_ctx *ctx, struct usb_interface *intf)
 			break;
 		}
 	}
+	if (in && !dev->in)
+		dev->in = usb_rcvbulkpipe(dev->udev,
+					  in->desc.bEndpointAddress &
+					  USB_ENDPOINT_NUMBER_MASK);
+	if (out && !dev->out)
+		dev->out = usb_sndbulkpipe(dev->udev,
+					   out->desc.bEndpointAddress &
+					   USB_ENDPOINT_NUMBER_MASK);
 }
 
 static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
@@ -477,11 +485,9 @@ advance:
 	if (temp)
 		goto error2;
 
-	cdc_ncm_find_endpoints(ctx, ctx->data);
-	cdc_ncm_find_endpoints(ctx, ctx->control);
-
-	if ((ctx->in_ep == NULL) || (ctx->out_ep == NULL) ||
-	    (ctx->status_ep == NULL))
+	cdc_ncm_find_endpoints(dev, ctx->data);
+	cdc_ncm_find_endpoints(dev, ctx->control);
+	if (!dev->in || !dev->out || !dev->status)
 		goto error2;
 
 	dev->net->ethtool_ops = &cdc_ncm_ethtool_ops;
@@ -496,12 +502,6 @@ advance:
 		dev_info(&dev->udev->dev, "MAC-Address: %pM\n", dev->net->dev_addr);
 	}
 
-
-	dev->in = usb_rcvbulkpipe(dev->udev,
-		ctx->in_ep->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK);
-	dev->out = usb_sndbulkpipe(dev->udev,
-		ctx->out_ep->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK);
-	dev->status = ctx->status_ep;
 	dev->rx_urb_size = ctx->rx_max;
 
 	/* cdc_ncm_setup will override dwNtbOutMaxSize if it is
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index c14e00fb1667..36e1e153ca2d 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -100,9 +100,6 @@ struct cdc_ncm_ctx {
 
 	struct net_device *netdev;
 	struct usb_device *udev;
-	struct usb_host_endpoint *in_ep;
-	struct usb_host_endpoint *out_ep;
-	struct usb_host_endpoint *status_ep;
 	struct usb_interface *control;
 	struct usb_interface *data;
 
-- 
cgit 


From bed6f762123fc53c63efef386531dd877cba2468 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:42 +0100
Subject: net: cdc_ncm: remove redundant netdev field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Too many pointers back and forth are likely to confuse developers,
creating subtle bugs whenever we forget to syncronize them all.

As a usbnet driver, we should stick with the standard struct
usbnet fields as much as possible.  The netdevice is one such
field.

Cc: Greg Suarez <gsuarez@smithmicro.com>
Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  |  2 +-
 drivers/net/usb/cdc_ncm.c   | 73 +++++++++++++++++++++++----------------------
 include/linux/usb/cdc_ncm.h |  3 +-
 3 files changed, 39 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 253472a8a983..af76aaf08b6b 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -175,7 +175,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 	}
 
 	spin_lock_bh(&ctx->mtx);
-	skb_out = cdc_ncm_fill_tx_frame(ctx, skb, sign);
+	skb_out = cdc_ncm_fill_tx_frame(dev, skb, sign);
 	spin_unlock_bh(&ctx->mtx);
 	return skb_out;
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index a989bd5290a6..e39e7678a798 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -80,8 +80,9 @@ cdc_ncm_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info)
 	usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info));
 }
 
-static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx)
+static u8 cdc_ncm_setup(struct usbnet *dev)
 {
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	u32 val;
 	u8 flags;
 	u8 iface_no;
@@ -90,7 +91,6 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx)
 	u16 ntb_fmt_supported;
 	u32 min_dgram_size;
 	u32 min_hdr_size;
-	struct usbnet *dev = netdev_priv(ctx->netdev);
 
 	iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
 
@@ -285,8 +285,8 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx)
 	}
 
 max_dgram_err:
-	if (ctx->netdev->mtu != (ctx->max_datagram_size - eth_hlen))
-		ctx->netdev->mtu = ctx->max_datagram_size - eth_hlen;
+	if (dev->net->mtu != (ctx->max_datagram_size - eth_hlen))
+		dev->net->mtu = ctx->max_datagram_size - eth_hlen;
 
 	return 0;
 }
@@ -375,11 +375,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	hrtimer_init(&ctx->tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	ctx->tx_timer.function = &cdc_ncm_tx_timer_cb;
-	ctx->bh.data = (unsigned long)ctx;
+	ctx->bh.data = (unsigned long)dev;
 	ctx->bh.func = cdc_ncm_txpath_bh;
 	atomic_set(&ctx->stop, 0);
 	spin_lock_init(&ctx->mtx);
-	ctx->netdev = dev->net;
 
 	/* store ctx pointer in device data field */
 	dev->data[0] = (unsigned long)ctx;
@@ -477,7 +476,7 @@ advance:
 		goto error2;
 
 	/* initialize data interface */
-	if (cdc_ncm_setup(ctx))
+	if (cdc_ncm_setup(dev))
 		goto error2;
 
 	/* configure data interface */
@@ -669,9 +668,9 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 }
 
 struct sk_buff *
-cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
+cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 {
-	struct usbnet *dev = netdev_priv(ctx->netdev);
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	struct usb_cdc_ncm_nth16 *nth16;
 	struct usb_cdc_ncm_ndp16 *ndp16;
 	struct sk_buff *skb_out;
@@ -695,7 +694,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
 		if (skb_out == NULL) {
 			if (skb != NULL) {
 				dev_kfree_skb_any(skb);
-				ctx->netdev->stats.tx_dropped++;
+				dev->net->stats.tx_dropped++;
 			}
 			goto exit_no_skb;
 		}
@@ -733,12 +732,12 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
 				/* won't fit, MTU problem? */
 				dev_kfree_skb_any(skb);
 				skb = NULL;
-				ctx->netdev->stats.tx_dropped++;
+				dev->net->stats.tx_dropped++;
 			} else {
 				/* no room for skb - store for later */
 				if (ctx->tx_rem_skb != NULL) {
 					dev_kfree_skb_any(ctx->tx_rem_skb);
-					ctx->netdev->stats.tx_dropped++;
+					dev->net->stats.tx_dropped++;
 				}
 				ctx->tx_rem_skb = skb;
 				ctx->tx_rem_sign = sign;
@@ -771,7 +770,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
 	if (skb != NULL) {
 		dev_kfree_skb_any(skb);
 		skb = NULL;
-		ctx->netdev->stats.tx_dropped++;
+		dev->net->stats.tx_dropped++;
 	}
 
 	ctx->tx_curr_frame_num = n;
@@ -814,7 +813,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign)
 
 	/* return skb */
 	ctx->tx_curr_skb = NULL;
-	ctx->netdev->stats.tx_packets += ctx->tx_curr_frame_num;
+	dev->net->stats.tx_packets += ctx->tx_curr_frame_num;
 	return skb_out;
 
 exit_no_skb:
@@ -846,18 +845,19 @@ static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *timer)
 
 static void cdc_ncm_txpath_bh(unsigned long param)
 {
-	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)param;
+	struct usbnet *dev = (struct usbnet *)param;
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 
 	spin_lock_bh(&ctx->mtx);
 	if (ctx->tx_timer_pending != 0) {
 		ctx->tx_timer_pending--;
 		cdc_ncm_tx_timeout_start(ctx);
 		spin_unlock_bh(&ctx->mtx);
-	} else if (ctx->netdev != NULL) {
+	} else if (dev->net != NULL) {
 		spin_unlock_bh(&ctx->mtx);
-		netif_tx_lock_bh(ctx->netdev);
-		usbnet_start_xmit(NULL, ctx->netdev);
-		netif_tx_unlock_bh(ctx->netdev);
+		netif_tx_lock_bh(dev->net);
+		usbnet_start_xmit(NULL, dev->net);
+		netif_tx_unlock_bh(dev->net);
 	} else {
 		spin_unlock_bh(&ctx->mtx);
 	}
@@ -880,7 +880,7 @@ cdc_ncm_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 		goto error;
 
 	spin_lock_bh(&ctx->mtx);
-	skb_out = cdc_ncm_fill_tx_frame(ctx, skb, cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN));
+	skb_out = cdc_ncm_fill_tx_frame(dev, skb, cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN));
 	spin_unlock_bh(&ctx->mtx);
 	return skb_out;
 
@@ -1047,9 +1047,10 @@ error:
 }
 
 static void
-cdc_ncm_speed_change(struct cdc_ncm_ctx *ctx,
+cdc_ncm_speed_change(struct usbnet *dev,
 		     struct usb_cdc_speed_change *data)
 {
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	uint32_t rx_speed = le32_to_cpu(data->DLBitRRate);
 	uint32_t tx_speed = le32_to_cpu(data->ULBitRate);
 
@@ -1063,18 +1064,18 @@ cdc_ncm_speed_change(struct cdc_ncm_ctx *ctx,
 
 		if ((tx_speed > 1000000) && (rx_speed > 1000000)) {
 			printk(KERN_INFO KBUILD_MODNAME
-				": %s: %u mbit/s downlink "
-				"%u mbit/s uplink\n",
-				ctx->netdev->name,
-				(unsigned int)(rx_speed / 1000000U),
-				(unsigned int)(tx_speed / 1000000U));
+			       ": %s: %u mbit/s downlink "
+			       "%u mbit/s uplink\n",
+			       dev->net->name,
+			       (unsigned int)(rx_speed / 1000000U),
+			       (unsigned int)(tx_speed / 1000000U));
 		} else {
 			printk(KERN_INFO KBUILD_MODNAME
-				": %s: %u kbit/s downlink "
-				"%u kbit/s uplink\n",
-				ctx->netdev->name,
-				(unsigned int)(rx_speed / 1000U),
-				(unsigned int)(tx_speed / 1000U));
+			       ": %s: %u kbit/s downlink "
+			       "%u kbit/s uplink\n",
+			       dev->net->name,
+			       (unsigned int)(rx_speed / 1000U),
+			       (unsigned int)(tx_speed / 1000U));
 		}
 	}
 }
@@ -1091,7 +1092,7 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 
 	/* test for split data in 8-byte chunks */
 	if (test_and_clear_bit(EVENT_STS_SPLIT, &dev->flags)) {
-		cdc_ncm_speed_change(ctx,
+		cdc_ncm_speed_change(dev,
 		      (struct usb_cdc_speed_change *)urb->transfer_buffer);
 		return;
 	}
@@ -1108,8 +1109,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 		ctx->connected = le16_to_cpu(event->wValue);
 
 		printk(KERN_INFO KBUILD_MODNAME ": %s: network connection:"
-			" %sconnected\n",
-			ctx->netdev->name, ctx->connected ? "" : "dis");
+		       " %sconnected\n",
+		       dev->net->name, ctx->connected ? "" : "dis");
 
 		usbnet_link_change(dev, ctx->connected, 0);
 		if (!ctx->connected)
@@ -1121,8 +1122,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 					sizeof(struct usb_cdc_speed_change)))
 			set_bit(EVENT_STS_SPLIT, &dev->flags);
 		else
-			cdc_ncm_speed_change(ctx,
-				(struct usb_cdc_speed_change *) &event[1]);
+			cdc_ncm_speed_change(dev,
+					     (struct usb_cdc_speed_change *)&event[1]);
 		break;
 
 	default:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 36e1e153ca2d..5c47bd9620d5 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -98,7 +98,6 @@ struct cdc_ncm_ctx {
 	const struct usb_cdc_union_desc *union_desc;
 	const struct usb_cdc_ether_desc *ether_desc;
 
-	struct net_device *netdev;
 	struct usb_device *udev;
 	struct usb_interface *control;
 	struct usb_interface *data;
@@ -129,7 +128,7 @@ struct cdc_ncm_ctx {
 extern u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf);
 extern int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
 extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
-extern struct sk_buff *cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign);
+extern struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
 extern int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
 extern int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
 
-- 
cgit 


From de5bee2720776989060b9686e6a89e938a346345 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:43 +0100
Subject: net: cdc_ncm: remove unused udev field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We already use the usbnet udev field everywhere this could have
been used.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 2 --
 include/linux/usb/cdc_ncm.h | 1 -
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index e39e7678a798..9cdd762916dc 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -388,8 +388,6 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	buf = intf->cur_altsetting->extra;
 	len = intf->cur_altsetting->extralen;
 
-	ctx->udev = dev->udev;
-
 	/* parse through descriptors associated with control interface */
 	while ((len > 0) && (buf[0] > 2) && (buf[0] <= len)) {
 
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 5c47bd9620d5..059dcc93c4d8 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -98,7 +98,6 @@ struct cdc_ncm_ctx {
 	const struct usb_cdc_union_desc *union_desc;
 	const struct usb_cdc_ether_desc *ether_desc;
 
-	struct usb_device *udev;
 	struct usb_interface *control;
 	struct usb_interface *data;
 
-- 
cgit 


From f3028c524a7cd4d97b034fc1f35dcaecb5d6f9d6 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:44 +0100
Subject: net: cdc_ncm: remove tx_speed and rx_speed fields
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These fields are only used to prevent printing the same speeds
multiple times if we receive multiple identical speed notifications.

The value of these printk's is questionable, and even more so when
we filter out some of the notifications sent us by the firmware. If
we are going to print any of these, then we should print them all.

Removing little used fields is a bonus.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 37 ++++++++++++++-----------------------
 include/linux/usb/cdc_ncm.h |  2 --
 2 files changed, 14 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 9cdd762916dc..fc36a99f8183 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -510,7 +510,6 @@ advance:
 	    ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
 		ctx->tx_max++;
 
-	ctx->tx_speed = ctx->rx_speed = 0;
 	return 0;
 
 error2:
@@ -1048,7 +1047,6 @@ static void
 cdc_ncm_speed_change(struct usbnet *dev,
 		     struct usb_cdc_speed_change *data)
 {
-	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
 	uint32_t rx_speed = le32_to_cpu(data->DLBitRRate);
 	uint32_t tx_speed = le32_to_cpu(data->ULBitRate);
 
@@ -1056,25 +1054,20 @@ cdc_ncm_speed_change(struct usbnet *dev,
 	 * Currently the USB-NET API does not support reporting the actual
 	 * device speed. Do print it instead.
 	 */
-	if ((tx_speed != ctx->tx_speed) || (rx_speed != ctx->rx_speed)) {
-		ctx->tx_speed = tx_speed;
-		ctx->rx_speed = rx_speed;
-
-		if ((tx_speed > 1000000) && (rx_speed > 1000000)) {
-			printk(KERN_INFO KBUILD_MODNAME
-			       ": %s: %u mbit/s downlink "
-			       "%u mbit/s uplink\n",
-			       dev->net->name,
-			       (unsigned int)(rx_speed / 1000000U),
-			       (unsigned int)(tx_speed / 1000000U));
-		} else {
-			printk(KERN_INFO KBUILD_MODNAME
-			       ": %s: %u kbit/s downlink "
-			       "%u kbit/s uplink\n",
-			       dev->net->name,
-			       (unsigned int)(rx_speed / 1000U),
-			       (unsigned int)(tx_speed / 1000U));
-		}
+	if ((tx_speed > 1000000) && (rx_speed > 1000000)) {
+		printk(KERN_INFO KBUILD_MODNAME
+		       ": %s: %u mbit/s downlink "
+		       "%u mbit/s uplink\n",
+		       dev->net->name,
+		       (unsigned int)(rx_speed / 1000000U),
+		       (unsigned int)(tx_speed / 1000000U));
+	} else {
+		printk(KERN_INFO KBUILD_MODNAME
+		       ": %s: %u kbit/s downlink "
+		       "%u kbit/s uplink\n",
+		       dev->net->name,
+		       (unsigned int)(rx_speed / 1000U),
+		       (unsigned int)(tx_speed / 1000U));
 	}
 }
 
@@ -1111,8 +1104,6 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 		       dev->net->name, ctx->connected ? "" : "dis");
 
 		usbnet_link_change(dev, ctx->connected, 0);
-		if (!ctx->connected)
-			ctx->tx_speed = ctx->rx_speed = 0;
 		break;
 
 	case USB_CDC_NOTIFY_SPEED_CHANGE:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 059dcc93c4d8..f14af3dd0cce 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -110,8 +110,6 @@ struct cdc_ncm_ctx {
 
 	u32 tx_timer_pending;
 	u32 tx_curr_frame_num;
-	u32 rx_speed;
-	u32 tx_speed;
 	u32 rx_max;
 	u32 tx_max;
 	u32 max_datagram_size;
-- 
cgit 


From 6a9612e2cb22b3fd6a7304dcbf2b4ee1cf2104b2 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:45 +0100
Subject: net: cdc_ncm: remove ncm_parm field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Moving the call to cdc_ncm_setup() after the endpoint
setup removes the last remaining reference to ncm_parm
outside cdc_ncm_setup.

Collecting all the ncm_parm based calculations in
cdc_ncm_setup improves readability.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 46 ++++++++++++++++++++++-----------------------
 include/linux/usb/cdc_ncm.h |  1 -
 2 files changed, 23 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index fc36a99f8183..4de3a5423e87 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -83,6 +83,7 @@ cdc_ncm_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info)
 static u8 cdc_ncm_setup(struct usbnet *dev)
 {
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	struct usb_cdc_ncm_ntb_parameters ncm_parm;
 	u32 val;
 	u8 flags;
 	u8 iface_no;
@@ -97,22 +98,22 @@ static u8 cdc_ncm_setup(struct usbnet *dev)
 	err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_PARAMETERS,
 			      USB_TYPE_CLASS | USB_DIR_IN
 			      |USB_RECIP_INTERFACE,
-			      0, iface_no, &ctx->ncm_parm,
-			      sizeof(ctx->ncm_parm));
+			      0, iface_no, &ncm_parm,
+			      sizeof(ncm_parm));
 	if (err < 0) {
 		pr_debug("failed GET_NTB_PARAMETERS\n");
 		return 1;
 	}
 
 	/* read correct set of parameters according to device mode */
-	ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize);
-	ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize);
-	ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder);
-	ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor);
-	ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment);
+	ctx->rx_max = le32_to_cpu(ncm_parm.dwNtbInMaxSize);
+	ctx->tx_max = le32_to_cpu(ncm_parm.dwNtbOutMaxSize);
+	ctx->tx_remainder = le16_to_cpu(ncm_parm.wNdpOutPayloadRemainder);
+	ctx->tx_modulus = le16_to_cpu(ncm_parm.wNdpOutDivisor);
+	ctx->tx_ndp_modulus = le16_to_cpu(ncm_parm.wNdpOutAlignment);
 	/* devices prior to NCM Errata shall set this field to zero */
-	ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams);
-	ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported);
+	ctx->tx_max_datagrams = le16_to_cpu(ncm_parm.wNtbOutMaxDatagrams);
+	ntb_fmt_supported = le16_to_cpu(ncm_parm.bmNtbFormatsSupported);
 
 	eth_hlen = ETH_HLEN;
 	min_dgram_size = CDC_NCM_MIN_DATAGRAM_SIZE;
@@ -153,7 +154,7 @@ static u8 cdc_ncm_setup(struct usbnet *dev)
 	}
 
 	/* inform device about NTB input size changes */
-	if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) {
+	if (ctx->rx_max != le32_to_cpu(ncm_parm.dwNtbInMaxSize)) {
 		__le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
 
 		err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE,
@@ -171,6 +172,14 @@ static u8 cdc_ncm_setup(struct usbnet *dev)
 		pr_debug("Using default maximum transmit length=%d\n",
 						CDC_NCM_NTB_MAX_SIZE_TX);
 		ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX;
+
+		/* Adding a pad byte here simplifies the handling in
+		 * cdc_ncm_fill_tx_frame, by making tx_max always
+		 * represent the real skb max size.
+		 */
+		if (ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
+			ctx->tx_max++;
+
 	}
 
 	/*
@@ -473,10 +482,6 @@ advance:
 	if (temp)
 		goto error2;
 
-	/* initialize data interface */
-	if (cdc_ncm_setup(dev))
-		goto error2;
-
 	/* configure data interface */
 	temp = usb_set_interface(dev->udev, iface_no, data_altsetting);
 	if (temp)
@@ -487,6 +492,10 @@ advance:
 	if (!dev->in || !dev->out || !dev->status)
 		goto error2;
 
+	/* initialize data interface */
+	if (cdc_ncm_setup(dev))
+		goto error2;
+
 	dev->net->ethtool_ops = &cdc_ncm_ethtool_ops;
 
 	usb_set_intfdata(ctx->data, dev);
@@ -501,15 +510,6 @@ advance:
 
 	dev->rx_urb_size = ctx->rx_max;
 
-	/* cdc_ncm_setup will override dwNtbOutMaxSize if it is
-	 * outside the sane range. Adding a pad byte here if necessary
-	 * simplifies the handling in cdc_ncm_fill_tx_frame, making
-	 * tx_max always represent the real skb max size.
-	 */
-	if (ctx->tx_max != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) &&
-	    ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
-		ctx->tx_max++;
-
 	return 0;
 
 error2:
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index f14af3dd0cce..89b52a0fe4b9 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -88,7 +88,6 @@
 #define cdc_ncm_data_intf_is_mbim(x)  ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
 
 struct cdc_ncm_ctx {
-	struct usb_cdc_ncm_ntb_parameters ncm_parm;
 	struct hrtimer tx_timer;
 	struct tasklet_struct bh;
 
-- 
cgit 


From 832922362e1308aaef95a43383577d56f51fbc3c Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:47 +0100
Subject: net: cdc_ncm: remove descriptor pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

header_desc was completely unused and union_desc was never used
outside cdc_ncm_bind_common.

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 12 ++++++------
 include/linux/usb/cdc_ncm.h |  4 +---
 2 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index b8de8ddd6d98..435fcc75d706 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -372,6 +372,7 @@ static const struct ethtool_ops cdc_ncm_ethtool_ops = {
 
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
 {
+	const struct usb_cdc_union_desc *union_desc = NULL;
 	struct cdc_ncm_ctx *ctx;
 	struct usb_driver *driver;
 	u8 *buf;
@@ -406,16 +407,15 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 		switch (buf[2]) {
 		case USB_CDC_UNION_TYPE:
-			if (buf[0] < sizeof(*(ctx->union_desc)))
+			if (buf[0] < sizeof(*union_desc))
 				break;
 
-			ctx->union_desc =
-					(const struct usb_cdc_union_desc *)buf;
+			union_desc = (const struct usb_cdc_union_desc *)buf;
 
 			ctx->control = usb_ifnum_to_if(dev->udev,
-					ctx->union_desc->bMasterInterface0);
+						       union_desc->bMasterInterface0);
 			ctx->data = usb_ifnum_to_if(dev->udev,
-					ctx->union_desc->bSlaveInterface0);
+						    union_desc->bSlaveInterface0);
 			break;
 
 		case USB_CDC_ETHERNET_TYPE:
@@ -458,7 +458,7 @@ advance:
 	}
 
 	/* some buggy devices have an IAD but no CDC Union */
-	if (!ctx->union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
+	if (!union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
 		ctx->control = intf;
 		ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1);
 		dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n");
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 89b52a0fe4b9..cad54ad4ad12 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -92,9 +92,7 @@ struct cdc_ncm_ctx {
 	struct tasklet_struct bh;
 
 	const struct usb_cdc_ncm_desc *func_desc;
-	const struct usb_cdc_mbim_desc   *mbim_desc;
-	const struct usb_cdc_header_desc *header_desc;
-	const struct usb_cdc_union_desc *union_desc;
+	const struct usb_cdc_mbim_desc *mbim_desc;
 	const struct usb_cdc_ether_desc *ether_desc;
 
 	struct usb_interface *control;
-- 
cgit 


From 6dd13e83ce37f716e36085cb8b58779da1e98f6d Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Fri, 1 Nov 2013 11:16:57 +0100
Subject: net: cdc_ncm: drop "extern" from header declarations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Cc: Alexey Orishko <alexey.orishko@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/usb/cdc_ncm.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index cad54ad4ad12..2300f7492927 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -119,11 +119,11 @@ struct cdc_ncm_ctx {
 	u16 connected;
 };
 
-extern u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf);
-extern int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
-extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
-extern struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
-extern int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
-extern int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
+u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf);
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
+void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
+struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
+int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
+int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
 
 #endif /* __LINUX_USB_CDC_NCM_H */
-- 
cgit 


From f6f0747e5bc69401d7f90313aa1b46709d27840a Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Mon, 28 Oct 2013 13:12:35 -0500
Subject: of: Add empty for_each_available_child_of_node() macro definition

Add this empty macro definition so users can be compiled without
excluding this macro call with preprocessor directives when CONFIG_OF
is disabled.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
 include/linux/of.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/of.h b/include/linux/of.h
index 54017b83650b..b97f685c941f 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -366,6 +366,9 @@ static inline bool of_have_populated_dt(void)
 #define for_each_child_of_node(parent, child) \
 	while (0)
 
+#define for_each_available_child_of_node(parent, child) \
+	while (0)
+
 static inline struct device_node *of_get_child_by_name(
 					const struct device_node *node,
 					const char *name)
-- 
cgit 


From f7b13e4330ef3c20e62ac4908cc96c1c318056c2 Mon Sep 17 00:00:00 2001
From: Holger Eitzenberger <holger@eitzenberger.org>
Date: Thu, 26 Sep 2013 17:31:51 +0200
Subject: netfilter: introduce nf_conn_acct structure

Encapsulate counters for both directions into nf_conn_acct. During
that process also consistently name pointers to the extend 'acct',
not 'counters'. This patch is a cleanup.

Signed-off-by: Holger Eitzenberger <holger@eitzenberger.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_acct.h   | 10 +++++++---
 include/net/netfilter/nf_conntrack_extend.h |  2 +-
 net/netfilter/nf_conntrack_acct.c           | 12 +++++++-----
 net/netfilter/nf_conntrack_core.c           | 16 ++++++++++------
 net/netfilter/nf_conntrack_netlink.c        | 16 +++++++++-------
 net/netfilter/xt_connbytes.c                |  6 ++++--
 6 files changed, 38 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index fef44edf49c1..79d8d16732b4 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -19,17 +19,21 @@ struct nf_conn_counter {
 	atomic64_t bytes;
 };
 
+struct nf_conn_acct {
+	struct nf_conn_counter counter[IP_CT_DIR_MAX];
+};
+
 static inline
-struct nf_conn_counter *nf_conn_acct_find(const struct nf_conn *ct)
+struct nf_conn_acct *nf_conn_acct_find(const struct nf_conn *ct)
 {
 	return nf_ct_ext_find(ct, NF_CT_EXT_ACCT);
 }
 
 static inline
-struct nf_conn_counter *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
+struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
 {
 	struct net *net = nf_ct_net(ct);
-	struct nf_conn_counter *acct;
+	struct nf_conn_acct *acct;
 
 	if (!net->ct.sysctl_acct)
 		return NULL;
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 86372ae0ee84..956b175523ff 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -36,7 +36,7 @@ enum nf_ct_ext_id {
 #define NF_CT_EXT_HELPER_TYPE struct nf_conn_help
 #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat
 #define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj
-#define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter
+#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct
 #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache
 #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone
 #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index 2d3030ab5b61..a4b5e2a435ac 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -39,21 +39,23 @@ static struct ctl_table acct_sysctl_table[] = {
 unsigned int
 seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
 {
-	struct nf_conn_counter *acct;
+	struct nf_conn_acct *acct;
+	struct nf_conn_counter *counter;
 
 	acct = nf_conn_acct_find(ct);
 	if (!acct)
 		return 0;
 
+	counter = acct->counter;
 	return seq_printf(s, "packets=%llu bytes=%llu ",
-			  (unsigned long long)atomic64_read(&acct[dir].packets),
-			  (unsigned long long)atomic64_read(&acct[dir].bytes));
+			  (unsigned long long)atomic64_read(&counter[dir].packets),
+			  (unsigned long long)atomic64_read(&counter[dir].bytes));
 };
 EXPORT_SYMBOL_GPL(seq_print_acct);
 
 static struct nf_ct_ext_type acct_extend __read_mostly = {
-	.len	= sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]),
-	.align	= __alignof__(struct nf_conn_counter[IP_CT_DIR_MAX]),
+	.len	= sizeof(struct nf_conn_acct),
+	.align	= __alignof__(struct nf_conn_acct),
 	.id	= NF_CT_EXT_ACCT,
 };
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5d892febd64c..e22d950c60b3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1109,12 +1109,14 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 
 acct:
 	if (do_acct) {
-		struct nf_conn_counter *acct;
+		struct nf_conn_acct *acct;
 
 		acct = nf_conn_acct_find(ct);
 		if (acct) {
-			atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
-			atomic64_add(skb->len, &acct[CTINFO2DIR(ctinfo)].bytes);
+			struct nf_conn_counter *counter = acct->counter;
+
+			atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
+			atomic64_add(skb->len, &counter[CTINFO2DIR(ctinfo)].bytes);
 		}
 	}
 }
@@ -1126,13 +1128,15 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
 		       int do_acct)
 {
 	if (do_acct) {
-		struct nf_conn_counter *acct;
+		struct nf_conn_acct *acct;
 
 		acct = nf_conn_acct_find(ct);
 		if (acct) {
-			atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
+			struct nf_conn_counter *counter = acct->counter;
+
+			atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
 			atomic64_add(skb->len - skb_network_offset(skb),
-				     &acct[CTINFO2DIR(ctinfo)].bytes);
+				     &counter[CTINFO2DIR(ctinfo)].bytes);
 		}
 	}
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index eea936b70d15..ddc3777d8340 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -237,19 +237,21 @@ static int
 ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct,
 			enum ip_conntrack_dir dir, int type)
 {
-	struct nf_conn_counter *acct;
+	struct nf_conn_acct *acct;
+	struct nf_conn_counter *counter;
 	u64 pkts, bytes;
 
 	acct = nf_conn_acct_find(ct);
 	if (!acct)
 		return 0;
 
+	counter = acct->counter;
 	if (type == IPCTNL_MSG_CT_GET_CTRZERO) {
-		pkts = atomic64_xchg(&acct[dir].packets, 0);
-		bytes = atomic64_xchg(&acct[dir].bytes, 0);
+		pkts = atomic64_xchg(&counter[dir].packets, 0);
+		bytes = atomic64_xchg(&counter[dir].bytes, 0);
 	} else {
-		pkts = atomic64_read(&acct[dir].packets);
-		bytes = atomic64_read(&acct[dir].bytes);
+		pkts = atomic64_read(&counter[dir].packets);
+		bytes = atomic64_read(&counter[dir].bytes);
 	}
 	return dump_counters(skb, pkts, bytes, dir);
 }
@@ -530,7 +532,7 @@ ctnetlink_proto_size(const struct nf_conn *ct)
 }
 
 static inline size_t
-ctnetlink_counters_size(const struct nf_conn *ct)
+ctnetlink_acct_size(const struct nf_conn *ct)
 {
 	if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT))
 		return 0;
@@ -579,7 +581,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
-	       + ctnetlink_counters_size(ct)
+	       + ctnetlink_acct_size(ct)
 	       + ctnetlink_timestamp_size(ct)
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
 	       + nla_total_size(0) /* CTA_PROTOINFO */
diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c
index e595e07a759b..1e634615ab9d 100644
--- a/net/netfilter/xt_connbytes.c
+++ b/net/netfilter/xt_connbytes.c
@@ -26,16 +26,18 @@ connbytes_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	u_int64_t what = 0;	/* initialize to make gcc happy */
 	u_int64_t bytes = 0;
 	u_int64_t pkts = 0;
+	const struct nf_conn_acct *acct;
 	const struct nf_conn_counter *counters;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (!ct)
 		return false;
 
-	counters = nf_conn_acct_find(ct);
-	if (!counters)
+	acct = nf_conn_acct_find(ct);
+	if (!acct)
 		return false;
 
+	counters = acct->counter;
 	switch (sinfo->what) {
 	case XT_CONNBYTES_PKTS:
 		switch (sinfo->direction) {
-- 
cgit 


From 6e95fcaa42e5078ac265964deebed597f9eae07a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 30 Oct 2013 11:50:49 +0100
Subject: lib: crc32: add functionality to combine two crc32{, c}s in GF(2)

This patch adds a combinator to merge two or more crc32{,c}s
into a new one. This is useful for checksum computations of
fragmented skbs that use crc32/crc32c as checksums.

The arithmetics for combining both in the GF(2) was taken and
slightly modified from zlib. Only passing two crcs is insufficient
as two crcs and the length of the second piece is needed for
merging. The code is made generic, so that only polynomials
need to be passed for crc32_le resp. crc32c_le.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/crc32.h | 40 +++++++++++++++++++++++++
 lib/crc32.c           | 81 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 121 insertions(+)

(limited to 'include')

diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 68267b64bb98..7d275c4fc011 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -11,8 +11,48 @@
 extern u32  crc32_le(u32 crc, unsigned char const *p, size_t len);
 extern u32  crc32_be(u32 crc, unsigned char const *p, size_t len);
 
+/**
+ * crc32_le_combine - Combine two crc32 check values into one. For two
+ * 		      sequences of bytes, seq1 and seq2 with lengths len1
+ * 		      and len2, crc32_le() check values were calculated
+ * 		      for each, crc1 and crc2.
+ *
+ * @crc1: crc32 of the first block
+ * @crc2: crc32 of the second block
+ * @len2: length of the second block
+ *
+ * Return: The crc32_le() check value of seq1 and seq2 concatenated,
+ * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
+ * 	   the concatenated memory area of seq1 with seq2, and crc_full
+ * 	   the crc32_le() value of seq_full, then crc_full ==
+ * 	   crc32_le_combine(crc1, crc2, len2) when crc_full was seeded
+ * 	   with the same initializer as crc1, and crc2 seed was 0. See
+ * 	   also crc32_combine_test().
+ */
+extern u32  crc32_le_combine(u32 crc1, u32 crc2, size_t len2);
+
 extern u32  __crc32c_le(u32 crc, unsigned char const *p, size_t len);
 
+/**
+ * __crc32c_le_combine - Combine two crc32c check values into one. For two
+ * 			 sequences of bytes, seq1 and seq2 with lengths len1
+ * 			 and len2, __crc32c_le() check values were calculated
+ * 			 for each, crc1 and crc2.
+ *
+ * @crc1: crc32c of the first block
+ * @crc2: crc32c of the second block
+ * @len2: length of the second block
+ *
+ * Return: The __crc32c_le() check value of seq1 and seq2 concatenated,
+ * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
+ * 	   the concatenated memory area of seq1 with seq2, and crc_full
+ * 	   the __crc32c_le() value of seq_full, then crc_full ==
+ * 	   __crc32c_le_combine(crc1, crc2, len2) when crc_full was
+ * 	   seeded with the same initializer as crc1, and crc2 seed
+ * 	   was 0. See also crc32c_combine_test().
+ */
+extern u32  __crc32c_le_combine(u32 crc1, u32 crc2, size_t len2);
+
 #define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
 
 /*
diff --git a/lib/crc32.c b/lib/crc32.c
index 429d61ce6aa0..595205cddc30 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -49,6 +49,30 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
 MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
+#define GF2_DIM		32
+
+static u32 gf2_matrix_times(u32 *mat, u32 vec)
+{
+	u32 sum = 0;
+
+	while (vec) {
+		if (vec & 1)
+			sum ^= *mat;
+		vec >>= 1;
+		mat++;
+	}
+
+	return sum;
+}
+
+static void gf2_matrix_square(u32 *square, u32 *mat)
+{
+	int i;
+
+	for (i = 0; i < GF2_DIM; i++)
+		square[i] = gf2_matrix_times(mat, mat[i]);
+}
+
 #if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
 
 /* implements slicing-by-4 or slicing-by-8 algorithm */
@@ -130,6 +154,52 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 }
 #endif
 
+/* For conditions of distribution and use, see copyright notice in zlib.h */
+static u32 crc32_generic_combine(u32 crc1, u32 crc2, size_t len2,
+				 u32 polynomial)
+{
+	u32 even[GF2_DIM]; /* Even-power-of-two zeros operator */
+	u32 odd[GF2_DIM];  /* Odd-power-of-two zeros operator  */
+	u32 row;
+	int i;
+
+	if (len2 <= 0)
+		return crc1;
+
+	/* Put operator for one zero bit in odd */
+	odd[0] = polynomial;
+	row = 1;
+	for (i = 1; i < GF2_DIM; i++) {
+		odd[i] = row;
+		row <<= 1;
+	}
+
+	gf2_matrix_square(even, odd); /* Put operator for two zero bits in even */
+	gf2_matrix_square(odd, even); /* Put operator for four zero bits in odd */
+
+	/* Apply len2 zeros to crc1 (first square will put the operator for one
+	 * zero byte, eight zero bits, in even).
+	 */
+	do {
+		/* Apply zeros operator for this bit of len2 */
+		gf2_matrix_square(even, odd);
+		if (len2 & 1)
+			crc1 = gf2_matrix_times(even, crc1);
+		len2 >>= 1;
+		/* If no more bits set, then done */
+		if (len2 == 0)
+			break;
+		/* Another iteration of the loop with odd and even swapped */
+		gf2_matrix_square(odd, even);
+		if (len2 & 1)
+			crc1 = gf2_matrix_times(odd, crc1);
+		len2 >>= 1;
+	} while (len2 != 0);
+
+	crc1 ^= crc2;
+	return crc1;
+}
+
 /**
  * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II
  *			CRC32/CRC32C
@@ -200,8 +270,19 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 			(const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE);
 }
 #endif
+u32 __pure crc32_le_combine(u32 crc1, u32 crc2, size_t len2)
+{
+	return crc32_generic_combine(crc1, crc2, len2, CRCPOLY_LE);
+}
+
+u32 __pure __crc32c_le_combine(u32 crc1, u32 crc2, size_t len2)
+{
+	return crc32_generic_combine(crc1, crc2, len2, CRC32C_POLY_LE);
+}
 EXPORT_SYMBOL(crc32_le);
+EXPORT_SYMBOL(crc32_le_combine);
 EXPORT_SYMBOL(__crc32c_le);
+EXPORT_SYMBOL(__crc32c_le_combine);
 
 /**
  * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
-- 
cgit 


From 2817a336d4d533fb8b68719723cd60ea7dd7c09e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 30 Oct 2013 11:50:51 +0100
Subject: net: skb_checksum: allow custom update/combine for walking skb

Currently, skb_checksum walks over 1) linearized, 2) frags[], and
3) frag_list data and calculats the one's complement, a 32 bit
result suitable for feeding into itself or csum_tcpudp_magic(),
but unsuitable for SCTP as we're calculating CRC32c there.

Hence, in order to not re-implement the very same function in
SCTP (and maybe other protocols) over and over again, use an
update() + combine() callback internally to allow for walking
over the skb with different algorithms.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 13 ++++++++++---
 include/net/checksum.h |  6 ++++++
 net/core/skbuff.c      | 31 +++++++++++++++++++++----------
 3 files changed, 37 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2c154976394b..44727b5d4981 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2360,8 +2360,6 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *from, int offset,
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
-__wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
-		    __wsum csum);
 int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len);
 int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len);
 __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to,
@@ -2373,9 +2371,18 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
 int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
 void skb_scrub_packet(struct sk_buff *skb, bool xnet);
-
 struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 
+struct skb_checksum_ops {
+	__wsum (*update)(const void *mem, int len, __wsum wsum);
+	__wsum (*combine)(__wsum csum, __wsum csum2, int offset, int len);
+};
+
+__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
+		      __wsum csum, const struct skb_checksum_ops *ops);
+__wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
+		    __wsum csum);
+
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
 {
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 8f59ca50477c..15f33fde826e 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -78,6 +78,12 @@ csum_block_add(__wsum csum, __wsum csum2, int offset)
 	return csum_add(csum, (__force __wsum)sum);
 }
 
+static inline __wsum
+csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len)
+{
+	return csum_block_add(csum, csum2, offset);
+}
+
 static inline __wsum
 csum_block_sub(__wsum csum, __wsum csum2, int offset)
 {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0ab32faa520f..31aab5376cb4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1928,9 +1928,8 @@ fault:
 EXPORT_SYMBOL(skb_store_bits);
 
 /* Checksum skb data. */
-
-__wsum skb_checksum(const struct sk_buff *skb, int offset,
-			  int len, __wsum csum)
+__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
+		      __wsum csum, const struct skb_checksum_ops *ops)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -1941,7 +1940,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		csum = csum_partial(skb->data + offset, copy, csum);
+		csum = ops->update(skb->data + offset, copy, csum);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -1962,10 +1961,10 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 			if (copy > len)
 				copy = len;
 			vaddr = kmap_atomic(skb_frag_page(frag));
-			csum2 = csum_partial(vaddr + frag->page_offset +
-					     offset - start, copy, 0);
+			csum2 = ops->update(vaddr + frag->page_offset +
+					    offset - start, copy, 0);
 			kunmap_atomic(vaddr);
-			csum = csum_block_add(csum, csum2, pos);
+			csum = ops->combine(csum, csum2, pos, copy);
 			if (!(len -= copy))
 				return csum;
 			offset += copy;
@@ -1984,9 +1983,9 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 			__wsum csum2;
 			if (copy > len)
 				copy = len;
-			csum2 = skb_checksum(frag_iter, offset - start,
-					     copy, 0);
-			csum = csum_block_add(csum, csum2, pos);
+			csum2 = __skb_checksum(frag_iter, offset - start,
+					       copy, 0, ops);
+			csum = ops->combine(csum, csum2, pos, copy);
 			if ((len -= copy) == 0)
 				return csum;
 			offset += copy;
@@ -1998,6 +1997,18 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 
 	return csum;
 }
+EXPORT_SYMBOL(__skb_checksum);
+
+__wsum skb_checksum(const struct sk_buff *skb, int offset,
+		    int len, __wsum csum)
+{
+	const struct skb_checksum_ops ops = {
+		.update  = csum_partial,
+		.combine = csum_block_add_ext,
+	};
+
+	return __skb_checksum(skb, offset, len, csum, &ops);
+}
 EXPORT_SYMBOL(skb_checksum);
 
 /* Both of above in one bottle. */
-- 
cgit 


From e6d8b64b34aa8a9fe39609bc2db8a243b0331ceb Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 30 Oct 2013 11:50:52 +0100
Subject: net: sctp: fix and consolidate SCTP checksumming code

This fixes an outstanding bug found through IPVS, where SCTP packets
with skb->data_len > 0 (non-linearized) and empty frag_list, but data
accumulated in frags[] member, are forwarded with incorrect checksum
letting SCTP initial handshake fail on some systems. Linearizing each
SCTP skb in IPVS to prevent that would not be a good solution as
this leads to an additional and unnecessary performance penalty on
the load-balancer itself for no good reason (as we actually only want
to update the checksum, and can do that in a different/better way
presented here).

The actual problem is elsewhere, namely, that SCTP's checksumming
in sctp_compute_cksum() does not take frags[] into account like
skb_checksum() does. So while we are fixing this up, we better reuse
the existing code that we have anyway in __skb_checksum() and use it
for walking through the data doing checksumming. This will not only
fix this issue, but also consolidates some SCTP code with core
sk_buff code, bringing it closer together and removing respectively
avoiding reimplementation of skb_checksum() for no good reason.

As crc32c() can use hardware implementation within the crypto layer,
we leave that intact (it wraps around / falls back to e.g. slice-by-8
algorithm in __crc32c_le() otherwise); plus use the __crc32c_le_combine()
combinator for crc32c blocks.

Also, we remove all other SCTP checksumming code, so that we only
have to use sctp_compute_cksum() from now on; for doing that, we need
to transform SCTP checkumming in output path slightly, and can leave
the rest intact.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/checksum.h | 56 +++++++++++++++------------------------------
 net/sctp/output.c           |  9 +-------
 2 files changed, 20 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h
index 259924d63ba6..6bd44fe94c26 100644
--- a/include/net/sctp/checksum.h
+++ b/include/net/sctp/checksum.h
@@ -42,56 +42,38 @@
 #include <linux/types.h>
 #include <net/sctp/sctp.h>
 #include <linux/crc32c.h>
+#include <linux/crc32.h>
 
-static inline __u32 sctp_crc32c(__u32 crc, u8 *buffer, u16 length)
+static inline __wsum sctp_csum_update(const void *buff, int len, __wsum sum)
 {
-	return crc32c(crc, buffer, length);
-}
-
-static inline __u32 sctp_start_cksum(__u8 *buffer, __u16 length)
-{
-	__u32 crc = ~(__u32)0;
-	__u8  zero[sizeof(__u32)] = {0};
-
-	/* Optimize this routine to be SCTP specific, knowing how
-	 * to skip the checksum field of the SCTP header.
+	/* This uses the crypto implementation of crc32c, which is either
+	 * implemented w/ hardware support or resolves to __crc32c_le().
 	 */
-
-	/* Calculate CRC up to the checksum. */
-	crc = sctp_crc32c(crc, buffer, sizeof(struct sctphdr) - sizeof(__u32));
-
-	/* Skip checksum field of the header. */
-	crc = sctp_crc32c(crc, zero, sizeof(__u32));
-
-	/* Calculate the rest of the CRC. */
-	crc = sctp_crc32c(crc, &buffer[sizeof(struct sctphdr)],
-			    length - sizeof(struct sctphdr));
-	return crc;
-}
-
-static inline __u32 sctp_update_cksum(__u8 *buffer, __u16 length, __u32 crc32)
-{
-	return sctp_crc32c(crc32, buffer, length);
+	return crc32c(sum, buff, len);
 }
 
-static inline __le32 sctp_end_cksum(__u32 crc32)
+static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
+				       int offset, int len)
 {
-	return cpu_to_le32(~crc32);
+	return __crc32c_le_combine(csum, csum2, len);
 }
 
-/* Calculate the CRC32C checksum of an SCTP packet.  */
 static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
 					unsigned int offset)
 {
-	const struct sk_buff *iter;
+	struct sctphdr *sh = sctp_hdr(skb);
+        __le32 ret, old = sh->checksum;
+	const struct skb_checksum_ops ops = {
+		.update  = sctp_csum_update,
+		.combine = sctp_csum_combine,
+	};
 
-	__u32 crc32 = sctp_start_cksum(skb->data + offset,
-				       skb_headlen(skb) - offset);
-	skb_walk_frags(skb, iter)
-		crc32 = sctp_update_cksum((__u8 *) iter->data,
-					  skb_headlen(iter), crc32);
+	sh->checksum = 0;
+	ret = cpu_to_le32(~__skb_checksum(skb, offset, skb->len - offset,
+					  ~(__u32)0, &ops));
+	sh->checksum = old;
 
-	return sctp_end_cksum(crc32);
+	return ret;
 }
 
 #endif /* __sctp_checksum_h__ */
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 319137340d15..e650978daf27 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -390,7 +390,6 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	__u8 has_data = 0;
 	struct dst_entry *dst = tp->dst;
 	unsigned char *auth = NULL;	/* pointer to auth in skb data */
-	__u32 cksum_buf_len = sizeof(struct sctphdr);
 
 	pr_debug("%s: packet:%p\n", __func__, packet);
 
@@ -493,7 +492,6 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 		if (chunk == packet->auth)
 			auth = skb_tail_pointer(nskb);
 
-		cksum_buf_len += chunk->skb->len;
 		memcpy(skb_put(nskb, chunk->skb->len),
 			       chunk->skb->data, chunk->skb->len);
 
@@ -538,12 +536,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	if (!sctp_checksum_disable) {
 		if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
 		    (dst_xfrm(dst) != NULL) || packet->ipfragok) {
-			__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
-
-			/* 3) Put the resultant value into the checksum field in the
-			 *    common header, and leave the rest of the bits unchanged.
-			 */
-			sh->checksum = sctp_end_cksum(crc32);
+			sh->checksum = sctp_compute_cksum(nskb, 0);
 		} else {
 			/* no need to seed pseudo checksum for SCTP */
 			nskb->ip_summed = CHECKSUM_PARTIAL;
-- 
cgit 


From 74d332c13b2148ae934ea94dac1745ae92efe8e5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Oct 2013 13:10:44 -0700
Subject: net: extend net_device allocation to vmalloc()

Joby Poriyath provided a xen-netback patch to reduce the size of
xenvif structure as some netdev allocation could fail under
memory pressure/fragmentation.

This patch is handling the problem at the core level, allowing
any netdev structures to use vmalloc() if kmalloc() failed.

As vmalloc() adds overhead on a critical network path, add __GFP_REPEAT
to kzalloc() flags to do this fallback only when really needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Joby Poriyath <joby.poriyath@citrix.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/netdevices.txt | 10 +++++-----
 include/linux/netdevice.h               |  1 +
 net/core/dev.c                          | 22 +++++++++++++++++-----
 net/core/net-sysfs.c                    |  2 +-
 4 files changed, 24 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt
index c7ecc7080494..0b1cf6b2a592 100644
--- a/Documentation/networking/netdevices.txt
+++ b/Documentation/networking/netdevices.txt
@@ -10,12 +10,12 @@ network devices.
 struct net_device allocation rules
 ==================================
 Network device structures need to persist even after module is unloaded and
-must be allocated with kmalloc.  If device has registered successfully,
-it will be freed on last use by free_netdev.  This is required to handle the
-pathologic case cleanly (example: rmmod mydriver </sys/class/net/myeth/mtu )
+must be allocated with alloc_netdev_mqs() and friends.
+If device has registered successfully, it will be freed on last use
+by free_netdev(). This is required to handle the pathologic case cleanly
+(example: rmmod mydriver </sys/class/net/myeth/mtu )
 
-There are routines in net_init.c to handle the common cases of
-alloc_etherdev, alloc_netdev.  These reserve extra space for driver
+alloc_netdev_mqs()/alloc_netdev() reserve extra space for driver
 private data which gets freed when the network device is freed. If
 separately allocated data is attached to the network device
 (netdev_priv(dev)) then it is up to the module exit handler to free that.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb1d918ecdf1..e6353cafbf05 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1800,6 +1800,7 @@ static inline void unregister_netdevice(struct net_device *dev)
 
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
+void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 0054c8c75f50..0e6136546a8c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6196,6 +6196,16 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
 
+void netdev_freemem(struct net_device *dev)
+{
+	char *addr = (char *)dev - dev->padded;
+
+	if (is_vmalloc_addr(addr))
+		vfree(addr);
+	else
+		kfree(addr);
+}
+
 /**
  *	alloc_netdev_mqs - allocate network device
  *	@sizeof_priv:	size of private data to allocate space for
@@ -6239,7 +6249,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	/* ensure 32-byte alignment of whole construct */
 	alloc_size += NETDEV_ALIGN - 1;
 
-	p = kzalloc(alloc_size, GFP_KERNEL);
+	p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!p)
+		p = vzalloc(alloc_size);
 	if (!p)
 		return NULL;
 
@@ -6248,7 +6260,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->pcpu_refcnt = alloc_percpu(int);
 	if (!dev->pcpu_refcnt)
-		goto free_p;
+		goto free_dev;
 
 	if (dev_addr_init(dev))
 		goto free_pcpu;
@@ -6301,8 +6313,8 @@ free_pcpu:
 	kfree(dev->_rx);
 #endif
 
-free_p:
-	kfree(p);
+free_dev:
+	netdev_freemem(dev);
 	return NULL;
 }
 EXPORT_SYMBOL(alloc_netdev_mqs);
@@ -6339,7 +6351,7 @@ void free_netdev(struct net_device *dev)
 
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
-		kfree((char *)dev - dev->padded);
+		netdev_freemem(dev);
 		return;
 	}
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d954b56b4e47..d03f2c9750fa 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1263,7 +1263,7 @@ static void netdev_release(struct device *d)
 	BUG_ON(dev->reg_state != NETREG_RELEASED);
 
 	kfree(dev->ifalias);
-	kfree((char *)dev - dev->padded);
+	netdev_freemem(dev);
 }
 
 static const void *net_namespace(struct device *d)
-- 
cgit 


From f421436a591d34fa5279b54a96ac07d70250cc8d Mon Sep 17 00:00:00 2001
From: Arvid Brodin <Arvid.Brodin@xdin.com>
Date: Wed, 30 Oct 2013 21:10:47 +0100
Subject: net/hsr: Add support for the High-availability Seamless Redundancy
 protocol (HSRv0)

High-availability Seamless Redundancy ("HSR") provides instant failover
redundancy for Ethernet networks. It requires a special network topology where
all nodes are connected in a ring (each node having two physical network
interfaces). It is suited for applications that demand high availability and
very short reaction time.

HSR acts on the Ethernet layer, using a registered Ethernet protocol type to
send special HSR frames in both directions over the ring. The driver creates
virtual network interfaces that can be used just like any ordinary Linux
network interface, for IP/TCP/UDP traffic etc. All nodes in the network ring
must be HSR capable.

This code is a "best effort" to comply with the HSR standard as described in
IEC 62439-3:2010 (HSRv0).

Signed-off-by: Arvid Brodin <arvid.brodin@xdin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/hsr_netlink.h |  50 ++++
 include/uapi/linux/if_ether.h    |   1 +
 include/uapi/linux/if_link.h     |  13 +
 net/Kconfig                      |   1 +
 net/Makefile                     |   1 +
 net/hsr/Kconfig                  |  27 ++
 net/hsr/Makefile                 |   7 +
 net/hsr/hsr_device.c             | 596 +++++++++++++++++++++++++++++++++++++++
 net/hsr/hsr_device.h             |  29 ++
 net/hsr/hsr_framereg.c           | 503 +++++++++++++++++++++++++++++++++
 net/hsr/hsr_framereg.h           |  53 ++++
 net/hsr/hsr_main.c               | 469 ++++++++++++++++++++++++++++++
 net/hsr/hsr_main.h               | 166 +++++++++++
 net/hsr/hsr_netlink.c            | 457 ++++++++++++++++++++++++++++++
 net/hsr/hsr_netlink.h            |  30 ++
 15 files changed, 2403 insertions(+)
 create mode 100644 include/uapi/linux/hsr_netlink.h
 create mode 100644 net/hsr/Kconfig
 create mode 100644 net/hsr/Makefile
 create mode 100644 net/hsr/hsr_device.c
 create mode 100644 net/hsr/hsr_device.h
 create mode 100644 net/hsr/hsr_framereg.c
 create mode 100644 net/hsr/hsr_framereg.h
 create mode 100644 net/hsr/hsr_main.c
 create mode 100644 net/hsr/hsr_main.h
 create mode 100644 net/hsr/hsr_netlink.c
 create mode 100644 net/hsr/hsr_netlink.h

(limited to 'include')

diff --git a/include/uapi/linux/hsr_netlink.h b/include/uapi/linux/hsr_netlink.h
new file mode 100644
index 000000000000..2475cb8a53af
--- /dev/null
+++ b/include/uapi/linux/hsr_netlink.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ */
+
+#ifndef __UAPI_HSR_NETLINK_H
+#define __UAPI_HSR_NETLINK_H
+
+/* Generic Netlink HSR family definition
+ */
+
+/* attributes */
+enum {
+	HSR_A_UNSPEC,
+	HSR_A_NODE_ADDR,
+	HSR_A_IFINDEX,
+	HSR_A_IF1_AGE,
+	HSR_A_IF2_AGE,
+	HSR_A_NODE_ADDR_B,
+	HSR_A_IF1_SEQ,
+	HSR_A_IF2_SEQ,
+	HSR_A_IF1_IFINDEX,
+	HSR_A_IF2_IFINDEX,
+	HSR_A_ADDR_B_IFINDEX,
+	__HSR_A_MAX,
+};
+#define HSR_A_MAX (__HSR_A_MAX - 1)
+
+
+/* commands */
+enum {
+	HSR_C_UNSPEC,
+	HSR_C_RING_ERROR,
+	HSR_C_NODE_DOWN,
+	HSR_C_GET_NODE_STATUS,
+	HSR_C_SET_NODE_STATUS,
+	HSR_C_GET_NODE_LIST,
+	HSR_C_SET_NODE_LIST,
+	__HSR_C_MAX,
+};
+#define HSR_C_MAX (__HSR_C_MAX - 1)
+
+#endif /* __UAPI_HSR_NETLINK_H */
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index ade07f1c491a..2ce0f6a78fa5 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -85,6 +85,7 @@
 #define ETH_P_8021AH	0x88E7          /* 802.1ah Backbone Service Tag */
 #define ETH_P_MVRP	0x88F5          /* 802.1Q MVRP                  */
 #define ETH_P_1588	0x88F7		/* IEEE 1588 Timesync */
+#define ETH_P_PRP	0x88FB		/* IEC 62439-3 PRP/HSRv0	*/
 #define ETH_P_FCOE	0x8906		/* Fibre Channel over Ethernet  */
 #define ETH_P_TDLS	0x890D          /* TDLS */
 #define ETH_P_FIP	0x8914		/* FCoE Initialization Protocol */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8a1e346243b7..b78566f59aba 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -481,4 +481,17 @@ enum {
 
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
+
+/* HSR section */
+
+enum {
+	IFLA_HSR_UNSPEC,
+	IFLA_HSR_SLAVE1,
+	IFLA_HSR_SLAVE2,
+	IFLA_HSR_MULTICAST_SPEC,
+	__IFLA_HSR_MAX,
+};
+
+#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/net/Kconfig b/net/Kconfig
index b50dacc072f0..0715db64a5c3 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -220,6 +220,7 @@ source "net/openvswitch/Kconfig"
 source "net/vmw_vsock/Kconfig"
 source "net/netlink/Kconfig"
 source "net/mpls/Kconfig"
+source "net/hsr/Kconfig"
 
 config RPS
 	boolean
diff --git a/net/Makefile b/net/Makefile
index 9492e8cb64e9..8fa2f91517f1 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -71,3 +71,4 @@ obj-$(CONFIG_NFC)		+= nfc/
 obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
 obj-$(CONFIG_VSOCKETS)	+= vmw_vsock/
 obj-$(CONFIG_NET_MPLS_GSO)	+= mpls/
+obj-$(CONFIG_HSR)		+= hsr/
diff --git a/net/hsr/Kconfig b/net/hsr/Kconfig
new file mode 100644
index 000000000000..0d3d709052ca
--- /dev/null
+++ b/net/hsr/Kconfig
@@ -0,0 +1,27 @@
+#
+# IEC 62439-3 High-availability Seamless Redundancy
+#
+
+config HSR
+	tristate "High-availability Seamless Redundancy (HSR)"
+	---help---
+	  If you say Y here, then your Linux box will be able to act as a
+	  DANH ("Doubly attached node implementing HSR"). For this to work,
+	  your Linux box needs (at least) two physical Ethernet interfaces,
+	  and it must be connected as a node in a ring network together with
+	  other HSR capable nodes.
+
+	  All Ethernet frames sent over the hsr device will be sent in both
+	  directions on the ring (over both slave ports), giving a redundant,
+	  instant fail-over network. Each HSR node in the ring acts like a
+	  bridge for HSR frames, but filters frames that have been forwarded
+	  earlier.
+
+	  This code is a "best effort" to comply with the HSR standard as
+	  described in IEC 62439-3:2010 (HSRv0), but no compliancy tests have
+	  been made.
+
+	  You need to perform any and all necessary tests yourself before
+	  relying on this code in a safety critical system!
+
+	  If unsure, say N.
diff --git a/net/hsr/Makefile b/net/hsr/Makefile
new file mode 100644
index 000000000000..b68359f181cc
--- /dev/null
+++ b/net/hsr/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for HSR
+#
+
+obj-$(CONFIG_HSR)	+= hsr.o
+
+hsr-y			:= hsr_main.o hsr_framereg.o hsr_device.o hsr_netlink.o
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
new file mode 100644
index 000000000000..cac505f166d5
--- /dev/null
+++ b/net/hsr/hsr_device.c
@@ -0,0 +1,596 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ *
+ * This file contains device methods for creating, using and destroying
+ * virtual HSR devices.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/etherdevice.h>
+#include <linux/if_arp.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_sched.h>
+#include "hsr_device.h"
+#include "hsr_framereg.h"
+#include "hsr_main.h"
+
+
+static bool is_admin_up(struct net_device *dev)
+{
+	return dev && (dev->flags & IFF_UP);
+}
+
+static bool is_slave_up(struct net_device *dev)
+{
+	return dev && is_admin_up(dev) && netif_oper_up(dev);
+}
+
+static void __hsr_set_operstate(struct net_device *dev, int transition)
+{
+	write_lock_bh(&dev_base_lock);
+	if (dev->operstate != transition) {
+		dev->operstate = transition;
+		write_unlock_bh(&dev_base_lock);
+		netdev_state_change(dev);
+	} else {
+		write_unlock_bh(&dev_base_lock);
+	}
+}
+
+void hsr_set_operstate(struct net_device *hsr_dev, struct net_device *slave1,
+		       struct net_device *slave2)
+{
+	if (!is_admin_up(hsr_dev)) {
+		__hsr_set_operstate(hsr_dev, IF_OPER_DOWN);
+		return;
+	}
+
+	if (is_slave_up(slave1) || is_slave_up(slave2))
+		__hsr_set_operstate(hsr_dev, IF_OPER_UP);
+	else
+		__hsr_set_operstate(hsr_dev, IF_OPER_LOWERLAYERDOWN);
+}
+
+void hsr_set_carrier(struct net_device *hsr_dev, struct net_device *slave1,
+		     struct net_device *slave2)
+{
+	if (is_slave_up(slave1) || is_slave_up(slave2))
+		netif_carrier_on(hsr_dev);
+	else
+		netif_carrier_off(hsr_dev);
+}
+
+
+void hsr_check_announce(struct net_device *hsr_dev, int old_operstate)
+{
+	struct hsr_priv *hsr_priv;
+
+	hsr_priv = netdev_priv(hsr_dev);
+
+	if ((hsr_dev->operstate == IF_OPER_UP) && (old_operstate != IF_OPER_UP)) {
+		/* Went up */
+		hsr_priv->announce_count = 0;
+		hsr_priv->announce_timer.expires = jiffies +
+				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
+		add_timer(&hsr_priv->announce_timer);
+	}
+
+	if ((hsr_dev->operstate != IF_OPER_UP) && (old_operstate == IF_OPER_UP))
+		/* Went down */
+		del_timer(&hsr_priv->announce_timer);
+}
+
+
+int hsr_get_max_mtu(struct hsr_priv *hsr_priv)
+{
+	int mtu_max;
+
+	if (hsr_priv->slave[0] && hsr_priv->slave[1])
+		mtu_max = min(hsr_priv->slave[0]->mtu, hsr_priv->slave[1]->mtu);
+	else if (hsr_priv->slave[0])
+		mtu_max = hsr_priv->slave[0]->mtu;
+	else if (hsr_priv->slave[1])
+		mtu_max = hsr_priv->slave[1]->mtu;
+	else
+		mtu_max = HSR_TAGLEN;
+
+	return mtu_max - HSR_TAGLEN;
+}
+
+static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct hsr_priv *hsr_priv;
+
+	hsr_priv = netdev_priv(dev);
+
+	if (new_mtu > hsr_get_max_mtu(hsr_priv)) {
+		netdev_info(hsr_priv->dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n",
+			    HSR_TAGLEN);
+		return -EINVAL;
+	}
+
+	dev->mtu = new_mtu;
+
+	return 0;
+}
+
+static int hsr_dev_open(struct net_device *dev)
+{
+	struct hsr_priv *hsr_priv;
+	int i;
+	char *slave_name;
+
+	hsr_priv = netdev_priv(dev);
+
+	for (i = 0; i < HSR_MAX_SLAVE; i++) {
+		if (hsr_priv->slave[i])
+			slave_name = hsr_priv->slave[i]->name;
+		else
+			slave_name = "null";
+
+		if (!is_slave_up(hsr_priv->slave[i]))
+			netdev_warn(dev, "Slave %c (%s) is not up; please bring it up to get a working HSR network\n",
+				    'A' + i, slave_name);
+	}
+
+	return 0;
+}
+
+static int hsr_dev_close(struct net_device *dev)
+{
+	/* Nothing to do here. We could try to restore the state of the slaves
+	 * to what they were before being changed by the hsr master dev's state,
+	 * but they might have been changed manually in the mean time too, so
+	 * taking them up or down here might be confusing and is probably not a
+	 * good idea.
+	 */
+	return 0;
+}
+
+
+static void hsr_fill_tag(struct hsr_ethhdr *hsr_ethhdr, struct hsr_priv *hsr_priv)
+{
+	unsigned long irqflags;
+
+	/* IEC 62439-1:2010, p 48, says the 4-bit "path" field can take values
+	 * between 0001-1001 ("ring identifier", for regular HSR frames),
+	 * or 1111 ("HSR management", supervision frames). Unfortunately, the
+	 * spec writers forgot to explain what a "ring identifier" is, or
+	 * how it is used. So we just set this to 0001 for regular frames,
+	 * and 1111 for supervision frames.
+	 */
+	set_hsr_tag_path(&hsr_ethhdr->hsr_tag, 0x1);
+
+	/* IEC 62439-1:2010, p 12: "The link service data unit in an Ethernet
+	 * frame is the content of the frame located between the Length/Type
+	 * field and the Frame Check Sequence."
+	 *
+	 * IEC 62439-3, p 48, specifies the "original LPDU" to include the
+	 * original "LT" field (what "LT" means is not explained anywhere as
+	 * far as I can see - perhaps "Length/Type"?). So LSDU_size might
+	 * equal original length + 2.
+	 *   Also, the fact that this field is not used anywhere (might be used
+	 * by a RedBox connecting HSR and PRP nets?) means I cannot test its
+	 * correctness. Instead of guessing, I set this to 0 here, to make any
+	 * problems immediately apparent. Anyone using this driver with PRP/HSR
+	 * RedBoxes might need to fix this...
+	 */
+	set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, 0);
+
+	spin_lock_irqsave(&hsr_priv->seqnr_lock, irqflags);
+	hsr_ethhdr->hsr_tag.sequence_nr = htons(hsr_priv->sequence_nr);
+	hsr_priv->sequence_nr++;
+	spin_unlock_irqrestore(&hsr_priv->seqnr_lock, irqflags);
+
+	hsr_ethhdr->hsr_tag.encap_proto = hsr_ethhdr->ethhdr.h_proto;
+
+	hsr_ethhdr->ethhdr.h_proto = htons(ETH_P_PRP);
+}
+
+static int slave_xmit(struct sk_buff *skb, struct hsr_priv *hsr_priv,
+		      enum hsr_dev_idx dev_idx)
+{
+	struct hsr_ethhdr *hsr_ethhdr;
+
+	hsr_ethhdr = (struct hsr_ethhdr *) skb->data;
+
+	skb->dev = hsr_priv->slave[dev_idx];
+
+	hsr_addr_subst_dest(hsr_priv, &hsr_ethhdr->ethhdr, dev_idx);
+
+	/* Address substitution (IEC62439-3 pp 26, 50): replace mac
+	 * address of outgoing frame with that of the outgoing slave's.
+	 */
+	memcpy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr, ETH_ALEN);
+
+	return dev_queue_xmit(skb);
+}
+
+
+static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct hsr_priv *hsr_priv;
+	struct hsr_ethhdr *hsr_ethhdr;
+	struct sk_buff *skb2;
+	int res1, res2;
+
+	hsr_priv = netdev_priv(dev);
+	hsr_ethhdr = (struct hsr_ethhdr *) skb->data;
+
+	if ((skb->protocol != htons(ETH_P_PRP)) ||
+	    (hsr_ethhdr->ethhdr.h_proto != htons(ETH_P_PRP))) {
+		hsr_fill_tag(hsr_ethhdr, hsr_priv);
+		skb->protocol = htons(ETH_P_PRP);
+	}
+
+	skb2 = pskb_copy(skb, GFP_ATOMIC);
+
+	res1 = NET_XMIT_DROP;
+	if (likely(hsr_priv->slave[HSR_DEV_SLAVE_A]))
+		res1 = slave_xmit(skb, hsr_priv, HSR_DEV_SLAVE_A);
+
+	res2 = NET_XMIT_DROP;
+	if (likely(skb2 && hsr_priv->slave[HSR_DEV_SLAVE_B]))
+		res2 = slave_xmit(skb2, hsr_priv, HSR_DEV_SLAVE_B);
+
+	if (likely(res1 == NET_XMIT_SUCCESS || res1 == NET_XMIT_CN ||
+		   res2 == NET_XMIT_SUCCESS || res2 == NET_XMIT_CN)) {
+		hsr_priv->dev->stats.tx_packets++;
+		hsr_priv->dev->stats.tx_bytes += skb->len;
+	} else {
+		hsr_priv->dev->stats.tx_dropped++;
+	}
+
+	return NETDEV_TX_OK;
+}
+
+
+static int hsr_header_create(struct sk_buff *skb, struct net_device *dev,
+			     unsigned short type, const void *daddr,
+			     const void *saddr, unsigned int len)
+{
+	int res;
+
+	/* Make room for the HSR tag now. We will fill it in later (in
+	 * hsr_dev_xmit)
+	 */
+	if (skb_headroom(skb) < HSR_TAGLEN + ETH_HLEN)
+		return -ENOBUFS;
+	skb_push(skb, HSR_TAGLEN);
+
+	/* To allow VLAN/HSR combos we should probably use
+	 * res = dev_hard_header(skb, dev, type, daddr, saddr, len + HSR_TAGLEN);
+	 * here instead. It would require other changes too, though - e.g.
+	 * separate headers for each slave etc...
+	 */
+	res = eth_header(skb, dev, type, daddr, saddr, len + HSR_TAGLEN);
+	if (res <= 0)
+		return res;
+	skb_reset_mac_header(skb);
+
+	return res + HSR_TAGLEN;
+}
+
+
+static const struct header_ops hsr_header_ops = {
+	.create	 = hsr_header_create,
+	.parse	 = eth_header_parse,
+};
+
+
+/* HSR:2010 supervision frames should be padded so that the whole frame,
+ * including headers and FCS, is 64 bytes (without VLAN).
+ */
+static int hsr_pad(int size)
+{
+	const int min_size = ETH_ZLEN - HSR_TAGLEN - ETH_HLEN;
+
+	if (size >= min_size)
+		return size;
+	return min_size;
+}
+
+static void send_hsr_supervision_frame(struct net_device *hsr_dev, u8 type)
+{
+	struct hsr_priv *hsr_priv;
+	struct sk_buff *skb;
+	int hlen, tlen;
+	struct hsr_sup_tag *hsr_stag;
+	struct hsr_sup_payload *hsr_sp;
+	unsigned long irqflags;
+
+	hlen = LL_RESERVED_SPACE(hsr_dev);
+	tlen = hsr_dev->needed_tailroom;
+	skb = alloc_skb(hsr_pad(sizeof(struct hsr_sup_payload)) + hlen + tlen,
+			GFP_ATOMIC);
+
+	if (skb == NULL)
+		return;
+
+	hsr_priv = netdev_priv(hsr_dev);
+
+	skb_reserve(skb, hlen);
+
+	skb->dev = hsr_dev;
+	skb->protocol = htons(ETH_P_PRP);
+	skb->priority = TC_PRIO_CONTROL;
+
+	if (dev_hard_header(skb, skb->dev, ETH_P_PRP,
+			    hsr_priv->sup_multicast_addr,
+			    skb->dev->dev_addr, skb->len) < 0)
+		goto out;
+
+	skb_pull(skb, sizeof(struct ethhdr));
+	hsr_stag = (typeof(hsr_stag)) skb->data;
+
+	set_hsr_stag_path(hsr_stag, 0xf);
+	set_hsr_stag_HSR_Ver(hsr_stag, 0);
+
+	spin_lock_irqsave(&hsr_priv->seqnr_lock, irqflags);
+	hsr_stag->sequence_nr = htons(hsr_priv->sequence_nr);
+	hsr_priv->sequence_nr++;
+	spin_unlock_irqrestore(&hsr_priv->seqnr_lock, irqflags);
+
+	hsr_stag->HSR_TLV_Type = type;
+	hsr_stag->HSR_TLV_Length = 12;
+
+	skb_push(skb, sizeof(struct ethhdr));
+
+	/* Payload: MacAddressA */
+	hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp));
+	memcpy(hsr_sp->MacAddressA, hsr_dev->dev_addr, ETH_ALEN);
+
+	dev_queue_xmit(skb);
+	return;
+
+out:
+	kfree_skb(skb);
+}
+
+
+/* Announce (supervision frame) timer function
+ */
+static void hsr_announce(unsigned long data)
+{
+	struct hsr_priv *hsr_priv;
+
+	hsr_priv = (struct hsr_priv *) data;
+
+	if (hsr_priv->announce_count < 3) {
+		send_hsr_supervision_frame(hsr_priv->dev, HSR_TLV_ANNOUNCE);
+		hsr_priv->announce_count++;
+	} else {
+		send_hsr_supervision_frame(hsr_priv->dev, HSR_TLV_LIFE_CHECK);
+	}
+
+	if (hsr_priv->announce_count < 3)
+		hsr_priv->announce_timer.expires = jiffies +
+				msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
+	else
+		hsr_priv->announce_timer.expires = jiffies +
+				msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL);
+
+	if (is_admin_up(hsr_priv->dev))
+		add_timer(&hsr_priv->announce_timer);
+}
+
+
+static void restore_slaves(struct net_device *hsr_dev)
+{
+	struct hsr_priv *hsr_priv;
+	int i;
+	int res;
+
+	hsr_priv = netdev_priv(hsr_dev);
+
+	rtnl_lock();
+
+	/* Restore promiscuity */
+	for (i = 0; i < HSR_MAX_SLAVE; i++) {
+		if (!hsr_priv->slave[i])
+			continue;
+		res = dev_set_promiscuity(hsr_priv->slave[i], -1);
+		if (res)
+			netdev_info(hsr_dev,
+				    "Cannot restore slave promiscuity (%s, %d)\n",
+				    hsr_priv->slave[i]->name, res);
+	}
+
+	rtnl_unlock();
+}
+
+static void reclaim_hsr_dev(struct rcu_head *rh)
+{
+	struct hsr_priv *hsr_priv;
+
+	hsr_priv = container_of(rh, struct hsr_priv, rcu_head);
+	free_netdev(hsr_priv->dev);
+}
+
+
+/* According to comments in the declaration of struct net_device, this function
+ * is "Called from unregister, can be used to call free_netdev". Ok then...
+ */
+static void hsr_dev_destroy(struct net_device *hsr_dev)
+{
+	struct hsr_priv *hsr_priv;
+
+	hsr_priv = netdev_priv(hsr_dev);
+
+	del_timer(&hsr_priv->announce_timer);
+	unregister_hsr_master(hsr_priv);    /* calls list_del_rcu on hsr_priv */
+	restore_slaves(hsr_dev);
+	call_rcu(&hsr_priv->rcu_head, reclaim_hsr_dev);   /* reclaim hsr_priv */
+}
+
+static const struct net_device_ops hsr_device_ops = {
+	.ndo_change_mtu = hsr_dev_change_mtu,
+	.ndo_open = hsr_dev_open,
+	.ndo_stop = hsr_dev_close,
+	.ndo_start_xmit = hsr_dev_xmit,
+};
+
+
+void hsr_dev_setup(struct net_device *dev)
+{
+	random_ether_addr(dev->dev_addr);
+
+	ether_setup(dev);
+	dev->header_ops		 = &hsr_header_ops;
+	dev->netdev_ops		 = &hsr_device_ops;
+	dev->tx_queue_len	 = 0;
+
+	dev->destructor = hsr_dev_destroy;
+}
+
+
+/* Return true if dev is a HSR master; return false otherwise.
+ */
+bool is_hsr_master(struct net_device *dev)
+{
+	return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit);
+}
+
+static int check_slave_ok(struct net_device *dev)
+{
+	/* Don't allow HSR on non-ethernet like devices */
+	if ((dev->flags & IFF_LOOPBACK) || (dev->type != ARPHRD_ETHER) ||
+	    (dev->addr_len != ETH_ALEN)) {
+		netdev_info(dev, "Cannot use loopback or non-ethernet device as HSR slave.\n");
+		return -EINVAL;
+	}
+
+	/* Don't allow enslaving hsr devices */
+	if (is_hsr_master(dev)) {
+		netdev_info(dev, "Cannot create trees of HSR devices.\n");
+		return -EINVAL;
+	}
+
+	if (is_hsr_slave(dev)) {
+		netdev_info(dev, "This device is already a HSR slave.\n");
+		return -EINVAL;
+	}
+
+	if (dev->priv_flags & IFF_802_1Q_VLAN) {
+		netdev_info(dev, "HSR on top of VLAN is not yet supported in this driver.\n");
+		return -EINVAL;
+	}
+
+	/* HSR over bonded devices has not been tested, but I'm not sure it
+	 * won't work...
+	 */
+
+	return 0;
+}
+
+
+/* Default multicast address for HSR Supervision frames */
+static const unsigned char def_multicast_addr[ETH_ALEN] = {
+	0x01, 0x15, 0x4e, 0x00, 0x01, 0x00
+};
+
+int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
+		     unsigned char multicast_spec)
+{
+	struct hsr_priv *hsr_priv;
+	int i;
+	int res;
+
+	hsr_priv = netdev_priv(hsr_dev);
+	hsr_priv->dev = hsr_dev;
+	INIT_LIST_HEAD(&hsr_priv->node_db);
+	INIT_LIST_HEAD(&hsr_priv->self_node_db);
+	for (i = 0; i < HSR_MAX_SLAVE; i++)
+		hsr_priv->slave[i] = slave[i];
+
+	spin_lock_init(&hsr_priv->seqnr_lock);
+	/* Overflow soon to find bugs easier: */
+	hsr_priv->sequence_nr = USHRT_MAX - 1024;
+
+	init_timer(&hsr_priv->announce_timer);
+	hsr_priv->announce_timer.function = hsr_announce;
+	hsr_priv->announce_timer.data = (unsigned long) hsr_priv;
+
+	memcpy(hsr_priv->sup_multicast_addr, def_multicast_addr, ETH_ALEN);
+	hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
+
+/* FIXME: should I modify the value of these?
+ *
+ * - hsr_dev->flags - i.e.
+ *			IFF_MASTER/SLAVE?
+ * - hsr_dev->priv_flags - i.e.
+ *			IFF_EBRIDGE?
+ *			IFF_TX_SKB_SHARING?
+ *			IFF_HSR_MASTER/SLAVE?
+ */
+
+	for (i = 0; i < HSR_MAX_SLAVE; i++) {
+		res = check_slave_ok(slave[i]);
+		if (res)
+			return res;
+	}
+
+	hsr_dev->features = slave[0]->features & slave[1]->features;
+	/* Prevent recursive tx locking */
+	hsr_dev->features |= NETIF_F_LLTX;
+	/* VLAN on top of HSR needs testing and probably some work on
+	 * hsr_header_create() etc.
+	 */
+	hsr_dev->features |= NETIF_F_VLAN_CHALLENGED;
+
+	/* Set hsr_dev's MAC address to that of mac_slave1 */
+	memcpy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+
+	/* Set required header length */
+	for (i = 0; i < HSR_MAX_SLAVE; i++) {
+		if (slave[i]->hard_header_len + HSR_TAGLEN >
+						hsr_dev->hard_header_len)
+			hsr_dev->hard_header_len =
+					slave[i]->hard_header_len + HSR_TAGLEN;
+	}
+
+	/* MTU */
+	for (i = 0; i < HSR_MAX_SLAVE; i++)
+		if (slave[i]->mtu - HSR_TAGLEN < hsr_dev->mtu)
+			hsr_dev->mtu = slave[i]->mtu - HSR_TAGLEN;
+
+	/* Make sure the 1st call to netif_carrier_on() gets through */
+	netif_carrier_off(hsr_dev);
+
+	/* Promiscuity */
+	for (i = 0; i < HSR_MAX_SLAVE; i++) {
+		res = dev_set_promiscuity(slave[i], 1);
+		if (res) {
+			netdev_info(hsr_dev, "Cannot set slave promiscuity (%s, %d)\n",
+				    slave[i]->name, res);
+			goto fail;
+		}
+	}
+
+	/* Make sure we recognize frames from ourselves in hsr_rcv() */
+	res = hsr_create_self_node(&hsr_priv->self_node_db,
+					hsr_dev->dev_addr,
+					hsr_priv->slave[1]->dev_addr);
+	if (res < 0)
+		goto fail;
+
+	res = register_netdevice(hsr_dev);
+	if (res)
+		goto fail;
+
+	register_hsr_master(hsr_priv);
+
+	return 0;
+
+fail:
+	restore_slaves(hsr_dev);
+	return res;
+}
diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h
new file mode 100644
index 000000000000..2c7148e73914
--- /dev/null
+++ b/net/hsr/hsr_device.h
@@ -0,0 +1,29 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ */
+
+#ifndef __HSR_DEVICE_H
+#define __HSR_DEVICE_H
+
+#include <linux/netdevice.h>
+#include "hsr_main.h"
+
+void hsr_dev_setup(struct net_device *dev);
+int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
+		     unsigned char multicast_spec);
+void hsr_set_operstate(struct net_device *hsr_dev, struct net_device *slave1,
+		       struct net_device *slave2);
+void hsr_set_carrier(struct net_device *hsr_dev, struct net_device *slave1,
+		     struct net_device *slave2);
+void hsr_check_announce(struct net_device *hsr_dev, int old_operstate);
+bool is_hsr_master(struct net_device *dev);
+int hsr_get_max_mtu(struct hsr_priv *hsr_priv);
+
+#endif /* __HSR_DEVICE_H */
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
new file mode 100644
index 000000000000..003f5bb3acd2
--- /dev/null
+++ b/net/hsr/hsr_framereg.c
@@ -0,0 +1,503 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ *
+ * The HSR spec says never to forward the same frame twice on the same
+ * interface. A frame is identified by its source MAC address and its HSR
+ * sequence number. This code keeps track of senders and their sequence numbers
+ * to allow filtering of duplicate frames, and to detect HSR ring errors.
+ */
+
+#include <linux/if_ether.h>
+#include <linux/etherdevice.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+#include "hsr_main.h"
+#include "hsr_framereg.h"
+#include "hsr_netlink.h"
+
+
+struct node_entry {
+	struct list_head mac_list;
+	unsigned char	MacAddressA[ETH_ALEN];
+	unsigned char	MacAddressB[ETH_ALEN];
+	enum hsr_dev_idx   AddrB_if;	/* The local slave through which AddrB
+					 * frames are received from this node
+					 */
+	unsigned long	time_in[HSR_MAX_SLAVE];
+	bool		time_in_stale[HSR_MAX_SLAVE];
+	u16		seq_out[HSR_MAX_DEV];
+	struct rcu_head rcu_head;
+};
+
+/*	TODO: use hash lists for mac addresses (linux/jhash.h)?    */
+
+
+
+/* Search for mac entry. Caller must hold rcu read lock.
+ */
+static struct node_entry *find_node_by_AddrA(struct list_head *node_db,
+					     const unsigned char addr[ETH_ALEN])
+{
+	struct node_entry *node;
+
+	list_for_each_entry_rcu(node, node_db, mac_list) {
+		if (ether_addr_equal(node->MacAddressA, addr))
+			return node;
+	}
+
+	return NULL;
+}
+
+
+/* Search for mac entry. Caller must hold rcu read lock.
+ */
+static struct node_entry *find_node_by_AddrB(struct list_head *node_db,
+					     const unsigned char addr[ETH_ALEN])
+{
+	struct node_entry *node;
+
+	list_for_each_entry_rcu(node, node_db, mac_list) {
+		if (ether_addr_equal(node->MacAddressB, addr))
+			return node;
+	}
+
+	return NULL;
+}
+
+
+/* Search for mac entry. Caller must hold rcu read lock.
+ */
+struct node_entry *hsr_find_node(struct list_head *node_db, struct sk_buff *skb)
+{
+	struct node_entry *node;
+	struct ethhdr *ethhdr;
+
+	if (!skb_mac_header_was_set(skb))
+		return NULL;
+
+	ethhdr = (struct ethhdr *) skb_mac_header(skb);
+
+	list_for_each_entry_rcu(node, node_db, mac_list) {
+		if (ether_addr_equal(node->MacAddressA, ethhdr->h_source))
+			return node;
+		if (ether_addr_equal(node->MacAddressB, ethhdr->h_source))
+			return node;
+	}
+
+	return NULL;
+}
+
+
+/* Helper for device init; the self_node_db is used in hsr_rcv() to recognize
+ * frames from self that's been looped over the HSR ring.
+ */
+int hsr_create_self_node(struct list_head *self_node_db,
+			 unsigned char addr_a[ETH_ALEN],
+			 unsigned char addr_b[ETH_ALEN])
+{
+	struct node_entry *node, *oldnode;
+
+	node = kmalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
+	memcpy(node->MacAddressA, addr_a, ETH_ALEN);
+	memcpy(node->MacAddressB, addr_b, ETH_ALEN);
+
+	rcu_read_lock();
+	oldnode = list_first_or_null_rcu(self_node_db,
+						struct node_entry, mac_list);
+	if (oldnode) {
+		list_replace_rcu(&oldnode->mac_list, &node->mac_list);
+		rcu_read_unlock();
+		synchronize_rcu();
+		kfree(oldnode);
+	} else {
+		rcu_read_unlock();
+		list_add_tail_rcu(&node->mac_list, self_node_db);
+	}
+
+	return 0;
+}
+
+static void node_entry_reclaim(struct rcu_head *rh)
+{
+	kfree(container_of(rh, struct node_entry, rcu_head));
+}
+
+
+/* Add/merge node to the database of nodes. 'skb' must contain an HSR
+ * supervision frame.
+ * - If the supervision header's MacAddressA field is not yet in the database,
+ * this frame is from an hitherto unknown node - add it to the database.
+ * - If the sender's MAC address is not the same as its MacAddressA address,
+ * the node is using PICS_SUBS (address substitution). Record the sender's
+ * address as the node's MacAddressB.
+ *
+ * This function needs to work even if the sender node has changed one of its
+ * slaves' MAC addresses. In this case, there are four different cases described
+ * by (Addr-changed, received-from) pairs as follows. Note that changing the
+ * SlaveA address is equal to changing the node's own address:
+ *
+ * - (AddrB, SlaveB): The new AddrB will be recorded by PICS_SUBS code since
+ *		      node == NULL.
+ * - (AddrB, SlaveA): Will work as usual (the AddrB change won't be detected
+ *		      from this frame).
+ *
+ * - (AddrA, SlaveB): The old node will be found. We need to detect this and
+ *		      remove the node.
+ * - (AddrA, SlaveA): A new node will be registered (non-PICS_SUBS at first).
+ *		      The old one will be pruned after HSR_NODE_FORGET_TIME.
+ *
+ * We also need to detect if the sender's SlaveA and SlaveB cables have been
+ * swapped.
+ */
+struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
+				  struct node_entry *node,
+				  struct sk_buff *skb,
+				  enum hsr_dev_idx dev_idx)
+{
+	struct hsr_sup_payload *hsr_sp;
+	struct hsr_ethhdr_sp *hsr_ethsup;
+	int i;
+	unsigned long now;
+
+	hsr_ethsup = (struct hsr_ethhdr_sp *) skb_mac_header(skb);
+	hsr_sp = (struct hsr_sup_payload *) skb->data;
+
+	if (node && !ether_addr_equal(node->MacAddressA, hsr_sp->MacAddressA)) {
+		/* Node has changed its AddrA, frame was received from SlaveB */
+		list_del_rcu(&node->mac_list);
+		call_rcu(&node->rcu_head, node_entry_reclaim);
+		node = NULL;
+	}
+
+	if (node && (dev_idx == node->AddrB_if) &&
+	    !ether_addr_equal(node->MacAddressB, hsr_ethsup->ethhdr.h_source)) {
+		/* Cables have been swapped */
+		list_del_rcu(&node->mac_list);
+		call_rcu(&node->rcu_head, node_entry_reclaim);
+		node = NULL;
+	}
+
+	if (node && (dev_idx != node->AddrB_if) &&
+	    (node->AddrB_if != HSR_DEV_NONE) &&
+	    !ether_addr_equal(node->MacAddressA, hsr_ethsup->ethhdr.h_source)) {
+		/* Cables have been swapped */
+		list_del_rcu(&node->mac_list);
+		call_rcu(&node->rcu_head, node_entry_reclaim);
+		node = NULL;
+	}
+
+	if (node)
+		return node;
+
+	node = find_node_by_AddrA(&hsr_priv->node_db, hsr_sp->MacAddressA);
+	if (node) {
+		/* Node is known, but frame was received from an unknown
+		 * address. Node is PICS_SUBS capable; merge its AddrB.
+		 */
+		memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+		node->AddrB_if = dev_idx;
+		return node;
+	}
+
+	node = kzalloc(sizeof(*node), GFP_ATOMIC);
+	if (!node)
+		return NULL;
+
+	memcpy(node->MacAddressA, hsr_sp->MacAddressA, ETH_ALEN);
+	memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN);
+	if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source))
+		node->AddrB_if = dev_idx;
+	else
+		node->AddrB_if = HSR_DEV_NONE;
+
+	/* We are only interested in time diffs here, so use current jiffies
+	 * as initialization. (0 could trigger an spurious ring error warning).
+	 */
+	now = jiffies;
+	for (i = 0; i < HSR_MAX_SLAVE; i++)
+		node->time_in[i] = now;
+	for (i = 0; i < HSR_MAX_DEV; i++)
+		node->seq_out[i] = ntohs(hsr_ethsup->hsr_sup.sequence_nr) - 1;
+
+	list_add_tail_rcu(&node->mac_list, &hsr_priv->node_db);
+
+	return node;
+}
+
+
+/* 'skb' is a frame meant for this host, that is to be passed to upper layers.
+ *
+ * If the frame was sent by a node's B interface, replace the sender
+ * address with that node's "official" address (MacAddressA) so that upper
+ * layers recognize where it came from.
+ */
+void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb)
+{
+	struct ethhdr *ethhdr;
+	struct node_entry *node;
+
+	if (!skb_mac_header_was_set(skb)) {
+		WARN_ONCE(1, "%s: Mac header not set\n", __func__);
+		return;
+	}
+	ethhdr = (struct ethhdr *) skb_mac_header(skb);
+
+	rcu_read_lock();
+	node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source);
+	if (node)
+		memcpy(ethhdr->h_source, node->MacAddressA, ETH_ALEN);
+	rcu_read_unlock();
+}
+
+
+/* 'skb' is a frame meant for another host.
+ * 'hsr_dev_idx' is the HSR index of the outgoing device
+ *
+ * Substitute the target (dest) MAC address if necessary, so the it matches the
+ * recipient interface MAC address, regardless of whether that is the
+ * recipient's A or B interface.
+ * This is needed to keep the packets flowing through switches that learn on
+ * which "side" the different interfaces are.
+ */
+void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr,
+			 enum hsr_dev_idx dev_idx)
+{
+	struct node_entry *node;
+
+	rcu_read_lock();
+	node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest);
+	if (node && (node->AddrB_if == dev_idx))
+		memcpy(ethhdr->h_dest, node->MacAddressB, ETH_ALEN);
+	rcu_read_unlock();
+}
+
+
+/* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b,
+ * false otherwise.
+ */
+static bool seq_nr_after(u16 a, u16 b)
+{
+	/* Remove inconsistency where
+	 * seq_nr_after(a, b) == seq_nr_before(a, b) */
+	if ((int) b - a == 32768)
+		return false;
+
+	return (((s16) (b - a)) < 0);
+}
+#define seq_nr_before(a, b)		seq_nr_after((b), (a))
+#define seq_nr_after_or_eq(a, b)	(!seq_nr_before((a), (b)))
+#define seq_nr_before_or_eq(a, b)	(!seq_nr_after((a), (b)))
+
+
+void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx)
+{
+	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+		WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
+		return;
+	}
+	node->time_in[dev_idx] = jiffies;
+	node->time_in_stale[dev_idx] = false;
+}
+
+
+/* 'skb' is a HSR Ethernet frame (with a HSR tag inserted), with a valid
+ * ethhdr->h_source address and skb->mac_header set.
+ *
+ * Return:
+ *	 1 if frame can be shown to have been sent recently on this interface,
+ *	 0 otherwise, or
+ *	 negative error code on error
+ */
+int hsr_register_frame_out(struct node_entry *node, enum hsr_dev_idx dev_idx,
+			   struct sk_buff *skb)
+{
+	struct hsr_ethhdr *hsr_ethhdr;
+	u16 sequence_nr;
+
+	if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) {
+		WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx);
+		return -EINVAL;
+	}
+	if (!skb_mac_header_was_set(skb)) {
+		WARN_ONCE(1, "%s: Mac header not set\n", __func__);
+		return -EINVAL;
+	}
+	hsr_ethhdr = (struct hsr_ethhdr *) skb_mac_header(skb);
+
+	sequence_nr = ntohs(hsr_ethhdr->hsr_tag.sequence_nr);
+	if (seq_nr_before_or_eq(sequence_nr, node->seq_out[dev_idx]))
+		return 1;
+
+	node->seq_out[dev_idx] = sequence_nr;
+	return 0;
+}
+
+
+
+static bool is_late(struct node_entry *node, enum hsr_dev_idx dev_idx)
+{
+	enum hsr_dev_idx other;
+
+	if (node->time_in_stale[dev_idx])
+		return true;
+
+	if (dev_idx == HSR_DEV_SLAVE_A)
+		other = HSR_DEV_SLAVE_B;
+	else
+		other = HSR_DEV_SLAVE_A;
+
+	if (node->time_in_stale[other])
+		return false;
+
+	if (time_after(node->time_in[other], node->time_in[dev_idx] +
+		       msecs_to_jiffies(MAX_SLAVE_DIFF)))
+		return true;
+
+	return false;
+}
+
+
+/* Remove stale sequence_nr records. Called by timer every
+ * HSR_LIFE_CHECK_INTERVAL (two seconds or so).
+ */
+void hsr_prune_nodes(struct hsr_priv *hsr_priv)
+{
+	struct node_entry *node;
+	unsigned long timestamp;
+	unsigned long time_a, time_b;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(node, &hsr_priv->node_db, mac_list) {
+		/* Shorthand */
+		time_a = node->time_in[HSR_DEV_SLAVE_A];
+		time_b = node->time_in[HSR_DEV_SLAVE_B];
+
+		/* Check for timestamps old enough to risk wrap-around */
+		if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET/2))
+			node->time_in_stale[HSR_DEV_SLAVE_A] = true;
+		if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET/2))
+			node->time_in_stale[HSR_DEV_SLAVE_B] = true;
+
+		/* Get age of newest frame from node.
+		 * At least one time_in is OK here; nodes get pruned long
+		 * before both time_ins can get stale
+		 */
+		timestamp = time_a;
+		if (node->time_in_stale[HSR_DEV_SLAVE_A] ||
+		    (!node->time_in_stale[HSR_DEV_SLAVE_B] &&
+		    time_after(time_b, time_a)))
+			timestamp = time_b;
+
+		/* Warn of ring error only as long as we get frames at all */
+		if (time_is_after_jiffies(timestamp +
+					msecs_to_jiffies(1.5*MAX_SLAVE_DIFF))) {
+
+			if (is_late(node, HSR_DEV_SLAVE_A))
+				hsr_nl_ringerror(hsr_priv, node->MacAddressA,
+						 HSR_DEV_SLAVE_A);
+			else if (is_late(node, HSR_DEV_SLAVE_B))
+				hsr_nl_ringerror(hsr_priv, node->MacAddressA,
+						 HSR_DEV_SLAVE_B);
+		}
+
+		/* Prune old entries */
+		if (time_is_before_jiffies(timestamp +
+					msecs_to_jiffies(HSR_NODE_FORGET_TIME))) {
+			hsr_nl_nodedown(hsr_priv, node->MacAddressA);
+			list_del_rcu(&node->mac_list);
+			/* Note that we need to free this entry later: */
+			call_rcu(&node->rcu_head, node_entry_reclaim);
+		}
+	}
+	rcu_read_unlock();
+}
+
+
+void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos,
+			unsigned char addr[ETH_ALEN])
+{
+	struct node_entry *node;
+
+	if (!_pos) {
+		node = list_first_or_null_rcu(&hsr_priv->node_db,
+						struct node_entry, mac_list);
+		if (node)
+			memcpy(addr, node->MacAddressA, ETH_ALEN);
+		return node;
+	}
+
+	node = _pos;
+	list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) {
+		memcpy(addr, node->MacAddressA, ETH_ALEN);
+		return node;
+	}
+
+	return NULL;
+}
+
+
+int hsr_get_node_data(struct hsr_priv *hsr_priv,
+		      const unsigned char *addr,
+		      unsigned char addr_b[ETH_ALEN],
+		      unsigned int *addr_b_ifindex,
+		      int *if1_age,
+		      u16 *if1_seq,
+		      int *if2_age,
+		      u16 *if2_seq)
+{
+	struct node_entry *node;
+	unsigned long tdiff;
+
+
+	rcu_read_lock();
+	node = find_node_by_AddrA(&hsr_priv->node_db, addr);
+	if (!node) {
+		rcu_read_unlock();
+		return -ENOENT;	/* No such entry */
+	}
+
+	memcpy(addr_b, node->MacAddressB, ETH_ALEN);
+
+	tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A];
+	if (node->time_in_stale[HSR_DEV_SLAVE_A])
+		*if1_age = INT_MAX;
+#if HZ <= MSEC_PER_SEC
+	else if (tdiff > msecs_to_jiffies(INT_MAX))
+		*if1_age = INT_MAX;
+#endif
+	else
+		*if1_age = jiffies_to_msecs(tdiff);
+
+	tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_B];
+	if (node->time_in_stale[HSR_DEV_SLAVE_B])
+		*if2_age = INT_MAX;
+#if HZ <= MSEC_PER_SEC
+	else if (tdiff > msecs_to_jiffies(INT_MAX))
+		*if2_age = INT_MAX;
+#endif
+	else
+		*if2_age = jiffies_to_msecs(tdiff);
+
+	/* Present sequence numbers as if they were incoming on interface */
+	*if1_seq = node->seq_out[HSR_DEV_SLAVE_B];
+	*if2_seq = node->seq_out[HSR_DEV_SLAVE_A];
+
+	if ((node->AddrB_if != HSR_DEV_NONE) && hsr_priv->slave[node->AddrB_if])
+		*addr_b_ifindex = hsr_priv->slave[node->AddrB_if]->ifindex;
+	else
+		*addr_b_ifindex = -1;
+
+	rcu_read_unlock();
+
+	return 0;
+}
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
new file mode 100644
index 000000000000..e6c4022030ad
--- /dev/null
+++ b/net/hsr/hsr_framereg.h
@@ -0,0 +1,53 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ */
+
+#ifndef _HSR_FRAMEREG_H
+#define _HSR_FRAMEREG_H
+
+#include "hsr_main.h"
+
+struct node_entry;
+
+struct node_entry *hsr_find_node(struct list_head *node_db, struct sk_buff *skb);
+
+struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv,
+				  struct node_entry *node,
+				  struct sk_buff *skb,
+				  enum hsr_dev_idx dev_idx);
+
+void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb);
+void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr,
+			 enum hsr_dev_idx dev_idx);
+
+void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx);
+
+int hsr_register_frame_out(struct node_entry *node, enum hsr_dev_idx dev_idx,
+			   struct sk_buff *skb);
+
+void hsr_prune_nodes(struct hsr_priv *hsr_priv);
+
+int hsr_create_self_node(struct list_head *self_node_db,
+			 unsigned char addr_a[ETH_ALEN],
+			 unsigned char addr_b[ETH_ALEN]);
+
+void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos,
+			unsigned char addr[ETH_ALEN]);
+
+int hsr_get_node_data(struct hsr_priv *hsr_priv,
+		      const unsigned char *addr,
+		      unsigned char addr_b[ETH_ALEN],
+		      unsigned int *addr_b_ifindex,
+		      int *if1_age,
+		      u16 *if1_seq,
+		      int *if2_age,
+		      u16 *if2_seq);
+
+#endif /* _HSR_FRAMEREG_H */
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
new file mode 100644
index 000000000000..af68dd83a4e3
--- /dev/null
+++ b/net/hsr/hsr_main.c
@@ -0,0 +1,469 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ *
+ * In addition to routines for registering and unregistering HSR support, this
+ * file also contains the receive routine that handles all incoming frames with
+ * Ethertype (protocol) ETH_P_PRP (HSRv0), and network device event handling.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/rculist.h>
+#include <linux/timer.h>
+#include <linux/etherdevice.h>
+#include "hsr_main.h"
+#include "hsr_device.h"
+#include "hsr_netlink.h"
+#include "hsr_framereg.h"
+
+
+/* List of all registered virtual HSR devices */
+static LIST_HEAD(hsr_list);
+
+void register_hsr_master(struct hsr_priv *hsr_priv)
+{
+	list_add_tail_rcu(&hsr_priv->hsr_list, &hsr_list);
+}
+
+void unregister_hsr_master(struct hsr_priv *hsr_priv)
+{
+	struct hsr_priv *hsr_priv_it;
+
+	list_for_each_entry(hsr_priv_it, &hsr_list, hsr_list)
+		if (hsr_priv_it == hsr_priv) {
+			list_del_rcu(&hsr_priv_it->hsr_list);
+			return;
+		}
+}
+
+bool is_hsr_slave(struct net_device *dev)
+{
+	struct hsr_priv *hsr_priv_it;
+
+	list_for_each_entry_rcu(hsr_priv_it, &hsr_list, hsr_list) {
+		if (dev == hsr_priv_it->slave[0])
+			return true;
+		if (dev == hsr_priv_it->slave[1])
+			return true;
+	}
+
+	return false;
+}
+
+
+/* If dev is a HSR slave device, return the virtual master device. Return NULL
+ * otherwise.
+ */
+static struct hsr_priv *get_hsr_master(struct net_device *dev)
+{
+	struct hsr_priv *hsr_priv;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hsr_priv, &hsr_list, hsr_list)
+		if ((dev == hsr_priv->slave[0]) ||
+		    (dev == hsr_priv->slave[1])) {
+			rcu_read_unlock();
+			return hsr_priv;
+		}
+
+	rcu_read_unlock();
+	return NULL;
+}
+
+
+/* If dev is a HSR slave device, return the other slave device. Return NULL
+ * otherwise.
+ */
+static struct net_device *get_other_slave(struct hsr_priv *hsr_priv,
+					  struct net_device *dev)
+{
+	if (dev == hsr_priv->slave[0])
+		return hsr_priv->slave[1];
+	if (dev == hsr_priv->slave[1])
+		return hsr_priv->slave[0];
+
+	return NULL;
+}
+
+
+static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *slave, *other_slave;
+	struct hsr_priv *hsr_priv;
+	int old_operstate;
+	int mtu_max;
+	int res;
+	struct net_device *dev;
+
+	dev = netdev_notifier_info_to_dev(ptr);
+
+	hsr_priv = get_hsr_master(dev);
+	if (hsr_priv) {
+		/* dev is a slave device */
+		slave = dev;
+		other_slave = get_other_slave(hsr_priv, slave);
+	} else {
+		if (!is_hsr_master(dev))
+			return NOTIFY_DONE;
+		hsr_priv = netdev_priv(dev);
+		slave = hsr_priv->slave[0];
+		other_slave = hsr_priv->slave[1];
+	}
+
+	switch (event) {
+	case NETDEV_UP:		/* Administrative state DOWN */
+	case NETDEV_DOWN:	/* Administrative state UP */
+	case NETDEV_CHANGE:	/* Link (carrier) state changes */
+		old_operstate = hsr_priv->dev->operstate;
+		hsr_set_carrier(hsr_priv->dev, slave, other_slave);
+		/* netif_stacked_transfer_operstate() cannot be used here since
+		 * it doesn't set IF_OPER_LOWERLAYERDOWN (?)
+		 */
+		hsr_set_operstate(hsr_priv->dev, slave, other_slave);
+		hsr_check_announce(hsr_priv->dev, old_operstate);
+		break;
+	case NETDEV_CHANGEADDR:
+
+		/* This should not happen since there's no ndo_set_mac_address()
+		 * for HSR devices - i.e. not supported.
+		 */
+		if (dev == hsr_priv->dev)
+			break;
+
+		if (dev == hsr_priv->slave[0])
+			memcpy(hsr_priv->dev->dev_addr,
+			       hsr_priv->slave[0]->dev_addr, ETH_ALEN);
+
+		/* Make sure we recognize frames from ourselves in hsr_rcv() */
+		res = hsr_create_self_node(&hsr_priv->self_node_db,
+					   hsr_priv->dev->dev_addr,
+					   hsr_priv->slave[1] ?
+						hsr_priv->slave[1]->dev_addr :
+						hsr_priv->dev->dev_addr);
+		if (res)
+			netdev_warn(hsr_priv->dev,
+				    "Could not update HSR node address.\n");
+
+		if (dev == hsr_priv->slave[0])
+			call_netdevice_notifiers(NETDEV_CHANGEADDR, hsr_priv->dev);
+		break;
+	case NETDEV_CHANGEMTU:
+		if (dev == hsr_priv->dev)
+			break; /* Handled in ndo_change_mtu() */
+		mtu_max = hsr_get_max_mtu(hsr_priv);
+		if (hsr_priv->dev->mtu > mtu_max)
+			dev_set_mtu(hsr_priv->dev, mtu_max);
+		break;
+	case NETDEV_UNREGISTER:
+		if (dev == hsr_priv->slave[0])
+			hsr_priv->slave[0] = NULL;
+		if (dev == hsr_priv->slave[1])
+			hsr_priv->slave[1] = NULL;
+
+		/* There should really be a way to set a new slave device... */
+
+		break;
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* HSR works only on Ethernet devices. Refuse slave to change
+		 * its type.
+		 */
+		return NOTIFY_BAD;
+	}
+
+	return NOTIFY_DONE;
+}
+
+
+static struct timer_list prune_timer;
+
+static void prune_nodes_all(unsigned long data)
+{
+	struct hsr_priv *hsr_priv;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hsr_priv, &hsr_list, hsr_list)
+		hsr_prune_nodes(hsr_priv);
+	rcu_read_unlock();
+
+	prune_timer.expires = jiffies + msecs_to_jiffies(PRUNE_PERIOD);
+	add_timer(&prune_timer);
+}
+
+
+static struct sk_buff *hsr_pull_tag(struct sk_buff *skb)
+{
+	struct hsr_tag *hsr_tag;
+	struct sk_buff *skb2;
+
+	skb2 = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb2))
+		goto err_free;
+	skb = skb2;
+
+	if (unlikely(!pskb_may_pull(skb, HSR_TAGLEN)))
+		goto err_free;
+
+	hsr_tag = (struct hsr_tag *) skb->data;
+	skb->protocol = hsr_tag->encap_proto;
+	skb_pull(skb, HSR_TAGLEN);
+
+	return skb;
+
+err_free:
+	kfree_skb(skb);
+	return NULL;
+}
+
+
+/* The uses I can see for these HSR supervision frames are:
+ * 1) Use the frames that are sent after node initialization ("HSR_TLV.Type =
+ *    22") to reset any sequence_nr counters belonging to that node. Useful if
+ *    the other node's counter has been reset for some reason.
+ *    --
+ *    Or not - resetting the counter and bridging the frame would create a
+ *    loop, unfortunately.
+ *
+ * 2) Use the LifeCheck frames to detect ring breaks. I.e. if no LifeCheck
+ *    frame is received from a particular node, we know something is wrong.
+ *    We just register these (as with normal frames) and throw them away.
+ *
+ * 3) Allow different MAC addresses for the two slave interfaces, using the
+ *    MacAddressA field.
+ */
+static bool is_supervision_frame(struct hsr_priv *hsr_priv, struct sk_buff *skb)
+{
+	struct hsr_sup_tag *hsr_stag;
+
+	if (!ether_addr_equal(eth_hdr(skb)->h_dest,
+			      hsr_priv->sup_multicast_addr))
+		return false;
+
+	hsr_stag = (struct hsr_sup_tag *) skb->data;
+	if (get_hsr_stag_path(hsr_stag) != 0x0f)
+		return false;
+	if ((hsr_stag->HSR_TLV_Type != HSR_TLV_ANNOUNCE) &&
+	    (hsr_stag->HSR_TLV_Type != HSR_TLV_LIFE_CHECK))
+		return false;
+	if (hsr_stag->HSR_TLV_Length != 12)
+		return false;
+
+	return true;
+}
+
+
+/* Implementation somewhat according to IEC-62439-3, p. 43
+ */
+static int hsr_rcv(struct sk_buff *skb, struct net_device *dev,
+		   struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct hsr_priv *hsr_priv;
+	struct net_device *other_slave;
+	struct node_entry *node;
+	bool deliver_to_self;
+	struct sk_buff *skb_deliver;
+	enum hsr_dev_idx dev_in_idx, dev_other_idx;
+	bool dup_out;
+	int ret;
+
+	hsr_priv = get_hsr_master(dev);
+
+	if (!hsr_priv) {
+		/* Non-HSR-slave device 'dev' is connected to a HSR network */
+		kfree_skb(skb);
+		dev->stats.rx_errors++;
+		return NET_RX_SUCCESS;
+	}
+
+	if (dev == hsr_priv->slave[0]) {
+		dev_in_idx = HSR_DEV_SLAVE_A;
+		dev_other_idx = HSR_DEV_SLAVE_B;
+	} else {
+		dev_in_idx = HSR_DEV_SLAVE_B;
+		dev_other_idx = HSR_DEV_SLAVE_A;
+	}
+
+	node = hsr_find_node(&hsr_priv->self_node_db, skb);
+	if (node) {
+		/* Always kill frames sent by ourselves */
+		kfree_skb(skb);
+		return NET_RX_SUCCESS;
+	}
+
+	/* Is this frame a candidate for local reception? */
+	deliver_to_self = false;
+	if ((skb->pkt_type == PACKET_HOST) ||
+	    (skb->pkt_type == PACKET_MULTICAST) ||
+	    (skb->pkt_type == PACKET_BROADCAST))
+		deliver_to_self = true;
+	else if (ether_addr_equal(eth_hdr(skb)->h_dest,
+				     hsr_priv->dev->dev_addr)) {
+		skb->pkt_type = PACKET_HOST;
+		deliver_to_self = true;
+	}
+
+
+	rcu_read_lock(); /* node_db */
+	node = hsr_find_node(&hsr_priv->node_db, skb);
+
+	if (is_supervision_frame(hsr_priv, skb)) {
+		skb_pull(skb, sizeof(struct hsr_sup_tag));
+		node = hsr_merge_node(hsr_priv, node, skb, dev_in_idx);
+		if (!node) {
+			rcu_read_unlock(); /* node_db */
+			kfree_skb(skb);
+			hsr_priv->dev->stats.rx_dropped++;
+			return NET_RX_DROP;
+		}
+		skb_push(skb, sizeof(struct hsr_sup_tag));
+		deliver_to_self = false;
+	}
+
+	if (!node) {
+		/* Source node unknown; this might be a HSR frame from
+		 * another net (different multicast address). Ignore it.
+		 */
+		rcu_read_unlock(); /* node_db */
+		kfree_skb(skb);
+		return NET_RX_SUCCESS;
+	}
+
+	/* Register ALL incoming frames as outgoing through the other interface.
+	 * This allows us to register frames as incoming only if they are valid
+	 * for the receiving interface, without using a specific counter for
+	 * incoming frames.
+	 */
+	dup_out = hsr_register_frame_out(node, dev_other_idx, skb);
+	if (!dup_out)
+		hsr_register_frame_in(node, dev_in_idx);
+
+	/* Forward this frame? */
+	if (!dup_out && (skb->pkt_type != PACKET_HOST))
+		other_slave = get_other_slave(hsr_priv, dev);
+	else
+		other_slave = NULL;
+
+	if (hsr_register_frame_out(node, HSR_DEV_MASTER, skb))
+		deliver_to_self = false;
+
+	rcu_read_unlock(); /* node_db */
+
+	if (!deliver_to_self && !other_slave) {
+		kfree_skb(skb);
+		/* Circulated frame; silently remove it. */
+		return NET_RX_SUCCESS;
+	}
+
+	skb_deliver = skb;
+	if (deliver_to_self && other_slave) {
+		/* skb_clone() is not enough since we will strip the hsr tag
+		 * and do address substitution below
+		 */
+		skb_deliver = pskb_copy(skb, GFP_ATOMIC);
+		if (!skb_deliver) {
+			deliver_to_self = false;
+			hsr_priv->dev->stats.rx_dropped++;
+		}
+	}
+
+	if (deliver_to_self) {
+		bool multicast_frame;
+
+		skb_deliver = hsr_pull_tag(skb_deliver);
+		if (!skb_deliver) {
+			hsr_priv->dev->stats.rx_dropped++;
+			goto forward;
+		}
+#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+		/* Move everything in the header that is after the HSR tag,
+		 * to work around alignment problems caused by the 6-byte HSR
+		 * tag. In practice, this removes/overwrites the HSR tag in
+		 * the header and restores a "standard" packet.
+		 */
+		memmove(skb_deliver->data - HSR_TAGLEN, skb_deliver->data,
+			skb_headlen(skb_deliver));
+
+		/* Adjust skb members so they correspond with the move above.
+		 * This cannot possibly underflow skb->data since hsr_pull_tag()
+		 * above succeeded.
+		 * At this point in the protocol stack, the transport and
+		 * network headers have not been set yet, and we haven't touched
+		 * the mac header nor the head. So we only need to adjust data
+		 * and tail:
+		 */
+		skb_deliver->data -= HSR_TAGLEN;
+		skb_deliver->tail -= HSR_TAGLEN;
+#endif
+		skb_deliver->dev = hsr_priv->dev;
+		hsr_addr_subst_source(hsr_priv, skb_deliver);
+		multicast_frame = (skb_deliver->pkt_type == PACKET_MULTICAST);
+		ret = netif_rx(skb_deliver);
+		if (ret == NET_RX_DROP) {
+			hsr_priv->dev->stats.rx_dropped++;
+		} else {
+			hsr_priv->dev->stats.rx_packets++;
+			hsr_priv->dev->stats.rx_bytes += skb->len;
+			if (multicast_frame)
+				hsr_priv->dev->stats.multicast++;
+		}
+	}
+
+forward:
+	if (other_slave) {
+		skb_push(skb, ETH_HLEN);
+		skb->dev = other_slave;
+		dev_queue_xmit(skb);
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+
+static struct packet_type hsr_pt __read_mostly = {
+	.type = htons(ETH_P_PRP),
+	.func = hsr_rcv,
+};
+
+static struct notifier_block hsr_nb = {
+	.notifier_call = hsr_netdev_notify,	/* Slave event notifications */
+};
+
+
+static int __init hsr_init(void)
+{
+	int res;
+
+	BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_TAGLEN);
+
+	dev_add_pack(&hsr_pt);
+
+	init_timer(&prune_timer);
+	prune_timer.function = prune_nodes_all;
+	prune_timer.data = 0;
+	prune_timer.expires = jiffies + msecs_to_jiffies(PRUNE_PERIOD);
+	add_timer(&prune_timer);
+
+	register_netdevice_notifier(&hsr_nb);
+
+	res = hsr_netlink_init();
+
+	return res;
+}
+
+static void __exit hsr_exit(void)
+{
+	unregister_netdevice_notifier(&hsr_nb);
+	del_timer(&prune_timer);
+	hsr_netlink_exit();
+	dev_remove_pack(&hsr_pt);
+}
+
+module_init(hsr_init);
+module_exit(hsr_exit);
+MODULE_LICENSE("GPL");
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
new file mode 100644
index 000000000000..56fe060c0ab1
--- /dev/null
+++ b/net/hsr/hsr_main.h
@@ -0,0 +1,166 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ */
+
+#ifndef _HSR_PRIVATE_H
+#define _HSR_PRIVATE_H
+
+#include <linux/netdevice.h>
+#include <linux/list.h>
+
+
+/* Time constants as specified in the HSR specification (IEC-62439-3 2010)
+ * Table 8.
+ * All values in milliseconds.
+ */
+#define HSR_LIFE_CHECK_INTERVAL		 2000 /* ms */
+#define HSR_NODE_FORGET_TIME		60000 /* ms */
+#define HSR_ANNOUNCE_INTERVAL		  100 /* ms */
+
+
+/* By how much may slave1 and slave2 timestamps of latest received frame from
+ * each node differ before we notify of communication problem?
+ */
+#define MAX_SLAVE_DIFF			 3000 /* ms */
+
+
+/* How often shall we check for broken ring and remove node entries older than
+ * HSR_NODE_FORGET_TIME?
+ */
+#define PRUNE_PERIOD			 3000 /* ms */
+
+
+#define HSR_TLV_ANNOUNCE		   22
+#define HSR_TLV_LIFE_CHECK		   23
+
+
+/* HSR Tag.
+ * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB,
+ * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest,
+ * h_source, h_proto = 0x88FB }, and add { path, LSDU_size, sequence Nr,
+ * encapsulated protocol } instead.
+ */
+#define HSR_TAGLEN	6
+
+/* Field names below as defined in the IEC:2010 standard for HSR. */
+struct hsr_tag {
+	__be16		path_and_LSDU_size;
+	__be16		sequence_nr;
+	__be16		encap_proto;
+} __packed;
+
+
+/* The helper functions below assumes that 'path' occupies the 4 most
+ * significant bits of the 16-bit field shared by 'path' and 'LSDU_size' (or
+ * equivalently, the 4 most significant bits of HSR tag byte 14).
+ *
+ * This is unclear in the IEC specification; its definition of MAC addresses
+ * indicates the spec is written with the least significant bit first (to the
+ * left). This, however, would mean that the LSDU field would be split in two
+ * with the path field in-between, which seems strange. I'm guessing the MAC
+ * address definition is in error.
+ */
+static inline u16 get_hsr_tag_path(struct hsr_tag *ht)
+{
+	return ntohs(ht->path_and_LSDU_size) >> 12;
+}
+
+static inline u16 get_hsr_tag_LSDU_size(struct hsr_tag *ht)
+{
+	return ntohs(ht->path_and_LSDU_size) & 0x0FFF;
+}
+
+static inline void set_hsr_tag_path(struct hsr_tag *ht, u16 path)
+{
+	ht->path_and_LSDU_size = htons(
+			(ntohs(ht->path_and_LSDU_size) & 0x0FFF) | (path << 12));
+}
+
+static inline void set_hsr_tag_LSDU_size(struct hsr_tag *ht, u16 LSDU_size)
+{
+	ht->path_and_LSDU_size = htons(
+			(ntohs(ht->path_and_LSDU_size) & 0xF000) |
+			(LSDU_size & 0x0FFF));
+}
+
+struct hsr_ethhdr {
+	struct ethhdr	ethhdr;
+	struct hsr_tag	hsr_tag;
+} __packed;
+
+
+/* HSR Supervision Frame data types.
+ * Field names as defined in the IEC:2010 standard for HSR.
+ */
+struct hsr_sup_tag {
+	__be16		path_and_HSR_Ver;
+	__be16		sequence_nr;
+	__u8		HSR_TLV_Type;
+	__u8		HSR_TLV_Length;
+} __packed;
+
+struct hsr_sup_payload {
+	unsigned char	MacAddressA[ETH_ALEN];
+} __packed;
+
+static inline u16 get_hsr_stag_path(struct hsr_sup_tag *hst)
+{
+	return get_hsr_tag_path((struct hsr_tag *) hst);
+}
+
+static inline u16 get_hsr_stag_HSR_ver(struct hsr_sup_tag *hst)
+{
+	return get_hsr_tag_LSDU_size((struct hsr_tag *) hst);
+}
+
+static inline void set_hsr_stag_path(struct hsr_sup_tag *hst, u16 path)
+{
+	set_hsr_tag_path((struct hsr_tag *) hst, path);
+}
+
+static inline void set_hsr_stag_HSR_Ver(struct hsr_sup_tag *hst, u16 HSR_Ver)
+{
+	set_hsr_tag_LSDU_size((struct hsr_tag *) hst, HSR_Ver);
+}
+
+struct hsr_ethhdr_sp {
+	struct ethhdr		ethhdr;
+	struct hsr_sup_tag	hsr_sup;
+} __packed;
+
+
+enum hsr_dev_idx {
+	HSR_DEV_NONE = -1,
+	HSR_DEV_SLAVE_A = 0,
+	HSR_DEV_SLAVE_B,
+	HSR_DEV_MASTER,
+};
+#define HSR_MAX_SLAVE	(HSR_DEV_SLAVE_B + 1)
+#define HSR_MAX_DEV	(HSR_DEV_MASTER + 1)
+
+struct hsr_priv {
+	struct list_head	hsr_list;	/* List of hsr devices */
+	struct rcu_head		rcu_head;
+	struct net_device	*dev;
+	struct net_device	*slave[HSR_MAX_SLAVE];
+	struct list_head	node_db;	/* Other HSR nodes */
+	struct list_head	self_node_db;	/* MACs of slaves */
+	struct timer_list	announce_timer;	/* Supervision frame dispatch */
+	int announce_count;
+	u16 sequence_nr;
+	spinlock_t seqnr_lock;			/* locking for sequence_nr */
+	unsigned char		sup_multicast_addr[ETH_ALEN];
+};
+
+void register_hsr_master(struct hsr_priv *hsr_priv);
+void unregister_hsr_master(struct hsr_priv *hsr_priv);
+bool is_hsr_slave(struct net_device *dev);
+
+#endif /*  _HSR_PRIVATE_H */
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
new file mode 100644
index 000000000000..4e66bf61f585
--- /dev/null
+++ b/net/hsr/hsr_netlink.c
@@ -0,0 +1,457 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ *
+ * Routines for handling Netlink messages for HSR.
+ */
+
+#include "hsr_netlink.h"
+#include <linux/kernel.h>
+#include <net/rtnetlink.h>
+#include <net/genetlink.h>
+#include "hsr_main.h"
+#include "hsr_device.h"
+#include "hsr_framereg.h"
+
+static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = {
+	[IFLA_HSR_SLAVE1]		= { .type = NLA_U32 },
+	[IFLA_HSR_SLAVE2]		= { .type = NLA_U32 },
+	[IFLA_HSR_MULTICAST_SPEC]	= { .type = NLA_U8 },
+};
+
+
+/* Here, it seems a netdevice has already been allocated for us, and the
+ * hsr_dev_setup routine has been executed. Nice!
+ */
+static int hsr_newlink(struct net *src_net, struct net_device *dev,
+		       struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_device *link[2];
+	unsigned char multicast_spec;
+
+	if (!data[IFLA_HSR_SLAVE1]) {
+		netdev_info(dev, "IFLA_HSR_SLAVE1 missing!\n");
+		return -EINVAL;
+	}
+	link[0] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE1]));
+	if (!data[IFLA_HSR_SLAVE2]) {
+		netdev_info(dev, "IFLA_HSR_SLAVE2 missing!\n");
+		return -EINVAL;
+	}
+	link[1] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE2]));
+
+	if (!link[0] || !link[1])
+		return -ENODEV;
+	if (link[0] == link[1])
+		return -EINVAL;
+
+	if (!data[IFLA_HSR_MULTICAST_SPEC])
+		multicast_spec = 0;
+	else
+		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
+
+	return hsr_dev_finalize(dev, link, multicast_spec);
+}
+
+static struct rtnl_link_ops hsr_link_ops __read_mostly = {
+	.kind		= "hsr",
+	.maxtype	= IFLA_HSR_MAX,
+	.policy		= hsr_policy,
+	.priv_size	= sizeof(struct hsr_priv),
+	.setup		= hsr_dev_setup,
+	.newlink	= hsr_newlink,
+};
+
+
+
+/* attribute policy */
+/* NLA_BINARY missing in libnl; use NLA_UNSPEC in userspace instead. */
+static const struct nla_policy hsr_genl_policy[HSR_A_MAX + 1] = {
+	[HSR_A_NODE_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN },
+	[HSR_A_NODE_ADDR_B] = { .type = NLA_BINARY, .len = ETH_ALEN },
+	[HSR_A_IFINDEX] = { .type = NLA_U32 },
+	[HSR_A_IF1_AGE] = { .type = NLA_U32 },
+	[HSR_A_IF2_AGE] = { .type = NLA_U32 },
+	[HSR_A_IF1_SEQ] = { .type = NLA_U16 },
+	[HSR_A_IF2_SEQ] = { .type = NLA_U16 },
+};
+
+static struct genl_family hsr_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = 0,
+	.name = "HSR",
+	.version = 1,
+	.maxattr = HSR_A_MAX,
+};
+
+static struct genl_multicast_group hsr_network_genl_mcgrp = {
+	.name = "hsr-network",
+};
+
+
+
+/* This is called if for some node with MAC address addr, we only get frames
+ * over one of the slave interfaces. This would indicate an open network ring
+ * (i.e. a link has failed somewhere).
+ */
+void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN],
+		      enum hsr_dev_idx dev_idx)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int res;
+	int ifindex;
+
+	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		goto fail;
+
+	msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_RING_ERROR);
+	if (!msg_head)
+		goto nla_put_failure;
+
+	res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+	if (res < 0)
+		goto nla_put_failure;
+
+	if (hsr_priv->slave[dev_idx])
+		ifindex = hsr_priv->slave[dev_idx]->ifindex;
+	else
+		ifindex = -1;
+	res = nla_put_u32(skb, HSR_A_IFINDEX, ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(skb, 0, hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+
+	return;
+
+nla_put_failure:
+	kfree_skb(skb);
+
+fail:
+	netdev_warn(hsr_priv->dev, "Could not send HSR ring error message\n");
+}
+
+/* This is called when we haven't heard from the node with MAC address addr for
+ * some time (just before the node is removed from the node table/list).
+ */
+void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN])
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int res;
+
+	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		goto fail;
+
+	msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_NODE_DOWN);
+	if (!msg_head)
+		goto nla_put_failure;
+
+
+	res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+	if (res < 0)
+		goto nla_put_failure;
+
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(skb, 0, hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+
+	return;
+
+nla_put_failure:
+	kfree_skb(skb);
+
+fail:
+	netdev_warn(hsr_priv->dev, "Could not send HSR node down\n");
+}
+
+
+/* HSR_C_GET_NODE_STATUS lets userspace query the internal HSR node table
+ * about the status of a specific node in the network, defined by its MAC
+ * address.
+ *
+ * Input: hsr ifindex, node mac address
+ * Output: hsr ifindex, node mac address (copied from request),
+ *	   age of latest frame from node over slave 1, slave 2 [ms]
+ */
+static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
+{
+	/* For receiving */
+	struct nlattr *na;
+	struct net_device *hsr_dev;
+
+	/* For sending */
+	struct sk_buff *skb_out;
+	void *msg_head;
+	struct hsr_priv *hsr_priv;
+	unsigned char hsr_node_addr_b[ETH_ALEN];
+	int hsr_node_if1_age;
+	u16 hsr_node_if1_seq;
+	int hsr_node_if2_age;
+	u16 hsr_node_if2_seq;
+	int addr_b_ifindex;
+	int res;
+
+	if (!info)
+		goto invalid;
+
+	na = info->attrs[HSR_A_IFINDEX];
+	if (!na)
+		goto invalid;
+	na = info->attrs[HSR_A_NODE_ADDR];
+	if (!na)
+		goto invalid;
+
+	hsr_dev = __dev_get_by_index(genl_info_net(info),
+					nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	if (!hsr_dev)
+		goto invalid;
+	if (!is_hsr_master(hsr_dev))
+		goto invalid;
+
+
+	/* Send reply */
+
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb_out) {
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
+				info->snd_seq, &hsr_genl_family, 0,
+				HSR_C_SET_NODE_STATUS);
+	if (!msg_head) {
+		res = -ENOMEM;
+		goto nla_put_failure;
+	}
+
+	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	hsr_priv = netdev_priv(hsr_dev);
+	res = hsr_get_node_data(hsr_priv,
+			(unsigned char *) nla_data(info->attrs[HSR_A_NODE_ADDR]),
+			hsr_node_addr_b,
+			&addr_b_ifindex,
+			&hsr_node_if1_age,
+			&hsr_node_if1_seq,
+			&hsr_node_if2_age,
+			&hsr_node_if2_seq);
+	if (res < 0)
+		goto fail;
+
+	res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN,
+					nla_data(info->attrs[HSR_A_NODE_ADDR]));
+	if (res < 0)
+		goto nla_put_failure;
+
+	if (addr_b_ifindex > -1) {
+		res = nla_put(skb_out, HSR_A_NODE_ADDR_B, ETH_ALEN,
+								hsr_node_addr_b);
+		if (res < 0)
+			goto nla_put_failure;
+
+		res = nla_put_u32(skb_out, HSR_A_ADDR_B_IFINDEX, addr_b_ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
+
+	res = nla_put_u32(skb_out, HSR_A_IF1_AGE, hsr_node_if1_age);
+	if (res < 0)
+		goto nla_put_failure;
+	res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq);
+	if (res < 0)
+		goto nla_put_failure;
+	if (hsr_priv->slave[0])
+		res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX,
+						hsr_priv->slave[0]->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	res = nla_put_u32(skb_out, HSR_A_IF2_AGE, hsr_node_if2_age);
+	if (res < 0)
+		goto nla_put_failure;
+	res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq);
+	if (res < 0)
+		goto nla_put_failure;
+	if (hsr_priv->slave[1])
+		res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX,
+						hsr_priv->slave[1]->ifindex);
+
+	genlmsg_end(skb_out, msg_head);
+	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
+
+	return 0;
+
+invalid:
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL);
+	return 0;
+
+nla_put_failure:
+	kfree_skb(skb_out);
+	/* Fall through */
+
+fail:
+	return res;
+}
+
+static struct genl_ops hsr_ops_get_node_status = {
+	.cmd = HSR_C_GET_NODE_STATUS,
+	.flags = 0,
+	.policy = hsr_genl_policy,
+	.doit = hsr_get_node_status,
+	.dumpit = NULL,
+};
+
+
+/* Get a list of MacAddressA of all nodes known to this node (other than self).
+ */
+static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
+{
+	/* For receiving */
+	struct nlattr *na;
+	struct net_device *hsr_dev;
+
+	/* For sending */
+	struct sk_buff *skb_out;
+	void *msg_head;
+	struct hsr_priv *hsr_priv;
+	void *pos;
+	unsigned char addr[ETH_ALEN];
+	int res;
+
+	if (!info)
+		goto invalid;
+
+	na = info->attrs[HSR_A_IFINDEX];
+	if (!na)
+		goto invalid;
+
+	hsr_dev = __dev_get_by_index(genl_info_net(info),
+				     nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	if (!hsr_dev)
+		goto invalid;
+	if (!is_hsr_master(hsr_dev))
+		goto invalid;
+
+
+	/* Send reply */
+
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb_out) {
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
+				info->snd_seq, &hsr_genl_family, 0,
+				HSR_C_SET_NODE_LIST);
+	if (!msg_head) {
+		res = -ENOMEM;
+		goto nla_put_failure;
+	}
+
+	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	hsr_priv = netdev_priv(hsr_dev);
+
+	rcu_read_lock();
+	pos = hsr_get_next_node(hsr_priv, NULL, addr);
+	while (pos) {
+		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+		if (res < 0) {
+			rcu_read_unlock();
+			goto nla_put_failure;
+		}
+		pos = hsr_get_next_node(hsr_priv, pos, addr);
+	}
+	rcu_read_unlock();
+
+	genlmsg_end(skb_out, msg_head);
+	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
+
+	return 0;
+
+invalid:
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL);
+	return 0;
+
+nla_put_failure:
+	kfree_skb(skb_out);
+	/* Fall through */
+
+fail:
+	return res;
+}
+
+
+static struct genl_ops hsr_ops_get_node_list = {
+	.cmd = HSR_C_GET_NODE_LIST,
+	.flags = 0,
+	.policy = hsr_genl_policy,
+	.doit = hsr_get_node_list,
+	.dumpit = NULL,
+};
+
+int __init hsr_netlink_init(void)
+{
+	int rc;
+
+	rc = rtnl_link_register(&hsr_link_ops);
+	if (rc)
+		goto fail_rtnl_link_register;
+
+	rc = genl_register_family(&hsr_genl_family);
+	if (rc)
+		goto fail_genl_register_family;
+
+	rc = genl_register_ops(&hsr_genl_family, &hsr_ops_get_node_status);
+	if (rc)
+		goto fail_genl_register_ops;
+
+	rc = genl_register_ops(&hsr_genl_family, &hsr_ops_get_node_list);
+	if (rc)
+		goto fail_genl_register_ops_node_list;
+
+	rc = genl_register_mc_group(&hsr_genl_family, &hsr_network_genl_mcgrp);
+	if (rc)
+		goto fail_genl_register_mc_group;
+
+	return 0;
+
+fail_genl_register_mc_group:
+	genl_unregister_ops(&hsr_genl_family, &hsr_ops_get_node_list);
+fail_genl_register_ops_node_list:
+	genl_unregister_ops(&hsr_genl_family, &hsr_ops_get_node_status);
+fail_genl_register_ops:
+	genl_unregister_family(&hsr_genl_family);
+fail_genl_register_family:
+	rtnl_link_unregister(&hsr_link_ops);
+fail_rtnl_link_register:
+
+	return rc;
+}
+
+void __exit hsr_netlink_exit(void)
+{
+	genl_unregister_mc_group(&hsr_genl_family, &hsr_network_genl_mcgrp);
+	genl_unregister_ops(&hsr_genl_family, &hsr_ops_get_node_status);
+	genl_unregister_family(&hsr_genl_family);
+
+	rtnl_link_unregister(&hsr_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("hsr");
diff --git a/net/hsr/hsr_netlink.h b/net/hsr/hsr_netlink.h
new file mode 100644
index 000000000000..d4579dcc3c7d
--- /dev/null
+++ b/net/hsr/hsr_netlink.h
@@ -0,0 +1,30 @@
+/* Copyright 2011-2013 Autronica Fire and Security AS
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * Author(s):
+ *	2011-2013 Arvid Brodin, arvid.brodin@xdin.com
+ */
+
+#ifndef __HSR_NETLINK_H
+#define __HSR_NETLINK_H
+
+#include <linux/if_ether.h>
+#include <linux/module.h>
+#include <uapi/linux/hsr_netlink.h>
+
+struct hsr_priv;
+
+int __init hsr_netlink_init(void);
+void __exit hsr_netlink_exit(void);
+
+void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN],
+		      int dev_idx);
+void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN]);
+void hsr_nl_framedrop(int dropcount, int dev_idx);
+void hsr_nl_linkdown(int dev_idx);
+
+#endif /* __HSR_NETLINK_H */
-- 
cgit 


From 9ed9c07d9b7d42fc7042247c2be283731186464f Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Tue, 8 Oct 2013 09:57:20 +0200
Subject: clk: new driver for efm32 SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for the clocks provided by the Clock Management
Unit of Energy Micro's efm32 Giant Gecko SoCs including device tree
bindings.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 .../devicetree/bindings/clock/efm32-clock.txt      | 11 +++
 drivers/clk/Makefile                               |  1 +
 drivers/clk/clk-efm32gg.c                          | 81 ++++++++++++++++++++++
 include/dt-bindings/clock/efm32-cmu.h              | 42 +++++++++++
 4 files changed, 135 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/efm32-clock.txt
 create mode 100644 drivers/clk/clk-efm32gg.c
 create mode 100644 include/dt-bindings/clock/efm32-cmu.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/efm32-clock.txt b/Documentation/devicetree/bindings/clock/efm32-clock.txt
new file mode 100644
index 000000000000..263d293f6a10
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/efm32-clock.txt
@@ -0,0 +1,11 @@
+* Clock bindings for Energy Micro efm32 Giant Gecko's Clock Management Unit
+
+Required properties:
+- compatible: Should be "efm32gg,cmu"
+- reg: Base address and length of the register set
+- interrupts: Interrupt used by the CMU
+- #clock-cells: Should be <1>
+
+The clock consumer should specify the desired clock by having the clock ID in
+its "clocks" phandle cell. The header efm32-clk.h contains a list of available
+IDs.
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index df33820b45ec..7a10bc9a23e7 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-composite.o
 
 # SoCs specific
 obj-$(CONFIG_ARCH_BCM2835)	+= clk-bcm2835.o
+obj-$(CONFIG_ARCH_EFM32)	+= clk-efm32gg.o
 obj-$(CONFIG_ARCH_NOMADIK)	+= clk-nomadik.o
 obj-$(CONFIG_ARCH_HIGHBANK)	+= clk-highbank.o
 obj-$(CONFIG_ARCH_NSPIRE)	+= clk-nspire.o
diff --git a/drivers/clk/clk-efm32gg.c b/drivers/clk/clk-efm32gg.c
new file mode 100644
index 000000000000..bac2ddf49d02
--- /dev/null
+++ b/drivers/clk/clk-efm32gg.c
@@ -0,0 +1,81 @@
+/*
+ * Copyright (C) 2013 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <dt-bindings/clock/efm32-cmu.h>
+
+#define CMU_HFPERCLKEN0		0x44
+
+static struct clk *clk[37];
+static struct clk_onecell_data clk_data = {
+	.clks = clk,
+	.clk_num = ARRAY_SIZE(clk),
+};
+
+static int __init efm32gg_cmu_init(struct device_node *np)
+{
+	int i;
+	void __iomem *base;
+
+	for (i = 0; i < ARRAY_SIZE(clk); ++i)
+		clk[i] = ERR_PTR(-ENOENT);
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_warn("Failed to map address range for efm32gg,cmu node\n");
+		return -EADDRNOTAVAIL;
+	}
+
+	clk[clk_HFXO] = clk_register_fixed_rate(NULL, "HFXO", NULL,
+			CLK_IS_ROOT, 48000000);
+
+	clk[clk_HFPERCLKUSART0] = clk_register_gate(NULL, "HFPERCLK.USART0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 0, 0, NULL);
+	clk[clk_HFPERCLKUSART1] = clk_register_gate(NULL, "HFPERCLK.USART1",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 1, 0, NULL);
+	clk[clk_HFPERCLKUSART2] = clk_register_gate(NULL, "HFPERCLK.USART2",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 2, 0, NULL);
+	clk[clk_HFPERCLKUART0] = clk_register_gate(NULL, "HFPERCLK.UART0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 3, 0, NULL);
+	clk[clk_HFPERCLKUART1] = clk_register_gate(NULL, "HFPERCLK.UART1",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 4, 0, NULL);
+	clk[clk_HFPERCLKTIMER0] = clk_register_gate(NULL, "HFPERCLK.TIMER0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 5, 0, NULL);
+	clk[clk_HFPERCLKTIMER1] = clk_register_gate(NULL, "HFPERCLK.TIMER1",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 6, 0, NULL);
+	clk[clk_HFPERCLKTIMER2] = clk_register_gate(NULL, "HFPERCLK.TIMER2",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 7, 0, NULL);
+	clk[clk_HFPERCLKTIMER3] = clk_register_gate(NULL, "HFPERCLK.TIMER3",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 8, 0, NULL);
+	clk[clk_HFPERCLKACMP0] = clk_register_gate(NULL, "HFPERCLK.ACMP0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 9, 0, NULL);
+	clk[clk_HFPERCLKACMP1] = clk_register_gate(NULL, "HFPERCLK.ACMP1",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 10, 0, NULL);
+	clk[clk_HFPERCLKI2C0] = clk_register_gate(NULL, "HFPERCLK.I2C0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 11, 0, NULL);
+	clk[clk_HFPERCLKI2C1] = clk_register_gate(NULL, "HFPERCLK.I2C1",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 12, 0, NULL);
+	clk[clk_HFPERCLKGPIO] = clk_register_gate(NULL, "HFPERCLK.GPIO",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 13, 0, NULL);
+	clk[clk_HFPERCLKVCMP] = clk_register_gate(NULL, "HFPERCLK.VCMP",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 14, 0, NULL);
+	clk[clk_HFPERCLKPRS] = clk_register_gate(NULL, "HFPERCLK.PRS",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 15, 0, NULL);
+	clk[clk_HFPERCLKADC0] = clk_register_gate(NULL, "HFPERCLK.ADC0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 16, 0, NULL);
+	clk[clk_HFPERCLKDAC0] = clk_register_gate(NULL, "HFPERCLK.DAC0",
+			"HFXO", 0, base + CMU_HFPERCLKEN0, 17, 0, NULL);
+
+	return of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+}
+CLK_OF_DECLARE(efm32ggcmu, "efm32gg,cmu", efm32gg_cmu_init);
diff --git a/include/dt-bindings/clock/efm32-cmu.h b/include/dt-bindings/clock/efm32-cmu.h
new file mode 100644
index 000000000000..b21b91e736af
--- /dev/null
+++ b/include/dt-bindings/clock/efm32-cmu.h
@@ -0,0 +1,42 @@
+#ifndef __DT_BINDINGS_CLOCK_EFM32_CMU_H
+#define __DT_BINDINGS_CLOCK_EFM32_CMU_H
+
+#define clk_HFXO		0
+#define clk_HFRCO		1
+#define clk_LFXO		2
+#define clk_LFRCO		3
+#define clk_ULFRCO		4
+#define clk_AUXHFRCO		5
+#define clk_HFCLKNODIV		6
+#define clk_HFCLK		7
+#define clk_HFPERCLK		8
+#define clk_HFCORECLK		9
+#define clk_LFACLK		10
+#define clk_LFBCLK		11
+#define clk_WDOGCLK		12
+#define clk_HFCORECLKDMA	13
+#define clk_HFCORECLKAES	14
+#define clk_HFCORECLKUSBC	15
+#define clk_HFCORECLKUSB	16
+#define clk_HFCORECLKLE		17
+#define clk_HFCORECLKEBI	18
+#define clk_HFPERCLKUSART0	19
+#define clk_HFPERCLKUSART1	20
+#define clk_HFPERCLKUSART2	21
+#define clk_HFPERCLKUART0	22
+#define clk_HFPERCLKUART1	23
+#define clk_HFPERCLKTIMER0	24
+#define clk_HFPERCLKTIMER1	25
+#define clk_HFPERCLKTIMER2	26
+#define clk_HFPERCLKTIMER3	27
+#define clk_HFPERCLKACMP0	28
+#define clk_HFPERCLKACMP1	29
+#define clk_HFPERCLKI2C0	30
+#define clk_HFPERCLKI2C1	31
+#define clk_HFPERCLKGPIO	32
+#define clk_HFPERCLKVCMP	33
+#define clk_HFPERCLKPRS		34
+#define clk_HFPERCLKADC0	35
+#define clk_HFPERCLKDAC0	36
+
+#endif /* __DT_BINDINGS_CLOCK_EFM32_CMU_H */
-- 
cgit 


From cea80ea8d2a4c646f240a8fd6ece5c8e7bc969d3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 4 Nov 2013 17:10:25 +0100
Subject: net: checksum: fix warning in skb_checksum

This patch fixes a build warning in skb_checksum() by wrapping the
csum_partial() usage in skb_checksum(). The problem is that on a few
architectures, csum_partial is used with prefix asmlinkage whereas
on most architectures it's not. So fix this up generically as we did
with csum_block_add_ext() to match the signature. Introduced by
2817a336d4d ("net: skb_checksum: allow custom update/combine for
walking skb").

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/checksum.h | 5 +++++
 net/core/skbuff.c      | 2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 15f33fde826e..37a0e24adbe7 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -98,6 +98,11 @@ static inline __wsum csum_unfold(__sum16 n)
 	return (__force __wsum)n;
 }
 
+static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
+{
+	return csum_partial(buff, len, sum);
+}
+
 #define CSUM_MANGLED_0 ((__force __sum16)0xffff)
 
 static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 31aab5376cb4..e4115597b38b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2003,7 +2003,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
 		    int len, __wsum csum)
 {
 	const struct skb_checksum_ops ops = {
-		.update  = csum_partial,
+		.update  = csum_partial_ext,
 		.combine = csum_block_add_ext,
 	};
 
-- 
cgit 


From f3f5a0f8cc40b942f4c0ae117df82eeb65f07d4d Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Mon, 4 Nov 2013 14:38:05 -0500
Subject: NFSv4.2: Fix a mismatch between Linux labeled NFS and the NFSv4.2
 spec

In the spec, the security label attribute id is '80', which means that
it should be bit number 80-64 == 16 in the 3rd word of the bitmap.

Fixes: 4488cc96c581: NFS: Add NFSv4.2 protocol constants
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Steve Dickson <steved@redhat.com>
Cc: stable@vger.kernel.org # 3.11+
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 include/linux/nfs4.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index c56fa8fedce9..bfe6c379a24e 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -395,7 +395,7 @@ enum lock_type4 {
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
-#define FATTR4_WORD2_SECURITY_LABEL     (1UL << 17)
+#define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
-- 
cgit 


From acddd5dd44d4fd9b45dd5ee69cd8b183052b1cdc Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Sun, 3 Nov 2013 10:03:18 +0200
Subject: net/mlx4_core: Fix reg/unreg vlan/mac to conform to the firmware spec

The functions mlx4_register_vlan, mlx4_unregister_vlan, mlx4_register_mac,
mlx4_unregister_mac all made illegal use of the out_param in multifunc mode
to pass the port number. The firmware spec specifies that the port number
should be passed in bits 8..15 of the input-modifier field for ALLOC_RES and
FREE_RES (sections 20.15.1 and 20.15.2).

For MAC register/unregister, this patch contains workarounds so that guests
running previous kernels continue to work on a new Hypervisor, and guests
running the new kernel will continue to work on old hypervisors.

Vlan registeration capability is still not operational in multifunction mode,
since the vlan wrapper functions are not implemented in this patch.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/port.c          | 45 +++++++++++++++-------
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 28 ++++++++------
 include/linux/mlx4/device.h                        |  1 +
 3 files changed, 49 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index d3d3106f588f..9433c1f6b0d4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -178,13 +178,24 @@ EXPORT_SYMBOL_GPL(__mlx4_register_mac);
 int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
 	u64 out_param = 0;
-	int err;
+	int err = -EINVAL;
 
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&out_param, port);
-		err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
-				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
-				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (!(dev->flags & MLX4_FLAG_OLD_REG_MAC)) {
+			err = mlx4_cmd_imm(dev, mac, &out_param,
+					   ((u32) port) << 8 | (u32) RES_MAC,
+					   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+					   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		}
+		if (err && err == -EINVAL && mlx4_is_slave(dev)) {
+			/* retry using old REG_MAC format */
+			set_param_l(&out_param, port);
+			err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+					   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+					   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+			if (!err)
+				dev->flags |= MLX4_FLAG_OLD_REG_MAC;
+		}
 		if (err)
 			return err;
 
@@ -231,10 +242,18 @@ void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	u64 out_param = 0;
 
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&out_param, port);
-		(void) mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
-				    RES_OP_RESERVE_AND_MAP, MLX4_CMD_FREE_RES,
-				    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (!(dev->flags & MLX4_FLAG_OLD_REG_MAC)) {
+			(void) mlx4_cmd_imm(dev, mac, &out_param,
+					    ((u32) port) << 8 | (u32) RES_MAC,
+					    RES_OP_RESERVE_AND_MAP, MLX4_CMD_FREE_RES,
+					    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		} else {
+			/* use old unregister mac format */
+			set_param_l(&out_param, port);
+			(void) mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+					    RES_OP_RESERVE_AND_MAP, MLX4_CMD_FREE_RES,
+					    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		}
 		return;
 	}
 	__mlx4_unregister_mac(dev, port, mac);
@@ -374,8 +393,8 @@ int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
 		return -EINVAL;
 
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&out_param, port);
-		err = mlx4_cmd_imm(dev, vlan, &out_param, RES_VLAN,
+		err = mlx4_cmd_imm(dev, vlan, &out_param,
+				   ((u32) port) << 8 | (u32) RES_VLAN,
 				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
 				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (!err)
@@ -418,8 +437,8 @@ void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
 	u64 out_param = 0;
 
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&out_param, port);
-		(void) mlx4_cmd_imm(dev, index, &out_param, RES_VLAN,
+		(void) mlx4_cmd_imm(dev, index, &out_param,
+				    ((u32) port) << 8 | (u32) RES_VLAN,
 				    RES_OP_RESERVE_AND_MAP,
 				    MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
 				    MLX4_CMD_WRAPPED);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index dd6876321116..a5aa3be554fe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1443,7 +1443,7 @@ static void rem_slave_macs(struct mlx4_dev *dev, int slave)
 }
 
 static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
-			 u64 in_param, u64 *out_param)
+			 u64 in_param, u64 *out_param, int in_port)
 {
 	int err = -EINVAL;
 	int port;
@@ -1452,7 +1452,7 @@ static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	if (op != RES_OP_RESERVE_AND_MAP)
 		return err;
 
-	port = get_param_l(out_param);
+	port = !in_port ? get_param_l(out_param) : in_port;
 	mac = in_param;
 
 	err = __mlx4_register_mac(dev, port, mac);
@@ -1470,7 +1470,7 @@ static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 }
 
 static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
-			 u64 in_param, u64 *out_param)
+			 u64 in_param, u64 *out_param, int port)
 {
 	return 0;
 }
@@ -1528,7 +1528,7 @@ int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	int alop = vhcr->op_modifier;
 
-	switch (vhcr->in_modifier) {
+	switch (vhcr->in_modifier & 0xFF) {
 	case RES_QP:
 		err = qp_alloc_res(dev, slave, vhcr->op_modifier, alop,
 				   vhcr->in_param, &vhcr->out_param);
@@ -1556,12 +1556,14 @@ int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
 
 	case RES_MAC:
 		err = mac_alloc_res(dev, slave, vhcr->op_modifier, alop,
-				    vhcr->in_param, &vhcr->out_param);
+				    vhcr->in_param, &vhcr->out_param,
+				    (vhcr->in_modifier >> 8) & 0xFF);
 		break;
 
 	case RES_VLAN:
 		err = vlan_alloc_res(dev, slave, vhcr->op_modifier, alop,
-				    vhcr->in_param, &vhcr->out_param);
+				     vhcr->in_param, &vhcr->out_param,
+				     (vhcr->in_modifier >> 8) & 0xFF);
 		break;
 
 	case RES_COUNTER:
@@ -1730,14 +1732,14 @@ static int srq_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 }
 
 static int mac_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
-			    u64 in_param, u64 *out_param)
+			    u64 in_param, u64 *out_param, int in_port)
 {
 	int port;
 	int err = 0;
 
 	switch (op) {
 	case RES_OP_RESERVE_AND_MAP:
-		port = get_param_l(out_param);
+		port = !in_port ? get_param_l(out_param) : in_port;
 		mac_del_from_slave(dev, slave, in_param, port);
 		__mlx4_unregister_mac(dev, port, in_param);
 		break;
@@ -1751,7 +1753,7 @@ static int mac_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 }
 
 static int vlan_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
-			    u64 in_param, u64 *out_param)
+			    u64 in_param, u64 *out_param, int port)
 {
 	return 0;
 }
@@ -1803,7 +1805,7 @@ int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
 	int err = -EINVAL;
 	int alop = vhcr->op_modifier;
 
-	switch (vhcr->in_modifier) {
+	switch (vhcr->in_modifier & 0xFF) {
 	case RES_QP:
 		err = qp_free_res(dev, slave, vhcr->op_modifier, alop,
 				  vhcr->in_param);
@@ -1831,12 +1833,14 @@ int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
 
 	case RES_MAC:
 		err = mac_free_res(dev, slave, vhcr->op_modifier, alop,
-				   vhcr->in_param, &vhcr->out_param);
+				   vhcr->in_param, &vhcr->out_param,
+				   (vhcr->in_modifier >> 8) & 0xFF);
 		break;
 
 	case RES_VLAN:
 		err = vlan_free_res(dev, slave, vhcr->op_modifier, alop,
-				   vhcr->in_param, &vhcr->out_param);
+				    vhcr->in_param, &vhcr->out_param,
+				    (vhcr->in_modifier >> 8) & 0xFF);
 		break;
 
 	case RES_COUNTER:
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 9ad0c18495ad..297a16309f00 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -54,6 +54,7 @@ enum {
 	MLX4_FLAG_MASTER	= 1 << 2,
 	MLX4_FLAG_SLAVE		= 1 << 3,
 	MLX4_FLAG_SRIOV		= 1 << 4,
+	MLX4_FLAG_OLD_REG_MAC	= 1 << 6,
 };
 
 enum {
-- 
cgit 


From 2009d0059c084288f060b1ffe3d14229588acb67 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Sun, 3 Nov 2013 10:03:19 +0200
Subject: net/mlx4_en: Use vlan id instead of vlan index for unregistration

Use of vlan_index created problems unregistering vlans on guests.

In addition, tools delete vlan by tag, not by index, lets follow that.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c           |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     |  6 +----
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  2 +-
 drivers/net/ethernet/mellanox/mlx4/port.c          | 27 ++++++++++++----------
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  2 +-
 include/linux/mlx4/device.h                        |  2 +-
 6 files changed, 20 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index ae8eb4c4fb6c..887d62576f54 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1687,7 +1687,7 @@ static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		if (NO_INDX != vp_oper->vlan_idx) {
 			__mlx4_unregister_vlan(&priv->dev,
-					       port, vp_oper->vlan_idx);
+					       port, vp_oper->state.default_vlan);
 			vp_oper->vlan_idx = NO_INDX;
 		}
 		if (NO_INDX != vp_oper->mac_idx) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 85d91665d400..b5554121aca4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -417,7 +417,6 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int err;
-	int idx;
 
 	en_dbg(HW, priv, "Killing VID:%d\n", vid);
 
@@ -425,10 +424,7 @@ static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev,
 
 	/* Remove VID from port VLAN filter */
 	mutex_lock(&mdev->state_lock);
-	if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx))
-		mlx4_unregister_vlan(mdev->dev, priv->port, idx);
-	else
-		en_dbg(HW, priv, "could not find vid %d in cache\n", vid);
+	mlx4_unregister_vlan(mdev->dev, priv->port, vid);
 
 	if (mdev->device_up && priv->port_up) {
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 348bb8c7d9a7..f2ad4f61f58c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1111,7 +1111,7 @@ int mlx4_change_port_types(struct mlx4_dev *dev,
 
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
 void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
-void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index);
+void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
 int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz);
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 9433c1f6b0d4..caaa15470395 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -406,23 +406,26 @@ int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
 }
 EXPORT_SYMBOL_GPL(mlx4_register_vlan);
 
-void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan)
 {
 	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
+	int index;
 
-	if (index < MLX4_VLAN_REGULAR) {
-		mlx4_warn(dev, "Trying to free special vlan index %d\n", index);
-		return;
+	mutex_lock(&table->mutex);
+	if (mlx4_find_cached_vlan(dev, port, vlan, &index)) {
+		mlx4_warn(dev, "vlan 0x%x is not in the vlan table\n", vlan);
+		goto out;
 	}
 
-	mutex_lock(&table->mutex);
-	if (!table->refs[index]) {
-		mlx4_warn(dev, "No vlan entry for index %d\n", index);
+	if (index < MLX4_VLAN_REGULAR) {
+		mlx4_warn(dev, "Trying to free special vlan index %d\n", index);
 		goto out;
 	}
+
 	if (--table->refs[index]) {
-		mlx4_dbg(dev, "Have more references for index %d,"
-			 "no need to modify vlan table\n", index);
+		mlx4_dbg(dev, "Have %d more references for index %d,"
+			 "no need to modify vlan table\n", table->refs[index],
+			 index);
 		goto out;
 	}
 	table->entries[index] = 0;
@@ -432,19 +435,19 @@ out:
 	mutex_unlock(&table->mutex);
 }
 
-void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan)
 {
 	u64 out_param = 0;
 
 	if (mlx4_is_mfunc(dev)) {
-		(void) mlx4_cmd_imm(dev, index, &out_param,
+		(void) mlx4_cmd_imm(dev, vlan, &out_param,
 				    ((u32) port) << 8 | (u32) RES_VLAN,
 				    RES_OP_RESERVE_AND_MAP,
 				    MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
 				    MLX4_CMD_WRAPPED);
 		return;
 	}
-	__mlx4_unregister_vlan(dev, port, index);
+	__mlx4_unregister_vlan(dev, port, vlan);
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_vlan);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index a5aa3be554fe..993a2ef13866 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4085,7 +4085,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
 	if (work->flags & MLX4_VF_IMMED_VLAN_FLAG_VLAN && !errors &&
 	    NO_INDX != work->orig_vlan_ix)
 		__mlx4_unregister_vlan(&work->priv->dev, work->port,
-				       work->orig_vlan_ix);
+				       work->orig_vlan_id);
 out:
 	kfree(work);
 	return;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 297a16309f00..e2e92885bdc1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1079,7 +1079,7 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
 		u8 *pg, u16 *ratelimit);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
-void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index);
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
 
 int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
 		      int npages, u64 iova, u32 *lkey, u32 *rkey);
-- 
cgit 


From 5a0d0a6161aecbbc76e4c1d2b82e4c7cef88bb29 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Sun, 3 Nov 2013 10:03:23 +0200
Subject: mlx4: Structures and init/teardown for VF resource quotas

This is step #1 for implementing SRIOV resource quotas for VFs.

Quotas are implemented per resource type for VFs and the PF, to prevent
any entity from simply grabbing all the resources for itself and leaving
the other entities unable to obtain such resources.

Resources which are allocated using quotas:  QPs, CQs, SRQs, MPTs, MTTs, MAC,
                                             VLAN, and Counters.

The quota system works as follows:
Each entity (VF or PF) is given a max number of a given resource (its quota),
and a guaranteed minimum number for each resource (starvation prevention).

For QPs, CQs, SRQs, MPTs and MTTs:
50% of the available quantity for the resource is divided equally among
the PF and all the active VFs (i.e., the number of VFs in the mlx4_core module
parameter "num_vfs"). This 50% represents the "guaranteed minimum" pool.
The other 50% is the "free pool", allocated on a first-come-first-serve basis.
For each VF/PF, resources are first allocated from its "guaranteed-minimum"
pool. When that pool is exhausted, the driver attempts to allocate from
the resource "free-pool".

The quota (i.e., max) for the VFs and the PF is:
  The free-pool amount (50% of the real max) + the guaranteed minimum

For MACs:
  Guarantee 2 MACs per VF/PF per port. As a result, since we have only
  128 MACs per port, reduce the allowable number of VFs from 64 to 63.
  Any remaining MACs are put into a free pool.

For VLANs:
  For the PF, the per-port quota is 128 and guarantee is 64
     (to allow the PF to register at least a VLAN per VF in VST mode).
  For the VFs, the per-port quota is 64 and the guarantee is 0.
      We assume that VGT VFs are trusted not to abuse the VLAN resource.

For Counters:
  For all functions (PF and VFs), the quota is 128 and the guarantee is 0.

In this patch, we define the needed structures, which are added to the
resource-tracker struct.  In addition, we do initialization
for the resource quota, and adjust the query_device response to use quotas
rather than resource maxima.

As part of the implementation, we introduce a new field in
mlx4_dev: quotas.  This field holds the resource quotas used
to report maxima to the upper layers (ib_core, via query_device).

The HCA maxima of these values are passed to the VFs (via
QUERY_HCA) so that they may continue to use these in handling
QPs, CQs, SRQs and MPTs.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c                  |   8 +-
 drivers/net/ethernet/mellanox/mlx4/fw.c            |  11 +-
 drivers/net/ethernet/mellanox/mlx4/main.c          |  32 +++--
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  17 +++
 drivers/net/ethernet/mellanox/mlx4/qp.c            |   3 +-
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 157 ++++++++++++++++++++-
 include/linux/mlx4/device.h                        |  17 +++
 7 files changed, 222 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f0612645de99..7567437dbd34 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -177,18 +177,18 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 
 	props->max_mr_size	   = ~0ull;
 	props->page_size_cap	   = dev->dev->caps.page_size_cap;
-	props->max_qp		   = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps;
+	props->max_qp		   = dev->dev->quotas.qp;
 	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
 	props->max_sge		   = min(dev->dev->caps.max_sq_sg,
 					 dev->dev->caps.max_rq_sg);
-	props->max_cq		   = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs;
+	props->max_cq		   = dev->dev->quotas.cq;
 	props->max_cqe		   = dev->dev->caps.max_cqes;
-	props->max_mr		   = dev->dev->caps.num_mpts - dev->dev->caps.reserved_mrws;
+	props->max_mr		   = dev->dev->quotas.mpt;
 	props->max_pd		   = dev->dev->caps.num_pds - dev->dev->caps.reserved_pds;
 	props->max_qp_rd_atom	   = dev->dev->caps.max_qp_dest_rdma;
 	props->max_qp_init_rd_atom = dev->dev->caps.max_qp_init_rdma;
 	props->max_res_rd_atom	   = props->max_qp_rd_atom * props->max_qp;
-	props->max_srq		   = dev->dev->caps.num_srqs - dev->dev->caps.reserved_srqs;
+	props->max_srq		   = dev->dev->quotas.srq;
 	props->max_srq_wr	   = dev->dev->caps.max_srq_wqes - 1;
 	props->max_srq_sge	   = dev->dev->caps.max_srq_sge;
 	props->max_fast_reg_page_list_len = MLX4_MAX_FAST_REG_PAGES;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index c151e7a6710a..f8c88c3ad9fc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -177,6 +177,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 				struct mlx4_cmd_mailbox *outbox,
 				struct mlx4_cmd_info *cmd)
 {
+	struct mlx4_priv *priv = mlx4_priv(dev);
 	u8	field;
 	u32	size;
 	int	err = 0;
@@ -250,13 +251,13 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		field = 0; /* protected FMR support not available as yet */
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FMR_OFFSET);
 
-		size = dev->caps.num_qps;
+		size = priv->mfunc.master.res_tracker.res_alloc[RES_QP].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP_QUOTA_OFFSET);
 
-		size = dev->caps.num_srqs;
+		size = priv->mfunc.master.res_tracker.res_alloc[RES_SRQ].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET);
 
-		size = dev->caps.num_cqs;
+		size = priv->mfunc.master.res_tracker.res_alloc[RES_CQ].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET);
 
 		size = dev->caps.num_eqs;
@@ -265,10 +266,10 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		size = dev->caps.reserved_eqs;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
 
-		size = dev->caps.num_mpts;
+		size = priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
 
-		size = dev->caps.num_mtts;
+		size = priv->mfunc.master.res_tracker.res_alloc[RES_MTT].quota[slave];
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET);
 
 		size = dev->caps.num_mgms + dev->caps.num_amgms;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 179d26709c94..7d2628dfdc29 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -562,13 +562,17 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	}
 
 	dev->caps.num_ports		= func_cap.num_ports;
-	dev->caps.num_qps		= func_cap.qp_quota;
-	dev->caps.num_srqs		= func_cap.srq_quota;
-	dev->caps.num_cqs		= func_cap.cq_quota;
-	dev->caps.num_eqs               = func_cap.max_eq;
-	dev->caps.reserved_eqs          = func_cap.reserved_eq;
-	dev->caps.num_mpts		= func_cap.mpt_quota;
-	dev->caps.num_mtts		= func_cap.mtt_quota;
+	dev->quotas.qp			= func_cap.qp_quota;
+	dev->quotas.srq			= func_cap.srq_quota;
+	dev->quotas.cq			= func_cap.cq_quota;
+	dev->quotas.mpt			= func_cap.mpt_quota;
+	dev->quotas.mtt			= func_cap.mtt_quota;
+	dev->caps.num_qps		= 1 << hca_param.log_num_qps;
+	dev->caps.num_srqs		= 1 << hca_param.log_num_srqs;
+	dev->caps.num_cqs		= 1 << hca_param.log_num_cqs;
+	dev->caps.num_mpts		= 1 << hca_param.log_mpt_sz;
+	dev->caps.num_eqs		= func_cap.max_eq;
+	dev->caps.reserved_eqs		= func_cap.reserved_eq;
 	dev->caps.num_pds               = MLX4_NUM_PDS;
 	dev->caps.num_mgms              = 0;
 	dev->caps.num_amgms             = 0;
@@ -2102,9 +2106,15 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 			"aborting.\n");
 		return err;
 	}
-	if (num_vfs > MLX4_MAX_NUM_VF) {
-		printk(KERN_ERR "There are more VF's (%d) than allowed(%d)\n",
-		       num_vfs, MLX4_MAX_NUM_VF);
+
+	/* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS
+	 * per port, we must limit the number of VFs to 63 (since their are
+	 * 128 MACs)
+	 */
+	if (num_vfs >= MLX4_MAX_NUM_VF) {
+		dev_err(&pdev->dev,
+			"Requested more VF's (%d) than allowed (%d)\n",
+			num_vfs, MLX4_MAX_NUM_VF - 1);
 		return -EINVAL;
 	}
 
@@ -2322,6 +2332,8 @@ slave_start:
 	if (err)
 		goto err_steer;
 
+	mlx4_init_quotas(dev);
+
 	for (port = 1; port <= dev->caps.num_ports; port++) {
 		err = mlx4_init_port_info(dev, port);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 97941269bc14..e7eb86ecc6ea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -504,12 +504,27 @@ struct slave_list {
 	struct list_head res_list[MLX4_NUM_OF_RESOURCE_TYPE];
 };
 
+struct resource_allocator {
+	union {
+		int res_reserved;
+		int res_port_rsvd[MLX4_MAX_PORTS];
+	};
+	union {
+		int res_free;
+		int res_port_free[MLX4_MAX_PORTS];
+	};
+	int *quota;
+	int *allocated;
+	int *guaranteed;
+};
+
 struct mlx4_resource_tracker {
 	spinlock_t lock;
 	/* tree for each resources */
 	struct rb_root res_tree[MLX4_NUM_OF_RESOURCE_TYPE];
 	/* num_of_slave's lists, one per slave */
 	struct slave_list *slave_list;
+	struct resource_allocator res_alloc[MLX4_NUM_OF_RESOURCE_TYPE];
 };
 
 #define SLAVE_EVENT_EQ_SIZE	128
@@ -1253,4 +1268,6 @@ static inline spinlock_t *mlx4_tlock(struct mlx4_dev *dev)
 
 void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work);
 
+void mlx4_init_quotas(struct mlx4_dev *dev);
+
 #endif /* MLX4_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index e891b058c1be..2715e61dbb74 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -480,8 +480,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	*/
 
 	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
-			       (1 << 23) - 1, dev->phys_caps.base_sqpn + 8 +
-			       16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev),
+			       (1 << 23) - 1, mlx4_num_reserved_sqps(dev),
 			       reserved_from_top);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 35863889bec0..cc5d6d0aad16 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -284,10 +284,59 @@ static const char *ResourceType(enum mlx4_resource rt)
 }
 
 static void rem_slave_vlans(struct mlx4_dev *dev, int slave);
+static inline void initialize_res_quotas(struct mlx4_dev *dev,
+					 struct resource_allocator *res_alloc,
+					 enum mlx4_resource res_type,
+					 int vf, int num_instances)
+{
+	res_alloc->guaranteed[vf] = num_instances / (2 * (dev->num_vfs + 1));
+	res_alloc->quota[vf] = (num_instances / 2) + res_alloc->guaranteed[vf];
+	if (vf == mlx4_master_func_num(dev)) {
+		res_alloc->res_free = num_instances;
+		if (res_type == RES_MTT) {
+			/* reserved mtts will be taken out of the PF allocation */
+			res_alloc->res_free += dev->caps.reserved_mtts;
+			res_alloc->guaranteed[vf] += dev->caps.reserved_mtts;
+			res_alloc->quota[vf] += dev->caps.reserved_mtts;
+		}
+	}
+}
+
+void mlx4_init_quotas(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int pf;
+
+	/* quotas for VFs are initialized in mlx4_slave_cap */
+	if (mlx4_is_slave(dev))
+		return;
+
+	if (!mlx4_is_mfunc(dev)) {
+		dev->quotas.qp = dev->caps.num_qps - dev->caps.reserved_qps -
+			mlx4_num_reserved_sqps(dev);
+		dev->quotas.cq = dev->caps.num_cqs - dev->caps.reserved_cqs;
+		dev->quotas.srq = dev->caps.num_srqs - dev->caps.reserved_srqs;
+		dev->quotas.mtt = dev->caps.num_mtts - dev->caps.reserved_mtts;
+		dev->quotas.mpt = dev->caps.num_mpts - dev->caps.reserved_mrws;
+		return;
+	}
+
+	pf = mlx4_master_func_num(dev);
+	dev->quotas.qp =
+		priv->mfunc.master.res_tracker.res_alloc[RES_QP].quota[pf];
+	dev->quotas.cq =
+		priv->mfunc.master.res_tracker.res_alloc[RES_CQ].quota[pf];
+	dev->quotas.srq =
+		priv->mfunc.master.res_tracker.res_alloc[RES_SRQ].quota[pf];
+	dev->quotas.mtt =
+		priv->mfunc.master.res_tracker.res_alloc[RES_MTT].quota[pf];
+	dev->quotas.mpt =
+		priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf];
+}
 int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int i;
+	int i, j;
 	int t;
 
 	priv->mfunc.master.res_tracker.slave_list =
@@ -308,8 +357,104 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 	for (i = 0 ; i < MLX4_NUM_OF_RESOURCE_TYPE; i++)
 		priv->mfunc.master.res_tracker.res_tree[i] = RB_ROOT;
 
+	for (i = 0; i < MLX4_NUM_OF_RESOURCE_TYPE; i++) {
+		struct resource_allocator *res_alloc =
+			&priv->mfunc.master.res_tracker.res_alloc[i];
+		res_alloc->quota = kmalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
+		res_alloc->guaranteed = kmalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
+		if (i == RES_MAC || i == RES_VLAN)
+			res_alloc->allocated = kzalloc(MLX4_MAX_PORTS *
+						       (dev->num_vfs + 1) * sizeof(int),
+							GFP_KERNEL);
+		else
+			res_alloc->allocated = kzalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
+
+		if (!res_alloc->quota || !res_alloc->guaranteed ||
+		    !res_alloc->allocated)
+			goto no_mem_err;
+
+		for (t = 0; t < dev->num_vfs + 1; t++) {
+			switch (i) {
+			case RES_QP:
+				initialize_res_quotas(dev, res_alloc, RES_QP,
+						      t, dev->caps.num_qps -
+						      dev->caps.reserved_qps -
+						      mlx4_num_reserved_sqps(dev));
+				break;
+			case RES_CQ:
+				initialize_res_quotas(dev, res_alloc, RES_CQ,
+						      t, dev->caps.num_cqs -
+						      dev->caps.reserved_cqs);
+				break;
+			case RES_SRQ:
+				initialize_res_quotas(dev, res_alloc, RES_SRQ,
+						      t, dev->caps.num_srqs -
+						      dev->caps.reserved_srqs);
+				break;
+			case RES_MPT:
+				initialize_res_quotas(dev, res_alloc, RES_MPT,
+						      t, dev->caps.num_mpts -
+						      dev->caps.reserved_mrws);
+				break;
+			case RES_MTT:
+				initialize_res_quotas(dev, res_alloc, RES_MTT,
+						      t, dev->caps.num_mtts -
+						      dev->caps.reserved_mtts);
+				break;
+			case RES_MAC:
+				if (t == mlx4_master_func_num(dev)) {
+					res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
+					res_alloc->guaranteed[t] = 2;
+					for (j = 0; j < MLX4_MAX_PORTS; j++)
+						res_alloc->res_port_free[j] = MLX4_MAX_MAC_NUM;
+				} else {
+					res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
+					res_alloc->guaranteed[t] = 2;
+				}
+				break;
+			case RES_VLAN:
+				if (t == mlx4_master_func_num(dev)) {
+					res_alloc->quota[t] = MLX4_MAX_VLAN_NUM;
+					res_alloc->guaranteed[t] = MLX4_MAX_VLAN_NUM / 2;
+					for (j = 0; j < MLX4_MAX_PORTS; j++)
+						res_alloc->res_port_free[j] =
+							res_alloc->quota[t];
+				} else {
+					res_alloc->quota[t] = MLX4_MAX_VLAN_NUM / 2;
+					res_alloc->guaranteed[t] = 0;
+				}
+				break;
+			case RES_COUNTER:
+				res_alloc->quota[t] = dev->caps.max_counters;
+				res_alloc->guaranteed[t] = 0;
+				if (t == mlx4_master_func_num(dev))
+					res_alloc->res_free = res_alloc->quota[t];
+				break;
+			default:
+				break;
+			}
+			if (i == RES_MAC || i == RES_VLAN) {
+				for (j = 0; j < MLX4_MAX_PORTS; j++)
+					res_alloc->res_port_rsvd[j] +=
+						res_alloc->guaranteed[t];
+			} else {
+				res_alloc->res_reserved += res_alloc->guaranteed[t];
+			}
+		}
+	}
 	spin_lock_init(&priv->mfunc.master.res_tracker.lock);
-	return 0 ;
+	return 0;
+
+no_mem_err:
+	for (i = 0; i < MLX4_NUM_OF_RESOURCE_TYPE; i++) {
+		kfree(priv->mfunc.master.res_tracker.res_alloc[i].allocated);
+		priv->mfunc.master.res_tracker.res_alloc[i].allocated = NULL;
+		kfree(priv->mfunc.master.res_tracker.res_alloc[i].guaranteed);
+		priv->mfunc.master.res_tracker.res_alloc[i].guaranteed = NULL;
+		kfree(priv->mfunc.master.res_tracker.res_alloc[i].quota);
+		priv->mfunc.master.res_tracker.res_alloc[i].quota = NULL;
+	}
+	return -ENOMEM;
 }
 
 void mlx4_free_resource_tracker(struct mlx4_dev *dev,
@@ -333,6 +478,14 @@ void mlx4_free_resource_tracker(struct mlx4_dev *dev,
 		}
 
 		if (type != RES_TR_FREE_SLAVES_ONLY) {
+			for (i = 0; i < MLX4_NUM_OF_RESOURCE_TYPE; i++) {
+				kfree(priv->mfunc.master.res_tracker.res_alloc[i].allocated);
+				priv->mfunc.master.res_tracker.res_alloc[i].allocated = NULL;
+				kfree(priv->mfunc.master.res_tracker.res_alloc[i].guaranteed);
+				priv->mfunc.master.res_tracker.res_alloc[i].guaranteed = NULL;
+				kfree(priv->mfunc.master.res_tracker.res_alloc[i].quota);
+				priv->mfunc.master.res_tracker.res_alloc[i].quota = NULL;
+			}
 			kfree(priv->mfunc.master.res_tracker.slave_list);
 			priv->mfunc.master.res_tracker.slave_list = NULL;
 		}
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e2e92885bdc1..f6f59271f857 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -641,12 +641,23 @@ struct mlx4_counter {
 	__be64	tx_bytes;
 };
 
+struct mlx4_quotas {
+	int qp;
+	int cq;
+	int srq;
+	int mpt;
+	int mtt;
+	int counter;
+	int xrcd;
+};
+
 struct mlx4_dev {
 	struct pci_dev	       *pdev;
 	unsigned long		flags;
 	unsigned long		num_slaves;
 	struct mlx4_caps	caps;
 	struct mlx4_phys_caps	phys_caps;
+	struct mlx4_quotas	quotas;
 	struct radix_tree_root	qp_table_tree;
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
@@ -772,6 +783,12 @@ static inline int mlx4_is_master(struct mlx4_dev *dev)
 	return dev->flags & MLX4_FLAG_MASTER;
 }
 
+static inline int mlx4_num_reserved_sqps(struct mlx4_dev *dev)
+{
+	return dev->phys_caps.base_sqpn + 8 +
+		16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev);
+}
+
 static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn)
 {
 	return (qpn < dev->phys_caps.base_sqpn + 8 +
-- 
cgit 


From b944dba31d2c23f1cf5d69a66cc3449e0ba78503 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Mon, 4 Nov 2013 15:20:20 -0500
Subject: NFSv4: Sanity check the server reply in _nfs4_server_capabilities

We don't want to be setting capabilities and/or requesting attributes
that are not appropriate for the NFSv4 minor version.

- Ensure that we clear the NFS_CAP_SECURITY_LABEL capability when appropriate
- Ensure that we limit the attribute bitmasks to the mounted_on_fileid
  attribute and less for NFSv4.0
- Ensure that we limit the attribute bitmasks to suppattr_exclcreat and
  less for NFSv4.1
- Ensure that we limit it to change_sec_label or less for NFSv4.2

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c    | 25 ++++++++++++++++++++-----
 include/linux/nfs4.h |  2 ++
 2 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7e28b5c77cbc..ed2a0e6b9aed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2706,6 +2706,10 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 		nfs4_close_state(ctx->state, ctx->mode);
 }
 
+#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
+#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_CHANGE_SECURITY_LABEL - 1UL)
+
 static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 {
 	struct nfs4_server_caps_arg args = {
@@ -2721,12 +2725,25 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 	if (status == 0) {
+		/* Sanity check the server answers */
+		switch (server->nfs_client->cl_minorversion) {
+		case 0:
+			res.attr_bitmask[1] &= FATTR4_WORD1_NFS40_MASK;
+			res.attr_bitmask[2] = 0;
+			break;
+		case 1:
+			res.attr_bitmask[2] &= FATTR4_WORD2_NFS41_MASK;
+			break;
+		case 2:
+			res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK;
+		}
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
 		server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
 				NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
 				NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
 				NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
-				NFS_CAP_CTIME|NFS_CAP_MTIME);
+				NFS_CAP_CTIME|NFS_CAP_MTIME|
+				NFS_CAP_SECURITY_LABEL);
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
 			server->caps |= NFS_CAP_ACLS;
 		if (res.has_links != 0)
@@ -2755,14 +2772,12 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 #endif
 		memcpy(server->attr_bitmask_nl, res.attr_bitmask,
 				sizeof(server->attr_bitmask));
+		server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
 
-		if (server->caps & NFS_CAP_SECURITY_LABEL) {
-			server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
-			res.attr_bitmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
-		}
 		memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
 		server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
 		server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+		server->cache_consistency_bitmask[2] = 0;
 		server->acl_bitmask = res.acl_bitmask;
 		server->fh_expire_type = res.fh_expire_type;
 	}
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index bfe6c379a24e..c6f41b616965 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -396,6 +396,8 @@ enum lock_type4 {
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
+#define FATTR4_WORD2_CHANGE_SECURITY_LABEL \
+					(1UL << 17)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
-- 
cgit 


From 9f9843a751d0a2057f9f3d313886e7e5e6ebaac9 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 31 Oct 2013 11:07:31 -0700
Subject: tcp: properly handle stretch acks in slow start

Slow start now increases cwnd by 1 if an ACK acknowledges some packets,
regardless the number of packets. Consequently slow start performance
is highly dependent on the degree of the stretch ACKs caused by
receiver or network ACK compression mechanisms (e.g., delayed-ACK,
GRO, etc).  But slow start algorithm is to send twice the amount of
packets of packets left so it should process a stretch ACK of degree
N as if N ACKs of degree 1, then exits when cwnd exceeds ssthresh. A
follow up patch will use the remainder of the N (if greater than 1)
to adjust cwnd in the congestion avoidance phase.

In addition this patch retires the experimental limited slow start
(LSS) feature. LSS has multiple drawbacks but questionable benefit. The
fractional cwnd increase in LSS requires a loop in slow start even
though it's rarely used. Configuring such an increase step via a global
sysctl on different BDPS seems hard. Finally and most importantly the
slow start overshoot concern is now better covered by the Hybrid slow
start (hystart) enabled by default.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 11 --------
 include/net/tcp.h                      |  7 +++--
 net/ipv4/sysctl_net_ipv4.c             |  7 -----
 net/ipv4/tcp_bic.c                     |  5 ++--
 net/ipv4/tcp_cong.c                    | 47 ++++++++++++----------------------
 net/ipv4/tcp_cubic.c                   |  5 ++--
 net/ipv4/tcp_highspeed.c               |  4 +--
 net/ipv4/tcp_htcp.c                    |  4 +--
 net/ipv4/tcp_hybla.c                   |  5 ++--
 net/ipv4/tcp_illinois.c                |  5 ++--
 net/ipv4/tcp_input.c                   |  6 ++---
 net/ipv4/tcp_lp.c                      |  5 ++--
 net/ipv4/tcp_scalable.c                |  5 ++--
 net/ipv4/tcp_vegas.c                   | 11 ++++----
 net/ipv4/tcp_veno.c                    |  9 ++++---
 net/ipv4/tcp_yeah.c                    |  5 ++--
 16 files changed, 59 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6c0098359ca6..8b8a05787641 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -267,17 +267,6 @@ tcp_max_orphans - INTEGER
 	more aggressively. Let me to remind again: each orphan eats
 	up to ~64K of unswappable memory.
 
-tcp_max_ssthresh - INTEGER
-	Limited Slow-Start for TCP with large congestion windows (cwnd) defined in
-	RFC3742. Limited slow-start is a mechanism to limit growth of the cwnd
-	on the region where cwnd is larger than tcp_max_ssthresh. TCP increases cwnd
-	by at most tcp_max_ssthresh segments, and by at least tcp_max_ssthresh/2
-	segments per RTT when the cwnd is above tcp_max_ssthresh.
-	If TCP connection increased cwnd to thousands (or tens of thousands) segments,
-	and thousands of packets were being dropped during slow-start, you can set
-	tcp_max_ssthresh to improve performance for new TCP connection.
-	Default: 0 (off)
-
 tcp_max_syn_backlog - INTEGER
 	Maximal number of remembered connection requests, which have not
 	received an acknowledgment from connecting client.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2d7b4bdc972f..70e55d200610 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -275,7 +275,6 @@ extern int sysctl_tcp_mtu_probing;
 extern int sysctl_tcp_base_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
-extern int sysctl_tcp_max_ssthresh;
 extern int sysctl_tcp_thin_linear_timeouts;
 extern int sysctl_tcp_thin_dupack;
 extern int sysctl_tcp_early_retrans;
@@ -797,7 +796,7 @@ struct tcp_congestion_ops {
 	/* lower bound for congestion window (optional) */
 	u32 (*min_cwnd)(const struct sock *sk);
 	/* do new cwnd calculation (required) */
-	void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight);
+	void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
 	/* call before changing ca_state (optional) */
 	void (*set_state)(struct sock *sk, u8 new_state);
 	/* call when cwnd event occurs (optional) */
@@ -824,12 +823,12 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-void tcp_slow_start(struct tcp_sock *tp);
+int tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
 u32 tcp_reno_ssthresh(struct sock *sk);
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
 u32 tcp_reno_min_cwnd(const struct sock *sk);
 extern struct tcp_congestion_ops tcp_reno;
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d5b1390eebbe..3d69ec8dac57 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -700,13 +700,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler   = proc_allowed_congestion_control,
 	},
-	{
-		.procname	= "tcp_max_ssthresh",
-		.data		= &sysctl_tcp_max_ssthresh,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname       = "tcp_thin_linear_timeouts",
 		.data           = &sysctl_tcp_thin_linear_timeouts,
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index f45e1c242440..821846fb0a7e 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -140,7 +140,8 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+			      u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -149,7 +150,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	else {
 		bictcp_update(ca, tp->snd_cwnd);
 		tcp_cong_avoid_ai(tp, ca->cnt);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 019c2389a341..ad37bf18ae4b 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -15,8 +15,6 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-int sysctl_tcp_max_ssthresh = 0;
-
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
 static LIST_HEAD(tcp_cong_list);
 
@@ -299,35 +297,24 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
 }
 EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
 
-/*
- * Slow start is used when congestion window is less than slow start
- * threshold. This version implements the basic RFC2581 version
- * and optionally supports:
- * 	RFC3742 Limited Slow Start  	  - growth limited to max_ssthresh
- *	RFC3465 Appropriate Byte Counting - growth limited by bytes acknowledged
+/* Slow start is used when congestion window is no greater than the slow start
+ * threshold. We base on RFC2581 and also handle stretch ACKs properly.
+ * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but
+ * something better;) a packet is only considered (s)acked in its entirety to
+ * defend the ACK attacks described in the RFC. Slow start processes a stretch
+ * ACK of degree N as if N acks of degree 1 are received back to back except
+ * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
+ * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp)
+int tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
-	int cnt; /* increase in packets */
-	unsigned int delta = 0;
-	u32 snd_cwnd = tp->snd_cwnd;
-
-	if (unlikely(!snd_cwnd)) {
-		pr_err_once("snd_cwnd is nul, please report this bug.\n");
-		snd_cwnd = 1U;
-	}
+	u32 cwnd = tp->snd_cwnd + acked;
 
-	if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
-		cnt = sysctl_tcp_max_ssthresh >> 1;	/* limited slow start */
-	else
-		cnt = snd_cwnd;				/* exponential increase */
-
-	tp->snd_cwnd_cnt += cnt;
-	while (tp->snd_cwnd_cnt >= snd_cwnd) {
-		tp->snd_cwnd_cnt -= snd_cwnd;
-		delta++;
-	}
-	tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp);
+	if (cwnd > tp->snd_ssthresh)
+		cwnd = tp->snd_ssthresh + 1;
+	acked -= cwnd - tp->snd_cwnd;
+	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
@@ -351,7 +338,7 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 /* This is Jacobson's slow start and congestion avoidance.
  * SIGCOMM '88, p. 328.
  */
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -360,7 +347,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 	/* In "safe" area, increase. */
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	/* In dangerous area, increase slowly. */
 	else
 		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index b6ae92a51f58..828e4c3ffbaf 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -304,7 +304,8 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+			      u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
@@ -315,7 +316,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
 		if (hystart && after(ack, ca->end_seq))
 			bictcp_hystart_reset(sk);
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	} else {
 		bictcp_update(ca, tp->snd_cwnd);
 		tcp_cong_avoid_ai(tp, ca->cnt);
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 30f27f6b3655..8ed9305dfdf4 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -109,7 +109,7 @@ static void hstcp_init(struct sock *sk)
 	tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
 }
 
-static void hstcp_cong_avoid(struct sock *sk, u32 adk, u32 in_flight)
+static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hstcp *ca = inet_csk_ca(sk);
@@ -118,7 +118,7 @@ static void hstcp_cong_avoid(struct sock *sk, u32 adk, u32 in_flight)
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	else {
 		/* Update AIMD parameters.
 		 *
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index c1a8175361e8..4a194acfd923 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -227,7 +227,7 @@ static u32 htcp_recalc_ssthresh(struct sock *sk)
 	return max((tp->snd_cwnd * ca->beta) >> 7, 2U);
 }
 
-static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct htcp *ca = inet_csk_ca(sk);
@@ -236,7 +236,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	else {
 		/* In dangerous area, increase slowly.
 		 * In theory this is tp->snd_cwnd += alpha / tp->snd_cwnd
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index 57bdd17dff4d..478fe82611bf 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -85,7 +85,8 @@ static inline u32 hybla_fraction(u32 odds)
  *     o Give cwnd a new value based on the model proposed
  *     o remember increments <1
  */
-static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+			     u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hybla *ca = inet_csk_ca(sk);
@@ -102,7 +103,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		return;
 
 	if (!ca->hybla_en) {
-		tcp_reno_cong_avoid(sk, ack, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 		return;
 	}
 
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 834857f3c871..8a520996f3d2 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -256,7 +256,8 @@ static void tcp_illinois_state(struct sock *sk, u8 new_state)
 /*
  * Increase window in response to successful acknowledgment.
  */
-static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+				    u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct illinois *ca = inet_csk_ca(sk);
@@ -270,7 +271,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 	/* In slow start */
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 
 	else {
 		u32 delta;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 63095b218b4a..c53b7f35c51d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2934,10 +2934,10 @@ static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
 		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
 }
 
-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight);
+	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked, in_flight);
 	tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
 }
 
@@ -3454,7 +3454,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	/* Advance cwnd if state allows */
 	if (tcp_may_raise_cwnd(sk, flag))
-		tcp_cong_avoid(sk, ack, prior_in_flight);
+		tcp_cong_avoid(sk, ack, acked, prior_in_flight);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 72f7218b03f5..991d62a2f9bb 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -115,12 +115,13 @@ static void tcp_lp_init(struct sock *sk)
  * Will only call newReno CA when away from inference.
  * From TCP-LP's paper, this will be handled in additive increasement.
  */
-static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+			      u32 in_flight)
 {
 	struct lp *lp = inet_csk_ca(sk);
 
 	if (!(lp->flag & LP_WITHIN_INF))
-		tcp_reno_cong_avoid(sk, ack, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 }
 
 /**
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 8ce55b8aaec8..19ea6c2951f3 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -15,7 +15,8 @@
 #define TCP_SCALABLE_AI_CNT	50U
 #define TCP_SCALABLE_MD_SCALE	3
 
-static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+				    u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -23,7 +24,7 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 	else
 		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
 }
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 80fa2bfd7ede..06cae62bf208 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -163,13 +163,14 @@ static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
 }
 
-static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+				 u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct vegas *vegas = inet_csk_ca(sk);
 
 	if (!vegas->doing_vegas_now) {
-		tcp_reno_cong_avoid(sk, ack, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 		return;
 	}
 
@@ -194,7 +195,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 			/* We don't have enough RTT samples to do the Vegas
 			 * calculation, so we'll behave like Reno.
 			 */
-			tcp_reno_cong_avoid(sk, ack, in_flight);
+			tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 		} else {
 			u32 rtt, diff;
 			u64 target_cwnd;
@@ -243,7 +244,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 			} else if (tp->snd_cwnd <= tp->snd_ssthresh) {
 				/* Slow start.  */
-				tcp_slow_start(tp);
+				tcp_slow_start(tp, acked);
 			} else {
 				/* Congestion avoidance. */
 
@@ -283,7 +284,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 	}
 	/* Use normal slow start */
 	else if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 
 }
 
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index ac43cd747bce..326475a94865 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -114,13 +114,14 @@ static void tcp_veno_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 		tcp_veno_init(sk);
 }
 
-static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+				u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct veno *veno = inet_csk_ca(sk);
 
 	if (!veno->doing_veno_now) {
-		tcp_reno_cong_avoid(sk, ack, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 		return;
 	}
 
@@ -133,7 +134,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		/* We don't have enough rtt samples to do the Veno
 		 * calculation, so we'll behave like Reno.
 		 */
-		tcp_reno_cong_avoid(sk, ack, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
 	} else {
 		u64 target_cwnd;
 		u32 rtt;
@@ -152,7 +153,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 
 		if (tp->snd_cwnd <= tp->snd_ssthresh) {
 			/* Slow start.  */
-			tcp_slow_start(tp);
+			tcp_slow_start(tp, acked);
 		} else {
 			/* Congestion avoidance. */
 			if (veno->diff < beta) {
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 05c3b6f0e8e1..a347a078ee07 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -69,7 +69,8 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
 	tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
 }
 
-static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked,
+				u32 in_flight)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct yeah *yeah = inet_csk_ca(sk);
@@ -78,7 +79,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp);
+		tcp_slow_start(tp, acked);
 
 	else if (!yeah->doing_reno_now) {
 		/* Scalable */
-- 
cgit 


From 1ba3aab3033b464f352659720824d7124c21dbf9 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <netoptimizer@brouer.com>
Date: Thu, 31 Oct 2013 22:10:55 +0100
Subject: net: codel: Avoid undefined behavior from signed overflow

As described in commit 5a581b367 (jiffies: Avoid undefined
behavior from signed overflow), according to the C standard
3.4.3p3, overflow of a signed integer results in undefined
behavior.

To fix this, do as the above commit, and do an unsigned
subtraction, and interpreting the result as a signed
two's-complement number.  This is based on the theory from
RFC 1982 and is nicely described in wikipedia here:
 https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution

A side-note, I have seen practical issues with the previous logic
when dealing with 16-bit, on a 64-bit machine (gcc version
4.4.5). This were 32-bit, which I have not observed issues with.

Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Jesper Dangaard Brouer <netoptimizer@brouer.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/codel.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/codel.h b/include/net/codel.h
index 389cf621161d..3b04ff5f6f8d 100644
--- a/include/net/codel.h
+++ b/include/net/codel.h
@@ -72,10 +72,21 @@ static inline codel_time_t codel_get_time(void)
 	return ns >> CODEL_SHIFT;
 }
 
-#define codel_time_after(a, b)		((s32)(a) - (s32)(b) > 0)
-#define codel_time_after_eq(a, b)	((s32)(a) - (s32)(b) >= 0)
-#define codel_time_before(a, b)		((s32)(a) - (s32)(b) < 0)
-#define codel_time_before_eq(a, b)	((s32)(a) - (s32)(b) <= 0)
+/* Dealing with timer wrapping, according to RFC 1982, as desc in wikipedia:
+ *  https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution
+ * codel_time_after(a,b) returns true if the time a is after time b.
+ */
+#define codel_time_after(a, b)						\
+	(typecheck(codel_time_t, a) &&					\
+	 typecheck(codel_time_t, b) &&					\
+	 ((s32)((a) - (b)) > 0))
+#define codel_time_before(a, b) 	codel_time_after(b, a)
+
+#define codel_time_after_eq(a, b)					\
+	(typecheck(codel_time_t, a) &&					\
+	 typecheck(codel_time_t, b) &&					\
+	 ((s32)((a) - (b)) >= 0))
+#define codel_time_before_eq(a, b)	codel_time_after_eq(b, a)
 
 /* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */
 struct codel_skb_cb {
-- 
cgit 


From f8e617e100d7369a0108f96abf4414e9fb82ced7 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 1 Nov 2013 14:07:47 +0800
Subject: net: introduce skb_coalesce_rx_frag()

Sometimes we need to coalesce the rx frags to avoid frag list. One example is
virtio-net driver which tries to use small frags for both MTU sized packet and
GSO packet. So this patch introduce skb_coalesce_rx_frag() to do this.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Michael Dalton <mwdalton@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  3 +++
 net/core/skbuff.c      | 12 ++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 44727b5d4981..2e153b69d318 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1372,6 +1372,9 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
+			  unsigned int truesize);
+
 #define SKB_PAGE_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->nr_frags)
 #define SKB_FRAG_ASSERT(skb) 	BUG_ON(skb_has_frag_list(skb))
 #define SKB_LINEAR_ASSERT(skb)  BUG_ON(skb_is_nonlinear(skb))
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e4115597b38b..3735fad5616e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -476,6 +476,18 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 }
 EXPORT_SYMBOL(skb_add_rx_frag);
 
+void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
+			  unsigned int truesize)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+	skb_frag_size_add(frag, size);
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += truesize;
+}
+EXPORT_SYMBOL(skb_coalesce_rx_frag);
+
 static void skb_drop_list(struct sk_buff **listp)
 {
 	kfree_skb_list(*listp);
-- 
cgit 


From b50eba7e2d534762a19a7207dda012f09302a8d2 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Mon, 16 Sep 2013 18:20:42 -0400
Subject: audit: format user messages to size of MAX_AUDIT_MESSAGE_LENGTH

Messages of type AUDIT_USER_TTY were being formatted to 1024 octets,
truncating messages approaching MAX_AUDIT_MESSAGE_LENGTH (8970 octets).

Set the formatting to 8560 characters, given maximum estimates for prefix and
suffix budgets.

See the problem discussion:
https://www.redhat.com/archives/linux-audit/2009-January/msg00030.html

And the new size rationale:
https://www.redhat.com/archives/linux-audit/2013-September/msg00016.html

Test ~8k messages with:
auditctl -m "$(for i in $(seq -w 001 820);do echo -n "${i}0______";done)"

Reported-by: LC Bruzenak <lenny@magitekltd.com>
Reported-by: Justin Stephenson <jstephen@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/uapi/linux/audit.h | 6 ++++++
 kernel/audit.c             | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 75cef3fd97ad..5dfcd85037e2 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -358,6 +358,12 @@ enum {
 #define AUDIT_PERM_READ		4
 #define AUDIT_PERM_ATTR		8
 
+/* MAX_AUDIT_MESSAGE_LENGTH is set in audit:lib/libaudit.h as:
+ * 8970 // PATH_MAX*2+CONTEXT_SIZE*2+11+256+1
+ * max header+body+tailer: 44 + 29 + 32 + 262 + 7 + pad
+ */
+#define AUDIT_MESSAGE_TEXT_MAX	8560
+
 struct audit_status {
 	__u32		mask;		/* Bit mask for valid entries */
 	__u32		enabled;	/* 1 = enabled, 0 = disabled */
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d04b6a9..dd63d2f978d5 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -715,7 +715,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			}
 			audit_log_common_recv_msg(&ab, msg_type);
 			if (msg_type != AUDIT_USER_TTY)
-				audit_log_format(ab, " msg='%.1024s'",
+				audit_log_format(ab, " msg='%.*s'",
+						 AUDIT_MESSAGE_TEXT_MAX,
 						 (char *)data);
 			else {
 				int size;
-- 
cgit 


From 42f74461a5b60cf6b42887e6d2ff5b7be4abf1ca Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Mon, 20 May 2013 15:08:18 -0400
Subject: audit: change decimal constant to macro for invalid uid

SFR reported this 2013-05-15:

> After merging the final tree, today's linux-next build (i386 defconfig)
> produced this warning:
>
> kernel/auditfilter.c: In function 'audit_data_to_entry':
> kernel/auditfilter.c:426:3: warning: this decimal constant is unsigned only
> in ISO C90 [enabled by default]
>
> Introduced by commit 780a7654cee8 ("audit: Make testing for a valid
> loginuid explicit") from Linus' tree.

Replace this decimal constant in the code with a macro to make it more readable
(add to the unsigned cast to quiet the warning).

Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/uapi/linux/audit.h | 2 ++
 kernel/auditfilter.c       | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 5dfcd85037e2..c1f0fced3ede 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -380,6 +380,8 @@ struct audit_tty_status {
 	__u32		log_passwd;	/* 1 = enabled, 0 = disabled */
 };
 
+#define AUDIT_UID_UNSET (unsigned int)-1
+
 /* audit_rule_data supports filter rules with both integer and string
  * fields.  It corresponds with AUDIT_ADD_RULE, AUDIT_DEL_RULE and
  * AUDIT_LIST_RULES requests.
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index f7aee8be7fb2..8a344cebd8bf 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -423,7 +423,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		f->lsm_rule = NULL;
 
 		/* Support legacy tests for a valid loginuid */
-		if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
+		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
 		}
-- 
cgit 


From b0fed40214ce79ef70d97584ebdf13f89786da0e Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Wed, 22 May 2013 12:54:49 -0400
Subject: audit: implement generic feature setting and retrieving

The audit_status structure was not designed with extensibility in mind.
Define a new AUDIT_SET_FEATURE message type which takes a new structure
of bits where things can be enabled/disabled/locked one at a time.  This
structure should be able to grow in the future while maintaining forward
and backward compatibility (based loosly on the ideas from capabilities
and prctl)

This does not actually add any features, but is just infrastructure to
allow new on/off types of audit system features.

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h      |   2 +
 include/uapi/linux/audit.h |  16 +++++++
 kernel/audit.c             | 109 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 729a4d165bcc..7b31bec9bccb 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -73,6 +73,8 @@ struct audit_field {
 	void				*lsm_rule;
 };
 
+extern int is_audit_feature_set(int which);
+
 extern int __init audit_register_class(int class, unsigned *list);
 extern int audit_classify_syscall(int abi, unsigned syscall);
 extern int audit_classify_arch(int arch);
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index c1f0fced3ede..9eddf2ca614f 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -68,6 +68,9 @@
 #define AUDIT_MAKE_EQUIV	1015	/* Append to watched tree */
 #define AUDIT_TTY_GET		1016	/* Get TTY auditing status */
 #define AUDIT_TTY_SET		1017	/* Set TTY auditing status */
+#define AUDIT_SET_FEATURE	1018	/* Turn an audit feature on or off */
+#define AUDIT_GET_FEATURE	1019	/* Get which features are enabled */
+#define AUDIT_FEATURE_CHANGE	1020	/* audit log listing feature changes */
 
 #define AUDIT_FIRST_USER_MSG	1100	/* Userspace messages mostly uninteresting to kernel */
 #define AUDIT_USER_AVC		1107	/* We filter this differently */
@@ -375,6 +378,19 @@ struct audit_status {
 	__u32		backlog;	/* messages waiting in queue */
 };
 
+struct audit_features {
+#define AUDIT_FEATURE_VERSION	1
+	__u32	vers;
+	__u32	mask;		/* which bits we are dealing with */
+	__u32	features;	/* which feature to enable/disable */
+	__u32	lock;		/* which features to lock */
+};
+
+#define AUDIT_LAST_FEATURE	-1
+
+#define audit_feature_valid(x)		((x) >= 0 && (x) <= AUDIT_LAST_FEATURE)
+#define AUDIT_FEATURE_TO_MASK(x)	(1 << ((x) & 31)) /* mask for __u32 */
+
 struct audit_tty_status {
 	__u32		enabled;	/* 1 = enabled, 0 = disabled */
 	__u32		log_passwd;	/* 1 = enabled, 0 = disabled */
diff --git a/kernel/audit.c b/kernel/audit.c
index 74550ff3644f..29ee6a421c6c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -139,6 +139,15 @@ static struct task_struct *kauditd_task;
 static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
 static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
 
+static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
+				   .mask = -1,
+				   .features = 0,
+				   .lock = 0,};
+
+static char *audit_feature_names[0] = {
+};
+
+
 /* Serialize requests from userspace. */
 DEFINE_MUTEX(audit_cmd_mutex);
 
@@ -583,6 +592,8 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 		return -EOPNOTSUPP;
 	case AUDIT_GET:
 	case AUDIT_SET:
+	case AUDIT_GET_FEATURE:
+	case AUDIT_SET_FEATURE:
 	case AUDIT_LIST_RULES:
 	case AUDIT_ADD_RULE:
 	case AUDIT_DEL_RULE:
@@ -627,6 +638,94 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
 	return rc;
 }
 
+int is_audit_feature_set(int i)
+{
+	return af.features & AUDIT_FEATURE_TO_MASK(i);
+}
+
+
+static int audit_get_feature(struct sk_buff *skb)
+{
+	u32 seq;
+
+	seq = nlmsg_hdr(skb)->nlmsg_seq;
+
+	audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
+			 &af, sizeof(af));
+
+	return 0;
+}
+
+static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature,
+				     u32 old_lock, u32 new_lock, int res)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+	audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d",
+			 audit_feature_names[which], !!old_feature, !!new_feature,
+			 !!old_lock, !!new_lock, res);
+	audit_log_end(ab);
+}
+
+static int audit_set_feature(struct sk_buff *skb)
+{
+	struct audit_features *uaf;
+	int i;
+
+	BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > sizeof(audit_feature_names)/sizeof(audit_feature_names[0]));
+	uaf = nlmsg_data(nlmsg_hdr(skb));
+
+	/* if there is ever a version 2 we should handle that here */
+
+	for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+		u32 feature = AUDIT_FEATURE_TO_MASK(i);
+		u32 old_feature, new_feature, old_lock, new_lock;
+
+		/* if we are not changing this feature, move along */
+		if (!(feature & uaf->mask))
+			continue;
+
+		old_feature = af.features & feature;
+		new_feature = uaf->features & feature;
+		new_lock = (uaf->lock | af.lock) & feature;
+		old_lock = af.lock & feature;
+
+		/* are we changing a locked feature? */
+		if ((af.lock & feature) && (new_feature != old_feature)) {
+			audit_log_feature_change(i, old_feature, new_feature,
+						 old_lock, new_lock, 0);
+			return -EPERM;
+		}
+	}
+	/* nothing invalid, do the changes */
+	for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+		u32 feature = AUDIT_FEATURE_TO_MASK(i);
+		u32 old_feature, new_feature, old_lock, new_lock;
+
+		/* if we are not changing this feature, move along */
+		if (!(feature & uaf->mask))
+			continue;
+
+		old_feature = af.features & feature;
+		new_feature = uaf->features & feature;
+		old_lock = af.lock & feature;
+		new_lock = (uaf->lock | af.lock) & feature;
+
+		if (new_feature != old_feature)
+			audit_log_feature_change(i, old_feature, new_feature,
+						 old_lock, new_lock, 1);
+
+		if (new_feature)
+			af.features |= feature;
+		else
+			af.features &= ~feature;
+		af.lock |= new_lock;
+	}
+
+	return 0;
+}
+
 static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	u32			seq;
@@ -698,6 +797,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
 			err = audit_set_backlog_limit(status_get->backlog_limit);
 		break;
+	case AUDIT_GET_FEATURE:
+		err = audit_get_feature(skb);
+		if (err)
+			return err;
+		break;
+	case AUDIT_SET_FEATURE:
+		err = audit_set_feature(skb);
+		if (err)
+			return err;
+		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
-- 
cgit 


From d040e5af380554c23ffe0a034ae5f3e53da93a1d Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Fri, 24 May 2013 09:18:04 -0400
Subject: audit: audit feature to only allow unsetting the loginuid

This is a new audit feature which only grants processes with
CAP_AUDIT_CONTROL the ability to unset their loginuid.  They cannot
directly set it from a valid uid to another valid uid.  The ability to
unset the loginuid is nice because a priviledged task, like that of
container creation, can unset the loginuid and then priv is not needed
inside the container when a login daemon needs to set the loginuid.

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/uapi/linux/audit.h | 3 ++-
 kernel/audit.c             | 3 ++-
 kernel/auditsc.c           | 3 +++
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 9eddf2ca614f..05e5e8fc2ac4 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -386,7 +386,8 @@ struct audit_features {
 	__u32	lock;		/* which features to lock */
 };
 
-#define AUDIT_LAST_FEATURE	-1
+#define AUDIT_FEATURE_ONLY_UNSET_LOGINUID	0
+#define AUDIT_LAST_FEATURE			AUDIT_FEATURE_ONLY_UNSET_LOGINUID
 
 #define audit_feature_valid(x)		((x) >= 0 && (x) <= AUDIT_LAST_FEATURE)
 #define AUDIT_FEATURE_TO_MASK(x)	(1 << ((x) & 31)) /* mask for __u32 */
diff --git a/kernel/audit.c b/kernel/audit.c
index 29ee6a421c6c..fbfa3a74decb 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -144,7 +144,8 @@ static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
 				   .features = 0,
 				   .lock = 0,};
 
-static char *audit_feature_names[0] = {
+static char *audit_feature_names[1] = {
+	"only_unset_loginuid",
 };
 
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c75d7813aef2..924c0bf048d2 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1974,6 +1974,9 @@ static int audit_set_loginuid_perm(kuid_t loginuid)
 	/* it is set, you need permission */
 	if (!capable(CAP_AUDIT_CONTROL))
 		return -EPERM;
+	/* reject if this is not an unset and we don't allow that */
+	if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid))
+		return -EPERM;
 	return 0;
 }
 
-- 
cgit 


From 21b85c31d23f2047d47e1f74bfa5caa8b75c1c77 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Thu, 23 May 2013 14:26:00 -0400
Subject: audit: audit feature to set loginuid immutable

This adds a new 'audit_feature' bit which allows userspace to set it
such that the loginuid is absolutely immutable, even if you have
CAP_AUDIT_CONTROL.

Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/uapi/linux/audit.h | 3 ++-
 kernel/audit.c             | 3 ++-
 kernel/auditsc.c           | 3 +++
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 05e5e8fc2ac4..e2f0d9977131 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -387,7 +387,8 @@ struct audit_features {
 };
 
 #define AUDIT_FEATURE_ONLY_UNSET_LOGINUID	0
-#define AUDIT_LAST_FEATURE			AUDIT_FEATURE_ONLY_UNSET_LOGINUID
+#define AUDIT_FEATURE_LOGINUID_IMMUTABLE	1
+#define AUDIT_LAST_FEATURE			AUDIT_FEATURE_LOGINUID_IMMUTABLE
 
 #define audit_feature_valid(x)		((x) >= 0 && (x) <= AUDIT_LAST_FEATURE)
 #define AUDIT_FEATURE_TO_MASK(x)	(1 << ((x) & 31)) /* mask for __u32 */
diff --git a/kernel/audit.c b/kernel/audit.c
index fbfa3a74decb..f3f36f5eb4ae 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -144,8 +144,9 @@ static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
 				   .features = 0,
 				   .lock = 0,};
 
-static char *audit_feature_names[1] = {
+static char *audit_feature_names[2] = {
 	"only_unset_loginuid",
+	"loginuid_immutable",
 };
 
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 924c0bf048d2..63223d671a6e 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1971,6 +1971,9 @@ static int audit_set_loginuid_perm(kuid_t loginuid)
 	/* if we are unset, we don't need privs */
 	if (!audit_loginuid_set(current))
 		return 0;
+	/* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
+	if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
+		return -EPERM;
 	/* it is set, you need permission */
 	if (!capable(CAP_AUDIT_CONTROL))
 		return -EPERM;
-- 
cgit 


From d9cfea91e97d5d19f9d69beaa844f5fe56a6adc6 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Wed, 30 Oct 2013 17:56:13 -0400
Subject: audit: move audit_aux_data_execve contents into audit_context union

audit_bprm() was being called to add an AUDIT_EXECVE record to the audit
context every time search_binary_handler() was recursively called.  Only one
reference is necessary, so just update it.  Move the the contents of
audit_aux_data_execve into the union in audit_context, removing dependence on a
kmalloc along the way.

Reported-by: Oleg Nesterov <onestero@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h |  4 ++--
 kernel/audit.h        |  4 ++++
 kernel/auditsc.c      | 41 ++++++++++++-----------------------------
 3 files changed, 18 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 7b31bec9bccb..08b38bf13eb9 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -209,7 +209,7 @@ static inline int audit_get_sessionid(struct task_struct *tsk)
 
 extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
 extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode);
-extern int __audit_bprm(struct linux_binprm *bprm);
+extern void __audit_bprm(struct linux_binprm *bprm);
 extern int __audit_socketcall(int nargs, unsigned long *args);
 extern int __audit_sockaddr(int len, void *addr);
 extern void __audit_fd_pair(int fd1, int fd2);
@@ -241,7 +241,7 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid
 static inline int audit_bprm(struct linux_binprm *bprm)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_bprm(bprm);
+		__audit_bprm(bprm);
 	return 0;
 }
 static inline int audit_socketcall(int nargs, unsigned long *args)
diff --git a/kernel/audit.h b/kernel/audit.h
index 123c9b7c3979..e7b94ab66c49 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -197,6 +197,10 @@ struct audit_context {
 			int			fd;
 			int			flags;
 		} mmap;
+		struct {
+			int			argc;
+			struct mm_struct	*mm;
+		} execve;
 	};
 	int fds[2];
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 11078f32d13e..425a8939be1a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -95,12 +95,6 @@ struct audit_aux_data {
 /* Number of target pids per aux struct. */
 #define AUDIT_AUX_PIDS	16
 
-struct audit_aux_data_execve {
-	struct audit_aux_data	d;
-	int argc;
-	struct mm_struct *mm;
-};
-
 struct audit_aux_data_pids {
 	struct audit_aux_data	d;
 	pid_t			target_pid[AUDIT_AUX_PIDS];
@@ -1144,20 +1138,19 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 }
 
 static void audit_log_execve_info(struct audit_context *context,
-				  struct audit_buffer **ab,
-				  struct audit_aux_data_execve *axi)
+				  struct audit_buffer **ab)
 {
 	int i, len;
 	size_t len_sent = 0;
 	const char __user *p;
 	char *buf;
 
-	if (axi->mm != current->mm)
+	if (context->execve.mm != current->mm)
 		return; /* execve failed, no additional info */
 
-	p = (const char __user *)axi->mm->arg_start;
+	p = (const char __user *)current->mm->arg_start;
 
-	audit_log_format(*ab, "argc=%d", axi->argc);
+	audit_log_format(*ab, "argc=%d", context->execve.argc);
 
 	/*
 	 * we need some kernel buffer to hold the userspace args.  Just
@@ -1171,7 +1164,7 @@ static void audit_log_execve_info(struct audit_context *context,
 		return;
 	}
 
-	for (i = 0; i < axi->argc; i++) {
+	for (i = 0; i < context->execve.argc; i++) {
 		len = audit_log_single_execve_arg(context, ab, i,
 						  &len_sent, p, buf);
 		if (len <= 0)
@@ -1274,6 +1267,9 @@ static void show_special(struct audit_context *context, int *call_panic)
 		audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
 				 context->mmap.flags);
 		break; }
+	case AUDIT_EXECVE: {
+		audit_log_execve_info(context, &ab);
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -1320,11 +1316,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 
 		switch (aux->type) {
 
-		case AUDIT_EXECVE: {
-			struct audit_aux_data_execve *axi = (void *)aux;
-			audit_log_execve_info(context, &ab, axi);
-			break; }
-
 		case AUDIT_BPRM_FCAPS: {
 			struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
 			audit_log_format(ab, "fver=%x", axs->fcap_ver);
@@ -2147,21 +2138,13 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo
 	context->ipc.has_perm = 1;
 }
 
-int __audit_bprm(struct linux_binprm *bprm)
+void __audit_bprm(struct linux_binprm *bprm)
 {
-	struct audit_aux_data_execve *ax;
 	struct audit_context *context = current->audit_context;
 
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->argc = bprm->argc;
-	ax->mm = bprm->mm;
-	ax->d.type = AUDIT_EXECVE;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_EXECVE;
+	context->execve.argc = bprm->argc;
+	context->execve.mm = bprm->mm;
 }
 
 
-- 
cgit 


From 9410d228a4cf434305306746bb799fb7acdd8648 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Wed, 30 Oct 2013 18:05:24 -0400
Subject: audit: call audit_bprm() only once to add AUDIT_EXECVE information

Move the audit_bprm() call from search_binary_handler() to exec_binprm().  This
allows us to get rid of the mm member of struct audit_aux_data_execve since
bprm->mm will equal current->mm.

This also mitigates the issue that ->argc could be modified by the
load_binary() call in search_binary_handler().

audit_bprm() was being called to add an AUDIT_EXECVE record to the audit
context every time search_binary_handler() was recursively called.  Only one
reference is necessary.

Reported-by: Oleg Nesterov <onestero@redhat.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
This patch is against 3.11, but was developed on Oleg's post-3.11 patches that
introduce exec_binprm().
---
 fs/exec.c             | 5 +----
 include/linux/audit.h | 9 +++------
 kernel/audit.h        | 1 -
 kernel/auditsc.c      | 4 ----
 4 files changed, 4 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index fd774c7cb483..c5c24f2fc44a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1383,10 +1383,6 @@ int search_binary_handler(struct linux_binprm *bprm)
 	if (retval)
 		return retval;
 
-	retval = audit_bprm(bprm);
-	if (retval)
-		return retval;
-
 	/* Need to fetch pid before load_binary changes it */
 	old_pid = current->pid;
 	rcu_read_lock();
@@ -1408,6 +1404,7 @@ int search_binary_handler(struct linux_binprm *bprm)
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
 				if (depth == 0) {
+					audit_bprm(bprm);
 					trace_sched_process_exec(current, old_pid, bprm);
 					ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
 				}
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 08b38bf13eb9..a40641954c29 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -238,11 +238,10 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid
 	if (unlikely(!audit_dummy_context()))
 		__audit_ipc_set_perm(qbytes, uid, gid, mode);
 }
-static inline int audit_bprm(struct linux_binprm *bprm)
+static inline void audit_bprm(struct linux_binprm *bprm)
 {
 	if (unlikely(!audit_dummy_context()))
 		__audit_bprm(bprm);
-	return 0;
 }
 static inline int audit_socketcall(int nargs, unsigned long *args)
 {
@@ -369,10 +368,8 @@ static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid,
 					gid_t gid, umode_t mode)
 { }
-static inline int audit_bprm(struct linux_binprm *bprm)
-{
-	return 0;
-}
+static inline void audit_bprm(struct linux_binprm *bprm)
+{ }
 static inline int audit_socketcall(int nargs, unsigned long *args)
 {
 	return 0;
diff --git a/kernel/audit.h b/kernel/audit.h
index e7b94ab66c49..b779642b29af 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -199,7 +199,6 @@ struct audit_context {
 		} mmap;
 		struct {
 			int			argc;
-			struct mm_struct	*mm;
 		} execve;
 	};
 	int fds[2];
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 425a8939be1a..dfc5d6745ee5 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1145,9 +1145,6 @@ static void audit_log_execve_info(struct audit_context *context,
 	const char __user *p;
 	char *buf;
 
-	if (context->execve.mm != current->mm)
-		return; /* execve failed, no additional info */
-
 	p = (const char __user *)current->mm->arg_start;
 
 	audit_log_format(*ab, "argc=%d", context->execve.argc);
@@ -2144,7 +2141,6 @@ void __audit_bprm(struct linux_binprm *bprm)
 
 	context->type = AUDIT_EXECVE;
 	context->execve.argc = bprm->argc;
-	context->execve.mm = bprm->mm;
 }
 
 
-- 
cgit 


From 2f69702c4db5f1c3149fd17fe30bdeb87cba9698 Mon Sep 17 00:00:00 2001
From: Enrico Mioso <mrkiko.rs@gmail.com>
Date: Mon, 4 Nov 2013 09:50:47 +0100
Subject: net: cdc_ncm: Export cdc_ncm_{tx, rx}_fixup functions for re-use
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some drivers implementing NCM-like protocols, may re-use those functions, as is
the case in the huawei_cdc_ncm driver.
Export them via EXPORT_SYMBOL_GPL, in accordance with how other functions have
been exported.

Signed-off-by: Enrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 6 ++++--
 include/linux/usb/cdc_ncm.h | 3 +++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 11c703337577..1763195bd599 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -830,7 +830,7 @@ static void cdc_ncm_txpath_bh(unsigned long param)
 	}
 }
 
-static struct sk_buff *
+struct sk_buff *
 cdc_ncm_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 {
 	struct sk_buff *skb_out;
@@ -857,6 +857,7 @@ error:
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_tx_fixup);
 
 /* verify NTB header and return offset of first NDP, or negative error */
 int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in)
@@ -943,7 +944,7 @@ error:
 }
 EXPORT_SYMBOL_GPL(cdc_ncm_rx_verify_ndp16);
 
-static int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
+int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
 {
 	struct sk_buff *skb;
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
@@ -1019,6 +1020,7 @@ err_ndp:
 error:
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cdc_ncm_rx_fixup);
 
 static void
 cdc_ncm_speed_change(struct usbnet *dev,
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 2300f7492927..c3fa80745996 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -125,5 +125,8 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
 int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
 int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset);
+struct sk_buff *
+cdc_ncm_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags);
+int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in);
 
 #endif /* __LINUX_USB_CDC_NCM_H */
-- 
cgit 


From f306cc82a93d6b19f01634b80c580b9755c8b7cc Mon Sep 17 00:00:00 2001
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Thu, 24 Oct 2013 08:34:17 -0500
Subject: tracing: Update event filters for multibuffer

The trace event filters are still tied to event calls rather than
event files, which means you don't get what you'd expect when using
filters in the multibuffer case:

Before:

  # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # mkdir /sys/kernel/debug/tracing/instances/test1
  # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 2048
  # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  bytes_alloc > 2048

Setting the filter in tracing/instances/test1/events shouldn't affect
the same event in tracing/events as it does above.

After:

  # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # mkdir /sys/kernel/debug/tracing/instances/test1
  # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  bytes_alloc > 2048

We'd like to just move the filter directly from ftrace_event_call to
ftrace_event_file, but there are a couple cases that don't yet have
multibuffer support and therefore have to continue using the current
event_call-based filters.  For those cases, a new USE_CALL_FILTER bit
is added to the event_call flags, whose main purpose is to keep the
old behavior for those cases until they can be updated with
multibuffer support; at that point, the USE_CALL_FILTER flag (and the
new associated call_filter_check_discard() function) can go away.

The multibuffer support also made filter_current_check_discard()
redundant, so this change removes that function as well and replaces
it with filter_check_discard() (or call_filter_check_discard() as
appropriate).

Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h         |  25 +++-
 include/linux/syscalls.h             |   4 +-
 include/trace/ftrace.h               |   7 +-
 kernel/trace/trace.c                 |  40 +++++--
 kernel/trace/trace.h                 |  18 +--
 kernel/trace/trace_branch.c          |   2 +-
 kernel/trace/trace_events.c          |  23 ++--
 kernel/trace/trace_events_filter.c   | 218 ++++++++++++++++++++++++++++-------
 kernel/trace/trace_export.c          |   2 +-
 kernel/trace/trace_functions_graph.c |   4 +-
 kernel/trace/trace_kprobe.c          |   4 +-
 kernel/trace/trace_mmiotrace.c       |   4 +-
 kernel/trace/trace_sched_switch.c    |   4 +-
 kernel/trace/trace_syscalls.c        |   8 +-
 kernel/trace/trace_uprobe.c          |   3 +-
 15 files changed, 264 insertions(+), 102 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 5eaa746735ff..9abbe630c456 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -202,6 +202,7 @@ enum {
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
 	TRACE_EVENT_FL_WAS_ENABLED_BIT,
+	TRACE_EVENT_FL_USE_CALL_FILTER_BIT,
 };
 
 /*
@@ -213,6 +214,7 @@ enum {
  *  WAS_ENABLED   - Set and stays set when an event was ever enabled
  *                    (used for module unloading, if a module event is enabled,
  *                     it is best to clear the buffers that used it).
+ *  USE_CALL_FILTER - For ftrace internal events, don't use file filter
  */
 enum {
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
@@ -220,6 +222,7 @@ enum {
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
 	TRACE_EVENT_FL_WAS_ENABLED	= (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT),
+	TRACE_EVENT_FL_USE_CALL_FILTER	= (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT),
 };
 
 struct ftrace_event_call {
@@ -238,6 +241,7 @@ struct ftrace_event_call {
 	 *   bit 2:		failed to apply filter
 	 *   bit 3:		ftrace internal event (do not enable)
 	 *   bit 4:		Event was enabled by module
+	 *   bit 5:		use call filter rather than file filter
 	 */
 	int			flags; /* static flags of different events */
 
@@ -253,6 +257,8 @@ struct ftrace_subsystem_dir;
 enum {
 	FTRACE_EVENT_FL_ENABLED_BIT,
 	FTRACE_EVENT_FL_RECORDED_CMD_BIT,
+	FTRACE_EVENT_FL_FILTERED_BIT,
+	FTRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	FTRACE_EVENT_FL_SOFT_MODE_BIT,
 	FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
 };
@@ -261,6 +267,8 @@ enum {
  * Ftrace event file flags:
  *  ENABLED	  - The event is enabled
  *  RECORDED_CMD  - The comms should be recorded at sched_switch
+ *  FILTERED	  - The event has a filter attached
+ *  NO_SET_FILTER - Set when filter has error and is to be ignored
  *  SOFT_MODE     - The event is enabled/disabled by SOFT_DISABLED
  *  SOFT_DISABLED - When set, do not trace the event (even though its
  *                   tracepoint may be enabled)
@@ -268,6 +276,8 @@ enum {
 enum {
 	FTRACE_EVENT_FL_ENABLED		= (1 << FTRACE_EVENT_FL_ENABLED_BIT),
 	FTRACE_EVENT_FL_RECORDED_CMD	= (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT),
+	FTRACE_EVENT_FL_FILTERED	= (1 << FTRACE_EVENT_FL_FILTERED_BIT),
+	FTRACE_EVENT_FL_NO_SET_FILTER	= (1 << FTRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	FTRACE_EVENT_FL_SOFT_MODE	= (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT),
 	FTRACE_EVENT_FL_SOFT_DISABLED	= (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT),
 };
@@ -275,6 +285,7 @@ enum {
 struct ftrace_event_file {
 	struct list_head		list;
 	struct ftrace_event_call	*event_call;
+	struct event_filter		*filter;
 	struct dentry			*dir;
 	struct trace_array		*tr;
 	struct ftrace_subsystem_dir	*system;
@@ -310,12 +321,16 @@ struct ftrace_event_file {
 
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
-extern void destroy_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_file *file);
+extern void destroy_call_preds(struct ftrace_event_call *call);
 extern int filter_match_preds(struct event_filter *filter, void *rec);
-extern int filter_current_check_discard(struct ring_buffer *buffer,
-					struct ftrace_event_call *call,
-					void *rec,
-					struct ring_buffer_event *event);
+
+extern int filter_check_discard(struct ftrace_event_file *file, void *rec,
+				struct ring_buffer *buffer,
+				struct ring_buffer_event *event);
+extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
+				     struct ring_buffer *buffer,
+				     struct ring_buffer_event *event);
 
 enum {
 	FILTER_OTHER = 0,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7fac04e7ff6e..10bafa97049d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -120,7 +120,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
+		.flags			= TRACE_EVENT_FL_CAP_ANY | TRACE_EVENT_FL_USE_CALL_FILTER,\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -134,7 +134,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		.flags			= TRACE_EVENT_FL_CAP_ANY,	\
+		.flags			= TRACE_EVENT_FL_CAP_ANY | TRACE_EVENT_FL_USE_CALL_FILTER,\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 5c7ab17cbb02..52594b20179e 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -437,9 +437,8 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *	{ <assign>; }  <-- Here we assign the entries by the __field and
  *			   __array macros.
  *
- *	if (!filter_current_check_discard(buffer, event_call, entry, event))
- *		trace_nowake_buffer_unlock_commit(buffer,
- *						   event, irq_flags, pc);
+ *	if (!filter_check_discard(ftrace_file, entry, buffer, event))
+ *		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
  * }
  *
  * static struct trace_event ftrace_event_type_<call> = {
@@ -553,7 +552,7 @@ ftrace_raw_event_##call(void *__data, proto)				\
 									\
 	{ assign; }							\
 									\
-	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+	if (!filter_check_discard(ftrace_file, entry, buffer, event))	\
 		trace_buffer_unlock_commit(buffer, event, irq_flags, pc); \
 }
 /*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 063a92bad578..489da8b19f30 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -235,13 +235,33 @@ void trace_array_put(struct trace_array *this_tr)
 	mutex_unlock(&trace_types_lock);
 }
 
-int filter_current_check_discard(struct ring_buffer *buffer,
-				 struct ftrace_event_call *call, void *rec,
-				 struct ring_buffer_event *event)
+int filter_check_discard(struct ftrace_event_file *file, void *rec,
+			 struct ring_buffer *buffer,
+			 struct ring_buffer_event *event)
 {
-	return filter_check_discard(call, rec, buffer, event);
+	if (unlikely(file->flags & FTRACE_EVENT_FL_FILTERED) &&
+	    !filter_match_preds(file->filter, rec)) {
+		ring_buffer_discard_commit(buffer, event);
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(filter_check_discard);
+
+int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
+			      struct ring_buffer *buffer,
+			      struct ring_buffer_event *event)
+{
+	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
+	    !filter_match_preds(call->filter, rec)) {
+		ring_buffer_discard_commit(buffer, event);
+		return 1;
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(filter_current_check_discard);
+EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
 cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
@@ -1633,7 +1653,7 @@ trace_function(struct trace_array *tr,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 }
 
@@ -1717,7 +1737,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 
 	entry->size = trace.nr_entries;
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
  out:
@@ -1819,7 +1839,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
  out_drop_count:
@@ -2011,7 +2031,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, buffer, event)) {
+	if (!call_filter_check_discard(call, entry, buffer, event)) {
 		__buffer_unlock_commit(buffer, event);
 		ftrace_trace_stack(buffer, flags, 6, pc);
 	}
@@ -2066,7 +2086,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
 
 	memcpy(&entry->buf, tbuffer, len);
 	entry->buf[len] = '\0';
-	if (!filter_check_discard(call, entry, buffer, event)) {
+	if (!call_filter_check_discard(call, entry, buffer, event)) {
 		__buffer_unlock_commit(buffer, event);
 		ftrace_trace_stack(buffer, flags, 6, pc);
 	}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d1cf5159bec0..12d1a612a73e 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1007,9 +1007,9 @@ struct filter_pred {
 
 extern enum regex_type
 filter_parse_regex(char *buff, int len, char **search, int *not);
-extern void print_event_filter(struct ftrace_event_call *call,
+extern void print_event_filter(struct ftrace_event_file *file,
 			       struct trace_seq *s);
-extern int apply_event_filter(struct ftrace_event_call *call,
+extern int apply_event_filter(struct ftrace_event_file *file,
 			      char *filter_string);
 extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 					char *filter_string);
@@ -1020,20 +1020,6 @@ extern int filter_assign_type(const char *type);
 struct ftrace_event_field *
 trace_find_event_field(struct ftrace_event_call *call, char *name);
 
-static inline int
-filter_check_discard(struct ftrace_event_call *call, void *rec,
-		     struct ring_buffer *buffer,
-		     struct ring_buffer_event *event)
-{
-	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
-	    !filter_match_preds(call->filter, rec)) {
-		ring_buffer_discard_commit(buffer, event);
-		return 1;
-	}
-
-	return 0;
-}
-
 extern void trace_event_enable_cmd_record(bool enable);
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index d594da0dc03c..697fb9bac8f0 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -78,7 +78,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
 	entry->line = f->line;
 	entry->correct = val == expect;
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
  out:
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 368a4d50cc30..043f833246a0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -989,7 +989,7 @@ static ssize_t
 event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
 	struct trace_seq *s;
 	int r = -ENODEV;
 
@@ -1004,12 +1004,12 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 	trace_seq_init(s);
 
 	mutex_lock(&event_mutex);
-	call = event_file_data(filp);
-	if (call)
-		print_event_filter(call, s);
+	file = event_file_data(filp);
+	if (file)
+		print_event_filter(file, s);
 	mutex_unlock(&event_mutex);
 
-	if (call)
+	if (file)
 		r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -1021,7 +1021,7 @@ static ssize_t
 event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_file *file;
 	char *buf;
 	int err = -ENODEV;
 
@@ -1039,9 +1039,9 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	buf[cnt] = '\0';
 
 	mutex_lock(&event_mutex);
-	call = event_file_data(filp);
-	if (call)
-		err = apply_event_filter(call, buf);
+	file = event_file_data(filp);
+	if (file)
+		err = apply_event_filter(file, buf);
 	mutex_unlock(&event_mutex);
 
 	free_page((unsigned long) buf);
@@ -1539,7 +1539,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 			return -1;
 		}
 	}
-	trace_create_file("filter", 0644, file->dir, call,
+	trace_create_file("filter", 0644, file->dir, file,
 			  &ftrace_event_filter_fops);
 
 	trace_create_file("format", 0444, file->dir, call,
@@ -1577,6 +1577,7 @@ static void event_remove(struct ftrace_event_call *call)
 		if (file->event_call != call)
 			continue;
 		ftrace_event_enable_disable(file, 0);
+		destroy_preds(file);
 		/*
 		 * The do_for_each_event_file() is
 		 * a double loop. After finding the call for this
@@ -1700,7 +1701,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
 	event_remove(call);
 	trace_destroy_fields(call);
-	destroy_preds(call);
+	destroy_call_preds(call);
 }
 
 static int probe_remove_event_call(struct ftrace_event_call *call)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 97daa8cf958d..2468f56dc5db 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -637,10 +637,18 @@ static void append_filter_err(struct filter_parse_state *ps,
 	free_page((unsigned long) buf);
 }
 
+static inline struct event_filter *event_filter(struct ftrace_event_file *file)
+{
+	if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		return file->event_call->filter;
+	else
+		return file->filter;
+}
+
 /* caller must hold event_mutex */
-void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
+void print_event_filter(struct ftrace_event_file *file, struct trace_seq *s)
 {
-	struct event_filter *filter = call->filter;
+	struct event_filter *filter = event_filter(file);
 
 	if (filter && filter->filter_string)
 		trace_seq_printf(s, "%s\n", filter->filter_string);
@@ -766,11 +774,21 @@ static void __free_preds(struct event_filter *filter)
 	filter->n_preds = 0;
 }
 
-static void filter_disable(struct ftrace_event_call *call)
+static void call_filter_disable(struct ftrace_event_call *call)
 {
 	call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
+static void filter_disable(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		call_filter_disable(call);
+	else
+		file->flags &= ~FTRACE_EVENT_FL_FILTERED;
+}
+
 static void __free_filter(struct event_filter *filter)
 {
 	if (!filter)
@@ -781,16 +799,30 @@ static void __free_filter(struct event_filter *filter)
 	kfree(filter);
 }
 
+void destroy_call_preds(struct ftrace_event_call *call)
+{
+	__free_filter(call->filter);
+	call->filter = NULL;
+}
+
+static void destroy_file_preds(struct ftrace_event_file *file)
+{
+	__free_filter(file->filter);
+	file->filter = NULL;
+}
+
 /*
- * Called when destroying the ftrace_event_call.
- * The call is being freed, so we do not need to worry about
- * the call being currently used. This is for module code removing
+ * Called when destroying the ftrace_event_file.
+ * The file is being freed, so we do not need to worry about
+ * the file being currently used. This is for module code removing
  * the tracepoints from within it.
  */
-void destroy_preds(struct ftrace_event_call *call)
+void destroy_preds(struct ftrace_event_file *file)
 {
-	__free_filter(call->filter);
-	call->filter = NULL;
+	if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		destroy_call_preds(file->event_call);
+	else
+		destroy_file_preds(file);
 }
 
 static struct event_filter *__alloc_filter(void)
@@ -825,28 +857,56 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)
 	return 0;
 }
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static inline void __remove_filter(struct ftrace_event_file *file)
 {
+	struct ftrace_event_call *call = file->event_call;
+
+	filter_disable(file);
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		remove_filter_string(call->filter);
+	else
+		remove_filter_string(file->filter);
+}
+
+static void filter_free_subsystem_preds(struct event_subsystem *system,
+					struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
+		call = file->event_call;
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		filter_disable(call);
-		remove_filter_string(call->filter);
+		__remove_filter(file);
 	}
 }
 
-static void filter_free_subsystem_filters(struct event_subsystem *system)
+static inline void __free_subsystem_filter(struct ftrace_event_file *file)
 {
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) {
+		__free_filter(call->filter);
+		call->filter = NULL;
+	} else {
+		__free_filter(file->filter);
+		file->filter = NULL;
+	}
+}
+
+static void filter_free_subsystem_filters(struct event_subsystem *system,
+					  struct trace_array *tr)
+{
+	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
+		call = file->event_call;
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
-		__free_filter(call->filter);
-		call->filter = NULL;
+		__free_subsystem_filter(file);
 	}
 }
 
@@ -1617,15 +1677,85 @@ fail:
 	return err;
 }
 
+static inline void event_set_filtered_flag(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		call->flags |= TRACE_EVENT_FL_FILTERED;
+	else
+		file->flags |= FTRACE_EVENT_FL_FILTERED;
+}
+
+static inline void event_set_filter(struct ftrace_event_file *file,
+				    struct event_filter *filter)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		rcu_assign_pointer(call->filter, filter);
+	else
+		rcu_assign_pointer(file->filter, filter);
+}
+
+static inline void event_clear_filter(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		RCU_INIT_POINTER(call->filter, NULL);
+	else
+		RCU_INIT_POINTER(file->filter, NULL);
+}
+
+static inline void
+event_set_no_set_filter_flag(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+	else
+		file->flags |= FTRACE_EVENT_FL_NO_SET_FILTER;
+}
+
+static inline void
+event_clear_no_set_filter_flag(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
+		call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
+	else
+		file->flags &= ~FTRACE_EVENT_FL_NO_SET_FILTER;
+}
+
+static inline bool
+event_no_set_filter_flag(struct ftrace_event_file *file)
+{
+	struct ftrace_event_call *call = file->event_call;
+
+	if (file->flags & FTRACE_EVENT_FL_NO_SET_FILTER)
+		return true;
+
+	if ((call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) &&
+	    (call->flags & TRACE_EVENT_FL_NO_SET_FILTER))
+		return true;
+
+	return false;
+}
+
 struct filter_list {
 	struct list_head	list;
 	struct event_filter	*filter;
 };
 
 static int replace_system_preds(struct event_subsystem *system,
+				struct trace_array *tr,
 				struct filter_parse_state *ps,
 				char *filter_string)
 {
+	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
 	struct filter_list *filter_item;
 	struct filter_list *tmp;
@@ -1633,8 +1763,8 @@ static int replace_system_preds(struct event_subsystem *system,
 	bool fail = true;
 	int err;
 
-	list_for_each_entry(call, &ftrace_events, list) {
-
+	list_for_each_entry(file, &tr->events, list) {
+		call = file->event_call;
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
@@ -1644,18 +1774,20 @@ static int replace_system_preds(struct event_subsystem *system,
 		 */
 		err = replace_preds(call, NULL, ps, filter_string, true);
 		if (err)
-			call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+			event_set_no_set_filter_flag(file);
 		else
-			call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
+			event_clear_no_set_filter_flag(file);
 	}
 
-	list_for_each_entry(call, &ftrace_events, list) {
+	list_for_each_entry(file, &tr->events, list) {
 		struct event_filter *filter;
 
+		call = file->event_call;
+
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-		if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+		if (event_no_set_filter_flag(file))
 			continue;
 
 		filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
@@ -1676,17 +1808,17 @@ static int replace_system_preds(struct event_subsystem *system,
 
 		err = replace_preds(call, filter, ps, filter_string, false);
 		if (err) {
-			filter_disable(call);
+			filter_disable(file);
 			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
 			append_filter_err(ps, filter);
 		} else
-			call->flags |= TRACE_EVENT_FL_FILTERED;
+			event_set_filtered_flag(file);
 		/*
 		 * Regardless of if this returned an error, we still
 		 * replace the filter for the call.
 		 */
-		filter = call->filter;
-		rcu_assign_pointer(call->filter, filter_item->filter);
+		filter = event_filter(file);
+		event_set_filter(file, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1816,6 +1948,7 @@ static int create_filter(struct ftrace_event_call *call,
  * and always remembers @filter_str.
  */
 static int create_system_filter(struct event_subsystem *system,
+				struct trace_array *tr,
 				char *filter_str, struct event_filter **filterp)
 {
 	struct event_filter *filter = NULL;
@@ -1824,7 +1957,7 @@ static int create_system_filter(struct event_subsystem *system,
 
 	err = create_filter_start(filter_str, true, &ps, &filter);
 	if (!err) {
-		err = replace_system_preds(system, ps, filter_str);
+		err = replace_system_preds(system, tr, ps, filter_str);
 		if (!err) {
 			/* System filters just show a default message */
 			kfree(filter->filter_string);
@@ -1840,20 +1973,25 @@ static int create_system_filter(struct event_subsystem *system,
 }
 
 /* caller must hold event_mutex */
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+int apply_event_filter(struct ftrace_event_file *file, char *filter_string)
 {
+	struct ftrace_event_call *call = file->event_call;
 	struct event_filter *filter;
 	int err;
 
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_disable(call);
-		filter = call->filter;
+		filter_disable(file);
+		filter = event_filter(file);
+
 		if (!filter)
 			return 0;
-		RCU_INIT_POINTER(call->filter, NULL);
+
+		event_clear_filter(file);
+
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
+
 		return 0;
 	}
 
@@ -1866,14 +2004,15 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 	 * string
 	 */
 	if (filter) {
-		struct event_filter *tmp = call->filter;
+		struct event_filter *tmp;
 
+		tmp = event_filter(file);
 		if (!err)
-			call->flags |= TRACE_EVENT_FL_FILTERED;
+			event_set_filtered_flag(file);
 		else
-			filter_disable(call);
+			filter_disable(file);
 
-		rcu_assign_pointer(call->filter, filter);
+		event_set_filter(file, filter);
 
 		if (tmp) {
 			/* Make sure the call is done with the filter */
@@ -1889,6 +2028,7 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 				 char *filter_string)
 {
 	struct event_subsystem *system = dir->subsystem;
+	struct trace_array *tr = dir->tr;
 	struct event_filter *filter;
 	int err = 0;
 
@@ -1901,18 +2041,18 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 	}
 
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_free_subsystem_preds(system);
+		filter_free_subsystem_preds(system, tr);
 		remove_filter_string(system->filter);
 		filter = system->filter;
 		system->filter = NULL;
 		/* Ensure all filters are no longer used */
 		synchronize_sched();
-		filter_free_subsystem_filters(system);
+		filter_free_subsystem_filters(system, tr);
 		__free_filter(filter);
 		goto out_unlock;
 	}
 
-	err = create_system_filter(system, filter_string, &filter);
+	err = create_system_filter(system, tr, filter_string, &filter);
 	if (filter) {
 		/*
 		 * No event actually uses the system filter
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d21a74670088..7c3e3e72e2b6 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -180,7 +180,7 @@ struct ftrace_event_call __used event_##call = {			\
 	.event.type		= etype,				\
 	.class			= &event_class_ftrace_##call,		\
 	.print_fmt		= print,				\
-	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE,		\
+	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \
 };									\
 struct ftrace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index e08c030b8f38..80387d1d27e1 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -270,7 +270,7 @@ int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	if (!filter_current_check_discard(buffer, call, entry, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
 	return 1;
@@ -385,7 +385,7 @@ void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	if (!filter_current_check_discard(buffer, call, entry, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 243f6834d026..dae9541ada9e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -835,7 +835,7 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 	entry->ip = (unsigned long)tp->rp.kp.addr;
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
-	if (!filter_current_check_discard(buffer, call, entry, event))
+	if (!filter_check_discard(ftrace_file, entry, buffer, event))
 		trace_buffer_unlock_commit_regs(buffer, event,
 						irq_flags, pc, regs);
 }
@@ -884,7 +884,7 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 	entry->ret_ip = (unsigned long)ri->ret_addr;
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
-	if (!filter_current_check_discard(buffer, call, entry, event))
+	if (!filter_check_discard(ftrace_file, entry, buffer, event))
 		trace_buffer_unlock_commit_regs(buffer, event,
 						irq_flags, pc, regs);
 }
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index b3dcfb2f0fef..0abd9b863474 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -323,7 +323,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
@@ -353,7 +353,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 4e98e3b257a3..3f34dc9b40f3 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -45,7 +45,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_state		= next->state;
 	entry->next_cpu	= task_cpu(next);
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
 
@@ -101,7 +101,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= wakee->state;
 	entry->next_cpu			= task_cpu(wakee);
 
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 559329d9bd2f..32644eece429 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -336,8 +336,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	if (!filter_current_check_discard(buffer, sys_data->enter_event,
-					  entry, event))
+	if (!call_filter_check_discard(sys_data->enter_event, entry,
+				       buffer, event))
 		trace_current_buffer_unlock_commit(buffer, event,
 						   irq_flags, pc);
 }
@@ -377,8 +377,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	if (!filter_current_check_discard(buffer, sys_data->exit_event,
-					  entry, event))
+	if (!call_filter_check_discard(sys_data->exit_event, entry,
+				       buffer, event))
 		trace_current_buffer_unlock_commit(buffer, event,
 						   irq_flags, pc);
 }
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 272261b5f94f..b6dcc42ef7f5 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -128,6 +128,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (is_ret)
 		tu->consumer.ret_handler = uretprobe_dispatcher;
 	init_trace_uprobe_filter(&tu->filter);
+	tu->call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
 	return tu;
 
 error:
@@ -561,7 +562,7 @@ static void uprobe_trace_print(struct trace_uprobe *tu,
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
-	if (!filter_current_check_discard(buffer, call, entry, event))
+	if (!call_filter_check_discard(call, entry, buffer, event))
 		trace_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-- 
cgit 


From 38de93abec8d8acd8d6dbbe9b0d92d6d5cdb3090 Mon Sep 17 00:00:00 2001
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Thu, 24 Oct 2013 08:34:18 -0500
Subject: tracing: Make register/unregister_ftrace_command __init

register/unregister_ftrace_command() are only ever called from __init
functions, so can themselves be made __init.

Also make register_snapshot_cmd() __init for the same reason.

Link: http://lkml.kernel.org/r/d4042c8cadb7ae6f843ac9a89a24e1c6a3099727.1382620672.git.tom.zanussi@linux.intel.com

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  4 ++--
 kernel/trace/ftrace.c  | 12 ++++++++++--
 kernel/trace/trace.c   |  4 ++--
 3 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ec85d48619e1..31ea4b428360 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -533,11 +533,11 @@ static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
-static inline int register_ftrace_command(struct ftrace_func_command *cmd)
+static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
 }
-static inline int unregister_ftrace_command(char *cmd_name)
+static inline __init int unregister_ftrace_command(char *cmd_name)
 {
 	return -EINVAL;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 080b7d41e17f..22fa55696760 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3307,7 +3307,11 @@ void unregister_ftrace_function_probe_all(char *glob)
 static LIST_HEAD(ftrace_commands);
 static DEFINE_MUTEX(ftrace_cmd_mutex);
 
-int register_ftrace_command(struct ftrace_func_command *cmd)
+/*
+ * Currently we only register ftrace commands from __init, so mark this
+ * __init too.
+ */
+__init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p;
 	int ret = 0;
@@ -3326,7 +3330,11 @@ int register_ftrace_command(struct ftrace_func_command *cmd)
 	return ret;
 }
 
-int unregister_ftrace_command(struct ftrace_func_command *cmd)
+/*
+ * Currently we only unregister ftrace commands from __init, so mark
+ * this __init too.
+ */
+__init int unregister_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p, *n;
 	int ret = -ENODEV;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 489da8b19f30..f9fa42b180e3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5477,12 +5477,12 @@ static struct ftrace_func_command ftrace_snapshot_cmd = {
 	.func			= ftrace_trace_snapshot_callback,
 };
 
-static int register_snapshot_cmd(void)
+static __init int register_snapshot_cmd(void)
 {
 	return register_ftrace_command(&ftrace_snapshot_cmd);
 }
 #else
-static inline int register_snapshot_cmd(void) { return 0; }
+static inline __init int register_snapshot_cmd(void) { return 0; }
 #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */
 
 struct dentry *tracing_init_dentry_tr(struct trace_array *tr)
-- 
cgit 


From d562aff93bfb530b0992141500a402d17081189d Mon Sep 17 00:00:00 2001
From: Tom Zanussi <tom.zanussi@linux.intel.com>
Date: Thu, 24 Oct 2013 08:34:19 -0500
Subject: tracing: Add support for SOFT_DISABLE to syscall events

The original SOFT_DISABLE patches didn't add support for soft disable
of syscall events; this adds it.

Add an array of ftrace_event_file pointers indexed by syscall number
to the trace array and remove the existing enabled bitmaps, which as a
result are now redundant.  The ftrace_event_file structs in turn
contain the soft disable flags we need for per-syscall soft disable
accounting.

Adding ftrace_event_files also means we can remove the USE_CALL_FILTER
bit, thus enabling multibuffer filter support for syscall events.

Link: http://lkml.kernel.org/r/6e72b566e85d8df8042f133efbc6c30e21fb017e.1382620672.git.tom.zanussi@linux.intel.com

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h      |  4 ++--
 kernel/trace/trace.h          |  4 ++--
 kernel/trace/trace_syscalls.c | 42 ++++++++++++++++++++++++++++++++----------
 3 files changed, 36 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 10bafa97049d..2ef31bfd620b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -120,7 +120,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		.flags			= TRACE_EVENT_FL_CAP_ANY | TRACE_EVENT_FL_USE_CALL_FILTER,\
+		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -134,7 +134,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		.flags			= TRACE_EVENT_FL_CAP_ANY | TRACE_EVENT_FL_USE_CALL_FILTER,\
+		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct ftrace_event_call __used				\
 	  __attribute__((section("_ftrace_events")))			\
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 12d1a612a73e..9c27cdadd71f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -192,8 +192,8 @@ struct trace_array {
 #ifdef CONFIG_FTRACE_SYSCALLS
 	int			sys_refcount_enter;
 	int			sys_refcount_exit;
-	DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
-	DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+	struct ftrace_event_file *enter_syscall_files[NR_syscalls];
+	struct ftrace_event_file *exit_syscall_files[NR_syscalls];
 #endif
 	int			stop_count;
 	int			clock_id;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 32644eece429..e4b6d11bdf78 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -302,6 +302,7 @@ static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
 static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 {
 	struct trace_array *tr = data;
+	struct ftrace_event_file *ftrace_file;
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
@@ -314,7 +315,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
+	ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
+	if (!ftrace_file)
+		return;
+
+	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -336,8 +343,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	if (!call_filter_check_discard(sys_data->enter_event, entry,
-				       buffer, event))
+	if (!filter_check_discard(ftrace_file, entry, buffer, event))
 		trace_current_buffer_unlock_commit(buffer, event,
 						   irq_flags, pc);
 }
@@ -345,6 +351,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 {
 	struct trace_array *tr = data;
+	struct ftrace_event_file *ftrace_file;
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
@@ -356,7 +363,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
+	ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
+	if (!ftrace_file)
+		return;
+
+	if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -377,8 +390,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	if (!call_filter_check_discard(sys_data->exit_event, entry,
-				       buffer, event))
+	if (!filter_check_discard(ftrace_file, entry, buffer, event))
 		trace_current_buffer_unlock_commit(buffer, event,
 						   irq_flags, pc);
 }
@@ -397,7 +409,7 @@ static int reg_event_syscall_enter(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_enter)
 		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
 	if (!ret) {
-		set_bit(num, tr->enabled_enter_syscalls);
+		rcu_assign_pointer(tr->enter_syscall_files[num], file);
 		tr->sys_refcount_enter++;
 	}
 	mutex_unlock(&syscall_trace_lock);
@@ -415,10 +427,15 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
 		return;
 	mutex_lock(&syscall_trace_lock);
 	tr->sys_refcount_enter--;
-	clear_bit(num, tr->enabled_enter_syscalls);
+	rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
 	if (!tr->sys_refcount_enter)
 		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
+	/*
+	 * Callers expect the event to be completely disabled on
+	 * return, so wait for current handlers to finish.
+	 */
+	synchronize_sched();
 }
 
 static int reg_event_syscall_exit(struct ftrace_event_file *file,
@@ -435,7 +452,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_exit)
 		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
 	if (!ret) {
-		set_bit(num, tr->enabled_exit_syscalls);
+		rcu_assign_pointer(tr->exit_syscall_files[num], file);
 		tr->sys_refcount_exit++;
 	}
 	mutex_unlock(&syscall_trace_lock);
@@ -453,10 +470,15 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
 		return;
 	mutex_lock(&syscall_trace_lock);
 	tr->sys_refcount_exit--;
-	clear_bit(num, tr->enabled_exit_syscalls);
+	rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
 	if (!tr->sys_refcount_exit)
 		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
+	/*
+	 * Callers expect the event to be completely disabled on
+	 * return, so wait for current handlers to finish.
+	 */
+	synchronize_sched();
 }
 
 static int __init init_syscall_trace(struct ftrace_event_call *call)
-- 
cgit 


From 8f6fce03ddaf10bfa40c7d6cd59b778d35d41800 Mon Sep 17 00:00:00 2001
From: Mario Kleiner <mario.kleiner.de@gmail.com>
Date: Wed, 30 Oct 2013 05:13:06 +0100
Subject: drm: Push latency sensitive bits of vblank scanoutpos timestamping
 into kms drivers.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A change in locking of some kms drivers (currently intel-kms) make
the old approach too inaccurate and also incompatible with the
PREEMPT_RT realtime kernel patchset.

The driver->get_scanout_position() method of intel-kms now needs
to aquire a spinlock, which clashes badly with the former
preempt_disable() calls in the drm, and it also introduces larger
delays and timing uncertainty on a contended lock than acceptable.

This patch changes the prototype of driver->get_scanout_position()
to require/allow kms drivers to perform the ktime_get() system time
queries which go along with actual scanout position readout in a way
that provides maximum precision and to return those timestamps to
the drm. kms drivers implementations of get_scanout_position() are
asked to implement timestamping and scanoutpos readout in a way
that is as precise as possible and compatible with preempt_disable()
on a PREMPT_RT kernel. A driver should follow this pattern in
get_scanout_position() for precision and compatibility:

spin_lock...(...);
preempt_disable_rt(); // On a PREEMPT_RT kernel, otherwise omit.
if (stime) *stime = ktime_get();
... Minimum amount of MMIO register reads to get scanout position ...
... no taking of locks allowed here! ...
if (etime) *etime = ktime_get();
preempt_enable_rt(); // On PREEMPT_RT kernel, otherwise omit.
spin_unlock...(...);

v2: Fix formatting of new multi-line code comments.

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c | 20 ++++++++++++--------
 include/drm/drmP.h        | 10 ++++++++--
 2 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 33ee515c9777..d80d95289e10 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -219,7 +219,7 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 	for (i = 0; i < num_crtcs; i++)
 		init_waitqueue_head(&dev->vblank[i].queue);
 
-	DRM_INFO("Supports vblank timestamp caching Rev 1 (10.10.2010).\n");
+	DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n");
 
 	/* Driver specific high-precision vblank timestamping supported? */
 	if (dev->driver->get_vblank_timestamp)
@@ -586,14 +586,17 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 	 * code gets preempted or delayed for some reason.
 	 */
 	for (i = 0; i < DRM_TIMESTAMP_MAXRETRIES; i++) {
-		/* Get system timestamp before query. */
-		stime = ktime_get();
-
-		/* Get vertical and horizontal scanout pos. vpos, hpos. */
-		vbl_status = dev->driver->get_scanout_position(dev, crtc, &vpos, &hpos);
+		/*
+		 * Get vertical and horizontal scanout position vpos, hpos,
+		 * and bounding timestamps stime, etime, pre/post query.
+		 */
+		vbl_status = dev->driver->get_scanout_position(dev, crtc, &vpos,
+							       &hpos, &stime, &etime);
 
-		/* Get system timestamp after query. */
-		etime = ktime_get();
+		/*
+		 * Get correction for CLOCK_MONOTONIC -> CLOCK_REALTIME if
+		 * CLOCK_REALTIME is requested.
+		 */
 		if (!drm_timestamp_monotonic)
 			mono_time_offset = ktime_get_monotonic_offset();
 
@@ -604,6 +607,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 			return -EIO;
 		}
 
+		/* Compute uncertainty in timestamp of scanout position query. */
 		duration_ns = ktime_to_ns(etime) - ktime_to_ns(stime);
 
 		/* Accept result with <  max_error nsecs timing uncertainty. */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index e6d0cd9f518e..748c72907829 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -836,12 +836,17 @@ struct drm_driver {
 	/**
 	 * Called by vblank timestamping code.
 	 *
-	 * Return the current display scanout position from a crtc.
+	 * Return the current display scanout position from a crtc, and an
+	 * optional accurate ktime_get timestamp of when position was measured.
 	 *
 	 * \param dev  DRM device.
 	 * \param crtc Id of the crtc to query.
 	 * \param *vpos Target location for current vertical scanout position.
 	 * \param *hpos Target location for current horizontal scanout position.
+	 * \param *stime Target location for timestamp taken immediately before
+	 *               scanout position query. Can be NULL to skip timestamp.
+	 * \param *etime Target location for timestamp taken immediately after
+	 *               scanout position query. Can be NULL to skip timestamp.
 	 *
 	 * Returns vpos as a positive number while in active scanout area.
 	 * Returns vpos as a negative number inside vblank, counting the number
@@ -858,7 +863,8 @@ struct drm_driver {
 	 *
 	 */
 	int (*get_scanout_position) (struct drm_device *dev, int crtc,
-				     int *vpos, int *hpos);
+				     int *vpos, int *hpos, ktime_t *stime,
+				     ktime_t *etime);
 
 	/**
 	 * Called by \c drm_get_last_vbltimestamp. Should return a precise
-- 
cgit 


From 7d74795b740135b7c89269ce21be51cc5b328de6 Mon Sep 17 00:00:00 2001
From: "Lespiau, Damien" <damien.lespiau@intel.com>
Date: Thu, 17 Oct 2013 19:09:53 +0100
Subject: drm: Constify struct drm_info_list * arguments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Those functions are just reading data from those pointers.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_debugfs.c | 4 ++--
 include/drm/drmP.h            | 9 +++++----
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index a05087cf846d..4813ff13960e 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -84,7 +84,7 @@ static const struct file_operations drm_debugfs_fops = {
  * Create a given set of debugfs files represented by an array of
  * gdm_debugfs_lists in the given root directory.
  */
-int drm_debugfs_create_files(struct drm_info_list *files, int count,
+int drm_debugfs_create_files(const struct drm_info_list *files, int count,
 			     struct dentry *root, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
@@ -188,7 +188,7 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id,
  *
  * Remove all debugfs entries created by debugfs_init().
  */
-int drm_debugfs_remove_files(struct drm_info_list *files, int count,
+int drm_debugfs_remove_files(const struct drm_info_list *files, int count,
 			     struct drm_minor *minor)
 {
 	struct list_head *pos, *q;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 748c72907829..0da45d930c0a 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1477,10 +1477,11 @@ extern struct drm_local_map *drm_getsarea(struct drm_device *dev);
 #if defined(CONFIG_DEBUG_FS)
 extern int drm_debugfs_init(struct drm_minor *minor, int minor_id,
 			    struct dentry *root);
-extern int drm_debugfs_create_files(struct drm_info_list *files, int count,
-				    struct dentry *root, struct drm_minor *minor);
-extern int drm_debugfs_remove_files(struct drm_info_list *files, int count,
-                                    struct drm_minor *minor);
+extern int drm_debugfs_create_files(const struct drm_info_list *files,
+				    int count, struct dentry *root,
+				    struct drm_minor *minor);
+extern int drm_debugfs_remove_files(const struct drm_info_list *files,
+				    int count, struct drm_minor *minor);
 extern int drm_debugfs_cleanup(struct drm_minor *minor);
 #endif
 
-- 
cgit 


From ff9befe8300d104de86fdb0d3f206ab36603f672 Mon Sep 17 00:00:00 2001
From: "Lespiau, Damien" <damien.lespiau@intel.com>
Date: Thu, 17 Oct 2013 19:09:54 +0100
Subject: drm: Remove drm_debugfs_node and drm_debugfs_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Those structures are not used anywhere.

Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 21 ---------------------
 1 file changed, 21 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0da45d930c0a..444751b9aa89 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1004,27 +1004,6 @@ struct drm_driver {
 #define DRM_MINOR_CONTROL 2
 #define DRM_MINOR_RENDER 3
 
-
-/**
- * debugfs node list. This structure represents a debugfs file to
- * be created by the drm core
- */
-struct drm_debugfs_list {
-	const char *name; /** file name */
-	int (*show)(struct seq_file*, void*); /** show callback */
-	u32 driver_features; /**< Required driver features for this entry */
-};
-
-/**
- * debugfs node structure. This structure represents a debugfs file.
- */
-struct drm_debugfs_node {
-	struct list_head list;
-	struct drm_minor *minor;
-	struct drm_debugfs_list *debugfs_ent;
-	struct dentry *dent;
-};
-
 /**
  * Info file list entry. This structure represents a debugfs or proc file to
  * be created by the drm core
-- 
cgit 


From 482fc6094afad572a4ea1fd722e7b11ca72022a0 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Tue, 5 Nov 2013 02:24:17 +0100
Subject: ipv4: introduce new IP_MTU_DISCOVER mode IP_PMTUDISC_INTERFACE

Sockets marked with IP_PMTUDISC_INTERFACE won't do path mtu discovery,
their sockets won't accept and install new path mtu information and they
will always use the interface mtu for outgoing packets. It is guaranteed
that the packet is not fragmented locally. But we won't set the DF-Flag
on the outgoing frames.

Florian Weimer had the idea to use this flag to ensure DNS servers are
never generating outgoing fragments. They may well be fragmented on the
path, but the server never stores or usees path mtu values, which could
well be forged in an attack.

(The root of the problem with path MTU discovery is that there is
no reliable way to authenticate ICMP Fragmentation Needed But DF Set
messages because they are sent from intermediate routers with their
source addresses, and the IMCP payload will not always contain sufficient
information to identify a flow.)

Recent research in the DNS community showed that it is possible to
implement an attack where DNS cache poisoning is feasible by spoofing
fragments. This work was done by Amir Herzberg and Haya Shulman:
<https://sites.google.com/site/hayashulman/files/fragmentation-poisoning.pdf>

This issue was previously discussed among the DNS community, e.g.
<http://www.ietf.org/mail-archive/web/dnsext/current/msg01204.html>,
without leading to fixes.

This patch depends on the patch "ipv4: fix DO and PROBE pmtu mode
regarding local fragmentation with UFO/CORK" for the enforcement of the
non-fragmentable checks. If other users than ip_append_page/data should
use this semantic too, we have to add a new flag to IPCB(skb)->flags to
suppress local fragmentation and check for this in ip_finish_output.

Many thanks to Florian Weimer for the idea and feedback while implementing
this patch.

Cc: David S. Miller <davem@davemloft.net>
Suggested-by: Florian Weimer <fweimer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h     | 16 ++++++++++++----
 include/uapi/linux/in.h |  5 +++++
 net/dccp/ipv4.c         |  1 +
 net/ipv4/ip_output.c    |  8 ++++----
 net/ipv4/ip_sockglue.c  |  2 +-
 net/ipv4/route.c        |  4 ++++
 net/ipv4/tcp_ipv4.c     |  1 +
 7 files changed, 28 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index dd4ae0029fd8..f68c167280a7 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -313,12 +313,20 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 	return hoplimit;
 }
 
-static inline int ip_skb_dst_mtu(struct sk_buff *skb)
+static inline bool ip_sk_accept_pmtu(const struct sock *sk)
 {
-	struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;
+	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;
+}
 
-	return (inet && inet->pmtudisc == IP_PMTUDISC_PROBE) ?
-	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+static inline bool ip_sk_use_pmtu(const struct sock *sk)
+{
+	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
+}
+
+static inline int ip_skb_dst_mtu(const struct sk_buff *skb)
+{
+	return (!skb->sk || ip_sk_use_pmtu(skb->sk)) ?
+	       dst_mtu(skb_dst(skb)) : skb_dst(skb)->dev->mtu;
 }
 
 #endif	/* _ROUTE_H */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index f9e8e496ae5d..393c5de09d42 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -115,6 +115,11 @@ struct in_addr {
 #define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
 #define IP_PMTUDISC_DO			2	/* Always DF		*/
 #define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
 
 #define IP_MULTICAST_IF			32
 #define IP_MULTICAST_TTL 		33
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 720c36225ed9..d9f65fc66db5 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -174,6 +174,7 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk,
 	mtu = dst_mtu(dst);
 
 	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
+	    ip_sk_accept_pmtu(sk) &&
 	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
 		dccp_sync_mss(sk, mtu);
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 51be64e18e32..912402752f2f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1037,7 +1037,6 @@ error:
 static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 			 struct ipcm_cookie *ipc, struct rtable **rtp)
 {
-	struct inet_sock *inet = inet_sk(sk);
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
@@ -1063,8 +1062,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	 * We steal reference to this route, caller should not release it
 	 */
 	*rtp = NULL;
-	cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ?
-			 rt->dst.dev->mtu : dst_mtu(&rt->dst);
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
 	cork->dst = &rt->dst;
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
@@ -1315,7 +1314,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	/* DF bit is set when we want to see DF on outgoing frames.
 	 * If local_df is set too, we still allow to fragment this frame
 	 * locally. */
-	if (inet->pmtudisc >= IP_PMTUDISC_DO ||
+	if (inet->pmtudisc == IP_PMTUDISC_DO ||
+	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
 	    (skb->len <= dst_mtu(&rt->dst) &&
 	     ip_dont_fragment(sk, &rt->dst)))
 		df = htons(IP_DF);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 0626f2cb192e..3f858266fa7e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -627,7 +627,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		inet->nodefrag = val ? 1 : 0;
 		break;
 	case IP_MTU_DISCOVER:
-		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
+		if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE)
 			goto e_inval;
 		inet->pmtudisc = val;
 		break;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d2d325382b13..f428935c50db 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1036,6 +1036,10 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	bool new = false;
 
 	bh_lock_sock(sk);
+
+	if (!ip_sk_accept_pmtu(sk))
+		goto out;
+
 	rt = (struct rtable *) __sk_dst_get(sk);
 
 	if (sock_owned_by_user(sk) || !rt) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 300ab2c93f29..14bba8a1c5a7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -288,6 +288,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
 	mtu = dst_mtu(dst);
 
 	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
+	    ip_sk_accept_pmtu(sk) &&
 	    inet_csk(sk)->icsk_pmtu_cookie > mtu) {
 		tcp_sync_mss(sk, mtu);
 
-- 
cgit 


From 3cf70dafd7bbbc91df0a9ecb081d46f9f3d867f6 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Fri, 11 Oct 2013 10:01:08 +0200
Subject: drm: add drm_set_preferred_mode

New helper function to set the preferred video mode.  Can be called
after drm_add_modes_noedid if you don't want the largest supported
video mode be used by default.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_edid.c | 13 +++++++++++++
 include/drm/drm_crtc.h     |  2 ++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 01275e6bf638..2f325bcd0708 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -3482,6 +3482,19 @@ int drm_add_modes_noedid(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_add_modes_noedid);
 
+void drm_set_preferred_mode(struct drm_connector *connector,
+			   int hpref, int vpref)
+{
+	struct drm_display_mode *mode;
+
+	list_for_each_entry(mode, &connector->probed_modes, head) {
+		if (drm_mode_width(mode)  == hpref &&
+		    drm_mode_height(mode) == vpref)
+			mode->type |= DRM_MODE_TYPE_PREFERRED;
+	}
+}
+EXPORT_SYMBOL(drm_set_preferred_mode);
+
 /**
  * drm_hdmi_avi_infoframe_from_display_mode() - fill an HDMI AVI infoframe with
  *                                              data from a DRM display mode
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index d3a91ade1d37..f32c5cd51f41 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1118,6 +1118,8 @@ extern struct drm_display_mode *drm_gtf_mode_complex(struct drm_device *dev,
 				int GTF_2C, int GTF_K, int GTF_2J);
 extern int drm_add_modes_noedid(struct drm_connector *connector,
 				int hdisplay, int vdisplay);
+extern void drm_set_preferred_mode(struct drm_connector *connector,
+				   int hpref, int vpref);
 
 extern int drm_edid_header_is_valid(const u8 *raw_edid);
 extern bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid);
-- 
cgit 


From 1020dc6990168a5081ffad620c440e220f05b460 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 29 Oct 2013 08:55:57 +0000
Subject: drm: Do not drop root privileges for a fancier younger process

When a second process opens the device and master transferrence is
complete, we walk the list of open devices and remove their
authentication. This also revokes our root privilege. Instead of simply
dropping the authentication, this patch reverts the authenticated state
back to its original value.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_fops.c | 5 +++--
 include/drm/drmP.h         | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index ee2d330a2fa0..3a7176ce2540 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -239,7 +239,8 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 
 	priv->ioctl_count = 0;
 	/* for compatibility root is always authenticated */
-	priv->authenticated = capable(CAP_SYS_ADMIN);
+	priv->always_authenticated = capable(CAP_SYS_ADMIN);
+	priv->authenticated = priv->always_authenticated;
 	priv->lock_count = 0;
 
 	INIT_LIST_HEAD(&priv->lhead);
@@ -533,7 +534,7 @@ int drm_release(struct inode *inode, struct file *filp)
 		list_for_each_entry(temp, &dev->filelist, lhead) {
 			if ((temp->master == file_priv->master) &&
 			    (temp != file_priv))
-				temp->authenticated = 0;
+				temp->authenticated = temp->always_authenticated;
 		}
 
 		/**
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 444751b9aa89..ea8bff3c8468 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -413,6 +413,7 @@ struct drm_prime_file_private {
 
 /** File private data */
 struct drm_file {
+	int always_authenticated;
 	int authenticated;
 	struct pid *pid;
 	kuid_t uid;
-- 
cgit 


From 39868bd7668bd47308b1dfd97c212757caee764f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 29 Oct 2013 08:55:58 +0000
Subject: drm: Compact booleans within struct drm_file

Replace the sparse array of booleans with a bitfield.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drmP.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index ea8bff3c8468..b3e4fa213000 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -413,8 +413,12 @@ struct drm_prime_file_private {
 
 /** File private data */
 struct drm_file {
-	int always_authenticated;
-	int authenticated;
+	unsigned always_authenticated :1;
+	unsigned authenticated :1;
+	unsigned is_master :1; /* this file private is a master for a minor */
+	/* true when the client has asked us to expose stereo 3D mode flags */
+	unsigned stereo_allowed :1;
+
 	struct pid *pid;
 	kuid_t uid;
 	drm_magic_t magic;
@@ -431,13 +435,8 @@ struct drm_file {
 	struct file *filp;
 	void *driver_priv;
 
-	int is_master; /* this file private is a master for a minor */
 	struct drm_master *master; /* master this node is currently associated with
 				      N.B. not always minor->master */
-
-	/* true when the client has asked us to expose stereo 3D mode flags */
-	bool stereo_allowed;
-
 	/**
 	 * fbs - List of framebuffers associated with this file.
 	 *
-- 
cgit 


From 4ac387f516bd3e5356cdb25266e244fa8a062281 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Sun, 20 Oct 2013 18:55:41 +0200
Subject: drm: simplify drm_put_minor()

Allow passing NULL as minor to simplify DRM destruction paths. Also remove
the double-pointer reset as it is no longer needed. drm_put_minor() is
only called when the underlying object is destroyed. Hence, resetting
minors to NULL is not necessary.

As drm_put_minor() is no longer used by other DRM files, we can make it
static, too.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_stub.c | 31 +++++++++++++------------------
 include/drm/drmP.h         |  1 -
 2 files changed, 13 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index ae3f293229ae..dd0cb02830f4 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -343,15 +343,17 @@ static void drm_unplug_minor(struct drm_minor *minor)
 
 /**
  * drm_put_minor - Destroy DRM minor
- * @minor_p: Double pointer to DRM minor
+ * @minor: Minor to destroy
  *
- * This calls drm_unplug_minor() on the given minor and then frees it. The minor
- * pointer is reset to NULL before this returns.
+ * This calls drm_unplug_minor() on the given minor and then frees it. Nothing
+ * is done if @minor is NULL. It is fine to call this on already unplugged
+ * minors.
  * The global DRM mutex must be held by the caller.
  */
-int drm_put_minor(struct drm_minor **minor_p)
+static void drm_put_minor(struct drm_minor *minor)
 {
-	struct drm_minor *minor = *minor_p;
+	if (!minor)
+		return;
 
 	DRM_DEBUG("release secondary minor %d\n", minor->index);
 
@@ -364,10 +366,7 @@ int drm_put_minor(struct drm_minor **minor_p)
 	idr_remove(&drm_minors_idr, minor->index);
 
 	kfree(minor);
-	*minor_p = NULL;
-	return 0;
 }
-EXPORT_SYMBOL(drm_put_minor);
 
 /**
  * Called via drm_exit() at module unload time or when pci device is
@@ -562,13 +561,11 @@ err_unload:
 	if (dev->driver->unload)
 		dev->driver->unload(dev);
 err_primary_node:
-	drm_put_minor(&dev->primary);
+	drm_put_minor(dev->primary);
 err_render_node:
-	if (dev->render)
-		drm_put_minor(&dev->render);
+	drm_put_minor(dev->render);
 err_control_node:
-	if (dev->control)
-		drm_put_minor(&dev->control);
+	drm_put_minor(dev->control);
 err_agp:
 	if (dev->driver->bus->agp_destroy)
 		dev->driver->bus->agp_destroy(dev);
@@ -603,11 +600,9 @@ void drm_dev_unregister(struct drm_device *dev)
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
 		drm_rmmap(dev, r_list->map);
 
-	if (dev->control)
-		drm_put_minor(&dev->control);
-	if (dev->render)
-		drm_put_minor(&dev->render);
-	drm_put_minor(&dev->primary);
+	drm_put_minor(dev->control);
+	drm_put_minor(dev->render);
+	drm_put_minor(dev->primary);
 
 	list_del(&dev->driver_item);
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index b3e4fa213000..62da57e914f8 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1436,7 +1436,6 @@ extern struct drm_master *drm_master_get(struct drm_master *master);
 extern void drm_master_put(struct drm_master **master);
 
 extern void drm_put_dev(struct drm_device *dev);
-extern int drm_put_minor(struct drm_minor **minor);
 extern void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
 extern unsigned int drm_rnodes;
-- 
cgit 


From a99ee459fd0ae38c0ccc7f93af718ef476657d1b Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Sun, 20 Oct 2013 18:55:42 +0200
Subject: drm: make drm_get_minor() static

drm_get_minor() is only used in one file. Make it static and add a
kernel-doc comment which documents the current semantics.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_stub.c | 19 +++++++++++--------
 include/drm/drmP.h         |  1 -
 2 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index dd0cb02830f4..76b4d718af60 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -255,16 +255,20 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
 }
 
 /**
- * Get a secondary minor number.
+ * drm_get_minor - Allocate and register new DRM minor
+ * @dev: DRM device
+ * @minor: Pointer to where new minor is stored
+ * @type: Type of minor
  *
- * \param dev device data structure
- * \param sec-minor structure to hold the assigned minor
- * \return negative number on failure.
+ * Allocate a new minor of the given type and register it. A pointer to the new
+ * minor is returned in @minor.
+ * Caller must hold the global DRM mutex.
  *
- * Search an empty entry and initialize it to the given parameters. This
- * routines assigns minor numbers to secondary heads of multi-headed cards
+ * RETURNS:
+ * 0 on success, negative error code on failure.
  */
-int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type)
+static int drm_get_minor(struct drm_device *dev, struct drm_minor **minor,
+			 int type)
 {
 	struct drm_minor *new_minor;
 	int ret;
@@ -321,7 +325,6 @@ err_idr:
 	*minor = NULL;
 	return ret;
 }
-EXPORT_SYMBOL(drm_get_minor);
 
 /**
  * drm_unplug_minor - Unplug DRM minor
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 62da57e914f8..1d4a920ef7ff 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1630,7 +1630,6 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 void drm_dev_free(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
 void drm_dev_unregister(struct drm_device *dev);
-int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type);
 /*@}*/
 
 /* PCI section */
-- 
cgit 


From b8a216269ec0ce2e961d32e6d640d7010b8a818e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 4 Oct 2013 22:06:53 +0200
Subject: sched: Move completion code from core.c to completion.c

Completions already have their own header file: linux/completion.h
Move the implementation out of kernel/sched/core.c and into its own
file: kernel/sched/completion.c.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-x2y49rmxu5dljt66ai2lcfuw@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/completion.h |   2 +-
 kernel/sched/Makefile      |   2 +-
 kernel/sched/completion.c  | 299 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/core.c        | 284 ------------------------------------------
 4 files changed, 301 insertions(+), 286 deletions(-)
 create mode 100644 kernel/sched/completion.c

(limited to 'include')

diff --git a/include/linux/completion.h b/include/linux/completion.h
index 3cd574d5b19e..22c33e35bcb2 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -5,7 +5,7 @@
  * (C) Copyright 2001 Linus Torvalds
  *
  * Atomic wait-for-completion handler data structures.
- * See kernel/sched/core.c for details.
+ * See kernel/sched/completion.c for details.
  */
 
 #include <linux/wait.h>
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index f8d3f4baa1a1..7b621409cf15 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -12,7 +12,7 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
 obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
-obj-y += wait.o
+obj-y += wait.o completion.o
 obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
new file mode 100644
index 000000000000..a63f4dc27909
--- /dev/null
+++ b/kernel/sched/completion.c
@@ -0,0 +1,299 @@
+/*
+ * Generic wait-for-completion handler;
+ *
+ * It differs from semaphores in that their default case is the opposite,
+ * wait_for_completion default blocks whereas semaphore default non-block. The
+ * interface also makes it easy to 'complete' multiple waiting threads,
+ * something which isn't entirely natural for semaphores.
+ *
+ * But more importantly, the primitive documents the usage. Semaphores would
+ * typically be used for exclusion which gives rise to priority inversion.
+ * Waiting for completion is a typically sync point, but not an exclusion point.
+ */
+
+#include <linux/sched.h>
+#include <linux/completion.h>
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+do_wait_for_common(struct completion *x,
+		   long (*action)(long), long timeout, int state)
+{
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		__add_wait_queue_tail_exclusive(&x->wait, &wait);
+		do {
+			if (signal_pending_state(state, current)) {
+				timeout = -ERESTARTSYS;
+				break;
+			}
+			__set_current_state(state);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = action(timeout);
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done && timeout);
+		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
+	}
+	x->done--;
+	return timeout ?: 1;
+}
+
+static inline long __sched
+__wait_for_common(struct completion *x,
+		  long (*action)(long), long timeout, int state)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	timeout = do_wait_for_common(x, action, timeout, state);
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+	wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be
+ * signaled or for a specified timeout to expire. It can be
+ * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_killable_timeout(struct completion *x,
+				     unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(wait_for_completion_killable_timeout);
+
+/**
+ *	try_wait_for_completion - try to decrement a completion without blocking
+ *	@x:	completion structure
+ *
+ *	Return: 0 if a decrement cannot be done without blocking
+ *		 1 if a decrement succeeded.
+ *
+ *	If a completion is being used as a counting completion,
+ *	attempt to decrement the counter without blocking. This
+ *	enables us to avoid waiting if the resource the completion
+ *	is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	else
+		x->done--;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *	completion_done - Test to see if a completion has any waiters
+ *	@x:	completion structure
+ *
+ *	Return: 0 if there are waiters (wait_for_completion() in progress)
+ *		 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 91b28454c218..aa066f306be2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2688,290 +2688,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 }
 EXPORT_SYMBOL(default_wake_function);
 
-/**
- * complete: - signals a single thread waiting on this completion
- * @x:  holds the state of this particular completion
- *
- * This will wake up a single thread waiting on this completion. Threads will be
- * awakened in the same order in which they were queued.
- *
- * See also complete_all(), wait_for_completion() and related routines.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete(struct completion *x)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done++;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete);
-
-/**
- * complete_all: - signals all threads waiting on this completion
- * @x:  holds the state of this particular completion
- *
- * This will wake up all threads waiting on this particular completion event.
- *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
- */
-void complete_all(struct completion *x)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done += UINT_MAX/2;
-	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-}
-EXPORT_SYMBOL(complete_all);
-
-static inline long __sched
-do_wait_for_common(struct completion *x,
-		   long (*action)(long), long timeout, int state)
-{
-	if (!x->done) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		__add_wait_queue_tail_exclusive(&x->wait, &wait);
-		do {
-			if (signal_pending_state(state, current)) {
-				timeout = -ERESTARTSYS;
-				break;
-			}
-			__set_current_state(state);
-			spin_unlock_irq(&x->wait.lock);
-			timeout = action(timeout);
-			spin_lock_irq(&x->wait.lock);
-		} while (!x->done && timeout);
-		__remove_wait_queue(&x->wait, &wait);
-		if (!x->done)
-			return timeout;
-	}
-	x->done--;
-	return timeout ?: 1;
-}
-
-static inline long __sched
-__wait_for_common(struct completion *x,
-		  long (*action)(long), long timeout, int state)
-{
-	might_sleep();
-
-	spin_lock_irq(&x->wait.lock);
-	timeout = do_wait_for_common(x, action, timeout, state);
-	spin_unlock_irq(&x->wait.lock);
-	return timeout;
-}
-
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
-{
-	return __wait_for_common(x, schedule_timeout, timeout, state);
-}
-
-static long __sched
-wait_for_common_io(struct completion *x, long timeout, int state)
-{
-	return __wait_for_common(x, io_schedule_timeout, timeout, state);
-}
-
-/**
- * wait_for_completion: - waits for completion of a task
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout.
- *
- * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
- * and interrupt capability. Also see complete().
- */
-void __sched wait_for_completion(struct completion *x)
-{
-	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion);
-
-/**
- * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_timeout(struct completion *x, unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_timeout);
-
-/**
- * wait_for_completion_io: - waits for completion of a task
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It is NOT
- * interruptible and there is no timeout. The caller is accounted as waiting
- * for IO.
- */
-void __sched wait_for_completion_io(struct completion *x)
-{
-	wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io);
-
-/**
- * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible. The caller is accounted as waiting for IO.
- *
- * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
- * till timeout) if completed.
- */
-unsigned long __sched
-wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
-{
-	return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_io_timeout);
-
-/**
- * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
- * @x:  holds the state of this particular completion
- *
- * This waits for completion of a specific task to be signaled. It is
- * interruptible.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_interruptible(struct completion *x)
-{
-	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
-	if (t == -ERESTARTSYS)
-		return t;
-	return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible);
-
-/**
- * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be signaled or for a
- * specified timeout to expire. It is interruptible. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_interruptible_timeout(struct completion *x,
-					  unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
-}
-EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
-
-/**
- * wait_for_completion_killable: - waits for completion of a task (killable)
- * @x:  holds the state of this particular completion
- *
- * This waits to be signaled for completion of a specific task. It can be
- * interrupted by a kill signal.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if completed.
- */
-int __sched wait_for_completion_killable(struct completion *x)
-{
-	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
-	if (t == -ERESTARTSYS)
-		return t;
-	return 0;
-}
-EXPORT_SYMBOL(wait_for_completion_killable);
-
-/**
- * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
- * @x:  holds the state of this particular completion
- * @timeout:  timeout value in jiffies
- *
- * This waits for either a completion of a specific task to be
- * signaled or for a specified timeout to expire. It can be
- * interrupted by a kill signal. The timeout is in jiffies.
- *
- * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
- * or number of jiffies left till timeout) if completed.
- */
-long __sched
-wait_for_completion_killable_timeout(struct completion *x,
-				     unsigned long timeout)
-{
-	return wait_for_common(x, timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(wait_for_completion_killable_timeout);
-
-/**
- *	try_wait_for_completion - try to decrement a completion without blocking
- *	@x:	completion structure
- *
- *	Return: 0 if a decrement cannot be done without blocking
- *		 1 if a decrement succeeded.
- *
- *	If a completion is being used as a counting completion,
- *	attempt to decrement the counter without blocking. This
- *	enables us to avoid waiting if the resource the completion
- *	is protecting is not available.
- */
-bool try_wait_for_completion(struct completion *x)
-{
-	unsigned long flags;
-	int ret = 1;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	if (!x->done)
-		ret = 0;
-	else
-		x->done--;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(try_wait_for_completion);
-
-/**
- *	completion_done - Test to see if a completion has any waiters
- *	@x:	completion structure
- *
- *	Return: 0 if there are waiters (wait_for_completion() in progress)
- *		 1 if there are no waiters.
- *
- */
-bool completion_done(struct completion *x)
-{
-	unsigned long flags;
-	int ret = 1;
-
-	spin_lock_irqsave(&x->wait.lock, flags);
-	if (!x->done)
-		ret = 0;
-	spin_unlock_irqrestore(&x->wait.lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(completion_done);
-
 static long __sched
 sleep_on_common(wait_queue_head_t *q, int state, long timeout)
 {
-- 
cgit 


From ce332f662deb545c8a4f3f58debcca26bb2e44b0 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 4 Nov 2013 22:36:17 +0200
Subject: srcu: API for barrier after srcu read unlock

srcu read lock/unlock include a full memory barrier
but that's an implementation detail.
Add an API for make memory fencing explicit for
users that need this barrier, to make sure we
can change it as needed without breaking all users.

Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 include/linux/srcu.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c114614ed172..9b058eecd403 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -237,4 +237,18 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__srcu_read_unlock(sp, idx);
 }
 
+/**
+ * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
+ *
+ * Converts the preceding srcu_read_unlock into a two-way memory barrier.
+ *
+ * Call this after srcu_read_unlock, to guarantee that all memory operations
+ * that occur after smp_mb__after_srcu_read_unlock will appear to happen after
+ * the preceding srcu_read_unlock.
+ */
+static inline void smp_mb__after_srcu_read_unlock(void)
+{
+	/* __srcu_read_unlock has smp_mb() internally so nothing to do here. */
+}
+
 #endif
-- 
cgit 


From 8b414521bc5375ae8ba18c083af95d44b8da0d04 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Fri, 11 Oct 2013 21:39:26 -0300
Subject: hung_task: add method to reset detector

In certain occasions it is possible for a hung task detector
positive to be false: continuation from a paused VM, for example.

Add a method to reset detection, similar as is done
with other kernel watchdogs.

Acked-by: Don Zickus <dzickus@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kernel/pvclock.c |  1 +
 include/linux/sched.h     |  8 ++++++++
 kernel/hung_task.c        | 11 +++++++++++
 3 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 6279928c0a71..2f355d229a58 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -48,6 +48,7 @@ void pvclock_touch_watchdogs(void)
 	touch_softlockup_watchdog_sync();
 	clocksource_touch_watchdog();
 	rcu_cpu_stall_reset();
+	reset_hung_task_detector();
 }
 
 static atomic64_t last_value = ATOMIC64_INIT(0);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6682da36b293..7bb4b4a2a101 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -285,6 +285,14 @@ static inline void lockup_detector_init(void)
 }
 #endif
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+void reset_hung_task_detector(void);
+#else
+static inline void reset_hung_task_detector(void)
+{
+}
+#endif
+
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched		__attribute__((__section__(".sched.text")))
 
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 3e97fb126e6b..dfdf51534b3e 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -203,6 +203,14 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
 	return ret;
 }
 
+static atomic_t reset_hung_task = ATOMIC_INIT(0);
+
+void reset_hung_task_detector(void)
+{
+	atomic_set(&reset_hung_task, 1);
+}
+EXPORT_SYMBOL_GPL(reset_hung_task_detector);
+
 /*
  * kthread which checks for tasks stuck in D state
  */
@@ -216,6 +224,9 @@ static int watchdog(void *dummy)
 		while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
 			timeout = sysctl_hung_task_timeout_secs;
 
+		if (atomic_xchg(&reset_hung_task, 0))
+			continue;
+
 		check_hung_uninterruptible_tasks(timeout);
 	}
 
-- 
cgit 


From 827da44c61419f29ae3be198c342e2147f1a10cb Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 7 Oct 2013 15:51:58 -0700
Subject: net: Explicitly initialize u64_stats_sync structures for lockdep

In order to enable lockdep on seqcount/seqlock structures, we
must explicitly initialize any locks.

The u64_stats_sync structure, uses a seqcount, and thus we need
to introduce a u64_stats_init() function and use it to initialize
the structure.

This unfortunately adds a lot of fairly trivial initialization code
to a number of drivers. But the benefit of ensuring correctness makes
this worth while.

Because these changes are required for lockdep to be enabled, and the
changes are quite trivial, I've not yet split this patch out into 30-some
separate patches, as I figured it would be better to get the various
maintainers thoughts on how to best merge this change along with
the seqcount lockdep enablement.

Feedback would be appreciated!

Signed-off-by: John Stultz <john.stultz@linaro.org>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: James Morris <jmorris@namei.org>
Cc: Jesse Gross <jesse@nicira.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Mirko Lindner <mlindner@marvell.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Roger Luethi <rl@hellgate.ch>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Simon Horman <horms@verge.net.au>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Wensong Zhang <wensong@linux-vs.org>
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/1381186321-4906-2-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/net/dummy.c                            |  6 ++++++
 drivers/net/ethernet/emulex/benet/be_main.c    |  4 ++++
 drivers/net/ethernet/intel/igb/igb_main.c      |  5 +++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c  |  4 ++++
 drivers/net/ethernet/marvell/mvneta.c          |  3 +++
 drivers/net/ethernet/marvell/sky2.c            |  3 +++
 drivers/net/ethernet/neterion/vxge/vxge-main.c |  4 ++++
 drivers/net/ethernet/nvidia/forcedeth.c        |  2 ++
 drivers/net/ethernet/realtek/8139too.c         |  3 +++
 drivers/net/ethernet/tile/tilepro.c            |  2 ++
 drivers/net/ethernet/via/via-rhine.c           |  3 +++
 drivers/net/ifb.c                              |  5 +++++
 drivers/net/loopback.c                         |  6 ++++++
 drivers/net/macvlan.c                          |  7 +++++++
 drivers/net/nlmon.c                            |  8 ++++++++
 drivers/net/team/team.c                        |  6 ++++++
 drivers/net/team/team_mode_loadbalance.c       |  9 ++++++++-
 drivers/net/veth.c                             |  8 ++++++++
 drivers/net/virtio_net.c                       |  8 ++++++++
 drivers/net/vxlan.c                            |  8 ++++++++
 drivers/net/xen-netfront.c                     |  6 ++++++
 include/linux/u64_stats_sync.h                 |  7 +++++++
 net/8021q/vlan_dev.c                           |  9 ++++++++-
 net/bridge/br_device.c                         |  7 +++++++
 net/ipv4/af_inet.c                             | 14 ++++++++++++++
 net/ipv4/ip_tunnel.c                           |  8 +++++++-
 net/ipv6/addrconf.c                            | 14 ++++++++++++++
 net/ipv6/af_inet6.c                            | 14 ++++++++++++++
 net/ipv6/ip6_gre.c                             | 15 +++++++++++++++
 net/ipv6/ip6_tunnel.c                          |  7 +++++++
 net/ipv6/sit.c                                 | 15 +++++++++++++++
 net/netfilter/ipvs/ip_vs_ctl.c                 | 25 ++++++++++++++++++++++---
 net/openvswitch/datapath.c                     |  6 ++++++
 net/openvswitch/vport.c                        |  8 ++++++++
 34 files changed, 253 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index b710c6b2d659..bd8f84b0b894 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -88,10 +88,16 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int dummy_dev_init(struct net_device *dev)
 {
+	int i;
 	dev->dstats = alloc_percpu(struct pcpu_dstats);
 	if (!dev->dstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_dstats *dstats;
+		dstats = per_cpu_ptr(dev->dstats, i);
+		u64_stats_init(&dstats->syncp);
+	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 2c38cc402119..edd75950855a 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2047,6 +2047,9 @@ static int be_tx_qs_create(struct be_adapter *adapter)
 		if (status)
 			return status;
 
+		u64_stats_init(&txo->stats.sync);
+		u64_stats_init(&txo->stats.sync_compl);
+
 		/* If num_evt_qs is less than num_tx_qs, then more than
 		 * one txq share an eq
 		 */
@@ -2108,6 +2111,7 @@ static int be_rx_cqs_create(struct be_adapter *adapter)
 		if (rc)
 			return rc;
 
+		u64_stats_init(&rxo->stats.sync);
 		eq = &adapter->eq_obj[i % adapter->num_evt_qs].q;
 		rc = be_cmd_cq_create(adapter, cq, eq, false, 3);
 		if (rc)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8cf44f2a8ccd..b6edb93a8fc1 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1223,6 +1223,9 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		ring->count = adapter->tx_ring_count;
 		ring->queue_index = txr_idx;
 
+		u64_stats_init(&ring->tx_syncp);
+		u64_stats_init(&ring->tx_syncp2);
+
 		/* assign ring to adapter */
 		adapter->tx_ring[txr_idx] = ring;
 
@@ -1256,6 +1259,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		ring->count = adapter->rx_ring_count;
 		ring->queue_index = rxr_idx;
 
+		u64_stats_init(&ring->rx_syncp);
+
 		/* assign ring to adapter */
 		adapter->rx_ring[rxr_idx] = ring;
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0ade0cd5ef53..c1750364ddc0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4867,6 +4867,8 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
+	u64_stats_init(&tx_ring->syncp);
+
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
@@ -4949,6 +4951,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring)
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
+	u64_stats_init(&rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e35bac7cfdf1..cb4635c0cd73 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2792,6 +2792,9 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	pp = netdev_priv(dev);
 
+	u64_stats_init(&pp->tx_stats.syncp);
+	u64_stats_init(&pp->rx_stats.syncp);
+
 	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index e09a8c6f8536..339d841a538b 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4763,6 +4763,9 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port,
 	sky2->hw = hw;
 	sky2->msg_enable = netif_msg_init(debug, default_msg);
 
+	u64_stats_init(&sky2->tx_stats.syncp);
+	u64_stats_init(&sky2->rx_stats.syncp);
+
 	/* Auto speed and flow control */
 	sky2->flags = SKY2_FLAG_AUTO_SPEED | SKY2_FLAG_AUTO_PAUSE;
 	if (hw->chip_id != CHIP_ID_YUKON_XL)
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 5a20eaf903dd..44626ec1127b 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2072,6 +2072,10 @@ static int vxge_open_vpaths(struct vxgedev *vdev)
 				vdev->config.tx_steering_type;
 			vpath->fifo.ndev = vdev->ndev;
 			vpath->fifo.pdev = vdev->pdev;
+
+			u64_stats_init(&vpath->fifo.stats.syncp);
+			u64_stats_init(&vpath->ring.stats.syncp);
+
 			if (vdev->config.tx_steering_type)
 				vpath->fifo.txq =
 					netdev_get_tx_queue(vdev->ndev, i);
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 098b96dad66f..2d045be4b5cf 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -5619,6 +5619,8 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	spin_lock_init(&np->lock);
 	spin_lock_init(&np->hwstats_lock);
 	SET_NETDEV_DEV(dev, &pci_dev->dev);
+	u64_stats_init(&np->swstats_rx_syncp);
+	u64_stats_init(&np->swstats_tx_syncp);
 
 	init_timer(&np->oom_kick);
 	np->oom_kick.data = (unsigned long) dev;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 3ccedeb8aba0..c40e984868ad 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -791,6 +791,9 @@ static struct net_device *rtl8139_init_board(struct pci_dev *pdev)
 
 	pci_set_master (pdev);
 
+	u64_stats_init(&tp->rx_stats.syncp);
+	u64_stats_init(&tp->tx_stats.syncp);
+
 retry:
 	/* PIO bar register comes first. */
 	bar = !use_io;
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index 106be47716e7..edb2e12a0fe2 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -1008,6 +1008,8 @@ static void tile_net_register(void *dev_ptr)
 	info->egress_timer.data = (long)info;
 	info->egress_timer.function = tile_net_handle_egress_timer;
 
+	u64_stats_init(&info->stats.syncp);
+
 	priv->cpu[my_cpu] = info;
 
 	/*
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index bdf697b184ae..dd99715e6645 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -987,6 +987,9 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	rp->base = ioaddr;
 
+	u64_stats_init(&rp->tx_stats.syncp);
+	u64_stats_init(&rp->rx_stats.syncp);
+
 	/* Get chip registers into a sane state */
 	rhine_power_init(dev);
 	rhine_hw_init(dev, pioaddr);
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index a3bed28197d2..c14d39bf32d0 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -265,6 +265,7 @@ MODULE_PARM_DESC(numifbs, "Number of ifb devices");
 static int __init ifb_init_one(int index)
 {
 	struct net_device *dev_ifb;
+	struct ifb_private *dp;
 	int err;
 
 	dev_ifb = alloc_netdev(sizeof(struct ifb_private),
@@ -273,6 +274,10 @@ static int __init ifb_init_one(int index)
 	if (!dev_ifb)
 		return -ENOMEM;
 
+	dp = netdev_priv(dev_ifb);
+	u64_stats_init(&dp->rsync);
+	u64_stats_init(&dp->tsync);
+
 	dev_ifb->rtnl_link_ops = &ifb_link_ops;
 	err = register_netdevice(dev_ifb);
 	if (err < 0)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index a17d85a331f1..ac24c27b4b2d 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -137,10 +137,16 @@ static const struct ethtool_ops loopback_ethtool_ops = {
 
 static int loopback_dev_init(struct net_device *dev)
 {
+	int i;
 	dev->lstats = alloc_percpu(struct pcpu_lstats);
 	if (!dev->lstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_lstats *lb_stats;
+		lb_stats = per_cpu_ptr(dev->lstats, i);
+		u64_stats_init(&lb_stats->syncp);
+	}
 	return 0;
 }
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 9bf46bd19b87..0924e51b9ee0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -501,6 +501,7 @@ static int macvlan_init(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct net_device *lowerdev = vlan->lowerdev;
+	int i;
 
 	dev->state		= (dev->state & ~MACVLAN_STATE_MASK) |
 				  (lowerdev->state & MACVLAN_STATE_MASK);
@@ -516,6 +517,12 @@ static int macvlan_init(struct net_device *dev)
 	if (!vlan->pcpu_stats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct macvlan_pcpu_stats *mvlstats;
+		mvlstats = per_cpu_ptr(vlan->pcpu_stats, i);
+		u64_stats_init(&mvlstats->syncp);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index b57ce5f48962..d2bb12bfabd5 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -47,8 +47,16 @@ static int nlmon_change_mtu(struct net_device *dev, int new_mtu)
 
 static int nlmon_dev_init(struct net_device *dev)
 {
+	int i;
+
 	dev->lstats = alloc_percpu(struct pcpu_lstats);
 
+	for_each_possible_cpu(i) {
+		struct pcpu_lstats *nlmstats;
+		nlmstats = per_cpu_ptr(dev->lstats, i);
+		u64_stats_init(&nlmstats->syncp);
+	}
+
 	return dev->lstats == NULL ? -ENOMEM : 0;
 }
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 50e43e64d51d..6574eb8766f9 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1540,6 +1540,12 @@ static int team_init(struct net_device *dev)
 	if (!team->pcpu_stats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct team_pcpu_stats *team_stats;
+		team_stats = per_cpu_ptr(team->pcpu_stats, i);
+		u64_stats_init(&team_stats->syncp);
+	}
+
 	for (i = 0; i < TEAM_PORT_HASHENTRIES; i++)
 		INIT_HLIST_HEAD(&team->en_port_hlist[i]);
 	INIT_LIST_HEAD(&team->port_list);
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 829a9cd2b4da..d671fc3ac5ac 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -570,7 +570,7 @@ static int lb_init(struct team *team)
 {
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	lb_select_tx_port_func_t *func;
-	int err;
+	int i, err;
 
 	/* set default tx port selector */
 	func = lb_select_tx_port_get_func("hash");
@@ -588,6 +588,13 @@ static int lb_init(struct team *team)
 		goto err_alloc_pcpu_stats;
 	}
 
+	for_each_possible_cpu(i) {
+		struct lb_pcpu_stats *team_lb_stats;
+		team_lb_stats = per_cpu_ptr(lb_priv->pcpu_stats, i);
+		u64_stats_init(&team_lb_stats->syncp);
+	}
+
+
 	INIT_DELAYED_WORK(&lb_priv->ex->stats.refresh_dw, lb_stats_refresh);
 
 	err = team_options_register(team, lb_options, ARRAY_SIZE(lb_options));
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index eee1f19ef1e9..46e83e3fe999 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -230,10 +230,18 @@ static int veth_change_mtu(struct net_device *dev, int new_mtu)
 
 static int veth_dev_init(struct net_device *dev)
 {
+	int i;
+
 	dev->vstats = alloc_percpu(struct pcpu_vstats);
 	if (!dev->vstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_vstats *veth_stats;
+		veth_stats = per_cpu_ptr(dev->vstats, i);
+		u64_stats_init(&veth_stats->syncp);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9fbdfcd1e1a0..ee384f3d612b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1569,6 +1569,14 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (vi->stats == NULL)
 		goto free;
 
+	for_each_possible_cpu(i) {
+		struct virtnet_stats *virtnet_stats;
+		virtnet_stats = per_cpu_ptr(vi->stats, i);
+		u64_stats_init(&virtnet_stats->tx_syncp);
+		u64_stats_init(&virtnet_stats->rx_syncp);
+	}
+
+
 	vi->vq_index = alloc_percpu(int);
 	if (vi->vq_index == NULL)
 		goto free_stats;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2ef5b6219f3f..01ab64d5f9a4 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1884,11 +1884,19 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_sock *vs;
+	int i;
 
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *vxlan_stats;
+		vxlan_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&vxlan_stats->syncp);
+	}
+
+
 	spin_lock(&vn->sock_lock);
 	vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
 	if (vs) {
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 36808bf25677..54223ac6d8a6 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1338,6 +1338,12 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	if (np->stats == NULL)
 		goto exit;
 
+	for_each_possible_cpu(i) {
+		struct netfront_stats *xen_nf_stats;
+		xen_nf_stats = per_cpu_ptr(np->stats, i);
+		u64_stats_init(&xen_nf_stats->syncp);
+	}
+
 	/* Initialise tx_skbs as a free chain containing every entry. */
 	np->tx_skb_freelist = 0;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 8da8c4e87da3..7bfabd20204c 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -67,6 +67,13 @@ struct u64_stats_sync {
 #endif
 };
 
+
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+# define u64_stats_init(syncp)	seqcount_init(syncp.seq)
+#else
+# define u64_stats_init(syncp)	do { } while (0)
+#endif
+
 static inline void u64_stats_update_begin(struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 09bf1c38805b..4deff3ed1da1 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -558,7 +558,7 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0;
+	int subclass = 0, i;
 
 	netif_carrier_off(dev);
 
@@ -612,6 +612,13 @@ static int vlan_dev_init(struct net_device *dev)
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct vlan_pcpu_stats *vlan_stat;
+		vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
+		u64_stats_init(&vlan_stat->syncp);
+	}
+
+
 	return 0;
 }
 
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ca04163635da..7893d641775b 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -88,11 +88,18 @@ out:
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
+	int i;
 
 	br->stats = alloc_percpu(struct br_cpu_netstats);
 	if (!br->stats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct br_cpu_netstats *br_dev_stats;
+		br_dev_stats = per_cpu_ptr(br->stats, i);
+		u64_stats_init(&br_dev_stats->syncp);
+	}
+
 	return 0;
 }
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cfeb85cff4f0..5f4617e377b8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1518,6 +1518,7 @@ int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
 	ptr[0] = __alloc_percpu(mibsize, align);
 	if (!ptr[0])
 		return -ENOMEM;
+
 #if SNMP_ARRAY_SZ == 2
 	ptr[1] = __alloc_percpu(mibsize, align);
 	if (!ptr[1]) {
@@ -1561,6 +1562,8 @@ static const struct net_protocol icmp_protocol = {
 
 static __net_init int ipv4_mib_init_net(struct net *net)
 {
+	int i;
+
 	if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
 			  sizeof(struct tcp_mib),
 			  __alignof__(struct tcp_mib)) < 0)
@@ -1569,6 +1572,17 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 			  sizeof(struct ipstats_mib),
 			  __alignof__(struct ipstats_mib)) < 0)
 		goto err_ip_mib;
+
+	for_each_possible_cpu(i) {
+		struct ipstats_mib *af_inet_stats;
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[0], i);
+		u64_stats_init(&af_inet_stats->syncp);
+#if SNMP_ARRAY_SZ == 2
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[1], i);
+		u64_stats_init(&af_inet_stats->syncp);
+#endif
+	}
+
 	if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
 			  sizeof(struct linux_mib),
 			  __alignof__(struct linux_mib)) < 0)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 63a6d6d6b875..caf01176a5e4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -976,13 +976,19 @@ int ip_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
-	int err;
+	int i, err;
 
 	dev->destructor	= ip_tunnel_dev_free;
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ipt_stats;
+		ipt_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ipt_stats->syncp);
+	}
+
 	err = gro_cells_init(&tunnel->gro_cells, dev);
 	if (err) {
 		free_percpu(dev->tstats);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cd3fb301da38..d62d589bb622 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -281,10 +281,24 @@ static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
 {
+	int i;
+
 	if (snmp_mib_init((void __percpu **)idev->stats.ipv6,
 			  sizeof(struct ipstats_mib),
 			  __alignof__(struct ipstats_mib)) < 0)
 		goto err_ip;
+
+	for_each_possible_cpu(i) {
+		struct ipstats_mib *addrconf_stats;
+		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[0], i);
+		u64_stats_init(&addrconf_stats->syncp);
+#if SNMP_ARRAY_SZ == 2
+		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[1], i);
+		u64_stats_init(&addrconf_stats->syncp);
+#endif
+	}
+
+
 	idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device),
 					GFP_KERNEL);
 	if (!idev->stats.icmpv6dev)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7c96100b021e..a8f8559b3dce 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -719,6 +719,8 @@ static void ipv6_packet_cleanup(void)
 
 static int __net_init ipv6_init_mibs(struct net *net)
 {
+	int i;
+
 	if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6,
 			  sizeof(struct udp_mib),
 			  __alignof__(struct udp_mib)) < 0)
@@ -731,6 +733,18 @@ static int __net_init ipv6_init_mibs(struct net *net)
 			  sizeof(struct ipstats_mib),
 			  __alignof__(struct ipstats_mib)) < 0)
 		goto err_ip_mib;
+
+	for_each_possible_cpu(i) {
+		struct ipstats_mib *af_inet6_stats;
+		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[0], i);
+		u64_stats_init(&af_inet6_stats->syncp);
+#if SNMP_ARRAY_SZ == 2
+		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[1], i);
+		u64_stats_init(&af_inet6_stats->syncp);
+#endif
+	}
+
+
 	if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics,
 			  sizeof(struct icmpv6_mib),
 			  __alignof__(struct icmpv6_mib)) < 0)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index bf4a9a084de5..8acb28621f9c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1252,6 +1252,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 static int ip6gre_tunnel_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
+	int i;
 
 	tunnel = netdev_priv(dev);
 
@@ -1269,6 +1270,13 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ip6gre_tunnel_stats;
+		ip6gre_tunnel_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ip6gre_tunnel_stats->syncp);
+	}
+
+
 	return 0;
 }
 
@@ -1449,6 +1457,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 static int ip6gre_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
+	int i;
 
 	tunnel = netdev_priv(dev);
 
@@ -1462,6 +1471,12 @@ static int ip6gre_tap_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ip6gre_tap_stats;
+		ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ip6gre_tap_stats->syncp);
+	}
+
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 583b77e2f69b..df1fa58528c6 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1494,12 +1494,19 @@ static inline int
 ip6_tnl_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
+	int i;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
+
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ip6_tnl_stats;
+		ip6_tnl_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ip6_tnl_stats->syncp);
+	}
 	return 0;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 19269453a8ea..365dc5473eb2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1310,6 +1310,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 static int ipip6_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1322,6 +1323,12 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ipip6_tunnel_stats;
+		ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ipip6_tunnel_stats->syncp);
+	}
+
 	return 0;
 }
 
@@ -1331,6 +1338,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1344,6 +1352,13 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
+
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *ipip6_fb_stats;
+		ipip6_fb_stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&ipip6_fb_stats->syncp);
+	}
+
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
 	return 0;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a3df9bddc4f7..3825725907f6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -842,7 +842,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 	       struct ip_vs_dest **dest_p)
 {
 	struct ip_vs_dest *dest;
-	unsigned int atype;
+	unsigned int atype, i;
 
 	EnterFunction(2);
 
@@ -869,6 +869,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
 	if (!dest->stats.cpustats)
 		goto err_alloc;
 
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *ip_vs_dest_stats;
+		ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i);
+		u64_stats_init(&ip_vs_dest_stats->syncp);
+	}
+
 	dest->af = svc->af;
 	dest->protocol = svc->protocol;
 	dest->vaddr = svc->addr;
@@ -1134,7 +1140,7 @@ static int
 ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		  struct ip_vs_service **svc_p)
 {
-	int ret = 0;
+	int ret = 0, i;
 	struct ip_vs_scheduler *sched = NULL;
 	struct ip_vs_pe *pe = NULL;
 	struct ip_vs_service *svc = NULL;
@@ -1184,6 +1190,13 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 		goto out_err;
 	}
 
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *ip_vs_stats;
+		ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i);
+		u64_stats_init(&ip_vs_stats->syncp);
+	}
+
+
 	/* I'm the first user of the service */
 	atomic_set(&svc->refcnt, 0);
 
@@ -3780,7 +3793,7 @@ static struct notifier_block ip_vs_dst_notifier = {
 
 int __net_init ip_vs_control_net_init(struct net *net)
 {
-	int idx;
+	int i, idx;
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	/* Initialize rs_table */
@@ -3799,6 +3812,12 @@ int __net_init ip_vs_control_net_init(struct net *net)
 	if (!ipvs->tot_stats.cpustats)
 		return -ENOMEM;
 
+	for_each_possible_cpu(i) {
+		struct ip_vs_cpu_stats *ipvs_tot_stats;
+		ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats.cpustats, i);
+		u64_stats_init(&ipvs_tot_stats->syncp);
+	}
+
 	spin_lock_init(&ipvs->tot_stats.lock);
 
 	proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2aa13bd7f2b2..b92553c02279 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1698,6 +1698,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto err_destroy_table;
 	}
 
+	for_each_possible_cpu(i) {
+		struct dp_stats_percpu *dpath_stats;
+		dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
+		u64_stats_init(&dpath_stats->sync);
+	}
+
 	dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
 			GFP_KERNEL);
 	if (!dp->ports) {
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 6f65dbe13812..d830a95f03a4 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -118,6 +118,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 {
 	struct vport *vport;
 	size_t alloc_size;
+	int i;
 
 	alloc_size = sizeof(struct vport);
 	if (priv_size) {
@@ -141,6 +142,13 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *vport_stats;
+		vport_stats = per_cpu_ptr(vport->percpu_stats, i);
+		u64_stats_init(&vport_stats->syncp);
+	}
+
+
 	spin_lock_init(&vport->stats_lock);
 
 	return vport;
-- 
cgit 


From 1ca7d67cf5d5a2aef26a8d9afd789006fa098347 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 7 Oct 2013 15:51:59 -0700
Subject: seqcount: Add lockdep functionality to seqcount/seqlock structures

Currently seqlocks and seqcounts don't support lockdep.

After running across a seqcount related deadlock in the timekeeping
code, I used a less-refined and more focused variant of this patch
to narrow down the cause of the issue.

This is a first-pass attempt to properly enable lockdep functionality
on seqlocks and seqcounts.

Since seqcounts are used in the vdso gettimeofday code, I've provided
non-lockdep accessors for those needs.

I've also handled one case where there were nested seqlock writers
and there may be more edge cases.

Comments and feedback would be appreciated!

Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/1381186321-4906-3-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/vdso/vclock_gettime.c |  8 ++---
 fs/dcache.c                    |  4 +--
 fs/fs_struct.c                 |  2 +-
 include/linux/init_task.h      |  8 ++---
 include/linux/lockdep.h        |  8 +++--
 include/linux/seqlock.h        | 79 ++++++++++++++++++++++++++++++++++++++----
 mm/filemap_xip.c               |  2 +-
 7 files changed, 90 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 72074d528400..2ada505067cc 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->wall_time_snsec;
@@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
 		ns = gtod->monotonic_time_snsec;
@@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin(&gtod->seq);
+		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
 		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
diff --git a/fs/dcache.c b/fs/dcache.c
index ae6ebb88ceff..f750be22c08c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2574,7 +2574,7 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	dentry_lock_for_move(dentry, target);
 
 	write_seqcount_begin(&dentry->d_seq);
-	write_seqcount_begin(&target->d_seq);
+	write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
 
 	/* __d_drop does write_seqcount_barrier, but they're OK to nest. */
 
@@ -2706,7 +2706,7 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
 	dentry_lock_for_move(anon, dentry);
 
 	write_seqcount_begin(&dentry->d_seq);
-	write_seqcount_begin(&anon->d_seq);
+	write_seqcount_begin_nested(&anon->d_seq, DENTRY_D_LOCK_NESTED);
 
 	dparent = dentry->d_parent;
 
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index d8ac61d0c932..7dca743b2ce1 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -161,6 +161,6 @@ EXPORT_SYMBOL(current_umask);
 struct fs_struct init_fs = {
 	.users		= 1,
 	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
-	.seq		= SEQCNT_ZERO,
+	.seq		= SEQCNT_ZERO(init_fs.seq),
 	.umask		= 0022,
 };
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5cd0f0949927..b0ed422e4e4a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -32,10 +32,10 @@ extern struct fs_struct init_fs;
 #endif
 
 #ifdef CONFIG_CPUSETS
-#define INIT_CPUSET_SEQ							\
-	.mems_allowed_seq = SEQCNT_ZERO,
+#define INIT_CPUSET_SEQ(tsk)							\
+	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
 #else
-#define INIT_CPUSET_SEQ
+#define INIT_CPUSET_SEQ(tsk)
 #endif
 
 #define INIT_SIGNALS(sig) {						\
@@ -220,7 +220,7 @@ extern struct task_group root_task_group;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
-	INIT_CPUSET_SEQ							\
+	INIT_CPUSET_SEQ(tsk)						\
 	INIT_VTIME(tsk)							\
 }
 
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index cfc2f119779a..92b1bfc5da60 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -497,6 +497,10 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define rwlock_acquire_read(l, s, t, i)		lock_acquire_shared_recursive(l, s, t, NULL, i)
 #define rwlock_release(l, n, i)			lock_release(l, n, i)
 
+#define seqcount_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
+#define seqcount_acquire_read(l, s, t, i)	lock_acquire_shared_recursive(l, s, t, NULL, i)
+#define seqcount_release(l, n, i)		lock_release(l, n, i)
+
 #define mutex_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define mutex_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define mutex_release(l, n, i)			lock_release(l, n, i)
@@ -504,11 +508,11 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define rwsem_acquire(l, s, t, i)		lock_acquire_exclusive(l, s, t, NULL, i)
 #define rwsem_acquire_nest(l, s, t, n, i)	lock_acquire_exclusive(l, s, t, n, i)
 #define rwsem_acquire_read(l, s, t, i)		lock_acquire_shared(l, s, t, NULL, i)
-# define rwsem_release(l, n, i)			lock_release(l, n, i)
+#define rwsem_release(l, n, i)			lock_release(l, n, i)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
-# define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
+#define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
 # define might_lock(lock) 						\
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 21a209336e79..1e8a8b6e837d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -34,6 +34,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
+#include <linux/lockdep.h>
 #include <asm/processor.h>
 
 /*
@@ -44,10 +45,50 @@
  */
 typedef struct seqcount {
 	unsigned sequence;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
 } seqcount_t;
 
-#define SEQCNT_ZERO { 0 }
-#define seqcount_init(x)	do { *(x) = (seqcount_t) SEQCNT_ZERO; } while (0)
+static inline void __seqcount_init(seqcount_t *s, const char *name,
+					  struct lock_class_key *key)
+{
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	lockdep_init_map(&s->dep_map, name, key, 0);
+	s->sequence = 0;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define SEQCOUNT_DEP_MAP_INIT(lockname) \
+		.dep_map = { .name = #lockname } \
+
+# define seqcount_init(s)				\
+	do {						\
+		static struct lock_class_key __key;	\
+		__seqcount_init((s), #s, &__key);	\
+	} while (0)
+
+static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
+{
+	seqcount_t *l = (seqcount_t *)s;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_);
+	seqcount_release(&l->dep_map, 1, _RET_IP_);
+	local_irq_restore(flags);
+}
+
+#else
+# define SEQCOUNT_DEP_MAP_INIT(lockname)
+# define seqcount_init(s) __seqcount_init(s, NULL, NULL)
+# define seqcount_lockdep_reader_access(x)
+#endif
+
+#define SEQCNT_ZERO(lockname) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(lockname)}
+
 
 /**
  * __read_seqcount_begin - begin a seq-read critical section (without barrier)
@@ -75,6 +116,22 @@ repeat:
 	return ret;
 }
 
+/**
+ * read_seqcount_begin_no_lockdep - start seq-read critical section w/o lockdep
+ * @s: pointer to seqcount_t
+ * Returns: count to be passed to read_seqcount_retry
+ *
+ * read_seqcount_begin_no_lockdep opens a read critical section of the given
+ * seqcount, but without any lockdep checking. Validity of the critical
+ * section is tested by checking read_seqcount_retry function.
+ */
+static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
+{
+	unsigned ret = __read_seqcount_begin(s);
+	smp_rmb();
+	return ret;
+}
+
 /**
  * read_seqcount_begin - begin a seq-read critical section
  * @s: pointer to seqcount_t
@@ -86,9 +143,8 @@ repeat:
  */
 static inline unsigned read_seqcount_begin(const seqcount_t *s)
 {
-	unsigned ret = __read_seqcount_begin(s);
-	smp_rmb();
-	return ret;
+	seqcount_lockdep_reader_access(s);
+	return read_seqcount_begin_no_lockdep(s);
 }
 
 /**
@@ -108,6 +164,8 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = ACCESS_ONCE(s->sequence);
+
+	seqcount_lockdep_reader_access(s);
 	smp_rmb();
 	return ret & ~1;
 }
@@ -152,14 +210,21 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
-static inline void write_seqcount_begin(seqcount_t *s)
+static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
 	s->sequence++;
 	smp_wmb();
+	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
+}
+
+static inline void write_seqcount_begin(seqcount_t *s)
+{
+	write_seqcount_begin_nested(s, 0);
 }
 
 static inline void write_seqcount_end(seqcount_t *s)
 {
+	seqcount_release(&s->dep_map, 1, _RET_IP_);
 	smp_wmb();
 	s->sequence++;
 }
@@ -188,7 +253,7 @@ typedef struct {
  */
 #define __SEQLOCK_UNLOCKED(lockname)			\
 	{						\
-		.seqcount = SEQCNT_ZERO,		\
+		.seqcount = SEQCNT_ZERO(lockname),	\
 		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
 	}
 
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 28fe26b64f8a..d8d9fe3f685c 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -26,7 +26,7 @@
  * of ZERO_PAGE(), such as /dev/zero
  */
 static DEFINE_MUTEX(xip_sparse_mutex);
-static seqcount_t xip_sparse_seq = SEQCNT_ZERO;
+static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq);
 static struct page *__xip_sparse_page;
 
 /* called under xip_sparse_mutex */
-- 
cgit 


From db751fe3ea6880ff5ac5abe60cb7b80deb5a4140 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 7 Oct 2013 15:52:00 -0700
Subject: cpuset: Fix potential deadlock w/ set_mems_allowed

After adding lockdep support to seqlock/seqcount structures,
I started seeing the following warning:

[    1.070907] ======================================================
[    1.072015] [ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ]
[    1.073181] 3.11.0+ #67 Not tainted
[    1.073801] ------------------------------------------------------
[    1.074882] kworker/u4:2/708 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
[    1.076088]  (&p->mems_allowed_seq){+.+...}, at: [<ffffffff81187d7f>] new_slab+0x5f/0x280
[    1.077572]
[    1.077572] and this task is already holding:
[    1.078593]  (&(&q->__queue_lock)->rlock){..-...}, at: [<ffffffff81339f03>] blk_execute_rq_nowait+0x53/0xf0
[    1.080042] which would create a new lock dependency:
[    1.080042]  (&(&q->__queue_lock)->rlock){..-...} -> (&p->mems_allowed_seq){+.+...}
[    1.080042]
[    1.080042] but this new dependency connects a SOFTIRQ-irq-safe lock:
[    1.080042]  (&(&q->__queue_lock)->rlock){..-...}
[    1.080042] ... which became SOFTIRQ-irq-safe at:
[    1.080042]   [<ffffffff810ec179>] __lock_acquire+0x5b9/0x1db0
[    1.080042]   [<ffffffff810edfe5>] lock_acquire+0x95/0x130
[    1.080042]   [<ffffffff818968a1>] _raw_spin_lock+0x41/0x80
[    1.080042]   [<ffffffff81560c9e>] scsi_device_unbusy+0x7e/0xd0
[    1.080042]   [<ffffffff8155a612>] scsi_finish_command+0x32/0xf0
[    1.080042]   [<ffffffff81560e91>] scsi_softirq_done+0xa1/0x130
[    1.080042]   [<ffffffff8133b0f3>] blk_done_softirq+0x73/0x90
[    1.080042]   [<ffffffff81095dc0>] __do_softirq+0x110/0x2f0
[    1.080042]   [<ffffffff81095fcd>] run_ksoftirqd+0x2d/0x60
[    1.080042]   [<ffffffff810bc506>] smpboot_thread_fn+0x156/0x1e0
[    1.080042]   [<ffffffff810b3916>] kthread+0xd6/0xe0
[    1.080042]   [<ffffffff818980ac>] ret_from_fork+0x7c/0xb0
[    1.080042]
[    1.080042] to a SOFTIRQ-irq-unsafe lock:
[    1.080042]  (&p->mems_allowed_seq){+.+...}
[    1.080042] ... which became SOFTIRQ-irq-unsafe at:
[    1.080042] ...  [<ffffffff810ec1d3>] __lock_acquire+0x613/0x1db0
[    1.080042]   [<ffffffff810edfe5>] lock_acquire+0x95/0x130
[    1.080042]   [<ffffffff810b3df2>] kthreadd+0x82/0x180
[    1.080042]   [<ffffffff818980ac>] ret_from_fork+0x7c/0xb0
[    1.080042]
[    1.080042] other info that might help us debug this:
[    1.080042]
[    1.080042]  Possible interrupt unsafe locking scenario:
[    1.080042]
[    1.080042]        CPU0                    CPU1
[    1.080042]        ----                    ----
[    1.080042]   lock(&p->mems_allowed_seq);
[    1.080042]                                local_irq_disable();
[    1.080042]                                lock(&(&q->__queue_lock)->rlock);
[    1.080042]                                lock(&p->mems_allowed_seq);
[    1.080042]   <Interrupt>
[    1.080042]     lock(&(&q->__queue_lock)->rlock);
[    1.080042]
[    1.080042]  *** DEADLOCK ***

The issue stems from the kthreadd() function calling set_mems_allowed
with irqs enabled. While its possibly unlikely for the actual deadlock
to trigger, a fix is fairly simple: disable irqs before taking the
mems_allowed_seq lock.

Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/1381186321-4906-4-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/cpuset.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index cc1b01cf2035..3fe661fe96d1 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -110,10 +110,14 @@ static inline bool put_mems_allowed(unsigned int seq)
 
 static inline void set_mems_allowed(nodemask_t nodemask)
 {
+	unsigned long flags;
+
 	task_lock(current);
+	local_irq_save(flags);
 	write_seqcount_begin(&current->mems_allowed_seq);
 	current->mems_allowed = nodemask;
 	write_seqcount_end(&current->mems_allowed_seq);
+	local_irq_restore(flags);
 	task_unlock(current);
 }
 
-- 
cgit 


From 7aeb7448d8d02868ef30a6d08e856b2220319273 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 24 Oct 2013 01:24:54 -0700
Subject: drm/ttm: Enable the dma page pool also for intel IOMMUs

Used by the vmwgfx driver

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/gpu/drm/ttm/Makefile             |  6 +-----
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c |  3 +++
 include/drm/ttm/ttm_page_alloc.h         | 11 ++++++++++-
 3 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile
index b2b33dde2afb..b433b9f040c9 100644
--- a/drivers/gpu/drm/ttm/Makefile
+++ b/drivers/gpu/drm/ttm/Makefile
@@ -5,10 +5,6 @@ ccflags-y := -Iinclude/drm
 ttm-y := ttm_agp_backend.o ttm_memory.o ttm_tt.o ttm_bo.o \
 	ttm_bo_util.o ttm_bo_vm.o ttm_module.o \
 	ttm_object.o ttm_lock.o ttm_execbuf_util.o ttm_page_alloc.o \
-	ttm_bo_manager.o
-
-ifeq ($(CONFIG_SWIOTLB),y)
-ttm-y += ttm_page_alloc_dma.o
-endif
+	ttm_bo_manager.o ttm_page_alloc_dma.o
 
 obj-$(CONFIG_DRM_TTM) += ttm.o
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 7957beeeaf73..fb8259f69839 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -33,6 +33,7 @@
  *   when freed).
  */
 
+#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
 #define pr_fmt(fmt) "[TTM] " fmt
 
 #include <linux/dma-mapping.h>
@@ -1142,3 +1143,5 @@ int ttm_dma_page_alloc_debugfs(struct seq_file *m, void *data)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_page_alloc_debugfs);
+
+#endif
diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h
index 706b962c6467..d1f61bfe0ebe 100644
--- a/include/drm/ttm/ttm_page_alloc.h
+++ b/include/drm/ttm/ttm_page_alloc.h
@@ -62,7 +62,7 @@ extern void ttm_pool_unpopulate(struct ttm_tt *ttm);
 extern int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
 
 
-#ifdef CONFIG_SWIOTLB
+#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
 /**
  * Initialize pool allocator.
  */
@@ -94,6 +94,15 @@ static inline int ttm_dma_page_alloc_debugfs(struct seq_file *m, void *data)
 {
 	return 0;
 }
+static inline int ttm_dma_populate(struct ttm_dma_tt *ttm_dma,
+				   struct device *dev)
+{
+	return -ENOMEM;
+}
+static inline void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma,
+				      struct device *dev)
+{
+}
 #endif
 
 #endif
-- 
cgit 


From 3820b4d2789f5166afdb136bb14f93166e6cfbc2 Mon Sep 17 00:00:00 2001
From: "David A. Long" <dave.long@linaro.org>
Date: Tue, 15 Oct 2013 17:04:16 -0400
Subject: uprobes: Move function declarations out of arch

Move the function declarations from the arch headers to the common
header, since only the function bodies are architecture-specific.
These changes are from Vincent Rabin's uprobes patch.

[ oleg: update arch/powerpc/include/asm/uprobes.h ]

Signed-off-by: Rabin Vincent <rabin@rab.in>
Signed-off-by: David A. Long <dave.long@linaro.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 arch/powerpc/include/asm/uprobes.h | 7 -------
 arch/x86/include/asm/uprobes.h     | 7 -------
 include/linux/uprobes.h            | 8 ++++++++
 3 files changed, 8 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index 23016020915e..b6fc3178372a 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -45,11 +45,4 @@ struct arch_uprobe_task {
 	unsigned long	saved_trap_nr;
 };
 
-extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
-extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
-extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
-extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 6e5197910fd8..b20b4d68b934 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -49,11 +49,4 @@ struct arch_uprobe_task {
 	unsigned int			saved_tf;
 };
 
-extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
-extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
-extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
-extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 9e0d5a6fe7a8..28473e3f6068 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -30,6 +30,7 @@
 struct vm_area_struct;
 struct mm_struct;
 struct inode;
+struct notifier_block;
 
 #ifdef CONFIG_ARCH_SUPPORTS_UPROBES
 # include <asm/uprobes.h>
@@ -125,6 +126,13 @@ extern void uprobe_notify_resume(struct pt_regs *regs);
 extern bool uprobe_deny_signal(void);
 extern bool arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void uprobe_clear_state(struct mm_struct *mm);
+extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
+extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
+extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
+extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
-- 
cgit 


From f72d41fa902fb19a9b63028202a400b0ce497491 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 5 Nov 2013 19:50:39 +0100
Subject: uprobes: Export write_opcode() as uprobe_write_opcode()

set_swbp() and set_orig_insn() are __weak, but this is pointless
because write_opcode() is static.

Export write_opcode() as uprobe_write_opcode() for the upcoming
arm port, this way it can actually override set_swbp() and use
__opcode_to_mem_arm(bpinsn) instead if UPROBE_SWBP_INSN.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/uprobes.h |  1 +
 kernel/events/uprobes.c | 14 +++++++-------
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 28473e3f6068..319eae70fe84 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -109,6 +109,7 @@ extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsign
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
+extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index fbcff61b5099..0ac346ae5edb 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -245,12 +245,12 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * the architecture. If an arch has variable length instruction and the
  * breakpoint instruction is not of the smallest length instruction
  * supported by that architecture then we need to modify is_trap_at_addr and
- * write_opcode accordingly. This would never be a problem for archs that
- * have fixed length instructions.
+ * uprobe_write_opcode accordingly. This would never be a problem for archs
+ * that have fixed length instructions.
  */
 
 /*
- * write_opcode - write the opcode at a given virtual address.
+ * uprobe_write_opcode - write the opcode at a given virtual address.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
@@ -261,7 +261,7 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * For mm @mm, write the opcode at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
+int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
 			uprobe_opcode_t opcode)
 {
 	struct page *old_page, *new_page;
@@ -315,7 +315,7 @@ put_old:
  */
 int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
+	return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
 }
 
 /**
@@ -330,7 +330,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -577,7 +577,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	if (ret)
 		goto out;
 
-	/* write_opcode() assumes we don't cross page boundary */
+	/* uprobe_write_opcode() assumes we don't cross page boundary */
 	BUG_ON((uprobe->offset & ~PAGE_MASK) +
 			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
 
-- 
cgit 


From 042b10d83d05174e50ee861ee3aca55fd6204324 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 6 Nov 2013 12:19:37 -0500
Subject: tracing: Remove unused function ftrace_off_permanent()

In the past, ftrace_off_permanent() was called if something
strange was detected. But the ftrace_bug() now handles all the
anomolies that can happen with ftrace (function tracing), and there
are no uses of ftrace_off_permanent(). Get rid of it.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/kernel.h |  2 --
 kernel/trace/trace.c   | 15 ---------------
 2 files changed, 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 672ddc4de4af..d4e98d13eff4 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -501,7 +501,6 @@ void tracing_snapshot_alloc(void);
 
 extern void tracing_start(void);
 extern void tracing_stop(void);
-extern void ftrace_off_permanent(void);
 
 static inline __printf(1, 2)
 void ____trace_printk_check_format(const char *fmt, ...)
@@ -639,7 +638,6 @@ extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
 #else
 static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
-static inline void ftrace_off_permanent(void) { }
 static inline void trace_dump_stack(int skip) { }
 
 static inline void tracing_on(void) { }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a595cf14f1c..d72a15c0b32c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1283,21 +1283,6 @@ int is_tracing_stopped(void)
 	return global_trace.stop_count;
 }
 
-/**
- * ftrace_off_permanent - disable all ftrace code permanently
- *
- * This should only be called when a serious anomally has
- * been detected.  This will turn off the function tracing,
- * ring buffers, and other tracing utilites. It takes no
- * locks and can be called from any context.
- */
-void ftrace_off_permanent(void)
-{
-	tracing_disabled = 1;
-	ftrace_stop();
-	tracing_off_permanent();
-}
-
 /**
  * tracing_start - quick start of the tracer
  *
-- 
cgit 


From 0e4ccb1505a9e29c50170742ce26ac4655baab2d Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 6 Nov 2013 16:16:56 -0500
Subject: PCI: Add x86_msi.msi_mask_irq() and msix_mask_irq()

Certain platforms do not allow writes in the MSI-X BARs to setup or tear
down vector values.  To combat against the generic code trying to write to
that and either silently being ignored or crashing due to the pagetables
being marked R/O this patch introduces a platform override.

Note that we keep two separate, non-weak, functions default_mask_msi_irqs()
and default_mask_msix_irqs() for the behavior of the arch_mask_msi_irqs()
and arch_mask_msix_irqs(), as the default behavior is needed by x86 PCI
code.

For Xen, which does not allow the guest to write to MSI-X tables - as the
hypervisor is solely responsible for setting the vector values - we
implement two nops.

This fixes a Xen guest crash when passing a PCI device with MSI-X to the
guest.  See the bugzilla for more details.

[bhelgaas: add bugzilla info]
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=64581
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
CC: Zhenzhong Duan <zhenzhong.duan@oracle.com>
---
 arch/x86/include/asm/x86_init.h |  3 +++
 arch/x86/kernel/x86_init.c      | 10 ++++++++++
 arch/x86/pci/xen.c              | 13 ++++++++++++-
 drivers/pci/msi.c               | 22 ++++++++++++++++------
 include/linux/msi.h             |  2 ++
 5 files changed, 43 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 828a1565ba57..0f1be11e43d2 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -172,6 +172,7 @@ struct x86_platform_ops {
 
 struct pci_dev;
 struct msi_msg;
+struct msi_desc;
 
 struct x86_msi_ops {
 	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
@@ -182,6 +183,8 @@ struct x86_msi_ops {
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
 	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
+	u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
+	u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);
 };
 
 struct IO_APIC_route_entry;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 8ce0072cd700..021783b1f46a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -116,6 +116,8 @@ struct x86_msi_ops x86_msi = {
 	.teardown_msi_irqs	= default_teardown_msi_irqs,
 	.restore_msi_irqs	= default_restore_msi_irqs,
 	.setup_hpet_msi		= default_setup_hpet_msi,
+	.msi_mask_irq		= default_msi_mask_irq,
+	.msix_mask_irq		= default_msix_mask_irq,
 };
 
 /* MSI arch specific hooks */
@@ -138,6 +140,14 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq)
 {
 	x86_msi.restore_msi_irqs(dev, irq);
 }
+u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	return x86_msi.msi_mask_irq(desc, mask, flag);
+}
+u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	return x86_msi.msix_mask_irq(desc, flag);
+}
 #endif
 
 struct x86_io_apic_ops x86_io_apic_ops = {
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 48e8461057ba..5eee4959785d 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -382,7 +382,14 @@ static void xen_teardown_msi_irq(unsigned int irq)
 {
 	xen_destroy_irq(irq);
 }
-
+static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	return 0;
+}
+static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	return 0;
+}
 #endif
 
 int __init pci_xen_init(void)
@@ -406,6 +413,8 @@ int __init pci_xen_init(void)
 	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
 	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
 	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
+	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
+	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 #endif
 	return 0;
 }
@@ -485,6 +494,8 @@ int __init pci_xen_initial_domain(void)
 	x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
 	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
 	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
+	x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
+	x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
 #endif
 	xen_setup_acpi_sci();
 	__acpi_register_gsi = acpi_register_gsi_xen;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 604265c40853..5e63645a7abe 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -185,7 +185,7 @@ static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
  * reliably as devices without an INTx disable bit will then generate a
  * level IRQ which will never be cleared.
  */
-static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 
@@ -199,9 +199,14 @@ static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 	return mask_bits;
 }
 
+__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	return default_msi_mask_irq(desc, mask, flag);
+}
+
 static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
-	desc->masked = __msi_mask_irq(desc, mask, flag);
+	desc->masked = arch_msi_mask_irq(desc, mask, flag);
 }
 
 /*
@@ -211,7 +216,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
  * file.  This saves a few milliseconds when initialising devices with lots
  * of MSI-X interrupts.
  */
-static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
+u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
@@ -224,9 +229,14 @@ static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
 	return mask_bits;
 }
 
+__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	return default_msix_mask_irq(desc, flag);
+}
+
 static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
-	desc->masked = __msix_mask_irq(desc, flag);
+	desc->masked = arch_msix_mask_irq(desc, flag);
 }
 
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
@@ -902,7 +912,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
 	mask = msi_capable_mask(ctrl);
 	/* Keep cached state to be restored */
-	__msi_mask_irq(desc, mask, ~mask);
+	arch_msi_mask_irq(desc, mask, ~mask);
 
 	/* Restore dev->irq to its default pin-assertion irq */
 	dev->irq = desc->msi_attrib.default_irq;
@@ -998,7 +1008,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI-X masked as initial states */
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		/* Keep cached states to be restored */
-		__msix_mask_irq(entry, 1);
+		arch_msix_mask_irq(entry, 1);
 	}
 
 	msix_set_enable(dev, 0);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index b17ead818aec..87cce50bd121 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -64,6 +64,8 @@ void arch_restore_msi_irqs(struct pci_dev *dev, int irq);
 
 void default_teardown_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev, int irq);
+u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
+u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag);
 
 struct msi_chip {
 	struct module *owner;
-- 
cgit 


From 5add99cfef416487d32b4b7075fe1a409f3a5e82 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 7 Nov 2013 01:41:39 +0100
Subject: ACPI / hotplug: Simplify device ejection routines

Simplify handle_root_bridge_removal() and acpi_eject_store() by
getting rid of struct acpi_eject_event and passing device objects
directly to async routines executed via acpi_os_hotplug_execute().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
---
 drivers/acpi/pci_root.c | 20 ++------------------
 drivers/acpi/scan.c     | 46 ++++++++++++++++++----------------------------
 include/acpi/acpi_bus.h |  5 -----
 3 files changed, 20 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index d7e53ea53d6c..2c03aaee1006 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -593,27 +593,11 @@ static void handle_root_bridge_insertion(acpi_handle handle)
 static void handle_root_bridge_removal(struct acpi_device *device)
 {
 	acpi_status status;
-	struct acpi_eject_event *ej_event;
-
-	ej_event = kmalloc(sizeof(*ej_event), GFP_KERNEL);
-	if (!ej_event) {
-		/* Inform firmware the hot-remove operation has error */
-		(void) acpi_evaluate_hotplug_ost(device->handle,
-					ACPI_NOTIFY_EJECT_REQUEST,
-					ACPI_OST_SC_NON_SPECIFIC_FAILURE,
-					NULL);
-		return;
-	}
-
-	ej_event->device = device;
-	ej_event->event = ACPI_NOTIFY_EJECT_REQUEST;
 
 	get_device(&device->dev);
-	status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, ej_event);
-	if (ACPI_FAILURE(status)) {
+	status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, device);
+	if (ACPI_FAILURE(status))
 		put_device(&device->dev);
-		kfree(ej_event);
-	}
 }
 
 static void _handle_hotplug_event_root(struct work_struct *work)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 9bdcc187bf4b..cc19d623a18f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -441,18 +441,8 @@ static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 					  NULL);
 }
 
-/**
- * acpi_bus_hot_remove_device: hot-remove a device and its children
- * @context: struct acpi_eject_event pointer (freed in this func)
- *
- * Hot-remove a device and its children. This function frees up the
- * memory space passed by arg context, so that the caller may call
- * this function asynchronously through acpi_os_hotplug_execute().
- */
-void acpi_bus_hot_remove_device(void *context)
+void __acpi_bus_hot_remove_device(struct acpi_device *device, u32 ost_src)
 {
-	struct acpi_eject_event *ej_event = context;
-	struct acpi_device *device = ej_event->device;
 	acpi_handle handle = device->handle;
 	int error;
 
@@ -461,13 +451,21 @@ void acpi_bus_hot_remove_device(void *context)
 
 	error = acpi_scan_hot_remove(device);
 	if (error && handle)
-		acpi_evaluate_hotplug_ost(handle, ej_event->event,
+		acpi_evaluate_hotplug_ost(handle, ost_src,
 					  ACPI_OST_SC_NON_SPECIFIC_FAILURE,
 					  NULL);
 
 	mutex_unlock(&acpi_scan_lock);
 	unlock_device_hotplug();
-	kfree(context);
+}
+
+/**
+ * acpi_bus_hot_remove_device: Hot-remove a device and its children.
+ * @context: Address of the ACPI device object to hot-remove.
+ */
+void acpi_bus_hot_remove_device(void *context)
+{
+	__acpi_bus_hot_remove_device(context, ACPI_NOTIFY_EJECT_REQUEST);
 }
 EXPORT_SYMBOL(acpi_bus_hot_remove_device);
 
@@ -497,15 +495,18 @@ static ssize_t power_state_show(struct device *dev,
 
 static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
 
+static void acpi_eject_store_work(void *context)
+{
+	__acpi_bus_hot_remove_device(context, ACPI_OST_EC_OSPM_EJECT);
+}
+
 static ssize_t
 acpi_eject_store(struct device *d, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct acpi_device *acpi_device = to_acpi_device(d);
-	struct acpi_eject_event *ej_event;
 	acpi_object_type not_used;
 	acpi_status status;
-	int ret;
 
 	if (!count || buf[0] != '1')
 		return -EINVAL;
@@ -518,28 +519,17 @@ acpi_eject_store(struct device *d, struct device_attribute *attr,
 	if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable)
 		return -ENODEV;
 
-	ej_event = kmalloc(sizeof(*ej_event), GFP_KERNEL);
-	if (!ej_event) {
-		ret = -ENOMEM;
-		goto err_out;
-	}
 	acpi_evaluate_hotplug_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
 				  ACPI_OST_SC_EJECT_IN_PROGRESS, NULL);
-	ej_event->device = acpi_device;
-	ej_event->event = ACPI_OST_EC_OSPM_EJECT;
 	get_device(&acpi_device->dev);
-	status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, ej_event);
+	status = acpi_os_hotplug_execute(acpi_eject_store_work, acpi_device);
 	if (ACPI_SUCCESS(status))
 		return count;
 
 	put_device(&acpi_device->dev);
-	kfree(ej_event);
-	ret = status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
-
- err_out:
 	acpi_evaluate_hotplug_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
 				  ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL);
-	return ret;
+	return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN;
 }
 
 static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 02e113bb8b7d..06b644ca052c 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -339,11 +339,6 @@ struct acpi_bus_event {
 	u32 data;
 };
 
-struct acpi_eject_event {
-	struct acpi_device	*device;
-	u32		event;
-};
-
 struct acpi_hp_work {
 	struct work_struct work;
 	acpi_handle handle;
-- 
cgit 


From ace8238b00eafd493b8dbcc7db813ed72b8b6e87 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 7 Nov 2013 01:41:48 +0100
Subject: ACPI / hotplug: Make acpi_bus_hot_remove_device() internal

Notice that handle_root_bridge_removal() is the only user of
acpi_bus_hot_remove_device(), so it doesn't have to be exported
any more and can be made internal to the ACPI core.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
---
 drivers/acpi/internal.h | 1 +
 drivers/acpi/pci_root.c | 2 ++
 drivers/acpi/scan.c     | 1 -
 include/acpi/acpi_bus.h | 1 -
 4 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index ebc3ad0a188d..6c79ae69d344 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -87,6 +87,7 @@ void acpi_device_add_finalize(struct acpi_device *device);
 void acpi_free_pnp_ids(struct acpi_device_pnp *pnp);
 int acpi_bind_one(struct device *dev, acpi_handle handle);
 int acpi_unbind_one(struct device *dev);
+void acpi_bus_hot_remove_device(void *context);
 
 /* --------------------------------------------------------------------------
                                   Power Resource
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 2c03aaee1006..add408b07c93 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -39,6 +39,8 @@
 #include <acpi/acpi_drivers.h>
 #include <acpi/apei.h>
 
+#include "internal.h"
+
 #define PREFIX "ACPI: "
 
 #define _COMPONENT		ACPI_PCI_COMPONENT
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index cc19d623a18f..1217ba33f8bf 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -467,7 +467,6 @@ void acpi_bus_hot_remove_device(void *context)
 {
 	__acpi_bus_hot_remove_device(context, ACPI_NOTIFY_EJECT_REQUEST);
 }
-EXPORT_SYMBOL(acpi_bus_hot_remove_device);
 
 static ssize_t real_power_state_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 06b644ca052c..eb37a6fb8665 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -386,7 +386,6 @@ int acpi_scan_add_handler(struct acpi_scan_handler *handler);
 int acpi_bus_register_driver(struct acpi_driver *driver);
 void acpi_bus_unregister_driver(struct acpi_driver *driver);
 int acpi_bus_scan(acpi_handle handle);
-void acpi_bus_hot_remove_device(void *context);
 void acpi_bus_trim(struct acpi_device *start);
 acpi_status acpi_bus_get_ejd(acpi_handle handle, acpi_handle * ejd);
 int acpi_match_device_ids(struct acpi_device *device,
-- 
cgit 


From f9bddcdf1fbbbab4996e079c5ea614baa1803b47 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 5 Nov 2013 14:13:47 -0800
Subject: udp: Remove unnecessary semicolon from do{}while (0) macro

Just an unnecessary semicolon that should be removed...

Whitespace neatening of macro too.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/udp.h b/include/net/udp.h
index fe4ba9f32429..a24f0f3e107f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -230,13 +230,13 @@ struct sock *__udp6_lib_lookup(struct net *net,
 } while(0)
 
 #if IS_ENABLED(CONFIG_IPV6)
-#define UDPX_INC_STATS_BH(sk, field) \
-	do { \
-		if ((sk)->sk_family == AF_INET) \
-			UDP_INC_STATS_BH(sock_net(sk), field, 0); \
-		else \
-			UDP6_INC_STATS_BH(sock_net(sk), field, 0); \
-	} while (0);
+#define UDPX_INC_STATS_BH(sk, field)					\
+do {									\
+	if ((sk)->sk_family == AF_INET)					\
+		UDP_INC_STATS_BH(sock_net(sk), field, 0);		\
+	else								\
+		UDP6_INC_STATS_BH(sock_net(sk), field, 0);		\
+} while (0)
 #else
 #define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(sock_net(sk), field, 0)
 #endif
-- 
cgit 


From f83c3838b9146b891d0405d3a83660e8f6aed02f Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Date: Sun, 13 Oct 2013 18:05:23 -0300
Subject: mtd: Move major number definitions to major.h

This patch moves the char and block major number definitions
to major.h to be with the rest of the major numbers.
While doing this, include major.h in the files that need it.

Signed-off-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/devices/block2mtd.c | 1 +
 drivers/mtd/mtdblock.c          | 1 +
 drivers/mtd/mtdblock_ro.c       | 1 +
 drivers/mtd/mtdchar.c           | 1 +
 drivers/mtd/mtdcore.c           | 1 +
 drivers/mtd/mtdsuper.c          | 1 +
 drivers/mtd/ubi/build.c         | 1 +
 include/linux/mtd/mtd.h         | 3 ---
 include/uapi/linux/major.h      | 2 ++
 9 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 5cb4c04726b2..d9fd87a4c8dc 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -20,6 +20,7 @@
 #include <linux/mutex.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/major.h>
 
 /* Info for the block device */
 struct block2mtd_dev {
diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c
index 53884cc25916..485ea751c7f9 100644
--- a/drivers/mtd/mtdblock.c
+++ b/drivers/mtd/mtdblock.c
@@ -32,6 +32,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/blktrans.h>
 #include <linux/mutex.h>
+#include <linux/major.h>
 
 
 struct mtdblk_dev {
diff --git a/drivers/mtd/mtdblock_ro.c b/drivers/mtd/mtdblock_ro.c
index 70d27b4d632b..fb5dc89369de 100644
--- a/drivers/mtd/mtdblock_ro.c
+++ b/drivers/mtd/mtdblock_ro.c
@@ -24,6 +24,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/blktrans.h>
 #include <linux/module.h>
+#include <linux/major.h>
 
 static int mtdblock_readsect(struct mtd_blktrans_dev *dev,
 			      unsigned long block, char *buf)
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 684bfa39e4ee..9aa0c5e49c1d 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -32,6 +32,7 @@
 #include <linux/mount.h>
 #include <linux/blkpg.h>
 #include <linux/magic.h>
+#include <linux/major.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/map.h>
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 92311a56939f..7189089d87e3 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -37,6 +37,7 @@
 #include <linux/backing-dev.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/major.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index 334da5f583c0..20c02a3b7417 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -17,6 +17,7 @@
 #include <linux/export.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
+#include <linux/major.h>
 
 /*
  * compare superblocks to see if they're equivalent
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 315dcc6ec1f5..e05dc6298c1d 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -41,6 +41,7 @@
 #include <linux/kthread.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/major.h>
 #include "ubi.h"
 
 /* Maximum length of the 'mtd=' parameter */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 88409b813418..8cc0e2fb6894 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -29,9 +29,6 @@
 
 #include <asm/div64.h>
 
-#define MTD_CHAR_MAJOR 90
-#define MTD_BLOCK_MAJOR 31
-
 #define MTD_ERASE_PENDING	0x01
 #define MTD_ERASING		0x02
 #define MTD_ERASE_SUSPEND	0x04
diff --git a/include/uapi/linux/major.h b/include/uapi/linux/major.h
index 6a8ca98c9a96..620252e69b44 100644
--- a/include/uapi/linux/major.h
+++ b/include/uapi/linux/major.h
@@ -54,6 +54,7 @@
 #define ACSI_MAJOR		28
 #define AZTECH_CDROM_MAJOR	29
 #define FB_MAJOR		29   /* /dev/fb* framebuffers */
+#define MTD_BLOCK_MAJOR		31
 #define CM206_CDROM_MAJOR	32
 #define IDE2_MAJOR		33
 #define IDE3_MAJOR		34
@@ -105,6 +106,7 @@
 #define IDE6_MAJOR		88
 #define IDE7_MAJOR		89
 #define IDE8_MAJOR		90
+#define MTD_CHAR_MAJOR		90
 #define IDE9_MAJOR		91
 
 #define DASD_MAJOR		94
-- 
cgit 


From a4d62babf988fe5dfde24437fa135ef147bc7aa0 Mon Sep 17 00:00:00 2001
From: Wang Haitao <wang.haitao1@zte.com.cn>
Date: Thu, 22 Aug 2013 19:32:38 +0800
Subject: mtd: map: fixed bug in 64-bit systems

Hardware:
	CPU: XLP832,the 64-bit OS
	NOR Flash:S29GL128S 128M
Software:
	Kernel:2.6.32.41
	Filesystem:JFFS2
When writing files, errors appear:
	Write len 182  but return retlen 180
	Write of 182 bytes at 0x072c815c failed. returned -5, retlen 180
	Write len 186  but return retlen 184
	Write of 186 bytes at 0x072caff4 failed. returned -5, retlen 184
These errors exist only in 64-bit systems,not in 32-bit systems. After analysis, we
found that the left shift operation is wrong in map_word_load_partial. For instance:
	unsigned char buf[3] ={0x9e,0x3a,0xea};
	map_bankwidth(map) is 4;
	for (i=0; i < 3; i++) {
		int bitpos;
		bitpos = (map_bankwidth(map)-1-i)*8;
		orig.x[0] &= ~(0xff << bitpos);
		orig.x[0] |= buf[i] << bitpos;
	}

The value of orig.x[0] is expected to be 0x9e3aeaff, but in this situation(64-bit
System) we'll get the wrong value of 0xffffffff9e3aeaff due to the 64-bit sign
extension:
buf[i] is defined as "unsigned char" and the left-shift operation will convert it
to the type of "signed int", so when left-shift buf[i] by 24 bits, the final result
will get the wrong value: 0xffffffff9e3aeaff.

If the left-shift bits are less than 24, then sign extension will not occur. Whereas
the bankwidth of the nor flash we used is 4, therefore this BUG emerges.

Signed-off-by: Pang Xunlei <pang.xunlei@zte.com.cn>
Signed-off-by: Zhang Yi <zhang.yi20@zte.com.cn>
Signed-off-by: Lu Zhongjun <lu.zhongjun@zte.com.cn>
Cc: <stable@vger.kernel.org>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/map.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 4b02512e421c..5f487d776411 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -365,7 +365,7 @@ static inline map_word map_word_load_partial(struct map_info *map, map_word orig
 			bitpos = (map_bankwidth(map)-1-i)*8;
 #endif
 			orig.x[0] &= ~(0xff << bitpos);
-			orig.x[0] |= buf[i-start] << bitpos;
+			orig.x[0] |= (unsigned long)buf[i-start] << bitpos;
 		}
 	}
 	return orig;
@@ -384,7 +384,7 @@ static inline map_word map_word_ff(struct map_info *map)
 
 	if (map_bankwidth(map) < MAP_FF_LIMIT) {
 		int bw = 8 * map_bankwidth(map);
-		r.x[0] = (1 << bw) - 1;
+		r.x[0] = (1UL << bw) - 1;
 	} else {
 		for (i=0; i<map_words(map); i++)
 			r.x[i] = ~0UL;
-- 
cgit 


From ac65caf514ec3e55e8d3d510ee37f80dd97418fe Mon Sep 17 00:00:00 2001
From: Pekon Gupta <pekon@ti.com>
Date: Thu, 24 Oct 2013 18:20:17 +0530
Subject: ARM: OMAP2+: cleaned-up DT support of various ECC schemes

OMAP NAND driver support multiple ECC scheme, which can used in different
flavours, depending on in-build Hardware engines present on SoC.

This patch updates following in DT bindings related to sectionion of ecc-schemes
- ti,elm-id: replaces elm_id (maintains backward compatibility)
- ti,nand-ecc-opts: selection of h/w or s/w implementation of an ecc-scheme
	depends on ti,elm-id. (supported values ham1, bch4, and bch8)
- maintain backward compatibility to deprecated DT bindings (sw, hw, hw-romcode)

Below table shows different flavours of ecc-schemes supported by OMAP devices
+---------------------------------------+---------------+---------------+
| ECC scheme                            |ECC calculation|Error detection|
+---------------------------------------+---------------+---------------+
|OMAP_ECC_HAM1_CODE_HW                  |H/W (GPMC)     |S/W            |
+---------------------------------------+---------------+---------------+
|OMAP_ECC_BCH8_CODE_HW_DETECTION_SW     |H/W (GPMC)     |S/W            |
|(requires CONFIG_MTD_NAND_ECC_BCH)     |               |               |
+---------------------------------------+---------------+---------------+
|OMAP_ECC_BCH8_CODE_HW                  |H/W (GPMC)     |H/W (ELM)      |
|(requires CONFIG_MTD_NAND_OMAP_BCH &&  |               |               |
| ti,elm-id in DT)                      |               |               |
+---------------------------------------+---------------+---------------+

To optimize footprint of omap2-nand driver, selection of some ECC schemes
also require enabling following Kconfigs, in addition to setting appropriate
DT bindings
- Kconfig:CONFIG_MTD_NAND_ECC_BCH        error detection done in software
- Kconfig:CONFIG_MTD_NAND_OMAP_BCH       error detection done by h/w engine

Signed-off-by: Pekon Gupta <pekon@ti.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 .../devicetree/bindings/mtd/gpmc-nand.txt          |  8 +++-
 arch/arm/mach-omap2/gpmc.c                         | 48 +++++++++++++++-------
 include/linux/platform_data/mtd-nand-omap2.h       | 13 +++++-
 3 files changed, 51 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index df338cb5059c..bfe07e152738 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -36,8 +36,12 @@ Optional properties:
 		"prefetch-dma"		Prefetch enabled sDMA mode
 		"prefetch-irq"		Prefetch enabled irq mode
 
- - elm_id:	Specifies elm device node. This is required to support BCH
- 		error correction using ELM module.
+ - elm_id:	<deprecated> use "ti,elm-id" instead
+ - ti,elm-id:	Specifies phandle of the ELM devicetree node.
+		ELM is an on-chip hardware engine on TI SoC which is used for
+		locating ECC errors for BCHx algorithms. SoC devices which have
+		ELM hardware engines should specify this device node in .dtsi
+		Using ELM for ECC error correction frees some CPU cycles.
 
 For inline partiton table parsing (optional):
 
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 579697adaae7..c877129142ba 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1341,14 +1341,6 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np,
 
 #ifdef CONFIG_MTD_NAND
 
-static const char * const nand_ecc_opts[] = {
-	[OMAP_ECC_HAMMING_CODE_DEFAULT]		= "sw",
-	[OMAP_ECC_HAMMING_CODE_HW]		= "hw",
-	[OMAP_ECC_HAMMING_CODE_HW_ROMCODE]	= "hw-romcode",
-	[OMAP_ECC_BCH4_CODE_HW]			= "bch4",
-	[OMAP_ECC_BCH8_CODE_HW]			= "bch8",
-};
-
 static const char * const nand_xfer_types[] = {
 	[NAND_OMAP_PREFETCH_POLLED]		= "prefetch-polled",
 	[NAND_OMAP_POLLED]			= "polled",
@@ -1378,13 +1370,41 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 	gpmc_nand_data->cs = val;
 	gpmc_nand_data->of_node = child;
 
-	if (!of_property_read_string(child, "ti,nand-ecc-opt", &s))
-		for (val = 0; val < ARRAY_SIZE(nand_ecc_opts); val++)
-			if (!strcasecmp(s, nand_ecc_opts[val])) {
-				gpmc_nand_data->ecc_opt = val;
-				break;
-			}
+	/* Detect availability of ELM module */
+	gpmc_nand_data->elm_of_node = of_parse_phandle(child, "ti,elm-id", 0);
+	if (gpmc_nand_data->elm_of_node == NULL)
+		gpmc_nand_data->elm_of_node =
+					of_parse_phandle(child, "elm_id", 0);
+	if (gpmc_nand_data->elm_of_node == NULL)
+		pr_warn("%s: ti,elm-id property not found\n", __func__);
+
+	/* select ecc-scheme for NAND */
+	if (of_property_read_string(child, "ti,nand-ecc-opt", &s)) {
+		pr_err("%s: ti,nand-ecc-opt not found\n", __func__);
+		return -ENODEV;
+	}
+	if (!strcmp(s, "ham1") || !strcmp(s, "sw") ||
+		!strcmp(s, "hw") || !strcmp(s, "hw-romcode"))
+		gpmc_nand_data->ecc_opt =
+				OMAP_ECC_HAM1_CODE_HW;
+	else if (!strcmp(s, "bch4"))
+		if (gpmc_nand_data->elm_of_node)
+			gpmc_nand_data->ecc_opt =
+				OMAP_ECC_BCH4_CODE_HW;
+		else
+			gpmc_nand_data->ecc_opt =
+				OMAP_ECC_BCH4_CODE_HW_DETECTION_SW;
+	else if (!strcmp(s, "bch8"))
+		if (gpmc_nand_data->elm_of_node)
+			gpmc_nand_data->ecc_opt =
+				OMAP_ECC_BCH8_CODE_HW;
+		else
+			gpmc_nand_data->ecc_opt =
+				OMAP_ECC_BCH8_CODE_HW_DETECTION_SW;
+	else
+		pr_err("%s: ti,nand-ecc-opt invalid value\n", __func__);
 
+	/* select data transfer mode for NAND controller */
 	if (!of_property_read_string(child, "ti,nand-xfer-type", &s))
 		for (val = 0; val < ARRAY_SIZE(nand_xfer_types); val++)
 			if (!strcasecmp(s, nand_xfer_types[val])) {
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 6bf9ef43ddb1..e4128f1510bf 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -28,8 +28,16 @@ enum omap_ecc {
 	OMAP_ECC_HAMMING_CODE_HW, /* gpmc to detect the error */
 		/* 1-bit ecc: stored at beginning of spare area as romcode */
 	OMAP_ECC_HAMMING_CODE_HW_ROMCODE, /* gpmc method & romcode layout */
-	OMAP_ECC_BCH4_CODE_HW, /* 4-bit BCH ecc code */
-	OMAP_ECC_BCH8_CODE_HW, /* 8-bit BCH ecc code */
+	/* 1-bit  ECC calculation by GPMC, Error detection by Software */
+	OMAP_ECC_HAM1_CODE_HW,
+	/* 4-bit  ECC calculation by GPMC, Error detection by Software */
+	OMAP_ECC_BCH4_CODE_HW_DETECTION_SW,
+	/* 4-bit  ECC calculation by GPMC, Error detection by ELM */
+	OMAP_ECC_BCH4_CODE_HW,
+	/* 8-bit  ECC calculation by GPMC, Error detection by Software */
+	OMAP_ECC_BCH8_CODE_HW_DETECTION_SW,
+	/* 8-bit  ECC calculation by GPMC, Error detection by ELM */
+	OMAP_ECC_BCH8_CODE_HW,
 };
 
 struct gpmc_nand_regs {
@@ -63,5 +71,6 @@ struct omap_nand_platform_data {
 
 	/* for passing the partitions */
 	struct device_node	*of_node;
+	struct device_node	*elm_of_node;
 };
 #endif
-- 
cgit 


From c66d039197e42af8867e5d0d9b904daf0fb9e6bc Mon Sep 17 00:00:00 2001
From: Pekon Gupta <pekon@ti.com>
Date: Thu, 24 Oct 2013 18:20:18 +0530
Subject: mtd: nand: omap: combine different flavours of 1-bit hamming ecc
 schemes

OMAP NAND driver currently supports multiple flavours of 1-bit Hamming
ecc-scheme, like:
- OMAP_ECC_HAMMING_CODE_DEFAULT
	1-bit hamming ecc code using software library
- OMAP_ECC_HAMMING_CODE_HW
	1-bit hamming ecc-code using GPMC h/w engine
- OMAP_ECC_HAMMING_CODE_HW_ROMCODE
	1-bit hamming ecc-code using GPMC h/w engin with ecc-layout compatible
	to ROM code.

This patch combines above multiple ecc-schemes into single implementation:
- OMAP_ECC_HAM1_CODE_HW
	1-bit hamming ecc-code using GPMC h/w engine with ROM-code compatible
	ecc-layout.

Signed-off-by: Pekon Gupta <pekon@ti.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 Documentation/devicetree/bindings/mtd/gpmc-nand.txt | 8 ++++----
 arch/arm/mach-omap2/board-flash.c                   | 2 +-
 drivers/mtd/nand/omap2.c                            | 9 +++------
 include/linux/platform_data/mtd-nand-omap2.h        | 7 +------
 4 files changed, 9 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index bfe07e152738..5e1f31b5ff70 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -22,10 +22,10 @@ Optional properties:
 				width of 8 is assumed.
 
  - ti,nand-ecc-opt:		A string setting the ECC layout to use. One of:
-
-		"sw"		Software method (default)
-		"hw"		Hardware method
-		"hw-romcode"	gpmc hamming mode method & romcode layout
+		"sw"		<deprecated> use "ham1" instead
+		"hw"		<deprecated> use "ham1" instead
+		"hw-romcode"	<deprecated> use "ham1" instead
+		"ham1"		1-bit Hamming ecc code
 		"bch4"		4-bit BCH ecc code
 		"bch8"		8-bit BCH ecc code
 
diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index fc20a61f6b2a..ac82512b9c8c 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs,
 	board_nand_data.nr_parts	= nr_parts;
 	board_nand_data.devsize		= nand_type;
 
-	board_nand_data.ecc_opt = OMAP_ECC_HAMMING_CODE_DEFAULT;
+	board_nand_data.ecc_opt = OMAP_ECC_BCH8_CODE_HW;
 	gpmc_nand_init(&board_nand_data, gpmc_t);
 }
 #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 4ecf0e5fd484..8d521aa001c8 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1993,10 +1993,7 @@ static int omap_nand_probe(struct platform_device *pdev)
 	}
 
 	/* select the ecc type */
-	if (pdata->ecc_opt == OMAP_ECC_HAMMING_CODE_DEFAULT)
-		info->nand.ecc.mode = NAND_ECC_SOFT;
-	else if ((pdata->ecc_opt == OMAP_ECC_HAMMING_CODE_HW) ||
-		(pdata->ecc_opt == OMAP_ECC_HAMMING_CODE_HW_ROMCODE)) {
+	if (pdata->ecc_opt == OMAP_ECC_HAM1_CODE_HW) {
 		info->nand.ecc.bytes            = 3;
 		info->nand.ecc.size             = 512;
 		info->nand.ecc.strength         = 1;
@@ -2025,7 +2022,7 @@ static int omap_nand_probe(struct platform_device *pdev)
 	}
 
 	/* rom code layout */
-	if (pdata->ecc_opt == OMAP_ECC_HAMMING_CODE_HW_ROMCODE) {
+	if (pdata->ecc_opt == OMAP_ECC_HAM1_CODE_HW) {
 
 		if (info->nand.options & NAND_BUSWIDTH_16)
 			offset = 2;
@@ -2033,7 +2030,7 @@ static int omap_nand_probe(struct platform_device *pdev)
 			offset = 1;
 			info->nand.badblock_pattern = &bb_descrip_flashbased;
 		}
-		omap_oobinfo.eccbytes = 3 * (info->mtd.oobsize/16);
+		omap_oobinfo.eccbytes = 3 * (info->mtd.writesize / 512);
 		for (i = 0; i < omap_oobinfo.eccbytes; i++)
 			omap_oobinfo.eccpos[i] = i+offset;
 
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index e4128f1510bf..4da5bfa2147f 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -23,13 +23,8 @@ enum nand_io {
 };
 
 enum omap_ecc {
-		/* 1-bit ecc: stored at end of spare area */
-	OMAP_ECC_HAMMING_CODE_DEFAULT = 0, /* Default, s/w method */
-	OMAP_ECC_HAMMING_CODE_HW, /* gpmc to detect the error */
-		/* 1-bit ecc: stored at beginning of spare area as romcode */
-	OMAP_ECC_HAMMING_CODE_HW_ROMCODE, /* gpmc method & romcode layout */
 	/* 1-bit  ECC calculation by GPMC, Error detection by Software */
-	OMAP_ECC_HAM1_CODE_HW,
+	OMAP_ECC_HAM1_CODE_HW = 0,
 	/* 4-bit  ECC calculation by GPMC, Error detection by Software */
 	OMAP_ECC_BCH4_CODE_HW_DETECTION_SW,
 	/* 4-bit  ECC calculation by GPMC, Error detection by ELM */
-- 
cgit 


From 5961ad2cb4dd14933889f5219e0d8505669d752d Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Wed, 30 Oct 2013 00:41:30 -0400
Subject: mtd: nand_bbt: kill NAND_BBT_SCANALLPAGES

Now that the last user of NAND_BBT_SCANALLPAGES has been removed, let's
kill this peculiar BBT feature flag.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Reviewed-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
---
 Documentation/DocBook/mtdnand.tmpl |  2 --
 drivers/mtd/nand/nand_bbt.c        | 37 +++----------------------------------
 include/linux/mtd/bbm.h            |  2 --
 3 files changed, 3 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index a248f42a121e..cd11926e07c7 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -1222,8 +1222,6 @@ in this page</entry>
 #define NAND_BBT_VERSION	0x00000100
 /* Create a bbt if none axists */
 #define NAND_BBT_CREATE		0x00000200
-/* Search good / bad pattern through all pages of a block */
-#define NAND_BBT_SCANALLPAGES	0x00000400
 /* Write bbt if neccecary */
 #define NAND_BBT_WRITE		0x00001000
 /* Read and write back block contents when writing bbt */
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index c75b6a7c6ea4..c0615d1526f9 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -412,25 +412,6 @@ static void read_abs_bbts(struct mtd_info *mtd, uint8_t *buf,
 	}
 }
 
-/* Scan a given block full */
-static int scan_block_full(struct mtd_info *mtd, struct nand_bbt_descr *bd,
-			   loff_t offs, uint8_t *buf, size_t readlen,
-			   int scanlen, int numpages)
-{
-	int ret, j;
-
-	ret = scan_read_oob(mtd, buf, offs, readlen);
-	/* Ignore ECC errors when checking for BBM */
-	if (ret && !mtd_is_bitflip_or_eccerr(ret))
-		return ret;
-
-	for (j = 0; j < numpages; j++, buf += scanlen) {
-		if (check_pattern(buf, scanlen, mtd->writesize, bd))
-			return 1;
-	}
-	return 0;
-}
-
 /* Scan a given block partially */
 static int scan_block_fast(struct mtd_info *mtd, struct nand_bbt_descr *bd,
 			   loff_t offs, uint8_t *buf, int numpages)
@@ -477,24 +458,17 @@ static int create_bbt(struct mtd_info *mtd, uint8_t *buf,
 	struct nand_bbt_descr *bd, int chip)
 {
 	struct nand_chip *this = mtd->priv;
-	int i, numblocks, numpages, scanlen;
+	int i, numblocks, numpages;
 	int startblock;
 	loff_t from;
-	size_t readlen;
 
 	pr_info("Scanning device for bad blocks\n");
 
-	if (bd->options & NAND_BBT_SCANALLPAGES)
-		numpages = 1 << (this->bbt_erase_shift - this->page_shift);
-	else if (bd->options & NAND_BBT_SCAN2NDPAGE)
+	if (bd->options & NAND_BBT_SCAN2NDPAGE)
 		numpages = 2;
 	else
 		numpages = 1;
 
-	/* We need only read few bytes from the OOB area */
-	scanlen = 0;
-	readlen = bd->len;
-
 	if (chip == -1) {
 		numblocks = mtd->size >> this->bbt_erase_shift;
 		startblock = 0;
@@ -519,12 +493,7 @@ static int create_bbt(struct mtd_info *mtd, uint8_t *buf,
 
 		BUG_ON(bd->options & NAND_BBT_NO_OOB);
 
-		if (bd->options & NAND_BBT_SCANALLPAGES)
-			ret = scan_block_full(mtd, bd, from, buf, readlen,
-					      scanlen, numpages);
-		else
-			ret = scan_block_fast(mtd, bd, from, buf, numpages);
-
+		ret = scan_block_fast(mtd, bd, from, buf, numpages);
 		if (ret < 0)
 			return ret;
 
diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h
index 95fc482cef36..36bb6a503f19 100644
--- a/include/linux/mtd/bbm.h
+++ b/include/linux/mtd/bbm.h
@@ -91,8 +91,6 @@ struct nand_bbt_descr {
  * with NAND_BBT_CREATE.
  */
 #define NAND_BBT_CREATE_EMPTY	0x00000400
-/* Search good / bad pattern through all pages of a block */
-#define NAND_BBT_SCANALLPAGES	0x00000800
 /* Write bbt if neccecary */
 #define NAND_BBT_WRITE		0x00002000
 /* Read and write back block contents when writing bbt */
-- 
cgit 


From f44f2a5417b2968a8724b352cc0b2545a6bcb1f4 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vinod.koul@intel.com>
Date: Thu, 7 Nov 2013 10:08:22 +0100
Subject: ALSA: compress: fix drain calls blocking other compress functions
 (v6)

The drain and drain_notify callback were blocked by low level driver
until the draining was complete. Due to this being invoked with big
fat mutex held, others ops like reading timestamp, calling pause, drop
were blocked.

So to fix this we add a new snd_compr_drain_notify() API. This would
be required to be invoked by low level driver when drain or partial
drain has been completed by the DSP. Thus we make the drain and
partial_drain callback as non blocking and driver returns immediately
after notifying DSP.  The waiting is done while releasing the lock so
that other ops can go ahead.

[ The commit 917f4b5cba78 was wrongly applied from the preliminary
  patch.  This commit corrects to the final version.
  Sorry for inconvenience!  -- tiwai ]

Signed-off-by: Vinod Koul <vinod.koul@intel.com>
CC: stable@vger.kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/compress_driver.h | 11 ++++-------
 sound/core/compress_offload.c   | 31 +++++++++++++++++++------------
 2 files changed, 23 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 175ab3237b58..ae6c3b8ed2f5 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -48,8 +48,6 @@ struct snd_compr_ops;
  *	the ring buffer
  * @total_bytes_transferred: cumulative bytes transferred by offload DSP
  * @sleep: poll sleep
- * @wait: drain wait queue
- * @drain_wake: condition for drain wake
  */
 struct snd_compr_runtime {
 	snd_pcm_state_t state;
@@ -61,8 +59,6 @@ struct snd_compr_runtime {
 	u64 total_bytes_available;
 	u64 total_bytes_transferred;
 	wait_queue_head_t sleep;
-	wait_queue_head_t wait;
-	unsigned int drain_wake;
 	void *private_data;
 };
 
@@ -177,10 +173,11 @@ static inline void snd_compr_fragment_elapsed(struct snd_compr_stream *stream)
 
 static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
 {
-	snd_BUG_ON(!stream);
+	if (snd_BUG_ON(!stream))
+		return;
 
-	stream->runtime->drain_wake = 1;
-	wake_up(&stream->runtime->wait);
+	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+	wake_up(&stream->runtime->sleep);
 }
 
 #endif
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 3eb47d0006a7..d9af6387f37c 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -123,7 +123,6 @@ static int snd_compr_open(struct inode *inode, struct file *f)
 	}
 	runtime->state = SNDRV_PCM_STATE_OPEN;
 	init_waitqueue_head(&runtime->sleep);
-	init_waitqueue_head(&runtime->wait);
 	data->stream.runtime = runtime;
 	f->private_data = (void *)data;
 	mutex_lock(&compr->lock);
@@ -681,8 +680,6 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 		return -EPERM;
 	retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
 	if (!retval) {
-		stream->runtime->state = SNDRV_PCM_STATE_SETUP;
-		wake_up(&stream->runtime->sleep);
 		snd_compr_drain_notify(stream);
 		stream->runtime->total_bytes_available = 0;
 		stream->runtime->total_bytes_transferred = 0;
@@ -692,6 +689,8 @@ static int snd_compr_stop(struct snd_compr_stream *stream)
 
 static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
 {
+	int ret;
+
 	/*
 	 * We are called with lock held. So drop the lock while we wait for
 	 * drain complete notfication from the driver
@@ -703,12 +702,24 @@ static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
 	stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
 	mutex_unlock(&stream->device->lock);
 
-	wait_event(stream->runtime->wait, stream->runtime->drain_wake);
+	/* we wait for drain to complete here, drain can return when
+	 * interruption occurred, wait returned error or success.
+	 * For the first two cases we don't do anything different here and
+	 * return after waking up
+	 */
+
+	ret = wait_event_interruptible(stream->runtime->sleep,
+			(stream->runtime->state != SNDRV_PCM_STATE_DRAINING));
+	if (ret == -ERESTARTSYS)
+		pr_debug("wait aborted by a signal");
+	else if (ret)
+		pr_debug("wait for drain failed with %d\n", ret);
+
 
 	wake_up(&stream->runtime->sleep);
 	mutex_lock(&stream->device->lock);
 
-	return 0;
+	return ret;
 }
 
 static int snd_compr_drain(struct snd_compr_stream *stream)
@@ -719,17 +730,14 @@ static int snd_compr_drain(struct snd_compr_stream *stream)
 			stream->runtime->state == SNDRV_PCM_STATE_SETUP)
 		return -EPERM;
 
-	stream->runtime->drain_wake = 0;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
 	if (retval) {
-		pr_err("SND_COMPR_TRIGGER_DRAIN failed %d\n", retval);
+		pr_debug("SND_COMPR_TRIGGER_DRAIN failed %d\n", retval);
 		wake_up(&stream->runtime->sleep);
 		return retval;
 	}
 
-	retval = snd_compress_wait_for_drain(stream);
-	stream->runtime->state = SNDRV_PCM_STATE_SETUP;
-	return retval;
+	return snd_compress_wait_for_drain(stream);
 }
 
 static int snd_compr_next_track(struct snd_compr_stream *stream)
@@ -764,10 +772,9 @@ static int snd_compr_partial_drain(struct snd_compr_stream *stream)
 	if (stream->next_track == false)
 		return -EPERM;
 
-	stream->runtime->drain_wake = 0;
 	retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
 	if (retval) {
-		pr_err("Partial drain returned failure\n");
+		pr_debug("Partial drain returned failure\n");
 		wake_up(&stream->runtime->sleep);
 		return retval;
 	}
-- 
cgit 


From 3b098eb486868d57d7f2666d05b86c19a07df71b Mon Sep 17 00:00:00 2001
From: Chen Gang <gang.chen@asianux.com>
Date: Thu, 7 Nov 2013 11:14:29 +0800
Subject: ALSA: include/uapi/sound/firewire.h: use "_UAPI" instead of "UAPI"

When installing, "scripts/headers_install.sh" will strip guard macro'
"_UAPI" to prevent from appearing it to users. And also, all another
files which need uapi prefix always use "_UAPI", not "UAPI".

So use "_UAPI" instead of "UAPI" on the guard macro, and also give a
comment for "#endif".

Signed-off-by: Chen Gang <gang.chen@asianux.com>
Acked-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/firewire.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h
index e86131ca49e5..59f5961302bf 100644
--- a/include/uapi/sound/firewire.h
+++ b/include/uapi/sound/firewire.h
@@ -1,5 +1,5 @@
-#ifndef UAPI_SOUND_FIREWIRE_H_INCLUDED
-#define UAPI_SOUND_FIREWIRE_H_INCLUDED
+#ifndef _UAPI_SOUND_FIREWIRE_H_INCLUDED
+#define _UAPI_SOUND_FIREWIRE_H_INCLUDED
 
 #include <linux/ioctl.h>
 
@@ -48,4 +48,4 @@ struct snd_firewire_get_info {
  * Returns -EBUSY if the driver is already streaming.
  */
 
-#endif
+#endif /* _UAPI_SOUND_FIREWIRE_H_INCLUDED */
-- 
cgit 


From 5702941eec32cfd7b8cf9e36a0936e48170011a4 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Fri, 5 Jul 2013 00:31:36 +0800
Subject: irqchip: bcm2835: Convert to use IRQCHIP_DECLARE macro

This patch converts irq-bcm2835 driver to use the new IRQCHIP_DECLARE and
irqchip_init.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Tested-by: Stephen Warren <swarren@wwwdotorg.org>
Cc: Simon Arlott <simon@fire.lp0.eu>
Cc: Olof Johansson <olof@lixom.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-rpi-kernel@lists.infradead.org
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/arm/mach-bcm2835/bcm2835.c |  5 ++---
 drivers/irqchip/irq-bcm2835.c   | 22 ++++++++++------------
 include/linux/irqchip/bcm2835.h | 29 -----------------------------
 3 files changed, 12 insertions(+), 44 deletions(-)
 delete mode 100644 include/linux/irqchip/bcm2835.h

(limited to 'include')

diff --git a/arch/arm/mach-bcm2835/bcm2835.c b/arch/arm/mach-bcm2835/bcm2835.c
index 40686d7ef500..a4abd851905a 100644
--- a/arch/arm/mach-bcm2835/bcm2835.c
+++ b/arch/arm/mach-bcm2835/bcm2835.c
@@ -14,7 +14,7 @@
 
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/irqchip/bcm2835.h>
+#include <linux/irqchip.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/clk/bcm2835.h>
@@ -131,8 +131,7 @@ static const char * const bcm2835_compat[] = {
 
 DT_MACHINE_START(BCM2835, "BCM2835")
 	.map_io = bcm2835_map_io,
-	.init_irq = bcm2835_init_irq,
-	.handle_irq = bcm2835_handle_irq,
+	.init_irq = irqchip_init,
 	.init_machine = bcm2835_init,
 	.init_time = clocksource_of_init,
 	.restart = bcm2835_restart,
diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c
index 16c78f1c5ef2..1693b8e7f26a 100644
--- a/drivers/irqchip/irq-bcm2835.c
+++ b/drivers/irqchip/irq-bcm2835.c
@@ -49,9 +49,11 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/irqdomain.h>
-#include <linux/irqchip/bcm2835.h>
 
 #include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#include "irqchip.h"
 
 /* Put the bank and irq (32 bits) into the hwirq */
 #define MAKE_HWIRQ(b, n)	((b << 5) | (n))
@@ -93,6 +95,8 @@ struct armctrl_ic {
 };
 
 static struct armctrl_ic intc __read_mostly;
+static asmlinkage void __exception_irq_entry bcm2835_handle_irq(
+	struct pt_regs *regs);
 
 static void armctrl_mask_irq(struct irq_data *d)
 {
@@ -164,17 +168,9 @@ static int __init armctrl_of_init(struct device_node *node,
 			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
 		}
 	}
-	return 0;
-}
-
-static struct of_device_id irq_of_match[] __initconst = {
-	{ .compatible = "brcm,bcm2835-armctrl-ic", .data = armctrl_of_init },
-	{ }
-};
 
-void __init bcm2835_init_irq(void)
-{
-	of_irq_init(irq_of_match);
+	set_handle_irq(bcm2835_handle_irq);
+	return 0;
 }
 
 /*
@@ -200,7 +196,7 @@ static void armctrl_handle_shortcut(int bank, struct pt_regs *regs,
 	handle_IRQ(irq_linear_revmap(intc.domain, irq), regs);
 }
 
-asmlinkage void __exception_irq_entry bcm2835_handle_irq(
+static asmlinkage void __exception_irq_entry bcm2835_handle_irq(
 	struct pt_regs *regs)
 {
 	u32 stat, irq;
@@ -222,3 +218,5 @@ asmlinkage void __exception_irq_entry bcm2835_handle_irq(
 		}
 	}
 }
+
+IRQCHIP_DECLARE(bcm2835_armctrl_ic, "brcm,bcm2835-armctrl-ic", armctrl_of_init);
diff --git a/include/linux/irqchip/bcm2835.h b/include/linux/irqchip/bcm2835.h
deleted file mode 100644
index 48a859bc9dca..000000000000
--- a/include/linux/irqchip/bcm2835.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright (C) 2010 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __LINUX_IRQCHIP_BCM2835_H_
-#define __LINUX_IRQCHIP_BCM2835_H_
-
-#include <asm/exception.h>
-
-extern void bcm2835_init_irq(void);
-
-extern asmlinkage void __exception_irq_entry bcm2835_handle_irq(
-	struct pt_regs *regs);
-
-#endif
-- 
cgit 


From 7b98118aaa5d75644c48f41fc5d0cc181e478383 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 7 Nov 2013 01:45:40 +0100
Subject: ACPI / hotplug: Consolidate deferred execution of ACPI hotplug
 routines

There are two different interfaces for queuing up work items on the
ACPI hotplug workqueue, alloc_acpi_hp_work() used by PCI and PCI host
bridge hotplug code and acpi_os_hotplug_execute() used by the common
ACPI hotplug code and docking stations.  They both are somewhat
cumbersome to use and work slightly differently.

The users of alloc_acpi_hp_work() have to submit a work function that
will extract the necessary data items from a struct acpi_hp_work
object allocated by alloc_acpi_hp_work() and then will free that
object, while it would be more straightforward to simply use a work
function with one more argument and let the interface take care of
the execution details.

The users of acpi_os_hotplug_execute() also have to deal with the
fact that it takes only one argument in addition to the work function
pointer, although acpi_os_execute_deferred() actually takes care of
the allocation and freeing of memory, so it would have been able to
pass more arguments to the work function if it hadn't been
constrained by the connection with acpi_os_execute().

Moreover, while alloc_acpi_hp_work() makes GFP_KERNEL memory
allocations, which is correct, because hotplug work items are
always queued up from process context, acpi_os_hotplug_execute()
uses GFP_ATOMIC, as that is needed by acpi_os_execute().  Also,
acpi_os_execute_deferred() queued up by it waits for the ACPI event
workqueues to flush before executing the work function, whereas
alloc_acpi_hp_work() can't do anything similar.  That leads to
somewhat arbitrary differences in behavior between various ACPI
hotplug code paths and has to be straightened up.

For this reason, replace both alloc_acpi_hp_work() and
acpi_os_hotplug_execute() with a single interface,
acpi_hotplug_execute(), combining their behavior and being more
friendly to its users than any of the two.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/dock.c                | 25 ++--------
 drivers/acpi/internal.h            |  2 +-
 drivers/acpi/osl.c                 | 96 ++++++++++++++++++--------------------
 drivers/acpi/pci_root.c            | 14 ++----
 drivers/acpi/scan.c                | 43 ++++-------------
 drivers/pci/hotplug/acpiphp_glue.c | 18 +++----
 include/acpi/acpi_bus.h            | 12 ++---
 include/acpi/acpiosxf.h            |  3 --
 8 files changed, 71 insertions(+), 142 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 05ea4be01a83..eab7d1145bfa 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -671,39 +671,20 @@ static void dock_notify(struct dock_station *ds, u32 event)
 	}
 }
 
-struct dock_data {
-	struct dock_station *ds;
-	u32 event;
-};
-
-static void acpi_dock_deferred_cb(void *context)
+static void acpi_dock_deferred_cb(void *data, u32 event)
 {
-	struct dock_data *data = context;
-
 	acpi_scan_lock_acquire();
-	dock_notify(data->ds, data->event);
+	dock_notify(data, event);
 	acpi_scan_lock_release();
-	kfree(data);
 }
 
 static void dock_notify_handler(acpi_handle handle, u32 event, void *data)
 {
-	struct dock_data *dd;
-
 	if (event != ACPI_NOTIFY_BUS_CHECK && event != ACPI_NOTIFY_DEVICE_CHECK
 	   && event != ACPI_NOTIFY_EJECT_REQUEST)
 		return;
 
-	dd = kmalloc(sizeof(*dd), GFP_KERNEL);
-	if (dd) {
-		acpi_status status;
-
-		dd->ds = data;
-		dd->event = event;
-		status = acpi_os_hotplug_execute(acpi_dock_deferred_cb, dd);
-		if (ACPI_FAILURE(status))
-			kfree(dd);
-	}
+	acpi_hotplug_execute(acpi_dock_deferred_cb, data, event);
 }
 
 /**
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 80cd1a10c4c3..c6db680c826c 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -87,7 +87,7 @@ void acpi_device_add_finalize(struct acpi_device *device);
 void acpi_free_pnp_ids(struct acpi_device_pnp *pnp);
 int acpi_bind_one(struct device *dev, acpi_handle handle);
 int acpi_unbind_one(struct device *dev);
-void acpi_bus_device_eject(struct acpi_device *device, u32 ost_src);
+void acpi_bus_device_eject(void *data, u32 ost_src);
 
 /* --------------------------------------------------------------------------
                                   Power Resource
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index e5f416c7f66e..cfc3e260a688 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -61,7 +61,6 @@ struct acpi_os_dpc {
 	acpi_osd_exec_callback function;
 	void *context;
 	struct work_struct work;
-	int wait;
 };
 
 #ifdef CONFIG_ACPI_CUSTOM_DSDT
@@ -1067,9 +1066,6 @@ static void acpi_os_execute_deferred(struct work_struct *work)
 {
 	struct acpi_os_dpc *dpc = container_of(work, struct acpi_os_dpc, work);
 
-	if (dpc->wait)
-		acpi_os_wait_events_complete();
-
 	dpc->function(dpc->context);
 	kfree(dpc);
 }
@@ -1089,8 +1085,8 @@ static void acpi_os_execute_deferred(struct work_struct *work)
  *
  ******************************************************************************/
 
-static acpi_status __acpi_os_execute(acpi_execute_type type,
-	acpi_osd_exec_callback function, void *context, int hp)
+acpi_status acpi_os_execute(acpi_execute_type type,
+			    acpi_osd_exec_callback function, void *context)
 {
 	acpi_status status = AE_OK;
 	struct acpi_os_dpc *dpc;
@@ -1117,20 +1113,11 @@ static acpi_status __acpi_os_execute(acpi_execute_type type,
 	dpc->context = context;
 
 	/*
-	 * We can't run hotplug code in keventd_wq/kacpid_wq/kacpid_notify_wq
-	 * because the hotplug code may call driver .remove() functions,
-	 * which invoke flush_scheduled_work/acpi_os_wait_events_complete
-	 * to flush these workqueues.
-	 *
 	 * To prevent lockdep from complaining unnecessarily, make sure that
 	 * there is a different static lockdep key for each workqueue by using
 	 * INIT_WORK() for each of them separately.
 	 */
-	if (hp) {
-		queue = kacpi_hotplug_wq;
-		dpc->wait = 1;
-		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	} else if (type == OSL_NOTIFY_HANDLER) {
+	if (type == OSL_NOTIFY_HANDLER) {
 		queue = kacpi_notify_wq;
 		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
 	} else {
@@ -1155,28 +1142,59 @@ static acpi_status __acpi_os_execute(acpi_execute_type type,
 	}
 	return status;
 }
+EXPORT_SYMBOL(acpi_os_execute);
 
-acpi_status acpi_os_execute(acpi_execute_type type,
-			    acpi_osd_exec_callback function, void *context)
+void acpi_os_wait_events_complete(void)
 {
-	return __acpi_os_execute(type, function, context, 0);
+	flush_workqueue(kacpid_wq);
+	flush_workqueue(kacpi_notify_wq);
 }
-EXPORT_SYMBOL(acpi_os_execute);
 
-acpi_status acpi_os_hotplug_execute(acpi_osd_exec_callback function,
-	void *context)
+struct acpi_hp_work {
+	struct work_struct work;
+	acpi_hp_callback func;
+	void *data;
+	u32 src;
+};
+
+static void acpi_hotplug_work_fn(struct work_struct *work)
 {
-	return __acpi_os_execute(0, function, context, 1);
+	struct acpi_hp_work *hpw = container_of(work, struct acpi_hp_work, work);
+
+	acpi_os_wait_events_complete();
+	hpw->func(hpw->data, hpw->src);
+	kfree(hpw);
 }
-EXPORT_SYMBOL(acpi_os_hotplug_execute);
 
-void acpi_os_wait_events_complete(void)
+acpi_status acpi_hotplug_execute(acpi_hp_callback func, void *data, u32 src)
 {
-	flush_workqueue(kacpid_wq);
-	flush_workqueue(kacpi_notify_wq);
+	struct acpi_hp_work *hpw;
+
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+		  "Scheduling function [%p(%p, %u)] for deferred execution.\n",
+		  func, data, src));
+
+	hpw = kmalloc(sizeof(*hpw), GFP_KERNEL);
+	if (!hpw)
+		return AE_NO_MEMORY;
+
+	INIT_WORK(&hpw->work, acpi_hotplug_work_fn);
+	hpw->func = func;
+	hpw->data = data;
+	hpw->src = src;
+	/*
+	 * We can't run hotplug code in kacpid_wq/kacpid_notify_wq etc., because
+	 * the hotplug code may call driver .remove() functions, which may
+	 * invoke flush_scheduled_work()/acpi_os_wait_events_complete() to flush
+	 * these workqueues.
+	 */
+	if (!queue_work(kacpi_hotplug_wq, &hpw->work)) {
+		kfree(hpw);
+		return AE_ERROR;
+	}
+	return AE_OK;
 }
 
-EXPORT_SYMBOL(acpi_os_wait_events_complete);
 
 acpi_status
 acpi_os_create_semaphore(u32 max_units, u32 initial_units, acpi_handle * handle)
@@ -1825,25 +1843,3 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state,
 {
 	__acpi_os_prepare_extended_sleep = func;
 }
-
-
-void alloc_acpi_hp_work(acpi_handle handle, u32 type, void *context,
-			void (*func)(struct work_struct *work))
-{
-	struct acpi_hp_work *hp_work;
-	int ret;
-
-	hp_work = kmalloc(sizeof(*hp_work), GFP_KERNEL);
-	if (!hp_work)
-		return;
-
-	hp_work->handle = handle;
-	hp_work->type = type;
-	hp_work->context = context;
-
-	INIT_WORK(&hp_work->work, func);
-	ret = queue_work(kacpi_hotplug_wq, &hp_work->work);
-	if (!ret)
-		kfree(hp_work);
-}
-EXPORT_SYMBOL_GPL(alloc_acpi_hp_work);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index d77f0bf7eda0..417876bce854 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -592,17 +592,10 @@ static void handle_root_bridge_insertion(acpi_handle handle)
 		acpi_handle_err(handle, "cannot add bridge to acpi list\n");
 }
 
-static void _handle_hotplug_event_root(struct work_struct *work)
+static void hotplug_event_root(void *data, u32 type)
 {
+	acpi_handle handle = data;
 	struct acpi_pci_root *root;
-	struct acpi_hp_work *hp_work;
-	acpi_handle handle;
-	u32 type;
-
-	hp_work = container_of(work, struct acpi_hp_work, work);
-	handle = hp_work->handle;
-	type = hp_work->type;
-	kfree(hp_work); /* allocated in handle_hotplug_event_bridge */
 
 	acpi_scan_lock_acquire();
 
@@ -654,8 +647,7 @@ static void _handle_hotplug_event_root(struct work_struct *work)
 static void handle_hotplug_event_root(acpi_handle handle, u32 type,
 					void *context)
 {
-	alloc_acpi_hp_work(handle, type, context,
-				_handle_hotplug_event_root);
+	acpi_hotplug_execute(hotplug_event_root, handle, type);
 }
 
 static acpi_status __init
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 5cd7f8c5666a..276cde70a514 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -285,8 +285,9 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 	return 0;
 }
 
-void acpi_bus_device_eject(struct acpi_device *device, u32 ost_src)
+void acpi_bus_device_eject(void *data, u32 ost_src)
 {
+	struct acpi_device *device = data;
 	acpi_handle handle = device->handle;
 	struct acpi_scan_handler *handler;
 	u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
@@ -327,8 +328,9 @@ void acpi_bus_device_eject(struct acpi_device *device, u32 ost_src)
 	goto out;
 }
 
-static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source)
+static void acpi_scan_bus_device_check(void *data, u32 ost_source)
 {
+	acpi_handle handle = data;
 	struct acpi_device *device = NULL;
 	u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
 	int error;
@@ -363,18 +365,6 @@ static void acpi_scan_bus_device_check(acpi_handle handle, u32 ost_source)
 	unlock_device_hotplug();
 }
 
-static void acpi_scan_bus_check(void *context)
-{
-	acpi_scan_bus_device_check((acpi_handle)context,
-				   ACPI_NOTIFY_BUS_CHECK);
-}
-
-static void acpi_scan_device_check(void *context)
-{
-	acpi_scan_bus_device_check((acpi_handle)context,
-				   ACPI_NOTIFY_DEVICE_CHECK);
-}
-
 static void acpi_hotplug_unsupported(acpi_handle handle, u32 type)
 {
 	u32 ost_status;
@@ -403,18 +393,8 @@ static void acpi_hotplug_unsupported(acpi_handle handle, u32 type)
 	acpi_evaluate_hotplug_ost(handle, type, ost_status, NULL);
 }
 
-/**
- * acpi_bus_hot_remove_device: Hot-remove a device and its children.
- * @context: Address of the ACPI device object to hot-remove.
- */
-static void acpi_bus_hot_remove_device(void *context)
-{
-	acpi_bus_device_eject(context, ACPI_NOTIFY_EJECT_REQUEST);
-}
-
 static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 {
-	acpi_osd_exec_callback callback;
 	struct acpi_scan_handler *handler = data;
 	struct acpi_device *adev;
 	acpi_status status;
@@ -425,11 +405,9 @@ static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 	switch (type) {
 	case ACPI_NOTIFY_BUS_CHECK:
 		acpi_handle_debug(handle, "ACPI_NOTIFY_BUS_CHECK event\n");
-		callback = acpi_scan_bus_check;
 		break;
 	case ACPI_NOTIFY_DEVICE_CHECK:
 		acpi_handle_debug(handle, "ACPI_NOTIFY_DEVICE_CHECK event\n");
-		callback = acpi_scan_device_check;
 		break;
 	case ACPI_NOTIFY_EJECT_REQUEST:
 		acpi_handle_debug(handle, "ACPI_NOTIFY_EJECT_REQUEST event\n");
@@ -438,8 +416,7 @@ static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 			goto err_out;
 
 		get_device(&adev->dev);
-		callback = acpi_bus_hot_remove_device;
-		status = acpi_os_hotplug_execute(callback, adev);
+		status = acpi_hotplug_execute(acpi_bus_device_eject, adev, type);
 		if (ACPI_SUCCESS(status))
 			return;
 
@@ -449,7 +426,7 @@ static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
 		/* non-hotplug event; possibly handled by other handler */
 		return;
 	}
-	status = acpi_os_hotplug_execute(callback, handle);
+	status = acpi_hotplug_execute(acpi_scan_bus_device_check, handle, type);
 	if (ACPI_SUCCESS(status))
 		return;
 
@@ -484,11 +461,6 @@ static ssize_t power_state_show(struct device *dev,
 
 static DEVICE_ATTR(power_state, 0444, power_state_show, NULL);
 
-static void acpi_eject_store_work(void *context)
-{
-	acpi_bus_device_eject(context, ACPI_OST_EC_OSPM_EJECT);
-}
-
 static ssize_t
 acpi_eject_store(struct device *d, struct device_attribute *attr,
 		const char *buf, size_t count)
@@ -511,7 +483,8 @@ acpi_eject_store(struct device *d, struct device_attribute *attr,
 	acpi_evaluate_hotplug_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT,
 				  ACPI_OST_SC_EJECT_IN_PROGRESS, NULL);
 	get_device(&acpi_device->dev);
-	status = acpi_os_hotplug_execute(acpi_eject_store_work, acpi_device);
+	status = acpi_hotplug_execute(acpi_bus_device_eject, acpi_device,
+				      ACPI_OST_EC_OSPM_EJECT);
 	if (ACPI_SUCCESS(status))
 		return count;
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 0b7d23b4ad95..5246ba297470 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -875,21 +875,17 @@ static void hotplug_event(acpi_handle handle, u32 type, void *data)
 		put_bridge(bridge);
 }
 
-static void hotplug_event_work(struct work_struct *work)
+static void hotplug_event_work(void *data, u32 type)
 {
-	struct acpiphp_context *context;
-	struct acpi_hp_work *hp_work;
+	struct acpiphp_context *context = data;
+	acpi_handle handle = context->handle;
 
-	hp_work = container_of(work, struct acpi_hp_work, work);
-	context = hp_work->context;
 	acpi_scan_lock_acquire();
 
-	hotplug_event(hp_work->handle, hp_work->type, context);
+	hotplug_event(handle, type, context);
 
 	acpi_scan_lock_release();
-	acpi_evaluate_hotplug_ost(hp_work->handle, hp_work->type,
-				  ACPI_OST_SC_SUCCESS, NULL);
-	kfree(hp_work); /* allocated in handle_hotplug_event() */
+	acpi_evaluate_hotplug_ost(handle, type, ACPI_OST_SC_SUCCESS, NULL);
 	put_bridge(context->func.parent);
 }
 
@@ -940,10 +936,10 @@ static void handle_hotplug_event(acpi_handle handle, u32 type, void *data)
 
 	mutex_lock(&acpiphp_context_lock);
 	context = acpiphp_get_context(handle);
-	if (context) {
+	if (context && !WARN_ON(context->handle != handle)) {
 		get_bridge(context->func.parent);
 		acpiphp_put_context(context);
-		alloc_acpi_hp_work(handle, type, context, hotplug_event_work);
+		acpi_hotplug_execute(hotplug_event_work, context, type);
 		mutex_unlock(&acpiphp_context_lock);
 		return;
 	}
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index eb37a6fb8665..d64a3010332f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -339,15 +339,6 @@ struct acpi_bus_event {
 	u32 data;
 };
 
-struct acpi_hp_work {
-	struct work_struct work;
-	acpi_handle handle;
-	u32 type;
-	void *context;
-};
-void alloc_acpi_hp_work(acpi_handle handle, u32 type, void *context,
-			void (*func)(struct work_struct *work));
-
 extern struct kobject *acpi_kobj;
 extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int);
 void acpi_bus_private_data_handler(acpi_handle, void *);
@@ -393,6 +384,9 @@ int acpi_match_device_ids(struct acpi_device *device,
 int acpi_create_dir(struct acpi_device *);
 void acpi_remove_dir(struct acpi_device *);
 
+typedef void (*acpi_hp_callback)(void *data, u32 src);
+
+acpi_status acpi_hotplug_execute(acpi_hp_callback func, void *data, u32 src);
 
 /**
  * module_acpi_driver(acpi_driver) - Helper macro for registering an ACPI driver
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 64b8c7639520..505cb4d59f23 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -200,9 +200,6 @@ acpi_status
 acpi_os_execute(acpi_execute_type type,
 		acpi_osd_exec_callback function, void *context);
 
-acpi_status
-acpi_os_hotplug_execute(acpi_osd_exec_callback function, void *context);
-
 void acpi_os_wait_events_complete(void);
 
 void acpi_os_sleep(u64 milliseconds);
-- 
cgit 


From c6bde215acfd637708142ae671843b6f0eadbc6d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Nov 2013 10:11:48 -0700
Subject: PCI: Add pci_upstream_bridge()

This adds a pci_upstream_bridge() interface to find the PCI-to-PCI bridge
upstream from a device.  This is typically just "dev->bus->self", but in
the case of a VF on a virtual bus, we have to start from the corresponding
PF.  Returns NULL if there is no upstream PCI bridge, i.e., if the device
is on a root bus.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Yinghai Lu <yinghai@kernel.org>
---
 include/linux/pci.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index d3a888ae4b2e..835ec7bf6c05 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -480,6 +480,15 @@ static inline bool pci_is_root_bus(struct pci_bus *pbus)
 	return !(pbus->parent);
 }
 
+static inline struct pci_dev *pci_upstream_bridge(struct pci_dev *dev)
+{
+	dev = pci_physfn(dev);
+	if (pci_is_root_bus(dev->bus))
+		return NULL;
+
+	return dev->bus->self;
+}
+
 #ifdef CONFIG_PCI_MSI
 static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev)
 {
-- 
cgit 


From 5277797dc4ed873d067477d84e910b39d113f649 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 6 Nov 2013 21:03:43 -0800
Subject: target: Add percpu refcounting for se_lun access

This patch adds percpu refcounting for se_lun access that allows the
association of an se_lun + se_cmd in transport_lookup_cmd_lun() to
occur without an extra list_head for tracking outstanding I/O during
se_lun shutdown.

This effectively changes se_lun shutdown logic to wait for outstanding
I/O percpu references to complete in transport_lun_remove_cmd() using
se_lun->lun_ref_comp, instead of explicitly draining the per se_lun
command list and waiting for individual se_cmd descriptor processing
to complete.

Cc: Kent Overstreet <kmo@daterainc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c    | 10 ++++++----
 drivers/target/target_core_internal.h  |  2 +-
 drivers/target/target_core_tpg.c       | 27 ++++++++++++++++++++++++---
 drivers/target/target_core_transport.c | 18 ++++++++----------
 drivers/target/target_core_xcopy.c     |  1 +
 include/target/target_core_base.h      |  5 +++++
 6 files changed, 45 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index d90dbb0f1a69..569a3c7c9e5a 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -92,6 +92,9 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		se_cmd->pr_res_key = deve->pr_res_key;
 		se_cmd->orig_fe_lun = unpacked_lun;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
+
+		percpu_ref_get(&se_lun->lun_ref);
+		se_cmd->lun_ref_active = true;
 	}
 	spin_unlock_irqrestore(&se_sess->se_node_acl->device_list_lock, flags);
 
@@ -119,6 +122,9 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		se_cmd->se_lun = &se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->orig_fe_lun = 0;
 		se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD;
+
+		percpu_ref_get(&se_lun->lun_ref);
+		se_cmd->lun_ref_active = true;
 	}
 
 	/* Directly associate cmd with se_dev */
@@ -134,10 +140,6 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 		dev->read_bytes += se_cmd->data_length;
 	spin_unlock_irqrestore(&dev->stats_lock, flags);
 
-	spin_lock_irqsave(&se_lun->lun_cmd_lock, flags);
-	list_add_tail(&se_cmd->se_lun_node, &se_lun->lun_cmd_list);
-	spin_unlock_irqrestore(&se_lun->lun_cmd_lock, flags);
-
 	return 0;
 }
 EXPORT_SYMBOL(transport_lookup_cmd_lun);
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 889af4df8562..47b63b094cdc 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -100,7 +100,7 @@ int	transport_dump_vpd_assoc(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
 bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
-int	transport_clear_lun_from_sessions(struct se_lun *);
+int	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
 void	target_qf_do_work(struct work_struct *work);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index ec992208dc55..f321af04ef03 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -634,6 +634,13 @@ int core_tpg_set_initiator_node_tag(
 }
 EXPORT_SYMBOL(core_tpg_set_initiator_node_tag);
 
+static void core_tpg_lun_ref_release(struct percpu_ref *ref)
+{
+	struct se_lun *lun = container_of(ref, struct se_lun, lun_ref);
+
+	complete(&lun->lun_ref_comp);
+}
+
 static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
 {
 	/* Set in core_dev_setup_virtual_lun0() */
@@ -651,11 +658,18 @@ static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
 	spin_lock_init(&lun->lun_acl_lock);
 	spin_lock_init(&lun->lun_cmd_lock);
 	spin_lock_init(&lun->lun_sep_lock);
+	init_completion(&lun->lun_ref_comp);
 
-	ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
+	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
 	if (ret < 0)
 		return ret;
 
+	ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
+	if (ret < 0) {
+		percpu_ref_cancel_init(&lun->lun_ref);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -696,6 +710,7 @@ int core_tpg_register(
 		spin_lock_init(&lun->lun_acl_lock);
 		spin_lock_init(&lun->lun_cmd_lock);
 		spin_lock_init(&lun->lun_sep_lock);
+		init_completion(&lun->lun_ref_comp);
 	}
 
 	se_tpg->se_tpg_type = se_tpg_type;
@@ -816,10 +831,16 @@ int core_tpg_post_addlun(
 {
 	int ret;
 
-	ret = core_dev_export(lun_ptr, tpg, lun);
+	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
 	if (ret < 0)
 		return ret;
 
+	ret = core_dev_export(lun_ptr, tpg, lun);
+	if (ret < 0) {
+		percpu_ref_cancel_init(&lun->lun_ref);
+		return ret;
+	}
+
 	spin_lock(&tpg->tpg_lun_lock);
 	lun->lun_access = lun_access;
 	lun->lun_status = TRANSPORT_LUN_STATUS_ACTIVE;
@@ -833,7 +854,7 @@ static void core_tpg_shutdown_lun(
 	struct se_lun *lun)
 {
 	core_clear_lun_from_tpg(lun, tpg);
-	transport_clear_lun_from_sessions(lun);
+	transport_clear_lun_ref(lun);
 }
 
 struct se_lun *core_tpg_pre_dellun(
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 84747cc1aac0..ad143d7293ec 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -575,15 +575,11 @@ static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 static void transport_lun_remove_cmd(struct se_cmd *cmd)
 {
 	struct se_lun *lun = cmd->se_lun;
-	unsigned long flags;
 
-	if (!lun)
+	if (!lun || !cmd->lun_ref_active)
 		return;
 
-	spin_lock_irqsave(&lun->lun_cmd_lock, flags);
-	if (!list_empty(&cmd->se_lun_node))
-		list_del_init(&cmd->se_lun_node);
-	spin_unlock_irqrestore(&lun->lun_cmd_lock, flags);
+	percpu_ref_put(&lun->lun_ref);
 }
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
@@ -2537,21 +2533,23 @@ check_cond:
 	spin_unlock_irqrestore(&lun->lun_cmd_lock, lun_flags);
 }
 
-static int transport_clear_lun_thread(void *p)
+static int transport_clear_lun_ref_thread(void *p)
 {
 	struct se_lun *lun = p;
 
-	__transport_clear_lun_from_sessions(lun);
+	percpu_ref_kill(&lun->lun_ref);
+
+	wait_for_completion(&lun->lun_ref_comp);
 	complete(&lun->lun_shutdown_comp);
 
 	return 0;
 }
 
-int transport_clear_lun_from_sessions(struct se_lun *lun)
+int transport_clear_lun_ref(struct se_lun *lun)
 {
 	struct task_struct *kt;
 
-	kt = kthread_run(transport_clear_lun_thread, lun,
+	kt = kthread_run(transport_clear_lun_ref_thread, lun,
 			"tcm_cl_%u", lun->unpacked_lun);
 	if (IS_ERR(kt)) {
 		pr_err("Unable to start clear_lun thread\n");
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 4d22e7d2adca..7a870f6add7b 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -579,6 +579,7 @@ static int target_xcopy_init_pt_lun(
 	spin_lock_init(&pt_cmd->se_lun->lun_acl_lock);
 	spin_lock_init(&pt_cmd->se_lun->lun_cmd_lock);
 	spin_lock_init(&pt_cmd->se_lun->lun_sep_lock);
+	init_completion(&pt_cmd->se_lun->lun_ref_comp);
 
 	pt_cmd->se_dev = se_dev;
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 22e752c4406d..4d16fd9330a6 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -499,6 +499,9 @@ struct se_cmd {
 
 	/* backend private data */
 	void			*priv;
+
+	/* Used for lun->lun_ref counting */
+	bool			lun_ref_active;
 };
 
 struct se_ua {
@@ -757,6 +760,8 @@ struct se_lun {
 	struct se_port		*lun_sep;
 	struct config_group	lun_group;
 	struct se_port_stat_grps port_stat_grps;
+	struct completion	lun_ref_comp;
+	struct percpu_ref	lun_ref;
 };
 
 struct scsi_port_stats {
-- 
cgit 


From 4a9a6c8d538eff6d627fa14409c7c25aff652541 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 6 Nov 2013 21:05:19 -0800
Subject: target: Drop left-over se_lun->lun_cmd_list shutdown code

Now with percpu refcounting for se_lun in place, go ahead and drop
the legacy per se_cmd accounting for se_lun shutdown.

This includes __transport_clear_lun_from_sessions(), the associated
transport_lun_wait_for_tasks() logic, along with a handful of now
unused se_cmd structure members and ->transport_state bits.

Cc: Kent Overstreet <kmo@daterainc.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/infiniband/ulp/srpt/ib_srpt.c  |  10 --
 drivers/target/target_core_tpg.c       |  15 +--
 drivers/target/target_core_transport.c | 219 +--------------------------------
 drivers/target/target_core_xcopy.c     |   2 -
 include/target/target_core_base.h      |  13 +-
 5 files changed, 7 insertions(+), 252 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 653ac6bfc57a..16087966cb7d 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1352,11 +1352,8 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx)
 
 		/* XXX(hch): this is a horrible layering violation.. */
 		spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
-		ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
 		ioctx->cmd.transport_state &= ~CMD_T_ACTIVE;
 		spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
-
-		complete(&ioctx->cmd.transport_lun_stop_comp);
 		break;
 	case SRPT_STATE_CMD_RSP_SENT:
 		/*
@@ -1364,9 +1361,6 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx)
 		 * not been received in time.
 		 */
 		srpt_unmap_sg_to_ib_sge(ioctx->ch, ioctx);
-		spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
-		ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
-		spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
 		target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd);
 		break;
 	case SRPT_STATE_MGMT_RSP_SENT:
@@ -1476,7 +1470,6 @@ static void srpt_handle_rdma_err_comp(struct srpt_rdma_ch *ch,
 {
 	struct se_cmd *cmd;
 	enum srpt_command_state state;
-	unsigned long flags;
 
 	cmd = &ioctx->cmd;
 	state = srpt_get_cmd_state(ioctx);
@@ -1496,9 +1489,6 @@ static void srpt_handle_rdma_err_comp(struct srpt_rdma_ch *ch,
 			       __func__, __LINE__, state);
 		break;
 	case SRPT_RDMA_WRITE_LAST:
-		spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags);
-		ioctx->cmd.transport_state |= CMD_T_LUN_STOP;
-		spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags);
 		break;
 	default:
 		printk(KERN_ERR "%s[%d]: opcode = %u\n", __func__,
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index f321af04ef03..f697f8baec54 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -654,9 +654,7 @@ static int core_tpg_setup_virtual_lun0(struct se_portal_group *se_tpg)
 	atomic_set(&lun->lun_acl_count, 0);
 	init_completion(&lun->lun_shutdown_comp);
 	INIT_LIST_HEAD(&lun->lun_acl_list);
-	INIT_LIST_HEAD(&lun->lun_cmd_list);
 	spin_lock_init(&lun->lun_acl_lock);
-	spin_lock_init(&lun->lun_cmd_lock);
 	spin_lock_init(&lun->lun_sep_lock);
 	init_completion(&lun->lun_ref_comp);
 
@@ -706,9 +704,7 @@ int core_tpg_register(
 		atomic_set(&lun->lun_acl_count, 0);
 		init_completion(&lun->lun_shutdown_comp);
 		INIT_LIST_HEAD(&lun->lun_acl_list);
-		INIT_LIST_HEAD(&lun->lun_cmd_list);
 		spin_lock_init(&lun->lun_acl_lock);
-		spin_lock_init(&lun->lun_cmd_lock);
 		spin_lock_init(&lun->lun_sep_lock);
 		init_completion(&lun->lun_ref_comp);
 	}
@@ -849,14 +845,6 @@ int core_tpg_post_addlun(
 	return 0;
 }
 
-static void core_tpg_shutdown_lun(
-	struct se_portal_group *tpg,
-	struct se_lun *lun)
-{
-	core_clear_lun_from_tpg(lun, tpg);
-	transport_clear_lun_ref(lun);
-}
-
 struct se_lun *core_tpg_pre_dellun(
 	struct se_portal_group *tpg,
 	u32 unpacked_lun)
@@ -891,7 +879,8 @@ int core_tpg_post_dellun(
 	struct se_portal_group *tpg,
 	struct se_lun *lun)
 {
-	core_tpg_shutdown_lun(tpg, lun);
+	core_clear_lun_from_tpg(lun, tpg);
+	transport_clear_lun_ref(lun);
 
 	core_dev_unexport(lun->lun_se_dev, tpg, lun);
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index ad143d7293ec..e0669ac9278b 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -505,23 +505,6 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 	if (write_pending)
 		cmd->t_state = TRANSPORT_WRITE_PENDING;
 
-	/*
-	 * Determine if IOCTL context caller in requesting the stopping of this
-	 * command for LUN shutdown purposes.
-	 */
-	if (cmd->transport_state & CMD_T_LUN_STOP) {
-		pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
-
-		cmd->transport_state &= ~CMD_T_ACTIVE;
-		if (remove_from_lists)
-			target_remove_from_state_list(cmd);
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-		complete(&cmd->transport_lun_stop_comp);
-		return 1;
-	}
-
 	if (remove_from_lists) {
 		target_remove_from_state_list(cmd);
 
@@ -1078,13 +1061,10 @@ void transport_init_se_cmd(
 	int task_attr,
 	unsigned char *sense_buffer)
 {
-	INIT_LIST_HEAD(&cmd->se_lun_node);
 	INIT_LIST_HEAD(&cmd->se_delayed_node);
 	INIT_LIST_HEAD(&cmd->se_qf_node);
 	INIT_LIST_HEAD(&cmd->se_cmd_list);
 	INIT_LIST_HEAD(&cmd->state_list);
-	init_completion(&cmd->transport_lun_fe_stop_comp);
-	init_completion(&cmd->transport_lun_stop_comp);
 	init_completion(&cmd->t_transport_stop_comp);
 	init_completion(&cmd->cmd_wait_comp);
 	init_completion(&cmd->task_stop_comp);
@@ -1705,29 +1685,14 @@ void target_execute_cmd(struct se_cmd *cmd)
 	/*
 	 * If the received CDB has aleady been aborted stop processing it here.
 	 */
-	if (transport_check_aborted_status(cmd, 1)) {
-		complete(&cmd->transport_lun_stop_comp);
+	if (transport_check_aborted_status(cmd, 1))
 		return;
-	}
 
-	/*
-	 * Determine if IOCTL context caller in requesting the stopping of this
-	 * command for LUN shutdown purposes.
-	 */
-	spin_lock_irq(&cmd->t_state_lock);
-	if (cmd->transport_state & CMD_T_LUN_STOP) {
-		pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n",
-			__func__, __LINE__, cmd->se_tfo->get_task_tag(cmd));
-
-		cmd->transport_state &= ~CMD_T_ACTIVE;
-		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->transport_lun_stop_comp);
-		return;
-	}
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
 	 */
+	spin_lock_irq(&cmd->t_state_lock);
 	if (cmd->transport_state & CMD_T_STOP) {
 		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n",
 			__func__, __LINE__,
@@ -2390,149 +2355,6 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
-/*	transport_lun_wait_for_tasks():
- *
- *	Called from ConfigFS context to stop the passed struct se_cmd to allow
- *	an struct se_lun to be successfully shutdown.
- */
-static int transport_lun_wait_for_tasks(struct se_cmd *cmd, struct se_lun *lun)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	/*
-	 * If the frontend has already requested this struct se_cmd to
-	 * be stopped, we can safely ignore this struct se_cmd.
-	 */
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (cmd->transport_state & CMD_T_STOP) {
-		cmd->transport_state &= ~CMD_T_LUN_STOP;
-
-		pr_debug("ConfigFS ITT[0x%08x] - CMD_T_STOP, skipping\n",
-			 cmd->se_tfo->get_task_tag(cmd));
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		transport_cmd_check_stop(cmd, false, false);
-		return -EPERM;
-	}
-	cmd->transport_state |= CMD_T_LUN_FE_STOP;
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-	// XXX: audit task_flags checks.
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if ((cmd->transport_state & CMD_T_BUSY) &&
-	    (cmd->transport_state & CMD_T_SENT)) {
-		if (!target_stop_cmd(cmd, &flags))
-			ret++;
-	}
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-
-	pr_debug("ConfigFS: cmd: %p stop tasks ret:"
-			" %d\n", cmd, ret);
-	if (!ret) {
-		pr_debug("ConfigFS: ITT[0x%08x] - stopping cmd....\n",
-				cmd->se_tfo->get_task_tag(cmd));
-		wait_for_completion(&cmd->transport_lun_stop_comp);
-		pr_debug("ConfigFS: ITT[0x%08x] - stopped cmd....\n",
-				cmd->se_tfo->get_task_tag(cmd));
-	}
-
-	return 0;
-}
-
-static void __transport_clear_lun_from_sessions(struct se_lun *lun)
-{
-	struct se_cmd *cmd = NULL;
-	unsigned long lun_flags, cmd_flags;
-	/*
-	 * Do exception processing and return CHECK_CONDITION status to the
-	 * Initiator Port.
-	 */
-	spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
-	while (!list_empty(&lun->lun_cmd_list)) {
-		cmd = list_first_entry(&lun->lun_cmd_list,
-		       struct se_cmd, se_lun_node);
-		list_del_init(&cmd->se_lun_node);
-
-		spin_lock(&cmd->t_state_lock);
-		pr_debug("SE_LUN[%d] - Setting cmd->transport"
-			"_lun_stop for  ITT: 0x%08x\n",
-			cmd->se_lun->unpacked_lun,
-			cmd->se_tfo->get_task_tag(cmd));
-		cmd->transport_state |= CMD_T_LUN_STOP;
-		spin_unlock(&cmd->t_state_lock);
-
-		spin_unlock_irqrestore(&lun->lun_cmd_lock, lun_flags);
-
-		if (!cmd->se_lun) {
-			pr_err("ITT: 0x%08x, [i,t]_state: %u/%u\n",
-				cmd->se_tfo->get_task_tag(cmd),
-				cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
-			BUG();
-		}
-		/*
-		 * If the Storage engine still owns the iscsi_cmd_t, determine
-		 * and/or stop its context.
-		 */
-		pr_debug("SE_LUN[%d] - ITT: 0x%08x before transport"
-			"_lun_wait_for_tasks()\n", cmd->se_lun->unpacked_lun,
-			cmd->se_tfo->get_task_tag(cmd));
-
-		if (transport_lun_wait_for_tasks(cmd, cmd->se_lun) < 0) {
-			spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
-			continue;
-		}
-
-		pr_debug("SE_LUN[%d] - ITT: 0x%08x after transport_lun"
-			"_wait_for_tasks(): SUCCESS\n",
-			cmd->se_lun->unpacked_lun,
-			cmd->se_tfo->get_task_tag(cmd));
-
-		spin_lock_irqsave(&cmd->t_state_lock, cmd_flags);
-		if (!(cmd->transport_state & CMD_T_DEV_ACTIVE)) {
-			spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
-			goto check_cond;
-		}
-		cmd->transport_state &= ~CMD_T_DEV_ACTIVE;
-		target_remove_from_state_list(cmd);
-		spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
-
-		/*
-		 * The Storage engine stopped this struct se_cmd before it was
-		 * send to the fabric frontend for delivery back to the
-		 * Initiator Node.  Return this SCSI CDB back with an
-		 * CHECK_CONDITION status.
-		 */
-check_cond:
-		transport_send_check_condition_and_sense(cmd,
-				TCM_NON_EXISTENT_LUN, 0);
-		/*
-		 *  If the fabric frontend is waiting for this iscsi_cmd_t to
-		 * be released, notify the waiting thread now that LU has
-		 * finished accessing it.
-		 */
-		spin_lock_irqsave(&cmd->t_state_lock, cmd_flags);
-		if (cmd->transport_state & CMD_T_LUN_FE_STOP) {
-			pr_debug("SE_LUN[%d] - Detected FE stop for"
-				" struct se_cmd: %p ITT: 0x%08x\n",
-				lun->unpacked_lun,
-				cmd, cmd->se_tfo->get_task_tag(cmd));
-
-			spin_unlock_irqrestore(&cmd->t_state_lock,
-					cmd_flags);
-			transport_cmd_check_stop(cmd, false, false);
-			complete(&cmd->transport_lun_fe_stop_comp);
-			spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
-			continue;
-		}
-		pr_debug("SE_LUN[%d] - ITT: 0x%08x finished processing\n",
-			lun->unpacked_lun, cmd->se_tfo->get_task_tag(cmd));
-
-		spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags);
-		spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags);
-	}
-	spin_unlock_irqrestore(&lun->lun_cmd_lock, lun_flags);
-}
-
 static int transport_clear_lun_ref_thread(void *p)
 {
 	struct se_lun *lun = p;
@@ -2583,43 +2405,6 @@ bool transport_wait_for_tasks(struct se_cmd *cmd)
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		return false;
 	}
-	/*
-	 * If we are already stopped due to an external event (ie: LUN shutdown)
-	 * sleep until the connection can have the passed struct se_cmd back.
-	 * The cmd->transport_lun_stopped_sem will be upped by
-	 * transport_clear_lun_from_sessions() once the ConfigFS context caller
-	 * has completed its operation on the struct se_cmd.
-	 */
-	if (cmd->transport_state & CMD_T_LUN_STOP) {
-		pr_debug("wait_for_tasks: Stopping"
-			" wait_for_completion(&cmd->t_tasktransport_lun_fe"
-			"_stop_comp); for ITT: 0x%08x\n",
-			cmd->se_tfo->get_task_tag(cmd));
-		/*
-		 * There is a special case for WRITES where a FE exception +
-		 * LUN shutdown means ConfigFS context is still sleeping on
-		 * transport_lun_stop_comp in transport_lun_wait_for_tasks().
-		 * We go ahead and up transport_lun_stop_comp just to be sure
-		 * here.
-		 */
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->transport_lun_stop_comp);
-		wait_for_completion(&cmd->transport_lun_fe_stop_comp);
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
-
-		target_remove_from_state_list(cmd);
-		/*
-		 * At this point, the frontend who was the originator of this
-		 * struct se_cmd, now owns the structure and can be released through
-		 * normal means below.
-		 */
-		pr_debug("wait_for_tasks: Stopped"
-			" wait_for_completion(&cmd->t_tasktransport_lun_fe_"
-			"stop_comp); for ITT: 0x%08x\n",
-			cmd->se_tfo->get_task_tag(cmd));
-
-		cmd->transport_state &= ~CMD_T_LUN_STOP;
-	}
 
 	if (!(cmd->transport_state & CMD_T_ACTIVE)) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 7a870f6add7b..b12fc43b5463 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -574,10 +574,8 @@ static int target_xcopy_init_pt_lun(
 		return -ENOMEM;
 	}
 	init_completion(&pt_cmd->se_lun->lun_shutdown_comp);
-	INIT_LIST_HEAD(&pt_cmd->se_lun->lun_cmd_list);
 	INIT_LIST_HEAD(&pt_cmd->se_lun->lun_acl_list);
 	spin_lock_init(&pt_cmd->se_lun->lun_acl_lock);
-	spin_lock_init(&pt_cmd->se_lun->lun_cmd_lock);
 	spin_lock_init(&pt_cmd->se_lun->lun_sep_lock);
 	init_completion(&pt_cmd->se_lun->lun_ref_comp);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 4d16fd9330a6..1ad0a4240b00 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -443,7 +443,6 @@ struct se_cmd {
 	/* Used for sense data */
 	void			*sense_buffer;
 	struct list_head	se_delayed_node;
-	struct list_head	se_lun_node;
 	struct list_head	se_qf_node;
 	struct se_device      *se_dev;
 	struct se_dev_entry   *se_deve;
@@ -471,15 +470,11 @@ struct se_cmd {
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
 #define CMD_T_FAILED		(1 << 6)
-#define CMD_T_LUN_STOP		(1 << 7)
-#define CMD_T_LUN_FE_STOP	(1 << 8)
-#define CMD_T_DEV_ACTIVE	(1 << 9)
-#define CMD_T_REQUEST_STOP	(1 << 10)
-#define CMD_T_BUSY		(1 << 11)
+#define CMD_T_DEV_ACTIVE	(1 << 7)
+#define CMD_T_REQUEST_STOP	(1 << 8)
+#define CMD_T_BUSY		(1 << 9)
 	spinlock_t		t_state_lock;
 	struct completion	t_transport_stop_comp;
-	struct completion	transport_lun_fe_stop_comp;
-	struct completion	transport_lun_stop_comp;
 
 	struct work_struct	work;
 
@@ -751,10 +746,8 @@ struct se_lun {
 	u32			unpacked_lun;
 	atomic_t		lun_acl_count;
 	spinlock_t		lun_acl_lock;
-	spinlock_t		lun_cmd_lock;
 	spinlock_t		lun_sep_lock;
 	struct completion	lun_shutdown_comp;
-	struct list_head	lun_cmd_list;
 	struct list_head	lun_acl_list;
 	struct se_device	*lun_se_dev;
 	struct se_port		*lun_sep;
-- 
cgit 


From d32435391974e39c35ade4d115f17c538a96a708 Mon Sep 17 00:00:00 2001
From: Eyal Perry <eyalpe@mellanox.com>
Date: Wed, 6 Nov 2013 15:37:23 +0200
Subject: net/vlan: Provide read access to the vlan egress map

Provide a method for read-only access to the vlan device egress mapping.

Do this by refactoring vlan_dev_get_egress_qos_mask() such that now it
receives as an argument the skb priority instead of pointer to the skb.

Such an access is needed for the IBoE stack where the control plane
goes through the network stack. This is an add-on step on top of commit
d4a968658c "net/route: export symbol ip_tos2prio" which allowed the RDMA-CM
to use ip_tos2prio.

Signed-off-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h |  9 ++++++++-
 net/8021q/vlan_dev.c    | 18 ++++++++++++------
 2 files changed, 20 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 715c343f7c00..f3088a0112cf 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -88,7 +88,8 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
-
+extern u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
+					u32 skprio);
 extern bool vlan_do_receive(struct sk_buff **skb);
 extern struct sk_buff *vlan_untag(struct sk_buff *skb);
 
@@ -121,6 +122,12 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 	return 0;
 }
 
+static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
+					       u32 skprio)
+{
+	return 0;
+}
+
 static inline bool vlan_do_receive(struct sk_buff **skb)
 {
 	return false;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 09bf1c38805b..13904a414929 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -69,15 +69,15 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb)
 }
 
 static inline u16
-vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb)
+__vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
 {
 	struct vlan_priority_tci_mapping *mp;
 
 	smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
 
-	mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)];
+	mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)];
 	while (mp) {
-		if (mp->priority == skb->priority) {
+		if (mp->priority == skprio) {
 			return mp->vlan_qos; /* This should already be shifted
 					      * to mask correctly with the
 					      * VLAN's TCI */
@@ -87,6 +87,12 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb)
 	return 0;
 }
 
+u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
+{
+	return __vlan_dev_get_egress_qos_mask(dev, skprio);
+}
+EXPORT_SYMBOL(vlan_dev_get_egress_qos_mask);
+
 /*
  *	Create the VLAN header for an arbitrary protocol layer
  *
@@ -111,7 +117,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
 
 		vlan_tci = vlan->vlan_id;
-		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
+		vlan_tci |= __vlan_dev_get_egress_qos_mask(dev, skb->priority);
 		vhdr->h_vlan_TCI = htons(vlan_tci);
 
 		/*
@@ -168,7 +174,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 	    vlan->flags & VLAN_FLAG_REORDER_HDR) {
 		u16 vlan_tci;
 		vlan_tci = vlan->vlan_id;
-		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
+		vlan_tci |= __vlan_dev_get_egress_qos_mask(dev, skb->priority);
 		skb = __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
 	}
 
@@ -253,7 +259,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
 	np->vlan_qos = vlan_qos;
 	/* Before inserting this element in hash table, make sure all its fields
 	 * are committed to memory.
-	 * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
+	 * coupled with smp_rmb() in __vlan_dev_get_egress_qos_mask()
 	 */
 	smp_wmb();
 	vlan->egress_priority_map[skb_prio & 0xF] = np;
-- 
cgit 


From df42153c59a38a65c6f7440d5c70d87d1c24438d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 7 Nov 2013 10:48:49 +0300
Subject: net: make ndev->irq signed for error handling

There is a bug in cpsw_probe() where we do:

	ndev->irq = platform_get_irq(pdev, 0);
	if (ndev->irq < 0) {

The problem is that "ndev->irq" is unsigned so the error handling
doesn't work.  I have changed it to a regular int.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e6353cafbf05..b6f6efbcfc74 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1132,7 +1132,7 @@ struct net_device {
 	unsigned long		mem_end;	/* shared mem end	*/
 	unsigned long		mem_start;	/* shared mem start	*/
 	unsigned long		base_addr;	/* device I/O address	*/
-	unsigned int		irq;		/* device IRQ number	*/
+	int			irq;		/* device IRQ number	*/
 
 	/*
 	 *	Some hardware also needs these fields, but they are not
-- 
cgit 


From a6cc0cfa72e0b6d9f2c8fd858aacc32313c4f272 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Wed, 6 Nov 2013 09:54:46 -0800
Subject: net: Add layer 2 hardware acceleration operations for macvlan devices

Add a operations structure that allows a network interface to export
the fact that it supports package forwarding in hardware between
physical interfaces and other mac layer devices assigned to it (such
as macvlans). This operaions structure can be used by virtual mac
devices to bypass software switching so that forwarding can be done
in hardware more efficiently.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c           | 36 +++++++++++++++++++++++++++++++++++-
 include/linux/if_macvlan.h      |  1 +
 include/linux/netdev_features.h |  2 ++
 include/linux/netdevice.h       | 36 +++++++++++++++++++++++++++++++++++-
 include/uapi/linux/if.h         |  1 +
 net/core/dev.c                  | 18 +++++++++++++-----
 net/core/ethtool.c              |  1 +
 net/sched/sch_generic.c         |  2 +-
 8 files changed, 89 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index cc9845ec91c1..af4aaa5893ff 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -297,7 +297,13 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
 	int ret;
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 
-	ret = macvlan_queue_xmit(skb, dev);
+	if (vlan->fwd_priv) {
+		skb->dev = vlan->lowerdev;
+		ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+	} else {
+		ret = macvlan_queue_xmit(skb, dev);
+	}
+
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
 		struct macvlan_pcpu_stats *pcpu_stats;
 
@@ -347,6 +353,21 @@ static int macvlan_open(struct net_device *dev)
 		goto hash_add;
 	}
 
+	if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
+		vlan->fwd_priv =
+		      lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
+
+		/* If we get a NULL pointer back, or if we get an error
+		 * then we should just fall through to the non accelerated path
+		 */
+		if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
+			vlan->fwd_priv = NULL;
+		} else {
+			dev->features &= ~NETIF_F_LLTX;
+			return 0;
+		}
+	}
+
 	err = -EBUSY;
 	if (macvlan_addr_busy(vlan->port, dev->dev_addr))
 		goto out;
@@ -367,6 +388,11 @@ hash_add:
 del_unicast:
 	dev_uc_del(lowerdev, dev->dev_addr);
 out:
+	if (vlan->fwd_priv) {
+		lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
+							   vlan->fwd_priv);
+		vlan->fwd_priv = NULL;
+	}
 	return err;
 }
 
@@ -375,6 +401,13 @@ static int macvlan_stop(struct net_device *dev)
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
 
+	if (vlan->fwd_priv) {
+		lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev,
+							   vlan->fwd_priv);
+		vlan->fwd_priv = NULL;
+		return 0;
+	}
+
 	dev_uc_unsync(lowerdev, dev);
 	dev_mc_unsync(lowerdev, dev);
 
@@ -833,6 +866,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto destroy_port;
 
+	dev->priv_flags |= IFF_MACVLAN;
 	err = netdev_upper_dev_link(lowerdev, dev);
 	if (err)
 		goto destroy_port;
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index ddd33fd5904d..c2702856295e 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -61,6 +61,7 @@ struct macvlan_dev {
 	struct hlist_node	hlist;
 	struct macvlan_port	*port;
 	struct net_device	*lowerdev;
+	void			*fwd_priv;
 	struct macvlan_pcpu_stats __percpu *pcpu_stats;
 
 	DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ);
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index b05a4b501ab5..1005ebf17575 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -62,6 +62,7 @@ enum {
 	NETIF_F_HW_VLAN_STAG_TX_BIT,	/* Transmit VLAN STAG HW acceleration */
 	NETIF_F_HW_VLAN_STAG_RX_BIT,	/* Receive VLAN STAG HW acceleration */
 	NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */
+	NETIF_F_HW_L2FW_DOFFLOAD_BIT,	/* Allow L2 Forwarding in Hardware */
 
 	/*
 	 * Add your fresh new feature above and remember to update
@@ -116,6 +117,7 @@ enum {
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
+#define NETIF_F_HW_L2FW_DOFFLOAD	__NETIF_F(HW_L2FW_DOFFLOAD)
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b6f6efbcfc74..15fa01c9a3bf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -962,6 +962,25 @@ struct netdev_phys_port_id {
  *	Called by vxlan to notify the driver about a UDP port and socket
  *	address family that vxlan is not listening to anymore. The operation
  *	is protected by the vxlan_net->sock_lock.
+ *
+ * void* (*ndo_dfwd_add_station)(struct net_device *pdev,
+ *				 struct net_device *dev)
+ *	Called by upper layer devices to accelerate switching or other
+ *	station functionality into hardware. 'pdev is the lowerdev
+ *	to use for the offload and 'dev' is the net device that will
+ *	back the offload. Returns a pointer to the private structure
+ *	the upper layer will maintain.
+ * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv)
+ *	Called by upper layer device to delete the station created
+ *	by 'ndo_dfwd_add_station'. 'pdev' is the net device backing
+ *	the station and priv is the structure returned by the add
+ *	operation.
+ * netdev_tx_t (*ndo_dfwd_start_xmit)(struct sk_buff *skb,
+ *				      struct net_device *dev,
+ *				      void *priv);
+ *	Callback to use for xmit over the accelerated station. This
+ *	is used in place of ndo_start_xmit on accelerated net
+ *	devices.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1098,6 +1117,15 @@ struct net_device_ops {
 	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
 						      sa_family_t sa_family,
 						      __be16 port);
+
+	void*			(*ndo_dfwd_add_station)(struct net_device *pdev,
+							struct net_device *dev);
+	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
+							void *priv);
+
+	netdev_tx_t		(*ndo_dfwd_start_xmit) (struct sk_buff *skb,
+							struct net_device *dev,
+							void *priv);
 };
 
 /*
@@ -1195,6 +1223,7 @@ struct net_device {
 	/* Management operations */
 	const struct net_device_ops *netdev_ops;
 	const struct ethtool_ops *ethtool_ops;
+	const struct forwarding_accel_ops *fwd_ops;
 
 	/* Hardware header description */
 	const struct header_ops *header_ops;
@@ -2388,7 +2417,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq);
+			struct netdev_queue *txq, void *accel_priv);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
@@ -2967,6 +2996,11 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 	dev->gso_max_size = size;
 }
 
+static inline bool netif_is_macvlan(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_MACVLAN;
+}
+
 static inline bool netif_is_bond_master(struct net_device *dev)
 {
 	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 1ec407b01e46..d758163b0e43 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -83,6 +83,7 @@
 #define IFF_SUPP_NOFCS	0x80000		/* device supports sending custom FCS */
 #define IFF_LIVE_ADDR_CHANGE 0x100000	/* device supports hardware address
 					 * change when it's running */
+#define IFF_MACVLAN 0x200000		/* Macvlan device */
 
 
 #define IF_GET_IFACE	0x0001		/* for querying only */
diff --git a/net/core/dev.c b/net/core/dev.c
index 0e6136546a8c..8ffc52e01ece 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2538,7 +2538,7 @@ static inline int skb_needs_linearize(struct sk_buff *skb,
 }
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq)
+			struct netdev_queue *txq, void *accel_priv)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
@@ -2604,9 +2604,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			dev_queue_xmit_nit(skb, dev);
 
 		skb_len = skb->len;
-		rc = ops->ndo_start_xmit(skb, dev);
+		if (accel_priv)
+			rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
+		else
+			rc = ops->ndo_start_xmit(skb, dev);
+
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK)
+		if (rc == NETDEV_TX_OK && txq)
 			txq_trans_update(txq);
 		return rc;
 	}
@@ -2622,7 +2626,10 @@ gso:
 			dev_queue_xmit_nit(nskb, dev);
 
 		skb_len = nskb->len;
-		rc = ops->ndo_start_xmit(nskb, dev);
+		if (accel_priv)
+			rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
+		else
+			rc = ops->ndo_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -2647,6 +2654,7 @@ out_kfree_skb:
 out:
 	return rc;
 }
+EXPORT_SYMBOL_GPL(dev_hard_start_xmit);
 
 static void qdisc_pkt_len_init(struct sk_buff *skb)
 {
@@ -2854,7 +2862,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq);
+				rc = dev_hard_start_xmit(skb, dev, txq, NULL);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 862989898f61..30071dec287a 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -96,6 +96,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_LOOPBACK_BIT] =         "loopback",
 	[NETIF_F_RXFCS_BIT] =            "rx-fcs",
 	[NETIF_F_RXALL_BIT] =            "rx-all",
+	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7fc899a943a8..922a09406ba7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq);
+		ret = dev_hard_start_xmit(skb, dev, txq, NULL);
 
 	HARD_TX_UNLOCK(dev, txq);
 
-- 
cgit 


From 6e7136ed7793fa4948b0192dcd6862d12a50d67c Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Thu, 7 Nov 2013 12:19:53 +0200
Subject: net/mlx4_core: ICM pages are allocated on device NUMA node

This is done to optimize FW/HW access to host memory.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/icm.c  | 42 ++++++++++++++++++++++---------
 drivers/net/ethernet/mellanox/mlx4/main.c |  1 +
 include/linux/mlx4/device.h               |  1 +
 3 files changed, 32 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 31d02649be41..5fbf4924c272 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -93,13 +93,17 @@ void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
 	kfree(icm);
 }
 
-static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order, gfp_t gfp_mask)
+static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order,
+				gfp_t gfp_mask, int node)
 {
 	struct page *page;
 
-	page = alloc_pages(gfp_mask, order);
-	if (!page)
-		return -ENOMEM;
+	page = alloc_pages_node(node, gfp_mask, order);
+	if (!page) {
+		page = alloc_pages(gfp_mask, order);
+		if (!page)
+			return -ENOMEM;
+	}
 
 	sg_set_page(mem, page, PAGE_SIZE << order, 0);
 	return 0;
@@ -130,9 +134,15 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 	/* We use sg_set_buf for coherent allocs, which assumes low memory */
 	BUG_ON(coherent && (gfp_mask & __GFP_HIGHMEM));
 
-	icm = kmalloc(sizeof *icm, gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
-	if (!icm)
-		return NULL;
+	icm = kmalloc_node(sizeof(*icm),
+			   gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN),
+			   dev->numa_node);
+	if (!icm) {
+		icm = kmalloc(sizeof(*icm),
+			      gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
+		if (!icm)
+			return NULL;
+	}
 
 	icm->refcount = 0;
 	INIT_LIST_HEAD(&icm->chunk_list);
@@ -141,10 +151,17 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 
 	while (npages > 0) {
 		if (!chunk) {
-			chunk = kmalloc(sizeof *chunk,
-					gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
-			if (!chunk)
-				goto fail;
+			chunk = kmalloc_node(sizeof(*chunk),
+					     gfp_mask & ~(__GFP_HIGHMEM |
+							  __GFP_NOWARN),
+					     dev->numa_node);
+			if (!chunk) {
+				chunk = kmalloc(sizeof(*chunk),
+						gfp_mask & ~(__GFP_HIGHMEM |
+							     __GFP_NOWARN));
+				if (!chunk)
+					goto fail;
+			}
 
 			sg_init_table(chunk->mem, MLX4_ICM_CHUNK_LEN);
 			chunk->npages = 0;
@@ -161,7 +178,8 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 						      cur_order, gfp_mask);
 		else
 			ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
-						   cur_order, gfp_mask);
+						   cur_order, gfp_mask,
+						   dev->numa_node);
 
 		if (ret) {
 			if (--cur_order < 0)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7d2628dfdc29..5789ea2c934d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2191,6 +2191,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	mutex_init(&priv->bf_mutex);
 
 	dev->rev_id = pdev->revision;
+	dev->numa_node = dev_to_node(&pdev->dev);
 	/* Detect if this device is a virtual function */
 	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
 		/* When acting as pf, we normally skip vfs unless explicitly
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f6f59271f857..4cf0b0153639 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -662,6 +662,7 @@ struct mlx4_dev {
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 	int			num_vfs;
+	int			numa_node;
 	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
-- 
cgit 


From 163561a4e2f8af44e96453bc10c7a4f9bcc736e1 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Thu, 7 Nov 2013 12:19:54 +0200
Subject: net/mlx4_en: Datapath structures are allocated per NUMA node

For each RX/TX ring and its CQ, allocation is done on a NUMA node that
corresponds to the core that the data structure should operate on.
The assumption is that the core number is reflected by the ring index.
The affected allocations are the ring/CQ data structures,
the TX/RX info and the shared HW/SW buffer.
For TX rings, each core has rings of all UPs.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     | 17 ++++++++++---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 12 ++++++---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     | 23 +++++++++++------
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     | 34 +++++++++++++++++---------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  6 ++---
 drivers/net/ethernet/mellanox/mlx4/pd.c        | 11 ++++++---
 include/linux/mlx4/device.h                    |  2 +-
 7 files changed, 71 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index d203f11b9edf..3a098cc4d349 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -45,16 +45,20 @@ static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 		      struct mlx4_en_cq **pcq,
-		      int entries, int ring, enum cq_type mode)
+		      int entries, int ring, enum cq_type mode,
+		      int node)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_cq *cq;
 	int err;
 
-	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, node);
 	if (!cq) {
-		en_err(priv, "Failed to allocate CQ structure\n");
-		return -ENOMEM;
+		cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+		if (!cq) {
+			en_err(priv, "Failed to allocate CQ structure\n");
+			return -ENOMEM;
+		}
 	}
 
 	cq->size = entries;
@@ -64,8 +68,13 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	cq->is_tx = mode;
 	spin_lock_init(&cq->lock);
 
+	/* Allocate HW buffers on provided NUMA node.
+	 * dev->numa_node is used in mtt range allocation flow.
+	 */
+	set_dev_node(&mdev->dev->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
 				cq->buf_size, 2 * PAGE_SIZE);
+	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
 	if (err)
 		goto err_cq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index f430788cc4fe..e72d8a112a6b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1895,6 +1895,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
 	int err;
+	int node;
 
 	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
 	if (err) {
@@ -1904,23 +1905,26 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 
 	/* Create tx Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
+		node = cpu_to_node(i % num_online_cpus());
 		if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
-				      prof->tx_ring_size, i, TX))
+				      prof->tx_ring_size, i, TX, node))
 			goto err;
 
 		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i], priv->base_tx_qpn + i,
-					   prof->tx_ring_size, TXBB_SIZE))
+					   prof->tx_ring_size, TXBB_SIZE, node))
 			goto err;
 	}
 
 	/* Create rx Rings */
 	for (i = 0; i < priv->rx_ring_num; i++) {
+		node = cpu_to_node(i % num_online_cpus());
 		if (mlx4_en_create_cq(priv, &priv->rx_cq[i],
-				      prof->rx_ring_size, i, RX))
+				      prof->rx_ring_size, i, RX, node))
 			goto err;
 
 		if (mlx4_en_create_rx_ring(priv, &priv->rx_ring[i],
-					   prof->rx_ring_size, priv->stride))
+					   prof->rx_ring_size, priv->stride,
+					   node))
 			goto err;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 1c45f88776c5..07a1d0fbae47 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -320,17 +320,20 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
-			   u32 size, u16 stride)
+			   u32 size, u16 stride, int node)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_rx_ring *ring;
 	int err = -ENOMEM;
 	int tmp;
 
-	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		en_err(priv, "Failed to allocate RX ring structure\n");
-		return -ENOMEM;
+		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+		if (!ring) {
+			en_err(priv, "Failed to allocate RX ring structure\n");
+			return -ENOMEM;
+		}
 	}
 
 	ring->prod = 0;
@@ -343,17 +346,23 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
-	ring->rx_info = vmalloc(tmp);
+	ring->rx_info = vmalloc_node(tmp, node);
 	if (!ring->rx_info) {
-		err = -ENOMEM;
-		goto err_ring;
+		ring->rx_info = vmalloc(tmp);
+		if (!ring->rx_info) {
+			err = -ENOMEM;
+			goto err_ring;
+		}
 	}
 
 	en_dbg(DRV, priv, "Allocated rx_info ring at addr:%p size:%d\n",
 		 ring->rx_info, tmp);
 
+	/* Allocate HW buffers on provided NUMA node */
+	set_dev_node(&mdev->dev->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres,
 				 ring->buf_size, 2 * PAGE_SIZE);
+	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
 	if (err)
 		goto err_info;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d4e4cf30a720..f54ebd5a1702 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -55,17 +55,20 @@ MODULE_PARM_DESC(inline_thold, "threshold for using inline data");
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring, int qpn, u32 size,
-			   u16 stride)
+			   u16 stride, int node)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_tx_ring *ring;
 	int tmp;
 	int err;
 
-	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		en_err(priv, "Failed allocating TX ring\n");
-		return -ENOMEM;
+		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+		if (!ring) {
+			en_err(priv, "Failed allocating TX ring\n");
+			return -ENOMEM;
+		}
 	}
 
 	ring->size = size;
@@ -75,24 +78,33 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	inline_thold = min(inline_thold, MAX_INLINE);
 
 	tmp = size * sizeof(struct mlx4_en_tx_info);
-	ring->tx_info = vmalloc(tmp);
+	ring->tx_info = vmalloc_node(tmp, node);
 	if (!ring->tx_info) {
-		err = -ENOMEM;
-		goto err_ring;
+		ring->tx_info = vmalloc(tmp);
+		if (!ring->tx_info) {
+			err = -ENOMEM;
+			goto err_ring;
+		}
 	}
 
 	en_dbg(DRV, priv, "Allocated tx_info ring at addr:%p size:%d\n",
 		 ring->tx_info, tmp);
 
-	ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+	ring->bounce_buf = kmalloc_node(MAX_DESC_SIZE, GFP_KERNEL, node);
 	if (!ring->bounce_buf) {
-		err = -ENOMEM;
-		goto err_info;
+		ring->bounce_buf = kmalloc(MAX_DESC_SIZE, GFP_KERNEL);
+		if (!ring->bounce_buf) {
+			err = -ENOMEM;
+			goto err_info;
+		}
 	}
 	ring->buf_size = ALIGN(size * ring->stride, MLX4_EN_PAGE_SIZE);
 
+	/* Allocate HW buffers on provided NUMA node */
+	set_dev_node(&mdev->dev->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size,
 				 2 * PAGE_SIZE);
+	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
 	if (err) {
 		en_err(priv, "Failed allocating hwq resources\n");
 		goto err_bounce;
@@ -118,7 +130,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	}
 	ring->qp.event = mlx4_en_sqp_event;
 
-	err = mlx4_bf_alloc(mdev->dev, &ring->bf);
+	err = mlx4_bf_alloc(mdev->dev, &ring->bf, node);
 	if (err) {
 		en_dbg(DRV, priv, "working without blueflame (%d)", err);
 		ring->bf.uar = &mdev->priv_uar;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b2547ae07dfa..f3758de59c05 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -705,7 +705,7 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv);
 int mlx4_en_alloc_resources(struct mlx4_en_priv *priv);
 
 int mlx4_en_create_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq,
-		      int entries, int ring, enum cq_type mode);
+		      int entries, int ring, enum cq_type mode, int node);
 void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq);
 int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			int cq_idx);
@@ -719,7 +719,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
-			   int qpn, u32 size, u16 stride);
+			   int qpn, u32 size, u16 stride, int node);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);
 int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
@@ -730,7 +730,7 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
 
 int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring **pring,
-			   u32 size, u16 stride);
+			   u32 size, u16 stride, int node);
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride);
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 00f223acada7..84cfb40bf451 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -168,7 +168,7 @@ void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar)
 }
 EXPORT_SYMBOL_GPL(mlx4_uar_free);
 
-int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_uar *uar;
@@ -186,10 +186,13 @@ int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
 			err = -ENOMEM;
 			goto out;
 		}
-		uar = kmalloc(sizeof *uar, GFP_KERNEL);
+		uar = kmalloc_node(sizeof(*uar), GFP_KERNEL, node);
 		if (!uar) {
-			err = -ENOMEM;
-			goto out;
+			uar = kmalloc(sizeof(*uar), GFP_KERNEL);
+			if (!uar) {
+				err = -ENOMEM;
+				goto out;
+			}
 		}
 		err = mlx4_uar_alloc(dev, uar);
 		if (err)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 4cf0b0153639..7d3a523160ba 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -835,7 +835,7 @@ void mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn);
 
 int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar);
 void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar);
-int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf);
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf, int node);
 void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf);
 
 int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
-- 
cgit 


From 0c7ddf36c29c3ce12f2d2931a357ccaa0861035a Mon Sep 17 00:00:00 2001
From: Mathias Krause <mathias.krause@secunet.com>
Date: Thu, 7 Nov 2013 14:18:24 +0100
Subject: net: move pskb_put() to core code

This function has usage beside IPsec so move it to the core skbuff code.
While doing so, give it some documentation and change its return type to
'unsigned char *' to be in line with skb_put().

Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  1 +
 include/net/esp.h      |  2 --
 net/core/skbuff.c      | 23 +++++++++++++++++++++++
 net/xfrm/xfrm_algo.c   | 13 -------------
 4 files changed, 24 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2e153b69d318..491dd6c2c6cc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1417,6 +1417,7 @@ static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset)
 /*
  *	Add data to an sk_buff
  */
+unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
 unsigned char *skb_put(struct sk_buff *skb, unsigned int len);
 static inline unsigned char *__skb_put(struct sk_buff *skb, unsigned int len)
 {
diff --git a/include/net/esp.h b/include/net/esp.h
index c92213c38312..a43be85aedc4 100644
--- a/include/net/esp.h
+++ b/include/net/esp.h
@@ -3,8 +3,6 @@
 
 #include <linux/skbuff.h>
 
-void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len);
-
 struct ip_esp_hdr;
 
 static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3735fad5616e..2fbea08c4f50 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1263,6 +1263,29 @@ free_skb:
 }
 EXPORT_SYMBOL(skb_pad);
 
+/**
+ *	pskb_put - add data to the tail of a potentially fragmented buffer
+ *	@skb: start of the buffer to use
+ *	@tail: tail fragment of the buffer to use
+ *	@len: amount of data to add
+ *
+ *	This function extends the used data area of the potentially
+ *	fragmented buffer. @tail must be the last fragment of @skb -- or
+ *	@skb itself. If this would exceed the total buffer size the kernel
+ *	will panic. A pointer to the first byte of the extra data is
+ *	returned.
+ */
+
+unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
+{
+	if (tail != skb) {
+		skb->data_len += len;
+		skb->len += len;
+	}
+	return skb_put(tail, len);
+}
+EXPORT_SYMBOL_GPL(pskb_put);
+
 /**
  *	skb_put - add data to a buffer
  *	@skb: buffer to use
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index ab4ef72f0b1d..debe733386f8 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -802,17 +802,4 @@ int xfrm_count_pfkey_enc_supported(void)
 }
 EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported);
 
-#if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE)
-
-void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len)
-{
-	if (tail != skb) {
-		skb->data_len += len;
-		skb->len += len;
-	}
-	return skb_put(tail, len);
-}
-EXPORT_SYMBOL_GPL(pskb_put);
-#endif
-
 MODULE_LICENSE("GPL");
-- 
cgit 


From bc32383cd6496d595e6a25cdc7cff1da6b694462 Mon Sep 17 00:00:00 2001
From: Mathias Krause <mathias.krause@secunet.com>
Date: Thu, 7 Nov 2013 14:18:26 +0100
Subject: net: skbuff - kernel-doc fixes

Use "@" to refer to parameters in the kernel-doc description. According
to Documentation/kernel-doc-nano-HOWTO.txt "&" shall be used to refer to
structures only.

Signed-off-by: Mathias Krause <mathias.krause@secunet.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  2 +-
 net/core/skbuff.c      | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 491dd6c2c6cc..036ec7d8a83a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1357,7 +1357,7 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
  * @size: the length of the data
  *
  * As per __skb_fill_page_desc() -- initialises the @i'th fragment of
- * @skb to point to &size bytes at offset @off within @page. In
+ * @skb to point to @size bytes at offset @off within @page. In
  * addition updates @skb such that @i is the last fragment.
  *
  * Does not take any additional reference on the fragment.
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2fbea08c4f50..8c5197fe55a4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1051,8 +1051,8 @@ EXPORT_SYMBOL(__pskb_copy);
  *	@ntail: room to add at tail
  *	@gfp_mask: allocation priority
  *
- *	Expands (or creates identical copy, if &nhead and &ntail are zero)
- *	header of skb. &sk_buff itself is not changed. &sk_buff MUST have
+ *	Expands (or creates identical copy, if @nhead and @ntail are zero)
+ *	header of @skb. &sk_buff itself is not changed. &sk_buff MUST have
  *	reference count of 1. Returns zero in the case of success or error,
  *	if expansion failed. In the last case, &sk_buff is not changed.
  *
@@ -2563,14 +2563,14 @@ EXPORT_SYMBOL(skb_prepare_seq_read);
  * @data: destination pointer for data to be returned
  * @st: state variable
  *
- * Reads a block of skb data at &consumed relative to the
+ * Reads a block of skb data at @consumed relative to the
  * lower offset specified to skb_prepare_seq_read(). Assigns
- * the head of the data block to &data and returns the length
+ * the head of the data block to @data and returns the length
  * of the block or 0 if the end of the skb data or the upper
  * offset has been reached.
  *
  * The caller is not required to consume all of the data
- * returned, i.e. &consumed is typically set to the number
+ * returned, i.e. @consumed is typically set to the number
  * of bytes already consumed and the next call to
  * skb_seq_read() will return the remaining part of the block.
  *
-- 
cgit 


From a404d5576bbe586a1097a8bc2f32c5f22651b0aa Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 17 Sep 2013 22:30:31 +0200
Subject: blktrace: Send BLK_TN_PROCESS events to all running traces

Currently each task sends BLK_TN_PROCESS event to the first traced
device it interacts with after a new trace is started. When there are
several traced devices and the task accesses more devices, this logic
can result in BLK_TN_PROCESS being sent several times to some devices
while it is never sent to other devices. Thus blkparse doesn't display
command name when parsing some blktrace files.

Fix the problem by sending BLK_TN_PROCESS event to all traced devices
when a task interacts with any of them.

Signed-off-by: Jan Kara <jack@suse.cz>
Review-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blktrace_api.h |  2 ++
 kernel/trace/blktrace.c      | 33 +++++++++++++++++++++++++++------
 2 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 7c2e030e72f1..a12f6ed91c84 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -5,6 +5,7 @@
 #include <linux/relay.h>
 #include <linux/compat.h>
 #include <uapi/linux/blktrace_api.h>
+#include <linux/list.h>
 
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
 
@@ -23,6 +24,7 @@ struct blk_trace {
 	struct dentry *dir;
 	struct dentry *dropped_file;
 	struct dentry *msg_file;
+	struct list_head running_list;
 	atomic_t dropped;
 };
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b8b8560bfb95..7f727b34280d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
+#include <linux/list.h>
 
 #include <trace/events/block.h>
 
@@ -38,6 +39,9 @@ static unsigned int blktrace_seq __read_mostly = 1;
 static struct trace_array *blk_tr;
 static bool blk_tracer_enabled __read_mostly;
 
+static LIST_HEAD(running_trace_list);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock);
+
 /* Select an alternative, minimalistic output than the original one */
 #define TRACE_BLK_OPT_CLASSIC	0x1
 
@@ -107,10 +111,18 @@ record_it:
  * Send out a notify for this process, if we haven't done so since a trace
  * started
  */
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+static void trace_note_tsk(struct task_struct *tsk)
 {
+	unsigned long flags;
+	struct blk_trace *bt;
+
 	tsk->btrace_seq = blktrace_seq;
-	trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+	spin_lock_irqsave(&running_trace_lock, flags);
+	list_for_each_entry(bt, &running_trace_list, running_list) {
+		trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm,
+			   sizeof(tsk->comm));
+	}
+	spin_unlock_irqrestore(&running_trace_lock, flags);
 }
 
 static void trace_note_time(struct blk_trace *bt)
@@ -229,16 +241,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		goto record_it;
 	}
 
+	if (unlikely(tsk->btrace_seq != blktrace_seq))
+		trace_note_tsk(tsk);
+
 	/*
 	 * A word about the locking here - we disable interrupts to reserve
 	 * some space in the relay per-cpu buffer, to prevent an irq
 	 * from coming in and stepping on our toes.
 	 */
 	local_irq_save(flags);
-
-	if (unlikely(tsk->btrace_seq != blktrace_seq))
-		trace_note_tsk(bt, tsk);
-
 	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
 	if (t) {
 		sequence = per_cpu_ptr(bt->sequence, cpu);
@@ -477,6 +488,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	bt->dir = dir;
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
+	INIT_LIST_HEAD(&bt->running_list);
 
 	ret = -EIO;
 	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
@@ -601,6 +613,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 			blktrace_seq++;
 			smp_mb();
 			bt->trace_state = Blktrace_running;
+			spin_lock_irq(&running_trace_lock);
+			list_add(&bt->running_list, &running_trace_list);
+			spin_unlock_irq(&running_trace_lock);
 
 			trace_note_time(bt);
 			ret = 0;
@@ -608,6 +623,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 	} else {
 		if (bt->trace_state == Blktrace_running) {
 			bt->trace_state = Blktrace_stopped;
+			spin_lock_irq(&running_trace_lock);
+			list_del_init(&bt->running_list);
+			spin_unlock_irq(&running_trace_lock);
 			relay_flush(bt->rchan);
 			ret = 0;
 		}
@@ -1472,6 +1490,9 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	if (atomic_dec_and_test(&blk_probes_ref))
 		blk_unregister_tracepoints();
 
+	spin_lock_irq(&running_trace_lock);
+	list_del(&bt->running_list);
+	spin_unlock_irq(&running_trace_lock);
 	blk_trace_free(bt);
 	return 0;
 }
-- 
cgit 


From 8077c0d983ab276ec5f2700df56a64d671781905 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 14 Oct 2013 12:14:13 -0400
Subject: bdi: test bdi_init failure

There were two places where return value from bdi_init was not tested.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/char_dev.c               | 3 ++-
 include/linux/backing-dev.h | 4 ++--
 mm/swap.c                   | 3 ++-
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/char_dev.c b/fs/char_dev.c
index afc2bb691780..b9bc05b9513a 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -574,7 +574,8 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data)
 void __init chrdev_init(void)
 {
 	cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
-	bdi_init(&directly_mappable_cdev_bdi);
+	if (bdi_init(&directly_mappable_cdev_bdi))
+		panic("Failed to init directly mappable cdev bdi");
 }
 
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5f66d519a726..24819001f5c8 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -109,7 +109,7 @@ struct backing_dev_info {
 #endif
 };
 
-int bdi_init(struct backing_dev_info *bdi);
+int __must_check bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
 
 __printf(3, 4)
@@ -117,7 +117,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
-int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
+int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
diff --git a/mm/swap.c b/mm/swap.c
index 759c3caf44bd..7a9f80d451f5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -934,7 +934,8 @@ void __init swap_setup(void)
 #ifdef CONFIG_SWAP
 	int i;
 
-	bdi_init(swapper_spaces[0].backing_dev_info);
+	if (bdi_init(swapper_spaces[0].backing_dev_info))
+		panic("Failed to init swap bdi");
 	for (i = 0; i < MAX_SWAPFILES; i++) {
 		spin_lock_init(&swapper_spaces[i].tree_lock);
 		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
-- 
cgit 


From 6678d83f18386eb103f8345024e52c5abe61725c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kmo@daterainc.com>
Date: Wed, 7 Aug 2013 11:14:32 -0700
Subject: block: Consolidate duplicated bio_trim() implementations

Someone cut and pasted md's md_trim_bio() into xen-blkfront.c. Come on,
we should know better than this.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/xen-blkfront.c | 53 +-------------------------------------------
 drivers/md/md.c              | 40 ---------------------------------
 drivers/md/md.h              |  1 -
 drivers/md/raid1.c           | 10 ++++-----
 drivers/md/raid10.c          | 18 +++++++--------
 fs/bio.c                     | 46 ++++++++++++++++++++++++++++++++++++++
 include/linux/bio.h          |  1 +
 7 files changed, 61 insertions(+), 108 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a4660bbee8a6..8d53ed293606 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1336,57 +1336,6 @@ static int blkfront_probe(struct xenbus_device *dev,
 	return 0;
 }
 
-/*
- * This is a clone of md_trim_bio, used to split a bio into smaller ones
- */
-static void trim_bio(struct bio *bio, int offset, int size)
-{
-	/* 'bio' is a cloned bio which we need to trim to match
-	 * the given offset and size.
-	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
-	 */
-	int i;
-	struct bio_vec *bvec;
-	int sofar = 0;
-
-	size <<= 9;
-	if (offset == 0 && size == bio->bi_size)
-		return;
-
-	bio->bi_sector += offset;
-	bio->bi_size = size;
-	offset <<= 9;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
-
-	while (bio->bi_idx < bio->bi_vcnt &&
-	       bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
-		/* remove this whole bio_vec */
-		offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
-		bio->bi_idx++;
-	}
-	if (bio->bi_idx < bio->bi_vcnt) {
-		bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
-		bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
-	}
-	/* avoid any complications with bi_idx being non-zero*/
-	if (bio->bi_idx) {
-		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
-			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
-		bio->bi_vcnt -= bio->bi_idx;
-		bio->bi_idx = 0;
-	}
-	/* Make sure vcnt and last bv are not too big */
-	bio_for_each_segment(bvec, bio, i) {
-		if (sofar + bvec->bv_len > size)
-			bvec->bv_len = size - sofar;
-		if (bvec->bv_len == 0) {
-			bio->bi_vcnt = i;
-			break;
-		}
-		sofar += bvec->bv_len;
-	}
-}
-
 static void split_bio_end(struct bio *bio, int error)
 {
 	struct split_bio *split_bio = bio->bi_private;
@@ -1522,7 +1471,7 @@ static int blkif_recover(struct blkfront_info *info)
 					   (unsigned int)(bio->bi_size >> 9) - offset);
 				cloned_bio = bio_clone(bio, GFP_NOIO);
 				BUG_ON(cloned_bio == NULL);
-				trim_bio(cloned_bio, offset, size);
+				bio_trim(cloned_bio, offset, size);
 				cloned_bio->bi_private = split_bio;
 				cloned_bio->bi_end_io = split_bio_end;
 				submit_bio(cloned_bio->bi_rw, cloned_bio);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 561a65f82e26..752119068d66 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -183,46 +183,6 @@ struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
 }
 EXPORT_SYMBOL_GPL(bio_clone_mddev);
 
-void md_trim_bio(struct bio *bio, int offset, int size)
-{
-	/* 'bio' is a cloned bio which we need to trim to match
-	 * the given offset and size.
-	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
-	 */
-	int i;
-	struct bio_vec *bvec;
-	int sofar = 0;
-
-	size <<= 9;
-	if (offset == 0 && size == bio->bi_size)
-		return;
-
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
-
-	bio_advance(bio, offset << 9);
-
-	bio->bi_size = size;
-
-	/* avoid any complications with bi_idx being non-zero*/
-	if (bio->bi_idx) {
-		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
-			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
-		bio->bi_vcnt -= bio->bi_idx;
-		bio->bi_idx = 0;
-	}
-	/* Make sure vcnt and last bv are not too big */
-	bio_for_each_segment(bvec, bio, i) {
-		if (sofar + bvec->bv_len > size)
-			bvec->bv_len = size - sofar;
-		if (bvec->bv_len == 0) {
-			bio->bi_vcnt = i;
-			break;
-		}
-		sofar += bvec->bv_len;
-	}
-}
-EXPORT_SYMBOL_GPL(md_trim_bio);
-
 /*
  * We have a system wide 'event count' that is incremented
  * on any 'interesting' event, and readers of /proc/mdstat
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 608050c43f17..c96456c16700 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -617,7 +617,6 @@ extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask,
 				   struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   struct mddev *mddev);
-extern void md_trim_bio(struct bio *bio, int offset, int size);
 
 extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
 static inline int mddev_check_plugged(struct mddev *mddev)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index aacf6bf352d8..af6681b19776 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1097,8 +1097,8 @@ read_again:
 		r1_bio->read_disk = rdisk;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(read_bio, r1_bio->sector - bio->bi_sector,
-			    max_sectors);
+		bio_trim(read_bio, r1_bio->sector - bio->bi_sector,
+			 max_sectors);
 
 		r1_bio->bios[rdisk] = read_bio;
 
@@ -1266,7 +1266,7 @@ read_again:
 			continue;
 
 		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(mbio, r1_bio->sector - bio->bi_sector, max_sectors);
+		bio_trim(mbio, r1_bio->sector - bio->bi_sector, max_sectors);
 
 		if (first_clone) {
 			/* do behind I/O ?
@@ -2126,7 +2126,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		wbio->bi_sector = r1_bio->sector;
 		wbio->bi_size = r1_bio->sectors << 9;
 
-		md_trim_bio(wbio, sector - r1_bio->sector, sectors);
+		bio_trim(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_sector += rdev->data_offset;
 		wbio->bi_bdev = rdev->bdev;
 		if (submit_bio_wait(WRITE, wbio) == 0)
@@ -2241,7 +2241,7 @@ read_more:
 		}
 		r1_bio->read_disk = disk;
 		bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
-		md_trim_bio(bio, r1_bio->sector - bio->bi_sector, max_sectors);
+		bio_trim(bio, r1_bio->sector - bio->bi_sector, max_sectors);
 		r1_bio->bios[r1_bio->read_disk] = bio;
 		rdev = conf->mirrors[disk].rdev;
 		printk_ratelimited(KERN_ERR
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 73dc8a377522..7c3508abb5e1 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1302,8 +1302,8 @@ read_again:
 		slot = r10_bio->read_slot;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(read_bio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
+		bio_trim(read_bio, r10_bio->sector - bio->bi_sector,
+			 max_sectors);
 
 		r10_bio->devs[slot].bio = read_bio;
 		r10_bio->devs[slot].rdev = rdev;
@@ -1510,8 +1510,8 @@ retry_write:
 		if (r10_bio->devs[i].bio) {
 			struct md_rdev *rdev = conf->mirrors[d].rdev;
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-				    max_sectors);
+			bio_trim(mbio, r10_bio->sector - bio->bi_sector,
+				 max_sectors);
 			r10_bio->devs[i].bio = mbio;
 
 			mbio->bi_sector	= (r10_bio->devs[i].addr+
@@ -1553,8 +1553,8 @@ retry_write:
 				rdev = conf->mirrors[d].rdev;
 			}
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-				    max_sectors);
+			bio_trim(mbio, r10_bio->sector - bio->bi_sector,
+				 max_sectors);
 			r10_bio->devs[i].repl_bio = mbio;
 
 			mbio->bi_sector	= (r10_bio->devs[i].addr +
@@ -2614,7 +2614,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 			sectors = sect_to_write;
 		/* Write at 'sector' for 'sectors' */
 		wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(wbio, sector - bio->bi_sector, sectors);
+		bio_trim(wbio, sector - bio->bi_sector, sectors);
 		wbio->bi_sector = (r10_bio->devs[i].addr+
 				   choose_data_offset(r10_bio, rdev) +
 				   (sector - r10_bio->sector));
@@ -2687,9 +2687,7 @@ read_more:
 		(unsigned long long)r10_bio->sector);
 	bio = bio_clone_mddev(r10_bio->master_bio,
 			      GFP_NOIO, mddev);
-	md_trim_bio(bio,
-		    r10_bio->sector - bio->bi_sector,
-		    max_sectors);
+	bio_trim(bio, r10_bio->sector - bio->bi_sector, max_sectors);
 	r10_bio->devs[slot].bio = bio;
 	r10_bio->devs[slot].rdev = rdev;
 	bio->bi_sector = r10_bio->devs[slot].addr
diff --git a/fs/bio.c b/fs/bio.c
index ea5035da4d9a..2bdb4e25ee77 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1804,6 +1804,52 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 }
 EXPORT_SYMBOL(bio_split);
 
+/**
+ * bio_trim - trim a bio
+ * @bio:	bio to trim
+ * @offset:	number of sectors to trim from the front of @bio
+ * @size:	size we want to trim @bio to, in sectors
+ */
+void bio_trim(struct bio *bio, int offset, int size)
+{
+	/* 'bio' is a cloned bio which we need to trim to match
+	 * the given offset and size.
+	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
+	 */
+	int i;
+	struct bio_vec *bvec;
+	int sofar = 0;
+
+	size <<= 9;
+	if (offset == 0 && size == bio->bi_size)
+		return;
+
+	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+
+	bio_advance(bio, offset << 9);
+
+	bio->bi_size = size;
+
+	/* avoid any complications with bi_idx being non-zero*/
+	if (bio->bi_idx) {
+		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
+			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
+		bio->bi_vcnt -= bio->bi_idx;
+		bio->bi_idx = 0;
+	}
+	/* Make sure vcnt and last bv are not too big */
+	bio_for_each_segment(bvec, bio, i) {
+		if (sofar + bvec->bv_len > size)
+			bvec->bv_len = size - sofar;
+		if (bvec->bv_len == 0) {
+			bio->bi_vcnt = i;
+			break;
+		}
+		sofar += bvec->bv_len;
+	}
+}
+EXPORT_SYMBOL_GPL(bio_trim);
+
 /**
  *      bio_sector_offset - Find hardware sector offset in bio
  *      @bio:           bio to inspect
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec48bac5b039..162036aca741 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -218,6 +218,7 @@ struct bio_pair {
 };
 extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
 extern void bio_pair_release(struct bio_pair *dbio);
+extern void bio_trim(struct bio *bio, int offset, int size);
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
-- 
cgit 


From f8c5e94486671ffcac696886c246baa6ba89b5cf Mon Sep 17 00:00:00 2001
From: Chen Gang <gang.chen@asianux.com>
Date: Sun, 3 Nov 2013 22:23:39 +0800
Subject: kernel: trace: blktrace: remove redundent memcpy() in
 compat_blk_trace_setup()

do_blk_trace_setup() will fully initialize 'buts.name', so can remove
the related memcpy(). And also use BLKTRACE_BDEV_SIZE and ARRAY_SIZE
instead of hard code number '32'.

Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blktrace_api.h | 2 +-
 kernel/trace/blktrace.c      | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index a12f6ed91c84..afc1343df3c7 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -89,7 +89,7 @@ static inline int blk_trace_init_sysfs(struct device *dev)
 #ifdef CONFIG_COMPAT
 
 struct compat_blk_user_trace_setup {
-	char name[32];
+	char name[BLKTRACE_BDEV_SIZE];
 	u16 act_mask;
 	u32 buf_size;
 	u32 buf_nr;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7f727b34280d..f785aef65799 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -579,13 +579,12 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 		.end_lba = cbuts.end_lba,
 		.pid = cbuts.pid,
 	};
-	memcpy(&buts.name, &cbuts.name, 32);
 
 	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
 	if (ret)
 		return ret;
 
-	if (copy_to_user(arg, &buts.name, 32)) {
+	if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
 		blk_trace_remove(q);
 		return -EFAULT;
 	}
-- 
cgit 


From a8d3f362f52b65207cacbfb4c50f75e9d4751ef6 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Thu, 7 Nov 2013 12:13:27 -0600
Subject: dt/irq: add empty of_irq_count for !OF_IRQ

Add an empty version of of_irq_count for !OF_IRQ. This fixes build error
on sparc in linux-next:

drivers/gpio/gpio-bcm-kona.c:542: undefined reference to `of_irq_count'

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
---
 include/linux/of_irq.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index c0d6dfe80895..3f23b4472c31 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -37,12 +37,20 @@ extern int of_irq_parse_one(struct device_node *device, int index,
 extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data);
 extern int of_irq_to_resource(struct device_node *dev, int index,
 			      struct resource *r);
-extern int of_irq_count(struct device_node *dev);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);
 
 extern void of_irq_init(const struct of_device_id *matches);
 
+#ifdef CONFIG_OF_IRQ
+extern int of_irq_count(struct device_node *dev);
+#else
+static inline int of_irq_count(struct device_node *dev)
+{
+	return 0;
+}
+#endif
+
 #if defined(CONFIG_OF)
 /*
  * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC
-- 
cgit 


From 4d4dead67a4ab1d5de393f15ed5e4e2aa63d3bcf Mon Sep 17 00:00:00 2001
From: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Sun, 3 Nov 2013 16:47:33 -0800
Subject: drm/i915/bdw: Add device IDs

v2: Squash in "drm/i915/bdw: Add BDW to the HAS_DDI check" as
suggested by Damien.

v3: Squash in VEBOX enabling from  Zhao Yakui <yakui.zhao@intel.com>

v4: Rebase on top of Jesse's patch to extract all pci ids to
include/drm/i915_pciids.h.

v4: Replace Halo by its marketing moniker Iris. Requested by Ben.

v5: Switch from info->has*ring to info->ring_mask.

v6: Add 0x16X2 variant (which is newer than this patch)
Rename to use new naming scheme (Chris)
Remove Simulator PCI ids. These snuck in during rebase (Chris)

v7: Fix poor sed job from v6
Make the desktop variants use the desktop macro (Rebase error). Notice
that this makes no functional difference - it's just confusing.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.c | 22 +++++++++++++++++++++-
 include/drm/i915_pciids.h       | 25 +++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a0804fa1e306..70799febb8ba 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -336,6 +336,24 @@ static const struct intel_device_info intel_haswell_m_info = {
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 };
 
+static const struct intel_device_info intel_broadwell_d_info = {
+	.is_preliminary = 1,
+	.gen = 8,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+};
+
+static const struct intel_device_info intel_broadwell_m_info = {
+	.is_preliminary = 1,
+	.gen = 8, .is_mobile = 1,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+};
+
 /*
  * Make sure any device matches here are from most specific to most
  * general.  For example, since the Quanta match is based on the subsystem
@@ -367,7 +385,9 @@ static const struct intel_device_info intel_haswell_m_info = {
 	INTEL_HSW_D_IDS(&intel_haswell_d_info), \
 	INTEL_HSW_M_IDS(&intel_haswell_m_info), \
 	INTEL_VLV_M_IDS(&intel_valleyview_m_info),	\
-	INTEL_VLV_D_IDS(&intel_valleyview_d_info)
+	INTEL_VLV_D_IDS(&intel_valleyview_d_info),	\
+	INTEL_BDW_M_IDS(&intel_broadwell_m_info),	\
+	INTEL_BDW_D_IDS(&intel_broadwell_d_info)
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_PCI_IDS,
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 8a10f5c354e6..940ece4934ba 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -208,4 +208,29 @@
 #define INTEL_VLV_D_IDS(info) \
 	INTEL_VGA_DEVICE(0x0155, info)
 
+#define _INTEL_BDW_M(gt, id, info) \
+	INTEL_VGA_DEVICE((((gt) - 1) << 4) | (id), info)
+#define _INTEL_BDW_D(gt, id, info) \
+	INTEL_VGA_DEVICE((((gt) - 1) << 4) | (id), info)
+
+#define _INTEL_BDW_M_IDS(gt, info) \
+	_INTEL_BDW_M(gt, 0x1602, info), /* ULT */ \
+	_INTEL_BDW_M(gt, 0x1606, info), /* ULT */ \
+	_INTEL_BDW_M(gt, 0x160B, info), /* Iris */ \
+	_INTEL_BDW_M(gt, 0x160E, info) /* ULX */
+
+#define _INTEL_BDW_D_IDS(gt, info) \
+	_INTEL_BDW_D(gt, 0x160A, info), /* Server */ \
+	_INTEL_BDW_D(gt, 0x160D, info) /* Workstation */
+
+#define INTEL_BDW_M_IDS(info) \
+	_INTEL_BDW_M_IDS(1, info), \
+	_INTEL_BDW_M_IDS(2, info), \
+	_INTEL_BDW_M_IDS(3, info)
+
+#define INTEL_BDW_D_IDS(info) \
+	_INTEL_BDW_D_IDS(1, info), \
+	_INTEL_BDW_D_IDS(2, info), \
+	_INTEL_BDW_D_IDS(3, info)
+
 #endif /* _I915_PCIIDS_H */
-- 
cgit 


From 9459d252378aea80d28dc12bfec9a0d31b2a61bf Mon Sep 17 00:00:00 2001
From: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Sun, 3 Nov 2013 16:53:55 -0800
Subject: drm/i915/bdw: support GMS and GGMS changes

All the BARs have the ability to grow.

v2: Pulled out the simulator workaround to a separate patch.
Rebased.

v3: Rebase onto latest vlv patches from Jesse.

v4: Rebased on top of the early stolen quirk patch from Jesse.

v5: Use the new macro names.
s/INTEL_BDW_PCI_IDS_D/INTEL_BDW_D_IDS
s/INTEL_BDW_PCI_IDS_M/INTEL_BDW_M_IDS
It's Jesse's fault for not following the convention I originally set.

Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 arch/x86/kernel/early-quirks.c      | 12 ++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.c | 29 ++++++++++++++++++++++++++---
 include/drm/i915_drm.h              |  4 ++++
 3 files changed, 42 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index b3cd3ebae077..96f958d8cd45 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -313,6 +313,16 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
 	return gmch_ctrl << 25; /* 32 MB units */
 }
 
+static inline size_t gen8_stolen_size(int num, int slot, int func)
+{
+	u16 gmch_ctrl;
+
+	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+	gmch_ctrl >>= BDW_GMCH_GMS_SHIFT;
+	gmch_ctrl &= BDW_GMCH_GMS_MASK;
+	return gmch_ctrl << 25; /* 32 MB units */
+}
+
 typedef size_t (*stolen_size_fn)(int num, int slot, int func);
 
 static struct pci_device_id intel_stolen_ids[] __initdata = {
@@ -336,6 +346,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = {
 	INTEL_IVB_D_IDS(gen6_stolen_size),
 	INTEL_HSW_D_IDS(gen6_stolen_size),
 	INTEL_HSW_M_IDS(gen6_stolen_size),
+	INTEL_BDW_M_IDS(gen8_stolen_size),
+	INTEL_BDW_D_IDS(gen8_stolen_size)
 };
 
 static void __init intel_graphics_stolen(int num, int slot, int func)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7d5a51fea1bb..074aec11fc9b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -869,6 +869,15 @@ static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
 	return snb_gmch_ctl << 20;
 }
 
+static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
+{
+	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
+	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
+	if (bdw_gmch_ctl)
+		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+	return bdw_gmch_ctl << 20;
+}
+
 static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
 {
 	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
@@ -876,6 +885,13 @@ static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
 	return snb_gmch_ctl << 25; /* 32 MB units */
 }
 
+static inline size_t gen8_get_stolen_size(u16 bdw_gmch_ctl)
+{
+	bdw_gmch_ctl >>= BDW_GMCH_GMS_SHIFT;
+	bdw_gmch_ctl &= BDW_GMCH_GMS_MASK;
+	return bdw_gmch_ctl << 25; /* 32 MB units */
+}
+
 static int gen6_gmch_probe(struct drm_device *dev,
 			   size_t *gtt_total,
 			   size_t *stolen,
@@ -903,10 +919,16 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(40)))
 		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(40));
 	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
 
-	*stolen = gen6_get_stolen_size(snb_gmch_ctl);
-	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
+	if (IS_GEN8(dev)) {
+		gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl);
+		*gtt_total = (gtt_size / 8) << PAGE_SHIFT;
+		*stolen = gen8_get_stolen_size(snb_gmch_ctl);
+	} else {
+		gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
+		*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
+		*stolen = gen6_get_stolen_size(snb_gmch_ctl);
+	}
 
 	/* For Modern GENs the PTEs and register space are split in the BAR */
 	gtt_bus_addr = pci_resource_start(dev->pdev, 0) +
@@ -916,6 +938,7 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	if (!dev_priv->gtt.gsm) {
 		DRM_ERROR("Failed to map the gtt page table\n");
 		return -ENOMEM;
+
 	}
 
 	ret = setup_scratch_page(dev);
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 3abfa6ea226e..97d5497debc1 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -49,6 +49,10 @@ extern bool i915_gpu_turbo_disable(void);
 #define    SNB_GMCH_GGMS_MASK	0x3
 #define    SNB_GMCH_GMS_SHIFT   3 /* Graphics Mode Select */
 #define    SNB_GMCH_GMS_MASK    0x1f
+#define    BDW_GMCH_GGMS_SHIFT	6
+#define    BDW_GMCH_GGMS_MASK	0x3
+#define    BDW_GMCH_GMS_SHIFT   8
+#define    BDW_GMCH_GMS_MASK    0xff
 
 #define I830_GMCH_CTRL			0x52
 
-- 
cgit 


From 96212fe8c27b39cc713cd8eb8d8e7a55ce3405d5 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 9 Aug 2013 17:28:54 -0400
Subject: drm/radeon: add pci ids for hawaii

This adds the pci ids for hawaii.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/drm_pciids.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 3d79e513c0b3..87578c109e48 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -261,6 +261,18 @@
 	{0x1002, 0x679B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x679E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x679F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67A8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67A9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67AA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67B0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67B1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67B8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67B9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67BA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x67BE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HAWAII|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6801, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6802, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-- 
cgit 


From 3fdfa5ff50aee5b524fb22b6e0e511b73752a257 Mon Sep 17 00:00:00 2001
From: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Date: Thu, 7 Nov 2013 17:53:12 +0100
Subject: ipv6: enable IPV6_FLOWLABEL_MGR for getsockopt

It is already possible to set/put/renew a label
with IPV6_FLOWLABEL_MGR and setsockopt. This patch
add the possibility to get information about this
label (current value, time before expiration, etc).

It helps application to take decision for a renew
or a release of the label.

v2:
 * Add spin_lock to prevent race condition
 * return -ENOENT if no result found
 * check if flr_action is GET

v3:
 * move the spin_lock to protect only the
   relevant code

Signed-off-by: Florent Fourcot <florent.fourcot@enst-bretagne.fr>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       |  1 +
 net/ipv6/ip6_flowlabel.c | 26 ++++++++++++++++++++++++++
 net/ipv6/ipv6_sockglue.c | 28 ++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index dd96638ab8ff..2a5f668cd683 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -250,6 +250,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
 					 struct ipv6_txoptions *fopt);
 void fl6_free_socklist(struct sock *sk);
 int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen);
+int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq);
 int ip6_flowlabel_init(void);
 void ip6_flowlabel_cleanup(void);
 
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 819578e92499..4a06ed01d0c3 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -475,6 +475,32 @@ static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl,
 	spin_unlock_bh(&ip6_sk_fl_lock);
 }
 
+int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_fl_socklist *sfl;
+
+	rcu_read_lock_bh();
+
+	for_each_sk_fl_rcu(np, sfl) {
+		if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) {
+			spin_lock_bh(&ip6_fl_lock);
+			freq->flr_label = sfl->fl->label;
+			freq->flr_dst = sfl->fl->dst;
+			freq->flr_share = sfl->fl->share;
+			freq->flr_expires = (sfl->fl->expires - jiffies) / HZ;
+			freq->flr_linger = sfl->fl->linger / HZ;
+
+			spin_unlock_bh(&ip6_fl_lock);
+			rcu_read_unlock_bh();
+			return 0;
+		}
+	}
+	rcu_read_unlock_bh();
+
+	return -ENOENT;
+}
+
 int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 {
 	int uninitialized_var(err);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4919a8e6063e..1c6ce3119ff8 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1212,6 +1212,34 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		val = np->sndflow;
 		break;
 
+	case IPV6_FLOWLABEL_MGR:
+	{
+		struct in6_flowlabel_req freq;
+
+		if (len < sizeof(freq))
+			return -EINVAL;
+
+		if (copy_from_user(&freq, optval, sizeof(freq)))
+			return -EFAULT;
+
+		if (freq.flr_action != IPV6_FL_A_GET)
+			return -EINVAL;
+
+		len = sizeof(freq);
+		memset(&freq, 0, sizeof(freq));
+
+		val = ipv6_flowlabel_opt_get(sk, &freq);
+		if (val < 0)
+			return val;
+
+		if (put_user(len, optlen))
+			return -EFAULT;
+		if (copy_to_user(optval, &freq, len))
+			return -EFAULT;
+
+		return 0;
+	}
+
 	case IPV6_ADDR_PREFERENCES:
 		val = 0;
 
-- 
cgit 


From 8deb3eb1461e4cb136c88d03ec5a6729ccf2f933 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Fri, 25 Oct 2013 16:26:02 -0400
Subject: xen/mcfg: Call PHYSDEVOP_pci_mmcfg_reserved for MCFG areas.

The PCI MMCONFIG area is usually reserved via the E820 so the Xen hypervisor
is aware of these regions. But they can also be enumerated in the ACPI
DSDT which means the hypervisor won't know of them until the initial
domain informs it of via PHYSDEVOP_pci_mmcfg_reserved.

This is what this patch does for all of the MCFG regions that the
initial domain is aware of (E820 enumerated and ACPI).

Reported-by:  Santosh Jodh <Santosh.Jodh@citrix.com>
CC: Jan Beulich <JBeulich@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
CC: David Vrabel <david.vrabel@citrix.com>
CC: Mukesh Rathor <mukesh.rathor@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
[v1: Redid it a bit]
[v2: Dropped the P2M 1-1 setting]
[v3: Check for Xen in-case we are running under baremetal]
[v4: Wrap with CONFIG_PCI_MMCONFIG]
---
 drivers/xen/pci.c               | 47 +++++++++++++++++++++++++++++++++++++++++
 include/xen/interface/physdev.h | 11 ++++++++++
 2 files changed, 58 insertions(+)

(limited to 'include')

diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index 18fff88254eb..d15f6e80479f 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -26,6 +26,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include "../pci/pci.h"
+#include <asm/pci_x86.h>
 
 static bool __read_mostly pci_seg_supported = true;
 
@@ -192,3 +193,49 @@ static int __init register_xen_pci_notifier(void)
 }
 
 arch_initcall(register_xen_pci_notifier);
+
+#ifdef CONFIG_PCI_MMCONFIG
+static int __init xen_mcfg_late(void)
+{
+	struct pci_mmcfg_region *cfg;
+	int rc;
+
+	if (!xen_initial_domain())
+		return 0;
+
+	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+		return 0;
+
+	if (list_empty(&pci_mmcfg_list))
+		return 0;
+
+	/* Check whether they are in the right area. */
+	list_for_each_entry(cfg, &pci_mmcfg_list, list) {
+		struct physdev_pci_mmcfg_reserved r;
+
+		r.address = cfg->address;
+		r.segment = cfg->segment;
+		r.start_bus = cfg->start_bus;
+		r.end_bus = cfg->end_bus;
+		r.flags = XEN_PCI_MMCFG_RESERVED;
+
+		rc = HYPERVISOR_physdev_op(PHYSDEVOP_pci_mmcfg_reserved, &r);
+		switch (rc) {
+		case 0:
+		case -ENOSYS:
+			continue;
+
+		default:
+			pr_warn("Failed to report MMCONFIG reservation"
+				" state for %s to hypervisor"
+				" (%d)\n",
+				cfg->name, rc);
+		}
+	}
+	return 0;
+}
+/*
+ * Needs to be done after acpi_init which are subsys_initcall.
+ */
+subsys_initcall_sync(xen_mcfg_late);
+#endif
diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h
index 7000bb1f6e96..42721d13a106 100644
--- a/include/xen/interface/physdev.h
+++ b/include/xen/interface/physdev.h
@@ -231,6 +231,17 @@ struct physdev_get_free_pirq {
 #define XEN_PCI_DEV_VIRTFN             0x2
 #define XEN_PCI_DEV_PXM                0x4
 
+#define XEN_PCI_MMCFG_RESERVED         0x1
+
+#define PHYSDEVOP_pci_mmcfg_reserved    24
+struct physdev_pci_mmcfg_reserved {
+    uint64_t address;
+    uint16_t segment;
+    uint8_t start_bus;
+    uint8_t end_bus;
+    uint32_t flags;
+};
+
 #define PHYSDEVOP_pci_device_add        25
 struct physdev_pci_device_add {
     /* IN */
-- 
cgit 


From 6fe19278ffebdd57e5c5ec10275e6d423404364e Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Date: Mon, 4 Nov 2013 17:54:27 +0000
Subject: swiotlb-xen: missing include dma-direction.h

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 include/xen/swiotlb-xen.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index de8bcc641c49..4d81cccf1097 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -1,6 +1,7 @@
 #ifndef __LINUX_SWIOTLB_XEN_H
 #define __LINUX_SWIOTLB_XEN_H
 
+#include <linux/dma-direction.h>
 #include <linux/swiotlb.h>
 
 extern int xen_swiotlb_init(int verbose, bool early);
-- 
cgit 


From 4863e525659abbc903aacc67fd916f12914f6c1d Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Fri, 8 Nov 2013 13:10:44 -0800
Subject: target: Add per device xcopy_lun for copy offload I/O

This patch adds a se_device->xcopy_lun that is used for local
copy offload I/O, instead of allocating + initializing a pseudo
se_lun for each received EXTENDED_COPY operation.

Also, move declaration of struct se_lun + struct se_port_stat_grps
ahead of struct se_device.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c |  9 ++++++
 drivers/target/target_core_xcopy.c  | 18 +-----------
 include/target/target_core_base.h   | 57 +++++++++++++++++++------------------
 3 files changed, 39 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 569a3c7c9e5a..dbe40ef14776 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1409,6 +1409,7 @@ static void scsi_dump_inquiry(struct se_device *dev)
 struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 {
 	struct se_device *dev;
+	struct se_lun *xcopy_lun;
 
 	dev = hba->transport->alloc_device(hba, name);
 	if (!dev)
@@ -1471,6 +1472,14 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
 	dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
 
+	xcopy_lun = &dev->xcopy_lun;
+	xcopy_lun->lun_se_dev = dev;
+	init_completion(&xcopy_lun->lun_shutdown_comp);
+	INIT_LIST_HEAD(&xcopy_lun->lun_acl_list);
+	spin_lock_init(&xcopy_lun->lun_acl_lock);
+	spin_lock_init(&xcopy_lun->lun_sep_lock);
+	init_completion(&xcopy_lun->lun_ref_comp);
+
 	return dev;
 }
 
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index b12fc43b5463..d67304a6aa9e 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -401,9 +401,6 @@ static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
 	struct xcopy_pt_cmd *xpt_cmd = container_of(se_cmd,
 				struct xcopy_pt_cmd, se_cmd);
 
-	if (xpt_cmd->remote_port)
-		kfree(se_cmd->se_lun);
-
 	kfree(xpt_cmd);
 }
 
@@ -568,21 +565,10 @@ static int target_xcopy_init_pt_lun(
 		return 0;
 	}
 
-	pt_cmd->se_lun = kzalloc(sizeof(struct se_lun), GFP_KERNEL);
-	if (!pt_cmd->se_lun) {
-		pr_err("Unable to allocate pt_cmd->se_lun\n");
-		return -ENOMEM;
-	}
-	init_completion(&pt_cmd->se_lun->lun_shutdown_comp);
-	INIT_LIST_HEAD(&pt_cmd->se_lun->lun_acl_list);
-	spin_lock_init(&pt_cmd->se_lun->lun_acl_lock);
-	spin_lock_init(&pt_cmd->se_lun->lun_sep_lock);
-	init_completion(&pt_cmd->se_lun->lun_ref_comp);
-
+	pt_cmd->se_lun = &se_dev->xcopy_lun;
 	pt_cmd->se_dev = se_dev;
 
 	pr_debug("Setup emulated se_dev: %p from se_dev\n", pt_cmd->se_dev);
-	pt_cmd->se_lun->lun_se_dev = se_dev;
 	pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH;
 
 	pr_debug("Setup emulated se_dev: %p to pt_cmd->se_lun->lun_se_dev\n",
@@ -653,8 +639,6 @@ static int target_xcopy_setup_pt_cmd(
 	return 0;
 
 out:
-	if (remote_port == true)
-		kfree(cmd->se_lun);
 	return ret;
 }
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 1ad0a4240b00..96bf1b0239cc 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -627,6 +627,34 @@ struct se_dev_attrib {
 	struct config_group da_group;
 };
 
+struct se_port_stat_grps {
+	struct config_group stat_group;
+	struct config_group scsi_port_group;
+	struct config_group scsi_tgt_port_group;
+	struct config_group scsi_transport_group;
+};
+
+struct se_lun {
+#define SE_LUN_LINK_MAGIC			0xffff7771
+	u32			lun_link_magic;
+	/* See transport_lun_status_table */
+	enum transport_lun_status_table lun_status;
+	u32			lun_access;
+	u32			lun_flags;
+	u32			unpacked_lun;
+	atomic_t		lun_acl_count;
+	spinlock_t		lun_acl_lock;
+	spinlock_t		lun_sep_lock;
+	struct completion	lun_shutdown_comp;
+	struct list_head	lun_acl_list;
+	struct se_device	*lun_se_dev;
+	struct se_port		*lun_sep;
+	struct config_group	lun_group;
+	struct se_port_stat_grps port_stat_grps;
+	struct completion	lun_ref_comp;
+	struct percpu_ref	lun_ref;
+};
+
 struct se_dev_stat_grps {
 	struct config_group stat_group;
 	struct config_group scsi_dev_group;
@@ -710,6 +738,7 @@ struct se_device {
 	struct se_subsystem_api *transport;
 	/* Linked list for struct se_hba struct se_device list */
 	struct list_head	dev_list;
+	struct se_lun		xcopy_lun;
 };
 
 struct se_hba {
@@ -729,34 +758,6 @@ struct se_hba {
 	struct se_subsystem_api *transport;
 };
 
-struct se_port_stat_grps {
-	struct config_group stat_group;
-	struct config_group scsi_port_group;
-	struct config_group scsi_tgt_port_group;
-	struct config_group scsi_transport_group;
-};
-
-struct se_lun {
-#define SE_LUN_LINK_MAGIC			0xffff7771
-	u32			lun_link_magic;
-	/* See transport_lun_status_table */
-	enum transport_lun_status_table lun_status;
-	u32			lun_access;
-	u32			lun_flags;
-	u32			unpacked_lun;
-	atomic_t		lun_acl_count;
-	spinlock_t		lun_acl_lock;
-	spinlock_t		lun_sep_lock;
-	struct completion	lun_shutdown_comp;
-	struct list_head	lun_acl_list;
-	struct se_device	*lun_se_dev;
-	struct se_port		*lun_sep;
-	struct config_group	lun_group;
-	struct se_port_stat_grps port_stat_grps;
-	struct completion	lun_ref_comp;
-	struct percpu_ref	lun_ref;
-};
-
 struct scsi_port_stats {
        u64     cmd_pdus;
        u64     tx_data_octets;
-- 
cgit 


From 746b5583c1a48a837f4891adaff5e09d61b204a6 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Wed, 23 Oct 2013 09:53:14 +0300
Subject: IB/mlx5: Multithreaded create MR

Use asynchronous commands to execute up to eight concurrent create MR
commands. This is to fill memory caches faster so we keep consuming
from there.  Also, increase timeout for shrinking caches to five
minutes.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/main.c                 |   3 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h              |   6 +
 drivers/infiniband/hw/mlx5/mr.c                   | 163 +++++++++++++++++-----
 drivers/infiniband/hw/mlx5/qp.c                   |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c     | 106 ++++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/debugfs.c |   8 +-
 drivers/net/ethernet/mellanox/mlx5/core/mr.c      |  32 +++--
 include/linux/mlx5/driver.h                       |  17 ++-
 8 files changed, 255 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index b1a6cb3a2809..306534109627 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -745,7 +745,8 @@ static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
 	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 	seg->start_addr = 0;
 
-	err = mlx5_core_create_mkey(&dev->mdev, &mr, in, sizeof(*in));
+	err = mlx5_core_create_mkey(&dev->mdev, &mr, in, sizeof(*in),
+				    NULL, NULL, NULL);
 	if (err) {
 		mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
 		goto err_in;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 836be9157242..4c134d93d4fc 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -262,6 +262,9 @@ struct mlx5_ib_mr {
 	int			npages;
 	struct completion	done;
 	enum ib_wc_status	status;
+	struct mlx5_ib_dev     *dev;
+	struct mlx5_create_mkey_mbox_out out;
+	unsigned long		start;
 };
 
 struct mlx5_ib_fast_reg_page_list {
@@ -323,6 +326,7 @@ struct mlx5_cache_ent {
 	struct mlx5_ib_dev     *dev;
 	struct work_struct	work;
 	struct delayed_work	dwork;
+	int			pending;
 };
 
 struct mlx5_mr_cache {
@@ -358,6 +362,8 @@ struct mlx5_ib_dev {
 	spinlock_t			mr_lock;
 	struct mlx5_ib_resources	devr;
 	struct mlx5_mr_cache		cache;
+	struct timer_list		delay_timer;
+	int				fill_delay;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3453580b1eb2..d7f202290747 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -35,11 +35,13 @@
 #include <linux/random.h>
 #include <linux/debugfs.h>
 #include <linux/export.h>
+#include <linux/delay.h>
 #include <rdma/ib_umem.h>
 #include "mlx5_ib.h"
 
 enum {
 	DEF_CACHE_SIZE	= 10,
+	MAX_PENDING_REG_MR = 8,
 };
 
 enum {
@@ -63,6 +65,57 @@ static int order2idx(struct mlx5_ib_dev *dev, int order)
 		return order - cache->ent[0].order;
 }
 
+static void reg_mr_callback(int status, void *context)
+{
+	struct mlx5_ib_mr *mr = context;
+	struct mlx5_ib_dev *dev = mr->dev;
+	struct mlx5_mr_cache *cache = &dev->cache;
+	int c = order2idx(dev, mr->order);
+	struct mlx5_cache_ent *ent = &cache->ent[c];
+	u8 key;
+	unsigned long delta = jiffies - mr->start;
+	unsigned long index;
+	unsigned long flags;
+
+	index = find_last_bit(&delta, 8 * sizeof(delta));
+	if (index == 64)
+		index = 0;
+
+	spin_lock_irqsave(&ent->lock, flags);
+	ent->pending--;
+	spin_unlock_irqrestore(&ent->lock, flags);
+	if (status) {
+		mlx5_ib_warn(dev, "async reg mr failed. status %d\n", status);
+		kfree(mr);
+		dev->fill_delay = 1;
+		mod_timer(&dev->delay_timer, jiffies + HZ);
+		return;
+	}
+
+	if (mr->out.hdr.status) {
+		mlx5_ib_warn(dev, "failed - status %d, syndorme 0x%x\n",
+			     mr->out.hdr.status,
+			     be32_to_cpu(mr->out.hdr.syndrome));
+		kfree(mr);
+		dev->fill_delay = 1;
+		mod_timer(&dev->delay_timer, jiffies + HZ);
+		return;
+	}
+
+	spin_lock_irqsave(&dev->mdev.priv.mkey_lock, flags);
+	key = dev->mdev.priv.mkey_key++;
+	spin_unlock_irqrestore(&dev->mdev.priv.mkey_lock, flags);
+	mr->mmr.key = mlx5_idx_to_mkey(be32_to_cpu(mr->out.mkey) & 0xffffff) | key;
+
+	cache->last_add = jiffies;
+
+	spin_lock_irqsave(&ent->lock, flags);
+	list_add_tail(&mr->list, &ent->head);
+	ent->cur++;
+	ent->size++;
+	spin_unlock_irqrestore(&ent->lock, flags);
+}
+
 static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
@@ -78,36 +131,39 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 		return -ENOMEM;
 
 	for (i = 0; i < num; i++) {
+		if (ent->pending >= MAX_PENDING_REG_MR) {
+			err = -EAGAIN;
+			break;
+		}
+
 		mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 		if (!mr) {
 			err = -ENOMEM;
-			goto out;
+			break;
 		}
 		mr->order = ent->order;
 		mr->umred = 1;
+		mr->dev = dev;
 		in->seg.status = 1 << 6;
 		in->seg.xlt_oct_size = cpu_to_be32((npages + 1) / 2);
 		in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 		in->seg.flags = MLX5_ACCESS_MODE_MTT | MLX5_PERM_UMR_EN;
 		in->seg.log2_page_size = 12;
 
+		spin_lock_irq(&ent->lock);
+		ent->pending++;
+		spin_unlock_irq(&ent->lock);
+		mr->start = jiffies;
 		err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in,
-					    sizeof(*in));
+					    sizeof(*in), reg_mr_callback,
+					    mr, &mr->out);
 		if (err) {
 			mlx5_ib_warn(dev, "create mkey failed %d\n", err);
 			kfree(mr);
-			goto out;
+			break;
 		}
-		cache->last_add = jiffies;
-
-		spin_lock(&ent->lock);
-		list_add_tail(&mr->list, &ent->head);
-		ent->cur++;
-		ent->size++;
-		spin_unlock(&ent->lock);
 	}
 
-out:
 	kfree(in);
 	return err;
 }
@@ -121,16 +177,16 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num)
 	int i;
 
 	for (i = 0; i < num; i++) {
-		spin_lock(&ent->lock);
+		spin_lock_irq(&ent->lock);
 		if (list_empty(&ent->head)) {
-			spin_unlock(&ent->lock);
+			spin_unlock_irq(&ent->lock);
 			return;
 		}
 		mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list);
 		list_del(&mr->list);
 		ent->cur--;
 		ent->size--;
-		spin_unlock(&ent->lock);
+		spin_unlock_irq(&ent->lock);
 		err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
 		if (err)
 			mlx5_ib_warn(dev, "failed destroy mkey\n");
@@ -162,9 +218,13 @@ static ssize_t size_write(struct file *filp, const char __user *buf,
 		return -EINVAL;
 
 	if (var > ent->size) {
-		err = add_keys(dev, c, var - ent->size);
-		if (err)
-			return err;
+		do {
+			err = add_keys(dev, c, var - ent->size);
+			if (err && err != -EAGAIN)
+				return err;
+
+			usleep_range(3000, 5000);
+		} while (err);
 	} else if (var < ent->size) {
 		remove_keys(dev, c, ent->size - var);
 	}
@@ -280,23 +340,37 @@ static void __cache_work_func(struct mlx5_cache_ent *ent)
 	struct mlx5_ib_dev *dev = ent->dev;
 	struct mlx5_mr_cache *cache = &dev->cache;
 	int i = order2idx(dev, ent->order);
+	int err;
 
 	if (cache->stopped)
 		return;
 
 	ent = &dev->cache.ent[i];
-	if (ent->cur < 2 * ent->limit) {
-		add_keys(dev, i, 1);
-		if (ent->cur < 2 * ent->limit)
-			queue_work(cache->wq, &ent->work);
+	if (ent->cur < 2 * ent->limit && !dev->fill_delay) {
+		err = add_keys(dev, i, 1);
+		if (ent->cur < 2 * ent->limit) {
+			if (err == -EAGAIN) {
+				mlx5_ib_dbg(dev, "returned eagain, order %d\n",
+					    i + 2);
+				queue_delayed_work(cache->wq, &ent->dwork,
+						   msecs_to_jiffies(3));
+			} else if (err) {
+				mlx5_ib_warn(dev, "command failed order %d, err %d\n",
+					     i + 2, err);
+				queue_delayed_work(cache->wq, &ent->dwork,
+						   msecs_to_jiffies(1000));
+			} else {
+				queue_work(cache->wq, &ent->work);
+			}
+		}
 	} else if (ent->cur > 2 * ent->limit) {
 		if (!someone_adding(cache) &&
-		    time_after(jiffies, cache->last_add + 60 * HZ)) {
+		    time_after(jiffies, cache->last_add + 300 * HZ)) {
 			remove_keys(dev, i, 1);
 			if (ent->cur > ent->limit)
 				queue_work(cache->wq, &ent->work);
 		} else {
-			queue_delayed_work(cache->wq, &ent->dwork, 60 * HZ);
+			queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ);
 		}
 	}
 }
@@ -336,18 +410,18 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
 
 		mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i);
 
-		spin_lock(&ent->lock);
+		spin_lock_irq(&ent->lock);
 		if (!list_empty(&ent->head)) {
 			mr = list_first_entry(&ent->head, struct mlx5_ib_mr,
 					      list);
 			list_del(&mr->list);
 			ent->cur--;
-			spin_unlock(&ent->lock);
+			spin_unlock_irq(&ent->lock);
 			if (ent->cur < ent->limit)
 				queue_work(cache->wq, &ent->work);
 			break;
 		}
-		spin_unlock(&ent->lock);
+		spin_unlock_irq(&ent->lock);
 
 		queue_work(cache->wq, &ent->work);
 
@@ -374,12 +448,12 @@ static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		return;
 	}
 	ent = &cache->ent[c];
-	spin_lock(&ent->lock);
+	spin_lock_irq(&ent->lock);
 	list_add_tail(&mr->list, &ent->head);
 	ent->cur++;
 	if (ent->cur > 2 * ent->limit)
 		shrink = 1;
-	spin_unlock(&ent->lock);
+	spin_unlock_irq(&ent->lock);
 
 	if (shrink)
 		queue_work(cache->wq, &ent->work);
@@ -394,16 +468,16 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c)
 
 	cancel_delayed_work(&ent->dwork);
 	while (1) {
-		spin_lock(&ent->lock);
+		spin_lock_irq(&ent->lock);
 		if (list_empty(&ent->head)) {
-			spin_unlock(&ent->lock);
+			spin_unlock_irq(&ent->lock);
 			return;
 		}
 		mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list);
 		list_del(&mr->list);
 		ent->cur--;
 		ent->size--;
-		spin_unlock(&ent->lock);
+		spin_unlock_irq(&ent->lock);
 		err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
 		if (err)
 			mlx5_ib_warn(dev, "failed destroy mkey\n");
@@ -464,6 +538,13 @@ static void mlx5_mr_cache_debugfs_cleanup(struct mlx5_ib_dev *dev)
 	debugfs_remove_recursive(dev->cache.root);
 }
 
+static void delay_time_func(unsigned long ctx)
+{
+	struct mlx5_ib_dev *dev = (struct mlx5_ib_dev *)ctx;
+
+	dev->fill_delay = 0;
+}
+
 int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mr_cache *cache = &dev->cache;
@@ -479,6 +560,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		return -ENOMEM;
 	}
 
+	setup_timer(&dev->delay_timer, delay_time_func, (unsigned long)dev);
 	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
 		INIT_LIST_HEAD(&cache->ent[i].head);
 		spin_lock_init(&cache->ent[i].lock);
@@ -522,6 +604,7 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 		clean_keys(dev, i);
 
 	destroy_workqueue(dev->cache.wq);
+	del_timer_sync(&dev->delay_timer);
 
 	return 0;
 }
@@ -551,7 +634,8 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc)
 	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
 	seg->start_addr = 0;
 
-	err = mlx5_core_create_mkey(mdev, &mr->mmr, in, sizeof(*in));
+	err = mlx5_core_create_mkey(mdev, &mr->mmr, in, sizeof(*in), NULL, NULL,
+				    NULL);
 	if (err)
 		goto err_in;
 
@@ -660,14 +744,14 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	int err;
 	int i;
 
-	for (i = 0; i < 10; i++) {
+	for (i = 0; i < 1; i++) {
 		mr = alloc_cached_mr(dev, order);
 		if (mr)
 			break;
 
 		err = add_keys(dev, order2idx(dev, order), 1);
-		if (err) {
-			mlx5_ib_warn(dev, "add_keys failed\n");
+		if (err && err != -EAGAIN) {
+			mlx5_ib_warn(dev, "add_keys failed, err %d\n", err);
 			break;
 		}
 	}
@@ -759,8 +843,10 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 	in->seg.xlt_oct_size = cpu_to_be32(get_octo_len(virt_addr, length, 1 << page_shift));
 	in->seg.log2_page_size = page_shift;
 	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-	in->xlat_oct_act_size = cpu_to_be32(get_octo_len(virt_addr, length, 1 << page_shift));
-	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, inlen);
+	in->xlat_oct_act_size = cpu_to_be32(get_octo_len(virt_addr, length,
+							 1 << page_shift));
+	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, inlen, NULL,
+				    NULL, NULL);
 	if (err) {
 		mlx5_ib_warn(dev, "create mkey failed\n");
 		goto err_2;
@@ -944,7 +1030,8 @@ struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 	 * TBD not needed - issue 197292 */
 	in->seg.log2_page_size = PAGE_SHIFT;
 
-	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in));
+	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in), NULL,
+				    NULL, NULL);
 	kfree(in);
 	if (err)
 		goto err_free;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 5659ea880741..e3881433f5d7 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1744,6 +1744,7 @@ static void set_reg_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 			MLX5_MKEY_MASK_PD		|
 			MLX5_MKEY_MASK_LR		|
 			MLX5_MKEY_MASK_LW		|
+			MLX5_MKEY_MASK_KEY		|
 			MLX5_MKEY_MASK_RR		|
 			MLX5_MKEY_MASK_RW		|
 			MLX5_MKEY_MASK_A		|
@@ -1800,7 +1801,8 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *w
 	seg->start_addr = cpu_to_be64(wr->wr.fast_reg.iova_start);
 	seg->len = cpu_to_be64(wr->wr.fast_reg.length);
 	seg->log2_page_size = wr->wr.fast_reg.page_shift;
-	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff00 |
+				       mlx5_mkey_variant(wr->wr.fast_reg.rkey));
 }
 
 static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 6ca30739625f..8675d26a678b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -98,6 +98,7 @@ enum {
 static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
 					   struct mlx5_cmd_msg *in,
 					   struct mlx5_cmd_msg *out,
+					   void *uout, int uout_size,
 					   mlx5_cmd_cbk_t cbk,
 					   void *context, int page_queue)
 {
@@ -110,6 +111,8 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
 
 	ent->in		= in;
 	ent->out	= out;
+	ent->uout	= uout;
+	ent->uout_size	= uout_size;
 	ent->callback	= cbk;
 	ent->context	= context;
 	ent->cmd	= cmd;
@@ -534,6 +537,7 @@ static void cmd_work_handler(struct work_struct *work)
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
 	memcpy(lay->in, ent->in->first.data, sizeof(lay->in));
+	ent->op = be32_to_cpu(lay->in[0]) >> 16;
 	if (ent->in->next)
 		lay->in_ptr = cpu_to_be64(ent->in->next->dma);
 	lay->inlen = cpu_to_be32(ent->in->len);
@@ -628,7 +632,8 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
  *    2. page queue commands do not support asynchrous completion
  */
 static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
-			   struct mlx5_cmd_msg *out, mlx5_cmd_cbk_t callback,
+			   struct mlx5_cmd_msg *out, void *uout, int uout_size,
+			   mlx5_cmd_cbk_t callback,
 			   void *context, int page_queue, u8 *status)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
@@ -642,7 +647,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (callback && page_queue)
 		return -EINVAL;
 
-	ent = alloc_cmd(cmd, in, out, callback, context, page_queue);
+	ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context,
+			page_queue);
 	if (IS_ERR(ent))
 		return PTR_ERR(ent);
 
@@ -670,10 +676,10 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		op = be16_to_cpu(((struct mlx5_inbox_hdr *)in->first.data)->opcode);
 		if (op < ARRAY_SIZE(cmd->stats)) {
 			stats = &cmd->stats[op];
-			spin_lock(&stats->lock);
+			spin_lock_irq(&stats->lock);
 			stats->sum += ds;
 			++stats->n;
-			spin_unlock(&stats->lock);
+			spin_unlock_irq(&stats->lock);
 		}
 		mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
 				   "fw exec time for %s is %lld nsec\n",
@@ -826,7 +832,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
 	int n;
 	int i;
 
-	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
+	msg = kzalloc(sizeof(*msg), flags);
 	if (!msg)
 		return ERR_PTR(-ENOMEM);
 
@@ -1109,6 +1115,19 @@ void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
 		up(&cmd->sem);
 }
 
+static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
+{
+	unsigned long flags;
+
+	if (msg->cache) {
+		spin_lock_irqsave(&msg->cache->lock, flags);
+		list_add_tail(&msg->list, &msg->cache->head);
+		spin_unlock_irqrestore(&msg->cache->lock, flags);
+	} else {
+		mlx5_free_cmd_msg(dev, msg);
+	}
+}
+
 void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
@@ -1117,6 +1136,10 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
 	void *context;
 	int err;
 	int i;
+	ktime_t t1, t2, delta;
+	s64 ds;
+	struct mlx5_cmd_stats *stats;
+	unsigned long flags;
 
 	for (i = 0; i < (1 << cmd->log_sz); i++) {
 		if (test_bit(i, &vector)) {
@@ -1141,9 +1164,29 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector)
 			}
 			free_ent(cmd, ent->idx);
 			if (ent->callback) {
+				t1 = timespec_to_ktime(ent->ts1);
+				t2 = timespec_to_ktime(ent->ts2);
+				delta = ktime_sub(t2, t1);
+				ds = ktime_to_ns(delta);
+				if (ent->op < ARRAY_SIZE(cmd->stats)) {
+					stats = &cmd->stats[ent->op];
+					spin_lock_irqsave(&stats->lock, flags);
+					stats->sum += ds;
+					++stats->n;
+					spin_unlock_irqrestore(&stats->lock, flags);
+				}
+
 				callback = ent->callback;
 				context = ent->context;
 				err = ent->ret;
+				if (!err)
+					err = mlx5_copy_from_msg(ent->uout,
+								 ent->out,
+								 ent->uout_size);
+
+				mlx5_free_cmd_msg(dev, ent->out);
+				free_msg(dev, ent->in);
+
 				free_cmd(ent);
 				callback(err, context);
 			} else {
@@ -1160,7 +1203,8 @@ static int status_to_err(u8 status)
 	return status ? -1 : 0; /* TBD more meaningful codes */
 }
 
-static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size)
+static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
+				      gfp_t gfp)
 {
 	struct mlx5_cmd_msg *msg = ERR_PTR(-ENOMEM);
 	struct mlx5_cmd *cmd = &dev->cmd;
@@ -1172,7 +1216,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size)
 		ent = &cmd->cache.med;
 
 	if (ent) {
-		spin_lock(&ent->lock);
+		spin_lock_irq(&ent->lock);
 		if (!list_empty(&ent->head)) {
 			msg = list_entry(ent->head.next, typeof(*msg), list);
 			/* For cached lists, we must explicitly state what is
@@ -1181,43 +1225,34 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size)
 			msg->len = in_size;
 			list_del(&msg->list);
 		}
-		spin_unlock(&ent->lock);
+		spin_unlock_irq(&ent->lock);
 	}
 
 	if (IS_ERR(msg))
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, in_size);
+		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
 
 	return msg;
 }
 
-static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
-{
-	if (msg->cache) {
-		spin_lock(&msg->cache->lock);
-		list_add_tail(&msg->list, &msg->cache->head);
-		spin_unlock(&msg->cache->lock);
-	} else {
-		mlx5_free_cmd_msg(dev, msg);
-	}
-}
-
 static int is_manage_pages(struct mlx5_inbox_hdr *in)
 {
 	return be16_to_cpu(in->opcode) == MLX5_CMD_OP_MANAGE_PAGES;
 }
 
-int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
-		  int out_size)
+static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
+		    int out_size, mlx5_cmd_cbk_t callback, void *context)
 {
 	struct mlx5_cmd_msg *inb;
 	struct mlx5_cmd_msg *outb;
 	int pages_queue;
+	gfp_t gfp;
 	int err;
 	u8 status = 0;
 
 	pages_queue = is_manage_pages(in);
+	gfp = callback ? GFP_ATOMIC : GFP_KERNEL;
 
-	inb = alloc_msg(dev, in_size);
+	inb = alloc_msg(dev, in_size, gfp);
 	if (IS_ERR(inb)) {
 		err = PTR_ERR(inb);
 		return err;
@@ -1229,13 +1264,14 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		goto out_in;
 	}
 
-	outb = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, out_size);
+	outb = mlx5_alloc_cmd_msg(dev, gfp, out_size);
 	if (IS_ERR(outb)) {
 		err = PTR_ERR(outb);
 		goto out_in;
 	}
 
-	err = mlx5_cmd_invoke(dev, inb, outb, NULL, NULL, pages_queue, &status);
+	err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
+			      pages_queue, &status);
 	if (err)
 		goto out_out;
 
@@ -1248,14 +1284,30 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	err = mlx5_copy_from_msg(out, outb, out_size);
 
 out_out:
-	mlx5_free_cmd_msg(dev, outb);
+	if (!callback)
+		mlx5_free_cmd_msg(dev, outb);
 
 out_in:
-	free_msg(dev, inb);
+	if (!callback)
+		free_msg(dev, inb);
 	return err;
 }
+
+int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
+		  int out_size)
+{
+	return cmd_exec(dev, in, in_size, out, out_size, NULL, NULL);
+}
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
+int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
+		     void *out, int out_size, mlx5_cmd_cbk_t callback,
+		     void *context)
+{
+	return cmd_exec(dev, in, in_size, out, out_size, callback, context);
+}
+EXPORT_SYMBOL(mlx5_cmd_exec_cb);
+
 static void destroy_msg_cache(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 9c7194b26ee2..80f6d127257a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -154,10 +154,10 @@ static ssize_t average_read(struct file *filp, char __user *buf, size_t count,
 		return 0;
 
 	stats = filp->private_data;
-	spin_lock(&stats->lock);
+	spin_lock_irq(&stats->lock);
 	if (stats->n)
 		field = div64_u64(stats->sum, stats->n);
-	spin_unlock(&stats->lock);
+	spin_unlock_irq(&stats->lock);
 	ret = snprintf(tbuf, sizeof(tbuf), "%llu\n", field);
 	if (ret > 0) {
 		if (copy_to_user(buf, tbuf, ret))
@@ -175,10 +175,10 @@ static ssize_t average_write(struct file *filp, const char __user *buf,
 	struct mlx5_cmd_stats *stats;
 
 	stats = filp->private_data;
-	spin_lock(&stats->lock);
+	spin_lock_irq(&stats->lock);
 	stats->sum = 0;
 	stats->n = 0;
-	spin_unlock(&stats->lock);
+	spin_unlock_irq(&stats->lock);
 
 	*pos += count;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 5b44e2e46daf..35e514dc7b7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -37,31 +37,41 @@
 #include "mlx5_core.h"
 
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
-			  struct mlx5_create_mkey_mbox_in *in, int inlen)
+			  struct mlx5_create_mkey_mbox_in *in, int inlen,
+			  mlx5_cmd_cbk_t callback, void *context,
+			  struct mlx5_create_mkey_mbox_out *out)
 {
-	struct mlx5_create_mkey_mbox_out out;
+	struct mlx5_create_mkey_mbox_out lout;
 	int err;
 	u8 key;
 
-	memset(&out, 0, sizeof(out));
-	spin_lock(&dev->priv.mkey_lock);
+	memset(&lout, 0, sizeof(lout));
+	spin_lock_irq(&dev->priv.mkey_lock);
 	key = dev->priv.mkey_key++;
-	spin_unlock(&dev->priv.mkey_lock);
+	spin_unlock_irq(&dev->priv.mkey_lock);
 	in->seg.qpn_mkey7_0 |= cpu_to_be32(key);
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_MKEY);
-	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
+	if (callback) {
+		err = mlx5_cmd_exec_cb(dev, in, inlen, out, sizeof(*out),
+				       callback, context);
+		return err;
+	} else {
+		err = mlx5_cmd_exec(dev, in, inlen, &lout, sizeof(lout));
+	}
+
 	if (err) {
 		mlx5_core_dbg(dev, "cmd exec faile %d\n", err);
 		return err;
 	}
 
-	if (out.hdr.status) {
-		mlx5_core_dbg(dev, "status %d\n", out.hdr.status);
-		return mlx5_cmd_status_to_err(&out.hdr);
+	if (lout.hdr.status) {
+		mlx5_core_dbg(dev, "status %d\n", lout.hdr.status);
+		return mlx5_cmd_status_to_err(&lout.hdr);
 	}
 
-	mr->key = mlx5_idx_to_mkey(be32_to_cpu(out.mkey) & 0xffffff) | key;
-	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n", be32_to_cpu(out.mkey), key, mr->key);
+	mr->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key;
+	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
+		      be32_to_cpu(lout.mkey), key, mr->key);
 
 	return err;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6b8c496572c8..513619a75695 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -557,9 +557,11 @@ typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 struct mlx5_cmd_work_ent {
 	struct mlx5_cmd_msg    *in;
 	struct mlx5_cmd_msg    *out;
+	void		       *uout;
+	int			uout_size;
 	mlx5_cmd_cbk_t		callback;
 	void		       *context;
-	int idx;
+	int			idx;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
@@ -570,6 +572,7 @@ struct mlx5_cmd_work_ent {
 	u8			token;
 	struct timespec		ts1;
 	struct timespec		ts2;
+	u16			op;
 };
 
 struct mlx5_pas {
@@ -653,6 +656,9 @@ void mlx5_cmd_use_polling(struct mlx5_core_dev *dev);
 int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr);
 int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		  int out_size);
+int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
+		     void *out, int out_size, mlx5_cmd_cbk_t callback,
+		     void *context);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari);
@@ -676,7 +682,9 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		      u16 lwm, int is_srq);
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
-			  struct mlx5_create_mkey_mbox_in *in, int inlen);
+			  struct mlx5_create_mkey_mbox_in *in, int inlen,
+			  mlx5_cmd_cbk_t callback, void *context,
+			  struct mlx5_create_mkey_mbox_out *out);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr);
 int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			 struct mlx5_query_mkey_mbox_out *out, int outlen);
@@ -745,6 +753,11 @@ static inline u32 mlx5_idx_to_mkey(u32 mkey_idx)
 	return mkey_idx << 8;
 }
 
+static inline u8 mlx5_mkey_variant(u32 mkey)
+{
+	return mkey & 0xff;
+}
+
 enum {
 	MLX5_PROF_MASK_QP_SIZE		= (u64)1 << 0,
 	MLX5_PROF_MASK_MR_CACHE		= (u64)1 << 1,
-- 
cgit 


From bf0bf77f6519e5dcd57a77b47e1d151c1e81b7ec Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Wed, 23 Oct 2013 09:53:19 +0300
Subject: mlx5: Support communicating arbitrary host page size to firmware

Connect-IB firmware requires 4K pages to be communicated with the
driver. This patch breaks larger pages to 4K units to enable support
for architectures utilizing larger page size, such as PowerPC.  This
patch also fixes several places that referred to PAGE_SHIFT instead of
explicit 12 which is the inherent page shift on Connect-IB.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/cq.c                    |   2 +-
 drivers/infiniband/hw/mlx5/qp.c                    |   4 +-
 drivers/infiniband/hw/mlx5/srq.c                   |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |   2 +-
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 174 ++++++++++++++-------
 include/linux/mlx5/driver.h                        |   1 +
 6 files changed, 127 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 84591865e39d..eecac7b52bcb 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -620,7 +620,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	}
 	mlx5_fill_page_array(&cq->buf.buf, (*cqb)->pas);
 
-	(*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - PAGE_SHIFT;
+	(*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - 12;
 	*index = dev->mdev.priv.uuari.uars[0].index;
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8a36fd78c89f..ce14008a5702 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -551,7 +551,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	}
 	mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
 	(*in)->ctx.log_pg_sz_remote_qpn =
-		cpu_to_be32((page_shift - PAGE_SHIFT) << 24);
+		cpu_to_be32((page_shift - 12) << 24);
 	(*in)->ctx.params2 = cpu_to_be32(offset << 6);
 
 	(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
@@ -648,7 +648,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 		goto err_buf;
 	}
 	(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
-	(*in)->ctx.log_pg_sz_remote_qpn = cpu_to_be32((qp->buf.page_shift - PAGE_SHIFT) << 24);
+	(*in)->ctx.log_pg_sz_remote_qpn = cpu_to_be32((qp->buf.page_shift - 12) << 24);
 	/* Set "fast registration enabled" for all kernel QPs */
 	(*in)->ctx.params1 |= cpu_to_be32(1 << 11);
 	(*in)->ctx.sq_crq_size |= cpu_to_be16(1 << 4);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index f1e5845b42b0..dbc2c7188c5e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -123,7 +123,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 		goto err_in;
 	}
 
-	(*in)->ctx.log_pg_sz = page_shift - PAGE_SHIFT;
+	(*in)->ctx.log_pg_sz = page_shift - 12;
 	(*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26);
 
 	return 0;
@@ -192,7 +192,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	}
 	srq->wq_sig = !!srq_signature;
 
-	(*in)->ctx.log_pg_sz = page_shift - PAGE_SHIFT;
+	(*in)->ctx.log_pg_sz = page_shift - 12;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 2231d93cc7ad..6b4b436840bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -354,7 +354,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_EQ);
 	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(eq->nent) << 24 | uar->index);
 	in->ctx.intr = vecidx;
-	in->ctx.log_page_size = PAGE_SHIFT - 12;
+	in->ctx.log_page_size = eq->buf.page_shift - 12;
 	in->events_mask = cpu_to_be64(mask);
 
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index a0d0da35578c..013aa422adee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -57,10 +57,13 @@ struct mlx5_pages_req {
 };
 
 struct fw_page {
-	struct rb_node	rb_node;
-	u64		addr;
-	struct page	*page;
-	u16		func_id;
+	struct rb_node		rb_node;
+	u64			addr;
+	struct page	       *page;
+	u16			func_id;
+	unsigned long		bitmask;
+	struct list_head	list;
+	unsigned		free_count;
 };
 
 struct mlx5_query_pages_inbox {
@@ -94,6 +97,11 @@ enum {
 	MAX_RECLAIM_TIME_MSECS	= 5000,
 };
 
+enum {
+	MLX5_MAX_RECLAIM_TIME_MILI	= 5000,
+	MLX5_NUM_4K_IN_PAGE		= PAGE_SIZE / 4096,
+};
+
 static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id)
 {
 	struct rb_root *root = &dev->priv.page_root;
@@ -101,6 +109,7 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u
 	struct rb_node *parent = NULL;
 	struct fw_page *nfp;
 	struct fw_page *tfp;
+	int i;
 
 	while (*new) {
 		parent = *new;
@@ -113,25 +122,29 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u
 			return -EEXIST;
 	}
 
-	nfp = kmalloc(sizeof(*nfp), GFP_KERNEL);
+	nfp = kzalloc(sizeof(*nfp), GFP_KERNEL);
 	if (!nfp)
 		return -ENOMEM;
 
 	nfp->addr = addr;
 	nfp->page = page;
 	nfp->func_id = func_id;
+	nfp->free_count = MLX5_NUM_4K_IN_PAGE;
+	for (i = 0; i < MLX5_NUM_4K_IN_PAGE; i++)
+		set_bit(i, &nfp->bitmask);
 
 	rb_link_node(&nfp->rb_node, parent, new);
 	rb_insert_color(&nfp->rb_node, root);
+	list_add(&nfp->list, &dev->priv.free_list);
 
 	return 0;
 }
 
-static struct page *remove_page(struct mlx5_core_dev *dev, u64 addr)
+static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr)
 {
 	struct rb_root *root = &dev->priv.page_root;
 	struct rb_node *tmp = root->rb_node;
-	struct page *result = NULL;
+	struct fw_page *result = NULL;
 	struct fw_page *tfp;
 
 	while (tmp) {
@@ -141,9 +154,7 @@ static struct page *remove_page(struct mlx5_core_dev *dev, u64 addr)
 		} else if (tfp->addr > addr) {
 			tmp = tmp->rb_right;
 		} else {
-			rb_erase(&tfp->rb_node, root);
-			result = tfp->page;
-			kfree(tfp);
+			result = tfp;
 			break;
 		}
 	}
@@ -176,13 +187,97 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	return err;
 }
 
+static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
+{
+	struct fw_page *fp;
+	unsigned n;
+
+	if (list_empty(&dev->priv.free_list)) {
+		return -ENOMEM;
+		mlx5_core_warn(dev, "\n");
+	}
+
+	fp = list_entry(dev->priv.free_list.next, struct fw_page, list);
+	n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask));
+	if (n >= MLX5_NUM_4K_IN_PAGE) {
+		mlx5_core_warn(dev, "alloc 4k bug\n");
+		return -ENOENT;
+	}
+	clear_bit(n, &fp->bitmask);
+	fp->free_count--;
+	if (!fp->free_count)
+		list_del(&fp->list);
+
+	*addr = fp->addr + n * 4096;
+
+	return 0;
+}
+
+static void free_4k(struct mlx5_core_dev *dev, u64 addr)
+{
+	struct fw_page *fwp;
+	int n;
+
+	fwp = find_fw_page(dev, addr & PAGE_MASK);
+	if (!fwp) {
+		mlx5_core_warn(dev, "page not found\n");
+		return;
+	}
+
+	n = (addr & ~PAGE_MASK) % 4096;
+	fwp->free_count++;
+	set_bit(n, &fwp->bitmask);
+	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
+		rb_erase(&fwp->rb_node, &dev->priv.page_root);
+		list_del(&fwp->list);
+		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+		__free_page(fwp->page);
+		kfree(fwp);
+	} else if (fwp->free_count == 1) {
+		list_add(&fwp->list, &dev->priv.free_list);
+	}
+}
+
+static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
+{
+	struct page *page;
+	u64 addr;
+	int err;
+
+	page = alloc_page(GFP_HIGHUSER);
+	if (!page) {
+		mlx5_core_warn(dev, "failed to allocate page\n");
+		return -ENOMEM;
+	}
+	addr = dma_map_page(&dev->pdev->dev, page, 0,
+			    PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&dev->pdev->dev, addr)) {
+		mlx5_core_warn(dev, "failed dma mapping page\n");
+		err = -ENOMEM;
+		goto out_alloc;
+	}
+	err = insert_page(dev, addr, page, func_id);
+	if (err) {
+		mlx5_core_err(dev, "failed to track allocated page\n");
+		goto out_mapping;
+	}
+
+	return 0;
+
+out_mapping:
+	dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+
+out_alloc:
+	__free_page(page);
+
+	return err;
+}
 static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 		      int notify_fail)
 {
 	struct mlx5_manage_pages_inbox *in;
 	struct mlx5_manage_pages_outbox out;
 	struct mlx5_manage_pages_inbox *nin;
-	struct page *page;
 	int inlen;
 	u64 addr;
 	int err;
@@ -197,27 +292,15 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	memset(&out, 0, sizeof(out));
 
 	for (i = 0; i < npages; i++) {
-		page = alloc_page(GFP_HIGHUSER);
-		if (!page) {
-			err = -ENOMEM;
-			mlx5_core_warn(dev, "failed to allocate page\n");
-			goto out_alloc;
-		}
-		addr = dma_map_page(&dev->pdev->dev, page, 0,
-				    PAGE_SIZE, DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(&dev->pdev->dev, addr)) {
-			mlx5_core_warn(dev, "failed dma mapping page\n");
-			__free_page(page);
-			err = -ENOMEM;
-			goto out_alloc;
-		}
-		err = insert_page(dev, addr, page, func_id);
+retry:
+		err = alloc_4k(dev, &addr);
 		if (err) {
-			mlx5_core_err(dev, "failed to track allocated page\n");
-			dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-			__free_page(page);
-			err = -ENOMEM;
-			goto out_alloc;
+			if (err == -ENOMEM)
+				err = alloc_system_page(dev, func_id);
+			if (err)
+				goto out_4k;
+
+			goto retry;
 		}
 		in->pas[i] = cpu_to_be64(addr);
 	}
@@ -227,7 +310,6 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 	in->func_id = cpu_to_be16(func_id);
 	in->num_entries = cpu_to_be32(npages);
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
-	mlx5_core_dbg(dev, "err %d\n", err);
 	if (err) {
 		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n", func_id, npages, err);
 		goto out_alloc;
@@ -251,7 +333,7 @@ out_alloc:
 		nin = kzalloc(sizeof(*nin), GFP_KERNEL);
 		if (!nin) {
 			mlx5_core_warn(dev, "allocation failed\n");
-			goto unmap;
+			goto out_4k;
 		}
 		memset(&out, 0, sizeof(out));
 		nin->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES);
@@ -261,19 +343,9 @@ out_alloc:
 		kfree(nin);
 	}
 
-unmap:
-	for (i--; i >= 0; i--) {
-		addr = be64_to_cpu(in->pas[i]);
-		page = remove_page(dev, addr);
-		if (!page) {
-			mlx5_core_err(dev, "BUG: can't remove page at addr 0x%llx\n",
-				      addr);
-			continue;
-		}
-		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-		__free_page(page);
-	}
-
+out_4k:
+	for (i--; i >= 0; i--)
+		free_4k(dev, be64_to_cpu(in->pas[i]));
 out_free:
 	mlx5_vfree(in);
 	return err;
@@ -284,7 +356,6 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 {
 	struct mlx5_manage_pages_inbox   in;
 	struct mlx5_manage_pages_outbox *out;
-	struct page *page;
 	int num_claimed;
 	int outlen;
 	u64 addr;
@@ -323,13 +394,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 
 	for (i = 0; i < num_claimed; i++) {
 		addr = be64_to_cpu(out->pas[i]);
-		page = remove_page(dev, addr);
-		if (!page) {
-			mlx5_core_warn(dev, "FW reported unknown DMA address 0x%llx\n", addr);
-		} else {
-			dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-			__free_page(page);
-		}
+		free_4k(dev, addr);
 	}
 
 out_free:
@@ -435,6 +500,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 void mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 {
 	dev->priv.page_root = RB_ROOT;
+	INIT_LIST_HEAD(&dev->priv.free_list);
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 513619a75695..554548cd3dd4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -483,6 +483,7 @@ struct mlx5_priv {
 	struct rb_root		page_root;
 	int			fw_pages;
 	int			reg_pages;
+	struct list_head	free_list;
 
 	struct mlx5_core_health health;
 
-- 
cgit 


From 87b8de492da34942fc554f2958a570ce0642296a Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Wed, 23 Oct 2013 09:53:20 +0300
Subject: mlx5: Clear reserved area in set_hca_cap()

Firmware spec requires reserved fields to be cleared when calling
set_hca_cap.  Current code queries and copy to the set area, possibly
resulting in reserved bits not cleared. This patch copies only
writable fields to the set area.

Fix also typo - msx => max

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 35 +++++++++++++++++++++++---
 include/linux/mlx5/device.h                    |  9 +++++--
 2 files changed, 39 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index bc0f5fb66e24..40a9f5ed814d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -159,6 +159,36 @@ struct mlx5_reg_host_endianess {
 	u8      rsvd[15];
 };
 
+
+#define CAP_MASK(pos, size) ((u64)((1 << (size)) - 1) << (pos))
+
+enum {
+	MLX5_CAP_BITS_RW_MASK	= CAP_MASK(MLX5_CAP_OFF_CMDIF_CSUM, 2) |
+				  CAP_MASK(MLX5_CAP_OFF_DCT, 1),
+};
+
+/* selectively copy writable fields clearing any reserved area
+ */
+static void copy_rw_fields(struct mlx5_hca_cap *to, struct mlx5_hca_cap *from)
+{
+	u64 v64;
+
+	to->log_max_qp = from->log_max_qp & 0x1f;
+	to->log_max_ra_req_dc = from->log_max_ra_req_dc & 0x3f;
+	to->log_max_ra_res_dc = from->log_max_ra_res_dc & 0x3f;
+	to->log_max_ra_req_qp = from->log_max_ra_req_qp & 0x3f;
+	to->log_max_ra_res_qp = from->log_max_ra_res_qp & 0x3f;
+	to->log_max_atomic_size_qp = from->log_max_atomic_size_qp;
+	to->log_max_atomic_size_dc = from->log_max_atomic_size_dc;
+	v64 = be64_to_cpu(from->flags) & MLX5_CAP_BITS_RW_MASK;
+	to->flags = cpu_to_be64(v64);
+}
+
+enum {
+	HCA_CAP_OPMOD_GET_MAX	= 0,
+	HCA_CAP_OPMOD_GET_CUR	= 1,
+};
+
 static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd_query_hca_cap_mbox_out *query_out = NULL;
@@ -180,7 +210,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 	}
 
 	query_ctx.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_HCA_CAP);
-	query_ctx.hdr.opmod  = cpu_to_be16(0x1);
+	query_ctx.hdr.opmod  = cpu_to_be16(HCA_CAP_OPMOD_GET_CUR);
 	err = mlx5_cmd_exec(dev, &query_ctx, sizeof(query_ctx),
 				 query_out, sizeof(*query_out));
 	if (err)
@@ -192,8 +222,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 		goto query_ex;
 	}
 
-	memcpy(&set_ctx->hca_cap, &query_out->hca_cap,
-	       sizeof(set_ctx->hca_cap));
+	copy_rw_fields(&set_ctx->hca_cap, &query_out->hca_cap);
 
 	if (dev->profile->mask & MLX5_PROF_MASK_QP_SIZE)
 		set_ctx->hca_cap.log_max_qp = dev->profile->log_max_qp;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5eb4e31af22b..3d789f43e34b 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -230,6 +230,11 @@ enum {
 	MLX5_MAX_PAGE_SHIFT		= 31
 };
 
+enum {
+	MLX5_CAP_OFF_DCT		= 41,
+	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
+};
+
 struct mlx5_inbox_hdr {
 	__be16		opcode;
 	u8		rsvd[4];
@@ -319,9 +324,9 @@ struct mlx5_hca_cap {
 	u8	rsvd25[42];
 	__be16  log_uar_page_sz;
 	u8	rsvd26[28];
-	u8	log_msx_atomic_size_qp;
+	u8	log_max_atomic_size_qp;
 	u8	rsvd27[2];
-	u8	log_msx_atomic_size_dc;
+	u8	log_max_atomic_size_dc;
 	u8	rsvd28[76];
 };
 
-- 
cgit 


From 1b77d2bd753d119eedcbc08fda58934307676554 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Thu, 24 Oct 2013 12:01:03 +0300
Subject: mlx5: Use enum to indicate adapter page size

The Connect-IB adapter has an inherent page size which equals 4K.
Define an new enum that equals the page shift and use it instead of
using the value 12 throughout the code.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/cq.c              | 2 +-
 drivers/infiniband/hw/mlx5/qp.c              | 5 +++--
 drivers/infiniband/hw/mlx5/srq.c             | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +-
 include/linux/mlx5/device.h                  | 4 ++++
 5 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index eecac7b52bcb..28344773f640 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -620,7 +620,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	}
 	mlx5_fill_page_array(&cq->buf.buf, (*cqb)->pas);
 
-	(*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - 12;
+	(*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	*index = dev->mdev.priv.uuari.uars[0].index;
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 5bcf57943b84..7c6b4ba49bec 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -551,7 +551,7 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	}
 	mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
 	(*in)->ctx.log_pg_sz_remote_qpn =
-		cpu_to_be32((page_shift - 12) << 24);
+		cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
 	(*in)->ctx.params2 = cpu_to_be32(offset << 6);
 
 	(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
@@ -648,7 +648,8 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 		goto err_buf;
 	}
 	(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
-	(*in)->ctx.log_pg_sz_remote_qpn = cpu_to_be32((qp->buf.page_shift - 12) << 24);
+	(*in)->ctx.log_pg_sz_remote_qpn =
+		cpu_to_be32((qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
 	/* Set "fast registration enabled" for all kernel QPs */
 	(*in)->ctx.params1 |= cpu_to_be32(1 << 11);
 	(*in)->ctx.sq_crq_size |= cpu_to_be16(1 << 4);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index dbc2c7188c5e..210b3eaf188a 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -123,7 +123,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 		goto err_in;
 	}
 
-	(*in)->ctx.log_pg_sz = page_shift - 12;
+	(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	(*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26);
 
 	return 0;
@@ -192,7 +192,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 	}
 	srq->wq_sig = !!srq_signature;
 
-	(*in)->ctx.log_pg_sz = page_shift - 12;
+	(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 6b4b436840bd..64a61b286b2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -354,7 +354,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_EQ);
 	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(eq->nent) << 24 | uar->index);
 	in->ctx.intr = vecidx;
-	in->ctx.log_page_size = eq->buf.page_shift - 12;
+	in->ctx.log_page_size = eq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	in->events_mask = cpu_to_be64(mask);
 
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 3d789f43e34b..da78875807fc 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -230,6 +230,10 @@ enum {
 	MLX5_MAX_PAGE_SHIFT		= 31
 };
 
+enum {
+	MLX5_ADAPTER_PAGE_SHIFT		= 12
+};
+
 enum {
 	MLX5_CAP_OFF_DCT		= 41,
 	MLX5_CAP_OFF_CMDIF_CSUM		= 46,
-- 
cgit 


From 9dd69a600a680fab1c9235a644c886d8d6a2da2a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 26 Oct 2013 14:32:30 +0200
Subject: IB/srp: Keep rport as long as the IB transport layer

Keep the rport data structure around after srp_remove_host() has
finished until cleanup of the IB transport layer has finished
completely. This is necessary because later patches use the rport
pointer inside the queuecommand callback. Without this patch
accessing the rport from inside a queuecommand callback is racy
because srp_remove_host() must be invoked before scsi_remove_host()
and because the queuecommand callback could get invoked after
srp_remove_host() has finished. In other words, without this patch
the queuecommand callback can get invoked after the rport data
structure has been freed.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/ulp/srp/ib_srp.c |  3 +++
 drivers/infiniband/ulp/srp/ib_srp.h |  1 +
 drivers/scsi/scsi_transport_srp.c   | 18 ++++++++++++++++++
 include/scsi/scsi_transport_srp.h   |  2 ++
 4 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 11ebf3e7646a..6edab7855f5e 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -528,11 +528,13 @@ static void srp_remove_target(struct srp_target_port *target)
 	WARN_ON_ONCE(target->state != SRP_TARGET_REMOVED);
 
 	srp_del_scsi_host_attr(target->scsi_host);
+	srp_rport_get(target->rport);
 	srp_remove_host(target->scsi_host);
 	scsi_remove_host(target->scsi_host);
 	srp_disconnect_target(target);
 	ib_destroy_cm_id(target->cm_id);
 	srp_free_target_ib(target);
+	srp_rport_put(target->rport);
 	srp_free_req_data(target);
 	scsi_host_put(target->scsi_host);
 }
@@ -2004,6 +2006,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	}
 
 	rport->lld_data = target;
+	target->rport = rport;
 
 	spin_lock(&host->target_lock);
 	list_add_tail(&target->list, &host->target_list);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 84d821b24ec7..2a1768fcc57d 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -153,6 +153,7 @@ struct srp_target_port {
 	u16			io_class;
 	struct srp_host	       *srp_host;
 	struct Scsi_Host       *scsi_host;
+	struct srp_rport       *rport;
 	char			target_name[32];
 	unsigned int		scsi_id;
 	unsigned int		sg_tablesize;
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index f379c7f3034c..f7ba94aa52cb 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -184,6 +184,24 @@ static int srp_host_match(struct attribute_container *cont, struct device *dev)
 	return &i->t.host_attrs.ac == cont;
 }
 
+/**
+ * srp_rport_get() - increment rport reference count
+ */
+void srp_rport_get(struct srp_rport *rport)
+{
+	get_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_get);
+
+/**
+ * srp_rport_put() - decrement rport reference count
+ */
+void srp_rport_put(struct srp_rport *rport)
+{
+	put_device(&rport->dev);
+}
+EXPORT_SYMBOL(srp_rport_put);
+
 /**
  * srp_rport_add - add a SRP remote port to the device hierarchy
  * @shost:	scsi host the remote port is connected to.
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index ff0f04ac91aa..5a2d2d1081c1 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -38,6 +38,8 @@ extern struct scsi_transport_template *
 srp_attach_transport(struct srp_function_template *);
 extern void srp_release_transport(struct scsi_transport_template *);
 
+extern void srp_rport_get(struct srp_rport *rport);
+extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-- 
cgit 


From 29c17324803c8a3bb5b2b69309e43571164cc4de Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 26 Oct 2013 14:33:30 +0200
Subject: scsi_transport_srp: Add transport layer error handling

Add the necessary functions in the SRP transport module to allow an
SRP initiator driver to implement transport layer error handling
similar to the functionality already provided by the FC transport
layer. This includes:

- Support for implementing fast_io_fail_tmo, the time that should
  elapse after having detected a transport layer problem and
  before failing I/O.
- Support for implementing dev_loss_tmo, the time that should
  elapse after having detected a transport layer problem and
  before removing a remote port.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 Documentation/ABI/stable/sysfs-transport-srp |  31 ++
 drivers/scsi/scsi_transport_srp.c            | 430 ++++++++++++++++++++++++++-
 include/scsi/scsi_transport_srp.h            |  74 ++++-
 3 files changed, 532 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-transport-srp b/Documentation/ABI/stable/sysfs-transport-srp
index b36fb0dc13c8..8b6acc775b71 100644
--- a/Documentation/ABI/stable/sysfs-transport-srp
+++ b/Documentation/ABI/stable/sysfs-transport-srp
@@ -5,6 +5,24 @@ Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
 Description:	Instructs an SRP initiator to disconnect from a target and to
 		remove all LUNs imported from that target.
 
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/dev_loss_tmo
+Date:		February 1, 2014
+KernelVersion:	3.13
+Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
+Description:	Number of seconds the SCSI layer will wait after a transport
+		layer error has been observed before removing a target port.
+		Zero means immediate removal. Setting this attribute to "off"
+		will disable the dev_loss timer.
+
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/fast_io_fail_tmo
+Date:		February 1, 2014
+KernelVersion:	3.13
+Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
+Description:	Number of seconds the SCSI layer will wait after a transport
+		layer error has been observed before failing I/O. Zero means
+		failing I/O immediately. Setting this attribute to "off" will
+		disable the fast_io_fail timer.
+
 What:		/sys/class/srp_remote_ports/port-<h>:<n>/port_id
 Date:		June 27, 2007
 KernelVersion:	2.6.24
@@ -17,3 +35,16 @@ Date:		June 27, 2007
 KernelVersion:	2.6.24
 Contact:	linux-scsi@vger.kernel.org
 Description:	Role of the remote port. Either "SRP Initiator" or "SRP Target".
+
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/state
+Date:		February 1, 2014
+KernelVersion:	3.13
+Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
+Description:	State of the transport layer used for communication with the
+		remote port. "running" if the transport layer is operational;
+		"blocked" if a transport layer error has been encountered but
+		the fast_io_fail_tmo timer has not yet fired; "fail-fast"
+		after the fast_io_fail_tmo timer has fired and before the
+		"dev_loss_tmo" timer has fired; "lost" after the
+		"dev_loss_tmo" timer has fired and before the port is finally
+		removed.
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index f7ba94aa52cb..2696e26b3423 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -24,12 +24,15 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/delay.h>
 
 #include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
 #include <scsi/scsi_transport_srp.h>
+#include "scsi_priv.h"
 #include "scsi_transport_srp_internal.h"
 
 struct srp_host_attrs {
@@ -38,7 +41,7 @@ struct srp_host_attrs {
 #define to_srp_host_attrs(host)	((struct srp_host_attrs *)(host)->shost_data)
 
 #define SRP_HOST_ATTRS 0
-#define SRP_RPORT_ATTRS 3
+#define SRP_RPORT_ATTRS 6
 
 struct srp_internal {
 	struct scsi_transport_template t;
@@ -54,6 +57,34 @@ struct srp_internal {
 
 #define	dev_to_rport(d)	container_of(d, struct srp_rport, dev)
 #define transport_class_to_srp_rport(dev) dev_to_rport((dev)->parent)
+static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
+{
+	return dev_to_shost(r->dev.parent);
+}
+
+/**
+ * srp_tmo_valid() - check timeout combination validity
+ *
+ * The combination of the timeout parameters must be such that SCSI commands
+ * are finished in a reasonable time. Hence do not allow the fast I/O fail
+ * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT. Furthermore, these
+ * parameters must be such that multipath can detect failed paths timely.
+ * Hence do not allow both parameters to be disabled simultaneously.
+ */
+int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo)
+{
+	if (fast_io_fail_tmo < 0 && dev_loss_tmo < 0)
+		return -EINVAL;
+	if (fast_io_fail_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
+		return -EINVAL;
+	if (dev_loss_tmo >= LONG_MAX / HZ)
+		return -EINVAL;
+	if (fast_io_fail_tmo >= 0 && dev_loss_tmo >= 0 &&
+	    fast_io_fail_tmo >= dev_loss_tmo)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(srp_tmo_valid);
 
 static int srp_host_setup(struct transport_container *tc, struct device *dev,
 			  struct device *cdev)
@@ -134,10 +165,383 @@ static ssize_t store_srp_rport_delete(struct device *dev,
 
 static DEVICE_ATTR(delete, S_IWUSR, NULL, store_srp_rport_delete);
 
+static ssize_t show_srp_rport_state(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	static const char *const state_name[] = {
+		[SRP_RPORT_RUNNING]	= "running",
+		[SRP_RPORT_BLOCKED]	= "blocked",
+		[SRP_RPORT_FAIL_FAST]	= "fail-fast",
+		[SRP_RPORT_LOST]	= "lost",
+	};
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	enum srp_rport_state state = rport->state;
+
+	return sprintf(buf, "%s\n",
+		       (unsigned)state < ARRAY_SIZE(state_name) ?
+		       state_name[state] : "???");
+}
+
+static DEVICE_ATTR(state, S_IRUGO, show_srp_rport_state, NULL);
+
+static ssize_t srp_show_tmo(char *buf, int tmo)
+{
+	return tmo >= 0 ? sprintf(buf, "%d\n", tmo) : sprintf(buf, "off\n");
+}
+
+static int srp_parse_tmo(int *tmo, const char *buf)
+{
+	int res = 0;
+
+	if (strncmp(buf, "off", 3) != 0)
+		res = kstrtoint(buf, 0, tmo);
+	else
+		*tmo = -1;
+
+	return res;
+}
+
+static ssize_t show_srp_rport_fast_io_fail_tmo(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	return srp_show_tmo(buf, rport->fast_io_fail_tmo);
+}
+
+static ssize_t store_srp_rport_fast_io_fail_tmo(struct device *dev,
+						struct device_attribute *attr,
+						const char *buf, size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res;
+	int fast_io_fail_tmo;
+
+	res = srp_parse_tmo(&fast_io_fail_tmo, buf);
+	if (res)
+		goto out;
+	res = srp_tmo_valid(fast_io_fail_tmo, rport->dev_loss_tmo);
+	if (res)
+		goto out;
+	rport->fast_io_fail_tmo = fast_io_fail_tmo;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR,
+		   show_srp_rport_fast_io_fail_tmo,
+		   store_srp_rport_fast_io_fail_tmo);
+
+static ssize_t show_srp_rport_dev_loss_tmo(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	return srp_show_tmo(buf, rport->dev_loss_tmo);
+}
+
+static ssize_t store_srp_rport_dev_loss_tmo(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res;
+	int dev_loss_tmo;
+
+	res = srp_parse_tmo(&dev_loss_tmo, buf);
+	if (res)
+		goto out;
+	res = srp_tmo_valid(rport->fast_io_fail_tmo, dev_loss_tmo);
+	if (res)
+		goto out;
+	rport->dev_loss_tmo = dev_loss_tmo;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(dev_loss_tmo, S_IRUGO | S_IWUSR,
+		   show_srp_rport_dev_loss_tmo,
+		   store_srp_rport_dev_loss_tmo);
+
+static int srp_rport_set_state(struct srp_rport *rport,
+			       enum srp_rport_state new_state)
+{
+	enum srp_rport_state old_state = rport->state;
+
+	lockdep_assert_held(&rport->mutex);
+
+	switch (new_state) {
+	case SRP_RPORT_RUNNING:
+		switch (old_state) {
+		case SRP_RPORT_LOST:
+			goto invalid;
+		default:
+			break;
+		}
+		break;
+	case SRP_RPORT_BLOCKED:
+		switch (old_state) {
+		case SRP_RPORT_RUNNING:
+			break;
+		default:
+			goto invalid;
+		}
+		break;
+	case SRP_RPORT_FAIL_FAST:
+		switch (old_state) {
+		case SRP_RPORT_LOST:
+			goto invalid;
+		default:
+			break;
+		}
+		break;
+	case SRP_RPORT_LOST:
+		break;
+	}
+	rport->state = new_state;
+	return 0;
+
+invalid:
+	return -EINVAL;
+}
+
+static void __rport_fail_io_fast(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i;
+
+	lockdep_assert_held(&rport->mutex);
+
+	if (srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST))
+		return;
+	scsi_target_unblock(rport->dev.parent, SDEV_TRANSPORT_OFFLINE);
+
+	/* Involve the LLD if possible to terminate all I/O on the rport. */
+	i = to_srp_internal(shost->transportt);
+	if (i->f->terminate_rport_io)
+		i->f->terminate_rport_io(rport);
+}
+
+/**
+ * rport_fast_io_fail_timedout() - fast I/O failure timeout handler
+ */
+static void rport_fast_io_fail_timedout(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, fast_io_fail_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+
+	pr_info("fast_io_fail_tmo expired for SRP %s / %s.\n",
+		dev_name(&rport->dev), dev_name(&shost->shost_gendev));
+
+	mutex_lock(&rport->mutex);
+	if (rport->state == SRP_RPORT_BLOCKED)
+		__rport_fail_io_fast(rport);
+	mutex_unlock(&rport->mutex);
+}
+
+/**
+ * rport_dev_loss_timedout() - device loss timeout handler
+ */
+static void rport_dev_loss_timedout(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, dev_loss_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+
+	pr_info("dev_loss_tmo expired for SRP %s / %s.\n",
+		dev_name(&rport->dev), dev_name(&shost->shost_gendev));
+
+	mutex_lock(&rport->mutex);
+	WARN_ON(srp_rport_set_state(rport, SRP_RPORT_LOST) != 0);
+	scsi_target_unblock(rport->dev.parent, SDEV_TRANSPORT_OFFLINE);
+	mutex_unlock(&rport->mutex);
+
+	i->f->rport_delete(rport);
+}
+
+static void __srp_start_tl_fail_timers(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	int fast_io_fail_tmo, dev_loss_tmo;
+
+	lockdep_assert_held(&rport->mutex);
+
+	if (!rport->deleted) {
+		fast_io_fail_tmo = rport->fast_io_fail_tmo;
+		dev_loss_tmo = rport->dev_loss_tmo;
+		pr_debug("%s current state: %d\n",
+			 dev_name(&shost->shost_gendev), rport->state);
+
+		if (fast_io_fail_tmo >= 0 &&
+		    srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
+			pr_debug("%s new state: %d\n",
+				 dev_name(&shost->shost_gendev),
+				 rport->state);
+			scsi_target_block(&shost->shost_gendev);
+			queue_delayed_work(system_long_wq,
+					   &rport->fast_io_fail_work,
+					   1UL * fast_io_fail_tmo * HZ);
+		}
+		if (dev_loss_tmo >= 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->dev_loss_work,
+					   1UL * dev_loss_tmo * HZ);
+	} else {
+		pr_debug("%s has already been deleted\n",
+			 dev_name(&shost->shost_gendev));
+		srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST);
+		scsi_target_unblock(&shost->shost_gendev,
+				    SDEV_TRANSPORT_OFFLINE);
+	}
+}
+
+/**
+ * srp_start_tl_fail_timers() - start the transport layer failure timers
+ *
+ * Start the transport layer fast I/O failure and device loss timers. Do not
+ * modify a timer that was already started.
+ */
+void srp_start_tl_fail_timers(struct srp_rport *rport)
+{
+	mutex_lock(&rport->mutex);
+	__srp_start_tl_fail_timers(rport);
+	mutex_unlock(&rport->mutex);
+}
+EXPORT_SYMBOL(srp_start_tl_fail_timers);
+
+/**
+ * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ */
+static int scsi_request_fn_active(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+	int request_fn_active = 0;
+
+	shost_for_each_device(sdev, shost) {
+		q = sdev->request_queue;
+
+		spin_lock_irq(q->queue_lock);
+		request_fn_active += q->request_fn_active;
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return request_fn_active;
+}
+
+/**
+ * srp_reconnect_rport() - reconnect to an SRP target port
+ *
+ * Blocks SCSI command queueing before invoking reconnect() such that
+ * queuecommand() won't be invoked concurrently with reconnect() from outside
+ * the SCSI EH. This is important since a reconnect() implementation may
+ * reallocate resources needed by queuecommand().
+ *
+ * Notes:
+ * - This function neither waits until outstanding requests have finished nor
+ *   tries to abort these. It is the responsibility of the reconnect()
+ *   function to finish outstanding commands before reconnecting to the target
+ *   port.
+ * - It is the responsibility of the caller to ensure that the resources
+ *   reallocated by the reconnect() function won't be used while this function
+ *   is in progress. One possible strategy is to invoke this function from
+ *   the context of the SCSI EH thread only. Another possible strategy is to
+ *   lock the rport mutex inside each SCSI LLD callback that can be invoked by
+ *   the SCSI EH (the scsi_host_template.eh_*() functions and also the
+ *   scsi_host_template.queuecommand() function).
+ */
+int srp_reconnect_rport(struct srp_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+	struct scsi_device *sdev;
+	int res;
+
+	pr_debug("SCSI host %s\n", dev_name(&shost->shost_gendev));
+
+	res = mutex_lock_interruptible(&rport->mutex);
+	if (res)
+		goto out;
+	scsi_target_block(&shost->shost_gendev);
+	while (scsi_request_fn_active(shost))
+		msleep(20);
+	res = i->f->reconnect(rport);
+	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
+		 dev_name(&shost->shost_gendev), rport->state, res);
+	if (res == 0) {
+		cancel_delayed_work(&rport->fast_io_fail_work);
+		cancel_delayed_work(&rport->dev_loss_work);
+
+		srp_rport_set_state(rport, SRP_RPORT_RUNNING);
+		scsi_target_unblock(&shost->shost_gendev, SDEV_RUNNING);
+		/*
+		 * If the SCSI error handler has offlined one or more devices,
+		 * invoking scsi_target_unblock() won't change the state of
+		 * these devices into running so do that explicitly.
+		 */
+		spin_lock_irq(shost->host_lock);
+		__shost_for_each_device(sdev, shost)
+			if (sdev->sdev_state == SDEV_OFFLINE)
+				sdev->sdev_state = SDEV_RUNNING;
+		spin_unlock_irq(shost->host_lock);
+	} else if (rport->state == SRP_RPORT_RUNNING) {
+		/*
+		 * srp_reconnect_rport() was invoked with fast_io_fail
+		 * off. Mark the port as failed and start the TL failure
+		 * timers if these had not yet been started.
+		 */
+		__rport_fail_io_fast(rport);
+		scsi_target_unblock(&shost->shost_gendev,
+				    SDEV_TRANSPORT_OFFLINE);
+		__srp_start_tl_fail_timers(rport);
+	} else if (rport->state != SRP_RPORT_BLOCKED) {
+		scsi_target_unblock(&shost->shost_gendev,
+				    SDEV_TRANSPORT_OFFLINE);
+	}
+	mutex_unlock(&rport->mutex);
+
+out:
+	return res;
+}
+EXPORT_SYMBOL(srp_reconnect_rport);
+
+/**
+ * srp_timed_out() - SRP transport intercept of the SCSI timeout EH
+ *
+ * If a timeout occurs while an rport is in the blocked state, ask the SCSI
+ * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
+ * handle the timeout (BLK_EH_NOT_HANDLED).
+ *
+ * Note: This function is called from soft-IRQ context and with the request
+ * queue lock held.
+ */
+static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
+{
+	struct scsi_device *sdev = scmd->device;
+	struct Scsi_Host *shost = sdev->host;
+	struct srp_internal *i = to_srp_internal(shost->transportt);
+
+	pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev));
+	return i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
+		BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
+}
+
 static void srp_rport_release(struct device *dev)
 {
 	struct srp_rport *rport = dev_to_rport(dev);
 
+	cancel_delayed_work_sync(&rport->fast_io_fail_work);
+	cancel_delayed_work_sync(&rport->dev_loss_work);
+
 	put_device(dev->parent);
 	kfree(rport);
 }
@@ -214,12 +618,15 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 {
 	struct srp_rport *rport;
 	struct device *parent = &shost->shost_gendev;
+	struct srp_internal *i = to_srp_internal(shost->transportt);
 	int id, ret;
 
 	rport = kzalloc(sizeof(*rport), GFP_KERNEL);
 	if (!rport)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&rport->mutex);
+
 	device_initialize(&rport->dev);
 
 	rport->dev.parent = get_device(parent);
@@ -228,6 +635,13 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 	memcpy(rport->port_id, ids->port_id, sizeof(rport->port_id));
 	rport->roles = ids->roles;
 
+	rport->fast_io_fail_tmo = i->f->fast_io_fail_tmo ?
+		*i->f->fast_io_fail_tmo : 15;
+	rport->dev_loss_tmo = i->f->dev_loss_tmo ? *i->f->dev_loss_tmo : 60;
+	INIT_DELAYED_WORK(&rport->fast_io_fail_work,
+			  rport_fast_io_fail_timedout);
+	INIT_DELAYED_WORK(&rport->dev_loss_work, rport_dev_loss_timedout);
+
 	id = atomic_inc_return(&to_srp_host_attrs(shost)->next_port_id);
 	dev_set_name(&rport->dev, "port-%d:%d", shost->host_no, id);
 
@@ -277,6 +691,13 @@ void srp_rport_del(struct srp_rport *rport)
 	transport_remove_device(dev);
 	device_del(dev);
 	transport_destroy_device(dev);
+
+	mutex_lock(&rport->mutex);
+	if (rport->state == SRP_RPORT_BLOCKED)
+		__rport_fail_io_fast(rport);
+	rport->deleted = true;
+	mutex_unlock(&rport->mutex);
+
 	put_device(dev);
 }
 EXPORT_SYMBOL_GPL(srp_rport_del);
@@ -328,6 +749,8 @@ srp_attach_transport(struct srp_function_template *ft)
 	if (!i)
 		return NULL;
 
+	i->t.eh_timed_out = srp_timed_out;
+
 	i->t.tsk_mgmt_response = srp_tsk_mgmt_response;
 	i->t.it_nexus_response = srp_it_nexus_response;
 
@@ -345,6 +768,11 @@ srp_attach_transport(struct srp_function_template *ft)
 	count = 0;
 	i->rport_attrs[count++] = &dev_attr_port_id;
 	i->rport_attrs[count++] = &dev_attr_roles;
+	if (ft->has_rport_state) {
+		i->rport_attrs[count++] = &dev_attr_state;
+		i->rport_attrs[count++] = &dev_attr_fast_io_fail_tmo;
+		i->rport_attrs[count++] = &dev_attr_dev_loss_tmo;
+	}
 	if (ft->rport_delete)
 		i->rport_attrs[count++] = &dev_attr_delete;
 	i->rport_attrs[count++] = NULL;
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index 5a2d2d1081c1..ee7001677f64 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -13,6 +13,26 @@ struct srp_rport_identifiers {
 	u8 roles;
 };
 
+/**
+ * enum srp_rport_state - SRP transport layer state
+ * @SRP_RPORT_RUNNING:   Transport layer operational.
+ * @SRP_RPORT_BLOCKED:   Transport layer not operational; fast I/O fail timer
+ *                       is running and I/O has been blocked.
+ * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast.
+ * @SRP_RPORT_LOST:      Device loss timer has expired; port is being removed.
+ */
+enum srp_rport_state {
+	SRP_RPORT_RUNNING,
+	SRP_RPORT_BLOCKED,
+	SRP_RPORT_FAIL_FAST,
+	SRP_RPORT_LOST,
+};
+
+/**
+ * struct srp_rport
+ * @lld_data: LLD private data.
+ * @mutex:    Protects against concurrent rport fast_io_fail / dev_loss_tmo.
+ */
 struct srp_rport {
 	/* for initiator and target drivers */
 
@@ -23,11 +43,38 @@ struct srp_rport {
 
 	/* for initiator drivers */
 
-	void *lld_data;	/* LLD private data */
+	void			*lld_data;
+
+	struct mutex		mutex;
+	enum srp_rport_state	state;
+	bool			deleted;
+	int			fast_io_fail_tmo;
+	int			dev_loss_tmo;
+	struct delayed_work	fast_io_fail_work;
+	struct delayed_work	dev_loss_work;
 };
 
+/**
+ * struct srp_function_template
+ * @has_rport_state: Whether or not to create the state, fast_io_fail_tmo and
+ *     dev_loss_tmo sysfs attribute for an rport.
+ * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
+ *     timer if the device on which it has been queued is blocked.
+ * @fast_io_fail_tmo: If not NULL, points to the default fast_io_fail_tmo value.
+ * @dev_loss_tmo: If not NULL, points to the default dev_loss_tmo value.
+ * @reconnect: Callback function for reconnecting to the target. See also
+ *     srp_reconnect_rport().
+ * @terminate_rport_io: Callback function for terminating all outstanding I/O
+ *     requests for an rport.
+ */
 struct srp_function_template {
 	/* for initiator drivers */
+	bool has_rport_state;
+	bool reset_timer_if_blocked;
+	int *fast_io_fail_tmo;
+	int *dev_loss_tmo;
+	int (*reconnect)(struct srp_rport *rport);
+	void (*terminate_rport_io)(struct srp_rport *rport);
 	void (*rport_delete)(struct srp_rport *rport);
 	/* for target drivers */
 	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
@@ -43,7 +90,30 @@ extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-
+extern int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo);
+extern int srp_reconnect_rport(struct srp_rport *rport);
+extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 
+/**
+ * srp_chkready() - evaluate the transport layer state before I/O
+ *
+ * Returns a SCSI result code that can be returned by the LLD queuecommand()
+ * implementation. The role of this function is similar to that of
+ * fc_remote_port_chkready().
+ */
+static inline int srp_chkready(struct srp_rport *rport)
+{
+	switch (rport->state) {
+	case SRP_RPORT_RUNNING:
+	case SRP_RPORT_BLOCKED:
+	default:
+		return 0;
+	case SRP_RPORT_FAIL_FAST:
+		return DID_TRANSPORT_FAILFAST << 16;
+	case SRP_RPORT_LOST:
+		return DID_NO_CONNECT << 16;
+	}
+}
+
 #endif
-- 
cgit 


From 8c64e4531c3c3bedf11d723196270d4a7553db45 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Sat, 26 Oct 2013 14:35:59 +0200
Subject: scsi_transport_srp: Add periodic reconnect support

Add support for periodically reconnecting to an SRP target until
the dev_loss timer expires. After the tenth reconnection attempt,
gradually slow down subsequent reconnect attempts.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 Documentation/ABI/stable/sysfs-transport-srp |   8 ++
 drivers/infiniband/ulp/srp/ib_srp.c          |   4 +-
 drivers/scsi/scsi_transport_srp.c            | 106 +++++++++++++++++++++++++--
 include/scsi/scsi_transport_srp.h            |  11 ++-
 4 files changed, 118 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-transport-srp b/Documentation/ABI/stable/sysfs-transport-srp
index 8b6acc775b71..ec7af69fea0a 100644
--- a/Documentation/ABI/stable/sysfs-transport-srp
+++ b/Documentation/ABI/stable/sysfs-transport-srp
@@ -30,6 +30,14 @@ Contact:	linux-scsi@vger.kernel.org
 Description:	16-byte local SRP port identifier in hexadecimal format. An
 		example: 4c:49:4e:55:58:20:56:49:4f:00:00:00:00:00:00:00.
 
+What:		/sys/class/srp_remote_ports/port-<h>:<n>/reconnect_delay
+Date:		February 1, 2014
+KernelVersion:	3.13
+Contact:	linux-scsi@vger.kernel.org, linux-rdma@vger.kernel.org
+Description:	Number of seconds the SCSI layer will wait after a reconnect
+		attempt failed before retrying. Setting this attribute to
+		"off" will disable time-based reconnecting.
+
 What:		/sys/class/srp_remote_ports/port-<h>:<n>/roles
 Date:		June 27, 2007
 KernelVersion:	2.6.24
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 076a3ab7f779..99c893d1c2ac 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -145,9 +145,9 @@ static int srp_tmo_set(const char *val, const struct kernel_param *kp)
 		tmo = -1;
 	}
 	if (kp->arg == &srp_fast_io_fail_tmo)
-		res = srp_tmo_valid(tmo, srp_dev_loss_tmo);
+		res = srp_tmo_valid(-1, tmo, srp_dev_loss_tmo);
 	else
-		res = srp_tmo_valid(srp_fast_io_fail_tmo, tmo);
+		res = srp_tmo_valid(-1, srp_fast_io_fail_tmo, tmo);
 	if (res)
 		goto out;
 	*(int *)kp->arg = tmo;
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 2696e26b3423..2700a5a09bd4 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -41,7 +41,7 @@ struct srp_host_attrs {
 #define to_srp_host_attrs(host)	((struct srp_host_attrs *)(host)->shost_data)
 
 #define SRP_HOST_ATTRS 0
-#define SRP_RPORT_ATTRS 6
+#define SRP_RPORT_ATTRS 8
 
 struct srp_internal {
 	struct scsi_transport_template t;
@@ -69,11 +69,13 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
  * are finished in a reasonable time. Hence do not allow the fast I/O fail
  * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT. Furthermore, these
  * parameters must be such that multipath can detect failed paths timely.
- * Hence do not allow both parameters to be disabled simultaneously.
+ * Hence do not allow all three parameters to be disabled simultaneously.
  */
-int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo)
+int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo)
 {
-	if (fast_io_fail_tmo < 0 && dev_loss_tmo < 0)
+	if (reconnect_delay < 0 && fast_io_fail_tmo < 0 && dev_loss_tmo < 0)
+		return -EINVAL;
+	if (reconnect_delay == 0)
 		return -EINVAL;
 	if (fast_io_fail_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
 		return -EINVAL;
@@ -202,6 +204,56 @@ static int srp_parse_tmo(int *tmo, const char *buf)
 	return res;
 }
 
+static ssize_t show_reconnect_delay(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	return srp_show_tmo(buf, rport->reconnect_delay);
+}
+
+static ssize_t store_reconnect_delay(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, const size_t count)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+	int res, delay;
+
+	res = srp_parse_tmo(&delay, buf);
+	if (res)
+		goto out;
+	res = srp_tmo_valid(delay, rport->fast_io_fail_tmo,
+			    rport->dev_loss_tmo);
+	if (res)
+		goto out;
+
+	if (rport->reconnect_delay <= 0 && delay > 0 &&
+	    rport->state != SRP_RPORT_RUNNING) {
+		queue_delayed_work(system_long_wq, &rport->reconnect_work,
+				   delay * HZ);
+	} else if (delay <= 0) {
+		cancel_delayed_work(&rport->reconnect_work);
+	}
+	rport->reconnect_delay = delay;
+	res = count;
+
+out:
+	return res;
+}
+
+static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, show_reconnect_delay,
+		   store_reconnect_delay);
+
+static ssize_t show_failed_reconnects(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct srp_rport *rport = transport_class_to_srp_rport(dev);
+
+	return sprintf(buf, "%d\n", rport->failed_reconnects);
+}
+
+static DEVICE_ATTR(failed_reconnects, S_IRUGO, show_failed_reconnects, NULL);
+
 static ssize_t show_srp_rport_fast_io_fail_tmo(struct device *dev,
 					       struct device_attribute *attr,
 					       char *buf)
@@ -222,7 +274,8 @@ static ssize_t store_srp_rport_fast_io_fail_tmo(struct device *dev,
 	res = srp_parse_tmo(&fast_io_fail_tmo, buf);
 	if (res)
 		goto out;
-	res = srp_tmo_valid(fast_io_fail_tmo, rport->dev_loss_tmo);
+	res = srp_tmo_valid(rport->reconnect_delay, fast_io_fail_tmo,
+			    rport->dev_loss_tmo);
 	if (res)
 		goto out;
 	rport->fast_io_fail_tmo = fast_io_fail_tmo;
@@ -256,7 +309,8 @@ static ssize_t store_srp_rport_dev_loss_tmo(struct device *dev,
 	res = srp_parse_tmo(&dev_loss_tmo, buf);
 	if (res)
 		goto out;
-	res = srp_tmo_valid(rport->fast_io_fail_tmo, dev_loss_tmo);
+	res = srp_tmo_valid(rport->reconnect_delay, rport->fast_io_fail_tmo,
+			    dev_loss_tmo);
 	if (res)
 		goto out;
 	rport->dev_loss_tmo = dev_loss_tmo;
@@ -312,6 +366,29 @@ invalid:
 	return -EINVAL;
 }
 
+/**
+ * srp_reconnect_work() - reconnect and schedule a new attempt if necessary
+ */
+static void srp_reconnect_work(struct work_struct *work)
+{
+	struct srp_rport *rport = container_of(to_delayed_work(work),
+					struct srp_rport, reconnect_work);
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	int delay, res;
+
+	res = srp_reconnect_rport(rport);
+	if (res != 0) {
+		shost_printk(KERN_ERR, shost,
+			     "reconnect attempt %d failed (%d)\n",
+			     ++rport->failed_reconnects, res);
+		delay = rport->reconnect_delay *
+			min(100, max(1, rport->failed_reconnects - 10));
+		if (delay > 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->reconnect_work, delay * HZ);
+	}
+}
+
 static void __rport_fail_io_fast(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
@@ -371,16 +448,21 @@ static void rport_dev_loss_timedout(struct work_struct *work)
 static void __srp_start_tl_fail_timers(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
-	int fast_io_fail_tmo, dev_loss_tmo;
+	int delay, fast_io_fail_tmo, dev_loss_tmo;
 
 	lockdep_assert_held(&rport->mutex);
 
 	if (!rport->deleted) {
+		delay = rport->reconnect_delay;
 		fast_io_fail_tmo = rport->fast_io_fail_tmo;
 		dev_loss_tmo = rport->dev_loss_tmo;
 		pr_debug("%s current state: %d\n",
 			 dev_name(&shost->shost_gendev), rport->state);
 
+		if (delay > 0)
+			queue_delayed_work(system_long_wq,
+					   &rport->reconnect_work,
+					   1UL * delay * HZ);
 		if (fast_io_fail_tmo >= 0 &&
 		    srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
 			pr_debug("%s new state: %d\n",
@@ -481,6 +563,7 @@ int srp_reconnect_rport(struct srp_rport *rport)
 		cancel_delayed_work(&rport->fast_io_fail_work);
 		cancel_delayed_work(&rport->dev_loss_work);
 
+		rport->failed_reconnects = 0;
 		srp_rport_set_state(rport, SRP_RPORT_RUNNING);
 		scsi_target_unblock(&shost->shost_gendev, SDEV_RUNNING);
 		/*
@@ -539,6 +622,7 @@ static void srp_rport_release(struct device *dev)
 {
 	struct srp_rport *rport = dev_to_rport(dev);
 
+	cancel_delayed_work_sync(&rport->reconnect_work);
 	cancel_delayed_work_sync(&rport->fast_io_fail_work);
 	cancel_delayed_work_sync(&rport->dev_loss_work);
 
@@ -635,6 +719,10 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 	memcpy(rport->port_id, ids->port_id, sizeof(rport->port_id));
 	rport->roles = ids->roles;
 
+	if (i->f->reconnect)
+		rport->reconnect_delay = i->f->reconnect_delay ?
+			*i->f->reconnect_delay : 10;
+	INIT_DELAYED_WORK(&rport->reconnect_work, srp_reconnect_work);
 	rport->fast_io_fail_tmo = i->f->fast_io_fail_tmo ?
 		*i->f->fast_io_fail_tmo : 15;
 	rport->dev_loss_tmo = i->f->dev_loss_tmo ? *i->f->dev_loss_tmo : 60;
@@ -773,6 +861,10 @@ srp_attach_transport(struct srp_function_template *ft)
 		i->rport_attrs[count++] = &dev_attr_fast_io_fail_tmo;
 		i->rport_attrs[count++] = &dev_attr_dev_loss_tmo;
 	}
+	if (ft->reconnect) {
+		i->rport_attrs[count++] = &dev_attr_reconnect_delay;
+		i->rport_attrs[count++] = &dev_attr_failed_reconnects;
+	}
 	if (ft->rport_delete)
 		i->rport_attrs[count++] = &dev_attr_delete;
 	i->rport_attrs[count++] = NULL;
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index ee7001677f64..4ebf6913b7b2 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -31,7 +31,8 @@ enum srp_rport_state {
 /**
  * struct srp_rport
  * @lld_data: LLD private data.
- * @mutex:    Protects against concurrent rport fast_io_fail / dev_loss_tmo.
+ * @mutex:    Protects against concurrent rport reconnect / fast_io_fail /
+ *   dev_loss_tmo activity.
  */
 struct srp_rport {
 	/* for initiator and target drivers */
@@ -48,6 +49,9 @@ struct srp_rport {
 	struct mutex		mutex;
 	enum srp_rport_state	state;
 	bool			deleted;
+	int			reconnect_delay;
+	int			failed_reconnects;
+	struct delayed_work	reconnect_work;
 	int			fast_io_fail_tmo;
 	int			dev_loss_tmo;
 	struct delayed_work	fast_io_fail_work;
@@ -60,6 +64,7 @@ struct srp_rport {
  *     dev_loss_tmo sysfs attribute for an rport.
  * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
  *     timer if the device on which it has been queued is blocked.
+ * @reconnect_delay: If not NULL, points to the default reconnect_delay value.
  * @fast_io_fail_tmo: If not NULL, points to the default fast_io_fail_tmo value.
  * @dev_loss_tmo: If not NULL, points to the default dev_loss_tmo value.
  * @reconnect: Callback function for reconnecting to the target. See also
@@ -71,6 +76,7 @@ struct srp_function_template {
 	/* for initiator drivers */
 	bool has_rport_state;
 	bool reset_timer_if_blocked;
+	int *reconnect_delay;
 	int *fast_io_fail_tmo;
 	int *dev_loss_tmo;
 	int (*reconnect)(struct srp_rport *rport);
@@ -90,7 +96,8 @@ extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-extern int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo);
+extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
+			 int dev_loss_tmo);
 extern int srp_reconnect_rport(struct srp_rport *rport);
 extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
-- 
cgit 


From 4d8981f6b784ae445a28de909d77e27836c3ed44 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Tue, 29 Oct 2013 16:02:00 +0100
Subject: ARM: 7871/1: amba: Extend number of IRQS

Xilinx Zynq pl330 dma driver has 9 irqs which all have to
be used by the driver to get it work properly.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/amba/bus.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 43ec7e247a80..b327a1b1b7e8 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -21,7 +21,7 @@
 #include <linux/resource.h>
 #include <linux/regulator/consumer.h>
 
-#define AMBA_NR_IRQS	2
+#define AMBA_NR_IRQS	9
 #define AMBA_CID	0xb105f00d
 
 struct clk;
-- 
cgit 


From 48a066e72d970a3e225a9c18690d570c736fc455 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 29 Sep 2013 22:06:07 -0400
Subject: RCU'd vfsmounts

* RCU-delayed freeing of vfsmounts
* vfsmount_lock replaced with a seqlock (mount_lock)
* sequence number from mount_lock is stored in nameidata->m_seq and
used when we exit RCU mode
* new vfsmount flag - MNT_SYNC_UMOUNT.  Set by umount_tree() when its
caller knows that vfsmount will have no surviving references.
* synchronize_rcu() done between unlocking namespace_sem in namespace_unlock()
and doing pending mntput().
* new helper: legitimize_mnt(mnt, seq).  Checks the mount_lock sequence
number against seq, then grabs reference to mnt.  Then it rechecks mount_lock
again to close the race and either returns success or drops the reference it
has acquired.  The subtle point is that in case of MNT_SYNC_UMOUNT we can
simply decrement the refcount and sod off - aforementioned synchronize_rcu()
makes sure that final mntput() won't come until we leave RCU mode.  We need
that, since we don't want to end up with some lazy pathwalk racing with
umount() and stealing the final mntput() from it - caller of umount() may
expect it to return only once the fs is shut down and we don't want to break
that.  In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do
full-blown mntput() in case of mount_lock sequence number mismatch happening
just as we'd grabbed the reference, but in those cases we won't be stealing
the final mntput() from anything that would care.
* mntput_no_expire() doesn't lock anything on the fast path now.  Incidentally,
SMP and UP cases are handled the same way - no ifdefs there.
* normal pathname resolution does *not* do any writes to mount_lock.  It does,
of course, bump the refcounts of vfsmount and dentry in the very end, but that's
it.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c           |  20 +++++---
 fs/mount.h            |  10 ++--
 fs/namei.c            |  50 ++++++++++---------
 fs/namespace.c        | 135 ++++++++++++++++++++++++++++++++------------------
 include/linux/mount.h |   2 +
 include/linux/namei.h |   2 +-
 6 files changed, 136 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index eb0978da1bd4..aafa2a146434 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2887,24 +2887,28 @@ static int prepend_path(const struct path *path,
 	struct vfsmount *vfsmnt = path->mnt;
 	struct mount *mnt = real_mount(vfsmnt);
 	int error = 0;
-	unsigned seq = 0;
+	unsigned seq, m_seq = 0;
 	char *bptr;
 	int blen;
 
-	br_read_lock(&vfsmount_lock);
 	rcu_read_lock();
+restart_mnt:
+	read_seqbegin_or_lock(&mount_lock, &m_seq);
+	seq = 0;
 restart:
 	bptr = *buffer;
 	blen = *buflen;
+	error = 0;
 	read_seqbegin_or_lock(&rename_lock, &seq);
 	while (dentry != root->dentry || vfsmnt != root->mnt) {
 		struct dentry * parent;
 
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
+			struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
 			/* Global root? */
-			if (mnt_has_parent(mnt)) {
-				dentry = mnt->mnt_mountpoint;
-				mnt = mnt->mnt_parent;
+			if (mnt != parent) {
+				dentry = ACCESS_ONCE(mnt->mnt_mountpoint);
+				mnt = parent;
 				vfsmnt = &mnt->mnt;
 				continue;
 			}
@@ -2938,7 +2942,11 @@ restart:
 		goto restart;
 	}
 	done_seqretry(&rename_lock, seq);
-	br_read_unlock(&vfsmount_lock);
+	if (need_seqretry(&mount_lock, m_seq)) {
+		m_seq = 1;
+		goto restart_mnt;
+	}
+	done_seqretry(&mount_lock, m_seq);
 
 	if (error >= 0 && bptr == *buffer) {
 		if (--blen < 0)
diff --git a/fs/mount.h b/fs/mount.h
index f0866076de6e..d64c594be6c4 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -1,7 +1,6 @@
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/poll.h>
-#include <linux/lglock.h>
 
 struct mnt_namespace {
 	atomic_t		count;
@@ -30,6 +29,7 @@ struct mount {
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
+	struct rcu_head mnt_rcu;
 #ifdef CONFIG_SMP
 	struct mnt_pcp __percpu *mnt_pcp;
 #else
@@ -80,21 +80,23 @@ static inline int is_mounted(struct vfsmount *mnt)
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
 extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
+extern bool legitimize_mnt(struct vfsmount *, unsigned);
+
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
 }
 
-extern struct lglock vfsmount_lock;
+extern seqlock_t mount_lock;
 
 static inline void lock_mount_hash(void)
 {
-	br_write_lock(&vfsmount_lock);
+	write_seqlock(&mount_lock);
 }
 
 static inline void unlock_mount_hash(void)
 {
-	br_write_unlock(&vfsmount_lock);
+	write_sequnlock(&mount_lock);
 }
 
 struct proc_mounts {
diff --git a/fs/namei.c b/fs/namei.c
index 1f844fbfce72..cb0ebae07e52 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -484,14 +484,12 @@ EXPORT_SYMBOL(path_put);
 
 static inline void lock_rcu_walk(void)
 {
-	br_read_lock(&vfsmount_lock);
 	rcu_read_lock();
 }
 
 static inline void unlock_rcu_walk(void)
 {
 	rcu_read_unlock();
-	br_read_unlock(&vfsmount_lock);
 }
 
 /**
@@ -512,26 +510,23 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 	BUG_ON(!(nd->flags & LOOKUP_RCU));
 
 	/*
-	 * Get a reference to the parent first: we're
-	 * going to make "path_put(nd->path)" valid in
-	 * non-RCU context for "terminate_walk()".
-	 *
-	 * If this doesn't work, return immediately with
-	 * RCU walking still active (and then we will do
-	 * the RCU walk cleanup in terminate_walk()).
+	 * After legitimizing the bastards, terminate_walk()
+	 * will do the right thing for non-RCU mode, and all our
+	 * subsequent exit cases should rcu_read_unlock()
+	 * before returning.  Do vfsmount first; if dentry
+	 * can't be legitimized, just set nd->path.dentry to NULL
+	 * and rely on dput(NULL) being a no-op.
 	 */
-	if (!lockref_get_not_dead(&parent->d_lockref))
+	if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
 		return -ECHILD;
-
-	/*
-	 * After the mntget(), we terminate_walk() will do
-	 * the right thing for non-RCU mode, and all our
-	 * subsequent exit cases should unlock_rcu_walk()
-	 * before returning.
-	 */
-	mntget(nd->path.mnt);
 	nd->flags &= ~LOOKUP_RCU;
 
+	if (!lockref_get_not_dead(&parent->d_lockref)) {
+		nd->path.dentry = NULL;	
+		unlock_rcu_walk();
+		return -ECHILD;
+	}
+
 	/*
 	 * For a negative lookup, the lookup sequence point is the parents
 	 * sequence point, and it only needs to revalidate the parent dentry.
@@ -608,16 +603,21 @@ static int complete_walk(struct nameidata *nd)
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
 
+		if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
+			unlock_rcu_walk();
+			return -ECHILD;
+		}
 		if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
 			unlock_rcu_walk();
+			mntput(nd->path.mnt);
 			return -ECHILD;
 		}
 		if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
 			unlock_rcu_walk();
 			dput(dentry);
+			mntput(nd->path.mnt);
 			return -ECHILD;
 		}
-		mntget(nd->path.mnt);
 		unlock_rcu_walk();
 	}
 
@@ -909,15 +909,15 @@ int follow_up(struct path *path)
 	struct mount *parent;
 	struct dentry *mountpoint;
 
-	br_read_lock(&vfsmount_lock);
+	read_seqlock_excl(&mount_lock);
 	parent = mnt->mnt_parent;
 	if (parent == mnt) {
-		br_read_unlock(&vfsmount_lock);
+		read_sequnlock_excl(&mount_lock);
 		return 0;
 	}
 	mntget(&parent->mnt);
 	mountpoint = dget(mnt->mnt_mountpoint);
-	br_read_unlock(&vfsmount_lock);
+	read_sequnlock_excl(&mount_lock);
 	dput(path->dentry);
 	path->dentry = mountpoint;
 	mntput(path->mnt);
@@ -1048,8 +1048,8 @@ static int follow_managed(struct path *path, unsigned flags)
 
 			/* Something is mounted on this dentry in another
 			 * namespace and/or whatever was mounted there in this
-			 * namespace got unmounted before we managed to get the
-			 * vfsmount_lock */
+			 * namespace got unmounted before lookup_mnt() could
+			 * get it */
 		}
 
 		/* Handle an automount point */
@@ -1864,6 +1864,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		if (flags & LOOKUP_RCU) {
 			lock_rcu_walk();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+			nd->m_seq = read_seqbegin(&mount_lock);
 		} else {
 			path_get(&nd->path);
 		}
@@ -1872,6 +1873,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 
 	nd->root.mnt = NULL;
 
+	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*name=='/') {
 		if (flags & LOOKUP_RCU) {
 			lock_rcu_walk();
diff --git a/fs/namespace.c b/fs/namespace.c
index 500202ce10db..ac2ce8a766e1 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(fs_kobj);
  * It should be taken for write in all cases where the vfsmount
  * tree or hash is modified or when a vfsmount structure is modified.
  */
-DEFINE_BRLOCK(vfsmount_lock);
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
 static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 {
@@ -547,16 +547,38 @@ static void free_vfsmnt(struct mount *mnt)
 	kmem_cache_free(mnt_cache, mnt);
 }
 
+/* call under rcu_read_lock */
+bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
+{
+	struct mount *mnt;
+	if (read_seqretry(&mount_lock, seq))
+		return false;
+	if (bastard == NULL)
+		return true;
+	mnt = real_mount(bastard);
+	mnt_add_count(mnt, 1);
+	if (likely(!read_seqretry(&mount_lock, seq)))
+		return true;
+	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
+		mnt_add_count(mnt, -1);
+		return false;
+	}
+	rcu_read_unlock();
+	mntput(bastard);
+	rcu_read_lock();
+	return false;
+}
+
 /*
  * find the first mount at @dentry on vfsmount @mnt.
- * vfsmount_lock must be held for read or write.
+ * call under rcu_read_lock()
  */
 struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct list_head *head = mount_hashtable + hash(mnt, dentry);
 	struct mount *p;
 
-	list_for_each_entry(p, head, mnt_hash)
+	list_for_each_entry_rcu(p, head, mnt_hash)
 		if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
 			return p;
 	return NULL;
@@ -564,7 +586,7 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 
 /*
  * find the last mount at @dentry on vfsmount @mnt.
- * vfsmount_lock must be held for read or write.
+ * mount_lock must be held.
  */
 struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
 {
@@ -596,17 +618,17 @@ struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
 struct vfsmount *lookup_mnt(struct path *path)
 {
 	struct mount *child_mnt;
+	struct vfsmount *m;
+	unsigned seq;
 
-	br_read_lock(&vfsmount_lock);
-	child_mnt = __lookup_mnt(path->mnt, path->dentry);
-	if (child_mnt) {
-		mnt_add_count(child_mnt, 1);
-		br_read_unlock(&vfsmount_lock);
-		return &child_mnt->mnt;
-	} else {
-		br_read_unlock(&vfsmount_lock);
-		return NULL;
-	}
+	rcu_read_lock();
+	do {
+		seq = read_seqbegin(&mount_lock);
+		child_mnt = __lookup_mnt(path->mnt, path->dentry);
+		m = child_mnt ? &child_mnt->mnt : NULL;
+	} while (!legitimize_mnt(m, seq));
+	rcu_read_unlock();
+	return m;
 }
 
 static struct mountpoint *new_mountpoint(struct dentry *dentry)
@@ -874,38 +896,46 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return ERR_PTR(err);
 }
 
+static void delayed_free(struct rcu_head *head)
+{
+	struct mount *mnt = container_of(head, struct mount, mnt_rcu);
+	kfree(mnt->mnt_devname);
+#ifdef CONFIG_SMP
+	free_percpu(mnt->mnt_pcp);
+#endif
+	kmem_cache_free(mnt_cache, mnt);
+}
+
 static void mntput_no_expire(struct mount *mnt)
 {
 put_again:
-#ifdef CONFIG_SMP
-	br_read_lock(&vfsmount_lock);
-	if (likely(mnt->mnt_ns)) {
-		/* shouldn't be the last one */
-		mnt_add_count(mnt, -1);
-		br_read_unlock(&vfsmount_lock);
+	rcu_read_lock();
+	mnt_add_count(mnt, -1);
+	if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+		rcu_read_unlock();
 		return;
 	}
-	br_read_unlock(&vfsmount_lock);
-
 	lock_mount_hash();
-	mnt_add_count(mnt, -1);
 	if (mnt_get_count(mnt)) {
+		rcu_read_unlock();
 		unlock_mount_hash();
 		return;
 	}
-#else
-	mnt_add_count(mnt, -1);
-	if (likely(mnt_get_count(mnt)))
-		return;
-	lock_mount_hash();
-#endif
 	if (unlikely(mnt->mnt_pinned)) {
 		mnt_add_count(mnt, mnt->mnt_pinned + 1);
 		mnt->mnt_pinned = 0;
+		rcu_read_unlock();
 		unlock_mount_hash();
 		acct_auto_close_mnt(&mnt->mnt);
 		goto put_again;
 	}
+	if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) {
+		rcu_read_unlock();
+		unlock_mount_hash();
+		return;
+	}
+	mnt->mnt.mnt_flags |= MNT_DOOMED;
+	rcu_read_unlock();
 
 	list_del(&mnt->mnt_instance);
 	unlock_mount_hash();
@@ -924,7 +954,8 @@ put_again:
 	fsnotify_vfsmount_delete(&mnt->mnt);
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
-	free_vfsmnt(mnt);
+	mnt_free_id(mnt);
+	call_rcu(&mnt->mnt_rcu, delayed_free);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -1137,6 +1168,8 @@ static void namespace_unlock(void)
 	list_splice_init(&unmounted, &head);
 	up_write(&namespace_sem);
 
+	synchronize_rcu();
+
 	while (!list_empty(&head)) {
 		mnt = list_first_entry(&head, struct mount, mnt_hash);
 		list_del_init(&mnt->mnt_hash);
@@ -1152,10 +1185,13 @@ static inline void namespace_lock(void)
 }
 
 /*
- * vfsmount lock must be held for write
+ * mount_lock must be held
  * namespace_sem must be held for write
+ * how = 0 => just this tree, don't propagate
+ * how = 1 => propagate; we know that nobody else has reference to any victims
+ * how = 2 => lazy umount
  */
-void umount_tree(struct mount *mnt, int propagate)
+void umount_tree(struct mount *mnt, int how)
 {
 	LIST_HEAD(tmp_list);
 	struct mount *p;
@@ -1163,7 +1199,7 @@ void umount_tree(struct mount *mnt, int propagate)
 	for (p = mnt; p; p = next_mnt(p, mnt))
 		list_move(&p->mnt_hash, &tmp_list);
 
-	if (propagate)
+	if (how)
 		propagate_umount(&tmp_list);
 
 	list_for_each_entry(p, &tmp_list, mnt_hash) {
@@ -1171,6 +1207,8 @@ void umount_tree(struct mount *mnt, int propagate)
 		list_del_init(&p->mnt_list);
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
+		if (how < 2)
+			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 		list_del_init(&p->mnt_child);
 		if (mnt_has_parent(p)) {
 			put_mountpoint(p->mnt_mp);
@@ -1262,14 +1300,18 @@ static int do_umount(struct mount *mnt, int flags)
 	lock_mount_hash();
 	event++;
 
-	if (!(flags & MNT_DETACH))
-		shrink_submounts(mnt);
-
-	retval = -EBUSY;
-	if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) {
+	if (flags & MNT_DETACH) {
 		if (!list_empty(&mnt->mnt_list))
-			umount_tree(mnt, 1);
+			umount_tree(mnt, 2);
 		retval = 0;
+	} else {
+		shrink_submounts(mnt);
+		retval = -EBUSY;
+		if (!propagate_mount_busy(mnt, 2)) {
+			if (!list_empty(&mnt->mnt_list))
+				umount_tree(mnt, 1);
+			retval = 0;
+		}
 	}
 	unlock_mount_hash();
 	namespace_unlock();
@@ -1955,7 +1997,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);
+	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
@@ -2172,7 +2214,7 @@ resume:
  * process a list of expirable mountpoints with the intent of discarding any
  * submounts of a specific parent mountpoint
  *
- * vfsmount_lock must be held for write
+ * mount_lock must be held for write
  */
 static void shrink_submounts(struct mount *mnt)
 {
@@ -2558,7 +2600,7 @@ out_type:
 /*
  * Return true if path is reachable from root
  *
- * namespace_sem or vfsmount_lock is held
+ * namespace_sem or mount_lock is held
  */
 bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
 			 const struct path *root)
@@ -2573,9 +2615,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
 int path_is_under(struct path *path1, struct path *path2)
 {
 	int res;
-	br_read_lock(&vfsmount_lock);
+	read_seqlock_excl(&mount_lock);
 	res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
-	br_read_unlock(&vfsmount_lock);
+	read_sequnlock_excl(&mount_lock);
 	return res;
 }
 EXPORT_SYMBOL(path_is_under);
@@ -2748,8 +2790,6 @@ void __init mnt_init(void)
 	for (u = 0; u < HASH_SIZE; u++)
 		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
 
-	br_lock_init(&vfsmount_lock);
-
 	err = sysfs_init();
 	if (err)
 		printk(KERN_WARNING "%s: sysfs_init error: %d\n",
@@ -2788,9 +2828,8 @@ void kern_unmount(struct vfsmount *mnt)
 {
 	/* release long term mount so mount point can be released */
 	if (!IS_ERR_OR_NULL(mnt)) {
-		lock_mount_hash();
 		real_mount(mnt)->mnt_ns = NULL;
-		unlock_mount_hash();
+		synchronize_rcu();	/* yecchhh... */
 		mntput(mnt);
 	}
 }
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 38cd98f112a0..371d346fa270 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -49,6 +49,8 @@ struct mnt_namespace;
 
 #define MNT_LOCK_READONLY	0x400000
 #define MNT_LOCKED		0x800000
+#define MNT_DOOMED		0x1000000
+#define MNT_SYNC_UMOUNT		0x2000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 8e47bc7a1665..492de72560fa 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -16,7 +16,7 @@ struct nameidata {
 	struct path	root;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags;
-	unsigned	seq;
+	unsigned	seq, m_seq;
 	int		last_type;
 	unsigned	depth;
 	char *saved_names[MAX_NESTED_LINKS + 1];
-- 
cgit 


From eee5cc2702929fd41cce28058dc6d6717f723f87 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 4 Oct 2013 11:06:42 -0400
Subject: get rid of s_files and files_lock

The only thing we need it for is alt-sysrq-r (emergency remount r/o)
and these days we can do just as well without going through the
list of files.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c    | 125 -----------------------------------------------------
 fs/internal.h      |   3 --
 fs/open.c          |   2 -
 fs/super.c         |  15 +------
 include/linux/fs.h |  13 ------
 5 files changed, 2 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/fs/file_table.c b/fs/file_table.c
index e61e5529fa9d..23b6dca03ba0 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -36,8 +36,6 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DEFINE_STATIC_LGLOCK(files_lglock);
-
 /* SLAB cache for file structures */
 static struct kmem_cache *filp_cachep __read_mostly;
 
@@ -134,7 +132,6 @@ struct file *get_empty_filp(void)
 		return ERR_PTR(error);
 	}
 
-	INIT_LIST_HEAD(&f->f_u.fu_list);
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
@@ -304,7 +301,6 @@ void fput(struct file *file)
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 
-		file_sb_list_del(file);
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
 			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
@@ -333,7 +329,6 @@ void __fput_sync(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
-		file_sb_list_del(file);
 		BUG_ON(!(task->flags & PF_KTHREAD));
 		__fput(file);
 	}
@@ -345,129 +340,10 @@ void put_filp(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		security_file_free(file);
-		file_sb_list_del(file);
 		file_free(file);
 	}
 }
 
-static inline int file_list_cpu(struct file *file)
-{
-#ifdef CONFIG_SMP
-	return file->f_sb_list_cpu;
-#else
-	return smp_processor_id();
-#endif
-}
-
-/* helper for file_sb_list_add to reduce ifdefs */
-static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	struct list_head *list;
-#ifdef CONFIG_SMP
-	int cpu;
-	cpu = smp_processor_id();
-	file->f_sb_list_cpu = cpu;
-	list = per_cpu_ptr(sb->s_files, cpu);
-#else
-	list = &sb->s_files;
-#endif
-	list_add(&file->f_u.fu_list, list);
-}
-
-/**
- * file_sb_list_add - add a file to the sb's file list
- * @file: file to add
- * @sb: sb to add it to
- *
- * Use this function to associate a file with the superblock of the inode it
- * refers to.
- */
-void file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	if (likely(!(file->f_mode & FMODE_WRITE)))
-		return;
-	if (!S_ISREG(file_inode(file)->i_mode))
-		return;
-	lg_local_lock(&files_lglock);
-	__file_sb_list_add(file, sb);
-	lg_local_unlock(&files_lglock);
-}
-
-/**
- * file_sb_list_del - remove a file from the sb's file list
- * @file: file to remove
- * @sb: sb to remove it from
- *
- * Use this function to remove a file from its superblock.
- */
-void file_sb_list_del(struct file *file)
-{
-	if (!list_empty(&file->f_u.fu_list)) {
-		lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
-		list_del_init(&file->f_u.fu_list);
-		lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
-	}
-}
-
-#ifdef CONFIG_SMP
-
-/*
- * These macros iterate all files on all CPUs for a given superblock.
- * files_lglock must be held globally.
- */
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	int i;							\
-	for_each_possible_cpu(i) {				\
-		struct list_head *list;				\
-		list = per_cpu_ptr((__sb)->s_files, i);		\
-		list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-	}							\
-}
-
-#else
-
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	struct list_head *list;					\
-	list = &(sb)->s_files;					\
-	list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-}
-
-#endif
-
-/**
- *	mark_files_ro - mark all files read-only
- *	@sb: superblock in question
- *
- *	All files are marked read-only.  We don't care about pending
- *	delete files so this should be used in 'force' mode only.
- */
-void mark_files_ro(struct super_block *sb)
-{
-	struct file *f;
-
-	lg_global_lock(&files_lglock);
-	do_file_list_for_each_entry(sb, f) {
-		if (!file_count(f))
-			continue;
-		if (!(f->f_mode & FMODE_WRITE))
-			continue;
-		spin_lock(&f->f_lock);
-		f->f_mode &= ~FMODE_WRITE;
-		spin_unlock(&f->f_lock);
-		if (file_check_writeable(f) != 0)
-			continue;
-		__mnt_drop_write(f->f_path.mnt);
-		file_release_write(f);
-	} while_file_list_for_each_entry;
-	lg_global_unlock(&files_lglock);
-}
-
 void __init files_init(unsigned long mempages)
 { 
 	unsigned long n;
@@ -483,6 +359,5 @@ void __init files_init(unsigned long mempages)
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	files_defer_init();
-	lg_lock_init(&files_lglock, "files_lglock");
 	percpu_counter_init(&nr_files, 0);
 } 
diff --git a/fs/internal.h b/fs/internal.h
index 4a11e75ce14d..465742407466 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -73,9 +73,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern void file_sb_list_add(struct file *f, struct super_block *sb);
-extern void file_sb_list_del(struct file *f);
-extern void mark_files_ro(struct super_block *);
 extern struct file *get_empty_filp(void);
 
 /*
diff --git a/fs/open.c b/fs/open.c
index a1465b1ec8c7..fffbed40dbe9 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -685,7 +685,6 @@ static int do_dentry_open(struct file *f,
 	}
 
 	f->f_mapping = inode->i_mapping;
-	file_sb_list_add(f, inode->i_sb);
 
 	if (unlikely(f->f_mode & FMODE_PATH)) {
 		f->f_op = &empty_fops;
@@ -724,7 +723,6 @@ static int do_dentry_open(struct file *f,
 
 cleanup_all:
 	fops_put(f->f_op);
-	file_sb_list_del(f);
 	if (f->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
 		if (!special_file(inode->i_mode)) {
diff --git a/fs/super.c b/fs/super.c
index 743bb7118053..e5f6c2cfac38 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -140,9 +140,6 @@ static void destroy_super(struct super_block *s)
 	int i;
 	list_lru_destroy(&s->s_dentry_lru);
 	list_lru_destroy(&s->s_inode_lru);
-#ifdef CONFIG_SMP
-	free_percpu(s->s_files);
-#endif
 	for (i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_counter_destroy(&s->s_writers.counter[i]);
 	security_sb_free(s);
@@ -172,15 +169,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	if (security_sb_alloc(s))
 		goto fail;
 
-#ifdef CONFIG_SMP
-	s->s_files = alloc_percpu(struct list_head);
-	if (!s->s_files)
-		goto fail;
-	for_each_possible_cpu(i)
-		INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i));
-#else
-	INIT_LIST_HEAD(&s->s_files);
-#endif
 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
 		if (percpu_counter_init(&s->s_writers.counter[i], 0) < 0)
 			goto fail;
@@ -722,7 +710,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	   make sure there are no rw files opened */
 	if (remount_ro) {
 		if (force) {
-			mark_files_ro(sb);
+			sb->s_readonly_remount = 1;
+			smp_wmb();
 		} else {
 			retval = sb_prepare_remount_readonly(sb);
 			if (retval)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ab8a67ee054..2b0f4e974480 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -764,12 +764,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 #define FILE_MNT_WRITE_RELEASED	2
 
 struct file {
-	/*
-	 * fu_list becomes invalid after file_free is called and queued via
-	 * fu_rcuhead for RCU freeing
-	 */
 	union {
-		struct list_head	fu_list;
 		struct llist_node	fu_llist;
 		struct rcu_head 	fu_rcuhead;
 	} f_u;
@@ -783,9 +778,6 @@ struct file {
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
-#ifdef CONFIG_SMP
-	int			f_sb_list_cpu;
-#endif
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
@@ -1264,11 +1256,6 @@ struct super_block {
 
 	struct list_head	s_inodes;	/* all inodes */
 	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
-#ifdef CONFIG_SMP
-	struct list_head __percpu *s_files;
-#else
-	struct list_head	s_files;
-#endif
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;
-- 
cgit 


From 0f6ed63b170778b9c93fb0ae4017f110c9ee6416 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Oct 2013 14:19:39 -0400
Subject: no need to keep brlock macros anymore...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/lglock.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 0d24e932db0b..96549abe8842 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -25,16 +25,6 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 
-/* can make br locks by using local lock for read side, global lock for write */
-#define br_lock_init(name)	lg_lock_init(name, #name)
-#define br_read_lock(name)	lg_local_lock(name)
-#define br_read_unlock(name)	lg_local_unlock(name)
-#define br_write_lock(name)	lg_global_lock(name)
-#define br_write_unlock(name)	lg_global_unlock(name)
-
-#define DEFINE_BRLOCK(name)		DEFINE_LGLOCK(name)
-#define DEFINE_STATIC_BRLOCK(name)	DEFINE_STATIC_LGLOCK(name)
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define LOCKDEP_INIT_MAP lockdep_init_map
 #else
-- 
cgit 


From ecc8c7725e6c21528329b34acae2a1d64b3af89b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Oct 2013 15:32:35 -0400
Subject: new helper: dump_emit()

dump_write() analog, takes core_dump_params instead of file,
keeps track of the amount written in cprm->written and checks for
cprm->limit.  Start using it in binfmt_elf.c...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/binfmt_elf.c          | 60 +++++++++++++++++++-----------------------------
 fs/coredump.c            | 14 +++++++++++
 include/linux/binfmts.h  |  1 +
 include/linux/coredump.h |  2 ++
 4 files changed, 40 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 501c8a4d6eb1..00fd9c969a27 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1225,35 +1225,23 @@ static int notesize(struct memelfnote *en)
 	return sz;
 }
 
-#define DUMP_WRITE(addr, nr, foffset)	\
-	do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0)
-
-static int alignfile(struct file *file, loff_t *foffset)
+static int alignfile(struct coredump_params *cprm)
 {
 	static const char buf[4] = { 0, };
-	DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
-	return 1;
+	return dump_emit(cprm, buf, roundup(cprm->written, 4) - cprm->written);
 }
 
-static int writenote(struct memelfnote *men, struct file *file,
-			loff_t *foffset)
+static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 {
 	struct elf_note en;
 	en.n_namesz = strlen(men->name) + 1;
 	en.n_descsz = men->datasz;
 	en.n_type = men->type;
 
-	DUMP_WRITE(&en, sizeof(en), foffset);
-	DUMP_WRITE(men->name, en.n_namesz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-	DUMP_WRITE(men->data, men->datasz, foffset);
-	if (!alignfile(file, foffset))
-		return 0;
-
-	return 1;
+	return dump_emit(cprm, &en, sizeof(en)) &&
+	    dump_emit(cprm, men->name, en.n_namesz) && alignfile(cprm) &&
+	    dump_emit(cprm, men->data, men->datasz) && alignfile(cprm);
 }
-#undef DUMP_WRITE
 
 static void fill_elf_header(struct elfhdr *elf, int segs,
 			    u16 machine, u32 flags)
@@ -1702,7 +1690,7 @@ static size_t get_note_info_size(struct elf_note_info *info)
  * process-wide notes are interleaved after the first thread-specific note.
  */
 static int write_note_info(struct elf_note_info *info,
-			   struct file *file, loff_t *foffset)
+			   struct coredump_params *cprm)
 {
 	bool first = 1;
 	struct elf_thread_core_info *t = info->thread;
@@ -1710,22 +1698,22 @@ static int write_note_info(struct elf_note_info *info,
 	do {
 		int i;
 
-		if (!writenote(&t->notes[0], file, foffset))
+		if (!writenote(&t->notes[0], cprm))
 			return 0;
 
-		if (first && !writenote(&info->psinfo, file, foffset))
+		if (first && !writenote(&info->psinfo, cprm))
 			return 0;
-		if (first && !writenote(&info->signote, file, foffset))
+		if (first && !writenote(&info->signote, cprm))
 			return 0;
-		if (first && !writenote(&info->auxv, file, foffset))
+		if (first && !writenote(&info->auxv, cprm))
 			return 0;
 		if (first && info->files.data &&
-				!writenote(&info->files, file, foffset))
+				!writenote(&info->files, cprm))
 			return 0;
 
 		for (i = 1; i < info->thread_notes; ++i)
 			if (t->notes[i].data &&
-			    !writenote(&t->notes[i], file, foffset))
+			    !writenote(&t->notes[i], cprm))
 				return 0;
 
 		first = 0;
@@ -1935,13 +1923,13 @@ static size_t get_note_info_size(struct elf_note_info *info)
 }
 
 static int write_note_info(struct elf_note_info *info,
-			   struct file *file, loff_t *foffset)
+			   struct coredump_params *cprm)
 {
 	int i;
 	struct list_head *t;
 
 	for (i = 0; i < info->numnote; i++)
-		if (!writenote(info->notes + i, file, foffset))
+		if (!writenote(info->notes + i, cprm))
 			return 0;
 
 	/* write out the thread status notes section */
@@ -1950,7 +1938,7 @@ static int write_note_info(struct elf_note_info *info,
 				list_entry(t, struct elf_thread_status, list);
 
 		for (i = 0; i < tmp->num_notes; i++)
-			if (!writenote(&tmp->notes[i], file, foffset))
+			if (!writenote(&tmp->notes[i], cprm))
 				return 0;
 	}
 
@@ -2136,13 +2124,10 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	offset = dataoff;
 
-	size += sizeof(*elf);
-	if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf)))
+	if (!dump_emit(cprm, elf, sizeof(*elf)))
 		goto end_coredump;
 
-	size += sizeof(*phdr4note);
-	if (size > cprm->limit
-	    || !dump_write(cprm->file, phdr4note, sizeof(*phdr4note)))
+	if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
 		goto end_coredump;
 
 	/* Write program headers for segments dump */
@@ -2164,19 +2149,20 @@ static int elf_core_dump(struct coredump_params *cprm)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
-		size += sizeof(phdr);
-		if (size > cprm->limit
-		    || !dump_write(cprm->file, &phdr, sizeof(phdr)))
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			goto end_coredump;
 	}
+	size = cprm->written;
 
 	if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
 		goto end_coredump;
 
+	cprm->written = foffset;	/* will disappear */
  	/* write out the notes section */
-	if (!write_note_info(&info, cprm->file, &foffset))
+	if (!write_note_info(&info, cprm))
 		goto end_coredump;
 
+	foffset = cprm->written;
 	if (elf_coredump_extra_notes_write(cprm->file, &foffset))
 		goto end_coredump;
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 42c3b8423669..319f973bab72 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -693,6 +693,20 @@ int dump_write(struct file *file, const void *addr, int nr)
 }
 EXPORT_SYMBOL(dump_write);
 
+int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
+{
+	struct file *file = cprm->file;
+	if (dump_interrupted() || !access_ok(VERIFY_READ, addr, nr))
+		return 0;
+	if (cprm->written + nr > cprm->limit)
+		return 0;
+	if (file->f_op->write(file, addr, nr, &file->f_pos) != nr)
+		return 0;
+	cprm->written += nr;
+	return 1;
+}
+EXPORT_SYMBOL(dump_emit);
+
 int dump_seek(struct file *file, loff_t off)
 {
 	int ret = 1;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index e8112ae50531..8aa507e7a41a 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -61,6 +61,7 @@ struct coredump_params {
 	struct file *file;
 	unsigned long limit;
 	unsigned long mm_flags;
+	loff_t written;
 };
 
 /*
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index a98f1ca60407..2959376a9ad5 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -10,8 +10,10 @@
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
  */
+struct coredump_params;
 extern int dump_write(struct file *file, const void *addr, int nr);
 extern int dump_seek(struct file *file, loff_t off);
+extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(siginfo_t *siginfo);
 #else
-- 
cgit 


From 506f21c556c747bb07b893f146220ec45cda381b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Oct 2013 17:22:57 -0400
Subject: switch elf_core_write_extra_phdrs() to dump_emit()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/kernel/elfcore.c |  6 ++----
 arch/x86/um/elfcore.c      |  7 ++-----
 fs/binfmt_elf.c            |  4 ++--
 fs/binfmt_elf_fdpic.c      |  4 +++-
 include/linux/elfcore.h    |  5 +++--
 kernel/elfcore.c           | 10 +++-------
 6 files changed, 15 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c
index bac1639bc320..798ce543da4b 100644
--- a/arch/ia64/kernel/elfcore.c
+++ b/arch/ia64/kernel/elfcore.c
@@ -11,8 +11,7 @@ Elf64_Half elf_core_extra_phdrs(void)
 	return GATE_EHDR->e_phnum;
 }
 
-int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-			       unsigned long limit)
+int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	const struct elf_phdr *const gate_phdrs =
 		(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
@@ -35,8 +34,7 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
 			phdr.p_offset += ofs;
 		}
 		phdr.p_paddr = 0; /* match other core phdrs */
-		*size += sizeof(phdr);
-		if (*size > limit || !dump_write(file, &phdr, sizeof(phdr)))
+		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			return 0;
 	}
 	return 1;
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 6bb49b687c97..fc21f98efafe 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -11,8 +11,7 @@ Elf32_Half elf_core_extra_phdrs(void)
 	return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
 }
 
-int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-			       unsigned long limit)
+int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
@@ -32,9 +31,7 @@ int elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
 				phdr.p_offset += ofs;
 			}
 			phdr.p_paddr = 0; /* match other core phdrs */
-			*size += sizeof(phdr);
-			if (*size > limit
-			    || !dump_write(file, &phdr, sizeof(phdr)))
+			if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 				return 0;
 		}
 	}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 00fd9c969a27..35c4886dae2d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2152,11 +2152,11 @@ static int elf_core_dump(struct coredump_params *cprm)
 		if (!dump_emit(cprm, &phdr, sizeof(phdr)))
 			goto end_coredump;
 	}
-	size = cprm->written;
 
-	if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
+	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
+	size = cprm->written;
 	cprm->written = foffset;	/* will disappear */
  	/* write out the notes section */
 	if (!write_note_info(&info, cprm))
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index ea4c6273b4a5..44db8b92121a 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1791,9 +1791,11 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 			goto end_coredump;
 	}
 
-	if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit))
+	cprm->written = size;
+	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
+	size = cprm->written;
  	/* write out the notes section */
 	for (i = 0; i < numnote; i++)
 		if (!writenote(notes + i, cprm->file, &foffset))
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index cdd3d13efce7..1b92a8c40624 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -6,6 +6,8 @@
 #include <asm/elf.h>
 #include <uapi/linux/elfcore.h>
 
+struct coredump_params;
+
 static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
 {
 #ifdef ELF_CORE_COPY_REGS
@@ -63,8 +65,7 @@ static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregse
  */
 extern Elf_Half elf_core_extra_phdrs(void);
 extern int
-elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-			   unsigned long limit);
+elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
 extern int
 elf_core_write_extra_data(struct file *file, size_t *size, unsigned long limit);
 extern size_t elf_core_extra_data_size(void);
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
index ff915efef66d..e556751d15d9 100644
--- a/kernel/elfcore.c
+++ b/kernel/elfcore.c
@@ -1,23 +1,19 @@
 #include <linux/elf.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
-
-#include <asm/elf.h>
-
+#include <linux/binfmts.h>
 
 Elf_Half __weak elf_core_extra_phdrs(void)
 {
 	return 0;
 }
 
-int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
-				      unsigned long limit)
+int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
 	return 1;
 }
 
-int __weak elf_core_write_extra_data(struct file *file, size_t *size,
-				     unsigned long limit)
+int __weak elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	return 1;
 }
-- 
cgit 


From aa3e7eaf0a0f06edd2b733e84e7e8ffe108e8786 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Oct 2013 17:50:15 -0400
Subject: switch elf_core_write_extra_data() to dump_emit()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/kernel/elfcore.c | 6 ++----
 arch/x86/um/elfcore.c      | 8 ++------
 fs/binfmt_elf.c            | 4 +++-
 fs/binfmt_elf_fdpic.c      | 4 +++-
 include/linux/elfcore.h    | 2 +-
 5 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c
index 798ce543da4b..04bc8fd5f893 100644
--- a/arch/ia64/kernel/elfcore.c
+++ b/arch/ia64/kernel/elfcore.c
@@ -40,8 +40,7 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 	return 1;
 }
 
-int elf_core_write_extra_data(struct file *file, size_t *size,
-			      unsigned long limit)
+int elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	const struct elf_phdr *const gate_phdrs =
 		(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
@@ -52,8 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size,
 			void *addr = (void *)gate_phdrs[i].p_vaddr;
 			size_t memsz = PAGE_ALIGN(gate_phdrs[i].p_memsz);
 
-			*size += memsz;
-			if (*size > limit || !dump_write(file, addr, memsz))
+			if (!dump_emit(cprm, addr, memsz))
 				return 0;
 			break;
 		}
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index fc21f98efafe..7bb89a27a5e4 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -38,8 +38,7 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 	return 1;
 }
 
-int elf_core_write_extra_data(struct file *file, size_t *size,
-			      unsigned long limit)
+int elf_core_write_extra_data(struct coredump_params *cprm)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
@@ -52,10 +51,7 @@ int elf_core_write_extra_data(struct file *file, size_t *size,
 			if (phdrp[i].p_type == PT_LOAD) {
 				void *addr = (void *) phdrp[i].p_vaddr;
 				size_t filesz = phdrp[i].p_filesz;
-
-				*size += filesz;
-				if (*size > limit
-				    || !dump_write(file, addr, filesz))
+				if (!dump_emit(cprm, addr, filesz))
 					return 0;
 			}
 		}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 35c4886dae2d..a998b221b53a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2196,8 +2196,10 @@ static int elf_core_dump(struct coredump_params *cprm)
 		}
 	}
 
-	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
+	cprm->written = size;
+	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
+	size = cprm->written;
 
 	if (e_phnum == PN_XNUM) {
 		size += sizeof(*shdr4extnum);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 44db8b92121a..77bf7e33e706 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1818,8 +1818,10 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 				    cprm->mm_flags) < 0)
 		goto end_coredump;
 
-	if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit))
+	cprm->written = size;
+	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
+	size = cprm->written;
 
 	if (e_phnum == PN_XNUM) {
 		size += sizeof(*shdr4extnum);
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 1b92a8c40624..698d51a0eea3 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -67,7 +67,7 @@ extern Elf_Half elf_core_extra_phdrs(void);
 extern int
 elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
 extern int
-elf_core_write_extra_data(struct file *file, size_t *size, unsigned long limit);
+elf_core_write_extra_data(struct coredump_params *cprm);
 extern size_t elf_core_extra_data_size(void);
 
 #endif /* _LINUX_ELFCORE_H */
-- 
cgit 


From cdc3d5627d5f7c4e6b6372b9fb39cba0fe6a9b2a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 5 Oct 2013 22:24:29 -0400
Subject: switch elf_coredump_extra_notes_write() to dump_emit()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/include/asm/spu.h               |  3 +-
 arch/powerpc/platforms/cell/spu_syscalls.c   |  5 ++--
 arch/powerpc/platforms/cell/spufs/coredump.c | 44 +++++++++++-----------------
 arch/powerpc/platforms/cell/spufs/spufs.h    |  3 +-
 fs/binfmt_elf.c                              |  7 ++---
 include/linux/elf.h                          |  6 ++--
 6 files changed, 30 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h
index 93f280e23279..37b7ca39ec9f 100644
--- a/arch/powerpc/include/asm/spu.h
+++ b/arch/powerpc/include/asm/spu.h
@@ -235,6 +235,7 @@ extern long spu_sys_callback(struct spu_syscall_block *s);
 
 /* syscalls implemented in spufs */
 struct file;
+struct coredump_params;
 struct spufs_calls {
 	long (*create_thread)(const char __user *name,
 					unsigned int flags, umode_t mode,
@@ -242,7 +243,7 @@ struct spufs_calls {
 	long (*spu_run)(struct file *filp, __u32 __user *unpc,
 						__u32 __user *ustatus);
 	int (*coredump_extra_notes_size)(void);
-	int (*coredump_extra_notes_write)(struct file *file, loff_t *foffset);
+	int (*coredump_extra_notes_write)(struct coredump_params *cprm);
 	void (*notify_spus_active)(void);
 	struct module *owner;
 };
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index db4e638cf408..3844f1397fc3 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/syscalls.h>
 #include <linux/rcupdate.h>
+#include <linux/binfmts.h>
 
 #include <asm/spu.h>
 
@@ -126,7 +127,7 @@ int elf_coredump_extra_notes_size(void)
 	return ret;
 }
 
-int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int elf_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spufs_calls *calls;
 	int ret;
@@ -135,7 +136,7 @@ int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 	if (!calls)
 		return 0;
 
-	ret = calls->coredump_extra_notes_write(file, foffset);
+	ret = calls->coredump_extra_notes_write(cprm);
 
 	spufs_calls_put(calls);
 
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index c9500ea7be2f..5d9b0a288f36 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -27,6 +27,8 @@
 #include <linux/gfp.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
+#include <linux/coredump.h>
+#include <linux/binfmts.h>
 
 #include <asm/uaccess.h>
 
@@ -52,35 +54,24 @@ static ssize_t do_coredump_read(int num, struct spu_context *ctx, void *buffer,
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
  */
-static int spufs_dump_write(struct file *file, const void *addr, int nr, loff_t *foffset)
+static int spufs_dump_write(struct coredump_params *cprm, const void *addr, int nr)
 {
-	unsigned long limit = rlimit(RLIMIT_CORE);
-	ssize_t written;
-
-	if (*foffset + nr > limit)
+	if (!dump_emit(cprm, addr, nr))
 		return -EIO;
-
-	written = file->f_op->write(file, addr, nr, &file->f_pos);
-	*foffset += written;
-
-	if (written != nr)
-		return -EIO;
-
 	return 0;
 }
 
-static int spufs_dump_align(struct file *file, char *buf, loff_t new_off,
-			    loff_t *foffset)
+static int spufs_dump_align(struct coredump_params *cprm, char *buf, loff_t new_off)
 {
 	int rc, size;
 
-	size = min((loff_t)PAGE_SIZE, new_off - *foffset);
+	size = min((loff_t)PAGE_SIZE, new_off - cprm->written);
 	memset(buf, 0, size);
 
 	rc = 0;
-	while (rc == 0 && new_off > *foffset) {
-		size = min((loff_t)PAGE_SIZE, new_off - *foffset);
-		rc = spufs_dump_write(file, buf, size, foffset);
+	while (rc == 0 && new_off > cprm->written) {
+		size = min((loff_t)PAGE_SIZE, new_off - cprm->written);
+		rc = spufs_dump_write(cprm, buf, size);
 	}
 
 	return rc;
@@ -165,7 +156,7 @@ int spufs_coredump_extra_notes_size(void)
 }
 
 static int spufs_arch_write_note(struct spu_context *ctx, int i,
-				  struct file *file, int dfd, loff_t *foffset)
+				  struct coredump_params *cprm, int dfd)
 {
 	loff_t pos = 0;
 	int sz, rc, nread, total = 0;
@@ -186,22 +177,22 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	en.n_descsz = sz;
 	en.n_type = NT_SPU;
 
-	rc = spufs_dump_write(file, &en, sizeof(en), foffset);
+	rc = spufs_dump_write(cprm, &en, sizeof(en));
 	if (rc)
 		goto out;
 
-	rc = spufs_dump_write(file, fullname, en.n_namesz, foffset);
+	rc = spufs_dump_write(cprm, fullname, en.n_namesz);
 	if (rc)
 		goto out;
 
-	rc = spufs_dump_align(file, buf, roundup(*foffset, 4), foffset);
+	rc = spufs_dump_align(cprm, buf, roundup(cprm->written, 4));
 	if (rc)
 		goto out;
 
 	do {
 		nread = do_coredump_read(i, ctx, buf, bufsz, &pos);
 		if (nread > 0) {
-			rc = spufs_dump_write(file, buf, nread, foffset);
+			rc = spufs_dump_write(cprm, buf, nread);
 			if (rc)
 				goto out;
 			total += nread;
@@ -213,15 +204,14 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 		goto out;
 	}
 
-	rc = spufs_dump_align(file, buf, roundup(*foffset - total + sz, 4),
-			      foffset);
+	rc = spufs_dump_align(cprm, buf, roundup(cprm->written - total + sz, 4));
 
 out:
 	free_page((unsigned long)buf);
 	return rc;
 }
 
-int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
+int spufs_coredump_extra_notes_write(struct coredump_params *cprm)
 {
 	struct spu_context *ctx;
 	int fd, j, rc;
@@ -233,7 +223,7 @@ int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset)
 			return rc;
 
 		for (j = 0; spufs_coredump_read[j].name != NULL; j++) {
-			rc = spufs_arch_write_note(ctx, j, file, fd, foffset);
+			rc = spufs_arch_write_note(ctx, j, cprm, fd);
 			if (rc) {
 				spu_release_saved(ctx);
 				return rc;
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 67852ade4c01..0ba3c9598358 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -247,12 +247,13 @@ extern const struct spufs_tree_descr spufs_dir_debug_contents[];
 
 /* system call implementation */
 extern struct spufs_calls spufs_calls;
+struct coredump_params;
 long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *status);
 long spufs_create(struct path *nd, struct dentry *dentry, unsigned int flags,
 			umode_t mode, struct file *filp);
 /* ELF coredump callbacks for writing SPU ELF notes */
 extern int spufs_coredump_extra_notes_size(void);
-extern int spufs_coredump_extra_notes_write(struct file *file, loff_t *foffset);
+extern int spufs_coredump_extra_notes_write(struct coredump_params *cprm);
 
 extern const struct file_operations spufs_context_fops;
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index ddab40d3d828..3bf75d767a4a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2037,7 +2037,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	size_t size = 0;
 	struct vm_area_struct *vma, *gate_vma;
 	struct elfhdr *elf = NULL;
-	loff_t offset = 0, dataoff, foffset;
+	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
 	struct elf_phdr *phdr4note = NULL;
 	struct elf_shdr *shdr4extnum = NULL;
@@ -2160,12 +2160,11 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!write_note_info(&info, cprm))
 		goto end_coredump;
 
-	foffset = cprm->written;
-	if (elf_coredump_extra_notes_write(cprm->file, &foffset))
+	if (elf_coredump_extra_notes_write(cprm))
 		goto end_coredump;
 
 	/* Align to page */
-	if (!dump_seek(cprm->file, dataoff - foffset))
+	if (!dump_seek(cprm->file, dataoff - cprm->written))
 		goto end_coredump;
 
 	cprm->written = size;
diff --git a/include/linux/elf.h b/include/linux/elf.h
index 40a3c0e01b2b..67a5fa7830c4 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -39,13 +39,13 @@ extern Elf64_Dyn _DYNAMIC [];
 
 /* Optional callbacks to write extra ELF notes. */
 struct file;
+struct coredump_params;
 
 #ifndef ARCH_HAVE_EXTRA_ELF_NOTES
 static inline int elf_coredump_extra_notes_size(void) { return 0; }
-static inline int elf_coredump_extra_notes_write(struct file *file,
-			loff_t *foffset) { return 0; }
+static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; }
 #else
 extern int elf_coredump_extra_notes_size(void);
-extern int elf_coredump_extra_notes_write(struct file *file, loff_t *foffset);
+extern int elf_coredump_extra_notes_write(struct coredump_params *cprm);
 #endif
 #endif /* _LINUX_ELF_H */
-- 
cgit 


From 9b56d54380adb5fef71f687109bbd6f8413d694f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 8 Oct 2013 09:26:08 -0400
Subject: dump_skip(): dump_seek() replacement taking coredump_params

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/ia32/ia32_aout.c |  2 +-
 fs/binfmt_aout.c          |  2 +-
 fs/binfmt_elf.c           |  4 ++--
 fs/binfmt_elf_fdpic.c     | 11 +++--------
 fs/coredump.c             | 43 ++++++++++++++-----------------------------
 include/linux/coredump.h  |  3 +--
 6 files changed, 22 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 9e26e9e85576..d21ff89207cd 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -187,7 +187,7 @@ static int aout_core_dump(struct coredump_params *cprm)
 	if (!dump_emit(cprm, &dump, sizeof(dump)))
 		goto end_coredump;
 	/* Now dump all of the user data.  Include malloced stuff as well */
-	if (!dump_seek(cprm->file, PAGE_SIZE - sizeof(dump)))
+	if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
 		goto end_coredump;
 	/* now we start writing out the user space info */
 	set_fs(USER_DS);
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index a4f847f77234..ca0ba15a7306 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -87,7 +87,7 @@ static int aout_core_dump(struct coredump_params *cprm)
 	if (!dump_emit(cprm, &dump, sizeof(dump)))
 		goto end_coredump;
 /* Now dump all of the user data.  Include malloced stuff as well */
-	if (!dump_seek(cprm->file, PAGE_SIZE - sizeof(dump)))
+	if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump)))
 		goto end_coredump;
 /* now we start writing out the user space info */
 	set_fs(USER_DS);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 4f7dda9d86b5..c56ae3264a65 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2162,7 +2162,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* Align to page */
-	if (!dump_seek(cprm->file, dataoff - cprm->written))
+	if (!dump_skip(cprm, dataoff - cprm->written))
 		goto end_coredump;
 
 	for (vma = first_vma(current, gate_vma); vma != NULL;
@@ -2183,7 +2183,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				kunmap(page);
 				page_cache_release(page);
 			} else
-				stop = !dump_seek(cprm->file, PAGE_SIZE);
+				stop = !dump_skip(cprm, PAGE_SIZE);
 			if (stop)
 				goto end_coredump;
 		}
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 70e299917898..a69fc4ae1c85 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1509,7 +1509,7 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 				kunmap(page);
 				page_cache_release(page);
 			} else {
-				res = dump_seek(file, PAGE_SIZE);
+				res = dump_skip(cprm, PAGE_SIZE);
 			}
 			if (!res)
 				return false;
@@ -1547,11 +1547,10 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	int has_dumped = 0;
 	mm_segment_t fs;
 	int segs;
-	size_t size = 0;
 	int i;
 	struct vm_area_struct *vma;
 	struct elfhdr *elf = NULL;
-	loff_t offset = 0, dataoff, foffset;
+	loff_t offset = 0, dataoff;
 	int numnote;
 	struct memelfnote *notes = NULL;
 	struct elf_prstatus *prstatus = NULL;	/* NT_PRSTATUS */
@@ -1682,7 +1681,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 
 	offset += sizeof(*elf);				/* Elf header */
 	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
-	foffset = offset;
 
 	/* Write notes phdr entry */
 	{
@@ -1751,8 +1749,6 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
-	size = cprm->written;
-	cprm->written = foffset;
  	/* write out the notes section */
 	for (i = 0; i < numnote; i++)
 		if (!writenote(notes + i, cprm))
@@ -1768,10 +1764,9 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 	}
 
-	if (!dump_seek(cprm->file, dataoff - cprm->written))
+	if (!dump_skip(cprm, dataoff - cprm->written))
 		goto end_coredump;
 
-	cprm->written = size;
 	if (!elf_fdpic_dump_segments(cprm))
 		goto end_coredump;
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 2472ed9e682c..18baf2c009d4 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -685,14 +685,6 @@ fail:
  * do on a core-file: use only these functions to write out all the
  * necessary info.
  */
-int dump_write(struct file *file, const void *addr, int nr)
-{
-	return !dump_interrupted() &&
-		access_ok(VERIFY_READ, addr, nr) &&
-		file->f_op->write(file, addr, nr, &file->f_pos) == nr;
-}
-EXPORT_SYMBOL(dump_write);
-
 int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 {
 	struct file *file = cprm->file;
@@ -714,32 +706,25 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 }
 EXPORT_SYMBOL(dump_emit);
 
-int dump_seek(struct file *file, loff_t off)
+int dump_skip(struct coredump_params *cprm, size_t nr)
 {
-	int ret = 1;
-
+	static char zeroes[PAGE_SIZE];
+	struct file *file = cprm->file;
 	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (cprm->written + nr > cprm->limit)
+			return 0;
 		if (dump_interrupted() ||
-		    file->f_op->llseek(file, off, SEEK_CUR) < 0)
+		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
+		cprm->written += nr;
+		return 1;
 	} else {
-		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
-
-		if (!buf)
-			return 0;
-		while (off > 0) {
-			unsigned long n = off;
-
-			if (n > PAGE_SIZE)
-				n = PAGE_SIZE;
-			if (!dump_write(file, buf, n)) {
-				ret = 0;
-				break;
-			}
-			off -= n;
+		while (nr > PAGE_SIZE) {
+			if (!dump_emit(cprm, zeroes, PAGE_SIZE))
+				return 0;
+			nr -= PAGE_SIZE;
 		}
-		free_page((unsigned long)buf);
+		return dump_emit(cprm, zeroes, nr);
 	}
-	return ret;
 }
-EXPORT_SYMBOL(dump_seek);
+EXPORT_SYMBOL(dump_skip);
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 2959376a9ad5..07a0af93f230 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -11,8 +11,7 @@
  * functions to write out all the necessary info.
  */
 struct coredump_params;
-extern int dump_write(struct file *file, const void *addr, int nr);
-extern int dump_seek(struct file *file, loff_t off);
+extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(siginfo_t *siginfo);
-- 
cgit 


From 22a8cb8248ba5d340307ba72432253b1dbdb5cf7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 8 Oct 2013 11:05:01 -0400
Subject: new helper: dump_align()

dump_skip to given alignment...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/platforms/cell/spufs/coredump.c |  2 +-
 fs/binfmt_elf.c                              | 10 ++--------
 fs/binfmt_elf_fdpic.c                        | 10 ++--------
 fs/coredump.c                                |  9 +++++++++
 include/linux/coredump.h                     |  1 +
 5 files changed, 15 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 1aaaa586fa50..be6212ddbf06 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -156,7 +156,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	if (!dump_emit(cprm, fullname, en.n_namesz))
 		goto Eio;
 
-	if (!dump_skip(cprm, roundup(cprm->written, 4) - cprm->written))
+	if (!dump_align(cprm, 4))
 		goto Eio;
 
 	do {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c56ae3264a65..864154972670 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1225,12 +1225,6 @@ static int notesize(struct memelfnote *en)
 	return sz;
 }
 
-static int alignfile(struct coredump_params *cprm)
-{
-	static const char buf[4] = { 0, };
-	return dump_emit(cprm, buf, roundup(cprm->written, 4) - cprm->written);
-}
-
 static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 {
 	struct elf_note en;
@@ -1239,8 +1233,8 @@ static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 	en.n_type = men->type;
 
 	return dump_emit(cprm, &en, sizeof(en)) &&
-	    dump_emit(cprm, men->name, en.n_namesz) && alignfile(cprm) &&
-	    dump_emit(cprm, men->data, men->datasz) && alignfile(cprm);
+	    dump_emit(cprm, men->name, en.n_namesz) && dump_align(cprm, 4) &&
+	    dump_emit(cprm, men->data, men->datasz) && dump_align(cprm, 4);
 }
 
 static void fill_elf_header(struct elfhdr *elf, int segs,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index a69fc4ae1c85..645f6e56f378 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1267,12 +1267,6 @@ static int notesize(struct memelfnote *en)
 
 /* #define DEBUG */
 
-static int alignfile(struct coredump_params *cprm)
-{
-	static const char buf[4] = { 0, };
-	return dump_emit(cprm, buf, roundup(cprm->written, 4) - cprm->written);
-}
-
 static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 {
 	struct elf_note en;
@@ -1281,8 +1275,8 @@ static int writenote(struct memelfnote *men, struct coredump_params *cprm)
 	en.n_type = men->type;
 
 	return dump_emit(cprm, &en, sizeof(en)) &&
-		dump_emit(cprm, men->name, en.n_namesz) && alignfile(cprm) &&
-		dump_emit(cprm, men->data, men->datasz) && alignfile(cprm);
+		dump_emit(cprm, men->name, en.n_namesz) && dump_align(cprm, 4) &&
+		dump_emit(cprm, men->data, men->datasz) && dump_align(cprm, 4);
 }
 
 static inline void fill_elf_fdpic_header(struct elfhdr *elf, int segs)
diff --git a/fs/coredump.c b/fs/coredump.c
index 18baf2c009d4..dc1f937413d5 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -728,3 +728,12 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
 	}
 }
 EXPORT_SYMBOL(dump_skip);
+
+int dump_align(struct coredump_params *cprm, int align)
+{
+	unsigned mod = cprm->written & (align - 1);
+	if (align & (align - 1))
+		return -EINVAL;
+	return mod ? dump_skip(cprm, align - mod) : 0;
+}
+EXPORT_SYMBOL(dump_align);
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 07a0af93f230..d8eb880be82a 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -13,6 +13,7 @@
 struct coredump_params;
 extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
+extern int dump_align(struct coredump_params *cprm, int align);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(siginfo_t *siginfo);
 #else
-- 
cgit 


From 6987843ff7e836ea65b554905aec34d2fad05c94 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Oct 2013 22:35:11 -0400
Subject: take anon inode allocation to libfs.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/anon_inodes.c   | 50 ++------------------------------------------------
 fs/libfs.c         | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  1 +
 3 files changed, 46 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 85c961849953..22f9698a1214 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -24,7 +24,6 @@
 
 static struct vfsmount *anon_inode_mnt __read_mostly;
 static struct inode *anon_inode_inode;
-static const struct file_operations anon_inode_fops;
 
 /*
  * anon_inodefs_dname() is called from d_path().
@@ -39,51 +38,6 @@ static const struct dentry_operations anon_inodefs_dentry_operations = {
 	.d_dname	= anon_inodefs_dname,
 };
 
-/*
- * nop .set_page_dirty method so that people can use .page_mkwrite on
- * anon inodes.
- */
-static int anon_set_page_dirty(struct page *page)
-{
-	return 0;
-};
-
-static const struct address_space_operations anon_aops = {
-	.set_page_dirty = anon_set_page_dirty,
-};
-
-/*
- * A single inode exists for all anon_inode files. Contrary to pipes,
- * anon_inode inodes have no associated per-instance data, so we need
- * only allocate one of them.
- */
-static struct inode *anon_inode_mkinode(struct super_block *s)
-{
-	struct inode *inode = new_inode_pseudo(s);
-
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
-
-	inode->i_ino = get_next_ino();
-	inode->i_fop = &anon_inode_fops;
-
-	inode->i_mapping->a_ops = &anon_aops;
-
-	/*
-	 * Mark the inode dirty from the very beginning,
-	 * that way it will never be moved to the dirty
-	 * list because mark_inode_dirty() will think
-	 * that it already _is_ on the dirty list.
-	 */
-	inode->i_state = I_DIRTY;
-	inode->i_mode = S_IRUSR | S_IWUSR;
-	inode->i_uid = current_fsuid();
-	inode->i_gid = current_fsgid();
-	inode->i_flags |= S_PRIVATE;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	return inode;
-}
-
 static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
@@ -92,7 +46,7 @@ static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
 			&anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
 	if (!IS_ERR(root)) {
 		struct super_block *s = root->d_sb;
-		anon_inode_inode = anon_inode_mkinode(s);
+		anon_inode_inode = alloc_anon_inode(s);
 		if (IS_ERR(anon_inode_inode)) {
 			dput(root);
 			deactivate_locked_super(s);
@@ -134,7 +88,7 @@ struct file *anon_inode_getfile_private(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	inode = anon_inode_mkinode(anon_inode_mnt->mnt_sb);
+	inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
 	if (IS_ERR(inode)) {
 		file = ERR_PTR(-ENOMEM);
 		goto err_module;
diff --git a/fs/libfs.c b/fs/libfs.c
index 8c5018493154..5de06947ba5e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1002,3 +1002,46 @@ void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
 		kfree(s);
 }
 EXPORT_SYMBOL(kfree_put_link);
+
+/*
+ * nop .set_page_dirty method so that people can use .page_mkwrite on
+ * anon inodes.
+ */
+static int anon_set_page_dirty(struct page *page)
+{
+	return 0;
+};
+
+/*
+ * A single inode exists for all anon_inode files. Contrary to pipes,
+ * anon_inode inodes have no associated per-instance data, so we need
+ * only allocate one of them.
+ */
+struct inode *alloc_anon_inode(struct super_block *s)
+{
+	static const struct address_space_operations anon_aops = {
+		.set_page_dirty = anon_set_page_dirty,
+	};
+	struct inode *inode = new_inode_pseudo(s);
+
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_ino = get_next_ino();
+	inode->i_mapping->a_ops = &anon_aops;
+
+	/*
+	 * Mark the inode dirty from the very beginning,
+	 * that way it will never be moved to the dirty
+	 * list because mark_inode_dirty() will think
+	 * that it already _is_ on the dirty list.
+	 */
+	inode->i_state = I_DIRTY;
+	inode->i_mode = S_IRUSR | S_IWUSR;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_flags |= S_PRIVATE;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	return inode;
+}
+EXPORT_SYMBOL(alloc_anon_inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2b0f4e974480..e190326ac212 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2562,6 +2562,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata);
+extern struct inode *alloc_anon_inode(struct super_block *);
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
-- 
cgit 


From 078d8e624c1837aa8ad65e58054a4a40d7ac46d2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 9 Oct 2013 10:26:28 -0400
Subject: ... and kill anon_inode_getfile_private()

it's a seriously misguided API, now fortunately without users.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/anon_inodes.c            | 66 ---------------------------------------------
 include/linux/anon_inodes.h |  3 ---
 2 files changed, 69 deletions(-)

(limited to 'include')

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 22f9698a1214..24084732b1d0 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -62,72 +62,6 @@ static struct file_system_type anon_inode_fs_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-/**
- * anon_inode_getfile_private - creates a new file instance by hooking it up to an
- *                      anonymous inode, and a dentry that describe the "class"
- *                      of the file
- *
- * @name:    [in]    name of the "class" of the new file
- * @fops:    [in]    file operations for the new file
- * @priv:    [in]    private data for the new file (will be file's private_data)
- * @flags:   [in]    flags
- *
- *
- * Similar to anon_inode_getfile, but each file holds a single inode.
- *
- */
-struct file *anon_inode_getfile_private(const char *name,
-					const struct file_operations *fops,
-					void *priv, int flags)
-{
-	struct qstr this;
-	struct path path;
-	struct file *file;
-	struct inode *inode;
-
-	if (fops->owner && !try_module_get(fops->owner))
-		return ERR_PTR(-ENOENT);
-
-	inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
-	if (IS_ERR(inode)) {
-		file = ERR_PTR(-ENOMEM);
-		goto err_module;
-	}
-
-	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
-
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file))
-		goto err_dput;
-
-	file->f_mapping = inode->i_mapping;
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
-	file->private_data = priv;
-
-	return file;
-
-err_dput:
-	path_put(&path);
-err_module:
-	module_put(fops->owner);
-	return file;
-}
-EXPORT_SYMBOL_GPL(anon_inode_getfile_private);
-
 /**
  * anon_inode_getfile - creates a new file instance by hooking it up to an
  *                      anonymous inode, and a dentry that describe the "class"
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index cf573c22b81e..8013a45242fe 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -13,9 +13,6 @@ struct file_operations;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_private(const char *name,
-				const struct file_operations *fops,
-				void *priv, int flags);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
 
-- 
cgit 


From ce3959604878c1c693979ec552069dc8bdb5ccde Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 13 Oct 2013 17:23:53 -0400
Subject: constify copy_siginfo_to_user{,32}()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/kernel/signal32.c     | 2 +-
 arch/ia64/kernel/signal.c        | 2 +-
 arch/mips/kernel/signal32.c      | 2 +-
 arch/parisc/kernel/signal32.c    | 2 +-
 arch/parisc/kernel/signal32.h    | 2 +-
 arch/powerpc/kernel/signal_32.c  | 2 +-
 arch/s390/kernel/compat_signal.c | 2 +-
 arch/sparc/kernel/signal32.c     | 2 +-
 arch/tile/kernel/compat_signal.c | 2 +-
 arch/x86/ia32/ia32_signal.c      | 2 +-
 fs/binfmt_elf.c                  | 2 +-
 include/asm-generic/siginfo.h    | 2 +-
 include/linux/compat.h           | 2 +-
 kernel/signal.c                  | 2 +-
 14 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e393174fe859..07da8c0fde2e 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -150,7 +150,7 @@ static inline int get_sigset_t(sigset_t *set,
 	return 0;
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 3637e03d2282..33cab9a8adff 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -105,7 +105,7 @@ restore_sigcontext (struct sigcontext __user *sc, struct sigscratch *scr)
 }
 
 int
-copy_siginfo_to_user (siginfo_t __user *to, siginfo_t *from)
+copy_siginfo_to_user (siginfo_t __user *to, const siginfo_t *from)
 {
 	if (!access_ok(VERIFY_WRITE, to, sizeof(siginfo_t)))
 		return -EFAULT;
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 57de8b751627..1905a419aa46 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -314,7 +314,7 @@ SYSCALL_DEFINE3(32_sigaction, long, sig, const struct compat_sigaction __user *,
 	return ret;
 }
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 
diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c
index 6c6a271a6140..984abbee71ca 100644
--- a/arch/parisc/kernel/signal32.c
+++ b/arch/parisc/kernel/signal32.c
@@ -319,7 +319,7 @@ copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from)
 }
 
 int
-copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from)
+copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	compat_uptr_t addr;
 	compat_int_t val;
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index 72ab41a51f32..af51d4ccee42 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -34,7 +34,7 @@ struct compat_ucontext {
 
 /* ELF32 signal handling */
 
-int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from);
+int copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from);
 int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from);
 
 /* In a deft move of uber-hackery, we decide to carry the top half of all
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index bebdf1a1a540..149cd583d061 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -891,7 +891,7 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 #endif
 
 #ifdef CONFIG_PPC64
-int copy_siginfo_to_user32(struct compat_siginfo __user *d, siginfo_t *s)
+int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
 {
 	int err;
 
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 1389b637dae5..44b25269a970 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -49,7 +49,7 @@ typedef struct
 	__u32 gprs_high[NUM_GPRS];
 } rt_sigframe32;
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index b524f91dd0e5..ee789d2ef05d 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -68,7 +68,7 @@ struct rt_signal_frame32 {
 	/* __siginfo_rwin_t * */u32 rwin_save;
 } __attribute__((aligned(8)));
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 85e00b2f39bf..19c04b5ce408 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -49,7 +49,7 @@ struct compat_rt_sigframe {
 	struct compat_ucontext uc;
 };
 
-int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from)
 {
 	int err;
 
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 665a730307f2..220675795e08 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -34,7 +34,7 @@
 #include <asm/sys_ia32.h>
 #include <asm/smap.h>
 
-int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err = 0;
 	bool ia32 = test_thread_flag(TIF_IA32);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 864154972670..a6f8cb498b0e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1374,7 +1374,7 @@ static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
 }
 
 static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
-		siginfo_t *siginfo)
+		const siginfo_t *siginfo)
 {
 	mm_segment_t old_fs = get_fs();
 	set_fs(KERNEL_DS);
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index b685d3bd32e2..3d1a3af5cf59 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -32,6 +32,6 @@ static inline void copy_siginfo(struct siginfo *to, struct siginfo *from)
 
 #endif
 
-extern int copy_siginfo_to_user(struct siginfo __user *to, struct siginfo *from);
+extern int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from);
 
 #endif
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 345da00a86e0..78cdf51ff5ba 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -362,7 +362,7 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
 long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
 		       unsigned long bitmap_size);
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from);
-int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from);
+int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from);
 int get_compat_sigevent(struct sigevent *event,
 		const struct compat_sigevent __user *u_event);
 long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
diff --git a/kernel/signal.c b/kernel/signal.c
index ded28b91fa53..940b30ee9a30 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2723,7 +2723,7 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset,
 
 #ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER
 
-int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
+int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
 
-- 
cgit 


From ec57941e031685de434916e5398d0ca1d44cd374 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 13 Oct 2013 17:57:29 -0400
Subject: constify do_coredump() argument

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/binfmt_elf.c          | 4 ++--
 fs/coredump.c            | 2 +-
 include/linux/binfmts.h  | 2 +-
 include/linux/coredump.h | 4 ++--
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a6f8cb498b0e..1af412b96e06 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1581,7 +1581,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,
 			  struct elf_note_info *info,
-			  siginfo_t *siginfo, struct pt_regs *regs)
+			  const siginfo_t *siginfo, struct pt_regs *regs)
 {
 	struct task_struct *dump_task = current;
 	const struct user_regset_view *view = task_user_regset_view(dump_task);
@@ -1830,7 +1830,7 @@ static int elf_note_info_init(struct elf_note_info *info)
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,
 			  struct elf_note_info *info,
-			  siginfo_t *siginfo, struct pt_regs *regs)
+			  const siginfo_t *siginfo, struct pt_regs *regs)
 {
 	struct list_head *t;
 
diff --git a/fs/coredump.c b/fs/coredump.c
index dc1f937413d5..62406b6959b6 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -485,7 +485,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 	return err;
 }
 
-void do_coredump(siginfo_t *siginfo)
+void do_coredump(const siginfo_t *siginfo)
 {
 	struct core_state core_state;
 	struct core_name cn;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 8aa507e7a41a..790d3305a5a7 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -56,7 +56,7 @@ struct linux_binprm {
 
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
-	siginfo_t *siginfo;
+	const siginfo_t *siginfo;
 	struct pt_regs *regs;
 	struct file *file;
 	unsigned long limit;
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index d8eb880be82a..d016a121a8c4 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -15,9 +15,9 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 #ifdef CONFIG_COREDUMP
-extern void do_coredump(siginfo_t *siginfo);
+extern void do_coredump(const siginfo_t *siginfo);
 #else
-static inline void do_coredump(siginfo_t *siginfo) {}
+static inline void do_coredump(const siginfo_t *siginfo) {}
 #endif
 
 #endif /* _LINUX_COREDUMP_H */
-- 
cgit 


From b18825a7c8e37a7cf6abb97a12a6ad71af160de7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 12 Sep 2013 19:22:53 +0100
Subject: VFS: Put a small type field into struct dentry::d_flags

Put a type field into struct dentry::d_flags to indicate if the dentry is one
of the following types that relate particularly to pathwalk:

	Miss (negative dentry)
	Directory
	"Automount" directory (defective - no i_op->lookup())
	Symlink
	Other (regular, socket, fifo, device)

The type field is set to one of the first five types on a dentry by calls to
__d_instantiate() and d_obtain_alias() from information in the inode (if one is
given).

The type is cleared by dentry_unlink_inode() when it reconstitutes an existing
dentry as a negative dentry.

Accessors provided are:

	d_set_type(dentry, type)
	d_is_directory(dentry)
	d_is_autodir(dentry)
	d_is_symlink(dentry)
	d_is_file(dentry)
	d_is_negative(dentry)
	d_is_positive(dentry)

A bunch of checks in pathname resolution switched to those.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            |  42 +++++++++++++++++---
 fs/namei.c             |  95 ++++++++++++++++++---------------------------
 include/linux/dcache.h | 103 +++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 158 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index fb7bcf3ba5d6..525770e576db 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -343,6 +343,7 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
+	__d_clear_type(dentry);
 	dentry->d_inode = NULL;
 	hlist_del_init(&dentry->d_alias);
 	dentry_rcuwalk_barrier(dentry);
@@ -1648,14 +1649,42 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 }
 EXPORT_SYMBOL(d_set_d_op);
 
+static unsigned d_flags_for_inode(struct inode *inode)
+{
+	unsigned add_flags = DCACHE_FILE_TYPE;
+
+	if (!inode)
+		return DCACHE_MISS_TYPE;
+
+	if (S_ISDIR(inode->i_mode)) {
+		add_flags = DCACHE_DIRECTORY_TYPE;
+		if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) {
+			if (unlikely(!inode->i_op->lookup))
+				add_flags = DCACHE_AUTODIR_TYPE;
+			else
+				inode->i_opflags |= IOP_LOOKUP;
+		}
+	} else if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
+		if (unlikely(inode->i_op->follow_link))
+			add_flags = DCACHE_SYMLINK_TYPE;
+		else
+			inode->i_opflags |= IOP_NOFOLLOW;
+	}
+
+	if (unlikely(IS_AUTOMOUNT(inode)))
+		add_flags |= DCACHE_NEED_AUTOMOUNT;
+	return add_flags;
+}
+
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
+	unsigned add_flags = d_flags_for_inode(inode);
+
 	spin_lock(&dentry->d_lock);
-	if (inode) {
-		if (unlikely(IS_AUTOMOUNT(inode)))
-			dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
+	dentry->d_flags &= ~DCACHE_ENTRY_TYPE;
+	dentry->d_flags |= add_flags;
+	if (inode)
 		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
-	}
 	dentry->d_inode = inode;
 	dentry_rcuwalk_barrier(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -1860,6 +1889,7 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	static const struct qstr anonstring = QSTR_INIT("/", 1);
 	struct dentry *tmp;
 	struct dentry *res;
+	unsigned add_flags;
 
 	if (!inode)
 		return ERR_PTR(-ESTALE);
@@ -1885,9 +1915,11 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	}
 
 	/* attach a disconnected dentry */
+	add_flags = d_flags_for_inode(inode) | DCACHE_DISCONNECTED;
+
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
-	tmp->d_flags |= DCACHE_DISCONNECTED;
+	tmp->d_flags |= add_flags;
 	hlist_add_head(&tmp->d_alias, &inode->i_dentry);
 	hlist_bl_lock(&tmp->d_sb->s_anon);
 	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
diff --git a/fs/namei.c b/fs/namei.c
index e5c0118ba9f8..e1fa43346c61 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1501,18 +1501,9 @@ static void terminate_walk(struct nameidata *nd)
  * so we keep a cache of "no, this doesn't need follow_link"
  * for the common case.
  */
-static inline int should_follow_link(struct inode *inode, int follow)
+static inline int should_follow_link(struct dentry *dentry, int follow)
 {
-	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
-		if (likely(inode->i_op->follow_link))
-			return follow;
-
-		/* This gets set once for the inode lifetime */
-		spin_lock(&inode->i_lock);
-		inode->i_opflags |= IOP_NOFOLLOW;
-		spin_unlock(&inode->i_lock);
-	}
-	return 0;
+	return unlikely(d_is_symlink(dentry)) ? follow : 0;
 }
 
 static inline int walk_component(struct nameidata *nd, struct path *path,
@@ -1542,7 +1533,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 	if (!inode)
 		goto out_path_put;
 
-	if (should_follow_link(inode, follow)) {
+	if (should_follow_link(path->dentry, follow)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
 				err = -ECHILD;
@@ -1600,26 +1591,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 	return res;
 }
 
-/*
- * We really don't want to look at inode->i_op->lookup
- * when we don't have to. So we keep a cache bit in
- * the inode ->i_opflags field that says "yes, we can
- * do lookup on this inode".
- */
-static inline int can_lookup(struct inode *inode)
-{
-	if (likely(inode->i_opflags & IOP_LOOKUP))
-		return 1;
-	if (likely(!inode->i_op->lookup))
-		return 0;
-
-	/* We do this once for the lifetime of the inode */
-	spin_lock(&inode->i_lock);
-	inode->i_opflags |= IOP_LOOKUP;
-	spin_unlock(&inode->i_lock);
-	return 1;
-}
-
 /*
  * We can do the critical dentry name comparison and hashing
  * operations one word at a time, but we are limited to:
@@ -1823,7 +1794,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
-		if (!can_lookup(nd->inode)) {
+		if (!d_is_directory(nd->path.dentry)) {
 			err = -ENOTDIR; 
 			break;
 		}
@@ -1841,9 +1812,10 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	nd->flags = flags | LOOKUP_JUMPED;
 	nd->depth = 0;
 	if (flags & LOOKUP_ROOT) {
-		struct inode *inode = nd->root.dentry->d_inode;
+		struct dentry *root = nd->root.dentry;
+		struct inode *inode = root->d_inode;
 		if (*name) {
-			if (!can_lookup(inode))
+			if (!d_is_directory(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1899,7 +1871,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!can_lookup(dentry->d_inode)) {
+			if (!d_is_directory(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
@@ -1981,7 +1953,7 @@ static int path_lookupat(int dfd, const char *name,
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!can_lookup(nd->inode)) {
+		if (!d_is_directory(nd->path.dentry)) {
 			path_put(&nd->path);
 			err = -ENOTDIR;
 		}
@@ -2273,7 +2245,7 @@ done:
 	}
 	path->dentry = dentry;
 	path->mnt = mntget(nd->path.mnt);
-	if (should_follow_link(dentry->d_inode, nd->flags & LOOKUP_FOLLOW))
+	if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
 		return 1;
 	follow_mount(path);
 	error = 0;
@@ -2417,12 +2389,14 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
  * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
  *     nfs_async_unlink().
  */
-static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
+static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 {
+	struct inode *inode = victim->d_inode;
 	int error;
 
-	if (!victim->d_inode)
+	if (d_is_negative(victim))
 		return -ENOENT;
+	BUG_ON(!inode);
 
 	BUG_ON(victim->d_parent->d_inode != dir);
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
@@ -2432,15 +2406,16 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
 		return error;
 	if (IS_APPEND(dir))
 		return -EPERM;
-	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
-	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
+
+	if (check_sticky(dir, inode) || IS_APPEND(inode) ||
+	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
-		if (!S_ISDIR(victim->d_inode->i_mode))
+		if (!d_is_directory(victim) && !d_is_autodir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (S_ISDIR(victim->d_inode->i_mode))
+	} else if (d_is_directory(victim) || d_is_autodir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
@@ -2974,7 +2949,7 @@ retry_lookup:
 	/*
 	 * create/update audit record if it already exists.
 	 */
-	if (path->dentry->d_inode)
+	if (d_is_positive(path->dentry))
 		audit_inode(name, path->dentry, 0);
 
 	/*
@@ -3003,12 +2978,12 @@ retry_lookup:
 finish_lookup:
 	/* we _can_ be in RCU mode here */
 	error = -ENOENT;
-	if (!inode) {
+	if (d_is_negative(path->dentry)) {
 		path_to_nameidata(path, nd);
 		goto out;
 	}
 
-	if (should_follow_link(inode, !symlink_ok)) {
+	if (should_follow_link(path->dentry, !symlink_ok)) {
 		if (nd->flags & LOOKUP_RCU) {
 			if (unlikely(unlazy_walk(nd, path->dentry))) {
 				error = -ECHILD;
@@ -3037,10 +3012,11 @@ finish_open:
 	}
 	audit_inode(name, nd->path.dentry, 0);
 	error = -EISDIR;
-	if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
+	if ((open_flag & O_CREAT) &&
+	    (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
 		goto out;
 	error = -ENOTDIR;
-	if ((nd->flags & LOOKUP_DIRECTORY) && !can_lookup(nd->inode))
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
 		goto out;
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -3266,7 +3242,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	nd.root.mnt = mnt;
 	nd.root.dentry = dentry;
 
-	if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
+	if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
 		return ERR_PTR(-ELOOP);
 
 	file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_RCU);
@@ -3316,8 +3292,9 @@ struct dentry *kern_path_create(int dfd, const char *pathname,
 		goto unlock;
 
 	error = -EEXIST;
-	if (dentry->d_inode)
+	if (d_is_positive(dentry))
 		goto fail;
+
 	/*
 	 * Special case - lookup gave negative, but... we had foo/bar/
 	 * From the vfs_mknod() POV we just have a negative dentry -
@@ -3706,7 +3683,7 @@ retry:
 		if (nd.last.name[nd.last.len])
 			goto slashes;
 		inode = dentry->d_inode;
-		if (!inode)
+		if (d_is_negative(dentry))
 			goto slashes;
 		ihold(inode);
 		error = security_path_unlink(&nd.path, dentry);
@@ -3731,8 +3708,12 @@ exit1:
 	return error;
 
 slashes:
-	error = !dentry->d_inode ? -ENOENT :
-		S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
+	if (d_is_negative(dentry))
+		error = -ENOENT;
+	else if (d_is_directory(dentry) || d_is_autodir(dentry))
+		error = -EISDIR;
+	else
+		error = -ENOTDIR;
 	goto exit2;
 }
 
@@ -4046,7 +4027,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	       struct inode *new_dir, struct dentry *new_dentry)
 {
 	int error;
-	int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
+	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
 	const unsigned char *old_name;
 
 	if (old_dentry->d_inode == new_dentry->d_inode)
@@ -4134,10 +4115,10 @@ retry:
 		goto exit3;
 	/* source must exist */
 	error = -ENOENT;
-	if (!old_dentry->d_inode)
+	if (d_is_negative(old_dentry))
 		goto exit4;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!S_ISDIR(old_dentry->d_inode->i_mode)) {
+	if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit4;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 716c3760ee39..57e87e749a48 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -169,13 +169,13 @@ struct dentry_operations {
  */
 
 /* d_flags entries */
-#define DCACHE_OP_HASH		0x0001
-#define DCACHE_OP_COMPARE	0x0002
-#define DCACHE_OP_REVALIDATE	0x0004
-#define DCACHE_OP_DELETE	0x0008
-#define DCACHE_OP_PRUNE         0x0010
+#define DCACHE_OP_HASH			0x00000001
+#define DCACHE_OP_COMPARE		0x00000002
+#define DCACHE_OP_REVALIDATE		0x00000004
+#define DCACHE_OP_DELETE		0x00000008
+#define DCACHE_OP_PRUNE			0x00000010
 
-#define	DCACHE_DISCONNECTED	0x0020
+#define	DCACHE_DISCONNECTED		0x00000020
      /* This dentry is possibly not currently connected to the dcache tree, in
       * which case its parent will either be itself, or will have this flag as
       * well.  nfsd will not use a dentry with this bit set, but will first
@@ -186,30 +186,38 @@ struct dentry_operations {
       * dentry into place and return that dentry rather than the passed one,
       * typically using d_splice_alias. */
 
-#define DCACHE_REFERENCED	0x0040  /* Recently used, don't discard. */
-#define DCACHE_RCUACCESS	0x0080	/* Entry has ever been RCU-visible */
+#define DCACHE_REFERENCED		0x00000040 /* Recently used, don't discard. */
+#define DCACHE_RCUACCESS		0x00000080 /* Entry has ever been RCU-visible */
 
-#define DCACHE_CANT_MOUNT	0x0100
-#define DCACHE_GENOCIDE		0x0200
-#define DCACHE_SHRINK_LIST	0x0400
+#define DCACHE_CANT_MOUNT		0x00000100
+#define DCACHE_GENOCIDE			0x00000200
+#define DCACHE_SHRINK_LIST		0x00000400
 
-#define DCACHE_OP_WEAK_REVALIDATE	0x0800
+#define DCACHE_OP_WEAK_REVALIDATE	0x00000800
 
-#define DCACHE_NFSFS_RENAMED	0x1000
+#define DCACHE_NFSFS_RENAMED		0x00001000
      /* this dentry has been "silly renamed" and has to be deleted on the last
       * dput() */
-#define DCACHE_COOKIE		0x2000	/* For use by dcookie subsystem */
-#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x4000
+#define DCACHE_COOKIE			0x00002000 /* For use by dcookie subsystem */
+#define DCACHE_FSNOTIFY_PARENT_WATCHED	0x00004000
      /* Parent inode is watched by some fsnotify listener */
 
-#define DCACHE_MOUNTED		0x10000	/* is a mountpoint */
-#define DCACHE_NEED_AUTOMOUNT	0x20000	/* handle automount on this dir */
-#define DCACHE_MANAGE_TRANSIT	0x40000	/* manage transit from this dirent */
+#define DCACHE_DENTRY_KILLED		0x00008000
+
+#define DCACHE_MOUNTED			0x00010000 /* is a mountpoint */
+#define DCACHE_NEED_AUTOMOUNT		0x00020000 /* handle automount on this dir */
+#define DCACHE_MANAGE_TRANSIT		0x00040000 /* manage transit from this dirent */
 #define DCACHE_MANAGED_DENTRY \
 	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
 
-#define DCACHE_LRU_LIST		0x80000
-#define DCACHE_DENTRY_KILLED	0x100000
+#define DCACHE_LRU_LIST			0x00080000
+
+#define DCACHE_ENTRY_TYPE		0x00700000
+#define DCACHE_MISS_TYPE		0x00000000 /* Negative dentry */
+#define DCACHE_DIRECTORY_TYPE		0x00100000 /* Normal directory */
+#define DCACHE_AUTODIR_TYPE		0x00200000 /* Lookupless directory (presumed automount) */
+#define DCACHE_SYMLINK_TYPE		0x00300000 /* Symlink */
+#define DCACHE_FILE_TYPE		0x00400000 /* Other file type */
 
 extern seqlock_t rename_lock;
 
@@ -394,6 +402,61 @@ static inline bool d_mountpoint(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_MOUNTED;
 }
 
+/*
+ * Directory cache entry type accessor functions.
+ */
+static inline void __d_set_type(struct dentry *dentry, unsigned type)
+{
+	dentry->d_flags = (dentry->d_flags & ~DCACHE_ENTRY_TYPE) | type;
+}
+
+static inline void __d_clear_type(struct dentry *dentry)
+{
+	__d_set_type(dentry, DCACHE_MISS_TYPE);
+}
+
+static inline void d_set_type(struct dentry *dentry, unsigned type)
+{
+	spin_lock(&dentry->d_lock);
+	__d_set_type(dentry, type);
+	spin_unlock(&dentry->d_lock);
+}
+
+static inline unsigned __d_entry_type(const struct dentry *dentry)
+{
+	return dentry->d_flags & DCACHE_ENTRY_TYPE;
+}
+
+static inline bool d_is_directory(const struct dentry *dentry)
+{
+	return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
+}
+
+static inline bool d_is_autodir(const struct dentry *dentry)
+{
+	return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
+}
+
+static inline bool d_is_symlink(const struct dentry *dentry)
+{
+	return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;
+}
+
+static inline bool d_is_file(const struct dentry *dentry)
+{
+	return __d_entry_type(dentry) == DCACHE_FILE_TYPE;
+}
+
+static inline bool d_is_negative(const struct dentry *dentry)
+{
+	return __d_entry_type(dentry) == DCACHE_MISS_TYPE;
+}
+
+static inline bool d_is_positive(const struct dentry *dentry)
+{
+	return !d_is_negative(dentry);
+}
+
 extern int sysctl_vfs_cache_pressure;
 
 static inline unsigned long vfs_pressure_ratio(unsigned long val)
-- 
cgit 


From b7a6ec52dd4eced4a9bcda9ca85b3c8af84d3c90 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Wed, 2 Oct 2013 17:01:18 -0400
Subject: vfs: split out vfs_getattr_nosec

The filehandle lookup code wants this version of getattr.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c          | 31 +++++++++++++++++++++++++------
 include/linux/fs.h |  1 +
 2 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/stat.c b/fs/stat.c
index d0ea7ef75e26..ae0c3cef9927 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -37,14 +37,21 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 
 EXPORT_SYMBOL(generic_fillattr);
 
-int vfs_getattr(struct path *path, struct kstat *stat)
+/**
+ * vfs_getattr_nosec - getattr without security checks
+ * @path: file to get attributes from
+ * @stat: structure to return attributes in
+ *
+ * Get attributes without calling security_inode_getattr.
+ *
+ * Currently the only caller other than vfs_getattr is internal to the
+ * filehandle lookup code, which uses only the inode number and returns
+ * no attributes to any user.  Any other code probably wants
+ * vfs_getattr.
+ */
+int vfs_getattr_nosec(struct path *path, struct kstat *stat)
 {
 	struct inode *inode = path->dentry->d_inode;
-	int retval;
-
-	retval = security_inode_getattr(path->mnt, path->dentry);
-	if (retval)
-		return retval;
 
 	if (inode->i_op->getattr)
 		return inode->i_op->getattr(path->mnt, path->dentry, stat);
@@ -53,6 +60,18 @@ int vfs_getattr(struct path *path, struct kstat *stat)
 	return 0;
 }
 
+EXPORT_SYMBOL(vfs_getattr_nosec);
+
+int vfs_getattr(struct path *path, struct kstat *stat)
+{
+	int retval;
+
+	retval = security_inode_getattr(path->mnt, path->dentry);
+	if (retval)
+		return retval;
+	return vfs_getattr_nosec(path, stat);
+}
+
 EXPORT_SYMBOL(vfs_getattr);
 
 int vfs_fstat(unsigned int fd, struct kstat *stat)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e190326ac212..5e44b0893db8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2504,6 +2504,7 @@ extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
 extern int generic_readlink(struct dentry *, char __user *, int);
 extern void generic_fillattr(struct inode *, struct kstat *);
+int vfs_getattr_nosec(struct path *path, struct kstat *stat);
 extern int vfs_getattr(struct path *, struct kstat *);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
 void inode_add_bytes(struct inode *inode, loff_t bytes);
-- 
cgit 


From 375e289ea85166c5241c570940e7e7e966c63a9f Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Wed, 18 Apr 2012 15:16:33 -0400
Subject: vfs: pull ext4's double-i_mutex-locking into common code

We want to do this elsewhere as well.

Also catch any attempts to use it for directories (where this ordering
would conflict with ancestor-first directory ordering in lock_rename).

Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Dave Chinner <david@fromorbit.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Acked-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ext4/ext4.h        |  2 --
 fs/ext4/ioctl.c       |  4 ++--
 fs/ext4/move_extent.c | 40 ++--------------------------------------
 fs/inode.c            | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/fs.h    |  3 +++
 5 files changed, 43 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index af815ea9d7cc..d01d62315f7e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2734,8 +2734,6 @@ extern void ext4_double_down_write_data_sem(struct inode *first,
 					    struct inode *second);
 extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
 					  struct inode *donor_inode);
-void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2);
-void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2);
 extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a569d335f804..60589b60e9b0 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -130,7 +130,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	/* Protect orig inodes against a truncate and make sure,
 	 * that only 1 swap_inode_boot_loader is running. */
-	ext4_inode_double_lock(inode, inode_bl);
+	lock_two_nondirectories(inode, inode_bl);
 
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_inode_pages(&inode_bl->i_data, 0);
@@ -205,7 +205,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	ext4_inode_resume_unlocked_dio(inode);
 	ext4_inode_resume_unlocked_dio(inode_bl);
 
-	ext4_inode_double_unlock(inode, inode_bl);
+	unlock_two_nondirectories(inode, inode_bl);
 
 	iput(inode_bl);
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 7fa4d855dbd5..773b503bd18c 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -1202,42 +1202,6 @@ mext_check_arguments(struct inode *orig_inode,
 	return 0;
 }
 
-/**
- * ext4_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
- *
- * @inode1:	the inode structure
- * @inode2:	the inode structure
- *
- * Lock two inodes' i_mutex
- */
-void
-ext4_inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
-	BUG_ON(inode1 == inode2);
-	if (inode1 < inode2) {
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
-	} else {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
-	}
-}
-
-/**
- * ext4_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
- *
- * @inode1:     the inode that is released first
- * @inode2:     the inode that is released second
- *
- */
-
-void
-ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
-	mutex_unlock(&inode1->i_mutex);
-	mutex_unlock(&inode2->i_mutex);
-}
-
 /**
  * ext4_move_extents - Exchange the specified range of a file
  *
@@ -1327,7 +1291,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		return -EINVAL;
 	}
 	/* Protect orig and donor inodes against a truncate */
-	ext4_inode_double_lock(orig_inode, donor_inode);
+	lock_two_nondirectories(orig_inode, donor_inode);
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(orig_inode);
@@ -1535,7 +1499,7 @@ out:
 	ext4_double_up_write_data_sem(orig_inode, donor_inode);
 	ext4_inode_resume_unlocked_dio(orig_inode);
 	ext4_inode_resume_unlocked_dio(donor_inode);
-	ext4_inode_double_unlock(orig_inode, donor_inode);
+	unlock_two_nondirectories(orig_inode, donor_inode);
 
 	return ret;
 }
diff --git a/fs/inode.c b/fs/inode.c
index bf7a8b3ab937..ef25afdf3906 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -942,6 +942,42 @@ void unlock_new_inode(struct inode *inode)
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
+/**
+ * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ * @inode1: first inode to lock
+ * @inode2: second inode to lock
+ */
+void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
+	if (inode1 == inode2 || !inode2) {
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+		return;
+	}
+	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
+	if (inode1 < inode2) {
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	} else {
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+	}
+}
+EXPORT_SYMBOL(lock_two_nondirectories);
+
+/**
+ * unlock_two_nondirectories - release locks from lock_two_nondirectories()
+ * @inode1: first inode to unlock
+ * @inode2: second inode to unlock
+ */
+void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+	mutex_unlock(&inode1->i_mutex);
+	if (inode2 && inode2 != inode1)
+		mutex_unlock(&inode2->i_mutex);
+}
+EXPORT_SYMBOL(unlock_two_nondirectories);
+
 /**
  * iget5_locked - obtain an inode from a mounted file system
  * @sb:		super block of file system
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5e44b0893db8..4e1a0b41f966 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -637,6 +637,9 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_QUOTA
 };
 
+void lock_two_nondirectories(struct inode *, struct inode*);
+void unlock_two_nondirectories(struct inode *, struct inode*);
+
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
-- 
cgit 


From 40bd22c9f8617ddd5da06044c81f72a2cf700791 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Wed, 18 Apr 2012 15:21:34 -0400
Subject: vfs: rename I_MUTEX_QUOTA now that it's not used for quotas

I_MUTEX_QUOTA is now just being used whenever we want to lock two
non-directories.  So the name isn't right.  I_MUTEX_NONDIR2 isn't
especially elegant but it's the best I could think of.

Also fix some outdated documentation.

Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/inode.c         | 4 ++--
 include/linux/fs.h | 9 ++++++---
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/inode.c b/fs/inode.c
index 51f329b98aa4..ce48c359ce9e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -957,10 +957,10 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
 	if (inode1 < inode2) {
 		mutex_lock(&inode1->i_mutex);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_QUOTA);
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
 	} else {
 		mutex_lock(&inode2->i_mutex);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_QUOTA);
+		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
 	}
 }
 EXPORT_SYMBOL(lock_two_nondirectories);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4e1a0b41f966..ed7f94af1ab2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -623,10 +623,13 @@ static inline int inode_unhashed(struct inode *inode)
  * 0: the object of the current VFS operation
  * 1: parent
  * 2: child/target
- * 3: quota file
+ * 3: xattr
+ * 4: second non-directory
+ * The last is for certain operations (such as rename) which lock two
+ * non-directories at once.
  *
  * The locking order between these classes is
- * parent -> child -> normal -> xattr -> quota
+ * parent -> child -> normal -> xattr -> second non-directory
  */
 enum inode_i_mutex_lock_class
 {
@@ -634,7 +637,7 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_PARENT,
 	I_MUTEX_CHILD,
 	I_MUTEX_XATTR,
-	I_MUTEX_QUOTA
+	I_MUTEX_NONDIR2
 };
 
 void lock_two_nondirectories(struct inode *, struct inode*);
-- 
cgit 


From 617588d5186c887eb94321b021bb5a46f896f4b3 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Fri, 1 Jul 2011 15:18:34 -0400
Subject: locks: introduce new FL_DELEG lock flag

For now FL_DELEG is just a synonym for FL_LEASE.  So this patch doesn't
change behavior.

Next we'll modify break_lease to treat FL_DELEG leases differently, to
account for the fact that NFSv4 delegations should be broken in more
situations than Windows oplocks.

Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/locks.c          | 2 +-
 fs/nfsd/nfs4state.c | 2 +-
 include/linux/fs.h  | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index f155ffd648bb..079abcd8a836 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -134,7 +134,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & FL_LEASE)
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
 
 static bool lease_breaking(struct file_lock *fl)
 {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a601fd49f997..f36a30a9f2d1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3008,7 +3008,7 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int f
 		return NULL;
 	locks_init_lock(fl);
 	fl->fl_lmops = &nfsd_lease_mng_ops;
-	fl->fl_flags = FL_LEASE;
+	fl->fl_flags = FL_DELEG;
 	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
 	fl->fl_end = OFFSET_MAX;
 	fl->fl_owner = (fl_owner_t)(dp->dl_file);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ed7f94af1ab2..129e150f9e94 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -880,6 +880,7 @@ static inline int file_check_writeable(struct file *filp)
 
 #define FL_POSIX	1
 #define FL_FLOCK	2
+#define FL_DELEG	4	/* NFSv4 delegation */
 #define FL_ACCESS	8	/* not trying to lock, just looking */
 #define FL_EXISTS	16	/* when unlocking, test for existence */
 #define FL_LEASE	32	/* lease held on this file */
-- 
cgit 


From df4e8d2c1d2bbbbace706bfe5417320c9e3fbee3 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Mon, 5 Mar 2012 13:18:59 -0500
Subject: locks: implement delegations

Implement NFSv4 delegations at the vfs level using the new FL_DELEG lock
type.

Note nfsd is the only delegation user and is only using read
delegations.  Warn on any attempt to set a write delegation for now.
We'll come back to that case later.

Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/locks.c         | 55 ++++++++++++++++++++++++++++++++++++++++++++----------
 include/linux/fs.h | 18 +++++++++++++++---
 2 files changed, 60 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 079abcd8a836..f99d52bdd05a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1292,28 +1292,40 @@ static void time_out_leases(struct inode *inode)
 	}
 }
 
+static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
+{
+	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
+		return false;
+	return locks_conflict(breaker, lease);
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
- *	@mode: the open mode (read or write)
+ *	@mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
+ *	    break all leases
+ *	@type: FL_LEASE: break leases and delegations; FL_DELEG: break
+ *	    only delegations
  *
  *	break_lease (inlined for speed) has checked there already is at least
  *	some kind of lock (maybe a lease) on this file.  Leases are broken on
  *	a call to open() or truncate().  This function can sleep unless you
  *	specified %O_NONBLOCK to your open().
  */
-int __break_lease(struct inode *inode, unsigned int mode)
+int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl, *flock;
 	struct file_lock *fl;
 	unsigned long break_time;
 	int i_have_this_lease = 0;
+	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
 		return PTR_ERR(new_fl);
+	new_fl->fl_flags = type;
 
 	spin_lock(&inode->i_lock);
 
@@ -1323,13 +1335,16 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	if ((flock == NULL) || !IS_LEASE(flock))
 		goto out;
 
-	if (!locks_conflict(flock, new_fl))
+	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (leases_conflict(fl, new_fl)) {
+			lease_conflict = true;
+			if (fl->fl_owner == current->files)
+				i_have_this_lease = 1;
+		}
+	}
+	if (!lease_conflict)
 		goto out;
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next)
-		if (fl->fl_owner == current->files)
-			i_have_this_lease = 1;
-
 	break_time = 0;
 	if (lease_break_time > 0) {
 		break_time = jiffies + lease_break_time * HZ;
@@ -1338,6 +1353,8 @@ int __break_lease(struct inode *inode, unsigned int mode)
 	}
 
 	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (!leases_conflict(fl, new_fl))
+			continue;
 		if (want_write) {
 			if (fl->fl_flags & FL_UNLOCK_PENDING)
 				continue;
@@ -1379,7 +1396,7 @@ restart:
 		 */
 		for (flock = inode->i_flock; flock && IS_LEASE(flock);
 				flock = flock->fl_next) {
-			if (locks_conflict(new_fl, flock))
+			if (leases_conflict(new_fl, flock))
 				goto restart;
 		}
 		error = 0;
@@ -1460,9 +1477,26 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 
 	lease = *flp;
+	/*
+	 * In the delegation case we need mutual exclusion with
+	 * a number of operations that take the i_mutex.  We trylock
+	 * because delegations are an optional optimization, and if
+	 * there's some chance of a conflict--we'd rather not
+	 * bother, maybe that's a sign this just isn't a good file to
+	 * hand out a delegation on.
+	 */
+	if (is_deleg && !mutex_trylock(&inode->i_mutex))
+		return -EAGAIN;
+
+	if (is_deleg && arg == F_WRLCK) {
+		/* Write delegations are not currently supported: */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
 
 	error = -EAGAIN;
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
@@ -1514,9 +1548,10 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		goto out;
 
 	locks_insert_lock(before, lease);
-	return 0;
-
+	error = 0;
 out:
+	if (is_deleg)
+		mutex_unlock(&inode->i_mutex);
 	return error;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 129e150f9e94..8e4be1be1a62 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1022,7 +1022,7 @@ extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
-extern int __break_lease(struct inode *inode, unsigned int flags);
+extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **);
 extern int vfs_setlease(struct file *, long, struct file_lock **);
@@ -1131,7 +1131,7 @@ static inline int flock_lock_file_wait(struct file *filp,
 	return -ENOLCK;
 }
 
-static inline int __break_lease(struct inode *inode, unsigned int mode)
+static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	return 0;
 }
@@ -1961,9 +1961,17 @@ static inline int locks_verify_truncate(struct inode *inode,
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	if (inode->i_flock)
-		return __break_lease(inode, mode);
+		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
 }
+
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	if (inode->i_flock)
+		return __break_lease(inode, mode, FL_DELEG);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct inode *inode)
 {
@@ -2003,6 +2011,10 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 	return 0;
 }
 
+static inline int break_deleg(struct inode *inode, unsigned int mode)
+{
+	return 0;
+}
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
-- 
cgit 


From b21996e36c8e3b92a84e972378bde80b43acd890 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 20 Sep 2011 09:14:34 -0400
Subject: locks: break delegations on unlink

We need to break delegations on any operation that changes the set of
links pointing to an inode.  Start with unlink.

Such operations also hold the i_mutex on a parent directory.  Breaking a
delegation may require waiting for a timeout (by default 90 seconds) in
the case of a unresponsive NFS client.  To avoid blocking all directory
operations, we therefore drop locks before waiting for the delegation.
The logic then looks like:

	acquire locks
	...
	test for delegation; if found:
		take reference on inode
		release locks
		wait for delegation break
		drop reference on inode
		retry

It is possible this could never terminate.  (Even if we take precautions
to prevent another delegation being acquired on the same inode, we could
get a different inode on each retry.)  But this seems very unlikely.

The initial test for a delegation happens after the lock on the target
inode is acquired, but the directory inode may have been acquired
further up the call stack.  We therefore add a "struct inode **"
argument to any intervening functions, which we use to pass the inode
back up to the caller in the case it needs a delegation synchronously
broken.

Cc: David Howells <dhowells@redhat.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Dustin Kirkland <dustin.kirkland@gazzang.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/base/devtmpfs.c |  2 +-
 fs/cachefiles/namei.c   |  2 +-
 fs/ecryptfs/inode.c     |  4 ++--
 fs/namei.c              | 42 +++++++++++++++++++++++++++++++++++++++---
 fs/nfsd/vfs.c           |  2 +-
 include/linux/fs.h      |  2 +-
 ipc/mqueue.c            |  2 +-
 7 files changed, 46 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 7413d065906b..1b8490e2fbde 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -324,7 +324,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			mutex_lock(&dentry->d_inode->i_mutex);
 			notify_change(dentry, &newattrs);
 			mutex_unlock(&dentry->d_inode->i_mutex);
-			err = vfs_unlink(parent.dentry->d_inode, dentry);
+			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)
 				deleted = 1;
 		}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index f4a08d7fa2f7..31d480c0e046 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -294,7 +294,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 		if (ret < 0) {
 			cachefiles_io_error(cache, "Unlink security error");
 		} else {
-			ret = vfs_unlink(dir->d_inode, rep);
+			ret = vfs_unlink(dir->d_inode, rep, NULL);
 
 			if (preemptive)
 				cachefiles_mark_object_buried(cache, rep);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 0f9b66eaa767..dc60b8bd09ec 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -153,7 +153,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
 
 	dget(lower_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	rc = vfs_unlink(lower_dir_inode, lower_dentry);
+	rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
 	if (rc) {
 		printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
 		goto out_unlock;
@@ -208,7 +208,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
 				     directory_inode->i_sb);
 	if (IS_ERR(inode)) {
-		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry);
+		vfs_unlink(lower_dir_dentry->d_inode, lower_dentry, NULL);
 		goto out_lock;
 	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
diff --git a/fs/namei.c b/fs/namei.c
index e633a58d4222..67ce331a3ed8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3615,7 +3615,25 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
 	return do_rmdir(AT_FDCWD, pathname);
 }
 
-int vfs_unlink(struct inode *dir, struct dentry *dentry)
+/**
+ * vfs_unlink - unlink a filesystem object
+ * @dir:	parent directory
+ * @dentry:	victim
+ * @delegated_inode: returns victim inode, if the inode is delegated.
+ *
+ * The caller must hold dir->i_mutex.
+ *
+ * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
+ * return a reference to the inode in delegated_inode.  The caller
+ * should then break the delegation on that inode and retry.  Because
+ * breaking a delegation may take a long time, the caller should drop
+ * dir->i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
 {
 	struct inode *target = dentry->d_inode;
 	int error = may_delete(dir, dentry, 0);
@@ -3632,11 +3650,20 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
+			error = break_deleg(target, O_WRONLY|O_NONBLOCK);
+			if (error) {
+				if (error == -EWOULDBLOCK && delegated_inode) {
+					*delegated_inode = target;
+					ihold(target);
+				}
+				goto out;
+			}
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
 				dont_mount(dentry);
 		}
 	}
+out:
 	mutex_unlock(&target->i_mutex);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
@@ -3661,6 +3688,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	struct dentry *dentry;
 	struct nameidata nd;
 	struct inode *inode = NULL;
+	struct inode *delegated_inode = NULL;
 	unsigned int lookup_flags = 0;
 retry:
 	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
@@ -3675,7 +3703,7 @@ retry:
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit1;
-
+retry_deleg:
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
 	error = PTR_ERR(dentry);
@@ -3690,13 +3718,21 @@ retry:
 		error = security_path_unlink(&nd.path, dentry);
 		if (error)
 			goto exit2;
-		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+		error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
 exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
+	inode = NULL;
+	if (delegated_inode) {
+		error = break_deleg(delegated_inode, O_WRONLY);
+		iput(delegated_inode);
+		delegated_inode = NULL;
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 13886f7f40d5..7a810235d599 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1910,7 +1910,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_put;
 	if (type != S_IFDIR)
-		host_err = vfs_unlink(dirp, rdentry);
+		host_err = vfs_unlink(dirp, rdentry, NULL);
 	else
 		host_err = vfs_rmdir(dirp, rdentry);
 	if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8e4be1be1a62..a5799233142a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1455,7 +1455,7 @@ extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
-extern int vfs_unlink(struct inode *, struct dentry *);
+extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
 
 /*
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ae1996d3c539..95827ce2f3c7 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -886,7 +886,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
 		err = -ENOENT;
 	} else {
 		ihold(inode);
-		err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+		err = vfs_unlink(dentry->d_parent->d_inode, dentry, NULL);
 	}
 	dput(dentry);
 
-- 
cgit 


From 5a14696c1795d3843673b5cf1982d0e5357a5bbf Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 28 Aug 2012 07:50:40 -0700
Subject: locks: helper functions for delegation breaking

We'll need the same logic for rename and link.

Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c         | 13 +++----------
 include/linux/fs.h | 39 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 40 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 67ce331a3ed8..cfaeaae0f2db 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3650,14 +3650,9 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
-			error = break_deleg(target, O_WRONLY|O_NONBLOCK);
-			if (error) {
-				if (error == -EWOULDBLOCK && delegated_inode) {
-					*delegated_inode = target;
-					ihold(target);
-				}
+			error = try_break_deleg(target, delegated_inode);
+			if (error)
 				goto out;
-			}
 			error = dir->i_op->unlink(dir, dentry);
 			if (!error)
 				dont_mount(dentry);
@@ -3727,9 +3722,7 @@ exit2:
 		iput(inode);	/* truncate the inode here */
 	inode = NULL;
 	if (delegated_inode) {
-		error = break_deleg(delegated_inode, O_WRONLY);
-		iput(delegated_inode);
-		delegated_inode = NULL;
+		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a5799233142a..931f919f44e1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1905,6 +1905,9 @@ extern bool fs_fully_visible(struct file_system_type *);
 
 extern int current_umask(void);
 
+extern void ihold(struct inode * inode);
+extern void iput(struct inode *);
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1972,6 +1975,28 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 	return 0;
 }
 
+static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+{
+	int ret;
+
+	ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
+	if (ret == -EWOULDBLOCK && delegated_inode) {
+		*delegated_inode = inode;
+		ihold(inode);
+	}
+	return ret;
+}
+
+static inline int break_deleg_wait(struct inode **delegated_inode)
+{
+	int ret;
+
+	ret = break_deleg(*delegated_inode, O_WRONLY);
+	iput(*delegated_inode);
+	*delegated_inode = NULL;
+	return ret;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct inode *inode)
 {
@@ -2015,6 +2040,18 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
 	return 0;
 }
+
+static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+{
+	return 0;
+}
+
+static inline int break_deleg_wait(struct inode **delegated_inode)
+{
+	BUG();
+	return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
@@ -2350,8 +2387,6 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
 extern void address_space_init_once(struct address_space *mapping);
-extern void ihold(struct inode * inode);
-extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
 extern int inode_needs_sync(struct inode *inode);
-- 
cgit 


From 8e6d782cab50884ba94324632700e6233a252f6a Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 20 Sep 2011 16:59:58 -0400
Subject: locks: break delegations on rename

Cc: David Howells <dhowells@redhat.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 .../lustre/lustre/include/linux/lustre_compat25.h  |  4 +-
 drivers/staging/lustre/lustre/lvfs/lvfs_linux.c    |  2 +-
 fs/cachefiles/namei.c                              |  2 +-
 fs/ecryptfs/inode.c                                |  3 +-
 fs/namei.c                                         | 47 ++++++++++++++++++++--
 fs/nfsd/vfs.c                                      |  2 +-
 include/linux/fs.h                                 |  2 +-
 7 files changed, 51 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
index 9243dfab43d3..80b019bf969c 100644
--- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
+++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1) \
-		vfs_rename(old,old_dir,new,new_dir)
+#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
+		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))
diff --git a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
index 18e1b47a1d65..4ed7c9f0a8be 100644
--- a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
+++ b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
@@ -220,7 +220,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt);
+			    dir->d_inode, dchild_new, mnt, NULL);
 
 	dput(dchild_new);
 put_old:
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 31d480c0e046..ca65f39dc8dc 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -396,7 +396,7 @@ try_again:
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave);
+				 cache->graveyard->d_inode, grave, NULL);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index dc60b8bd09ec..c23b01bb7e04 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -640,7 +640,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		goto out_lock;
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
-			lower_new_dir_dentry->d_inode, lower_new_dentry);
+			lower_new_dir_dentry->d_inode, lower_new_dentry,
+			NULL);
 	if (rc)
 		goto out_lock;
 	if (target_inode)
diff --git a/fs/namei.c b/fs/namei.c
index cfaeaae0f2db..ce7e580e4e14 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4022,7 +4022,8 @@ out:
 }
 
 static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
-			    struct inode *new_dir, struct dentry *new_dentry)
+			    struct inode *new_dir, struct dentry *new_dentry,
+			    struct inode **delegated_inode)
 {
 	struct inode *target = new_dentry->d_inode;
 	struct inode *source = old_dentry->d_inode;
@@ -4039,6 +4040,14 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
 	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
 		goto out;
 
+	error = try_break_deleg(source, delegated_inode);
+	if (error)
+		goto out;
+	if (target) {
+		error = try_break_deleg(target, delegated_inode);
+		if (error)
+			goto out;
+	}
 	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (error)
 		goto out;
@@ -4053,8 +4062,30 @@ out:
 	return error;
 }
 
+/**
+ * vfs_rename - rename a filesystem object
+ * @old_dir:	parent of source
+ * @old_dentry:	source
+ * @new_dir:	parent of destination
+ * @new_dentry:	destination
+ * @delegated_inode: returns an inode needing a delegation break
+ *
+ * The caller must hold multiple mutexes--see lock_rename()).
+ *
+ * If vfs_rename discovers a delegation in need of breaking at either
+ * the source or destination, it will return -EWOULDBLOCK and return a
+ * reference to the inode in delegated_inode.  The caller should then
+ * break the delegation and retry.  Because breaking a delegation may
+ * take a long time, the caller should drop all locks before doing
+ * so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
 int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
-	       struct inode *new_dir, struct dentry *new_dentry)
+	       struct inode *new_dir, struct dentry *new_dentry,
+	       struct inode **delegated_inode)
 {
 	int error;
 	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
@@ -4082,7 +4113,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (is_dir)
 		error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
 	else
-		error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
+		error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode);
 	if (!error)
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
 			      new_dentry->d_inode, old_dentry);
@@ -4098,6 +4129,7 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
 	struct nameidata oldnd, newnd;
+	struct inode *delegated_inode = NULL;
 	struct filename *from;
 	struct filename *to;
 	unsigned int lookup_flags = 0;
@@ -4137,6 +4169,7 @@ retry:
 	newnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags |= LOOKUP_RENAME_TARGET;
 
+retry_deleg:
 	trap = lock_rename(new_dir, old_dir);
 
 	old_dentry = lookup_hash(&oldnd);
@@ -4173,13 +4206,19 @@ retry:
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry);
+				   new_dir->d_inode, new_dentry,
+				   &delegated_inode);
 exit5:
 	dput(new_dentry);
 exit4:
 	dput(old_dentry);
 exit3:
 	unlock_rename(new_dir, old_dir);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(oldnd.path.mnt);
 exit2:
 	if (retry_estale(error, lookup_flags))
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7a810235d599..45bf0295894d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1837,7 +1837,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		if (host_err)
 			goto out_dput_new;
 	}
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 931f919f44e1..5bcff883fa90 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1456,7 +1456,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
 
 /*
  * VFS dentry helper functions.
-- 
cgit 


From 146a8595c6399ee6ab4b5cc34c0d28aa4835fdc5 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 20 Sep 2011 17:14:31 -0400
Subject: locks: break delegations on link

Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Dustin Kirkland <dustin.kirkland@gazzang.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ecryptfs/inode.c |  2 +-
 fs/namei.c          | 36 ++++++++++++++++++++++++++++++++----
 fs/nfsd/vfs.c       |  2 +-
 include/linux/fs.h  |  2 +-
 4 files changed, 35 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index c23b01bb7e04..1c628f023041 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -475,7 +475,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
 	dget(lower_new_dentry);
 	lower_dir_dentry = lock_parent(lower_new_dentry);
 	rc = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
-		      lower_new_dentry);
+		      lower_new_dentry, NULL);
 	if (rc || !lower_new_dentry->d_inode)
 		goto out_lock;
 	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
diff --git a/fs/namei.c b/fs/namei.c
index ce7e580e4e14..251178a1e383 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3819,7 +3819,26 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
 	return sys_symlinkat(oldname, AT_FDCWD, newname);
 }
 
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
+/**
+ * vfs_link - create a new link
+ * @old_dentry:	object to be linked
+ * @dir:	new parent
+ * @new_dentry:	where to create the new link
+ * @delegated_inode: returns inode needing a delegation break
+ *
+ * The caller must hold dir->i_mutex
+ *
+ * If vfs_link discovers a delegation on the to-be-linked file in need
+ * of breaking, it will return -EWOULDBLOCK and return a reference to the
+ * inode in delegated_inode.  The caller should then break the delegation
+ * and retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ */
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
 {
 	struct inode *inode = old_dentry->d_inode;
 	unsigned max_links = dir->i_sb->s_max_links;
@@ -3855,8 +3874,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		error =  -ENOENT;
 	else if (max_links && inode->i_nlink >= max_links)
 		error = -EMLINK;
-	else
-		error = dir->i_op->link(old_dentry, dir, new_dentry);
+	else {
+		error = try_break_deleg(inode, delegated_inode);
+		if (!error)
+			error = dir->i_op->link(old_dentry, dir, new_dentry);
+	}
 
 	if (!error && (inode->i_state & I_LINKABLE)) {
 		spin_lock(&inode->i_lock);
@@ -3883,6 +3905,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 {
 	struct dentry *new_dentry;
 	struct path old_path, new_path;
+	struct inode *delegated_inode = NULL;
 	int how = 0;
 	int error;
 
@@ -3921,9 +3944,14 @@ retry:
 	error = security_path_link(old_path.dentry, &new_path, new_dentry);
 	if (error)
 		goto out_dput;
-	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
+	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
 out_dput:
 	done_path_create(&new_path, new_dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, how)) {
 		how |= LOOKUP_REVAL;
 		goto retry;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 45bf0295894d..27ba21b5f383 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1736,7 +1736,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		err = nfserrno(host_err);
 		goto out_dput;
 	}
-	host_err = vfs_link(dold, dirp, dnew);
+	host_err = vfs_link(dold, dirp, dnew, NULL);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
 		if (!err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5bcff883fa90..6e36e7118ec1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1453,7 +1453,7 @@ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
 extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
 extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 extern int vfs_symlink(struct inode *, struct dentry *, const char *);
-extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
+extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
-- 
cgit 


From 27ac0ffeac80ba6b9580529568d06144df044366 Mon Sep 17 00:00:00 2001
From: "J. Bruce Fields" <bfields@redhat.com>
Date: Tue, 20 Sep 2011 17:19:26 -0400
Subject: locks: break delegations on any attribute modification

NFSv4 uses leases to guarantee that clients can cache metadata as well
as data.

Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
Cc: David Howells <dhowells@redhat.com>
Cc: Tyler Hicks <tyhicks@canonical.com>
Cc: Dustin Kirkland <dustin.kirkland@gazzang.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/base/devtmpfs.c   |  4 ++--
 fs/attr.c                 | 25 ++++++++++++++++++++++++-
 fs/cachefiles/interface.c |  4 ++--
 fs/ecryptfs/inode.c       |  4 ++--
 fs/hpfs/namei.c           |  2 +-
 fs/inode.c                |  6 +++++-
 fs/nfsd/vfs.c             |  8 ++++++--
 fs/open.c                 | 22 ++++++++++++++++++----
 fs/utimes.c               |  9 ++++++++-
 include/linux/fs.h        |  2 +-
 10 files changed, 69 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 1b8490e2fbde..0f3820121e02 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -216,7 +216,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		newattrs.ia_gid = gid;
 		newattrs.ia_valid = ATTR_MODE|ATTR_UID|ATTR_GID;
 		mutex_lock(&dentry->d_inode->i_mutex);
-		notify_change(dentry, &newattrs);
+		notify_change(dentry, &newattrs, NULL);
 		mutex_unlock(&dentry->d_inode->i_mutex);
 
 		/* mark as kernel-created inode */
@@ -322,7 +322,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 			newattrs.ia_valid =
 				ATTR_UID|ATTR_GID|ATTR_MODE;
 			mutex_lock(&dentry->d_inode->i_mutex);
-			notify_change(dentry, &newattrs);
+			notify_change(dentry, &newattrs, NULL);
 			mutex_unlock(&dentry->d_inode->i_mutex);
 			err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
 			if (!err || err == -ENOENT)
diff --git a/fs/attr.c b/fs/attr.c
index 1449adb14ef6..267968d94673 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -167,7 +167,27 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int notify_change(struct dentry * dentry, struct iattr * attr)
+/**
+ * notify_change - modify attributes of a filesytem object
+ * @dentry:	object affected
+ * @iattr:	new attributes
+ * @delegated_inode: returns inode, if the inode is delegated
+ *
+ * The caller must hold the i_mutex on the affected object.
+ *
+ * If notify_change discovers a delegation in need of breaking,
+ * it will return -EWOULDBLOCK and return a reference to the inode in
+ * delegated_inode.  The caller should then break the delegation and
+ * retry.  Because breaking a delegation may take a long time, the
+ * caller should drop the i_mutex before doing so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.  Also, passing NULL is fine for callers holding
+ * the file open for write, as there can be no conflicting delegation in
+ * that case.
+ */
+int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	umode_t mode = inode->i_mode;
@@ -241,6 +261,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 		return 0;
 
 	error = security_inode_setattr(dentry, attr);
+	if (error)
+		return error;
+	error = try_break_deleg(inode, delegated_inode);
 	if (error)
 		return error;
 
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 43eb5592cdea..5088a418ac4d 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -449,14 +449,14 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 		_debug("discard tail %llx", oi_size);
 		newattrs.ia_valid = ATTR_SIZE;
 		newattrs.ia_size = oi_size & PAGE_MASK;
-		ret = notify_change(object->backer, &newattrs);
+		ret = notify_change(object->backer, &newattrs, NULL);
 		if (ret < 0)
 			goto truncate_failed;
 	}
 
 	newattrs.ia_valid = ATTR_SIZE;
 	newattrs.ia_size = ni_size;
-	ret = notify_change(object->backer, &newattrs);
+	ret = notify_change(object->backer, &newattrs, NULL);
 
 truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1c628f023041..c36c44824471 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -882,7 +882,7 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 		struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 
 		mutex_lock(&lower_dentry->d_inode->i_mutex);
-		rc = notify_change(lower_dentry, &lower_ia);
+		rc = notify_change(lower_dentry, &lower_ia, NULL);
 		mutex_unlock(&lower_dentry->d_inode->i_mutex);
 	}
 	return rc;
@@ -983,7 +983,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 		lower_ia.ia_valid &= ~ATTR_MODE;
 
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-	rc = notify_change(lower_dentry, &lower_ia);
+	rc = notify_change(lower_dentry, &lower_ia, NULL);
 	mutex_unlock(&lower_dentry->d_inode->i_mutex);
 out:
 	fsstack_copy_attr_all(inode, lower_inode);
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 345713d2f8f3..1b39afdd86fd 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -407,7 +407,7 @@ again:
 			/*printk("HPFS: truncating file before delete.\n");*/
 			newattrs.ia_size = 0;
 			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs);
+			err = notify_change(dentry, &newattrs, NULL);
 			put_write_access(inode);
 			if (!err)
 				goto again;
diff --git a/fs/inode.c b/fs/inode.c
index ce48c359ce9e..4bcdad3c9361 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1603,7 +1603,11 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	struct iattr newattrs;
 
 	newattrs.ia_valid = ATTR_FORCE | kill;
-	return notify_change(dentry, &newattrs);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	return notify_change(dentry, &newattrs, NULL);
 }
 
 int file_remove_suid(struct file *file)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 27ba21b5f383..94b5f5d2bfed 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -427,7 +427,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			goto out_nfserr;
 		fh_lock(fhp);
 
-		host_err = notify_change(dentry, iap);
+		host_err = notify_change(dentry, iap, NULL);
 		err = nfserrno(host_err);
 		fh_unlock(fhp);
 	}
@@ -988,7 +988,11 @@ static void kill_suid(struct dentry *dentry)
 	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	notify_change(dentry, &ia);
+	/*
+	 * Note we call this on write, so notify_change will not
+	 * encounter any conflicting delegations:
+	 */
+	notify_change(dentry, &ia, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 }
 
diff --git a/fs/open.c b/fs/open.c
index fffbed40dbe9..4b3e1edf2fe4 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -57,7 +57,8 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
 	mutex_lock(&dentry->d_inode->i_mutex);
-	ret = notify_change(dentry, &newattrs);
+	/* Note any delegations or leases have already been broken: */
+	ret = notify_change(dentry, &newattrs, NULL);
 	mutex_unlock(&dentry->d_inode->i_mutex);
 	return ret;
 }
@@ -464,21 +465,28 @@ out:
 static int chmod_common(struct path *path, umode_t mode)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	struct iattr newattrs;
 	int error;
 
 	error = mnt_want_write(path->mnt);
 	if (error)
 		return error;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chmod(path, mode);
 	if (error)
 		goto out_unlock;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 out_unlock:
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	mnt_drop_write(path->mnt);
 	return error;
 }
@@ -522,6 +530,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 static int chown_common(struct path *path, uid_t user, gid_t group)
 {
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 	int error;
 	struct iattr newattrs;
 	kuid_t uid;
@@ -546,12 +555,17 @@ static int chown_common(struct path *path, uid_t user, gid_t group)
 	if (!S_ISDIR(inode->i_mode))
 		newattrs.ia_valid |=
 			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
 	error = security_path_chown(path, uid, gid);
 	if (!error)
-		error = notify_change(path->dentry, &newattrs);
+		error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
-
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 	return error;
 }
 
diff --git a/fs/utimes.c b/fs/utimes.c
index f4fb7eca10e8..aa138d64560a 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -53,6 +53,7 @@ static int utimes_common(struct path *path, struct timespec *times)
 	int error;
 	struct iattr newattrs;
 	struct inode *inode = path->dentry->d_inode;
+	struct inode *delegated_inode = NULL;
 
 	error = mnt_want_write(path->mnt);
 	if (error)
@@ -101,9 +102,15 @@ static int utimes_common(struct path *path, struct timespec *times)
 				goto mnt_drop_write_and_out;
 		}
 	}
+retry_deleg:
 	mutex_lock(&inode->i_mutex);
-	error = notify_change(path->dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs, &delegated_inode);
 	mutex_unlock(&inode->i_mutex);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry_deleg;
+	}
 
 mnt_drop_write_and_out:
 	mnt_drop_write(path->mnt);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6e36e7118ec1..ab2a0ca82dc5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2278,7 +2278,7 @@ extern void emergency_remount(void);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
-extern int notify_change(struct dentry *, struct iattr *);
+extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
 
-- 
cgit 


From 180771a3707a4c0577cbf4f830c754dbabfdfccb Mon Sep 17 00:00:00 2001
From: "Upinder Malhi \\(umalhi\\)" <umalhi@cisco.com>
Date: Tue, 10 Sep 2013 03:36:59 +0000
Subject: IB/core: Add Cisco usNIC rdma node and transport types

This patch adds new rdma node and new rdma transport, and supporting
code used by Cisco's low latency driver called usNIC.  usNIC uses its
own transport, distinct from IB and iWARP.

Signed-off-by: Upinder Malhi <umalhi@cisco.com>
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/sysfs.c | 1 +
 drivers/infiniband/core/verbs.c | 3 +++
 include/rdma/ib_verbs.h         | 6 ++++--
 3 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index cde1e7b5b85d..faad2caf22b1 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -612,6 +612,7 @@ static ssize_t show_node_type(struct device *device,
 	switch (dev->node_type) {
 	case RDMA_NODE_IB_CA:	  return sprintf(buf, "%d: CA\n", dev->node_type);
 	case RDMA_NODE_RNIC:	  return sprintf(buf, "%d: RNIC\n", dev->node_type);
+	case RDMA_NODE_USNIC:	  return sprintf(buf, "%d: usNIC\n", dev->node_type);
 	case RDMA_NODE_IB_SWITCH: return sprintf(buf, "%d: switch\n", dev->node_type);
 	case RDMA_NODE_IB_ROUTER: return sprintf(buf, "%d: router\n", dev->node_type);
 	default:		  return sprintf(buf, "%d: <unknown>\n", dev->node_type);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index a321df28bab2..84f502785f89 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -114,6 +114,8 @@ rdma_node_get_transport(enum rdma_node_type node_type)
 		return RDMA_TRANSPORT_IB;
 	case RDMA_NODE_RNIC:
 		return RDMA_TRANSPORT_IWARP;
+	case RDMA_NODE_USNIC:
+		return RDMA_TRANSPORT_USNIC;
 	default:
 		BUG();
 		return 0;
@@ -130,6 +132,7 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_
 	case RDMA_TRANSPORT_IB:
 		return IB_LINK_LAYER_INFINIBAND;
 	case RDMA_TRANSPORT_IWARP:
+	case RDMA_TRANSPORT_USNIC:
 		return IB_LINK_LAYER_ETHERNET;
 	default:
 		return IB_LINK_LAYER_UNSPECIFIED;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e393171e2fac..60354d53948e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -67,12 +67,14 @@ enum rdma_node_type {
 	RDMA_NODE_IB_CA 	= 1,
 	RDMA_NODE_IB_SWITCH,
 	RDMA_NODE_IB_ROUTER,
-	RDMA_NODE_RNIC
+	RDMA_NODE_RNIC,
+	RDMA_NODE_USNIC,
 };
 
 enum rdma_transport_type {
 	RDMA_TRANSPORT_IB,
-	RDMA_TRANSPORT_IWARP
+	RDMA_TRANSPORT_IWARP,
+	RDMA_TRANSPORT_USNIC
 };
 
 enum rdma_transport_type
-- 
cgit 


From a33c4a2663c19ac01e557d6b78806271eec2a150 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 8 Nov 2013 10:23:34 +0800
Subject: net_sched: tbf: support of 64bit rates

With psched_ratecfg_precompute(), tbf can deal with 64bit rates.
Add two new attributes so that tc can use them to break the 32bit
limit.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Suggested-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  2 ++
 net/sched/sch_tbf.c            | 22 ++++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index f2624b549e61..307f293477e8 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -171,6 +171,8 @@ enum {
 	TCA_TBF_PARMS,
 	TCA_TBF_RTAB,
 	TCA_TBF_PTAB,
+	TCA_TBF_RATE64,
+	TCA_TBF_PRATE64,
 	__TCA_TBF_MAX,
 };
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index b0571224f3c9..68f98595819c 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -266,20 +266,23 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[TCA_TBF_PARMS]	= { .len = sizeof(struct tc_tbf_qopt) },
 	[TCA_TBF_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
 };
 
 static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	int err;
 	struct tbf_sched_data *q = qdisc_priv(sch);
-	struct nlattr *tb[TCA_TBF_PTAB + 1];
+	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
 	struct qdisc_rate_table *rtab = NULL;
 	struct qdisc_rate_table *ptab = NULL;
 	struct Qdisc *child = NULL;
 	int max_size, n;
+	u64 rate64 = 0, prate64 = 0;
 
-	err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy);
+	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
 	if (err < 0)
 		return err;
 
@@ -341,9 +344,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	psched_ratecfg_precompute(&q->rate, &rtab->rate, 0);
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64);
 	if (ptab) {
-		psched_ratecfg_precompute(&q->peak, &ptab->rate, 0);
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
 		q->peak_present = true;
 	} else {
 		q->peak_present = false;
@@ -402,6 +409,13 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	opt.buffer = PSCHED_NS2TICKS(q->buffer);
 	if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
+	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
+		goto nla_put_failure;
+	if (q->peak_present &&
+	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
+		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 	return skb->len;
-- 
cgit 


From 2c140a246dc0bc085b98eddde978060fcec1080c Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Fri, 1 Nov 2013 18:27:41 -0400
Subject: dm: allow remove to be deferred

This patch allows the removal of an open device to be deferred until
it is closed.  (Previously such a removal attempt would fail.)

The deferred remove functionality is enabled by setting the flag
DM_DEFERRED_REMOVE in the ioctl structure on DM_DEV_REMOVE or
DM_REMOVE_ALL ioctl.

On return from DM_DEV_REMOVE, the flag DM_DEFERRED_REMOVE indicates if
the device was removed immediately or flagged to be removed on close -
if the flag is clear, the device was removed.

On return from DM_DEV_STATUS and other ioctls, the flag
DM_DEFERRED_REMOVE is set if the device is scheduled to be removed on
closure.

A device that is scheduled to be deleted can be revived using the
message "@cancel_deferred_remove". This message clears the
DMF_DEFERRED_REMOVE flag so that the device won't be deleted on close.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-ioctl.c         | 36 +++++++++++++++++++++++++++------
 drivers/md/dm.c               | 47 ++++++++++++++++++++++++++++++++++++++++---
 drivers/md/dm.h               | 13 +++++++++++-
 include/uapi/linux/dm-ioctl.h | 15 ++++++++++++--
 4 files changed, 99 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index afe08146f73e..51521429fb59 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -57,7 +57,7 @@ struct vers_iter {
 static struct list_head _name_buckets[NUM_BUCKETS];
 static struct list_head _uuid_buckets[NUM_BUCKETS];
 
-static void dm_hash_remove_all(int keep_open_devices);
+static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred);
 
 /*
  * Guards access to both hash tables.
@@ -86,7 +86,7 @@ static int dm_hash_init(void)
 
 static void dm_hash_exit(void)
 {
-	dm_hash_remove_all(0);
+	dm_hash_remove_all(false, false, false);
 }
 
 /*-----------------------------------------------------------------
@@ -276,7 +276,7 @@ static struct dm_table *__hash_remove(struct hash_cell *hc)
 	return table;
 }
 
-static void dm_hash_remove_all(int keep_open_devices)
+static void dm_hash_remove_all(bool keep_open_devices, bool mark_deferred, bool only_deferred)
 {
 	int i, dev_skipped;
 	struct hash_cell *hc;
@@ -293,7 +293,8 @@ retry:
 			md = hc->md;
 			dm_get(md);
 
-			if (keep_open_devices && dm_lock_for_deletion(md)) {
+			if (keep_open_devices &&
+			    dm_lock_for_deletion(md, mark_deferred, only_deferred)) {
 				dm_put(md);
 				dev_skipped++;
 				continue;
@@ -450,6 +451,11 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
 	return md;
 }
 
+void dm_deferred_remove(void)
+{
+	dm_hash_remove_all(true, false, true);
+}
+
 /*-----------------------------------------------------------------
  * Implementation of the ioctl commands
  *---------------------------------------------------------------*/
@@ -461,7 +467,7 @@ typedef int (*ioctl_fn)(struct dm_ioctl *param, size_t param_size);
 
 static int remove_all(struct dm_ioctl *param, size_t param_size)
 {
-	dm_hash_remove_all(1);
+	dm_hash_remove_all(true, !!(param->flags & DM_DEFERRED_REMOVE), false);
 	param->data_size = 0;
 	return 0;
 }
@@ -683,6 +689,9 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
 	if (dm_suspended_md(md))
 		param->flags |= DM_SUSPEND_FLAG;
 
+	if (dm_test_deferred_remove_flag(md))
+		param->flags |= DM_DEFERRED_REMOVE;
+
 	param->dev = huge_encode_dev(disk_devt(disk));
 
 	/*
@@ -832,8 +841,13 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 	/*
 	 * Ensure the device is not open and nothing further can open it.
 	 */
-	r = dm_lock_for_deletion(md);
+	r = dm_lock_for_deletion(md, !!(param->flags & DM_DEFERRED_REMOVE), false);
 	if (r) {
+		if (r == -EBUSY && param->flags & DM_DEFERRED_REMOVE) {
+			up_write(&_hash_lock);
+			dm_put(md);
+			return 0;
+		}
 		DMDEBUG_LIMIT("unable to remove open device %s", hc->name);
 		up_write(&_hash_lock);
 		dm_put(md);
@@ -848,6 +862,8 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
 		dm_table_destroy(t);
 	}
 
+	param->flags &= ~DM_DEFERRED_REMOVE;
+
 	if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr))
 		param->flags |= DM_UEVENT_GENERATED_FLAG;
 
@@ -1469,6 +1485,14 @@ static int message_for_md(struct mapped_device *md, unsigned argc, char **argv,
 	if (**argv != '@')
 		return 2; /* no '@' prefix, deliver to target */
 
+	if (!strcasecmp(argv[0], "@cancel_deferred_remove")) {
+		if (argc != 1) {
+			DMERR("Invalid arguments for @cancel_deferred_remove");
+			return -EINVAL;
+		}
+		return dm_cancel_deferred_remove(md);
+	}
+
 	r = dm_stats_message(md, argc, argv, result, maxlen);
 	if (r < 2)
 		return r;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b3e26c7d1417..0704c523a76b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -49,6 +49,11 @@ static unsigned int _major = 0;
 static DEFINE_IDR(_minor_idr);
 
 static DEFINE_SPINLOCK(_minor_lock);
+
+static void do_deferred_remove(struct work_struct *w);
+
+static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -116,6 +121,7 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_DELETING 4
 #define DMF_NOFLUSH_SUSPENDING 5
 #define DMF_MERGE_IS_OPTIONAL 6
+#define DMF_DEFERRED_REMOVE 7
 
 /*
  * A dummy definition to make RCU happy.
@@ -299,6 +305,8 @@ out_free_io_cache:
 
 static void local_exit(void)
 {
+	flush_scheduled_work();
+
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -404,7 +412,10 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	spin_lock(&_minor_lock);
 
-	atomic_dec(&md->open_count);
+	if (atomic_dec_and_test(&md->open_count) &&
+	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
+		schedule_work(&deferred_remove_work);
+
 	dm_put(md);
 
 	spin_unlock(&_minor_lock);
@@ -418,14 +429,18 @@ int dm_open_count(struct mapped_device *md)
 /*
  * Guarantees nothing is using the device before it's deleted.
  */
-int dm_lock_for_deletion(struct mapped_device *md)
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred)
 {
 	int r = 0;
 
 	spin_lock(&_minor_lock);
 
-	if (dm_open_count(md))
+	if (dm_open_count(md)) {
 		r = -EBUSY;
+		if (mark_deferred)
+			set_bit(DMF_DEFERRED_REMOVE, &md->flags);
+	} else if (only_deferred && !test_bit(DMF_DEFERRED_REMOVE, &md->flags))
+		r = -EEXIST;
 	else
 		set_bit(DMF_DELETING, &md->flags);
 
@@ -434,6 +449,27 @@ int dm_lock_for_deletion(struct mapped_device *md)
 	return r;
 }
 
+int dm_cancel_deferred_remove(struct mapped_device *md)
+{
+	int r = 0;
+
+	spin_lock(&_minor_lock);
+
+	if (test_bit(DMF_DELETING, &md->flags))
+		r = -EBUSY;
+	else
+		clear_bit(DMF_DEFERRED_REMOVE, &md->flags);
+
+	spin_unlock(&_minor_lock);
+
+	return r;
+}
+
+static void do_deferred_remove(struct work_struct *w)
+{
+	dm_deferred_remove();
+}
+
 sector_t dm_get_size(struct mapped_device *md)
 {
 	return get_capacity(md->disk);
@@ -2894,6 +2930,11 @@ int dm_suspended_md(struct mapped_device *md)
 	return test_bit(DMF_SUSPENDED, &md->flags);
 }
 
+int dm_test_deferred_remove_flag(struct mapped_device *md)
+{
+	return test_bit(DMF_DEFERRED_REMOVE, &md->flags);
+}
+
 int dm_suspended(struct dm_target *ti)
 {
 	return dm_suspended_md(dm_table_get_md(ti->table));
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 1d1ad7b7e527..c57ba550f69e 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -128,6 +128,16 @@ int dm_deleting_md(struct mapped_device *md);
  */
 int dm_suspended_md(struct mapped_device *md);
 
+/*
+ * Test if the device is scheduled for deferred remove.
+ */
+int dm_test_deferred_remove_flag(struct mapped_device *md);
+
+/*
+ * Try to remove devices marked for deferred removal.
+ */
+void dm_deferred_remove(void);
+
 /*
  * The device-mapper can be driven through one of two interfaces;
  * ioctl or filesystem, depending which patch you have applied.
@@ -158,7 +168,8 @@ void dm_stripe_exit(void);
 void dm_destroy(struct mapped_device *md);
 void dm_destroy_immediate(struct mapped_device *md);
 int dm_open_count(struct mapped_device *md);
-int dm_lock_for_deletion(struct mapped_device *md);
+int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
+int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
 sector_t dm_get_size(struct mapped_device *md);
 struct dm_stats *dm_get_stats(struct mapped_device *md);
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index f1e12bd40b3b..c8a4302093a3 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	26
+#define DM_VERSION_MINOR	27
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2013-08-15)"
+#define DM_VERSION_EXTRA	"-ioctl (2013-10-30)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
@@ -341,4 +341,15 @@ enum {
  */
 #define DM_DATA_OUT_FLAG		(1 << 16) /* Out */
 
+/*
+ * If set with DM_DEV_REMOVE or DM_REMOVE_ALL this indicates that if
+ * the device cannot be removed immediately because it is still in use
+ * it should instead be scheduled for removal when it gets closed.
+ *
+ * On return from DM_DEV_REMOVE, DM_DEV_STATUS or other ioctls, this
+ * flag indicates that the device is scheduled to be removed when it
+ * gets closed.
+ */
+#define DM_DEFERRED_REMOVE		(1 << 17) /* In/Out */
+
 #endif				/* _LINUX_DM_IOCTL_H */
-- 
cgit 


From 6aafeef03b9d9ecf255f3a80ed85ee070260e1ae Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 6 Nov 2013 17:52:20 +0100
Subject: netfilter: push reasm skb through instead of original frag skbs

Pushing original fragments through causes several problems. For example
for matching, frags may not be matched correctly. Take following
example:

<example>
On HOSTA do:
ip6tables -I INPUT -p icmpv6 -j DROP
ip6tables -I INPUT -p icmpv6 -m icmp6 --icmpv6-type 128 -j ACCEPT

and on HOSTB you do:
ping6 HOSTA -s2000    (MTU is 1500)

Incoming echo requests will be filtered out on HOSTA. This issue does
not occur with smaller packets than MTU (where fragmentation does not happen)
</example>

As was discussed previously, the only correct solution seems to be to use
reassembled skb instead of separete frags. Doing this has positive side
effects in reducing sk_buff by one pointer (nfct_reasm) and also the reams
dances in ipvs and conntrack can be removed.

Future plan is to remove net/ipv6/netfilter/nf_conntrack_reasm.c
entirely and use code in net/ipv6/reassembly.c instead.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Ricardo Leitner <mleitner@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h                         | 32 ---------------
 include/net/ip_vs.h                            | 32 +--------------
 include/net/netfilter/ipv6/nf_defrag_ipv6.h    |  4 +-
 net/core/skbuff.c                              |  3 --
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 56 +-------------------------
 net/ipv6/netfilter/nf_conntrack_reasm.c        | 19 +--------
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |  7 +++-
 net/netfilter/ipvs/ip_vs_core.c                | 55 +------------------------
 net/netfilter/ipvs/ip_vs_pe_sip.c              |  8 +---
 9 files changed, 13 insertions(+), 203 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 036ec7d8a83a..215b5ea1cb30 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -337,11 +337,6 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
-#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
-    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
-#endif
-
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
@@ -374,7 +369,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
  *	@nfct: Associated connection, if any
- *	@nfct_reasm: netfilter conntrack re-assembly pointer
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
@@ -463,9 +457,6 @@ struct sk_buff {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	struct sk_buff		*nfct_reasm;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif
@@ -2595,18 +2586,6 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 		atomic_inc(&nfct->use);
 }
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		atomic_inc(&skb->users);
-}
-static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		kfree_skb(skb);
-}
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {
@@ -2625,10 +2604,6 @@ static inline void nf_reset(struct sk_buff *skb)
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-	skb->nfct_reasm = NULL;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;
@@ -2650,10 +2625,6 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	dst->nfct_reasm = src->nfct_reasm;
-	nf_conntrack_get_reasm(src->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);
@@ -2665,9 +2636,6 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src)
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(dst->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(dst->nf_bridge);
 #endif
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cd7275f9c463..5679d927562b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -109,7 +109,6 @@ extern int ip_vs_conn_tab_size;
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
 			   IPv6 where L4 Transport Header starts */
-	__u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;
@@ -117,34 +116,12 @@ struct ip_vs_iphdr {
 	union nf_inet_addr daddr;
 };
 
-/* Dependency to module: nf_defrag_ipv6 */
-#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return skb->nfct_reasm;
-}
-static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
-				      int len, void *buffer,
-				      const struct ip_vs_iphdr *ipvsh)
-{
-	if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
-		return skb_header_pointer(skb_nfct_reasm(skb),
-					  ipvsh->thoff_reasm, len, buffer);
-
-	return skb_header_pointer(skb, offset, len, buffer);
-}
-#else
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return NULL;
-}
 static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
 				      int len, void *buffer,
 				      const struct ip_vs_iphdr *ipvsh)
 {
 	return skb_header_pointer(skb, offset, len, buffer);
 }
-#endif
 
 static inline void
 ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
@@ -171,19 +148,12 @@ ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr)
 			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
-		/* ipv6_find_hdr() updates len, flags, thoff_reasm */
-		iphdr->thoff_reasm = 0;
+		/* ipv6_find_hdr() updates len, flags */
 		iphdr->len	 = 0;
 		iphdr->flags	 = 0;
 		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
 						 &iphdr->fragoffs,
 						 &iphdr->flags);
-		/* get proto from re-assembled packet and it's offset */
-		if (skb_nfct_reasm(skb))
-			iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
-							&iphdr->thoff_reasm,
-							-1, NULL, NULL);
-
 	} else
 #endif
 	{
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index 5613412e7dc2..27666d8a0bd0 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -6,9 +6,7 @@ void nf_defrag_ipv6_enable(void);
 int nf_ct_frag6_init(void);
 void nf_ct_frag6_cleanup(void);
 struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			struct net_device *in, struct net_device *out,
-			int (*okfn)(struct sk_buff *));
+void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8c5197fe55a4..8cec1e6b844d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -592,9 +592,6 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 #endif
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 486545eb42ce..4cbc6b290dd5 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -169,64 +169,13 @@ out:
 	return nf_conntrack_confirm(skb);
 }
 
-static unsigned int __ipv6_conntrack_in(struct net *net,
-					unsigned int hooknum,
-					struct sk_buff *skb,
-					const struct net_device *in,
-					const struct net_device *out,
-					int (*okfn)(struct sk_buff *))
-{
-	struct sk_buff *reasm = skb->nfct_reasm;
-	const struct nf_conn_help *help;
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-
-	/* This packet is fragmented and has reassembled packet. */
-	if (reasm) {
-		/* Reassembled packet isn't parsed yet ? */
-		if (!reasm->nfct) {
-			unsigned int ret;
-
-			ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-
-		/* Conntrack helpers need the entire reassembled packet in the
-		 * POST_ROUTING hook. In case of unconfirmed connections NAT
-		 * might reassign a helper, so the entire packet is also
-		 * required.
-		 */
-		ct = nf_ct_get(reasm, &ctinfo);
-		if (ct != NULL && !nf_ct_is_untracked(ct)) {
-			help = nfct_help(ct);
-			if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
-				nf_conntrack_get_reasm(reasm);
-				NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
-					       (struct net_device *)in,
-					       (struct net_device *)out,
-					       okfn, NF_IP6_PRI_CONNTRACK + 1);
-				return NF_DROP_ERR(-ECANCELED);
-			}
-		}
-
-		nf_conntrack_get(reasm->nfct);
-		skb->nfct = reasm->nfct;
-		skb->nfctinfo = reasm->nfctinfo;
-		return NF_ACCEPT;
-	}
-
-	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
-}
-
 static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops,
 				      struct sk_buff *skb,
 				      const struct net_device *in,
 				      const struct net_device *out,
 				      int (*okfn)(struct sk_buff *))
 {
-	return __ipv6_conntrack_in(dev_net(in), ops->hooknum, skb, in, out,
-				   okfn);
+	return nf_conntrack_in(dev_net(in), PF_INET6, ops->hooknum, skb);
 }
 
 static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
@@ -240,8 +189,7 @@ static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops,
 		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
 		return NF_ACCEPT;
 	}
-	return __ipv6_conntrack_in(dev_net(out), ops->hooknum, skb, in, out,
-				   okfn);
+	return nf_conntrack_in(dev_net(out), PF_INET6, ops->hooknum, skb);
 }
 
 static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 4a258263d8ec..767ab8da8218 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -633,31 +633,16 @@ ret_orig:
 	return skb;
 }
 
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			struct net_device *in, struct net_device *out,
-			int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
 {
 	struct sk_buff *s, *s2;
-	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
-		nf_conntrack_put_reasm(s->nfct_reasm);
-		nf_conntrack_get_reasm(skb);
-		s->nfct_reasm = skb;
-
 		s2 = s->next;
 		s->next = NULL;
-
-		if (ret != -ECANCELED)
-			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
-					     in, out, okfn,
-					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
-		else
-			kfree_skb(s);
-
+		consume_skb(s);
 		s = s2;
 	}
-	nf_conntrack_put_reasm(skb);
 }
 
 static int nf_ct_net_init(struct net *net)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index ec483aa3f60f..7b9a748c6bac 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops,
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(ops->hooknum, reasm, (struct net_device *)in,
-			   (struct net_device *)out, okfn);
+	nf_ct_frag6_consume_orig(reasm);
+
+	NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, reasm,
+		       (struct net_device *) in, (struct net_device *) out,
+		       okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
 
 	return NF_STOLEN;
 }
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 34fda62f40f6..4f26ee46b51f 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1139,12 +1139,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
 	ip_vs_fill_iph_skb(af, skb, &iph);
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
-			struct sk_buff *reasm = skb_nfct_reasm(skb);
-			/* Save fw mark for coming frags */
-			reasm->ipvs_property = 1;
-			reasm->mark = skb->mark;
-		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1614,12 +1608,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (!iph.fragoffs && skb_nfct_reasm(skb)) {
-			struct sk_buff *reasm = skb_nfct_reasm(skb);
-			/* Save fw mark for coming frags. */
-			reasm->ipvs_property = 1;
-			reasm->mark = skb->mark;
-		}
 		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
 			int related;
 			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
@@ -1671,9 +1659,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 		/* sorry, all this trouble for a no-hit :) */
 		IP_VS_DBG_PKT(12, af, pp, skb, 0,
 			      "ip_vs_in: packet continues traversal as normal");
-		if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+		if (iph.fragoffs) {
 			/* Fragment that couldn't be mapped to a conn entry
-			 * and don't have any pointer to a reasm skb
 			 * is missing module nf_defrag_ipv6
 			 */
 			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
@@ -1755,38 +1742,6 @@ ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
 
 #ifdef CONFIG_IP_VS_IPV6
 
-/*
- * AF_INET6 fragment handling
- * Copy info from first fragment, to the rest of them.
- */
-static unsigned int
-ip_vs_preroute_frag6(const struct nf_hook_ops *ops, struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
-{
-	struct sk_buff *reasm = skb_nfct_reasm(skb);
-	struct net *net;
-
-	/* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
-	 * ipvs_property is set when checking first fragment
-	 * in ip_vs_in() and ip_vs_out().
-	 */
-	if (reasm)
-		IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
-	if (!reasm || !reasm->ipvs_property)
-		return NF_ACCEPT;
-
-	net = skb_net(skb);
-	if (!net_ipvs(net)->enable)
-		return NF_ACCEPT;
-
-	/* Copy stored fw mark, saved in ip_vs_{in,out} */
-	skb->mark = reasm->mark;
-
-	return NF_ACCEPT;
-}
-
 /*
  *	AF_INET6 handler in NF_INET_LOCAL_IN chain
  *	Schedule and forward packets from remote clients
@@ -1924,14 +1879,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 		.priority	= 100,
 	},
 #ifdef CONFIG_IP_VS_IPV6
-	/* After mangle & nat fetch 2:nd fragment and following */
-	{
-		.hook		= ip_vs_preroute_frag6,
-		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP6_PRI_NAT_DST + 1,
-	},
 	/* After packet filtering, change source only for VS/NAT */
 	{
 		.hook		= ip_vs_reply6,
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 9ef22bdce9f1..bed5f7042529 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -65,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff,
 static int
 ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 {
-	struct sk_buff *reasm = skb_nfct_reasm(skb);
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;
@@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 	/* todo: IPv6 fragments:
 	 *       I think this only should be done for the first fragment. /HS
 	 */
-	if (reasm) {
-		skb = reasm;
-		dataoff = iph.thoff_reasm + sizeof(struct udphdr);
-	} else
-		dataoff = iph.len + sizeof(struct udphdr);
+	dataoff = iph.len + sizeof(struct udphdr);
 
 	if (dataoff >= skb->len)
 		return -EINVAL;
-	/* todo: Check if this will mess-up the reasm skb !!! /HS */
 	retc = skb_linearize(skb);
 	if (retc < 0)
 		return retc;
-- 
cgit 


From e267cb960ab790c94a5019272c0e4dac95dc4dba Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 11 Nov 2013 00:42:07 -0500
Subject: vlan: Implement vlan_dev_get_egress_qos_mask as an inline.

This is to avoid very silly Kconfig dependencies for modules
using this routine.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 98 ++++++++++++++++++++++++++++++++++++++++++++++++-
 net/8021q/vlan.h        | 77 --------------------------------------
 net/8021q/vlan_dev.c    | 31 ++--------------
 3 files changed, 99 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index f3088a0112cf..f252deb99454 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -88,8 +88,102 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
-extern u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
-					u32 skprio);
+
+/**
+ *	struct vlan_priority_tci_mapping - vlan egress priority mappings
+ *	@priority: skb priority
+ *	@vlan_qos: vlan priority: (skb->priority << 13) & 0xE000
+ *	@next: pointer to next struct
+ */
+struct vlan_priority_tci_mapping {
+	u32					priority;
+	u16					vlan_qos;
+	struct vlan_priority_tci_mapping	*next;
+};
+
+/**
+ *	struct vlan_pcpu_stats - VLAN percpu rx/tx stats
+ *	@rx_packets: number of received packets
+ *	@rx_bytes: number of received bytes
+ *	@rx_multicast: number of received multicast packets
+ *	@tx_packets: number of transmitted packets
+ *	@tx_bytes: number of transmitted bytes
+ *	@syncp: synchronization point for 64bit counters
+ *	@rx_errors: number of rx errors
+ *	@tx_dropped: number of tx drops
+ */
+struct vlan_pcpu_stats {
+	u64			rx_packets;
+	u64			rx_bytes;
+	u64			rx_multicast;
+	u64			tx_packets;
+	u64			tx_bytes;
+	struct u64_stats_sync	syncp;
+	u32			rx_errors;
+	u32			tx_dropped;
+};
+
+struct proc_dir_entry;
+struct netpoll;
+
+/**
+ *	struct vlan_dev_priv - VLAN private device data
+ *	@nr_ingress_mappings: number of ingress priority mappings
+ *	@ingress_priority_map: ingress priority mappings
+ *	@nr_egress_mappings: number of egress priority mappings
+ *	@egress_priority_map: hash of egress priority mappings
+ *	@vlan_proto: VLAN encapsulation protocol
+ *	@vlan_id: VLAN identifier
+ *	@flags: device flags
+ *	@real_dev: underlying netdevice
+ *	@real_dev_addr: address of underlying netdevice
+ *	@dent: proc dir entry
+ *	@vlan_pcpu_stats: ptr to percpu rx stats
+ */
+struct vlan_dev_priv {
+	unsigned int				nr_ingress_mappings;
+	u32					ingress_priority_map[8];
+	unsigned int				nr_egress_mappings;
+	struct vlan_priority_tci_mapping	*egress_priority_map[16];
+
+	__be16					vlan_proto;
+	u16					vlan_id;
+	u16					flags;
+
+	struct net_device			*real_dev;
+	unsigned char				real_dev_addr[ETH_ALEN];
+
+	struct proc_dir_entry			*dent;
+	struct vlan_pcpu_stats __percpu		*vlan_pcpu_stats;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll				*netpoll;
+#endif
+};
+
+static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+static inline u16
+vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
+{
+	struct vlan_priority_tci_mapping *mp;
+
+	smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
+
+	mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)];
+	while (mp) {
+		if (mp->priority == skprio) {
+			return mp->vlan_qos; /* This should already be shifted
+					      * to mask correctly with the
+					      * VLAN's TCI */
+		}
+		mp = mp->next;
+	}
+	return 0;
+}
+
 extern bool vlan_do_receive(struct sk_buff **skb);
 extern struct sk_buff *vlan_untag(struct sk_buff *skb);
 
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index a2caf00b82cc..5704ed9c3a23 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -5,83 +5,6 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/list.h>
 
-
-/**
- *	struct vlan_priority_tci_mapping - vlan egress priority mappings
- *	@priority: skb priority
- *	@vlan_qos: vlan priority: (skb->priority << 13) & 0xE000
- *	@next: pointer to next struct
- */
-struct vlan_priority_tci_mapping {
-	u32					priority;
-	u16					vlan_qos;
-	struct vlan_priority_tci_mapping	*next;
-};
-
-
-/**
- *	struct vlan_pcpu_stats - VLAN percpu rx/tx stats
- *	@rx_packets: number of received packets
- *	@rx_bytes: number of received bytes
- *	@rx_multicast: number of received multicast packets
- *	@tx_packets: number of transmitted packets
- *	@tx_bytes: number of transmitted bytes
- *	@syncp: synchronization point for 64bit counters
- *	@rx_errors: number of rx errors
- *	@tx_dropped: number of tx drops
- */
-struct vlan_pcpu_stats {
-	u64			rx_packets;
-	u64			rx_bytes;
-	u64			rx_multicast;
-	u64			tx_packets;
-	u64			tx_bytes;
-	struct u64_stats_sync	syncp;
-	u32			rx_errors;
-	u32			tx_dropped;
-};
-
-struct netpoll;
-
-/**
- *	struct vlan_dev_priv - VLAN private device data
- *	@nr_ingress_mappings: number of ingress priority mappings
- *	@ingress_priority_map: ingress priority mappings
- *	@nr_egress_mappings: number of egress priority mappings
- *	@egress_priority_map: hash of egress priority mappings
- *	@vlan_proto: VLAN encapsulation protocol
- *	@vlan_id: VLAN identifier
- *	@flags: device flags
- *	@real_dev: underlying netdevice
- *	@real_dev_addr: address of underlying netdevice
- *	@dent: proc dir entry
- *	@vlan_pcpu_stats: ptr to percpu rx stats
- */
-struct vlan_dev_priv {
-	unsigned int				nr_ingress_mappings;
-	u32					ingress_priority_map[8];
-	unsigned int				nr_egress_mappings;
-	struct vlan_priority_tci_mapping	*egress_priority_map[16];
-
-	__be16					vlan_proto;
-	u16					vlan_id;
-	u16					flags;
-
-	struct net_device			*real_dev;
-	unsigned char				real_dev_addr[ETH_ALEN];
-
-	struct proc_dir_entry			*dent;
-	struct vlan_pcpu_stats __percpu		*vlan_pcpu_stats;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	struct netpoll				*netpoll;
-#endif
-};
-
-static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
-{
-	return netdev_priv(dev);
-}
-
 /* if this changes, algorithm will have to be reworked because this
  * depends on completely exhausting the VLAN identifier space.  Thus
  * it gives constant time look-up, but in many cases it wastes memory.
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 13904a414929..8db1b985dbf1 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -68,31 +68,6 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb)
 	return 0;
 }
 
-static inline u16
-__vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
-{
-	struct vlan_priority_tci_mapping *mp;
-
-	smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
-
-	mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)];
-	while (mp) {
-		if (mp->priority == skprio) {
-			return mp->vlan_qos; /* This should already be shifted
-					      * to mask correctly with the
-					      * VLAN's TCI */
-		}
-		mp = mp->next;
-	}
-	return 0;
-}
-
-u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
-{
-	return __vlan_dev_get_egress_qos_mask(dev, skprio);
-}
-EXPORT_SYMBOL(vlan_dev_get_egress_qos_mask);
-
 /*
  *	Create the VLAN header for an arbitrary protocol layer
  *
@@ -117,7 +92,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
 
 		vlan_tci = vlan->vlan_id;
-		vlan_tci |= __vlan_dev_get_egress_qos_mask(dev, skb->priority);
+		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
 		vhdr->h_vlan_TCI = htons(vlan_tci);
 
 		/*
@@ -174,7 +149,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 	    vlan->flags & VLAN_FLAG_REORDER_HDR) {
 		u16 vlan_tci;
 		vlan_tci = vlan->vlan_id;
-		vlan_tci |= __vlan_dev_get_egress_qos_mask(dev, skb->priority);
+		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority);
 		skb = __vlan_hwaccel_put_tag(skb, vlan->vlan_proto, vlan_tci);
 	}
 
@@ -259,7 +234,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
 	np->vlan_qos = vlan_qos;
 	/* Before inserting this element in hash table, make sure all its fields
 	 * are committed to memory.
-	 * coupled with smp_rmb() in __vlan_dev_get_egress_qos_mask()
+	 * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
 	 */
 	smp_wmb();
 	vlan->egress_priority_map[skb_prio & 0xF] = np;
-- 
cgit 


From 220bb38c21b83e2f7b842f33220bf727093eca89 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kmo@daterainc.com>
Date: Tue, 10 Sep 2013 19:02:45 -0700
Subject: bcache: Break up struct search

With all the recent refactoring around struct btree op struct search has
gotten rather large.

But we can now easily break it up in a different way - we break out
struct btree_insert_op which is for inserting data into the cache, and
that's now what the copying gc code uses - struct search is now specific
to request.c

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
---
 drivers/md/bcache/debug.c     |  38 +--
 drivers/md/bcache/debug.h     |   4 +-
 drivers/md/bcache/movinggc.c  |  56 ++--
 drivers/md/bcache/request.c   | 580 ++++++++++++++++++++++--------------------
 drivers/md/bcache/request.h   |  37 +--
 drivers/md/bcache/stats.c     |  26 +-
 drivers/md/bcache/stats.h     |  13 +-
 drivers/md/bcache/trace.c     |   1 -
 include/trace/events/bcache.h |  18 +-
 9 files changed, 378 insertions(+), 395 deletions(-)

(limited to 'include')

diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 88e6411eab4f..d9ccb3169aa2 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -8,7 +8,6 @@
 #include "bcache.h"
 #include "btree.h"
 #include "debug.h"
-#include "request.h"
 
 #include <linux/console.h>
 #include <linux/debugfs.h>
@@ -176,42 +175,25 @@ void bch_btree_verify(struct btree *b, struct bset *new)
 	mutex_unlock(&b->c->verify_lock);
 }
 
-static void data_verify_endio(struct bio *bio, int error)
-{
-	struct closure *cl = bio->bi_private;
-	closure_put(cl);
-}
-
-void bch_data_verify(struct search *s)
+void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 {
 	char name[BDEVNAME_SIZE];
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
-	struct closure *cl = &s->cl;
 	struct bio *check;
 	struct bio_vec *bv;
 	int i;
 
-	if (!s->unaligned_bvec)
-		bio_for_each_segment(bv, s->orig_bio, i)
-			bv->bv_offset = 0, bv->bv_len = PAGE_SIZE;
-
-	check = bio_clone(s->orig_bio, GFP_NOIO);
+	check = bio_clone(bio, GFP_NOIO);
 	if (!check)
 		return;
 
 	if (bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
-	check->bi_rw		= READ_SYNC;
-	check->bi_private	= cl;
-	check->bi_end_io	= data_verify_endio;
-
-	closure_bio_submit(check, cl, &dc->disk);
-	closure_sync(cl);
+	submit_bio_wait(READ_SYNC, check);
 
-	bio_for_each_segment(bv, s->orig_bio, i) {
-		void *p1 = kmap(bv->bv_page);
-		void *p2 = kmap(check->bi_io_vec[i].bv_page);
+	bio_for_each_segment(bv, bio, i) {
+		void *p1 = kmap_atomic(bv->bv_page);
+		void *p2 = page_address(check->bi_io_vec[i].bv_page);
 
 		if (memcmp(p1 + bv->bv_offset,
 			   p2 + bv->bv_offset,
@@ -219,13 +201,11 @@ void bch_data_verify(struct search *s)
 			printk(KERN_ERR
 			       "bcache (%s): verify failed at sector %llu\n",
 			       bdevname(dc->bdev, name),
-			       (uint64_t) s->orig_bio->bi_sector);
-
-		kunmap(bv->bv_page);
-		kunmap(check->bi_io_vec[i].bv_page);
+			       (uint64_t) bio->bi_sector);
+		kunmap_atomic(p1);
 	}
 
-	__bio_for_each_segment(bv, check, i, 0)
+	bio_for_each_segment_all(bv, check, i)
 		__free_page(bv->bv_page);
 out_put:
 	bio_put(check);
diff --git a/drivers/md/bcache/debug.h b/drivers/md/bcache/debug.h
index 1c39b5a2489b..0f4b3440512c 100644
--- a/drivers/md/bcache/debug.h
+++ b/drivers/md/bcache/debug.h
@@ -29,12 +29,12 @@ void bch_check_keys(struct btree *, const char *, ...);
 #ifdef CONFIG_BCACHE_DEBUG
 
 void bch_btree_verify(struct btree *, struct bset *);
-void bch_data_verify(struct search *);
+void bch_data_verify(struct cached_dev *, struct bio *);
 
 #else /* DEBUG */
 
 static inline void bch_btree_verify(struct btree *b, struct bset *i) {}
-static inline void bch_data_verify(struct search *s) {};
+static inline void bch_data_verify(struct cached_dev *dc, struct bio *bio) {};
 
 #endif
 
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 601c96a62b30..7c1275e66025 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -12,8 +12,9 @@
 #include <trace/events/bcache.h>
 
 struct moving_io {
+	struct closure		cl;
 	struct keybuf_key	*w;
-	struct search		s;
+	struct data_insert_op	op;
 	struct bbio		bio;
 };
 
@@ -38,13 +39,13 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 
 static void moving_io_destructor(struct closure *cl)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	struct moving_io *io = container_of(cl, struct moving_io, cl);
 	kfree(io);
 }
 
 static void write_moving_finish(struct closure *cl)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	struct moving_io *io = container_of(cl, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 	struct bio_vec *bv;
 	int i;
@@ -52,12 +53,12 @@ static void write_moving_finish(struct closure *cl)
 	bio_for_each_segment_all(bv, bio, i)
 		__free_page(bv->bv_page);
 
-	if (io->s.insert_collision)
+	if (io->op.replace_collision)
 		trace_bcache_gc_copy_collision(&io->w->key);
 
-	bch_keybuf_del(&io->s.c->moving_gc_keys, io->w);
+	bch_keybuf_del(&io->op.c->moving_gc_keys, io->w);
 
-	up(&io->s.c->moving_in_flight);
+	up(&io->op.c->moving_in_flight);
 
 	closure_return_with_destructor(cl, moving_io_destructor);
 }
@@ -65,12 +66,12 @@ static void write_moving_finish(struct closure *cl)
 static void read_moving_endio(struct bio *bio, int error)
 {
 	struct moving_io *io = container_of(bio->bi_private,
-					    struct moving_io, s.cl);
+					    struct moving_io, cl);
 
 	if (error)
-		io->s.error = error;
+		io->op.error = error;
 
-	bch_bbio_endio(io->s.c, bio, error, "reading data to move");
+	bch_bbio_endio(io->op.c, bio, error, "reading data to move");
 }
 
 static void moving_init(struct moving_io *io)
@@ -84,32 +85,30 @@ static void moving_init(struct moving_io *io)
 	bio->bi_size		= KEY_SIZE(&io->w->key) << 9;
 	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&io->w->key),
 					       PAGE_SECTORS);
-	bio->bi_private		= &io->s.cl;
+	bio->bi_private		= &io->cl;
 	bio->bi_io_vec		= bio->bi_inline_vecs;
 	bch_bio_map(bio, NULL);
 }
 
 static void write_moving(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, cl);
-	struct moving_io *io = container_of(s, struct moving_io, s);
+	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	struct data_insert_op *op = &io->op;
 
-	if (!s->error) {
+	if (!op->error) {
 		moving_init(io);
 
-		io->bio.bio.bi_sector	= KEY_START(&io->w->key);
-		s->op.lock		= -1;
-		s->write_prio		= 1;
-		s->cache_bio		= &io->bio.bio;
+		io->bio.bio.bi_sector = KEY_START(&io->w->key);
+		op->write_prio		= 1;
+		op->bio			= &io->bio.bio;
 
-		s->writeback		= KEY_DIRTY(&io->w->key);
-		s->csum			= KEY_CSUM(&io->w->key);
+		op->writeback		= KEY_DIRTY(&io->w->key);
+		op->csum		= KEY_CSUM(&io->w->key);
 
-		bkey_copy(&s->replace_key, &io->w->key);
-		s->replace = true;
+		bkey_copy(&op->replace_key, &io->w->key);
+		op->replace		= true;
 
-		closure_init(&s->btree, cl);
-		bch_data_insert(&s->btree);
+		closure_call(&op->cl, bch_data_insert, NULL, cl);
 	}
 
 	continue_at(cl, write_moving_finish, system_wq);
@@ -117,11 +116,10 @@ static void write_moving(struct closure *cl)
 
 static void read_moving_submit(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, cl);
-	struct moving_io *io = container_of(s, struct moving_io, s);
+	struct moving_io *io = container_of(cl, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
-	bch_submit_bbio(bio, s->c, &io->w->key, 0);
+	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
 
 	continue_at(cl, write_moving, system_wq);
 }
@@ -151,8 +149,8 @@ static void read_moving(struct cache_set *c)
 
 		w->private	= io;
 		io->w		= w;
-		io->s.inode	= KEY_INODE(&w->key);
-		io->s.c		= c;
+		io->op.inode	= KEY_INODE(&w->key);
+		io->op.c	= c;
 
 		moving_init(io);
 		bio = &io->bio.bio;
@@ -166,7 +164,7 @@ static void read_moving(struct cache_set *c)
 		trace_bcache_gc_copy(&w->key);
 
 		down(&c->moving_in_flight);
-		closure_call(&io->s.cl, read_moving_submit, NULL, &cl);
+		closure_call(&io->cl, read_moving_submit, NULL, &cl);
 	}
 
 	if (0) {
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 6cee2ae1d87f..05c7c216f65e 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -215,9 +215,9 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 static void bch_data_insert_keys(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	atomic_t *journal_ref = NULL;
-	struct bkey *replace_key = s->replace ? &s->replace_key : NULL;
+	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
 
 	/*
@@ -232,27 +232,26 @@ static void bch_data_insert_keys(struct closure *cl)
 		closure_sync(&s->cl);
 #endif
 
-	if (s->write)
-		journal_ref = bch_journal(s->c, &s->insert_keys,
-					  s->flush_journal
-					  ? &s->cl : NULL);
+	if (!op->replace)
+		journal_ref = bch_journal(op->c, &op->insert_keys,
+					  op->flush_journal ? cl : NULL);
 
-	ret = bch_btree_insert(s->c, &s->insert_keys,
+	ret = bch_btree_insert(op->c, &op->insert_keys,
 			       journal_ref, replace_key);
 	if (ret == -ESRCH) {
-		s->insert_collision = true;
+		op->replace_collision = true;
 	} else if (ret) {
-		s->error		= -ENOMEM;
-		s->insert_data_done	= true;
+		op->error		= -ENOMEM;
+		op->insert_data_done	= true;
 	}
 
 	if (journal_ref)
 		atomic_dec_bug(journal_ref);
 
-	if (!s->insert_data_done)
+	if (!op->insert_data_done)
 		continue_at(cl, bch_data_insert_start, bcache_wq);
 
-	bch_keylist_free(&s->insert_keys);
+	bch_keylist_free(&op->insert_keys);
 	closure_return(cl);
 }
 
@@ -349,10 +348,10 @@ found:
  *
  * If s->writeback is true, will not fail.
  */
-static bool bch_alloc_sectors(struct bkey *k, unsigned sectors,
-			      struct search *s)
+static bool bch_alloc_sectors(struct data_insert_op *op,
+			      struct bkey *k, unsigned sectors)
 {
-	struct cache_set *c = s->c;
+	struct cache_set *c = op->c;
 	struct open_bucket *b;
 	BKEY_PADDED(key) alloc;
 	unsigned i;
@@ -367,15 +366,15 @@ static bool bch_alloc_sectors(struct bkey *k, unsigned sectors,
 	bkey_init(&alloc.key);
 	spin_lock(&c->data_bucket_lock);
 
-	while (!(b = pick_data_bucket(c, k, s->task, &alloc.key))) {
-		unsigned watermark = s->write_prio
+	while (!(b = pick_data_bucket(c, k, op->task, &alloc.key))) {
+		unsigned watermark = op->write_prio
 			? WATERMARK_MOVINGGC
 			: WATERMARK_NONE;
 
 		spin_unlock(&c->data_bucket_lock);
 
 		if (bch_bucket_alloc_set(c, watermark, &alloc.key,
-					 1, s->writeback))
+					 1, op->writeback))
 			return false;
 
 		spin_lock(&c->data_bucket_lock);
@@ -409,7 +408,7 @@ static bool bch_alloc_sectors(struct bkey *k, unsigned sectors,
 	 */
 	list_move_tail(&b->list, &c->data_buckets);
 	bkey_copy_key(&b->key, k);
-	b->last = s->task;
+	b->last = op->task;
 
 	b->sectors_free	-= sectors;
 
@@ -438,8 +437,8 @@ static bool bch_alloc_sectors(struct bkey *k, unsigned sectors,
 
 static void bch_data_invalidate(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
-	struct bio *bio = s->cache_bio;
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	struct bio *bio = op->bio;
 
 	pr_debug("invalidating %i sectors from %llu",
 		 bio_sectors(bio), (uint64_t) bio->bi_sector);
@@ -447,17 +446,17 @@ static void bch_data_invalidate(struct closure *cl)
 	while (bio_sectors(bio)) {
 		unsigned len = min(bio_sectors(bio), 1U << 14);
 
-		if (bch_keylist_realloc(&s->insert_keys, 0, s->c))
+		if (bch_keylist_realloc(&op->insert_keys, 0, op->c))
 			goto out;
 
 		bio->bi_sector	+= len;
 		bio->bi_size	-= len << 9;
 
-		bch_keylist_add(&s->insert_keys,
-				&KEY(s->inode, bio->bi_sector, len));
+		bch_keylist_add(&op->insert_keys,
+				&KEY(op->inode, bio->bi_sector, len));
 	}
 
-	s->insert_data_done = true;
+	op->insert_data_done = true;
 	bio_put(bio);
 out:
 	continue_at(cl, bch_data_insert_keys, bcache_wq);
@@ -465,7 +464,7 @@ out:
 
 static void bch_data_insert_error(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
 	/*
 	 * Our data write just errored, which means we've got a bunch of keys to
@@ -476,9 +475,9 @@ static void bch_data_insert_error(struct closure *cl)
 	 * from the keys we'll accomplish just that.
 	 */
 
-	struct bkey *src = s->insert_keys.keys, *dst = s->insert_keys.keys;
+	struct bkey *src = op->insert_keys.keys, *dst = op->insert_keys.keys;
 
-	while (src != s->insert_keys.top) {
+	while (src != op->insert_keys.top) {
 		struct bkey *n = bkey_next(src);
 
 		SET_KEY_PTRS(src, 0);
@@ -488,7 +487,7 @@ static void bch_data_insert_error(struct closure *cl)
 		src = n;
 	}
 
-	s->insert_keys.top = dst;
+	op->insert_keys.top = dst;
 
 	bch_data_insert_keys(cl);
 }
@@ -496,32 +495,32 @@ static void bch_data_insert_error(struct closure *cl)
 static void bch_data_insert_endio(struct bio *bio, int error)
 {
 	struct closure *cl = bio->bi_private;
-	struct search *s = container_of(cl, struct search, btree);
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
 	if (error) {
 		/* TODO: We could try to recover from this. */
-		if (s->writeback)
-			s->error = error;
-		else if (s->write)
+		if (op->writeback)
+			op->error = error;
+		else if (!op->replace)
 			set_closure_fn(cl, bch_data_insert_error, bcache_wq);
 		else
 			set_closure_fn(cl, NULL, NULL);
 	}
 
-	bch_bbio_endio(s->c, bio, error, "writing data to cache");
+	bch_bbio_endio(op->c, bio, error, "writing data to cache");
 }
 
 static void bch_data_insert_start(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
-	struct bio *bio = s->cache_bio, *n;
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	struct bio *bio = op->bio, *n;
 
-	if (s->bypass)
+	if (op->bypass)
 		return bch_data_invalidate(cl);
 
-	if (atomic_sub_return(bio_sectors(bio), &s->c->sectors_to_gc) < 0) {
-		set_gc_sectors(s->c);
-		wake_up_gc(s->c);
+	if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) {
+		set_gc_sectors(op->c);
+		wake_up_gc(op->c);
 	}
 
 	/*
@@ -533,21 +532,20 @@ static void bch_data_insert_start(struct closure *cl)
 	do {
 		unsigned i;
 		struct bkey *k;
-		struct bio_set *split = s->d
-			? s->d->bio_split : s->c->bio_split;
+		struct bio_set *split = op->c->bio_split;
 
 		/* 1 for the device pointer and 1 for the chksum */
-		if (bch_keylist_realloc(&s->insert_keys,
-					1 + (s->csum ? 1 : 0),
-					s->c))
+		if (bch_keylist_realloc(&op->insert_keys,
+					1 + (op->csum ? 1 : 0),
+					op->c))
 			continue_at(cl, bch_data_insert_keys, bcache_wq);
 
-		k = s->insert_keys.top;
+		k = op->insert_keys.top;
 		bkey_init(k);
-		SET_KEY_INODE(k, s->inode);
+		SET_KEY_INODE(k, op->inode);
 		SET_KEY_OFFSET(k, bio->bi_sector);
 
-		if (!bch_alloc_sectors(k, bio_sectors(bio), s))
+		if (!bch_alloc_sectors(op, k, bio_sectors(bio)))
 			goto err;
 
 		n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split);
@@ -555,30 +553,30 @@ static void bch_data_insert_start(struct closure *cl)
 		n->bi_end_io	= bch_data_insert_endio;
 		n->bi_private	= cl;
 
-		if (s->writeback) {
+		if (op->writeback) {
 			SET_KEY_DIRTY(k, true);
 
 			for (i = 0; i < KEY_PTRS(k); i++)
-				SET_GC_MARK(PTR_BUCKET(s->c, k, i),
+				SET_GC_MARK(PTR_BUCKET(op->c, k, i),
 					    GC_MARK_DIRTY);
 		}
 
-		SET_KEY_CSUM(k, s->csum);
+		SET_KEY_CSUM(k, op->csum);
 		if (KEY_CSUM(k))
 			bio_csum(n, k);
 
 		trace_bcache_cache_insert(k);
-		bch_keylist_push(&s->insert_keys);
+		bch_keylist_push(&op->insert_keys);
 
 		n->bi_rw |= REQ_WRITE;
-		bch_submit_bbio(n, s->c, k, 0);
+		bch_submit_bbio(n, op->c, k, 0);
 	} while (n != bio);
 
-	s->insert_data_done = true;
+	op->insert_data_done = true;
 	continue_at(cl, bch_data_insert_keys, bcache_wq);
 err:
 	/* bch_alloc_sectors() blocks if s->writeback = true */
-	BUG_ON(s->writeback);
+	BUG_ON(op->writeback);
 
 	/*
 	 * But if it's not a writeback write we'd rather just bail out if
@@ -586,24 +584,24 @@ err:
 	 * we might be starving btree writes for gc or something.
 	 */
 
-	if (s->write) {
+	if (!op->replace) {
 		/*
 		 * Writethrough write: We can't complete the write until we've
 		 * updated the index. But we don't want to delay the write while
 		 * we wait for buckets to be freed up, so just invalidate the
 		 * rest of the write.
 		 */
-		s->bypass = true;
+		op->bypass = true;
 		return bch_data_invalidate(cl);
 	} else {
 		/*
 		 * From a cache miss, we can just insert the keys for the data
 		 * we have written or bail out if we didn't do anything.
 		 */
-		s->insert_data_done = true;
+		op->insert_data_done = true;
 		bio_put(bio);
 
-		if (!bch_keylist_empty(&s->insert_keys))
+		if (!bch_keylist_empty(&op->insert_keys))
 			continue_at(cl, bch_data_insert_keys, bcache_wq);
 		else
 			closure_return(cl);
@@ -631,15 +629,169 @@ err:
  */
 void bch_data_insert(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
+	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	bch_keylist_init(&s->insert_keys);
-	bio_get(s->cache_bio);
+	trace_bcache_write(op->bio, op->writeback, op->bypass);
+
+	bch_keylist_init(&op->insert_keys);
+	bio_get(op->bio);
 	bch_data_insert_start(cl);
 }
 
+/* Congested? */
+
+unsigned bch_get_congested(struct cache_set *c)
+{
+	int i;
+	long rand;
+
+	if (!c->congested_read_threshold_us &&
+	    !c->congested_write_threshold_us)
+		return 0;
+
+	i = (local_clock_us() - c->congested_last_us) / 1024;
+	if (i < 0)
+		return 0;
+
+	i += atomic_read(&c->congested);
+	if (i >= 0)
+		return 0;
+
+	i += CONGESTED_MAX;
+
+	if (i > 0)
+		i = fract_exp_two(i, 6);
+
+	rand = get_random_int();
+	i -= bitmap_weight(&rand, BITS_PER_LONG);
+
+	return i > 0 ? i : 1;
+}
+
+static void add_sequential(struct task_struct *t)
+{
+	ewma_add(t->sequential_io_avg,
+		 t->sequential_io, 8, 0);
+
+	t->sequential_io = 0;
+}
+
+static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
+{
+	return &dc->io_hash[hash_64(k, RECENT_IO_BITS)];
+}
+
+static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
+{
+	struct cache_set *c = dc->disk.c;
+	unsigned mode = cache_mode(dc, bio);
+	unsigned sectors, congested = bch_get_congested(c);
+	struct task_struct *task = current;
+
+	if (atomic_read(&dc->disk.detaching) ||
+	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
+	    (bio->bi_rw & REQ_DISCARD))
+		goto skip;
+
+	if (mode == CACHE_MODE_NONE ||
+	    (mode == CACHE_MODE_WRITEAROUND &&
+	     (bio->bi_rw & REQ_WRITE)))
+		goto skip;
+
+	if (bio->bi_sector & (c->sb.block_size - 1) ||
+	    bio_sectors(bio) & (c->sb.block_size - 1)) {
+		pr_debug("skipping unaligned io");
+		goto skip;
+	}
+
+	if (!congested && !dc->sequential_cutoff)
+		goto rescale;
+
+	if (!congested &&
+	    mode == CACHE_MODE_WRITEBACK &&
+	    (bio->bi_rw & REQ_WRITE) &&
+	    (bio->bi_rw & REQ_SYNC))
+		goto rescale;
+
+	if (dc->sequential_merge) {
+		struct io *i;
+
+		spin_lock(&dc->io_lock);
+
+		hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash)
+			if (i->last == bio->bi_sector &&
+			    time_before(jiffies, i->jiffies))
+				goto found;
+
+		i = list_first_entry(&dc->io_lru, struct io, lru);
+
+		add_sequential(task);
+		i->sequential = 0;
+found:
+		if (i->sequential + bio->bi_size > i->sequential)
+			i->sequential	+= bio->bi_size;
+
+		i->last			 = bio_end_sector(bio);
+		i->jiffies		 = jiffies + msecs_to_jiffies(5000);
+		task->sequential_io	 = i->sequential;
+
+		hlist_del(&i->hash);
+		hlist_add_head(&i->hash, iohash(dc, i->last));
+		list_move_tail(&i->lru, &dc->io_lru);
+
+		spin_unlock(&dc->io_lock);
+	} else {
+		task->sequential_io = bio->bi_size;
+
+		add_sequential(task);
+	}
+
+	sectors = max(task->sequential_io,
+		      task->sequential_io_avg) >> 9;
+
+	if (dc->sequential_cutoff &&
+	    sectors >= dc->sequential_cutoff >> 9) {
+		trace_bcache_bypass_sequential(bio);
+		goto skip;
+	}
+
+	if (congested && sectors >= congested) {
+		trace_bcache_bypass_congested(bio);
+		goto skip;
+	}
+
+rescale:
+	bch_rescale_priorities(c, bio_sectors(bio));
+	return false;
+skip:
+	bch_mark_sectors_bypassed(c, dc, bio_sectors(bio));
+	return true;
+}
+
 /* Cache lookup */
 
+struct search {
+	/* Stack frame for bio_complete */
+	struct closure		cl;
+
+	struct bcache_device	*d;
+
+	struct bbio		bio;
+	struct bio		*orig_bio;
+	struct bio		*cache_miss;
+
+	unsigned		insert_bio_sectors;
+
+	unsigned		recoverable:1;
+	unsigned		unaligned_bvec:1;
+	unsigned		write:1;
+
+	unsigned long		start_time;
+
+	struct btree_op		op;
+	struct data_insert_op	iop;
+};
+
 static void bch_cache_read_endio(struct bio *bio, int error)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
@@ -654,13 +806,13 @@ static void bch_cache_read_endio(struct bio *bio, int error)
 	 */
 
 	if (error)
-		s->error = error;
-	else if (ptr_stale(s->c, &b->key, 0)) {
-		atomic_long_inc(&s->c->cache_read_races);
-		s->error = -EINTR;
+		s->iop.error = error;
+	else if (ptr_stale(s->iop.c, &b->key, 0)) {
+		atomic_long_inc(&s->iop.c->cache_read_races);
+		s->iop.error = -EINTR;
 	}
 
-	bch_bbio_endio(s->c, bio, error, "reading from cache");
+	bch_bbio_endio(s->iop.c, bio, error, "reading from cache");
 }
 
 /*
@@ -674,13 +826,13 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	struct bkey *bio_key;
 	unsigned ptr;
 
-	if (bkey_cmp(k, &KEY(s->inode, bio->bi_sector, 0)) <= 0)
+	if (bkey_cmp(k, &KEY(s->iop.inode, bio->bi_sector, 0)) <= 0)
 		return MAP_CONTINUE;
 
-	if (KEY_INODE(k) != s->inode ||
+	if (KEY_INODE(k) != s->iop.inode ||
 	    KEY_START(k) > bio->bi_sector) {
 		unsigned bio_sectors = bio_sectors(bio);
-		unsigned sectors = KEY_INODE(k) == s->inode
+		unsigned sectors = KEY_INODE(k) == s->iop.inode
 			? min_t(uint64_t, INT_MAX,
 				KEY_START(k) - bio->bi_sector)
 			: INT_MAX;
@@ -708,8 +860,8 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	bio_key = &container_of(n, struct bbio, bio)->key;
 	bch_bkey_copy_single_ptr(bio_key, k, ptr);
 
-	bch_cut_front(&KEY(s->inode, n->bi_sector, 0), bio_key);
-	bch_cut_back(&KEY(s->inode, bio_end_sector(n), 0), bio_key);
+	bch_cut_front(&KEY(s->iop.inode, n->bi_sector, 0), bio_key);
+	bch_cut_back(&KEY(s->iop.inode, bio_end_sector(n), 0), bio_key);
 
 	n->bi_end_io	= bch_cache_read_endio;
 	n->bi_private	= &s->cl;
@@ -731,11 +883,11 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 
 static void cache_lookup(struct closure *cl)
 {
-	struct search *s = container_of(cl, struct search, btree);
+	struct search *s = container_of(cl, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
 
-	int ret = bch_btree_map_keys(&s->op, s->c,
-				     &KEY(s->inode, bio->bi_sector, 0),
+	int ret = bch_btree_map_keys(&s->op, s->iop.c,
+				     &KEY(s->iop.inode, bio->bi_sector, 0),
 				     cache_lookup_fn, MAP_END_KEY);
 	if (ret == -EAGAIN)
 		continue_at(cl, cache_lookup, bcache_wq);
@@ -751,7 +903,7 @@ static void request_endio(struct bio *bio, int error)
 
 	if (error) {
 		struct search *s = container_of(cl, struct search, cl);
-		s->error = error;
+		s->iop.error = error;
 		/* Only cache read errors are recoverable */
 		s->recoverable = false;
 	}
@@ -771,8 +923,8 @@ static void bio_complete(struct search *s)
 		part_stat_add(cpu, &s->d->disk->part0, ticks[rw], duration);
 		part_stat_unlock();
 
-		trace_bcache_request_end(s, s->orig_bio);
-		bio_endio(s->orig_bio, s->error);
+		trace_bcache_request_end(s->d, s->orig_bio);
+		bio_endio(s->orig_bio, s->iop.error);
 		s->orig_bio = NULL;
 	}
 }
@@ -792,8 +944,8 @@ static void search_free(struct closure *cl)
 	struct search *s = container_of(cl, struct search, cl);
 	bio_complete(s);
 
-	if (s->cache_bio)
-		bio_put(s->cache_bio);
+	if (s->iop.bio)
+		bio_put(s->iop.bio);
 
 	if (s->unaligned_bvec)
 		mempool_free(s->bio.bio.bi_io_vec, s->d->unaligned_bvec);
@@ -808,18 +960,18 @@ static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
 	struct bio_vec *bv;
 
 	s = mempool_alloc(d->c->search, GFP_NOIO);
-	memset(s, 0, offsetof(struct search, insert_keys));
+	memset(s, 0, offsetof(struct search, iop.insert_keys));
 
 	__closure_init(&s->cl, NULL);
 
-	s->inode		= d->id;
-	s->c			= d->c;
+	s->iop.inode		= d->id;
+	s->iop.c		= d->c;
 	s->d			= d;
 	s->op.lock		= -1;
-	s->task			= current;
+	s->iop.task		= current;
 	s->orig_bio		= bio;
 	s->write		= (bio->bi_rw & REQ_WRITE) != 0;
-	s->flush_journal	= (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
+	s->iop.flush_journal	= (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
 	s->recoverable		= 1;
 	s->start_time		= jiffies;
 	do_bio_hook(s);
@@ -847,148 +999,20 @@ static void cached_dev_bio_complete(struct closure *cl)
 	cached_dev_put(dc);
 }
 
-unsigned bch_get_congested(struct cache_set *c)
-{
-	int i;
-	long rand;
-
-	if (!c->congested_read_threshold_us &&
-	    !c->congested_write_threshold_us)
-		return 0;
-
-	i = (local_clock_us() - c->congested_last_us) / 1024;
-	if (i < 0)
-		return 0;
-
-	i += atomic_read(&c->congested);
-	if (i >= 0)
-		return 0;
-
-	i += CONGESTED_MAX;
-
-	if (i > 0)
-		i = fract_exp_two(i, 6);
-
-	rand = get_random_int();
-	i -= bitmap_weight(&rand, BITS_PER_LONG);
-
-	return i > 0 ? i : 1;
-}
-
-static void add_sequential(struct task_struct *t)
-{
-	ewma_add(t->sequential_io_avg,
-		 t->sequential_io, 8, 0);
-
-	t->sequential_io = 0;
-}
-
-static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
-{
-	return &dc->io_hash[hash_64(k, RECENT_IO_BITS)];
-}
-
-static bool check_should_bypass(struct cached_dev *dc, struct search *s)
-{
-	struct cache_set *c = s->c;
-	struct bio *bio = &s->bio.bio;
-	unsigned mode = cache_mode(dc, bio);
-	unsigned sectors, congested = bch_get_congested(c);
-
-	if (atomic_read(&dc->disk.detaching) ||
-	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
-	    (bio->bi_rw & REQ_DISCARD))
-		goto skip;
-
-	if (mode == CACHE_MODE_NONE ||
-	    (mode == CACHE_MODE_WRITEAROUND &&
-	     (bio->bi_rw & REQ_WRITE)))
-		goto skip;
-
-	if (bio->bi_sector & (c->sb.block_size - 1) ||
-	    bio_sectors(bio) & (c->sb.block_size - 1)) {
-		pr_debug("skipping unaligned io");
-		goto skip;
-	}
-
-	if (!congested && !dc->sequential_cutoff)
-		goto rescale;
-
-	if (!congested &&
-	    mode == CACHE_MODE_WRITEBACK &&
-	    (bio->bi_rw & REQ_WRITE) &&
-	    (bio->bi_rw & REQ_SYNC))
-		goto rescale;
-
-	if (dc->sequential_merge) {
-		struct io *i;
-
-		spin_lock(&dc->io_lock);
-
-		hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash)
-			if (i->last == bio->bi_sector &&
-			    time_before(jiffies, i->jiffies))
-				goto found;
-
-		i = list_first_entry(&dc->io_lru, struct io, lru);
-
-		add_sequential(s->task);
-		i->sequential = 0;
-found:
-		if (i->sequential + bio->bi_size > i->sequential)
-			i->sequential	+= bio->bi_size;
-
-		i->last			 = bio_end_sector(bio);
-		i->jiffies		 = jiffies + msecs_to_jiffies(5000);
-		s->task->sequential_io	 = i->sequential;
-
-		hlist_del(&i->hash);
-		hlist_add_head(&i->hash, iohash(dc, i->last));
-		list_move_tail(&i->lru, &dc->io_lru);
-
-		spin_unlock(&dc->io_lock);
-	} else {
-		s->task->sequential_io = bio->bi_size;
-
-		add_sequential(s->task);
-	}
-
-	sectors = max(s->task->sequential_io,
-		      s->task->sequential_io_avg) >> 9;
-
-	if (dc->sequential_cutoff &&
-	    sectors >= dc->sequential_cutoff >> 9) {
-		trace_bcache_bypass_sequential(s->orig_bio);
-		goto skip;
-	}
-
-	if (congested && sectors >= congested) {
-		trace_bcache_bypass_congested(s->orig_bio);
-		goto skip;
-	}
-
-rescale:
-	bch_rescale_priorities(c, bio_sectors(bio));
-	return false;
-skip:
-	bch_mark_sectors_bypassed(s, bio_sectors(bio));
-	return true;
-}
-
 /* Process reads */
 
 static void cached_dev_cache_miss_done(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
-	if (s->insert_collision)
-		bch_mark_cache_miss_collision(s);
+	if (s->iop.replace_collision)
+		bch_mark_cache_miss_collision(s->iop.c, s->d);
 
-	if (s->cache_bio) {
+	if (s->iop.bio) {
 		int i;
 		struct bio_vec *bv;
 
-		bio_for_each_segment_all(bv, s->cache_bio, i)
+		bio_for_each_segment_all(bv, s->iop.bio, i)
 			__free_page(bv->bv_page);
 	}
 
@@ -1006,7 +1030,7 @@ static void cached_dev_read_error(struct closure *cl)
 		/* Retry from the backing device: */
 		trace_bcache_read_retry(s->orig_bio);
 
-		s->error = 0;
+		s->iop.error = 0;
 		bv = s->bio.bio.bi_io_vec;
 		do_bio_hook(s);
 		s->bio.bio.bi_io_vec = bv;
@@ -1041,29 +1065,28 @@ static void cached_dev_read_done(struct closure *cl)
 	 * to the buffers the original bio pointed to:
 	 */
 
-	if (s->cache_bio) {
-		bio_reset(s->cache_bio);
-		s->cache_bio->bi_sector =
-			s->cache_miss->bi_sector;
-		s->cache_bio->bi_bdev = s->cache_miss->bi_bdev;
-		s->cache_bio->bi_size = s->cache_bio_sectors << 9;
-		bch_bio_map(s->cache_bio, NULL);
+	if (s->iop.bio) {
+		bio_reset(s->iop.bio);
+		s->iop.bio->bi_sector = s->cache_miss->bi_sector;
+		s->iop.bio->bi_bdev = s->cache_miss->bi_bdev;
+		s->iop.bio->bi_size = s->insert_bio_sectors << 9;
+		bch_bio_map(s->iop.bio, NULL);
 
-		bio_copy_data(s->cache_miss, s->cache_bio);
+		bio_copy_data(s->cache_miss, s->iop.bio);
 
 		bio_put(s->cache_miss);
 		s->cache_miss = NULL;
 	}
 
-	if (verify(dc, &s->bio.bio) && s->recoverable)
-		bch_data_verify(s);
+	if (verify(dc, &s->bio.bio) && s->recoverable && !s->unaligned_bvec)
+		bch_data_verify(dc, s->orig_bio);
 
 	bio_complete(s);
 
-	if (s->cache_bio &&
-	    !test_bit(CACHE_SET_STOPPING, &s->c->flags)) {
-		BUG_ON(!s->replace);
-		closure_call(&s->btree, bch_data_insert, NULL, cl);
+	if (s->iop.bio &&
+	    !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) {
+		BUG_ON(!s->iop.replace);
+		closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
 	}
 
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
@@ -1074,12 +1097,13 @@ static void cached_dev_read_done_bh(struct closure *cl)
 	struct search *s = container_of(cl, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
-	bch_mark_cache_accounting(s, !s->cache_miss, s->bypass);
-	trace_bcache_read(s->orig_bio, !s->cache_miss, s->bypass);
+	bch_mark_cache_accounting(s->iop.c, s->d,
+				  !s->cache_miss, s->iop.bypass);
+	trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass);
 
-	if (s->error)
+	if (s->iop.error)
 		continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq);
-	else if (s->cache_bio || verify(dc, &s->bio.bio))
+	else if (s->iop.bio || verify(dc, &s->bio.bio))
 		continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq);
 	else
 		continue_at_nobarrier(cl, cached_dev_bio_complete, NULL);
@@ -1093,7 +1117,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 	struct bio *miss, *cache_bio;
 
-	if (s->cache_miss || s->bypass) {
+	if (s->cache_miss || s->iop.bypass) {
 		miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
 		ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
 		goto out_submit;
@@ -1101,20 +1125,21 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 
 	if (!(bio->bi_rw & REQ_RAHEAD) &&
 	    !(bio->bi_rw & REQ_META) &&
-	    s->c->gc_stats.in_use < CUTOFF_CACHE_READA)
+	    s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
 		reada = min_t(sector_t, dc->readahead >> 9,
 			      bdev_sectors(bio->bi_bdev) - bio_end_sector(bio));
 
-	s->cache_bio_sectors = min(sectors, bio_sectors(bio) + reada);
+	s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada);
 
-	s->replace_key = KEY(s->inode, bio->bi_sector +
-			     s->cache_bio_sectors, s->cache_bio_sectors);
+	s->iop.replace_key = KEY(s->iop.inode,
+				 bio->bi_sector + s->insert_bio_sectors,
+				 s->insert_bio_sectors);
 
-	ret = bch_btree_insert_check_key(b, &s->op, &s->replace_key);
+	ret = bch_btree_insert_check_key(b, &s->op, &s->iop.replace_key);
 	if (ret)
 		return ret;
 
-	s->replace = true;
+	s->iop.replace = true;
 
 	miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
 
@@ -1122,14 +1147,14 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	ret = miss == bio ? MAP_DONE : -EINTR;
 
 	cache_bio = bio_alloc_bioset(GFP_NOWAIT,
-			DIV_ROUND_UP(s->cache_bio_sectors, PAGE_SECTORS),
+			DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
 			dc->disk.bio_split);
 	if (!cache_bio)
 		goto out_submit;
 
 	cache_bio->bi_sector	= miss->bi_sector;
 	cache_bio->bi_bdev	= miss->bi_bdev;
-	cache_bio->bi_size	= s->cache_bio_sectors << 9;
+	cache_bio->bi_size	= s->insert_bio_sectors << 9;
 
 	cache_bio->bi_end_io	= request_endio;
 	cache_bio->bi_private	= &s->cl;
@@ -1138,8 +1163,11 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	if (bio_alloc_pages(cache_bio, __GFP_NOWARN|GFP_NOIO))
 		goto out_put;
 
+	if (reada)
+		bch_mark_cache_readahead(s->iop.c, s->d);
+
 	s->cache_miss	= miss;
-	s->cache_bio = cache_bio;
+	s->iop.bio	= cache_bio;
 	bio_get(cache_bio);
 	closure_bio_submit(cache_bio, &s->cl, s->d);
 
@@ -1157,7 +1185,7 @@ static void cached_dev_read(struct cached_dev *dc, struct search *s)
 {
 	struct closure *cl = &s->cl;
 
-	closure_call(&s->btree, cache_lookup, NULL, cl);
+	closure_call(&s->iop.cl, cache_lookup, NULL, cl);
 	continue_at(cl, cached_dev_read_done_bh, NULL);
 }
 
@@ -1179,7 +1207,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 	struct bkey start = KEY(dc->disk.id, bio->bi_sector, 0);
 	struct bkey end = KEY(dc->disk.id, bio_end_sector(bio), 0);
 
-	bch_keybuf_check_overlapping(&s->c->moving_gc_keys, &start, &end);
+	bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &start, &end);
 
 	down_read_non_owner(&dc->writeback_lock);
 	if (bch_keybuf_check_overlapping(&dc->writeback_keys, &start, &end)) {
@@ -1187,8 +1215,8 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 		 * We overlap with some dirty data undergoing background
 		 * writeback, force this write to writeback
 		 */
-		s->bypass	= false;
-		s->writeback	= true;
+		s->iop.bypass = false;
+		s->iop.writeback = true;
 	}
 
 	/*
@@ -1199,27 +1227,25 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 	 * so we still want to call it.
 	 */
 	if (bio->bi_rw & REQ_DISCARD)
-		s->bypass = true;
+		s->iop.bypass = true;
 
 	if (should_writeback(dc, s->orig_bio,
 			     cache_mode(dc, bio),
-			     s->bypass)) {
-		s->bypass = false;
-		s->writeback = true;
+			     s->iop.bypass)) {
+		s->iop.bypass = false;
+		s->iop.writeback = true;
 	}
 
-	trace_bcache_write(s->orig_bio, s->writeback, s->bypass);
-
-	if (s->bypass) {
-		s->cache_bio = s->orig_bio;
-		bio_get(s->cache_bio);
+	if (s->iop.bypass) {
+		s->iop.bio = s->orig_bio;
+		bio_get(s->iop.bio);
 
 		if (!(bio->bi_rw & REQ_DISCARD) ||
 		    blk_queue_discard(bdev_get_queue(dc->bdev)))
 			closure_bio_submit(bio, cl, s->d);
-	} else if (s->writeback) {
+	} else if (s->iop.writeback) {
 		bch_writeback_add(dc);
-		s->cache_bio = bio;
+		s->iop.bio = bio;
 
 		if (bio->bi_rw & REQ_FLUSH) {
 			/* Also need to send a flush to the backing device */
@@ -1234,13 +1260,13 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			closure_bio_submit(flush, cl, s->d);
 		}
 	} else {
-		s->cache_bio = bio_clone_bioset(bio, GFP_NOIO,
-						dc->disk.bio_split);
+		s->iop.bio = bio_clone_bioset(bio, GFP_NOIO,
+					      dc->disk.bio_split);
 
 		closure_bio_submit(bio, cl, s->d);
 	}
 
-	closure_call(&s->btree, bch_data_insert, NULL, cl);
+	closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
 	continue_at(cl, cached_dev_write_complete, NULL);
 }
 
@@ -1249,8 +1275,8 @@ static void cached_dev_nodata(struct closure *cl)
 	struct search *s = container_of(cl, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
-	if (s->flush_journal)
-		bch_journal_meta(s->c, cl);
+	if (s->iop.flush_journal)
+		bch_journal_meta(s->iop.c, cl);
 
 	/* If it's a flush, we send the flush to the backing device too */
 	closure_bio_submit(bio, cl, s->d);
@@ -1277,7 +1303,7 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 
 	if (cached_dev_get(dc)) {
 		s = search_alloc(bio, d);
-		trace_bcache_request_start(s, bio);
+		trace_bcache_request_start(s->d, bio);
 
 		if (!bio->bi_size) {
 			/*
@@ -1288,7 +1314,7 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 					      cached_dev_nodata,
 					      bcache_wq);
 		} else {
-			s->bypass = check_should_bypass(dc, s);
+			s->iop.bypass = check_should_bypass(dc, bio);
 
 			if (rw)
 				cached_dev_write(dc, s);
@@ -1378,8 +1404,8 @@ static void flash_dev_nodata(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
-	if (s->flush_journal)
-		bch_journal_meta(s->c, cl);
+	if (s->iop.flush_journal)
+		bch_journal_meta(s->iop.c, cl);
 
 	continue_at(cl, search_free, NULL);
 }
@@ -1400,7 +1426,7 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 	cl = &s->cl;
 	bio = &s->bio.bio;
 
-	trace_bcache_request_start(s, bio);
+	trace_bcache_request_start(s->d, bio);
 
 	if (!bio->bi_size) {
 		/*
@@ -1411,17 +1437,17 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 				      flash_dev_nodata,
 				      bcache_wq);
 	} else if (rw) {
-		bch_keybuf_check_overlapping(&s->c->moving_gc_keys,
+		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
 
-		s->bypass	= (bio->bi_rw & REQ_DISCARD) != 0;
-		s->writeback	= true;
-		s->cache_bio	= bio;
+		s->iop.bypass		= (bio->bi_rw & REQ_DISCARD) != 0;
+		s->iop.writeback	= true;
+		s->iop.bio		= bio;
 
-		closure_call(&s->btree, bch_data_insert, NULL, cl);
+		closure_call(&s->iop.cl, bch_data_insert, NULL, cl);
 	} else {
-		closure_call(&s->btree, cache_lookup, NULL, cl);
+		closure_call(&s->iop.cl, cache_lookup, NULL, cl);
 	}
 
 	continue_at(cl, search_free, NULL);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index f0e930b4ca89..54d7de27356f 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -3,46 +3,25 @@
 
 #include <linux/cgroup.h>
 
-struct search {
-	/* Stack frame for bio_complete */
+struct data_insert_op {
 	struct closure		cl;
-	struct closure		btree;
-
-	struct bcache_device	*d;
 	struct cache_set	*c;
 	struct task_struct	*task;
-
-	struct bbio		bio;
-	struct bio		*orig_bio;
-	struct bio		*cache_miss;
-
-	/* Bio to be inserted into the cache */
-	struct bio		*cache_bio;
-	unsigned		cache_bio_sectors;
+	struct bio		*bio;
 
 	unsigned		inode;
+	uint16_t		write_prio;
+	short			error;
 
-	unsigned		recoverable:1;
-	unsigned		unaligned_bvec:1;
-
-	unsigned		write:1;
-	unsigned		writeback:1;
-
-	unsigned		csum:1;
 	unsigned		bypass:1;
+	unsigned		writeback:1;
 	unsigned		flush_journal:1;
+	unsigned		csum:1;
 
-	unsigned		insert_data_done:1;
 	unsigned		replace:1;
-	unsigned		insert_collision:1;
-
-	uint16_t		write_prio;
-
-	/* IO error returned to s->bio */
-	short			error;
-	unsigned long		start_time;
+	unsigned		replace_collision:1;
 
-	struct btree_op		op;
+	unsigned		insert_data_done:1;
 
 	/* Anything past this point won't get zeroed in search_alloc() */
 	struct keylist		insert_keys;
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index ea77263cf7ef..84d0782f702e 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -7,7 +7,6 @@
 #include "bcache.h"
 #include "stats.h"
 #include "btree.h"
-#include "request.h"
 #include "sysfs.h"
 
 /*
@@ -196,35 +195,36 @@ static void mark_cache_stats(struct cache_stat_collector *stats,
 			atomic_inc(&stats->cache_bypass_misses);
 }
 
-void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass)
+void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
+			       bool hit, bool bypass)
 {
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
 	mark_cache_stats(&dc->accounting.collector, hit, bypass);
-	mark_cache_stats(&s->c->accounting.collector, hit, bypass);
+	mark_cache_stats(&c->accounting.collector, hit, bypass);
 #ifdef CONFIG_CGROUP_BCACHE
 	mark_cache_stats(&(bch_bio_to_cgroup(s->orig_bio)->stats), hit, bypass);
 #endif
 }
 
-void bch_mark_cache_readahead(struct search *s)
+void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d)
 {
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
 	atomic_inc(&dc->accounting.collector.cache_readaheads);
-	atomic_inc(&s->c->accounting.collector.cache_readaheads);
+	atomic_inc(&c->accounting.collector.cache_readaheads);
 }
 
-void bch_mark_cache_miss_collision(struct search *s)
+void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d)
 {
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
+	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
 	atomic_inc(&dc->accounting.collector.cache_miss_collisions);
-	atomic_inc(&s->c->accounting.collector.cache_miss_collisions);
+	atomic_inc(&c->accounting.collector.cache_miss_collisions);
 }
 
-void bch_mark_sectors_bypassed(struct search *s, int sectors)
+void bch_mark_sectors_bypassed(struct cache_set *c, struct cached_dev *dc,
+			       int sectors)
 {
-	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 	atomic_add(sectors, &dc->accounting.collector.sectors_bypassed);
-	atomic_add(sectors, &s->c->accounting.collector.sectors_bypassed);
+	atomic_add(sectors, &c->accounting.collector.sectors_bypassed);
 }
 
 void bch_cache_accounting_init(struct cache_accounting *acc,
diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h
index c7c7a8fd29fe..adbff141c887 100644
--- a/drivers/md/bcache/stats.h
+++ b/drivers/md/bcache/stats.h
@@ -38,7 +38,9 @@ struct cache_accounting {
 	struct cache_stats day;
 };
 
-struct search;
+struct cache_set;
+struct cached_dev;
+struct bcache_device;
 
 void bch_cache_accounting_init(struct cache_accounting *acc,
 			       struct closure *parent);
@@ -50,9 +52,10 @@ void bch_cache_accounting_clear(struct cache_accounting *acc);
 
 void bch_cache_accounting_destroy(struct cache_accounting *acc);
 
-void bch_mark_cache_accounting(struct search *s, bool hit, bool bypass);
-void bch_mark_cache_readahead(struct search *s);
-void bch_mark_cache_miss_collision(struct search *s);
-void bch_mark_sectors_bypassed(struct search *s, int sectors);
+void bch_mark_cache_accounting(struct cache_set *, struct bcache_device *,
+			       bool, bool);
+void bch_mark_cache_readahead(struct cache_set *, struct bcache_device *);
+void bch_mark_cache_miss_collision(struct cache_set *, struct bcache_device *);
+void bch_mark_sectors_bypassed(struct cache_set *, struct cached_dev *, int);
 
 #endif /* _BCACHE_STATS_H_ */
diff --git a/drivers/md/bcache/trace.c b/drivers/md/bcache/trace.c
index f7b6c197f90f..adbc3df17a80 100644
--- a/drivers/md/bcache/trace.c
+++ b/drivers/md/bcache/trace.c
@@ -1,6 +1,5 @@
 #include "bcache.h"
 #include "btree.h"
-#include "request.h"
 
 #include <linux/blktrace_api.h>
 #include <linux/module.h>
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index 5ebda976ea93..32c89b33c391 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -6,11 +6,9 @@
 
 #include <linux/tracepoint.h>
 
-struct search;
-
 DECLARE_EVENT_CLASS(bcache_request,
-	TP_PROTO(struct search *s, struct bio *bio),
-	TP_ARGS(s, bio),
+	TP_PROTO(struct bcache_device *d, struct bio *bio),
+	TP_ARGS(d, bio),
 
 	TP_STRUCT__entry(
 		__field(dev_t,		dev			)
@@ -24,8 +22,8 @@ DECLARE_EVENT_CLASS(bcache_request,
 
 	TP_fast_assign(
 		__entry->dev		= bio->bi_bdev->bd_dev;
-		__entry->orig_major	= s->d->disk->major;
-		__entry->orig_minor	= s->d->disk->first_minor;
+		__entry->orig_major	= d->disk->major;
+		__entry->orig_minor	= d->disk->first_minor;
 		__entry->sector		= bio->bi_sector;
 		__entry->orig_sector	= bio->bi_sector - 16;
 		__entry->nr_sector	= bio->bi_size >> 9;
@@ -79,13 +77,13 @@ DECLARE_EVENT_CLASS(btree_node,
 /* request.c */
 
 DEFINE_EVENT(bcache_request, bcache_request_start,
-	TP_PROTO(struct search *s, struct bio *bio),
-	TP_ARGS(s, bio)
+	TP_PROTO(struct bcache_device *d, struct bio *bio),
+	TP_ARGS(d, bio)
 );
 
 DEFINE_EVENT(bcache_request, bcache_request_end,
-	TP_PROTO(struct search *s, struct bio *bio),
-	TP_ARGS(s, bio)
+	TP_PROTO(struct bcache_device *d, struct bio *bio),
+	TP_ARGS(d, bio)
 );
 
 DECLARE_EVENT_CLASS(bcache_bio,
-- 
cgit 


From 81ab4190ac17df41686a37c97f701623276b652a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kmo@daterainc.com>
Date: Thu, 31 Oct 2013 15:46:42 -0700
Subject: bcache: Pull on disk data structures out into a separate header

Now, the on disk data structures are in a header that can be exported to
userspace - and having them all centralized is nice too.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
---
 drivers/md/bcache/bcache.h  | 244 +----------------------------
 drivers/md/bcache/bset.c    |   4 +-
 drivers/md/bcache/bset.h    |  31 ----
 drivers/md/bcache/btree.c   |   2 +-
 drivers/md/bcache/journal.c |   4 +-
 drivers/md/bcache/journal.h |  37 -----
 drivers/md/bcache/request.c |   9 +-
 drivers/md/bcache/super.c   |  13 +-
 drivers/md/bcache/util.h    |  10 --
 include/uapi/linux/bcache.h | 373 ++++++++++++++++++++++++++++++++++++++++++++
 10 files changed, 387 insertions(+), 340 deletions(-)
 create mode 100644 include/uapi/linux/bcache.h

(limited to 'include')

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index e32f6fd91755..045cb99f1ca6 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -177,6 +177,7 @@
 
 #define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
 
+#include <linux/bcache.h>
 #include <linux/bio.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
@@ -210,168 +211,6 @@ BITMASK(GC_MARK,	 struct bucket, gc_mark, 0, 2);
 #define GC_MARK_METADATA	2
 BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14);
 
-struct bkey {
-	uint64_t	high;
-	uint64_t	low;
-	uint64_t	ptr[];
-};
-
-/* Enough for a key with 6 pointers */
-#define BKEY_PAD		8
-
-#define BKEY_PADDED(key)					\
-	union { struct bkey key; uint64_t key ## _pad[BKEY_PAD]; }
-
-/* Version 0: Cache device
- * Version 1: Backing device
- * Version 2: Seed pointer into btree node checksum
- * Version 3: Cache device with new UUID format
- * Version 4: Backing device with data offset
- */
-#define BCACHE_SB_VERSION_CDEV			0
-#define BCACHE_SB_VERSION_BDEV			1
-#define BCACHE_SB_VERSION_CDEV_WITH_UUID	3
-#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET	4
-#define BCACHE_SB_MAX_VERSION			4
-
-#define SB_SECTOR		8
-#define SB_SIZE			4096
-#define SB_LABEL_SIZE		32
-#define SB_JOURNAL_BUCKETS	256U
-/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
-#define MAX_CACHES_PER_SET	8
-
-#define BDEV_DATA_START_DEFAULT	16	/* sectors */
-
-struct cache_sb {
-	uint64_t		csum;
-	uint64_t		offset;	/* sector where this sb was written */
-	uint64_t		version;
-
-	uint8_t			magic[16];
-
-	uint8_t			uuid[16];
-	union {
-		uint8_t		set_uuid[16];
-		uint64_t	set_magic;
-	};
-	uint8_t			label[SB_LABEL_SIZE];
-
-	uint64_t		flags;
-	uint64_t		seq;
-	uint64_t		pad[8];
-
-	union {
-	struct {
-		/* Cache devices */
-		uint64_t	nbuckets;	/* device size */
-
-		uint16_t	block_size;	/* sectors */
-		uint16_t	bucket_size;	/* sectors */
-
-		uint16_t	nr_in_set;
-		uint16_t	nr_this_dev;
-	};
-	struct {
-		/* Backing devices */
-		uint64_t	data_offset;
-
-		/*
-		 * block_size from the cache device section is still used by
-		 * backing devices, so don't add anything here until we fix
-		 * things to not need it for backing devices anymore
-		 */
-	};
-	};
-
-	uint32_t		last_mount;	/* time_t */
-
-	uint16_t		first_bucket;
-	union {
-		uint16_t	njournal_buckets;
-		uint16_t	keys;
-	};
-	uint64_t		d[SB_JOURNAL_BUCKETS];	/* journal buckets */
-};
-
-BITMASK(CACHE_SYNC,		struct cache_sb, flags, 0, 1);
-BITMASK(CACHE_DISCARD,		struct cache_sb, flags, 1, 1);
-BITMASK(CACHE_REPLACEMENT,	struct cache_sb, flags, 2, 3);
-#define CACHE_REPLACEMENT_LRU	0U
-#define CACHE_REPLACEMENT_FIFO	1U
-#define CACHE_REPLACEMENT_RANDOM 2U
-
-BITMASK(BDEV_CACHE_MODE,	struct cache_sb, flags, 0, 4);
-#define CACHE_MODE_WRITETHROUGH	0U
-#define CACHE_MODE_WRITEBACK	1U
-#define CACHE_MODE_WRITEAROUND	2U
-#define CACHE_MODE_NONE		3U
-BITMASK(BDEV_STATE,		struct cache_sb, flags, 61, 2);
-#define BDEV_STATE_NONE		0U
-#define BDEV_STATE_CLEAN	1U
-#define BDEV_STATE_DIRTY	2U
-#define BDEV_STATE_STALE	3U
-
-/* Version 1: Seed pointer into btree node checksum
- */
-#define BCACHE_BSET_VERSION	1
-
-/*
- * This is the on disk format for btree nodes - a btree node on disk is a list
- * of these; within each set the keys are sorted
- */
-struct bset {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		keys;
-
-	union {
-		struct bkey	start[0];
-		uint64_t	d[0];
-	};
-};
-
-/*
- * On disk format for priorities and gens - see super.c near prio_write() for
- * more.
- */
-struct prio_set {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		pad;
-
-	uint64_t		next_bucket;
-
-	struct bucket_disk {
-		uint16_t	prio;
-		uint8_t		gen;
-	} __attribute((packed)) data[];
-};
-
-struct uuid_entry {
-	union {
-		struct {
-			uint8_t		uuid[16];
-			uint8_t		label[32];
-			uint32_t	first_reg;
-			uint32_t	last_reg;
-			uint32_t	invalidated;
-
-			uint32_t	flags;
-			/* Size of flash only volumes */
-			uint64_t	sectors;
-		};
-
-		uint8_t	pad[128];
-	};
-};
-
-BITMASK(UUID_FLASH_ONLY,	struct uuid_entry, flags, 0, 1);
-
 #include "journal.h"
 #include "stats.h"
 struct search;
@@ -868,12 +707,6 @@ static inline bool key_merging_disabled(struct cache_set *c)
 #endif
 }
 
-static inline bool SB_IS_BDEV(const struct cache_sb *sb)
-{
-	return sb->version == BCACHE_SB_VERSION_BDEV
-		|| sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
-}
-
 struct bbio {
 	unsigned		submit_time_us;
 	union {
@@ -927,59 +760,6 @@ static inline unsigned local_clock_us(void)
 #define prio_buckets(c)					\
 	DIV_ROUND_UP((size_t) (c)->sb.nbuckets, prios_per_bucket(c))
 
-#define JSET_MAGIC		0x245235c1a3625032ULL
-#define PSET_MAGIC		0x6750e15f87337f91ULL
-#define BSET_MAGIC		0x90135c78b99e07f5ULL
-
-#define jset_magic(c)		((c)->sb.set_magic ^ JSET_MAGIC)
-#define pset_magic(c)		((c)->sb.set_magic ^ PSET_MAGIC)
-#define bset_magic(c)		((c)->sb.set_magic ^ BSET_MAGIC)
-
-/* Bkey fields: all units are in sectors */
-
-#define KEY_FIELD(name, field, offset, size)				\
-	BITMASK(name, struct bkey, field, offset, size)
-
-#define PTR_FIELD(name, offset, size)					\
-	static inline uint64_t name(const struct bkey *k, unsigned i)	\
-	{ return (k->ptr[i] >> offset) & ~(((uint64_t) ~0) << size); }	\
-									\
-	static inline void SET_##name(struct bkey *k, unsigned i, uint64_t v)\
-	{								\
-		k->ptr[i] &= ~(~((uint64_t) ~0 << size) << offset);	\
-		k->ptr[i] |= v << offset;				\
-	}
-
-KEY_FIELD(KEY_PTRS,	high, 60, 3)
-KEY_FIELD(HEADER_SIZE,	high, 58, 2)
-KEY_FIELD(KEY_CSUM,	high, 56, 2)
-KEY_FIELD(KEY_PINNED,	high, 55, 1)
-KEY_FIELD(KEY_DIRTY,	high, 36, 1)
-
-KEY_FIELD(KEY_SIZE,	high, 20, 16)
-KEY_FIELD(KEY_INODE,	high, 0,  20)
-
-/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */
-
-static inline uint64_t KEY_OFFSET(const struct bkey *k)
-{
-	return k->low;
-}
-
-static inline void SET_KEY_OFFSET(struct bkey *k, uint64_t v)
-{
-	k->low = v;
-}
-
-PTR_FIELD(PTR_DEV,		51, 12)
-PTR_FIELD(PTR_OFFSET,		8,  43)
-PTR_FIELD(PTR_GEN,		0,  8)
-
-#define PTR_CHECK_DEV		((1 << 12) - 1)
-
-#define PTR(gen, offset, dev)						\
-	((((uint64_t) dev) << 51) | ((uint64_t) offset) << 8 | gen)
-
 static inline size_t sector_to_bucket(struct cache_set *c, sector_t s)
 {
 	return s >> c->bucket_bits;
@@ -1018,31 +798,11 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
 
 /* Btree key macros */
 
-/*
- * The high bit being set is a relic from when we used it to do binary
- * searches - it told you where a key started. It's not used anymore,
- * and can probably be safely dropped.
- */
-#define KEY(dev, sector, len)						\
-((struct bkey) {							\
-	.high = (1ULL << 63) | ((uint64_t) (len) << 20) | (dev),	\
-	.low = (sector)							\
-})
-
 static inline void bkey_init(struct bkey *k)
 {
-	*k = KEY(0, 0, 0);
+	*k = ZERO_KEY;
 }
 
-#define KEY_START(k)		(KEY_OFFSET(k) - KEY_SIZE(k))
-#define START_KEY(k)		KEY(KEY_INODE(k), KEY_START(k), 0)
-
-#define MAX_KEY_INODE		(~(~0 << 20))
-#define MAX_KEY_OFFSET		(((uint64_t) ~0) >> 1)
-#define MAX_KEY			KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0)
-
-#define ZERO_KEY		KEY(0, 0, 0)
-
 /*
  * This is used for various on disk data structures - cache_sb, prio_set, bset,
  * jset: The checksum is _always_ the first 8 bytes of these structs
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index f7b5525ddafa..7b8713c66050 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -684,7 +684,7 @@ void bch_bset_init_next(struct btree *b)
 	} else
 		get_random_bytes(&i->seq, sizeof(uint64_t));
 
-	i->magic	= bset_magic(b->c);
+	i->magic	= bset_magic(&b->c->sb);
 	i->version	= 0;
 	i->keys		= 0;
 
@@ -1034,7 +1034,7 @@ static void __btree_sort(struct btree *b, struct btree_iter *iter,
 		 * memcpy()
 		 */
 
-		out->magic	= bset_magic(b->c);
+		out->magic	= bset_magic(&b->c->sb);
 		out->seq	= b->sets[0].data->seq;
 		out->version	= b->sets[0].data->version;
 		swap(out, b->sets[0].data);
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index 8a9305685b7e..5cd90565dfe2 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -193,37 +193,6 @@ static __always_inline int64_t bkey_cmp(const struct bkey *l,
 		: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
 }
 
-static inline size_t bkey_u64s(const struct bkey *k)
-{
-	BUG_ON(KEY_CSUM(k) > 1);
-	return 2 + KEY_PTRS(k) + (KEY_CSUM(k) ? 1 : 0);
-}
-
-static inline size_t bkey_bytes(const struct bkey *k)
-{
-	return bkey_u64s(k) * sizeof(uint64_t);
-}
-
-static inline void bkey_copy(struct bkey *dest, const struct bkey *src)
-{
-	memcpy(dest, src, bkey_bytes(src));
-}
-
-static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
-{
-	if (!src)
-		src = &KEY(0, 0, 0);
-
-	SET_KEY_INODE(dest, KEY_INODE(src));
-	SET_KEY_OFFSET(dest, KEY_OFFSET(src));
-}
-
-static inline struct bkey *bkey_next(const struct bkey *k)
-{
-	uint64_t *d = (void *) k;
-	return (struct bkey *) (d + bkey_u64s(k));
-}
-
 /* Keylists */
 
 struct keylist {
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index f5aa4adadf1d..aba787d954e5 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -231,7 +231,7 @@ static void bch_btree_node_read_done(struct btree *b)
 			goto err;
 
 		err = "bad magic";
-		if (i->magic != bset_magic(b->c))
+		if (i->magic != bset_magic(&b->c->sb))
 			goto err;
 
 		err = "bad checksum";
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 86de64a6bf26..ecdaa671bd50 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -74,7 +74,7 @@ reread:		left = ca->sb.bucket_size - offset;
 			struct list_head *where;
 			size_t blocks, bytes = set_bytes(j);
 
-			if (j->magic != jset_magic(ca->set))
+			if (j->magic != jset_magic(&ca->sb))
 				return ret;
 
 			if (bytes > left << 9)
@@ -596,7 +596,7 @@ static void journal_write_unlocked(struct closure *cl)
 	for_each_cache(ca, c, i)
 		w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
 
-	w->data->magic		= jset_magic(c);
+	w->data->magic		= jset_magic(&c->sb);
 	w->data->version	= BCACHE_JSET_VERSION;
 	w->data->last_seq	= last_seq(&c->journal);
 	w->data->csum		= csum_set(w->data);
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index 5e9edb9ef376..a6472fda94b2 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -75,43 +75,6 @@
  * nodes that are pinning the oldest journal entries first.
  */
 
-#define BCACHE_JSET_VERSION_UUIDv1	1
-/* Always latest UUID format */
-#define BCACHE_JSET_VERSION_UUID	1
-#define BCACHE_JSET_VERSION		1
-
-/*
- * On disk format for a journal entry:
- * seq is monotonically increasing; every journal entry has its own unique
- * sequence number.
- *
- * last_seq is the oldest journal entry that still has keys the btree hasn't
- * flushed to disk yet.
- *
- * version is for on disk format changes.
- */
-struct jset {
-	uint64_t		csum;
-	uint64_t		magic;
-	uint64_t		seq;
-	uint32_t		version;
-	uint32_t		keys;
-
-	uint64_t		last_seq;
-
-	BKEY_PADDED(uuid_bucket);
-	BKEY_PADDED(btree_root);
-	uint16_t		btree_level;
-	uint16_t		pad[3];
-
-	uint64_t		prio_bucket[MAX_CACHES_PER_SET];
-
-	union {
-		struct bkey	start[0];
-		uint64_t	d[0];
-	};
-};
-
 /*
  * Only used for holding the journal entries we read in btree_journal_read()
  * during cache_registration
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index cf7850a7592c..932300f18973 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -264,16 +264,17 @@ static void bch_data_invalidate(struct closure *cl)
 		 bio_sectors(bio), (uint64_t) bio->bi_sector);
 
 	while (bio_sectors(bio)) {
-		unsigned len = min(bio_sectors(bio), 1U << 14);
+		unsigned sectors = min(bio_sectors(bio),
+				       1U << (KEY_SIZE_BITS - 1));
 
 		if (bch_keylist_realloc(&op->insert_keys, 0, op->c))
 			goto out;
 
-		bio->bi_sector	+= len;
-		bio->bi_size	-= len << 9;
+		bio->bi_sector	+= sectors;
+		bio->bi_size	-= sectors << 9;
 
 		bch_keylist_add(&op->insert_keys,
-				&KEY(op->inode, bio->bi_sector, len));
+				&KEY(op->inode, bio->bi_sector, sectors));
 	}
 
 	op->insert_data_done = true;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a314c771263f..c67d19a8913d 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -45,15 +45,6 @@ const char * const bch_cache_modes[] = {
 	NULL
 };
 
-struct uuid_entry_v0 {
-	uint8_t		uuid[16];
-	uint8_t		label[32];
-	uint32_t	first_reg;
-	uint32_t	last_reg;
-	uint32_t	invalidated;
-	uint32_t	pad;
-};
-
 static struct kobject *bcache_kobj;
 struct mutex bch_register_lock;
 LIST_HEAD(bch_cache_sets);
@@ -562,7 +553,7 @@ void bch_prio_write(struct cache *ca)
 		}
 
 		p->next_bucket	= ca->prio_buckets[i + 1];
-		p->magic	= pset_magic(ca);
+		p->magic	= pset_magic(&ca->sb);
 		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
 		bucket = bch_bucket_alloc(ca, WATERMARK_PRIO, true);
@@ -613,7 +604,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
 			if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
 				pr_warn("bad csum reading priorities");
 
-			if (p->magic != pset_magic(ca))
+			if (p->magic != pset_magic(&ca->sb))
 				pr_warn("bad magic reading priorities");
 
 			bucket = p->next_bucket;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index ea345c6896f4..38ae7a4ce928 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -27,16 +27,6 @@ struct closure;
 
 #endif
 
-#define BITMASK(name, type, field, offset, size)		\
-static inline uint64_t name(const type *k)			\
-{ return (k->field >> offset) & ~(((uint64_t) ~0) << size); }	\
-								\
-static inline void SET_##name(type *k, uint64_t v)		\
-{								\
-	k->field &= ~(~((uint64_t) ~0 << size) << offset);	\
-	k->field |= v << offset;				\
-}
-
 #define DECLARE_HEAP(type, name)					\
 	struct {							\
 		size_t size, used;					\
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
new file mode 100644
index 000000000000..164a7e263988
--- /dev/null
+++ b/include/uapi/linux/bcache.h
@@ -0,0 +1,373 @@
+#ifndef _LINUX_BCACHE_H
+#define _LINUX_BCACHE_H
+
+/*
+ * Bcache on disk data structures
+ */
+
+#include <asm/types.h>
+
+#define BITMASK(name, type, field, offset, size)		\
+static inline __u64 name(const type *k)				\
+{ return (k->field >> offset) & ~(~0ULL << size); }		\
+								\
+static inline void SET_##name(type *k, __u64 v)			\
+{								\
+	k->field &= ~(~(~0ULL << size) << offset);		\
+	k->field |= (v & ~(~0ULL << size)) << offset;		\
+}
+
+/* Btree keys - all units are in sectors */
+
+struct bkey {
+	__u64	high;
+	__u64	low;
+	__u64	ptr[];
+};
+
+#define KEY_FIELD(name, field, offset, size)				\
+	BITMASK(name, struct bkey, field, offset, size)
+
+#define PTR_FIELD(name, offset, size)					\
+static inline __u64 name(const struct bkey *k, unsigned i)		\
+{ return (k->ptr[i] >> offset) & ~(~0ULL << size); }			\
+									\
+static inline void SET_##name(struct bkey *k, unsigned i, __u64 v)	\
+{									\
+	k->ptr[i] &= ~(~(~0ULL << size) << offset);			\
+	k->ptr[i] |= (v & ~(~0ULL << size)) << offset;			\
+}
+
+#define KEY_SIZE_BITS		16
+
+KEY_FIELD(KEY_PTRS,	high, 60, 3)
+KEY_FIELD(HEADER_SIZE,	high, 58, 2)
+KEY_FIELD(KEY_CSUM,	high, 56, 2)
+KEY_FIELD(KEY_PINNED,	high, 55, 1)
+KEY_FIELD(KEY_DIRTY,	high, 36, 1)
+
+KEY_FIELD(KEY_SIZE,	high, 20, KEY_SIZE_BITS)
+KEY_FIELD(KEY_INODE,	high, 0,  20)
+
+/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */
+
+static inline __u64 KEY_OFFSET(const struct bkey *k)
+{
+	return k->low;
+}
+
+static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v)
+{
+	k->low = v;
+}
+
+/*
+ * The high bit being set is a relic from when we used it to do binary
+ * searches - it told you where a key started. It's not used anymore,
+ * and can probably be safely dropped.
+ */
+#define KEY(inode, offset, size)					\
+((struct bkey) {							\
+	.high = (1ULL << 63) | ((__u64) (size) << 20) | (inode),	\
+	.low = (offset)							\
+})
+
+#define ZERO_KEY			KEY(0, 0, 0)
+
+#define MAX_KEY_INODE			(~(~0 << 20))
+#define MAX_KEY_OFFSET			(~0ULL >> 1)
+#define MAX_KEY				KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0)
+
+#define KEY_START(k)			(KEY_OFFSET(k) - KEY_SIZE(k))
+#define START_KEY(k)			KEY(KEY_INODE(k), KEY_START(k), 0)
+
+#define PTR_DEV_BITS			12
+
+PTR_FIELD(PTR_DEV,			51, PTR_DEV_BITS)
+PTR_FIELD(PTR_OFFSET,			8,  43)
+PTR_FIELD(PTR_GEN,			0,  8)
+
+#define PTR_CHECK_DEV			((1 << PTR_DEV_BITS) - 1)
+
+#define PTR(gen, offset, dev)						\
+	((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen)
+
+/* Bkey utility code */
+
+static inline unsigned long bkey_u64s(const struct bkey *k)
+{
+	return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k);
+}
+
+static inline unsigned long bkey_bytes(const struct bkey *k)
+{
+	return bkey_u64s(k) * sizeof(__u64);
+}
+
+#define bkey_copy(_dest, _src)	memcpy(_dest, _src, bkey_bytes(_src))
+
+static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
+{
+	SET_KEY_INODE(dest, KEY_INODE(src));
+	SET_KEY_OFFSET(dest, KEY_OFFSET(src));
+}
+
+static inline struct bkey *bkey_next(const struct bkey *k)
+{
+	__u64 *d = (void *) k;
+	return (struct bkey *) (d + bkey_u64s(k));
+}
+
+static inline struct bkey *bkey_last(const struct bkey *k, unsigned nr_keys)
+{
+	__u64 *d = (void *) k;
+	return (struct bkey *) (d + nr_keys);
+}
+/* Enough for a key with 6 pointers */
+#define BKEY_PAD		8
+
+#define BKEY_PADDED(key)					\
+	union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; }
+
+/* Superblock */
+
+/* Version 0: Cache device
+ * Version 1: Backing device
+ * Version 2: Seed pointer into btree node checksum
+ * Version 3: Cache device with new UUID format
+ * Version 4: Backing device with data offset
+ */
+#define BCACHE_SB_VERSION_CDEV		0
+#define BCACHE_SB_VERSION_BDEV		1
+#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3
+#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4
+#define BCACHE_SB_MAX_VERSION		4
+
+#define SB_SECTOR			8
+#define SB_SIZE				4096
+#define SB_LABEL_SIZE			32
+#define SB_JOURNAL_BUCKETS		256U
+/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */
+#define MAX_CACHES_PER_SET		8
+
+#define BDEV_DATA_START_DEFAULT		16	/* sectors */
+
+struct cache_sb {
+	__u64			csum;
+	__u64			offset;	/* sector where this sb was written */
+	__u64			version;
+
+	__u8			magic[16];
+
+	__u8			uuid[16];
+	union {
+		__u8		set_uuid[16];
+		__u64		set_magic;
+	};
+	__u8			label[SB_LABEL_SIZE];
+
+	__u64			flags;
+	__u64			seq;
+	__u64			pad[8];
+
+	union {
+	struct {
+		/* Cache devices */
+		__u64		nbuckets;	/* device size */
+
+		__u16		block_size;	/* sectors */
+		__u16		bucket_size;	/* sectors */
+
+		__u16		nr_in_set;
+		__u16		nr_this_dev;
+	};
+	struct {
+		/* Backing devices */
+		__u64		data_offset;
+
+		/*
+		 * block_size from the cache device section is still used by
+		 * backing devices, so don't add anything here until we fix
+		 * things to not need it for backing devices anymore
+		 */
+	};
+	};
+
+	__u32			last_mount;	/* time_t */
+
+	__u16			first_bucket;
+	union {
+		__u16		njournal_buckets;
+		__u16		keys;
+	};
+	__u64			d[SB_JOURNAL_BUCKETS];	/* journal buckets */
+};
+
+static inline _Bool SB_IS_BDEV(const struct cache_sb *sb)
+{
+	return sb->version == BCACHE_SB_VERSION_BDEV
+		|| sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET;
+}
+
+BITMASK(CACHE_SYNC,			struct cache_sb, flags, 0, 1);
+BITMASK(CACHE_DISCARD,			struct cache_sb, flags, 1, 1);
+BITMASK(CACHE_REPLACEMENT,		struct cache_sb, flags, 2, 3);
+#define CACHE_REPLACEMENT_LRU		0U
+#define CACHE_REPLACEMENT_FIFO		1U
+#define CACHE_REPLACEMENT_RANDOM	2U
+
+BITMASK(BDEV_CACHE_MODE,		struct cache_sb, flags, 0, 4);
+#define CACHE_MODE_WRITETHROUGH		0U
+#define CACHE_MODE_WRITEBACK		1U
+#define CACHE_MODE_WRITEAROUND		2U
+#define CACHE_MODE_NONE			3U
+BITMASK(BDEV_STATE,			struct cache_sb, flags, 61, 2);
+#define BDEV_STATE_NONE			0U
+#define BDEV_STATE_CLEAN		1U
+#define BDEV_STATE_DIRTY		2U
+#define BDEV_STATE_STALE		3U
+
+/*
+ * Magic numbers
+ *
+ * The various other data structures have their own magic numbers, which are
+ * xored with the first part of the cache set's UUID
+ */
+
+#define JSET_MAGIC			0x245235c1a3625032ULL
+#define PSET_MAGIC			0x6750e15f87337f91ULL
+#define BSET_MAGIC			0x90135c78b99e07f5ULL
+
+static inline __u64 jset_magic(struct cache_sb *sb)
+{
+	return sb->set_magic ^ JSET_MAGIC;
+}
+
+static inline __u64 pset_magic(struct cache_sb *sb)
+{
+	return sb->set_magic ^ PSET_MAGIC;
+}
+
+static inline __u64 bset_magic(struct cache_sb *sb)
+{
+	return sb->set_magic ^ BSET_MAGIC;
+}
+
+/*
+ * Journal
+ *
+ * On disk format for a journal entry:
+ * seq is monotonically increasing; every journal entry has its own unique
+ * sequence number.
+ *
+ * last_seq is the oldest journal entry that still has keys the btree hasn't
+ * flushed to disk yet.
+ *
+ * version is for on disk format changes.
+ */
+
+#define BCACHE_JSET_VERSION_UUIDv1	1
+#define BCACHE_JSET_VERSION_UUID	1	/* Always latest UUID format */
+#define BCACHE_JSET_VERSION		1
+
+struct jset {
+	__u64			csum;
+	__u64			magic;
+	__u64			seq;
+	__u32			version;
+	__u32			keys;
+
+	__u64			last_seq;
+
+	BKEY_PADDED(uuid_bucket);
+	BKEY_PADDED(btree_root);
+	__u16			btree_level;
+	__u16			pad[3];
+
+	__u64			prio_bucket[MAX_CACHES_PER_SET];
+
+	union {
+		struct bkey	start[0];
+		__u64		d[0];
+	};
+};
+
+/* Bucket prios/gens */
+
+struct prio_set {
+	__u64			csum;
+	__u64			magic;
+	__u64			seq;
+	__u32			version;
+	__u32			pad;
+
+	__u64			next_bucket;
+
+	struct bucket_disk {
+		__u16		prio;
+		__u8		gen;
+	} __attribute((packed)) data[];
+};
+
+/* UUIDS - per backing device/flash only volume metadata */
+
+struct uuid_entry {
+	union {
+		struct {
+			__u8	uuid[16];
+			__u8	label[32];
+			__u32	first_reg;
+			__u32	last_reg;
+			__u32	invalidated;
+
+			__u32	flags;
+			/* Size of flash only volumes */
+			__u64	sectors;
+		};
+
+		__u8		pad[128];
+	};
+};
+
+BITMASK(UUID_FLASH_ONLY,	struct uuid_entry, flags, 0, 1);
+
+/* Btree nodes */
+
+/* Version 1: Seed pointer into btree node checksum
+ */
+#define BCACHE_BSET_CSUM		1
+#define BCACHE_BSET_VERSION		1
+
+/*
+ * Btree nodes
+ *
+ * On disk a btree node is a list/log of these; within each set the keys are
+ * sorted
+ */
+struct bset {
+	__u64			csum;
+	__u64			magic;
+	__u64			seq;
+	__u32			version;
+	__u32			keys;
+
+	union {
+		struct bkey	start[0];
+		__u64		d[0];
+	};
+};
+
+/* OBSOLETE */
+
+/* UUIDS - per backing device/flash only volume metadata */
+
+struct uuid_entry_v0 {
+	__u8		uuid[16];
+	__u8		label[32];
+	__u32		first_reg;
+	__u32		last_reg;
+	__u32		invalidated;
+	__u32		pad;
+};
+
+#endif /* _LINUX_BCACHE_H */
-- 
cgit 


From 48a915a87f0bd98c3d68d029acf223a2e5116f07 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kmo@daterainc.com>
Date: Thu, 31 Oct 2013 15:43:22 -0700
Subject: bcache: Better full stripe scanning

The old scanning-by-stripe code burned too much CPU, this should be
better.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
---
 drivers/md/bcache/bcache.h    |  5 ++-
 drivers/md/bcache/btree.c     | 19 +++++----
 drivers/md/bcache/super.c     | 17 +++++++-
 drivers/md/bcache/writeback.c | 94 ++++++++++++++++++++++++++-----------------
 drivers/md/bcache/writeback.h | 21 ++++++----
 include/trace/events/bcache.h | 29 +++++++++++++
 6 files changed, 128 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 816d07958fac..ab0b2150fed6 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -237,7 +237,7 @@ struct keybuf {
 
 	struct rb_root		keys;
 
-#define KEYBUF_NR		100
+#define KEYBUF_NR		500
 	DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
 };
 
@@ -273,9 +273,10 @@ struct bcache_device {
 	atomic_t		detaching;
 	int			flush_done;
 
-	uint64_t		nr_stripes;
+	unsigned		nr_stripes;
 	unsigned		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
+	unsigned long		*full_dirty_stripes;
 
 	unsigned long		sectors_dirty_last;
 	long			sectors_dirty_derivative;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 6def7c9a1228..5e2765aadce1 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -2378,6 +2378,7 @@ static inline int keybuf_nonoverlapping_cmp(struct keybuf_key *l,
 
 struct refill {
 	struct btree_op	op;
+	unsigned	nr_found;
 	struct keybuf	*buf;
 	struct bkey	*end;
 	keybuf_pred_fn	*pred;
@@ -2414,6 +2415,8 @@ static int refill_keybuf_fn(struct btree_op *op, struct btree *b,
 
 		if (RB_INSERT(&buf->keys, w, node, keybuf_cmp))
 			array_free(&buf->freelist, w);
+		else
+			refill->nr_found++;
 
 		if (array_freelist_empty(&buf->freelist))
 			ret = MAP_DONE;
@@ -2434,18 +2437,18 @@ void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf,
 	cond_resched();
 
 	bch_btree_op_init(&refill.op, -1);
-	refill.buf = buf;
-	refill.end = end;
-	refill.pred = pred;
+	refill.nr_found	= 0;
+	refill.buf	= buf;
+	refill.end	= end;
+	refill.pred	= pred;
 
 	bch_btree_map_keys(&refill.op, c, &buf->last_scanned,
 			   refill_keybuf_fn, MAP_END_KEY);
 
-	pr_debug("found %s keys from %llu:%llu to %llu:%llu",
-		 RB_EMPTY_ROOT(&buf->keys) ? "no" :
-		 array_freelist_empty(&buf->freelist) ? "some" : "a few",
-		 KEY_INODE(&start), KEY_OFFSET(&start),
-		 KEY_INODE(&buf->last_scanned), KEY_OFFSET(&buf->last_scanned));
+	trace_bcache_keyscan(refill.nr_found,
+			     KEY_INODE(&start), KEY_OFFSET(&start),
+			     KEY_INODE(&buf->last_scanned),
+			     KEY_OFFSET(&buf->last_scanned));
 
 	spin_lock(&buf->lock);
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4813ef67cef5..43fcfe38be11 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -738,6 +738,10 @@ static void bcache_device_free(struct bcache_device *d)
 		mempool_destroy(d->unaligned_bvec);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
+	if (is_vmalloc_addr(d->full_dirty_stripes))
+		vfree(d->full_dirty_stripes);
+	else
+		kfree(d->full_dirty_stripes);
 	if (is_vmalloc_addr(d->stripe_sectors_dirty))
 		vfree(d->stripe_sectors_dirty);
 	else
@@ -757,8 +761,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 
 	d->nr_stripes = DIV_ROUND_UP_ULL(sectors, d->stripe_size);
 
-	if (!d->nr_stripes || d->nr_stripes > SIZE_MAX / sizeof(atomic_t))
+	if (!d->nr_stripes ||
+	    d->nr_stripes > INT_MAX ||
+	    d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
+		pr_err("nr_stripes too large");
 		return -ENOMEM;
+	}
 
 	n = d->nr_stripes * sizeof(atomic_t);
 	d->stripe_sectors_dirty = n < PAGE_SIZE << 6
@@ -767,6 +775,13 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (!d->stripe_sectors_dirty)
 		return -ENOMEM;
 
+	n = BITS_TO_LONGS(d->nr_stripes) * sizeof(unsigned long);
+	d->full_dirty_stripes = n < PAGE_SIZE << 6
+		? kzalloc(n, GFP_KERNEL)
+		: vzalloc(n);
+	if (!d->full_dirty_stripes)
+		return -ENOMEM;
+
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
 	    !(d->unaligned_bvec = mempool_create_kmalloc_pool(1,
 				sizeof(struct bio_vec) * BIO_MAX_PAGES)) ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index ab0f6b449111..22e21dc9a037 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -292,14 +292,12 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 				  uint64_t offset, int nr_sectors)
 {
 	struct bcache_device *d = c->devices[inode];
-	unsigned stripe_offset;
-	uint64_t stripe = offset;
+	unsigned stripe_offset, stripe, sectors_dirty;
 
 	if (!d)
 		return;
 
-	do_div(stripe, d->stripe_size);
-
+	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
 	while (nr_sectors) {
@@ -309,7 +307,16 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 		if (nr_sectors < 0)
 			s = -s;
 
-		atomic_add(s, d->stripe_sectors_dirty + stripe);
+		if (stripe >= d->nr_stripes)
+			return;
+
+		sectors_dirty = atomic_add_return(s,
+					d->stripe_sectors_dirty + stripe);
+		if (sectors_dirty == d->stripe_size)
+			set_bit(stripe, d->full_dirty_stripes);
+		else
+			clear_bit(stripe, d->full_dirty_stripes);
+
 		nr_sectors -= s;
 		stripe_offset = 0;
 		stripe++;
@@ -321,59 +328,70 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k)
 	return KEY_DIRTY(k);
 }
 
-static bool dirty_full_stripe_pred(struct keybuf *buf, struct bkey *k)
+static void refill_full_stripes(struct cached_dev *dc)
 {
-	uint64_t stripe = KEY_START(k);
-	unsigned nr_sectors = KEY_SIZE(k);
-	struct cached_dev *dc = container_of(buf, struct cached_dev,
-					     writeback_keys);
+	struct keybuf *buf = &dc->writeback_keys;
+	unsigned start_stripe, stripe, next_stripe;
+	bool wrapped = false;
+
+	stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
 
-	if (!KEY_DIRTY(k))
-		return false;
+	if (stripe >= dc->disk.nr_stripes)
+		stripe = 0;
 
-	do_div(stripe, dc->disk.stripe_size);
+	start_stripe = stripe;
 
 	while (1) {
-		if (atomic_read(dc->disk.stripe_sectors_dirty + stripe) ==
-		    dc->disk.stripe_size)
-			return true;
+		stripe = find_next_bit(dc->disk.full_dirty_stripes,
+				       dc->disk.nr_stripes, stripe);
 
-		if (nr_sectors <= dc->disk.stripe_size)
-			return false;
+		if (stripe == dc->disk.nr_stripes)
+			goto next;
 
-		nr_sectors -= dc->disk.stripe_size;
-		stripe++;
+		next_stripe = find_next_zero_bit(dc->disk.full_dirty_stripes,
+						 dc->disk.nr_stripes, stripe);
+
+		buf->last_scanned = KEY(dc->disk.id,
+					stripe * dc->disk.stripe_size, 0);
+
+		bch_refill_keybuf(dc->disk.c, buf,
+				  &KEY(dc->disk.id,
+				       next_stripe * dc->disk.stripe_size, 0),
+				  dirty_pred);
+
+		if (array_freelist_empty(&buf->freelist))
+			return;
+
+		stripe = next_stripe;
+next:
+		if (wrapped && stripe > start_stripe)
+			return;
+
+		if (stripe == dc->disk.nr_stripes) {
+			stripe = 0;
+			wrapped = true;
+		}
 	}
 }
 
 static bool refill_dirty(struct cached_dev *dc)
 {
 	struct keybuf *buf = &dc->writeback_keys;
-	bool searched_from_start = false;
 	struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
+	bool searched_from_start = false;
+
+	if (dc->partial_stripes_expensive) {
+		refill_full_stripes(dc);
+		if (array_freelist_empty(&buf->freelist))
+			return false;
+	}
 
 	if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
 		buf->last_scanned = KEY(dc->disk.id, 0, 0);
 		searched_from_start = true;
 	}
 
-	if (dc->partial_stripes_expensive) {
-		uint64_t i;
-
-		for (i = 0; i < dc->disk.nr_stripes; i++)
-			if (atomic_read(dc->disk.stripe_sectors_dirty + i) ==
-			    dc->disk.stripe_size)
-				goto full_stripes;
-
-		goto normal_refill;
-full_stripes:
-		searched_from_start = false;	/* not searching entire btree */
-		bch_refill_keybuf(dc->disk.c, buf, &end,
-				  dirty_full_stripe_pred);
-	} else {
-normal_refill:
-		bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
-	}
+	bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
 
 	return bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start;
 }
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 60516bfa6052..fe7d9d56492b 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -14,22 +14,27 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline bool bcache_dev_stripe_dirty(struct bcache_device *d,
+static inline unsigned offset_to_stripe(struct bcache_device *d,
+					uint64_t offset)
+{
+	do_div(offset, d->stripe_size);
+	return offset;
+}
+
+static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc,
 					   uint64_t offset,
 					   unsigned nr_sectors)
 {
-	uint64_t stripe = offset;
-
-	do_div(stripe, d->stripe_size);
+	unsigned stripe = offset_to_stripe(&dc->disk, offset);
 
 	while (1) {
-		if (atomic_read(d->stripe_sectors_dirty + stripe))
+		if (atomic_read(dc->disk.stripe_sectors_dirty + stripe))
 			return true;
 
-		if (nr_sectors <= d->stripe_size)
+		if (nr_sectors <= dc->disk.stripe_size)
 			return false;
 
-		nr_sectors -= d->stripe_size;
+		nr_sectors -= dc->disk.stripe_size;
 		stripe++;
 	}
 }
@@ -45,7 +50,7 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
 		return false;
 
 	if (dc->partial_stripes_expensive &&
-	    bcache_dev_stripe_dirty(&dc->disk, bio->bi_sector,
+	    bcache_dev_stripe_dirty(dc, bio->bi_sector,
 				    bio_sectors(bio)))
 		return true;
 
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index 32c89b33c391..e2b9576d00e2 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -368,6 +368,35 @@ DEFINE_EVENT(btree_node, bcache_btree_set_root,
 	TP_ARGS(b)
 );
 
+TRACE_EVENT(bcache_keyscan,
+	TP_PROTO(unsigned nr_found,
+		 unsigned start_inode, uint64_t start_offset,
+		 unsigned end_inode, uint64_t end_offset),
+	TP_ARGS(nr_found,
+		start_inode, start_offset,
+		end_inode, end_offset),
+
+	TP_STRUCT__entry(
+		__field(__u32,	nr_found			)
+		__field(__u32,	start_inode			)
+		__field(__u64,	start_offset			)
+		__field(__u32,	end_inode			)
+		__field(__u64,	end_offset			)
+	),
+
+	TP_fast_assign(
+		__entry->nr_found	= nr_found;
+		__entry->start_inode	= start_inode;
+		__entry->start_offset	= start_offset;
+		__entry->end_inode	= end_inode;
+		__entry->end_offset	= end_offset;
+	),
+
+	TP_printk("found %u keys from %u:%llu to %u:%llu", __entry->nr_found,
+		  __entry->start_inode, __entry->start_offset,
+		  __entry->end_inode, __entry->end_offset)
+);
+
 /* Allocator */
 
 TRACE_EVENT(bcache_alloc_invalidate,
-- 
cgit 


From 03e361b25ee8dfb1fd9b890072c23c4aae01c6c7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 29 Oct 2013 10:03:04 +0100
Subject: mfd: Stop setting refcounting pointers in original mfd_cell arrays

Commit 1e29af62f2b285bd18685da93c3ce8c33ca2d1db ("mfd: Add refcounting
support to mfd_cells") had to drop the "const" keyword on the "cell"
parameter of mfd_add_devices(), as it added the refcounting pointers
to the objects of the passed mfd_cell array itself.

However, the mfd core code operates on copies of the mfd_cell objects,
so there's no need to modify the originally passed objects.

Hence, move the setting of the refcounting pointers from mfd_add_devices()
to mfd_platform_add_cell(), where the copy of the mfd_cell objects is made.
mfd_clone_cell() can just pass (a copy of) the original usage_count
pointer.

This allows to make the "cell" parameter of mfd_add_devices() "const"
again, and avoids future race conditions when registering multiple
instances of the same device in parallel.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/mfd-core.c   | 17 +++++++++--------
 include/linux/mfd/core.h |  2 +-
 2 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index f421586f29fb..8736f4539bc0 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -63,7 +63,8 @@ int mfd_cell_disable(struct platform_device *pdev)
 EXPORT_SYMBOL(mfd_cell_disable);
 
 static int mfd_platform_add_cell(struct platform_device *pdev,
-				 const struct mfd_cell *cell)
+				 const struct mfd_cell *cell,
+				 atomic_t *usage_count)
 {
 	if (!cell)
 		return 0;
@@ -72,11 +73,12 @@ static int mfd_platform_add_cell(struct platform_device *pdev,
 	if (!pdev->mfd_cell)
 		return -ENOMEM;
 
+	pdev->mfd_cell->usage_count = usage_count;
 	return 0;
 }
 
 static int mfd_add_device(struct device *parent, int id,
-			  const struct mfd_cell *cell,
+			  const struct mfd_cell *cell, atomic_t *usage_count,
 			  struct resource *mem_base,
 			  int irq_base, struct irq_domain *domain)
 {
@@ -115,7 +117,7 @@ static int mfd_add_device(struct device *parent, int id,
 			goto fail_res;
 	}
 
-	ret = mfd_platform_add_cell(pdev, cell);
+	ret = mfd_platform_add_cell(pdev, cell, usage_count);
 	if (ret)
 		goto fail_res;
 
@@ -180,7 +182,7 @@ fail_alloc:
 }
 
 int mfd_add_devices(struct device *parent, int id,
-		    struct mfd_cell *cells, int n_devs,
+		    const struct mfd_cell *cells, int n_devs,
 		    struct resource *mem_base,
 		    int irq_base, struct irq_domain *domain)
 {
@@ -195,8 +197,7 @@ int mfd_add_devices(struct device *parent, int id,
 
 	for (i = 0; i < n_devs; i++) {
 		atomic_set(&cnts[i], 0);
-		cells[i].usage_count = &cnts[i];
-		ret = mfd_add_device(parent, id, cells + i, mem_base,
+		ret = mfd_add_device(parent, id, cells + i, cnts + i, mem_base,
 				     irq_base, domain);
 		if (ret)
 			break;
@@ -259,8 +260,8 @@ int mfd_clone_cell(const char *cell, const char **clones, size_t n_clones)
 	for (i = 0; i < n_clones; i++) {
 		cell_entry.name = clones[i];
 		/* don't give up if a single call fails; just report error */
-		if (mfd_add_device(pdev->dev.parent, -1, &cell_entry, NULL, 0,
-				   NULL))
+		if (mfd_add_device(pdev->dev.parent, -1, &cell_entry,
+				   cell_entry.usage_count, NULL, 0, NULL))
 			dev_err(dev, "failed to create platform device '%s'\n",
 					clones[i]);
 	}
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index cebe97ee98b8..60ced604664f 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -98,7 +98,7 @@ static inline const struct mfd_cell *mfd_get_cell(struct platform_device *pdev)
 }
 
 extern int mfd_add_devices(struct device *parent, int id,
-			   struct mfd_cell *cells, int n_devs,
+			   const struct mfd_cell *cells, int n_devs,
 			   struct resource *mem_base,
 			   int irq_base, struct irq_domain *irq_domain);
 
-- 
cgit 


From 67a6de49bf545c34eb8dee99abbb92d9ea268200 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 8 Nov 2013 08:26:39 +0100
Subject: locking/doc: Update references to kernel/mutex.c

Fix this docbook error:

  >> docproc: kernel/mutex.c: No such file or directory

by updating the stale references to kernel/mutex.c.

Reported-by: fengguang.wu@intel.com
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-34pikw1tlsskj65rrt5iusrq@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/DocBook/kernel-locking.tmpl |  2 +-
 Documentation/mutex-design.txt            | 10 +++++-----
 include/linux/mutex.h                     |  2 +-
 kernel/locking/mutex.c                    |  2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index 09e884e5b9f5..19f2a5a5a5b4 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1958,7 +1958,7 @@ machines due to caching.
   <chapter id="apiref-mutex">
    <title>Mutex API reference</title>
 !Iinclude/linux/mutex.h
-!Ekernel/mutex.c
+!Ekernel/locking/mutex.c
   </chapter>
 
   <chapter id="apiref-futex">
diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt
index 38c10fd7f411..1dfe62c3641d 100644
--- a/Documentation/mutex-design.txt
+++ b/Documentation/mutex-design.txt
@@ -116,11 +116,11 @@ using mutexes at the moment, please let me know if you find any. ]
 Implementation of mutexes
 -------------------------
 
-'struct mutex' is the new mutex type, defined in include/linux/mutex.h
-and implemented in kernel/mutex.c. It is a counter-based mutex with a
-spinlock and a wait-list. The counter has 3 states: 1 for "unlocked",
-0 for "locked" and negative numbers (usually -1) for "locked, potential
-waiters queued".
+'struct mutex' is the new mutex type, defined in include/linux/mutex.h and
+implemented in kernel/locking/mutex.c. It is a counter-based mutex with a
+spinlock and a wait-list. The counter has 3 states: 1 for "unlocked", 0 for
+"locked" and negative numbers (usually -1) for "locked, potential waiters
+queued".
 
 the APIs of 'struct mutex' have been streamlined:
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index bab49da8a0f0..d3181936c138 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -131,7 +131,7 @@ static inline int mutex_is_locked(struct mutex *lock)
 }
 
 /*
- * See kernel/mutex.c for detailed documentation of these APIs.
+ * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/mutex-design.txt.
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index d24105b1b794..4dd6e4c219de 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -1,5 +1,5 @@
 /*
- * kernel/mutex.c
+ * kernel/locking/mutex.c
  *
  * Mutexes: blocking mutual exclusion locks
  *
-- 
cgit 


From a941f8360f200d6849b292f9dc50250bca531c0e Mon Sep 17 00:00:00 2001
From: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Date: Fri, 8 Nov 2013 20:47:36 +0800
Subject: mm, slub: fix the typo in include/linux/slub_def.h

Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/slub_def.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 027276fa8713..2dc4e78fc234 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -17,7 +17,7 @@
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
 	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
-	FREE_FASTPATH,		/* Free to cpu slub */
+	FREE_FASTPATH,		/* Free to cpu slab */
 	FREE_SLOWPATH,		/* Freeing not to cpu slab */
 	FREE_FROZEN,		/* Freeing to frozen slab */
 	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
-- 
cgit 


From 51c37a70aaa3f95773af560e6db3073520513912 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 11 Nov 2013 12:20:32 +0100
Subject: random32: fix off-by-one in seeding requirement

For properly initialising the Tausworthe generator [1], we have
a strict seeding requirement, that is, s1 > 1, s2 > 7, s3 > 15.

Commit 697f8d0348 ("random32: seeding improvement") introduced
a __seed() function that imposes boundary checks proposed by the
errata paper [2] to properly ensure above conditions.

However, we're off by one, as the function is implemented as:
"return (x < m) ? x + m : x;", and called with __seed(X, 1),
__seed(X, 7), __seed(X, 15). Thus, an unwanted seed of 1, 7, 15
would be possible, whereas the lower boundary should actually
be of at least 2, 8, 16, just as GSL does. Fix this, as otherwise
an initialization with an unwanted seed could have the effect
that Tausworthe's PRNG properties cannot not be ensured.

Note that this PRNG is *not* used for cryptography in the kernel.

 [1] http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
 [2] http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps

Joint work with Hannes Frederic Sowa.

Fixes: 697f8d0348a6 ("random32: seeding improvement")
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/random.h |  6 +++---
 lib/random32.c         | 14 +++++++-------
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index 6312dd9ba449..bf9085e89fb5 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -50,9 +50,9 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 {
 	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
 
-	state->s1 = __seed(i, 1);
-	state->s2 = __seed(i, 7);
-	state->s3 = __seed(i, 15);
+	state->s1 = __seed(i, 2);
+	state->s2 = __seed(i, 8);
+	state->s3 = __seed(i, 16);
 }
 
 #ifdef CONFIG_ARCH_RANDOM
diff --git a/lib/random32.c b/lib/random32.c
index 52280d5526be..01e8890d1089 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -141,7 +141,7 @@ void prandom_seed(u32 entropy)
 	 */
 	for_each_possible_cpu (i) {
 		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		state->s1 = __seed(state->s1 ^ entropy, 1);
+		state->s1 = __seed(state->s1 ^ entropy, 2);
 	}
 }
 EXPORT_SYMBOL(prandom_seed);
@@ -158,9 +158,9 @@ static int __init prandom_init(void)
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
 
 #define LCG(x)	((x) * 69069)	/* super-duper LCG */
-		state->s1 = __seed(LCG(i + jiffies), 1);
-		state->s2 = __seed(LCG(state->s1), 7);
-		state->s3 = __seed(LCG(state->s2), 15);
+		state->s1 = __seed(LCG(i + jiffies), 2);
+		state->s2 = __seed(LCG(state->s1), 8);
+		state->s3 = __seed(LCG(state->s2), 16);
 
 		/* "warm it up" */
 		prandom_u32_state(state);
@@ -187,9 +187,9 @@ static int __init prandom_reseed(void)
 		u32 seeds[3];
 
 		get_random_bytes(&seeds, sizeof(seeds));
-		state->s1 = __seed(seeds[0], 1);
-		state->s2 = __seed(seeds[1], 7);
-		state->s3 = __seed(seeds[2], 15);
+		state->s1 = __seed(seeds[0], 2);
+		state->s2 = __seed(seeds[1], 8);
+		state->s3 = __seed(seeds[2], 16);
 
 		/* mix it in */
 		prandom_u32_state(state);
-- 
cgit 


From 4af712e8df998475736f3e2727701bd31e3751a9 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 11 Nov 2013 12:20:34 +0100
Subject: random32: add prandom_reseed_late() and call when nonblocking pool
 becomes initialized

The Tausworthe PRNG is initialized at late_initcall time. At that time the
entropy pool serving get_random_bytes is not filled sufficiently. This
patch adds an additional reseeding step as soon as the nonblocking pool
gets marked as initialized.

On some machines it might be possible that late_initcall gets called after
the pool has been initialized. In this situation we won't reseed again.

(A call to prandom_seed_late blocks later invocations of early reseed
attempts.)

Joint work with Daniel Borkmann.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/char/random.c  |  5 ++++-
 include/linux/random.h |  1 +
 lib/random32.c         | 23 ++++++++++++++++++++++-
 3 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 7a744d391756..4fe5609eeb72 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -603,8 +603,11 @@ retry:
 
 	if (!r->initialized && nbits > 0) {
 		r->entropy_total += nbits;
-		if (r->entropy_total > 128)
+		if (r->entropy_total > 128) {
 			r->initialized = 1;
+			if (r == &nonblocking_pool)
+				prandom_reseed_late();
+		}
 	}
 
 	trace_credit_entropy_bits(r->name, nbits, entropy_count,
diff --git a/include/linux/random.h b/include/linux/random.h
index bf9085e89fb5..5117ae348fe8 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -29,6 +29,7 @@ unsigned long randomize_range(unsigned long start, unsigned long end, unsigned l
 u32 prandom_u32(void);
 void prandom_bytes(void *buf, int nbytes);
 void prandom_seed(u32 seed);
+void prandom_reseed_late(void);
 
 u32 prandom_u32_state(struct rnd_state *);
 void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
diff --git a/lib/random32.c b/lib/random32.c
index 12215df701e8..9f2f2fb03dfe 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -200,9 +200,18 @@ static void prandom_start_seed_timer(void)
  *	Generate better values after random number generator
  *	is fully initialized.
  */
-static int __init prandom_reseed(void)
+static void __prandom_reseed(bool late)
 {
 	int i;
+	unsigned long flags;
+	static bool latch = false;
+	static DEFINE_SPINLOCK(lock);
+
+	/* only allow initial seeding (late == false) once */
+	spin_lock_irqsave(&lock, flags);
+	if (latch && !late)
+		goto out;
+	latch = true;
 
 	for_each_possible_cpu(i) {
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
@@ -216,6 +225,18 @@ static int __init prandom_reseed(void)
 		/* mix it in */
 		prandom_u32_state(state);
 	}
+out:
+	spin_unlock_irqrestore(&lock, flags);
+}
+
+void prandom_reseed_late(void)
+{
+	__prandom_reseed(true);
+}
+
+static int __init prandom_reseed(void)
+{
+	__prandom_reseed(false);
 	prandom_start_seed_timer();
 	return 0;
 }
-- 
cgit 


From 38e9efcdb33270b4da72143d8e7ca4dcf7f0989b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 11 Nov 2013 12:20:35 +0100
Subject: random32: move rnd_state to linux/random.h

struct rnd_state got mistakenly pulled into uapi header. It is not
used anywhere and does also not belong there!

Commit 5960164fde ("lib/random32: export pseudo-random number
generator for modules"), the last commit on rnd_state before it
got moved to uapi, says:

  This patch moves the definition of struct rnd_state and the inline
  __seed() function to linux/random.h.  It renames the static __random32()
  function to prandom32() and exports it for use in modules.

Hence, the structure was moved from lib/random32.c to linux/random.h
so that it can be used within modules (FCoE-related code in this
case), but not from user space. However, it seems to have been
mistakenly moved to uapi header through the uapi script. Since no-one
should make use of it from the linux headers, move the structure back
to the kernel for internal use, so that it can be modified on demand.

Joint work with Hannes Frederic Sowa.

Cc: Joe Eykholt <jeykholt@cisco.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/random.h      | 4 ++++
 include/uapi/linux/random.h | 7 -------
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index 5117ae348fe8..8ef0b70bd1f9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -31,6 +31,10 @@ void prandom_bytes(void *buf, int nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+struct rnd_state {
+	__u32 s1, s2, s3;
+};
+
 u32 prandom_u32_state(struct rnd_state *);
 void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
 
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index 7471b5b3b8ba..fff3528a078f 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -40,11 +40,4 @@ struct rand_pool_info {
 	__u32	buf[0];
 };
 
-struct rnd_state {
-	__u32 s1, s2, s3;
-};
-
-/* Exported functions */
-
-
 #endif /* _UAPI_LINUX_RANDOM_H */
-- 
cgit 


From a98814cef87946d2708812ad9f8b1e03b8366b6f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 11 Nov 2013 12:20:36 +0100
Subject: random32: upgrade taus88 generator to taus113 from errata paper

Since we use prandom*() functions quite often in networking code
i.e. in UDP port selection, netfilter code, etc, upgrade the PRNG
from Pierre L'Ecuyer's original paper "Maximally Equidistributed
Combined Tausworthe Generators", Mathematics of Computation, 65,
213 (1996), 203--213 to the version published in his errata paper [1].

The Tausworthe generator is a maximally-equidistributed generator,
that is fast and has good statistical properties [1].

The version presented there upgrades the 3 state LFSR to a 4 state
LFSR with increased periodicity from about 2^88 to 2^113. The
algorithm is presented in [1] by the very same author who also
designed the original algorithm in [2].

Also, by increasing the state, we make it a bit harder for attackers
to "guess" the PRNGs internal state. See also discussion in [3].

Now, as we use this sort of weak initialization discussed in [3]
only between core_initcall() until late_initcall() time [*] for
prandom32*() users, namely in prandom_init(), it is less relevant
from late_initcall() onwards as we overwrite seeds through
prandom_reseed() anyways with a seed source of higher entropy, that
is, get_random_bytes(). In other words, a exhaustive keysearch of
96 bit would be needed. Now, with the help of this patch, this
state-search increases further to 128 bit. Initialization needs
to make sure that s1 > 1, s2 > 7, s3 > 15, s4 > 127.

taus88 and taus113 algorithm is also part of GSL. I added a test
case in the next patch to verify internal behaviour of this patch
with GSL and ran tests with the dieharder 3.31.1 RNG test suite:

$ dieharder -g 052 -a -m 10 -s 1 -S 4137730333 #taus88
$ dieharder -g 054 -a -m 10 -s 1 -S 4137730333 #taus113

With this seed configuration, in order to compare both, we get
the following differences:

algorithm                 taus88           taus113
rands/second [**]         1.61e+08         1.37e+08
sts_serial(4, 1st run)    WEAK             PASSED
sts_serial(9, 2nd run)    WEAK             PASSED
rgb_lagged_sum(31)        WEAK             PASSED

We took out diehard_sums test as according to the authors it is
considered broken and unusable [4]. Despite that and the slight
decrease in performance (which is acceptable), taus113 here passes
all 113 tests (only rgb_minimum_distance_5 in WEAK, the rest PASSED).
In general, taus/taus113 is considered "very good" by the authors
of dieharder [5].

The papers [1][2] states a single warm-up step is sufficient by
running quicktaus once on each state to ensure proper initialization
of ~s_{0}:

Our selection of (s) according to Table 1 of [1] row 1 holds the
condition L - k <= r - s, that is,

  (32 32 32 32) - (31 29 28 25) <= (25 27 15 22) - (18 2 7 13)

with r = k - q and q = (6 2 13 3) as also stated by the paper.
So according to [2] we are safe with one round of quicktaus for
initialization. However we decided to include the warm-up phase
of the PRNG as done in GSL in every case as a safety net. We also
use the warm up phase to make the output of the RNG easier to
verify by the GSL output.

In prandom_init(), we also mix random_get_entropy() into it, just
like drivers/char/random.c does it, jiffies ^ random_get_entropy().
random-get_entropy() is get_cycles(). xor is entropy preserving so
it is fine if it is not implemented by some architectures.

Note, this PRNG is *not* used for cryptography in the kernel, but
rather as a fast PRNG for various randomizations i.e. in the
networking code, or elsewhere for debugging purposes, for example.

[*]: In order to generate some "sort of pseduo-randomness", since
get_random_bytes() is not yet available for us, we use jiffies and
initialize states s1 - s3 with a simple linear congruential generator
(LCG), that is x <- x * 69069; and derive s2, s3, from the 32bit
initialization from s1. So the above quote from [3] accounts only
for the time from core to late initcall, not afterwards.
[**] Single threaded run on MacBook Air w/ Intel Core i5-3317U

 [1] http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
 [2] http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
 [3] http://thread.gmane.org/gmane.comp.encryption.general/12103/
 [4] http://code.google.com/p/dieharder/source/browse/trunk/libdieharder/diehard_sums.c?spec=svn490&r=490#20
 [5] http://www.phy.duke.edu/~rgb/General/dieharder.php

Joint work with Hannes Frederic Sowa.

Cc: Florian Weimer <fweimer@redhat.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/random.h | 11 +++----
 lib/random32.c         | 80 +++++++++++++++++++++++++++++---------------------
 2 files changed, 52 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/random.h b/include/linux/random.h
index 8ef0b70bd1f9..4002b3df4c85 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -32,10 +32,10 @@ void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
 struct rnd_state {
-	__u32 s1, s2, s3;
+	__u32 s1, s2, s3, s4;
 };
 
-u32 prandom_u32_state(struct rnd_state *);
+u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes);
 
 /*
@@ -55,9 +55,10 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 {
 	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
 
-	state->s1 = __seed(i, 2);
-	state->s2 = __seed(i, 8);
-	state->s3 = __seed(i, 16);
+	state->s1 = __seed(i,   2U);
+	state->s2 = __seed(i,   8U);
+	state->s3 = __seed(i,  16U);
+	state->s4 = __seed(i, 128U);
 }
 
 #ifdef CONFIG_ARCH_RANDOM
diff --git a/lib/random32.c b/lib/random32.c
index 9f2f2fb03dfe..27adb753180f 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -2,19 +2,19 @@
   This is a maximally equidistributed combined Tausworthe generator
   based on code from GNU Scientific Library 1.5 (30 Jun 2004)
 
-   x_n = (s1_n ^ s2_n ^ s3_n)
+  lfsr113 version:
 
-   s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19))
-   s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25))
-   s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11))
+   x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n)
 
-   The period of this generator is about 2^88.
+   s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n <<  6) ^ s1_n) >> 13))
+   s2_{n+1} = (((s2_n & 4294967288) <<  2) ^ (((s2_n <<  2) ^ s2_n) >> 27))
+   s3_{n+1} = (((s3_n & 4294967280) <<  7) ^ (((s3_n << 13) ^ s3_n) >> 21))
+   s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n <<  3) ^ s4_n) >> 12))
 
-   From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
-   Generators", Mathematics of Computation, 65, 213 (1996), 203--213.
-
-   This is available on the net from L'Ecuyer's home page,
+   The period of this generator is about 2^113 (see erratum paper).
 
+   From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
+   Generators", Mathematics of Computation, 65, 213 (1996), 203--213:
    http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
    ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
 
@@ -29,7 +29,7 @@
         that paper.)
 
    This affects the seeding procedure by imposing the requirement
-   s1 > 1, s2 > 7, s3 > 15.
+   s1 > 1, s2 > 7, s3 > 15, s4 > 127.
 
 */
 
@@ -52,11 +52,12 @@ u32 prandom_u32_state(struct rnd_state *state)
 {
 #define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
 
-	state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12);
-	state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4);
-	state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17);
+	state->s1 = TAUSWORTHE(state->s1,  6U, 13U, 4294967294U, 18U);
+	state->s2 = TAUSWORTHE(state->s2,  2U, 27U, 4294967288U,  2U);
+	state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U,  7U);
+	state->s4 = TAUSWORTHE(state->s4,  3U, 12U, 4294967168U, 13U);
 
-	return (state->s1 ^ state->s2 ^ state->s3);
+	return (state->s1 ^ state->s2 ^ state->s3 ^ state->s4);
 }
 EXPORT_SYMBOL(prandom_u32_state);
 
@@ -126,6 +127,21 @@ void prandom_bytes(void *buf, int bytes)
 }
 EXPORT_SYMBOL(prandom_bytes);
 
+static void prandom_warmup(struct rnd_state *state)
+{
+	/* Calling RNG ten times to satify recurrence condition */
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+	prandom_u32_state(state);
+}
+
 /**
  *	prandom_seed - add entropy to pseudo random number generator
  *	@seed: seed value
@@ -141,8 +157,9 @@ void prandom_seed(u32 entropy)
 	 */
 	for_each_possible_cpu (i) {
 		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		state->s1 = __seed(state->s1 ^ entropy, 2);
-		prandom_u32_state(state);
+
+		state->s1 = __seed(state->s1 ^ entropy, 2U);
+		prandom_warmup(state);
 	}
 }
 EXPORT_SYMBOL(prandom_seed);
@@ -158,18 +175,13 @@ static int __init prandom_init(void)
 	for_each_possible_cpu(i) {
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
 
-#define LCG(x)	((x) * 69069)	/* super-duper LCG */
-		state->s1 = __seed(LCG(i + jiffies), 2);
-		state->s2 = __seed(LCG(state->s1), 8);
-		state->s3 = __seed(LCG(state->s2), 16);
-
-		/* "warm it up" */
-		prandom_u32_state(state);
-		prandom_u32_state(state);
-		prandom_u32_state(state);
-		prandom_u32_state(state);
-		prandom_u32_state(state);
-		prandom_u32_state(state);
+#define LCG(x)	((x) * 69069U)	/* super-duper LCG */
+		state->s1 = __seed(LCG((i + jiffies) ^ random_get_entropy()), 2U);
+		state->s2 = __seed(LCG(state->s1),   8U);
+		state->s3 = __seed(LCG(state->s2),  16U);
+		state->s4 = __seed(LCG(state->s3), 128U);
+
+		prandom_warmup(state);
 	}
 	return 0;
 }
@@ -215,15 +227,15 @@ static void __prandom_reseed(bool late)
 
 	for_each_possible_cpu(i) {
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
-		u32 seeds[3];
+		u32 seeds[4];
 
 		get_random_bytes(&seeds, sizeof(seeds));
-		state->s1 = __seed(seeds[0], 2);
-		state->s2 = __seed(seeds[1], 8);
-		state->s3 = __seed(seeds[2], 16);
+		state->s1 = __seed(seeds[0],   2U);
+		state->s2 = __seed(seeds[1],   8U);
+		state->s3 = __seed(seeds[2],  16U);
+		state->s4 = __seed(seeds[3], 128U);
 
-		/* mix it in */
-		prandom_u32_state(state);
+		prandom_warmup(state);
 	}
 out:
 	spin_unlock_irqrestore(&lock, flags);
-- 
cgit 


From 294e30fee35d3151d100cfe59e839c2dbc16a374 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fusionio.com>
Date: Wed, 9 Oct 2013 12:00:56 -0400
Subject: Btrfs: add tests for find_lock_delalloc_range

So both Liu and I made huge messes of find_lock_delalloc_range trying to fix
stuff, me first by fixing extent size, then him by fixing something I broke and
then me again telling him to fix it a different way.  So this is obviously a
candidate for some testing.  This patch adds a pseudo fs so we can allocate fake
inodes for tests that need an inode or pages.  Then it addes a bunch of tests to
make sure find_lock_delalloc_range is acting the way it is supposed to.  With
this patch and all of our previous patches to find_lock_delalloc_range I am sure
it is working as expected now.  Thanks,

Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
---
 fs/btrfs/Makefile                |   2 +-
 fs/btrfs/ctree.h                 |   6 +
 fs/btrfs/extent_io.c             |   9 +-
 fs/btrfs/extent_io.h             |   6 +
 fs/btrfs/super.c                 |  14 +-
 fs/btrfs/tests/btrfs-tests.c     |  68 ++++++++++
 fs/btrfs/tests/btrfs-tests.h     |  15 +++
 fs/btrfs/tests/extent-io-tests.c | 276 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/magic.h       |   2 +-
 9 files changed, 389 insertions(+), 9 deletions(-)
 create mode 100644 fs/btrfs/tests/btrfs-tests.c
 create mode 100644 fs/btrfs/tests/extent-io-tests.c

(limited to 'include')

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 4c7dfbfaa3b3..cac4f2d001a3 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -15,4 +15,4 @@ btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
-	tests/extent-buffer-tests.o
+	tests/extent-buffer-tests.o tests/btrfs-tests.o tests/extent-io-tests.o
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9ca15a84cc5a..2f398062b942 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -47,6 +47,12 @@ extern struct kmem_cache *btrfs_path_cachep;
 extern struct kmem_cache *btrfs_free_space_cachep;
 struct btrfs_ordered_sum;
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+#define STATIC noinline
+#else
+#define STATIC static noinline
+#endif
+
 #define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
 
 #define BTRFS_MAX_MIRRORS 3
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2bf6f46fae44..c10291cc4fd1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1598,11 +1598,10 @@ done:
  *
  * 1 is returned if we find something, 0 if nothing was in the tree
  */
-static noinline u64 find_lock_delalloc_range(struct inode *inode,
-					     struct extent_io_tree *tree,
-					     struct page *locked_page,
-					     u64 *start, u64 *end,
-					     u64 max_bytes)
+STATIC u64 find_lock_delalloc_range(struct inode *inode,
+				    struct extent_io_tree *tree,
+				    struct page *locked_page, u64 *start,
+				    u64 *end, u64 max_bytes)
 {
 	u64 delalloc_start;
 	u64 delalloc_end;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 6dbc645f1f3d..f98602eac808 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -345,4 +345,10 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 			 int mirror_num);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+noinline u64 find_lock_delalloc_range(struct inode *inode,
+				      struct extent_io_tree *tree,
+				      struct page *locked_page, u64 *start,
+				      u64 *end, u64 max_bytes);
+#endif
 #endif
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0e398657d759..78041e34d15a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1791,10 +1791,20 @@ static int btrfs_run_sanity_tests(void)
 {
 	int ret;
 
-	ret = btrfs_test_free_space_cache();
+	ret = btrfs_init_test_fs();
 	if (ret)
 		return ret;
-	return btrfs_test_extent_buffer_operations();
+
+	ret = btrfs_test_free_space_cache();
+	if (ret)
+		goto out;
+	ret = btrfs_test_extent_buffer_operations();
+	if (ret)
+		goto out;
+	ret = btrfs_test_extent_io();
+out:
+	btrfs_destroy_test_fs();
+	return ret;
 }
 
 static int __init init_btrfs_fs(void)
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
new file mode 100644
index 000000000000..697d527377c1
--- /dev/null
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2013 Fusion IO.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/magic.h>
+#include "btrfs-tests.h"
+#include "../ctree.h"
+
+static struct vfsmount *test_mnt = NULL;
+
+static struct dentry *btrfs_test_mount(struct file_system_type *fs_type,
+				       int flags, const char *dev_name,
+				       void *data)
+{
+	return mount_pseudo(fs_type, "btrfs_test:", NULL, NULL, BTRFS_TEST_MAGIC);
+}
+
+static struct file_system_type test_type = {
+	.name		= "btrfs_test_fs",
+	.mount		= btrfs_test_mount,
+	.kill_sb	= kill_anon_super,
+};
+
+struct inode *btrfs_new_test_inode(void)
+{
+	return new_inode(test_mnt->mnt_sb);
+}
+
+int btrfs_init_test_fs(void)
+{
+	int ret;
+
+	ret = register_filesystem(&test_type);
+	if (ret) {
+		printk(KERN_ERR "btrfs: cannot register test file system\n");
+		return ret;
+	}
+
+	test_mnt = kern_mount(&test_type);
+	if (IS_ERR(test_mnt)) {
+		printk(KERN_ERR "btrfs: cannot mount test file system\n");
+		unregister_filesystem(&test_type);
+		return ret;
+	}
+	return 0;
+}
+
+void btrfs_destroy_test_fs(void)
+{
+	kern_unmount(test_mnt);
+	unregister_filesystem(&test_type);
+}
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 04f2cd2ca568..e935fe5291e7 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -25,6 +25,10 @@
 
 int btrfs_test_free_space_cache(void);
 int btrfs_test_extent_buffer_operations(void);
+int btrfs_test_extent_io(void);
+int btrfs_init_test_fs(void);
+void btrfs_destroy_test_fs(void);
+struct inode *btrfs_new_test_inode(void);
 #else
 static inline int btrfs_test_free_space_cache(void)
 {
@@ -34,6 +38,17 @@ static inline int btrfs_test_extent_buffer_operations(void)
 {
 	return 0;
 }
+static inline int btrfs_init_test_fs(void)
+{
+	return 0;
+}
+static inline void btrfs_destroy_test_fs(void)
+{
+}
+static inline int btrfs_test_extent_io(void)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
new file mode 100644
index 000000000000..7e99c2f98dd0
--- /dev/null
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -0,0 +1,276 @@
+/*
+ * Copyright (C) 2013 Fusion IO.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+#include "btrfs-tests.h"
+#include "../extent_io.h"
+
+#define PROCESS_UNLOCK		(1 << 0)
+#define PROCESS_RELEASE		(1 << 1)
+#define PROCESS_TEST_LOCKED	(1 << 2)
+
+static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
+				       unsigned long flags)
+{
+	int ret;
+	struct page *pages[16];
+	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	unsigned long nr_pages = end_index - index + 1;
+	int i;
+	int count = 0;
+	int loops = 0;
+
+	while (nr_pages > 0) {
+		ret = find_get_pages_contig(inode->i_mapping, index,
+				     min_t(unsigned long, nr_pages,
+				     ARRAY_SIZE(pages)), pages);
+		for (i = 0; i < ret; i++) {
+			if (flags & PROCESS_TEST_LOCKED &&
+			    !PageLocked(pages[i]))
+				count++;
+			if (flags & PROCESS_UNLOCK && PageLocked(pages[i]))
+				unlock_page(pages[i]);
+			page_cache_release(pages[i]);
+			if (flags & PROCESS_RELEASE)
+				page_cache_release(pages[i]);
+		}
+		nr_pages -= ret;
+		index += ret;
+		cond_resched();
+		loops++;
+		if (loops > 100000) {
+			printk(KERN_ERR "stuck in a loop, start %Lu, end %Lu, nr_pages %lu, ret %d\n", start, end, nr_pages, ret);
+			break;
+		}
+	}
+	return count;
+}
+
+static int test_find_delalloc(void)
+{
+	struct inode *inode;
+	struct extent_io_tree tmp;
+	struct page *page;
+	struct page *locked_page = NULL;
+	unsigned long index = 0;
+	u64 total_dirty = 256 * 1024 * 1024;
+	u64 max_bytes = 128 * 1024 * 1024;
+	u64 start, end, test_start;
+	u64 found;
+	int ret = -EINVAL;
+
+	inode = btrfs_new_test_inode();
+	if (!inode) {
+		test_msg("Failed to allocate test inode\n");
+		return -ENOMEM;
+	}
+
+	extent_io_tree_init(&tmp, &inode->i_data);
+
+	/*
+	 * First go through and create and mark all of our pages dirty, we pin
+	 * everything to make sure our pages don't get evicted and screw up our
+	 * test.
+	 */
+	for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) {
+		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+		if (!page) {
+			test_msg("Failed to allocate test page\n");
+			ret = -ENOMEM;
+			goto out;
+		}
+		SetPageDirty(page);
+		if (index) {
+			unlock_page(page);
+		} else {
+			page_cache_get(page);
+			locked_page = page;
+		}
+	}
+
+	/* Test this scenario
+	 * |--- delalloc ---|
+	 * |---  search  ---|
+	 */
+	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS);
+	start = 0;
+	end = 0;
+	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
+					 &end, max_bytes);
+	if (!found) {
+		test_msg("Should have found at least one delalloc\n");
+		goto out_bits;
+	}
+	if (start != 0 || end != 4095) {
+		test_msg("Expected start 0 end 4095, got start %Lu end %Lu\n",
+			 start, end);
+		goto out_bits;
+	}
+	unlock_extent(&tmp, start, end);
+	unlock_page(locked_page);
+	page_cache_release(locked_page);
+
+	/*
+	 * Test this scenario
+	 *
+	 * |--- delalloc ---|
+	 *           |--- search ---|
+	 */
+	test_start = 64 * 1024 * 1024;
+	locked_page = find_lock_page(inode->i_mapping,
+				     test_start >> PAGE_CACHE_SHIFT);
+	if (!locked_page) {
+		test_msg("Couldn't find the locked page\n");
+		goto out_bits;
+	}
+	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS);
+	start = test_start;
+	end = 0;
+	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
+					 &end, max_bytes);
+	if (!found) {
+		test_msg("Couldn't find delalloc in our range\n");
+		goto out_bits;
+	}
+	if (start != test_start || end != max_bytes - 1) {
+		test_msg("Expected start %Lu end %Lu, got start %Lu, end "
+			 "%Lu\n", test_start, max_bytes - 1, start, end);
+		goto out_bits;
+	}
+	if (process_page_range(inode, start, end,
+			       PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
+		test_msg("There were unlocked pages in the range\n");
+		goto out_bits;
+	}
+	unlock_extent(&tmp, start, end);
+	/* locked_page was unlocked above */
+	page_cache_release(locked_page);
+
+	/*
+	 * Test this scenario
+	 * |--- delalloc ---|
+	 *                    |--- search ---|
+	 */
+	test_start = max_bytes + 4096;
+	locked_page = find_lock_page(inode->i_mapping, test_start >>
+				     PAGE_CACHE_SHIFT);
+	if (!locked_page) {
+		test_msg("Could'nt find the locked page\n");
+		goto out_bits;
+	}
+	start = test_start;
+	end = 0;
+	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
+					 &end, max_bytes);
+	if (found) {
+		test_msg("Found range when we shouldn't have\n");
+		goto out_bits;
+	}
+	if (end != (u64)-1) {
+		test_msg("Did not return the proper end offset\n");
+		goto out_bits;
+	}
+
+	/*
+	 * Test this scenario
+	 * [------- delalloc -------|
+	 * [max_bytes]|-- search--|
+	 *
+	 * We are re-using our test_start from above since it works out well.
+	 */
+	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS);
+	start = test_start;
+	end = 0;
+	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
+					 &end, max_bytes);
+	if (!found) {
+		test_msg("Didn't find our range\n");
+		goto out_bits;
+	}
+	if (start != test_start || end != total_dirty - 1) {
+		test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
+			 test_start, total_dirty - 1, start, end);
+		goto out_bits;
+	}
+	if (process_page_range(inode, start, end,
+			       PROCESS_TEST_LOCKED | PROCESS_UNLOCK)) {
+		test_msg("Pages in range were not all locked\n");
+		goto out_bits;
+	}
+	unlock_extent(&tmp, start, end);
+
+	/*
+	 * Now to test where we run into a page that is no longer dirty in the
+	 * range we want to find.
+	 */
+	page = find_get_page(inode->i_mapping, (max_bytes + (1 * 1024 * 1024))
+			     >> PAGE_CACHE_SHIFT);
+	if (!page) {
+		test_msg("Couldn't find our page\n");
+		goto out_bits;
+	}
+	ClearPageDirty(page);
+	page_cache_release(page);
+
+	/* We unlocked it in the previous test */
+	lock_page(locked_page);
+	start = test_start;
+	end = 0;
+	/*
+	 * Currently if we fail to find dirty pages in the delalloc range we
+	 * will adjust max_bytes down to PAGE_CACHE_SIZE and then re-search.  If
+	 * this changes at any point in the future we will need to fix this
+	 * tests expected behavior.
+	 */
+	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
+					 &end, max_bytes);
+	if (!found) {
+		test_msg("Didn't find our range\n");
+		goto out_bits;
+	}
+	if (start != test_start && end != test_start + PAGE_CACHE_SIZE - 1) {
+		test_msg("Expected start %Lu end %Lu, got start %Lu end %Lu\n",
+			 test_start, test_start + PAGE_CACHE_SIZE - 1, start,
+			 end);
+		goto out_bits;
+	}
+	if (process_page_range(inode, start, end, PROCESS_TEST_LOCKED |
+			       PROCESS_UNLOCK)) {
+		test_msg("Pages in range were not all locked\n");
+		goto out_bits;
+	}
+	ret = 0;
+out_bits:
+	clear_extent_bits(&tmp, 0, total_dirty - 1,
+			  (unsigned long)-1, GFP_NOFS);
+out:
+	if (locked_page)
+		page_cache_release(locked_page);
+	process_page_range(inode, 0, total_dirty - 1,
+			   PROCESS_UNLOCK | PROCESS_RELEASE);
+	iput(inode);
+	return ret;
+}
+
+int btrfs_test_extent_io(void)
+{
+	test_msg("Running find delalloc tests\n");
+	return test_find_delalloc();
+}
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 2944278a8ba7..77c60311a6c6 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -71,6 +71,6 @@
 #define USBDEVICE_SUPER_MAGIC	0x9fa2
 #define MTD_INODE_FS_MAGIC      0x11307854
 #define ANON_INODE_FS_MAGIC	0x09041934
-
+#define BTRFS_TEST_MAGIC	0x73727279
 
 #endif /* __LINUX_MAGIC_H__ */
-- 
cgit 


From 7f7caf6aa74a4f4ad21ebe08bf23b594fce45ca7 Mon Sep 17 00:00:00 2001
From: Andy Grover <agrover@redhat.com>
Date: Mon, 11 Nov 2013 08:59:17 -0800
Subject: target: Pass through I/O topology for block backstores

In addition to block size (already implemented), passing through
alignment offset, logical-to-phys block exponent, I/O granularity and
optimal I/O length will allow initiators to properly handle layout on
LUNs with 4K block sizes.

Tested with various weird values via scsi_debug module.

One thing to look at with this patch is the new block limits values --
instead of granularity 1 optimal 8192, Lio will now be returning whatever
the block device says, which may affect performance.

Signed-off-by: Andy Grover <agrover@redhat.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_iblock.c  | 43 ++++++++++++++++++++++++++++++++++++
 drivers/target/target_core_sbc.c     | 12 +++++++++-
 drivers/target/target_core_spc.c     | 11 +++++++--
 include/target/target_core_backend.h |  5 +++++
 4 files changed, 68 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index b9a3394fe479..c87959f12760 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -710,6 +710,45 @@ static sector_t iblock_get_blocks(struct se_device *dev)
 	return iblock_emulate_read_cap_with_block_size(dev, bd, q);
 }
 
+static sector_t iblock_get_alignment_offset_lbas(struct se_device *dev)
+{
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
+	int ret;
+
+	ret = bdev_alignment_offset(bd);
+	if (ret == -1)
+		return 0;
+
+	/* convert offset-bytes to offset-lbas */
+	return ret / bdev_logical_block_size(bd);
+}
+
+static unsigned int iblock_get_lbppbe(struct se_device *dev)
+{
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
+	int logs_per_phys = bdev_physical_block_size(bd) / bdev_logical_block_size(bd);
+
+	return ilog2(logs_per_phys);
+}
+
+static unsigned int iblock_get_io_min(struct se_device *dev)
+{
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
+
+	return bdev_io_min(bd);
+}
+
+static unsigned int iblock_get_io_opt(struct se_device *dev)
+{
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bd = ib_dev->ibd_bd;
+
+	return bdev_io_opt(bd);
+}
+
 static struct sbc_ops iblock_sbc_ops = {
 	.execute_rw		= iblock_execute_rw,
 	.execute_sync_cache	= iblock_execute_sync_cache,
@@ -749,6 +788,10 @@ static struct se_subsystem_api iblock_template = {
 	.show_configfs_dev_params = iblock_show_configfs_dev_params,
 	.get_device_type	= sbc_get_device_type,
 	.get_blocks		= iblock_get_blocks,
+	.get_alignment_offset_lbas = iblock_get_alignment_offset_lbas,
+	.get_lbppbe		= iblock_get_lbppbe,
+	.get_io_min		= iblock_get_io_min,
+	.get_io_opt		= iblock_get_io_opt,
 	.get_write_cache	= iblock_get_write_cache,
 };
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 6c17295e8d7c..61a30f0d7583 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -105,12 +105,22 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 	buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff;
 	buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff;
 	buf[11] = dev->dev_attrib.block_size & 0xff;
+
+	if (dev->transport->get_lbppbe)
+		buf[13] = dev->transport->get_lbppbe(dev) & 0x0f;
+
+	if (dev->transport->get_alignment_offset_lbas) {
+		u16 lalba = dev->transport->get_alignment_offset_lbas(dev);
+		buf[14] = (lalba >> 8) & 0x3f;
+		buf[15] = lalba & 0xff;
+	}
+
 	/*
 	 * Set Thin Provisioning Enable bit following sbc3r22 in section
 	 * READ CAPACITY (16) byte 14 if emulate_tpu or emulate_tpws is enabled.
 	 */
 	if (dev->dev_attrib.emulate_tpu || dev->dev_attrib.emulate_tpws)
-		buf[14] = 0x80;
+		buf[14] |= 0x80;
 
 	rbuf = transport_kmap_data_sg(cmd);
 	if (rbuf) {
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 074539558a54..f89a86f29ee3 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -452,6 +452,7 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	struct se_device *dev = cmd->se_dev;
 	u32 max_sectors;
 	int have_tp = 0;
+	int opt, min;
 
 	/*
 	 * Following spc3r22 section 6.5.3 Block Limits VPD page, when
@@ -475,7 +476,10 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set OPTIMAL TRANSFER LENGTH GRANULARITY
 	 */
-	put_unaligned_be16(1, &buf[6]);
+	if (dev->transport->get_io_min && (min = dev->transport->get_io_min(dev)))
+		put_unaligned_be16(min / dev->dev_attrib.block_size, &buf[6]);
+	else
+		put_unaligned_be16(1, &buf[6]);
 
 	/*
 	 * Set MAXIMUM TRANSFER LENGTH
@@ -487,7 +491,10 @@ spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
 	/*
 	 * Set OPTIMAL TRANSFER LENGTH
 	 */
-	put_unaligned_be32(dev->dev_attrib.optimal_sectors, &buf[12]);
+	if (dev->transport->get_io_opt && (opt = dev->transport->get_io_opt(dev)))
+		put_unaligned_be32(opt / dev->dev_attrib.block_size, &buf[12]);
+	else
+		put_unaligned_be32(dev->dev_attrib.optimal_sectors, &buf[12]);
 
 	/*
 	 * Exit now if we don't support TP.
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 5ebe21cd5d1c..39e0114d70c5 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -34,6 +34,11 @@ struct se_subsystem_api {
 	sense_reason_t (*parse_cdb)(struct se_cmd *cmd);
 	u32 (*get_device_type)(struct se_device *);
 	sector_t (*get_blocks)(struct se_device *);
+	sector_t (*get_alignment_offset_lbas)(struct se_device *);
+	/* lbppbe = logical blocks per physical block exponent. see SBC-3 */
+	unsigned int (*get_lbppbe)(struct se_device *);
+	unsigned int (*get_io_min)(struct se_device *);
+	unsigned int (*get_io_opt)(struct se_device *);
 	unsigned char *(*get_sense_buffer)(struct se_cmd *);
 	bool (*get_write_cache)(struct se_device *);
 };
-- 
cgit 


From b9921ecdee66984b00c38c00a358ef3f611d2b50 Mon Sep 17 00:00:00 2001
From: Qiang Huang <h.huangqiang@huawei.com>
Date: Tue, 12 Nov 2013 15:07:22 -0800
Subject: mm: add a helper function to check may oom condition

Use helper function to check if we need to deal with oom condition.

Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/oom.h | 5 +++++
 mm/memcontrol.c     | 9 +--------
 mm/page_alloc.c     | 2 +-
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index da60007075b5..4cd62677feb9 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -82,6 +82,11 @@ static inline void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
+static inline bool oom_gfp_allowed(gfp_t gfp_mask)
+{
+	return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
+}
+
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
 /* sysctls */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 13b9d0f221b8..3427de9897a5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2984,21 +2984,14 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	struct res_counter *fail_res;
 	struct mem_cgroup *_memcg;
 	int ret = 0;
-	bool may_oom;
 
 	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
 	if (ret)
 		return ret;
 
-	/*
-	 * Conditions under which we can wait for the oom_killer. Those are
-	 * the same conditions tested by the core page allocator
-	 */
-	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
-
 	_memcg = memcg;
 	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
-				      &_memcg, may_oom);
+				      &_memcg, oom_gfp_allowed(gfp));
 
 	if (ret == -EINTR)  {
 		/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3d1d75a6629f..e0412c026e0d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2593,7 +2593,7 @@ rebalance:
 	 * running out of options and have to consider going OOM
 	 */
 	if (!did_some_progress) {
-		if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+		if (oom_gfp_allowed(gfp_mask)) {
 			if (oom_killer_disabled)
 				goto nopage;
 			/* Coredumps can quickly deplete all memory reserves */
-- 
cgit 


From 01b0f19707c51ef247404e6af1d4a97a11ba34f7 Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hp.com>
Date: Tue, 12 Nov 2013 15:07:25 -0800
Subject: cpu/mem hotplug: add try_online_node() for cpu_up()

cpu_up() has #ifdef CONFIG_MEMORY_HOTPLUG code blocks, which call
mem_online_node() to put its node online if offlined and then call
build_all_zonelists() to initialize the zone list.

These steps are specific to memory hotplug, and should be managed in
mm/memory_hotplug.c.  lock_memory_hotplug() should also be held for the
whole steps.

For this reason, this patch replaces mem_online_node() with
try_online_node(), which performs the whole steps with
lock_memory_hotplug() held.  try_online_node() is named after
try_offline_node() as they have similar purpose.

There is no functional change in this patch.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  8 +++++++-
 kernel/cpu.c                   | 29 +++--------------------------
 mm/memory_hotplug.c            | 16 ++++++++++++++--
 3 files changed, 24 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index dd38e62b84d2..22203c293f07 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -94,6 +94,8 @@ extern void __online_page_set_limits(struct page *page);
 extern void __online_page_increment_counters(struct page *page);
 extern void __online_page_free(struct page *page);
 
+extern int try_online_node(int nid);
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
 extern int arch_remove_memory(u64 start, u64 size);
@@ -225,6 +227,11 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
 
+static inline int try_online_node(int nid)
+{
+	return 0;
+}
+
 static inline void lock_memory_hotplug(void) {}
 static inline void unlock_memory_hotplug(void) {}
 
@@ -256,7 +263,6 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
-extern int mem_online_node(int nid);
 extern int add_memory(int nid, u64 start, u64 size);
 extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 63aa50d7ce1e..973d034acf84 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -437,11 +437,6 @@ int cpu_up(unsigned int cpu)
 {
 	int err = 0;
 
-#ifdef	CONFIG_MEMORY_HOTPLUG
-	int nid;
-	pg_data_t	*pgdat;
-#endif
-
 	if (!cpu_possible(cpu)) {
 		printk(KERN_ERR "can't online cpu %d because it is not "
 			"configured as may-hotadd at boot time\n", cpu);
@@ -452,27 +447,9 @@ int cpu_up(unsigned int cpu)
 		return -EINVAL;
 	}
 
-#ifdef	CONFIG_MEMORY_HOTPLUG
-	nid = cpu_to_node(cpu);
-	if (!node_online(nid)) {
-		err = mem_online_node(nid);
-		if (err)
-			return err;
-	}
-
-	pgdat = NODE_DATA(nid);
-	if (!pgdat) {
-		printk(KERN_ERR
-			"Can't online cpu %d due to NULL pgdat\n", cpu);
-		return -ENOMEM;
-	}
-
-	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
-		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL, NULL);
-		mutex_unlock(&zonelists_mutex);
-	}
-#endif
+	err = try_online_node(cpu_to_node(cpu));
+	if (err)
+		return err;
 
 	cpu_maps_update_begin();
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5118028468eb..8285346be663 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1043,17 +1043,23 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-/*
+/**
+ * try_online_node - online a node if offlined
+ *
  * called by cpu_up() to online a node without onlined memory.
  */
-int mem_online_node(int nid)
+int try_online_node(int nid)
 {
 	pg_data_t	*pgdat;
 	int	ret;
 
+	if (node_online(nid))
+		return 0;
+
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
 	if (!pgdat) {
+		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1061,6 +1067,12 @@ int mem_online_node(int nid)
 	ret = register_one_node(nid);
 	BUG_ON(ret);
 
+	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
+		mutex_lock(&zonelists_mutex);
+		build_all_zonelists(NULL, NULL);
+		mutex_unlock(&zonelists_mutex);
+	}
+
 out:
 	unlock_memory_hotplug();
 	return ret;
-- 
cgit 


From 948927ee9e4f35f287e61a79c9f0e85ca2202c7d Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Tue, 12 Nov 2013 15:07:28 -0800
Subject: mm, mempolicy: make mpol_to_str robust and always succeed

mpol_to_str() should not fail.  Currently, it either fails because the
string buffer is too small or because a string hasn't been defined for a
mempolicy mode.

If a new mempolicy mode is introduced and no string is defined for it,
just warn and return "unknown".

If the buffer is too small, just truncate the string and return, the
same behavior as snprintf().

This also fixes a bug where there was no NULL-byte termination when doing
*p++ = '=' and *p++ ':' and maxlen has been reached.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Chen Gang <gang.chen@asianux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c        | 14 ++++++-------
 include/linux/mempolicy.h |  5 ++---
 mm/mempolicy.c            | 52 +++++++++++++++--------------------------------
 3 files changed, 24 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 390bdab01c3c..9f1369fe0afb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1387,8 +1387,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {};
 	struct mempolicy *pol;
-	int n;
-	char buffer[50];
+	char buffer[64];
+	int nid;
 
 	if (!mm)
 		return 0;
@@ -1404,10 +1404,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	walk.mm = mm;
 
 	pol = get_vma_policy(task, vma, vma->vm_start);
-	n = mpol_to_str(buffer, sizeof(buffer), pol);
+	mpol_to_str(buffer, sizeof(buffer), pol);
 	mpol_cond_put(pol);
-	if (n < 0)
-		return n;
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
@@ -1460,9 +1458,9 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (md->writeback)
 		seq_printf(m, " writeback=%lu", md->writeback);
 
-	for_each_node_state(n, N_MEMORY)
-		if (md->node[n])
-			seq_printf(m, " N%d=%lu", n, md->node[n]);
+	for_each_node_state(nid, N_MEMORY)
+		if (md->node[nid])
+			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
 out:
 	seq_putc(m, '\n');
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index ea4d2495c646..9fe426b30a41 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -169,7 +169,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 extern int mpol_parse_str(char *str, struct mempolicy **mpol);
 #endif
 
-extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
+extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 
 /* Check if a vma is migratable */
 static inline int vma_migratable(struct vm_area_struct *vma)
@@ -307,9 +307,8 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 }
 #endif
 
-static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+static inline void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
-	return 0;
 }
 
 static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 71cb253368cb..260b8213a873 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2914,62 +2914,45 @@ out:
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
  *
- * Convert a mempolicy into a string.
- * Returns the number of characters in buffer (if positive)
- * or an error (negative)
+ * Convert @pol into a string.  If @buffer is too short, truncate the string.
+ * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
+ * longest flag, "relative", and to display at least a few node ids.
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
 	char *p = buffer;
-	int l;
-	nodemask_t nodes;
-	unsigned short mode;
-	unsigned short flags = pol ? pol->flags : 0;
-
-	/*
-	 * Sanity check:  room for longest mode, flag and some nodes
-	 */
-	VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
+	nodemask_t nodes = NODE_MASK_NONE;
+	unsigned short mode = MPOL_DEFAULT;
+	unsigned short flags = 0;
 
-	if (!pol || pol == &default_policy)
-		mode = MPOL_DEFAULT;
-	else
+	if (pol && pol != &default_policy) {
 		mode = pol->mode;
+		flags = pol->flags;
+	}
 
 	switch (mode) {
 	case MPOL_DEFAULT:
-		nodes_clear(nodes);
 		break;
-
 	case MPOL_PREFERRED:
-		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
 			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
-
 	case MPOL_BIND:
-		/* Fall through */
 	case MPOL_INTERLEAVE:
 		nodes = pol->v.nodes;
 		break;
-
 	default:
-		return -EINVAL;
+		WARN_ON_ONCE(1);
+		snprintf(p, maxlen, "unknown");
+		return;
 	}
 
-	l = strlen(policy_modes[mode]);
-	if (buffer + maxlen < p + l + 1)
-		return -ENOSPC;
-
-	strcpy(p, policy_modes[mode]);
-	p += l;
+	p += snprintf(p, maxlen, policy_modes[mode]);
 
 	if (flags & MPOL_MODE_FLAGS) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = '=';
+		p += snprintf(p, buffer + maxlen - p, "=");
 
 		/*
 		 * Currently, the only defined flags are mutually exclusive
@@ -2981,10 +2964,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	}
 
 	if (!nodes_empty(nodes)) {
-		if (buffer + maxlen < p + 2)
-			return -ENOSPC;
-		*p++ = ':';
+		p += snprintf(p, buffer + maxlen - p, ":");
 	 	p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
 	}
-	return p - buffer;
 }
-- 
cgit 


From 85b35feaecd4d2284505b22708795bc1f03fc897 Mon Sep 17 00:00:00 2001
From: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Date: Tue, 12 Nov 2013 15:07:42 -0800
Subject: mm/sparsemem: use PAGES_PER_SECTION to remove redundant nr_pages
 parameter

For below functions,

- sparse_add_one_section()
- kmalloc_section_memmap()
- __kmalloc_section_memmap()
- __kfree_section_memmap()

they are always invoked to operate on one memory section, so it is
redundant to always pass a nr_pages parameter, which is the page numbers
in one section.  So we can directly use predefined macro PAGES_PER_SECTION
instead of passing the parameter.

Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  3 +--
 mm/memory_hotplug.c            |  3 +--
 mm/sparse.c                    | 33 +++++++++++++++------------------
 3 files changed, 17 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 22203c293f07..4ca3d951fe91 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -268,8 +268,7 @@ extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
-extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
-								int nr_pages);
+extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 8285346be663..1b6fe8ca71e6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -401,13 +401,12 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 static int __meminit __add_section(int nid, struct zone *zone,
 					unsigned long phys_start_pfn)
 {
-	int nr_pages = PAGES_PER_SECTION;
 	int ret;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
 
-	ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
+	ret = sparse_add_one_section(zone, phys_start_pfn);
 
 	if (ret < 0)
 		return ret;
diff --git a/mm/sparse.c b/mm/sparse.c
index 4ac1d7ef548f..fbb9dbc6aca9 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -590,16 +590,15 @@ void __init sparse_init(void)
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						 unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
 	/* This will make the necessary allocations eventually. */
 	return sparse_mem_map_populate(pnum, nid);
 }
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
 
 	vmemmap_free(start, end);
 }
@@ -613,10 +612,10 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 #else
-static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+static struct page *__kmalloc_section_memmap(void)
 {
 	struct page *page, *ret;
-	unsigned long memmap_size = sizeof(struct page) * nr_pages;
+	unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
 
 	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
 	if (page)
@@ -634,19 +633,18 @@ got_map_ptr:
 	return ret;
 }
 
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
-						  unsigned long nr_pages)
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid)
 {
-	return __kmalloc_section_memmap(nr_pages);
+	return __kmalloc_section_memmap();
 }
 
-static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+static void __kfree_section_memmap(struct page *memmap)
 {
 	if (is_vmalloc_addr(memmap))
 		vfree(memmap);
 	else
 		free_pages((unsigned long)memmap,
-			   get_order(sizeof(struct page) * nr_pages));
+			   get_order(sizeof(struct page) * PAGES_PER_SECTION));
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
@@ -684,8 +682,7 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
  * set.  If this is <=0, then that means that the passed-in
  * map was not consumed and must be freed.
  */
-int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
-			   int nr_pages)
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct pglist_data *pgdat = zone->zone_pgdat;
@@ -702,12 +699,12 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 	ret = sparse_index_init(section_nr, pgdat->node_id);
 	if (ret < 0 && ret != -EEXIST)
 		return ret;
-	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+	memmap = kmalloc_section_memmap(section_nr, pgdat->node_id);
 	if (!memmap)
 		return -ENOMEM;
 	usemap = __kmalloc_section_usemap();
 	if (!usemap) {
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 		return -ENOMEM;
 	}
 
@@ -719,7 +716,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
-	memset(memmap, 0, sizeof(struct page) * nr_pages);
+	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
 
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
@@ -729,7 +726,7 @@ out:
 	pgdat_resize_unlock(pgdat, &flags);
 	if (ret <= 0) {
 		kfree(usemap);
-		__kfree_section_memmap(memmap, nr_pages);
+		__kfree_section_memmap(memmap);
 	}
 	return ret;
 }
@@ -771,7 +768,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	if (PageSlab(usemap_page) || PageCompound(usemap_page)) {
 		kfree(usemap);
 		if (memmap)
-			__kfree_section_memmap(memmap, PAGES_PER_SECTION);
+			__kfree_section_memmap(memmap);
 		return;
 	}
 
-- 
cgit 


From 46c77e2bb07eba3b38edfec76873f12942c49dd3 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Tue, 12 Nov 2013 15:07:50 -0800
Subject: tools/vm/page-types.c: support KPF_SOFTDIRTY bit

Soft dirty bit allows us to track which pages are written since the last
clear_ref (by "echo 4 > /proc/pid/clear_refs".) This is useful for
userspace applications to know their memory footprints.

Note that the kernel exposes this flag via bit[55] of /proc/pid/pagemap,
and the semantics is not a default one (scheduled to be the default in the
near future.) However, it shifts to the new semantics at the first
clear_ref, and the users of soft dirty bit always do it before utilizing
the bit, so that's not a big deal.  Users must avoid relying on the bit in
page-types before the first clear_ref.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel-page-flags.h |  1 +
 tools/vm/page-types.c             | 32 ++++++++++++++++++++------------
 2 files changed, 21 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index 546eb6a76934..f65ce09784f1 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -15,5 +15,6 @@
 #define KPF_OWNER_PRIVATE	37
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
+#define KPF_SOFTDIRTY		40
 
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 71c9c2511ee7..d5e9d6d185c8 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -59,12 +59,14 @@
 #define PM_PSHIFT_BITS      6
 #define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
 #define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define __PM_PSHIFT(x)      (((uint64_t) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
 #define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
 #define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
 
+#define __PM_SOFT_DIRTY      (1LL)
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
+#define PM_SOFT_DIRTY       __PM_PSHIFT(__PM_SOFT_DIRTY)
 
 
 /*
@@ -83,6 +85,7 @@
 #define KPF_OWNER_PRIVATE	37
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
+#define KPF_SOFTDIRTY		40
 
 /* [48-] take some arbitrary free slots for expanding overloaded flags
  * not part of kernel API
@@ -132,6 +135,7 @@ static const char * const page_flag_names[] = {
 	[KPF_OWNER_PRIVATE]	= "O:owner_private",
 	[KPF_ARCH]		= "h:arch",
 	[KPF_UNCACHED]		= "c:uncached",
+	[KPF_SOFTDIRTY]		= "f:softdirty",
 
 	[KPF_READAHEAD]		= "I:readahead",
 	[KPF_SLOB_FREE]		= "P:slob_free",
@@ -417,7 +421,7 @@ static int bit_mask_ok(uint64_t flags)
 	return 1;
 }
 
-static uint64_t expand_overloaded_flags(uint64_t flags)
+static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 {
 	/* SLOB/SLUB overload several page flags */
 	if (flags & BIT(SLAB)) {
@@ -433,6 +437,9 @@ static uint64_t expand_overloaded_flags(uint64_t flags)
 	if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
 		flags ^= BIT(RECLAIM) | BIT(READAHEAD);
 
+	if (pme & PM_SOFT_DIRTY)
+		flags |= BIT(SOFTDIRTY);
+
 	return flags;
 }
 
@@ -448,11 +455,11 @@ static uint64_t well_known_flags(uint64_t flags)
 	return flags;
 }
 
-static uint64_t kpageflags_flags(uint64_t flags)
+static uint64_t kpageflags_flags(uint64_t flags, uint64_t pme)
 {
-	flags = expand_overloaded_flags(flags);
-
-	if (!opt_raw)
+	if (opt_raw)
+		flags = expand_overloaded_flags(flags, pme);
+	else
 		flags = well_known_flags(flags);
 
 	return flags;
@@ -545,9 +552,9 @@ static size_t hash_slot(uint64_t flags)
 }
 
 static void add_page(unsigned long voffset,
-		     unsigned long offset, uint64_t flags)
+		     unsigned long offset, uint64_t flags, uint64_t pme)
 {
-	flags = kpageflags_flags(flags);
+	flags = kpageflags_flags(flags, pme);
 
 	if (!bit_mask_ok(flags))
 		return;
@@ -569,7 +576,8 @@ static void add_page(unsigned long voffset,
 #define KPAGEFLAGS_BATCH	(64 << 10)	/* 64k pages */
 static void walk_pfn(unsigned long voffset,
 		     unsigned long index,
-		     unsigned long count)
+		     unsigned long count,
+		     uint64_t pme)
 {
 	uint64_t buf[KPAGEFLAGS_BATCH];
 	unsigned long batch;
@@ -583,7 +591,7 @@ static void walk_pfn(unsigned long voffset,
 			break;
 
 		for (i = 0; i < pages; i++)
-			add_page(voffset + i, index + i, buf[i]);
+			add_page(voffset + i, index + i, buf[i], pme);
 
 		index += pages;
 		count -= pages;
@@ -608,7 +616,7 @@ static void walk_vma(unsigned long index, unsigned long count)
 		for (i = 0; i < pages; i++) {
 			pfn = pagemap_pfn(buf[i]);
 			if (pfn)
-				walk_pfn(index + i, pfn, 1);
+				walk_pfn(index + i, pfn, 1, buf[i]);
 		}
 
 		index += pages;
@@ -659,7 +667,7 @@ static void walk_addr_ranges(void)
 
 	for (i = 0; i < nr_addr_ranges; i++)
 		if (!opt_pid)
-			walk_pfn(0, opt_offset[i], opt_size[i]);
+			walk_pfn(0, opt_offset[i], opt_size[i], 0);
 		else
 			walk_task(opt_offset[i], opt_size[i]);
 
-- 
cgit 


From c4a391b53a72d2df4ee97f96f78c1d5971b47489 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 12 Nov 2013 15:07:51 -0800
Subject: writeback: do not sync data dirtied after sync start

When there are processes heavily creating small files while sync(2) is
running, it can easily happen that quite some new files are created
between WB_SYNC_NONE and WB_SYNC_ALL pass of sync(2).  That can happen
especially if there are several busy filesystems (remember that sync
traverses filesystems sequentially and waits in WB_SYNC_ALL phase on one
fs before starting it on another fs).  Because WB_SYNC_ALL pass is slow
(e.g.  causes a transaction commit and cache flush for each inode in
ext3), resulting sync(2) times are rather large.

The following script reproduces the problem:

  function run_writers
  {
    for (( i = 0; i < 10; i++ )); do
      mkdir $1/dir$i
      for (( j = 0; j < 40000; j++ )); do
        dd if=/dev/zero of=$1/dir$i/$j bs=4k count=4 &>/dev/null
      done &
    done
  }

  for dir in "$@"; do
    run_writers $dir
  done

  sleep 40
  time sync

Fix the problem by disregarding inodes dirtied after sync(2) was called
in the WB_SYNC_ALL pass.  To allow for this, sync_inodes_sb() now takes
a time stamp when sync has started which is used for setting up work for
flusher threads.

To give some numbers, when above script is run on two ext4 filesystems
on simple SATA drive, the average sync time from 10 runs is 267.549
seconds with standard deviation 104.799426.  With the patched kernel,
the average sync time from 10 runs is 2.995 seconds with standard
deviation 0.096.

Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Fengguang Wu <fengguang.wu@intel.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fs-writeback.c                | 33 ++++++++++++++++++++++-----------
 fs/sync.c                        | 15 +++++++++------
 fs/xfs/xfs_super.c               |  2 +-
 include/linux/writeback.h        |  2 +-
 include/trace/events/writeback.h |  6 +++---
 5 files changed, 36 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9f4935b8f208..4afdbd6d9678 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -39,13 +39,18 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	unsigned long *older_than_this;
+	/*
+	 * Write only inodes dirtied before this time. Don't forget to set
+	 * older_than_this_is_set when you set this.
+	 */
+	unsigned long older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
 	unsigned int range_cyclic:1;
 	unsigned int for_background:1;
 	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
+	unsigned int older_than_this_is_set:1;
 	enum wb_reason reason;		/* why was writeback initiated? */
 
 	struct list_head list;		/* pending work list */
@@ -246,10 +251,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
+	WARN_ON_ONCE(!work->older_than_this_is_set);
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (work->older_than_this &&
-		    inode_dirtied_after(inode, *work->older_than_this))
+		if (inode_dirtied_after(inode, work->older_than_this))
 			break;
 		list_move(&inode->i_wb_list, &tmp);
 		moved++;
@@ -733,6 +738,8 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 		.range_cyclic	= 1,
 		.reason		= reason,
+		.older_than_this = jiffies,
+		.older_than_this_is_set = 1,
 	};
 
 	spin_lock(&wb->list_lock);
@@ -791,12 +798,13 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
-	unsigned long oldest_jif;
 	struct inode *inode;
 	long progress;
 
-	oldest_jif = jiffies;
-	work->older_than_this = &oldest_jif;
+	if (!work->older_than_this_is_set) {
+		work->older_than_this = jiffies;
+		work->older_than_this_is_set = 1;
+	}
 
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -830,10 +838,10 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			oldest_jif = jiffies -
+			work->older_than_this = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			oldest_jif = jiffies;
+			work->older_than_this = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))
@@ -1345,18 +1353,21 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
 
 /**
  * sync_inodes_sb	-	sync sb inode pages
- * @sb: the superblock
+ * @sb:			the superblock
+ * @older_than_this:	timestamp
  *
  * This function writes and waits on any dirty inode belonging to this
- * super_block.
+ * superblock that has been dirtied before given timestamp.
  */
-void sync_inodes_sb(struct super_block *sb)
+void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct wb_writeback_work work = {
 		.sb		= sb,
 		.sync_mode	= WB_SYNC_ALL,
 		.nr_pages	= LONG_MAX,
+		.older_than_this = older_than_this,
+		.older_than_this_is_set = 1,
 		.range_cyclic	= 0,
 		.done		= &done,
 		.reason		= WB_REASON_SYNC,
diff --git a/fs/sync.c b/fs/sync.c
index 905f3f6b3d85..ff96f99fef64 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,10 +27,11 @@
  * wait == 1 case since in that case write_inode() functions do
  * sync_dirty_buffer() and thus effectively write one block at a time.
  */
-static int __sync_filesystem(struct super_block *sb, int wait)
+static int __sync_filesystem(struct super_block *sb, int wait,
+			     unsigned long start)
 {
 	if (wait)
-		sync_inodes_sb(sb);
+		sync_inodes_sb(sb, start);
 	else
 		writeback_inodes_sb(sb, WB_REASON_SYNC);
 
@@ -47,6 +48,7 @@ static int __sync_filesystem(struct super_block *sb, int wait)
 int sync_filesystem(struct super_block *sb)
 {
 	int ret;
+	unsigned long start = jiffies;
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -60,17 +62,17 @@ int sync_filesystem(struct super_block *sb)
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
 
-	ret = __sync_filesystem(sb, 0);
+	ret = __sync_filesystem(sb, 0, start);
 	if (ret < 0)
 		return ret;
-	return __sync_filesystem(sb, 1);
+	return __sync_filesystem(sb, 1, start);
 }
 EXPORT_SYMBOL_GPL(sync_filesystem);
 
 static void sync_inodes_one_sb(struct super_block *sb, void *arg)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		sync_inodes_sb(sb);
+		sync_inodes_sb(sb, *((unsigned long *)arg));
 }
 
 static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -102,9 +104,10 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
 SYSCALL_DEFINE0(sync)
 {
 	int nowait = 0, wait = 1;
+	unsigned long start = jiffies;
 
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
-	iterate_supers(sync_inodes_one_sb, NULL);
+	iterate_supers(sync_inodes_one_sb, &start);
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &wait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 15188cc99449..8968f5036fa1 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -918,7 +918,7 @@ xfs_flush_inodes(
 	struct super_block	*sb = mp->m_super;
 
 	if (down_read_trylock(&sb->s_umount)) {
-		sync_inodes_sb(sb);
+		sync_inodes_sb(sb, jiffies);
 		up_read(&sb->s_umount);
 	}
 }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 021b8a319b9e..fc0e4320aa6d 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -97,7 +97,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 				  enum wb_reason reason);
-void sync_inodes_sb(struct super_block *);
+void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this);
 void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
 void inode_wait_for_writeback(struct inode *inode);
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 464ea82e10db..c7bbbe794e65 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -287,11 +287,11 @@ TRACE_EVENT(writeback_queue_io,
 		__field(int,		reason)
 	),
 	TP_fast_assign(
-		unsigned long *older_than_this = work->older_than_this;
+		unsigned long older_than_this = work->older_than_this;
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__entry->older	= older_than_this ?  *older_than_this : 0;
+		__entry->older	= older_than_this;
 		__entry->age	= older_than_this ?
-				  (jiffies - *older_than_this) * 1000 / HZ : -1;
+				  (jiffies - older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
 	),
-- 
cgit 


From 79442ed189acb8b949662676e750eda173c06f9b Mon Sep 17 00:00:00 2001
From: Tang Chen <tangchen@cn.fujitsu.com>
Date: Tue, 12 Nov 2013 15:07:59 -0800
Subject: mm/memblock.c: introduce bottom-up allocation mode

The Linux kernel cannot migrate pages used by the kernel.  As a result,
kernel pages cannot be hot-removed.  So we cannot allocate hotpluggable
memory for the kernel.

ACPI SRAT (System Resource Affinity Table) contains the memory hotplug
info.  But before SRAT is parsed, memblock has already started to allocate
memory for the kernel.  So we need to prevent memblock from doing this.

In a memory hotplug system, any numa node the kernel resides in should be
unhotpluggable.  And for a modern server, each node could have at least
16GB memory.  So memory around the kernel image is highly likely
unhotpluggable.

So the basic idea is: Allocate memory from the end of the kernel image and
to the higher memory.  Since memory allocation before SRAT is parsed won't
be too much, it could highly likely be in the same node with kernel image.

The current memblock can only allocate memory top-down.  So this patch
introduces a new bottom-up allocation mode to allocate memory bottom-up.
And later when we use this allocation direction to allocate memory, we
will limit the start address above the kernel.

Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Thomas Renninger <trenn@suse.de>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Taku Izumi <izumi.taku@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h | 24 ++++++++++++++
 include/linux/mm.h       |  4 +++
 mm/memblock.c            | 83 ++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 108 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 31e95acddb4d..77c60e52939d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -35,6 +35,7 @@ struct memblock_type {
 };
 
 struct memblock {
+	bool bottom_up;  /* is bottom up direction? */
 	phys_addr_t current_limit;
 	struct memblock_type memory;
 	struct memblock_type reserved;
@@ -148,6 +149,29 @@ phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 
 phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
 
+#ifdef CONFIG_MOVABLE_NODE
+/*
+ * Set the allocation direction to bottom-up or top-down.
+ */
+static inline void memblock_set_bottom_up(bool enable)
+{
+	memblock.bottom_up = enable;
+}
+
+/*
+ * Check if the allocation direction is bottom-up or not.
+ * if this is true, that said, memblock will allocate memory
+ * in bottom-up direction.
+ */
+static inline bool memblock_bottom_up(void)
+{
+	return memblock.bottom_up;
+}
+#else
+static inline void memblock_set_bottom_up(bool enable) {}
+static inline bool memblock_bottom_up(void) { return false; }
+#endif
+
 /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8aa4006b9636..42a35d94b82c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -50,6 +50,10 @@ extern int sysctl_legacy_va_layout;
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 
+#ifndef __pa_symbol
+#define __pa_symbol(x)  __pa(RELOC_HIDE((unsigned long)(x), 0))
+#endif
+
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
diff --git a/mm/memblock.c b/mm/memblock.c
index accff1087137..53e477bb5558 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,6 +20,8 @@
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
+#include <asm-generic/sections.h>
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 
@@ -32,6 +34,7 @@ struct memblock memblock __initdata_memblock = {
 	.reserved.cnt		= 1,	/* empty dummy entry */
 	.reserved.max		= INIT_MEMBLOCK_REGIONS,
 
+	.bottom_up		= false,
 	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
 };
 
@@ -82,6 +85,38 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return (i < type->cnt) ? i : -1;
 }
 
+/*
+ * __memblock_find_range_bottom_up - find free area utility in bottom-up
+ * @start: start of candidate range
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @size: size of free area to find
+ * @align: alignment of free area to find
+ * @nid: nid of the free area to find, %MAX_NUMNODES for any node
+ *
+ * Utility called from memblock_find_in_range_node(), find free area bottom-up.
+ *
+ * RETURNS:
+ * Found address on success, 0 on failure.
+ */
+static phys_addr_t __init_memblock
+__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
+				phys_addr_t size, phys_addr_t align, int nid)
+{
+	phys_addr_t this_start, this_end, cand;
+	u64 i;
+
+	for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) {
+		this_start = clamp(this_start, start, end);
+		this_end = clamp(this_end, start, end);
+
+		cand = round_up(this_start, align);
+		if (cand < this_end && this_end - cand >= size)
+			return cand;
+	}
+
+	return 0;
+}
+
 /**
  * __memblock_find_range_top_down - find free area utility, in top-down
  * @start: start of candidate range
@@ -93,7 +128,7 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
  * Utility called from memblock_find_in_range_node(), find free area top-down.
  *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 static phys_addr_t __init_memblock
 __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
@@ -127,13 +162,24 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  *
  * Find @size free area aligned to @align in the specified range and node.
  *
+ * When allocation direction is bottom-up, the @start should be greater
+ * than the end of the kernel image. Otherwise, it will be trimmed. The
+ * reason is that we want the bottom-up allocation just near the kernel
+ * image so it is highly likely that the allocated memory and the kernel
+ * will reside in the same node.
+ *
+ * If bottom-up allocation failed, will try to allocate memory top-down.
+ *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
 					phys_addr_t align, int nid)
 {
+	int ret;
+	phys_addr_t kernel_end;
+
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
 		end = memblock.current_limit;
@@ -141,6 +187,37 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	/* avoid allocating the first page */
 	start = max_t(phys_addr_t, start, PAGE_SIZE);
 	end = max(start, end);
+	kernel_end = __pa_symbol(_end);
+
+	/*
+	 * try bottom-up allocation only when bottom-up mode
+	 * is set and @end is above the kernel image.
+	 */
+	if (memblock_bottom_up() && end > kernel_end) {
+		phys_addr_t bottom_up_start;
+
+		/* make sure we will allocate above the kernel */
+		bottom_up_start = max(start, kernel_end);
+
+		/* ok, try bottom-up allocation first */
+		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
+						      size, align, nid);
+		if (ret)
+			return ret;
+
+		/*
+		 * we always limit bottom-up allocation above the kernel,
+		 * but top-down allocation doesn't have the limit, so
+		 * retrying top-down allocation may succeed when bottom-up
+		 * allocation failed.
+		 *
+		 * bottom-up allocation is expected to be fail very rarely,
+		 * so we use WARN_ONCE() here to see the stack trace if
+		 * fail happens.
+		 */
+		WARN_ONCE(1, "memblock: bottom-up allocation failed, "
+			     "memory hotunplug may be affected\n");
+	}
 
 	return __memblock_find_range_top_down(start, end, size, align, nid);
 }
@@ -155,7 +232,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
  * Find @size free area aligned to @align in the specified range.
  *
  * RETURNS:
- * Found address on success, %0 on failure.
+ * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t end, phys_addr_t size,
-- 
cgit 


From 52c8f6a5aeb0bdd396849ecaa72d96f8175528f5 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Tue, 12 Nov 2013 15:08:19 -0800
Subject: mm: get rid of unnecessary overhead of trace_mm_page_alloc_extfrag()

In general, every tracepoint should be zero overhead if it is disabled.
However, trace_mm_page_alloc_extfrag() is one of exception.  It evaluate
"new_type == start_migratetype" even if tracepoint is disabled.

However, the code can be moved into tracepoint's TP_fast_assign() and
TP_fast_assign exist exactly such purpose.  This patch does it.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/kmem.h | 10 ++++------
 mm/page_alloc.c             |  5 ++---
 2 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index d0c613476620..aece1346ceb7 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -267,14 +267,12 @@ DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
 TRACE_EVENT(mm_page_alloc_extfrag,
 
 	TP_PROTO(struct page *page,
-			int alloc_order, int fallback_order,
-			int alloc_migratetype, int fallback_migratetype,
-			int change_ownership),
+		int alloc_order, int fallback_order,
+		int alloc_migratetype, int fallback_migratetype, int new_migratetype),
 
 	TP_ARGS(page,
 		alloc_order, fallback_order,
-		alloc_migratetype, fallback_migratetype,
-		change_ownership),
+		alloc_migratetype, fallback_migratetype, new_migratetype),
 
 	TP_STRUCT__entry(
 		__field(	struct page *,	page			)
@@ -291,7 +289,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->fallback_order		= fallback_order;
 		__entry->alloc_migratetype	= alloc_migratetype;
 		__entry->fallback_migratetype	= fallback_migratetype;
-		__entry->change_ownership	= change_ownership;
+		__entry->change_ownership	= (new_migratetype == alloc_migratetype);
 	),
 
 	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5a9883614d99..442f1298f9a7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1103,9 +1103,8 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			       is_migrate_cma(migratetype)
 			     ? migratetype : start_migratetype);
 
-			trace_mm_page_alloc_extfrag(page, order,
-				current_order, start_migratetype, migratetype,
-				new_type == start_migratetype);
+			trace_mm_page_alloc_extfrag(page, order, current_order,
+				start_migratetype, migratetype, new_type);
 
 			return page;
 		}
-- 
cgit 


From 00619bcc44d6b779aa366130b354153c222e4380 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Tue, 12 Nov 2013 15:08:31 -0800
Subject: mm: factor commit limit calculation

The same calculation is currently done in three differents places.
Factor that code so future changes has to be made at only one place.

[akpm@linux-foundation.org: uninline vm_commit_limit()]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/meminfo.c    |  5 +----
 include/linux/mman.h |  2 ++
 mm/mmap.c            |  4 +---
 mm/nommu.c           |  3 +--
 mm/util.c            | 13 +++++++++++++
 5 files changed, 18 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 59d85d608898..c805d5b69ba1 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -24,7 +24,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 {
 	struct sysinfo i;
 	unsigned long committed;
-	unsigned long allowed;
 	struct vmalloc_info vmi;
 	long cached;
 	unsigned long pages[NR_LRU_LISTS];
@@ -37,8 +36,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	si_meminfo(&i);
 	si_swapinfo(&i);
 	committed = percpu_counter_read_positive(&vm_committed_as);
-	allowed = ((totalram_pages - hugetlb_total_pages())
-		* sysctl_overcommit_ratio / 100) + total_swap_pages;
 
 	cached = global_page_state(NR_FILE_PAGES) -
 			total_swapcache_pages() - i.bufferram;
@@ -147,7 +144,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(global_page_state(NR_UNSTABLE_NFS)),
 		K(global_page_state(NR_BOUNCE)),
 		K(global_page_state(NR_WRITEBACK_TEMP)),
-		K(allowed),
+		K(vm_commit_limit()),
 		K(committed),
 		(unsigned long)VMALLOC_TOTAL >> 10,
 		vmi.used >> 10,
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 92dc257251e4..7f7f8dae4b1d 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -87,4 +87,6 @@ calc_vm_flag_bits(unsigned long flags)
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    );
 }
+
+unsigned long vm_commit_limit(void);
 #endif /* _LINUX_MMAN_H */
diff --git a/mm/mmap.c b/mm/mmap.c
index 3d3e224be771..803048e9c568 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -179,14 +179,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = (totalram_pages - hugetlb_total_pages())
-	       	* sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
diff --git a/mm/nommu.c b/mm/nommu.c
index ecd1f158548e..d8a957bb9e31 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1948,13 +1948,12 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		goto error;
 	}
 
-	allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+	allowed = vm_commit_limit();
 	/*
 	 * Reserve some 3% for root
 	 */
 	if (!cap_sys_admin)
 		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-	allowed += total_swap_pages;
 
 	/*
 	 * Don't let a single process grow so big a user can't recover
diff --git a/mm/util.c b/mm/util.c
index eaf63fc2c92f..f7bc2096071c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -7,6 +7,9 @@
 #include <linux/security.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mman.h>
+#include <linux/hugetlb.h>
+
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -398,6 +401,16 @@ struct address_space *page_mapping(struct page *page)
 	return mapping;
 }
 
+/*
+ * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
+ */
+unsigned long vm_commit_limit(void)
+{
+	return ((totalram_pages - hugetlb_total_pages())
+		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+}
+
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
-- 
cgit 


From 72403b4a0fbdf433c1fe0127e49864658f6f6468 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Tue, 12 Nov 2013 15:08:32 -0800
Subject: mm: numa: return the number of base pages altered by protection
 changes

Commit 0255d4918480 ("mm: Account for a THP NUMA hinting update as one
PTE update") was added to account for the number of PTE updates when
marking pages prot_numa.  task_numa_work was using the old return value
to track how much address space had been updated.  Altering the return
value causes the scanner to do more work than it is configured or
documented to in a single unit of work.

This patch reverts that commit and accounts for the number of THP
updates separately in vmstat.  It is up to the administrator to
interpret the pair of values correctly.  This is a straight-forward
operation and likely to only be of interest when actively debugging NUMA
balancing problems.

The impact of this patch is that the NUMA PTE scanner will scan slower
when THP is enabled and workloads may converge slower as a result.  On
the flip size system CPU usage should be lower than recent tests
reported.  This is an illustrative example of a short single JVM specjbb
test

specjbb
                       3.12.0                3.12.0
                      vanilla      acctupdates
TPut 1      26143.00 (  0.00%)     25747.00 ( -1.51%)
TPut 7     185257.00 (  0.00%)    183202.00 ( -1.11%)
TPut 13    329760.00 (  0.00%)    346577.00 (  5.10%)
TPut 19    442502.00 (  0.00%)    460146.00 (  3.99%)
TPut 25    540634.00 (  0.00%)    549053.00 (  1.56%)
TPut 31    512098.00 (  0.00%)    519611.00 (  1.47%)
TPut 37    461276.00 (  0.00%)    474973.00 (  2.97%)
TPut 43    403089.00 (  0.00%)    414172.00 (  2.75%)

              3.12.0      3.12.0
             vanillaacctupdates
User         5169.64     5184.14
System        100.45       80.02
Elapsed       252.75      251.85

Performance is similar but note the reduction in system CPU time.  While
this showed a performance gain, it will not be universal but at least
it'll be behaving as documented.  The vmstats are obviously different but
here is an obvious interpretation of them from mmtests.

                                3.12.0      3.12.0
                               vanillaacctupdates
NUMA page range updates        1408326    11043064
NUMA huge PMD updates                0       21040
NUMA PTE updates               1408326      291624

"NUMA page range updates" == nr_pte_updates and is the value returned to
the NUMA pte scanner.  NUMA huge PMD updates were the number of THP
updates which in combination can be used to calculate how many ptes were
updated from userspace.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Alex Thorlton <athorlton@sgi.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vm_event_item.h |  1 +
 mm/mprotect.c                 | 10 +++++++---
 mm/vmstat.c                   |  1 +
 3 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 1855f0a22add..c557c6d096de 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -39,6 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
+		NUMA_HUGE_PTE_UPDATES,
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a597f2ffcd6f..26667971c824 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -112,6 +112,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 	pmd_t *pmd;
 	unsigned long next;
 	unsigned long pages = 0;
+	unsigned long nr_huge_updates = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
@@ -126,9 +127,10 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 						newprot, prot_numa);
 
 				if (nr_ptes) {
-					if (nr_ptes == HPAGE_PMD_NR)
-						pages++;
-
+					if (nr_ptes == HPAGE_PMD_NR) {
+						pages += HPAGE_PMD_NR;
+						nr_huge_updates++;
+					}
 					continue;
 				}
 			}
@@ -141,6 +143,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pages += this_pages;
 	} while (pmd++, addr = next, addr != end);
 
+	if (nr_huge_updates)
+		count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
 	return pages;
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b6d17edf8cf3..72496140ac08 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -812,6 +812,7 @@ const char * const vmstat_text[] = {
 
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
+	"numa_huge_pte_updates",
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
-- 
cgit 


From 83460ec8dcac14142e7860a01fa59c267ac4657c Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 12 Nov 2013 15:08:36 -0800
Subject: syscalls.h: use gcc alias instead of assembler aliases for syscalls

Use standard gcc __attribute__((alias(foo))) to define the syscall aliases
instead of custom assembler macros.

This is far cleaner, and also fixes my LTO kernel build.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compat.h   | 4 ++--
 include/linux/syscalls.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 345da00a86e0..ada34c92b684 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -41,14 +41,14 @@
 	COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
 
 #define COMPAT_SYSCALL_DEFINEx(x, name, ...)				\
-	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\
+		__attribute__((alias(__stringify(compat_SyS##name))));  \
 	static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
 	asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\
 	asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\
 	{								\
 		return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
 	}								\
-	SYSCALL_ALIAS(compat_sys##name, compat_SyS##name);		\
 	static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
 #ifndef compat_user_stack_pointer
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7fac04e7ff6e..c27f846f6b71 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -184,7 +184,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 
 #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
 #define __SYSCALL_DEFINEx(x, name, ...)					\
-	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
+		__attribute__((alias(__stringify(SyS##name))));		\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
@@ -194,7 +195,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
 		return ret;						\
 	}								\
-	SYSCALL_ALIAS(sys##name, SyS##name);				\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
 asmlinkage long sys_time(time_t __user *tloc);
-- 
cgit 


From 0ca43435188b9f911c8efcdf10731f726142dda1 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Tue, 12 Nov 2013 15:08:40 -0800
Subject: errno.h: remove "NFS" from descriptions in comments

glibc recently changed the error string for ESTALE to remove "NFS" -

https://sourceware.org/git/?p=glibc.git;a=commitdiff;h=96945714ec61951cc748da2b4b8a80cf02127ee9

from: [ERR_REMAP (ESTALE)] = N_("Stale NFS file handle"),
to:   [ERR_REMAP (ESTALE)] = N_("Stale file handle"),

And some have expressed concern that the kernel's errno.h
comments still refer to NFS.

So make that change... note that this is a comment-only change,
and has no functional difference.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/uapi/asm/errno.h                         | 2 +-
 arch/mips/include/uapi/asm/errno.h                          | 2 +-
 arch/parisc/include/uapi/asm/errno.h                        | 2 +-
 arch/sparc/include/uapi/asm/errno.h                         | 2 +-
 drivers/staging/lustre/lustre/include/lustre/lustre_errno.h | 2 +-
 include/uapi/asm-generic/errno.h                            | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/errno.h b/arch/alpha/include/uapi/asm/errno.h
index e5f29ca28180..17f92aa76b2f 100644
--- a/arch/alpha/include/uapi/asm/errno.h
+++ b/arch/alpha/include/uapi/asm/errno.h
@@ -43,7 +43,7 @@
 
 #define	EUSERS		68	/* Too many users */
 #define	EDQUOT		69	/* Quota exceeded */
-#define	ESTALE		70	/* Stale NFS file handle */
+#define	ESTALE		70	/* Stale file handle */
 #define	EREMOTE		71	/* Object is remote */
 
 #define	ENOLCK		77	/* No record locks available */
diff --git a/arch/mips/include/uapi/asm/errno.h b/arch/mips/include/uapi/asm/errno.h
index 31575e2fd1bd..02d645d7aa9a 100644
--- a/arch/mips/include/uapi/asm/errno.h
+++ b/arch/mips/include/uapi/asm/errno.h
@@ -102,7 +102,7 @@
 #define EWOULDBLOCK	EAGAIN	/* Operation would block */
 #define EALREADY	149	/* Operation already in progress */
 #define EINPROGRESS	150	/* Operation now in progress */
-#define ESTALE		151	/* Stale NFS file handle */
+#define ESTALE		151	/* Stale file handle */
 #define ECANCELED	158	/* AIO operation canceled */
 
 /*
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index 135ad6047e51..f3a8aa554841 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -37,7 +37,7 @@
 #define	EBADMSG		67	/* Not a data message */
 #define	EUSERS		68	/* Too many users */
 #define	EDQUOT		69	/* Quota exceeded */
-#define	ESTALE		70	/* Stale NFS file handle */
+#define	ESTALE		70	/* Stale file handle */
 #define	EREMOTE		71	/* Object is remote */
 #define	EOVERFLOW	72	/* Value too large for defined data type */
 
diff --git a/arch/sparc/include/uapi/asm/errno.h b/arch/sparc/include/uapi/asm/errno.h
index c351aba997b7..20423e172853 100644
--- a/arch/sparc/include/uapi/asm/errno.h
+++ b/arch/sparc/include/uapi/asm/errno.h
@@ -40,7 +40,7 @@
 #define EPROCLIM        67      /* SUNOS: Too many processes */
 #define	EUSERS		68	/* Too many users */
 #define	EDQUOT		69	/* Quota exceeded */
-#define	ESTALE		70	/* Stale NFS file handle */
+#define	ESTALE		70	/* Stale file handle */
 #define	EREMOTE		71	/* Object is remote */
 #define	ENOSTR		72	/* Device not a stream */
 #define	ETIME		73	/* Timer expired */
diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_errno.h b/drivers/staging/lustre/lustre/include/lustre/lustre_errno.h
index 2870487dd286..35aefa2cdad1 100644
--- a/drivers/staging/lustre/lustre/include/lustre/lustre_errno.h
+++ b/drivers/staging/lustre/lustre/include/lustre/lustre_errno.h
@@ -165,7 +165,7 @@
 #define LUSTRE_EHOSTUNREACH	113	/* No route to host */
 #define LUSTRE_EALREADY		114	/* Operation already in progress */
 #define LUSTRE_EINPROGRESS	115	/* Operation now in progress */
-#define LUSTRE_ESTALE		116	/* Stale NFS file handle */
+#define LUSTRE_ESTALE		116	/* Stale file handle */
 #define LUSTRE_EUCLEAN		117	/* Structure needs cleaning */
 #define LUSTRE_ENOTNAM		118	/* Not a XENIX named type file */
 #define LUSTRE_ENAVAIL		119	/* No XENIX semaphores available */
diff --git a/include/uapi/asm-generic/errno.h b/include/uapi/asm-generic/errno.h
index a1331ce50445..1e1ea6e6e7a5 100644
--- a/include/uapi/asm-generic/errno.h
+++ b/include/uapi/asm-generic/errno.h
@@ -86,7 +86,7 @@
 #define	EHOSTUNREACH	113	/* No route to host */
 #define	EALREADY	114	/* Operation already in progress */
 #define	EINPROGRESS	115	/* Operation now in progress */
-#define	ESTALE		116	/* Stale NFS file handle */
+#define	ESTALE		116	/* Stale file handle */
 #define	EUCLEAN		117	/* Structure needs cleaning */
 #define	ENOTNAM		118	/* Not a XENIX named type file */
 #define	ENAVAIL		119	/* No XENIX semaphores available */
-- 
cgit 


From 261adc9a609dbfde815337889b9e2c8728959ab8 Mon Sep 17 00:00:00 2001
From: Roel Kluin <roel.kluin@gmail.com>
Date: Tue, 12 Nov 2013 15:08:44 -0800
Subject: jump_label: unlikely(x) > 0

if (unlikely(x) > 0) doesn't seem to help branch prediction

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/jump_label.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a5079072da66..cf08540d6204 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -132,14 +132,14 @@ static __always_inline void jump_label_init(void)
 
 static __always_inline bool static_key_false(struct static_key *key)
 {
-	if (unlikely(atomic_read(&key->enabled)) > 0)
+	if (unlikely(atomic_read(&key->enabled) > 0))
 		return true;
 	return false;
 }
 
 static __always_inline bool static_key_true(struct static_key *key)
 {
-	if (likely(atomic_read(&key->enabled)) > 0)
+	if (likely(atomic_read(&key->enabled) > 0))
 		return true;
 	return false;
 }
-- 
cgit 


From 27f69e68a5e534412faebc53a4e04acc9ce7fd7e Mon Sep 17 00:00:00 2001
From: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Date: Tue, 12 Nov 2013 15:08:47 -0800
Subject: sched: remove ARCH specific fpu_counter from task_struct

fpu_counter in task_struct was used only by sh/x86.  Both of these now
carry it in ARCH specific thread_struct, hence this can now be removed
from generic task_struct, shrinking it slightly for other arches.

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul Mundt <paul.mundt@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 045b0d227846..5e226fe3e512 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1062,15 +1062,6 @@ struct task_struct {
 	struct hlist_head preempt_notifiers;
 #endif
 
-	/*
-	 * fpu_counter contains the number of consecutive context switches
-	 * that the FPU is used. If this is over a threshold, the lazy fpu
-	 * saving becomes unlazy to save the trap. This is an unsigned char
-	 * so that after 256 times the counter wraps and the behavior turns
-	 * lazy again; this to deal with bursty apps that only use FPU for
-	 * a short time
-	 */
-	unsigned char fpu_counter;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	unsigned int btrace_seq;
 #endif
-- 
cgit 


From 5812c13a4e636da4bd7f7cabbbbc59d9dbf3c86c Mon Sep 17 00:00:00 2001
From: Milo Kim <milo.kim@ti.com>
Date: Tue, 12 Nov 2013 15:08:57 -0800
Subject: backlight: lp855x_bl: support new LP8555 device

LP8555 is one of the LP855x family devices.

This device needs pre_init_device() and post_init_device() driver
structure.  It's same as LP8557, so the device configuration code is
shared with LP8557.  Backlight outputs are generated from dual DC-DC boost
converters.  It's configurable EPROM settings which are defined in the
platform data.

Driver documentation and device tree bindings are updated.

Signed-off-by: Milo Kim <milo.kim@ti.com>
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/backlight/lp855x-driver.txt          |  5 ++--
 .../devicetree/bindings/video/backlight/lp855x.txt | 29 +++++++++++++++++++++-
 drivers/video/backlight/Kconfig                    |  4 +--
 drivers/video/backlight/lp855x_bl.c                | 17 +++++++++++--
 include/linux/platform_data/lp855x.h               | 19 ++++++++++++++
 5 files changed, 67 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/backlight/lp855x-driver.txt b/Documentation/backlight/lp855x-driver.txt
index 1c732f0c6758..01bce243d3d7 100644
--- a/Documentation/backlight/lp855x-driver.txt
+++ b/Documentation/backlight/lp855x-driver.txt
@@ -4,7 +4,8 @@ Kernel driver lp855x
 Backlight driver for LP855x ICs
 
 Supported chips:
-	Texas Instruments LP8550, LP8551, LP8552, LP8553, LP8556 and LP8557
+	Texas Instruments LP8550, LP8551, LP8552, LP8553, LP8555, LP8556 and
+	LP8557
 
 Author: Milo(Woogyom) Kim <milo.kim@ti.com>
 
@@ -24,7 +25,7 @@ Value : pwm based or register based
 
 2) chip_id
 The lp855x chip id.
-Value : lp8550/lp8551/lp8552/lp8553/lp8556/lp8557
+Value : lp8550/lp8551/lp8552/lp8553/lp8555/lp8556/lp8557
 
 Platform data for lp855x
 ------------------------
diff --git a/Documentation/devicetree/bindings/video/backlight/lp855x.txt b/Documentation/devicetree/bindings/video/backlight/lp855x.txt
index 1482103d288f..96e83a56048e 100644
--- a/Documentation/devicetree/bindings/video/backlight/lp855x.txt
+++ b/Documentation/devicetree/bindings/video/backlight/lp855x.txt
@@ -2,7 +2,7 @@ lp855x bindings
 
 Required properties:
   - compatible: "ti,lp8550", "ti,lp8551", "ti,lp8552", "ti,lp8553",
-                "ti,lp8556", "ti,lp8557"
+                "ti,lp8555", "ti,lp8556", "ti,lp8557"
   - reg: I2C slave address (u8)
   - dev-ctrl: Value of DEVICE CONTROL register (u8). It depends on the device.
 
@@ -15,6 +15,33 @@ Optional properties:
 
 Example:
 
+	/* LP8555 */
+	backlight@2c {
+		compatible = "ti,lp8555";
+		reg = <0x2c>;
+
+		dev-ctrl = /bits/ 8 <0x00>;
+		pwm-period = <10000>;
+
+		/* 4V OV, 4 output LED0 string enabled */
+		rom_14h {
+			rom-addr = /bits/ 8 <0x14>;
+			rom-val = /bits/ 8 <0xcf>;
+		};
+
+		/* Heavy smoothing, 24ms ramp time step */
+		rom_15h {
+			rom-addr = /bits/ 8 <0x15>;
+			rom-val = /bits/ 8 <0xc7>;
+		};
+
+		/* 4 output LED1 string enabled */
+		rom_19h {
+			rom-addr = /bits/ 8 <0x19>;
+			rom-val = /bits/ 8 <0x0f>;
+		};
+	};
+
 	/* LP8556 */
 	backlight@2c {
 		compatible = "ti,lp8556";
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index d4a7a351d67c..a65dd063ecad 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -388,8 +388,8 @@ config BACKLIGHT_LP855X
 	tristate "Backlight driver for TI LP855X"
 	depends on BACKLIGHT_CLASS_DEVICE && I2C
 	help
-	  This supports TI LP8550, LP8551, LP8552, LP8553, LP8556 and LP8557
-	  backlight driver.
+	  This supports TI LP8550, LP8551, LP8552, LP8553, LP8555, LP8556 and
+	  LP8557 backlight driver.
 
 config BACKLIGHT_LP8788
 	tristate "Backlight driver for TI LP8788 MFD"
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index c0b41f13bd4a..c952175d4113 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -26,13 +26,15 @@
 #define LP8556_EPROM_START		0xA0
 #define LP8556_EPROM_END		0xAF
 
-/* LP8557 Registers */
+/* LP8555/7 Registers */
 #define LP8557_BL_CMD			0x00
 #define LP8557_BL_MASK			0x01
 #define LP8557_BL_ON			0x01
 #define LP8557_BL_OFF			0x00
 #define LP8557_BRIGHTNESS_CTRL		0x04
 #define LP8557_CONFIG			0x10
+#define LP8555_EPROM_START		0x10
+#define LP8555_EPROM_END		0x7A
 #define LP8557_EPROM_START		0x10
 #define LP8557_EPROM_END		0x1E
 
@@ -111,6 +113,10 @@ static bool lp855x_is_valid_rom_area(struct lp855x *lp, u8 addr)
 		start = LP8556_EPROM_START;
 		end = LP8556_EPROM_END;
 		break;
+	case LP8555:
+		start = LP8555_EPROM_START;
+		end = LP8555_EPROM_END;
+		break;
 	case LP8557:
 		start = LP8557_EPROM_START;
 		end = LP8557_EPROM_END;
@@ -165,9 +171,14 @@ static int lp855x_configure(struct lp855x *lp)
 	struct lp855x_platform_data *pd = lp->pdata;
 
 	switch (lp->chip_id) {
-	case LP8550 ... LP8556:
+	case LP8550:
+	case LP8551:
+	case LP8552:
+	case LP8553:
+	case LP8556:
 		lp->cfg = &lp855x_dev_cfg;
 		break;
+	case LP8555:
 	case LP8557:
 		lp->cfg = &lp8557_dev_cfg;
 		break;
@@ -470,6 +481,7 @@ static const struct of_device_id lp855x_dt_ids[] = {
 	{ .compatible = "ti,lp8551", },
 	{ .compatible = "ti,lp8552", },
 	{ .compatible = "ti,lp8553", },
+	{ .compatible = "ti,lp8555", },
 	{ .compatible = "ti,lp8556", },
 	{ .compatible = "ti,lp8557", },
 	{ }
@@ -481,6 +493,7 @@ static const struct i2c_device_id lp855x_ids[] = {
 	{"lp8551", LP8551},
 	{"lp8552", LP8552},
 	{"lp8553", LP8553},
+	{"lp8555", LP8555},
 	{"lp8556", LP8556},
 	{"lp8557", LP8557},
 	{ }
diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h
index ea3200527dd3..1b2ba24e4e03 100644
--- a/include/linux/platform_data/lp855x.h
+++ b/include/linux/platform_data/lp855x.h
@@ -40,6 +40,17 @@
 #define LP8553_PWM_CONFIG	LP8550_PWM_CONFIG
 #define LP8553_I2C_CONFIG	LP8550_I2C_CONFIG
 
+/* CONFIG register - LP8555 */
+#define LP8555_PWM_STANDBY	BIT(7)
+#define LP8555_PWM_FILTER	BIT(6)
+#define LP8555_RELOAD_EPROM	BIT(3)	/* use it if EPROMs should be reset
+					   when the backlight turns on */
+#define LP8555_OFF_OPENLEDS	BIT(2)
+#define LP8555_PWM_CONFIG	LP8555_PWM_ONLY
+#define LP8555_I2C_CONFIG	LP8555_I2C_ONLY
+#define LP8555_COMB1_CONFIG	LP8555_COMBINED1
+#define LP8555_COMB2_CONFIG	LP8555_COMBINED2
+
 /* DEVICE CONTROL register - LP8556 */
 #define LP8556_PWM_CONFIG	(LP8556_PWM_ONLY << BRT_MODE_SHFT)
 #define LP8556_COMB1_CONFIG	(LP8556_COMBINED1 << BRT_MODE_SHFT)
@@ -65,6 +76,7 @@ enum lp855x_chip_id {
 	LP8551,
 	LP8552,
 	LP8553,
+	LP8555,
 	LP8556,
 	LP8557,
 };
@@ -89,6 +101,13 @@ enum lp8553_brighntess_source {
 	LP8553_I2C_ONLY = LP8550_I2C_ONLY,
 };
 
+enum lp8555_brightness_source {
+	LP8555_PWM_ONLY,
+	LP8555_I2C_ONLY,
+	LP8555_COMBINED1,	/* Brightness register with shaped PWM */
+	LP8555_COMBINED2,	/* PWM with shaped brightness register */
+};
+
 enum lp8556_brightness_source {
 	LP8556_PWM_ONLY,
 	LP8556_COMBINED1,	/* pwm + i2c before the shaper block */
-- 
cgit 


From 28e64a68a2ef1c48f30e8b6803725199929069fc Mon Sep 17 00:00:00 2001
From: Daniel Jeong <gshark.jeong@gmail.com>
Date: Tue, 12 Nov 2013 15:08:58 -0800
Subject: backlight: lm3630: apply chip revision

The LM3630 chip was revised by TI and chip name was also changed to
LM3630A.  And register map, default values and initial sequences are
changed.  The files, lm3630_bl.{c,h} are replaced by lm3630a_bl.{c,h} You
can find more information about LM3630A(datasheet, evm etc) at
http://www.ti.com/product/lm3630a

Signed-off-by: Daniel Jeong <gshark.jeong@gmail.com>
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/video/backlight/Kconfig          |   6 +-
 drivers/video/backlight/Makefile         |   2 +-
 drivers/video/backlight/lm3630_bl.c      | 475 ------------------------------
 drivers/video/backlight/lm3630a_bl.c     | 483 +++++++++++++++++++++++++++++++
 include/linux/platform_data/lm3630_bl.h  |  57 ----
 include/linux/platform_data/lm3630a_bl.h |  65 +++++
 6 files changed, 552 insertions(+), 536 deletions(-)
 delete mode 100644 drivers/video/backlight/lm3630_bl.c
 create mode 100644 drivers/video/backlight/lm3630a_bl.c
 delete mode 100644 include/linux/platform_data/lm3630_bl.h
 create mode 100644 include/linux/platform_data/lm3630a_bl.h

(limited to 'include')

diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index a65dd063ecad..5a3eb2ecb525 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -368,12 +368,12 @@ config BACKLIGHT_AAT2870
 	  If you have a AnalogicTech AAT2870 say Y to enable the
 	  backlight driver.
 
-config BACKLIGHT_LM3630
-	tristate "Backlight Driver for LM3630"
+config BACKLIGHT_LM3630A
+	tristate "Backlight Driver for LM3630A"
 	depends on BACKLIGHT_CLASS_DEVICE && I2C
 	select REGMAP_I2C
 	help
-	  This supports TI LM3630 Backlight Driver
+	  This supports TI LM3630A Backlight Driver
 
 config BACKLIGHT_LM3639
 	tristate "Backlight Driver for LM3639"
diff --git a/drivers/video/backlight/Makefile b/drivers/video/backlight/Makefile
index 38e1babb1946..bb820024f346 100644
--- a/drivers/video/backlight/Makefile
+++ b/drivers/video/backlight/Makefile
@@ -37,7 +37,7 @@ obj-$(CONFIG_BACKLIGHT_GPIO)		+= gpio_backlight.o
 obj-$(CONFIG_BACKLIGHT_HP680)		+= hp680_bl.o
 obj-$(CONFIG_BACKLIGHT_HP700)		+= jornada720_bl.o
 obj-$(CONFIG_BACKLIGHT_LM3533)		+= lm3533_bl.o
-obj-$(CONFIG_BACKLIGHT_LM3630)		+= lm3630_bl.o
+obj-$(CONFIG_BACKLIGHT_LM3630A)		+= lm3630a_bl.o
 obj-$(CONFIG_BACKLIGHT_LM3639)		+= lm3639_bl.o
 obj-$(CONFIG_BACKLIGHT_LOCOMO)		+= locomolcd.o
 obj-$(CONFIG_BACKLIGHT_LP855X)		+= lp855x_bl.o
diff --git a/drivers/video/backlight/lm3630_bl.c b/drivers/video/backlight/lm3630_bl.c
deleted file mode 100644
index 76a62e978fc3..000000000000
--- a/drivers/video/backlight/lm3630_bl.c
+++ /dev/null
@@ -1,475 +0,0 @@
-/*
-* Simple driver for Texas Instruments LM3630 Backlight driver chip
-* Copyright (C) 2012 Texas Instruments
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License version 2 as
-* published by the Free Software Foundation.
-*
-*/
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/i2c.h>
-#include <linux/backlight.h>
-#include <linux/err.h>
-#include <linux/delay.h>
-#include <linux/uaccess.h>
-#include <linux/interrupt.h>
-#include <linux/regmap.h>
-#include <linux/platform_data/lm3630_bl.h>
-
-#define REG_CTRL	0x00
-#define REG_CONFIG	0x01
-#define REG_BRT_A	0x03
-#define REG_BRT_B	0x04
-#define REG_INT_STATUS	0x09
-#define REG_INT_EN	0x0A
-#define REG_FAULT	0x0B
-#define REG_PWM_OUTLOW	0x12
-#define REG_PWM_OUTHIGH	0x13
-#define REG_MAX		0x1F
-
-#define INT_DEBOUNCE_MSEC	10
-
-enum lm3630_leds {
-	BLED_ALL = 0,
-	BLED_1,
-	BLED_2
-};
-
-static const char * const bled_name[] = {
-	[BLED_ALL] = "lm3630_bled",	/*Bank1 controls all string */
-	[BLED_1] = "lm3630_bled1",	/*Bank1 controls bled1 */
-	[BLED_2] = "lm3630_bled2",	/*Bank1 or 2 controls bled2 */
-};
-
-struct lm3630_chip_data {
-	struct device *dev;
-	struct delayed_work work;
-	int irq;
-	struct workqueue_struct *irqthread;
-	struct lm3630_platform_data *pdata;
-	struct backlight_device *bled1;
-	struct backlight_device *bled2;
-	struct regmap *regmap;
-};
-
-/* initialize chip */
-static int lm3630_chip_init(struct lm3630_chip_data *pchip)
-{
-	int ret;
-	unsigned int reg_val;
-	struct lm3630_platform_data *pdata = pchip->pdata;
-
-	/*pwm control */
-	reg_val = ((pdata->pwm_active & 0x01) << 2) | (pdata->pwm_ctrl & 0x03);
-	ret = regmap_update_bits(pchip->regmap, REG_CONFIG, 0x07, reg_val);
-	if (ret < 0)
-		goto out;
-
-	/* bank control */
-	reg_val = ((pdata->bank_b_ctrl & 0x01) << 1) |
-			(pdata->bank_a_ctrl & 0x07);
-	ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x07, reg_val);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-	if (ret < 0)
-		goto out;
-
-	/* set initial brightness */
-	if (pdata->bank_a_ctrl != BANK_A_CTRL_DISABLE) {
-		ret = regmap_write(pchip->regmap,
-				   REG_BRT_A, pdata->init_brt_led1);
-		if (ret < 0)
-			goto out;
-	}
-
-	if (pdata->bank_b_ctrl != BANK_B_CTRL_DISABLE) {
-		ret = regmap_write(pchip->regmap,
-				   REG_BRT_B, pdata->init_brt_led2);
-		if (ret < 0)
-			goto out;
-	}
-	return ret;
-
-out:
-	dev_err(pchip->dev, "i2c failed to access register\n");
-	return ret;
-}
-
-/* interrupt handling */
-static void lm3630_delayed_func(struct work_struct *work)
-{
-	int ret;
-	unsigned int reg_val;
-	struct lm3630_chip_data *pchip;
-
-	pchip = container_of(work, struct lm3630_chip_data, work.work);
-
-	ret = regmap_read(pchip->regmap, REG_INT_STATUS, &reg_val);
-	if (ret < 0) {
-		dev_err(pchip->dev,
-			"i2c failed to access REG_INT_STATUS Register\n");
-		return;
-	}
-
-	dev_info(pchip->dev, "REG_INT_STATUS Register is 0x%x\n", reg_val);
-}
-
-static irqreturn_t lm3630_isr_func(int irq, void *chip)
-{
-	int ret;
-	struct lm3630_chip_data *pchip = chip;
-	unsigned long delay = msecs_to_jiffies(INT_DEBOUNCE_MSEC);
-
-	queue_delayed_work(pchip->irqthread, &pchip->work, delay);
-
-	ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-	if (ret < 0)
-		goto out;
-
-	return IRQ_HANDLED;
-out:
-	dev_err(pchip->dev, "i2c failed to access register\n");
-	return IRQ_HANDLED;
-}
-
-static int lm3630_intr_config(struct lm3630_chip_data *pchip)
-{
-	INIT_DELAYED_WORK(&pchip->work, lm3630_delayed_func);
-	pchip->irqthread = create_singlethread_workqueue("lm3630-irqthd");
-	if (!pchip->irqthread) {
-		dev_err(pchip->dev, "create irq thread fail...\n");
-		return -1;
-	}
-	if (request_threaded_irq
-	    (pchip->irq, NULL, lm3630_isr_func,
-	     IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "lm3630_irq", pchip)) {
-		dev_err(pchip->dev, "request threaded irq fail..\n");
-		return -1;
-	}
-	return 0;
-}
-
-static bool
-set_intensity(struct backlight_device *bl, struct lm3630_chip_data *pchip)
-{
-	if (!pchip->pdata->pwm_set_intensity)
-		return false;
-	pchip->pdata->pwm_set_intensity(bl->props.brightness - 1,
-					pchip->pdata->pwm_period);
-	return true;
-}
-
-/* update and get brightness */
-static int lm3630_bank_a_update_status(struct backlight_device *bl)
-{
-	int ret;
-	struct lm3630_chip_data *pchip = bl_get_data(bl);
-	enum lm3630_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
-
-	/* brightness 0 means disable */
-	if (!bl->props.brightness) {
-		ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x04, 0x00);
-		if (ret < 0)
-			goto out;
-		return bl->props.brightness;
-	}
-
-	/* pwm control */
-	if (pwm_ctrl == PWM_CTRL_BANK_A || pwm_ctrl == PWM_CTRL_BANK_ALL) {
-		if (!set_intensity(bl, pchip))
-			dev_err(pchip->dev, "No pwm control func. in plat-data\n");
-	} else {
-
-		/* i2c control */
-		ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-		if (ret < 0)
-			goto out;
-		mdelay(1);
-		ret = regmap_write(pchip->regmap,
-				   REG_BRT_A, bl->props.brightness - 1);
-		if (ret < 0)
-			goto out;
-	}
-	return bl->props.brightness;
-out:
-	dev_err(pchip->dev, "i2c failed to access REG_CTRL\n");
-	return bl->props.brightness;
-}
-
-static int lm3630_bank_a_get_brightness(struct backlight_device *bl)
-{
-	unsigned int reg_val;
-	int brightness, ret;
-	struct lm3630_chip_data *pchip = bl_get_data(bl);
-	enum lm3630_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
-
-	if (pwm_ctrl == PWM_CTRL_BANK_A || pwm_ctrl == PWM_CTRL_BANK_ALL) {
-		ret = regmap_read(pchip->regmap, REG_PWM_OUTHIGH, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = reg_val & 0x01;
-		ret = regmap_read(pchip->regmap, REG_PWM_OUTLOW, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = ((brightness << 8) | reg_val) + 1;
-	} else {
-		ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-		if (ret < 0)
-			goto out;
-		mdelay(1);
-		ret = regmap_read(pchip->regmap, REG_BRT_A, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = reg_val + 1;
-	}
-	bl->props.brightness = brightness;
-	return bl->props.brightness;
-out:
-	dev_err(pchip->dev, "i2c failed to access register\n");
-	return 0;
-}
-
-static const struct backlight_ops lm3630_bank_a_ops = {
-	.options = BL_CORE_SUSPENDRESUME,
-	.update_status = lm3630_bank_a_update_status,
-	.get_brightness = lm3630_bank_a_get_brightness,
-};
-
-static int lm3630_bank_b_update_status(struct backlight_device *bl)
-{
-	int ret;
-	struct lm3630_chip_data *pchip = bl_get_data(bl);
-	enum lm3630_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
-
-	if (pwm_ctrl == PWM_CTRL_BANK_B || pwm_ctrl == PWM_CTRL_BANK_ALL) {
-		if (!set_intensity(bl, pchip))
-			dev_err(pchip->dev,
-				"no pwm control func. in plat-data\n");
-	} else {
-		ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-		if (ret < 0)
-			goto out;
-		mdelay(1);
-		ret = regmap_write(pchip->regmap,
-				   REG_BRT_B, bl->props.brightness - 1);
-	}
-	return bl->props.brightness;
-out:
-	dev_err(pchip->dev, "i2c failed to access register\n");
-	return bl->props.brightness;
-}
-
-static int lm3630_bank_b_get_brightness(struct backlight_device *bl)
-{
-	unsigned int reg_val;
-	int brightness, ret;
-	struct lm3630_chip_data *pchip = bl_get_data(bl);
-	enum lm3630_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
-
-	if (pwm_ctrl == PWM_CTRL_BANK_B || pwm_ctrl == PWM_CTRL_BANK_ALL) {
-		ret = regmap_read(pchip->regmap, REG_PWM_OUTHIGH, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = reg_val & 0x01;
-		ret = regmap_read(pchip->regmap, REG_PWM_OUTLOW, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = ((brightness << 8) | reg_val) + 1;
-	} else {
-		ret = regmap_update_bits(pchip->regmap, REG_CTRL, 0x80, 0x00);
-		if (ret < 0)
-			goto out;
-		mdelay(1);
-		ret = regmap_read(pchip->regmap, REG_BRT_B, &reg_val);
-		if (ret < 0)
-			goto out;
-		brightness = reg_val + 1;
-	}
-	bl->props.brightness = brightness;
-
-	return bl->props.brightness;
-out:
-	dev_err(pchip->dev, "i2c failed to access register\n");
-	return bl->props.brightness;
-}
-
-static const struct backlight_ops lm3630_bank_b_ops = {
-	.options = BL_CORE_SUSPENDRESUME,
-	.update_status = lm3630_bank_b_update_status,
-	.get_brightness = lm3630_bank_b_get_brightness,
-};
-
-static int lm3630_backlight_register(struct lm3630_chip_data *pchip,
-				     enum lm3630_leds ledno)
-{
-	const char *name = bled_name[ledno];
-	struct backlight_properties props;
-	struct lm3630_platform_data *pdata = pchip->pdata;
-
-	props.type = BACKLIGHT_RAW;
-	switch (ledno) {
-	case BLED_1:
-	case BLED_ALL:
-		props.brightness = pdata->init_brt_led1;
-		props.max_brightness = pdata->max_brt_led1;
-		pchip->bled1 =
-		    backlight_device_register(name, pchip->dev, pchip,
-					      &lm3630_bank_a_ops, &props);
-		if (IS_ERR(pchip->bled1))
-			return PTR_ERR(pchip->bled1);
-		break;
-	case BLED_2:
-		props.brightness = pdata->init_brt_led2;
-		props.max_brightness = pdata->max_brt_led2;
-		pchip->bled2 =
-		    backlight_device_register(name, pchip->dev, pchip,
-					      &lm3630_bank_b_ops, &props);
-		if (IS_ERR(pchip->bled2))
-			return PTR_ERR(pchip->bled2);
-		break;
-	}
-	return 0;
-}
-
-static void lm3630_backlight_unregister(struct lm3630_chip_data *pchip)
-{
-	if (pchip->bled1)
-		backlight_device_unregister(pchip->bled1);
-	if (pchip->bled2)
-		backlight_device_unregister(pchip->bled2);
-}
-
-static const struct regmap_config lm3630_regmap = {
-	.reg_bits = 8,
-	.val_bits = 8,
-	.max_register = REG_MAX,
-};
-
-static int lm3630_probe(struct i2c_client *client,
-				  const struct i2c_device_id *id)
-{
-	struct lm3630_platform_data *pdata = client->dev.platform_data;
-	struct lm3630_chip_data *pchip;
-	int ret;
-
-	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
-		dev_err(&client->dev, "fail : i2c functionality check...\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (pdata == NULL) {
-		dev_err(&client->dev, "fail : no platform data.\n");
-		return -ENODATA;
-	}
-
-	pchip = devm_kzalloc(&client->dev, sizeof(struct lm3630_chip_data),
-			     GFP_KERNEL);
-	if (!pchip)
-		return -ENOMEM;
-	pchip->pdata = pdata;
-	pchip->dev = &client->dev;
-
-	pchip->regmap = devm_regmap_init_i2c(client, &lm3630_regmap);
-	if (IS_ERR(pchip->regmap)) {
-		ret = PTR_ERR(pchip->regmap);
-		dev_err(&client->dev, "fail : allocate register map: %d\n",
-			ret);
-		return ret;
-	}
-	i2c_set_clientdata(client, pchip);
-
-	/* chip initialize */
-	ret = lm3630_chip_init(pchip);
-	if (ret < 0) {
-		dev_err(&client->dev, "fail : init chip\n");
-		goto err_chip_init;
-	}
-
-	switch (pdata->bank_a_ctrl) {
-	case BANK_A_CTRL_ALL:
-		ret = lm3630_backlight_register(pchip, BLED_ALL);
-		pdata->bank_b_ctrl = BANK_B_CTRL_DISABLE;
-		break;
-	case BANK_A_CTRL_LED1:
-		ret = lm3630_backlight_register(pchip, BLED_1);
-		break;
-	case BANK_A_CTRL_LED2:
-		ret = lm3630_backlight_register(pchip, BLED_2);
-		pdata->bank_b_ctrl = BANK_B_CTRL_DISABLE;
-		break;
-	default:
-		break;
-	}
-
-	if (ret < 0)
-		goto err_bl_reg;
-
-	if (pdata->bank_b_ctrl && pchip->bled2 == NULL) {
-		ret = lm3630_backlight_register(pchip, BLED_2);
-		if (ret < 0)
-			goto err_bl_reg;
-	}
-
-	/* interrupt enable  : irq 0 is not allowed for lm3630 */
-	pchip->irq = client->irq;
-	if (pchip->irq)
-		lm3630_intr_config(pchip);
-
-	dev_info(&client->dev, "LM3630 backlight register OK.\n");
-	return 0;
-
-err_bl_reg:
-	dev_err(&client->dev, "fail : backlight register.\n");
-	lm3630_backlight_unregister(pchip);
-err_chip_init:
-	return ret;
-}
-
-static int lm3630_remove(struct i2c_client *client)
-{
-	int ret;
-	struct lm3630_chip_data *pchip = i2c_get_clientdata(client);
-
-	ret = regmap_write(pchip->regmap, REG_BRT_A, 0);
-	if (ret < 0)
-		dev_err(pchip->dev, "i2c failed to access register\n");
-
-	ret = regmap_write(pchip->regmap, REG_BRT_B, 0);
-	if (ret < 0)
-		dev_err(pchip->dev, "i2c failed to access register\n");
-
-	lm3630_backlight_unregister(pchip);
-	if (pchip->irq) {
-		free_irq(pchip->irq, pchip);
-		flush_workqueue(pchip->irqthread);
-		destroy_workqueue(pchip->irqthread);
-	}
-	return 0;
-}
-
-static const struct i2c_device_id lm3630_id[] = {
-	{LM3630_NAME, 0},
-	{}
-};
-
-MODULE_DEVICE_TABLE(i2c, lm3630_id);
-
-static struct i2c_driver lm3630_i2c_driver = {
-	.driver = {
-		   .name = LM3630_NAME,
-		   },
-	.probe = lm3630_probe,
-	.remove = lm3630_remove,
-	.id_table = lm3630_id,
-};
-
-module_i2c_driver(lm3630_i2c_driver);
-
-MODULE_DESCRIPTION("Texas Instruments Backlight driver for LM3630");
-MODULE_AUTHOR("G.Shark Jeong <gshark.jeong@gmail.com>");
-MODULE_AUTHOR("Daniel Jeong <daniel.jeong@ti.com>");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c
new file mode 100644
index 000000000000..cf40cc8e662b
--- /dev/null
+++ b/drivers/video/backlight/lm3630a_bl.c
@@ -0,0 +1,483 @@
+/*
+* Simple driver for Texas Instruments LM3630A Backlight driver chip
+* Copyright (C) 2012 Texas Instruments
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+*/
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/backlight.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+#include <linux/interrupt.h>
+#include <linux/regmap.h>
+#include <linux/pwm.h>
+#include <linux/platform_data/lm3630a_bl.h>
+
+#define REG_CTRL	0x00
+#define REG_BOOST	0x02
+#define REG_CONFIG	0x01
+#define REG_BRT_A	0x03
+#define REG_BRT_B	0x04
+#define REG_I_A		0x05
+#define REG_I_B		0x06
+#define REG_INT_STATUS	0x09
+#define REG_INT_EN	0x0A
+#define REG_FAULT	0x0B
+#define REG_PWM_OUTLOW	0x12
+#define REG_PWM_OUTHIGH	0x13
+#define REG_MAX		0x1F
+
+#define INT_DEBOUNCE_MSEC	10
+struct lm3630a_chip {
+	struct device *dev;
+	struct delayed_work work;
+
+	int irq;
+	struct workqueue_struct *irqthread;
+	struct lm3630a_platform_data *pdata;
+	struct backlight_device *bleda;
+	struct backlight_device *bledb;
+	struct regmap *regmap;
+	struct pwm_device *pwmd;
+};
+
+/* i2c access */
+static int lm3630a_read(struct lm3630a_chip *pchip, unsigned int reg)
+{
+	int rval;
+	unsigned int reg_val;
+
+	rval = regmap_read(pchip->regmap, reg, &reg_val);
+	if (rval < 0)
+		return rval;
+	return reg_val & 0xFF;
+}
+
+static int lm3630a_write(struct lm3630a_chip *pchip,
+			 unsigned int reg, unsigned int data)
+{
+	return regmap_write(pchip->regmap, reg, data);
+}
+
+static int lm3630a_update(struct lm3630a_chip *pchip,
+			  unsigned int reg, unsigned int mask,
+			  unsigned int data)
+{
+	return regmap_update_bits(pchip->regmap, reg, mask, data);
+}
+
+/* initialize chip */
+static int lm3630a_chip_init(struct lm3630a_chip *pchip)
+{
+	int rval;
+	struct lm3630a_platform_data *pdata = pchip->pdata;
+
+	usleep_range(1000, 2000);
+	/* set Filter Strength Register */
+	rval = lm3630a_write(pchip, 0x50, 0x03);
+	/* set Cofig. register */
+	rval |= lm3630a_update(pchip, REG_CONFIG, 0x07, pdata->pwm_ctrl);
+	/* set boost control */
+	rval |= lm3630a_write(pchip, REG_BOOST, 0x38);
+	/* set current A */
+	rval |= lm3630a_update(pchip, REG_I_A, 0x1F, 0x1F);
+	/* set current B */
+	rval |= lm3630a_write(pchip, REG_I_B, 0x1F);
+	/* set control */
+	rval |=
+	    lm3630a_write(pchip, REG_CTRL, pdata->leda_ctrl | pdata->ledb_ctrl);
+	usleep_range(1000, 2000);
+	/* set brightness A and B */
+	rval |= lm3630a_write(pchip, REG_BRT_A, pdata->leda_init_brt);
+	rval |= lm3630a_write(pchip, REG_BRT_B, pdata->ledb_init_brt);
+
+	if (rval < 0)
+		dev_err(pchip->dev, "i2c failed to access register\n");
+	return rval;
+}
+
+/* interrupt handling */
+static void lm3630a_delayed_func(struct work_struct *work)
+{
+	unsigned int rval;
+	struct lm3630a_chip *pchip;
+
+	pchip = container_of(work, struct lm3630a_chip, work.work);
+
+	rval = lm3630a_read(pchip, REG_INT_STATUS);
+	if (rval < 0) {
+		dev_err(pchip->dev,
+			"i2c failed to access REG_INT_STATUS Register\n");
+		return;
+	}
+
+	dev_info(pchip->dev, "REG_INT_STATUS Register is 0x%x\n", rval);
+}
+
+static irqreturn_t lm3630a_isr_func(int irq, void *chip)
+{
+	int rval;
+	struct lm3630a_chip *pchip = chip;
+	unsigned long delay = msecs_to_jiffies(INT_DEBOUNCE_MSEC);
+
+	queue_delayed_work(pchip->irqthread, &pchip->work, delay);
+
+	rval = lm3630a_update(pchip, REG_CTRL, 0x80, 0x00);
+	if (rval < 0) {
+		dev_err(pchip->dev, "i2c failed to access register\n");
+		return IRQ_NONE;
+	}
+	return IRQ_HANDLED;
+}
+
+static int lm3630a_intr_config(struct lm3630a_chip *pchip)
+{
+	int rval;
+
+	rval = lm3630a_write(pchip, REG_INT_EN, 0x87);
+	if (rval < 0)
+		return rval;
+
+	INIT_DELAYED_WORK(&pchip->work, lm3630a_delayed_func);
+	pchip->irqthread = create_singlethread_workqueue("lm3630a-irqthd");
+	if (!pchip->irqthread) {
+		dev_err(pchip->dev, "create irq thread fail\n");
+		return -ENOMEM;
+	}
+	if (request_threaded_irq
+	    (pchip->irq, NULL, lm3630a_isr_func,
+	     IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "lm3630a_irq", pchip)) {
+		dev_err(pchip->dev, "request threaded irq fail\n");
+		return -ENOMEM;
+	}
+	return rval;
+}
+
+static void lm3630a_pwm_ctrl(struct lm3630a_chip *pchip, int br, int br_max)
+{
+	unsigned int period = pwm_get_period(pchip->pwmd);
+	unsigned int duty = br * period / br_max;
+
+	pwm_config(pchip->pwmd, duty, period);
+	if (duty)
+		pwm_enable(pchip->pwmd);
+	else
+		pwm_disable(pchip->pwmd);
+}
+
+/* update and get brightness */
+static int lm3630a_bank_a_update_status(struct backlight_device *bl)
+{
+	int ret;
+	struct lm3630a_chip *pchip = bl_get_data(bl);
+	enum lm3630a_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
+
+	/* pwm control */
+	if ((pwm_ctrl & LM3630A_PWM_BANK_A) != 0) {
+		lm3630a_pwm_ctrl(pchip, bl->props.brightness,
+				 bl->props.max_brightness);
+		return bl->props.brightness;
+	}
+
+	/* disable sleep */
+	ret = lm3630a_update(pchip, REG_CTRL, 0x80, 0x00);
+	if (ret < 0)
+		goto out_i2c_err;
+	usleep_range(1000, 2000);
+	/* minimum brightness is 0x04 */
+	ret = lm3630a_write(pchip, REG_BRT_A, bl->props.brightness);
+	if (bl->props.brightness < 0x4)
+		ret |= lm3630a_update(pchip, REG_CTRL, LM3630A_LEDA_ENABLE, 0);
+	else
+		ret |= lm3630a_update(pchip, REG_CTRL,
+				      LM3630A_LEDA_ENABLE, LM3630A_LEDA_ENABLE);
+	if (ret < 0)
+		goto out_i2c_err;
+	return bl->props.brightness;
+
+out_i2c_err:
+	dev_err(pchip->dev, "i2c failed to access\n");
+	return bl->props.brightness;
+}
+
+static int lm3630a_bank_a_get_brightness(struct backlight_device *bl)
+{
+	int brightness, rval;
+	struct lm3630a_chip *pchip = bl_get_data(bl);
+	enum lm3630a_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
+
+	if ((pwm_ctrl & LM3630A_PWM_BANK_A) != 0) {
+		rval = lm3630a_read(pchip, REG_PWM_OUTHIGH);
+		if (rval < 0)
+			goto out_i2c_err;
+		brightness = (rval & 0x01) << 8;
+		rval = lm3630a_read(pchip, REG_PWM_OUTLOW);
+		if (rval < 0)
+			goto out_i2c_err;
+		brightness |= rval;
+		goto out;
+	}
+
+	/* disable sleep */
+	rval = lm3630a_update(pchip, REG_CTRL, 0x80, 0x00);
+	if (rval < 0)
+		goto out_i2c_err;
+	usleep_range(1000, 2000);
+	rval = lm3630a_read(pchip, REG_BRT_A);
+	if (rval < 0)
+		goto out_i2c_err;
+	brightness = rval;
+
+out:
+	bl->props.brightness = brightness;
+	return bl->props.brightness;
+out_i2c_err:
+	dev_err(pchip->dev, "i2c failed to access register\n");
+	return 0;
+}
+
+static const struct backlight_ops lm3630a_bank_a_ops = {
+	.options = BL_CORE_SUSPENDRESUME,
+	.update_status = lm3630a_bank_a_update_status,
+	.get_brightness = lm3630a_bank_a_get_brightness,
+};
+
+/* update and get brightness */
+static int lm3630a_bank_b_update_status(struct backlight_device *bl)
+{
+	int ret;
+	struct lm3630a_chip *pchip = bl_get_data(bl);
+	enum lm3630a_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
+
+	/* pwm control */
+	if ((pwm_ctrl & LM3630A_PWM_BANK_B) != 0) {
+		lm3630a_pwm_ctrl(pchip, bl->props.brightness,
+				 bl->props.max_brightness);
+		return bl->props.brightness;
+	}
+
+	/* disable sleep */
+	ret = lm3630a_update(pchip, REG_CTRL, 0x80, 0x00);
+	if (ret < 0)
+		goto out_i2c_err;
+	usleep_range(1000, 2000);
+	/* minimum brightness is 0x04 */
+	ret = lm3630a_write(pchip, REG_BRT_B, bl->props.brightness);
+	if (bl->props.brightness < 0x4)
+		ret |= lm3630a_update(pchip, REG_CTRL, LM3630A_LEDB_ENABLE, 0);
+	else
+		ret |= lm3630a_update(pchip, REG_CTRL,
+				      LM3630A_LEDB_ENABLE, LM3630A_LEDB_ENABLE);
+	if (ret < 0)
+		goto out_i2c_err;
+	return bl->props.brightness;
+
+out_i2c_err:
+	dev_err(pchip->dev, "i2c failed to access REG_CTRL\n");
+	return bl->props.brightness;
+}
+
+static int lm3630a_bank_b_get_brightness(struct backlight_device *bl)
+{
+	int brightness, rval;
+	struct lm3630a_chip *pchip = bl_get_data(bl);
+	enum lm3630a_pwm_ctrl pwm_ctrl = pchip->pdata->pwm_ctrl;
+
+	if ((pwm_ctrl & LM3630A_PWM_BANK_B) != 0) {
+		rval = lm3630a_read(pchip, REG_PWM_OUTHIGH);
+		if (rval < 0)
+			goto out_i2c_err;
+		brightness = (rval & 0x01) << 8;
+		rval = lm3630a_read(pchip, REG_PWM_OUTLOW);
+		if (rval < 0)
+			goto out_i2c_err;
+		brightness |= rval;
+		goto out;
+	}
+
+	/* disable sleep */
+	rval = lm3630a_update(pchip, REG_CTRL, 0x80, 0x00);
+	if (rval < 0)
+		goto out_i2c_err;
+	usleep_range(1000, 2000);
+	rval = lm3630a_read(pchip, REG_BRT_B);
+	if (rval < 0)
+		goto out_i2c_err;
+	brightness = rval;
+
+out:
+	bl->props.brightness = brightness;
+	return bl->props.brightness;
+out_i2c_err:
+	dev_err(pchip->dev, "i2c failed to access register\n");
+	return 0;
+}
+
+static const struct backlight_ops lm3630a_bank_b_ops = {
+	.options = BL_CORE_SUSPENDRESUME,
+	.update_status = lm3630a_bank_b_update_status,
+	.get_brightness = lm3630a_bank_b_get_brightness,
+};
+
+static int lm3630a_backlight_register(struct lm3630a_chip *pchip)
+{
+	struct backlight_properties props;
+	struct lm3630a_platform_data *pdata = pchip->pdata;
+
+	props.type = BACKLIGHT_RAW;
+	if (pdata->leda_ctrl != LM3630A_LEDA_DISABLE) {
+		props.brightness = pdata->leda_init_brt;
+		props.max_brightness = pdata->leda_max_brt;
+		pchip->bleda =
+		    devm_backlight_device_register(pchip->dev, "lm3630a_leda",
+						   pchip->dev, pchip,
+						   &lm3630a_bank_a_ops, &props);
+		if (IS_ERR(pchip->bleda))
+			return PTR_ERR(pchip->bleda);
+	}
+
+	if ((pdata->ledb_ctrl != LM3630A_LEDB_DISABLE) &&
+	    (pdata->ledb_ctrl != LM3630A_LEDB_ON_A)) {
+		props.brightness = pdata->ledb_init_brt;
+		props.max_brightness = pdata->ledb_max_brt;
+		pchip->bledb =
+		    devm_backlight_device_register(pchip->dev, "lm3630a_ledb",
+						   pchip->dev, pchip,
+						   &lm3630a_bank_b_ops, &props);
+		if (IS_ERR(pchip->bledb))
+			return PTR_ERR(pchip->bledb);
+	}
+	return 0;
+}
+
+static const struct regmap_config lm3630a_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = REG_MAX,
+};
+
+static int lm3630a_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct lm3630a_platform_data *pdata = client->dev.platform_data;
+	struct lm3630a_chip *pchip;
+	int rval;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(&client->dev, "fail : i2c functionality check\n");
+		return -EOPNOTSUPP;
+	}
+
+	pchip = devm_kzalloc(&client->dev, sizeof(struct lm3630a_chip),
+			     GFP_KERNEL);
+	if (!pchip)
+		return -ENOMEM;
+	pchip->dev = &client->dev;
+
+	pchip->regmap = devm_regmap_init_i2c(client, &lm3630a_regmap);
+	if (IS_ERR(pchip->regmap)) {
+		rval = PTR_ERR(pchip->regmap);
+		dev_err(&client->dev, "fail : allocate reg. map: %d\n", rval);
+		return rval;
+	}
+
+	i2c_set_clientdata(client, pchip);
+	if (pdata == NULL) {
+		pchip->pdata = devm_kzalloc(pchip->dev,
+					    sizeof(struct
+						   lm3630a_platform_data),
+					    GFP_KERNEL);
+		if (pchip->pdata == NULL)
+			return -ENOMEM;
+		/* default values */
+		pchip->pdata->leda_ctrl = LM3630A_LEDA_ENABLE;
+		pchip->pdata->ledb_ctrl = LM3630A_LEDB_ENABLE;
+		pchip->pdata->leda_max_brt = LM3630A_MAX_BRIGHTNESS;
+		pchip->pdata->ledb_max_brt = LM3630A_MAX_BRIGHTNESS;
+		pchip->pdata->leda_init_brt = LM3630A_MAX_BRIGHTNESS;
+		pchip->pdata->ledb_init_brt = LM3630A_MAX_BRIGHTNESS;
+	} else {
+		pchip->pdata = pdata;
+	}
+	/* chip initialize */
+	rval = lm3630a_chip_init(pchip);
+	if (rval < 0) {
+		dev_err(&client->dev, "fail : init chip\n");
+		return rval;
+	}
+	/* backlight register */
+	rval = lm3630a_backlight_register(pchip);
+	if (rval < 0) {
+		dev_err(&client->dev, "fail : backlight register.\n");
+		return rval;
+	}
+	/* pwm */
+	if (pdata->pwm_ctrl != LM3630A_PWM_DISABLE) {
+		pchip->pwmd = devm_pwm_get(pchip->dev, "lm3630a-pwm");
+		if (IS_ERR(pchip->pwmd)) {
+			dev_err(&client->dev, "fail : get pwm device\n");
+			return PTR_ERR(pchip->pwmd);
+		}
+	}
+	pchip->pwmd->period = pdata->pwm_period;
+
+	/* interrupt enable  : irq 0 is not allowed */
+	pchip->irq = client->irq;
+	if (pchip->irq) {
+		rval = lm3630a_intr_config(pchip);
+		if (rval < 0)
+			return rval;
+	}
+	dev_info(&client->dev, "LM3630A backlight register OK.\n");
+	return 0;
+}
+
+static int lm3630a_remove(struct i2c_client *client)
+{
+	int rval;
+	struct lm3630a_chip *pchip = i2c_get_clientdata(client);
+
+	rval = lm3630a_write(pchip, REG_BRT_A, 0);
+	if (rval < 0)
+		dev_err(pchip->dev, "i2c failed to access register\n");
+
+	rval = lm3630a_write(pchip, REG_BRT_B, 0);
+	if (rval < 0)
+		dev_err(pchip->dev, "i2c failed to access register\n");
+
+	if (pchip->irq) {
+		free_irq(pchip->irq, pchip);
+		flush_workqueue(pchip->irqthread);
+		destroy_workqueue(pchip->irqthread);
+	}
+	return 0;
+}
+
+static const struct i2c_device_id lm3630a_id[] = {
+	{LM3630A_NAME, 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, lm3630a_id);
+
+static struct i2c_driver lm3630a_i2c_driver = {
+	.driver = {
+		   .name = LM3630A_NAME,
+		   },
+	.probe = lm3630a_probe,
+	.remove = lm3630a_remove,
+	.id_table = lm3630a_id,
+};
+
+module_i2c_driver(lm3630a_i2c_driver);
+
+MODULE_DESCRIPTION("Texas Instruments Backlight driver for LM3630A");
+MODULE_AUTHOR("Daniel Jeong <gshark.jeong@gmail.com>");
+MODULE_AUTHOR("LDD MLP <ldd-mlp@list.ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/platform_data/lm3630_bl.h b/include/linux/platform_data/lm3630_bl.h
deleted file mode 100644
index 9176dd3f2d63..000000000000
--- a/include/linux/platform_data/lm3630_bl.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
-* Simple driver for Texas Instruments LM3630 LED Flash driver chip
-* Copyright (C) 2012 Texas Instruments
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License version 2 as
-* published by the Free Software Foundation.
-*
-*/
-
-#ifndef __LINUX_LM3630_H
-#define __LINUX_LM3630_H
-
-#define LM3630_NAME "lm3630_bl"
-
-enum lm3630_pwm_ctrl {
-	PWM_CTRL_DISABLE = 0,
-	PWM_CTRL_BANK_A,
-	PWM_CTRL_BANK_B,
-	PWM_CTRL_BANK_ALL,
-};
-
-enum lm3630_pwm_active {
-	PWM_ACTIVE_HIGH = 0,
-	PWM_ACTIVE_LOW,
-};
-
-enum lm3630_bank_a_ctrl {
-	BANK_A_CTRL_DISABLE = 0x0,
-	BANK_A_CTRL_LED1 = 0x4,
-	BANK_A_CTRL_LED2 = 0x1,
-	BANK_A_CTRL_ALL = 0x5,
-};
-
-enum lm3630_bank_b_ctrl {
-	BANK_B_CTRL_DISABLE = 0,
-	BANK_B_CTRL_LED2,
-};
-
-struct lm3630_platform_data {
-
-	/* maximum brightness */
-	int max_brt_led1;
-	int max_brt_led2;
-
-	/* initial on brightness */
-	int init_brt_led1;
-	int init_brt_led2;
-	enum lm3630_pwm_ctrl pwm_ctrl;
-	enum lm3630_pwm_active pwm_active;
-	enum lm3630_bank_a_ctrl bank_a_ctrl;
-	enum lm3630_bank_b_ctrl bank_b_ctrl;
-	unsigned int pwm_period;
-	void (*pwm_set_intensity) (int brightness, int max_brightness);
-};
-
-#endif /* __LINUX_LM3630_H */
diff --git a/include/linux/platform_data/lm3630a_bl.h b/include/linux/platform_data/lm3630a_bl.h
new file mode 100644
index 000000000000..7538e38e270b
--- /dev/null
+++ b/include/linux/platform_data/lm3630a_bl.h
@@ -0,0 +1,65 @@
+/*
+* Simple driver for Texas Instruments LM3630A LED Flash driver chip
+* Copyright (C) 2012 Texas Instruments
+*
+* This program is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License version 2 as
+* published by the Free Software Foundation.
+*
+*/
+
+#ifndef __LINUX_LM3630A_H
+#define __LINUX_LM3630A_H
+
+#define LM3630A_NAME "lm3630a_bl"
+
+enum lm3630a_pwm_ctrl {
+	LM3630A_PWM_DISABLE = 0x00,
+	LM3630A_PWM_BANK_A,
+	LM3630A_PWM_BANK_B,
+	LM3630A_PWM_BANK_ALL,
+	LM3630A_PWM_BANK_A_ACT_LOW = 0x05,
+	LM3630A_PWM_BANK_B_ACT_LOW,
+	LM3630A_PWM_BANK_ALL_ACT_LOW,
+};
+
+enum lm3630a_leda_ctrl {
+	LM3630A_LEDA_DISABLE = 0x00,
+	LM3630A_LEDA_ENABLE = 0x04,
+	LM3630A_LEDA_ENABLE_LINEAR = 0x14,
+};
+
+enum lm3630a_ledb_ctrl {
+	LM3630A_LEDB_DISABLE = 0x00,
+	LM3630A_LEDB_ON_A = 0x01,
+	LM3630A_LEDB_ENABLE = 0x02,
+	LM3630A_LEDB_ENABLE_LINEAR = 0x0A,
+};
+
+#define LM3630A_MAX_BRIGHTNESS 255
+/*
+ *@leda_init_brt : led a init brightness. 4~255
+ *@leda_max_brt  : led a max brightness.  4~255
+ *@leda_ctrl     : led a disable, enable linear, enable exponential
+ *@ledb_init_brt : led b init brightness. 4~255
+ *@ledb_max_brt  : led b max brightness.  4~255
+ *@ledb_ctrl     : led b disable, enable linear, enable exponential
+ *@pwm_period    : pwm period
+ *@pwm_ctrl      : pwm disable, bank a or b, active high or low
+ */
+struct lm3630a_platform_data {
+
+	/* led a config.  */
+	int leda_init_brt;
+	int leda_max_brt;
+	enum lm3630a_leda_ctrl leda_ctrl;
+	/* led b config. */
+	int ledb_init_brt;
+	int ledb_max_brt;
+	enum lm3630a_ledb_ctrl ledb_ctrl;
+	/* pwm config. */
+	unsigned int pwm_period;
+	enum lm3630a_pwm_ctrl pwm_ctrl;
+};
+
+#endif /* __LINUX_LM3630A_H */
-- 
cgit 


From ec778edf97dcaa517e5b0eea6f1a9ba9d476e4a8 Mon Sep 17 00:00:00 2001
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Date: Tue, 12 Nov 2013 15:09:48 -0800
Subject: bitops/find: clarify and extend documentation

Add return value documentation and clarify the units of the @size
parameter.

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/bitops/find.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 71c778033f57..998d4d544f18 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -7,6 +7,9 @@
  * @addr: The address to base the search on
  * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
  */
 extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
 		size, unsigned long offset);
@@ -18,6 +21,9 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long
  * @addr: The address to base the search on
  * @offset: The bitnumber to start searching at
  * @size: The bitmap size in bits
+ *
+ * Returns the bit number of the next zero bit
+ * If no bits are zero, returns @size.
  */
 extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
 		long size, unsigned long offset);
@@ -28,9 +34,10 @@ extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned
 /**
  * find_first_bit - find the first set bit in a memory region
  * @addr: The address to start the search at
- * @size: The maximum size to search
+ * @size: The maximum number of bits to search
  *
  * Returns the bit number of the first set bit.
+ * If no bits are set, returns @size.
  */
 extern unsigned long find_first_bit(const unsigned long *addr,
 				    unsigned long size);
@@ -38,9 +45,10 @@ extern unsigned long find_first_bit(const unsigned long *addr,
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region
  * @addr: The address to start the search at
- * @size: The maximum size to search
+ * @size: The maximum number of bits to search
  *
  * Returns the bit number of the first cleared bit.
+ * If no bits are zero, returns @size.
  */
 extern unsigned long find_first_zero_bit(const unsigned long *addr,
 					 unsigned long size);
-- 
cgit 


From 684f0d3d14f2744ae7ad79063b21909e32bf444e Mon Sep 17 00:00:00 2001
From: Nicolin Chen <b42378@freescale.com>
Date: Tue, 12 Nov 2013 15:09:52 -0800
Subject: lib/genalloc: add a helper function for DMA buffer allocation

When using pool space for DMA buffer, there might be duplicated calling of
gen_pool_alloc() and gen_pool_virt_to_phys() in each implementation.

Thus it's better to add a simple helper function, a compatible one to the
common dma_alloc_coherent(), to save some code.

Signed-off-by: Nicolin Chen <b42378@freescale.com>
Cc: "Hans J. Koch" <hjk@hansjkoch.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Kevin Hilman <khilman@deeprootsystems.com>
Cc: Liam Girdwood <lgirdwood@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Mauro Carvalho Chehab <m.chehab@samsung.com>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Sekhar Nori <nsekhar@ti.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/genalloc.h |  2 ++
 lib/genalloc.c           | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index f8d41cb1cbe0..1eda33d7cb10 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -94,6 +94,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr,
 }
 extern void gen_pool_destroy(struct gen_pool *);
 extern unsigned long gen_pool_alloc(struct gen_pool *, size_t);
+extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size,
+		dma_addr_t *dma);
 extern void gen_pool_free(struct gen_pool *, unsigned long, size_t);
 extern void gen_pool_for_each_chunk(struct gen_pool *,
 	void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *);
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 26cf20be72b7..dda31168844f 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -312,6 +312,34 @@ retry:
 }
 EXPORT_SYMBOL(gen_pool_alloc);
 
+/**
+ * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage
+ * @pool: pool to allocate from
+ * @size: number of bytes to allocate from the pool
+ * @dma: dma-view physical address
+ *
+ * Allocate the requested number of bytes from the specified pool.
+ * Uses the pool allocation function (with first-fit algorithm by default).
+ * Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
+ */
+void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma)
+{
+	unsigned long vaddr;
+
+	if (!pool)
+		return NULL;
+
+	vaddr = gen_pool_alloc(pool, size);
+	if (!vaddr)
+		return NULL;
+
+	*dma = gen_pool_virt_to_phys(pool, vaddr);
+
+	return (void *)vaddr;
+}
+EXPORT_SYMBOL(gen_pool_dma_alloc);
+
 /**
  * gen_pool_free - free allocated special memory back to the pool
  * @pool: pool to free to
-- 
cgit 


From 008208c6b26f21c2648c250a09c55e737c02c5f8 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 12 Nov 2013 15:10:01 -0800
Subject: list: introduce list_next_entry() and list_prev_entry()

Add two trivial helpers list_next_entry() and list_prev_entry(), they
can have a lot of users including list.h itself.  In fact the 1st one is
already defined in events/core.c and bnx2x_sp.c, so the patch simply
moves the definition to list.h.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Eilon Greenstein <eilong@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c |  3 ---
 include/linux/list.h                           | 16 ++++++++++++++++
 kernel/events/core.c                           |  3 ---
 3 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 9fbeee522d2c..32c92abf5094 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -1217,9 +1217,6 @@ static void bnx2x_set_one_vlan_mac_e1h(struct bnx2x *bp,
 				     ETH_VLAN_FILTER_CLASSIFY, config);
 }
 
-#define list_next_entry(pos, member) \
-	list_entry((pos)->member.next, typeof(*(pos)), member)
-
 /**
  * bnx2x_vlan_mac_restore - reconfigure next MAC/VLAN/VLAN-MAC element
  *
diff --git a/include/linux/list.h b/include/linux/list.h
index f4d8a2f12a33..2ece63847001 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -372,6 +372,22 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_first_entry_or_null(ptr, type, member) \
 	(!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
 
+/**
+ * list_next_entry - get the next element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_next_entry(pos, member) \
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos:	the type * to cursor
+ * @member:	the name of the list_struct within the struct.
+ */
+#define list_prev_entry(pos, member) \
+	list_entry((pos)->member.prev, typeof(*(pos)), member)
+
 /**
  * list_for_each	-	iterate over a list
  * @pos:	the &struct list_head to use as a loop cursor.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8c875ef6e120..d724e7757cd1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2234,9 +2234,6 @@ static void __perf_event_sync_stat(struct perf_event *event,
 	perf_event_update_userpage(next_event);
 }
 
-#define list_next_entry(pos, member) \
-	list_entry(pos->member.next, typeof(*pos), member)
-
 static void perf_event_sync_stat(struct perf_event_context *ctx,
 				   struct perf_event_context *next_ctx)
 {
-- 
cgit 


From 8120e2e5141a420edee725ff28f18aa264795f7a Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 12 Nov 2013 15:10:02 -0800
Subject: list: change list_for_each_entry*() to use list_*_entry()

Now that we have list_{next,prev}_entry() we can change
list_for_each_entry*() and list_safe_reset_next() to use the new helpers
to improve the readability.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Eilon Greenstein <eilong@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index 2ece63847001..c88a591d1c02 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -433,8 +433,8 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_entry((head)->next, typeof(*pos), member);	\
-	     &pos->member != (head); 	\
-	     pos = list_entry(pos->member.next, typeof(*pos), member))
+	     &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
 
 /**
  * list_for_each_entry_reverse - iterate backwards over list of given type.
@@ -444,8 +444,8 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
-	     &pos->member != (head); 	\
-	     pos = list_entry(pos->member.prev, typeof(*pos), member))
+	     &pos->member != (head); 					\
+	     pos = list_prev_entry(pos, member))
 
 /**
  * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
@@ -468,9 +468,9 @@ static inline void list_splice_tail_init(struct list_head *list,
  * the current position.
  */
 #define list_for_each_entry_continue(pos, head, member) 		\
-	for (pos = list_entry(pos->member.next, typeof(*pos), member);	\
-	     &pos->member != (head);	\
-	     pos = list_entry(pos->member.next, typeof(*pos), member))
+	for (pos = list_next_entry(pos, member);			\
+	     &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
 
 /**
  * list_for_each_entry_continue_reverse - iterate backwards from the given point
@@ -482,9 +482,9 @@ static inline void list_splice_tail_init(struct list_head *list,
  * the current position.
  */
 #define list_for_each_entry_continue_reverse(pos, head, member)		\
-	for (pos = list_entry(pos->member.prev, typeof(*pos), member);	\
-	     &pos->member != (head);	\
-	     pos = list_entry(pos->member.prev, typeof(*pos), member))
+	for (pos = list_prev_entry(pos, member);			\
+	     &pos->member != (head);					\
+	     pos = list_prev_entry(pos, member))
 
 /**
  * list_for_each_entry_from - iterate over list of given type from the current point
@@ -495,8 +495,8 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from(pos, head, member) 			\
-	for (; &pos->member != (head);	\
-	     pos = list_entry(pos->member.next, typeof(*pos), member))
+	for (; &pos->member != (head);					\
+	     pos = list_next_entry(pos, member))
 
 /**
  * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
@@ -507,9 +507,9 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_entry((head)->next, typeof(*pos), member),	\
-		n = list_entry(pos->member.next, typeof(*pos), member);	\
+		n = list_next_entry(pos, member);			\
 	     &pos->member != (head); 					\
-	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+	     pos = n, n = list_next_entry(n, member))
 
 /**
  * list_for_each_entry_safe_continue - continue list iteration safe against removal
@@ -522,10 +522,10 @@ static inline void list_splice_tail_init(struct list_head *list,
  * safe against removal of list entry.
  */
 #define list_for_each_entry_safe_continue(pos, n, head, member) 		\
-	for (pos = list_entry(pos->member.next, typeof(*pos), member), 		\
-		n = list_entry(pos->member.next, typeof(*pos), member);		\
+	for (pos = list_next_entry(pos, member), 				\
+		n = list_next_entry(pos, member);				\
 	     &pos->member != (head);						\
-	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+	     pos = n, n = list_next_entry(n, member))
 
 /**
  * list_for_each_entry_safe_from - iterate over list from current point safe against removal
@@ -538,9 +538,9 @@ static inline void list_splice_tail_init(struct list_head *list,
  * removal of list entry.
  */
 #define list_for_each_entry_safe_from(pos, n, head, member) 			\
-	for (n = list_entry(pos->member.next, typeof(*pos), member);		\
+	for (n = list_next_entry(pos, member);					\
 	     &pos->member != (head);						\
-	     pos = n, n = list_entry(n->member.next, typeof(*n), member))
+	     pos = n, n = list_next_entry(n, member))
 
 /**
  * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
@@ -554,9 +554,9 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_safe_reverse(pos, n, head, member)		\
 	for (pos = list_entry((head)->prev, typeof(*pos), member),	\
-		n = list_entry(pos->member.prev, typeof(*pos), member);	\
+		n = list_prev_entry(pos, member);			\
 	     &pos->member != (head); 					\
-	     pos = n, n = list_entry(n->member.prev, typeof(*n), member))
+	     pos = n, n = list_prev_entry(n, member))
 
 /**
  * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
@@ -571,7 +571,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * completing the current iteration of the loop body.
  */
 #define list_safe_reset_next(pos, n, member)				\
-	n = list_entry(pos->member.next, typeof(*pos), member)
+	n = list_next_entry(pos, member)
 
 /*
  * Double linked lists with a single pointer list head.
-- 
cgit 


From 93be3c2eb3371f022ad88acf1ab6bee8e3c38378 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 12 Nov 2013 15:10:03 -0800
Subject: list: introduce list_last_entry(), use list_{first,last}_entry()

We already have list_first_entry(), it makes sense to also add
list_last_entry() for consistency.  And we use both helpers in
list_for_each_*().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Eilon Greenstein <eilong@broadcom.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index c88a591d1c02..ef9594171062 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -361,6 +361,17 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_first_entry(ptr, type, member) \
 	list_entry((ptr)->next, type, member)
 
+/**
+ * list_last_entry - get the last element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
 /**
  * list_first_entry_or_null - get the first element from a list
  * @ptr:	the list head to take the element from.
@@ -432,7 +443,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @member:	the name of the list_struct within the struct.
  */
 #define list_for_each_entry(pos, head, member)				\
-	for (pos = list_entry((head)->next, typeof(*pos), member);	\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
 	     &pos->member != (head);					\
 	     pos = list_next_entry(pos, member))
 
@@ -443,7 +454,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @member:	the name of the list_struct within the struct.
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
-	for (pos = list_entry((head)->prev, typeof(*pos), member);	\
+	for (pos = list_last_entry(head, typeof(*pos), member);		\
 	     &pos->member != (head); 					\
 	     pos = list_prev_entry(pos, member))
 
@@ -506,7 +517,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * @member:	the name of the list_struct within the struct.
  */
 #define list_for_each_entry_safe(pos, n, head, member)			\
-	for (pos = list_entry((head)->next, typeof(*pos), member),	\
+	for (pos = list_first_entry(head, typeof(*pos), member),	\
 		n = list_next_entry(pos, member);			\
 	     &pos->member != (head); 					\
 	     pos = n, n = list_next_entry(n, member))
@@ -553,7 +564,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * of list entry.
  */
 #define list_for_each_entry_safe_reverse(pos, n, head, member)		\
-	for (pos = list_entry((head)->prev, typeof(*pos), member),	\
+	for (pos = list_last_entry(head, typeof(*pos), member),		\
 		n = list_prev_entry(pos, member);			\
 	     &pos->member != (head); 					\
 	     pos = n, n = list_prev_entry(n, member))
-- 
cgit 


From 65321547c8be5b00427ac8de23fd15801b68de1f Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 12 Nov 2013 15:10:19 -0800
Subject: init.h: document the existence of __initconst

Initdata can be const since more than 5 years, using the __initconst
keyword.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/init.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/init.h b/include/linux/init.h
index f1c27a71d03c..8e68a64bfe00 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -26,8 +26,8 @@
  * extern int initialize_foobar_device(int, int, int) __init;
  *
  * For initialized data:
- * You should insert __initdata between the variable name and equal
- * sign followed by value, e.g.:
+ * You should insert __initdata or __initconst between the variable name
+ * and equal sign followed by value, e.g.:
  *
  * static int init_variable __initdata = 0;
  * static const char linux_logo[] __initconst = { 0x32, 0x36, ... };
@@ -35,8 +35,6 @@
  * Don't forget to initialize data not at file scope, i.e. within a function,
  * as gcc otherwise puts the data into the bss section and not into the init
  * section.
- * 
- * Also note, that this data cannot be "const".
  */
 
 /* These are for everybody (although not all archs will actually
-- 
cgit 


From 5bccae6ec4587044779f0b8e6fcb8f87db4181f0 Mon Sep 17 00:00:00 2001
From: Sangbeom Kim <sbkim73@samsung.com>
Date: Tue, 12 Nov 2013 15:11:04 -0800
Subject: rtc: s5m-rtc: add real-time clock driver for s5m8767

Add real-time clock driver for s5m8767.

Signed-off-by: Sangbeom Kim <sbkim73@samsung.com>
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Cc: Todd Broch <tbroch@chromium.org>
Cc: Mark Brown <broonie@kernel.org>
Acked-by: Lee Jones <lee.jones@linaro.org>	[mfd parts]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rtc/Kconfig              |  10 +
 drivers/rtc/Makefile             |   1 +
 drivers/rtc/rtc-s5m.c            | 635 +++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/samsung/core.h |   1 +
 include/linux/mfd/samsung/rtc.h  |  11 +
 5 files changed, 658 insertions(+)
 create mode 100644 drivers/rtc/rtc-s5m.c

(limited to 'include')

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 9654aa3c05cb..4f48b9a26aa0 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -497,6 +497,16 @@ config RTC_DRV_RV3029C2
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-rv3029c2.
 
+config RTC_DRV_S5M
+	tristate "Samsung S5M series"
+	depends on MFD_SEC_CORE
+	help
+	  If you say yes here you will get support for the
+	  RTC of Samsung S5M PMIC series.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-s5m.
+
 endif # I2C
 
 comment "SPI RTC drivers"
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 2dff3d2009b5..9312e7965365 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -107,6 +107,7 @@ obj-$(CONFIG_RTC_DRV_RX8025)	+= rtc-rx8025.o
 obj-$(CONFIG_RTC_DRV_RX8581)	+= rtc-rx8581.o
 obj-$(CONFIG_RTC_DRV_S35390A)	+= rtc-s35390a.o
 obj-$(CONFIG_RTC_DRV_S3C)	+= rtc-s3c.o
+obj-$(CONFIG_RTC_DRV_S5M)	+= rtc-s5m.o
 obj-$(CONFIG_RTC_DRV_SA1100)	+= rtc-sa1100.o
 obj-$(CONFIG_RTC_DRV_SH)	+= rtc-sh.o
 obj-$(CONFIG_RTC_DRV_SNVS)	+= rtc-snvs.o
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
new file mode 100644
index 000000000000..b7fd02bc0a14
--- /dev/null
+++ b/drivers/rtc/rtc-s5m.c
@@ -0,0 +1,635 @@
+/*
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd
+ *	http://www.samsung.com
+ *
+ *  Copyright (C) 2013 Google, Inc
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/bcd.h>
+#include <linux/bitops.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/samsung/core.h>
+#include <linux/mfd/samsung/irq.h>
+#include <linux/mfd/samsung/rtc.h>
+
+struct s5m_rtc_info {
+	struct device *dev;
+	struct sec_pmic_dev *s5m87xx;
+	struct regmap *rtc;
+	struct rtc_device *rtc_dev;
+	int irq;
+	int device_type;
+	int rtc_24hr_mode;
+	bool wtsr_smpl;
+};
+
+static void s5m8767_data_to_tm(u8 *data, struct rtc_time *tm,
+			       int rtc_24hr_mode)
+{
+	tm->tm_sec = data[RTC_SEC] & 0x7f;
+	tm->tm_min = data[RTC_MIN] & 0x7f;
+	if (rtc_24hr_mode) {
+		tm->tm_hour = data[RTC_HOUR] & 0x1f;
+	} else {
+		tm->tm_hour = data[RTC_HOUR] & 0x0f;
+		if (data[RTC_HOUR] & HOUR_PM_MASK)
+			tm->tm_hour += 12;
+	}
+
+	tm->tm_wday = ffs(data[RTC_WEEKDAY] & 0x7f);
+	tm->tm_mday = data[RTC_DATE] & 0x1f;
+	tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1;
+	tm->tm_year = (data[RTC_YEAR1] & 0x7f) + 100;
+	tm->tm_yday = 0;
+	tm->tm_isdst = 0;
+}
+
+static int s5m8767_tm_to_data(struct rtc_time *tm, u8 *data)
+{
+	data[RTC_SEC] = tm->tm_sec;
+	data[RTC_MIN] = tm->tm_min;
+
+	if (tm->tm_hour >= 12)
+		data[RTC_HOUR] = tm->tm_hour | HOUR_PM_MASK;
+	else
+		data[RTC_HOUR] = tm->tm_hour & ~HOUR_PM_MASK;
+
+	data[RTC_WEEKDAY] = 1 << tm->tm_wday;
+	data[RTC_DATE] = tm->tm_mday;
+	data[RTC_MONTH] = tm->tm_mon + 1;
+	data[RTC_YEAR1] = tm->tm_year > 100 ? (tm->tm_year - 100) : 0;
+
+	if (tm->tm_year < 100) {
+		pr_err("s5m8767 RTC cannot handle the year %d.\n",
+		       1900 + tm->tm_year);
+		return -EINVAL;
+	} else {
+		return 0;
+	}
+}
+
+static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
+{
+	int ret;
+	unsigned int data;
+
+	ret = regmap_read(info->rtc, SEC_RTC_UDR_CON, &data);
+	if (ret < 0) {
+		dev_err(info->dev, "failed to read update reg(%d)\n", ret);
+		return ret;
+	}
+
+	data |= RTC_TIME_EN_MASK;
+	data |= RTC_UDR_MASK;
+
+	ret = regmap_write(info->rtc, SEC_RTC_UDR_CON, data);
+	if (ret < 0) {
+		dev_err(info->dev, "failed to write update reg(%d)\n", ret);
+		return ret;
+	}
+
+	do {
+		ret = regmap_read(info->rtc, SEC_RTC_UDR_CON, &data);
+	} while ((data & RTC_UDR_MASK) && !ret);
+
+	return ret;
+}
+
+static inline int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
+{
+	int ret;
+	unsigned int data;
+
+	ret = regmap_read(info->rtc, SEC_RTC_UDR_CON, &data);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to read update reg(%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	data &= ~RTC_TIME_EN_MASK;
+	data |= RTC_UDR_MASK;
+
+	ret = regmap_write(info->rtc, SEC_RTC_UDR_CON, data);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write update reg(%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	do {
+		ret = regmap_read(info->rtc, SEC_RTC_UDR_CON, &data);
+	} while ((data & RTC_UDR_MASK) && !ret);
+
+	return ret;
+}
+
+static void s5m8763_data_to_tm(u8 *data, struct rtc_time *tm)
+{
+	tm->tm_sec = bcd2bin(data[RTC_SEC]);
+	tm->tm_min = bcd2bin(data[RTC_MIN]);
+
+	if (data[RTC_HOUR] & HOUR_12) {
+		tm->tm_hour = bcd2bin(data[RTC_HOUR] & 0x1f);
+		if (data[RTC_HOUR] & HOUR_PM)
+			tm->tm_hour += 12;
+	} else {
+		tm->tm_hour = bcd2bin(data[RTC_HOUR] & 0x3f);
+	}
+
+	tm->tm_wday = data[RTC_WEEKDAY] & 0x07;
+	tm->tm_mday = bcd2bin(data[RTC_DATE]);
+	tm->tm_mon = bcd2bin(data[RTC_MONTH]);
+	tm->tm_year = bcd2bin(data[RTC_YEAR1]) + bcd2bin(data[RTC_YEAR2]) * 100;
+	tm->tm_year -= 1900;
+}
+
+static void s5m8763_tm_to_data(struct rtc_time *tm, u8 *data)
+{
+	data[RTC_SEC] = bin2bcd(tm->tm_sec);
+	data[RTC_MIN] = bin2bcd(tm->tm_min);
+	data[RTC_HOUR] = bin2bcd(tm->tm_hour);
+	data[RTC_WEEKDAY] = tm->tm_wday;
+	data[RTC_DATE] = bin2bcd(tm->tm_mday);
+	data[RTC_MONTH] = bin2bcd(tm->tm_mon);
+	data[RTC_YEAR1] = bin2bcd(tm->tm_year % 100);
+	data[RTC_YEAR2] = bin2bcd((tm->tm_year + 1900) / 100);
+}
+
+static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct s5m_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[8];
+	int ret;
+
+	ret = regmap_bulk_read(info->rtc, SEC_RTC_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	switch (info->device_type) {
+	case S5M8763X:
+		s5m8763_data_to_tm(data, tm);
+		break;
+
+	case S5M8767X:
+		s5m8767_data_to_tm(data, tm, info->rtc_24hr_mode);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + tm->tm_year, 1 + tm->tm_mon, tm->tm_mday,
+		tm->tm_hour, tm->tm_min, tm->tm_sec, tm->tm_wday);
+
+	return rtc_valid_tm(tm);
+}
+
+static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct s5m_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[8];
+	int ret = 0;
+
+	switch (info->device_type) {
+	case S5M8763X:
+		s5m8763_tm_to_data(tm, data);
+		break;
+	case S5M8767X:
+		ret = s5m8767_tm_to_data(tm, data);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + tm->tm_year, 1 + tm->tm_mon, tm->tm_mday,
+		tm->tm_hour, tm->tm_min, tm->tm_sec, tm->tm_wday);
+
+	ret = regmap_raw_write(info->rtc, SEC_RTC_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	ret = s5m8767_rtc_set_time_reg(info);
+
+	return ret;
+}
+
+static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct s5m_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[8];
+	unsigned int val;
+	int ret, i;
+
+	ret = regmap_bulk_read(info->rtc, SEC_ALARM0_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	switch (info->device_type) {
+	case S5M8763X:
+		s5m8763_data_to_tm(data, &alrm->time);
+		ret = regmap_read(info->rtc, SEC_ALARM0_CONF, &val);
+		if (ret < 0)
+			return ret;
+
+		alrm->enabled = !!val;
+
+		ret = regmap_read(info->rtc, SEC_RTC_STATUS, &val);
+		if (ret < 0)
+			return ret;
+
+		break;
+
+	case S5M8767X:
+		s5m8767_data_to_tm(data, &alrm->time, info->rtc_24hr_mode);
+		dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+			1900 + alrm->time.tm_year, 1 + alrm->time.tm_mon,
+			alrm->time.tm_mday, alrm->time.tm_hour,
+			alrm->time.tm_min, alrm->time.tm_sec,
+			alrm->time.tm_wday);
+
+		alrm->enabled = 0;
+		for (i = 0; i < 7; i++) {
+			if (data[i] & ALARM_ENABLE_MASK) {
+				alrm->enabled = 1;
+				break;
+			}
+		}
+
+		alrm->pending = 0;
+		ret = regmap_read(info->rtc, SEC_RTC_STATUS, &val);
+		if (ret < 0)
+			return ret;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (val & ALARM0_STATUS)
+		alrm->pending = 1;
+	else
+		alrm->pending = 0;
+
+	return 0;
+}
+
+static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)
+{
+	u8 data[8];
+	int ret, i;
+	struct rtc_time tm;
+
+	ret = regmap_bulk_read(info->rtc, SEC_ALARM0_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	s5m8767_data_to_tm(data, &tm, info->rtc_24hr_mode);
+	dev_dbg(info->dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + tm.tm_year, 1 + tm.tm_mon, tm.tm_mday,
+		tm.tm_hour, tm.tm_min, tm.tm_sec, tm.tm_wday);
+
+	switch (info->device_type) {
+	case S5M8763X:
+		ret = regmap_write(info->rtc, SEC_ALARM0_CONF, 0);
+		break;
+
+	case S5M8767X:
+		for (i = 0; i < 7; i++)
+			data[i] &= ~ALARM_ENABLE_MASK;
+
+		ret = regmap_raw_write(info->rtc, SEC_ALARM0_SEC, data, 8);
+		if (ret < 0)
+			return ret;
+
+		ret = s5m8767_rtc_set_alarm_reg(info);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
+{
+	int ret;
+	u8 data[8];
+	u8 alarm0_conf;
+	struct rtc_time tm;
+
+	ret = regmap_bulk_read(info->rtc, SEC_ALARM0_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	s5m8767_data_to_tm(data, &tm, info->rtc_24hr_mode);
+	dev_dbg(info->dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + tm.tm_year, 1 + tm.tm_mon, tm.tm_mday,
+		tm.tm_hour, tm.tm_min, tm.tm_sec, tm.tm_wday);
+
+	switch (info->device_type) {
+	case S5M8763X:
+		alarm0_conf = 0x77;
+		ret = regmap_write(info->rtc, SEC_ALARM0_CONF, alarm0_conf);
+		break;
+
+	case S5M8767X:
+		data[RTC_SEC] |= ALARM_ENABLE_MASK;
+		data[RTC_MIN] |= ALARM_ENABLE_MASK;
+		data[RTC_HOUR] |= ALARM_ENABLE_MASK;
+		data[RTC_WEEKDAY] &= ~ALARM_ENABLE_MASK;
+		if (data[RTC_DATE] & 0x1f)
+			data[RTC_DATE] |= ALARM_ENABLE_MASK;
+		if (data[RTC_MONTH] & 0xf)
+			data[RTC_MONTH] |= ALARM_ENABLE_MASK;
+		if (data[RTC_YEAR1] & 0x7f)
+			data[RTC_YEAR1] |= ALARM_ENABLE_MASK;
+
+		ret = regmap_raw_write(info->rtc, SEC_ALARM0_SEC, data, 8);
+		if (ret < 0)
+			return ret;
+		ret = s5m8767_rtc_set_alarm_reg(info);
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct s5m_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[8];
+	int ret;
+
+	switch (info->device_type) {
+	case S5M8763X:
+		s5m8763_tm_to_data(&alrm->time, data);
+		break;
+
+	case S5M8767X:
+		s5m8767_tm_to_data(&alrm->time, data);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + alrm->time.tm_year, 1 + alrm->time.tm_mon,
+		alrm->time.tm_mday, alrm->time.tm_hour, alrm->time.tm_min,
+		alrm->time.tm_sec, alrm->time.tm_wday);
+
+	ret = s5m_rtc_stop_alarm(info);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_raw_write(info->rtc, SEC_ALARM0_SEC, data, 8);
+	if (ret < 0)
+		return ret;
+
+	ret = s5m8767_rtc_set_alarm_reg(info);
+	if (ret < 0)
+		return ret;
+
+	if (alrm->enabled)
+		ret = s5m_rtc_start_alarm(info);
+
+	return ret;
+}
+
+static int s5m_rtc_alarm_irq_enable(struct device *dev,
+				    unsigned int enabled)
+{
+	struct s5m_rtc_info *info = dev_get_drvdata(dev);
+
+	if (enabled)
+		return s5m_rtc_start_alarm(info);
+	else
+		return s5m_rtc_stop_alarm(info);
+}
+
+static irqreturn_t s5m_rtc_alarm_irq(int irq, void *data)
+{
+	struct s5m_rtc_info *info = data;
+
+	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops s5m_rtc_ops = {
+	.read_time = s5m_rtc_read_time,
+	.set_time = s5m_rtc_set_time,
+	.read_alarm = s5m_rtc_read_alarm,
+	.set_alarm = s5m_rtc_set_alarm,
+	.alarm_irq_enable = s5m_rtc_alarm_irq_enable,
+};
+
+static void s5m_rtc_enable_wtsr(struct s5m_rtc_info *info, bool enable)
+{
+	int ret;
+	ret = regmap_update_bits(info->rtc, SEC_WTSR_SMPL_CNTL,
+				 WTSR_ENABLE_MASK,
+				 enable ? WTSR_ENABLE_MASK : 0);
+	if (ret < 0)
+		dev_err(info->dev, "%s: fail to update WTSR reg(%d)\n",
+			__func__, ret);
+}
+
+static void s5m_rtc_enable_smpl(struct s5m_rtc_info *info, bool enable)
+{
+	int ret;
+	ret = regmap_update_bits(info->rtc, SEC_WTSR_SMPL_CNTL,
+				 SMPL_ENABLE_MASK,
+				 enable ? SMPL_ENABLE_MASK : 0);
+	if (ret < 0)
+		dev_err(info->dev, "%s: fail to update SMPL reg(%d)\n",
+			__func__, ret);
+}
+
+static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info)
+{
+	u8 data[2];
+	unsigned int tp_read;
+	int ret;
+	struct rtc_time tm;
+
+	ret = regmap_read(info->rtc, SEC_RTC_UDR_CON, &tp_read);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to read control reg(%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	/* Set RTC control register : Binary mode, 24hour mode */
+	data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+	data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+
+	info->rtc_24hr_mode = 1;
+	ret = regmap_raw_write(info->rtc, SEC_ALARM0_CONF, data, 2);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write controlm reg(%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	/* In first boot time, Set rtc time to 1/1/2012 00:00:00(SUN) */
+	if ((tp_read & RTC_TCON_MASK) == 0) {
+		dev_dbg(info->dev, "rtc init\n");
+		tm.tm_sec = 0;
+		tm.tm_min = 0;
+		tm.tm_hour = 0;
+		tm.tm_wday = 0;
+		tm.tm_mday = 1;
+		tm.tm_mon = 0;
+		tm.tm_year = 112;
+		tm.tm_yday = 0;
+		tm.tm_isdst = 0;
+		ret = s5m_rtc_set_time(info->dev, &tm);
+	}
+
+	ret = regmap_update_bits(info->rtc, SEC_RTC_UDR_CON,
+				 RTC_TCON_MASK, tp_read | RTC_TCON_MASK);
+	if (ret < 0)
+		dev_err(info->dev, "%s: fail to update TCON reg(%d)\n",
+			__func__, ret);
+
+	return ret;
+}
+
+static int s5m_rtc_probe(struct platform_device *pdev)
+{
+	struct sec_pmic_dev *s5m87xx = dev_get_drvdata(pdev->dev.parent);
+	struct sec_platform_data *pdata = s5m87xx->pdata;
+	struct s5m_rtc_info *info;
+	int ret;
+
+	if (!pdata) {
+		dev_err(pdev->dev.parent, "Platform data not supplied\n");
+		return -ENODEV;
+	}
+
+	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = &pdev->dev;
+	info->s5m87xx = s5m87xx;
+	info->rtc = s5m87xx->rtc;
+	info->device_type = s5m87xx->device_type;
+	info->wtsr_smpl = s5m87xx->wtsr_smpl;
+
+	switch (pdata->device_type) {
+	case S5M8763X:
+		info->irq = s5m87xx->irq_base + S5M8763_IRQ_ALARM0;
+		break;
+
+	case S5M8767X:
+		info->irq = s5m87xx->irq_base + S5M8767_IRQ_RTCA1;
+		break;
+
+	default:
+		ret = -EINVAL;
+		dev_err(&pdev->dev, "Unsupported device type: %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, info);
+
+	ret = s5m8767_rtc_init_reg(info);
+
+	if (info->wtsr_smpl) {
+		s5m_rtc_enable_wtsr(info, true);
+		s5m_rtc_enable_smpl(info, true);
+	}
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "s5m-rtc",
+						 &s5m_rtc_ops, THIS_MODULE);
+
+	if (IS_ERR(info->rtc_dev))
+		return PTR_ERR(info->rtc_dev);
+
+	ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
+					s5m_rtc_alarm_irq, 0, "rtc-alarm0",
+					info);
+	if (ret < 0)
+		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
+			info->irq, ret);
+
+	return ret;
+}
+
+static void s5m_rtc_shutdown(struct platform_device *pdev)
+{
+	struct s5m_rtc_info *info = platform_get_drvdata(pdev);
+	int i;
+	unsigned int val = 0;
+	if (info->wtsr_smpl) {
+		for (i = 0; i < 3; i++) {
+			s5m_rtc_enable_wtsr(info, false);
+			regmap_read(info->rtc, SEC_WTSR_SMPL_CNTL, &val);
+			pr_debug("%s: WTSR_SMPL reg(0x%02x)\n", __func__, val);
+			if (val & WTSR_ENABLE_MASK)
+				pr_emerg("%s: fail to disable WTSR\n",
+					 __func__);
+			else {
+				pr_info("%s: success to disable WTSR\n",
+					__func__);
+				break;
+			}
+		}
+	}
+	/* Disable SMPL when power off */
+	s5m_rtc_enable_smpl(info, false);
+}
+
+static const struct platform_device_id s5m_rtc_id[] = {
+	{ "s5m-rtc", 0 },
+};
+
+static struct platform_driver s5m_rtc_driver = {
+	.driver		= {
+		.name	= "s5m-rtc",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= s5m_rtc_probe,
+	.shutdown	= s5m_rtc_shutdown,
+	.id_table	= s5m_rtc_id,
+};
+
+module_platform_driver(s5m_rtc_driver);
+
+/* Module information */
+MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
+MODULE_DESCRIPTION("Samsung S5M RTC driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:s5m-rtc");
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 378ae8a04c6a..2d0c9071bcfb 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -51,6 +51,7 @@ struct sec_pmic_dev {
 	int ono;
 	int type;
 	bool wakeup;
+	bool wtsr_smpl;
 };
 
 int sec_irq_init(struct sec_pmic_dev *sec_pmic);
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 71597e20cddb..94b7cd6d8891 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -62,6 +62,11 @@ enum sec_rtc_reg {
 /* RTC Update Register1 */
 #define RTC_UDR_SHIFT		0
 #define RTC_UDR_MASK		(1 << RTC_UDR_SHIFT)
+#define RTC_TCON_SHIFT		1
+#define RTC_TCON_MASK		(1 << RTC_TCON_SHIFT)
+#define RTC_TIME_EN_SHIFT	3
+#define RTC_TIME_EN_MASK	(1 << RTC_TIME_EN_SHIFT)
+
 /* RTC Hour register */
 #define HOUR_PM_SHIFT		6
 #define HOUR_PM_MASK		(1 << HOUR_PM_SHIFT)
@@ -69,6 +74,12 @@ enum sec_rtc_reg {
 #define ALARM_ENABLE_SHIFT	7
 #define ALARM_ENABLE_MASK	(1 << ALARM_ENABLE_SHIFT)
 
+#define SMPL_ENABLE_SHIFT	7
+#define SMPL_ENABLE_MASK	(1 << SMPL_ENABLE_SHIFT)
+
+#define WTSR_ENABLE_SHIFT	6
+#define WTSR_ENABLE_MASK	(1 << WTSR_ENABLE_SHIFT)
+
 enum {
 	RTC_SEC = 0,
 	RTC_MIN,
-- 
cgit 


From d049f74f2dbe71354d43d393ac3a188947811348 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Nov 2013 15:11:17 -0800
Subject: exec/ptrace: fix get_dumpable() incorrect tests

The get_dumpable() return value is not boolean.  Most users of the
function actually want to be testing for non-SUID_DUMP_USER(1) rather than
SUID_DUMP_DISABLE(0).  The SUID_DUMP_ROOT(2) is also considered a
protected state.  Almost all places did this correctly, excepting the two
places fixed in this patch.

Wrong logic:
    if (dumpable == SUID_DUMP_DISABLE) { /* be protective */ }
        or
    if (dumpable == 0) { /* be protective */ }
        or
    if (!dumpable) { /* be protective */ }

Correct logic:
    if (dumpable != SUID_DUMP_USER) { /* be protective */ }
        or
    if (dumpable != 1) { /* be protective */ }

Without this patch, if the system had set the sysctl fs/suid_dumpable=2, a
user was able to ptrace attach to processes that had dropped privileges to
that user.  (This may have been partially mitigated if Yama was enabled.)

The macros have been moved into the file that declares get/set_dumpable(),
which means things like the ia64 code can see them too.

CVE-2013-2929

Reported-by: Vasily Kulikov <segoon@openwall.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/include/asm/processor.h | 2 +-
 fs/exec.c                         | 6 ++++++
 include/linux/binfmts.h           | 3 ---
 include/linux/sched.h             | 4 ++++
 kernel/ptrace.c                   | 3 ++-
 5 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index e0a899a1a8a6..5a84b3a50741 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -319,7 +319,7 @@ struct thread_struct {
 	regs->loadrs = 0;									\
 	regs->r8 = get_dumpable(current->mm);	/* set "don't zap registers" flag */		\
 	regs->r12 = new_sp - 16;	/* allocate 16 byte scratch area */			\
-	if (unlikely(!get_dumpable(current->mm))) {							\
+	if (unlikely(get_dumpable(current->mm) != SUID_DUMP_USER)) {	\
 		/*										\
 		 * Zap scratch regs to avoid leaking bits between processes with different	\
 		 * uid/privileges.								\
diff --git a/fs/exec.c b/fs/exec.c
index 2ea437e5acf4..12120620f040 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1669,6 +1669,12 @@ int __get_dumpable(unsigned long mm_flags)
 	return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret;
 }
 
+/*
+ * This returns the actual value of the suid_dumpable flag. For things
+ * that are using this for checking for privilege transitions, it must
+ * test against SUID_DUMP_USER rather than treating it as a boolean
+ * value.
+ */
 int get_dumpable(struct mm_struct *mm)
 {
 	return __get_dumpable(mm->flags);
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index e8112ae50531..7554fd410bcc 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -99,9 +99,6 @@ extern void setup_new_exec(struct linux_binprm * bprm);
 extern void would_dump(struct linux_binprm *, struct file *);
 
 extern int suid_dumpable;
-#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
-#define SUID_DUMP_USER		1	/* Dump as user of process */
-#define SUID_DUMP_ROOT		2	/* Dump as root */
 
 /* Stack area protections */
 #define EXSTACK_DEFAULT   0	/* Whatever the arch defaults to */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5e226fe3e512..f7efc8604652 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -323,6 +323,10 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
 
+#define SUID_DUMP_DISABLE	0	/* No setuid dumping */
+#define SUID_DUMP_USER		1	/* Dump as user of process */
+#define SUID_DUMP_ROOT		2	/* Dump as root */
+
 /* mm flags */
 /* dumpable bits */
 #define MMF_DUMPABLE      0  /* core dump is permitted */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index dd562e9aa2c8..1f4bcb3cc21c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -257,7 +257,8 @@ ok:
 	if (task->mm)
 		dumpable = get_dumpable(task->mm);
 	rcu_read_lock();
-	if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+	if (dumpable != SUID_DUMP_USER &&
+	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
-- 
cgit 


From 1310a5a99d900ee30b9f171146406bde0c6c2bd4 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 12 Nov 2013 15:11:19 -0800
Subject: rbtree: fix rbtree_postorder_for_each_entry_safe() iterator

The iterator rbtree_postorder_for_each_entry_safe() relies on pointer
underflow behavior when testing for loop termination.  In particular it
expects that

  &rb_entry(NULL, type, field)->field

is NULL.  But the result of this expression is not defined by a C standard
and some gcc versions (e.g.  4.3.4) assume the above expression can never
be equal to NULL.  The net result is an oops because the iteration is not
properly terminated.

Fix the problem by modifying the iterator to avoid pointer underflows.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: <stable@vger.kernel.org>		[3.12.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rbtree.h | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index aa870a4ddf54..57e75ae9910f 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -85,6 +85,11 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
 	*rb_link = node;
 }
 
+#define rb_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+	})
+
 /**
  * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
  * given type safe against removal of rb_node entry
@@ -95,12 +100,9 @@ static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
  * @field:	the name of the rb_node field within 'type'.
  */
 #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
-	for (pos = rb_entry(rb_first_postorder(root), typeof(*pos), field),\
-		n = rb_entry(rb_next_postorder(&pos->field), \
-			typeof(*pos), field); \
-	     &pos->field; \
-	     pos = n, \
-		n = rb_entry(rb_next_postorder(&pos->field), \
-			typeof(*pos), field))
+	for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
+	     pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
+			typeof(*pos), field); 1; }); \
+	     pos = n)
 
 #endif	/* _LINUX_RBTREE_H */
-- 
cgit 


From 4e9b45a19241354daec281d7a785739829b52359 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@googlemail.com>
Date: Tue, 12 Nov 2013 15:11:47 -0800
Subject: ipc, msg: fix message length check for negative values

On 64 bit systems the test for negative message sizes is bogus as the
size, which may be positive when evaluated as a long, will get truncated
to an int when passed to load_msg().  So a long might very well contain a
positive value but when truncated to an int it would become negative.

That in combination with a small negative value of msg_ctlmax (which will
be promoted to an unsigned type for the comparison against msgsz, making
it a big positive value and therefore make it pass the check) will lead to
two problems: 1/ The kmalloc() call in alloc_msg() will allocate a too
small buffer as the addition of alen is effectively a subtraction.  2/ The
copy_from_user() call in load_msg() will first overflow the buffer with
userland data and then, when the userland access generates an access
violation, the fixup handler copy_user_handle_tail() will try to fill the
remainder with zeros -- roughly 4GB.  That almost instantly results in a
system crash or reset.

  ,-[ Reproducer (needs to be run as root) ]--
  | #include <sys/stat.h>
  | #include <sys/msg.h>
  | #include <unistd.h>
  | #include <fcntl.h>
  |
  | int main(void) {
  |     long msg = 1;
  |     int fd;
  |
  |     fd = open("/proc/sys/kernel/msgmax", O_WRONLY);
  |     write(fd, "-1", 2);
  |     close(fd);
  |
  |     msgsnd(0, &msg, 0xfffffff0, IPC_NOWAIT);
  |
  |     return 0;
  | }
  '---

Fix the issue by preventing msgsz from getting truncated by consistently
using size_t for the message length.  This way the size checks in
do_msgsnd() could still be passed with a negative value for msg_ctlmax but
we would fail on the buffer allocation in that case and error out.

Also change the type of m_ts from int to size_t to avoid similar nastiness
in other code paths -- it is used in similar constructs, i.e.  signed vs.
unsigned checks.  It should never become negative under normal
circumstances, though.

Setting msg_ctlmax to a negative value is an odd configuration and should
be prevented.  As that might break existing userland, it will be handled
in a separate commit so it could easily be reverted and reworked without
reintroducing the above described bug.

Hardening mechanisms for user copy operations would have catched that bug
early -- e.g.  checking slab object sizes on user copy operations as the
usercopy feature of the PaX patch does.  Or, for that matter, detect the
long vs.  int sign change due to truncation, as the size overflow plugin
of the very same patch does.

[akpm@linux-foundation.org: fix i386 min() warnings]
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: Pax Team <pageexec@freemail.hu>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Brad Spengler <spender@grsecurity.net>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: <stable@vger.kernel.org>	[ v2.3.27+ -- yes, that old ;) ]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/msg.h |  6 +++---
 ipc/msgutil.c       | 20 ++++++++++----------
 ipc/util.h          |  4 ++--
 3 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/msg.h b/include/linux/msg.h
index 391af8d11cce..e21f9d44307f 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -6,9 +6,9 @@
 
 /* one msg_msg structure for each message */
 struct msg_msg {
-	struct list_head m_list; 
-	long  m_type;          
-	int m_ts;           /* message text size */
+	struct list_head m_list;
+	long m_type;
+	size_t m_ts;		/* message text size */
 	struct msg_msgseg* next;
 	void *security;
 	/* the actual message follows immediately */
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 491e71f2a1b8..7e7095974d54 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -41,15 +41,15 @@ struct msg_msgseg {
 	/* the next part of the message follows immediately */
 };
 
-#define DATALEN_MSG	(int)(PAGE_SIZE-sizeof(struct msg_msg))
-#define DATALEN_SEG	(int)(PAGE_SIZE-sizeof(struct msg_msgseg))
+#define DATALEN_MSG	((size_t)PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG	((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
 
 
-static struct msg_msg *alloc_msg(int len)
+static struct msg_msg *alloc_msg(size_t len)
 {
 	struct msg_msg *msg;
 	struct msg_msgseg **pseg;
-	int alen;
+	size_t alen;
 
 	alen = min(len, DATALEN_MSG);
 	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
@@ -80,12 +80,12 @@ out_err:
 	return NULL;
 }
 
-struct msg_msg *load_msg(const void __user *src, int len)
+struct msg_msg *load_msg(const void __user *src, size_t len)
 {
 	struct msg_msg *msg;
 	struct msg_msgseg *seg;
 	int err = -EFAULT;
-	int alen;
+	size_t alen;
 
 	msg = alloc_msg(len);
 	if (msg == NULL)
@@ -117,8 +117,8 @@ out_err:
 struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
 {
 	struct msg_msgseg *dst_pseg, *src_pseg;
-	int len = src->m_ts;
-	int alen;
+	size_t len = src->m_ts;
+	size_t alen;
 
 	BUG_ON(dst == NULL);
 	if (src->m_ts > dst->m_ts)
@@ -147,9 +147,9 @@ struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
 	return ERR_PTR(-ENOSYS);
 }
 #endif
-int store_msg(void __user *dest, struct msg_msg *msg, int len)
+int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
 {
-	int alen;
+	size_t alen;
 	struct msg_msgseg *seg;
 
 	alen = min(len, DATALEN_MSG);
diff --git a/ipc/util.h b/ipc/util.h
index f2f5036f2eed..59d78aa94987 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -148,9 +148,9 @@ int ipc_parse_version (int *cmd);
 #endif
 
 extern void free_msg(struct msg_msg *msg);
-extern struct msg_msg *load_msg(const void __user *src, int len);
+extern struct msg_msg *load_msg(const void __user *src, size_t len);
 extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
-extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
 
 extern void recompute_msgmni(struct ipc_namespace *);
 
-- 
cgit 


From b39898cd4077f4b6ec706e717c938751c34e1dc4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Nov 2013 12:30:07 +0100
Subject: genirq: Prevent spurious detection for unconditionally polled
 interrupts

On a 68k platform a couple of interrupts are demultiplexed and
"polled" from a top level interrupt. Unfortunately there is no way to
determine which of the sub interrupts raised the top level interrupt,
so all of the demultiplexed interrupt handlers need to be
invoked. Given a high enough frequency this can trigger the spurious
interrupt detection mechanism, if one of the demultiplex interrupts
returns IRQ_NONE continuously. But this is a false positive as the
polling causes this behaviour and not buggy hardware/software.

Introduce IRQ_POLLED which can be set at interrupt chip setup time via
irq_set_status_flags(). The flag excludes the interrupt from the
spurious detector and from all core polling activities.

Reported-and-tested-by: Michael Schmitz <schmitzmic@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: linux-m68k@vger.kernel.org
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1311061149250.23353@ionos.tec.linutronix.de
---
 include/linux/irq.h   |  7 ++++++-
 kernel/irq/settings.h |  7 +++++++
 kernel/irq/spurious.c | 12 +++++++++---
 3 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 56bb0dc8b7d4..7dc10036eff5 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -70,6 +70,9 @@ typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
  * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
  * IRQ_NESTED_TRHEAD		- Interrupt nests into another thread
  * IRQ_PER_CPU_DEVID		- Dev_id is a per-cpu variable
+ * IRQ_IS_POLLED		- Always polled by another interrupt. Exclude
+ *				  it from the spurious interrupt detection
+ *				  mechanism and from core side polling.
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -94,12 +97,14 @@ enum {
 	IRQ_NESTED_THREAD	= (1 << 15),
 	IRQ_NOTHREAD		= (1 << 16),
 	IRQ_PER_CPU_DEVID	= (1 << 17),
+	IRQ_IS_POLLED		= (1 << 18),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
-	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID)
+	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
+	 IRQ_IS_POLLED)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 1162f1030f18..3320b84cc60f 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,6 +14,7 @@ enum {
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
 	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
+	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -26,6 +27,7 @@ enum {
 #define IRQ_NOAUTOEN		GOT_YOU_MORON
 #define IRQ_NESTED_THREAD	GOT_YOU_MORON
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
+#define IRQ_IS_POLLED		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -147,3 +149,8 @@ static inline bool irq_settings_is_nested_thread(struct irq_desc *desc)
 {
 	return desc->status_use_accessors & _IRQ_NESTED_THREAD;
 }
+
+static inline bool irq_settings_is_polled(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_IS_POLLED;
+}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7b5f012bde9d..a1d8cc63b56e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -67,8 +67,13 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 
 	raw_spin_lock(&desc->lock);
 
-	/* PER_CPU and nested thread interrupts are never polled */
-	if (irq_settings_is_per_cpu(desc) || irq_settings_is_nested_thread(desc))
+	/*
+	 * PER_CPU, nested thread interrupts and interrupts explicitely
+	 * marked polled are excluded from polling.
+	 */
+	if (irq_settings_is_per_cpu(desc) ||
+	    irq_settings_is_nested_thread(desc) ||
+	    irq_settings_is_polled(desc))
 		goto out;
 
 	/*
@@ -268,7 +273,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
-	if (desc->istate & IRQS_POLL_INPROGRESS)
+	if (desc->istate & IRQS_POLL_INPROGRESS ||
+	    irq_settings_is_polled(desc))
 		return;
 
 	/* we get here again via the threaded handler */
-- 
cgit 


From 54197e43a4a9a0f3fc406d72d9815754e84fab1e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 17 Sep 2013 18:53:05 +0000
Subject: hardirq: Make hardirq bits generic

There is no reason for per arch hardirq bits. Make them all generic

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20130917183628.534494408@linutronix.de
---
 arch/blackfin/include/asm/hardirq.h |  3 ---
 arch/cris/include/asm/hardirq.h     | 12 ------------
 arch/m32r/include/asm/hardirq.h     | 16 ----------------
 arch/m68k/include/asm/hardirq.h     | 11 -----------
 arch/s390/include/asm/hardirq.h     |  2 --
 arch/sparc/include/asm/hardirq_32.h |  1 -
 arch/sparc/include/asm/hardirq_64.h |  2 --
 arch/tile/include/asm/hardirq.h     |  2 --
 include/linux/preempt_mask.h        | 30 ++++++++----------------------
 9 files changed, 8 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/arch/blackfin/include/asm/hardirq.h b/arch/blackfin/include/asm/hardirq.h
index c078dd78d998..58b54a6d5a16 100644
--- a/arch/blackfin/include/asm/hardirq.h
+++ b/arch/blackfin/include/asm/hardirq.h
@@ -12,9 +12,6 @@
 extern void ack_bad_irq(unsigned int irq);
 #define ack_bad_irq ack_bad_irq
 
-/* Define until common code gets sane defaults */
-#define HARDIRQ_BITS 9
-
 #include <asm-generic/hardirq.h>
 
 #endif
diff --git a/arch/cris/include/asm/hardirq.h b/arch/cris/include/asm/hardirq.h
index 17bb12d760b2..04126f7bfab2 100644
--- a/arch/cris/include/asm/hardirq.h
+++ b/arch/cris/include/asm/hardirq.h
@@ -2,18 +2,6 @@
 #define __ASM_HARDIRQ_H
 
 #include <asm/irq.h>
-
-#define HARDIRQ_BITS	8
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #include <asm-generic/hardirq.h>
 
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/m32r/include/asm/hardirq.h b/arch/m32r/include/asm/hardirq.h
index 4c31c0ae215e..5f2ac4f64ddf 100644
--- a/arch/m32r/include/asm/hardirq.h
+++ b/arch/m32r/include/asm/hardirq.h
@@ -3,22 +3,6 @@
 #define __ASM_HARDIRQ_H
 
 #include <asm/irq.h>
-
-#if NR_IRQS > 256
-#define HARDIRQ_BITS	9
-#else
-#define HARDIRQ_BITS	8
-#endif
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #include <asm-generic/hardirq.h>
 
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/m68k/include/asm/hardirq.h b/arch/m68k/include/asm/hardirq.h
index db30ed276878..6c618529d9b9 100644
--- a/arch/m68k/include/asm/hardirq.h
+++ b/arch/m68k/include/asm/hardirq.h
@@ -5,17 +5,6 @@
 #include <linux/cache.h>
 #include <asm/irq.h>
 
-#define HARDIRQ_BITS	8
-
-/*
- * The hardirq mask has to be large enough to have
- * space for potentially all IRQ sources in the system
- * nesting on a single CPU:
- */
-#if (1 << HARDIRQ_BITS) < NR_IRQS
-# error HARDIRQ_BITS is too low!
-#endif
-
 #ifdef CONFIG_MMU
 
 static inline void ack_bad_irq(unsigned int irq)
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index a908d2941c5d..b7eabaaeffbd 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -18,8 +18,6 @@
 #define __ARCH_HAS_DO_SOFTIRQ
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED
 
-#define HARDIRQ_BITS	8
-
 static inline void ack_bad_irq(unsigned int irq)
 {
 	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
diff --git a/arch/sparc/include/asm/hardirq_32.h b/arch/sparc/include/asm/hardirq_32.h
index 162007643cdc..ee93923b7f82 100644
--- a/arch/sparc/include/asm/hardirq_32.h
+++ b/arch/sparc/include/asm/hardirq_32.h
@@ -7,7 +7,6 @@
 #ifndef __SPARC_HARDIRQ_H
 #define __SPARC_HARDIRQ_H
 
-#define HARDIRQ_BITS    8
 #include <asm-generic/hardirq.h>
 
 #endif /* __SPARC_HARDIRQ_H */
diff --git a/arch/sparc/include/asm/hardirq_64.h b/arch/sparc/include/asm/hardirq_64.h
index 7c29fd1a87aa..f478ff1ddd02 100644
--- a/arch/sparc/include/asm/hardirq_64.h
+++ b/arch/sparc/include/asm/hardirq_64.h
@@ -14,6 +14,4 @@
 
 void ack_bad_irq(unsigned int irq);
 
-#define HARDIRQ_BITS	8
-
 #endif /* !(__SPARC64_HARDIRQ_H) */
diff --git a/arch/tile/include/asm/hardirq.h b/arch/tile/include/asm/hardirq.h
index 822390f9a154..54110af23985 100644
--- a/arch/tile/include/asm/hardirq.h
+++ b/arch/tile/include/asm/hardirq.h
@@ -42,6 +42,4 @@ DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#define HARDIRQ_BITS	8
-
 #endif /* _ASM_TILE_HARDIRQ_H */
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index 931bc616219f..810d7e386f20 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -11,36 +11,22 @@
  * - bits 0-7 are the preemption count (max preemption depth: 256)
  * - bits 8-15 are the softirq count (max # of softirqs: 256)
  *
- * The hardirq count can in theory reach the same as NR_IRQS.
- * In reality, the number of nested IRQS is limited to the stack
- * size as well. For archs with over 1000 IRQS it is not practical
- * to expect that they will all nest. We give a max of 10 bits for
- * hardirq nesting. An arch may choose to give less than 10 bits.
- * m68k expects it to be 8.
- *
- * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
- * - bit 26 is the NMI_MASK
- * - bit 27 is the PREEMPT_ACTIVE flag
+ * The hardirq count could in theory be the same as the number of
+ * interrupts in the system, but we run all interrupt handlers with
+ * interrupts disabled, so we cannot have nesting interrupts. Though
+ * there are a few palaeontologic drivers which reenable interrupts in
+ * the handler, so we need more than one bit here.
  *
  * PREEMPT_MASK: 0x000000ff
  * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x03ff0000
- *     NMI_MASK: 0x04000000
+ * HARDIRQ_MASK: 0x000f0000
+ *     NMI_MASK: 0x00100000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
+#define HARDIRQ_BITS	4
 #define NMI_BITS	1
 
-#define MAX_HARDIRQ_BITS 10
-
-#ifndef HARDIRQ_BITS
-# define HARDIRQ_BITS	MAX_HARDIRQ_BITS
-#endif
-
-#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
-#error HARDIRQ_BITS too high!
-#endif
-
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
 #define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
-- 
cgit 


From 00d1a39e69d5afa7523dad515a05b21abd17c389 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 17 Sep 2013 18:53:09 +0000
Subject: preempt: Make PREEMPT_ACTIVE generic

No point in having this bit defined by architecture.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20130917183629.090698799@linutronix.de
---
 arch/alpha/include/asm/thread_info.h      |  2 --
 arch/arc/include/asm/thread_info.h        |  2 --
 arch/arm/include/asm/thread_info.h        |  6 ------
 arch/arm64/include/asm/thread_info.h      |  6 ------
 arch/avr32/include/asm/thread_info.h      |  2 --
 arch/blackfin/include/asm/thread_info.h   |  2 --
 arch/c6x/include/asm/thread_info.h        |  2 --
 arch/cris/include/asm/thread_info.h       |  2 --
 arch/frv/include/asm/thread_info.h        |  2 --
 arch/hexagon/include/asm/thread_info.h    |  4 ----
 arch/ia64/include/asm/thread_info.h       |  3 ---
 arch/m32r/include/asm/thread_info.h       |  2 --
 arch/m68k/include/asm/thread_info.h       |  2 --
 arch/metag/include/asm/thread_info.h      |  2 --
 arch/microblaze/include/asm/thread_info.h |  2 --
 arch/mips/include/asm/thread_info.h       |  2 --
 arch/mn10300/include/asm/thread_info.h    |  2 --
 arch/parisc/include/asm/thread_info.h     |  3 ---
 arch/powerpc/include/asm/thread_info.h    |  2 --
 arch/s390/include/asm/thread_info.h       |  2 --
 arch/score/include/asm/thread_info.h      |  2 --
 arch/sh/include/asm/thread_info.h         |  2 --
 arch/sh/kernel/entry-common.S             |  6 ++----
 arch/sparc/include/asm/thread_info_32.h   |  2 --
 arch/sparc/include/asm/thread_info_64.h   |  2 --
 arch/tile/include/asm/thread_info.h       |  2 --
 arch/um/include/asm/thread_info.h         |  2 --
 arch/unicore32/include/asm/thread_info.h  |  6 ------
 arch/x86/include/asm/thread_info.h        |  2 --
 arch/xtensa/include/asm/thread_info.h     |  2 --
 include/linux/preempt_mask.h              | 15 +++++----------
 include/linux/sched.h                     |  2 +-
 32 files changed, 8 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 52cd2a4a3ff4..453597b91f3a 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -58,8 +58,6 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define THREAD_SIZE_ORDER 1
 #define THREAD_SIZE (2*PAGE_SIZE)
 
-#define PREEMPT_ACTIVE		0x40000000
-
 /*
  * Thread information flags:
  * - these are process state flags and used from assembly
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 2d50a4cdd7f3..45be21672011 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -80,8 +80,6 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
 
 #endif /* !__ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE      0x10000000
-
 /*
  * thread information flags
  * - these are process state flags that various assembly files may need to
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index df5e13d64f2c..71a06b293489 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -140,12 +140,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 				    struct user_vfp_exc __user *);
 #endif
 
-/*
- * We use bit 30 of the preempt_count to indicate that kernel
- * preemption is occurring.  See <asm/hardirq.h>.
- */
-#define PREEMPT_ACTIVE	0x40000000
-
 /*
  * thread information flags:
  *  TIF_SYSCALL_TRACE	- syscall trace active
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 23a3c4791d86..720e70b66ffd 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -88,12 +88,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif
 
-/*
- * We use bit 30 of the preempt_count to indicate that kernel
- * preemption is occurring.  See <asm/hardirq.h>.
- */
-#define PREEMPT_ACTIVE	0x40000000
-
 /*
  * thread information flags:
  *  TIF_SYSCALL_TRACE	- syscall trace active
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
index 6dc62e1f94c7..a978f3fe7c25 100644
--- a/arch/avr32/include/asm/thread_info.h
+++ b/arch/avr32/include/asm/thread_info.h
@@ -66,8 +66,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif /* !__ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x40000000
-
 /*
  * Thread information flags
  * - these are process state flags that various assembly files may need to access
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 3894005337ba..55f473bdad36 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -88,8 +88,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TI_CPU		12
 #define TI_PREEMPT	16
 
-#define	PREEMPT_ACTIVE	0x4000000
-
 /*
  * thread information flag bit numbers
  */
diff --git a/arch/c6x/include/asm/thread_info.h b/arch/c6x/include/asm/thread_info.h
index 4c8dc562bd90..d4e9ef87076d 100644
--- a/arch/c6x/include/asm/thread_info.h
+++ b/arch/c6x/include/asm/thread_info.h
@@ -84,8 +84,6 @@ struct thread_info *current_thread_info(void)
 #define put_thread_info(ti)	put_task_struct((ti)->task)
 #endif /* __ASSEMBLY__ */
 
-#define	PREEMPT_ACTIVE	0x10000000
-
 /*
  * thread information flag bit numbers
  * - pending work-to-be-done flags are in LSW
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index 07c8c40c52b3..55dede18c032 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -44,8 +44,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * macros/functions for gaining access to the thread information structure
  */
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index bebd7eadc772..af29e17c0181 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -52,8 +52,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * macros/functions for gaining access to the thread information structure
  */
diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h
index f7c32406a711..a59dad3b3695 100644
--- a/arch/hexagon/include/asm/thread_info.h
+++ b/arch/hexagon/include/asm/thread_info.h
@@ -73,10 +73,6 @@ struct thread_info {
 
 #endif  /* __ASSEMBLY__  */
 
-/*  looks like "linux/hardirq.h" uses this.  */
-
-#define PREEMPT_ACTIVE		0x10000000
-
 #ifndef __ASSEMBLY__
 
 #define INIT_THREAD_INFO(tsk)                   \
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index cade13dd0299..5957cf61f898 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -11,9 +11,6 @@
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 
-#define PREEMPT_ACTIVE_BIT 30
-#define PREEMPT_ACTIVE	(1 << PREEMPT_ACTIVE_BIT)
-
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index c074f4c2e858..00171703402f 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -53,8 +53,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #define THREAD_SIZE		(PAGE_SIZE << 1)
 #define THREAD_SIZE_ORDER	1
 /*
diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h
index 126131f94a2c..21a4784ca5a1 100644
--- a/arch/m68k/include/asm/thread_info.h
+++ b/arch/m68k/include/asm/thread_info.h
@@ -35,8 +35,6 @@ struct thread_info {
 };
 #endif /* __ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x4000000
-
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,			\
diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h
index 7c4a33006142..b19e9c588a16 100644
--- a/arch/metag/include/asm/thread_info.h
+++ b/arch/metag/include/asm/thread_info.h
@@ -46,8 +46,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #ifdef CONFIG_4KSTACKS
 #define THREAD_SHIFT		12
 #else
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index de26ea6373de..8c9d36591a03 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -106,8 +106,6 @@ static inline struct thread_info *current_thread_info(void)
 /* thread information allocation */
 #endif /* __ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * thread information flags
  * - these are process state flags that various assembly files may
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index f9b24bfbdbae..4f58ef6d0eed 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -92,8 +92,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #define STACK_WARN	(THREAD_SIZE / 8)
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * thread information flags
  * - these are process state flags that various assembly files may need to
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 224b4262486d..bf280eaccd36 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -16,8 +16,6 @@
 
 #include <asm/page.h>
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #ifdef CONFIG_4KSTACKS
 #define THREAD_SIZE		(4096)
 #define THREAD_SIZE_ORDER	(0)
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index bc7cf120106b..d5f97ea3a4e1 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -46,9 +46,6 @@ struct thread_info {
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
 
-#define PREEMPT_ACTIVE_BIT	28
-#define PREEMPT_ACTIVE		(1 << PREEMPT_ACTIVE_BIT)
-
 /*
  * thread information flags
  */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index ba7b1973866e..8fd6cf6dcee8 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -82,8 +82,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif /* __ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * thread information flag bit numbers
  */
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index eb5f64d26d06..10e0fcd3633d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -111,6 +111,4 @@ static inline struct thread_info *current_thread_info(void)
 #define is_32bit_task()		(1)
 #endif
 
-#define PREEMPT_ACTIVE		0x4000000
-
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/score/include/asm/thread_info.h b/arch/score/include/asm/thread_info.h
index 1425cc034872..656b7ada9326 100644
--- a/arch/score/include/asm/thread_info.h
+++ b/arch/score/include/asm/thread_info.h
@@ -72,8 +72,6 @@ register struct thread_info *__current_thread_info __asm__("r28");
 
 #endif /* !__ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * thread information flags
  * - these are process state flags that various assembly files may need to
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index 45a93669289d..ad27ffa65e2e 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -41,8 +41,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #if defined(CONFIG_4KSTACKS)
 #define THREAD_SHIFT	12
 #else
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 9b6e4beeb296..ca46834294b7 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -108,7 +108,7 @@ need_resched:
 	and	#(0xf0>>1), r0		! interrupts off (exception path)?
 	cmp/eq	#(0xf0>>1), r0
 	bt	noresched
-	mov.l	3f, r0
+	mov.l	1f, r0
 	jsr	@r0			! call preempt_schedule_irq
 	 nop
 	bra	need_resched
@@ -119,9 +119,7 @@ noresched:
 	 nop
 
 	.align 2
-1:	.long	PREEMPT_ACTIVE
-2:	.long	schedule
-3:	.long	preempt_schedule_irq
+1:	.long	preempt_schedule_irq
 #endif
 
 ENTRY(resume_userspace)
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index dd3807599bb9..96efa7adc223 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -105,8 +105,6 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TI_W_SAVED	0x250
 /* #define TI_RESTART_BLOCK 0x25n */ /* Nobody cares */
 
-#define PREEMPT_ACTIVE		0x4000000
-
 /*
  * thread information flag bit numbers
  */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index d5e504251079..2b4e17b79e9c 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -111,8 +111,6 @@ struct thread_info {
 #define THREAD_SHIFT PAGE_SHIFT
 #endif /* PAGE_SHIFT == 13 */
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * macros/functions for gaining access to the thread information structure
  */
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index b8aa6df3e102..729aa107f64e 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -113,8 +113,6 @@ extern void _cpu_idle(void);
 
 #endif /* !__ASSEMBLY__ */
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * Thread information flags that various assembly files may need to access.
  * Keep flags accessed frequently in low bits, particular since it makes
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 2c8eeb2df8b4..1c5b2a83046a 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -60,8 +60,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
diff --git a/arch/unicore32/include/asm/thread_info.h b/arch/unicore32/include/asm/thread_info.h
index 818b4a1edb5b..af36d8eabdf1 100644
--- a/arch/unicore32/include/asm/thread_info.h
+++ b/arch/unicore32/include/asm/thread_info.h
@@ -117,12 +117,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif
 
-/*
- * We use bit 30 of the preempt_count to indicate that kernel
- * preemption is occurring.  See <asm/hardirq.h>.
- */
-#define PREEMPT_ACTIVE	0x40000000
-
 /*
  * thread information flags:
  *  TIF_SYSCALL_TRACE	- syscall trace active
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c46a46be1ec6..3ba3de457d05 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -153,8 +153,6 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #ifdef CONFIG_X86_32
 
 #define STACK_WARN	(THREAD_SIZE/8)
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 9481004ac119..470153e8547c 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -76,8 +76,6 @@ struct thread_info {
 
 #endif
 
-#define PREEMPT_ACTIVE		0x10000000
-
 /*
  * macros/functions for gaining access to the thread information structure
  */
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index 810d7e386f20..d169820203dd 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -17,10 +17,11 @@
  * there are a few palaeontologic drivers which reenable interrupts in
  * the handler, so we need more than one bit here.
  *
- * PREEMPT_MASK: 0x000000ff
- * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x000f0000
- *     NMI_MASK: 0x00100000
+ * PREEMPT_MASK:	0x000000ff
+ * SOFTIRQ_MASK:	0x0000ff00
+ * HARDIRQ_MASK:	0x000f0000
+ *     NMI_MASK:	0x00100000
+ * PREEMPT_ACTIVE:	0x00200000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
@@ -46,15 +47,9 @@
 
 #define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
 
-#ifndef PREEMPT_ACTIVE
 #define PREEMPT_ACTIVE_BITS	1
 #define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
 #define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-#endif
-
-#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
-#error PREEMPT_ACTIVE is too low!
-#endif
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 045b0d227846..55080df48b70 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -22,7 +22,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt.h>
+#include <linux/preempt_mask.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
-- 
cgit 


From d38a8c622a1b382336c3e152c6caf4e11d1f1b2a Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 18 Oct 2013 19:35:23 +0200
Subject: dmaengine: prepare for generic 'unmap' data

Add a hook for a common dma unmap implementation to enable removal of
the per driver custom unmap code.  (A reworked version of Bartlomiej
Zolnierkiewicz's patches to remove the custom callbacks and the size
increase of dma_async_tx_descriptor for drivers that don't care about
raid).

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
[bzolnier: prepare pl330 driver for adding missing unmap while at it]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dma/amba-pl08x.c  |  1 +
 drivers/dma/at_hdmac.c    |  1 +
 drivers/dma/dw/core.c     |  1 +
 drivers/dma/ep93xx_dma.c  |  1 +
 drivers/dma/fsldma.c      |  1 +
 drivers/dma/ioat/dma.c    |  1 +
 drivers/dma/ioat/dma_v2.c |  1 +
 drivers/dma/ioat/dma_v3.c |  1 +
 drivers/dma/iop-adma.c    |  1 +
 drivers/dma/mv_xor.c      |  1 +
 drivers/dma/pl330.c       |  2 ++
 drivers/dma/ppc4xx/adma.c |  1 +
 drivers/dma/timb_dma.c    |  1 +
 drivers/dma/txx9dmac.c    |  1 +
 include/linux/dmaengine.h | 26 ++++++++++++++++++++++++++
 15 files changed, 41 insertions(+)

(limited to 'include')

diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index fce46c5bf1c7..7f9846464b77 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1197,6 +1197,7 @@ static void pl08x_desc_free(struct virt_dma_desc *vd)
 	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(vd->tx.chan);
 
+	dma_descriptor_unmap(txd);
 	if (!plchan->slave)
 		pl08x_unmap_buffers(txd);
 
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c787f38a186a..cc7098ddf9d4 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -345,6 +345,7 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	list_move(&desc->desc_node, &atchan->free_list);
 
 	/* unmap dma addresses (not on slave channels) */
+	dma_descriptor_unmap(txd);
 	if (!atchan->chan_common.private) {
 		struct device *parent = chan2parent(&atchan->chan_common);
 		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 89eb89f22284..e3fe1b1a73b1 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -311,6 +311,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
+	dma_descriptor_unmap(txd);
 	if (!is_slave_direction(dwc->direction)) {
 		struct device *parent = chan2parent(&dwc->chan);
 		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 591cd8c63abb..dcd6bf5d3091 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -791,6 +791,7 @@ static void ep93xx_dma_tasklet(unsigned long data)
 		 * For the memcpy channels the API requires us to unmap the
 		 * buffers unless requested otherwise.
 		 */
+		dma_descriptor_unmap(&desc->txd);
 		if (!edmac->chan.private)
 			ep93xx_dma_unmap_buffers(desc);
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index b3f3e90054f2..66c4052a1f34 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -868,6 +868,7 @@ static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
 	/* Run any dependencies */
 	dma_run_dependencies(txd);
 
+	dma_descriptor_unmap(txd);
 	/* Unmap the dst buffer, if requested */
 	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
 		if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 5ff6fc1819dc..26f8cfd6bc3f 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -602,6 +602,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, dma_addr_t phys_complete)
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
 			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
 			ioat->active -= desc->hw->tx_cnt;
 			if (tx->callback) {
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b1d139..fc7b50a813cc 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -148,6 +148,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
 		tx = &desc->txd;
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
+			dma_descriptor_unmap(tx);
 			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
 			dma_cookie_complete(tx);
 			if (tx->callback) {
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index d8ececaf1b57..57a2901b917a 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -577,6 +577,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
 		tx = &desc->txd;
 		if (tx->cookie) {
 			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
 			ioat3_dma_unmap(ioat, desc, idx + i);
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index dd8b44a56e5d..8f6e426590eb 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -152,6 +152,7 @@ iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 		if (tx->callback)
 			tx->callback(tx->callback_param);
 
+		dma_descriptor_unmap(tx);
 		/* unmap dma addresses
 		 * (unmap_single vs unmap_page?)
 		 */
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 536dcb8ba5fd..ed1ab1d0875e 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -278,6 +278,7 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 			desc->async_tx.callback(
 				desc->async_tx.callback_param);
 
+		dma_descriptor_unmap(&desc->async_tx);
 		/* unmap dma addresses
 		 * (unmap_single vs unmap_page?)
 		 */
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index a562d24d20bf..ab25e52cd43b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2268,6 +2268,8 @@ static void pl330_tasklet(unsigned long data)
 			list_move_tail(&desc->node, &pch->dmac->desc_pool);
 		}
 
+		dma_descriptor_unmap(&desc->txd);
+
 		if (callback) {
 			spin_unlock_irqrestore(&pch->lock, flags);
 			callback(callback_param);
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 370ff8265630..442492da7415 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -1765,6 +1765,7 @@ static dma_cookie_t ppc440spe_adma_run_tx_complete_actions(
 			desc->async_tx.callback(
 				desc->async_tx.callback_param);
 
+		dma_descriptor_unmap(&desc->async_tx);
 		/* unmap dma addresses
 		 * (unmap_single vs unmap_page?)
 		 *
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 28af214fce04..1d0c98839087 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -293,6 +293,7 @@ static void __td_finish(struct timb_dma_chan *td_chan)
 
 	list_move(&td_desc->desc_node, &td_chan->free_list);
 
+	dma_descriptor_unmap(txd);
 	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
 		__td_unmap_descs(td_desc,
 			txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 71e8e775189e..22a0b6c78c77 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -419,6 +419,7 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 	list_splice_init(&desc->tx_list, &dc->free_list);
 	list_move(&desc->desc_node, &dc->free_list);
 
+	dma_descriptor_unmap(txd);
 	if (!ds) {
 		dma_addr_t dmaaddr;
 		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 0bc727534108..9070050fbcd8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -413,6 +413,17 @@ void dma_chan_cleanup(struct kref *kref);
 typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
 
 typedef void (*dma_async_tx_callback)(void *dma_async_param);
+
+struct dmaengine_unmap_data {
+	u8 to_cnt;
+	u8 from_cnt;
+	u8 bidi_cnt;
+	struct device *dev;
+	struct kref kref;
+	size_t len;
+	dma_addr_t addr[0];
+};
+
 /**
  * struct dma_async_tx_descriptor - async transaction descriptor
  * ---dma generic offload fields---
@@ -438,6 +449,7 @@ struct dma_async_tx_descriptor {
 	dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx);
 	dma_async_tx_callback callback;
 	void *callback_param;
+	struct dmaengine_unmap_data *unmap;
 #ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	struct dma_async_tx_descriptor *next;
 	struct dma_async_tx_descriptor *parent;
@@ -445,6 +457,20 @@ struct dma_async_tx_descriptor {
 #endif
 };
 
+static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
+				 struct dmaengine_unmap_data *unmap)
+{
+	kref_get(&unmap->kref);
+	tx->unmap = unmap;
+}
+
+static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx)
+{
+	if (tx->unmap) {
+		tx->unmap = NULL;
+	}
+}
+
 #ifndef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH
 static inline void txd_lock(struct dma_async_tx_descriptor *txd)
 {
-- 
cgit 


From 45c463ae924c62af4aa64ded1ca831f334a1db65 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 18 Oct 2013 19:35:24 +0200
Subject: dmaengine: reference counted unmap data

Hang a common 'unmap' object off of dma descriptors for the purpose of
providing a unified unmapping interface.  The lifetime of a mapping may
span multiple descriptors, so these unmap objects are reference counted
by related descriptor.

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
[bzolnier: fix IS_ENABLED() check]
[bzolnier: fix release ordering in dmaengine_destroy_unmap_pool()]
[bzolnier: fix check for success in dmaengine_init_unmap_pool()]
[bzolnier: use mempool_free() instead of kmem_cache_free()]
[bzolnier: add missing unmap->len initializations]
[bzolnier: add __init tag to dmaengine_init_unmap_pool()]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
[djbw: move DMAENGINE=n support to this patch for async_tx]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dma/dmaengine.c   | 156 +++++++++++++++++++++++++++++++++++++++++++---
 include/linux/dmaengine.h |   3 +
 2 files changed, 150 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index bbc89df6bc56..e721a1caff7f 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -65,6 +65,7 @@
 #include <linux/acpi.h>
 #include <linux/acpi_dma.h>
 #include <linux/of_dma.h>
+#include <linux/mempool.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDR(dma_idr);
@@ -901,6 +902,129 @@ void dma_async_device_unregister(struct dma_device *device)
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
+struct dmaengine_unmap_pool {
+	struct kmem_cache *cache;
+	const char *name;
+	mempool_t *pool;
+	size_t size;
+};
+
+#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
+static struct dmaengine_unmap_pool unmap_pool[] = {
+	__UNMAP_POOL(2),
+	#if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
+	__UNMAP_POOL(16),
+	__UNMAP_POOL(128),
+	__UNMAP_POOL(256),
+	#endif
+};
+
+static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
+{
+	int order = get_count_order(nr);
+
+	switch (order) {
+	case 0 ... 1:
+		return &unmap_pool[0];
+	case 2 ... 4:
+		return &unmap_pool[1];
+	case 5 ... 7:
+		return &unmap_pool[2];
+	case 8:
+		return &unmap_pool[3];
+	default:
+		BUG();
+		return NULL;
+	}
+}
+
+static void dmaengine_unmap(struct kref *kref)
+{
+	struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref);
+	struct device *dev = unmap->dev;
+	int cnt, i;
+
+	cnt = unmap->to_cnt;
+	for (i = 0; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_TO_DEVICE);
+	cnt += unmap->from_cnt;
+	for (; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_FROM_DEVICE);
+	cnt += unmap->bidi_cnt;
+	for (; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_BIDIRECTIONAL);
+	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
+}
+
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
+{
+	if (unmap)
+		kref_put(&unmap->kref, dmaengine_unmap);
+}
+EXPORT_SYMBOL_GPL(dmaengine_unmap_put);
+
+static void dmaengine_destroy_unmap_pool(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+		struct dmaengine_unmap_pool *p = &unmap_pool[i];
+
+		if (p->pool)
+			mempool_destroy(p->pool);
+		p->pool = NULL;
+		if (p->cache)
+			kmem_cache_destroy(p->cache);
+		p->cache = NULL;
+	}
+}
+
+static int __init dmaengine_init_unmap_pool(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+		struct dmaengine_unmap_pool *p = &unmap_pool[i];
+		size_t size;
+
+		size = sizeof(struct dmaengine_unmap_data) +
+		       sizeof(dma_addr_t) * p->size;
+
+		p->cache = kmem_cache_create(p->name, size, 0,
+					     SLAB_HWCACHE_ALIGN, NULL);
+		if (!p->cache)
+			break;
+		p->pool = mempool_create_slab_pool(1, p->cache);
+		if (!p->pool)
+			break;
+	}
+
+	if (i == ARRAY_SIZE(unmap_pool))
+		return 0;
+
+	dmaengine_destroy_unmap_pool();
+	return -ENOMEM;
+}
+
+static struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+{
+	struct dmaengine_unmap_data *unmap;
+
+	unmap = mempool_alloc(__get_unmap_pool(nr)->pool, flags);
+	if (!unmap)
+		return NULL;
+
+	memset(unmap, 0, sizeof(*unmap));
+	kref_init(&unmap->kref);
+	unmap->dev = dev;
+
+	return unmap;
+}
+
 /**
  * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
  * @chan: DMA channel to offload copy to
@@ -922,24 +1046,34 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 {
 	struct dma_device *dev = chan->device;
 	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
+	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	unsigned long flags;
 
-	dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
-	dma_dest = dma_map_page(dev->dev, dest_pg, dest_off, len,
-				DMA_FROM_DEVICE);
-	flags = DMA_CTRL_ACK;
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO);
+	if (!unmap)
+		return -ENOMEM;
+
+	unmap->to_cnt = 1;
+	unmap->from_cnt = 1;
+	unmap->addr[0] = dma_map_page(dev->dev, src_pg, src_off, len,
+				      DMA_TO_DEVICE);
+	unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
+				      DMA_FROM_DEVICE);
+	unmap->len = len;
+	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_SRC_UNMAP |
+		DMA_COMPL_SKIP_DEST_UNMAP;
+	tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
+					 len, flags);
 
 	if (!tx) {
-		dma_unmap_page(dev->dev, dma_src, len, DMA_TO_DEVICE);
-		dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
+		dmaengine_unmap_put(unmap);
 		return -ENOMEM;
 	}
 
-	tx->callback = NULL;
+	dma_set_unmap(tx, unmap);
 	cookie = tx->tx_submit(tx);
+	dmaengine_unmap_put(unmap);
 
 	preempt_disable();
 	__this_cpu_add(chan->local->bytes_transferred, len);
@@ -1069,6 +1203,10 @@ EXPORT_SYMBOL_GPL(dma_run_dependencies);
 
 static int __init dma_bus_init(void)
 {
+	int err = dmaengine_init_unmap_pool();
+
+	if (err)
+		return err;
 	return class_register(&dma_devclass);
 }
 arch_initcall(dma_bus_init);
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 9070050fbcd8..2fe855a7cab1 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -464,9 +464,12 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
 	tx->unmap = unmap;
 }
 
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap);
+
 static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx)
 {
 	if (tx->unmap) {
+		dmaengine_unmap_put(tx->unmap);
 		tx->unmap = NULL;
 	}
 }
-- 
cgit 


From ee480683d975973e3ff679850871e00e011c4a96 Mon Sep 17 00:00:00 2001
From: Nicholas Bellinger <nab@linux-iscsi.org>
Date: Wed, 13 Nov 2013 18:34:55 -0800
Subject: target: Convert se_device statistics to atomic_long_t

This patch converts the handful of se_device statistics to type
atomic_long_t, instead of using se_device->stats_lock when
incrementing these values.

More importantly, go ahead and drop the spinlock usage within
transport_lookup_cmd_lun() fast-path code.

Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_device.c | 10 +++-------
 drivers/target/target_core_stat.c   | 15 +++++++++------
 drivers/target/target_core_tmr.c    |  4 +---
 include/target/target_core_base.h   |  9 ++++-----
 4 files changed, 17 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index dbe40ef14776..986afd2ee3f6 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -130,15 +130,12 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u32 unpacked_lun)
 	/* Directly associate cmd with se_dev */
 	se_cmd->se_dev = se_lun->lun_se_dev;
 
-	/* TODO: get rid of this and use atomics for stats */
 	dev = se_lun->lun_se_dev;
-	spin_lock_irqsave(&dev->stats_lock, flags);
-	dev->num_cmds++;
+	atomic_long_inc(&dev->num_cmds);
 	if (se_cmd->data_direction == DMA_TO_DEVICE)
-		dev->write_bytes += se_cmd->data_length;
+		atomic_long_add(se_cmd->data_length, &dev->write_bytes);
 	else if (se_cmd->data_direction == DMA_FROM_DEVICE)
-		dev->read_bytes += se_cmd->data_length;
-	spin_unlock_irqrestore(&dev->stats_lock, flags);
+		atomic_long_add(se_cmd->data_length, &dev->read_bytes);
 
 	return 0;
 }
@@ -1426,7 +1423,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	INIT_LIST_HEAD(&dev->state_list);
 	INIT_LIST_HEAD(&dev->qf_cmd_list);
 	INIT_LIST_HEAD(&dev->g_dev_node);
-	spin_lock_init(&dev->stats_lock);
 	spin_lock_init(&dev->execute_task_lock);
 	spin_lock_init(&dev->delayed_cmd_lock);
 	spin_lock_init(&dev->dev_reservation_lock);
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 632665c026a8..03538994d2f7 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -213,7 +213,8 @@ static ssize_t target_stat_scsi_tgt_dev_show_attr_resets(
 	struct se_device *dev =
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
-	return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&dev->num_resets));
 }
 DEV_STAT_SCSI_TGT_DEV_ATTR_RO(resets);
 
@@ -396,8 +397,8 @@ static ssize_t target_stat_scsi_lu_show_attr_num_cmds(
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuNumCommands */
-	return snprintf(page, PAGE_SIZE, "%llu\n",
-			(unsigned long long)dev->num_cmds);
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&dev->num_cmds));
 }
 DEV_STAT_SCSI_LU_ATTR_RO(num_cmds);
 
@@ -408,7 +409,8 @@ static ssize_t target_stat_scsi_lu_show_attr_read_mbytes(
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuReadMegaBytes */
-	return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->read_bytes >> 20));
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&dev->read_bytes) >> 20);
 }
 DEV_STAT_SCSI_LU_ATTR_RO(read_mbytes);
 
@@ -419,7 +421,8 @@ static ssize_t target_stat_scsi_lu_show_attr_write_mbytes(
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuWrittenMegaBytes */
-	return snprintf(page, PAGE_SIZE, "%u\n", (u32)(dev->write_bytes >> 20));
+	return snprintf(page, PAGE_SIZE, "%lu\n",
+			atomic_long_read(&dev->write_bytes) >> 20);
 }
 DEV_STAT_SCSI_LU_ATTR_RO(write_mbytes);
 
@@ -430,7 +433,7 @@ static ssize_t target_stat_scsi_lu_show_attr_resets(
 		container_of(sgrps, struct se_device, dev_stat_grps);
 
 	/* scsiLuInResets */
-	return snprintf(page, PAGE_SIZE, "%u\n", dev->num_resets);
+	return snprintf(page, PAGE_SIZE, "%lu\n", atomic_long_read(&dev->num_resets));
 }
 DEV_STAT_SCSI_LU_ATTR_RO(resets);
 
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 250009909d49..70c638f730af 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -386,9 +386,7 @@ int core_tmr_lun_reset(
 		pr_debug("LUN_RESET: SCSI-2 Released reservation\n");
 	}
 
-	spin_lock_irq(&dev->stats_lock);
-	dev->num_resets++;
-	spin_unlock_irq(&dev->stats_lock);
+	atomic_long_inc(&dev->num_resets);
 
 	pr_debug("LUN_RESET: %s for [%s] Complete\n",
 			(preempt_and_abort_list) ? "Preempt" : "TMR",
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 96bf1b0239cc..fab91baf8ef4 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -683,11 +683,10 @@ struct se_device {
 	/* Pointer to transport specific device structure */
 	u32			dev_index;
 	u64			creation_time;
-	u32			num_resets;
-	u64			num_cmds;
-	u64			read_bytes;
-	u64			write_bytes;
-	spinlock_t		stats_lock;
+	atomic_long_t		num_resets;
+	atomic_long_t		num_cmds;
+	atomic_long_t		read_bytes;
+	atomic_long_t		write_bytes;
 	/* Active commands on this virtual SE device */
 	atomic_t		simple_cmds;
 	atomic_t		dev_ordered_id;
-- 
cgit 


From 82e06c811163c4d853ed335d56c3378088bc89cc Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@kernel.org>
Date: Thu, 14 Nov 2013 15:16:16 +1100
Subject: wait: add wait_event_cmd()

Add a new API wait_event_cmd(). It's a variant of wait_even() with two
commands executed. One is executed before sleep, another after sleep.

Modified to match use wait.h approach based on suggestion by
Peter Zijlstra <peterz@infradead.org> - neilb

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 include/linux/wait.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 61939ba30aa0..eaa00b10abaa 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -278,6 +278,31 @@ do {									\
 	__ret;								\
 })
 
+#define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
+	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
+			    cmd1; schedule(); cmd2)
+
+/**
+ * wait_event_cmd - sleep until a condition gets true
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * cmd1: the command will be executed before sleep
+ * cmd2: the command will be executed after sleep
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ */
+#define wait_event_cmd(wq, condition, cmd1, cmd2)			\
+do {									\
+	if (condition)							\
+		break;							\
+	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
+} while (0)
+
 #define __wait_event_interruptible(wq, condition)			\
 	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
 		      schedule())
-- 
cgit 


From f7625980f5820edd1a73536e1a03bcbc1f889fec Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 14 Nov 2013 11:28:18 -0700
Subject: PCI: Fix whitespace, capitalization, and spelling errors

Fix whitespace, capitalization, and spelling errors.  No functional change.
I know "busses" is not an error, but "buses" was more common, so I used it
consistently.

Signed-off-by: Marta Rybczynska <rybczynska@gmail.com> (pci_reset_bridge_secondary_bus())
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pci/ats.c                       |   2 +-
 drivers/pci/host/pci-tegra.c            |  12 ++--
 drivers/pci/host/pcie-designware.c      |   2 +-
 drivers/pci/hotplug/Kconfig             |   4 +-
 drivers/pci/hotplug/Makefile            |   2 +-
 drivers/pci/hotplug/acpiphp_core.c      |  12 ++--
 drivers/pci/hotplug/acpiphp_glue.c      |   2 +-
 drivers/pci/hotplug/acpiphp_ibm.c       |  14 ++--
 drivers/pci/hotplug/cpci_hotplug_core.c |   2 +-
 drivers/pci/hotplug/cpci_hotplug_pci.c  |   2 +-
 drivers/pci/hotplug/cpcihp_generic.c    |  20 +++---
 drivers/pci/hotplug/cpcihp_zt5550.c     |  22 +++----
 drivers/pci/hotplug/cpcihp_zt5550.h     |  18 +++---
 drivers/pci/hotplug/cpqphp_core.c       |   4 +-
 drivers/pci/hotplug/cpqphp_ctrl.c       |  10 +--
 drivers/pci/hotplug/cpqphp_pci.c        |   5 +-
 drivers/pci/hotplug/ibmphp.h            |  12 ++--
 drivers/pci/hotplug/ibmphp_core.c       | 109 ++++++++++++++++----------------
 drivers/pci/hotplug/ibmphp_ebda.c       | 103 +++++++++++++++---------------
 drivers/pci/hotplug/ibmphp_hpc.c        |  24 +++----
 drivers/pci/hotplug/ibmphp_pci.c        |  71 ++++++++++-----------
 drivers/pci/hotplug/ibmphp_res.c        |  76 +++++++++++-----------
 drivers/pci/hotplug/pci_hotplug_core.c  |   8 +--
 drivers/pci/hotplug/pciehp.h            |   2 +-
 drivers/pci/hotplug/pciehp_acpi.c       |   2 +-
 drivers/pci/hotplug/pciehp_core.c       |   4 +-
 drivers/pci/hotplug/pciehp_hpc.c        |   6 +-
 drivers/pci/hotplug/pcihp_skeleton.c    |   8 +--
 drivers/pci/hotplug/rpadlpar_core.c     |   2 +-
 drivers/pci/hotplug/rpaphp.h            |   6 +-
 drivers/pci/hotplug/rpaphp_core.c       |   8 +--
 drivers/pci/hotplug/rpaphp_pci.c        |   3 +-
 drivers/pci/hotplug/rpaphp_slot.c       |  19 +++---
 drivers/pci/hotplug/shpchp.h            |   8 +--
 drivers/pci/hotplug/shpchp_core.c       |  10 +--
 drivers/pci/hotplug/shpchp_hpc.c        |   2 +-
 drivers/pci/iov.c                       |   2 +-
 drivers/pci/irq.c                       |   2 +-
 drivers/pci/msi.c                       |   2 +-
 drivers/pci/pci-acpi.c                  |   2 +-
 drivers/pci/pci-driver.c                |  16 ++---
 drivers/pci/pci-stub.c                  |   4 +-
 drivers/pci/pci-sysfs.c                 |  28 ++++----
 drivers/pci/pci.c                       |  46 +++++++-------
 drivers/pci/pcie/aer/aerdrv_core.c      |   2 +-
 drivers/pci/pcie/aspm.c                 |   2 +-
 drivers/pci/pcie/pme.c                  |   4 +-
 drivers/pci/pcie/portdrv.h              |   2 +-
 drivers/pci/pcie/portdrv_bus.c          |   4 +-
 drivers/pci/pcie/portdrv_core.c         |   2 +-
 drivers/pci/pcie/portdrv_pci.c          |   6 +-
 drivers/pci/probe.c                     |  10 +--
 drivers/pci/proc.c                      |   2 +-
 drivers/pci/quirks.c                    | 104 +++++++++++++++---------------
 drivers/pci/remove.c                    |   2 +-
 drivers/pci/search.c                    |  12 ++--
 drivers/pci/setup-bus.c                 |  18 +++---
 drivers/pci/setup-res.c                 |   2 +-
 drivers/pci/slot.c                      |   2 +-
 drivers/pci/syscall.c                   |   2 +-
 include/linux/msi.h                     |  10 +--
 include/linux/pci.h                     |  55 ++++++++--------
 include/linux/pci_hotplug.h             |   5 +-
 include/linux/pcieport_if.h             |   2 +-
 include/uapi/linux/pci_regs.h           |  72 ++++++++++-----------
 65 files changed, 518 insertions(+), 520 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 95655d7c0d0b..e52d7ffa38b9 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -410,7 +410,7 @@ EXPORT_SYMBOL_GPL(pci_disable_pasid);
  * Otherwise is returns a bitmask with supported features. Current
  * features reported are:
  * PCI_PASID_CAP_EXEC - Execute permission supported
- * PCI_PASID_CAP_PRIV - Priviledged mode supported
+ * PCI_PASID_CAP_PRIV - Privileged mode supported
  */
 int pci_pasid_features(struct pci_dev *pdev)
 {
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 7c4f38dd42ba..0afbbbc55c81 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -249,7 +249,7 @@ struct tegra_pcie {
 	void __iomem *afi;
 	int irq;
 
-	struct list_head busses;
+	struct list_head buses;
 	struct resource *cs;
 
 	struct resource io;
@@ -399,14 +399,14 @@ free:
 
 /*
  * Look up a virtual address mapping for the specified bus number. If no such
- * mapping existis, try to create one.
+ * mapping exists, try to create one.
  */
 static void __iomem *tegra_pcie_bus_map(struct tegra_pcie *pcie,
 					unsigned int busnr)
 {
 	struct tegra_pcie_bus *bus;
 
-	list_for_each_entry(bus, &pcie->busses, list)
+	list_for_each_entry(bus, &pcie->buses, list)
 		if (bus->nr == busnr)
 			return (void __iomem *)bus->area->addr;
 
@@ -414,7 +414,7 @@ static void __iomem *tegra_pcie_bus_map(struct tegra_pcie *pcie,
 	if (IS_ERR(bus))
 		return NULL;
 
-	list_add_tail(&bus->list, &pcie->busses);
+	list_add_tail(&bus->list, &pcie->buses);
 
 	return (void __iomem *)bus->area->addr;
 }
@@ -808,7 +808,7 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value &= ~AFI_FUSE_PCIE_T0_GEN2_DIS;
 	afi_writel(pcie, value, AFI_FUSE);
 
-	/* initialze internal PHY, enable up to 16 PCIE lanes */
+	/* initialize internal PHY, enable up to 16 PCIE lanes */
 	pads_writel(pcie, 0x0, PADS_CTL_SEL);
 
 	/* override IDDQ to 1 on all 4 lanes */
@@ -1624,7 +1624,7 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 	if (!pcie)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&pcie->busses);
+	INIT_LIST_HEAD(&pcie->buses);
 	INIT_LIST_HEAD(&pcie->ports);
 	pcie->soc_data = match->data;
 	pcie->dev = &pdev->dev;
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 1e1fea4d959b..e33b68be0391 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -197,7 +197,7 @@ static int find_valid_pos0(struct pcie_port *pp, int msgvec, int pos, int *pos0)
 			return -ENOSPC;
 		/*
 		 * Check if this position is at correct offset.nvec is always a
-		 * power of two. pos0 must be nvec bit alligned.
+		 * power of two. pos0 must be nvec bit aligned.
 		 */
 		if (pos % msgvec)
 			pos += msgvec - (pos % msgvec);
diff --git a/drivers/pci/hotplug/Kconfig b/drivers/pci/hotplug/Kconfig
index 0a648af89531..df8caec59789 100644
--- a/drivers/pci/hotplug/Kconfig
+++ b/drivers/pci/hotplug/Kconfig
@@ -133,8 +133,8 @@ config HOTPLUG_PCI_RPA_DLPAR
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called rpadlpar_io.
- 
- 	  When in doubt, say N.
+
+	  When in doubt, say N.
 
 config HOTPLUG_PCI_SGI
 	tristate "SGI PCI Hotplug Support"
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
index 47ec8c80e16d..3e6532b945c1 100644
--- a/drivers/pci/hotplug/Makefile
+++ b/drivers/pci/hotplug/Makefile
@@ -31,7 +31,7 @@ pci_hotplug-objs	+=	cpci_hotplug_core.o	\
 				cpci_hotplug_pci.o
 endif
 ifdef CONFIG_ACPI
-pci_hotplug-objs 	+= 	acpi_pcihp.o
+pci_hotplug-objs	+=	acpi_pcihp.o
 endif
 
 cpqphp-objs		:=	cpqphp_core.o	\
diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 8650d39db392..dca66bc44578 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -111,7 +111,7 @@ int acpiphp_register_attention(struct acpiphp_attention_info *info)
  * @info: must match the pointer used to register
  *
  * Description: This is used to un-register a hardware specific acpi
- * driver that manipulates the attention LED.  The pointer to the 
+ * driver that manipulates the attention LED.  The pointer to the
  * info struct must be the same as the one used to set it.
  */
 int acpiphp_unregister_attention(struct acpiphp_attention_info *info)
@@ -169,8 +169,8 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
  * was registered with us.  This allows hardware specific
  * ACPI implementations to blink the light for us.
  */
- static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
- {
+static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
+{
 	int retval = -ENODEV;
 
 	pr_debug("%s - physical_slot = %s\n", __func__,
@@ -182,8 +182,8 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 	} else
 		attention_info = NULL;
 	return retval;
- }
- 
+}
+
 
 /**
  * get_power_status - get power status of a slot
@@ -323,7 +323,7 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot,
 	if (retval) {
 		pr_err("pci_hp_register failed with error %d\n", retval);
 		goto error_hpslot;
- 	}
+	}
 
 	pr_info("Slot [%s] registered\n", slot_name(slot));
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 5b4e9eb0e8ff..1cf605f67673 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -325,7 +325,7 @@ static acpi_status register_slot(acpi_handle handle, u32 lvl, void *data,
 
 	list_add_tail(&slot->node, &bridge->slots);
 
-	/* Register slots for ejectable funtions only. */
+	/* Register slots for ejectable functions only. */
 	if (acpi_pci_check_ejectable(pbus, handle)  || is_dock_device(handle)) {
 		unsigned long long sun;
 		int retval;
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index 0d64c414bf78..ecfac7e72d91 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -116,7 +116,7 @@ static struct bin_attribute ibm_apci_table_attr = {
 	    .read = ibm_read_apci_table,
 	    .write = NULL,
 };
-static struct acpiphp_attention_info ibm_attention_info = 
+static struct acpiphp_attention_info ibm_attention_info =
 {
 	.set_attn = ibm_set_attention_status,
 	.get_attn = ibm_get_attention_status,
@@ -171,9 +171,9 @@ ibm_slot_done:
  */
 static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status)
 {
-	union acpi_object args[2]; 
+	union acpi_object args[2];
 	struct acpi_object_list params = { .pointer = args, .count = 2 };
-	acpi_status stat; 
+	acpi_status stat;
 	unsigned long long rc;
 	union apci_descriptor *ibm_slot;
 
@@ -208,7 +208,7 @@ static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status)
  *
  * Description: This method is registered with the acpiphp module as a
  * callback to do the device specific task of getting the LED status.
- * 
+ *
  * Because there is no direct method of getting the LED status directly
  * from an ACPI call, we read the aPCI table and parse out our
  * slot descriptor to read the status from that.
@@ -259,7 +259,7 @@ static void ibm_handle_events(acpi_handle handle, u32 event, void *context)
 	pr_debug("%s: Received notification %02x\n", __func__, event);
 
 	if (subevent == 0x80) {
-		pr_debug("%s: generationg bus event\n", __func__);
+		pr_debug("%s: generating bus event\n", __func__);
 		acpi_bus_generate_netlink_event(note->device->pnp.device_class,
 						  dev_name(&note->device->dev),
 						  note->event, detail);
@@ -387,7 +387,7 @@ static acpi_status __init ibm_find_acpi_device(acpi_handle handle,
 		u32 lvl, void *context, void **rv)
 {
 	acpi_handle *phandle = (acpi_handle *)context;
-	acpi_status status; 
+	acpi_status status;
 	struct acpi_device_info *info;
 	int retval = 0;
 
@@ -405,7 +405,7 @@ static acpi_status __init ibm_find_acpi_device(acpi_handle handle,
 			info->hardware_id.string, handle);
 		*phandle = handle;
 		/* returning non-zero causes the search to stop
-		 * and returns this value to the caller of 
+		 * and returns this value to the caller of
 		 * acpi_walk_namespace, but it also causes some warnings
 		 * in the acpi debug code to print...
 		 */
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 2b4c412f94c3..00c81a3cefc9 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -46,7 +46,7 @@
 	do {							\
 		if (cpci_debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c
index d8add34177f2..d3add9819f63 100644
--- a/drivers/pci/hotplug/cpci_hotplug_pci.c
+++ b/drivers/pci/hotplug/cpci_hotplug_pci.c
@@ -39,7 +39,7 @@ extern int cpci_debug;
 	do {							\
 		if (cpci_debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c
index a6a71c41cdf8..7536eef620b0 100644
--- a/drivers/pci/hotplug/cpcihp_generic.c
+++ b/drivers/pci/hotplug/cpcihp_generic.c
@@ -13,14 +13,14 @@
  * option) any later version.
  *
  * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * You should have received a copy of the GNU General Public License along
@@ -53,9 +53,9 @@
 
 #define dbg(format, arg...)					\
 	do {							\
-		if(debug)					\
+		if (debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while(0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.c b/drivers/pci/hotplug/cpcihp_zt5550.c
index 449b4bbc8301..e8c4a7ccf578 100644
--- a/drivers/pci/hotplug/cpcihp_zt5550.c
+++ b/drivers/pci/hotplug/cpcihp_zt5550.c
@@ -13,14 +13,14 @@
  * option) any later version.
  *
  * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * You should have received a copy of the GNU General Public License along
@@ -48,9 +48,9 @@
 
 #define dbg(format, arg...)					\
 	do {							\
-		if(debug)					\
+		if (debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while(0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
@@ -285,7 +285,7 @@ static struct pci_device_id zt5550_hc_pci_tbl[] = {
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, zt5550_hc_pci_tbl);
-	
+
 static struct pci_driver zt5550_hc_driver = {
 	.name		= "zt5550_hc",
 	.id_table	= zt5550_hc_pci_tbl,
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.h b/drivers/pci/hotplug/cpcihp_zt5550.h
index bebc6060a558..9a57fda5348c 100644
--- a/drivers/pci/hotplug/cpcihp_zt5550.h
+++ b/drivers/pci/hotplug/cpcihp_zt5550.h
@@ -13,14 +13,14 @@
  * option) any later version.
  *
  * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
- * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY 
- * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL 
- * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, 
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, 
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+ * AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
+ * THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * You should have received a copy of the GNU General Public License along
@@ -55,7 +55,7 @@
 #define HC_CMD_REG		0x0C
 #define ARB_CONFIG_GNT_REG	0x10
 #define ARB_CONFIG_CFG_REG	0x12
-#define ARB_CONFIG_REG	 	0x10
+#define ARB_CONFIG_REG		0x10
 #define ISOL_CONFIG_REG		0x18
 #define FAULT_STATUS_REG	0x20
 #define FAULT_CONFIG_REG	0x24
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index c8eaeb43fa5d..31273e155e6c 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -862,10 +862,10 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_disable_device;
 	}
 
-	/* Check for the proper subsystem ID's
+	/* Check for the proper subsystem IDs
 	 * Intel uses a different SSID programming model than Compaq.
 	 * For Intel, each SSID bit identifies a PHP capability.
-	 * Also Intel HPC's may have RID=0.
+	 * Also Intel HPCs may have RID=0.
 	 */
 	if ((pdev->revision <= 2) && (vendor_id != PCI_VENDOR_ID_INTEL)) {
 		err(msg_HPC_not_supported);
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
index d282019cda5f..11845b796799 100644
--- a/drivers/pci/hotplug/cpqphp_ctrl.c
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -1231,7 +1231,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
 
 	/* Only if mode change...*/
 	if (((bus->cur_bus_speed == PCI_SPEED_66MHz) && (adapter_speed == PCI_SPEED_66MHz_PCIX)) ||
-		((bus->cur_bus_speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz))) 
+		((bus->cur_bus_speed == PCI_SPEED_66MHz_PCIX) && (adapter_speed == PCI_SPEED_66MHz)))
 			set_SOGO(ctrl);
 
 	wait_for_ctrl_irq(ctrl);
@@ -1828,7 +1828,7 @@ static void interrupt_event_handler(struct controller *ctrl)
 
 				if (ctrl->event_queue[loop].event_type == INT_BUTTON_PRESS) {
 					dbg("button pressed\n");
-				} else if (ctrl->event_queue[loop].event_type == 
+				} else if (ctrl->event_queue[loop].event_type ==
 					   INT_BUTTON_CANCEL) {
 					dbg("button cancel\n");
 					del_timer(&p_slot->task_event);
@@ -2411,11 +2411,11 @@ static int configure_new_function(struct controller *ctrl, struct pci_func *func
 		if (rc)
 			return rc;
 
-		/* find range of busses to use */
+		/* find range of buses to use */
 		dbg("find ranges of buses to use\n");
 		bus_node = get_max_resource(&(resources->bus_head), 1);
 
-		/* If we don't have any busses to allocate, we can't continue */
+		/* If we don't have any buses to allocate, we can't continue */
 		if (!bus_node)
 			return -ENOMEM;
 
@@ -2900,7 +2900,7 @@ static int configure_new_function(struct controller *ctrl, struct pci_func *func
 
 			/* If this function needs an interrupt and we are behind
 			 * a bridge and the pin is tied to something that's
-			 * alread mapped, set this one the same */
+			 * already mapped, set this one the same */
 			if (temp_byte && resources->irqs &&
 			    (resources->irqs->valid_INT &
 			     (0x01 << ((temp_byte + resources->irqs->barber_pole - 1) & 0x03)))) {
diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index 09801c6945ce..6e4a12c91adb 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -291,7 +291,7 @@ int cpqhp_get_bus_dev (struct controller *ctrl, u8 * bus_num, u8 * dev_num, u8 s
  *
  * Reads configuration for all slots in a PCI bus and saves info.
  *
- * Note:  For non-hot plug busses, the slot # saved is the device #
+ * Note:  For non-hot plug buses, the slot # saved is the device #
  *
  * returns 0 if success
  */
@@ -455,7 +455,7 @@ int cpqhp_save_config(struct controller *ctrl, int busnumber, int is_hot_plug)
  * cpqhp_save_slot_config
  *
  * Saves configuration info for all PCI devices in a given slot
- * including subordinate busses.
+ * including subordinate buses.
  *
  * returns 0 if success
  */
@@ -1556,4 +1556,3 @@ void cpqhp_destroy_board_resources (struct pci_func * func)
 		kfree(tres);
 	}
 }
-
diff --git a/drivers/pci/hotplug/ibmphp.h b/drivers/pci/hotplug/ibmphp.h
index 8c5b25871d02..e3e46a7b3ee7 100644
--- a/drivers/pci/hotplug/ibmphp.h
+++ b/drivers/pci/hotplug/ibmphp.h
@@ -59,7 +59,7 @@ extern int ibmphp_debug;
 
 
 /************************************************************
-*  RESOURE TYPE                                             *
+*  RESOURCE TYPE                                             *
 ************************************************************/
 
 #define EBDA_RSRC_TYPE_MASK		0x03
@@ -103,7 +103,7 @@ extern int ibmphp_debug;
 //--------------------------------------------------------------
 
 struct rio_table_hdr {
-	u8 ver_num; 
+	u8 ver_num;
 	u8 scal_count;
 	u8 riodev_count;
 	u16 offset;
@@ -127,7 +127,7 @@ struct scal_detail {
 };
 
 //--------------------------------------------------------------
-// RIO DETAIL 
+// RIO DETAIL
 //--------------------------------------------------------------
 
 struct rio_detail {
@@ -152,7 +152,7 @@ struct opt_rio {
 	u8 first_slot_num;
 	u8 middle_num;
 	struct list_head opt_rio_list;
-};	
+};
 
 struct opt_rio_lo {
 	u8 rio_type;
@@ -161,7 +161,7 @@ struct opt_rio_lo {
 	u8 middle_num;
 	u8 pack_count;
 	struct list_head opt_rio_lo_list;
-};	
+};
 
 /****************************************************************
 *  HPC DESCRIPTOR NODE                                          *
@@ -574,7 +574,7 @@ void ibmphp_hpc_stop_poll_thread(void);
 #define HPC_CTLR_IRQ_PENDG	0x80
 
 //----------------------------------------------------------------------------
-// HPC_CTLR_WROKING status return codes
+// HPC_CTLR_WORKING status return codes
 //----------------------------------------------------------------------------
 #define HPC_CTLR_WORKING_NO	0x00
 #define HPC_CTLR_WORKING_YES	0x01
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index cbd72d81d253..efdc13adbe41 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -58,7 +58,7 @@ MODULE_DESCRIPTION (DRIVER_DESC);
 struct pci_bus *ibmphp_pci_bus;
 static int max_slots;
 
-static int irqs[16];    /* PIC mode IRQ's we're using so far (in case MPS
+static int irqs[16];    /* PIC mode IRQs we're using so far (in case MPS
 			 * tables don't provide default info for empty slots */
 
 static int init_flag;
@@ -71,20 +71,20 @@ static inline int get_max_adapter_speed (struct hotplug_slot *hs, u8 *value)
 	return get_max_adapter_speed_1 (hs, value, 1);
 }
 */
-static inline int get_cur_bus_info(struct slot **sl) 
+static inline int get_cur_bus_info(struct slot **sl)
 {
 	int rc = 1;
 	struct slot * slot_cur = *sl;
 
 	debug("options = %x\n", slot_cur->ctrl->options);
-	debug("revision = %x\n", slot_cur->ctrl->revision);	
+	debug("revision = %x\n", slot_cur->ctrl->revision);
 
-	if (READ_BUS_STATUS(slot_cur->ctrl)) 
+	if (READ_BUS_STATUS(slot_cur->ctrl))
 		rc = ibmphp_hpc_readslot(slot_cur, READ_BUSSTATUS, NULL);
-	
-	if (rc) 
+
+	if (rc)
 		return rc;
-	  
+
 	slot_cur->bus_on->current_speed = CURRENT_BUS_SPEED(slot_cur->busstatus);
 	if (READ_BUS_MODE(slot_cur->ctrl))
 		slot_cur->bus_on->current_bus_mode =
@@ -96,7 +96,7 @@ static inline int get_cur_bus_info(struct slot **sl)
 			slot_cur->busstatus,
 			slot_cur->bus_on->current_speed,
 			slot_cur->bus_on->current_bus_mode);
-	
+
 	*sl = slot_cur;
 	return 0;
 }
@@ -104,8 +104,8 @@ static inline int get_cur_bus_info(struct slot **sl)
 static inline int slot_update(struct slot **sl)
 {
 	int rc;
- 	rc = ibmphp_hpc_readslot(*sl, READ_ALLSTAT, NULL);
-	if (rc) 
+	rc = ibmphp_hpc_readslot(*sl, READ_ALLSTAT, NULL);
+	if (rc)
 		return rc;
 	if (!init_flag)
 		rc = get_cur_bus_info(sl);
@@ -172,7 +172,7 @@ int ibmphp_init_devno(struct slot **cur_slot)
 			debug("(*cur_slot)->irq[3] = %x\n",
 					(*cur_slot)->irq[3]);
 
-			debug("rtable->exlusive_irqs = %x\n",
+			debug("rtable->exclusive_irqs = %x\n",
 					rtable->exclusive_irqs);
 			debug("rtable->slots[loop].irq[0].bitmap = %x\n",
 					rtable->slots[loop].irq[0].bitmap);
@@ -271,7 +271,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value)
 			else
 				rc = -ENODEV;
 		}
-	} else	
+	} else
 		rc = -ENODEV;
 
 	ibmphp_unlock_operations();
@@ -288,7 +288,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
 
 	debug("get_attention_status - Entry hotplug_slot[%lx] pvalue[%lx]\n",
 					(ulong) hotplug_slot, (ulong) value);
-        
+
 	ibmphp_lock_operations();
 	if (hotplug_slot) {
 		pslot = hotplug_slot->private;
@@ -406,14 +406,14 @@ static int get_max_bus_speed(struct slot *slot)
 
 	ibmphp_lock_operations();
 	mode = slot->supported_bus_mode;
-	speed = slot->supported_speed; 
+	speed = slot->supported_speed;
 	ibmphp_unlock_operations();
 
 	switch (speed) {
 	case BUS_SPEED_33:
 		break;
 	case BUS_SPEED_66:
-		if (mode == BUS_MODE_PCIX) 
+		if (mode == BUS_MODE_PCIX)
 			speed += 0x01;
 		break;
 	case BUS_SPEED_100:
@@ -515,13 +515,13 @@ static int __init init_ops(void)
 
 		debug("BEFORE GETTING SLOT STATUS, slot # %x\n",
 							slot_cur->number);
-		if (slot_cur->ctrl->revision == 0xFF) 
+		if (slot_cur->ctrl->revision == 0xFF)
 			if (get_ctrl_revision(slot_cur,
 						&slot_cur->ctrl->revision))
 				return -1;
 
-		if (slot_cur->bus_on->current_speed == 0xFF) 
-			if (get_cur_bus_info(&slot_cur)) 
+		if (slot_cur->bus_on->current_speed == 0xFF)
+			if (get_cur_bus_info(&slot_cur))
 				return -1;
 		get_max_bus_speed(slot_cur);
 
@@ -539,8 +539,8 @@ static int __init init_ops(void)
 		debug("SLOT_PRESENT = %x\n", SLOT_PRESENT(slot_cur->status));
 		debug("SLOT_LATCH = %x\n", SLOT_LATCH(slot_cur->status));
 
-		if ((SLOT_PWRGD(slot_cur->status)) && 
-		    !(SLOT_PRESENT(slot_cur->status)) && 
+		if ((SLOT_PWRGD(slot_cur->status)) &&
+		    !(SLOT_PRESENT(slot_cur->status)) &&
 		    !(SLOT_LATCH(slot_cur->status))) {
 			debug("BEFORE POWER OFF COMMAND\n");
 				rc = power_off(slot_cur);
@@ -581,13 +581,13 @@ static int validate(struct slot *slot_cur, int opn)
 
 	switch (opn) {
 		case ENABLE:
-			if (!(SLOT_PWRGD(slot_cur->status)) && 
-			     (SLOT_PRESENT(slot_cur->status)) && 
+			if (!(SLOT_PWRGD(slot_cur->status)) &&
+			     (SLOT_PRESENT(slot_cur->status)) &&
 			     !(SLOT_LATCH(slot_cur->status)))
 				return 0;
 			break;
 		case DISABLE:
-			if ((SLOT_PWRGD(slot_cur->status)) && 
+			if ((SLOT_PWRGD(slot_cur->status)) &&
 			    (SLOT_PRESENT(slot_cur->status)) &&
 			    !(SLOT_LATCH(slot_cur->status)))
 				return 0;
@@ -617,7 +617,7 @@ int ibmphp_update_slot_info(struct slot *slot_cur)
 		err("out of system memory\n");
 		return -ENOMEM;
 	}
-        
+
 	info->power_status = SLOT_PWRGD(slot_cur->status);
 	info->attention_status = SLOT_ATTN(slot_cur->status,
 						slot_cur->ext_status);
@@ -638,7 +638,7 @@ int ibmphp_update_slot_info(struct slot *slot_cur)
 		case BUS_SPEED_33:
 			break;
 		case BUS_SPEED_66:
-			if (mode == BUS_MODE_PCIX) 
+			if (mode == BUS_MODE_PCIX)
 				bus_speed += 0x01;
 			else if (mode == BUS_MODE_PCI)
 				;
@@ -654,8 +654,8 @@ int ibmphp_update_slot_info(struct slot *slot_cur)
 	}
 
 	bus->cur_bus_speed = bus_speed;
-	// To do: bus_names 
-	
+	// To do: bus_names
+
 	rc = pci_hp_change_slot_info(slot_cur->hotplug_slot, info);
 	kfree(info);
 	return rc;
@@ -729,8 +729,8 @@ static void ibm_unconfigure_device(struct pci_func *func)
 }
 
 /*
- * The following function is to fix kernel bug regarding 
- * getting bus entries, here we manually add those primary 
+ * The following function is to fix kernel bug regarding
+ * getting bus entries, here we manually add those primary
  * bus entries to kernel bus structure whenever apply
  */
 static u8 bus_structure_fixup(u8 busno)
@@ -814,7 +814,7 @@ static int ibm_configure_device(struct pci_func *func)
 }
 
 /*******************************************************
- * Returns whether the bus is empty or not 
+ * Returns whether the bus is empty or not
  *******************************************************/
 static int is_bus_empty(struct slot * slot_cur)
 {
@@ -842,7 +842,7 @@ static int is_bus_empty(struct slot * slot_cur)
 }
 
 /***********************************************************
- * If the HPC permits and the bus currently empty, tries to set the 
+ * If the HPC permits and the bus currently empty, tries to set the
  * bus speed and mode at the maximum card and bus capability
  * Parameters: slot
  * Returns: bus is set (0) or error code
@@ -856,7 +856,7 @@ static int set_bus(struct slot * slot_cur)
 	static struct pci_device_id ciobx[] = {
 		{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS, 0x0101) },
 	        { },
-	};	
+	};
 
 	debug("%s - entry slot # %d\n", __func__, slot_cur->number);
 	if (SET_BUS_STATUS(slot_cur->ctrl) && is_bus_empty(slot_cur)) {
@@ -877,7 +877,7 @@ static int set_bus(struct slot * slot_cur)
 				else if (!SLOT_BUS_MODE(slot_cur->ext_status))
 					/* if max slot/bus capability is 66 pci
 					and there's no bus mode mismatch, then
-					the adapter supports 66 pci */ 
+					the adapter supports 66 pci */
 					cmd = HPC_BUS_66CONVMODE;
 				else
 					cmd = HPC_BUS_33CONVMODE;
@@ -930,7 +930,7 @@ static int set_bus(struct slot * slot_cur)
 			return -EIO;
 		}
 	}
-	/* This is for x440, once Brandon fixes the firmware, 
+	/* This is for x440, once Brandon fixes the firmware,
 	will not need this delay */
 	msleep(1000);
 	debug("%s -Exit\n", __func__);
@@ -938,9 +938,9 @@ static int set_bus(struct slot * slot_cur)
 }
 
 /* This routine checks the bus limitations that the slot is on from the BIOS.
- * This is used in deciding whether or not to power up the slot.  
+ * This is used in deciding whether or not to power up the slot.
  * (electrical/spec limitations. For example, >1 133 MHz or >2 66 PCI cards on
- * same bus) 
+ * same bus)
  * Parameters: slot
  * Returns: 0 = no limitations, -EINVAL = exceeded limitations on the bus
  */
@@ -986,7 +986,7 @@ static int check_limitations(struct slot *slot_cur)
 static inline void print_card_capability(struct slot *slot_cur)
 {
 	info("capability of the card is ");
-	if ((slot_cur->ext_status & CARD_INFO) == PCIX133) 
+	if ((slot_cur->ext_status & CARD_INFO) == PCIX133)
 		info("   133 MHz PCI-X\n");
 	else if ((slot_cur->ext_status & CARD_INFO) == PCIX66)
 		info("    66 MHz PCI-X\n");
@@ -1020,7 +1020,7 @@ static int enable_slot(struct hotplug_slot *hs)
 	}
 
 	attn_LED_blink(slot_cur);
-	
+
 	rc = set_bus(slot_cur);
 	if (rc) {
 		err("was not able to set the bus\n");
@@ -1082,7 +1082,7 @@ static int enable_slot(struct hotplug_slot *hs)
 	rc = slot_update(&slot_cur);
 	if (rc)
 		goto error_power;
-	
+
 	rc = -EINVAL;
 	if (SLOT_POWER(slot_cur->status) && !(SLOT_PWRGD(slot_cur->status))) {
 		err("power fault occurred trying to power up...\n");
@@ -1093,7 +1093,7 @@ static int enable_slot(struct hotplug_slot *hs)
 					"speed and card capability\n");
 		print_card_capability(slot_cur);
 		goto error_power;
-	} 
+	}
 	/* Don't think this case will happen after above checks...
 	 * but just in case, for paranoia sake */
 	if (!(SLOT_POWER(slot_cur->status))) {
@@ -1144,7 +1144,7 @@ static int enable_slot(struct hotplug_slot *hs)
 	ibmphp_print_test();
 	rc = ibmphp_update_slot_info(slot_cur);
 exit:
-	ibmphp_unlock_operations(); 
+	ibmphp_unlock_operations();
 	return rc;
 
 error_nopower:
@@ -1180,7 +1180,7 @@ static int ibmphp_disable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct slot *slot = hotplug_slot->private;
 	int rc;
-	
+
 	ibmphp_lock_operations();
 	rc = ibmphp_do_disable_slot(slot);
 	ibmphp_unlock_operations();
@@ -1192,12 +1192,12 @@ int ibmphp_do_disable_slot(struct slot *slot_cur)
 	int rc;
 	u8 flag;
 
-	debug("DISABLING SLOT...\n"); 
-		
+	debug("DISABLING SLOT...\n");
+
 	if ((slot_cur == NULL) || (slot_cur->ctrl == NULL)) {
 		return -ENODEV;
 	}
-	
+
 	flag = slot_cur->flag;
 	slot_cur->flag = 1;
 
@@ -1210,7 +1210,7 @@ int ibmphp_do_disable_slot(struct slot *slot_cur)
 	attn_LED_blink(slot_cur);
 
 	if (slot_cur->func == NULL) {
-		/* We need this for fncs's that were there on bootup */
+		/* We need this for functions that were there on bootup */
 		slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL);
 		if (!slot_cur->func) {
 			err("out of system memory\n");
@@ -1222,12 +1222,13 @@ int ibmphp_do_disable_slot(struct slot *slot_cur)
 	}
 
 	ibm_unconfigure_device(slot_cur->func);
-        
-	/* If we got here from latch suddenly opening on operating card or 
-	a power fault, there's no power to the card, so cannot
-	read from it to determine what resources it occupied.  This operation
-	is forbidden anyhow.  The best we can do is remove it from kernel
-	lists at least */
+
+	/*
+	 * If we got here from latch suddenly opening on operating card or
+	 * a power fault, there's no power to the card, so cannot
+	 * read from it to determine what resources it occupied.  This operation
+	 * is forbidden anyhow.  The best we can do is remove it from kernel
+	 * lists at least */
 
 	if (!flag) {
 		attn_off(slot_cur);
@@ -1264,7 +1265,7 @@ error:
 		rc = -EFAULT;
 		goto exit;
 	}
-	if (flag)		
+	if (flag)
 		ibmphp_update_slot_info(slot_cur);
 	goto exit;
 }
@@ -1339,7 +1340,7 @@ static int __init ibmphp_init(void)
 	debug("AFTER Resource & EBDA INITIALIZATIONS\n");
 
 	max_slots = get_max_slots();
-	
+
 	if ((rc = ibmphp_register_pci()))
 		goto error;
 
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index 9df78bc14541..bd044158b36c 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -123,7 +123,7 @@ static struct ebda_pci_rsrc *alloc_ebda_pci_rsrc (void)
 static void __init print_bus_info (void)
 {
 	struct bus_info *ptr;
-	
+
 	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
 		debug ("%s - slot_min = %x\n", __func__, ptr->slot_min);
 		debug ("%s - slot_max = %x\n", __func__, ptr->slot_max);
@@ -131,7 +131,7 @@ static void __init print_bus_info (void)
 		debug ("%s - bus# = %x\n", __func__, ptr->busno);
 		debug ("%s - current_speed = %x\n", __func__, ptr->current_speed);
 		debug ("%s - controller_id = %x\n", __func__, ptr->controller_id);
-		
+
 		debug ("%s - slots_at_33_conv = %x\n", __func__, ptr->slots_at_33_conv);
 		debug ("%s - slots_at_66_conv = %x\n", __func__, ptr->slots_at_66_conv);
 		debug ("%s - slots_at_66_pcix = %x\n", __func__, ptr->slots_at_66_pcix);
@@ -144,7 +144,7 @@ static void __init print_bus_info (void)
 static void print_lo_info (void)
 {
 	struct rio_detail *ptr;
-	debug ("print_lo_info ----\n");	
+	debug ("print_lo_info ----\n");
 	list_for_each_entry(ptr, &rio_lo_head, rio_detail_list) {
 		debug ("%s - rio_node_id = %x\n", __func__, ptr->rio_node_id);
 		debug ("%s - rio_type = %x\n", __func__, ptr->rio_type);
@@ -176,7 +176,7 @@ static void __init print_ebda_pci_rsrc (void)
 	struct ebda_pci_rsrc *ptr;
 
 	list_for_each_entry(ptr, &ibmphp_ebda_pci_rsrc_head, ebda_pci_rsrc_list) {
-		debug ("%s - rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n", 
+		debug ("%s - rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
 			__func__, ptr->rsrc_type ,ptr->bus_num, ptr->dev_fun,ptr->start_addr, ptr->end_addr);
 	}
 }
@@ -259,7 +259,7 @@ int __init ibmphp_access_ebda (void)
 	ebda_seg = readw (io_mem);
 	iounmap (io_mem);
 	debug ("returned ebda segment: %x\n", ebda_seg);
-	
+
 	io_mem = ioremap(ebda_seg<<4, 1);
 	if (!io_mem)
 		return -ENOMEM;
@@ -310,7 +310,7 @@ int __init ibmphp_access_ebda (void)
 			re = readw (io_mem + sub_addr);	/* next sub blk */
 
 			sub_addr += 2;
-			rc_id = readw (io_mem + sub_addr); 	/* sub blk id */
+			rc_id = readw (io_mem + sub_addr);	/* sub blk id */
 
 			sub_addr += 2;
 			if (rc_id != 0x5243)
@@ -330,7 +330,7 @@ int __init ibmphp_access_ebda (void)
 			debug ("info about hpc descriptor---\n");
 			debug ("hot blk format: %x\n", format);
 			debug ("num of controller: %x\n", num_ctlrs);
-			debug ("offset of hpc data structure enteries: %x\n ", sub_addr);
+			debug ("offset of hpc data structure entries: %x\n ", sub_addr);
 
 			sub_addr = base + re;	/* re sub blk */
 			/* FIXME: rc is never used/checked */
@@ -359,7 +359,7 @@ int __init ibmphp_access_ebda (void)
 			debug ("info about rsrc descriptor---\n");
 			debug ("format: %x\n", format);
 			debug ("num of rsrc: %x\n", num_entries);
-			debug ("offset of rsrc data structure enteries: %x\n ", sub_addr);
+			debug ("offset of rsrc data structure entries: %x\n ", sub_addr);
 
 			hs_complete = 1;
 		} else {
@@ -376,7 +376,7 @@ int __init ibmphp_access_ebda (void)
 			rio_table_ptr->scal_count = readb (io_mem + offset + 1);
 			rio_table_ptr->riodev_count = readb (io_mem + offset + 2);
 			rio_table_ptr->offset = offset +3 ;
-			
+
 			debug("info about rio table hdr ---\n");
 			debug("ver_num: %x\nscal_count: %x\nriodev_count: %x\noffset of rio table: %x\n ",
 				rio_table_ptr->ver_num, rio_table_ptr->scal_count,
@@ -440,12 +440,12 @@ static int __init ebda_rio_table (void)
 		rio_detail_ptr->chassis_num = readb (io_mem + offset + 14);
 //		debug ("rio_node_id: %x\nbbar: %x\nrio_type: %x\nowner_id: %x\nport0_node: %x\nport0_port: %x\nport1_node: %x\nport1_port: %x\nfirst_slot_num: %x\nstatus: %x\n", rio_detail_ptr->rio_node_id, rio_detail_ptr->bbar, rio_detail_ptr->rio_type, rio_detail_ptr->owner_id, rio_detail_ptr->port0_node_connect, rio_detail_ptr->port0_port_connect, rio_detail_ptr->port1_node_connect, rio_detail_ptr->port1_port_connect, rio_detail_ptr->first_slot_num, rio_detail_ptr->status);
 		//create linked list of chassis
-		if (rio_detail_ptr->rio_type == 4 || rio_detail_ptr->rio_type == 5) 
+		if (rio_detail_ptr->rio_type == 4 || rio_detail_ptr->rio_type == 5)
 			list_add (&rio_detail_ptr->rio_detail_list, &rio_vg_head);
-		//create linked list of expansion box				
-		else if (rio_detail_ptr->rio_type == 6 || rio_detail_ptr->rio_type == 7) 
+		//create linked list of expansion box
+		else if (rio_detail_ptr->rio_type == 6 || rio_detail_ptr->rio_type == 7)
 			list_add (&rio_detail_ptr->rio_detail_list, &rio_lo_head);
-		else 
+		else
 			// not in my concern
 			kfree (rio_detail_ptr);
 		offset += 15;
@@ -456,7 +456,7 @@ static int __init ebda_rio_table (void)
 }
 
 /*
- * reorganizing linked list of chassis	 
+ * reorganizing linked list of chassis
  */
 static struct opt_rio *search_opt_vg (u8 chassis_num)
 {
@@ -464,7 +464,7 @@ static struct opt_rio *search_opt_vg (u8 chassis_num)
 	list_for_each_entry(ptr, &opt_vg_head, opt_rio_list) {
 		if (ptr->chassis_num == chassis_num)
 			return ptr;
-	}		
+	}
 	return NULL;
 }
 
@@ -472,7 +472,7 @@ static int __init combine_wpg_for_chassis (void)
 {
 	struct opt_rio *opt_rio_ptr = NULL;
 	struct rio_detail *rio_detail_ptr = NULL;
-	
+
 	list_for_each_entry(rio_detail_ptr, &rio_vg_head, rio_detail_list) {
 		opt_rio_ptr = search_opt_vg (rio_detail_ptr->chassis_num);
 		if (!opt_rio_ptr) {
@@ -484,14 +484,14 @@ static int __init combine_wpg_for_chassis (void)
 			opt_rio_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
 			opt_rio_ptr->middle_num = rio_detail_ptr->first_slot_num;
 			list_add (&opt_rio_ptr->opt_rio_list, &opt_vg_head);
-		} else {	
+		} else {
 			opt_rio_ptr->first_slot_num = min (opt_rio_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
 			opt_rio_ptr->middle_num = max (opt_rio_ptr->middle_num, rio_detail_ptr->first_slot_num);
-		}	
+		}
 	}
 	print_opt_vg ();
-	return 0;	
-}	
+	return 0;
+}
 
 /*
  * reorganizing linked list of expansion box
@@ -502,7 +502,7 @@ static struct opt_rio_lo *search_opt_lo (u8 chassis_num)
 	list_for_each_entry(ptr, &opt_lo_head, opt_rio_lo_list) {
 		if (ptr->chassis_num == chassis_num)
 			return ptr;
-	}		
+	}
 	return NULL;
 }
 
@@ -510,7 +510,7 @@ static int combine_wpg_for_expansion (void)
 {
 	struct opt_rio_lo *opt_rio_lo_ptr = NULL;
 	struct rio_detail *rio_detail_ptr = NULL;
-	
+
 	list_for_each_entry(rio_detail_ptr, &rio_lo_head, rio_detail_list) {
 		opt_rio_lo_ptr = search_opt_lo (rio_detail_ptr->chassis_num);
 		if (!opt_rio_lo_ptr) {
@@ -522,22 +522,22 @@ static int combine_wpg_for_expansion (void)
 			opt_rio_lo_ptr->first_slot_num = rio_detail_ptr->first_slot_num;
 			opt_rio_lo_ptr->middle_num = rio_detail_ptr->first_slot_num;
 			opt_rio_lo_ptr->pack_count = 1;
-			
+
 			list_add (&opt_rio_lo_ptr->opt_rio_lo_list, &opt_lo_head);
-		} else {	
+		} else {
 			opt_rio_lo_ptr->first_slot_num = min (opt_rio_lo_ptr->first_slot_num, rio_detail_ptr->first_slot_num);
 			opt_rio_lo_ptr->middle_num = max (opt_rio_lo_ptr->middle_num, rio_detail_ptr->first_slot_num);
 			opt_rio_lo_ptr->pack_count = 2;
-		}	
+		}
 	}
-	return 0;	
+	return 0;
 }
-	
+
 
 /* Since we don't know the max slot number per each chassis, hence go
  * through the list of all chassis to find out the range
- * Arguments: slot_num, 1st slot number of the chassis we think we are on, 
- * var (0 = chassis, 1 = expansion box) 
+ * Arguments: slot_num, 1st slot number of the chassis we think we are on,
+ * var (0 = chassis, 1 = expansion box)
  */
 static int first_slot_num (u8 slot_num, u8 first_slot, u8 var)
 {
@@ -547,7 +547,7 @@ static int first_slot_num (u8 slot_num, u8 first_slot, u8 var)
 
 	if (!var) {
 		list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
-			if ((first_slot < opt_vg_ptr->first_slot_num) && (slot_num >= opt_vg_ptr->first_slot_num)) { 
+			if ((first_slot < opt_vg_ptr->first_slot_num) && (slot_num >= opt_vg_ptr->first_slot_num)) {
 				rc = -ENODEV;
 				break;
 			}
@@ -569,7 +569,7 @@ static struct opt_rio_lo * find_rxe_num (u8 slot_num)
 
 	list_for_each_entry(opt_lo_ptr, &opt_lo_head, opt_rio_lo_list) {
 		//check to see if this slot_num belongs to expansion box
-		if ((slot_num >= opt_lo_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_lo_ptr->first_slot_num, 1))) 
+		if ((slot_num >= opt_lo_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_lo_ptr->first_slot_num, 1)))
 			return opt_lo_ptr;
 	}
 	return NULL;
@@ -580,8 +580,8 @@ static struct opt_rio * find_chassis_num (u8 slot_num)
 	struct opt_rio *opt_vg_ptr;
 
 	list_for_each_entry(opt_vg_ptr, &opt_vg_head, opt_rio_list) {
-		//check to see if this slot_num belongs to chassis 
-		if ((slot_num >= opt_vg_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_vg_ptr->first_slot_num, 0))) 
+		//check to see if this slot_num belongs to chassis
+		if ((slot_num >= opt_vg_ptr->first_slot_num) && (!first_slot_num (slot_num, opt_vg_ptr->first_slot_num, 0)))
 			return opt_vg_ptr;
 	}
 	return NULL;
@@ -594,13 +594,13 @@ static u8 calculate_first_slot (u8 slot_num)
 {
 	u8 first_slot = 1;
 	struct slot * slot_cur;
-	
+
 	list_for_each_entry(slot_cur, &ibmphp_slot_head, ibm_slot_list) {
 		if (slot_cur->ctrl) {
-			if ((slot_cur->ctrl->ctlr_type != 4) && (slot_cur->ctrl->ending_slot_num > first_slot) && (slot_num > slot_cur->ctrl->ending_slot_num)) 
+			if ((slot_cur->ctrl->ctlr_type != 4) && (slot_cur->ctrl->ending_slot_num > first_slot) && (slot_num > slot_cur->ctrl->ending_slot_num))
 				first_slot = slot_cur->ctrl->ending_slot_num;
 		}
-	}			
+	}
 	return first_slot + 1;
 
 }
@@ -622,11 +622,11 @@ static char *create_file_name (struct slot * slot_cur)
 		err ("Structure passed is empty\n");
 		return NULL;
 	}
-	
+
 	slot_num = slot_cur->number;
 
 	memset (str, 0, sizeof(str));
-	
+
 	if (rio_table_ptr) {
 		if (rio_table_ptr->ver_num == 3) {
 			opt_vg_ptr = find_chassis_num (slot_num);
@@ -660,7 +660,7 @@ static char *create_file_name (struct slot * slot_cur)
 			/* if both NULL and we DO have correct RIO table in BIOS */
 			return NULL;
 		}
-	} 
+	}
 	if (!flag) {
 		if (slot_cur->ctrl->ctlr_type == 4) {
 			first_slot = calculate_first_slot (slot_num);
@@ -798,7 +798,7 @@ static int __init ebda_rsrc_controller (void)
 			slot_ptr->ctl_index = readb (io_mem + addr_slot + 2*slot_num);
 			slot_ptr->slot_cap = readb (io_mem + addr_slot + 3*slot_num);
 
-			// create bus_info lined list --- if only one slot per bus: slot_min = slot_max 
+			// create bus_info lined list --- if only one slot per bus: slot_min = slot_max
 
 			bus_info_ptr2 = ibmphp_find_same_bus_num (slot_ptr->slot_bus_num);
 			if (!bus_info_ptr2) {
@@ -814,9 +814,9 @@ static int __init ebda_rsrc_controller (void)
 				bus_info_ptr1->index = bus_index++;
 				bus_info_ptr1->current_speed = 0xff;
 				bus_info_ptr1->current_bus_mode = 0xff;
-				
+
 				bus_info_ptr1->controller_id = hpc_ptr->ctlr_id;
-				
+
 				list_add_tail (&bus_info_ptr1->bus_info_list, &bus_info_head);
 
 			} else {
@@ -851,7 +851,7 @@ static int __init ebda_rsrc_controller (void)
 				bus_info_ptr2->slots_at_66_conv = bus_ptr->slots_at_66_conv;
 				bus_info_ptr2->slots_at_66_pcix = bus_ptr->slots_at_66_pcix;
 				bus_info_ptr2->slots_at_100_pcix = bus_ptr->slots_at_100_pcix;
-				bus_info_ptr2->slots_at_133_pcix = bus_ptr->slots_at_133_pcix; 
+				bus_info_ptr2->slots_at_133_pcix = bus_ptr->slots_at_133_pcix;
 			}
 			bus_ptr++;
 		}
@@ -864,7 +864,7 @@ static int __init ebda_rsrc_controller (void)
 				hpc_ptr->u.pci_ctlr.dev_fun = readb (io_mem + addr + 1);
 				hpc_ptr->irq = readb (io_mem + addr + 2);
 				addr += 3;
-				debug ("ctrl bus = %x, ctlr devfun = %x, irq = %x\n", 
+				debug ("ctrl bus = %x, ctlr devfun = %x, irq = %x\n",
 					hpc_ptr->u.pci_ctlr.bus,
 					hpc_ptr->u.pci_ctlr.dev_fun, hpc_ptr->irq);
 				break;
@@ -932,7 +932,7 @@ static int __init ebda_rsrc_controller (void)
 				tmp_slot->supported_speed =  2;
 			else if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_66_MAX) == EBDA_SLOT_66_MAX)
 				tmp_slot->supported_speed =  1;
-				
+
 			if ((hpc_ptr->slots[index].slot_cap & EBDA_SLOT_PCIX_CAP) == EBDA_SLOT_PCIX_CAP)
 				tmp_slot->supported_bus_mode = 1;
 			else
@@ -1000,7 +1000,7 @@ error_no_hpc:
 	return rc;
 }
 
-/* 
+/*
  * map info (bus, devfun, start addr, end addr..) of i/o, memory,
  * pfm from the physical addr to a list of resource.
  */
@@ -1057,7 +1057,7 @@ static int __init ebda_rsrc_rsrc (void)
 			addr += 10;
 
 			debug ("rsrc from mem or pfm ---\n");
-			debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n", 
+			debug ("rsrc type: %x bus#: %x dev_func: %x start addr: %x end addr: %x\n",
 				rsrc_ptr->rsrc_type, rsrc_ptr->bus_num, rsrc_ptr->dev_fun, rsrc_ptr->start_addr, rsrc_ptr->end_addr);
 
 			list_add (&rsrc_ptr->ebda_pci_rsrc_list, &ibmphp_ebda_pci_rsrc_head);
@@ -1096,7 +1096,7 @@ struct bus_info *ibmphp_find_same_bus_num (u32 num)
 	struct bus_info *ptr;
 
 	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
-		if (ptr->busno == num) 
+		if (ptr->busno == num)
 			 return ptr;
 	}
 	return NULL;
@@ -1110,7 +1110,7 @@ int ibmphp_get_bus_index (u8 num)
 	struct bus_info *ptr;
 
 	list_for_each_entry(ptr, &bus_info_head, bus_info_list) {
-		if (ptr->busno == num)  
+		if (ptr->busno == num)
 			return ptr->index;
 	}
 	return -ENODEV;
@@ -1168,7 +1168,7 @@ static struct pci_device_id id_table[] = {
 		.subdevice	= HPC_SUBSYSTEM_ID,
 		.class		= ((PCI_CLASS_SYSTEM_PCI_HOTPLUG << 8) | 0x00),
 	}, {}
-};		
+};
 
 MODULE_DEVICE_TABLE(pci, id_table);
 
@@ -1197,7 +1197,7 @@ static int ibmphp_probe (struct pci_dev * dev, const struct pci_device_id *ids)
 	struct controller *ctrl;
 
 	debug ("inside ibmphp_probe\n");
-	
+
 	list_for_each_entry(ctrl, &ebda_hpc_head, ebda_hpc_list) {
 		if (ctrl->ctlr_type == 1) {
 			if ((dev->devfn == ctrl->u.pci_ctlr.dev_fun) && (dev->bus->number == ctrl->u.pci_ctlr.bus)) {
@@ -1210,4 +1210,3 @@ static int ibmphp_probe (struct pci_dev * dev, const struct pci_device_id *ids)
 	}
 	return -ENODEV;
 }
-
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
index f59ed30512b5..5fc7a089f532 100644
--- a/drivers/pci/hotplug/ibmphp_hpc.c
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -258,7 +258,7 @@ static u8 i2c_ctrl_write (struct controller *ctlr_ptr, void __iomem *WPGBbar, u8
 {
 	u8 rc;
 	void __iomem *wpg_addr;	// base addr + offset
-	unsigned long wpg_data;	// data to/from WPG LOHI format 
+	unsigned long wpg_data;	// data to/from WPG LOHI format
 	unsigned long ultemp;
 	unsigned long data;	// actual data HILO format
 	int i;
@@ -351,7 +351,7 @@ static u8 i2c_ctrl_write (struct controller *ctlr_ptr, void __iomem *WPGBbar, u8
 }
 
 //------------------------------------------------------------
-//  Read from ISA type HPC 
+//  Read from ISA type HPC
 //------------------------------------------------------------
 static u8 isa_ctrl_read (struct controller *ctlr_ptr, u8 offset)
 {
@@ -372,7 +372,7 @@ static void isa_ctrl_write (struct controller *ctlr_ptr, u8 offset, u8 data)
 {
 	u16 start_address;
 	u16 port_address;
-	
+
 	start_address = ctlr_ptr->u.isa_ctlr.io_start;
 	port_address = start_address + (u16) offset;
 	outb (data, port_address);
@@ -656,11 +656,11 @@ int ibmphp_hpc_readslot (struct slot * pslot, u8 cmd, u8 * pstatus)
 	//--------------------------------------------------------------------
 	// cleanup
 	//--------------------------------------------------------------------
-	
+
 	// remove physical to logical address mapping
 	if ((ctlr_ptr->ctlr_type == 2) || (ctlr_ptr->ctlr_type == 4))
 		iounmap (wpg_bbar);
-	
+
 	free_hpc_access ();
 
 	debug_polling ("%s - Exit rc[%d]\n", __func__, rc);
@@ -835,7 +835,7 @@ static int poll_hpc(void *data)
 		down (&semOperations);
 
 		switch (poll_state) {
-		case POLL_LATCH_REGISTER: 
+		case POLL_LATCH_REGISTER:
 			oldlatchlow = curlatchlow;
 			ctrl_count = 0x00;
 			list_for_each (pslotlist, &ibmphp_slot_head) {
@@ -892,16 +892,16 @@ static int poll_hpc(void *data)
 
 			if (kthread_should_stop())
 				goto out_sleep;
-			
+
 			down (&semOperations);
-			
+
 			if (poll_count >= POLL_LATCH_CNT) {
 				poll_count = 0;
 				poll_state = POLL_SLOTS;
 			} else
 				poll_state = POLL_LATCH_REGISTER;
 			break;
-		}	
+		}
 		/* give up the hardware semaphore */
 		up (&semOperations);
 		/* sleep for a short time just for good measure */
@@ -958,7 +958,7 @@ static int process_changeinstatus (struct slot *pslot, struct slot *poldslot)
 	// bit 5 - HPC_SLOT_PWRGD
 	if ((pslot->status & 0x20) != (poldslot->status & 0x20))
 		// OFF -> ON: ignore, ON -> OFF: disable slot
-		if ((poldslot->status & 0x20) && (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status))) 
+		if ((poldslot->status & 0x20) && (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status)))
 			disable = 1;
 
 	// bit 6 - HPC_SLOT_BUS_SPEED
@@ -980,7 +980,7 @@ static int process_changeinstatus (struct slot *pslot, struct slot *poldslot)
 					pslot->status &= ~HPC_SLOT_POWER;
 			}
 		}
-		// CLOSE -> OPEN 
+		// CLOSE -> OPEN
 		else if ((SLOT_PWRGD (poldslot->status) == HPC_SLOT_PWRGD_GOOD)
 			&& (SLOT_CONNECT (poldslot->status) == HPC_SLOT_CONNECTED) && (SLOT_PRESENT (poldslot->status))) {
 			disable = 1;
@@ -1075,7 +1075,7 @@ void __exit ibmphp_hpc_stop_poll_thread (void)
 	debug ("before locking operations \n");
 	ibmphp_lock_operations ();
 	debug ("after locking operations \n");
-	
+
 	// wait for poll thread to exit
 	debug ("before sem_exit down \n");
 	down (&sem_exit);
diff --git a/drivers/pci/hotplug/ibmphp_pci.c b/drivers/pci/hotplug/ibmphp_pci.c
index c60f5f3e838d..639ea3a75e14 100644
--- a/drivers/pci/hotplug/ibmphp_pci.c
+++ b/drivers/pci/hotplug/ibmphp_pci.c
@@ -1,8 +1,8 @@
 /*
  * IBM Hot Plug Controller Driver
- * 
+ *
  * Written By: Irene Zubarev, IBM Corporation
- * 
+ *
  * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
  * Copyright (C) 2001,2002 IBM Corp.
  *
@@ -42,7 +42,7 @@ static u8 find_sec_number (u8 primary_busno, u8 slotno);
 
 /*
  * NOTE..... If BIOS doesn't provide default routing, we assign:
- * 9 for SCSI, 10 for LAN adapters, and 11 for everything else. 
+ * 9 for SCSI, 10 for LAN adapters, and 11 for everything else.
  * If adapter is bridged, then we assign 11 to it and devices behind it.
  * We also assign the same irq numbers for multi function devices.
  * These are PIC mode, so shouldn't matter n.e.ways (hopefully)
@@ -71,11 +71,11 @@ static void assign_alt_irq (struct pci_func * cur_func, u8 class_code)
  * Configures the device to be added (will allocate needed resources if it
  * can), the device can be a bridge or a regular pci device, can also be
  * multi-functional
- * 
+ *
  * Input: function to be added
- * 
+ *
  * TO DO:  The error case with Multifunction device or multi function bridge,
- * if there is an error, will need to go through all previous functions and 
+ * if there is an error, will need to go through all previous functions and
  * unconfigure....or can add some code into unconfigure_card....
  */
 int ibmphp_configure_card (struct pci_func *func, u8 slotno)
@@ -98,7 +98,7 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 	cur_func = func;
 
 	/* We only get bus and device from IRQ routing table.  So at this point,
-	 * func->busno is correct, and func->device contains only device (at the 5 
+	 * func->busno is correct, and func->device contains only device (at the 5
 	 * highest bits)
 	 */
 
@@ -151,7 +151,7 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 						     cur_func->device, cur_func->busno);
 						cleanup_count = 6;
 						goto error;
-					}	
+					}
 					cur_func->next = NULL;
 					function = 0x8;
 					break;
@@ -339,7 +339,7 @@ error:
 }
 
 /*
- * This function configures the pci BARs of a single device.  
+ * This function configures the pci BARs of a single device.
  * Input: pointer to the pci_func
  * Output: configured PCI, 0, or error
  */
@@ -371,17 +371,17 @@ static int configure_device (struct pci_func *func)
 
 	for (count = 0; address[count]; count++) {	/* for 6 BARs */
 
-		/* not sure if i need this.  per scott, said maybe need smth like this
+		/* not sure if i need this.  per scott, said maybe need * something like this
 		   if devices don't adhere 100% to the spec, so don't want to write
 		   to the reserved bits
 
-		pcibios_read_config_byte(cur_func->busno, cur_func->device, 
+		pcibios_read_config_byte(cur_func->busno, cur_func->device,
 		PCI_BASE_ADDRESS_0 + 4 * count, &tmp);
 		if (tmp & 0x01) // IO
-			pcibios_write_config_dword(cur_func->busno, cur_func->device, 
+			pcibios_write_config_dword(cur_func->busno, cur_func->device,
 			PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFD);
 		else  // Memory
-			pcibios_write_config_dword(cur_func->busno, cur_func->device, 
+			pcibios_write_config_dword(cur_func->busno, cur_func->device,
 			PCI_BASE_ADDRESS_0 + 4 * count, 0xFFFFFFFF);
 		 */
 		pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], 0xFFFFFFFF);
@@ -421,8 +421,8 @@ static int configure_device (struct pci_func *func)
 				return -EIO;
 			}
 			pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->io[count]->start);
-	
-			/* _______________This is for debugging purposes only_____________________ */ 
+
+			/* _______________This is for debugging purposes only_____________________ */
 			debug ("b4 writing, the IO address is %x\n", func->io[count]->start);
 			pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
 			debug ("after writing.... the start address is %x\n", bar[count]);
@@ -484,7 +484,7 @@ static int configure_device (struct pci_func *func)
 
 				pci_bus_write_config_dword (ibmphp_pci_bus, devfn, address[count], func->pfmem[count]->start);
 
-				/*_______________This is for debugging purposes only______________________________*/				
+				/*_______________This is for debugging purposes only______________________________*/
 				debug ("b4 writing, start address is %x\n", func->pfmem[count]->start);
 				pci_bus_read_config_dword (ibmphp_pci_bus, devfn, address[count], &bar[count]);
 				debug ("after writing, start address is %x\n", bar[count]);
@@ -559,7 +559,7 @@ static int configure_device (struct pci_func *func)
 /******************************************************************************
  * This routine configures a PCI-2-PCI bridge and the functions behind it
  * Parameters: pci_func
- * Returns: 
+ * Returns:
  ******************************************************************************/
 static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 {
@@ -622,7 +622,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 	debug ("AFTER FIND_SEC_NUMBER, func->busno IS %x\n", func->busno);
 
 	pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, sec_number);
-	
+
 	/* __________________For debugging purposes only __________________________________
 	pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_number);
 	debug ("sec_number after write/read is %x\n", sec_number);
@@ -644,7 +644,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 
 
 	/* !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
-	   !!!!!!!!!!!!!!!NEED TO ADD!!!  FAST BACK-TO-BACK ENABLE!!!!!!!!!!!!!!!!!!!! 
+	   !!!!!!!!!!!!!!!NEED TO ADD!!!  FAST BACK-TO-BACK ENABLE!!!!!!!!!!!!!!!!!!!!
 	   !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!*/
 
 
@@ -670,7 +670,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 			debug ("len[count] in IO = %x\n", len[count]);
 
 			bus_io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL);
-		
+
 			if (!bus_io[count]) {
 				err ("out of system memory\n");
 				retval = -ENOMEM;
@@ -735,7 +735,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 						ibmphp_add_pfmem_from_mem (bus_pfmem[count]);
 						func->pfmem[count] = bus_pfmem[count];
 					} else {
-						err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n", 
+						err ("cannot allocate requested pfmem for bus %x, device %x, len %x\n",
 						     func->busno, func->device, len[count]);
 						kfree (mem_tmp);
 						kfree (bus_pfmem[count]);
@@ -805,7 +805,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 	debug ("amount_needed->mem = %x\n", amount_needed->mem);
 	debug ("amount_needed->pfmem =  %x\n", amount_needed->pfmem);
 
-	if (amount_needed->not_correct) {		
+	if (amount_needed->not_correct) {
 		debug ("amount_needed is not correct\n");
 		for (count = 0; address[count]; count++) {
 			/* for 2 BARs */
@@ -830,7 +830,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 	} else {
 		debug ("it wants %x IO behind the bridge\n", amount_needed->io);
 		io = kzalloc(sizeof(*io), GFP_KERNEL);
-		
+
 		if (!io) {
 			err ("out of system memory\n");
 			retval = -ENOMEM;
@@ -959,7 +959,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 
 		if (bus->noIORanges) {
 			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, 0x00 | bus->rangeIO->start >> 8);
-			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00 | bus->rangeIO->end >> 8);	
+			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_IO_LIMIT, 0x00 | bus->rangeIO->end >> 8);
 
 			/* _______________This is for debugging purposes only ____________________
 			pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_IO_BASE, &temp);
@@ -980,7 +980,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 		if (bus->noMemRanges) {
 			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, 0x0000 | bus->rangeMem->start >> 16);
 			pci_bus_write_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, 0x0000 | bus->rangeMem->end >> 16);
-			
+
 			/* ____________________This is for debugging purposes only ________________________
 			pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &temp);
 			debug ("mem_base = %x\n", (temp & PCI_MEMORY_RANGE_TYPE_MASK) << 16);
@@ -1017,7 +1017,7 @@ static int configure_bridge (struct pci_func **func_passed, u8 slotno)
 		pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_PIN, &irq);
 		if ((irq > 0x00) && (irq < 0x05))
 			pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_INTERRUPT_LINE, func->irq[irq - 1]);
-		/*    
+		/*
 		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, ctrl);
 		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_PARITY);
 		pci_bus_write_config_byte (ibmphp_pci_bus, devfn, PCI_BRIDGE_CONTROL, PCI_BRIDGE_CTL_SERR);
@@ -1071,7 +1071,7 @@ error:
  * This function adds up the amount of resources needed behind the PPB bridge
  * and passes it to the configure_bridge function
  * Input: bridge function
- * Ouput: amount of resources needed
+ * Output: amount of resources needed
  *****************************************************************************/
 static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
 {
@@ -1204,9 +1204,9 @@ static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
 	return amount;
 }
 
-/* The following 3 unconfigure_boot_ routines deal with the case when we had the card 
- * upon bootup in the system, since we don't allocate func to such case, we need to read 
- * the start addresses from pci config space and then find the corresponding entries in 
+/* The following 3 unconfigure_boot_ routines deal with the case when we had the card
+ * upon bootup in the system, since we don't allocate func to such case, we need to read
+ * the start addresses from pci config space and then find the corresponding entries in
  * our resource lists.  The functions return either 0, -ENODEV, or -1 (general failure)
  * Change: we also call these functions even if we configured the card ourselves (i.e., not
  * the bootup case), since it should work same way
@@ -1561,8 +1561,8 @@ static int unconfigure_boot_card (struct slot *slot_cur)
  * unconfiguring the device
  * TO DO:  will probably need to add some code in case there was some resource,
  * to remove it... this is from when we have errors in the configure_card...
- * 			!!!!!!!!!!!!!!!!!!!!!!!!!FOR BUSES!!!!!!!!!!!!
- * Returns: 0, -1, -ENODEV 
+ *			!!!!!!!!!!!!!!!!!!!!!!!!!FOR BUSES!!!!!!!!!!!!
+ * Returns: 0, -1, -ENODEV
  */
 int ibmphp_unconfigure_card (struct slot **slot_cur, int the_end)
 {
@@ -1634,7 +1634,7 @@ int ibmphp_unconfigure_card (struct slot **slot_cur, int the_end)
  * Input: bus and the amount of resources needed (we know we can assign those,
  *        since they've been checked already
  * Output: bus added to the correct spot
- *         0, -1, error 
+ *         0, -1, error
  */
 static int add_new_bus (struct bus_node *bus, struct resource_node *io, struct resource_node *mem, struct resource_node *pfmem, u8 parent_busno)
 {
@@ -1650,7 +1650,7 @@ static int add_new_bus (struct bus_node *bus, struct resource_node *io, struct r
 			err ("strange, cannot find bus which is supposed to be at the system... something is terribly wrong...\n");
 			return -ENODEV;
 		}
-	
+
 		list_add (&bus->bus_list, &cur_bus->bus_list);
 	}
 	if (io) {
@@ -1679,7 +1679,7 @@ static int add_new_bus (struct bus_node *bus, struct resource_node *io, struct r
 	}
 	if (pfmem) {
 		pfmem_range = kzalloc(sizeof(*pfmem_range), GFP_KERNEL);
-		if (!pfmem_range) {	
+		if (!pfmem_range) {
 			err ("out of system memory\n");
 			return -ENOMEM;
 		}
@@ -1726,4 +1726,3 @@ static u8 find_sec_number (u8 primary_busno, u8 slotno)
 		return busno;
 	return 0xff;
 }
-
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
index e2dc289f767c..a265acb2d518 100644
--- a/drivers/pci/hotplug/ibmphp_res.c
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -72,7 +72,7 @@ static struct bus_node * __init alloc_error_bus (struct ebda_pci_rsrc * curr, u8
 static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc * curr)
 {
 	struct resource_node *rs;
-	
+
 	if (!curr) {
 		err ("NULL passed to allocate\n");
 		return NULL;
@@ -128,7 +128,7 @@ static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node
 	}
 	newrange->start = curr->start_addr;
 	newrange->end = curr->end_addr;
-		
+
 	if (first_bus || (!num_ranges))
 		newrange->rangeno = 1;
 	else {
@@ -162,7 +162,7 @@ static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node
 			newbus->rangePFMem = newrange;
 			if (first_bus)
 				newbus->noPFMemRanges = 1;
-			else {	
+			else {
 				debug ("1st PFMemory Primary on Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
 				++newbus->noPFMemRanges;
 				fix_resources (newbus);
@@ -190,7 +190,7 @@ static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node
  * This is the Resource Management initialization function.  It will go through
  * the Resource list taken from EBDA and fill in this module's data structures
  *
- * THIS IS NOT TAKING INTO CONSIDERATION IO RESTRICTIONS OF PRIMARY BUSES, 
+ * THIS IS NOT TAKING INTO CONSIDERATION IO RESTRICTIONS OF PRIMARY BUSES,
  * SINCE WE'RE GOING TO ASSUME FOR NOW WE DON'T HAVE THOSE ON OUR BUSES FOR NOW
  *
  * Input: ptr to the head of the resource list from EBDA
@@ -382,7 +382,7 @@ int __init ibmphp_rsrc_init (void)
  * pci devices' resources for the appropriate resource
  *
  * Input: type of the resource, range to add, current bus
- * Output: 0 or -1, bus and range ptrs 
+ * Output: 0 or -1, bus and range ptrs
  ********************************************************************************/
 static int add_bus_range (int type, struct range_node *range, struct bus_node *bus_cur)
 {
@@ -466,7 +466,7 @@ static void update_resources (struct bus_node *bus_cur, int type, int rangeno)
 
 	switch (type) {
 		case MEM:
-			if (bus_cur->firstMem) 
+			if (bus_cur->firstMem)
 				res = bus_cur->firstMem;
 			break;
 		case PFMEM:
@@ -583,7 +583,7 @@ static void fix_resources (struct bus_node *bus_cur)
 }
 
 /*******************************************************************************
- * This routine adds a resource to the list of resources to the appropriate bus 
+ * This routine adds a resource to the list of resources to the appropriate bus
  * based on their resource type and sorted by their starting addresses.  It assigns
  * the ptrs to next and nextRange if needed.
  *
@@ -605,11 +605,11 @@ int ibmphp_add_resource (struct resource_node *res)
 		err ("NULL passed to add\n");
 		return -ENODEV;
 	}
-	
+
 	bus_cur = find_bus_wprev (res->busno, NULL, 0);
-	
+
 	if (!bus_cur) {
-		/* didn't find a bus, smth's wrong!!! */
+		/* didn't find a bus, something's wrong!!! */
 		debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
 		return -ENODEV;
 	}
@@ -648,7 +648,7 @@ int ibmphp_add_resource (struct resource_node *res)
 	if (!range_cur) {
 		switch (res->type) {
 			case IO:
-				++bus_cur->needIOUpdate;					
+				++bus_cur->needIOUpdate;
 				break;
 			case MEM:
 				++bus_cur->needMemUpdate;
@@ -659,13 +659,13 @@ int ibmphp_add_resource (struct resource_node *res)
 		}
 		res->rangeno = -1;
 	}
-	
+
 	debug ("The range is %d\n", res->rangeno);
 	if (!res_start) {
 		/* no first{IO,Mem,Pfmem} on the bus, 1st IO/Mem/Pfmem resource ever */
 		switch (res->type) {
 			case IO:
-				bus_cur->firstIO = res;					
+				bus_cur->firstIO = res;
 				break;
 			case MEM:
 				bus_cur->firstMem = res;
@@ -673,7 +673,7 @@ int ibmphp_add_resource (struct resource_node *res)
 			case PFMEM:
 				bus_cur->firstPFMem = res;
 				break;
-		}	
+		}
 		res->next = NULL;
 		res->nextRange = NULL;
 	} else {
@@ -770,7 +770,7 @@ int ibmphp_add_resource (struct resource_node *res)
  * This routine will remove the resource from the list of resources
  *
  * Input: io, mem, and/or pfmem resource to be deleted
- * Ouput: modified resource list
+ * Output: modified resource list
  *        0 or error code
  ****************************************************************************/
 int ibmphp_remove_resource (struct resource_node *res)
@@ -825,7 +825,7 @@ int ibmphp_remove_resource (struct resource_node *res)
 
 	if (!res_cur) {
 		if (res->type == PFMEM) {
-			/* 
+			/*
 			 * case where pfmem might be in the PFMemFromMem list
 			 * so will also need to remove the corresponding mem
 			 * entry
@@ -961,12 +961,12 @@ static struct range_node * find_range (struct bus_node *bus_cur, struct resource
 }
 
 /*****************************************************************************
- * This routine will check to make sure the io/mem/pfmem->len that the device asked for 
+ * This routine will check to make sure the io/mem/pfmem->len that the device asked for
  * can fit w/i our list of available IO/MEM/PFMEM resources.  If cannot, returns -EINVAL,
  * otherwise, returns 0
  *
  * Input: resource
- * Ouput: the correct start and end address are inputted into the resource node,
+ * Output: the correct start and end address are inputted into the resource node,
  *        0 or -EINVAL
  *****************************************************************************/
 int ibmphp_check_resource (struct resource_node *res, u8 bridge)
@@ -996,7 +996,7 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 	bus_cur = find_bus_wprev (res->busno, NULL, 0);
 
 	if (!bus_cur) {
-		/* didn't find a bus, smth's wrong!!! */
+		/* didn't find a bus, something's wrong!!! */
 		debug ("no bus in the system, either pci_dev's wrong or allocation failed\n");
 		return -EINVAL;
 	}
@@ -1066,7 +1066,7 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 								break;
 						}
 					}
-			
+
 					if (flag && len_cur == res->len) {
 						debug ("but we are not here, right?\n");
 						res->start = start_cur;
@@ -1118,10 +1118,10 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 		if (res_prev) {
 			if (res_prev->rangeno != res_cur->rangeno) {
 				/* 1st device on this range */
-				if ((res_cur->start != range->start) && 
+				if ((res_cur->start != range->start) &&
 					((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
 					if ((len_tmp < len_cur) || (len_cur == 0)) {
-						if ((range->start % tmp_divide) == 0) {	
+						if ((range->start % tmp_divide) == 0) {
 							/* just perfect, starting address is divisible by length */
 							flag = 1;
 							len_cur = len_tmp;
@@ -1344,7 +1344,7 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
  * This routine is called from remove_card if the card contained PPB.
  * It will remove all the resources on the bus as well as the bus itself
  * Input: Bus
- * Ouput: 0, -ENODEV
+ * Output: 0, -ENODEV
  ********************************************************************************/
 int ibmphp_remove_bus (struct bus_node *bus, u8 parent_busno)
 {
@@ -1353,7 +1353,7 @@ int ibmphp_remove_bus (struct bus_node *bus, u8 parent_busno)
 	struct bus_node *prev_bus;
 	int rc;
 
-	prev_bus = find_bus_wprev (parent_busno, NULL, 0);	
+	prev_bus = find_bus_wprev (parent_busno, NULL, 0);
 
 	if (!prev_bus) {
 		debug ("something terribly wrong. Cannot find parent bus to the one to remove\n");
@@ -1424,7 +1424,7 @@ int ibmphp_remove_bus (struct bus_node *bus, u8 parent_busno)
 }
 
 /******************************************************************************
- * This routine deletes the ranges from a given bus, and the entries from the 
+ * This routine deletes the ranges from a given bus, and the entries from the
  * parent's bus in the resources
  * Input: current bus, previous bus
  * Output: 0, -EINVAL
@@ -1453,7 +1453,7 @@ static int remove_ranges (struct bus_node *bus_cur, struct bus_node *bus_prev)
 	if (bus_cur->noMemRanges) {
 		range_cur = bus_cur->rangeMem;
 		for (i = 0; i < bus_cur->noMemRanges; i++) {
-			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, MEM) < 0) 
+			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, MEM) < 0)
 				return -EINVAL;
 
 			ibmphp_remove_resource (res);
@@ -1467,7 +1467,7 @@ static int remove_ranges (struct bus_node *bus_cur, struct bus_node *bus_prev)
 	if (bus_cur->noPFMemRanges) {
 		range_cur = bus_cur->rangePFMem;
 		for (i = 0; i < bus_cur->noPFMemRanges; i++) {
-			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, PFMEM) < 0) 
+			if (ibmphp_find_resource (bus_prev, range_cur->start, &res, PFMEM) < 0)
 				return -EINVAL;
 
 			ibmphp_remove_resource (res);
@@ -1482,7 +1482,7 @@ static int remove_ranges (struct bus_node *bus_cur, struct bus_node *bus_prev)
 }
 
 /*
- * find the resource node in the bus 
+ * find the resource node in the bus
  * Input: Resource needed, start address of the resource, type of resource
  */
 int ibmphp_find_resource (struct bus_node *bus, u32 start_address, struct resource_node **res, int flag)
@@ -1512,7 +1512,7 @@ int ibmphp_find_resource (struct bus_node *bus, u32 start_address, struct resour
 			err ("wrong type of flag\n");
 			return -EINVAL;
 	}
-	
+
 	while (res_cur) {
 		if (res_cur->start == start_address) {
 			*res = res_cur;
@@ -1718,7 +1718,7 @@ static int __init once_over (void)
 			}	/* end for pfmem */
 		}	/* end if */
 	}	/* end list_for_each bus */
-	return 0; 
+	return 0;
 }
 
 int ibmphp_add_pfmem_from_mem (struct resource_node *pfmem)
@@ -1760,9 +1760,9 @@ static struct bus_node *find_bus_wprev (u8 bus_number, struct bus_node **prev, u
 	list_for_each (tmp, &gbuses) {
 		tmp_prev = tmp->prev;
 		bus_cur = list_entry (tmp, struct bus_node, bus_list);
-		if (flag) 
+		if (flag)
 			*prev = list_entry (tmp_prev, struct bus_node, bus_list);
-		if (bus_cur->busno == bus_number) 
+		if (bus_cur->busno == bus_number)
 			return bus_cur;
 	}
 
@@ -1776,7 +1776,7 @@ void ibmphp_print_test (void)
 	struct range_node *range;
 	struct resource_node *res;
 	struct list_head *tmp;
-	
+
 	debug_pci ("*****************START**********************\n");
 
 	if ((!list_empty(&gbuses)) && flags) {
@@ -1906,7 +1906,7 @@ static int range_exists_already (struct range_node * range, struct bus_node * bu
 			return 1;
 		range_cur = range_cur->next;
 	}
-	
+
 	return 0;
 }
 
@@ -1920,7 +1920,7 @@ static int range_exists_already (struct range_node * range, struct bus_node * bu
  * Returns: none
  * Note: this function doesn't take into account IO restrictions etc,
  *	 so will only work for bridges with no video/ISA devices behind them It
- *	 also will not work for onboard PPB's that can have more than 1 *bus
+ *	 also will not work for onboard PPBs that can have more than 1 *bus
  *	 behind them All these are TO DO.
  *	 Also need to add more error checkings... (from fnc returns etc)
  */
@@ -1963,7 +1963,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 					case PCI_HEADER_TYPE_BRIDGE:
 						function = 0x8;
 					case PCI_HEADER_TYPE_MULTIBRIDGE:
-						/* We assume here that only 1 bus behind the bridge 
+						/* We assume here that only 1 bus behind the bridge
 						   TO DO: add functionality for several:
 						   temp = secondary;
 						   while (temp < subordinate) {
@@ -1972,7 +1972,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 						   }
 						 */
 						pci_bus_read_config_byte (ibmphp_pci_bus, devfn, PCI_SECONDARY_BUS, &sec_busno);
-						bus_sec = find_bus_wprev (sec_busno, NULL, 0); 
+						bus_sec = find_bus_wprev (sec_busno, NULL, 0);
 						/* this bus structure doesn't exist yet, PPB was configured during previous loading of ibmphp */
 						if (!bus_sec) {
 							bus_sec = alloc_error_bus (NULL, sec_busno, 1);
@@ -2028,7 +2028,7 @@ static int __init update_bridge_ranges (struct bus_node **bus)
 								io->len = io->end - io->start + 1;
 								ibmphp_add_resource (io);
 							}
-						}	
+						}
 
 						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_BASE, &start_mem_address);
 						pci_bus_read_config_word (ibmphp_pci_bus, devfn, PCI_MEMORY_LIMIT, &end_mem_address);
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index ec20f74c8981..cfa92a984e62 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -131,7 +131,7 @@ static ssize_t power_write_file(struct pci_slot *pci_slot, const char *buf,
 	}
 	module_put(slot->ops->owner);
 
-exit:	
+exit:
 	if (retval)
 		return retval;
 	return count;
@@ -177,7 +177,7 @@ static ssize_t attention_write_file(struct pci_slot *slot, const char *buf,
 		retval = ops->set_attention_status(slot->hotplug, attention);
 	module_put(ops->owner);
 
-exit:	
+exit:
 	if (retval)
 		return retval;
 	return count;
@@ -247,7 +247,7 @@ static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf,
 		retval = slot->ops->hardware_test(slot, test);
 	module_put(slot->ops->owner);
 
-exit:	
+exit:
 	if (retval)
 		return retval;
 	return count;
@@ -512,7 +512,7 @@ int pci_hp_deregister(struct hotplug_slot *hotplug)
  * @hotplug: pointer to the slot whose info has changed
  * @info: pointer to the info copy into the slot's info structure
  *
- * @slot must have been registered with the pci 
+ * @slot must have been registered with the pci
  * hotplug subsystem previously with a call to pci_hp_register().
  *
  * Returns 0 if successful, anything else for an error.
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 541bbe6d5343..21e865ded1dc 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -180,5 +180,5 @@ static inline int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
 {
 	return 0;
 }
-#endif 				/* CONFIG_ACPI */
+#endif				/* CONFIG_ACPI */
 #endif				/* _PCIEHP_H */
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
index ead7c534095e..55ea2a07f266 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -78,7 +78,7 @@ static int __initdata dup_slot_id;
 static int __initdata acpi_slot_detected;
 static struct list_head __initdata dummy_slots = LIST_HEAD_INIT(dummy_slots);
 
-/* Dummy driver for dumplicate name detection */
+/* Dummy driver for duplicate name detection */
 static int __init dummy_probe(struct pcie_device *dev)
 {
 	u32 slot_cap;
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index f4a18f51a29c..bbd48bbe4e9b 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -351,8 +351,8 @@ static int __init pcied_init(void)
 
 	pciehp_firmware_init();
 	retval = pcie_port_service_register(&hpdriver_portdrv);
- 	dbg("pcie_port_service_register = %d\n", retval);
-  	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
+	dbg("pcie_port_service_register = %d\n", retval);
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	if (retval)
 		dbg("Failure to register service\n");
 
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 51f56ef4ab6f..3eea3fdd4b0b 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -92,7 +92,7 @@ static void start_int_poll_timer(struct controller *ctrl, int sec)
 {
 	/* Clamp to sane value */
 	if ((sec <= 0) || (sec > 60))
-        	sec = 2;
+		sec = 2;
 
 	ctrl->poll_timer.function = &int_poll_timeout;
 	ctrl->poll_timer.data = (unsigned long)ctrl;
@@ -194,7 +194,7 @@ static int pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
 			ctrl_dbg(ctrl, "CMD_COMPLETED not clear after 1 sec\n");
 		} else if (!NO_CMD_CMPL(ctrl)) {
 			/*
-			 * This controller semms to notify of command completed
+			 * This controller seems to notify of command completed
 			 * event even though it supports none of power
 			 * controller, attention led, power led and EMI.
 			 */
@@ -926,7 +926,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 	if (pciehp_writew(ctrl, PCI_EXP_SLTSTA, 0x1f))
 		goto abort_ctrl;
 
-	/* Disable sotfware notification */
+	/* Disable software notification */
 	pcie_disable_notification(ctrl);
 
 	ctrl_info(ctrl, "HPC vendor_id %x device_id %x ss_vid %x ss_did %x\n",
diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c
index 1f00b937f721..ac69094e4b20 100644
--- a/drivers/pci/hotplug/pcihp_skeleton.c
+++ b/drivers/pci/hotplug/pcihp_skeleton.c
@@ -52,7 +52,7 @@ static LIST_HEAD(slot_list);
 	do {							\
 		if (debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
@@ -287,7 +287,7 @@ static int __init init_slots(void)
 		hotplug_slot->release = &release_slot;
 		make_slot_name(slot);
 		hotplug_slot->ops = &skel_hotplug_slot_ops;
-		
+
 		/*
 		 * Initialize the slot info structure with some known
 		 * good values.
@@ -296,7 +296,7 @@ static int __init init_slots(void)
 		get_attention_status(hotplug_slot, &info->attention_status);
 		get_latch_status(hotplug_slot, &info->latch_status);
 		get_adapter_status(hotplug_slot, &info->adapter_status);
-		
+
 		dbg("registering slot %d\n", i);
 		retval = pci_hp_register(slot->hotplug_slot);
 		if (retval) {
@@ -336,7 +336,7 @@ static void __exit cleanup_slots(void)
 		pci_hp_deregister(slot->hotplug_slot);
 	}
 }
-		
+
 static int __init pcihp_skel_init(void)
 {
 	int retval;
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index bb7af78e4eed..e9c044d15add 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -217,7 +217,7 @@ static int dlpar_remove_phb(char *drc_name, struct device_node *dn)
 	if (!pcibios_find_pci_bus(dn))
 		return -EINVAL;
 
-	/* If pci slot is hotplugable, use hotplug to remove it */
+	/* If pci slot is hotpluggable, use hotplug to remove it */
 	slot = find_php_slot(dn);
 	if (slot && rpaphp_deregister_slot(slot)) {
 		printk(KERN_ERR "%s: unable to remove hotplug slot %s\n",
diff --git a/drivers/pci/hotplug/rpaphp.h b/drivers/pci/hotplug/rpaphp.h
index 3135856e5e1c..b2593e876a09 100644
--- a/drivers/pci/hotplug/rpaphp.h
+++ b/drivers/pci/hotplug/rpaphp.h
@@ -49,9 +49,9 @@
 extern bool rpaphp_debug;
 #define dbg(format, arg...)					\
 	do {							\
-		if (rpaphp_debug)					\
+		if (rpaphp_debug)				\
 			printk(KERN_DEBUG "%s: " format,	\
-				MY_NAME , ## arg); 		\
+				MY_NAME , ## arg);		\
 	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format, MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format, MY_NAME , ## arg)
@@ -99,5 +99,5 @@ void dealloc_slot_struct(struct slot *slot);
 struct slot *alloc_slot_struct(struct device_node *dn, int drc_index, char *drc_name, int power_domain);
 int rpaphp_register_slot(struct slot *slot);
 int rpaphp_deregister_slot(struct slot *slot);
-	
+
 #endif				/* _PPC64PHP_H */
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index 127d6e600185..b7fc5c9255a5 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -226,7 +226,7 @@ int rpaphp_get_drc_props(struct device_node *dn, int *drc_index,
 	for (i = 0; i < indexes[0]; i++) {
 		if ((unsigned int) indexes[i + 1] == *my_index) {
 			if (drc_name)
-                		*drc_name = name_tmp;
+				*drc_name = name_tmp;
 			if (drc_type)
 				*drc_type = type_tmp;
 			if (drc_index)
@@ -289,7 +289,7 @@ static int is_php_dn(struct device_node *dn, const int **indexes,
  * rpaphp_add_slot -- declare a hotplug slot to the hotplug subsystem.
  * @dn: device node of slot
  *
- * This subroutine will register a hotplugable slot with the
+ * This subroutine will register a hotpluggable slot with the
  * PCI hotplug infrastructure. This routine is typically called
  * during boot time, if the hotplug slots are present at boot time,
  * or is called later, by the dlpar add code, if the slot is
@@ -328,7 +328,7 @@ int rpaphp_add_slot(struct device_node *dn)
 			return -ENOMEM;
 
 		slot->type = simple_strtoul(type, NULL, 10);
-				
+
 		dbg("Found drc-index:0x%x drc-name:%s drc-type:%s\n",
 				indexes[i + 1], name, type);
 
@@ -356,7 +356,7 @@ static void __exit cleanup_slots(void)
 	/*
 	 * Unregister all of our slots with the pci_hotplug subsystem,
 	 * and free up all memory that we had allocated.
-	 * memory will be freed in release_slot callback. 
+	 * memory will be freed in release_slot callback.
 	 */
 
 	list_for_each_safe(tmp, n, &rpaphp_slot_head) {
diff --git a/drivers/pci/hotplug/rpaphp_pci.c b/drivers/pci/hotplug/rpaphp_pci.c
index 513e1e282391..9243f3e7a1c9 100644
--- a/drivers/pci/hotplug/rpaphp_pci.c
+++ b/drivers/pci/hotplug/rpaphp_pci.c
@@ -44,7 +44,7 @@ int rpaphp_get_sensor_state(struct slot *slot, int *state)
 			dbg("%s: slot must be power up to get sensor-state\n",
 			    __func__);
 
-			/* some slots have to be powered up 
+			/* some slots have to be powered up
 			 * before get-sensor will succeed.
 			 */
 			rc = rtas_set_power_level(slot->power_domain, POWER_ON,
@@ -133,4 +133,3 @@ int rpaphp_enable_slot(struct slot *slot)
 
 	return 0;
 }
-
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index b283bbea6d24..a6082cc263f7 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -1,5 +1,5 @@
 /*
- * RPA Virtual I/O device functions 
+ * RPA Virtual I/O device functions
  * Copyright (C) 2004 Linda Xie <lxie@us.ibm.com>
  *
  * All rights reserved.
@@ -51,27 +51,27 @@ struct slot *alloc_slot_struct(struct device_node *dn,
                        int drc_index, char *drc_name, int power_domain)
 {
 	struct slot *slot;
-	
+
 	slot = kzalloc(sizeof(struct slot), GFP_KERNEL);
 	if (!slot)
 		goto error_nomem;
 	slot->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL);
 	if (!slot->hotplug_slot)
-		goto error_slot;	
+		goto error_slot;
 	slot->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info),
 					   GFP_KERNEL);
 	if (!slot->hotplug_slot->info)
 		goto error_hpslot;
 	slot->name = kstrdup(drc_name, GFP_KERNEL);
 	if (!slot->name)
-		goto error_info;	
+		goto error_info;
 	slot->dn = dn;
 	slot->index = drc_index;
 	slot->power_domain = power_domain;
 	slot->hotplug_slot->private = slot;
 	slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops;
 	slot->hotplug_slot->release = &rpaphp_release_slot;
-	
+
 	return (slot);
 
 error_info:
@@ -91,7 +91,7 @@ static int is_registered(struct slot *slot)
 	list_for_each_entry(tmp_slot, &rpaphp_slot_head, rpaphp_slot_list) {
 		if (!strcmp(tmp_slot->name, slot->name))
 			return 1;
-	}	
+	}
 	return 0;
 }
 
@@ -104,7 +104,7 @@ int rpaphp_deregister_slot(struct slot *slot)
 		__func__, slot->name);
 
 	list_del(&slot->rpaphp_slot_list);
-	
+
 	retval = pci_hp_deregister(php_slot);
 	if (retval)
 		err("Problem unregistering a slot %s\n", slot->name);
@@ -120,7 +120,7 @@ int rpaphp_register_slot(struct slot *slot)
 	int retval;
 	int slotno;
 
-	dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n", 
+	dbg("%s registering slot:path[%s] index[%x], name[%s] pdomain[%x] type[%d]\n",
 		__func__, slot->dn->full_name, slot->index, slot->name,
 		slot->power_domain, slot->type);
 
@@ -128,7 +128,7 @@ int rpaphp_register_slot(struct slot *slot)
 	if (is_registered(slot)) {
 		err("rpaphp_register_slot: slot[%s] is already registered\n", slot->name);
 		return -EAGAIN;
-	}	
+	}
 
 	if (slot->dn->child)
 		slotno = PCI_SLOT(PCI_DN(slot->dn->child)->devfn);
@@ -145,4 +145,3 @@ int rpaphp_register_slot(struct slot *slot)
 	info("Slot [%s] registered\n", slot->name);
 	return 0;
 }
-
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index d876e4b3c6a9..61529097464d 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -216,13 +216,13 @@ struct ctrl_reg {
 
 /* offsets to the controller registers based on the above structure layout */
 enum ctrl_offsets {
-	BASE_OFFSET 	 = offsetof(struct ctrl_reg, base_offset),
-	SLOT_AVAIL1 	 = offsetof(struct ctrl_reg, slot_avail1),
+	BASE_OFFSET	 = offsetof(struct ctrl_reg, base_offset),
+	SLOT_AVAIL1	 = offsetof(struct ctrl_reg, slot_avail1),
 	SLOT_AVAIL2	 = offsetof(struct ctrl_reg, slot_avail2),
-	SLOT_CONFIG 	 = offsetof(struct ctrl_reg, slot_config),
+	SLOT_CONFIG	 = offsetof(struct ctrl_reg, slot_config),
 	SEC_BUS_CONFIG	 = offsetof(struct ctrl_reg, sec_bus_config),
 	MSI_CTRL	 = offsetof(struct ctrl_reg, msi_ctrl),
-	PROG_INTERFACE 	 = offsetof(struct ctrl_reg, prog_interface),
+	PROG_INTERFACE	 = offsetof(struct ctrl_reg, prog_interface),
 	CMD		 = offsetof(struct ctrl_reg, cmd),
 	CMD_STATUS	 = offsetof(struct ctrl_reg, cmd_status),
 	INTR_LOC	 = offsetof(struct ctrl_reg, intr_loc),
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index d3f757df691c..faf13abd5b99 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -143,11 +143,11 @@ static int init_slots(struct controller *ctrl)
 		snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
 		hotplug_slot->ops = &shpchp_hotplug_slot_ops;
 
- 		ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
- 			 "hp_slot=%x sun=%x slot_device_offset=%x\n",
- 			 pci_domain_nr(ctrl->pci_dev->subordinate),
- 			 slot->bus, slot->device, slot->hp_slot, slot->number,
- 			 ctrl->slot_device_offset);
+		ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
+			 "hp_slot=%x sun=%x slot_device_offset=%x\n",
+			 pci_domain_nr(ctrl->pci_dev->subordinate),
+			 slot->bus, slot->device, slot->hp_slot, slot->number,
+			 ctrl->slot_device_offset);
 		retval = pci_hp_register(slot->hotplug_slot,
 				ctrl->pci_dev->subordinate, slot->device, name);
 		if (retval) {
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 75ba2311b54f..2d7f474ca0ec 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -116,7 +116,7 @@
 #define SLOT_REG_RSVDZ_MASK	((1 << 15) | (7 << 21))
 
 /*
- * SHPC Command Code definitnions
+ * SHPC Command Code definitions
  *
  *     Slot Operation				00h - 3Fh
  *     Set Bus Segment Speed/Mode A		40h - 47h
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 21a7182dccd4..1fe2d6fb19d5 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -610,7 +610,7 @@ resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno)
 	struct resource tmp;
 	enum pci_bar_type type;
 	int reg = pci_iov_resource_bar(dev, resno, &type);
-	
+
 	if (!reg)
 		return 0;
 
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index b008cf86b9c3..6684f153ab57 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -25,7 +25,7 @@ static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
 /**
  * pci_lost_interrupt - reports a lost PCI interrupt
  * @pdev:	device whose interrupt is lost
- * 
+ *
  * The primary function of this routine is to report a lost interrupt
  * in a standard way which users can recognise (instead of blaming the
  * driver).
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5e63645a7abe..3fcd67a16677 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -784,7 +784,7 @@ error:
  * @nvec: how many MSIs have been requested ?
  * @type: are we checking for MSI or MSI-X ?
  *
- * Look at global flags, the device itself, and its parent busses
+ * Look at global flags, the device itself, and its parent buses
  * to determine if MSI/-X are supported for the device. If MSI/-X is
  * supported return 0, else return an error code.
  **/
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index dfd1f59de729..92a49c2b1fda 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -141,7 +141,7 @@ phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle)
  * if (_PRW at S-state x)
  *	choose from highest power _SxD to lowest power _SxW
  * else // no _PRW at S-state x
- * 	choose highest power _SxD or any lower power
+ *	choose highest power _SxD or any lower power
  */
 
 static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 454853507b7e..9042fdbd7244 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -312,7 +312,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
  * __pci_device_probe - check if a driver wants to claim a specific PCI device
  * @drv: driver to call to check if it wants the PCI device
  * @pci_dev: PCI device being probed
- * 
+ *
  * returns 0 on success, else error.
  * side-effect: pci_dev->driver is set to drv when drv claims pci_dev.
  */
@@ -378,7 +378,7 @@ static int pci_device_remove(struct device * dev)
 	 * We would love to complain here if pci_dev->is_enabled is set, that
 	 * the driver should have called pci_disable_device(), but the
 	 * unfortunate fact is there are too many odd BIOS and bridge setups
-	 * that don't like drivers doing that all of the time.  
+	 * that don't like drivers doing that all of the time.
 	 * Oh well, we can dream of sane hardware when we sleep, no matter how
 	 * horrible the crap we have to deal with is when we are awake...
 	 */
@@ -1156,10 +1156,10 @@ static const struct dev_pm_ops pci_dev_pm_ops = {
  * @drv: the driver structure to register
  * @owner: owner module of drv
  * @mod_name: module name string
- * 
+ *
  * Adds the driver structure to the list of registered drivers.
- * Returns a negative value on error, otherwise 0. 
- * If no error occurred, the driver remains registered even if 
+ * Returns a negative value on error, otherwise 0.
+ * If no error occurred, the driver remains registered even if
  * no device was claimed during registration.
  */
 int __pci_register_driver(struct pci_driver *drv, struct module *owner,
@@ -1181,7 +1181,7 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
 /**
  * pci_unregister_driver - unregister a pci driver
  * @drv: the driver structure to unregister
- * 
+ *
  * Deletes the driver structure from the list of registered PCI drivers,
  * gives it a chance to clean up by calling its remove() function for
  * each device it was responsible for, and marks those devices as
@@ -1203,7 +1203,7 @@ static struct pci_driver pci_compat_driver = {
  * pci_dev_driver - get the pci_driver of a device
  * @dev: the device to query
  *
- * Returns the appropriate pci_driver structure or %NULL if there is no 
+ * Returns the appropriate pci_driver structure or %NULL if there is no
  * registered driver for the device.
  */
 struct pci_driver *
@@ -1224,7 +1224,7 @@ pci_dev_driver(const struct pci_dev *dev)
  * pci_bus_match - Tell if a PCI device structure has a matching PCI device id structure
  * @dev: the PCI device structure to match against
  * @drv: the device driver to search for matching PCI device id structures
- * 
+ *
  * Used by a driver to check whether a PCI device present in the
  * system is in its list of supported devices. Returns the matching
  * pci_device_id structure or %NULL if there is no match.
diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c
index 6e47c519c510..2ff77509d8e5 100644
--- a/drivers/pci/pci-stub.c
+++ b/drivers/pci/pci-stub.c
@@ -2,13 +2,13 @@
  *
  * Copyright (C) 2008 Red Hat, Inc.
  * Author:
- * 	Chris Wright
+ *	Chris Wright
  *
  * This work is licensed under the terms of the GNU GPL, version 2.
  *
  * Usage is simple, allocate a new id to the stub driver and bind the
  * device to it.  For example:
- * 
+ *
  * # echo "8086 10f5" > /sys/bus/pci/drivers/pci-stub/new_id
  * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
  * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/pci-stub/bind
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 2aaa83c85a4e..c91e6c18debc 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -10,7 +10,7 @@
  *
  * File attributes for PCI devices
  *
- * Modeled after usb's driverfs.c 
+ * Modeled after usb's driverfs.c
  *
  */
 
@@ -270,13 +270,17 @@ msi_bus_store(struct device *dev, struct device_attribute *attr,
 	if (kstrtoul(buf, 0, &val) < 0)
 		return -EINVAL;
 
-	/* bad things may happen if the no_msi flag is changed
-	 * while some drivers are loaded */
+	/*
+	 * Bad things may happen if the no_msi flag is changed
+	 * while drivers are loaded.
+	 */
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	/* Maybe pci devices without subordinate busses shouldn't even have this
-	 * attribute in the first place?  */
+	/*
+	 * Maybe devices without subordinate buses shouldn't have this
+	 * attribute in the first place?
+	 */
 	if (!pdev->subordinate)
 		return count;
 
@@ -670,7 +674,7 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 		size = dev->cfg_size - off;
 		count = size;
 	}
-	
+
 	pci_config_pm_runtime_get(dev);
 
 	if ((off & 1) && size) {
@@ -678,7 +682,7 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 		off++;
 		size--;
 	}
-	
+
 	if ((off & 3) && size > 2) {
 		u16 val = data[off - init_off];
 		val |= (u16) data[off - init_off + 1] << 8;
@@ -696,7 +700,7 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 		off += 4;
 		size -= 4;
 	}
-	
+
 	if (size >= 2) {
 		u16 val = data[off - init_off];
 		val |= (u16) data[off - init_off + 1] << 8;
@@ -1229,21 +1233,21 @@ pci_read_rom(struct file *filp, struct kobject *kobj,
 
 	if (!pdev->rom_attr_enabled)
 		return -EINVAL;
-	
+
 	rom = pci_map_rom(pdev, &size);	/* size starts out as PCI window size */
 	if (!rom || !size)
 		return -EIO;
-		
+
 	if (off >= size)
 		count = 0;
 	else {
 		if (off + count > size)
 			count = size - off;
-		
+
 		memcpy_fromio(buf, rom + off, count);
 	}
 	pci_unmap_rom(pdev, rom);
-		
+
 	return count;
 }
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b127fbda6fc8..33120d156668 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -198,7 +198,7 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus,
 }
 
 /**
- * pci_find_capability - query for devices' capabilities 
+ * pci_find_capability - query for devices' capabilities
  * @dev: PCI device to query
  * @cap: capability code
  *
@@ -207,12 +207,12 @@ static int __pci_bus_find_cap_start(struct pci_bus *bus,
  * device's PCI configuration space or 0 in case the device does not
  * support it.  Possible values for @cap:
  *
- *  %PCI_CAP_ID_PM           Power Management 
- *  %PCI_CAP_ID_AGP          Accelerated Graphics Port 
- *  %PCI_CAP_ID_VPD          Vital Product Data 
- *  %PCI_CAP_ID_SLOTID       Slot Identification 
+ *  %PCI_CAP_ID_PM           Power Management
+ *  %PCI_CAP_ID_AGP          Accelerated Graphics Port
+ *  %PCI_CAP_ID_VPD          Vital Product Data
+ *  %PCI_CAP_ID_SLOTID       Slot Identification
  *  %PCI_CAP_ID_MSI          Message Signalled Interrupts
- *  %PCI_CAP_ID_CHSWP        CompactPCI HotSwap 
+ *  %PCI_CAP_ID_CHSWP        CompactPCI HotSwap
  *  %PCI_CAP_ID_PCIX         PCI-X
  *  %PCI_CAP_ID_EXP          PCI Express
  */
@@ -228,13 +228,13 @@ int pci_find_capability(struct pci_dev *dev, int cap)
 }
 
 /**
- * pci_bus_find_capability - query for devices' capabilities 
+ * pci_bus_find_capability - query for devices' capabilities
  * @bus:   the PCI bus to query
  * @devfn: PCI device to query
  * @cap:   capability code
  *
  * Like pci_find_capability() but works for pci devices that do not have a
- * pci_dev structure set up yet. 
+ * pci_dev structure set up yet.
  *
  * Returns the address of the requested capability structure within the
  * device's PCI configuration space or 0 in case the device does not
@@ -515,7 +515,7 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
 		return -EINVAL;
 
 	/* Validate current state:
-	 * Can enter D0 from any state, but if we can only go deeper 
+	 * Can enter D0 from any state, but if we can only go deeper
 	 * to sleep if we're already in a low power state
 	 */
 	if (state != PCI_D0 && dev->current_state <= PCI_D3cold
@@ -998,7 +998,7 @@ static void pci_restore_config_space(struct pci_dev *pdev)
 	}
 }
 
-/** 
+/**
  * pci_restore_state - Restore the saved state of a PCI device
  * @dev: - PCI device that we're dealing with
  */
@@ -1030,7 +1030,7 @@ struct pci_saved_state {
  *			   the device saved state.
  * @dev: PCI device that we're dealing with
  *
- * Rerturn NULL if no state or error.
+ * Return NULL if no state or error.
  */
 struct pci_saved_state *pci_store_saved_state(struct pci_dev *dev)
 {
@@ -1880,7 +1880,7 @@ int pci_finish_runtime_suspend(struct pci_dev *dev)
  * pci_dev_run_wake - Check if device can generate run-time wake-up events.
  * @dev: Device to check.
  *
- * Return true if the device itself is cabable of generating wake-up events
+ * Return true if the device itself is capable of generating wake-up events
  * (through the platform or using the native PCIe PME) or if the device supports
  * PME and one of its upstream bridges can generate wake-up events.
  */
@@ -2447,7 +2447,7 @@ bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
 	switch (pci_pcie_type(pdev)) {
 	/*
 	 * PCI/X-to-PCIe bridges are not specifically mentioned by the spec,
-	 * but since their primary inteface is PCI/X, we conservatively
+	 * but since their primary interface is PCI/X, we conservatively
 	 * handle them as we would a non-PCIe device.
 	 */
 	case PCI_EXP_TYPE_PCIE_BRIDGE:
@@ -2471,7 +2471,7 @@ bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
 	/*
 	 * PCIe 3.0, 6.12.1.2 specifies ACS capabilities that should be
 	 * implemented by the remaining PCIe types to indicate peer-to-peer
-	 * capabilities, but only when they are part of a multifunciton
+	 * capabilities, but only when they are part of a multifunction
 	 * device.  The footnote for section 6.12 indicates the specific
 	 * PCIe types included here.
 	 */
@@ -2486,7 +2486,7 @@ bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
 	}
 
 	/*
-	 * PCIe 3.0, 6.12.1.3 specifies no ACS capabilties are applicable
+	 * PCIe 3.0, 6.12.1.3 specifies no ACS capabilities are applicable
 	 * to single function devices with the exception of downstream ports.
 	 */
 	return true;
@@ -2622,7 +2622,7 @@ void pci_release_region(struct pci_dev *pdev, int bar)
  *
  *	If @exclusive is set, then the region is marked so that userspace
  *	is explicitly not allowed to map the resource via /dev/mem or
- * 	sysfs MMIO access.
+ *	sysfs MMIO access.
  *
  *	Returns 0 on success, or %EBUSY on error.  A warning
  *	message is also printed on failure.
@@ -2634,7 +2634,7 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_n
 
 	if (pci_resource_len(pdev, bar) == 0)
 		return 0;
-		
+
 	if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) {
 		if (!request_region(pci_resource_start(pdev, bar),
 			    pci_resource_len(pdev, bar), res_name))
@@ -2694,7 +2694,7 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
  *
  *	The key difference that _exclusive makes it that userspace is
  *	explicitly not allowed to map the resource via /dev/mem or
- * 	sysfs.
+ *	sysfs.
  */
 int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name)
 {
@@ -2799,7 +2799,7 @@ int pci_request_regions(struct pci_dev *pdev, const char *res_name)
  *	successfully.
  *
  *	pci_request_regions_exclusive() will mark the region so that
- * 	/dev/mem and the sysfs MMIO access will not be allowed.
+ *	/dev/mem and the sysfs MMIO access will not be allowed.
  *
  *	Returns 0 on success, or %EBUSY on error.  A warning
  *	message is also printed on failure.
@@ -2967,7 +2967,7 @@ pci_set_mwi(struct pci_dev *dev)
 		cmd |= PCI_COMMAND_INVALIDATE;
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
-	
+
 	return 0;
 }
 
@@ -3292,7 +3292,7 @@ clear:
  *
  * NOTE: This causes the caller to sleep for twice the device power transition
  * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
- * by devault (i.e. unless the @dev's d3_delay field has a different value).
+ * by default (i.e. unless the @dev's d3_delay field has a different value).
  * Moreover, only devices in D0 can be reset by this function.
  */
 static int pci_pm_reset(struct pci_dev *dev, int probe)
@@ -3341,7 +3341,7 @@ void pci_reset_bridge_secondary_bus(struct pci_dev *dev)
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
 	/*
 	 * PCI spec v3.0 7.6.4.2 requires minimum Trst of 1ms.  Double
-	 * this to 2ms to ensure that we meet the minium requirement.
+	 * this to 2ms to ensure that we meet the minimum requirement.
 	 */
 	msleep(2);
 
@@ -3998,7 +3998,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps)
 		return -EINVAL;
 
 	v = ffs(mps) - 8;
-	if (v > dev->pcie_mpss) 
+	if (v > dev->pcie_mpss)
 		return -EINVAL;
 	v <<= 5;
 
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 85ca36f2136d..688e48e51073 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -525,7 +525,7 @@ static void handle_error_source(struct pcie_device *aerdev,
 
 	if (info->severity == AER_CORRECTABLE) {
 		/*
-		 * Correctable error does not need software intevention.
+		 * Correctable error does not need software intervention.
 		 * No need to go through error recovery process.
 		 */
 		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 403a44374ed5..f1272dc54de1 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -548,7 +548,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 
 /*
  * pcie_aspm_init_link_state: Initiate PCI express link state.
- * It is called after the pcie and its children devices are scaned.
+ * It is called after the pcie and its children devices are scanned.
  * @pdev: the root port or switch downstream port
  */
 void pcie_aspm_init_link_state(struct pci_dev *pdev)
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index e56e594ce112..bbc3bdd2b189 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -419,8 +419,8 @@ static void pcie_pme_remove(struct pcie_device *srv)
 
 static struct pcie_port_service_driver pcie_pme_driver = {
 	.name		= "pcie_pme",
-	.port_type 	= PCI_EXP_TYPE_ROOT_PORT,
-	.service 	= PCIE_PORT_SERVICE_PME,
+	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
+	.service	= PCIE_PORT_SERVICE_PME,
 
 	.probe		= pcie_pme_probe,
 	.suspend	= pcie_pme_suspend,
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index d2eb80aab569..d525548404d6 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -14,7 +14,7 @@
 #define PCIE_PORT_DEVICE_MAXSERVICES   4
 /*
  * According to the PCI Express Base Specification 2.0, the indices of
- * the MSI-X table entires used by port services must not exceed 31
+ * the MSI-X table entries used by port services must not exceed 31
  */
 #define PCIE_PORT_MAX_MSIX_ENTRIES	32
 
diff --git a/drivers/pci/pcie/portdrv_bus.c b/drivers/pci/pcie/portdrv_bus.c
index 67be55a7f260..87e79a6ffb5a 100644
--- a/drivers/pci/pcie/portdrv_bus.c
+++ b/drivers/pci/pcie/portdrv_bus.c
@@ -18,8 +18,8 @@
 static int pcie_port_bus_match(struct device *dev, struct device_driver *drv);
 
 struct bus_type pcie_port_bus_type = {
-	.name 		= "pci_express",
-	.match 		= pcie_port_bus_match,
+	.name		= "pci_express",
+	.match		= pcie_port_bus_match,
 };
 EXPORT_SYMBOL_GPL(pcie_port_bus_type);
 
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 08d131f7815b..0b6e76604068 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -46,7 +46,7 @@ static void release_pcie_device(struct device *dev)
  * pcie_port_msix_add_entry - add entry to given array of MSI-X entries
  * @entries: Array of MSI-X entries
  * @new_entry: Index of the entry to add to the array
- * @nr_entries: Number of entries aleady in the array
+ * @nr_entries: Number of entries already in the array
  *
  * Return value: Position of the added entry in the array
  */
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 696caed5fdf5..cd1e57e51aa7 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -390,9 +390,9 @@ static struct pci_driver pcie_portdriver = {
 	.probe		= pcie_portdrv_probe,
 	.remove		= pcie_portdrv_remove,
 
-	.err_handler 	= &pcie_portdrv_err_handler,
+	.err_handler	= &pcie_portdrv_err_handler,
 
-	.driver.pm 	= PCIE_PORTDRV_PM_OPS,
+	.driver.pm	= PCIE_PORTDRV_PM_OPS,
 };
 
 static int __init dmi_pcie_pme_disable_msi(const struct dmi_system_id *d)
@@ -412,7 +412,7 @@ static struct dmi_system_id __initdata pcie_portdrv_dmi_table[] = {
 	 .ident = "MSI Wind U-100",
 	 .matches = {
 		     DMI_MATCH(DMI_SYS_VENDOR,
-		     		"MICRO-STAR INTERNATIONAL CO., LTD"),
+				"MICRO-STAR INTERNATIONAL CO., LTD"),
 		     DMI_MATCH(DMI_PRODUCT_NAME, "U-100"),
 		     },
 	 },
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 5e14f5a51357..38e403dddf6e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -582,7 +582,7 @@ static enum pci_bus_speed agp_speed(int agp3, int agpstat)
 		index = 1;
 	else
 		goto out;
-	
+
 	if (agp3) {
 		index += 2;
 		if (index == 5)
@@ -789,7 +789,7 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 	}
 
 	/* Disable MasterAbortMode during probing to avoid reporting
-	   of bus errors (in some architectures) */ 
+	   of bus errors (in some architectures) */
 	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bctl);
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
 			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
@@ -1005,7 +1005,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev)
  * pci_setup_device - fill in class and map information of a device
  * @dev: the device structure to fill
  *
- * Initialize the device structure with information about the device's 
+ * Initialize the device structure with information about the device's
  * vendor,class,memory and IO-space addresses,IRQ lines etc.
  * Called at initialisation of the PCI subsystem and by CardBus services.
  * Returns 0 on success and negative if unknown type of device (not normal,
@@ -1111,7 +1111,7 @@ int pci_setup_device(struct pci_dev *dev)
 			goto bad;
 		/* The PCI-to-PCI bridge spec requires that subtractive
 		   decoding (i.e. transparent) bridge must have programming
-		   interface code of 0x01. */ 
+		   interface code of 0x01. */
 		pci_read_irq(dev);
 		dev->transparent = ((dev->class & 0xff) == 1);
 		pci_read_bases(dev, 2, PCI_ROM_ADDRESS1);
@@ -1570,7 +1570,7 @@ static void pcie_write_mrrs(struct pci_dev *dev)
 	 * subsequent read will verify if the value is acceptable or not.
 	 * If the MRRS value provided is not acceptable (e.g., too large),
 	 * shrink the value until it is acceptable to the HW.
- 	 */
+	 */
 	while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) {
 		rc = pcie_set_readrq(dev, mrrs);
 		if (!rc)
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index cdc7836d7e3d..46d1378f2e9e 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -222,7 +222,7 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 	default:
 		ret = -EINVAL;
 		break;
-	};
+	}
 
 	return ret;
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 91490453c229..b3b1b9aa8863 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -55,7 +55,7 @@ static void quirk_mellanox_tavor(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR,quirk_mellanox_tavor);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE,quirk_mellanox_tavor);
 
-/* Deal with broken BIOS'es that neglect to enable passive release,
+/* Deal with broken BIOSes that neglect to enable passive release,
    which can cause problems in combination with the 82441FX/PPro MTRRs */
 static void quirk_passive_release(struct pci_dev *dev)
 {
@@ -78,11 +78,11 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_p
 
 /*  The VIA VP2/VP3/MVP3 seem to have some 'features'. There may be a workaround
     but VIA don't answer queries. If you happen to have good contacts at VIA
-    ask them for me please -- Alan 
-    
-    This appears to be BIOS not version dependent. So presumably there is a 
+    ask them for me please -- Alan
+
+    This appears to be BIOS not version dependent. So presumably there is a
     chipset level fix */
-    
+
 static void quirk_isa_dma_hangs(struct pci_dev *dev)
 {
 	if (!isa_dma_bridge_buggy) {
@@ -97,7 +97,7 @@ static void quirk_isa_dma_hangs(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C586_0,	quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C596,	quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82371SB_0,  quirk_isa_dma_hangs);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1533, 	quirk_isa_dma_hangs);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1533,		quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_1,	quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_2,	quirk_isa_dma_hangs);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NEC,	PCI_DEVICE_ID_NEC_CBUS_3,	quirk_isa_dma_hangs);
@@ -157,10 +157,10 @@ static void quirk_triton(struct pci_dev *dev)
 		pci_pci_problems |= PCIPCI_TRITON;
 	}
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82437, 	quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82437VX, 	quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439, 	quirk_triton);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439TX, 	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82437,	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82437VX,	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82439,	quirk_triton);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82439TX,	quirk_triton);
 
 /*
  *	VIA Apollo KT133 needs PCI latency patch
@@ -171,7 +171,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82439TX, 	quir
  *      the info on which Mr Breese based his work.
  *
  *	Updated based on further information from the site and also on
- *	information provided by VIA 
+ *	information provided by VIA
  */
 static void quirk_vialatency(struct pci_dev *dev)
 {
@@ -179,7 +179,7 @@ static void quirk_vialatency(struct pci_dev *dev)
 	u8 busarb;
 	/* Ok we have a potential problem chipset here. Now see if we have
 	   a buggy southbridge */
-	   
+
 	p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, NULL);
 	if (p!=NULL) {
 		/* 0x40 - 0x4f == 686B, 0x10 - 0x2f == 686A; thanks Dan Hollis */
@@ -194,9 +194,9 @@ static void quirk_vialatency(struct pci_dev *dev)
 		if (p->revision < 0x10 || p->revision > 0x12)
 			goto exit;
 	}
-	
+
 	/*
-	 *	Ok we have the problem. Now set the PCI master grant to 
+	 *	Ok we have the problem. Now set the PCI master grant to
 	 *	occur every master grant. The apparent bug is that under high
 	 *	PCI load (quite common in Linux of course) you can get data
 	 *	loss when the CPU is held off the bus for 3 bus master requests
@@ -209,7 +209,7 @@ static void quirk_vialatency(struct pci_dev *dev)
 	 */
 
 	pci_read_config_byte(dev, 0x76, &busarb);
-	/* Set bit 4 and bi 5 of byte 76 to 0x01 
+	/* Set bit 4 and bi 5 of byte 76 to 0x01
 	   "Master priority rotation on every PCI master grant */
 	busarb &= ~(1<<5);
 	busarb |= (1<<4);
@@ -252,7 +252,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C576,	quirk_vsfx)
  *	that DMA to AGP space. Latency must be set to 0xA and triton
  *	workaround applied too
  *	[Info kindly provided by ALi]
- */	
+ */
 static void quirk_alimagik(struct pci_dev *dev)
 {
 	if ((pci_pci_problems&PCIPCI_ALIMAGIK)==0) {
@@ -260,8 +260,8 @@ static void quirk_alimagik(struct pci_dev *dev)
 		pci_pci_problems |= PCIPCI_ALIMAGIK|PCIPCI_TRITON;
 	}
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 	PCI_DEVICE_ID_AL_M1647, 	quirk_alimagik);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 	PCI_DEVICE_ID_AL_M1651, 	quirk_alimagik);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1647,		quirk_alimagik);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1651,		quirk_alimagik);
 
 /*
  *	Natoma has some interesting boundary conditions with Zoran stuff
@@ -274,12 +274,12 @@ static void quirk_natoma(struct pci_dev *dev)
 		pci_pci_problems |= PCIPCI_NATOMA;
 	}
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82441, 	quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443LX_0, 	quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443LX_1, 	quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_0, 	quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_1, 	quirk_natoma);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 	PCI_DEVICE_ID_INTEL_82443BX_2, 	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443LX_0,	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443LX_1,	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443BX_0,	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443BX_1,	quirk_natoma);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82443BX_2,	quirk_natoma);
 
 /*
  *  This chip can cause PCI parity errors if config register 0xA0 is read
@@ -400,7 +400,7 @@ static void piix4_io_quirk(struct pci_dev *dev, const char *name, unsigned int p
 	/*
 	 * For now we only print it out. Eventually we'll want to
 	 * reserve it (at least if it's in the 0x1000+ range), but
-	 * let's get enough confirmation reports first. 
+	 * let's get enough confirmation reports first.
 	 */
 	base &= -size;
 	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base + size - 1);
@@ -425,7 +425,7 @@ static void piix4_mem_quirk(struct pci_dev *dev, const char *name, unsigned int
 	}
 	/*
 	 * For now we only print it out. Eventually we'll want to
-	 * reserve it, but let's get enough confirmation reports first. 
+	 * reserve it, but let's get enough confirmation reports first.
 	 */
 	base &= -size;
 	dev_info(&dev->dev, "%s MMIO at %04x-%04x\n", name, base, base + size - 1);
@@ -682,7 +682,7 @@ static void quirk_xio2000a(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_XIO2000A,
 			quirk_xio2000a);
 
-#ifdef CONFIG_X86_IO_APIC 
+#ifdef CONFIG_X86_IO_APIC
 
 #include <asm/io_apic.h>
 
@@ -696,12 +696,12 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_XIO2000A,
 static void quirk_via_ioapic(struct pci_dev *dev)
 {
 	u8 tmp;
-	
+
 	if (nr_ioapics < 1)
 		tmp = 0;    /* nothing routed to external APIC */
 	else
 		tmp = 0x1f; /* all known bits (4-0) routed to external APIC */
-		
+
 	dev_info(&dev->dev, "%sbling VIA external APIC routing\n",
 	       tmp == 0 ? "Disa" : "Ena");
 
@@ -712,7 +712,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_i
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_ioapic);
 
 /*
- * VIA 8237: Some BIOSs don't set the 'Bypass APIC De-Assert Message' Bit.
+ * VIA 8237: Some BIOSes don't set the 'Bypass APIC De-Assert Message' Bit.
  * This leads to doubled level interrupt rates.
  * Set this bit to get rid of cycle wastage.
  * Otherwise uncritical.
@@ -986,7 +986,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_CYRIX,	PCI_DEVICE_ID_CYRIX_PCI_MASTER, qu
 static void quirk_disable_pxb(struct pci_dev *pdev)
 {
 	u16 config;
-	
+
 	if (pdev->revision != 0x04)		/* Only C0 requires this */
 		return;
 	pci_read_config_word(pdev, 0x40, &config);
@@ -1094,11 +1094,11 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82375,	quirk_e
  * On ASUS P4B boards, the SMBus PCI Device within the ICH2/4 southbridge
  * is not activated. The myth is that Asus said that they do not want the
  * users to be irritated by just another PCI Device in the Win98 device
- * manager. (see the file prog/hotplug/README.p4b in the lm_sensors 
+ * manager. (see the file prog/hotplug/README.p4b in the lm_sensors
  * package 2.7.0 for details)
  *
- * The SMBus PCI Device can be activated by setting a bit in the ICH LPC 
- * bridge. Unfortunately, this device has no subvendor/subdevice ID. So it 
+ * The SMBus PCI Device can be activated by setting a bit in the ICH LPC
+ * bridge. Unfortunately, this device has no subvendor/subdevice ID. So it
  * becomes necessary to do this tweak in two steps -- the chosen trigger
  * is either the Host bridge (preferred) or on-board VGA controller.
  *
@@ -1253,7 +1253,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82815_CGC,	asu
 static void asus_hides_smbus_lpc(struct pci_dev *dev)
 {
 	u16 val;
-	
+
 	if (likely(!asus_hides_smbus))
 		return;
 
@@ -1640,8 +1640,8 @@ static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev)
 	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
 		 dev->vendor, dev->device);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10,	quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10,	quirk_disable_intel_boot_interrupt);
 
 /*
  * disable boot interrupts on HT-1000
@@ -1673,8 +1673,8 @@ static void quirk_disable_broadcom_boot_interrupt(struct pci_dev *dev)
 	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
 		 dev->vendor, dev->device);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB,	quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB,	quirk_disable_broadcom_boot_interrupt);
 
 /*
  * disable boot interrupts on AMD and ATI chipsets
@@ -1730,8 +1730,8 @@ static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev)
 	dev_info(&dev->dev, "disabled boot interrupts on device [%04x:%04x]\n",
 		 dev->vendor, dev->device);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS,	quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS,	quirk_disable_amd_8111_boot_interrupt);
 #endif /* CONFIG_X86_IO_APIC */
 
 /*
@@ -2127,8 +2127,8 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_PLX, 0x8624, quirk_tile_plx_gen1);
 #ifdef CONFIG_PCI_MSI
 /* Some chipsets do not support MSI. We cannot easily rely on setting
  * PCI_BUS_FLAGS_NO_MSI in its bus flags because there are actually
- * some other busses controlled by the chipset even if Linux is not
- * aware of it.  Instead of setting the flag on all busses in the
+ * some other buses controlled by the chipset even if Linux is not
+ * aware of it.  Instead of setting the flag on all buses in the
  * machine, simply disable MSI globally.
  */
 static void quirk_disable_all_msi(struct pci_dev *dev)
@@ -2288,14 +2288,14 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
 			nvenet_msi_disable);
 
 /*
- * Some versions of the MCP55 bridge from nvidia have a legacy irq routing
- * config register.  This register controls the routing of legacy interrupts
- * from devices that route through the MCP55.  If this register is misprogramed
- * interrupts are only sent to the bsp, unlike conventional systems where the
- * irq is broadxast to all online cpus.  Not having this register set
- * properly prevents kdump from booting up properly, so lets make sure that
- * we have it set correctly.
- * Note this is an undocumented register.
+ * Some versions of the MCP55 bridge from Nvidia have a legacy IRQ routing
+ * config register.  This register controls the routing of legacy
+ * interrupts from devices that route through the MCP55.  If this register
+ * is misprogrammed, interrupts are only sent to the BSP, unlike
+ * conventional systems where the IRQ is broadcast to all online CPUs.  Not
+ * having this register set properly prevents kdump from booting up
+ * properly, so let's make sure that we have it set correctly.
+ * Note that this is an undocumented register.
  */
 static void nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
 {
@@ -2626,7 +2626,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, 0xe091,
 /* Allow manual resource allocation for PCI hotplug bridges
  * via pci=hpmemsize=nnM and pci=hpiosize=nnM parameters. For
  * some PCI-PCI hotplug bridges, like PLX 6254 (former HINT HB6),
- * kernel fails to allocate resources when hotplug device is 
+ * kernel fails to allocate resources when hotplug device is
  * inserted and PCI bus is rescanned.
  */
 static void quirk_hotplug_bridge(struct pci_dev *dev)
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 8fc54b7327bc..1576851028db 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -7,7 +7,7 @@ static void pci_free_resources(struct pci_dev *dev)
 {
 	int i;
 
- 	msi_remove_pci_irq_vectors(dev);
+	msi_remove_pci_irq_vectors(dev);
 
 	pci_cleanup_rom(dev);
 	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index d0627fa9f368..3ff2ac7c14e2 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -1,5 +1,5 @@
 /*
- * 	PCI searching functions.
+ *	PCI searching functions.
  *
  *	Copyright (C) 1993 -- 1997 Drew Eckhardt, Frederic Potter,
  *					David Mosberger-Tang
@@ -96,12 +96,12 @@ struct pci_bus * pci_find_bus(int domain, int busnr)
  * pci_find_next_bus - begin or continue searching for a PCI bus
  * @from: Previous PCI bus found, or %NULL for new search.
  *
- * Iterates through the list of known PCI busses.  A new search is
+ * Iterates through the list of known PCI buses.  A new search is
  * initiated by passing %NULL as the @from argument.  Otherwise if
  * @from is not %NULL, searches continue from next device on the
  * global list.
  */
-struct pci_bus * 
+struct pci_bus *
 pci_find_next_bus(const struct pci_bus *from)
 {
 	struct list_head *n;
@@ -119,11 +119,11 @@ pci_find_next_bus(const struct pci_bus *from)
 /**
  * pci_get_slot - locate PCI device for a given PCI slot
  * @bus: PCI bus on which desired PCI device resides
- * @devfn: encodes number of PCI slot in which the desired PCI 
- * device resides and the logical device number within that slot 
+ * @devfn: encodes number of PCI slot in which the desired PCI
+ * device resides and the logical device number within that slot
  * in case of multi-function devices.
  *
- * Given a PCI bus and slot/function number, the desired PCI device 
+ * Given a PCI bus and slot/function number, the desired PCI device
  * is located in the list of PCI devices.
  * If the device is found, its reference count is increased and this
  * function returns a pointer to its data structure.  The caller must
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 4ce83b26ae9e..219a4106480a 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -292,8 +292,8 @@ static void assign_requested_resources_sorted(struct list_head *head,
 				      (!(res->flags & IORESOURCE_ROM_ENABLE))))
 					add_to_list(fail_head,
 						    dev_res->dev, res,
-						    0 /* dont care */,
-						    0 /* dont care */);
+						    0 /* don't care */,
+						    0 /* don't care */);
 			}
 			reset_resource(res);
 		}
@@ -667,9 +667,9 @@ static void pci_bridge_check_ranges(struct pci_bus *bus)
 	if (!io) {
 		pci_write_config_word(bridge, PCI_IO_BASE, 0xf0f0);
 		pci_read_config_word(bridge, PCI_IO_BASE, &io);
- 		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
- 	}
- 	if (io)
+		pci_write_config_word(bridge, PCI_IO_BASE, 0x0);
+	}
+	if (io)
 		b_res[0].flags |= IORESOURCE_IO;
 	/*  DECchip 21050 pass 2 errata: the bridge may miss an address
 	    disconnect boundary by one PCI data phase.
@@ -819,7 +819,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
 	resource_size_t min_align, align;
 
 	if (!b_res)
- 		return;
+		return;
 
 	min_align = window_alignment(bus, IORESOURCE_IO);
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -950,7 +950,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (realloc_head && i >= PCI_IOV_RESOURCES &&
 					i <= PCI_IOV_RESOURCE_END) {
 				r->end = r->start - 1;
-				add_to_list(realloc_head, dev, r, r_size, 0/* dont' care */);
+				add_to_list(realloc_head, dev, r, r_size, 0/* don't care */);
 				children_add_size += r_size;
 				continue;
 			}
@@ -1456,8 +1456,8 @@ static enum enable_type pci_realloc_detect(struct pci_bus *bus,
 
 /*
  * first try will not touch pci bridge res
- * second  and later try will clear small leaf bridge res
- * will stop till to the max  deepth if can not find good one
+ * second and later try will clear small leaf bridge res
+ * will stop till to the max depth if can not find good one
  */
 void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
 {
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 07f2eddc09ce..83c4d3bc47ab 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -159,7 +159,7 @@ resource_size_t __weak pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx)
 	return 0;
 }
 
-static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, 
+static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 		int resno, resource_size_t size)
 {
 	struct resource *root, *conflict;
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index c1e9284a677b..448ca562d1f8 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -53,7 +53,7 @@ static ssize_t address_read_file(struct pci_slot *slot, char *buf)
 static const char *pci_bus_speed_strings[] = {
 	"33 MHz PCI",		/* 0x00 */
 	"66 MHz PCI",		/* 0x01 */
-	"66 MHz PCI-X", 	/* 0x02 */
+	"66 MHz PCI-X",		/* 0x02 */
 	"100 MHz PCI-X",	/* 0x03 */
 	"133 MHz PCI-X",	/* 0x04 */
 	NULL,			/* 0x05 */
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index e1c1ec540893..24750a1b39b6 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -44,7 +44,7 @@ SYSCALL_DEFINE5(pciconfig_read, unsigned long, bus, unsigned long, dfn,
 	default:
 		err = -EINVAL;
 		goto error;
-	};
+	}
 
 	err = -EIO;
 	if (cfg_ret != PCIBIOS_SUCCESSFUL)
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 87cce50bd121..009b02481436 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -26,11 +26,11 @@ struct msi_desc {
 	struct {
 		__u8	is_msix	: 1;
 		__u8	multiple: 3;	/* log2 number of messages */
-		__u8	maskbit	: 1; 	/* mask-pending bit supported ?   */
-		__u8	is_64	: 1;	/* Address size: 0=32bit 1=64bit  */
-		__u8	pos;	 	/* Location of the msi capability */
-		__u16	entry_nr;    	/* specific enabled entry 	  */
-		unsigned default_irq;	/* default pre-assigned irq	  */
+		__u8	maskbit	: 1;	/* mask-pending bit supported ? */
+		__u8	is_64	: 1;	/* Address size: 0=32bit 1=64bit */
+		__u8	pos;		/* Location of the msi capability */
+		__u16	entry_nr;	/* specific enabled entry */
+		unsigned default_irq;	/* default pre-assigned irq */
 	} msi_attrib;
 
 	u32 masked;			/* mask bits */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835ec7bf6c05..1084a15175e0 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -32,7 +32,6 @@
 #include <linux/irqreturn.h>
 #include <uapi/linux/pci.h>
 
-/* Include the ID list */
 #include <linux/pci_ids.h>
 
 /*
@@ -42,9 +41,10 @@
  *
  *	7:3 = slot
  *	2:0 = function
- * PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() are defined uapi/linux/pci.h
+ *
+ * PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() are defined in uapi/linux/pci.h.
  * In the interest of not exposing interfaces to user-space unnecessarily,
- * the following kernel only defines are being added here.
+ * the following kernel-only defines are being added here.
  */
 #define PCI_DEVID(bus, devfn)  ((((u16)bus) << 8) | devfn)
 /* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */
@@ -153,10 +153,10 @@ enum pcie_reset_state {
 	/* Reset is NOT asserted (Use to deassert reset) */
 	pcie_deassert_reset = (__force pcie_reset_state_t) 1,
 
-	/* Use #PERST to reset PCI-E device */
+	/* Use #PERST to reset PCIe device */
 	pcie_warm_reset = (__force pcie_reset_state_t) 2,
 
-	/* Use PCI-E Hot Reset to reset device */
+	/* Use PCIe Hot Reset to reset device */
 	pcie_hot_reset = (__force pcie_reset_state_t) 3
 };
 
@@ -259,13 +259,13 @@ struct pci_dev {
 	unsigned int	class;		/* 3 bytes: (base,sub,prog-if) */
 	u8		revision;	/* PCI revision, low byte of class word */
 	u8		hdr_type;	/* PCI header type (`multi' flag masked out) */
-	u8		pcie_cap;	/* PCI-E capability offset */
+	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
 	u8		msix_cap;	/* MSI-X capability offset */
-	u8		pcie_mpss:3;	/* PCI-E Max Payload Size Supported */
+	u8		pcie_mpss:3;	/* PCIe Max Payload Size Supported */
 	u8		rom_base_reg;	/* which config register controls the ROM */
-	u8		pin;  		/* which interrupt pin this device uses */
-	u16		pcie_flags_reg;	/* cached PCI-E Capabilities Register */
+	u8		pin;		/* which interrupt pin this device uses */
+	u16		pcie_flags_reg;	/* cached PCIe Capabilities Register */
 
 	struct pci_driver *driver;	/* which driver has allocated this device */
 	u64		dma_mask;	/* Mask of the bits of bus address this
@@ -300,7 +300,7 @@ struct pci_dev {
 	unsigned int	d3cold_delay;	/* D3cold->D0 transition time in ms */
 
 #ifdef CONFIG_PCIEASPM
-	struct pcie_link_state	*link_state;	/* ASPM link state. */
+	struct pcie_link_state	*link_state;	/* ASPM link state */
 #endif
 
 	pci_channel_state_t error_state;	/* current connectivity state */
@@ -317,7 +317,7 @@ struct pci_dev {
 
 	bool match_driver;		/* Skip attaching driver */
 	/* These fields are used by common fixups */
-	unsigned int	transparent:1;	/* Transparent PCI bridge */
+	unsigned int	transparent:1;	/* Subtractive decode PCI bridge */
 	unsigned int	multifunction:1;/* Part of multi-function device */
 	/* keep track of device state */
 	unsigned int	is_added:1;
@@ -326,7 +326,7 @@ struct pci_dev {
 	unsigned int	block_cfg_access:1;	/* config space access is blocked */
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int	irq_reroute_variant:2;	/* device needs IRQ rerouting variant */
-	unsigned int 	msi_enabled:1;
+	unsigned int	msi_enabled:1;
 	unsigned int	msix_enabled:1;
 	unsigned int	ari_enabled:1;	/* ARI forwarding */
 	unsigned int	is_managed:1;
@@ -371,7 +371,6 @@ static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
 	if (dev->is_virtfn)
 		dev = dev->physfn;
 #endif
-
 	return dev;
 }
 
@@ -456,7 +455,7 @@ struct pci_bus {
 	char		name[48];
 
 	unsigned short  bridge_ctl;	/* manage NO_ISA/FBB/et al behaviors */
-	pci_bus_flags_t bus_flags;	/* Inherited by child busses */
+	pci_bus_flags_t bus_flags;	/* inherited by child buses */
 	struct device		*bridge;
 	struct device		dev;
 	struct bin_attribute	*legacy_io; /* legacy I/O for this bus */
@@ -468,7 +467,7 @@ struct pci_bus {
 #define to_pci_bus(n)	container_of(n, struct pci_bus, dev)
 
 /*
- * Returns true if the pci bus is root (behind host-pci bridge),
+ * Returns true if the PCI bus is root (behind host-PCI bridge),
  * false otherwise
  *
  * Some code assumes that "bus->self == NULL" means that bus is a root bus.
@@ -510,7 +509,7 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false;
 #define PCIBIOS_BUFFER_TOO_SMALL	0x89
 
 /*
- * Translate above to generic errno for passing back through non-pci.
+ * Translate above to generic errno for passing back through non-PCI code.
  */
 static inline int pcibios_err_to_errno(int err)
 {
@@ -561,11 +560,12 @@ struct pci_dynids {
 	struct list_head list;      /* for IDs added at runtime */
 };
 
-/* ---------------------------------------------------------------- */
-/** PCI Error Recovery System (PCI-ERS).  If a PCI device driver provides
- *  a set of callbacks in struct pci_error_handlers, then that device driver
- *  will be notified of PCI bus errors, and will be driven to recovery
- *  when an error occurs.
+
+/*
+ * PCI Error Recovery System (PCI-ERS).  If a PCI device driver provides
+ * a set of callbacks in struct pci_error_handlers, that device driver
+ * will be notified of PCI bus errors, and will be driven to recovery
+ * when an error occurs.
  */
 
 typedef unsigned int __bitwise pci_ers_result_t;
@@ -609,7 +609,6 @@ struct pci_error_handlers {
 	void (*resume)(struct pci_dev *dev);
 };
 
-/* ---------------------------------------------------------------- */
 
 struct module;
 struct pci_driver {
@@ -713,10 +712,10 @@ extern enum pcie_bus_config_types pcie_bus_config;
 
 extern struct bus_type pci_bus_type;
 
-/* Do NOT directly access these two variables, unless you are arch specific pci
- * code, or pci core code. */
+/* Do NOT directly access these two variables, unless you are arch-specific PCI
+ * code, or PCI core code. */
 extern struct list_head pci_root_buses;	/* list of all known PCI buses */
-/* Some device drivers need know if pci is initiated */
+/* Some device drivers need know if PCI is initiated */
 int no_pci_devices(void);
 
 void pcibios_resource_survey_bus(struct pci_bus *bus);
@@ -724,7 +723,7 @@ void pcibios_add_bus(struct pci_bus *bus);
 void pcibios_remove_bus(struct pci_bus *bus);
 void pcibios_fixup_bus(struct pci_bus *);
 int __must_check pcibios_enable_device(struct pci_dev *, int mask);
-/* Architecture specific versions may override this (weak) */
+/* Architecture-specific versions may override this (weak) */
 char *pcibios_setup(char *str);
 
 /* Used only when drivers/pci/setup.c is used */
@@ -1258,7 +1257,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
 
 /*
  * PCI domain support.  Sometimes called PCI segment (eg by ACPI),
- * a PCI domain is defined to be a set of PCI busses which share
+ * a PCI domain is defined to be a set of PCI buses which share
  * configuration space.
  */
 #ifdef CONFIG_PCI_DOMAINS
@@ -1672,7 +1671,7 @@ extern u8 pci_cache_line_size;
 extern unsigned long pci_hotplug_io_size;
 extern unsigned long pci_hotplug_mem_size;
 
-/* Architecture specific versions may override these (weak) */
+/* Architecture-specific versions may override these (weak) */
 int pcibios_add_platform_entries(struct pci_dev *dev);
 void pcibios_disable_device(struct pci_dev *dev);
 void pcibios_set_master(struct pci_dev *dev);
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index 430dd963707b..a2e2f1d17e16 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -39,8 +39,8 @@
  * @hardware_test: Called to run a specified hardware test on the specified
  * slot.
  * @get_power_status: Called to get the current power status of a slot.
- * 	If this field is NULL, the value passed in the struct hotplug_slot_info
- * 	will be used when this value is requested by a user.
+ *	If this field is NULL, the value passed in the struct hotplug_slot_info
+ *	will be used when this value is requested by a user.
  * @get_attention_status: Called to get the current attention status of a slot.
  *	If this field is NULL, the value passed in the struct hotplug_slot_info
  *	will be used when this value is requested by a user.
@@ -191,4 +191,3 @@ static inline int pci_get_hp_params(struct pci_dev *dev,
 
 void pci_configure_slot(struct pci_dev *dev);
 #endif
-
diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h
index 9572669eea97..4f1089f2cc98 100644
--- a/include/linux/pcieport_if.h
+++ b/include/linux/pcieport_if.h
@@ -23,7 +23,7 @@
 #define PCIE_PORT_SERVICE_VC		(1 << PCIE_PORT_SERVICE_VC_SHIFT)
 
 struct pcie_device {
-	int 		irq;	    /* Service IRQ/MSI/MSI-X Vector */
+	int		irq;	    /* Service IRQ/MSI/MSI-X Vector */
 	struct pci_dev *port;	    /* Root/Upstream/Downstream Port */
 	u32		service;    /* Port service this device represents */
 	void		*priv_data; /* Service Private Data */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 0890556f779e..4a98e85438a7 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -13,10 +13,10 @@
  *	PCI to PCI Bridge Specification
  *	PCI System Design Guide
  *
- * 	For hypertransport information, please consult the following manuals
- * 	from http://www.hypertransport.org
+ *	For HyperTransport information, please consult the following manuals
+ *	from http://www.hypertransport.org
  *
- *	The Hypertransport I/O Link Specification
+ *	The HyperTransport I/O Link Specification
  */
 
 #ifndef LINUX_PCI_REGS_H
@@ -37,7 +37,7 @@
 #define  PCI_COMMAND_INVALIDATE	0x10	/* Use memory write and invalidate */
 #define  PCI_COMMAND_VGA_PALETTE 0x20	/* Enable palette snooping */
 #define  PCI_COMMAND_PARITY	0x40	/* Enable parity checking */
-#define  PCI_COMMAND_WAIT 	0x80	/* Enable address/data stepping */
+#define  PCI_COMMAND_WAIT	0x80	/* Enable address/data stepping */
 #define  PCI_COMMAND_SERR	0x100	/* Enable SERR */
 #define  PCI_COMMAND_FAST_BACK	0x200	/* Enable back-to-back writes */
 #define  PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */
@@ -45,7 +45,7 @@
 #define PCI_STATUS		0x06	/* 16 bits */
 #define  PCI_STATUS_INTERRUPT	0x08	/* Interrupt status */
 #define  PCI_STATUS_CAP_LIST	0x10	/* Support Capability List */
-#define  PCI_STATUS_66MHZ	0x20	/* Support 66 Mhz PCI 2.1 bus */
+#define  PCI_STATUS_66MHZ	0x20	/* Support 66 MHz PCI 2.1 bus */
 #define  PCI_STATUS_UDF		0x40	/* Support User Definable Features [obsolete] */
 #define  PCI_STATUS_FAST_BACK	0x80	/* Accept fast-back to back */
 #define  PCI_STATUS_PARITY	0x100	/* Detected parity error */
@@ -205,14 +205,14 @@
 #define  PCI_CAP_ID_CHSWP	0x06	/* CompactPCI HotSwap */
 #define  PCI_CAP_ID_PCIX	0x07	/* PCI-X */
 #define  PCI_CAP_ID_HT		0x08	/* HyperTransport */
-#define  PCI_CAP_ID_VNDR	0x09	/* Vendor specific */
+#define  PCI_CAP_ID_VNDR	0x09	/* Vendor-Specific */
 #define  PCI_CAP_ID_DBG		0x0A	/* Debug port */
 #define  PCI_CAP_ID_CCRC	0x0B	/* CompactPCI Central Resource Control */
-#define  PCI_CAP_ID_SHPC 	0x0C	/* PCI Standard Hot-Plug Controller */
+#define  PCI_CAP_ID_SHPC	0x0C	/* PCI Standard Hot-Plug Controller */
 #define  PCI_CAP_ID_SSVID	0x0D	/* Bridge subsystem vendor/device ID */
 #define  PCI_CAP_ID_AGP3	0x0E	/* AGP Target PCI-PCI bridge */
 #define  PCI_CAP_ID_SECDEV	0x0F	/* Secure Device */
-#define  PCI_CAP_ID_EXP 	0x10	/* PCI Express */
+#define  PCI_CAP_ID_EXP		0x10	/* PCI Express */
 #define  PCI_CAP_ID_MSIX	0x11	/* MSI-X */
 #define  PCI_CAP_ID_SATA	0x12	/* SATA Data/Index Conf. */
 #define  PCI_CAP_ID_AF		0x13	/* PCI Advanced Features */
@@ -268,8 +268,8 @@
 #define  PCI_AGP_COMMAND_RQ_MASK 0xff000000  /* Master: Maximum number of requests */
 #define  PCI_AGP_COMMAND_SBA	0x0200	/* Sideband addressing enabled */
 #define  PCI_AGP_COMMAND_AGP	0x0100	/* Allow processing of AGP transactions */
-#define  PCI_AGP_COMMAND_64BIT	0x0020 	/* Allow processing of 64-bit addresses */
-#define  PCI_AGP_COMMAND_FW	0x0010 	/* Force FW transfers */
+#define  PCI_AGP_COMMAND_64BIT	0x0020	/* Allow processing of 64-bit addresses */
+#define  PCI_AGP_COMMAND_FW	0x0010	/* Force FW transfers */
 #define  PCI_AGP_COMMAND_RATE4	0x0004	/* Use 4x rate */
 #define  PCI_AGP_COMMAND_RATE2	0x0002	/* Use 2x rate */
 #define  PCI_AGP_COMMAND_RATE1	0x0001	/* Use 1x rate */
@@ -321,7 +321,7 @@
 #define  PCI_MSIX_PBA_OFFSET	0xfffffff8 /* Offset into specified BAR */
 #define PCI_CAP_MSIX_SIZEOF	12	/* size of MSIX registers */
 
-/* MSI-X entry's format */
+/* MSI-X Table entry format */
 #define PCI_MSIX_ENTRY_SIZE		16
 #define  PCI_MSIX_ENTRY_LOWER_ADDR	0
 #define  PCI_MSIX_ENTRY_UPPER_ADDR	4
@@ -372,7 +372,7 @@
 #define  PCI_X_CMD_SPLIT_16	0x0060	/* Max 16 */
 #define  PCI_X_CMD_SPLIT_32	0x0070	/* Max 32 */
 #define  PCI_X_CMD_MAX_SPLIT	0x0070	/* Max Outstanding Split Transactions */
-#define  PCI_X_CMD_VERSION(x) 	(((x) >> 12) & 3) /* Version */
+#define  PCI_X_CMD_VERSION(x)	(((x) >> 12) & 3) /* Version */
 #define PCI_X_STATUS		4	/* PCI-X capabilities */
 #define  PCI_X_STATUS_DEVFN	0x000000ff	/* A copy of devfn */
 #define  PCI_X_STATUS_BUS	0x0000ff00	/* A copy of bus nr */
@@ -407,8 +407,8 @@
 
 /* PCI Bridge Subsystem ID registers */
 
-#define PCI_SSVID_VENDOR_ID     4	/* PCI-Bridge subsystem vendor id register */
-#define PCI_SSVID_DEVICE_ID     6	/* PCI-Bridge subsystem device id register */
+#define PCI_SSVID_VENDOR_ID     4	/* PCI Bridge subsystem vendor ID */
+#define PCI_SSVID_DEVICE_ID     6	/* PCI Bridge subsystem device ID */
 
 /* PCI Express capability registers */
 
@@ -484,12 +484,12 @@
 #define  PCI_EXP_LNKCTL_CLKREQ_EN 0x0100 /* Enable clkreq */
 #define  PCI_EXP_LNKCTL_HAWD	0x0200	/* Hardware Autonomous Width Disable */
 #define  PCI_EXP_LNKCTL_LBMIE	0x0400	/* Link Bandwidth Management Interrupt Enable */
-#define  PCI_EXP_LNKCTL_LABIE	0x0800	/* Lnk Autonomous Bandwidth Interrupt Enable */
+#define  PCI_EXP_LNKCTL_LABIE	0x0800	/* Link Autonomous Bandwidth Interrupt Enable */
 #define PCI_EXP_LNKSTA		18	/* Link Status */
 #define  PCI_EXP_LNKSTA_CLS	0x000f	/* Current Link Speed */
 #define  PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */
 #define  PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */
-#define  PCI_EXP_LNKSTA_NLW	0x03f0	/* Nogotiated Link Width */
+#define  PCI_EXP_LNKSTA_NLW	0x03f0	/* Negotiated Link Width */
 #define  PCI_EXP_LNKSTA_NLW_SHIFT 4	/* start of NLW mask in link status */
 #define  PCI_EXP_LNKSTA_LT	0x0800	/* Link Training */
 #define  PCI_EXP_LNKSTA_SLC	0x1000	/* Slot Clock Configuration */
@@ -593,7 +593,7 @@
 #define PCI_EXT_CAP_ID_MFVC	0x08	/* Multi-Function VC Capability */
 #define PCI_EXT_CAP_ID_VC9	0x09	/* same as _VC */
 #define PCI_EXT_CAP_ID_RCRB	0x0A	/* Root Complex RB? */
-#define PCI_EXT_CAP_ID_VNDR	0x0B	/* Vendor Specific */
+#define PCI_EXT_CAP_ID_VNDR	0x0B	/* Vendor-Specific */
 #define PCI_EXT_CAP_ID_CAC	0x0C	/* Config Access - obsolete */
 #define PCI_EXT_CAP_ID_ACS	0x0D	/* Access Control Services */
 #define PCI_EXT_CAP_ID_ARI	0x0E	/* Alternate Routing ID */
@@ -602,12 +602,12 @@
 #define PCI_EXT_CAP_ID_MRIOV	0x11	/* Multi Root I/O Virtualization */
 #define PCI_EXT_CAP_ID_MCAST	0x12	/* Multicast */
 #define PCI_EXT_CAP_ID_PRI	0x13	/* Page Request Interface */
-#define PCI_EXT_CAP_ID_AMD_XXX	0x14	/* reserved for AMD */
-#define PCI_EXT_CAP_ID_REBAR	0x15	/* resizable BAR */
-#define PCI_EXT_CAP_ID_DPA	0x16	/* dynamic power alloc */
-#define PCI_EXT_CAP_ID_TPH	0x17	/* TPH request */
-#define PCI_EXT_CAP_ID_LTR	0x18	/* latency tolerance reporting */
-#define PCI_EXT_CAP_ID_SECPCI	0x19	/* Secondary PCIe */
+#define PCI_EXT_CAP_ID_AMD_XXX	0x14	/* Reserved for AMD */
+#define PCI_EXT_CAP_ID_REBAR	0x15	/* Resizable BAR */
+#define PCI_EXT_CAP_ID_DPA	0x16	/* Dynamic Power Allocation */
+#define PCI_EXT_CAP_ID_TPH	0x17	/* TPH Requester */
+#define PCI_EXT_CAP_ID_LTR	0x18	/* Latency Tolerance Reporting */
+#define PCI_EXT_CAP_ID_SECPCI	0x19	/* Secondary PCIe Capability */
 #define PCI_EXT_CAP_ID_PMUX	0x1A	/* Protocol Multiplexing */
 #define PCI_EXT_CAP_ID_PASID	0x1B	/* Process Address Space ID */
 #define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PASID
@@ -667,9 +667,9 @@
 #define PCI_ERR_ROOT_COR_RCV		0x00000001	/* ERR_COR Received */
 /* Multi ERR_COR Received */
 #define PCI_ERR_ROOT_MULTI_COR_RCV	0x00000002
-/* ERR_FATAL/NONFATAL Recevied */
+/* ERR_FATAL/NONFATAL Received */
 #define PCI_ERR_ROOT_UNCOR_RCV		0x00000004
-/* Multi ERR_FATAL/NONFATAL Recevied */
+/* Multi ERR_FATAL/NONFATAL Received */
 #define PCI_ERR_ROOT_MULTI_UNCOR_RCV	0x00000008
 #define PCI_ERR_ROOT_FIRST_FATAL	0x00000010	/* First Fatal */
 #define PCI_ERR_ROOT_NONFATAL_RCV	0x00000020	/* Non-Fatal Received */
@@ -678,7 +678,7 @@
 
 /* Virtual Channel */
 #define PCI_VC_PORT_REG1	4
-#define  PCI_VC_REG1_EVCC	0x7	/* extended vc count */
+#define  PCI_VC_REG1_EVCC	0x7	/* extended VC count */
 #define PCI_VC_PORT_REG2	8
 #define  PCI_VC_REG2_32_PHASE	0x2
 #define  PCI_VC_REG2_64_PHASE	0x4
@@ -711,7 +711,7 @@
 #define  PCI_VNDR_HEADER_LEN(x)	(((x) >> 20) & 0xfff)
 
 /*
- * Hypertransport sub capability types
+ * HyperTransport sub capability types
  *
  * Unfortunately there are both 3 bit and 5 bit capability types defined
  * in the HT spec, catering for that is a little messy. You probably don't
@@ -739,8 +739,8 @@
 #define HT_CAPTYPE_DIRECT_ROUTE	0xB0	/* Direct routing configuration */
 #define HT_CAPTYPE_VCSET	0xB8	/* Virtual Channel configuration */
 #define HT_CAPTYPE_ERROR_RETRY	0xC0	/* Retry on error configuration */
-#define HT_CAPTYPE_GEN3		0xD0	/* Generation 3 hypertransport configuration */
-#define HT_CAPTYPE_PM		0xE0	/* Hypertransport powermanagement configuration */
+#define HT_CAPTYPE_GEN3		0xD0	/* Generation 3 HyperTransport configuration */
+#define HT_CAPTYPE_PM		0xE0	/* HyperTransport power management configuration */
 #define HT_CAP_SIZEOF_LONG	28	/* slave & primary */
 #define HT_CAP_SIZEOF_SHORT	24	/* host & secondary */
 
@@ -777,14 +777,14 @@
 #define PCI_PRI_ALLOC_REQ	0x0c	/* PRI max reqs allowed */
 #define PCI_EXT_CAP_PRI_SIZEOF	16
 
-/* PASID capability */
+/* Process Address Space ID */
 #define PCI_PASID_CAP		0x04    /* PASID feature register */
 #define  PCI_PASID_CAP_EXEC	0x02	/* Exec permissions Supported */
-#define  PCI_PASID_CAP_PRIV	0x04	/* Priviledge Mode Supported */
+#define  PCI_PASID_CAP_PRIV	0x04	/* Privilege Mode Supported */
 #define PCI_PASID_CTRL		0x06    /* PASID control register */
 #define  PCI_PASID_CTRL_ENABLE	0x01	/* Enable bit */
 #define  PCI_PASID_CTRL_EXEC	0x02	/* Exec permissions Enable */
-#define  PCI_PASID_CTRL_PRIV	0x04	/* Priviledge Mode Enable */
+#define  PCI_PASID_CTRL_PRIV	0x04	/* Privilege Mode Enable */
 #define PCI_EXT_CAP_PASID_SIZEOF	8
 
 /* Single Root I/O Virtualization */
@@ -839,22 +839,22 @@
 #define PCI_ACS_CTRL		0x06	/* ACS Control Register */
 #define PCI_ACS_EGRESS_CTL_V	0x08	/* ACS Egress Control Vector */
 
-#define PCI_VSEC_HDR		4	/* extended cap - vendor specific */
+#define PCI_VSEC_HDR		4	/* extended cap - vendor-specific */
 #define  PCI_VSEC_HDR_LEN_SHIFT	20	/* shift for length field */
 
-/* sata capability */
+/* SATA capability */
 #define PCI_SATA_REGS		4	/* SATA REGs specifier */
 #define  PCI_SATA_REGS_MASK	0xF	/* location - BAR#/inline */
 #define  PCI_SATA_REGS_INLINE	0xF	/* REGS in config space */
 #define PCI_SATA_SIZEOF_SHORT	8
 #define PCI_SATA_SIZEOF_LONG	16
 
-/* resizable BARs */
+/* Resizable BARs */
 #define PCI_REBAR_CTRL		8	/* control register */
 #define  PCI_REBAR_CTRL_NBAR_MASK	(7 << 5)	/* mask for # bars */
 #define  PCI_REBAR_CTRL_NBAR_SHIFT	5	/* shift for # bars */
 
-/* dynamic power allocation */
+/* Dynamic Power Allocation */
 #define PCI_DPA_CAP		4	/* capability register */
 #define  PCI_DPA_CAP_SUBSTATE_MASK	0x1F	/* # substates - 1 */
 #define PCI_DPA_BASE_SIZEOF	16	/* size with 0 substates */
-- 
cgit 


From 8971646294bda65f8666b60cb2cb3d5e172c99bf Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 18 Oct 2013 19:35:25 +0200
Subject: async_memcpy: convert to dmaengine_unmap_data

Use the generic unmap object to unmap dma buffers.

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Reported-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
[bzolnier: add missing unmap->len initialization]
[bzolnier: fix whitespace damage]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
[djbw: add DMA_ENGINE=n support]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 crypto/async_tx/async_memcpy.c | 40 +++++++++++++++++++++++-----------------
 drivers/dma/dmaengine.c        |  3 ++-
 include/linux/dmaengine.h      | 17 +++++++++++++++++
 3 files changed, 42 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 9e62feffb374..72750214f779 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -50,33 +50,37 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 						      &dest, 1, &src, 1, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
-	if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
-		dma_addr_t dma_dest, dma_src;
-		unsigned long dma_prep_flags = 0;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+
+	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
+		unsigned long dma_prep_flags = DMA_COMPL_SKIP_SRC_UNMAP |
+					       DMA_COMPL_SKIP_DEST_UNMAP;
 
 		if (submit->cb_fn)
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_prep_flags |= DMA_PREP_FENCE;
-		dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
-					DMA_FROM_DEVICE);
-
-		dma_src = dma_map_page(device->dev, src, src_offset, len,
-				       DMA_TO_DEVICE);
-
-		tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
-						    len, dma_prep_flags);
-		if (!tx) {
-			dma_unmap_page(device->dev, dma_dest, len,
-				       DMA_FROM_DEVICE);
-			dma_unmap_page(device->dev, dma_src, len,
-				       DMA_TO_DEVICE);
-		}
+
+		unmap->to_cnt = 1;
+		unmap->addr[0] = dma_map_page(device->dev, src, src_offset, len,
+					      DMA_TO_DEVICE);
+		unmap->from_cnt = 1;
+		unmap->addr[1] = dma_map_page(device->dev, dest, dest_offset, len,
+					      DMA_FROM_DEVICE);
+		unmap->len = len;
+
+		tx = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+						    unmap->addr[0], len,
+						    dma_prep_flags);
 	}
 
 	if (tx) {
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
+
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 	} else {
 		void *dest_buf, *src_buf;
@@ -96,6 +100,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 		async_tx_sync_epilog(submit);
 	}
 
+	dmaengine_unmap_put(unmap);
+
 	return tx;
 }
 EXPORT_SYMBOL_GPL(async_memcpy);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index e721a1caff7f..54138b57b37c 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1009,7 +1009,7 @@ static int __init dmaengine_init_unmap_pool(void)
 	return -ENOMEM;
 }
 
-static struct dmaengine_unmap_data *
+struct dmaengine_unmap_data *
 dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 {
 	struct dmaengine_unmap_data *unmap;
@@ -1024,6 +1024,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 
 	return unmap;
 }
+EXPORT_SYMBOL(dmaengine_get_unmap_data);
 
 /**
  * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 2fe855a7cab1..3782cdb782a8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -457,6 +457,7 @@ struct dma_async_tx_descriptor {
 #endif
 };
 
+#ifdef CONFIG_DMA_ENGINE
 static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
 				 struct dmaengine_unmap_data *unmap)
 {
@@ -464,7 +465,23 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
 	tx->unmap = unmap;
 }
 
+struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags);
 void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap);
+#else
+static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
+				 struct dmaengine_unmap_data *unmap)
+{
+}
+static inline struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+{
+	return NULL;
+}
+static inline void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
+{
+}
+#endif
 
 static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx)
 {
-- 
cgit 


From 0776ae7b89782124ddd72eafe0b1e0fdcdabe32e Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Date: Fri, 18 Oct 2013 19:35:33 +0200
Subject: dmaengine: remove DMA unmap flags

Remove no longer needed DMA unmap flags:
- DMA_COMPL_SKIP_SRC_UNMAP
- DMA_COMPL_SKIP_DEST_UNMAP
- DMA_COMPL_SRC_UNMAP_SINGLE
- DMA_COMPL_DEST_UNMAP_SINGLE

Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Tomasz Figa <t.figa@samsung.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Jon Mason <jon.mason@intel.com>
Acked-by: Mark Brown <broonie@linaro.org>
[djbw: clean up straggling skip unmap flags in ntb]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 crypto/async_tx/async_memcpy.c           |  3 +--
 crypto/async_tx/async_pq.c               |  1 -
 crypto/async_tx/async_raid6_recov.c      |  8 ++------
 crypto/async_tx/async_xor.c              |  6 ++----
 drivers/ata/pata_arasan_cf.c             |  3 +--
 drivers/dma/dmaengine.c                  |  3 +--
 drivers/dma/dmatest.c                    |  3 +--
 drivers/dma/ioat/dma.c                   |  3 +--
 drivers/dma/ioat/dma_v3.c                | 12 +++---------
 drivers/media/platform/m2m-deinterlace.c |  3 +--
 drivers/media/platform/timblogiw.c       |  2 +-
 drivers/misc/carma/carma-fpga.c          |  3 +--
 drivers/mtd/nand/atmel_nand.c            |  3 +--
 drivers/mtd/nand/fsmc_nand.c             |  2 --
 drivers/net/ethernet/micrel/ks8842.c     |  6 ++----
 drivers/ntb/ntb_transport.c              | 11 +++--------
 drivers/spi/spi-dw-mid.c                 |  4 ++--
 include/linux/dmaengine.h                | 18 ++++--------------
 18 files changed, 27 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 72750214f779..f8c0b8dbeb75 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -56,8 +56,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
 
 	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
-		unsigned long dma_prep_flags = DMA_COMPL_SKIP_SRC_UNMAP |
-					       DMA_COMPL_SKIP_DEST_UNMAP;
+		unsigned long dma_prep_flags = 0;
 
 		if (submit->cb_fn)
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 4126b56fbc01..d05327caf69d 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -62,7 +62,6 @@ do_async_gen_syndrome(struct dma_chan *chan,
 	dma_addr_t dma_dest[2];
 	int src_off = 0;
 
-	dma_flags |= DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
 	if (submit->flags & ASYNC_TX_FENCE)
 		dma_flags |= DMA_PREP_FENCE;
 
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index a3a72a784421..934a84981495 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -47,9 +47,7 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 		struct device *dev = dma->dev;
 		dma_addr_t pq[2];
 		struct dma_async_tx_descriptor *tx;
-		enum dma_ctrl_flags dma_flags = DMA_COMPL_SKIP_SRC_UNMAP |
-						DMA_COMPL_SKIP_DEST_UNMAP |
-						DMA_PREP_PQ_DISABLE_P;
+		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
@@ -113,9 +111,7 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 		dma_addr_t dma_dest[2];
 		struct device *dev = dma->dev;
 		struct dma_async_tx_descriptor *tx;
-		enum dma_ctrl_flags dma_flags = DMA_COMPL_SKIP_SRC_UNMAP |
-						DMA_COMPL_SKIP_DEST_UNMAP |
-						DMA_PREP_PQ_DISABLE_P;
+		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index d2cc77d501c7..3c562f5a60bb 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -41,7 +41,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 	void *cb_param_orig = submit->cb_param;
 	enum async_tx_flags flags_orig = submit->flags;
-	enum dma_ctrl_flags dma_flags;
+	enum dma_ctrl_flags dma_flags = 0;
 	int src_cnt = unmap->to_cnt;
 	int xor_src_cnt;
 	dma_addr_t dma_dest = unmap->addr[unmap->to_cnt];
@@ -55,7 +55,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 		/* if we are submitting additional xors, leave the chain open
 		 * and clear the callback parameters
 		 */
-		dma_flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
 		if (src_cnt > xor_src_cnt) {
 			submit->flags &= ~ASYNC_TX_ACK;
 			submit->flags |= ASYNC_TX_FENCE;
@@ -284,8 +283,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 	if (unmap && src_cnt <= device->max_xor &&
 	    is_dma_xor_aligned(device, offset, 0, len)) {
-		unsigned long dma_prep_flags = DMA_COMPL_SKIP_SRC_UNMAP |
-					       DMA_COMPL_SKIP_DEST_UNMAP;
+		unsigned long dma_prep_flags = 0;
 		int i;
 
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 853f610af28f..e88690ebfd82 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -396,8 +396,7 @@ dma_xfer(struct arasan_cf_dev *acdev, dma_addr_t src, dma_addr_t dest, u32 len)
 	struct dma_async_tx_descriptor *tx;
 	struct dma_chan *chan = acdev->dma_chan;
 	dma_cookie_t cookie;
-	unsigned long flags = DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
-		DMA_COMPL_SKIP_DEST_UNMAP;
+	unsigned long flags = DMA_PREP_INTERRUPT;
 	int ret = 0;
 
 	tx = chan->device->device_prep_dma_memcpy(chan, dest, src, len, flags);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index f878c808466e..b69ac3892b86 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1065,8 +1065,7 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 	unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
 				      DMA_FROM_DEVICE);
 	unmap->len = len;
-	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_SRC_UNMAP |
-		DMA_COMPL_SKIP_DEST_UNMAP;
+	flags = DMA_CTRL_ACK;
 	tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
 					 len, flags);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index f4a2a25fae31..5791091c13ca 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -599,8 +599,7 @@ static int dmatest_func(void *data)
 	/*
 	 * src and dst buffers are freed by ourselves below
 	 */
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT |
-		DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	while (!kthread_should_stop()
 	       && !(params->iterations && total_tests >= params->iterations)) {
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index c123e32dbbb0..6fcf741ad91b 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -818,8 +818,7 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-	flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
-		DMA_PREP_INTERRUPT;
+	flags = DMA_PREP_INTERRUPT;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
 						   IOAT_TEST_SIZE, flags);
 	if (!tx) {
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index 43386c171bba..a4798f0cc225 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -1279,9 +1279,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
 				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
-				      DMA_PREP_INTERRUPT |
-				      DMA_COMPL_SKIP_SRC_UNMAP |
-				      DMA_COMPL_SKIP_DEST_UNMAP);
+				      DMA_PREP_INTERRUPT);
 
 	if (!tx) {
 		dev_err(dev, "Self-test xor prep failed\n");
@@ -1342,9 +1340,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT |
-					  DMA_COMPL_SKIP_SRC_UNMAP |
-					  DMA_COMPL_SKIP_DEST_UNMAP);
+					  &xor_val_result, DMA_PREP_INTERRUPT);
 	if (!tx) {
 		dev_err(dev, "Self-test zero prep failed\n");
 		err = -ENODEV;
@@ -1389,9 +1385,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT |
-					  DMA_COMPL_SKIP_SRC_UNMAP |
-					  DMA_COMPL_SKIP_DEST_UNMAP);
+					  &xor_val_result, DMA_PREP_INTERRUPT);
 	if (!tx) {
 		dev_err(dev, "Self-test 2nd zero prep failed\n");
 		err = -ENODEV;
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 540516ca872c..879ea6fdd1be 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -341,8 +341,7 @@ static void deinterlace_issue_dma(struct deinterlace_ctx *ctx, int op,
 	ctx->xt->dir = DMA_MEM_TO_MEM;
 	ctx->xt->src_sgl = false;
 	ctx->xt->dst_sgl = true;
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT |
-		DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SKIP_SRC_UNMAP;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	tx = dmadev->device_prep_interleaved_dma(chan, ctx->xt, flags);
 	if (tx == NULL) {
diff --git a/drivers/media/platform/timblogiw.c b/drivers/media/platform/timblogiw.c
index b557caf5b1a4..59a95e3ab0e3 100644
--- a/drivers/media/platform/timblogiw.c
+++ b/drivers/media/platform/timblogiw.c
@@ -565,7 +565,7 @@ static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
 
 	desc = dmaengine_prep_slave_sg(fh->chan,
 		buf->sg, sg_elems, DMA_DEV_TO_MEM,
-		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+		DMA_PREP_INTERRUPT);
 	if (!desc) {
 		spin_lock_irq(&fh->queue_lock);
 		list_del_init(&vb->queue);
diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c
index 7b56563f8b74..5335104e7c84 100644
--- a/drivers/misc/carma/carma-fpga.c
+++ b/drivers/misc/carma/carma-fpga.c
@@ -631,8 +631,7 @@ static int data_submit_dma(struct fpga_device *priv, struct data_buf *buf)
 	struct dma_async_tx_descriptor *tx;
 	dma_cookie_t cookie;
 	dma_addr_t dst, src;
-	unsigned long dma_flags = DMA_COMPL_SKIP_DEST_UNMAP |
-				  DMA_COMPL_SKIP_SRC_UNMAP;
+	unsigned long dma_flags = 0;
 
 	dst_sg = buf->vb.sglist;
 	dst_nents = buf->vb.sglen;
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 060feeaf6b3e..2a837cb425d7 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -375,8 +375,7 @@ static int atmel_nand_dma_op(struct mtd_info *mtd, void *buf, int len,
 
 	dma_dev = host->dma_chan->device;
 
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
-		DMA_COMPL_SKIP_DEST_UNMAP;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	phys_addr = dma_map_single(dma_dev->dev, p, len, dir);
 	if (dma_mapping_error(dma_dev->dev, phys_addr)) {
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 3dc1a7564d87..8b2752263db9 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -573,8 +573,6 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
 	dma_dev = chan->device;
 	dma_addr = dma_map_single(dma_dev->dev, buffer, len, direction);
 
-	flags |= DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
-
 	if (direction == DMA_TO_DEVICE) {
 		dma_src = dma_addr;
 		dma_dst = host->data_pa;
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 0951f7aca1ef..822616e3c375 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -459,8 +459,7 @@ static int ks8842_tx_frame_dma(struct sk_buff *skb, struct net_device *netdev)
 		sg_dma_len(&ctl->sg) += 4 - sg_dma_len(&ctl->sg) % 4;
 
 	ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-		&ctl->sg, 1, DMA_MEM_TO_DEV,
-		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+		&ctl->sg, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 	if (!ctl->adesc)
 		return NETDEV_TX_BUSY;
 
@@ -571,8 +570,7 @@ static int __ks8842_start_new_rx_dma(struct net_device *netdev)
 		sg_dma_len(sg) = DMA_BUFFER_SIZE;
 
 		ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-			sg, 1, DMA_DEV_TO_MEM,
-			DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+			sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
 
 		if (!ctl->adesc)
 			goto out;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 222c2baa3a4b..d0222f13d154 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1037,7 +1037,6 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
 	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	void *buf = entry->buf;
-	unsigned long flags;
 
 	entry->len = len;
 
@@ -1073,10 +1072,9 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
 
 	unmap->from_cnt = 1;
 
-	flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
-		DMA_PREP_INTERRUPT;
 	txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
-					     unmap->addr[0], len, flags);
+					     unmap->addr[0], len,
+					     DMA_PREP_INTERRUPT);
 	if (!txd)
 		goto err_get_unmap;
 
@@ -1266,7 +1264,6 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 	void __iomem *offset;
 	size_t len = entry->len;
 	void *buf = entry->buf;
-	unsigned long flags;
 
 	offset = qp->tx_mw + qp->tx_max_frame * qp->tx_index;
 	hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
@@ -1301,10 +1298,8 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 
 	unmap->to_cnt = 1;
 
-	flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
-		DMA_PREP_INTERRUPT;
 	txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len,
-					    flags);
+					     DMA_PREP_INTERRUPT);
 	if (!txd)
 		goto err_get_unmap;
 
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index b9f0192758d6..6d207afec8cb 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -150,7 +150,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 				&dws->tx_sgl,
 				1,
 				DMA_MEM_TO_DEV,
-				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+				DMA_PREP_INTERRUPT);
 	txdesc->callback = dw_spi_dma_done;
 	txdesc->callback_param = dws;
 
@@ -173,7 +173,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 				&dws->rx_sgl,
 				1,
 				DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+				DMA_PREP_INTERRUPT);
 	rxdesc->callback = dw_spi_dma_done;
 	rxdesc->callback_param = dws;
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 3782cdb782a8..491072cb5ba0 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -171,12 +171,6 @@ struct dma_interleaved_template {
  * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client
  *  acknowledges receipt, i.e. has has a chance to establish any dependency
  *  chains
- * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
- * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
- * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single
- * 	(if not set, do the source dma-unmapping as page)
- * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single
- * 	(if not set, do the destination dma-unmapping as page)
  * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q
  * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P
  * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as
@@ -188,14 +182,10 @@ struct dma_interleaved_template {
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
 	DMA_CTRL_ACK = (1 << 1),
-	DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2),
-	DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
-	DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4),
-	DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5),
-	DMA_PREP_PQ_DISABLE_P = (1 << 6),
-	DMA_PREP_PQ_DISABLE_Q = (1 << 7),
-	DMA_PREP_CONTINUE = (1 << 8),
-	DMA_PREP_FENCE = (1 << 9),
+	DMA_PREP_PQ_DISABLE_P = (1 << 2),
+	DMA_PREP_PQ_DISABLE_Q = (1 << 3),
+	DMA_PREP_CONTINUE = (1 << 4),
+	DMA_PREP_FENCE = (1 << 5),
 };
 
 /**
-- 
cgit 


From 3686ec5e84977eddc796903177e7e0a122585c11 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2013 17:14:43 +0100
Subject: genetlink: remove genl_register_ops/genl_unregister_ops

genl_register_ops() is still needed for internal registration,
but is no longer available to users of the API.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  2 --
 net/netlink/genetlink.c | 57 +------------------------------------------------
 2 files changed, 1 insertion(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9b787b62cf16..617d718524b0 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -141,8 +141,6 @@ static inline int genl_register_family_with_ops(struct genl_family *family,
 }
 
 int genl_unregister_family(struct genl_family *family);
-int genl_register_ops(struct genl_family *, struct genl_ops *ops);
-int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
 int genl_register_mc_group(struct genl_family *family,
 			   struct genl_multicast_group *grp);
 void genl_unregister_mc_group(struct genl_family *family,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 0c741cec4d0d..fbccb45e8cc1 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -283,22 +283,7 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 		__genl_unregister_mc_group(family, grp);
 }
 
-/**
- * genl_register_ops - register generic netlink operations
- * @family: generic netlink family
- * @ops: operations to be registered
- *
- * Registers the specified operations and assigns them to the specified
- * family. Either a doit or dumpit callback must be specified or the
- * operation will fail. Only one operation structure per command
- * identifier may be registered.
- *
- * See include/net/genetlink.h for more documenation on the operations
- * structure.
- *
- * Returns 0 on success or a negative error code.
- */
-int genl_register_ops(struct genl_family *family, struct genl_ops *ops)
+static int genl_register_ops(struct genl_family *family, struct genl_ops *ops)
 {
 	int err = -EINVAL;
 
@@ -326,42 +311,6 @@ int genl_register_ops(struct genl_family *family, struct genl_ops *ops)
 errout:
 	return err;
 }
-EXPORT_SYMBOL(genl_register_ops);
-
-/**
- * genl_unregister_ops - unregister generic netlink operations
- * @family: generic netlink family
- * @ops: operations to be unregistered
- *
- * Unregisters the specified operations and unassigns them from the
- * specified family. The operation blocks until the current message
- * processing has finished and doesn't start again until the
- * unregister process has finished.
- *
- * Note: It is not necessary to unregister all operations before
- *       unregistering the family, unregistering the family will cause
- *       all assigned operations to be unregistered automatically.
- *
- * Returns 0 on success or a negative error code.
- */
-int genl_unregister_ops(struct genl_family *family, struct genl_ops *ops)
-{
-	struct genl_ops *rc;
-
-	genl_lock_all();
-	list_for_each_entry(rc, &family->ops_list, ops_list) {
-		if (rc == ops) {
-			list_del(&ops->ops_list);
-			genl_unlock_all();
-			genl_ctrl_event(CTRL_CMD_DELOPS, ops);
-			return 0;
-		}
-	}
-	genl_unlock_all();
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL(genl_unregister_ops);
 
 /**
  * __genl_register_family - register a generic netlink family
@@ -451,10 +400,6 @@ EXPORT_SYMBOL(__genl_register_family);
  * See include/net/genetlink.h for more documenation on the operations
  * structure.
  *
- * This is equivalent to calling genl_register_family() followed by
- * genl_register_ops() for every operation entry in the table taking
- * care to unregister the family on error path.
- *
  * Return 0 on success or a negative error code.
  */
 int __genl_register_family_with_ops(struct genl_family *family,
-- 
cgit 


From d91824c08fbcb265ec930d863fa905e8daa836a4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2013 17:14:44 +0100
Subject: genetlink: register family ops as array

Instead of using a linked list, use an array. This reduces
the data size needed by the users of genetlink, for example
in wireless (net/wireless/nl80211.c) on 64-bit it frees up
over 1K of data space.

Remove the attempted sending of CTRL_CMD_NEWOPS ctrl event
since genl_ctrl_event(CTRL_CMD_NEWOPS, ...) only returns
-EINVAL anyway, therefore no such event could ever be sent.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  7 +++--
 net/netlink/genetlink.c | 78 +++++++++++++++++++++----------------------------
 2 files changed, 37 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 617d718524b0..d4802af1a8b3 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -39,9 +39,10 @@ struct genl_info;
  * @post_doit: called after an operation's doit callback, it may
  *	undo operations done by pre_doit, for example release locks
  * @attrbuf: buffer to store parsed attributes
- * @ops_list: list of all assigned operations
  * @family_list: family list
  * @mcast_groups: multicast groups list
+ * @ops: the operations supported by this family (private)
+ * @n_ops: number of operations supported by this family (private)
  */
 struct genl_family {
 	unsigned int		id;
@@ -58,7 +59,8 @@ struct genl_family {
 					     struct sk_buff *skb,
 					     struct genl_info *info);
 	struct nlattr **	attrbuf;	/* private */
-	struct list_head	ops_list;	/* private */
+	struct genl_ops *	ops;		/* private */
+	unsigned int		n_ops;		/* private */
 	struct list_head	family_list;	/* private */
 	struct list_head	mcast_groups;	/* private */
 	struct module		*module;
@@ -119,7 +121,6 @@ struct genl_ops {
 	int		       (*dumpit)(struct sk_buff *skb,
 					 struct netlink_callback *cb);
 	int		       (*done)(struct netlink_callback *cb);
-	struct list_head	ops_list;
 };
 
 int __genl_register_family(struct genl_family *family);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index fbccb45e8cc1..d8273b057763 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -108,11 +108,11 @@ static struct genl_family *genl_family_find_byname(char *name)
 
 static struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family)
 {
-	struct genl_ops *ops;
+	int i;
 
-	list_for_each_entry(ops, &family->ops_list, ops_list)
-		if (ops->cmd == cmd)
-			return ops;
+	for (i = 0; i < family->n_ops; i++)
+		if (family->ops[i].cmd == cmd)
+			return &family->ops[i];
 
 	return NULL;
 }
@@ -283,33 +283,30 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 		__genl_unregister_mc_group(family, grp);
 }
 
-static int genl_register_ops(struct genl_family *family, struct genl_ops *ops)
+static int genl_validate_add_ops(struct genl_family *family, struct genl_ops *ops,
+				 unsigned int n_ops)
 {
-	int err = -EINVAL;
-
-	if (ops->dumpit == NULL && ops->doit == NULL)
-		goto errout;
-
-	if (genl_get_cmd(ops->cmd, family)) {
-		err = -EEXIST;
-		goto errout;
+	int i, j;
+
+	for (i = 0; i < n_ops; i++) {
+		if (ops[i].dumpit == NULL && ops[i].doit == NULL)
+			return -EINVAL;
+		for (j = i + 1; j < n_ops; j++)
+			if (ops[i].cmd == ops[j].cmd)
+				return -EINVAL;
+		if (ops[i].dumpit)
+			ops[i].flags |= GENL_CMD_CAP_DUMP;
+		if (ops[i].doit)
+			ops[i].flags |= GENL_CMD_CAP_DO;
+		if (ops[i].policy)
+			ops[i].flags |= GENL_CMD_CAP_HASPOL;
 	}
 
-	if (ops->dumpit)
-		ops->flags |= GENL_CMD_CAP_DUMP;
-	if (ops->doit)
-		ops->flags |= GENL_CMD_CAP_DO;
-	if (ops->policy)
-		ops->flags |= GENL_CMD_CAP_HASPOL;
-
-	genl_lock_all();
-	list_add_tail(&ops->ops_list, &family->ops_list);
-	genl_unlock_all();
+	/* family is not registered yet, so no locking needed */
+	family->ops = ops;
+	family->n_ops = n_ops;
 
-	genl_ctrl_event(CTRL_CMD_NEWOPS, ops);
-	err = 0;
-errout:
-	return err;
+	return 0;
 }
 
 /**
@@ -333,7 +330,6 @@ int __genl_register_family(struct genl_family *family)
 	if (family->id > GENL_MAX_ID)
 		goto errout;
 
-	INIT_LIST_HEAD(&family->ops_list);
 	INIT_LIST_HEAD(&family->mcast_groups);
 
 	genl_lock_all();
@@ -405,21 +401,13 @@ EXPORT_SYMBOL(__genl_register_family);
 int __genl_register_family_with_ops(struct genl_family *family,
 	struct genl_ops *ops, size_t n_ops)
 {
-	int err, i;
+	int err;
 
-	err = __genl_register_family(family);
+	err = genl_validate_add_ops(family, ops, n_ops);
 	if (err)
 		return err;
 
-	for (i = 0; i < n_ops; ++i, ++ops) {
-		err = genl_register_ops(family, ops);
-		if (err)
-			goto err_out;
-	}
-	return 0;
-err_out:
-	genl_unregister_family(family);
-	return err;
+	return __genl_register_family(family);
 }
 EXPORT_SYMBOL(__genl_register_family_with_ops);
 
@@ -444,7 +432,7 @@ int genl_unregister_family(struct genl_family *family)
 			continue;
 
 		list_del(&rc->family_list);
-		INIT_LIST_HEAD(&family->ops_list);
+		family->n_ops = 0;
 		genl_unlock_all();
 
 		kfree(family->attrbuf);
@@ -671,19 +659,19 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 	    nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
 		goto nla_put_failure;
 
-	if (!list_empty(&family->ops_list)) {
+	if (family->n_ops) {
 		struct nlattr *nla_ops;
-		struct genl_ops *ops;
-		int idx = 1;
+		int i;
 
 		nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS);
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
-		list_for_each_entry(ops, &family->ops_list, ops_list) {
+		for (i = 0; i < family->n_ops; i++) {
 			struct nlattr *nest;
+			struct genl_ops *ops = &family->ops[i];
 
-			nest = nla_nest_start(skb, idx++);
+			nest = nla_nest_start(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
-- 
cgit 


From f84f771d942182e39a56ec2989d6a67d3ca33a13 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2013 17:14:45 +0100
Subject: genetlink: allow making ops const

Allow making the ops array const by not modifying the ops
flags on registration but rather only when ops are sent
out in the family information.

No users are updated yet except for the pre_doit/post_doit
calls in wireless (the only ones that exist now.)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 10 +++++-----
 net/netlink/genetlink.c | 36 +++++++++++++++++++++---------------
 net/wireless/nl80211.c  |  8 ++++----
 3 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index d4802af1a8b3..d87486aa0611 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -52,14 +52,14 @@ struct genl_family {
 	unsigned int		maxattr;
 	bool			netnsok;
 	bool			parallel_ops;
-	int			(*pre_doit)(struct genl_ops *ops,
+	int			(*pre_doit)(const struct genl_ops *ops,
 					    struct sk_buff *skb,
 					    struct genl_info *info);
-	void			(*post_doit)(struct genl_ops *ops,
+	void			(*post_doit)(const struct genl_ops *ops,
 					     struct sk_buff *skb,
 					     struct genl_info *info);
 	struct nlattr **	attrbuf;	/* private */
-	struct genl_ops *	ops;		/* private */
+	const struct genl_ops *	ops;		/* private */
 	unsigned int		n_ops;		/* private */
 	struct list_head	family_list;	/* private */
 	struct list_head	mcast_groups;	/* private */
@@ -132,10 +132,10 @@ static inline int genl_register_family(struct genl_family *family)
 }
 
 int __genl_register_family_with_ops(struct genl_family *family,
-				    struct genl_ops *ops, size_t n_ops);
+				    const struct genl_ops *ops, size_t n_ops);
 
 static inline int genl_register_family_with_ops(struct genl_family *family,
-	struct genl_ops *ops, size_t n_ops)
+	const struct genl_ops *ops, size_t n_ops)
 {
 	family->module = THIS_MODULE;
 	return __genl_register_family_with_ops(family, ops, n_ops);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index d8273b057763..a7c62d3d05a1 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -106,7 +106,7 @@ static struct genl_family *genl_family_find_byname(char *name)
 	return NULL;
 }
 
-static struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family)
+static const struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family)
 {
 	int i;
 
@@ -283,7 +283,8 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 		__genl_unregister_mc_group(family, grp);
 }
 
-static int genl_validate_add_ops(struct genl_family *family, struct genl_ops *ops,
+static int genl_validate_add_ops(struct genl_family *family,
+				 const struct genl_ops *ops,
 				 unsigned int n_ops)
 {
 	int i, j;
@@ -294,12 +295,6 @@ static int genl_validate_add_ops(struct genl_family *family, struct genl_ops *op
 		for (j = i + 1; j < n_ops; j++)
 			if (ops[i].cmd == ops[j].cmd)
 				return -EINVAL;
-		if (ops[i].dumpit)
-			ops[i].flags |= GENL_CMD_CAP_DUMP;
-		if (ops[i].doit)
-			ops[i].flags |= GENL_CMD_CAP_DO;
-		if (ops[i].policy)
-			ops[i].flags |= GENL_CMD_CAP_HASPOL;
 	}
 
 	/* family is not registered yet, so no locking needed */
@@ -399,7 +394,7 @@ EXPORT_SYMBOL(__genl_register_family);
  * Return 0 on success or a negative error code.
  */
 int __genl_register_family_with_ops(struct genl_family *family,
-	struct genl_ops *ops, size_t n_ops)
+	const struct genl_ops *ops, size_t n_ops)
 {
 	int err;
 
@@ -479,7 +474,8 @@ EXPORT_SYMBOL(genlmsg_put);
 
 static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	struct genl_ops *ops = cb->data;
+	/* our ops are always const - netlink API doesn't propagate that */
+	const struct genl_ops *ops = cb->data;
 	int rc;
 
 	genl_lock();
@@ -490,7 +486,8 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static int genl_lock_done(struct netlink_callback *cb)
 {
-	struct genl_ops *ops = cb->data;
+	/* our ops are always const - netlink API doesn't propagate that */
+	const struct genl_ops *ops = cb->data;
 	int rc = 0;
 
 	if (ops->done) {
@@ -505,7 +502,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
 			       struct sk_buff *skb,
 			       struct nlmsghdr *nlh)
 {
-	struct genl_ops *ops;
+	const struct genl_ops *ops;
 	struct net *net = sock_net(skb->sk);
 	struct genl_info info;
 	struct genlmsghdr *hdr = nlmsg_data(nlh);
@@ -537,7 +534,8 @@ static int genl_family_rcv_msg(struct genl_family *family,
 		if (!family->parallel_ops) {
 			struct netlink_dump_control c = {
 				.module = family->module,
-				.data = ops,
+				/* we have const, but the netlink API doesn't */
+				.data = (void *)ops,
 				.dump = genl_lock_dumpit,
 				.done = genl_lock_done,
 			};
@@ -669,14 +667,22 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 
 		for (i = 0; i < family->n_ops; i++) {
 			struct nlattr *nest;
-			struct genl_ops *ops = &family->ops[i];
+			const struct genl_ops *ops = &family->ops[i];
+			u32 flags = ops->flags;
+
+			if (ops->dumpit)
+				flags |= GENL_CMD_CAP_DUMP;
+			if (ops->doit)
+				flags |= GENL_CMD_CAP_DO;
+			if (ops->policy)
+				flags |= GENL_CMD_CAP_HASPOL;
 
 			nest = nla_nest_start(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
 			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) ||
-			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, ops->flags))
+			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, flags))
 				goto nla_put_failure;
 
 			nla_nest_end(skb, nest);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a7f4e7902104..3fef55958e98 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -30,9 +30,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 				   struct cfg80211_crypto_settings *settings,
 				   int cipher_limit);
 
-static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb,
+static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			    struct genl_info *info);
-static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb,
+static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			      struct genl_info *info);
 
 /* the netlink family */
@@ -8851,7 +8851,7 @@ static int nl80211_crit_protocol_stop(struct sk_buff *skb,
 #define NL80211_FLAG_NEED_WDEV_UP	(NL80211_FLAG_NEED_WDEV |\
 					 NL80211_FLAG_CHECK_NETDEV_UP)
 
-static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb,
+static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			    struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev;
@@ -8920,7 +8920,7 @@ static int nl80211_pre_doit(struct genl_ops *ops, struct sk_buff *skb,
 	return 0;
 }
 
-static void nl80211_post_doit(struct genl_ops *ops, struct sk_buff *skb,
+static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 			      struct genl_info *info)
 {
 	if (info->user_ptr[1]) {
-- 
cgit 


From 3f5ccd06aecd0eb1651dd451439d5cb365170854 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2013 17:14:47 +0100
Subject: genetlink: make genl_ops flags a u8 and move to end

To save some space in the struct on 32-bit systems,
make the flags a u8 (only 4 bits are used) and also
move them to the end of the struct.

This has no impact on 64-bit systems as alignment of
the struct in an array uses up the space anyway.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index d87486aa0611..0b6a144468c6 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -112,15 +112,15 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net)
  * @ops_list: operations list
  */
 struct genl_ops {
-	u8			cmd;
-	u8			internal_flags;
-	unsigned int		flags;
 	const struct nla_policy	*policy;
 	int		       (*doit)(struct sk_buff *skb,
 				       struct genl_info *info);
 	int		       (*dumpit)(struct sk_buff *skb,
 					 struct netlink_callback *cb);
 	int		       (*done)(struct netlink_callback *cb);
+	u8			cmd;
+	u8			internal_flags;
+	u8			flags;
 };
 
 int __genl_register_family(struct genl_family *family);
-- 
cgit 


From 7b1998116bbb2f3e5dd6cb9a8ee6db479b0b50a9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 11 Nov 2013 22:41:56 +0100
Subject: ACPI / driver core: Store an ACPI device pointer in struct
 acpi_dev_node

Modify struct acpi_dev_node to contain a pointer to struct acpi_device
associated with the given device object (that is, its ACPI companion
device) instead of an ACPI handle corresponding to it.  Introduce two
new macros for manipulating that pointer in a CONFIG_ACPI-safe way,
ACPI_COMPANION() and ACPI_COMPANION_SET(), and rework the
ACPI_HANDLE() macro to take the above changes into account.
Drop the ACPI_HANDLE_SET() macro entirely and rework its users to
use ACPI_COMPANION_SET() instead.  For some of them who used to
pass the result of acpi_get_child() directly to ACPI_HANDLE_SET()
introduce a helper routine acpi_preset_companion() doing an
equivalent thing.

The main motivation for doing this is that there are things
represented by struct acpi_device objects that don't have valid
ACPI handles (so called fixed ACPI hardware features, such as
power and sleep buttons) and we would like to create platform
device objects for them and "glue" them to their ACPI companions
in the usual way (which currently is impossible due to the
lack of valid ACPI handles).  However, there are more reasons
why it may be useful.

First, struct acpi_device pointers allow of much better type checking
than void pointers which are ACPI handles, so it should be more
difficult to write buggy code using modified struct acpi_dev_node
and the new macros.  Second, the change should help to reduce (over
time) the number of places in which the result of ACPI_HANDLE() is
passed to acpi_bus_get_device() in order to obtain a pointer to the
struct acpi_device associated with the given "physical" device,
because now that pointer is returned by ACPI_COMPANION() directly.
Finally, the change should make it easier to write generic code that
will build both for CONFIG_ACPI set and unset without adding explicit
compiler directives to it.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com> # on Haswell
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Aaron Lu <aaron.lu@intel.com> # for ATA and SDIO part
---
 arch/ia64/hp/common/sba_iommu.c              |  2 +-
 arch/ia64/include/asm/pci.h                  |  2 +-
 arch/ia64/pci/pci.c                          |  6 ++--
 arch/ia64/sn/kernel/io_acpi_init.c           |  4 +--
 arch/x86/include/asm/pci.h                   |  2 +-
 arch/x86/pci/acpi.c                          |  4 +--
 drivers/acpi/acpi_platform.c                 |  2 +-
 drivers/acpi/device_pm.c                     |  6 +---
 drivers/acpi/glue.c                          | 47 ++++++++++++++--------------
 drivers/ata/libata-acpi.c                    |  4 +--
 drivers/base/platform.c                      |  4 +--
 drivers/gpio/gpiolib.c                       |  1 +
 drivers/gpu/drm/radeon/radeon_atpx_handler.c |  3 +-
 drivers/hid/i2c-hid/i2c-hid.c                |  2 +-
 drivers/i2c/i2c-core.c                       |  4 +--
 drivers/ide/ide-acpi.c                       |  3 +-
 drivers/mmc/core/sdio_bus.c                  |  3 +-
 drivers/pci/hotplug/sgi_hotplug.c            |  8 ++---
 drivers/spi/spi.c                            |  2 +-
 include/acpi/acpi_bus.h                      |  2 +-
 include/linux/acpi.h                         | 15 +++++++++
 include/linux/device.h                       | 12 ++-----
 22 files changed, 70 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index d43daf192b21..4c530a82fc46 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1992,7 +1992,7 @@ sba_connect_bus(struct pci_bus *bus)
 	if (PCI_CONTROLLER(bus)->iommu)
 		return;
 
-	handle = PCI_CONTROLLER(bus)->acpi_handle;
+	handle = acpi_device_handle(PCI_CONTROLLER(bus)->companion);
 	if (!handle)
 		return;
 
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 80775f55f03f..71fbaaa495cc 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -95,7 +95,7 @@ struct iospace_resource {
 };
 
 struct pci_controller {
-	void *acpi_handle;
+	struct acpi_device *companion;
 	void *iommu;
 	int segment;
 	int node;		/* nearest node with memory or -1 for global allocation */
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 2326790b7d8b..9e4938d8ca4d 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -436,9 +436,9 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 	if (!controller)
 		return NULL;
 
-	controller->acpi_handle = device->handle;
+	controller->companion = device;
 
-	pxm = acpi_get_pxm(controller->acpi_handle);
+	pxm = acpi_get_pxm(device->handle);
 #ifdef CONFIG_NUMA
 	if (pxm >= 0)
 		controller->node = pxm_to_node(pxm);
@@ -489,7 +489,7 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
 	struct pci_controller *controller = bridge->bus->sysdata;
 
-	ACPI_HANDLE_SET(&bridge->dev, controller->acpi_handle);
+	ACPI_COMPANION_SET(&bridge->dev, controller->companion);
 	return 0;
 }
 
diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c
index b1725398b5af..0640739cc20c 100644
--- a/arch/ia64/sn/kernel/io_acpi_init.c
+++ b/arch/ia64/sn/kernel/io_acpi_init.c
@@ -132,7 +132,7 @@ sn_get_bussoft_ptr(struct pci_bus *bus)
 	struct acpi_resource_vendor_typed *vendor;
 
 
-	handle = PCI_CONTROLLER(bus)->acpi_handle;
+	handle = acpi_device_handle(PCI_CONTROLLER(bus)->companion);
 	status = acpi_get_vendor_resource(handle, METHOD_NAME__CRS,
 					  &sn_uuid, &buffer);
 	if (ACPI_FAILURE(status)) {
@@ -360,7 +360,7 @@ sn_acpi_get_pcidev_info(struct pci_dev *dev, struct pcidev_info **pcidev_info,
 	acpi_status status;
 	struct acpi_buffer name_buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
-	rootbus_handle = PCI_CONTROLLER(dev)->acpi_handle;
+	rootbus_handle = acpi_device_handle(PCI_CONTROLLER(dev)->companion);
         status = acpi_evaluate_integer(rootbus_handle, METHOD_NAME__SEG, NULL,
                                        &segment);
         if (ACPI_SUCCESS(status)) {
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 7d7443283a9d..947b5c417e83 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -15,7 +15,7 @@ struct pci_sysdata {
 	int		domain;		/* PCI domain */
 	int		node;		/* NUMA node */
 #ifdef CONFIG_ACPI
-	void		*acpi;		/* ACPI-specific data */
+	struct acpi_device *companion;	/* ACPI companion device */
 #endif
 #ifdef CONFIG_X86_64
 	void		*iommu;		/* IOMMU private data */
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 7fb24e53d4c8..4f25ec077552 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -518,7 +518,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 	sd = &info->sd;
 	sd->domain = domain;
 	sd->node = node;
-	sd->acpi = device->handle;
+	sd->companion = device;
 	/*
 	 * Maybe the desired pci bus has been already scanned. In such case
 	 * it is unnecessary to scan the pci bus with the given domain,busnum.
@@ -589,7 +589,7 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
 	struct pci_sysdata *sd = bridge->bus->sysdata;
 
-	ACPI_HANDLE_SET(&bridge->dev, sd->acpi);
+	ACPI_COMPANION_SET(&bridge->dev, sd->companion);
 	return 0;
 }
 
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 8a4cfc7e71f0..dbfe49e5fd63 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -111,7 +111,7 @@ int acpi_create_platform_device(struct acpi_device *adev,
 	pdevinfo.id = -1;
 	pdevinfo.res = resources;
 	pdevinfo.num_res = count;
-	pdevinfo.acpi_node.handle = adev->handle;
+	pdevinfo.acpi_node.companion = adev;
 	pdev = platform_device_register_full(&pdevinfo);
 	if (IS_ERR(pdev)) {
 		dev_err(&adev->dev, "platform device creation failed: %ld\n",
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index d42b2fb5a7e9..119afda0968c 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -22,16 +22,12 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
-#include <linux/device.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 
-#include <acpi/acpi.h>
-#include <acpi/acpi_bus.h>
-#include <acpi/acpi_drivers.h>
-
 #include "internal.h"
 
 #define _COMPONENT	ACPI_POWER_COMPONENT
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 10f0f40587bb..782071fd3df3 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -197,30 +197,27 @@ static void acpi_physnode_link_name(char *buf, unsigned int node_id)
 
 int acpi_bind_one(struct device *dev, acpi_handle handle)
 {
-	struct acpi_device *acpi_dev;
-	acpi_status status;
+	struct acpi_device *acpi_dev = NULL;
 	struct acpi_device_physical_node *physical_node, *pn;
 	char physical_node_name[PHYSICAL_NODE_NAME_SIZE];
 	struct list_head *physnode_list;
 	unsigned int node_id;
 	int retval = -EINVAL;
 
-	if (ACPI_HANDLE(dev)) {
+	if (ACPI_COMPANION(dev)) {
 		if (handle) {
-			dev_warn(dev, "ACPI handle is already set\n");
+			dev_warn(dev, "ACPI companion already set\n");
 			return -EINVAL;
 		} else {
-			handle = ACPI_HANDLE(dev);
+			acpi_dev = ACPI_COMPANION(dev);
 		}
+	} else {
+		acpi_bus_get_device(handle, &acpi_dev);
 	}
-	if (!handle)
+	if (!acpi_dev)
 		return -EINVAL;
 
 	get_device(dev);
-	status = acpi_bus_get_device(handle, &acpi_dev);
-	if (ACPI_FAILURE(status))
-		goto err;
-
 	physical_node = kzalloc(sizeof(*physical_node), GFP_KERNEL);
 	if (!physical_node) {
 		retval = -ENOMEM;
@@ -242,7 +239,7 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 
 			dev_warn(dev, "Already associated with ACPI node\n");
 			kfree(physical_node);
-			if (ACPI_HANDLE(dev) != handle)
+			if (ACPI_COMPANION(dev) != acpi_dev)
 				goto err;
 
 			put_device(dev);
@@ -259,8 +256,8 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 	list_add(&physical_node->node, physnode_list);
 	acpi_dev->physical_node_count++;
 
-	if (!ACPI_HANDLE(dev))
-		ACPI_HANDLE_SET(dev, acpi_dev->handle);
+	if (!ACPI_COMPANION(dev))
+		ACPI_COMPANION_SET(dev, acpi_dev);
 
 	acpi_physnode_link_name(physical_node_name, node_id);
 	retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
@@ -283,7 +280,7 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
 	return 0;
 
  err:
-	ACPI_HANDLE_SET(dev, NULL);
+	ACPI_COMPANION_SET(dev, NULL);
 	put_device(dev);
 	return retval;
 }
@@ -291,19 +288,12 @@ EXPORT_SYMBOL_GPL(acpi_bind_one);
 
 int acpi_unbind_one(struct device *dev)
 {
+	struct acpi_device *acpi_dev = ACPI_COMPANION(dev);
 	struct acpi_device_physical_node *entry;
-	struct acpi_device *acpi_dev;
-	acpi_status status;
 
-	if (!ACPI_HANDLE(dev))
+	if (!acpi_dev)
 		return 0;
 
-	status = acpi_bus_get_device(ACPI_HANDLE(dev), &acpi_dev);
-	if (ACPI_FAILURE(status)) {
-		dev_err(dev, "Oops, ACPI handle corrupt in %s()\n", __func__);
-		return -EINVAL;
-	}
-
 	mutex_lock(&acpi_dev->physical_node_lock);
 
 	list_for_each_entry(entry, &acpi_dev->physical_node_list, node)
@@ -316,7 +306,7 @@ int acpi_unbind_one(struct device *dev)
 			acpi_physnode_link_name(physnode_name, entry->node_id);
 			sysfs_remove_link(&acpi_dev->dev.kobj, physnode_name);
 			sysfs_remove_link(&dev->kobj, "firmware_node");
-			ACPI_HANDLE_SET(dev, NULL);
+			ACPI_COMPANION_SET(dev, NULL);
 			/* acpi_bind_one() increase refcnt by one. */
 			put_device(dev);
 			kfree(entry);
@@ -328,6 +318,15 @@ int acpi_unbind_one(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(acpi_unbind_one);
 
+void acpi_preset_companion(struct device *dev, acpi_handle parent, u64 addr)
+{
+	struct acpi_device *adev;
+
+	if (!acpi_bus_get_device(acpi_get_child(parent, addr), &adev))
+		ACPI_COMPANION_SET(dev, adev);
+}
+EXPORT_SYMBOL_GPL(acpi_preset_companion);
+
 static int acpi_platform_notify(struct device *dev)
 {
 	struct acpi_bus_type *type = acpi_get_bus_type(dev);
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index ab714d2ad978..4372cfa883c9 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -185,7 +185,7 @@ void ata_acpi_bind_port(struct ata_port *ap)
 	if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA || !host_handle)
 		return;
 
-	ACPI_HANDLE_SET(&ap->tdev, acpi_get_child(host_handle, ap->port_no));
+	acpi_preset_companion(&ap->tdev, host_handle, ap->port_no);
 
 	if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0)
 		ap->pflags |= ATA_PFLAG_INIT_GTM_VALID;
@@ -222,7 +222,7 @@ void ata_acpi_bind_dev(struct ata_device *dev)
 		parent_handle = port_handle;
 	}
 
-	ACPI_HANDLE_SET(&dev->tdev, acpi_get_child(parent_handle, adr));
+	acpi_preset_companion(&dev->tdev, parent_handle, adr);
 
 	register_hotplug_dock_device(ata_dev_acpi_handle(dev),
 				     &ata_acpi_dev_dock_ops, dev, NULL, NULL);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 47051cd25113..3a94b799f166 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -432,7 +432,7 @@ struct platform_device *platform_device_register_full(
 		goto err_alloc;
 
 	pdev->dev.parent = pdevinfo->parent;
-	ACPI_HANDLE_SET(&pdev->dev, pdevinfo->acpi_node.handle);
+	ACPI_COMPANION_SET(&pdev->dev, pdevinfo->acpi_node.companion);
 
 	if (pdevinfo->dma_mask) {
 		/*
@@ -463,7 +463,7 @@ struct platform_device *platform_device_register_full(
 	ret = platform_device_add(pdev);
 	if (ret) {
 err:
-		ACPI_HANDLE_SET(&pdev->dev, NULL);
+		ACPI_COMPANION_SET(&pdev->dev, NULL);
 		kfree(pdev->dev.dma_mask);
 
 err_alloc:
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 7dd446150294..4e10b10d3ddd 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -13,6 +13,7 @@
 #include <linux/acpi_gpio.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
+#include <linux/acpi.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/gpio.h>
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index d96070bf8388..27a6e9dbd0c4 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -8,8 +8,7 @@
  */
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
-#include <acpi/acpi.h>
-#include <acpi/acpi_bus.h>
+#include <linux/acpi.h>
 #include <linux/pci.h>
 
 #include "radeon_acpi.h"
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index fd7ce374f812..b7ecc3623a43 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -1012,7 +1012,7 @@ static int i2c_hid_probe(struct i2c_client *client,
 	hid->hid_get_raw_report = i2c_hid_get_raw_report;
 	hid->hid_output_raw_report = i2c_hid_output_raw_report;
 	hid->dev.parent = &client->dev;
-	ACPI_HANDLE_SET(&hid->dev, ACPI_HANDLE(&client->dev));
+	ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
 	hid->bus = BUS_I2C;
 	hid->version = le16_to_cpu(ihid->hdesc.bcdVersion);
 	hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 75ba8608383e..f74af33f5ddc 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -674,7 +674,7 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.bus = &i2c_bus_type;
 	client->dev.type = &i2c_client_type;
 	client->dev.of_node = info->of_node;
-	ACPI_HANDLE_SET(&client->dev, info->acpi_node.handle);
+	ACPI_COMPANION_SET(&client->dev, info->acpi_node.companion);
 
 	/* For 10-bit clients, add an arbitrary offset to avoid collisions */
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
@@ -1103,7 +1103,7 @@ static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
 		return AE_OK;
 
 	memset(&info, 0, sizeof(info));
-	info.acpi_node.handle = handle;
+	info.acpi_node.companion = adev;
 	info.irq = -1;
 
 	INIT_LIST_HEAD(&resource_list);
diff --git a/drivers/ide/ide-acpi.c b/drivers/ide/ide-acpi.c
index 140c8ef50529..3662c4c536d6 100644
--- a/drivers/ide/ide-acpi.c
+++ b/drivers/ide/ide-acpi.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2006 Hannes Reinecke
  */
 
+#include <linux/acpi.h>
 #include <linux/ata.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -19,8 +20,6 @@
 #include <linux/dmi.h>
 #include <linux/module.h>
 
-#include <acpi/acpi_bus.h>
-
 #define REGS_PER_GTF		7
 
 struct GTM_buffer {
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index ef8956568c3a..157b570ba343 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -308,8 +308,7 @@ static void sdio_acpi_set_handle(struct sdio_func *func)
 	struct mmc_host *host = func->card->host;
 	u64 addr = (host->slotno << 16) | func->num;
 
-	ACPI_HANDLE_SET(&func->dev,
-			acpi_get_child(ACPI_HANDLE(host->parent), addr));
+	acpi_preset_companion(&func->dev, ACPI_HANDLE(host->parent), addr);
 }
 #else
 static inline void sdio_acpi_set_handle(struct sdio_func *func) {}
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index b2781dfe60e9..5b05a68cca6c 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -9,6 +9,7 @@
  * Work to add BIOS PROM support was completed by Mike Habeck.
  */
 
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -29,7 +30,6 @@
 #include <asm/sn/sn_feature_sets.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/types.h>
-#include <linux/acpi.h>
 #include <asm/sn/acpi.h>
 
 #include "../pci.h"
@@ -414,7 +414,7 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
 		acpi_handle rethandle;
 		acpi_status ret;
 
-		phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+		phandle = acpi_device_handle(PCI_CONTROLLER(slot->pci_bus)->companion);
 
 		if (acpi_bus_get_device(phandle, &pdevice)) {
 			dev_dbg(&slot->pci_bus->self->dev,
@@ -495,7 +495,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 
 	/* free the ACPI resources for the slot */
 	if (SN_ACPI_BASE_SUPPORT() &&
-            PCI_CONTROLLER(slot->pci_bus)->acpi_handle) {
+            PCI_CONTROLLER(slot->pci_bus)->companion) {
 		unsigned long long adr;
 		struct acpi_device *device;
 		acpi_handle phandle;
@@ -504,7 +504,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 		acpi_status ret;
 
 		/* Get the rootbus node pointer */
-		phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+		phandle = acpi_device_handle(PCI_CONTROLLER(slot->pci_bus)->companion);
 
 		acpi_scan_lock_acquire();
 		/*
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 927998aa5e71..a968d8549ee5 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1144,7 +1144,7 @@ static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
 		return AE_NO_MEMORY;
 	}
 
-	ACPI_HANDLE_SET(&spi->dev, handle);
+	ACPI_COMPANION_SET(&spi->dev, adev);
 	spi->irq = -1;
 
 	INIT_LIST_HEAD(&resource_list);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 89c60b0f6408..7b2de026a4f3 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -431,9 +431,9 @@ static inline acpi_handle acpi_get_child(acpi_handle handle, u64 addr)
 {
 	return acpi_find_child(handle, addr, false);
 }
+void acpi_preset_companion(struct device *dev, acpi_handle parent, u64 addr);
 int acpi_is_root_bridge(acpi_handle);
 struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle);
-#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)ACPI_HANDLE(dev))
 
 int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index b0972c4ce81c..47369aadb1d1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -44,6 +44,15 @@
 #include <acpi/acpi_numa.h>
 #include <asm/acpi.h>
 
+static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
+{
+	return adev ? adev->handle : NULL;
+}
+
+#define ACPI_COMPANION(dev)		((dev)->acpi_node.companion)
+#define ACPI_COMPANION_SET(dev, adev)	ACPI_COMPANION(dev) = (adev)
+#define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
+
 enum acpi_irq_model_id {
 	ACPI_IRQ_MODEL_PIC = 0,
 	ACPI_IRQ_MODEL_IOAPIC,
@@ -401,6 +410,10 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #define acpi_disabled 1
 
+#define ACPI_COMPANION(dev)		(NULL)
+#define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
+#define ACPI_HANDLE(dev)		(NULL)
+
 static inline void acpi_early_init(void) { }
 
 static inline int early_acpi_boot_init(void)
@@ -469,6 +482,8 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #endif	/* !CONFIG_ACPI */
 
+#define DEVICE_ACPI_HANDLE(dev)	ACPI_HANDLE(dev)
+
 #ifdef CONFIG_ACPI
 void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 			       u32 pm1a_ctrl,  u32 pm1b_ctrl));
diff --git a/include/linux/device.h b/include/linux/device.h
index b025925df7f7..952b01033c32 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -644,9 +644,11 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
+struct acpi_device;
+
 struct acpi_dev_node {
 #ifdef CONFIG_ACPI
-	void	*handle;
+	struct acpi_device *companion;
 #endif
 };
 
@@ -790,14 +792,6 @@ static inline struct device *kobj_to_dev(struct kobject *kobj)
 	return container_of(kobj, struct device, kobj);
 }
 
-#ifdef CONFIG_ACPI
-#define ACPI_HANDLE(dev)	((dev)->acpi_node.handle)
-#define ACPI_HANDLE_SET(dev, _handle_)	(dev)->acpi_node.handle = (_handle_)
-#else
-#define ACPI_HANDLE(dev)	(NULL)
-#define ACPI_HANDLE_SET(dev, _handle_)	do { } while (0)
-#endif
-
 /* Get the wakeup routines, which depend on struct device */
 #include <linux/pm_wakeup.h>
 
-- 
cgit 


From 3a83f992490f8235661b768e53bd5f14915420ac Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 14 Nov 2013 23:17:21 +0100
Subject: ACPI: Eliminate the DEVICE_ACPI_HANDLE() macro

Since DEVICE_ACPI_HANDLE() is now literally identical to
ACPI_HANDLE(), replace it with the latter everywhere and drop its
definition from include/acpi.h.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/acpi/device_pm.c                       |  8 ++++----
 drivers/gpu/drm/i915/intel_acpi.c              |  2 +-
 drivers/gpu/drm/i915/intel_opregion.c          |  2 +-
 drivers/gpu/drm/nouveau/core/subdev/mxm/base.c |  2 +-
 drivers/gpu/drm/nouveau/nouveau_acpi.c         |  6 +++---
 drivers/gpu/drm/radeon/radeon_acpi.c           |  8 ++++----
 drivers/gpu/drm/radeon/radeon_atpx_handler.c   |  4 ++--
 drivers/gpu/drm/radeon/radeon_bios.c           |  2 +-
 drivers/ide/ide-acpi.c                         |  2 +-
 drivers/pci/hotplug/acpi_pcihp.c               |  2 +-
 drivers/pci/hotplug/pciehp_acpi.c              |  4 ++--
 drivers/pci/ioapic.c                           |  2 +-
 drivers/pci/pci-acpi.c                         |  6 +++---
 drivers/pci/pci-label.c                        |  6 +++---
 drivers/platform/x86/apple-gmux.c              |  2 +-
 drivers/pnp/pnpacpi/core.c                     | 10 +++++-----
 drivers/usb/core/hub.c                         |  2 +-
 drivers/usb/core/usb-acpi.c                    |  4 ++--
 drivers/xen/pci.c                              |  6 +++---
 include/linux/acpi.h                           |  2 --
 include/linux/pci-acpi.h                       |  4 ++--
 21 files changed, 42 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 119afda0968c..b3480cf7db1a 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -544,7 +544,7 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev,
  */
 int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+	acpi_handle handle = ACPI_HANDLE(dev);
 	struct acpi_device *adev;
 	int ret, d_min, d_max;
 
@@ -652,7 +652,7 @@ int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
 	if (!device_run_wake(phys_dev))
 		return -EINVAL;
 
-	handle = DEVICE_ACPI_HANDLE(phys_dev);
+	handle = ACPI_HANDLE(phys_dev);
 	if (!handle || acpi_bus_get_device(handle, &adev)) {
 		dev_dbg(phys_dev, "ACPI handle without context in %s!\n",
 			__func__);
@@ -696,7 +696,7 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 	if (!device_can_wakeup(dev))
 		return -EINVAL;
 
-	handle = DEVICE_ACPI_HANDLE(dev);
+	handle = ACPI_HANDLE(dev);
 	if (!handle || acpi_bus_get_device(handle, &adev)) {
 		dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
 		return -ENODEV;
@@ -718,7 +718,7 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
  */
 struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+	acpi_handle handle = ACPI_HANDLE(dev);
 	struct acpi_device *adev;
 
 	return handle && !acpi_bus_get_device(handle, &adev) ? adev : NULL;
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index 43959edd4291..dfff0907f70e 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -196,7 +196,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev)
 	acpi_handle dhandle;
 	int ret;
 
-	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
 
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 119771ff46ab..8a94b8e15b27 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -289,7 +289,7 @@ static void intel_didl_outputs(struct drm_device *dev)
 	u32 temp;
 	int i = 0;
 
-	handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev);
+	handle = ACPI_HANDLE(&dev->pdev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev))
 		return;
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c b/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
index e286e132c7e7..129120473f6c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
@@ -116,7 +116,7 @@ mxm_shadow_dsm(struct nouveau_mxm *mxm, u8 version)
 	acpi_handle handle;
 	int ret;
 
-	handle = DEVICE_ACPI_HANDLE(&device->pdev->dev);
+	handle = ACPI_HANDLE(&device->pdev->dev);
 	if (!handle)
 		return false;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index cfbeee607b3a..d9eb65dae1f7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -256,7 +256,7 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
 	acpi_handle dhandle;
 	int retval = 0;
 
-	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
 
@@ -404,7 +404,7 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev)
 	if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
 		return false;
 
-	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
 
@@ -438,7 +438,7 @@ nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector)
 		return NULL;
 	}
 
-	handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev);
+	handle = ACPI_HANDLE(&dev->pdev->dev);
 	if (!handle)
 		return NULL;
 
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 10f98c7742d8..98a9074b306b 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -369,7 +369,7 @@ int radeon_atif_handler(struct radeon_device *rdev,
 		return NOTIFY_DONE;
 
 	/* Check pending SBIOS requests */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	count = radeon_atif_get_sbios_requests(handle, &req);
 
 	if (count <= 0)
@@ -556,7 +556,7 @@ int radeon_acpi_pcie_notify_device_ready(struct radeon_device *rdev)
 	struct radeon_atcs *atcs = &rdev->atcs;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	if (!handle)
 		return -EINVAL;
 
@@ -596,7 +596,7 @@ int radeon_acpi_pcie_performance_request(struct radeon_device *rdev,
 	u32 retry = 3;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 	if (!handle)
 		return -EINVAL;
 
@@ -699,7 +699,7 @@ int radeon_acpi_init(struct radeon_device *rdev)
 	int ret;
 
 	/* Get the device handle */
-	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+	handle = ACPI_HANDLE(&rdev->pdev->dev);
 
 	/* No need to proceed if we're sure that ATIF is not supported */
 	if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 27a6e9dbd0c4..933bd946057b 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -442,7 +442,7 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 	acpi_handle dhandle, atpx_handle;
 	acpi_status status;
 
-	dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
 
@@ -488,7 +488,7 @@ static int radeon_atpx_init(void)
  */
 static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 {
-	if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
+	if (radeon_atpx_priv.dhandle == ACPI_HANDLE(&pdev->dev))
 		return VGA_SWITCHEROO_IGD;
 	else
 		return VGA_SWITCHEROO_DIS;
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 061b227dae0c..374eaba78a69 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -185,7 +185,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 		return false;
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
-		dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+		dhandle = ACPI_HANDLE(&pdev->dev);
 		if (!dhandle)
 			continue;
 
diff --git a/drivers/ide/ide-acpi.c b/drivers/ide/ide-acpi.c
index 3662c4c536d6..d9e1f7ccfe6f 100644
--- a/drivers/ide/ide-acpi.c
+++ b/drivers/ide/ide-acpi.c
@@ -127,7 +127,7 @@ static int ide_get_dev_handle(struct device *dev, acpi_handle *handle,
 
 	DEBPRINT("ENTER: pci %02x:%02x.%01x\n", bus, devnum, func);
 
-	dev_handle = DEVICE_ACPI_HANDLE(dev);
+	dev_handle = ACPI_HANDLE(dev);
 	if (!dev_handle) {
 		DEBPRINT("no acpi handle for device\n");
 		goto err;
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 1ce8ee054f1a..a94d850ae228 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -367,7 +367,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
 		string = (struct acpi_buffer){ ACPI_ALLOCATE_BUFFER, NULL };
 	}
 
-	handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	handle = ACPI_HANDLE(&pdev->dev);
 	if (!handle) {
 		/*
 		 * This hotplug controller was not listed in the ACPI name
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
index ead7c534095e..cff7cadfc2e4 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -54,7 +54,7 @@ int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
 {
 	if (slot_detection_mode != PCIEHP_DETECT_ACPI)
 		return 0;
-	if (acpi_pci_detect_ejectable(DEVICE_ACPI_HANDLE(&dev->dev)))
+	if (acpi_pci_detect_ejectable(ACPI_HANDLE(&dev->dev)))
 		return 0;
 	return -ENODEV;
 }
@@ -96,7 +96,7 @@ static int __init dummy_probe(struct pcie_device *dev)
 			dup_slot_id++;
 	}
 	list_add_tail(&slot->list, &dummy_slots);
-	handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+	handle = ACPI_HANDLE(&pdev->dev);
 	if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle))
 		acpi_slot_detected = 1;
 	return -ENODEV;         /* dummy driver always returns error */
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 1b90579b233a..50ce68098298 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -37,7 +37,7 @@ static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 	char *type;
 	struct resource *res;
 
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	handle = ACPI_HANDLE(&dev->dev);
 	if (!handle)
 		return -EINVAL;
 
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index dfd1f59de729..f166126e28d1 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -173,14 +173,14 @@ static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
 
 static bool acpi_pci_power_manageable(struct pci_dev *dev)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	acpi_handle handle = ACPI_HANDLE(&dev->dev);
 
 	return handle ? acpi_bus_power_manageable(handle) : false;
 }
 
 static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	acpi_handle handle = ACPI_HANDLE(&dev->dev);
 	static const u8 state_conv[] = {
 		[PCI_D0] = ACPI_STATE_D0,
 		[PCI_D1] = ACPI_STATE_D1,
@@ -217,7 +217,7 @@ static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 static bool acpi_pci_can_wakeup(struct pci_dev *dev)
 {
-	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	acpi_handle handle = ACPI_HANDLE(&dev->dev);
 
 	return handle ? acpi_bus_can_wakeup(handle) : false;
 }
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index edaed6f4da6c..d51f45aa669e 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -263,7 +263,7 @@ device_has_dsm(struct device *dev)
 	acpi_handle handle;
 	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
 
-	handle = DEVICE_ACPI_HANDLE(dev);
+	handle = ACPI_HANDLE(dev);
 
 	if (!handle)
 		return FALSE;
@@ -295,7 +295,7 @@ acpilabel_show(struct device *dev, struct device_attribute *attr, char *buf)
 	acpi_handle handle;
 	int length;
 
-	handle = DEVICE_ACPI_HANDLE(dev);
+	handle = ACPI_HANDLE(dev);
 
 	if (!handle)
 		return -1;
@@ -316,7 +316,7 @@ acpiindex_show(struct device *dev, struct device_attribute *attr, char *buf)
 	acpi_handle handle;
 	int length;
 
-	handle = DEVICE_ACPI_HANDLE(dev);
+	handle = ACPI_HANDLE(dev);
 
 	if (!handle)
 		return -1;
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index 8eea2efbbb6d..5753c82335ad 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -519,7 +519,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
 
 	gmux_data->power_state = VGA_SWITCHEROO_ON;
 
-	gmux_data->dhandle = DEVICE_ACPI_HANDLE(&pnp->dev);
+	gmux_data->dhandle = ACPI_HANDLE(&pnp->dev);
 	if (!gmux_data->dhandle) {
 		pr_err("Cannot find acpi handle for pnp device %s\n",
 		       dev_name(&pnp->dev));
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index 747826d99059..14655a0f0431 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -89,7 +89,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
 
 	pnp_dbg(&dev->dev, "set resources\n");
 
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	handle = ACPI_HANDLE(&dev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
 		dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
 		return -ENODEV;
@@ -122,7 +122,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
 
 	dev_dbg(&dev->dev, "disable resources\n");
 
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	handle = ACPI_HANDLE(&dev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
 		dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
 		return 0;
@@ -144,7 +144,7 @@ static bool pnpacpi_can_wakeup(struct pnp_dev *dev)
 	struct acpi_device *acpi_dev;
 	acpi_handle handle;
 
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	handle = ACPI_HANDLE(&dev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
 		dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
 		return false;
@@ -159,7 +159,7 @@ static int pnpacpi_suspend(struct pnp_dev *dev, pm_message_t state)
 	acpi_handle handle;
 	int error = 0;
 
-	handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	handle = ACPI_HANDLE(&dev->dev);
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
 		dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
 		return 0;
@@ -194,7 +194,7 @@ static int pnpacpi_suspend(struct pnp_dev *dev, pm_message_t state)
 static int pnpacpi_resume(struct pnp_dev *dev)
 {
 	struct acpi_device *acpi_dev;
-	acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+	acpi_handle handle = ACPI_HANDLE(&dev->dev);
 	int error = 0;
 
 	if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 06cec635e703..a7c04e24ca48 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5501,6 +5501,6 @@ acpi_handle usb_get_hub_port_acpi_handle(struct usb_device *hdev,
 	if (!hub)
 		return NULL;
 
-	return DEVICE_ACPI_HANDLE(&hub->ports[port1 - 1]->dev);
+	return ACPI_HANDLE(&hub->ports[port1 - 1]->dev);
 }
 #endif
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index 255c14464bf2..4e243c37f17f 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -173,7 +173,7 @@ static int usb_acpi_find_device(struct device *dev, acpi_handle *handle)
 		}
 
 		/* root hub's parent is the usb hcd. */
-		parent_handle = DEVICE_ACPI_HANDLE(dev->parent);
+		parent_handle = ACPI_HANDLE(dev->parent);
 		*handle = acpi_get_child(parent_handle, udev->portnum);
 		if (!*handle)
 			return -ENODEV;
@@ -194,7 +194,7 @@ static int usb_acpi_find_device(struct device *dev, acpi_handle *handle)
 
 			raw_port_num = usb_hcd_find_raw_port_number(hcd,
 				port_num);
-			*handle = acpi_get_child(DEVICE_ACPI_HANDLE(&udev->dev),
+			*handle = acpi_get_child(ACPI_HANDLE(&udev->dev),
 				raw_port_num);
 			if (!*handle)
 				return -ENODEV;
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index 18fff88254eb..cc86b267056f 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -58,12 +58,12 @@ static int xen_add_device(struct device *dev)
 			add.flags = XEN_PCI_DEV_EXTFN;
 
 #ifdef CONFIG_ACPI
-		handle = DEVICE_ACPI_HANDLE(&pci_dev->dev);
+		handle = ACPI_HANDLE(&pci_dev->dev);
 		if (!handle && pci_dev->bus->bridge)
-			handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge);
+			handle = ACPI_HANDLE(pci_dev->bus->bridge);
 #ifdef CONFIG_PCI_IOV
 		if (!handle && pci_dev->is_virtfn)
-			handle = DEVICE_ACPI_HANDLE(physfn->bus->bridge);
+			handle = ACPI_HANDLE(physfn->bus->bridge);
 #endif
 		if (handle) {
 			acpi_status status;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 47369aadb1d1..86a3ba99a38d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -482,8 +482,6 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 #endif	/* !CONFIG_ACPI */
 
-#define DEVICE_ACPI_HANDLE(dev)	ACPI_HANDLE(dev)
-
 #ifdef CONFIG_ACPI
 void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 			       u32 pm1a_ctrl,  u32 pm1b_ctrl));
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index d006f0ca60f4..5a462c4e5009 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -27,7 +27,7 @@ static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev)
 	while (!pci_is_root_bus(pbus))
 		pbus = pbus->parent;
 
-	return DEVICE_ACPI_HANDLE(pbus->bridge);
+	return ACPI_HANDLE(pbus->bridge);
 }
 
 static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus)
@@ -39,7 +39,7 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus)
 	else
 		dev = &pbus->self->dev;
 
-	return DEVICE_ACPI_HANDLE(dev);
+	return ACPI_HANDLE(dev);
 }
 
 void acpi_pci_add_bus(struct pci_bus *bus);
-- 
cgit 


From 45c42a7f582cc07259bc78910de8b0b1c94094d5 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 14 Nov 2013 14:03:51 +0200
Subject: ACPI: Provide acpi_dev_name accessor for struct acpi_device device
 name

struct acpi_device fields are only available when CONFIG_ACPI is set. We may
find use for dev_name(&adev->dev) in generic code that is build also without
CONFIG_ACPI is set but currently this requires #ifdef CONFIG_ACPI churn.

Provide here an accessor that returns dev_name of embedded struct device dev
in struct acpi_device or NULL depending on CONFIG_ACPI setting.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 86a3ba99a38d..d9099b15b472 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -53,6 +53,11 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 #define ACPI_COMPANION_SET(dev, adev)	ACPI_COMPANION(dev) = (adev)
 #define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
 
+static inline const char *acpi_dev_name(struct acpi_device *adev)
+{
+	return dev_name(&adev->dev);
+}
+
 enum acpi_irq_model_id {
 	ACPI_IRQ_MODEL_PIC = 0,
 	ACPI_IRQ_MODEL_IOAPIC,
@@ -414,6 +419,11 @@ static inline bool acpi_driver_match_device(struct device *dev,
 #define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
 #define ACPI_HANDLE(dev)		(NULL)
 
+static inline const char *acpi_dev_name(struct acpi_device *adev)
+{
+	return NULL;
+}
+
 static inline void acpi_early_init(void) { }
 
 static inline int early_acpi_boot_init(void)
-- 
cgit 


From 57c1ffcefb5acb3c8b5f8436c325a6bdbd8e9c78 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:45 -0800
Subject: mm: rename USE_SPLIT_PTLOCKS to USE_SPLIT_PTE_PTLOCKS

We're going to introduce split page table lock for PMD level.  Let's
rename existing split ptlock for PTE level to avoid confusion.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/mm/fault-armv.c | 6 +++---
 arch/x86/xen/mmu.c       | 6 +++---
 include/linux/mm.h       | 6 +++---
 include/linux/mm_types.h | 8 ++++----
 4 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2a5907b5c8d2..ff379ac115df 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -65,7 +65,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	return ret;
 }
 
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 /*
  * If we are using split PTE locks, then we need to take the page
  * lock here.  Otherwise we are using shared mm->page_table_lock
@@ -84,10 +84,10 @@ static inline void do_pte_unlock(spinlock_t *ptl)
 {
 	spin_unlock(ptl);
 }
-#else /* !USE_SPLIT_PTLOCKS */
+#else /* !USE_SPLIT_PTE_PTLOCKS */
 static inline void do_pte_lock(spinlock_t *ptl) {}
 static inline void do_pte_unlock(spinlock_t *ptl) {}
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pfn)
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fdc3ba28ca38..455c873ce009 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -796,7 +796,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
 {
 	spinlock_t *ptl = NULL;
 
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 	ptl = __pte_lockptr(page);
 	spin_lock_nest_lock(ptl, &mm->page_table_lock);
 #endif
@@ -1637,7 +1637,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 
 			__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
 				__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
@@ -1671,7 +1671,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 		if (!PageHighMem(page)) {
 			xen_mc_batch();
 
-			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
+			if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
 				__pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 
 			__set_pfn_prot(pfn, PAGE_KERNEL);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 42a35d94b82c..dc3333d6c986 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1316,7 +1316,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 /*
  * We tuck a spinlock to guard each pagetable page into its struct page,
  * at page->private, with BUILD_BUG_ON to make sure that this will not
@@ -1329,14 +1329,14 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 } while (0)
 #define pte_lock_deinit(page)	((page)->mapping = NULL)
 #define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
-#else	/* !USE_SPLIT_PTLOCKS */
+#else	/* !USE_SPLIT_PTE_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
 #define pte_lock_init(page)	do {} while (0)
 #define pte_lock_deinit(page)	do {} while (0)
 #define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 static inline void pgtable_page_ctor(struct page *page)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index a3198e5aaf4e..f1ff66dfa79e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -23,7 +23,7 @@
 
 struct address_space;
 
-#define USE_SPLIT_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+#define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -141,7 +141,7 @@ struct page {
 						 * indicates order in the buddy
 						 * system if PG_buddy is set.
 						 */
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 		spinlock_t ptl;
 #endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
@@ -309,14 +309,14 @@ enum {
 	NR_MM_COUNTERS
 };
 
-#if USE_SPLIT_PTLOCKS && defined(CONFIG_MMU)
+#if USE_SPLIT_PTE_PTLOCKS && defined(CONFIG_MMU)
 #define SPLIT_RSS_COUNTING
 /* per-thread cached information, */
 struct task_rss_stat {
 	int events;	/* for synchronization threshold */
 	int count[NR_MM_COUNTERS];
 };
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 struct mm_rss_stat {
 	atomic_long_t count[NR_MM_COUNTERS];
-- 
cgit 


From e1f56c89b040134add93f686931cc266541d239a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:48 -0800
Subject: mm: convert mm->nr_ptes to atomic_long_t

With split page table lock for PMD level we can't hold mm->page_table_lock
while updating nr_ptes.

Let's convert it to atomic_long_t to avoid races.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c       |  3 ++-
 include/linux/mm_types.h |  2 +-
 kernel/fork.c            |  2 +-
 mm/huge_memory.c         | 10 +++++-----
 mm/memory.c              |  4 ++--
 mm/mmap.c                |  3 ++-
 mm/oom_kill.c            |  6 +++---
 7 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index abbe825d20ff..8faaebdc6b02 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -62,7 +62,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
-		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
+		(PTRS_PER_PTE * sizeof(pte_t) *
+		 atomic_long_read(&mm->nr_ptes)) >> 10,
 		swap << (PAGE_SHIFT-10));
 }
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f1ff66dfa79e..566df579c51f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -339,6 +339,7 @@ struct mm_struct {
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
+	atomic_long_t nr_ptes;			/* Page table pages */
 	int map_count;				/* number of VMAs */
 
 	spinlock_t page_table_lock;		/* Protects page tables and some counters */
@@ -360,7 +361,6 @@ struct mm_struct {
 	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */
 	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */
 	unsigned long def_flags;
-	unsigned long nr_ptes;		/* Page table pages */
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long start_brk, brk, start_stack;
 	unsigned long arg_start, arg_end, env_start, env_end;
diff --git a/kernel/fork.c b/kernel/fork.c
index f6d11fc67f72..e2520756e005 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -532,7 +532,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm->flags = (current->mm) ?
 		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
-	mm->nr_ptes = 0;
+	atomic_long_set(&mm->nr_ptes, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
 	mm_init_aio(mm);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0556c6a44959..e5b2d316be2e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -738,7 +738,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		set_pmd_at(mm, haddr, pmd, entry);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
-		mm->nr_ptes++;
+		atomic_long_inc(&mm->nr_ptes);
 		spin_unlock(&mm->page_table_lock);
 	}
 
@@ -771,7 +771,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
-	mm->nr_ptes++;
+	atomic_long_inc(&mm->nr_ptes);
 	return true;
 }
 
@@ -896,7 +896,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
-	dst_mm->nr_ptes++;
+	atomic_long_inc(&dst_mm->nr_ptes);
 
 	ret = 0;
 out_unlock:
@@ -1392,7 +1392,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
-			tlb->mm->nr_ptes--;
+			atomic_long_dec(&tlb->mm->nr_ptes);
 			spin_unlock(&tlb->mm->page_table_lock);
 			put_huge_zero_page();
 		} else {
@@ -1401,7 +1401,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
-			tlb->mm->nr_ptes--;
+			atomic_long_dec(&tlb->mm->nr_ptes);
 			spin_unlock(&tlb->mm->page_table_lock);
 			tlb_remove_page(tlb, page);
 		}
diff --git a/mm/memory.c b/mm/memory.c
index bf8665849a5f..0b5a93a49f27 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -382,7 +382,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
 	pgtable_t token = pmd_pgtable(*pmd);
 	pmd_clear(pmd);
 	pte_free_tlb(tlb, token, addr);
-	tlb->mm->nr_ptes--;
+	atomic_long_dec(&tlb->mm->nr_ptes);
 }
 
 static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -573,7 +573,7 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 	wait_split_huge_page = 0;
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
-		mm->nr_ptes++;
+		atomic_long_inc(&mm->nr_ptes);
 		pmd_populate(mm, pmd, new);
 		new = NULL;
 	} else if (unlikely(pmd_trans_splitting(*pmd)))
diff --git a/mm/mmap.c b/mm/mmap.c
index 5a6baddde15d..834b2d785f1e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2724,7 +2724,8 @@ void exit_mmap(struct mm_struct *mm)
 	}
 	vm_unacct_memory(nr_accounted);
 
-	WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+	WARN_ON(atomic_long_read(&mm->nr_ptes) >
+			(FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6738c47f1f72..1e4a600a6163 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -161,7 +161,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + p->mm->nr_ptes +
+	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
 		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
@@ -364,10 +364,10 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5hd %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			task->mm->nr_ptes,
+			atomic_long_read(&task->mm->nr_ptes),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
-- 
cgit 


From 9a86cb7bdc4ccbe3f99a1ca275b90a322a90f9ce Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:51 -0800
Subject: mm: introduce api for split page table lock for PMD level

Basic api, backed by mm->page_table_lock for now. Actual implementation
will be added later.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc3333d6c986..4f4ca41fcf27 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1378,6 +1378,19 @@ static inline void pgtable_page_dtor(struct page *page)
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
 		NULL: pte_offset_kernel(pmd, address))
 
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return &mm->page_table_lock;
+}
+
+
+static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
+{
+	spinlock_t *ptl = pmd_lockptr(mm, pmd);
+	spin_lock(ptl);
+	return ptl;
+}
+
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
-- 
cgit 


From bf929152e9f6c49b66fad4ebf08cc95b02ce48f5 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:54 -0800
Subject: mm, thp: change pmd_trans_huge_lock() to return taken lock

With split ptlock it's important to know which lock
pmd_trans_huge_lock() took.  This patch adds one more parameter to the
function to return the lock.

In most places migration to new api is trivial.  Exception is
move_huge_pmd(): we need to take two locks if pmd tables are different.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c      | 13 +++++++------
 include/linux/huge_mm.h | 14 +++++++-------
 mm/huge_memory.c        | 40 +++++++++++++++++++++++++++-------------
 mm/memcontrol.c         | 10 +++++-----
 4 files changed, 46 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8faaebdc6b02..42b5cf5d0326 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -506,9 +506,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		mss->anonymous_thp += HPAGE_PMD_SIZE;
 		return 0;
 	}
@@ -999,13 +999,14 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 {
 	struct vm_area_struct *vma;
 	struct pagemapread *pm = walk->private;
+	spinlock_t *ptl;
 	pte_t *pte;
 	int err = 0;
 	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
-	if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		int pmd_flags2;
 
 		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
@@ -1023,7 +1024,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			if (err)
 				break;
 		}
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		return err;
 	}
 
@@ -1325,7 +1326,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 
 	md = walk->private;
 
-	if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
@@ -1333,7 +1334,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		if (page)
 			gather_stats(page, md, pte_dirty(huge_pte),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
-		spin_unlock(&walk->mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 3935428c57cf..4aca0d8da112 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -129,15 +129,15 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
-extern int __pmd_trans_huge_lock(pmd_t *pmd,
-				 struct vm_area_struct *vma);
+extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl);
 /* mmap_sem must be held on entry */
-static inline int pmd_trans_huge_lock(pmd_t *pmd,
-				      struct vm_area_struct *vma)
+static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
 	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
 	if (pmd_trans_huge(*pmd))
-		return __pmd_trans_huge_lock(pmd, vma);
+		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
 		return 0;
 }
@@ -215,8 +215,8 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
-static inline int pmd_trans_huge_lock(pmd_t *pmd,
-				      struct vm_area_struct *vma)
+static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
 	return 0;
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e5b2d316be2e..471eb04066ff 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1376,9 +1376,10 @@ out:
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		struct page *page;
 		pgtable_t pgtable;
 		pmd_t orig_pmd;
@@ -1393,7 +1394,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
 		if (is_huge_zero_pmd(orig_pmd)) {
 			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(&tlb->mm->page_table_lock);
+			spin_unlock(ptl);
 			put_huge_zero_page();
 		} else {
 			page = pmd_page(orig_pmd);
@@ -1402,7 +1403,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
 			atomic_long_dec(&tlb->mm->nr_ptes);
-			spin_unlock(&tlb->mm->page_table_lock);
+			spin_unlock(ptl);
 			tlb_remove_page(tlb, page);
 		}
 		pte_free(tlb->mm, pgtable);
@@ -1415,14 +1416,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end,
 		unsigned char *vec)
 {
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		/*
 		 * All logical pages in the range are present
 		 * if backed by a huge page.
 		 */
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
 		ret = 1;
 	}
@@ -1435,6 +1437,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		  unsigned long new_addr, unsigned long old_end,
 		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
+	spinlock_t *old_ptl, *new_ptl;
 	int ret = 0;
 	pmd_t pmd;
 
@@ -1455,12 +1458,21 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		goto out;
 	}
 
-	ret = __pmd_trans_huge_lock(old_pmd, vma);
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_sem prevents deadlock.
+	 */
+	ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl);
 	if (ret == 1) {
+		new_ptl = pmd_lockptr(mm, new_pmd);
+		if (new_ptl != old_ptl)
+			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		spin_unlock(&mm->page_table_lock);
+		if (new_ptl != old_ptl)
+			spin_unlock(new_ptl);
+		spin_unlock(old_ptl);
 	}
 out:
 	return ret;
@@ -1476,9 +1488,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, pgprot_t newprot, int prot_numa)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int ret = 0;
 
-	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
 		ret = 1;
 		if (!prot_numa) {
@@ -1507,7 +1520,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		if (ret == HPAGE_PMD_NR)
 			set_pmd_at(mm, addr, pmd, entry);
 
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 	}
 
 	return ret;
@@ -1520,12 +1533,13 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
  * Note that if it returns 1, this routine returns without unlocking page
  * table locks. So callers must unlock them.
  */
-int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
+int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
+		spinlock_t **ptl)
 {
-	spin_lock(&vma->vm_mm->page_table_lock);
+	*ptl = pmd_lock(vma->vm_mm, pmd);
 	if (likely(pmd_trans_huge(*pmd))) {
 		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(*ptl);
 			wait_split_huge_page(vma->anon_vma, pmd);
 			return -1;
 		} else {
@@ -1534,7 +1548,7 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 			return 1;
 		}
 	}
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(*ptl);
 	return 0;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e3cd40b2d5d9..f1a0ae6e11b8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6605,10 +6605,10 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
 			mc.precharge += HPAGE_PMD_NR;
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
@@ -6797,9 +6797,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	 *    to be unlocked in __split_huge_page_splitting(), where the main
 	 *    part of thp split is not executed yet.
 	 */
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		if (mc.precharge < HPAGE_PMD_NR) {
-			spin_unlock(&vma->vm_mm->page_table_lock);
+			spin_unlock(ptl);
 			return 0;
 		}
 		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
@@ -6816,7 +6816,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			}
 			put_page(page);
 		}
-		spin_unlock(&vma->vm_mm->page_table_lock);
+		spin_unlock(ptl);
 		return 0;
 	}
 
-- 
cgit 


From 117b0791ac42f2ec447bc864e70ad622b5604059 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:56 -0800
Subject: mm, thp: move ptl taking inside page_check_address_pmd()

With split page table lock we can't know which lock we need to take
before we find the relevant pmd.

Let's move lock taking inside the function.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h |  3 ++-
 mm/huge_memory.c        | 43 +++++++++++++++++++++++++++----------------
 mm/rmap.c               | 13 +++++--------
 3 files changed, 34 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 4aca0d8da112..91672e2deec3 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -54,7 +54,8 @@ enum page_check_address_pmd_flag {
 extern pmd_t *page_check_address_pmd(struct page *page,
 				     struct mm_struct *mm,
 				     unsigned long address,
-				     enum page_check_address_pmd_flag flag);
+				     enum page_check_address_pmd_flag flag,
+				     spinlock_t **ptl);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 471eb04066ff..c2082ab4fc93 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1552,23 +1552,33 @@ int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 	return 0;
 }
 
+/*
+ * This function returns whether a given @page is mapped onto the @address
+ * in the virtual space of @mm.
+ *
+ * When it's true, this function returns *pmd with holding the page table lock
+ * and passing it back to the caller via @ptl.
+ * If it's false, returns NULL without holding the page table lock.
+ */
 pmd_t *page_check_address_pmd(struct page *page,
 			      struct mm_struct *mm,
 			      unsigned long address,
-			      enum page_check_address_pmd_flag flag)
+			      enum page_check_address_pmd_flag flag,
+			      spinlock_t **ptl)
 {
-	pmd_t *pmd, *ret = NULL;
+	pmd_t *pmd;
 
 	if (address & ~HPAGE_PMD_MASK)
-		goto out;
+		return NULL;
 
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd)
-		goto out;
+		return NULL;
+	*ptl = pmd_lock(mm, pmd);
 	if (pmd_none(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_page(*pmd) != page)
-		goto out;
+		goto unlock;
 	/*
 	 * split_vma() may create temporary aliased mappings. There is
 	 * no risk as long as all huge pmd are found and have their
@@ -1578,14 +1588,15 @@ pmd_t *page_check_address_pmd(struct page *page,
 	 */
 	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
 	    pmd_trans_splitting(*pmd))
-		goto out;
+		goto unlock;
 	if (pmd_trans_huge(*pmd)) {
 		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
 			  !pmd_trans_splitting(*pmd));
-		ret = pmd;
+		return pmd;
 	}
-out:
-	return ret;
+unlock:
+	spin_unlock(*ptl);
+	return NULL;
 }
 
 static int __split_huge_page_splitting(struct page *page,
@@ -1593,6 +1604,7 @@ static int __split_huge_page_splitting(struct page *page,
 				       unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd;
 	int ret = 0;
 	/* For mmu_notifiers */
@@ -1600,9 +1612,8 @@ static int __split_huge_page_splitting(struct page *page,
 	const unsigned long mmun_end   = address + HPAGE_PMD_SIZE;
 
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);
 	if (pmd) {
 		/*
 		 * We can't temporarily set the pmd to null in order
@@ -1613,8 +1624,8 @@ static int __split_huge_page_splitting(struct page *page,
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	return ret;
@@ -1745,14 +1756,14 @@ static int __split_huge_page_map(struct page *page,
 				 unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	pmd_t *pmd, _pmd;
 	int ret = 0, i;
 	pgtable_t pgtable;
 	unsigned long haddr;
 
-	spin_lock(&mm->page_table_lock);
 	pmd = page_check_address_pmd(page, mm, address,
-				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
+			PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
@@ -1807,8 +1818,8 @@ static int __split_huge_page_map(struct page *page,
 		pmdp_invalidate(vma, address, pmd);
 		pmd_populate(mm, pmd, pgtable);
 		ret = 1;
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 
 	return ret;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index fd3ee7a54a13..b59d741dcf65 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -665,25 +665,23 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
+	spinlock_t *ptl;
 	int referenced = 0;
 
 	if (unlikely(PageTransHuge(page))) {
 		pmd_t *pmd;
 
-		spin_lock(&mm->page_table_lock);
 		/*
 		 * rmap might return false positives; we must filter
 		 * these out using page_check_address_pmd().
 		 */
 		pmd = page_check_address_pmd(page, mm, address,
-					     PAGE_CHECK_ADDRESS_PMD_FLAG);
-		if (!pmd) {
-			spin_unlock(&mm->page_table_lock);
+					     PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+		if (!pmd)
 			goto out;
-		}
 
 		if (vma->vm_flags & VM_LOCKED) {
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(ptl);
 			*mapcount = 0;	/* break early from loop */
 			*vm_flags |= VM_LOCKED;
 			goto out;
@@ -692,10 +690,9 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		/* go ahead even if the pmd is pmd_trans_splitting() */
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
-		spinlock_t *ptl;
 
 		/*
 		 * rmap might return false positives; we must filter
-- 
cgit 


From c389a250ab4cfa4a3775d9f2c45271618af6d5b2 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:30:59 -0800
Subject: mm, thp: do not access mm->pmd_huge_pte directly

Currently mm->pmd_huge_pte protected by page table lock.  It will not
work with split lock.  We have to have per-pmd pmd_huge_pte for proper
access serialization.

For now, let's just introduce wrapper to access mm->pmd_huge_pte.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/mm/pgtable.c | 12 ++++++------
 arch/sparc/mm/tlb.c    | 12 ++++++------
 include/linux/mm.h     |  1 +
 mm/pgtable-generic.c   | 12 ++++++------
 4 files changed, 19 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 0a2e5e086749..1ea18fcfa211 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1244,11 +1244,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(lh);
 	else
-		list_add(lh, (struct list_head *) mm->pmd_huge_pte);
-	mm->pmd_huge_pte = pgtable;
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 
 pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
@@ -1260,12 +1260,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	lh = (struct list_head *) pgtable;
 	if (list_empty(lh))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = (pgtable_t) lh->next;
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
 		list_del(lh);
 	}
 	ptep = (pte_t *) pgtable;
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 7a91f288c708..656cc46a81f5 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -196,11 +196,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(lh);
 	else
-		list_add(lh, (struct list_head *) mm->pmd_huge_pte);
-	mm->pmd_huge_pte = pgtable;
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 
 pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
@@ -211,12 +211,12 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	lh = (struct list_head *) pgtable;
 	if (list_empty(lh))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = (pgtable_t) lh->next;
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
 		list_del(lh);
 	}
 	pte_val(pgtable[0]) = 0;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4f4ca41fcf27..861cad53b744 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1383,6 +1383,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return &mm->page_table_lock;
 }
 
+#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
 static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 3929a40bd6c0..41fee3e5d570 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -154,11 +154,11 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	if (!mm->pmd_huge_pte)
+	if (!pmd_huge_pte(mm, pmdp))
 		INIT_LIST_HEAD(&pgtable->lru);
 	else
-		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
-	mm->pmd_huge_pte = pgtable;
+		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
@@ -173,11 +173,11 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	assert_spin_locked(&mm->page_table_lock);
 
 	/* FIFO */
-	pgtable = mm->pmd_huge_pte;
+	pgtable = pmd_huge_pte(mm, pmdp);
 	if (list_empty(&pgtable->lru))
-		mm->pmd_huge_pte = NULL;
+		pmd_huge_pte(mm, pmdp) = NULL;
 	else {
-		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
+		pmd_huge_pte(mm, pmdp) = list_entry(pgtable->lru.next,
 					      struct page, lru);
 		list_del(&pgtable->lru);
 	}
-- 
cgit 


From cb900f41215447433cbc456d1c4294e858a84d7c Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:31:02 -0800
Subject: mm, hugetlb: convert hugetlbfs to use split pmd lock

Hugetlb supports multiple page sizes. We use split lock only for PMD
level, but not for PUD.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/meminfo.c       |   2 +-
 include/linux/hugetlb.h |  26 ++++++++++++
 include/linux/swapops.h |   7 +--
 mm/hugetlb.c            | 110 +++++++++++++++++++++++++++++-------------------
 mm/mempolicy.c          |   5 ++-
 mm/migrate.c            |   7 +--
 mm/rmap.c               |   2 +-
 7 files changed, 105 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index c805d5b69ba1..a77d2b299199 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -1,8 +1,8 @@
 #include <linux/fs.h>
-#include <linux/hugetlb.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/hugetlb.h>
 #include <linux/mman.h>
 #include <linux/mmzone.h>
 #include <linux/proc_fs.h>
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 0393270466c3..acd2010328f3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -392,6 +392,15 @@ static inline int hugepage_migration_support(struct hstate *h)
 	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
 }
 
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	if (huge_page_size(h) == PMD_SIZE)
+		return pmd_lockptr(mm, (pmd_t *) pte);
+	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
+	return &mm->page_table_lock;
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -401,6 +410,7 @@ struct hstate {};
 #define hstate_sizelog(s) NULL
 #define hstate_vma(v) NULL
 #define hstate_inode(i) NULL
+#define page_hstate(page) NULL
 #define huge_page_size(h) PAGE_SIZE
 #define huge_page_mask(h) PAGE_MASK
 #define vma_kernel_pagesize(v) PAGE_SIZE
@@ -421,6 +431,22 @@ static inline pgoff_t basepage_index(struct page *page)
 #define dissolve_free_huge_pages(s, e)	do {} while (0)
 #define pmd_huge_support()	0
 #define hugepage_migration_support(h)	0
+
+static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+					   struct mm_struct *mm, pte_t *pte)
+{
+	return &mm->page_table_lock;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
+static inline spinlock_t *huge_pte_lock(struct hstate *h,
+					struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl;
+
+	ptl = huge_pte_lockptr(h, mm, pte);
+	spin_lock(ptl);
+	return ptl;
+}
+
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 8d4fa82bfb91..c0f75261a728 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -139,7 +139,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
-extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
+extern void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte);
 #else
 
 #define make_migration_entry(page, write) swp_entry(0, 0)
@@ -151,8 +152,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
-static inline void migration_entry_wait_huge(struct mm_struct *mm,
-					pte_t *pte) { }
+static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte) { }
 static inline int is_write_migration_entry(swp_entry_t entry)
 {
 	return 0;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0b7656e804d1..7d57af21f49e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2376,6 +2376,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
@@ -2387,8 +2388,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		if (dst_pte == src_pte)
 			continue;
 
-		spin_lock(&dst->page_table_lock);
-		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
+		dst_ptl = huge_pte_lock(h, dst, dst_pte);
+		src_ptl = huge_pte_lockptr(h, src, src_pte);
+		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		if (!huge_pte_none(huge_ptep_get(src_pte))) {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
@@ -2398,8 +2400,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
-		spin_unlock(&src->page_table_lock);
-		spin_unlock(&dst->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 	}
 	return 0;
 
@@ -2442,6 +2444,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
+	spinlock_t *ptl;
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
@@ -2455,25 +2458,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 again:
-	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep))
-			continue;
+			goto unlock;
 
 		pte = huge_ptep_get(ptep);
 		if (huge_pte_none(pte))
-			continue;
+			goto unlock;
 
 		/*
 		 * HWPoisoned hugepage is already unmapped and dropped reference
 		 */
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
 			huge_pte_clear(mm, address, ptep);
-			continue;
+			goto unlock;
 		}
 
 		page = pte_page(pte);
@@ -2484,7 +2487,7 @@ again:
 		 */
 		if (ref_page) {
 			if (page != ref_page)
-				continue;
+				goto unlock;
 
 			/*
 			 * Mark the VMA as having unmapped its page so that
@@ -2501,13 +2504,18 @@ again:
 
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
-		if (force_flush)
+		if (force_flush) {
+			spin_unlock(ptl);
 			break;
+		}
 		/* Bail out after unmapping reference page if supplied */
-		if (ref_page)
+		if (ref_page) {
+			spin_unlock(ptl);
 			break;
+		}
+unlock:
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * mmu_gather ran out of room to batch pages, we break out of
 	 * the PTE lock to avoid doing the potential expensive TLB invalidate
@@ -2613,7 +2621,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
-			struct page *pagecache_page)
+			struct page *pagecache_page, spinlock_t *ptl)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
@@ -2647,8 +2655,8 @@ retry_avoidcopy:
 
 	page_cache_get(old_page);
 
-	/* Drop page_table_lock as buddy allocator may be called */
-	spin_unlock(&mm->page_table_lock);
+	/* Drop page table lock as buddy allocator may be called */
+	spin_unlock(ptl);
 	new_page = alloc_huge_page(vma, address, outside_reserve);
 
 	if (IS_ERR(new_page)) {
@@ -2666,13 +2674,13 @@ retry_avoidcopy:
 			BUG_ON(huge_pte_none(pte));
 			if (unmap_ref_private(mm, vma, old_page, address)) {
 				BUG_ON(huge_pte_none(pte));
-				spin_lock(&mm->page_table_lock);
+				spin_lock(ptl);
 				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 				if (likely(pte_same(huge_ptep_get(ptep), pte)))
 					goto retry_avoidcopy;
 				/*
-				 * race occurs while re-acquiring page_table_lock, and
-				 * our job is done.
+				 * race occurs while re-acquiring page table
+				 * lock, and our job is done.
 				 */
 				return 0;
 			}
@@ -2680,7 +2688,7 @@ retry_avoidcopy:
 		}
 
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
 		else
@@ -2695,7 +2703,7 @@ retry_avoidcopy:
 		page_cache_release(new_page);
 		page_cache_release(old_page);
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		return VM_FAULT_OOM;
 	}
 
@@ -2707,10 +2715,10 @@ retry_avoidcopy:
 	mmun_end = mmun_start + huge_page_size(h);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	/*
-	 * Retake the page_table_lock to check for racing updates
+	 * Retake the page table lock to check for racing updates
 	 * before the page tables are altered
 	 */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		ClearPagePrivate(new_page);
@@ -2724,13 +2732,13 @@ retry_avoidcopy:
 		/* Make the old page be freed below */
 		new_page = old_page;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 
 	/* Caller expects lock to be held */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	return 0;
 }
 
@@ -2778,6 +2786,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	spinlock_t *ptl;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -2864,7 +2873,8 @@ retry:
 			goto backout_unlocked;
 		}
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
@@ -2885,16 +2895,16 @@ retry:
 
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
+		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
 	}
 
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	unlock_page(page);
 out:
 	return ret;
 
 backout:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
 	put_page(page);
@@ -2906,6 +2916,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	pte_t *ptep;
 	pte_t entry;
+	spinlock_t *ptl;
 	int ret;
 	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
@@ -2918,7 +2929,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(mm, ptep);
+			migration_entry_wait_huge(vma, mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -2974,17 +2985,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (page != pagecache_page)
 		lock_page(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_page_table_lock;
+		goto out_ptl;
 
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
-							pagecache_page);
-			goto out_page_table_lock;
+					pagecache_page, ptl);
+			goto out_ptl;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
@@ -2993,8 +3005,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, ptep);
 
-out_page_table_lock:
-	spin_unlock(&mm->page_table_lock);
+out_ptl:
+	spin_unlock(ptl);
 
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
@@ -3020,9 +3032,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
-	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
+		spinlock_t *ptl = NULL;
 		int absent;
 		struct page *page;
 
@@ -3030,8 +3042,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
 		 * first, for the page indexing below to work.
+		 *
+		 * Note that page table lock is not held when pte is null.
 		 */
 		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+		if (pte)
+			ptl = huge_pte_lock(h, mm, pte);
 		absent = !pte || huge_pte_none(huge_ptep_get(pte));
 
 		/*
@@ -3043,6 +3059,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (absent && (flags & FOLL_DUMP) &&
 		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
+			if (pte)
+				spin_unlock(ptl);
 			remainder = 0;
 			break;
 		}
@@ -3062,10 +3080,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		      !huge_pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
-			spin_unlock(&mm->page_table_lock);
+			if (pte)
+				spin_unlock(ptl);
 			ret = hugetlb_fault(mm, vma, vaddr,
 				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
-			spin_lock(&mm->page_table_lock);
 			if (!(ret & VM_FAULT_ERROR))
 				continue;
 
@@ -3096,8 +3114,8 @@ same_page:
 			 */
 			goto same_page;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	*nr_pages = remainder;
 	*position = vaddr;
 
@@ -3118,13 +3136,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, address, end);
 
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
-	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
+		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
+			spin_unlock(ptl);
 			continue;
 		}
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
@@ -3134,8 +3154,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			set_huge_pte_at(mm, address, ptep, pte);
 			pages++;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
@@ -3298,6 +3318,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	unsigned long saddr;
 	pte_t *spte = NULL;
 	pte_t *pte;
+	spinlock_t *ptl;
 
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
@@ -3320,13 +3341,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!spte)
 		goto out;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
+	spin_lock(ptl);
 	if (pud_none(*pud))
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
 	else
 		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
@@ -3340,7 +3362,7 @@ out:
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * called with vma->vm_mm->page_table_lock held.
+ * called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4cc19f6ab6c6..c4403cdf3433 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,8 +525,9 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 #ifdef CONFIG_HUGETLB_PAGE
 	int nid;
 	struct page *page;
+	spinlock_t *ptl;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
+	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
 	page = pte_page(huge_ptep_get((pte_t *)pmd));
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
@@ -536,7 +537,7 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	    (flags & MPOL_MF_MOVE && page_mapcount(page) == 1))
 		isolate_huge_page(page, private);
 unlock:
-	spin_unlock(&vma->vm_mm->page_table_lock);
+	spin_unlock(ptl);
 #else
 	BUG();
 #endif
diff --git a/mm/migrate.c b/mm/migrate.c
index dfc8300ecbb2..01f45cefa4cd 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -130,7 +130,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		ptep = huge_pte_offset(mm, addr);
 		if (!ptep)
 			goto out;
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep);
 	} else {
 		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
@@ -249,9 +249,10 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	__migration_entry_wait(mm, ptep, ptl);
 }
 
-void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+void migration_entry_wait_huge(struct vm_area_struct *vma,
+		struct mm_struct *mm, pte_t *pte)
 {
-	spinlock_t *ptl = &(mm)->page_table_lock;
+	spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
 	__migration_entry_wait(mm, pte, ptl);
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
index b59d741dcf65..55c8b8dc9ffb 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -601,7 +601,7 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 
 	if (unlikely(PageHuge(page))) {
 		pte = huge_pte_offset(mm, address);
-		ptl = &mm->page_table_lock;
+		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
 		goto check;
 	}
 
-- 
cgit 


From e009bb30c8df8a52a9622b616b67436b6a03a0cd Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:31:07 -0800
Subject: mm: implement split page table lock for PMD level

The basic idea is the same as with PTE level: the lock is embedded into
struct page of table's page.

We can't use mm->pmd_huge_pte to store pgtables for THP, since we don't
take mm->page_table_lock anymore.  Let's reuse page->lru of table's page
for that.

pgtable_pmd_page_ctor() returns true, if initialization is successful
and false otherwise.  Current implementation never fails, but assumption
that constructor can fail will help to port it to -rt where spinlock_t
is rather huge and cannot be embedded into struct page -- dynamic
allocation is required.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Robin Holt <robinmholt@gmail.com>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h       | 32 ++++++++++++++++++++++++++++++++
 include/linux/mm_types.h |  7 ++++++-
 kernel/fork.c            |  4 ++--
 mm/Kconfig               |  3 +++
 4 files changed, 43 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 861cad53b744..255750d9b1be 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1378,13 +1378,45 @@ static inline void pgtable_page_dtor(struct page *page)
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
 		NULL: pte_offset_kernel(pmd, address))
 
+#if USE_SPLIT_PMD_PTLOCKS
+
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return &virt_to_page(pmd)->ptl;
+}
+
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+	spin_lock_init(&page->ptl);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	page->pmd_huge_pte = NULL;
+#endif
+	return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(page->pmd_huge_pte);
+#endif
+}
+
+#define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte)
+
+#else
+
 static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
 
+static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
+static inline void pgtable_pmd_page_dtor(struct page *page) {}
+
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
+#endif
+
 static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 {
 	spinlock_t *ptl = pmd_lockptr(mm, pmd);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 566df579c51f..934261099975 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -24,6 +24,8 @@
 struct address_space;
 
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
+#define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
+		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -63,6 +65,9 @@ struct page {
 						 * this page is only used to
 						 * free other pages.
 						 */
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+		pgtable_t pmd_huge_pte; /* protected by page->ptl */
+#endif
 		};
 
 		union {
@@ -406,7 +411,7 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/kernel/fork.c b/kernel/fork.c
index e2520756e005..728d5be9548c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -560,7 +560,7 @@ static void check_mm(struct mm_struct *mm)
 					  "mm:%p idx:%d val:%ld\n", mm, i, x);
 	}
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	VM_BUG_ON(mm->pmd_huge_pte);
 #endif
 }
@@ -814,7 +814,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	memcpy(mm, oldmm, sizeof(*mm));
 	mm_init_cpumask(mm);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
 #endif
 	if (!mm_init(mm, tsk))
diff --git a/mm/Kconfig b/mm/Kconfig
index c28d247e524a..7aa02def4666 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -222,6 +222,9 @@ config SPLIT_PTLOCK_CPUS
 	default "999999" if !64BIT && GENERIC_LOCKBREAK
 	default "4"
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	boolean
+
 #
 # support for memory balloon compaction
 config BALLOON_COMPACTION
-- 
cgit 


From 390f44e2aa2ab83f08231d7d05f066dc3494490e Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:31:20 -0800
Subject: mm: allow pgtable_page_ctor() to fail

Change pgtable_page_ctor() return type from void to bool.  Returns true,
if initialization is successful and false otherwise.

Current implementation never fails, but it will change later.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 255750d9b1be..e855351c3361 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1338,10 +1338,11 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 #define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
 #endif /* USE_SPLIT_PTE_PTLOCKS */
 
-static inline void pgtable_page_ctor(struct page *page)
+static inline bool pgtable_page_ctor(struct page *page)
 {
 	pte_lock_init(page);
 	inc_zone_page_state(page, NR_PAGETABLE);
+	return true;
 }
 
 static inline void pgtable_page_dtor(struct page *page)
-- 
cgit 


From 49076ec2ccaf68610aa03d96bced9a6694b93ca1 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:31:51 -0800
Subject: mm: dynamically allocate page->ptl if it cannot be embedded to struct
 page

If split page table lock is in use, we embed the lock into struct page
of table's page.  We have to disable split lock, if spinlock_t is too
big be to be embedded, like when DEBUG_SPINLOCK or DEBUG_LOCK_ALLOC
enabled.

This patch add support for dynamic allocation of split page table lock
if we can't embed it to struct page.

page->ptl is unsigned long now and we use it as spinlock_t if
sizeof(spinlock_t) <= sizeof(long), otherwise it's pointer to spinlock_t.

The spinlock_t allocated in pgtable_page_ctor() for PTE table and in
pgtable_pmd_page_ctor() for PMD table.  All other helpers converted to
support dynamically allocated page->ptl.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/split_page_table_lock | 94 ++++++++++++++++++++++++++++++++++
 arch/x86/xen/mmu.c                     |  2 +-
 include/linux/mm.h                     | 81 +++++++++++++++++++++--------
 include/linux/mm_types.h               |  5 +-
 mm/Kconfig                             |  2 -
 mm/memory.c                            | 19 +++++++
 6 files changed, 179 insertions(+), 24 deletions(-)
 create mode 100644 Documentation/vm/split_page_table_lock

(limited to 'include')

diff --git a/Documentation/vm/split_page_table_lock b/Documentation/vm/split_page_table_lock
new file mode 100644
index 000000000000..7521d367f21d
--- /dev/null
+++ b/Documentation/vm/split_page_table_lock
@@ -0,0 +1,94 @@
+Split page table lock
+=====================
+
+Originally, mm->page_table_lock spinlock protected all page tables of the
+mm_struct. But this approach leads to poor page fault scalability of
+multi-threaded applications due high contention on the lock. To improve
+scalability, split page table lock was introduced.
+
+With split page table lock we have separate per-table lock to serialize
+access to the table. At the moment we use split lock for PTE and PMD
+tables. Access to higher level tables protected by mm->page_table_lock.
+
+There are helpers to lock/unlock a table and other accessor functions:
+ - pte_offset_map_lock()
+	maps pte and takes PTE table lock, returns pointer to the taken
+	lock;
+ - pte_unmap_unlock()
+	unlocks and unmaps PTE table;
+ - pte_alloc_map_lock()
+	allocates PTE table if needed and take the lock, returns pointer
+	to taken lock or NULL if allocation failed;
+ - pte_lockptr()
+	returns pointer to PTE table lock;
+ - pmd_lock()
+	takes PMD table lock, returns pointer to taken lock;
+ - pmd_lockptr()
+	returns pointer to PMD table lock;
+
+Split page table lock for PTE tables is enabled compile-time if
+CONFIG_SPLIT_PTLOCK_CPUS (usually 4) is less or equal to NR_CPUS.
+If split lock is disabled, all tables guaded by mm->page_table_lock.
+
+Split page table lock for PMD tables is enabled, if it's enabled for PTE
+tables and the architecture supports it (see below).
+
+Hugetlb and split page table lock
+---------------------------------
+
+Hugetlb can support several page sizes. We use split lock only for PMD
+level, but not for PUD.
+
+Hugetlb-specific helpers:
+ - huge_pte_lock()
+	takes pmd split lock for PMD_SIZE page, mm->page_table_lock
+	otherwise;
+ - huge_pte_lockptr()
+	returns pointer to table lock;
+
+Support of split page table lock by an architecture
+---------------------------------------------------
+
+There's no need in special enabling of PTE split page table lock:
+everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
+which must be called on PTE table allocation / freeing.
+
+Make sure the architecture doesn't use slab allocator for page table
+allocation: slab uses page->slab_cache and page->first_page for its pages.
+These fields share storage with page->ptl.
+
+PMD split lock only makes sense if you have more than two page table
+levels.
+
+PMD split lock enabling requires pgtable_pmd_page_ctor() call on PMD table
+allocation and pgtable_pmd_page_dtor() on freeing.
+
+Allocation usually happens in pmd_alloc_one(), freeing in pmd_free(), but
+make sure you cover all PMD table allocation / freeing paths: i.e X86_PAE
+preallocate few PMDs on pgd_alloc().
+
+With everything in place you can set CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK.
+
+NOTE: pgtable_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must
+be handled properly.
+
+page->ptl
+---------
+
+page->ptl is used to access split page table lock, where 'page' is struct
+page of page containing the table. It shares storage with page->private
+(and few other fields in union).
+
+To avoid increasing size of struct page and have best performance, we use a
+trick:
+ - if spinlock_t fits into long, we use page->ptr as spinlock, so we
+   can avoid indirect access and save a cache line.
+ - if size of spinlock_t is bigger then size of long, we use page->ptl as
+   pointer to spinlock_t and allocate it dynamically. This allows to use
+   split lock with enabled DEBUG_SPINLOCK or DEBUG_LOCK_ALLOC, but costs
+   one more cache line for indirect access;
+
+The spinlock_t allocated in pgtable_page_ctor() for PTE table and in
+pgtable_pmd_page_ctor() for PMD table.
+
+Please, never access page->ptl directly -- use appropriate helper.
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 455c873ce009..49c962fe7e62 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -797,7 +797,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
 	spinlock_t *ptl = NULL;
 
 #if USE_SPLIT_PTE_PTLOCKS
-	ptl = __pte_lockptr(page);
+	ptl = ptlock_ptr(page);
 	spin_lock_nest_lock(ptl, &mm->page_table_lock);
 #endif
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e855351c3361..d0339741b6ce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1317,32 +1317,73 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
 #if USE_SPLIT_PTE_PTLOCKS
-/*
- * We tuck a spinlock to guard each pagetable page into its struct page,
- * at page->private, with BUILD_BUG_ON to make sure that this will not
- * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
- * When freeing, reset page->mapping so free_pages_check won't complain.
- */
-#define __pte_lockptr(page)	&((page)->ptl)
-#define pte_lock_init(_page)	do {					\
-	spin_lock_init(__pte_lockptr(_page));				\
-} while (0)
-#define pte_lock_deinit(page)	((page)->mapping = NULL)
-#define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
+bool __ptlock_alloc(struct page *page);
+void __ptlock_free(struct page *page);
+static inline bool ptlock_alloc(struct page *page)
+{
+	if (sizeof(spinlock_t) > sizeof(page->ptl))
+		return __ptlock_alloc(page);
+	return true;
+}
+static inline void ptlock_free(struct page *page)
+{
+	if (sizeof(spinlock_t) > sizeof(page->ptl))
+		__ptlock_free(page);
+}
+
+static inline spinlock_t *ptlock_ptr(struct page *page)
+{
+	if (sizeof(spinlock_t) > sizeof(page->ptl))
+		return (spinlock_t *) page->ptl;
+	else
+		return (spinlock_t *) &page->ptl;
+}
+
+static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return ptlock_ptr(pmd_page(*pmd));
+}
+
+static inline bool ptlock_init(struct page *page)
+{
+	/*
+	 * prep_new_page() initialize page->private (and therefore page->ptl)
+	 * with 0. Make sure nobody took it in use in between.
+	 *
+	 * It can happen if arch try to use slab for page table allocation:
+	 * slab code uses page->slab_cache and page->first_page (for tail
+	 * pages), which share storage with page->ptl.
+	 */
+	VM_BUG_ON(page->ptl);
+	if (!ptlock_alloc(page))
+		return false;
+	spin_lock_init(ptlock_ptr(page));
+	return true;
+}
+
+/* Reset page->mapping so free_pages_check won't complain. */
+static inline void pte_lock_deinit(struct page *page)
+{
+	page->mapping = NULL;
+	ptlock_free(page);
+}
+
 #else	/* !USE_SPLIT_PTE_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
-#define pte_lock_init(page)	do {} while (0)
-#define pte_lock_deinit(page)	do {} while (0)
-#define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
+static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+{
+	return &mm->page_table_lock;
+}
+static inline bool ptlock_init(struct page *page) { return true; }
+static inline void pte_lock_deinit(struct page *page) {}
 #endif /* USE_SPLIT_PTE_PTLOCKS */
 
 static inline bool pgtable_page_ctor(struct page *page)
 {
-	pte_lock_init(page);
 	inc_zone_page_state(page, NR_PAGETABLE);
-	return true;
+	return ptlock_init(page);
 }
 
 static inline void pgtable_page_dtor(struct page *page)
@@ -1383,16 +1424,15 @@ static inline void pgtable_page_dtor(struct page *page)
 
 static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
-	return &virt_to_page(pmd)->ptl;
+	return ptlock_ptr(virt_to_page(pmd));
 }
 
 static inline bool pgtable_pmd_page_ctor(struct page *page)
 {
-	spin_lock_init(&page->ptl);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	page->pmd_huge_pte = NULL;
 #endif
-	return true;
+	return ptlock_init(page);
 }
 
 static inline void pgtable_pmd_page_dtor(struct page *page)
@@ -1400,6 +1440,7 @@ static inline void pgtable_pmd_page_dtor(struct page *page)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	VM_BUG_ON(page->pmd_huge_pte);
 #endif
+	ptlock_free(page);
 }
 
 #define pmd_huge_pte(mm, pmd) (virt_to_page(pmd)->pmd_huge_pte)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 934261099975..423da79877e6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -147,7 +147,10 @@ struct page {
 						 * system if PG_buddy is set.
 						 */
 #if USE_SPLIT_PTE_PTLOCKS
-		spinlock_t ptl;
+		unsigned long ptl; /* It's spinlock_t if it fits to long,
+				    * otherwise it's pointer to dynamicaly
+				    * allocated spinlock_t.
+				    */
 #endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
 		struct page *first_page;	/* Compound tail pages */
diff --git a/mm/Kconfig b/mm/Kconfig
index 7aa02def4666..de31af256207 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -218,8 +218,6 @@ config SPLIT_PTLOCK_CPUS
 	int
 	default "999999" if ARM && !CPU_CACHE_VIPT
 	default "999999" if PARISC && !PA20
-	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
-	default "999999" if !64BIT && GENERIC_LOCKBREAK
 	default "4"
 
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
diff --git a/mm/memory.c b/mm/memory.c
index d05c6b10e926..24ffae2a530e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4270,3 +4270,22 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
+#if USE_SPLIT_PTE_PTLOCKS
+bool __ptlock_alloc(struct page *page)
+{
+	spinlock_t *ptl;
+
+	ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!ptl)
+		return false;
+	page->ptl = (unsigned long)ptl;
+	return true;
+}
+
+void __ptlock_free(struct page *page)
+{
+	if (sizeof(spinlock_t) > sizeof(page->ptl))
+		kfree((spinlock_t *)page->ptl);
+}
+#endif
-- 
cgit 


From 539edb5846c740d78a8b6c2e43a99ca4323df68f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 14 Nov 2013 14:31:52 -0800
Subject: mm: properly separate the bloated ptl from the regular case

Use kernel/bounds.c to convert build-time spinlock_t size check into a
preprocessor symbol and apply that to properly separate the page::ptl
situation.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h       | 24 +++++++++++++-----------
 include/linux/mm_types.h |  9 +++++----
 kernel/bounds.c          |  2 ++
 mm/memory.c              | 11 +++++------
 4 files changed, 25 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d0339741b6ce..1cedd000cf29 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1317,27 +1317,29 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
 #if USE_SPLIT_PTE_PTLOCKS
-bool __ptlock_alloc(struct page *page);
-void __ptlock_free(struct page *page);
+#if BLOATED_SPINLOCKS
+extern bool ptlock_alloc(struct page *page);
+extern void ptlock_free(struct page *page);
+
+static inline spinlock_t *ptlock_ptr(struct page *page)
+{
+	return page->ptl;
+}
+#else /* BLOATED_SPINLOCKS */
 static inline bool ptlock_alloc(struct page *page)
 {
-	if (sizeof(spinlock_t) > sizeof(page->ptl))
-		return __ptlock_alloc(page);
 	return true;
 }
+
 static inline void ptlock_free(struct page *page)
 {
-	if (sizeof(spinlock_t) > sizeof(page->ptl))
-		__ptlock_free(page);
 }
 
 static inline spinlock_t *ptlock_ptr(struct page *page)
 {
-	if (sizeof(spinlock_t) > sizeof(page->ptl))
-		return (spinlock_t *) page->ptl;
-	else
-		return (spinlock_t *) &page->ptl;
+	return &page->ptl;
 }
+#endif /* BLOATED_SPINLOCKS */
 
 static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
@@ -1354,7 +1356,7 @@ static inline bool ptlock_init(struct page *page)
 	 * slab code uses page->slab_cache and page->first_page (for tail
 	 * pages), which share storage with page->ptl.
 	 */
-	VM_BUG_ON(page->ptl);
+	VM_BUG_ON(*(unsigned long *)&page->ptl);
 	if (!ptlock_alloc(page))
 		return false;
 	spin_lock_init(ptlock_ptr(page));
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 423da79877e6..10f5a7272b80 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -147,10 +147,11 @@ struct page {
 						 * system if PG_buddy is set.
 						 */
 #if USE_SPLIT_PTE_PTLOCKS
-		unsigned long ptl; /* It's spinlock_t if it fits to long,
-				    * otherwise it's pointer to dynamicaly
-				    * allocated spinlock_t.
-				    */
+#if BLOATED_SPINLOCKS
+		spinlock_t *ptl;
+#else
+		spinlock_t ptl;
+#endif
 #endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
 		struct page *first_page;	/* Compound tail pages */
diff --git a/kernel/bounds.c b/kernel/bounds.c
index e8ca97b5c386..578782ef6ae1 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -11,6 +11,7 @@
 #include <linux/kbuild.h>
 #include <linux/page_cgroup.h>
 #include <linux/log2.h>
+#include <linux/spinlock.h>
 
 void foo(void)
 {
@@ -21,5 +22,6 @@ void foo(void)
 #ifdef CONFIG_SMP
 	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
 #endif
+	DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int));
 	/* End of constants */
 }
diff --git a/mm/memory.c b/mm/memory.c
index 24ffae2a530e..5d9025f3b3e1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4271,21 +4271,20 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
-#if USE_SPLIT_PTE_PTLOCKS
-bool __ptlock_alloc(struct page *page)
+#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+bool ptlock_alloc(struct page *page)
 {
 	spinlock_t *ptl;
 
 	ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
 	if (!ptl)
 		return false;
-	page->ptl = (unsigned long)ptl;
+	page->ptl = ptl;
 	return true;
 }
 
-void __ptlock_free(struct page *page)
+void ptlock_free(struct page *page)
 {
-	if (sizeof(spinlock_t) > sizeof(page->ptl))
-		kfree((spinlock_t *)page->ptl);
+	kfree(page->ptl);
 }
 #endif
-- 
cgit 


From ea1e7ed33708c7a760419ff9ded0a6cb90586a50 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 14 Nov 2013 14:31:53 -0800
Subject: mm: create a separate slab for page->ptl allocation

If DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC are enabled spinlock_t on x86_64
is 72 bytes.  For page->ptl they will be allocated from kmalloc-96 slab,
so we loose 24 on each.  An average system can easily allocate few tens
thousands of page->ptl and overhead is significant.

Let's create a separate slab for page->ptl allocation to solve this.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 9 +++++++++
 init/main.c        | 2 +-
 mm/memory.c        | 7 +++++++
 3 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1cedd000cf29..0548eb201e05 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1318,6 +1318,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 
 #if USE_SPLIT_PTE_PTLOCKS
 #if BLOATED_SPINLOCKS
+void __init ptlock_cache_init(void);
 extern bool ptlock_alloc(struct page *page);
 extern void ptlock_free(struct page *page);
 
@@ -1326,6 +1327,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
 	return page->ptl;
 }
 #else /* BLOATED_SPINLOCKS */
+static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_alloc(struct page *page)
 {
 	return true;
@@ -1378,10 +1380,17 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
+static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_init(struct page *page) { return true; }
 static inline void pte_lock_deinit(struct page *page) {}
 #endif /* USE_SPLIT_PTE_PTLOCKS */
 
+static inline void pgtable_init(void)
+{
+	ptlock_cache_init();
+	pgtable_cache_init();
+}
+
 static inline bool pgtable_page_ctor(struct page *page)
 {
 	inc_zone_page_state(page, NR_PAGETABLE);
diff --git a/init/main.c b/init/main.c
index 6ad1a533a8c7..5f191133376f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -473,7 +473,7 @@ static void __init mm_init(void)
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
-	pgtable_cache_init();
+	pgtable_init();
 	vmalloc_init();
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 5d9025f3b3e1..0409e8f43fa0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4272,6 +4272,13 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
 #if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+static struct kmem_cache *page_ptl_cachep;
+void __init ptlock_cache_init(void)
+{
+	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
+			SLAB_PANIC, NULL);
+}
+
 bool ptlock_alloc(struct page *page)
 {
 	spinlock_t *ptl;
-- 
cgit 


From 57f4257eae33e036125973858934730250d464e3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 14 Nov 2013 14:31:54 -0800
Subject: lockref: use BLOATED_SPINLOCKS to avoid explicit config dependencies

Avoid the fragile Kconfig construct guestimating spinlock_t sizes; use a
friendly compile-time test to determine this.

[kirill.shutemov@linux.intel.com: drop CONFIG_CMPXCHG_LOCKREF]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/lockref.h | 7 ++++++-
 lib/Kconfig             | 7 -------
 lib/lockref.c           | 2 +-
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index 13dfd36a3294..c8929c3832db 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -15,10 +15,15 @@
  */
 
 #include <linux/spinlock.h>
+#include <generated/bounds.h>
+
+#define USE_CMPXCHG_LOCKREF \
+	(IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \
+	 IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS)
 
 struct lockref {
 	union {
-#ifdef CONFIG_CMPXCHG_LOCKREF
+#if USE_CMPXCHG_LOCKREF
 		aligned_u64 lock_count;
 #endif
 		struct {
diff --git a/lib/Kconfig b/lib/Kconfig
index 75485e163ca3..06dc74200a51 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -51,13 +51,6 @@ config PERCPU_RWSEM
 config ARCH_USE_CMPXCHG_LOCKREF
 	bool
 
-config CMPXCHG_LOCKREF
-	def_bool y if ARCH_USE_CMPXCHG_LOCKREF
-	depends on SMP
-	depends on !GENERIC_LOCKBREAK
-	depends on !DEBUG_SPINLOCK
-	depends on !DEBUG_LOCK_ALLOC
-
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help
diff --git a/lib/lockref.c b/lib/lockref.c
index af6e95d0bed6..d2b123f8456b 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -1,7 +1,7 @@
 #include <linux/export.h>
 #include <linux/lockref.h>
 
-#ifdef CONFIG_CMPXCHG_LOCKREF
+#if USE_CMPXCHG_LOCKREF
 
 /*
  * Allow weakly-ordered memory architectures to provide barrier-less
-- 
cgit 


From 839cc2a94cc3665bafe32203c2f095f4dd470a80 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Thu, 14 Nov 2013 14:31:56 -0800
Subject: seq_file: introduce seq_setwidth() and seq_pad()

There are several users who want to know bytes written by seq_*() for
alignment purpose.  Currently they are using %n format for knowing it
because seq_*() returns 0 on success.

This patch introduces seq_setwidth() and seq_pad() for allowing them to
align without using %n format.

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Joe Perches <joe@perches.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/seq_file.c            | 15 +++++++++++++++
 include/linux/seq_file.h | 15 +++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/fs/seq_file.c b/fs/seq_file.c
index a290157265ef..1cd2388ca5bd 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -766,6 +766,21 @@ int seq_write(struct seq_file *seq, const void *data, size_t len)
 }
 EXPORT_SYMBOL(seq_write);
 
+/**
+ * seq_pad - write padding spaces to buffer
+ * @m: seq_file identifying the buffer to which data should be written
+ * @c: the byte to append after padding if non-zero
+ */
+void seq_pad(struct seq_file *m, char c)
+{
+	int size = m->pad_until - m->count;
+	if (size > 0)
+		seq_printf(m, "%*s", size, "");
+	if (c)
+		seq_putc(m, c);
+}
+EXPORT_SYMBOL(seq_pad);
+
 struct list_head *seq_list_start(struct list_head *head, loff_t pos)
 {
 	struct list_head *lh;
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 4e32edc8f506..52e0097f61f0 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -20,6 +20,7 @@ struct seq_file {
 	size_t size;
 	size_t from;
 	size_t count;
+	size_t pad_until;
 	loff_t index;
 	loff_t read_pos;
 	u64 version;
@@ -79,6 +80,20 @@ static inline void seq_commit(struct seq_file *m, int num)
 	}
 }
 
+/**
+ * seq_setwidth - set padding width
+ * @m: the seq_file handle
+ * @size: the max number of bytes to pad.
+ *
+ * Call seq_setwidth() for setting max width, then call seq_printf() etc. and
+ * finally call seq_pad() to pad the remaining bytes.
+ */
+static inline void seq_setwidth(struct seq_file *m, size_t size)
+{
+	m->pad_until = m->count + size;
+}
+void seq_pad(struct seq_file *m, char c);
+
 char *mangle_path(char *s, const char *p, const char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
-- 
cgit 


From c32f74ab2872994bc8336ed367313da3139350ca Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Thu, 14 Nov 2013 14:32:01 -0800
Subject: sched: replace INIT_COMPLETION with reinit_completion

For the casual device driver writer, it is hard to remember when to use
init_completion (to init a completion structure) or INIT_COMPLETION (to
*reinit* a completion structure).  Furthermore, while all other
completion functions exepct a pointer as a parameter, INIT_COMPLETION
does not.  To make it easier to remember which function to use and to
make code more readable, introduce a new inline function with the proper
name and consistent argument type.  Update the kernel-doc for
init_completion while we are here.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org> (personally at LCE13)
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/completion.h | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/completion.h b/include/linux/completion.h
index 22c33e35bcb2..124e4b4334c1 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -19,8 +19,8 @@
  *
  * See also:  complete(), wait_for_completion() (and friends _timeout,
  * _interruptible, _interruptible_timeout, and _killable), init_completion(),
- * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and
- * INIT_COMPLETION().
+ * reinit_completion(), and macros DECLARE_COMPLETION(),
+ * DECLARE_COMPLETION_ONSTACK().
  */
 struct completion {
 	unsigned int done;
@@ -65,7 +65,7 @@ struct completion {
 
 /**
  * init_completion - Initialize a dynamically allocated completion
- * @x:  completion structure that is to be initialized
+ * @x:  pointer to completion structure that is to be initialized
  *
  * This inline function will initialize a dynamically created completion
  * structure.
@@ -76,6 +76,18 @@ static inline void init_completion(struct completion *x)
 	init_waitqueue_head(&x->wait);
 }
 
+/**
+ * reinit_completion - reinitialize a completion structure
+ * @x:  pointer to completion structure that is to be reinitialized
+ *
+ * This inline function should be used to reinitialize a completion structure so it can
+ * be reused. This is especially important after complete_all() is used.
+ */
+static inline void reinit_completion(struct completion *x)
+{
+	x->done = 0;
+}
+
 extern void wait_for_completion(struct completion *);
 extern void wait_for_completion_io(struct completion *);
 extern int wait_for_completion_interruptible(struct completion *x);
-- 
cgit 


From 62026aedaacedbe1ffe94a3599ad4acd8ecdf587 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Thu, 14 Nov 2013 14:32:03 -0800
Subject: sched: remove INIT_COMPLETION

All users are converted over to reinit_completion(). Remove the old
macro now.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/completion.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/completion.h b/include/linux/completion.h
index 124e4b4334c1..5d5aaae3af43 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -106,14 +106,4 @@ extern bool completion_done(struct completion *x);
 extern void complete(struct completion *);
 extern void complete_all(struct completion *);
 
-/**
- * INIT_COMPLETION - reinitialize a completion structure
- * @x:  completion structure to be reinitialized
- *
- * This macro should be used to reinitialize a completion structure so it can
- * be reused. This is especially important after complete_all() is used.
- */
-#define INIT_COMPLETION(x)	((x).done = 0)
-
-
 #endif
-- 
cgit 


From fc21c0cff2f425891b28ff6fb6b03b325c977428 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Thu, 14 Nov 2013 14:32:06 -0800
Subject: revert "softirq: Add support for triggering softirq work on softirqs"

This commit was incomplete in that code to remove items from the per-cpu
lists was missing and never acquired a user in the 5 years it has been in
the tree.  We're going to implement what it seems to try to archive in a
simpler way, and this code is in the way of doing so.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/interrupt.h |  22 --------
 kernel/softirq.c          | 131 ----------------------------------------------
 2 files changed, 153 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c9e831dc80bc..db43b58a3355 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -11,8 +11,6 @@
 #include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
@@ -392,15 +390,6 @@ extern void __raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 
-/* This is the worklist that queues up per-cpu softirq work.
- *
- * send_remote_sendirq() adds work to these lists, and
- * the softirq handler itself dequeues from them.  The queues
- * are protected by disabling local cpu interrupts and they must
- * only be accessed by the local cpu that they are for.
- */
-DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
-
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
 static inline struct task_struct *this_cpu_ksoftirqd(void)
@@ -408,17 +397,6 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
 	return this_cpu_read(ksoftirqd);
 }
 
-/* Try to send a softirq to a remote cpu.  If this cannot be done, the
- * work will be queued to the local cpu.
- */
-extern void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq);
-
-/* Like send_remote_softirq(), but the caller must disable local cpu interrupts
- * and compute the current cpu, passed in as 'this_cpu'.
- */
-extern void __send_remote_softirq(struct call_single_data *cp, int cpu,
-				  int this_cpu, int softirq);
-
 /* Tasklets --- multithreaded analogue of BHs.
 
    Main feature differing them of generic softirqs: tasklet
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b24988353458..11025ccc06dd 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -6,8 +6,6 @@
  *	Distribute under GPLv2.
  *
  *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
- *
- *	Remote softirq infrastructure is by Jens Axboe.
  */
 
 #include <linux/export.h>
@@ -627,146 +625,17 @@ void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
 }
 EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
 
-/*
- * Remote softirq bits
- */
-
-DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
-EXPORT_PER_CPU_SYMBOL(softirq_work_list);
-
-static void __local_trigger(struct call_single_data *cp, int softirq)
-{
-	struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
-
-	list_add_tail(&cp->list, head);
-
-	/* Trigger the softirq only if the list was previously empty.  */
-	if (head->next == &cp->list)
-		raise_softirq_irqoff(softirq);
-}
-
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
-static void remote_softirq_receive(void *data)
-{
-	struct call_single_data *cp = data;
-	unsigned long flags;
-	int softirq;
-
-	softirq = *(int *)cp->info;
-	local_irq_save(flags);
-	__local_trigger(cp, softirq);
-	local_irq_restore(flags);
-}
-
-static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
-	if (cpu_online(cpu)) {
-		cp->func = remote_softirq_receive;
-		cp->info = &softirq;
-		cp->flags = 0;
-
-		__smp_call_function_single(cpu, cp, 0);
-		return 0;
-	}
-	return 1;
-}
-#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
-static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
-	return 1;
-}
-#endif
-
-/**
- * __send_remote_softirq - try to schedule softirq work on a remote cpu
- * @cp: private SMP call function data area
- * @cpu: the remote cpu
- * @this_cpu: the currently executing cpu
- * @softirq: the softirq for the work
- *
- * Attempt to schedule softirq work on a remote cpu.  If this cannot be
- * done, the work is instead queued up on the local cpu.
- *
- * Interrupts must be disabled.
- */
-void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
-{
-	if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
-		__local_trigger(cp, softirq);
-}
-EXPORT_SYMBOL(__send_remote_softirq);
-
-/**
- * send_remote_softirq - try to schedule softirq work on a remote cpu
- * @cp: private SMP call function data area
- * @cpu: the remote cpu
- * @softirq: the softirq for the work
- *
- * Like __send_remote_softirq except that disabling interrupts and
- * computing the current cpu is done for the caller.
- */
-void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
-{
-	unsigned long flags;
-	int this_cpu;
-
-	local_irq_save(flags);
-	this_cpu = smp_processor_id();
-	__send_remote_softirq(cp, cpu, this_cpu, softirq);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(send_remote_softirq);
-
-static int remote_softirq_cpu_notify(struct notifier_block *self,
-					       unsigned long action, void *hcpu)
-{
-	/*
-	 * If a CPU goes away, splice its entries to the current CPU
-	 * and trigger a run of the softirq
-	 */
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		int cpu = (unsigned long) hcpu;
-		int i;
-
-		local_irq_disable();
-		for (i = 0; i < NR_SOFTIRQS; i++) {
-			struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
-			struct list_head *local_head;
-
-			if (list_empty(head))
-				continue;
-
-			local_head = &__get_cpu_var(softirq_work_list[i]);
-			list_splice_init(head, local_head);
-			raise_softirq_irqoff(i);
-		}
-		local_irq_enable();
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block remote_softirq_cpu_notifier = {
-	.notifier_call	= remote_softirq_cpu_notify,
-};
-
 void __init softirq_init(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		int i;
-
 		per_cpu(tasklet_vec, cpu).tail =
 			&per_cpu(tasklet_vec, cpu).head;
 		per_cpu(tasklet_hi_vec, cpu).tail =
 			&per_cpu(tasklet_hi_vec, cpu).head;
-		for (i = 0; i < NR_SOFTIRQS; i++)
-			INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
 	}
 
-	register_hotcpu_notifier(&remote_softirq_cpu_notifier);
-
 	open_softirq(TASKLET_SOFTIRQ, tasklet_action);
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
-- 
cgit 


From 0a06ff068f1255bcd7965ab07bc0f4adc3eb639a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Thu, 14 Nov 2013 14:32:07 -0800
Subject: kernel: remove CONFIG_USE_GENERIC_SMP_HELPERS

We've switched over every architecture that supports SMP to it, so
remove the new useless config variable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/Kconfig          | 3 ---
 arch/alpha/Kconfig    | 1 -
 arch/arc/Kconfig      | 1 -
 arch/arm/Kconfig      | 1 -
 arch/arm64/Kconfig    | 1 -
 arch/blackfin/Kconfig | 1 -
 arch/hexagon/Kconfig  | 1 -
 arch/ia64/Kconfig     | 1 -
 arch/m32r/Kconfig     | 1 -
 arch/metag/Kconfig    | 1 -
 arch/mips/Kconfig     | 1 -
 arch/mn10300/Kconfig  | 1 -
 arch/parisc/Kconfig   | 1 -
 arch/powerpc/Kconfig  | 1 -
 arch/s390/Kconfig     | 1 -
 arch/sh/Kconfig       | 1 -
 arch/sparc/Kconfig    | 1 -
 arch/tile/Kconfig     | 1 -
 arch/x86/Kconfig      | 1 -
 block/blk-mq.c        | 4 ++--
 block/blk-softirq.c   | 4 ++--
 block/blk-sysfs.c     | 2 +-
 include/linux/smp.h   | 4 ----
 kernel/Kconfig.hz     | 2 +-
 kernel/smp.c          | 2 --
 25 files changed, 6 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index ded747c7b74c..f1cf895c040f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -207,9 +207,6 @@ config HAVE_DMA_ATTRS
 config HAVE_DMA_CONTIGUOUS
 	bool
 
-config USE_GENERIC_SMP_HELPERS
-	bool
-
 config GENERIC_SMP_IDLE_THREAD
        bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 35a300d4a9fb..8d2a4833acda 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -522,7 +522,6 @@ config ARCH_MAY_HAVE_PC_FDC
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on ALPHA_SABLE || ALPHA_LYNX || ALPHA_RAWHIDE || ALPHA_DP264 || ALPHA_WILDFIRE || ALPHA_TITAN || ALPHA_GENERIC || ALPHA_SHARK || ALPHA_MARVEL
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5ede5460c806..2ee0c9bfd032 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -125,7 +125,6 @@ config ARC_PLAT_NEEDS_CPU_TO_DMA
 config SMP
 	bool "Symmetric Multi-Processing (Incomplete)"
 	default n
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 603d661b445d..00c1ff45a158 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1432,7 +1432,6 @@ config SMP
 	depends on GENERIC_CLOCKEVENTS
 	depends on HAVE_SMP
 	depends on MMU || ARM_MPU
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index bb0bf1bfc05d..9714fe0403b7 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -143,7 +143,6 @@ config CPU_BIG_ENDIAN
 
 config SMP
 	bool "Symmetric Multi-Processing"
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU.  If
 	  you say N here, the kernel will run on single and
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index e887b57c3176..9ceccef9c649 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -34,7 +34,6 @@ config BLACKFIN
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 99041b07e610..09df2608f40a 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -4,7 +4,6 @@ comment "Linux Kernel Configuration for Hexagon"
 config HEXAGON
 	def_bool y
 	select HAVE_OPROFILE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	# Other pending projects/to-do items.
 	# select HAVE_REGS_AND_STACK_ACCESS_API
 	# select HAVE_HW_BREAKPOINT if PERF_EVENTS
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 7740ab10a171..dfe85e92ca2e 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -343,7 +343,6 @@ config FORCE_MAX_ZONEORDER
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N.  If you have a system with more
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 75661fbf4529..09ef94a8a7c3 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -275,7 +275,6 @@ source "kernel/Kconfig.preempt"
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index 36368eb07e13..e56abd2c1b4f 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -111,7 +111,6 @@ config METAG_META21
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on METAG_META21 && METAG_META21_MMU
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one thread running
 	  Linux. If you have a system with only one thread running Linux,
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 17cc7ff8458c..867d7db11581 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2125,7 +2125,6 @@ source "mm/Kconfig"
 config SMP
 	bool "Multi-Processing support"
 	depends on SYS_SUPPORTS_SMP
-	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 6aaa1607001a..8bde9237d13b 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -181,7 +181,6 @@ endmenu
 config SMP
 	bool "Symmetric multi-processing support"
 	default y
-	select USE_GENERIC_SMP_HELPERS
 	depends on MN10300_PROC_MN2WS0038 || MN10300_PROC_MN2WS0050
 	---help---
 	  This enables support for systems with more than one CPU. If you have
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 7dcde539d61e..c03567a9a915 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -226,7 +226,6 @@ endchoice
 
 config SMP
 	bool "Symmetric multi-processing support"
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2f898d63eb96..4740b0a15fa8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -106,7 +106,6 @@ config PPC
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_OPROFILE
 	select HAVE_DEBUG_KMEMLEAK
 	select GENERIC_ATOMIC64 if PPC32
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f75d7e517927..314fced4fc14 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -141,7 +141,6 @@ config S390
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select SYSCTL_EXCEPTION_TRACE
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select VIRT_CPU_ACCOUNTING
 	select VIRT_TO_BUS
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 224f4bc9925e..e78561bc30ef 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -711,7 +711,6 @@ config CC_STACKPROTECTOR
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP
-	select USE_GENERIC_SMP_HELPERS
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, like most personal computers, say N. If
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 78c4fdb91bc5..8591b201d9cc 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -28,7 +28,6 @@ config SPARC
 	select HAVE_ARCH_JUMP_LABEL
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
 	select HAVE_BPF_JIT
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index d45a2c48f185..b3692ce78f90 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -8,7 +8,6 @@ config TILE
 	select HAVE_KVM if !TILEGX
 	select GENERIC_FIND_FIRST_BIT
 	select SYSCTL_EXCEPTION_TRACE
-	select USE_GENERIC_SMP_HELPERS
 	select CC_OPTIMIZE_FOR_SIZE
 	select HAVE_DEBUG_KMEMLEAK
 	select GENERIC_IRQ_PROBE
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index af5513e5798a..83f521aa103f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -90,7 +90,6 @@ config X86
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select IRQ_FORCED_THREADING
-	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_BPF_JIT if X86_64
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select CLKEVT_I8253
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 88d4e864d4c0..c661896e2465 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -319,7 +319,7 @@ void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_complete_request(rq, error);
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#if defined(CONFIG_SMP)
 
 /*
  * Called with interrupts disabled.
@@ -361,7 +361,7 @@ static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
 
 	return true;
 }
-#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+#else /* CONFIG_SMP */
 static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
 			  struct request *rq, const int error)
 {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ce4b8bfd3d27..57790c1a97eb 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -36,7 +36,7 @@ static void blk_done_softirq(struct softirq_action *h)
 	}
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
@@ -71,7 +71,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 
 	return 1;
 }
-#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
+#else /* CONFIG_SMP */
 static int raise_blk_irq(int cpu, struct request *rq)
 {
 	return 1;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 4f8c4d90ec73..97779522472f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -288,7 +288,7 @@ static ssize_t
 queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 {
 	ssize_t ret = -EINVAL;
-#if defined(CONFIG_USE_GENERIC_SMP_HELPERS)
+#ifdef CONFIG_SMP
 	unsigned long val;
 
 	ret = queue_var_store(&val, page, count);
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 731f5237d5f4..78851513030d 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -106,14 +106,10 @@ void kick_all_cpus_sync(void);
 /*
  * Generic and arch helpers
  */
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
 void __init call_function_init(void);
 void generic_smp_call_function_single_interrupt(void);
 #define generic_smp_call_function_interrupt \
 	generic_smp_call_function_single_interrupt
-#else
-static inline void call_function_init(void) { }
-#endif
 
 /*
  * Mark the boot cpu "online" so that it can call console drivers in
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
index 94fabd534b03..2a202a846757 100644
--- a/kernel/Kconfig.hz
+++ b/kernel/Kconfig.hz
@@ -55,4 +55,4 @@ config HZ
 	default 1000 if HZ_1000
 
 config SCHED_HRTICK
-	def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS)
+	def_bool HIGH_RES_TIMERS
diff --git a/kernel/smp.c b/kernel/smp.c
index 46116100f0ee..1c194e20e943 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -15,7 +15,6 @@
 
 #include "smpboot.h"
 
-#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
 enum {
 	CSD_FLAG_LOCK		= 0x01,
 	CSD_FLAG_WAIT		= 0x02,
@@ -464,7 +463,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait)
 	return 0;
 }
 EXPORT_SYMBOL(smp_call_function);
-#endif /* USE_GENERIC_SMP_HELPERS */
 
 /* Setup configured maximum number of CPUs to activate */
 unsigned int setup_max_cpus = NR_CPUS;
-- 
cgit 


From 7cf64f861b7a43b395f0855994003254b06a7e5a Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Thu, 14 Nov 2013 14:32:09 -0800
Subject: kernel-provide-a-__smp_call_function_single-stub-for-config_smp-fix

x86_64 allnoconfig:

  kernel/up.c:25: error: redefinition of '__smp_call_function_single'
  include/linux/smp.h:154: note: previous definition of '__smp_call_function_single' was here

Cc: Christoph Hellwig <hch@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/smp.h | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 78851513030d..5da22ee42e16 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -49,6 +49,9 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
+void __smp_call_function_single(int cpuid, struct call_single_data *data,
+				int wait);
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -95,9 +98,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait);
 void smp_call_function_many(const struct cpumask *mask,
 			    smp_call_func_t func, void *info, bool wait);
 
-void __smp_call_function_single(int cpuid, struct call_single_data *data,
-				int wait);
-
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
 
@@ -151,12 +151,6 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 
 static inline void kick_all_cpus_sync(void) {  }
 
-static inline void __smp_call_function_single(int cpuid,
-		struct call_single_data *data, int wait)
-{
-	on_each_cpu(data->func, data->info, wait);
-}
-
 #endif /* !SMP */
 
 /*
-- 
cgit 


From b89241e8cdb8321c20546d47645a9b65b58113b5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Thu, 14 Nov 2013 14:32:11 -0800
Subject: llists: move llist_reverse_order from raid5 to llist.c

Make this useful helper available for other users.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/md/raid5.c    | 14 --------------
 include/linux/llist.h |  2 ++
 lib/llist.c           | 22 ++++++++++++++++++++++
 3 files changed, 24 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f8b906843926..7f0e17a27aeb 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -293,20 +293,6 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
 		do_release_stripe(conf, sh);
 }
 
-static struct llist_node *llist_reverse_order(struct llist_node *head)
-{
-	struct llist_node *new_head = NULL;
-
-	while (head) {
-		struct llist_node *tmp = head;
-		head = head->next;
-		tmp->next = new_head;
-		new_head = tmp;
-	}
-
-	return new_head;
-}
-
 /* should hold conf->device_lock already */
 static int release_stripe_list(struct r5conf *conf)
 {
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 8828a78dec9a..fbf10a0bc095 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -195,4 +195,6 @@ static inline struct llist_node *llist_del_all(struct llist_head *head)
 
 extern struct llist_node *llist_del_first(struct llist_head *head);
 
+struct llist_node *llist_reverse_order(struct llist_node *head);
+
 #endif /* LLIST_H */
diff --git a/lib/llist.c b/lib/llist.c
index 4a70d120138c..ef48b87247ec 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -81,3 +81,25 @@ struct llist_node *llist_del_first(struct llist_head *head)
 	return entry;
 }
 EXPORT_SYMBOL_GPL(llist_del_first);
+
+/**
+ * llist_reverse_order - reverse order of a llist chain
+ * @head:	first item of the list to be reversed
+ *
+ * Reverse the oder of a chain of llist entries and return the
+ * new first entry.
+ */
+struct llist_node *llist_reverse_order(struct llist_node *head)
+{
+	struct llist_node *new_head = NULL;
+
+	while (head) {
+		struct llist_node *tmp = head;
+		head = head->next;
+		tmp->next = new_head;
+		new_head = tmp;
+	}
+
+	return new_head;
+}
+EXPORT_SYMBOL_GPL(llist_reverse_order);
-- 
cgit 


From 498d319bb512992ef0784c278fa03679f2f5649d Mon Sep 17 00:00:00 2001
From: Stefani Seibold <stefani@seibold.net>
Date: Thu, 14 Nov 2013 14:32:17 -0800
Subject: kfifo API type safety

This patch enhances the type safety for the kfifo API.  It is now safe
to put const data into a non const FIFO and the API will now generate a
compiler warning when reading from the fifo where the destination
address is pointing to a const variable.

As a side effect the kfifo_put() does now expect the value of an element
instead a pointer to the element.  This was suggested Russell King.  It
make the handling of the kfifo_put easier since there is no need to
create a helper variable for getting the address of a pointer or to pass
integers of different sizes.

IMHO the API break is okay, since there are currently only six users of
kfifo_put().

The code is also cleaner by kicking out the "if (0)" expressions.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/drm_flip_work.c          |  2 +-
 drivers/iio/industrialio-event.c         |  2 +-
 drivers/net/wireless/rt2x00/rt2800mmio.c |  2 +-
 drivers/net/wireless/rt2x00/rt2800usb.c  |  2 +-
 drivers/pci/pcie/aer/aerdrv_core.c       |  2 +-
 include/linux/kfifo.h                    | 47 ++++++++++----------------------
 mm/memory-failure.c                      |  2 +-
 samples/kfifo/bytestream-example.c       |  4 +--
 samples/kfifo/dma-example.c              |  2 +-
 samples/kfifo/inttype-example.c          |  4 +--
 10 files changed, 25 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_flip_work.c b/drivers/gpu/drm/drm_flip_work.c
index e788882d9021..f9c7fa3d0012 100644
--- a/drivers/gpu/drm/drm_flip_work.c
+++ b/drivers/gpu/drm/drm_flip_work.c
@@ -34,7 +34,7 @@
  */
 void drm_flip_work_queue(struct drm_flip_work *work, void *val)
 {
-	if (kfifo_put(&work->fifo, (const void **)&val)) {
+	if (kfifo_put(&work->fifo, val)) {
 		atomic_inc(&work->pending);
 	} else {
 		DRM_ERROR("%s fifo full!\n", work->name);
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index dac15b9f9df8..c10eab64bc05 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -56,7 +56,7 @@ int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp)
 		ev.id = ev_code;
 		ev.timestamp = timestamp;
 
-		copied = kfifo_put(&ev_int->det_events, &ev);
+		copied = kfifo_put(&ev_int->det_events, ev);
 		if (copied != 0)
 			wake_up_locked_poll(&ev_int->wait, POLLIN);
 	}
diff --git a/drivers/net/wireless/rt2x00/rt2800mmio.c b/drivers/net/wireless/rt2x00/rt2800mmio.c
index ae152280e071..a8cc736b5063 100644
--- a/drivers/net/wireless/rt2x00/rt2800mmio.c
+++ b/drivers/net/wireless/rt2x00/rt2800mmio.c
@@ -446,7 +446,7 @@ static void rt2800mmio_txstatus_interrupt(struct rt2x00_dev *rt2x00dev)
 		if (!rt2x00_get_field32(status, TX_STA_FIFO_VALID))
 			break;
 
-		if (!kfifo_put(&rt2x00dev->txstatus_fifo, &status)) {
+		if (!kfifo_put(&rt2x00dev->txstatus_fifo, status)) {
 			rt2x00_warn(rt2x00dev, "TX status FIFO overrun, drop tx status report\n");
 			break;
 		}
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index 997df03a0c2e..a81ceb61d746 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -164,7 +164,7 @@ static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev,
 
 	valid = rt2x00_get_field32(tx_status, TX_STA_FIFO_VALID);
 	if (valid) {
-		if (!kfifo_put(&rt2x00dev->txstatus_fifo, &tx_status))
+		if (!kfifo_put(&rt2x00dev->txstatus_fifo, tx_status))
 			rt2x00_warn(rt2x00dev, "TX status FIFO overrun\n");
 
 		queue_work(rt2x00dev->workqueue, &rt2x00dev->txdone_work);
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 85ca36f2136d..6b3a958e1be6 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -574,7 +574,7 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 	};
 
 	spin_lock_irqsave(&aer_recover_ring_lock, flags);
-	if (kfifo_put(&aer_recover_ring, &entry))
+	if (kfifo_put(&aer_recover_ring, entry))
 		schedule_work(&aer_recover_work);
 	else
 		pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n",
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 10308c6a3d1c..552d51efb429 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -1,7 +1,7 @@
 /*
  * A generic kernel FIFO implementation
  *
- * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net>
+ * Copyright (C) 2013 Stefani Seibold <stefani@seibold.net>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -67,9 +67,10 @@ struct __kfifo {
 	union { \
 		struct __kfifo	kfifo; \
 		datatype	*type; \
+		const datatype	*const_type; \
 		char		(*rectype)[recsize]; \
 		ptrtype		*ptr; \
-		const ptrtype	*ptr_const; \
+		ptrtype const	*ptr_const; \
 	}
 
 #define __STRUCT_KFIFO(type, size, recsize, ptrtype) \
@@ -386,16 +387,12 @@ __kfifo_int_must_check_helper( \
 #define	kfifo_put(fifo, val) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(*__tmp->const_type) __val = (val); \
 	unsigned int __ret; \
-	const size_t __recsize = sizeof(*__tmp->rectype); \
+	size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \
-		__dummy = (typeof(__val))NULL; \
-	} \
 	if (__recsize) \
-		__ret = __kfifo_in_r(__kfifo, __val, sizeof(*__val), \
+		__ret = __kfifo_in_r(__kfifo, &__val, sizeof(__val), \
 			__recsize); \
 	else { \
 		__ret = !kfifo_is_full(__tmp); \
@@ -404,7 +401,7 @@ __kfifo_int_must_check_helper( \
 			((typeof(__tmp->type))__kfifo->data) : \
 			(__tmp->buf) \
 			)[__kfifo->in & __tmp->kfifo.mask] = \
-				*(typeof(__tmp->type))__val; \
+				(typeof(*__tmp->type))__val; \
 			smp_wmb(); \
 			__kfifo->in++; \
 		} \
@@ -415,7 +412,7 @@ __kfifo_int_must_check_helper( \
 /**
  * kfifo_get - get data from the fifo
  * @fifo: address of the fifo to be used
- * @val: the var where to store the data to be added
+ * @val: address where to store the data
  *
  * This macro reads the data from the fifo.
  * It returns 0 if the fifo was empty. Otherwise it returns the number
@@ -428,12 +425,10 @@ __kfifo_int_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(__tmp->ptr) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) \
-		__val = (typeof(__tmp->ptr))0; \
 	if (__recsize) \
 		__ret = __kfifo_out_r(__kfifo, __val, sizeof(*__val), \
 			__recsize); \
@@ -456,7 +451,7 @@ __kfifo_uint_must_check_helper( \
 /**
  * kfifo_peek - get data from the fifo without removing
  * @fifo: address of the fifo to be used
- * @val: the var where to store the data to be added
+ * @val: address where to store the data
  *
  * This reads the data from the fifo without removing it from the fifo.
  * It returns 0 if the fifo was empty. Otherwise it returns the number
@@ -469,12 +464,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((val) + 1) __val = (val); \
+	typeof(__tmp->ptr) __val = (val); \
 	unsigned int __ret; \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) \
-		__val = (typeof(__tmp->ptr))NULL; \
 	if (__recsize) \
 		__ret = __kfifo_out_peek_r(__kfifo, __val, sizeof(*__val), \
 			__recsize); \
@@ -508,14 +501,10 @@ __kfifo_uint_must_check_helper( \
 #define	kfifo_in(fifo, buf, n) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr_const) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr_const) __dummy __attribute__ ((unused)); \
-		__dummy = (typeof(__buf))NULL; \
-	} \
 	(__recsize) ?\
 	__kfifo_in_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_in(__kfifo, __buf, __n); \
@@ -561,14 +550,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr) __dummy = NULL; \
-		__buf = __dummy; \
-	} \
 	(__recsize) ?\
 	__kfifo_out_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_out(__kfifo, __buf, __n); \
@@ -773,14 +758,10 @@ __kfifo_uint_must_check_helper( \
 __kfifo_uint_must_check_helper( \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
-	typeof((buf) + 1) __buf = (buf); \
+	typeof(__tmp->ptr) __buf = (buf); \
 	unsigned long __n = (n); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (0) { \
-		typeof(__tmp->ptr) __dummy __attribute__ ((unused)) = NULL; \
-		__buf = __dummy; \
-	} \
 	(__recsize) ? \
 	__kfifo_out_peek_r(__kfifo, __buf, __n, __recsize) : \
 	__kfifo_out_peek(__kfifo, __buf, __n); \
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f9d78ec7831f..b7c171602ba1 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1269,7 +1269,7 @@ void memory_failure_queue(unsigned long pfn, int trapno, int flags)
 
 	mf_cpu = &get_cpu_var(memory_failure_cpu);
 	spin_lock_irqsave(&mf_cpu->lock, proc_flags);
-	if (kfifo_put(&mf_cpu->fifo, &entry))
+	if (kfifo_put(&mf_cpu->fifo, entry))
 		schedule_work_on(smp_processor_id(), &mf_cpu->work);
 	else
 		pr_err("Memory failure: buffer overflow when queuing memory failure at %#lx\n",
diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c
index cfe40addda76..2fca916d9edf 100644
--- a/samples/kfifo/bytestream-example.c
+++ b/samples/kfifo/bytestream-example.c
@@ -64,7 +64,7 @@ static int __init testfunc(void)
 
 	/* put values into the fifo */
 	for (i = 0; i != 10; i++)
-		kfifo_put(&test, &i);
+		kfifo_put(&test, i);
 
 	/* show the number of used elements */
 	printk(KERN_INFO "fifo len: %u\n", kfifo_len(&test));
@@ -85,7 +85,7 @@ static int __init testfunc(void)
 	kfifo_skip(&test);
 
 	/* put values into the fifo until is full */
-	for (i = 20; kfifo_put(&test, &i); i++)
+	for (i = 20; kfifo_put(&test, i); i++)
 		;
 
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&test));
diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c
index 06473791c08a..aa243db93f01 100644
--- a/samples/kfifo/dma-example.c
+++ b/samples/kfifo/dma-example.c
@@ -39,7 +39,7 @@ static int __init example_init(void)
 	kfifo_in(&fifo, "test", 4);
 
 	for (i = 0; i != 9; i++)
-		kfifo_put(&fifo, &i);
+		kfifo_put(&fifo, i);
 
 	/* kick away first byte */
 	kfifo_skip(&fifo);
diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c
index 6f8e79e76c9e..8dc3c2e7105a 100644
--- a/samples/kfifo/inttype-example.c
+++ b/samples/kfifo/inttype-example.c
@@ -61,7 +61,7 @@ static int __init testfunc(void)
 
 	/* put values into the fifo */
 	for (i = 0; i != 10; i++)
-		kfifo_put(&test, &i);
+		kfifo_put(&test, i);
 
 	/* show the number of used elements */
 	printk(KERN_INFO "fifo len: %u\n", kfifo_len(&test));
@@ -78,7 +78,7 @@ static int __init testfunc(void)
 	kfifo_skip(&test);
 
 	/* put values into the fifo until is full */
-	for (i = 20; kfifo_put(&test, &i); i++)
+	for (i = 20; kfifo_put(&test, i); i++)
 		;
 
 	printk(KERN_INFO "queue len: %u\n", kfifo_len(&test));
-- 
cgit 


From 8d3ef556aba2b5b7d8b7144f7be1814d75ea3cc6 Mon Sep 17 00:00:00 2001
From: Alexander Beregalov <a.beregalov@gmail.com>
Date: Thu, 14 Nov 2013 14:32:19 -0800
Subject: cmdline-parser: fix build

Fix following errors:

  include/linux/cmdline-parser.h:17:12: error: 'BDEVNAME_SIZE' undeclared here
  block/cmdline-parser.c:17:2: error: implicit declaration of function 'kzalloc'

Signed-off-by: Alexander Beregalov <alexander.beregalov@intel.com>
Cc: CaiZhiyong <caizhiyong@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cmdline-parser.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h
index 98e892ef6d5a..a0f9280421ec 100644
--- a/include/linux/cmdline-parser.h
+++ b/include/linux/cmdline-parser.h
@@ -8,6 +8,8 @@
 #define CMDLINEPARSEH
 
 #include <linux/blkdev.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
 
 /* partition flags */
 #define PF_RDONLY                   0x01 /* Device is read only */
-- 
cgit 


From 1c636f801615bdfc9b1d46904e8258c7a025670b Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Thu, 31 Oct 2013 15:26:32 +0200
Subject: IB/core: Encorce MR access rights rules on kernel consumers

Enforce the rule that when requesting remote write or atomic permissions, local
write must be indicated as well. See IB spec 11.2.8.2.

Spotted by: Hagay Abramovsky <hagaya@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 10 +++-------
 drivers/infiniband/core/verbs.c      | 14 ++++++++++++++
 include/rdma/ib_verbs.h              | 13 +++++++++++++
 3 files changed, 30 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 5bb2a82d52e7..7f671b7b8bac 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -939,13 +939,9 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 	if ((cmd.start & ~PAGE_MASK) != (cmd.hca_va & ~PAGE_MASK))
 		return -EINVAL;
 
-	/*
-	 * Local write permission is required if remote write or
-	 * remote atomic permission is also requested.
-	 */
-	if (cmd.access_flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) &&
-	    !(cmd.access_flags & IB_ACCESS_LOCAL_WRITE))
-		return -EINVAL;
+	ret = ib_check_mr_access(cmd.access_flags);
+	if (ret)
+		return ret;
 
 	uobj = kmalloc(sizeof *uobj, GFP_KERNEL);
 	if (!uobj)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 84f502785f89..d4f6ddf72ffa 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -961,6 +961,11 @@ EXPORT_SYMBOL(ib_resize_cq);
 struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags)
 {
 	struct ib_mr *mr;
+	int err;
+
+	err = ib_check_mr_access(mr_access_flags);
+	if (err)
+		return ERR_PTR(err);
 
 	mr = pd->device->get_dma_mr(pd, mr_access_flags);
 
@@ -983,6 +988,11 @@ struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
 			     u64 *iova_start)
 {
 	struct ib_mr *mr;
+	int err;
+
+	err = ib_check_mr_access(mr_access_flags);
+	if (err)
+		return ERR_PTR(err);
 
 	if (!pd->device->reg_phys_mr)
 		return ERR_PTR(-ENOSYS);
@@ -1013,6 +1023,10 @@ int ib_rereg_phys_mr(struct ib_mr *mr,
 	struct ib_pd *old_pd;
 	int ret;
 
+	ret = ib_check_mr_access(mr_access_flags);
+	if (ret)
+		return ret;
+
 	if (!mr->device->rereg_phys_mr)
 		return -ENOSYS;
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 60354d53948e..68c053d0d629 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2386,4 +2386,17 @@ struct ib_flow *ib_create_flow(struct ib_qp *qp,
 			       struct ib_flow_attr *flow_attr, int domain);
 int ib_destroy_flow(struct ib_flow *flow_id);
 
+static inline int ib_check_mr_access(int flags)
+{
+	/*
+	 * Local write permission is required if remote write or
+	 * remote atomic permission is also requested.
+	 */
+	if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) &&
+	    !(flags & IB_ACCESS_LOCAL_WRITE))
+		return -EINVAL;
+
+	return 0;
+}
+
 #endif /* IB_VERBS_H */
-- 
cgit 


From be9eac48274a2d9b142d6dd8567b9b2362939346 Mon Sep 17 00:00:00 2001
From: Michal Kubeček <mkubecek@suse.cz>
Date: Fri, 15 Nov 2013 06:18:40 +0100
Subject: macvlan: introduce macvlan_dev_real_dev() helper function

Introduce helper function macvlan_dev_real_dev which returns the
underlying device of a macvlan device, similar to vlan_dev_real_dev()
for 802.1q VLAN devices.

v2: IFF_MACVLAN flag and equivalent of is_macvlan_dev() were
introduced in the meantime

v3: do BUG() if compiled without macvlan support

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_macvlan.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index c2702856295e..84ba5ac39e03 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -119,4 +119,21 @@ extern int macvlan_link_register(struct rtnl_link_ops *ops);
 extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev);
 
+#if IS_ENABLED(CONFIG_MACVLAN)
+static inline struct net_device *
+macvlan_dev_real_dev(const struct net_device *dev)
+{
+	struct macvlan_dev *macvlan = netdev_priv(dev);
+
+	return macvlan->lowerdev;
+}
+#else
+static inline struct net_device *
+macvlan_dev_real_dev(const struct net_device *dev)
+{
+	BUG();
+	return NULL;
+}
+#endif
+
 #endif /* _LINUX_IF_MACVLAN_H */
-- 
cgit 


From 568508aa0724cc39bcf7d3d8001bd27a45609800 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 15 Nov 2013 14:19:08 +0100
Subject: genetlink: unify registration functions

Now that the ops assignment is just two variables rather than a
long list iteration etc., there's no reason to separately export
__genl_register_family() and __genl_register_family_with_ops().

Unify the two functions into __genl_register_family() and make
genl_register_family_with_ops() call it after assigning the ops.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 28 ++++++++++++++++++++++----
 net/netlink/genetlink.c | 53 +++++++++++++++----------------------------------
 2 files changed, 40 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 0b6a144468c6..e96385d46b48 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -131,14 +131,34 @@ static inline int genl_register_family(struct genl_family *family)
 	return __genl_register_family(family);
 }
 
-int __genl_register_family_with_ops(struct genl_family *family,
-				    const struct genl_ops *ops, size_t n_ops);
-
+/**
+ * genl_register_family_with_ops - register a generic netlink family with ops
+ * @family: generic netlink family
+ * @ops: operations to be registered
+ * @n_ops: number of elements to register
+ *
+ * Registers the specified family and operations from the specified table.
+ * Only one family may be registered with the same family name or identifier.
+ *
+ * The family id may equal GENL_ID_GENERATE causing an unique id to
+ * be automatically generated and assigned.
+ *
+ * Either a doit or dumpit callback must be specified for every registered
+ * operation or the function will fail. Only one operation structure per
+ * command identifier may be registered.
+ *
+ * See include/net/genetlink.h for more documenation on the operations
+ * structure.
+ *
+ * Return 0 on success or a negative error code.
+ */
 static inline int genl_register_family_with_ops(struct genl_family *family,
 	const struct genl_ops *ops, size_t n_ops)
 {
 	family->module = THIS_MODULE;
-	return __genl_register_family_with_ops(family, ops, n_ops);
+	family->ops = ops;
+	family->n_ops = n_ops;
+	return __genl_register_family(family);
 }
 
 int genl_unregister_family(struct genl_family *family);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index a7c62d3d05a1..f07eb568a1db 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -283,12 +283,18 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 		__genl_unregister_mc_group(family, grp);
 }
 
-static int genl_validate_add_ops(struct genl_family *family,
-				 const struct genl_ops *ops,
-				 unsigned int n_ops)
+static int genl_validate_ops(struct genl_family *family)
 {
+	const struct genl_ops *ops = family->ops;
+	unsigned int n_ops = family->n_ops;
 	int i, j;
 
+	if (WARN_ON(n_ops && !ops))
+		return -EINVAL;
+
+	if (!n_ops)
+		return 0;
+
 	for (i = 0; i < n_ops; i++) {
 		if (ops[i].dumpit == NULL && ops[i].doit == NULL)
 			return -EINVAL;
@@ -313,6 +319,9 @@ static int genl_validate_add_ops(struct genl_family *family,
  * The family id may equal GENL_ID_GENERATE causing an unique id to
  * be automatically generated and assigned.
  *
+ * The family's ops array must already be assigned, you can use the
+ * genl_register_family_with_ops() helper function.
+ *
  * Return 0 on success or a negative error code.
  */
 int __genl_register_family(struct genl_family *family)
@@ -325,6 +334,10 @@ int __genl_register_family(struct genl_family *family)
 	if (family->id > GENL_MAX_ID)
 		goto errout;
 
+	err = genl_validate_ops(family);
+	if (err)
+		return err;
+
 	INIT_LIST_HEAD(&family->mcast_groups);
 
 	genl_lock_all();
@@ -372,40 +385,6 @@ errout:
 }
 EXPORT_SYMBOL(__genl_register_family);
 
-/**
- * __genl_register_family_with_ops - register a generic netlink family
- * @family: generic netlink family
- * @ops: operations to be registered
- * @n_ops: number of elements to register
- *
- * Registers the specified family and operations from the specified table.
- * Only one family may be registered with the same family name or identifier.
- *
- * The family id may equal GENL_ID_GENERATE causing an unique id to
- * be automatically generated and assigned.
- *
- * Either a doit or dumpit callback must be specified for every registered
- * operation or the function will fail. Only one operation structure per
- * command identifier may be registered.
- *
- * See include/net/genetlink.h for more documenation on the operations
- * structure.
- *
- * Return 0 on success or a negative error code.
- */
-int __genl_register_family_with_ops(struct genl_family *family,
-	const struct genl_ops *ops, size_t n_ops)
-{
-	int err;
-
-	err = genl_validate_add_ops(family, ops, n_ops);
-	if (err)
-		return err;
-
-	return __genl_register_family(family);
-}
-EXPORT_SYMBOL(__genl_register_family_with_ops);
-
 /**
  * genl_unregister_family - unregister generic netlink family
  * @family: generic netlink family
-- 
cgit 


From 65c5189a2b57b9aa1d89e4b79da39928257c9505 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Nov 2013 08:57:26 -0800
Subject: pkt_sched: fq: warn users using defrate

Commit 7eec4174ff29 ("pkt_sched: fq: fix non TCP flows pacing")
obsoleted TCA_FQ_FLOW_DEFAULT_RATE without notice for the users.

Suggested by David Miller

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  4 +---
 net/sched/sch_fq.c             | 10 ++++------
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 307f293477e8..885001b62c83 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -763,9 +763,7 @@ enum {
 
 	TCA_FQ_RATE_ENABLE,	/* enable/disable rate limiting */
 
-	TCA_FQ_FLOW_DEFAULT_RATE,/* for sockets with unspecified sk_rate,
-				  * use the following rate
-				  */
+	TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
 
 	TCA_FQ_FLOW_MAX_RATE,	/* per flow max rate */
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index d4fa38e4af80..26906ab51c52 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -88,7 +88,6 @@ struct fq_sched_data {
 	struct fq_flow	internal;	/* for non classified or high prio packets */
 	u32		quantum;
 	u32		initial_quantum;
-	u32		flow_default_rate;/* rate per flow : bytes per second */
 	u32		flow_max_rate;	/* optional max rate per flow */
 	u32		flow_plimit;	/* max packets per flow */
 	struct rb_root	*fq_root;
@@ -650,7 +649,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 		q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
 
 	if (tb[TCA_FQ_FLOW_DEFAULT_RATE])
-		q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]);
+		pr_warn_ratelimited("sch_fq: defrate %u ignored.\n",
+				    nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]));
 
 	if (tb[TCA_FQ_FLOW_MAX_RATE])
 		q->flow_max_rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]);
@@ -699,7 +699,6 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->flow_plimit		= 100;
 	q->quantum		= 2 * psched_mtu(qdisc_dev(sch));
 	q->initial_quantum	= 10 * psched_mtu(qdisc_dev(sch));
-	q->flow_default_rate	= 0;
 	q->flow_max_rate	= ~0U;
 	q->rate_enable		= 1;
 	q->new_flows.first	= NULL;
@@ -726,9 +725,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (opts == NULL)
 		goto nla_put_failure;
 
-	/* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore,
-	 * do not bother giving its value
-	 */
+	/* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */
+
 	if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) ||
 	    nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) ||
-- 
cgit 


From f52ed89971adbe79b6438c459814034707b8ab91 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 15 Nov 2013 08:58:14 -0800
Subject: pkt_sched: fq: fix pacing for small frames
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For performance reasons, sch_fq tried hard to not setup timers for every
sent packet, using a quantum based heuristic : A delay is setup only if
the flow exhausted its credit.

Problem is that application limited flows can refill their credit
for every queued packet, and they can evade pacing.

This problem can also be triggered when TCP flows use small MSS values,
as TSO auto sizing builds packets that are smaller than the default fq
quantum (3028 bytes)

This patch adds a 40 ms delay to guard flow credit refill.

Fixes: afe4fd062416 ("pkt_sched: fq: Fair Queue packet scheduler")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  3 +++
 net/sched/sch_fq.c             | 22 ++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 885001b62c83..a806687ad98f 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -768,6 +768,9 @@ enum {
 	TCA_FQ_FLOW_MAX_RATE,	/* per flow max rate */
 
 	TCA_FQ_BUCKETS_LOG,	/* log2(number of buckets) */
+
+	TCA_FQ_FLOW_REFILL_DELAY,	/* flow credit refill delay in usec */
+
 	__TCA_FQ_MAX
 };
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 26906ab51c52..95d843961907 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -88,6 +88,7 @@ struct fq_sched_data {
 	struct fq_flow	internal;	/* for non classified or high prio packets */
 	u32		quantum;
 	u32		initial_quantum;
+	u32		flow_refill_delay;
 	u32		flow_max_rate;	/* optional max rate per flow */
 	u32		flow_plimit;	/* max packets per flow */
 	struct rb_root	*fq_root;
@@ -114,6 +115,7 @@ static struct fq_flow detached, throttled;
 static void fq_flow_set_detached(struct fq_flow *f)
 {
 	f->next = &detached;
+	f->age = jiffies;
 }
 
 static bool fq_flow_is_detached(const struct fq_flow *f)
@@ -366,17 +368,20 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	f->qlen++;
-	flow_queue_add(f, skb);
 	if (skb_is_retransmit(skb))
 		q->stat_tcp_retrans++;
 	sch->qstats.backlog += qdisc_pkt_len(skb);
 	if (fq_flow_is_detached(f)) {
 		fq_flow_add_tail(&q->new_flows, f);
-		if (q->quantum > f->credit)
-			f->credit = q->quantum;
+		if (time_after(jiffies, f->age + q->flow_refill_delay))
+			f->credit = max_t(u32, f->credit, q->quantum);
 		q->inactive_flows--;
 		qdisc_unthrottled(sch);
 	}
+
+	/* Note: this overwrites f->age */
+	flow_queue_add(f, skb);
+
 	if (unlikely(f == &q->internal)) {
 		q->stat_internal_packets++;
 		qdisc_unthrottled(sch);
@@ -454,7 +459,6 @@ begin:
 			fq_flow_add_tail(&q->old_flows, f);
 		} else {
 			fq_flow_set_detached(f);
-			f->age = jiffies;
 			q->inactive_flows++;
 		}
 		goto begin;
@@ -608,6 +612,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = {
 	[TCA_FQ_FLOW_DEFAULT_RATE]	= { .type = NLA_U32 },
 	[TCA_FQ_FLOW_MAX_RATE]		= { .type = NLA_U32 },
 	[TCA_FQ_BUCKETS_LOG]		= { .type = NLA_U32 },
+	[TCA_FQ_FLOW_REFILL_DELAY]	= { .type = NLA_U32 },
 };
 
 static int fq_change(struct Qdisc *sch, struct nlattr *opt)
@@ -664,6 +669,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 			err = -EINVAL;
 	}
 
+	if (tb[TCA_FQ_FLOW_REFILL_DELAY]) {
+		u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ;
+
+		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
+	}
+
 	if (!err)
 		err = fq_resize(q, fq_log);
 
@@ -699,6 +710,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->flow_plimit		= 100;
 	q->quantum		= 2 * psched_mtu(qdisc_dev(sch));
 	q->initial_quantum	= 10 * psched_mtu(qdisc_dev(sch));
+	q->flow_refill_delay	= msecs_to_jiffies(40);
 	q->flow_max_rate	= ~0U;
 	q->rate_enable		= 1;
 	q->new_flows.first	= NULL;
@@ -733,6 +745,8 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) ||
 	    nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
+	    nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY,
+			jiffies_to_usecs(q->flow_refill_delay)) ||
 	    nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
 		goto nla_put_failure;
 
-- 
cgit 


From 018c5bba052b3a383d83cf0c756da0e7bc748397 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 15 Nov 2013 21:11:16 -0500
Subject: net: Handle CHECKSUM_COMPLETE more adequately in pskb_trim_rcsum().

Currently pskb_trim_rcsum() just balks on CHECKSUM_COMPLETE packets
and remarks them as CHECKSUM_NONE, forcing a software checksum
validation later.

We have all of the mechanics available to fixup the skb->csum value,
even for complicated fragmented packets, via the helpers
skb_checksum() and csum_sub().

So just use them.

Based upon a suggestion by Herbert Xu.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 215b5ea1cb30..bec1cc7d5e3c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2263,24 +2263,6 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
 
-/**
- *	pskb_trim_rcsum - trim received skb and update checksum
- *	@skb: buffer to trim
- *	@len: new length
- *
- *	This is exactly the same as pskb_trim except that it ensures the
- *	checksum of received packets are still valid after the operation.
- */
-
-static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
-{
-	if (likely(len >= skb->len))
-		return 0;
-	if (skb->ip_summed == CHECKSUM_COMPLETE)
-		skb->ip_summed = CHECKSUM_NONE;
-	return __pskb_trim(skb, len);
-}
-
 #define skb_queue_walk(queue, skb) \
 		for (skb = (queue)->next;					\
 		     skb != (struct sk_buff *)(queue);				\
@@ -2378,6 +2360,27 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 __wsum skb_checksum(const struct sk_buff *skb, int offset, int len,
 		    __wsum csum);
 
+/**
+ *	pskb_trim_rcsum - trim received skb and update checksum
+ *	@skb: buffer to trim
+ *	@len: new length
+ *
+ *	This is exactly the same as pskb_trim except that it ensures the
+ *	checksum of received packets are still valid after the operation.
+ */
+
+static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len)
+{
+	if (likely(len >= skb->len))
+		return 0;
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__wsum adj = skb_checksum(skb, len, skb->len - len, 0);
+
+		skb->csum = csum_sub(skb->csum, adj);
+	}
+	return __pskb_trim(skb, len);
+}
+
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
 {
-- 
cgit 


From b26d4cd385fc51e8844e2cdf9ba2051f5bba11a5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 25 Oct 2013 18:47:37 -0400
Subject: consolidate simple ->d_delete() instances

Rename simple_delete_dentry() to always_delete_dentry() and export it.
Export simple_dentry_operations, while we are at it, and get rid of
their duplicates

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/ia64/kernel/perfmon.c |  8 +-------
 fs/9p/vfs_dentry.c         | 19 +------------------
 fs/configfs/dir.c          | 12 +-----------
 fs/efivarfs/super.c        | 11 +----------
 fs/hostfs/hostfs_kern.c    | 11 +----------
 fs/libfs.c                 | 12 +++++++-----
 fs/proc/generic.c          | 18 +-----------------
 fs/proc/namespaces.c       |  8 +-------
 include/linux/fs.h         |  2 ++
 kernel/cgroup.c            |  7 +------
 net/sunrpc/rpc_pipe.c      | 11 +----------
 11 files changed, 18 insertions(+), 101 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5a9ff1c3c3e9..cb592773c78b 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2166,12 +2166,6 @@ static const struct file_operations pfm_file_ops = {
 	.flush		= pfm_flush
 };
 
-static int
-pfmfs_delete_dentry(const struct dentry *dentry)
-{
-	return 1;
-}
-
 static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	return dynamic_dname(dentry, buffer, buflen, "pfm:[%lu]",
@@ -2179,7 +2173,7 @@ static char *pfmfs_dname(struct dentry *dentry, char *buffer, int buflen)
 }
 
 static const struct dentry_operations pfmfs_dentry_operations = {
-	.d_delete = pfmfs_delete_dentry,
+	.d_delete = always_delete_dentry,
 	.d_dname = pfmfs_dname,
 };
 
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index f039b104a98e..b03dd23feda8 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -42,23 +42,6 @@
 #include "v9fs_vfs.h"
 #include "fid.h"
 
-/**
- * v9fs_dentry_delete - called when dentry refcount equals 0
- * @dentry:  dentry in question
- *
- * By returning 1 here we should remove cacheing of unused
- * dentry components.
- *
- */
-
-static int v9fs_dentry_delete(const struct dentry *dentry)
-{
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
-
-	return 1;
-}
-
 /**
  * v9fs_cached_dentry_delete - called when dentry refcount equals 0
  * @dentry:  dentry in question
@@ -134,6 +117,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = {
 };
 
 const struct dentry_operations v9fs_dentry_operations = {
-	.d_delete = v9fs_dentry_delete,
+	.d_delete = always_delete_dentry,
 	.d_release = v9fs_dentry_release,
 };
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 277bd1be21fd..4522e0755773 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -66,19 +66,9 @@ static void configfs_d_iput(struct dentry * dentry,
 	iput(inode);
 }
 
-/*
- * We _must_ delete our dentries on last dput, as the chain-to-parent
- * behavior is required to clear the parents of default_groups.
- */
-static int configfs_d_delete(const struct dentry *dentry)
-{
-	return 1;
-}
-
 const struct dentry_operations configfs_dentry_ops = {
 	.d_iput		= configfs_d_iput,
-	/* simple_delete_dentry() isn't exported */
-	.d_delete	= configfs_d_delete,
+	.d_delete	= always_delete_dentry,
 };
 
 #ifdef CONFIG_LOCKDEP
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index a8766b880c07..becc725a1953 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -83,19 +83,10 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr)
 	return 0;
 }
 
-/*
- * Retaining negative dentries for an in-memory filesystem just wastes
- * memory and lookup time: arrange for them to be deleted immediately.
- */
-static int efivarfs_delete_dentry(const struct dentry *dentry)
-{
-	return 1;
-}
-
 static struct dentry_operations efivarfs_d_ops = {
 	.d_compare = efivarfs_d_compare,
 	.d_hash = efivarfs_d_hash,
-	.d_delete = efivarfs_delete_dentry,
+	.d_delete = always_delete_dentry,
 };
 
 static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name)
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 25437280a207..db23ce1bd903 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -33,15 +33,6 @@ static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
 
 #define FILE_HOSTFS_I(file) HOSTFS_I(file_inode(file))
 
-static int hostfs_d_delete(const struct dentry *dentry)
-{
-	return 1;
-}
-
-static const struct dentry_operations hostfs_dentry_ops = {
-	.d_delete		= hostfs_d_delete,
-};
-
 /* Changed in hostfs_args before the kernel starts running */
 static char *root_ino = "";
 static int append = 0;
@@ -925,7 +916,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
 	sb->s_blocksize_bits = 10;
 	sb->s_magic = HOSTFS_SUPER_MAGIC;
 	sb->s_op = &hostfs_sbops;
-	sb->s_d_op = &hostfs_dentry_ops;
+	sb->s_d_op = &simple_dentry_operations;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 
 	/* NULL is printed as <NULL> by sprintf: avoid that. */
diff --git a/fs/libfs.c b/fs/libfs.c
index 5de06947ba5e..a1844244246f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -47,10 +47,16 @@ EXPORT_SYMBOL(simple_statfs);
  * Retaining negative dentries for an in-memory filesystem just wastes
  * memory and lookup time: arrange for them to be deleted immediately.
  */
-static int simple_delete_dentry(const struct dentry *dentry)
+int always_delete_dentry(const struct dentry *dentry)
 {
 	return 1;
 }
+EXPORT_SYMBOL(always_delete_dentry);
+
+const struct dentry_operations simple_dentry_operations = {
+	.d_delete = always_delete_dentry,
+};
+EXPORT_SYMBOL(simple_dentry_operations);
 
 /*
  * Lookup the data. This is trivial - if the dentry didn't already
@@ -58,10 +64,6 @@ static int simple_delete_dentry(const struct dentry *dentry)
  */
 struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
-	static const struct dentry_operations simple_dentry_operations = {
-		.d_delete = simple_delete_dentry,
-	};
-
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 	if (!dentry->d_sb->s_d_op)
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 737e15615b04..cca93b6fb9a9 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -174,22 +174,6 @@ static const struct inode_operations proc_link_inode_operations = {
 	.follow_link	= proc_follow_link,
 };
 
-/*
- * As some entries in /proc are volatile, we want to 
- * get rid of unused dentries.  This could be made 
- * smarter: we could keep a "volatile" flag in the 
- * inode to indicate which ones to keep.
- */
-static int proc_delete_dentry(const struct dentry * dentry)
-{
-	return 1;
-}
-
-static const struct dentry_operations proc_dentry_operations =
-{
-	.d_delete	= proc_delete_dentry,
-};
-
 /*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
@@ -209,7 +193,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 			inode = proc_get_inode(dir->i_sb, de);
 			if (!inode)
 				return ERR_PTR(-ENOMEM);
-			d_set_d_op(dentry, &proc_dentry_operations);
+			d_set_d_op(dentry, &simple_dentry_operations);
 			d_add(dentry, inode);
 			return NULL;
 		}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 49a7fff2e83a..9ae46b87470d 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -42,12 +42,6 @@ static const struct inode_operations ns_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int ns_delete_dentry(const struct dentry *dentry)
-{
-	/* Don't cache namespace inodes when not in use */
-	return 1;
-}
-
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = dentry->d_inode;
@@ -59,7 +53,7 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 
 const struct dentry_operations ns_dentry_operations =
 {
-	.d_delete	= ns_delete_dentry,
+	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
 };
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bf5d574ebdf4..121f11f001c0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2622,7 +2622,9 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata);
+extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e0839bcd48c8..4c62513fe19f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -895,11 +895,6 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 	iput(inode);
 }
 
-static int cgroup_delete(const struct dentry *d)
-{
-	return 1;
-}
-
 static void remove_dir(struct dentry *d)
 {
 	struct dentry *parent = dget(d->d_parent);
@@ -1486,7 +1481,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
 {
 	static const struct dentry_operations cgroup_dops = {
 		.d_iput = cgroup_diput,
-		.d_delete = cgroup_delete,
+		.d_delete = always_delete_dentry,
 	};
 
 	struct inode *inode =
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index d0d14a04dce1..bf04b30a788a 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -471,15 +471,6 @@ struct rpc_filelist {
 	umode_t mode;
 };
 
-static int rpc_delete_dentry(const struct dentry *dentry)
-{
-	return 1;
-}
-
-static const struct dentry_operations rpc_dentry_operations = {
-	.d_delete = rpc_delete_dentry,
-};
-
 static struct inode *
 rpc_get_inode(struct super_block *sb, umode_t mode)
 {
@@ -1266,7 +1257,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
 	sb->s_magic = RPCAUTH_GSSMAGIC;
 	sb->s_op = &s_ops;
-	sb->s_d_op = &rpc_dentry_operations;
+	sb->s_d_op = &simple_dentry_operations;
 	sb->s_time_gran = 1;
 
 	inode = rpc_get_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO);
-- 
cgit 


From 2bc74feba12fbf052ec97aee8624c9f13593a9ac Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 25 Oct 2013 16:39:14 -0400
Subject: take read_seqbegin_or_lock() and friends to seqlock.h

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c             | 29 -----------------------------
 include/linux/seqlock.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 0a38ef8d7f00..667e23ab0b4c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -88,35 +88,6 @@ EXPORT_SYMBOL(rename_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
 
-/**
- * read_seqbegin_or_lock - begin a sequence number check or locking block
- * @lock: sequence lock
- * @seq : sequence number to be checked
- *
- * First try it once optimistically without taking the lock. If that fails,
- * take the lock. The sequence number is also used as a marker for deciding
- * whether to be a reader (even) or writer (odd).
- * N.B. seq must be initialized to an even number to begin with.
- */
-static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
-{
-	if (!(*seq & 1))	/* Even */
-		*seq = read_seqbegin(lock);
-	else			/* Odd */
-		read_seqlock_excl(lock);
-}
-
-static inline int need_seqretry(seqlock_t *lock, int seq)
-{
-	return !(seq & 1) && read_seqretry(lock, seq);
-}
-
-static inline void done_seqretry(seqlock_t *lock, int seq)
-{
-	if (seq & 1)
-		read_sequnlock_excl(lock);
-}
-
 /*
  * This is the single most critical data structure when it comes
  * to the dcache: the hashtable for lookups. Somebody should try
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 1e8a8b6e837d..cf87a24c0f92 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -354,6 +354,35 @@ static inline void read_sequnlock_excl(seqlock_t *sl)
 	spin_unlock(&sl->lock);
 }
 
+/**
+ * read_seqbegin_or_lock - begin a sequence number check or locking block
+ * @lock: sequence lock
+ * @seq : sequence number to be checked
+ *
+ * First try it once optimistically without taking the lock. If that fails,
+ * take the lock. The sequence number is also used as a marker for deciding
+ * whether to be a reader (even) or writer (odd).
+ * N.B. seq must be initialized to an even number to begin with.
+ */
+static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
+{
+	if (!(*seq & 1))	/* Even */
+		*seq = read_seqbegin(lock);
+	else			/* Odd */
+		read_seqlock_excl(lock);
+}
+
+static inline int need_seqretry(seqlock_t *lock, int seq)
+{
+	return !(seq & 1) && read_seqretry(lock, seq);
+}
+
+static inline void done_seqretry(seqlock_t *lock, int seq)
+{
+	if (seq & 1)
+		read_sequnlock_excl(lock);
+}
+
 static inline void read_seqlock_excl_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-- 
cgit 


From f88482743872230f5899b8344a057d6e2fd011e2 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 6 Nov 2013 23:21:44 +0100
Subject: IB/core: clarify overflow/underflow checks on ib_create/destroy_flow

This patch fixes the following issues:

1. Unneeded checks were removed

2. Removed the fixed size out of flow_attr.size, thus simplifying the checks.

3. Remove a 32bit hole on 64bit systems with strict alignment in
   struct ib_kern_flow_att by adding a reserved field.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 32 +++++++++++++++-----------------
 include/uapi/rdma/ib_user_verbs.h    |  1 +
 2 files changed, 16 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2f0f01b70e3b..26ee2d2a8c52 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2657,7 +2657,6 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	void *kern_spec;
 	void *ib_spec;
 	int i;
-	int kern_attr_size;
 
 	if (out_len < sizeof(resp))
 		return -ENOSPC;
@@ -2672,32 +2671,28 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	     !capable(CAP_NET_ADMIN)) || !capable(CAP_NET_RAW))
 		return -EPERM;
 
-	if (cmd.flow_attr.num_of_specs < 0 ||
-	    cmd.flow_attr.num_of_specs > IB_FLOW_SPEC_SUPPORT_LAYERS)
+	if (cmd.flow_attr.num_of_specs > IB_FLOW_SPEC_SUPPORT_LAYERS)
 		return -EINVAL;
 
-	kern_attr_size = cmd.flow_attr.size - sizeof(cmd) -
-			 sizeof(struct ib_uverbs_cmd_hdr_ex);
-
-	if (cmd.flow_attr.size < 0 || cmd.flow_attr.size > in_len ||
-	    kern_attr_size < 0 || kern_attr_size >
+	if (cmd.flow_attr.size > (in_len - sizeof(cmd)) ||
+	    cmd.flow_attr.size >
 	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_kern_spec)))
 		return -EINVAL;
 
 	if (cmd.flow_attr.num_of_specs) {
-		kern_flow_attr = kmalloc(cmd.flow_attr.size, GFP_KERNEL);
+		kern_flow_attr = kmalloc(sizeof(*kern_flow_attr) + cmd.flow_attr.size,
+					 GFP_KERNEL);
 		if (!kern_flow_attr)
 			return -ENOMEM;
 
 		memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
 		if (copy_from_user(kern_flow_attr + 1, buf + sizeof(cmd),
-				   kern_attr_size)) {
+				   cmd.flow_attr.size)) {
 			err = -EFAULT;
 			goto err_free_attr;
 		}
 	} else {
 		kern_flow_attr = &cmd.flow_attr;
-		kern_attr_size = sizeof(cmd.flow_attr);
 	}
 
 	uobj = kmalloc(sizeof(*uobj), GFP_KERNEL);
@@ -2714,7 +2709,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 		goto err_uobj;
 	}
 
-	flow_attr = kmalloc(cmd.flow_attr.size, GFP_KERNEL);
+	flow_attr = kmalloc(sizeof(*flow_attr) + cmd.flow_attr.size, GFP_KERNEL);
 	if (!flow_attr) {
 		err = -ENOMEM;
 		goto err_put;
@@ -2729,19 +2724,22 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 
 	kern_spec = kern_flow_attr + 1;
 	ib_spec = flow_attr + 1;
-	for (i = 0; i < flow_attr->num_of_specs && kern_attr_size > 0; i++) {
+	for (i = 0; i < flow_attr->num_of_specs &&
+	     cmd.flow_attr.size > offsetof(struct ib_kern_spec, reserved) &&
+	     cmd.flow_attr.size >=
+	     ((struct ib_kern_spec *)kern_spec)->size; i++) {
 		err = kern_spec_to_ib_spec(kern_spec, ib_spec);
 		if (err)
 			goto err_free;
 		flow_attr->size +=
 			((union ib_flow_spec *) ib_spec)->size;
-		kern_attr_size -= ((struct ib_kern_spec *) kern_spec)->size;
+		cmd.flow_attr.size -= ((struct ib_kern_spec *)kern_spec)->size;
 		kern_spec += ((struct ib_kern_spec *) kern_spec)->size;
 		ib_spec += ((union ib_flow_spec *) ib_spec)->size;
 	}
-	if (kern_attr_size) {
-		pr_warn("create flow failed, %d bytes left from uverb cmd\n",
-			kern_attr_size);
+	if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
+		pr_warn("create flow failed, flow %d: %d bytes left from uverb cmd\n",
+			i, cmd.flow_attr.size);
 		goto err_free;
 	}
 	flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index e3ddd86c90a6..99a58bdc1c64 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -771,6 +771,7 @@ struct ib_kern_flow_attr {
 
 struct ib_uverbs_create_flow  {
 	__u32 comp_mask;
+	__u32 reserved;
 	__u64 response;
 	__u32 qp_handle;
 	struct ib_kern_flow_attr flow_attr;
-- 
cgit 


From d82693dad09b49232cd727ee9e15bd027710edac Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 6 Nov 2013 23:21:45 +0100
Subject: IB/core: Rename 'flow' structs to match other uverbs structs

Commit 436f2ad05a0b ("IB/core: Export ib_create/destroy_flow through
uverbs") added public data structures to support receive flow
steering.  The new structs are not following the 'uverbs' pattern:
they're lacking the common prefix 'ib_uverbs'.

This patch replaces ib_kern prefix by ib_uverbs.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Link: http://marc.info/?i=cover.1383773832.git.ydroneaud@opteya.com
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 14 +++++++-------
 include/uapi/rdma/ib_user_verbs.h    | 36 ++++++++++++++++++------------------
 2 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 26ee2d2a8c52..f83c1dc08481 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2602,7 +2602,7 @@ out_put:
 }
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-static int kern_spec_to_ib_spec(struct ib_kern_spec *kern_spec,
+static int kern_spec_to_ib_spec(struct ib_uverbs_spec *kern_spec,
 				union ib_flow_spec *ib_spec)
 {
 	ib_spec->type = kern_spec->type;
@@ -2650,7 +2650,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	struct ib_uverbs_create_flow_resp resp;
 	struct ib_uobject		  *uobj;
 	struct ib_flow			  *flow_id;
-	struct ib_kern_flow_attr	  *kern_flow_attr;
+	struct ib_uverbs_flow_attr	  *kern_flow_attr;
 	struct ib_flow_attr		  *flow_attr;
 	struct ib_qp			  *qp;
 	int err = 0;
@@ -2676,7 +2676,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 
 	if (cmd.flow_attr.size > (in_len - sizeof(cmd)) ||
 	    cmd.flow_attr.size >
-	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_kern_spec)))
+	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_spec)))
 		return -EINVAL;
 
 	if (cmd.flow_attr.num_of_specs) {
@@ -2725,16 +2725,16 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	kern_spec = kern_flow_attr + 1;
 	ib_spec = flow_attr + 1;
 	for (i = 0; i < flow_attr->num_of_specs &&
-	     cmd.flow_attr.size > offsetof(struct ib_kern_spec, reserved) &&
+	     cmd.flow_attr.size > offsetof(struct ib_uverbs_spec, reserved) &&
 	     cmd.flow_attr.size >=
-	     ((struct ib_kern_spec *)kern_spec)->size; i++) {
+	     ((struct ib_uverbs_spec *)kern_spec)->size; i++) {
 		err = kern_spec_to_ib_spec(kern_spec, ib_spec);
 		if (err)
 			goto err_free;
 		flow_attr->size +=
 			((union ib_flow_spec *) ib_spec)->size;
-		cmd.flow_attr.size -= ((struct ib_kern_spec *)kern_spec)->size;
-		kern_spec += ((struct ib_kern_spec *) kern_spec)->size;
+		cmd.flow_attr.size -= ((struct ib_uverbs_spec *)kern_spec)->size;
+		kern_spec += ((struct ib_uverbs_spec *) kern_spec)->size;
 		ib_spec += ((union ib_flow_spec *) ib_spec)->size;
 	}
 	if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 99a58bdc1c64..96a660533236 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -701,61 +701,61 @@ struct ib_uverbs_detach_mcast {
 };
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-struct ib_kern_eth_filter {
+struct ib_uverbs_eth_filter {
 	__u8  dst_mac[6];
 	__u8  src_mac[6];
 	__be16 ether_type;
 	__be16 vlan_tag;
 };
 
-struct ib_kern_spec_eth {
+struct ib_uverbs_spec_eth {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_kern_eth_filter val;
-	struct ib_kern_eth_filter mask;
+	struct ib_uverbs_eth_filter val;
+	struct ib_uverbs_eth_filter mask;
 };
 
-struct ib_kern_ipv4_filter {
+struct ib_uverbs_ipv4_filter {
 	__be32 src_ip;
 	__be32 dst_ip;
 };
 
-struct ib_kern_spec_ipv4 {
+struct ib_uverbs_spec_ipv4 {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_kern_ipv4_filter val;
-	struct ib_kern_ipv4_filter mask;
+	struct ib_uverbs_ipv4_filter val;
+	struct ib_uverbs_ipv4_filter mask;
 };
 
-struct ib_kern_tcp_udp_filter {
+struct ib_uverbs_tcp_udp_filter {
 	__be16 dst_port;
 	__be16 src_port;
 };
 
-struct ib_kern_spec_tcp_udp {
+struct ib_uverbs_spec_tcp_udp {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_kern_tcp_udp_filter val;
-	struct ib_kern_tcp_udp_filter mask;
+	struct ib_uverbs_tcp_udp_filter val;
+	struct ib_uverbs_tcp_udp_filter mask;
 };
 
-struct ib_kern_spec {
+struct ib_uverbs_spec {
 	union {
 		struct {
 			__u32 type;
 			__u16 size;
 			__u16 reserved;
 		};
-		struct ib_kern_spec_eth	    eth;
-		struct ib_kern_spec_ipv4    ipv4;
-		struct ib_kern_spec_tcp_udp tcp_udp;
+		struct ib_uverbs_spec_eth	    eth;
+		struct ib_uverbs_spec_ipv4    ipv4;
+		struct ib_uverbs_spec_tcp_udp tcp_udp;
 	};
 };
 
-struct ib_kern_flow_attr {
+struct ib_uverbs_flow_attr {
 	__u32 type;
 	__u16 size;
 	__u16 priority;
@@ -774,7 +774,7 @@ struct ib_uverbs_create_flow  {
 	__u32 reserved;
 	__u64 response;
 	__u32 qp_handle;
-	struct ib_kern_flow_attr flow_attr;
+	struct ib_uverbs_flow_attr flow_attr;
 };
 
 struct ib_uverbs_create_flow_resp {
-- 
cgit 


From b68c956021386eead6b8b28e445f33c8c985d7d2 Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 6 Nov 2013 23:21:46 +0100
Subject: IB/core: Make uverbs flow structure use names like verbs ones

This patch adds "flow" prefix to most of data structure added as part
of commit 436f2ad05a0b ("IB/core: Export ib_create/destroy_flow through
uverbs") to keep those names in sync with the data structures added in
commit 319a441d1361 ("IB/core: Add receive flow steering support").

It's just a matter of translating 'ib_flow' to 'ib_uverbs_flow'.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Link: http://marc.info/?i=cover.1383773832.git.ydroneaud@opteya.com
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 12 ++++++------
 include/uapi/rdma/ib_user_verbs.h    | 32 ++++++++++++++++----------------
 2 files changed, 22 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index f83c1dc08481..19f14d82c988 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2602,7 +2602,7 @@ out_put:
 }
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-static int kern_spec_to_ib_spec(struct ib_uverbs_spec *kern_spec,
+static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 				union ib_flow_spec *ib_spec)
 {
 	ib_spec->type = kern_spec->type;
@@ -2676,7 +2676,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 
 	if (cmd.flow_attr.size > (in_len - sizeof(cmd)) ||
 	    cmd.flow_attr.size >
-	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_spec)))
+	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_flow_spec)))
 		return -EINVAL;
 
 	if (cmd.flow_attr.num_of_specs) {
@@ -2725,16 +2725,16 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	kern_spec = kern_flow_attr + 1;
 	ib_spec = flow_attr + 1;
 	for (i = 0; i < flow_attr->num_of_specs &&
-	     cmd.flow_attr.size > offsetof(struct ib_uverbs_spec, reserved) &&
+	     cmd.flow_attr.size > offsetof(struct ib_uverbs_flow_spec, reserved) &&
 	     cmd.flow_attr.size >=
-	     ((struct ib_uverbs_spec *)kern_spec)->size; i++) {
+	     ((struct ib_uverbs_flow_spec *)kern_spec)->size; i++) {
 		err = kern_spec_to_ib_spec(kern_spec, ib_spec);
 		if (err)
 			goto err_free;
 		flow_attr->size +=
 			((union ib_flow_spec *) ib_spec)->size;
-		cmd.flow_attr.size -= ((struct ib_uverbs_spec *)kern_spec)->size;
-		kern_spec += ((struct ib_uverbs_spec *) kern_spec)->size;
+		cmd.flow_attr.size -= ((struct ib_uverbs_flow_spec *)kern_spec)->size;
+		kern_spec += ((struct ib_uverbs_flow_spec *) kern_spec)->size;
 		ib_spec += ((union ib_flow_spec *) ib_spec)->size;
 	}
 	if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 96a660533236..ef2be64bf4c3 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -701,57 +701,57 @@ struct ib_uverbs_detach_mcast {
 };
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-struct ib_uverbs_eth_filter {
+struct ib_uverbs_flow_eth_filter {
 	__u8  dst_mac[6];
 	__u8  src_mac[6];
 	__be16 ether_type;
 	__be16 vlan_tag;
 };
 
-struct ib_uverbs_spec_eth {
+struct ib_uverbs_flow_spec_eth {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_uverbs_eth_filter val;
-	struct ib_uverbs_eth_filter mask;
+	struct ib_uverbs_flow_eth_filter val;
+	struct ib_uverbs_flow_eth_filter mask;
 };
 
-struct ib_uverbs_ipv4_filter {
+struct ib_uverbs_flow_ipv4_filter {
 	__be32 src_ip;
 	__be32 dst_ip;
 };
 
-struct ib_uverbs_spec_ipv4 {
+struct ib_uverbs_flow_spec_ipv4 {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_uverbs_ipv4_filter val;
-	struct ib_uverbs_ipv4_filter mask;
+	struct ib_uverbs_flow_ipv4_filter val;
+	struct ib_uverbs_flow_ipv4_filter mask;
 };
 
-struct ib_uverbs_tcp_udp_filter {
+struct ib_uverbs_flow_tcp_udp_filter {
 	__be16 dst_port;
 	__be16 src_port;
 };
 
-struct ib_uverbs_spec_tcp_udp {
+struct ib_uverbs_flow_spec_tcp_udp {
 	__u32  type;
 	__u16  size;
 	__u16  reserved;
-	struct ib_uverbs_tcp_udp_filter val;
-	struct ib_uverbs_tcp_udp_filter mask;
+	struct ib_uverbs_flow_tcp_udp_filter val;
+	struct ib_uverbs_flow_tcp_udp_filter mask;
 };
 
-struct ib_uverbs_spec {
+struct ib_uverbs_flow_spec {
 	union {
 		struct {
 			__u32 type;
 			__u16 size;
 			__u16 reserved;
 		};
-		struct ib_uverbs_spec_eth	    eth;
-		struct ib_uverbs_spec_ipv4    ipv4;
-		struct ib_uverbs_spec_tcp_udp tcp_udp;
+		struct ib_uverbs_flow_spec_eth	    eth;
+		struct ib_uverbs_flow_spec_ipv4    ipv4;
+		struct ib_uverbs_flow_spec_tcp_udp tcp_udp;
 	};
 };
 
-- 
cgit 


From 58913efba9c3aa7992f2a4d630135ded833d988e Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 6 Nov 2013 23:21:47 +0100
Subject: IB/core: Use a common header for uverbs flow_specs

A common header will allows better checking of flow specs size, while
ensuring strict alignment to 64 bits.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Link: http://marc.info/?i=cover.1383773832.git.ydroneaud@opteya.com
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 include/uapi/rdma/ib_user_verbs.h | 53 +++++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index ef2be64bf4c3..43014981550a 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -701,6 +701,14 @@ struct ib_uverbs_detach_mcast {
 };
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
+struct ib_uverbs_flow_spec_hdr {
+	__u32 type;
+	__u16 size;
+	__u16 reserved;
+	/* followed by flow_spec */
+	__u64 flow_spec_data[0];
+};
+
 struct ib_uverbs_flow_eth_filter {
 	__u8  dst_mac[6];
 	__u8  src_mac[6];
@@ -709,9 +717,14 @@ struct ib_uverbs_flow_eth_filter {
 };
 
 struct ib_uverbs_flow_spec_eth {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
 	struct ib_uverbs_flow_eth_filter val;
 	struct ib_uverbs_flow_eth_filter mask;
 };
@@ -722,9 +735,14 @@ struct ib_uverbs_flow_ipv4_filter {
 };
 
 struct ib_uverbs_flow_spec_ipv4 {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
 	struct ib_uverbs_flow_ipv4_filter val;
 	struct ib_uverbs_flow_ipv4_filter mask;
 };
@@ -735,19 +753,27 @@ struct ib_uverbs_flow_tcp_udp_filter {
 };
 
 struct ib_uverbs_flow_spec_tcp_udp {
-	__u32  type;
-	__u16  size;
-	__u16  reserved;
+	union {
+		struct ib_uverbs_flow_spec_hdr hdr;
+		struct {
+			__u32 type;
+			__u16 size;
+			__u16 reserved;
+		};
+	};
 	struct ib_uverbs_flow_tcp_udp_filter val;
 	struct ib_uverbs_flow_tcp_udp_filter mask;
 };
 
 struct ib_uverbs_flow_spec {
 	union {
-		struct {
-			__u32 type;
-			__u16 size;
-			__u16 reserved;
+		union {
+			struct ib_uverbs_flow_spec_hdr hdr;
+			struct {
+				__u32 type;
+				__u16 size;
+				__u16 reserved;
+			};
 		};
 		struct ib_uverbs_flow_spec_eth	    eth;
 		struct ib_uverbs_flow_spec_ipv4    ipv4;
@@ -767,6 +793,7 @@ struct ib_uverbs_flow_attr {
 	 * struct ib_flow_spec_xxx
 	 * struct ib_flow_spec_yyy
 	 */
+	struct ib_uverbs_flow_spec_hdr flow_specs[0];
 };
 
 struct ib_uverbs_create_flow  {
-- 
cgit 


From 2490f20be496c2da14ae4632a8c60e0633e97fd0 Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 6 Nov 2013 23:21:48 +0100
Subject: IB/core: Remove ib_uverbs_flow_spec structure from userspace

The structure holding any types of flow_spec is of no use to
userspace.  It would be wrong for userspace to do:

  struct ib_uverbs_flow_spec flow_spec;

  flow_spec.type = IB_FLOW_SPEC_TCP;
  flow_spec.size = sizeof(flow_spec);

Instead, userspace should use the dedicated flow_spec structure for
  - Ethernet : struct ib_uverbs_flow_spec_eth,
  - IPv4     : struct ib_uverbs_flow_spec_ipv4,
  - TCP/UDP  : struct ib_uverbs_flow_spec_tcp_udp.

In other words, struct ib_uverbs_flow_spec is a "virtual" data
structure that can only be use by the kernel as an alias to the other.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Link: http://marc.info/?i=cover.1383773832.git.ydroneaud@opteya.com
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs.h  | 16 ++++++++++++++++
 include/uapi/rdma/ib_user_verbs.h | 16 ----------------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index d8f9c6c272d7..777954f67270 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -178,6 +178,22 @@ void ib_uverbs_event_handler(struct ib_event_handler *handler,
 			     struct ib_event *event);
 void ib_uverbs_dealloc_xrcd(struct ib_uverbs_device *dev, struct ib_xrcd *xrcd);
 
+struct ib_uverbs_flow_spec {
+	union {
+		union {
+			struct ib_uverbs_flow_spec_hdr hdr;
+			struct {
+				__u32 type;
+				__u16 size;
+				__u16 reserved;
+			};
+		};
+		struct ib_uverbs_flow_spec_eth     eth;
+		struct ib_uverbs_flow_spec_ipv4    ipv4;
+		struct ib_uverbs_flow_spec_tcp_udp tcp_udp;
+	};
+};
+
 #define IB_UVERBS_DECLARE_CMD(name)					\
 	ssize_t ib_uverbs_##name(struct ib_uverbs_file *file,		\
 				 const char __user *buf, int in_len,	\
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 43014981550a..fc9bbe37cfce 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -765,22 +765,6 @@ struct ib_uverbs_flow_spec_tcp_udp {
 	struct ib_uverbs_flow_tcp_udp_filter mask;
 };
 
-struct ib_uverbs_flow_spec {
-	union {
-		union {
-			struct ib_uverbs_flow_spec_hdr hdr;
-			struct {
-				__u32 type;
-				__u16 size;
-				__u16 reserved;
-			};
-		};
-		struct ib_uverbs_flow_spec_eth	    eth;
-		struct ib_uverbs_flow_spec_ipv4    ipv4;
-		struct ib_uverbs_flow_spec_tcp_udp tcp_udp;
-	};
-};
-
 struct ib_uverbs_flow_attr {
 	__u32 type;
 	__u16 size;
-- 
cgit 


From f21519b23c1b6fa25366be4114ccf7fcf1c190f9 Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Wed, 6 Nov 2013 23:21:49 +0100
Subject: IB/core: extended command: an improved infrastructure for uverbs
 commands

Commit 400dbc96583f ("IB/core: Infrastructure for extensible uverbs
commands") added an infrastructure for extensible uverbs commands
while later commit 436f2ad05a0b ("IB/core: Export ib_create/destroy_flow
through uverbs") exported ib_create_flow()/ib_destroy_flow() functions
using this new infrastructure.

According to the commit 400dbc96583f, the purpose of this
infrastructure is to support passing around provider (eg. hardware)
specific buffers when userspace issue commands to the kernel, so that
it would be possible to extend uverbs (eg. core) buffers independently
from the provider buffers.

But the new kernel command function prototypes were not modified to
take advantage of this extension. This issue was exposed by Roland
Dreier in a previous review[1].

So the following patch is an attempt to a revised extensible command
infrastructure.

This improved extensible command infrastructure distinguish between
core (eg. legacy)'s command/response buffers from provider
(eg. hardware)'s command/response buffers: each extended command
implementing function is given a struct ib_udata to hold core
(eg. uverbs) input and output buffers, and another struct ib_udata to
hold the hw (eg. provider) input and output buffers.

Having those buffers identified separately make it easier to increase
one buffer to support extension without having to add some code to
guess the exact size of each command/response parts: This should make
the extended functions more reliable.

Additionally, instead of relying on command identifier being greater
than IB_USER_VERBS_CMD_THRESHOLD, the proposed infrastructure rely on
unused bits in command field: on the 32 bits provided by command
field, only 6 bits are really needed to encode the identifier of
commands currently supported by the kernel. (Even using only 6 bits
leaves room for about 23 new commands).

So this patch makes use of some high order bits in command field to
store flags, leaving enough room for more command identifiers than one
will ever need (eg. 256).

The new flags are used to specify if the command should be processed
as an extended one or a legacy one. While designing the new command
format, care was taken to make usage of flags itself extensible.

Using high order bits of the commands field ensure that newer
libibverbs on older kernel will properly fail when trying to call
extended commands. On the other hand, older libibverbs on newer kernel
will never be able to issue calls to extended commands.

The extended command header includes the optional response pointer so
that output buffer length and output buffer pointer are located
together in the command, allowing proper parameters checking. This
should make implementing functions easier and safer.

Additionally the extended header ensure 64bits alignment, while making
all sizes multiple of 8 bytes, extending the maximum buffer size:

                             legacy      extended

   Maximum command buffer:  256KBytes   1024KBytes (512KBytes + 512KBytes)
  Maximum response buffer:  256KBytes   1024KBytes (512KBytes + 512KBytes)

For the purpose of doing proper buffer size accounting, the headers
size are no more taken in account in "in_words".

One of the odds of the current extensible infrastructure, reading
twice the "legacy" command header, is fixed by removing the "legacy"
command header from the extended command header: they are processed as
two different parts of the command: memory is read once and
information are not duplicated: it's making clear that's an extended
command scheme and not a different command scheme.

The proposed scheme will format input (command) and output (response)
buffers this way:

- command:

  legacy header +
  extended header +
  command data (core + hw):

    +----------------------------------------+
    | flags     |   00      00    |  command |
    |        in_words    |   out_words       |
    +----------------------------------------+
    |                 response               |
    |                 response               |
    | provider_in_words | provider_out_words |
    |                 padding                |
    +----------------------------------------+
    |                                        |
    .              <uverbs input>            .
    .              (in_words * 8)            .
    |                                        |
    +----------------------------------------+
    |                                        |
    .             <provider input>           .
    .          (provider_in_words * 8)       .
    |                                        |
    +----------------------------------------+

- response, if present:

    +----------------------------------------+
    |                                        |
    .          <uverbs output space>         .
    .             (out_words * 8)            .
    |                                        |
    +----------------------------------------+
    |                                        |
    .         <provider output space>        .
    .         (provider_out_words * 8)       .
    |                                        |
    +----------------------------------------+

The overall design is to ensure that the extensible infrastructure is
itself extensible while begin more reliable with more input and bound
checking.

Note:

The unused field in the extended header would be perfect candidate to
hold the command "comp_mask" (eg. bit field used to handle
compatibility).  This was suggested by Roland Dreier in a previous
review[2].  But "comp_mask" field is likely to be present in the uverb
input and/or provider input, likewise for the response, as noted by
Matan Barak[3], so it doesn't make sense to put "comp_mask" in the
header.

[1]:
http://marc.info/?i=CAL1RGDWxmM17W2o_era24A-TTDeKyoL6u3NRu_=t_dhV_ZA9MA@mail.gmail.com

[2]:
http://marc.info/?i=CAL1RGDXJtrc849M6_XNZT5xO1+ybKtLWGq6yg6LhoSsKpsmkYA@mail.gmail.com

[3]:
http://marc.info/?i=525C1149.6000701@mellanox.com

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Link: http://marc.info/?i=cover.1383773832.git.ydroneaud@opteya.com

[ Convert "ret ? ret : 0" to the equivalent "ret".  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs.h      |  20 +++++-
 drivers/infiniband/core/uverbs_cmd.c  |  56 +++++++--------
 drivers/infiniband/core/uverbs_main.c | 127 ++++++++++++++++++++++++++--------
 drivers/infiniband/hw/mlx4/main.c     |   6 +-
 include/rdma/ib_verbs.h               |   1 +
 include/uapi/rdma/ib_user_verbs.h     |  23 +++---
 6 files changed, 160 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 777954f67270..24adccbf92f9 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -47,6 +47,14 @@
 #include <rdma/ib_umem.h>
 #include <rdma/ib_user_verbs.h>
 
+#define INIT_UDATA(udata, ibuf, obuf, ilen, olen)			\
+	do {								\
+		(udata)->inbuf  = (void __user *) (ibuf);		\
+		(udata)->outbuf = (void __user *) (obuf);		\
+		(udata)->inlen  = (ilen);				\
+		(udata)->outlen = (olen);				\
+	} while (0)
+
 /*
  * Our lifetime rules for these structs are the following:
  *
@@ -233,9 +241,17 @@ IB_UVERBS_DECLARE_CMD(destroy_srq);
 IB_UVERBS_DECLARE_CMD(create_xsrq);
 IB_UVERBS_DECLARE_CMD(open_xrcd);
 IB_UVERBS_DECLARE_CMD(close_xrcd);
+
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-IB_UVERBS_DECLARE_CMD(create_flow);
-IB_UVERBS_DECLARE_CMD(destroy_flow);
+
+#define IB_UVERBS_DECLARE_EX_CMD(name)				\
+	int ib_uverbs_ex_##name(struct ib_uverbs_file *file,	\
+				struct ib_udata *ucore,		\
+				struct ib_udata *uhw)
+
+IB_UVERBS_DECLARE_EX_CMD(create_flow);
+IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
+
 #endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 19f14d82c988..33a52785f812 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -58,14 +58,6 @@ static struct uverbs_lock_class xrcd_lock_class = { .name = "XRCD-uobj" };
 static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
 #endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
-#define INIT_UDATA(udata, ibuf, obuf, ilen, olen)			\
-	do {								\
-		(udata)->inbuf  = (void __user *) (ibuf);		\
-		(udata)->outbuf = (void __user *) (obuf);		\
-		(udata)->inlen  = (ilen);				\
-		(udata)->outlen = (olen);				\
-	} while (0)
-
 /*
  * The ib_uobject locking scheme is as follows:
  *
@@ -2642,9 +2634,9 @@ static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 	return 0;
 }
 
-ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
-			      const char __user *buf, int in_len,
-			      int out_len)
+int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
+			     struct ib_udata *ucore,
+			     struct ib_udata *uhw)
 {
 	struct ib_uverbs_create_flow	  cmd;
 	struct ib_uverbs_create_flow_resp resp;
@@ -2658,11 +2650,15 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	void *ib_spec;
 	int i;
 
-	if (out_len < sizeof(resp))
+	if (ucore->outlen < sizeof(resp))
 		return -ENOSPC;
 
-	if (copy_from_user(&cmd, buf, sizeof(cmd)))
-		return -EFAULT;
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	ucore->inbuf += sizeof(cmd);
+	ucore->inlen -= sizeof(cmd);
 
 	if (cmd.comp_mask)
 		return -EINVAL;
@@ -2674,7 +2670,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	if (cmd.flow_attr.num_of_specs > IB_FLOW_SPEC_SUPPORT_LAYERS)
 		return -EINVAL;
 
-	if (cmd.flow_attr.size > (in_len - sizeof(cmd)) ||
+	if (cmd.flow_attr.size > ucore->inlen ||
 	    cmd.flow_attr.size >
 	    (cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_flow_spec)))
 		return -EINVAL;
@@ -2686,11 +2682,10 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 			return -ENOMEM;
 
 		memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
-		if (copy_from_user(kern_flow_attr + 1, buf + sizeof(cmd),
-				   cmd.flow_attr.size)) {
-			err = -EFAULT;
+		err = ib_copy_from_udata(kern_flow_attr + 1, ucore,
+					 cmd.flow_attr.size);
+		if (err)
 			goto err_free_attr;
-		}
 	} else {
 		kern_flow_attr = &cmd.flow_attr;
 	}
@@ -2758,11 +2753,10 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	memset(&resp, 0, sizeof(resp));
 	resp.flow_handle = uobj->id;
 
-	if (copy_to_user((void __user *)(unsigned long) cmd.response,
-			 &resp, sizeof(resp))) {
-		err = -EFAULT;
+	err = ib_copy_to_udata(ucore,
+			       &resp, sizeof(resp));
+	if (err)
 		goto err_copy;
-	}
 
 	put_qp_read(qp);
 	mutex_lock(&file->mutex);
@@ -2775,7 +2769,7 @@ ssize_t ib_uverbs_create_flow(struct ib_uverbs_file *file,
 	kfree(flow_attr);
 	if (cmd.flow_attr.num_of_specs)
 		kfree(kern_flow_attr);
-	return in_len;
+	return 0;
 err_copy:
 	idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
 destroy_flow:
@@ -2792,16 +2786,18 @@ err_free_attr:
 	return err;
 }
 
-ssize_t ib_uverbs_destroy_flow(struct ib_uverbs_file *file,
-			       const char __user *buf, int in_len,
-			       int out_len) {
+int ib_uverbs_ex_destroy_flow(struct ib_uverbs_file *file,
+			      struct ib_udata *ucore,
+			      struct ib_udata *uhw)
+{
 	struct ib_uverbs_destroy_flow	cmd;
 	struct ib_flow			*flow_id;
 	struct ib_uobject		*uobj;
 	int				ret;
 
-	if (copy_from_user(&cmd, buf, sizeof(cmd)))
-		return -EFAULT;
+	ret = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (ret)
+		return ret;
 
 	uobj = idr_write_uobj(&ib_uverbs_rule_idr, cmd.flow_handle,
 			      file->ucontext);
@@ -2823,7 +2819,7 @@ ssize_t ib_uverbs_destroy_flow(struct ib_uverbs_file *file,
 
 	put_uobj(uobj);
 
-	return ret ? ret : in_len;
+	return ret;
 }
 #endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 2df31f68ea09..189d99e76d9f 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -115,11 +115,16 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_CMD_CLOSE_XRCD]		= ib_uverbs_close_xrcd,
 	[IB_USER_VERBS_CMD_CREATE_XSRQ]		= ib_uverbs_create_xsrq,
 	[IB_USER_VERBS_CMD_OPEN_QP]		= ib_uverbs_open_qp,
+};
+
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-	[IB_USER_VERBS_CMD_CREATE_FLOW]		= ib_uverbs_create_flow,
-	[IB_USER_VERBS_CMD_DESTROY_FLOW]	= ib_uverbs_destroy_flow
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
+static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
+				    struct ib_udata *ucore,
+				    struct ib_udata *uhw) = {
+	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
+	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow
 };
+#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 static void ib_uverbs_add_one(struct ib_device *device);
 static void ib_uverbs_remove_one(struct ib_device *device);
@@ -589,6 +594,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 {
 	struct ib_uverbs_file *file = filp->private_data;
 	struct ib_uverbs_cmd_hdr hdr;
+	__u32 flags;
 
 	if (count < sizeof hdr)
 		return -EINVAL;
@@ -596,45 +602,108 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(&hdr, buf, sizeof hdr))
 		return -EFAULT;
 
-	if (hdr.command >= ARRAY_SIZE(uverbs_cmd_table) ||
-	    !uverbs_cmd_table[hdr.command])
-		return -EINVAL;
+	flags = (hdr.command &
+		 IB_USER_VERBS_CMD_FLAGS_MASK) >> IB_USER_VERBS_CMD_FLAGS_SHIFT;
 
-	if (!file->ucontext &&
-	    hdr.command != IB_USER_VERBS_CMD_GET_CONTEXT)
-		return -EINVAL;
+	if (!flags) {
+		__u32 command;
 
-	if (!(file->device->ib_dev->uverbs_cmd_mask & (1ull << hdr.command)))
-		return -ENOSYS;
+		if (hdr.command & ~(__u32)(IB_USER_VERBS_CMD_FLAGS_MASK |
+					   IB_USER_VERBS_CMD_COMMAND_MASK))
+			return -EINVAL;
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-	if (hdr.command >= IB_USER_VERBS_CMD_THRESHOLD) {
-		struct ib_uverbs_cmd_hdr_ex hdr_ex;
+		command = hdr.command & IB_USER_VERBS_CMD_COMMAND_MASK;
 
-		if (copy_from_user(&hdr_ex, buf, sizeof(hdr_ex)))
-			return -EFAULT;
+		if (command >= ARRAY_SIZE(uverbs_cmd_table) ||
+		    !uverbs_cmd_table[command])
+			return -EINVAL;
 
-		if (((hdr_ex.in_words + hdr_ex.provider_in_words) * 4) != count)
+		if (!file->ucontext &&
+		    command != IB_USER_VERBS_CMD_GET_CONTEXT)
 			return -EINVAL;
 
-		return uverbs_cmd_table[hdr.command](file,
-						     buf + sizeof(hdr_ex),
-						     (hdr_ex.in_words +
-						      hdr_ex.provider_in_words) * 4,
-						     (hdr_ex.out_words +
-						      hdr_ex.provider_out_words) * 4);
-	} else {
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
+		if (!(file->device->ib_dev->uverbs_cmd_mask & (1ull << command)))
+			return -ENOSYS;
+
 		if (hdr.in_words * 4 != count)
 			return -EINVAL;
 
-		return uverbs_cmd_table[hdr.command](file,
-						     buf + sizeof(hdr),
-						     hdr.in_words * 4,
-						     hdr.out_words * 4);
+		return uverbs_cmd_table[command](file,
+						 buf + sizeof(hdr),
+						 hdr.in_words * 4,
+						 hdr.out_words * 4);
+
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
+
+	} else if (flags == IB_USER_VERBS_CMD_FLAG_EXTENDED) {
+		__u32 command;
+
+		struct ib_uverbs_ex_cmd_hdr ex_hdr;
+		struct ib_udata ucore;
+		struct ib_udata uhw;
+		int err;
+		size_t written_count = count;
+
+		if (hdr.command & ~(__u32)(IB_USER_VERBS_CMD_FLAGS_MASK |
+					   IB_USER_VERBS_CMD_COMMAND_MASK))
+			return -EINVAL;
+
+		command = hdr.command & IB_USER_VERBS_CMD_COMMAND_MASK;
+
+		if (command >= ARRAY_SIZE(uverbs_ex_cmd_table) ||
+		    !uverbs_ex_cmd_table[command])
+			return -ENOSYS;
+
+		if (!file->ucontext)
+			return -EINVAL;
+
+		if (!(file->device->ib_dev->uverbs_ex_cmd_mask & (1ull << command)))
+			return -ENOSYS;
+
+		if (count < (sizeof(hdr) + sizeof(ex_hdr)))
+			return -EINVAL;
+
+		if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr)))
+			return -EFAULT;
+
+		count -= sizeof(hdr) + sizeof(ex_hdr);
+		buf += sizeof(hdr) + sizeof(ex_hdr);
+
+		if ((hdr.in_words + ex_hdr.provider_in_words) * 8 != count)
+			return -EINVAL;
+
+		if (ex_hdr.response) {
+			if (!hdr.out_words && !ex_hdr.provider_out_words)
+				return -EINVAL;
+		} else {
+			if (hdr.out_words || ex_hdr.provider_out_words)
+				return -EINVAL;
+		}
+
+		INIT_UDATA(&ucore,
+			   (hdr.in_words) ? buf : 0,
+			   (unsigned long)ex_hdr.response,
+			   hdr.in_words * 8,
+			   hdr.out_words * 8);
+
+		INIT_UDATA(&uhw,
+			   (ex_hdr.provider_in_words) ? buf + ucore.inlen : 0,
+			   (ex_hdr.provider_out_words) ? (unsigned long)ex_hdr.response + ucore.outlen : 0,
+			   ex_hdr.provider_in_words * 8,
+			   ex_hdr.provider_out_words * 8);
+
+		err = uverbs_ex_cmd_table[command](file,
+						   &ucore,
+						   &uhw);
+
+		if (err)
+			return err;
+
+		return written_count;
 	}
 #endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
+
+	return -ENOSYS;
 }
 
 static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f0612645de99..4be29fef66d6 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1692,9 +1692,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ibdev->ib_dev.destroy_flow	= mlx4_ib_destroy_flow;
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-		ibdev->ib_dev.uverbs_cmd_mask	|=
-			(1ull << IB_USER_VERBS_CMD_CREATE_FLOW) |
-			(1ull << IB_USER_VERBS_CMD_DESTROY_FLOW);
+		ibdev->ib_dev.uverbs_ex_cmd_mask	|=
+			(1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
+			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
 #endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 	}
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e393171e2fac..a06fc122f803 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1436,6 +1436,7 @@ struct ib_device {
 
 	int			     uverbs_abi_ver;
 	u64			     uverbs_cmd_mask;
+	u64			     uverbs_ex_cmd_mask;
 
 	char			     node_desc[64];
 	__be64			     node_guid;
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index fc9bbe37cfce..6ace125e1af6 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -87,11 +87,14 @@ enum {
 	IB_USER_VERBS_CMD_CLOSE_XRCD,
 	IB_USER_VERBS_CMD_CREATE_XSRQ,
 	IB_USER_VERBS_CMD_OPEN_QP,
+};
+
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-	IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
-	IB_USER_VERBS_CMD_DESTROY_FLOW
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
+enum {
+	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
+	IB_USER_VERBS_EX_CMD_DESTROY_FLOW
 };
+#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 /*
  * Make sure that all structs defined in this file remain laid out so
@@ -122,6 +125,12 @@ struct ib_uverbs_comp_event_desc {
  * the rest of the command struct based on these value.
  */
 
+#define IB_USER_VERBS_CMD_COMMAND_MASK 0xff
+#define IB_USER_VERBS_CMD_FLAGS_MASK 0xff000000u
+#define IB_USER_VERBS_CMD_FLAGS_SHIFT 24
+
+#define IB_USER_VERBS_CMD_FLAG_EXTENDED 0x80
+
 struct ib_uverbs_cmd_hdr {
 	__u32 command;
 	__u16 in_words;
@@ -129,10 +138,8 @@ struct ib_uverbs_cmd_hdr {
 };
 
 #ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-struct ib_uverbs_cmd_hdr_ex {
-	__u32 command;
-	__u16 in_words;
-	__u16 out_words;
+struct ib_uverbs_ex_cmd_hdr {
+	__u64 response;
 	__u16 provider_in_words;
 	__u16 provider_out_words;
 	__u32 cmd_hdr_reserved;
@@ -782,8 +789,6 @@ struct ib_uverbs_flow_attr {
 
 struct ib_uverbs_create_flow  {
 	__u32 comp_mask;
-	__u32 reserved;
-	__u64 response;
 	__u32 qp_handle;
 	struct ib_uverbs_flow_attr flow_attr;
 };
-- 
cgit 


From 69ad5da41b4ed94aef31d4111a3442cfd73ce570 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 6 Nov 2013 23:21:50 +0100
Subject: IB/core: Re-enable create_flow/destroy_flow uverbs

This commit reverts commit 7afbddfae993 ("IB/core: Temporarily disable
create_flow/destroy_flow uverbs").  Since the uverbs extensions
functionality was experimental for v3.12, this patch re-enables the
support for them and flow-steering for v3.13.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/Kconfig            | 11 -----------
 drivers/infiniband/core/uverbs.h      |  4 ----
 drivers/infiniband/core/uverbs_cmd.c  |  4 ----
 drivers/infiniband/core/uverbs_main.c |  5 -----
 drivers/infiniband/hw/mlx4/main.c     |  2 --
 include/uapi/rdma/ib_user_verbs.h     |  6 ------
 6 files changed, 32 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index b84791f03a27..5ceda710f516 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -31,17 +31,6 @@ config INFINIBAND_USER_ACCESS
 	  libibverbs, libibcm and a hardware driver library from
 	  <http://www.openfabrics.org/git/>.
 
-config INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-       bool "Experimental and unstable ABI for userspace access to flow steering verbs"
-       depends on INFINIBAND_USER_ACCESS
-       depends on STAGING
-	---help---
-	  The final ABI for userspace access to flow steering verbs
-	  has not been defined.  To use the current ABI, *WHICH WILL
-	  CHANGE IN THE FUTURE*, say Y here.
-
-	  If unsure, say N.
-
 config INFINIBAND_USER_MEM
 	bool
 	depends on INFINIBAND_USER_ACCESS != n
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 24adccbf92f9..bdc842e9faef 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -242,8 +242,6 @@ IB_UVERBS_DECLARE_CMD(create_xsrq);
 IB_UVERBS_DECLARE_CMD(open_xrcd);
 IB_UVERBS_DECLARE_CMD(close_xrcd);
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-
 #define IB_UVERBS_DECLARE_EX_CMD(name)				\
 	int ib_uverbs_ex_##name(struct ib_uverbs_file *file,	\
 				struct ib_udata *ucore,		\
@@ -252,6 +250,4 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
 
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
-
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 33a52785f812..8233744b4140 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -54,9 +54,7 @@ static struct uverbs_lock_class qp_lock_class	= { .name = "QP-uobj" };
 static struct uverbs_lock_class ah_lock_class	= { .name = "AH-uobj" };
 static struct uverbs_lock_class srq_lock_class	= { .name = "SRQ-uobj" };
 static struct uverbs_lock_class xrcd_lock_class = { .name = "XRCD-uobj" };
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 /*
  * The ib_uobject locking scheme is as follows:
@@ -2593,7 +2591,6 @@ out_put:
 	return ret ? ret : in_len;
 }
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
 				union ib_flow_spec *ib_spec)
 {
@@ -2821,7 +2818,6 @@ int ib_uverbs_ex_destroy_flow(struct ib_uverbs_file *file,
 
 	return ret;
 }
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 				struct ib_uverbs_create_xsrq *cmd,
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 189d99e76d9f..34386943ebcf 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -117,14 +117,12 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_CMD_OPEN_QP]		= ib_uverbs_open_qp,
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 				    struct ib_udata *ucore,
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 static void ib_uverbs_add_one(struct ib_device *device);
 static void ib_uverbs_remove_one(struct ib_device *device);
@@ -633,8 +631,6 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 						 hdr.in_words * 4,
 						 hdr.out_words * 4);
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
-
 	} else if (flags == IB_USER_VERBS_CMD_FLAG_EXTENDED) {
 		__u32 command;
 
@@ -701,7 +697,6 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf,
 
 		return written_count;
 	}
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 	return -ENOSYS;
 }
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 4be29fef66d6..1aad9b3e6bdd 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1691,11 +1691,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ibdev->ib_dev.create_flow	= mlx4_ib_create_flow;
 		ibdev->ib_dev.destroy_flow	= mlx4_ib_destroy_flow;
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 		ibdev->ib_dev.uverbs_ex_cmd_mask	|=
 			(1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
 			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 	}
 
 	mlx4_ib_alloc_eqs(dev, ibdev);
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 6ace125e1af6..cbfdd4ca9510 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -89,12 +89,10 @@ enum {
 	IB_USER_VERBS_CMD_OPEN_QP,
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 enum {
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 /*
  * Make sure that all structs defined in this file remain laid out so
@@ -137,14 +135,12 @@ struct ib_uverbs_cmd_hdr {
 	__u16 out_words;
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 struct ib_uverbs_ex_cmd_hdr {
 	__u64 response;
 	__u16 provider_in_words;
 	__u16 provider_out_words;
 	__u32 cmd_hdr_reserved;
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 struct ib_uverbs_get_context {
 	__u64 response;
@@ -707,7 +703,6 @@ struct ib_uverbs_detach_mcast {
 	__u64 driver_data[0];
 };
 
-#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING
 struct ib_uverbs_flow_spec_hdr {
 	__u32 type;
 	__u16 size;
@@ -802,7 +797,6 @@ struct ib_uverbs_destroy_flow  {
 	__u32 comp_mask;
 	__u32 flow_handle;
 };
-#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */
 
 struct ib_uverbs_create_srq {
 	__u64 response;
-- 
cgit 


From 8d17fb4455eadbf2642e34e5584d0b0de64d33a8 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Fri, 15 Nov 2013 00:02:54 -0800
Subject: drm/ttm: Allow execbuf util reserves without ticket

If no reservation ticket is given to the execbuf reservation utilities,
try reservation with non-blocking semantics.
This is intended for eviction paths that use the execbuf reservation
utilities for convenience rather than for deadlock avoidance.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
---
 drivers/gpu/drm/ttm/ttm_execbuf_util.c | 32 +++++++++++++++++++-------------
 include/drm/ttm/ttm_execbuf_util.h     |  3 ++-
 2 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 6c911789ae5c..479e9418e3d7 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -32,8 +32,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 
-static void ttm_eu_backoff_reservation_locked(struct list_head *list,
-					      struct ww_acquire_ctx *ticket)
+static void ttm_eu_backoff_reservation_locked(struct list_head *list)
 {
 	struct ttm_validate_buffer *entry;
 
@@ -93,8 +92,9 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
 	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list, ticket);
-	ww_acquire_fini(ticket);
+	ttm_eu_backoff_reservation_locked(list);
+	if (ticket)
+		ww_acquire_fini(ticket);
 	spin_unlock(&glob->lru_lock);
 }
 EXPORT_SYMBOL(ttm_eu_backoff_reservation);
@@ -130,7 +130,8 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
 
-	ww_acquire_init(ticket, &reservation_ww_class);
+	if (ticket)
+		ww_acquire_init(ticket, &reservation_ww_class);
 retry:
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
@@ -139,16 +140,17 @@ retry:
 		if (entry->reserved)
 			continue;
 
-
-		ret = ttm_bo_reserve_nolru(bo, true, false, true, ticket);
+		ret = ttm_bo_reserve_nolru(bo, true, (ticket == NULL), true,
+					   ticket);
 
 		if (ret == -EDEADLK) {
 			/* uh oh, we lost out, drop every reservation and try
 			 * to only reserve this buffer, then start over if
 			 * this succeeds.
 			 */
+			BUG_ON(ticket == NULL);
 			spin_lock(&glob->lru_lock);
-			ttm_eu_backoff_reservation_locked(list, ticket);
+			ttm_eu_backoff_reservation_locked(list);
 			spin_unlock(&glob->lru_lock);
 			ttm_eu_list_ref_sub(list);
 			ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
@@ -175,7 +177,8 @@ retry:
 		}
 	}
 
-	ww_acquire_done(ticket);
+	if (ticket)
+		ww_acquire_done(ticket);
 	spin_lock(&glob->lru_lock);
 	ttm_eu_del_from_lru_locked(list);
 	spin_unlock(&glob->lru_lock);
@@ -184,12 +187,14 @@ retry:
 
 err:
 	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list, ticket);
+	ttm_eu_backoff_reservation_locked(list);
 	spin_unlock(&glob->lru_lock);
 	ttm_eu_list_ref_sub(list);
 err_fini:
-	ww_acquire_done(ticket);
-	ww_acquire_fini(ticket);
+	if (ticket) {
+		ww_acquire_done(ticket);
+		ww_acquire_fini(ticket);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(ttm_eu_reserve_buffers);
@@ -224,7 +229,8 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 	}
 	spin_unlock(&bdev->fence_lock);
 	spin_unlock(&glob->lru_lock);
-	ww_acquire_fini(ticket);
+	if (ticket)
+		ww_acquire_fini(ticket);
 
 	list_for_each_entry(entry, list, head) {
 		if (entry->old_sync_obj)
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index ec8a1d306510..16db7d01a336 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -70,7 +70,8 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 /**
  * function ttm_eu_reserve_buffers
  *
- * @ticket:  [out] ww_acquire_ctx returned by call.
+ * @ticket:  [out] ww_acquire_ctx filled in by call, or NULL if only
+ *           non-blocking reserves should be tried.
  * @list:    thread private list of ttm_validate_buffer structs.
  *
  * Tries to reserve bos pointed to by the list entries for validation.
-- 
cgit 


From 65981f7681abdf92b25942222b629b9c512d0705 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Wed, 13 Nov 2013 01:48:31 -0800
Subject: drm/ttm: Add a minimal prime implementation for ttm base objects

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
---
 drivers/gpu/drm/ttm/ttm_object.c | 254 ++++++++++++++++++++++++++++++++++++++-
 include/drm/ttm/ttm_object.h     |  61 +++++++++-
 2 files changed, 307 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index a868176c258a..6fe7b92a82d1 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -1,6 +1,6 @@
 /**************************************************************************
  *
- * Copyright (c) 2009 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2013 VMware, Inc., Palo Alto, CA., USA
  * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
@@ -26,6 +26,12 @@
  **************************************************************************/
 /*
  * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
+ *
+ * While no substantial code is shared, the prime code is inspired by
+ * drm_prime.c, with
+ * Authors:
+ *      Dave Airlie <airlied@redhat.com>
+ *      Rob Clark <rob.clark@linaro.org>
  */
 /** @file ttm_ref_object.c
  *
@@ -34,6 +40,7 @@
  * and release on file close.
  */
 
+
 /**
  * struct ttm_object_file
  *
@@ -84,6 +91,9 @@ struct ttm_object_device {
 	struct drm_open_hash object_hash;
 	atomic_t object_count;
 	struct ttm_mem_global *mem_glob;
+	struct dma_buf_ops ops;
+	void (*dmabuf_release)(struct dma_buf *dma_buf);
+	size_t dma_buf_size;
 };
 
 /**
@@ -116,6 +126,8 @@ struct ttm_ref_object {
 	struct ttm_object_file *tfile;
 };
 
+static void ttm_prime_dmabuf_release(struct dma_buf *dma_buf);
+
 static inline struct ttm_object_file *
 ttm_object_file_ref(struct ttm_object_file *tfile)
 {
@@ -416,9 +428,10 @@ out_err:
 }
 EXPORT_SYMBOL(ttm_object_file_init);
 
-struct ttm_object_device *ttm_object_device_init(struct ttm_mem_global
-						 *mem_glob,
-						 unsigned int hash_order)
+struct ttm_object_device *
+ttm_object_device_init(struct ttm_mem_global *mem_glob,
+		       unsigned int hash_order,
+		       const struct dma_buf_ops *ops)
 {
 	struct ttm_object_device *tdev = kmalloc(sizeof(*tdev), GFP_KERNEL);
 	int ret;
@@ -430,10 +443,17 @@ struct ttm_object_device *ttm_object_device_init(struct ttm_mem_global
 	spin_lock_init(&tdev->object_lock);
 	atomic_set(&tdev->object_count, 0);
 	ret = drm_ht_create(&tdev->object_hash, hash_order);
+	if (ret != 0)
+		goto out_no_object_hash;
 
-	if (likely(ret == 0))
-		return tdev;
+	tdev->ops = *ops;
+	tdev->dmabuf_release = tdev->ops.release;
+	tdev->ops.release = ttm_prime_dmabuf_release;
+	tdev->dma_buf_size = ttm_round_pot(sizeof(struct dma_buf)) +
+		ttm_round_pot(sizeof(struct file));
+	return tdev;
 
+out_no_object_hash:
 	kfree(tdev);
 	return NULL;
 }
@@ -452,3 +472,225 @@ void ttm_object_device_release(struct ttm_object_device **p_tdev)
 	kfree(tdev);
 }
 EXPORT_SYMBOL(ttm_object_device_release);
+
+/**
+ * get_dma_buf_unless_doomed - get a dma_buf reference if possible.
+ *
+ * @dma_buf: Non-refcounted pointer to a struct dma-buf.
+ *
+ * Obtain a file reference from a lookup structure that doesn't refcount
+ * the file, but synchronizes with its release method to make sure it has
+ * not been freed yet. See for example kref_get_unless_zero documentation.
+ * Returns true if refcounting succeeds, false otherwise.
+ *
+ * Nobody really wants this as a public API yet, so let it mature here
+ * for some time...
+ */
+static bool __must_check get_dma_buf_unless_doomed(struct dma_buf *dmabuf)
+{
+	return atomic_long_inc_not_zero(&dmabuf->file->f_count) != 0L;
+}
+
+/**
+ * ttm_prime_refcount_release - refcount release method for a prime object.
+ *
+ * @p_base: Pointer to ttm_base_object pointer.
+ *
+ * This is a wrapper that calls the refcount_release founction of the
+ * underlying object. At the same time it cleans up the prime object.
+ * This function is called when all references to the base object we
+ * derive from are gone.
+ */
+static void ttm_prime_refcount_release(struct ttm_base_object **p_base)
+{
+	struct ttm_base_object *base = *p_base;
+	struct ttm_prime_object *prime;
+
+	*p_base = NULL;
+	prime = container_of(base, struct ttm_prime_object, base);
+	BUG_ON(prime->dma_buf != NULL);
+	mutex_destroy(&prime->mutex);
+	if (prime->refcount_release)
+		prime->refcount_release(&base);
+}
+
+/**
+ * ttm_prime_dmabuf_release - Release method for the dma-bufs we export
+ *
+ * @dma_buf:
+ *
+ * This function first calls the dma_buf release method the driver
+ * provides. Then it cleans up our dma_buf pointer used for lookup,
+ * and finally releases the reference the dma_buf has on our base
+ * object.
+ */
+static void ttm_prime_dmabuf_release(struct dma_buf *dma_buf)
+{
+	struct ttm_prime_object *prime =
+		(struct ttm_prime_object *) dma_buf->priv;
+	struct ttm_base_object *base = &prime->base;
+	struct ttm_object_device *tdev = base->tfile->tdev;
+
+	if (tdev->dmabuf_release)
+		tdev->dmabuf_release(dma_buf);
+	mutex_lock(&prime->mutex);
+	if (prime->dma_buf == dma_buf)
+		prime->dma_buf = NULL;
+	mutex_unlock(&prime->mutex);
+	ttm_mem_global_free(tdev->mem_glob, tdev->dma_buf_size);
+	ttm_base_object_unref(&base);
+}
+
+/**
+ * ttm_prime_fd_to_handle - Get a base object handle from a prime fd
+ *
+ * @tfile: A struct ttm_object_file identifying the caller.
+ * @fd: The prime / dmabuf fd.
+ * @handle: The returned handle.
+ *
+ * This function returns a handle to an object that previously exported
+ * a dma-buf. Note that we don't handle imports yet, because we simply
+ * have no consumers of that implementation.
+ */
+int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
+			   int fd, u32 *handle)
+{
+	struct ttm_object_device *tdev = tfile->tdev;
+	struct dma_buf *dma_buf;
+	struct ttm_prime_object *prime;
+	struct ttm_base_object *base;
+	int ret;
+
+	dma_buf = dma_buf_get(fd);
+	if (IS_ERR(dma_buf))
+		return PTR_ERR(dma_buf);
+
+	if (dma_buf->ops != &tdev->ops)
+		return -ENOSYS;
+
+	prime = (struct ttm_prime_object *) dma_buf->priv;
+	base = &prime->base;
+	*handle = base->hash.key;
+	ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL);
+
+	dma_buf_put(dma_buf);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ttm_prime_fd_to_handle);
+
+/**
+ * ttm_prime_handle_to_fd - Return a dma_buf fd from a ttm prime object
+ *
+ * @tfile: Struct ttm_object_file identifying the caller.
+ * @handle: Handle to the object we're exporting from.
+ * @flags: flags for dma-buf creation. We just pass them on.
+ * @prime_fd: The returned file descriptor.
+ *
+ */
+int ttm_prime_handle_to_fd(struct ttm_object_file *tfile,
+			   uint32_t handle, uint32_t flags,
+			   int *prime_fd)
+{
+	struct ttm_object_device *tdev = tfile->tdev;
+	struct ttm_base_object *base;
+	struct dma_buf *dma_buf;
+	struct ttm_prime_object *prime;
+	int ret;
+
+	base = ttm_base_object_lookup(tfile, handle);
+	if (unlikely(base == NULL ||
+		     base->object_type != ttm_prime_type)) {
+		ret = -ENOENT;
+		goto out_unref;
+	}
+
+	prime = container_of(base, struct ttm_prime_object, base);
+	if (unlikely(!base->shareable)) {
+		ret = -EPERM;
+		goto out_unref;
+	}
+
+	ret = mutex_lock_interruptible(&prime->mutex);
+	if (unlikely(ret != 0)) {
+		ret = -ERESTARTSYS;
+		goto out_unref;
+	}
+
+	dma_buf = prime->dma_buf;
+	if (!dma_buf || !get_dma_buf_unless_doomed(dma_buf)) {
+
+		/*
+		 * Need to create a new dma_buf, with memory accounting.
+		 */
+		ret = ttm_mem_global_alloc(tdev->mem_glob, tdev->dma_buf_size,
+					   false, true);
+		if (unlikely(ret != 0)) {
+			mutex_unlock(&prime->mutex);
+			goto out_unref;
+		}
+
+		dma_buf = dma_buf_export(prime, &tdev->ops,
+					 prime->size, flags);
+		if (IS_ERR(dma_buf)) {
+			ret = PTR_ERR(dma_buf);
+			ttm_mem_global_free(tdev->mem_glob,
+					    tdev->dma_buf_size);
+			mutex_unlock(&prime->mutex);
+			goto out_unref;
+		}
+
+		/*
+		 * dma_buf has taken the base object reference
+		 */
+		base = NULL;
+		prime->dma_buf = dma_buf;
+	}
+	mutex_unlock(&prime->mutex);
+
+	ret = dma_buf_fd(dma_buf, flags);
+	if (ret >= 0) {
+		*prime_fd = ret;
+		ret = 0;
+	} else
+		dma_buf_put(dma_buf);
+
+out_unref:
+	if (base)
+		ttm_base_object_unref(&base);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ttm_prime_handle_to_fd);
+
+/**
+ * ttm_prime_object_init - Initialize a ttm_prime_object
+ *
+ * @tfile: struct ttm_object_file identifying the caller
+ * @size: The size of the dma_bufs we export.
+ * @prime: The object to be initialized.
+ * @shareable: See ttm_base_object_init
+ * @type: See ttm_base_object_init
+ * @refcount_release: See ttm_base_object_init
+ * @ref_obj_release: See ttm_base_object_init
+ *
+ * Initializes an object which is compatible with the drm_prime model
+ * for data sharing between processes and devices.
+ */
+int ttm_prime_object_init(struct ttm_object_file *tfile, size_t size,
+			  struct ttm_prime_object *prime, bool shareable,
+			  enum ttm_object_type type,
+			  void (*refcount_release) (struct ttm_base_object **),
+			  void (*ref_obj_release) (struct ttm_base_object *,
+						   enum ttm_ref_type ref_type))
+{
+	mutex_init(&prime->mutex);
+	prime->size = PAGE_ALIGN(size);
+	prime->real_type = type;
+	prime->dma_buf = NULL;
+	prime->refcount_release = refcount_release;
+	return ttm_base_object_init(tfile, &prime->base, shareable,
+				    ttm_prime_type,
+				    ttm_prime_refcount_release,
+				    ref_obj_release);
+}
+EXPORT_SYMBOL(ttm_prime_object_init);
diff --git a/include/drm/ttm/ttm_object.h b/include/drm/ttm/ttm_object.h
index fc0cf0649901..58b029894eb3 100644
--- a/include/drm/ttm/ttm_object.h
+++ b/include/drm/ttm/ttm_object.h
@@ -41,6 +41,7 @@
 #include <drm/drm_hashtab.h>
 #include <linux/kref.h>
 #include <linux/rcupdate.h>
+#include <linux/dma-buf.h>
 #include <ttm/ttm_memory.h>
 
 /**
@@ -77,6 +78,7 @@ enum ttm_object_type {
 	ttm_fence_type,
 	ttm_buffer_type,
 	ttm_lock_type,
+	ttm_prime_type,
 	ttm_driver_type0 = 256,
 	ttm_driver_type1,
 	ttm_driver_type2,
@@ -132,6 +134,30 @@ struct ttm_base_object {
 				 enum ttm_ref_type ref_type);
 };
 
+
+/**
+ * struct ttm_prime_object - Modified base object that is prime-aware
+ *
+ * @base: struct ttm_base_object that we derive from
+ * @mutex: Mutex protecting the @dma_buf member.
+ * @size: Size of the dma_buf associated with this object
+ * @real_type: Type of the underlying object. Needed since we're setting
+ * the value of @base::object_type to ttm_prime_type
+ * @dma_buf: Non ref-coutned pointer to a struct dma_buf created from this
+ * object.
+ * @refcount_release: The underlying object's release method. Needed since
+ * we set @base::refcount_release to our own release method.
+ */
+
+struct ttm_prime_object {
+	struct ttm_base_object base;
+	struct mutex mutex;
+	size_t size;
+	enum ttm_object_type real_type;
+	struct dma_buf *dma_buf;
+	void (*refcount_release) (struct ttm_base_object **);
+};
+
 /**
  * ttm_base_object_init
  *
@@ -248,14 +274,18 @@ extern void ttm_object_file_release(struct ttm_object_file **p_tfile);
 /**
  * ttm_object device init - initialize a struct ttm_object_device
  *
+ * @mem_glob: struct ttm_mem_global for memory accounting.
  * @hash_order: Order of hash table used to hash the base objects.
+ * @ops: DMA buf ops for prime objects of this device.
  *
  * This function is typically called on device initialization to prepare
  * data structures needed for ttm base and ref objects.
  */
 
-extern struct ttm_object_device *ttm_object_device_init
-    (struct ttm_mem_global *mem_glob, unsigned int hash_order);
+extern struct ttm_object_device *
+ttm_object_device_init(struct ttm_mem_global *mem_glob,
+		       unsigned int hash_order,
+		       const struct dma_buf_ops *ops);
 
 /**
  * ttm_object_device_release - release data held by a ttm_object_device
@@ -272,4 +302,31 @@ extern void ttm_object_device_release(struct ttm_object_device **p_tdev);
 
 #define ttm_base_object_kfree(__object, __base)\
 	kfree_rcu(__object, __base.rhead)
+
+extern int ttm_prime_object_init(struct ttm_object_file *tfile,
+				 size_t size,
+				 struct ttm_prime_object *prime,
+				 bool shareable,
+				 enum ttm_object_type type,
+				 void (*refcount_release)
+				 (struct ttm_base_object **),
+				 void (*ref_obj_release)
+				 (struct ttm_base_object *,
+				  enum ttm_ref_type ref_type));
+
+static inline enum ttm_object_type
+ttm_base_object_type(struct ttm_base_object *base)
+{
+	return (base->object_type == ttm_prime_type) ?
+		container_of(base, struct ttm_prime_object, base)->real_type :
+		base->object_type;
+}
+extern int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
+				  int fd, u32 *handle);
+extern int ttm_prime_handle_to_fd(struct ttm_object_file *tfile,
+				  uint32_t handle, uint32_t flags,
+				  int *prime_fd);
+
+#define ttm_prime_object_kfree(__obj, __prime)		\
+	kfree_rcu(__obj, __prime.base.rhead)
 #endif
-- 
cgit 


From 32f79a8a82b2ff6f1828b258da214869adc2a28c Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Mon, 18 Nov 2013 18:26:00 +0900
Subject: drm/radeon/cik: Add macrotile mode array query
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is required to properly calculate the tiling parameters
in userspace.

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/cik.c        | 3 +++
 drivers/gpu/drm/radeon/radeon.h     | 1 +
 drivers/gpu/drm/radeon/radeon_drv.c | 3 ++-
 drivers/gpu/drm/radeon/radeon_kms.c | 9 +++++++++
 include/uapi/drm/radeon_drm.h       | 2 ++
 5 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 08aa58ef8d0a..b43a3a3c9067 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -2427,6 +2427,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 4) {
@@ -2773,6 +2774,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 2) {
@@ -2990,6 +2992,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4970ac0ebc80..ecf2a3960c07 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1982,6 +1982,7 @@ struct cik_asic {
 
 	unsigned tile_config;
 	uint32_t tile_mode_array[32];
+	uint32_t macrotile_mode_array[16];
 };
 
 union radeon_asic_config {
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 1aee32213f66..9f5ff28864f6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -76,9 +76,10 @@
  *   2.32.0 - new info request for rings working
  *   2.33.0 - Add SI tiling mode array query
  *   2.34.0 - Add CIK tiling mode array query
+ *   2.35.0 - Add CIK macrotile mode array query
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	34
+#define KMS_DRIVER_MINOR	35
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index fa42c81da500..55d0b474bd37 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -449,6 +449,15 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			return -EINVAL;
 		}
 		break;
+	case RADEON_INFO_CIK_MACROTILE_MODE_ARRAY:
+		if (rdev->family >= CHIP_BONAIRE) {
+			value = rdev->config.cik.macrotile_mode_array;
+			value_size = sizeof(uint32_t)*16;
+		} else {
+			DRM_DEBUG_KMS("macrotile mode array is cik+ only!\n");
+			return -EINVAL;
+		}
+		break;
 	case RADEON_INFO_SI_CP_DMA_COMPUTE:
 		*value = 1;
 		break;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 46d41e8b0dcc..2f3f7ea8c77b 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -981,6 +981,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_SI_TILE_MODE_ARRAY	0x16
 /* query if CP DMA is supported on the compute ring */
 #define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
+/* CIK macrotile mode array */
+#define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY	0x18
 
 
 struct drm_radeon_info {
-- 
cgit 


From c0f8bd146a8b3e630798561c605f5669823107af Mon Sep 17 00:00:00 2001
From: Aurelien Jarno <aurelien@aurel32.net>
Date: Thu, 14 Nov 2013 15:16:19 +1100
Subject: UAPI: include <asm/byteorder.h> in linux/raid/md_p.h

linux/raid/md_p.h is using conditionals depending on endianess and fails
with an error if neither of __BIG_ENDIAN, __LITTLE_ENDIAN or
__BYTE_ORDER are defined, but it doesn't include any header which can
define these constants. This make this header unusable alone.

This patch adds a #include <asm/byteorder.h> at the beginning of this
header to make it usable alone. This is needed to compile klibc on MIPS.

Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: NeilBrown <neilb@suse.de>
---
 include/uapi/linux/raid/md_p.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index fe1a5406d4d9..f7cf7f351144 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -16,6 +16,7 @@
 #define _MD_P_H
 
 #include <linux/types.h>
+#include <asm/byteorder.h>
 
 /*
  * RAID superblock.
-- 
cgit 


From 94eddfbeaafa3e8040a2c47d370dea0e58e76941 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 19 Nov 2013 09:25:07 -0700
Subject: blk-mq: ensure that we set REQ_IO_STAT so diskstats work

If disk stats are enabled on the queue, a request needs to
be marked with REQ_IO_STAT for accounting to be active on
that request. This fixes an issue with virtio-blk not
showing up in /proc/diskstats after the conversion to
blk-mq.

Add QUEUE_FLAG_MQ_DEFAULT, setting stats and same cpu-group
completion on by default.

Reported-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         | 12 ++++++++----
 include/linux/blkdev.h |  3 +++
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 862f458d4760..32593dba4684 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -171,9 +171,12 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-static void blk_mq_rq_ctx_init(struct blk_mq_ctx *ctx, struct request *rq,
-			       unsigned int rw_flags)
+static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			       struct request *rq, unsigned int rw_flags)
 {
+	if (blk_queue_io_stat(q))
+		rw_flags |= REQ_IO_STAT;
+
 	rq->mq_ctx = ctx;
 	rq->cmd_flags = rw_flags;
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
@@ -197,7 +200,7 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 
 		rq = __blk_mq_alloc_request(hctx, gfp & ~__GFP_WAIT, reserved);
 		if (rq) {
-			blk_mq_rq_ctx_init(ctx, rq, rw);
+			blk_mq_rq_ctx_init(q, ctx, rq, rw);
 			break;
 		} else if (!(gfp & __GFP_WAIT))
 			break;
@@ -921,7 +924,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
-		blk_mq_rq_ctx_init(ctx, rq, rw);
+		blk_mq_rq_ctx_init(q, ctx, rq, rw);
 	else {
 		blk_mq_put_ctx(ctx);
 		trace_block_sleeprq(q, bio, rw);
@@ -1377,6 +1380,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	q->queue_hw_ctx = hctxs;
 
 	q->mq_ops = reg->ops;
+	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
 	blk_queue_make_request(q, blk_mq_make_request);
 	blk_queue_rq_timed_out(q, reg->ops->timeout);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f26ec20f6354..1b135d49b279 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -505,6 +505,9 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
+#define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_SAME_COMP))
+
 static inline void queue_lockdep_assert_held(struct request_queue *q)
 {
 	if (q->queue_lock)
-- 
cgit 


From c53ed7423619b4e8108914a9f31b426dd58ad591 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:31 +0100
Subject: genetlink: only pass array to genl_register_family_with_ops()

As suggested by David Miller, make genl_register_family_with_ops()
a macro and pass only the array, evaluating ARRAY_SIZE() in the
macro, this is a little safer.

The openvswitch has some indirection, assing ops/n_ops directly in
that code. This might ultimately just assign the pointers in the
family initializations, saving the struct genl_family_and_ops and
code (once mcast groups are handled differently.)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c               |  3 +--
 drivers/net/wireless/mac80211_hwsim.c |  3 +--
 fs/dlm/netlink.c                      | 10 ++++++----
 include/linux/genl_magic_func.h       |  3 +--
 include/net/genetlink.h               |  8 ++++++--
 kernel/taskstats.c                    |  3 +--
 net/core/drop_monitor.c               |  3 +--
 net/hsr/hsr_netlink.c                 |  3 +--
 net/ieee802154/netlink.c              |  3 +--
 net/ipv4/tcp_metrics.c                |  3 +--
 net/irda/irnetlink.c                  |  3 +--
 net/l2tp/l2tp_netlink.c               |  7 +------
 net/netfilter/ipvs/ip_vs_ctl.c        |  2 +-
 net/netlabel/netlabel_cipso_v4.c      |  2 +-
 net/netlabel/netlabel_mgmt.c          |  2 +-
 net/netlabel/netlabel_unlabeled.c     |  2 +-
 net/netlink/genetlink.c               | 14 ++++++++------
 net/nfc/netlink.c                     |  3 +--
 net/openvswitch/datapath.c            |  5 +++--
 net/tipc/netlink.c                    | 11 ++++++-----
 net/wimax/stack.c                     |  4 ++--
 net/wireless/nl80211.c                |  3 +--
 22 files changed, 47 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6390254beb7d..f55758b0840e 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2699,8 +2699,7 @@ static int team_nl_init(void)
 {
 	int err;
 
-	err = genl_register_family_with_ops(&team_nl_family, team_nl_ops,
-					    ARRAY_SIZE(team_nl_ops));
+	err = genl_register_family_with_ops(&team_nl_family, team_nl_ops);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index cfc3fda79a2d..9df7bc91a26f 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2148,8 +2148,7 @@ static int hwsim_init_netlink(void)
 
 	printk(KERN_INFO "mac80211_hwsim: initializing netlink\n");
 
-	rc = genl_register_family_with_ops(&hwsim_genl_family,
-		hwsim_ops, ARRAY_SIZE(hwsim_ops));
+	rc = genl_register_family_with_ops(&hwsim_genl_family, hwsim_ops);
 	if (rc)
 		goto failure;
 
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index 60a327863b11..e7cfbaf8d0e2 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -74,14 +74,16 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static struct genl_ops dlm_nl_ops = {
-	.cmd		= DLM_CMD_HELLO,
-	.doit		= user_cmd,
+static struct genl_ops dlm_nl_ops[] = {
+	{
+		.cmd	= DLM_CMD_HELLO,
+		.doit	= user_cmd,
+	},
 };
 
 int __init dlm_netlink_init(void)
 {
-	return genl_register_family_with_ops(&family, &dlm_nl_ops, 1);
+	return genl_register_family_with_ops(&family, dlm_nl_ops);
 }
 
 void dlm_netlink_exit(void)
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 023bc346b877..47086030ab31 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -293,8 +293,7 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
 
 int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void)
 {
-	int err = genl_register_family_with_ops(&ZZZ_genl_family,
-		ZZZ_genl_ops, ARRAY_SIZE(ZZZ_genl_ops));
+	int err = genl_register_family_with_ops(&ZZZ_genl_family, ZZZ_genl_ops);
 	if (err)
 		return err;
 #undef GENL_mc_group
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index e96385d46b48..9bd52a4c5e17 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -152,8 +152,9 @@ static inline int genl_register_family(struct genl_family *family)
  *
  * Return 0 on success or a negative error code.
  */
-static inline int genl_register_family_with_ops(struct genl_family *family,
-	const struct genl_ops *ops, size_t n_ops)
+static inline int _genl_register_family_with_ops(struct genl_family *family,
+						 const struct genl_ops *ops,
+						 size_t n_ops)
 {
 	family->module = THIS_MODULE;
 	family->ops = ops;
@@ -161,6 +162,9 @@ static inline int genl_register_family_with_ops(struct genl_family *family,
 	return __genl_register_family(family);
 }
 
+#define genl_register_family_with_ops(family, ops)	\
+	_genl_register_family_with_ops((family), (ops), ARRAY_SIZE(ops))
+
 int genl_unregister_family(struct genl_family *family);
 int genl_register_mc_group(struct genl_family *family,
 			   struct genl_multicast_group *grp);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 76595cd9d211..13d2f7cd65db 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -703,8 +703,7 @@ static int __init taskstats_init(void)
 {
 	int rc;
 
-	rc = genl_register_family_with_ops(&family, taskstats_ops,
-					   ARRAY_SIZE(taskstats_ops));
+	rc = genl_register_family_with_ops(&family, taskstats_ops);
 	if (rc)
 		return rc;
 
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index f9fe2f22d20b..0efc5028ba9d 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -365,8 +365,7 @@ static int __init init_net_drop_monitor(void)
 	}
 
 	rc = genl_register_family_with_ops(&net_drop_monitor_family,
-					   dropmon_ops,
-					   ARRAY_SIZE(dropmon_ops));
+					   dropmon_ops);
 	if (rc) {
 		pr_err("Could not create drop monitor netlink family\n");
 		return rc;
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 3b9205d2afc4..f182260be76d 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -414,8 +414,7 @@ int __init hsr_netlink_init(void)
 	if (rc)
 		goto fail_rtnl_link_register;
 
-	rc = genl_register_family_with_ops(&hsr_genl_family, hsr_ops,
-					   ARRAY_SIZE(hsr_ops));
+	rc = genl_register_family_with_ops(&hsr_genl_family, hsr_ops);
 	if (rc)
 		goto fail_genl_register_family;
 
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 3ffcdbb56aab..1a81709a4717 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -129,8 +129,7 @@ int __init ieee802154_nl_init(void)
 {
 	int rc;
 
-	rc = genl_register_family_with_ops(&nl802154_family, ieee8021154_ops,
-					   ARRAY_SIZE(ieee8021154_ops));
+	rc = genl_register_family_with_ops(&nl802154_family, ieee8021154_ops);
 	if (rc)
 		return rc;
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 8c121b523eee..06493736fbc8 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1082,8 +1082,7 @@ void __init tcp_metrics_init(void)
 	if (ret < 0)
 		goto cleanup;
 	ret = genl_register_family_with_ops(&tcp_metrics_nl_family,
-					    tcp_metrics_nl_ops,
-					    ARRAY_SIZE(tcp_metrics_nl_ops));
+					    tcp_metrics_nl_ops);
 	if (ret < 0)
 		goto cleanup_subsys;
 	return;
diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c
index bf5d7d476dae..a37b81fe0479 100644
--- a/net/irda/irnetlink.c
+++ b/net/irda/irnetlink.c
@@ -149,8 +149,7 @@ static const struct genl_ops irda_nl_ops[] = {
 
 int irda_nl_register(void)
 {
-	return genl_register_family_with_ops(&irda_nl_family,
-		irda_nl_ops, ARRAY_SIZE(irda_nl_ops));
+	return genl_register_family_with_ops(&irda_nl_family, irda_nl_ops);
 }
 
 void irda_nl_unregister(void)
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 57db66e24f1f..4cfd722e9153 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -887,13 +887,8 @@ EXPORT_SYMBOL_GPL(l2tp_nl_unregister_ops);
 
 static int l2tp_nl_init(void)
 {
-	int err;
-
 	pr_info("L2TP netlink interface\n");
-	err = genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops,
-					    ARRAY_SIZE(l2tp_nl_ops));
-
-	return err;
+	return genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops);
 }
 
 static void l2tp_nl_cleanup(void)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index fc8a04ed8854..393498704691 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3666,7 +3666,7 @@ static const struct genl_ops ip_vs_genl_ops[] __read_mostly = {
 static int __init ip_vs_genl_register(void)
 {
 	return genl_register_family_with_ops(&ip_vs_genl_family,
-		ip_vs_genl_ops, ARRAY_SIZE(ip_vs_genl_ops));
+					     ip_vs_genl_ops);
 }
 
 static void ip_vs_genl_unregister(void)
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 706691739b99..69345cebe3a3 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -783,5 +783,5 @@ static const struct genl_ops netlbl_cipsov4_ops[] = {
 int __init netlbl_cipsov4_genl_init(void)
 {
 	return genl_register_family_with_ops(&netlbl_cipsov4_gnl_family,
-		netlbl_cipsov4_ops, ARRAY_SIZE(netlbl_cipsov4_ops));
+					     netlbl_cipsov4_ops);
 }
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index 7de6f660b80a..8ef83ee97c6a 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -779,5 +779,5 @@ static const struct genl_ops netlbl_mgmt_genl_ops[] = {
 int __init netlbl_mgmt_genl_init(void)
 {
 	return genl_register_family_with_ops(&netlbl_mgmt_gnl_family,
-		netlbl_mgmt_genl_ops, ARRAY_SIZE(netlbl_mgmt_genl_ops));
+					     netlbl_mgmt_genl_ops);
 }
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 76ee9252daa7..43817d73ccf9 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1397,7 +1397,7 @@ static const struct genl_ops netlbl_unlabel_genl_ops[] = {
 int __init netlbl_unlabel_genl_init(void)
 {
 	return genl_register_family_with_ops(&netlbl_unlabel_gnl_family,
-		netlbl_unlabel_genl_ops, ARRAY_SIZE(netlbl_unlabel_genl_ops));
+					     netlbl_unlabel_genl_ops);
 }
 
 /*
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index f54215d7b8f3..c68ce73619b5 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -906,11 +906,13 @@ static int genl_ctrl_event(int event, void *data)
 	return 0;
 }
 
-static struct genl_ops genl_ctrl_ops = {
-	.cmd		= CTRL_CMD_GETFAMILY,
-	.doit		= ctrl_getfamily,
-	.dumpit		= ctrl_dumpfamily,
-	.policy		= ctrl_policy,
+static struct genl_ops genl_ctrl_ops[] = {
+	{
+		.cmd		= CTRL_CMD_GETFAMILY,
+		.doit		= ctrl_getfamily,
+		.dumpit		= ctrl_dumpfamily,
+		.policy		= ctrl_policy,
+	},
 };
 
 static struct genl_multicast_group notify_grp = {
@@ -954,7 +956,7 @@ static int __init genl_init(void)
 	for (i = 0; i < GENL_FAM_TAB_SIZE; i++)
 		INIT_LIST_HEAD(&family_ht[i]);
 
-	err = genl_register_family_with_ops(&genl_ctrl, &genl_ctrl_ops, 1);
+	err = genl_register_family_with_ops(&genl_ctrl, genl_ctrl_ops);
 	if (err < 0)
 		goto problem;
 
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index f5585611c098..fe6760d328a0 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1536,8 +1536,7 @@ int __init nfc_genl_init(void)
 {
 	int rc;
 
-	rc = genl_register_family_with_ops(&nfc_genl_family, nfc_genl_ops,
-					   ARRAY_SIZE(nfc_genl_ops));
+	rc = genl_register_family_with_ops(&nfc_genl_family, nfc_genl_ops);
 	if (rc)
 		return rc;
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 91e1c927a465..8ec8b73033e0 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1817,8 +1817,9 @@ static int dp_register_genl(void)
 	for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
 		const struct genl_family_and_ops *f = &dp_genl_families[i];
 
-		err = genl_register_family_with_ops(f->family, f->ops,
-						    f->n_ops);
+		f->family->ops = f->ops;
+		f->family->n_ops = f->n_ops;
+		err = genl_register_family(f->family);
 		if (err)
 			goto error;
 		n_registered++;
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 8bcd4985d0fb..9f72a6376362 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -76,9 +76,11 @@ static struct genl_family tipc_genl_family = {
 	.maxattr	= 0,
 };
 
-static struct genl_ops tipc_genl_ops = {
-	.cmd		= TIPC_GENL_CMD,
-	.doit		= handle_cmd,
+static struct genl_ops tipc_genl_ops[] = {
+	{
+		.cmd		= TIPC_GENL_CMD,
+		.doit		= handle_cmd,
+	},
 };
 
 static int tipc_genl_family_registered;
@@ -87,8 +89,7 @@ int tipc_netlink_start(void)
 {
 	int res;
 
-	res = genl_register_family_with_ops(&tipc_genl_family,
-		&tipc_genl_ops, 1);
+	res = genl_register_family_with_ops(&tipc_genl_family, tipc_genl_ops);
 	if (res) {
 		pr_err("Failed to register netlink interface\n");
 		return res;
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 47170c9495f1..6328afe90319 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -597,8 +597,8 @@ int __init wimax_subsys_init(void)
 
 	snprintf(wimax_gnl_family.name, sizeof(wimax_gnl_family.name),
 		 "WiMAX");
-	result = genl_register_family_with_ops(&wimax_gnl_family, wimax_gnl_ops,
-					       ARRAY_SIZE(wimax_gnl_ops));
+	result = genl_register_family_with_ops(&wimax_gnl_family,
+					       wimax_gnl_ops);
 	if (unlikely(result < 0)) {
 		printk(KERN_ERR "cannot register generic netlink family: %d\n",
 		       result);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 58c43c8e149f..1b6c5dd4dccf 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11329,8 +11329,7 @@ int nl80211_init(void)
 {
 	int err;
 
-	err = genl_register_family_with_ops(&nl80211_fam,
-		nl80211_ops, ARRAY_SIZE(nl80211_ops));
+	err = genl_register_family_with_ops(&nl80211_fam, nl80211_ops);
 	if (err)
 		return err;
 
-- 
cgit 


From 2ecf7536b2787580616d23b6507005d930975ca0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:33 +0100
Subject: quota/genetlink: use proper genetlink multicast APIs

The quota code is abusing the genetlink API and is using
its family ID as the multicast group ID, which is invalid
and may belong to somebody else (and likely will.)

Make the quota code use the correct API, but since this
is already used as-is by userspace, reserve a family ID
for this code and also reserve that group ID to not break
userspace assumptions.

Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/quota/netlink.c             | 17 +++++++++++++++--
 include/uapi/linux/genetlink.h |  1 +
 net/netlink/genetlink.c        | 10 ++++++++--
 3 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index 16e8abb7709b..aa22fe03b76c 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -11,13 +11,23 @@
 
 /* Netlink family structure for quota */
 static struct genl_family quota_genl_family = {
-	.id = GENL_ID_GENERATE,
+	/*
+	 * Needed due to multicast group ID abuse - old code assumed
+	 * the family ID was also a valid multicast group ID (which
+	 * isn't true) and userspace might thus rely on it. Assign a
+	 * static ID for this group to make dealing with that easier.
+	 */
+	.id = GENL_ID_VFS_DQUOT,
 	.hdrsize = 0,
 	.name = "VFS_DQUOT",
 	.version = 1,
 	.maxattr = QUOTA_NL_A_MAX,
 };
 
+static struct genl_multicast_group quota_mcgrp = {
+	.name = "events",
+};
+
 /**
  * quota_send_warning - Send warning to userspace about exceeded quota
  * @type: The quota type: USRQQUOTA, GRPQUOTA,...
@@ -78,7 +88,7 @@ void quota_send_warning(struct kqid qid, dev_t dev,
 		goto attr_err_out;
 	genlmsg_end(skb, msg_head);
 
-	genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS);
+	genlmsg_multicast(skb, 0, quota_mcgrp.id, GFP_NOFS);
 	return;
 attr_err_out:
 	printk(KERN_ERR "VFS: Not enough space to compose quota message!\n");
@@ -92,6 +102,9 @@ static int __init quota_init(void)
 	if (genl_register_family(&quota_genl_family) != 0)
 		printk(KERN_ERR
 		       "VFS: Failed to create quota netlink interface.\n");
+	if (genl_register_mc_group(&quota_genl_family, &quota_mcgrp))
+		printk(KERN_ERR
+		       "VFS: Failed to register quota mcast group.\n");
 	return 0;
 };
 
diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index c880a417d8a9..1af72d8228e0 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -27,6 +27,7 @@ struct genlmsghdr {
  */
 #define GENL_ID_GENERATE	0
 #define GENL_ID_CTRL		NLMSG_MIN_TYPE
+#define GENL_ID_VFS_DQUOT	(NLMSG_MIN_TYPE + 1)
 
 /**************************************************************************
  * Controller
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 353909d46dda..bee91a7527a5 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -69,8 +69,11 @@ static struct list_head family_ht[GENL_FAM_TAB_SIZE];
  * abuses the API and thinks it can statically use group 1.
  * That group will typically conflict with other groups that
  * any proper users use.
+ * Bit 17 is marked as already used since the VFS quota code
+ * also abused this API and relied on family == group ID, we
+ * cater to that by giving it a static family and group ID.
  */
-static unsigned long mc_group_start = 0x3;
+static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_VFS_DQUOT);
 static unsigned long *mc_groups = &mc_group_start;
 static unsigned long mc_groups_longs = 1;
 
@@ -130,7 +133,8 @@ static u16 genl_generate_id(void)
 	int i;
 
 	for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) {
-		if (!genl_family_find_byid(id_gen_idx))
+		if (id_gen_idx != GENL_ID_VFS_DQUOT &&
+		    !genl_family_find_byid(id_gen_idx))
 			return id_gen_idx;
 		if (++id_gen_idx > GENL_MAX_ID)
 			id_gen_idx = GENL_MIN_ID;
@@ -169,6 +173,8 @@ int genl_register_mc_group(struct genl_family *family,
 		id = GENL_ID_CTRL;
 	else if (strcmp(family->name, "NET_DM") == 0)
 		id = 1;
+	else if (strcmp(family->name, "VFS_DQUOT") == 0)
+		id = GENL_ID_VFS_DQUOT;
 	else
 		id = find_first_zero_bit(mc_groups,
 					 mc_groups_longs * BITS_PER_LONG);
-- 
cgit 


From 06fb555a273dc8ef0d876f4e864ad11cfcea63e0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:35 +0100
Subject: genetlink: remove genl_unregister_mc_group()

There are no users of this API remaining, and we'll soon
change group registration to be static (like ops are now)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  2 --
 net/netlink/genetlink.c | 23 -----------------------
 2 files changed, 25 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 9bd52a4c5e17..067569d1bc99 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -168,8 +168,6 @@ static inline int _genl_register_family_with_ops(struct genl_family *family,
 int genl_unregister_family(struct genl_family *family);
 int genl_register_mc_group(struct genl_family *family,
 			   struct genl_multicast_group *grp);
-void genl_unregister_mc_group(struct genl_family *family,
-			      struct genl_multicast_group *grp);
 void genl_notify(struct sk_buff *skb, struct net *net, u32 portid,
 		 u32 group, struct nlmsghdr *nlh, gfp_t flags);
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index bee91a7527a5..6efb0e9036b5 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -265,29 +265,6 @@ static void __genl_unregister_mc_group(struct genl_family *family,
 	grp->family = NULL;
 }
 
-/**
- * genl_unregister_mc_group - unregister a multicast group
- *
- * Unregisters the specified multicast group and notifies userspace
- * about it. All current listeners on the group are removed.
- *
- * Note: It is not necessary to unregister all multicast groups before
- *       unregistering the family, unregistering the family will cause
- *       all assigned multicast groups to be unregistered automatically.
- *
- * @family: Generic netlink family the group belongs to.
- * @grp: The group to unregister, must have been registered successfully
- *	 previously.
- */
-void genl_unregister_mc_group(struct genl_family *family,
-			      struct genl_multicast_group *grp)
-{
-	genl_lock_all();
-	__genl_unregister_mc_group(family, grp);
-	genl_unlock_all();
-}
-EXPORT_SYMBOL(genl_unregister_mc_group);
-
 static void genl_unregister_mc_groups(struct genl_family *family)
 {
 	struct genl_multicast_group *grp, *tmp;
-- 
cgit 


From c2ebb908469d507ff400dad94efc755e6c799672 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:36 +0100
Subject: genetlink: remove family pointer from genl_multicast_group

There's no reason to have the family pointer there since it
can just be passed internally where needed, so remove it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  2 --
 net/netlink/genetlink.c | 38 ++++++++++++++++++--------------------
 2 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 067569d1bc99..d8a8b1fd96c4 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -13,10 +13,8 @@
  * @id: multicast group ID, assigned by the core, to use with
  *      genlmsg_multicast().
  * @list: list entry for linking
- * @family: pointer to family, need not be set before registering
  */
 struct genl_multicast_group {
-	struct genl_family	*family;	/* private */
 	struct list_head	list;		/* private */
 	char			name[GENL_NAMSIZ];
 	u32			id;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 6efb0e9036b5..e9ef640200b4 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -77,7 +77,8 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_VFS_DQUOT);
 static unsigned long *mc_groups = &mc_group_start;
 static unsigned long mc_groups_longs = 1;
 
-static int genl_ctrl_event(int event, void *data);
+static int genl_ctrl_event(int event, struct genl_family *family,
+			   struct genl_multicast_group *grp);
 
 static inline unsigned int genl_family_hash(unsigned int id)
 {
@@ -235,9 +236,8 @@ int genl_register_mc_group(struct genl_family *family,
 	grp->id = id;
 	set_bit(id, mc_groups);
 	list_add_tail(&grp->list, &family->mcast_groups);
-	grp->family = family;
 
-	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, grp);
+	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family, grp);
  out:
 	genl_unlock_all();
 	return err;
@@ -248,7 +248,6 @@ static void __genl_unregister_mc_group(struct genl_family *family,
 				       struct genl_multicast_group *grp)
 {
 	struct net *net;
-	BUG_ON(grp->family != family);
 
 	netlink_table_grab();
 	rcu_read_lock();
@@ -260,9 +259,8 @@ static void __genl_unregister_mc_group(struct genl_family *family,
 	if (grp->id != 1)
 		clear_bit(grp->id, mc_groups);
 	list_del(&grp->list);
-	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, grp);
+	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, grp);
 	grp->id = 0;
-	grp->family = NULL;
 }
 
 static void genl_unregister_mc_groups(struct genl_family *family)
@@ -364,7 +362,7 @@ int __genl_register_family(struct genl_family *family)
 	list_add_tail(&family->family_list, genl_family_chain(family->id));
 	genl_unlock_all();
 
-	genl_ctrl_event(CTRL_CMD_NEWFAMILY, family);
+	genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL);
 
 	return 0;
 
@@ -400,7 +398,7 @@ int genl_unregister_family(struct genl_family *family)
 		genl_unlock_all();
 
 		kfree(family->attrbuf);
-		genl_ctrl_event(CTRL_CMD_DELFAMILY, family);
+		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL);
 		return 0;
 	}
 
@@ -693,7 +691,8 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid,
+static int ctrl_fill_mcgrp_info(struct genl_family *family,
+				struct genl_multicast_group *grp, u32 portid,
 				u32 seq, u32 flags, struct sk_buff *skb,
 				u8 cmd)
 {
@@ -705,8 +704,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid,
 	if (hdr == NULL)
 		return -1;
 
-	if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name) ||
-	    nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id))
+	if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) ||
+	    nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id))
 		goto nla_put_failure;
 
 	nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
@@ -783,7 +782,8 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
 	return skb;
 }
 
-static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
+static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_family *family,
+					    struct genl_multicast_group *grp,
 					    u32 portid, int seq, u8 cmd)
 {
 	struct sk_buff *skb;
@@ -793,7 +793,7 @@ static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
 	if (skb == NULL)
 		return ERR_PTR(-ENOBUFS);
 
-	err = ctrl_fill_mcgrp_info(grp, portid, seq, 0, skb, cmd);
+	err = ctrl_fill_mcgrp_info(family, grp, portid, seq, 0, skb, cmd);
 	if (err < 0) {
 		nlmsg_free(skb);
 		return ERR_PTR(err);
@@ -855,11 +855,10 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static int genl_ctrl_event(int event, void *data)
+static int genl_ctrl_event(int event, struct genl_family *family,
+			   struct genl_multicast_group *grp)
 {
 	struct sk_buff *msg;
-	struct genl_family *family;
-	struct genl_multicast_group *grp;
 
 	/* genl is still initialising */
 	if (!init_net.genl_sock)
@@ -868,14 +867,13 @@ static int genl_ctrl_event(int event, void *data)
 	switch (event) {
 	case CTRL_CMD_NEWFAMILY:
 	case CTRL_CMD_DELFAMILY:
-		family = data;
+		WARN_ON(grp);
 		msg = ctrl_build_family_msg(family, 0, 0, event);
 		break;
 	case CTRL_CMD_NEWMCAST_GRP:
 	case CTRL_CMD_DELMCAST_GRP:
-		grp = data;
-		family = grp->family;
-		msg = ctrl_build_mcgrp_msg(data, 0, 0, event);
+		BUG_ON(!grp);
+		msg = ctrl_build_mcgrp_msg(family, grp, 0, 0, event);
 		break;
 	default:
 		return -EINVAL;
-- 
cgit 


From 62b68e99faa802352e9cb2ae91adecd8dfddf1b8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:37 +0100
Subject: genetlink: add and use genl_set_err()

Add a static inline to generic netlink to wrap netlink_set_err()
to make it easier to use here - use it in openvswitch (the only
generic netlink user of netlink_set_err()).

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h     | 14 ++++++++++++++
 net/openvswitch/datapath.c  |  8 ++++----
 net/openvswitch/dp_notify.c |  6 +++---
 3 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index d8a8b1fd96c4..11ac77f6180c 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -351,5 +351,19 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags)
 	return nlmsg_new(genlmsg_total_size(payload), flags);
 }
 
+/**
+ * genl_set_err - report error to genetlink broadcast listeners
+ * @net: the network namespace to report the error to
+ * @portid: the PORTID of a process that we want to skip (if any)
+ * @group: the broadcast group that will notice the error
+ * @code: error code, must be negative (as usual in kernelspace)
+ *
+ * This function returns the number of broadcast listeners that have set the
+ * NETLINK_RECV_NO_ENOBUFS socket option.
+ */
+static inline int genl_set_err(struct net *net, u32 portid, u32 group, int code)
+{
+	return netlink_set_err(net->genl_sock, portid, group, code);
+}
 
 #endif	/* __NET_GENERIC_NETLINK_H */
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 8ec8b73033e0..3e2bb15fd717 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -879,8 +879,8 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 	if (!IS_ERR(reply))
 		ovs_notify(reply, info, &ovs_dp_flow_multicast_group);
 	else
-		netlink_set_err(sock_net(skb->sk)->genl_sock, 0,
-				ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
+		genl_set_err(sock_net(skb->sk), 0,
+			     ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
 	return 0;
 
 err_flow_free:
@@ -1326,8 +1326,8 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 				      info->snd_seq, OVS_DP_CMD_NEW);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
-		netlink_set_err(sock_net(skb->sk)->genl_sock, 0,
-				ovs_dp_datapath_multicast_group.id, err);
+		genl_set_err(sock_net(skb->sk), 0,
+			     ovs_dp_datapath_multicast_group.id, err);
 		err = 0;
 		goto unlock;
 	}
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index 5c2dab276109..3d55ead6095c 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -34,9 +34,9 @@ static void dp_detach_port_notify(struct vport *vport)
 					  OVS_VPORT_CMD_DEL);
 	ovs_dp_detach_port(vport);
 	if (IS_ERR(notify)) {
-		netlink_set_err(ovs_dp_get_net(dp)->genl_sock, 0,
-				ovs_dp_vport_multicast_group.id,
-				PTR_ERR(notify));
+		genl_set_err(ovs_dp_get_net(dp), 0,
+			     ovs_dp_vport_multicast_group.id,
+			     PTR_ERR(notify));
 		return;
 	}
 
-- 
cgit 


From 68eb55031da7c967d954e5f9415cd05f4abdb692 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:38 +0100
Subject: genetlink: pass family to functions using groups

This doesn't really change anything, but prepares for the
next patch that will change the APIs to pass the group ID
within the family, rather than the global group ID.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/acpi/event.c            |  3 +-
 drivers/net/team/team.c         |  5 +--
 drivers/scsi/pmcraid.c          |  3 +-
 drivers/thermal/thermal_core.c  |  3 +-
 fs/quota/netlink.c              |  2 +-
 include/linux/genl_magic_func.h |  3 +-
 include/net/genetlink.h         | 22 +++++++++----
 net/core/drop_monitor.c         |  3 +-
 net/hsr/hsr_netlink.c           |  6 ++--
 net/ieee802154/netlink.c        |  2 +-
 net/netlink/genetlink.c         | 12 ++++---
 net/nfc/netlink.c               | 39 +++++++++++++++--------
 net/openvswitch/datapath.c      | 35 +++++++++++++--------
 net/openvswitch/datapath.h      |  1 +
 net/openvswitch/dp_notify.c     |  5 +--
 net/wimax/op-msg.c              |  3 +-
 net/wimax/stack.c               |  3 +-
 net/wireless/nl80211.c          | 70 ++++++++++++++++++++---------------------
 18 files changed, 133 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 8247fcdde079..68a8755202ec 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -146,7 +146,8 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 		return result;
 	}
 
-	genlmsg_multicast(skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&acpi_event_genl_family,
+			  skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC);
 	return 0;
 }
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index f55758b0840e..2721e29935a6 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2677,8 +2677,9 @@ static struct genl_multicast_group team_change_event_mcgrp = {
 static int team_nl_send_multicast(struct sk_buff *skb,
 				  struct team *team, u32 portid)
 {
-	return genlmsg_multicast_netns(dev_net(team->dev), skb, 0,
-				       team_change_event_mcgrp.id, GFP_KERNEL);
+	return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev),
+				       skb, 0, team_change_event_mcgrp.id,
+				       GFP_KERNEL);
 }
 
 static int team_nl_send_event_options_get(struct team *team,
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 1eb7b0280a45..2775441111ff 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -1512,7 +1512,8 @@ static int pmcraid_notify_aen(
 	}
 
 	result =
-		genlmsg_multicast(skb, 0, pmcraid_event_family.id, GFP_ATOMIC);
+		genlmsg_multicast(&pmcraid_event_family, skb, 0,
+				  pmcraid_event_family.id, GFP_ATOMIC);
 
 	/* If there are no listeners, genlmsg_multicast may return non-zero
 	 * value.
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 4962a6aaf295..2570a944fffc 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1675,7 +1675,8 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz,
 		return result;
 	}
 
-	result = genlmsg_multicast(skb, 0, thermal_event_mcgrp.id, GFP_ATOMIC);
+	result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
+				   thermal_event_mcgrp.id, GFP_ATOMIC);
 	if (result)
 		dev_err(&tz->device, "Failed to send netlink event:%d", result);
 
diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index aa22fe03b76c..a5b5eddf6603 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -88,7 +88,7 @@ void quota_send_warning(struct kqid qid, dev_t dev,
 		goto attr_err_out;
 	genlmsg_end(skb, msg_head);
 
-	genlmsg_multicast(skb, 0, quota_mcgrp.id, GFP_NOFS);
+	genlmsg_multicast(&quota_genl_family, skb, 0, quota_mcgrp.id, GFP_NOFS);
 	return;
 attr_err_out:
 	printk(KERN_ERR "VFS: Not enough space to compose quota message!\n");
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 47086030ab31..5b9b8ae6748b 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -286,7 +286,8 @@ static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
 		CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id;	\
 	if (!group_id)							\
 		return -EINVAL;						\
-	return genlmsg_multicast(skb, 0, group_id, flags);		\
+	return genlmsg_multicast(&ZZZ_genl_family, skb, 0,		\
+				 group_id, flags);			\
 }
 
 #include GENL_MAGIC_INCLUDE_FILE
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 11ac77f6180c..60aef0df386b 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -166,7 +166,8 @@ static inline int _genl_register_family_with_ops(struct genl_family *family,
 int genl_unregister_family(struct genl_family *family);
 int genl_register_mc_group(struct genl_family *family,
 			   struct genl_multicast_group *grp);
-void genl_notify(struct sk_buff *skb, struct net *net, u32 portid,
+void genl_notify(struct genl_family *family,
+		 struct sk_buff *skb, struct net *net, u32 portid,
 		 u32 group, struct nlmsghdr *nlh, gfp_t flags);
 
 void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
@@ -246,13 +247,15 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr)
 
 /**
  * genlmsg_multicast_netns - multicast a netlink message to a specific netns
+ * @family: the generic netlink family
  * @net: the net namespace
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
  * @flags: allocation flags
  */
-static inline int genlmsg_multicast_netns(struct net *net, struct sk_buff *skb,
+static inline int genlmsg_multicast_netns(struct genl_family *family,
+					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
 	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
@@ -260,19 +263,23 @@ static inline int genlmsg_multicast_netns(struct net *net, struct sk_buff *skb,
 
 /**
  * genlmsg_multicast - multicast a netlink message to the default netns
+ * @family: the generic netlink family
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
  * @flags: allocation flags
  */
-static inline int genlmsg_multicast(struct sk_buff *skb, u32 portid,
+static inline int genlmsg_multicast(struct genl_family *family,
+				    struct sk_buff *skb, u32 portid,
 				    unsigned int group, gfp_t flags)
 {
-	return genlmsg_multicast_netns(&init_net, skb, portid, group, flags);
+	return genlmsg_multicast_netns(family, &init_net, skb,
+				       portid, group, flags);
 }
 
 /**
  * genlmsg_multicast_allns - multicast a netlink message to all net namespaces
+ * @family: the generic netlink family
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
@@ -280,7 +287,8 @@ static inline int genlmsg_multicast(struct sk_buff *skb, u32 portid,
  *
  * This function must hold the RTNL or rcu_read_lock().
  */
-int genlmsg_multicast_allns(struct sk_buff *skb, u32 portid,
+int genlmsg_multicast_allns(struct genl_family *family,
+			    struct sk_buff *skb, u32 portid,
 			    unsigned int group, gfp_t flags);
 
 /**
@@ -353,6 +361,7 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags)
 
 /**
  * genl_set_err - report error to genetlink broadcast listeners
+ * @family: the generic netlink family
  * @net: the network namespace to report the error to
  * @portid: the PORTID of a process that we want to skip (if any)
  * @group: the broadcast group that will notice the error
@@ -361,7 +370,8 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags)
  * This function returns the number of broadcast listeners that have set the
  * NETLINK_RECV_NO_ENOBUFS socket option.
  */
-static inline int genl_set_err(struct net *net, u32 portid, u32 group, int code)
+static inline int genl_set_err(struct genl_family *family, struct net *net,
+			       u32 portid, u32 group, int code)
 {
 	return netlink_set_err(net->genl_sock, portid, group, code);
 }
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 46ee488c0015..1eab1dc48821 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -120,7 +120,8 @@ static void send_dm_alert(struct work_struct *work)
 	skb = reset_per_cpu_data(data);
 
 	if (skb)
-		genlmsg_multicast(skb, 0, dm_mcgrp.id, GFP_KERNEL);
+		genlmsg_multicast(&net_drop_monitor_family, skb, 0,
+				  dm_mcgrp.id, GFP_KERNEL);
 }
 
 /*
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 908e335dcdc9..0009416c08c2 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -129,7 +129,8 @@ void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN],
 		goto nla_put_failure;
 
 	genlmsg_end(skb, msg_head);
-	genlmsg_multicast(skb, 0, hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&hsr_genl_family, skb, 0,
+			  hsr_network_genl_mcgrp.id, GFP_ATOMIC);
 
 	return;
 
@@ -163,7 +164,8 @@ void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN])
 		goto nla_put_failure;
 
 	genlmsg_end(skb, msg_head);
-	genlmsg_multicast(skb, 0, hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&hsr_genl_family, skb, 0,
+			  hsr_network_genl_mcgrp.id, GFP_ATOMIC);
 
 	return;
 
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 1a81709a4717..5172f467a383 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -70,7 +70,7 @@ int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
 	if (genlmsg_end(msg, hdr) < 0)
 		goto out;
 
-	return genlmsg_multicast(msg, 0, group, GFP_ATOMIC);
+	return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC);
 out:
 	nlmsg_free(msg);
 	return -ENOBUFS;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index e9ef640200b4..36e3a86cacf6 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -883,11 +883,12 @@ static int genl_ctrl_event(int event, struct genl_family *family,
 		return PTR_ERR(msg);
 
 	if (!family->netnsok) {
-		genlmsg_multicast_netns(&init_net, msg, 0,
+		genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0,
 					GENL_ID_CTRL, GFP_KERNEL);
 	} else {
 		rcu_read_lock();
-		genlmsg_multicast_allns(msg, 0, GENL_ID_CTRL, GFP_ATOMIC);
+		genlmsg_multicast_allns(&genl_ctrl, msg, 0,
+					GENL_ID_CTRL, GFP_ATOMIC);
 		rcu_read_unlock();
 	}
 
@@ -993,14 +994,15 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 	return err;
 }
 
-int genlmsg_multicast_allns(struct sk_buff *skb, u32 portid, unsigned int group,
-			    gfp_t flags)
+int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
+			    u32 portid, unsigned int group, gfp_t flags)
 {
 	return genlmsg_mcast(skb, portid, group, flags);
 }
 EXPORT_SYMBOL(genlmsg_multicast_allns);
 
-void genl_notify(struct sk_buff *skb, struct net *net, u32 portid, u32 group,
+void genl_notify(struct genl_family *family,
+		 struct sk_buff *skb, struct net *net, u32 portid, u32 group,
 		 struct nlmsghdr *nlh, gfp_t flags)
 {
 	struct sock *sk = net->genl_sock;
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index fe6760d328a0..3092df313fb1 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -194,7 +194,8 @@ int nfc_genl_targets_found(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	return genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	return genlmsg_multicast(&nfc_genl_family, msg, 0,
+				 nfc_genl_event_mcgrp.id, GFP_ATOMIC);
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -223,7 +224,8 @@ int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -255,7 +257,8 @@ int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -285,7 +288,8 @@ int nfc_genl_tm_deactivated(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -318,7 +322,8 @@ int nfc_genl_device_added(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -348,7 +353,8 @@ int nfc_genl_device_removed(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -414,7 +420,8 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list)
 
 	genlmsg_end(msg, hdr);
 
-	return genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	return genlmsg_multicast(&nfc_genl_family, msg, 0,
+				 nfc_genl_event_mcgrp.id, GFP_ATOMIC);
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -448,7 +455,8 @@ int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -479,7 +487,8 @@ int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -600,7 +609,8 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx,
 
 	dev->dep_link_up = true;
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_ATOMIC);
 
 	return 0;
 
@@ -632,7 +642,8 @@ int nfc_genl_dep_link_down_event(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_ATOMIC);
 
 	return 0;
 
@@ -1137,7 +1148,8 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	return 0;
 
@@ -1308,7 +1320,8 @@ static void se_io_cb(void *context, u8 *apdu, size_t apdu_len, int err)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0,
+			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
 
 	kfree(ctx);
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 3e2bb15fd717..5c19846b1d2a 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -61,10 +61,11 @@
 
 int ovs_net_id __read_mostly;
 
-static void ovs_notify(struct sk_buff *skb, struct genl_info *info,
+static void ovs_notify(struct genl_family *family,
+		       struct sk_buff *skb, struct genl_info *info,
 		       struct genl_multicast_group *grp)
 {
-	genl_notify(skb, genl_info_net(info), info->snd_portid,
+	genl_notify(family, skb, genl_info_net(info), info->snd_portid,
 		    grp->id, info->nlhdr, GFP_KERNEL);
 }
 
@@ -877,9 +878,10 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 	ovs_unlock();
 
 	if (!IS_ERR(reply))
-		ovs_notify(reply, info, &ovs_dp_flow_multicast_group);
+		ovs_notify(&dp_flow_genl_family, reply, info,
+			   &ovs_dp_flow_multicast_group);
 	else
-		genl_set_err(sock_net(skb->sk), 0,
+		genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0,
 			     ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
 	return 0;
 
@@ -990,7 +992,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_flow_free(flow, true);
 	ovs_unlock();
 
-	ovs_notify(reply, info, &ovs_dp_flow_multicast_group);
+	ovs_notify(&dp_flow_genl_family, reply, info,
+		   &ovs_dp_flow_multicast_group);
 	return 0;
 unlock:
 	ovs_unlock();
@@ -1237,7 +1240,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	ovs_unlock();
 
-	ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info,
+		   &ovs_dp_datapath_multicast_group);
 	return 0;
 
 err_destroy_local_port:
@@ -1302,7 +1306,8 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	__dp_destroy(dp);
 	ovs_unlock();
 
-	ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info,
+		   &ovs_dp_datapath_multicast_group);
 
 	return 0;
 unlock:
@@ -1326,14 +1331,15 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 				      info->snd_seq, OVS_DP_CMD_NEW);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
-		genl_set_err(sock_net(skb->sk), 0,
+		genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0,
 			     ovs_dp_datapath_multicast_group.id, err);
 		err = 0;
 		goto unlock;
 	}
 
 	ovs_unlock();
-	ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info,
+		   &ovs_dp_datapath_multicast_group);
 
 	return 0;
 unlock:
@@ -1425,7 +1431,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
 };
 
-static struct genl_family dp_vport_genl_family = {
+struct genl_family dp_vport_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.hdrsize = sizeof(struct ovs_header),
 	.name = OVS_VPORT_FAMILY,
@@ -1595,7 +1601,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock;
 	}
 
-	ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info,
+		   &ovs_dp_vport_multicast_group);
 
 exit_unlock:
 	ovs_unlock();
@@ -1642,7 +1649,8 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	BUG_ON(err < 0);
 
 	ovs_unlock();
-	ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info,
+		   &ovs_dp_vport_multicast_group);
 	return 0;
 
 exit_free:
@@ -1679,7 +1687,8 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	err = 0;
 	ovs_dp_detach_port(vport);
 
-	ovs_notify(reply, info, &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info,
+		   &ovs_dp_vport_multicast_group);
 
 exit_unlock:
 	ovs_unlock();
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index d3d14a58aa91..4067ea41be28 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -177,6 +177,7 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
 }
 
 extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_family dp_vport_genl_family;
 extern struct genl_multicast_group ovs_dp_vport_multicast_group;
 
 void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index 3d55ead6095c..f4b66c84ea0b 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -34,13 +34,14 @@ static void dp_detach_port_notify(struct vport *vport)
 					  OVS_VPORT_CMD_DEL);
 	ovs_dp_detach_port(vport);
 	if (IS_ERR(notify)) {
-		genl_set_err(ovs_dp_get_net(dp), 0,
+		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
 			     ovs_dp_vport_multicast_group.id,
 			     PTR_ERR(notify));
 		return;
 	}
 
-	genlmsg_multicast_netns(ovs_dp_get_net(dp), notify, 0,
+	genlmsg_multicast_netns(&dp_vport_genl_family,
+				ovs_dp_get_net(dp), notify, 0,
 				ovs_dp_vport_multicast_group.id,
 				GFP_KERNEL);
 }
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
index ff19cbeaf607..f37dd3c5576d 100644
--- a/net/wimax/op-msg.c
+++ b/net/wimax/op-msg.c
@@ -279,7 +279,8 @@ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
 
 	d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
 	d_dump(2, dev, msg, size);
-	genlmsg_multicast(skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
+	genlmsg_multicast(&wimax_gnl_family, skb, 0,
+			  wimax_gnl_mcg.id, GFP_KERNEL);
 	d_printf(1, dev, "CTX: genl multicast done\n");
 	return 0;
 }
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 6328afe90319..18888748e699 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -177,7 +177,8 @@ int wimax_gnl_re_state_change_send(
 		goto out;
 	}
 	genlmsg_end(report_skb, header);
-	genlmsg_multicast(report_skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
+	genlmsg_multicast(&wimax_gnl_family, report_skb, 0,
+			  wimax_gnl_mcg.id, GFP_KERNEL);
 out:
 	d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
 		wimax_dev, report_skb, result);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1b6c5dd4dccf..f20edfd2e1f0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6868,7 +6868,7 @@ void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
 
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0,
 				nl80211_testmode_mcgrp.id, gfp);
 }
 EXPORT_SYMBOL(cfg80211_testmode_event);
@@ -9597,7 +9597,7 @@ void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev)
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_config_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9707,7 +9707,7 @@ void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_scan_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9726,7 +9726,7 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_scan_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9745,7 +9745,7 @@ void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_scan_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9764,7 +9764,7 @@ void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_scan_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9782,7 +9782,7 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_scan_mcgrp.id, GFP_KERNEL);
 }
 
@@ -9837,8 +9837,8 @@ void nl80211_send_reg_change_event(struct regulatory_request *request)
 	genlmsg_end(msg, hdr);
 
 	rcu_read_lock();
-	genlmsg_multicast_allns(msg, 0, nl80211_regulatory_mcgrp.id,
-				GFP_ATOMIC);
+	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
+				nl80211_regulatory_mcgrp.id, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return;
@@ -9873,7 +9873,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -9961,7 +9961,7 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10017,7 +10017,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10056,7 +10056,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10094,7 +10094,7 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, GFP_KERNEL);
 	return;
 
@@ -10128,7 +10128,7 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10169,7 +10169,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10208,7 +10208,7 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10261,8 +10261,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy,
 	genlmsg_end(msg, hdr);
 
 	rcu_read_lock();
-	genlmsg_multicast_allns(msg, 0, nl80211_regulatory_mcgrp.id,
-				GFP_ATOMIC);
+	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
+				nl80211_regulatory_mcgrp.id, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return;
@@ -10307,7 +10307,7 @@ static void nl80211_send_remain_on_chan_event(
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10362,7 +10362,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 		return;
 	}
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 }
 EXPORT_SYMBOL(cfg80211_new_sta);
@@ -10392,7 +10392,7 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10428,7 +10428,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10590,7 +10590,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10639,7 +10639,7 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10684,7 +10684,7 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10742,7 +10742,7 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10789,7 +10789,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10866,7 +10866,7 @@ void cfg80211_cqm_txe_notify(struct net_device *dev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10915,7 +10915,7 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -10962,7 +10962,7 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -11002,7 +11002,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -11154,7 +11154,7 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -11196,7 +11196,7 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, gfp);
 	return;
 
@@ -11279,7 +11279,7 @@ void cfg80211_ft_event(struct net_device *netdev,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				nl80211_mlme_mcgrp.id, GFP_KERNEL);
 }
 EXPORT_SYMBOL(cfg80211_ft_event);
-- 
cgit 


From 2a94fe48f32ccf7321450a2cc07f2b724a444e5b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 19 Nov 2013 15:19:39 +0100
Subject: genetlink: make multicast groups const, prevent abuse

Register generic netlink multicast groups as an array with
the family and give them contiguous group IDs. Then instead
of passing the global group ID to the various functions that
send messages, pass the ID relative to the family - for most
families that's just 0 because the only have one group.

This avoids the list_head and ID in each group, adding a new
field for the mcast group ID offset to the family.

At the same time, this allows us to prevent abusing groups
again like the quota and dropmon code did, since we can now
check that a family only uses a group it owns.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/acpi/event.c            |  26 ++--
 drivers/net/team/team.c         |  25 +---
 drivers/thermal/thermal_core.c  |  24 ++--
 fs/quota/netlink.c              |  15 +--
 include/linux/genl_magic_func.h |  49 +++----
 include/net/genetlink.h         |  48 ++++---
 net/core/drop_monitor.c         |  18 +--
 net/hsr/hsr_netlink.c           |  19 +--
 net/ieee802154/ieee802154.h     |   6 +-
 net/ieee802154/netlink.c        |  26 ++--
 net/ieee802154/nl-mac.c         |  22 +---
 net/netlink/genetlink.c         | 278 ++++++++++++++++++++++++----------------
 net/nfc/netlink.c               |  51 +++-----
 net/openvswitch/datapath.c      |  43 +++----
 net/openvswitch/dp_notify.c     |   6 +-
 net/wimax/op-msg.c              |   3 +-
 net/wimax/stack.c               |  21 ++-
 net/wimax/wimax-internal.h      |   1 -
 net/wireless/nl80211.c          | 129 ++++++++-----------
 19 files changed, 377 insertions(+), 433 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 68a8755202ec..aeb5aa6ce068 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -78,15 +78,17 @@ enum {
 #define ACPI_GENL_VERSION		0x01
 #define ACPI_GENL_MCAST_GROUP_NAME 	"acpi_mc_group"
 
+static const struct genl_multicast_group acpi_event_mcgrps[] = {
+	{ .name = ACPI_GENL_MCAST_GROUP_NAME, },
+};
+
 static struct genl_family acpi_event_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.name = ACPI_GENL_FAMILY_NAME,
 	.version = ACPI_GENL_VERSION,
 	.maxattr = ACPI_GENL_ATTR_MAX,
-};
-
-static struct genl_multicast_group acpi_event_mcgrp = {
-	.name = ACPI_GENL_MCAST_GROUP_NAME,
+	.mcgrps = acpi_event_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(acpi_event_mcgrps),
 };
 
 int acpi_bus_generate_netlink_event(const char *device_class,
@@ -146,8 +148,7 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 		return result;
 	}
 
-	genlmsg_multicast(&acpi_event_genl_family,
-			  skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&acpi_event_genl_family, skb, 0, 0, GFP_ATOMIC);
 	return 0;
 }
 
@@ -155,18 +156,7 @@ EXPORT_SYMBOL(acpi_bus_generate_netlink_event);
 
 static int acpi_event_genetlink_init(void)
 {
-	int result;
-
-	result = genl_register_family(&acpi_event_genl_family);
-	if (result)
-		return result;
-
-	result = genl_register_mc_group(&acpi_event_genl_family,
-					&acpi_event_mcgrp);
-	if (result)
-		genl_unregister_family(&acpi_event_genl_family);
-
-	return result;
+	return genl_register_family(&acpi_event_genl_family);
 }
 
 #else
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2721e29935a6..0715de50b3dc 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2670,16 +2670,15 @@ static const struct genl_ops team_nl_ops[] = {
 	},
 };
 
-static struct genl_multicast_group team_change_event_mcgrp = {
-	.name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME,
+static const struct genl_multicast_group team_nl_mcgrps[] = {
+	{ .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, },
 };
 
 static int team_nl_send_multicast(struct sk_buff *skb,
 				  struct team *team, u32 portid)
 {
 	return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev),
-				       skb, 0, team_change_event_mcgrp.id,
-				       GFP_KERNEL);
+				       skb, 0, 0, GFP_KERNEL);
 }
 
 static int team_nl_send_event_options_get(struct team *team,
@@ -2698,22 +2697,8 @@ static int team_nl_send_event_port_get(struct team *team,
 
 static int team_nl_init(void)
 {
-	int err;
-
-	err = genl_register_family_with_ops(&team_nl_family, team_nl_ops);
-	if (err)
-		return err;
-
-	err = genl_register_mc_group(&team_nl_family, &team_change_event_mcgrp);
-	if (err)
-		goto err_change_event_grp_reg;
-
-	return 0;
-
-err_change_event_grp_reg:
-	genl_unregister_family(&team_nl_family);
-
-	return err;
+	return genl_register_family_with_ops_groups(&team_nl_family, team_nl_ops,
+						    team_nl_mcgrps);
 }
 
 static void team_nl_fini(void)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 2570a944fffc..19edd6124ca3 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1606,15 +1606,17 @@ exit:
 EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);
 
 #ifdef CONFIG_NET
+static const struct genl_multicast_group thermal_event_mcgrps[] = {
+	{ .name = THERMAL_GENL_MCAST_GROUP_NAME, },
+};
+
 static struct genl_family thermal_event_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.name = THERMAL_GENL_FAMILY_NAME,
 	.version = THERMAL_GENL_VERSION,
 	.maxattr = THERMAL_GENL_ATTR_MAX,
-};
-
-static struct genl_multicast_group thermal_event_mcgrp = {
-	.name = THERMAL_GENL_MCAST_GROUP_NAME,
+	.mcgrps = thermal_event_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps),
 };
 
 int thermal_generate_netlink_event(struct thermal_zone_device *tz,
@@ -1676,7 +1678,7 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz,
 	}
 
 	result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
-				   thermal_event_mcgrp.id, GFP_ATOMIC);
+				   0, GFP_ATOMIC);
 	if (result)
 		dev_err(&tz->device, "Failed to send netlink event:%d", result);
 
@@ -1686,17 +1688,7 @@ EXPORT_SYMBOL_GPL(thermal_generate_netlink_event);
 
 static int genetlink_init(void)
 {
-	int result;
-
-	result = genl_register_family(&thermal_event_genl_family);
-	if (result)
-		return result;
-
-	result = genl_register_mc_group(&thermal_event_genl_family,
-					&thermal_event_mcgrp);
-	if (result)
-		genl_unregister_family(&thermal_event_genl_family);
-	return result;
+	return genl_register_family(&thermal_event_genl_family);
 }
 
 static void genetlink_exit(void)
diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index a5b5eddf6603..72d29177998e 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -9,6 +9,10 @@
 #include <net/netlink.h>
 #include <net/genetlink.h>
 
+static const struct genl_multicast_group quota_mcgrps[] = {
+	{ .name = "events", },
+};
+
 /* Netlink family structure for quota */
 static struct genl_family quota_genl_family = {
 	/*
@@ -22,10 +26,8 @@ static struct genl_family quota_genl_family = {
 	.name = "VFS_DQUOT",
 	.version = 1,
 	.maxattr = QUOTA_NL_A_MAX,
-};
-
-static struct genl_multicast_group quota_mcgrp = {
-	.name = "events",
+	.mcgrps = quota_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(quota_mcgrps),
 };
 
 /**
@@ -88,7 +90,7 @@ void quota_send_warning(struct kqid qid, dev_t dev,
 		goto attr_err_out;
 	genlmsg_end(skb, msg_head);
 
-	genlmsg_multicast(&quota_genl_family, skb, 0, quota_mcgrp.id, GFP_NOFS);
+	genlmsg_multicast(&quota_genl_family, skb, 0, 0, GFP_NOFS);
 	return;
 attr_err_out:
 	printk(KERN_ERR "VFS: Not enough space to compose quota message!\n");
@@ -102,9 +104,6 @@ static int __init quota_init(void)
 	if (genl_register_family(&quota_genl_family) != 0)
 		printk(KERN_ERR
 		       "VFS: Failed to create quota netlink interface.\n");
-	if (genl_register_mc_group(&quota_genl_family, &quota_mcgrp))
-		printk(KERN_ERR
-		       "VFS: Failed to register quota mcast group.\n");
 	return 0;
 };
 
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 5b9b8ae6748b..c0894dd8827b 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -273,49 +273,40 @@ static struct genl_family ZZZ_genl_family __read_mostly = {
  * Magic: define multicast groups
  * Magic: define multicast group registration helper
  */
+#define ZZZ_genl_mcgrps		CONCAT_(GENL_MAGIC_FAMILY, _genl_mcgrps)
+static const struct genl_multicast_group ZZZ_genl_mcgrps[] = {
+#undef GENL_mc_group
+#define GENL_mc_group(group) { .name = #group, },
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
+enum CONCAT_(GENL_MAGIC_FAMILY, group_ids) {
+#undef GENL_mc_group
+#define GENL_mc_group(group) CONCAT_(GENL_MAGIC_FAMILY, _group_ ## group),
+#include GENL_MAGIC_INCLUDE_FILE
+};
+
 #undef GENL_mc_group
 #define GENL_mc_group(group)						\
-static struct genl_multicast_group					\
-CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group) __read_mostly = {		\
-	.name = #group,							\
-};									\
 static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
 	struct sk_buff *skb, gfp_t flags)				\
 {									\
 	unsigned int group_id =						\
-		CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id;	\
-	if (!group_id)							\
-		return -EINVAL;						\
+		CONCAT_(GENL_MAGIC_FAMILY, _group_ ## group);		\
 	return genlmsg_multicast(&ZZZ_genl_family, skb, 0,		\
 				 group_id, flags);			\
 }
 
 #include GENL_MAGIC_INCLUDE_FILE
 
-int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void)
-{
-	int err = genl_register_family_with_ops(&ZZZ_genl_family, ZZZ_genl_ops);
-	if (err)
-		return err;
-#undef GENL_mc_group
-#define GENL_mc_group(group)						\
-	err = genl_register_mc_group(&ZZZ_genl_family,			\
-		&CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group));		\
-	if (err)							\
-		goto fail;						\
-	else								\
-		pr_info("%s: mcg %s: %u\n", #group,			\
-			__stringify(GENL_MAGIC_FAMILY),			\
-			CONCAT_(GENL_MAGIC_FAMILY, _mcg_ ## group).id);
-
-#include GENL_MAGIC_INCLUDE_FILE
-
 #undef GENL_mc_group
 #define GENL_mc_group(group)
-	return 0;
-fail:
-	genl_unregister_family(&ZZZ_genl_family);
-	return err;
+
+int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void)
+{
+	return genl_register_family_with_ops_groups(&ZZZ_genl_family,	\
+						    ZZZ_genl_ops,	\
+						    ZZZ_genl_mcgrps);
 }
 
 void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void)
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 60aef0df386b..ace4abf118d7 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -10,14 +10,9 @@
 /**
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
- * @id: multicast group ID, assigned by the core, to use with
- *      genlmsg_multicast().
- * @list: list entry for linking
  */
 struct genl_multicast_group {
-	struct list_head	list;		/* private */
 	char			name[GENL_NAMSIZ];
-	u32			id;
 };
 
 struct genl_ops;
@@ -38,7 +33,9 @@ struct genl_info;
  *	undo operations done by pre_doit, for example release locks
  * @attrbuf: buffer to store parsed attributes
  * @family_list: family list
- * @mcast_groups: multicast groups list
+ * @mcgrps: multicast groups used by this family (private)
+ * @n_mcgrps: number of multicast groups (private)
+ * @mcgrp_offset: starting number of multicast group IDs in this family
  * @ops: the operations supported by this family (private)
  * @n_ops: number of operations supported by this family (private)
  */
@@ -58,9 +55,11 @@ struct genl_family {
 					     struct genl_info *info);
 	struct nlattr **	attrbuf;	/* private */
 	const struct genl_ops *	ops;		/* private */
+	const struct genl_multicast_group *mcgrps; /* private */
 	unsigned int		n_ops;		/* private */
+	unsigned int		n_mcgrps;	/* private */
+	unsigned int		mcgrp_offset;	/* private */
 	struct list_head	family_list;	/* private */
-	struct list_head	mcast_groups;	/* private */
 	struct module		*module;
 };
 
@@ -150,22 +149,30 @@ static inline int genl_register_family(struct genl_family *family)
  *
  * Return 0 on success or a negative error code.
  */
-static inline int _genl_register_family_with_ops(struct genl_family *family,
-						 const struct genl_ops *ops,
-						 size_t n_ops)
+static inline int
+_genl_register_family_with_ops_grps(struct genl_family *family,
+				    const struct genl_ops *ops, size_t n_ops,
+				    const struct genl_multicast_group *mcgrps,
+				    size_t n_mcgrps)
 {
 	family->module = THIS_MODULE;
 	family->ops = ops;
 	family->n_ops = n_ops;
+	family->mcgrps = mcgrps;
+	family->n_mcgrps = n_mcgrps;
 	return __genl_register_family(family);
 }
 
-#define genl_register_family_with_ops(family, ops)	\
-	_genl_register_family_with_ops((family), (ops), ARRAY_SIZE(ops))
+#define genl_register_family_with_ops(family, ops)			\
+	_genl_register_family_with_ops_grps((family),			\
+					    (ops), ARRAY_SIZE(ops),	\
+					    NULL, 0)
+#define genl_register_family_with_ops_groups(family, ops, grps)	\
+	_genl_register_family_with_ops_grps((family),			\
+					    (ops), ARRAY_SIZE(ops),	\
+					    (grps), ARRAY_SIZE(grps))
 
 int genl_unregister_family(struct genl_family *family);
-int genl_register_mc_group(struct genl_family *family,
-			   struct genl_multicast_group *grp);
 void genl_notify(struct genl_family *family,
 		 struct sk_buff *skb, struct net *net, u32 portid,
 		 u32 group, struct nlmsghdr *nlh, gfp_t flags);
@@ -251,13 +258,16 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr)
  * @net: the net namespace
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
- * @group: multicast group id
+ * @group: offset of multicast group in groups array
  * @flags: allocation flags
  */
 static inline int genlmsg_multicast_netns(struct genl_family *family,
 					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
+	if (group >= family->n_mcgrps)
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
 	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
 }
 
@@ -266,13 +276,16 @@ static inline int genlmsg_multicast_netns(struct genl_family *family,
  * @family: the generic netlink family
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
- * @group: multicast group id
+ * @group: offset of multicast group in groups array
  * @flags: allocation flags
  */
 static inline int genlmsg_multicast(struct genl_family *family,
 				    struct sk_buff *skb, u32 portid,
 				    unsigned int group, gfp_t flags)
 {
+	if (group >= family->n_mcgrps)
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
 	return genlmsg_multicast_netns(family, &init_net, skb,
 				       portid, group, flags);
 }
@@ -282,7 +295,7 @@ static inline int genlmsg_multicast(struct genl_family *family,
  * @family: the generic netlink family
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
- * @group: multicast group id
+ * @group: offset of multicast group in groups array
  * @flags: allocation flags
  *
  * This function must hold the RTNL or rcu_read_lock().
@@ -365,6 +378,7 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags)
  * @net: the network namespace to report the error to
  * @portid: the PORTID of a process that we want to skip (if any)
  * @group: the broadcast group that will notice the error
+ * 	(this is the offset of the multicast group in the groups array)
  * @code: error code, must be negative (as usual in kernelspace)
  *
  * This function returns the number of broadcast listeners that have set the
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 1eab1dc48821..95897183226e 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -106,8 +106,8 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
 	return skb;
 }
 
-static struct genl_multicast_group dm_mcgrp = {
-	.name = "events",
+static struct genl_multicast_group dropmon_mcgrps[] = {
+	{ .name = "events", },
 };
 
 static void send_dm_alert(struct work_struct *work)
@@ -121,7 +121,7 @@ static void send_dm_alert(struct work_struct *work)
 
 	if (skb)
 		genlmsg_multicast(&net_drop_monitor_family, skb, 0,
-				  dm_mcgrp.id, GFP_KERNEL);
+				  0, GFP_KERNEL);
 }
 
 /*
@@ -369,19 +369,13 @@ static int __init init_net_drop_monitor(void)
 		return -ENOSPC;
 	}
 
-	rc = genl_register_family_with_ops(&net_drop_monitor_family,
-					   dropmon_ops);
+	rc = genl_register_family_with_ops_groups(&net_drop_monitor_family,
+						  dropmon_ops, dropmon_mcgrps);
 	if (rc) {
 		pr_err("Could not create drop monitor netlink family\n");
 		return rc;
 	}
-
-	rc = genl_register_mc_group(&net_drop_monitor_family, &dm_mcgrp);
-	if (rc) {
-		pr_err("Failed to register drop monitor mcast group\n");
-		goto out_unreg;
-	}
-	WARN_ON(dm_mcgrp.id != NET_DM_GRP_ALERT);
+	WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
 
 	rc = register_netdevice_notifier(&dropmon_net_notifier);
 	if (rc < 0) {
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 0009416c08c2..5325af85eea6 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -90,8 +90,8 @@ static struct genl_family hsr_genl_family = {
 	.maxattr = HSR_A_MAX,
 };
 
-static struct genl_multicast_group hsr_network_genl_mcgrp = {
-	.name = "hsr-network",
+static const struct genl_multicast_group hsr_mcgrps[] = {
+	{ .name = "hsr-network", },
 };
 
 
@@ -129,8 +129,7 @@ void hsr_nl_ringerror(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN],
 		goto nla_put_failure;
 
 	genlmsg_end(skb, msg_head);
-	genlmsg_multicast(&hsr_genl_family, skb, 0,
-			  hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC);
 
 	return;
 
@@ -164,8 +163,7 @@ void hsr_nl_nodedown(struct hsr_priv *hsr_priv, unsigned char addr[ETH_ALEN])
 		goto nla_put_failure;
 
 	genlmsg_end(skb, msg_head);
-	genlmsg_multicast(&hsr_genl_family, skb, 0,
-			  hsr_network_genl_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC);
 
 	return;
 
@@ -416,18 +414,13 @@ int __init hsr_netlink_init(void)
 	if (rc)
 		goto fail_rtnl_link_register;
 
-	rc = genl_register_family_with_ops(&hsr_genl_family, hsr_ops);
+	rc = genl_register_family_with_ops_groups(&hsr_genl_family, hsr_ops,
+						  hsr_mcgrps);
 	if (rc)
 		goto fail_genl_register_family;
 
-	rc = genl_register_mc_group(&hsr_genl_family, &hsr_network_genl_mcgrp);
-	if (rc)
-		goto fail_genl_register_mc_group;
-
 	return 0;
 
-fail_genl_register_mc_group:
-	genl_unregister_family(&hsr_genl_family);
 fail_genl_register_family:
 	rtnl_link_unregister(&hsr_link_ops);
 fail_rtnl_link_register:
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index 14d5dab4436f..cee4425b9956 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -54,8 +54,10 @@ int ieee802154_dump_phy(struct sk_buff *skb, struct netlink_callback *cb);
 int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info);
 
-extern struct genl_multicast_group ieee802154_coord_mcgrp;
-extern struct genl_multicast_group ieee802154_beacon_mcgrp;
+enum ieee802154_mcgrp_ids {
+	IEEE802154_COORD_MCGRP,
+	IEEE802154_BEACON_MCGRP,
+};
 
 int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 5172f467a383..43f1b2bf469f 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -125,25 +125,17 @@ static const struct genl_ops ieee8021154_ops[] = {
 			ieee802154_dump_iface),
 };
 
-int __init ieee802154_nl_init(void)
-{
-	int rc;
-
-	rc = genl_register_family_with_ops(&nl802154_family, ieee8021154_ops);
-	if (rc)
-		return rc;
+static const struct genl_multicast_group ieee802154_mcgrps[] = {
+	[IEEE802154_COORD_MCGRP] = { .name = IEEE802154_MCAST_COORD_NAME, },
+	[IEEE802154_BEACON_MCGRP] = { .name = IEEE802154_MCAST_BEACON_NAME, },
+};
 
-	rc = genl_register_mc_group(&nl802154_family, &ieee802154_coord_mcgrp);
-	if (rc)
-		goto fail;
 
-	rc = genl_register_mc_group(&nl802154_family, &ieee802154_beacon_mcgrp);
-	if (rc)
-		goto fail;
-	return 0;
-fail:
-	genl_unregister_family(&nl802154_family);
-	return rc;
+int __init ieee802154_nl_init(void)
+{
+	return genl_register_family_with_ops_groups(&nl802154_family,
+						    ieee8021154_ops,
+						    ieee802154_mcgrps);
 }
 
 void __exit ieee802154_nl_exit(void)
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 28d493032132..ba5c1e002f37 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -39,14 +39,6 @@
 
 #include "ieee802154.h"
 
-struct genl_multicast_group ieee802154_coord_mcgrp = {
-	.name		= IEEE802154_MCAST_COORD_NAME,
-};
-
-struct genl_multicast_group ieee802154_beacon_mcgrp = {
-	.name		= IEEE802154_MCAST_BEACON_NAME,
-};
-
 int ieee802154_nl_assoc_indic(struct net_device *dev,
 		struct ieee802154_addr *addr, u8 cap)
 {
@@ -72,7 +64,7 @@ int ieee802154_nl_assoc_indic(struct net_device *dev,
 	    nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap))
 		goto nla_put_failure;
 
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -98,7 +90,7 @@ int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr,
 	    nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -133,7 +125,7 @@ int ieee802154_nl_disassoc_indic(struct net_device *dev,
 	}
 	if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -157,7 +149,7 @@ int ieee802154_nl_disassoc_confirm(struct net_device *dev, u8 status)
 		    dev->dev_addr) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -183,7 +175,7 @@ int ieee802154_nl_beacon_indic(struct net_device *dev,
 	    nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) ||
 	    nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -214,7 +206,7 @@ int ieee802154_nl_scan_confirm(struct net_device *dev,
 	    (edl &&
 	     nla_put(msg, IEEE802154_ATTR_ED_LIST, 27, edl)))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
@@ -238,7 +230,7 @@ int ieee802154_nl_start_confirm(struct net_device *dev, u8 status)
 		    dev->dev_addr) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_STATUS, status))
 		goto nla_put_failure;
-	return ieee802154_nl_mcast(msg, ieee802154_coord_mcgrp.id);
+	return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP);
 
 nla_put_failure:
 	nlmsg_free(msg);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 36e3a86cacf6..7dbc4f732c75 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -69,16 +69,20 @@ static struct list_head family_ht[GENL_FAM_TAB_SIZE];
  * abuses the API and thinks it can statically use group 1.
  * That group will typically conflict with other groups that
  * any proper users use.
+ * Bit 16 is marked as used since it's used for generic netlink
+ * and the code no longer marks pre-reserved IDs as used.
  * Bit 17 is marked as already used since the VFS quota code
  * also abused this API and relied on family == group ID, we
  * cater to that by giving it a static family and group ID.
  */
-static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_VFS_DQUOT);
+static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) |
+				      BIT(GENL_ID_VFS_DQUOT);
 static unsigned long *mc_groups = &mc_group_start;
 static unsigned long mc_groups_longs = 1;
 
 static int genl_ctrl_event(int event, struct genl_family *family,
-			   struct genl_multicast_group *grp);
+			   const struct genl_multicast_group *grp,
+			   int grp_id);
 
 static inline unsigned int genl_family_hash(unsigned int id)
 {
@@ -144,66 +148,110 @@ static u16 genl_generate_id(void)
 	return 0;
 }
 
-static struct genl_multicast_group notify_grp;
-
-/**
- * genl_register_mc_group - register a multicast group
- *
- * Registers the specified multicast group and notifies userspace
- * about the new group.
- *
- * Returns 0 on success or a negative error code.
- *
- * @family: The generic netlink family the group shall be registered for.
- * @grp: The group to register, must have a name.
- */
-int genl_register_mc_group(struct genl_family *family,
-			   struct genl_multicast_group *grp)
+static int genl_allocate_reserve_groups(int n_groups, int *first_id)
 {
-	int id;
 	unsigned long *new_groups;
-	int err = 0;
+	int start = 0;
+	int i;
+	int id;
+	bool fits;
+
+	do {
+		if (start == 0)
+			id = find_first_zero_bit(mc_groups,
+						 mc_groups_longs *
+						 BITS_PER_LONG);
+		else
+			id = find_next_zero_bit(mc_groups,
+						mc_groups_longs * BITS_PER_LONG,
+						start);
+
+		fits = true;
+		for (i = id;
+		     i < min_t(int, id + n_groups,
+			       mc_groups_longs * BITS_PER_LONG);
+		     i++) {
+			if (test_bit(i, mc_groups)) {
+				start = i;
+				fits = false;
+				break;
+			}
+		}
 
-	BUG_ON(grp->name[0] == '\0');
-	BUG_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL);
+		if (id >= mc_groups_longs * BITS_PER_LONG) {
+			unsigned long new_longs = mc_groups_longs +
+						  BITS_TO_LONGS(n_groups);
+			size_t nlen = new_longs * sizeof(unsigned long);
+
+			if (mc_groups == &mc_group_start) {
+				new_groups = kzalloc(nlen, GFP_KERNEL);
+				if (!new_groups)
+					return -ENOMEM;
+				mc_groups = new_groups;
+				*mc_groups = mc_group_start;
+			} else {
+				new_groups = krealloc(mc_groups, nlen,
+						      GFP_KERNEL);
+				if (!new_groups)
+					return -ENOMEM;
+				mc_groups = new_groups;
+				for (i = 0; i < BITS_TO_LONGS(n_groups); i++)
+					mc_groups[mc_groups_longs + i] = 0;
+			}
+			mc_groups_longs = new_longs;
+		}
+	} while (!fits);
 
-	genl_lock_all();
+	for (i = id; i < id + n_groups; i++)
+		set_bit(i, mc_groups);
+	*first_id = id;
+	return 0;
+}
+
+static struct genl_family genl_ctrl;
+
+static int genl_validate_assign_mc_groups(struct genl_family *family)
+{
+	int first_id;
+	int n_groups = family->n_mcgrps;
+	int err, i;
+	bool groups_allocated = false;
+
+	if (!n_groups)
+		return 0;
+
+	for (i = 0; i < n_groups; i++) {
+		const struct genl_multicast_group *grp = &family->mcgrps[i];
+
+		if (WARN_ON(grp->name[0] == '\0'))
+			return -EINVAL;
+		if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL))
+			return -EINVAL;
+	}
 
 	/* special-case our own group and hacks */
-	if (grp == &notify_grp)
-		id = GENL_ID_CTRL;
-	else if (strcmp(family->name, "NET_DM") == 0)
-		id = 1;
-	else if (strcmp(family->name, "VFS_DQUOT") == 0)
-		id = GENL_ID_VFS_DQUOT;
-	else
-		id = find_first_zero_bit(mc_groups,
-					 mc_groups_longs * BITS_PER_LONG);
-
-
-	if (id >= mc_groups_longs * BITS_PER_LONG) {
-		size_t nlen = (mc_groups_longs + 1) * sizeof(unsigned long);
-
-		if (mc_groups == &mc_group_start) {
-			new_groups = kzalloc(nlen, GFP_KERNEL);
-			if (!new_groups) {
-				err = -ENOMEM;
-				goto out;
-			}
-			mc_groups = new_groups;
-			*mc_groups = mc_group_start;
-		} else {
-			new_groups = krealloc(mc_groups, nlen, GFP_KERNEL);
-			if (!new_groups) {
-				err = -ENOMEM;
-				goto out;
-			}
-			mc_groups = new_groups;
-			mc_groups[mc_groups_longs] = 0;
-		}
-		mc_groups_longs++;
+	if (family == &genl_ctrl) {
+		first_id = GENL_ID_CTRL;
+		BUG_ON(n_groups != 1);
+	} else if (strcmp(family->name, "NET_DM") == 0) {
+		first_id = 1;
+		BUG_ON(n_groups != 1);
+	} else if (strcmp(family->name, "VFS_DQUOT") == 0) {
+		first_id = GENL_ID_VFS_DQUOT;
+		BUG_ON(n_groups != 1);
+	} else {
+		groups_allocated = true;
+		err = genl_allocate_reserve_groups(n_groups, &first_id);
+		if (err)
+			return err;
 	}
 
+	family->mcgrp_offset = first_id;
+
+	/* if still initializing, can't and don't need to to realloc bitmaps */
+	if (!init_net.genl_sock)
+		return 0;
+
 	if (family->netnsok) {
 		struct net *net;
 
@@ -219,9 +267,7 @@ int genl_register_mc_group(struct genl_family *family,
 				 * number of _possible_ groups has been
 				 * increased on some sockets which is ok.
 				 */
-				rcu_read_unlock();
-				netlink_table_ungrab();
-				goto out;
+				break;
 			}
 		}
 		rcu_read_unlock();
@@ -229,46 +275,39 @@ int genl_register_mc_group(struct genl_family *family,
 	} else {
 		err = netlink_change_ngroups(init_net.genl_sock,
 					     mc_groups_longs * BITS_PER_LONG);
-		if (err)
-			goto out;
 	}
 
-	grp->id = id;
-	set_bit(id, mc_groups);
-	list_add_tail(&grp->list, &family->mcast_groups);
+	if (groups_allocated && err) {
+		for (i = 0; i < family->n_mcgrps; i++)
+			clear_bit(family->mcgrp_offset + i, mc_groups);
+	}
 
-	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family, grp);
- out:
-	genl_unlock_all();
 	return err;
 }
-EXPORT_SYMBOL(genl_register_mc_group);
 
-static void __genl_unregister_mc_group(struct genl_family *family,
-				       struct genl_multicast_group *grp)
+static void genl_unregister_mc_groups(struct genl_family *family)
 {
 	struct net *net;
+	int i;
 
 	netlink_table_grab();
 	rcu_read_lock();
-	for_each_net_rcu(net)
-		__netlink_clear_multicast_users(net->genl_sock, grp->id);
+	for_each_net_rcu(net) {
+		for (i = 0; i < family->n_mcgrps; i++)
+			__netlink_clear_multicast_users(
+				net->genl_sock, family->mcgrp_offset + i);
+	}
 	rcu_read_unlock();
 	netlink_table_ungrab();
 
-	if (grp->id != 1)
-		clear_bit(grp->id, mc_groups);
-	list_del(&grp->list);
-	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, grp);
-	grp->id = 0;
-}
-
-static void genl_unregister_mc_groups(struct genl_family *family)
-{
-	struct genl_multicast_group *grp, *tmp;
+	for (i = 0; i < family->n_mcgrps; i++) {
+		int grp_id = family->mcgrp_offset + i;
 
-	list_for_each_entry_safe(grp, tmp, &family->mcast_groups, list)
-		__genl_unregister_mc_group(family, grp);
+		if (grp_id != 1)
+			clear_bit(grp_id, mc_groups);
+		genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family,
+				&family->mcgrps[i], grp_id);
+	}
 }
 
 static int genl_validate_ops(struct genl_family *family)
@@ -314,7 +353,7 @@ static int genl_validate_ops(struct genl_family *family)
  */
 int __genl_register_family(struct genl_family *family)
 {
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 
 	if (family->id && family->id < GENL_MIN_ID)
 		goto errout;
@@ -326,8 +365,6 @@ int __genl_register_family(struct genl_family *family)
 	if (err)
 		return err;
 
-	INIT_LIST_HEAD(&family->mcast_groups);
-
 	genl_lock_all();
 
 	if (genl_family_find_byname(family->name)) {
@@ -359,10 +396,18 @@ int __genl_register_family(struct genl_family *family)
 	} else
 		family->attrbuf = NULL;
 
+	err = genl_validate_assign_mc_groups(family);
+	if (err)
+		goto errout_locked;
+
 	list_add_tail(&family->family_list, genl_family_chain(family->id));
 	genl_unlock_all();
 
-	genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL);
+	/* send all events */
+	genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL, 0);
+	for (i = 0; i < family->n_mcgrps; i++)
+		genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family,
+				&family->mcgrps[i], family->mcgrp_offset + i);
 
 	return 0;
 
@@ -398,7 +443,7 @@ int genl_unregister_family(struct genl_family *family)
 		genl_unlock_all();
 
 		kfree(family->attrbuf);
-		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL);
+		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
 		return 0;
 	}
 
@@ -658,23 +703,26 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 		nla_nest_end(skb, nla_ops);
 	}
 
-	if (!list_empty(&family->mcast_groups)) {
-		struct genl_multicast_group *grp;
+	if (family->n_mcgrps) {
 		struct nlattr *nla_grps;
-		int idx = 1;
+		int i;
 
 		nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
 		if (nla_grps == NULL)
 			goto nla_put_failure;
 
-		list_for_each_entry(grp, &family->mcast_groups, list) {
+		for (i = 0; i < family->n_mcgrps; i++) {
 			struct nlattr *nest;
+			const struct genl_multicast_group *grp;
 
-			nest = nla_nest_start(skb, idx++);
+			grp = &family->mcgrps[i];
+
+			nest = nla_nest_start(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) ||
+			if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID,
+					family->mcgrp_offset + i) ||
 			    nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME,
 					   grp->name))
 				goto nla_put_failure;
@@ -692,9 +740,9 @@ nla_put_failure:
 }
 
 static int ctrl_fill_mcgrp_info(struct genl_family *family,
-				struct genl_multicast_group *grp, u32 portid,
-				u32 seq, u32 flags, struct sk_buff *skb,
-				u8 cmd)
+				const struct genl_multicast_group *grp,
+				int grp_id, u32 portid, u32 seq, u32 flags,
+				struct sk_buff *skb, u8 cmd)
 {
 	void *hdr;
 	struct nlattr *nla_grps;
@@ -716,7 +764,7 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family,
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) ||
+	if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp_id) ||
 	    nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME,
 			   grp->name))
 		goto nla_put_failure;
@@ -782,9 +830,10 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
 	return skb;
 }
 
-static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_family *family,
-					    struct genl_multicast_group *grp,
-					    u32 portid, int seq, u8 cmd)
+static struct sk_buff *
+ctrl_build_mcgrp_msg(struct genl_family *family,
+		     const struct genl_multicast_group *grp,
+		     int grp_id, u32 portid, int seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int err;
@@ -793,7 +842,8 @@ static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_family *family,
 	if (skb == NULL)
 		return ERR_PTR(-ENOBUFS);
 
-	err = ctrl_fill_mcgrp_info(family, grp, portid, seq, 0, skb, cmd);
+	err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid,
+				   seq, 0, skb, cmd);
 	if (err < 0) {
 		nlmsg_free(skb);
 		return ERR_PTR(err);
@@ -856,7 +906,8 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info)
 }
 
 static int genl_ctrl_event(int event, struct genl_family *family,
-			   struct genl_multicast_group *grp)
+			   const struct genl_multicast_group *grp,
+			   int grp_id)
 {
 	struct sk_buff *msg;
 
@@ -873,7 +924,7 @@ static int genl_ctrl_event(int event, struct genl_family *family,
 	case CTRL_CMD_NEWMCAST_GRP:
 	case CTRL_CMD_DELMCAST_GRP:
 		BUG_ON(!grp);
-		msg = ctrl_build_mcgrp_msg(family, grp, 0, 0, event);
+		msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event);
 		break;
 	default:
 		return -EINVAL;
@@ -884,11 +935,11 @@ static int genl_ctrl_event(int event, struct genl_family *family,
 
 	if (!family->netnsok) {
 		genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0,
-					GENL_ID_CTRL, GFP_KERNEL);
+					0, GFP_KERNEL);
 	} else {
 		rcu_read_lock();
 		genlmsg_multicast_allns(&genl_ctrl, msg, 0,
-					GENL_ID_CTRL, GFP_ATOMIC);
+					0, GFP_ATOMIC);
 		rcu_read_unlock();
 	}
 
@@ -904,8 +955,8 @@ static struct genl_ops genl_ctrl_ops[] = {
 	},
 };
 
-static struct genl_multicast_group notify_grp = {
-	.name		= "notify",
+static struct genl_multicast_group genl_ctrl_groups[] = {
+	{ .name = "notify", },
 };
 
 static int __net_init genl_pernet_init(struct net *net)
@@ -945,7 +996,8 @@ static int __init genl_init(void)
 	for (i = 0; i < GENL_FAM_TAB_SIZE; i++)
 		INIT_LIST_HEAD(&family_ht[i]);
 
-	err = genl_register_family_with_ops(&genl_ctrl, genl_ctrl_ops);
+	err = genl_register_family_with_ops_groups(&genl_ctrl, genl_ctrl_ops,
+						   genl_ctrl_groups);
 	if (err < 0)
 		goto problem;
 
@@ -953,10 +1005,6 @@ static int __init genl_init(void)
 	if (err)
 		goto problem;
 
-	err = genl_register_mc_group(&genl_ctrl, &notify_grp);
-	if (err < 0)
-		goto problem;
-
 	return 0;
 
 problem:
@@ -997,6 +1045,9 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
 			    u32 portid, unsigned int group, gfp_t flags)
 {
+	if (group >= family->n_mcgrps)
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
 	return genlmsg_mcast(skb, portid, group, flags);
 }
 EXPORT_SYMBOL(genlmsg_multicast_allns);
@@ -1011,6 +1062,9 @@ void genl_notify(struct genl_family *family,
 	if (nlh)
 		report = nlmsg_report(nlh);
 
+	if (group >= family->n_mcgrps)
+		return;
+	group = family->mcgrp_offset + group;
 	nlmsg_notify(sk, skb, portid, group, report, flags);
 }
 EXPORT_SYMBOL(genl_notify);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 3092df313fb1..a9b2342d5253 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -30,8 +30,8 @@
 #include "nfc.h"
 #include "llcp.h"
 
-static struct genl_multicast_group nfc_genl_event_mcgrp = {
-	.name = NFC_GENL_MCAST_EVENT_NAME,
+static const struct genl_multicast_group nfc_genl_mcgrps[] = {
+	{ .name = NFC_GENL_MCAST_EVENT_NAME, },
 };
 
 static struct genl_family nfc_genl_family = {
@@ -194,8 +194,7 @@ int nfc_genl_targets_found(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	return genlmsg_multicast(&nfc_genl_family, msg, 0,
-				 nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC);
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -224,8 +223,7 @@ int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -257,8 +255,7 @@ int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -288,8 +285,7 @@ int nfc_genl_tm_deactivated(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -322,8 +318,7 @@ int nfc_genl_device_added(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -353,8 +348,7 @@ int nfc_genl_device_removed(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -420,8 +414,7 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list)
 
 	genlmsg_end(msg, hdr);
 
-	return genlmsg_multicast(&nfc_genl_family, msg, 0,
-				 nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC);
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -455,8 +448,7 @@ int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -487,8 +479,7 @@ int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -609,8 +600,7 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx,
 
 	dev->dep_link_up = true;
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC);
 
 	return 0;
 
@@ -642,8 +632,7 @@ int nfc_genl_dep_link_down_event(struct nfc_dev *dev)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_ATOMIC);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC);
 
 	return 0;
 
@@ -1148,8 +1137,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	return 0;
 
@@ -1320,8 +1308,7 @@ static void se_io_cb(void *context, u8 *apdu, size_t apdu_len, int err)
 
 	genlmsg_end(msg, hdr);
 
-	genlmsg_multicast(&nfc_genl_family, msg, 0,
-			  nfc_genl_event_mcgrp.id, GFP_KERNEL);
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
 
 	kfree(ctx);
 
@@ -1549,15 +1536,15 @@ int __init nfc_genl_init(void)
 {
 	int rc;
 
-	rc = genl_register_family_with_ops(&nfc_genl_family, nfc_genl_ops);
+	rc = genl_register_family_with_ops_groups(&nfc_genl_family,
+						  nfc_genl_ops,
+						  nfc_genl_mcgrps);
 	if (rc)
 		return rc;
 
-	rc = genl_register_mc_group(&nfc_genl_family, &nfc_genl_event_mcgrp);
-
 	netlink_register_notifier(&nl_notifier);
 
-	return rc;
+	return 0;
 }
 
 /**
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 5c19846b1d2a..1de4d281e3f1 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -62,11 +62,10 @@
 int ovs_net_id __read_mostly;
 
 static void ovs_notify(struct genl_family *family,
-		       struct sk_buff *skb, struct genl_info *info,
-		       struct genl_multicast_group *grp)
+		       struct sk_buff *skb, struct genl_info *info)
 {
 	genl_notify(family, skb, genl_info_net(info), info->snd_portid,
-		    grp->id, info->nlhdr, GFP_KERNEL);
+		    0, info->nlhdr, GFP_KERNEL);
 }
 
 /**
@@ -878,11 +877,10 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 	ovs_unlock();
 
 	if (!IS_ERR(reply))
-		ovs_notify(&dp_flow_genl_family, reply, info,
-			   &ovs_dp_flow_multicast_group);
+		ovs_notify(&dp_flow_genl_family, reply, info);
 	else
 		genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0,
-			     ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
+			     0, PTR_ERR(reply));
 	return 0;
 
 err_flow_free:
@@ -992,8 +990,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_flow_free(flow, true);
 	ovs_unlock();
 
-	ovs_notify(&dp_flow_genl_family, reply, info,
-		   &ovs_dp_flow_multicast_group);
+	ovs_notify(&dp_flow_genl_family, reply, info);
 	return 0;
 unlock:
 	ovs_unlock();
@@ -1240,8 +1237,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	ovs_unlock();
 
-	ovs_notify(&dp_datapath_genl_family, reply, info,
-		   &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
 err_destroy_local_port:
@@ -1306,8 +1302,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	__dp_destroy(dp);
 	ovs_unlock();
 
-	ovs_notify(&dp_datapath_genl_family, reply, info,
-		   &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
 unlock:
@@ -1332,14 +1327,13 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
 		genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0,
-			     ovs_dp_datapath_multicast_group.id, err);
+			     0, err);
 		err = 0;
 		goto unlock;
 	}
 
 	ovs_unlock();
-	ovs_notify(&dp_datapath_genl_family, reply, info,
-		   &ovs_dp_datapath_multicast_group);
+	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
 unlock:
@@ -1601,8 +1595,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock;
 	}
 
-	ovs_notify(&dp_vport_genl_family, reply, info,
-		   &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info);
 
 exit_unlock:
 	ovs_unlock();
@@ -1649,8 +1642,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	BUG_ON(err < 0);
 
 	ovs_unlock();
-	ovs_notify(&dp_vport_genl_family, reply, info,
-		   &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info);
 	return 0;
 
 exit_free:
@@ -1687,8 +1679,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	err = 0;
 	ovs_dp_detach_port(vport);
 
-	ovs_notify(&dp_vport_genl_family, reply, info,
-		   &ovs_dp_vport_multicast_group);
+	ovs_notify(&dp_vport_genl_family, reply, info);
 
 exit_unlock:
 	ovs_unlock();
@@ -1790,7 +1781,7 @@ struct genl_family_and_ops {
 	struct genl_family *family;
 	const struct genl_ops *ops;
 	int n_ops;
-	struct genl_multicast_group *group;
+	const struct genl_multicast_group *group;
 };
 
 static const struct genl_family_and_ops dp_genl_families[] = {
@@ -1828,16 +1819,12 @@ static int dp_register_genl(void)
 
 		f->family->ops = f->ops;
 		f->family->n_ops = f->n_ops;
+		f->family->mcgrps = f->group;
+		f->family->n_mcgrps = f->group ? 1 : 0;
 		err = genl_register_family(f->family);
 		if (err)
 			goto error;
 		n_registered++;
-
-		if (f->group) {
-			err = genl_register_mc_group(f->family, f->group);
-			if (err)
-				goto error;
-		}
 	}
 
 	return 0;
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index f4b66c84ea0b..2c631fe76be1 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -35,15 +35,13 @@ static void dp_detach_port_notify(struct vport *vport)
 	ovs_dp_detach_port(vport);
 	if (IS_ERR(notify)) {
 		genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
-			     ovs_dp_vport_multicast_group.id,
-			     PTR_ERR(notify));
+			     0, PTR_ERR(notify));
 		return;
 	}
 
 	genlmsg_multicast_netns(&dp_vport_genl_family,
 				ovs_dp_get_net(dp), notify, 0,
-				ovs_dp_vport_multicast_group.id,
-				GFP_KERNEL);
+				0, GFP_KERNEL);
 }
 
 void ovs_dp_notify_wq(struct work_struct *work)
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
index f37dd3c5576d..c278b3356f75 100644
--- a/net/wimax/op-msg.c
+++ b/net/wimax/op-msg.c
@@ -279,8 +279,7 @@ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
 
 	d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
 	d_dump(2, dev, msg, size);
-	genlmsg_multicast(&wimax_gnl_family, skb, 0,
-			  wimax_gnl_mcg.id, GFP_KERNEL);
+	genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
 	d_printf(1, dev, "CTX: genl multicast done\n");
 	return 0;
 }
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 18888748e699..ef2191b969a7 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -116,8 +116,9 @@ struct sk_buff *wimax_gnl_re_state_change_alloc(
 		dev_err(dev, "RE_STCH: can't create message\n");
 		goto error_new;
 	}
-	data = genlmsg_put(report_skb, 0, wimax_gnl_mcg.id, &wimax_gnl_family,
-			   0, WIMAX_GNL_RE_STATE_CHANGE);
+	/* FIXME: sending a group ID as the seq is wrong */
+	data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
+			   &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
 	if (data == NULL) {
 		dev_err(dev, "RE_STCH: can't put data into message\n");
 		goto error_put;
@@ -177,8 +178,7 @@ int wimax_gnl_re_state_change_send(
 		goto out;
 	}
 	genlmsg_end(report_skb, header);
-	genlmsg_multicast(&wimax_gnl_family, report_skb, 0,
-			  wimax_gnl_mcg.id, GFP_KERNEL);
+	genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
 out:
 	d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
 		wimax_dev, report_skb, result);
@@ -580,8 +580,8 @@ struct genl_family wimax_gnl_family = {
 	.maxattr = WIMAX_GNL_ATTR_MAX,
 };
 
-struct genl_multicast_group wimax_gnl_mcg = {
-	.name = "msg",
+static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
+	{ .name = "msg", },
 };
 
 
@@ -598,21 +598,18 @@ int __init wimax_subsys_init(void)
 
 	snprintf(wimax_gnl_family.name, sizeof(wimax_gnl_family.name),
 		 "WiMAX");
-	result = genl_register_family_with_ops(&wimax_gnl_family,
-					       wimax_gnl_ops);
+	result = genl_register_family_with_ops_groups(&wimax_gnl_family,
+						      wimax_gnl_ops,
+						      wimax_gnl_mcgrps);
 	if (unlikely(result < 0)) {
 		printk(KERN_ERR "cannot register generic netlink family: %d\n",
 		       result);
 		goto error_register_family;
 	}
 
-	result = genl_register_mc_group(&wimax_gnl_family, &wimax_gnl_mcg);
-	if (result < 0)
-		goto error_mc_group;
 	d_fnend(4, NULL, "() = 0\n");
 	return 0;
 
-error_mc_group:
 	genl_unregister_family(&wimax_gnl_family);
 error_register_family:
 	d_fnend(4, NULL, "() = %d\n", result);
diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h
index 8567d3079a83..b445b82020a8 100644
--- a/net/wimax/wimax-internal.h
+++ b/net/wimax/wimax-internal.h
@@ -86,7 +86,6 @@ void wimax_rfkill_rm(struct wimax_dev *);
 
 /* generic netlink */
 extern struct genl_family wimax_gnl_family;
-extern struct genl_multicast_group wimax_gnl_mcg;
 
 /* ops */
 int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f20edfd2e1f0..a1eb21073176 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -47,6 +47,25 @@ static struct genl_family nl80211_fam = {
 	.post_doit = nl80211_post_doit,
 };
 
+/* multicast groups */
+enum nl80211_multicast_groups {
+	NL80211_MCGRP_CONFIG,
+	NL80211_MCGRP_SCAN,
+	NL80211_MCGRP_REGULATORY,
+	NL80211_MCGRP_MLME,
+	NL80211_MCGRP_TESTMODE /* keep last - ifdef! */
+};
+
+static const struct genl_multicast_group nl80211_mcgrps[] = {
+	[NL80211_MCGRP_CONFIG] = { .name = "config", },
+	[NL80211_MCGRP_SCAN] = { .name = "scan", },
+	[NL80211_MCGRP_REGULATORY] = { .name = "regulatory", },
+	[NL80211_MCGRP_MLME] = { .name = "mlme", },
+#ifdef CONFIG_NL80211_TESTMODE
+	[NL80211_MCGRP_TESTMODE] = { .name = "testmode", }
+#endif
+};
+
 /* returns ERR_PTR values */
 static struct wireless_dev *
 __cfg80211_wdev_from_attrs(struct net *netns, struct nlattr **attrs)
@@ -6656,10 +6675,6 @@ static int nl80211_set_mcast_rate(struct sk_buff *skb, struct genl_info *info)
 
 
 #ifdef CONFIG_NL80211_TESTMODE
-static struct genl_multicast_group nl80211_testmode_mcgrp = {
-	.name = "testmode",
-};
-
 static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -6869,7 +6884,7 @@ void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), skb, 0,
-				nl80211_testmode_mcgrp.id, gfp);
+				NL80211_MCGRP_TESTMODE, gfp);
 }
 EXPORT_SYMBOL(cfg80211_testmode_event);
 #endif
@@ -9566,21 +9581,6 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 };
 
-static struct genl_multicast_group nl80211_mlme_mcgrp = {
-	.name = "mlme",
-};
-
-/* multicast groups */
-static struct genl_multicast_group nl80211_config_mcgrp = {
-	.name = "config",
-};
-static struct genl_multicast_group nl80211_scan_mcgrp = {
-	.name = "scan",
-};
-static struct genl_multicast_group nl80211_regulatory_mcgrp = {
-	.name = "regulatory",
-};
-
 /* notification functions */
 
 void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev)
@@ -9598,7 +9598,7 @@ void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev)
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_config_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_CONFIG, GFP_KERNEL);
 }
 
 static int nl80211_add_scan_req(struct sk_buff *msg,
@@ -9708,7 +9708,7 @@ void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_scan_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
 void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
@@ -9727,7 +9727,7 @@ void nl80211_send_scan_done(struct cfg80211_registered_device *rdev,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_scan_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
 void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
@@ -9746,7 +9746,7 @@ void nl80211_send_scan_aborted(struct cfg80211_registered_device *rdev,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_scan_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
 void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
@@ -9765,7 +9765,7 @@ void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_scan_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
 void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
@@ -9783,7 +9783,7 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_scan_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
 /*
@@ -9838,7 +9838,7 @@ void nl80211_send_reg_change_event(struct regulatory_request *request)
 
 	rcu_read_lock();
 	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
-				nl80211_regulatory_mcgrp.id, GFP_ATOMIC);
+				NL80211_MCGRP_REGULATORY, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return;
@@ -9874,7 +9874,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -9962,7 +9962,7 @@ static void nl80211_send_mlme_timeout(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10018,7 +10018,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10057,7 +10057,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10095,7 +10095,7 @@ void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_MLME, GFP_KERNEL);
 	return;
 
  nla_put_failure:
@@ -10129,7 +10129,7 @@ void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10170,7 +10170,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10209,7 +10209,7 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10262,7 +10262,7 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy,
 
 	rcu_read_lock();
 	genlmsg_multicast_allns(&nl80211_fam, msg, 0,
-				nl80211_regulatory_mcgrp.id, GFP_ATOMIC);
+				NL80211_MCGRP_REGULATORY, GFP_ATOMIC);
 	rcu_read_unlock();
 
 	return;
@@ -10308,7 +10308,7 @@ static void nl80211_send_remain_on_chan_event(
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10363,7 +10363,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 	}
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 }
 EXPORT_SYMBOL(cfg80211_new_sta);
 
@@ -10393,7 +10393,7 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10429,7 +10429,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10591,7 +10591,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10640,7 +10640,7 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10685,7 +10685,7 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10743,7 +10743,7 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10790,7 +10790,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10867,7 +10867,7 @@ void cfg80211_cqm_txe_notify(struct net_device *dev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10916,7 +10916,7 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -10963,7 +10963,7 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -11003,7 +11003,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -11155,7 +11155,7 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  free_msg:
@@ -11197,7 +11197,7 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, gfp);
+				NL80211_MCGRP_MLME, gfp);
 	return;
 
  nla_put_failure:
@@ -11280,7 +11280,7 @@ void cfg80211_ft_event(struct net_device *netdev,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
-				nl80211_mlme_mcgrp.id, GFP_KERNEL);
+				NL80211_MCGRP_MLME, GFP_KERNEL);
 }
 EXPORT_SYMBOL(cfg80211_ft_event);
 
@@ -11329,32 +11329,11 @@ int nl80211_init(void)
 {
 	int err;
 
-	err = genl_register_family_with_ops(&nl80211_fam, nl80211_ops);
+	err = genl_register_family_with_ops_groups(&nl80211_fam, nl80211_ops,
+						   nl80211_mcgrps);
 	if (err)
 		return err;
 
-	err = genl_register_mc_group(&nl80211_fam, &nl80211_config_mcgrp);
-	if (err)
-		goto err_out;
-
-	err = genl_register_mc_group(&nl80211_fam, &nl80211_scan_mcgrp);
-	if (err)
-		goto err_out;
-
-	err = genl_register_mc_group(&nl80211_fam, &nl80211_regulatory_mcgrp);
-	if (err)
-		goto err_out;
-
-	err = genl_register_mc_group(&nl80211_fam, &nl80211_mlme_mcgrp);
-	if (err)
-		goto err_out;
-
-#ifdef CONFIG_NL80211_TESTMODE
-	err = genl_register_mc_group(&nl80211_fam, &nl80211_testmode_mcgrp);
-	if (err)
-		goto err_out;
-#endif
-
 	err = netlink_register_notifier(&nl80211_netlink_notifier);
 	if (err)
 		goto err_out;
-- 
cgit 


From c58f009e01c918717379c206a63baa66f56a77f9 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 14 Nov 2013 10:49:05 -0800
Subject: drm/ttm: Remove set_need_resched from the ttm fault handler

Addresses
"[BUG] completely bonkers use of set_need_resched + VM_FAULT_NOPAGE".

In the first occurence it was used to try to be nice while releasing the
mmap_sem and retrying the fault to work around a locking inversion.
The second occurence was never used.

There has been some discussion whether we should change the locking order to
mmap_sem -> bo_reserve. This patch doesn't address that issue, and leaves
that locking order undefined. The solution that we release the mmap_sem if
tryreserve fails and wait for the buffer to become unreserved is something
we want in any case, and follows how the core vm system waits for pages
to be come unlocked while releasing the mmap_sem.

The code also outlines what needs to be changed if we want to establish the
locking order as mmap_sem -> bo::reserve.

One slight issue that remains with this code is that the fault handler might
be prone to starvation if another thread countinously reserves the buffer.
IMO that usage pattern is highly unlikely.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 35 ++++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 26 ++++++++++++++++++++------
 include/drm/ttm/ttm_bo_api.h    |  4 +++-
 3 files changed, 57 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d5a646ebe6a..07e02c4bf5a8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -151,7 +151,7 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	atomic_dec(&bo->glob->bo_count);
 	if (bo->resv == &bo->ttm_resv)
 		reservation_object_fini(&bo->ttm_resv);
-
+	mutex_destroy(&bo->wu_mutex);
 	if (bo->destroy)
 		bo->destroy(bo);
 	else {
@@ -1123,6 +1123,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
 	INIT_LIST_HEAD(&bo->io_reserve_lru);
+	mutex_init(&bo->wu_mutex);
 	bo->bdev = bdev;
 	bo->glob = bdev->glob;
 	bo->type = type;
@@ -1704,3 +1705,35 @@ void ttm_bo_swapout_all(struct ttm_bo_device *bdev)
 		;
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
+
+/**
+ * ttm_bo_wait_unreserved - interruptible wait for a buffer object to become
+ * unreserved
+ *
+ * @bo: Pointer to buffer
+ */
+int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
+{
+	int ret;
+
+	/*
+	 * In the absense of a wait_unlocked API,
+	 * Use the bo::wu_mutex to avoid triggering livelocks due to
+	 * concurrent use of this function. Note that this use of
+	 * bo::wu_mutex can go away if we change locking order to
+	 * mmap_sem -> bo::reserve.
+	 */
+	ret = mutex_lock_interruptible(&bo->wu_mutex);
+	if (unlikely(ret != 0))
+		return -ERESTARTSYS;
+	if (!ww_mutex_is_locked(&bo->resv->lock))
+		goto out_unlock;
+	ret = ttm_bo_reserve_nolru(bo, true, false, false, NULL);
+	if (unlikely(ret != 0))
+		goto out_unlock;
+	ww_mutex_unlock(&bo->resv->lock);
+
+out_unlock:
+	mutex_unlock(&bo->wu_mutex);
+	return ret;
+}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index ac617f3ecd0c..b249ab9b1eb2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -107,13 +107,28 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/*
 	 * Work around locking order reversal in fault / nopfn
 	 * between mmap_sem and bo_reserve: Perform a trylock operation
-	 * for reserve, and if it fails, retry the fault after scheduling.
+	 * for reserve, and if it fails, retry the fault after waiting
+	 * for the buffer to become unreserved.
 	 */
-
-	ret = ttm_bo_reserve(bo, true, true, false, 0);
+	ret = ttm_bo_reserve(bo, true, true, false, NULL);
 	if (unlikely(ret != 0)) {
-		if (ret == -EBUSY)
-			set_need_resched();
+		if (ret != -EBUSY)
+			return VM_FAULT_NOPAGE;
+
+		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
+			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				up_read(&vma->vm_mm->mmap_sem);
+				(void) ttm_bo_wait_unreserved(bo);
+			}
+
+			return VM_FAULT_RETRY;
+		}
+
+		/*
+		 * If we'd want to change locking order to
+		 * mmap_sem -> bo::reserve, we'd use a blocking reserve here
+		 * instead of retrying the fault...
+		 */
 		return VM_FAULT_NOPAGE;
 	}
 
@@ -123,7 +138,6 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		case 0:
 			break;
 		case -EBUSY:
-			set_need_resched();
 		case -ERESTARTSYS:
 			retval = VM_FAULT_NOPAGE;
 			goto out_unlock;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 751eaffbf0d5..ee127ec33c60 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -169,6 +169,7 @@ struct ttm_tt;
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
  * @cur_placement: Hint of current placement.
+ * @wu_mutex: Wait unreserved mutex.
  *
  * Base class for TTM buffer object, that deals with data placement and CPU
  * mappings. GPU mappings are really up to the driver, but for simpler GPUs
@@ -250,6 +251,7 @@ struct ttm_buffer_object {
 
 	struct reservation_object *resv;
 	struct reservation_object ttm_resv;
+	struct mutex wu_mutex;
 };
 
 /**
@@ -702,5 +704,5 @@ extern ssize_t ttm_bo_io(struct ttm_bo_device *bdev, struct file *filp,
 			 size_t count, loff_t *f_pos, bool write);
 
 extern void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
-
+extern int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo);
 #endif
-- 
cgit 


From 125d0119d158180eb38580adfbc1a83d56120709 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Tue, 19 Nov 2013 09:07:46 +0100
Subject: target core: rename (ex,im)plict -> (ex,im)plicit

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_alua.c      | 110 ++++++++++++++++-----------------
 drivers/target/target_core_alua.h      |  20 +++---
 drivers/target/target_core_configfs.c  |  26 ++++----
 drivers/target/target_core_device.c    |   6 +-
 drivers/target/target_core_file.c      |   2 +-
 drivers/target/target_core_pr.c        |  24 +++----
 drivers/target/target_core_spc.c       |   6 +-
 drivers/target/target_core_transport.c |   4 +-
 drivers/target/target_core_ua.h        |   2 +-
 include/target/target_core_base.h      |   2 +-
 10 files changed, 101 insertions(+), 101 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 47244102281e..8297d3796d8c 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -44,7 +44,7 @@
 static sense_reason_t core_alua_check_transition(int state, int *primary);
 static int core_alua_set_tg_pt_secondary_state(
 		struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
-		struct se_port *port, int explict, int offline);
+		struct se_port *port, int explicit, int offline);
 
 static u16 alua_lu_gps_counter;
 static u32 alua_lu_gps_count;
@@ -175,7 +175,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 	if (ext_hdr != 0) {
 		buf[4] = 0x10;
 		/*
-		 * Set the implict transition time (in seconds) for the application
+		 * Set the implicit transition time (in seconds) for the application
 		 * client to use as a base for it's transition timeout value.
 		 *
 		 * Use the current tg_pt_gp_mem -> tg_pt_gp membership from the LUN
@@ -188,7 +188,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 			spin_lock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 			tg_pt_gp = tg_pt_gp_mem->tg_pt_gp;
 			if (tg_pt_gp)
-				buf[5] = tg_pt_gp->tg_pt_gp_implict_trans_secs;
+				buf[5] = tg_pt_gp->tg_pt_gp_implicit_trans_secs;
 			spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
 		}
 	}
@@ -199,7 +199,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 }
 
 /*
- * SET_TARGET_PORT_GROUPS for explict ALUA operation.
+ * SET_TARGET_PORT_GROUPS for explicit ALUA operation.
  *
  * See spc4r17 section 6.35
  */
@@ -232,7 +232,7 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	/*
-	 * Determine if explict ALUA via SET_TARGET_PORT_GROUPS is allowed
+	 * Determine if explicit ALUA via SET_TARGET_PORT_GROUPS is allowed
 	 * for the local tg_pt_gp.
 	 */
 	l_tg_pt_gp_mem = l_port->sep_alua_tg_pt_gp_mem;
@@ -251,9 +251,9 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 	}
 	spin_unlock(&l_tg_pt_gp_mem->tg_pt_gp_mem_lock);
 
-	if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA)) {
+	if (!(l_tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)) {
 		pr_debug("Unable to process SET_TARGET_PORT_GROUPS"
-				" while TPGS_EXPLICT_ALUA is disabled\n");
+				" while TPGS_EXPLICIT_ALUA is disabled\n");
 		rc = TCM_UNSUPPORTED_SCSI_OPCODE;
 		goto out;
 	}
@@ -620,7 +620,7 @@ out:
 }
 
 /*
- * Check implict and explict ALUA state change request.
+ * Check implicit and explicit ALUA state change request.
  */
 static sense_reason_t
 core_alua_check_transition(int state, int *primary)
@@ -676,10 +676,10 @@ char *core_alua_dump_status(int status)
 	switch (status) {
 	case ALUA_STATUS_NONE:
 		return "None";
-	case ALUA_STATUS_ALTERED_BY_EXPLICT_STPG:
-		return "Altered by Explict STPG";
-	case ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA:
-		return "Altered by Implict ALUA";
+	case ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG:
+		return "Altered by Explicit STPG";
+	case ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA:
+		return "Altered by Implicit ALUA";
 	default:
 		return "Unknown";
 	}
@@ -770,7 +770,7 @@ static int core_alua_do_transition_tg_pt(
 	struct se_node_acl *nacl,
 	unsigned char *md_buf,
 	int new_state,
-	int explict)
+	int explicit)
 {
 	struct se_dev_entry *se_deve;
 	struct se_lun_acl *lacl;
@@ -784,9 +784,9 @@ static int core_alua_do_transition_tg_pt(
 	old_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
 	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
 			ALUA_ACCESS_STATE_TRANSITION);
-	tg_pt_gp->tg_pt_gp_alua_access_status = (explict) ?
-				ALUA_STATUS_ALTERED_BY_EXPLICT_STPG :
-				ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA;
+	tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
+				ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
+				ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
 	/*
 	 * Check for the optional ALUA primary state transition delay
 	 */
@@ -821,12 +821,12 @@ static int core_alua_do_transition_tg_pt(
 			lacl = se_deve->se_lun_acl;
 			/*
 			 * se_deve->se_lun_acl pointer may be NULL for a
-			 * entry created without explict Node+MappedLUN ACLs
+			 * entry created without explicit Node+MappedLUN ACLs
 			 */
 			if (!lacl)
 				continue;
 
-			if (explict &&
+			if (explicit &&
 			   (nacl != NULL) && (nacl == lacl->se_lun_nacl) &&
 			   (l_port != NULL) && (l_port == port))
 				continue;
@@ -866,8 +866,8 @@ static int core_alua_do_transition_tg_pt(
 	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state, new_state);
 
 	pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
-		" from primary access state %s to %s\n", (explict) ? "explict" :
-		"implict", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+		" from primary access state %s to %s\n", (explicit) ? "explicit" :
+		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
 		tg_pt_gp->tg_pt_gp_id, core_alua_dump_state(old_state),
 		core_alua_dump_state(new_state));
 
@@ -880,7 +880,7 @@ int core_alua_do_port_transition(
 	struct se_port *l_port,
 	struct se_node_acl *l_nacl,
 	int new_state,
-	int explict)
+	int explicit)
 {
 	struct se_device *dev;
 	struct se_port *port;
@@ -917,7 +917,7 @@ int core_alua_do_port_transition(
 		 * success.
 		 */
 		core_alua_do_transition_tg_pt(l_tg_pt_gp, l_port, l_nacl,
-					md_buf, new_state, explict);
+					md_buf, new_state, explicit);
 		atomic_dec(&lu_gp->lu_gp_ref_cnt);
 		smp_mb__after_atomic_dec();
 		kfree(md_buf);
@@ -970,7 +970,7 @@ int core_alua_do_port_transition(
 			 * success.
 			 */
 			core_alua_do_transition_tg_pt(tg_pt_gp, port,
-					nacl, md_buf, new_state, explict);
+					nacl, md_buf, new_state, explicit);
 
 			spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 			atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
@@ -987,7 +987,7 @@ int core_alua_do_port_transition(
 	pr_debug("Successfully processed LU Group: %s all ALUA TG PT"
 		" Group IDs: %hu %s transition to primary state: %s\n",
 		config_item_name(&lu_gp->lu_gp_group.cg_item),
-		l_tg_pt_gp->tg_pt_gp_id, (explict) ? "explict" : "implict",
+		l_tg_pt_gp->tg_pt_gp_id, (explicit) ? "explicit" : "implicit",
 		core_alua_dump_state(new_state));
 
 	atomic_dec(&lu_gp->lu_gp_ref_cnt);
@@ -1034,7 +1034,7 @@ static int core_alua_update_tpg_secondary_metadata(
 static int core_alua_set_tg_pt_secondary_state(
 	struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem,
 	struct se_port *port,
-	int explict,
+	int explicit,
 	int offline)
 {
 	struct t10_alua_tg_pt_gp *tg_pt_gp;
@@ -1061,13 +1061,13 @@ static int core_alua_set_tg_pt_secondary_state(
 		atomic_set(&port->sep_tg_pt_secondary_offline, 0);
 
 	md_buf_len = tg_pt_gp->tg_pt_gp_md_buf_len;
-	port->sep_tg_pt_secondary_stat = (explict) ?
-			ALUA_STATUS_ALTERED_BY_EXPLICT_STPG :
-			ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA;
+	port->sep_tg_pt_secondary_stat = (explicit) ?
+			ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
+			ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
 
 	pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
-		" to secondary access state: %s\n", (explict) ? "explict" :
-		"implict", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+		" to secondary access state: %s\n", (explicit) ? "explicit" :
+		"implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
 		tg_pt_gp->tg_pt_gp_id, (offline) ? "OFFLINE" : "ONLINE");
 
 	spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock);
@@ -1356,16 +1356,16 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
 	atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
 		ALUA_ACCESS_STATE_ACTIVE_OPTMIZED);
 	/*
-	 * Enable both explict and implict ALUA support by default
+	 * Enable both explicit and implicit ALUA support by default
 	 */
 	tg_pt_gp->tg_pt_gp_alua_access_type =
-			TPGS_EXPLICT_ALUA | TPGS_IMPLICT_ALUA;
+			TPGS_EXPLICIT_ALUA | TPGS_IMPLICIT_ALUA;
 	/*
 	 * Set the default Active/NonOptimized Delay in milliseconds
 	 */
 	tg_pt_gp->tg_pt_gp_nonop_delay_msecs = ALUA_DEFAULT_NONOP_DELAY_MSECS;
 	tg_pt_gp->tg_pt_gp_trans_delay_msecs = ALUA_DEFAULT_TRANS_DELAY_MSECS;
-	tg_pt_gp->tg_pt_gp_implict_trans_secs = ALUA_DEFAULT_IMPLICT_TRANS_SECS;
+	tg_pt_gp->tg_pt_gp_implicit_trans_secs = ALUA_DEFAULT_IMPLICIT_TRANS_SECS;
 
 	if (def_group) {
 		spin_lock(&dev->t10_alua.tg_pt_gps_lock);
@@ -1465,7 +1465,7 @@ void core_alua_free_tg_pt_gp(
 	 * been called from target_core_alua_drop_tg_pt_gp().
 	 *
 	 * Here we remove *tg_pt_gp from the global list so that
-	 * no assications *OR* explict ALUA via SET_TARGET_PORT_GROUPS
+	 * no assications *OR* explicit ALUA via SET_TARGET_PORT_GROUPS
 	 * can be made while we are releasing struct t10_alua_tg_pt_gp.
 	 */
 	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
@@ -1740,13 +1740,13 @@ ssize_t core_alua_show_access_type(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	char *page)
 {
-	if ((tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA) &&
-	    (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA))
-		return sprintf(page, "Implict and Explict\n");
-	else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA)
-		return sprintf(page, "Implict\n");
-	else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICT_ALUA)
-		return sprintf(page, "Explict\n");
+	if ((tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA) &&
+	    (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA))
+		return sprintf(page, "Implicit and Explicit\n");
+	else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA)
+		return sprintf(page, "Implicit\n");
+	else if (tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_EXPLICIT_ALUA)
+		return sprintf(page, "Explicit\n");
 	else
 		return sprintf(page, "None\n");
 }
@@ -1771,11 +1771,11 @@ ssize_t core_alua_store_access_type(
 	}
 	if (tmp == 3)
 		tg_pt_gp->tg_pt_gp_alua_access_type =
-			TPGS_IMPLICT_ALUA | TPGS_EXPLICT_ALUA;
+			TPGS_IMPLICIT_ALUA | TPGS_EXPLICIT_ALUA;
 	else if (tmp == 2)
-		tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICT_ALUA;
+		tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_EXPLICIT_ALUA;
 	else if (tmp == 1)
-		tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICT_ALUA;
+		tg_pt_gp->tg_pt_gp_alua_access_type = TPGS_IMPLICIT_ALUA;
 	else
 		tg_pt_gp->tg_pt_gp_alua_access_type = 0;
 
@@ -1844,14 +1844,14 @@ ssize_t core_alua_store_trans_delay_msecs(
 	return count;
 }
 
-ssize_t core_alua_show_implict_trans_secs(
+ssize_t core_alua_show_implicit_trans_secs(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	char *page)
 {
-	return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_implict_trans_secs);
+	return sprintf(page, "%d\n", tg_pt_gp->tg_pt_gp_implicit_trans_secs);
 }
 
-ssize_t core_alua_store_implict_trans_secs(
+ssize_t core_alua_store_implicit_trans_secs(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	const char *page,
 	size_t count)
@@ -1861,16 +1861,16 @@ ssize_t core_alua_store_implict_trans_secs(
 
 	ret = kstrtoul(page, 0, &tmp);
 	if (ret < 0) {
-		pr_err("Unable to extract implict_trans_secs\n");
+		pr_err("Unable to extract implicit_trans_secs\n");
 		return ret;
 	}
-	if (tmp > ALUA_MAX_IMPLICT_TRANS_SECS) {
-		pr_err("Passed implict_trans_secs: %lu, exceeds"
-			" ALUA_MAX_IMPLICT_TRANS_SECS: %d\n", tmp,
-			ALUA_MAX_IMPLICT_TRANS_SECS);
+	if (tmp > ALUA_MAX_IMPLICIT_TRANS_SECS) {
+		pr_err("Passed implicit_trans_secs: %lu, exceeds"
+			" ALUA_MAX_IMPLICIT_TRANS_SECS: %d\n", tmp,
+			ALUA_MAX_IMPLICIT_TRANS_SECS);
 		return  -EINVAL;
 	}
-	tg_pt_gp->tg_pt_gp_implict_trans_secs = (int)tmp;
+	tg_pt_gp->tg_pt_gp_implicit_trans_secs = (int)tmp;
 
 	return count;
 }
@@ -1970,8 +1970,8 @@ ssize_t core_alua_store_secondary_status(
 		return ret;
 	}
 	if ((tmp != ALUA_STATUS_NONE) &&
-	    (tmp != ALUA_STATUS_ALTERED_BY_EXPLICT_STPG) &&
-	    (tmp != ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA)) {
+	    (tmp != ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+	    (tmp != ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA)) {
 		pr_err("Illegal value for alua_tg_pt_status: %lu\n",
 				tmp);
 		return -EINVAL;
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index e539c3e7f4ad..74cf0c0581e6 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -7,8 +7,8 @@
  * from spc4r17 section 6.4.2 Table 135
  */
 #define TPGS_NO_ALUA				0x00
-#define TPGS_IMPLICT_ALUA			0x10
-#define TPGS_EXPLICT_ALUA			0x20
+#define TPGS_IMPLICIT_ALUA			0x10
+#define TPGS_EXPLICIT_ALUA			0x20
 
 /*
  * ASYMMETRIC ACCESS STATE field
@@ -28,8 +28,8 @@
  * from spc4r17 section 6.27 Table 246
  */
 #define ALUA_STATUS_NONE				0x00
-#define ALUA_STATUS_ALTERED_BY_EXPLICT_STPG		0x01
-#define ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA		0x02
+#define ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG		0x01
+#define ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA		0x02
 
 /*
  * From spc4r17, Table D.1: ASC and ASCQ Assignement
@@ -46,17 +46,17 @@
 #define ALUA_DEFAULT_NONOP_DELAY_MSECS			100
 #define ALUA_MAX_NONOP_DELAY_MSECS			10000 /* 10 seconds */
 /*
- * Used for implict and explict ALUA transitional delay, that is disabled
+ * Used for implicit and explicit ALUA transitional delay, that is disabled
  * by default, and is intended to be used for debugging client side ALUA code.
  */
 #define ALUA_DEFAULT_TRANS_DELAY_MSECS			0
 #define ALUA_MAX_TRANS_DELAY_MSECS			30000 /* 30 seconds */
 /*
- * Used for the recommended application client implict transition timeout
+ * Used for the recommended application client implicit transition timeout
  * in seconds, returned by the REPORT_TARGET_PORT_GROUPS w/ extended header.
  */
-#define ALUA_DEFAULT_IMPLICT_TRANS_SECS			0
-#define ALUA_MAX_IMPLICT_TRANS_SECS			255
+#define ALUA_DEFAULT_IMPLICIT_TRANS_SECS			0
+#define ALUA_MAX_IMPLICIT_TRANS_SECS			255
 /*
  * Used by core_alua_update_tpg_primary_metadata() and
  * core_alua_update_tpg_secondary_metadata()
@@ -113,9 +113,9 @@ extern ssize_t core_alua_show_trans_delay_msecs(struct t10_alua_tg_pt_gp *,
 					char *);
 extern ssize_t core_alua_store_trans_delay_msecs(struct t10_alua_tg_pt_gp *,
 					const char *, size_t);
-extern ssize_t core_alua_show_implict_trans_secs(struct t10_alua_tg_pt_gp *,
+extern ssize_t core_alua_show_implicit_trans_secs(struct t10_alua_tg_pt_gp *,
 					char *);
-extern ssize_t core_alua_store_implict_trans_secs(struct t10_alua_tg_pt_gp *,
+extern ssize_t core_alua_store_implicit_trans_secs(struct t10_alua_tg_pt_gp *,
 					const char *, size_t);
 extern ssize_t core_alua_show_preferred_bit(struct t10_alua_tg_pt_gp *,
 					char *);
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index b04edc12f9d5..3a964fbf50ee 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2036,7 +2036,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 	int new_state, ret;
 
 	if (!tg_pt_gp->tg_pt_gp_valid_id) {
-		pr_err("Unable to do implict ALUA on non valid"
+		pr_err("Unable to do implicit ALUA on non valid"
 			" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
 		return -EINVAL;
 	}
@@ -2049,9 +2049,9 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 	}
 	new_state = (int)tmp;
 
-	if (!(tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICT_ALUA)) {
-		pr_err("Unable to process implict configfs ALUA"
-			" transition while TPGS_IMPLICT_ALUA is disabled\n");
+	if (!(tg_pt_gp->tg_pt_gp_alua_access_type & TPGS_IMPLICIT_ALUA)) {
+		pr_err("Unable to process implicit configfs ALUA"
+			" transition while TPGS_IMPLICIT_ALUA is disabled\n");
 		return -EINVAL;
 	}
 
@@ -2097,8 +2097,8 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_status(
 	new_status = (int)tmp;
 
 	if ((new_status != ALUA_STATUS_NONE) &&
-	    (new_status != ALUA_STATUS_ALTERED_BY_EXPLICT_STPG) &&
-	    (new_status != ALUA_STATUS_ALTERED_BY_IMPLICT_ALUA)) {
+	    (new_status != ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG) &&
+	    (new_status != ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA)) {
 		pr_err("Illegal ALUA access status: 0x%02x\n",
 				new_status);
 		return -EINVAL;
@@ -2210,24 +2210,24 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_trans_delay_msecs(
 SE_DEV_ALUA_TG_PT_ATTR(trans_delay_msecs, S_IRUGO | S_IWUSR);
 
 /*
- * implict_trans_secs
+ * implicit_trans_secs
  */
-static ssize_t target_core_alua_tg_pt_gp_show_attr_implict_trans_secs(
+static ssize_t target_core_alua_tg_pt_gp_show_attr_implicit_trans_secs(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	char *page)
 {
-	return core_alua_show_implict_trans_secs(tg_pt_gp, page);
+	return core_alua_show_implicit_trans_secs(tg_pt_gp, page);
 }
 
-static ssize_t target_core_alua_tg_pt_gp_store_attr_implict_trans_secs(
+static ssize_t target_core_alua_tg_pt_gp_store_attr_implicit_trans_secs(
 	struct t10_alua_tg_pt_gp *tg_pt_gp,
 	const char *page,
 	size_t count)
 {
-	return core_alua_store_implict_trans_secs(tg_pt_gp, page, count);
+	return core_alua_store_implicit_trans_secs(tg_pt_gp, page, count);
 }
 
-SE_DEV_ALUA_TG_PT_ATTR(implict_trans_secs, S_IRUGO | S_IWUSR);
+SE_DEV_ALUA_TG_PT_ATTR(implicit_trans_secs, S_IRUGO | S_IWUSR);
 
 /*
  * preferred
@@ -2353,7 +2353,7 @@ static struct configfs_attribute *target_core_alua_tg_pt_gp_attrs[] = {
 	&target_core_alua_tg_pt_gp_alua_write_metadata.attr,
 	&target_core_alua_tg_pt_gp_nonop_delay_msecs.attr,
 	&target_core_alua_tg_pt_gp_trans_delay_msecs.attr,
-	&target_core_alua_tg_pt_gp_implict_trans_secs.attr,
+	&target_core_alua_tg_pt_gp_implicit_trans_secs.attr,
 	&target_core_alua_tg_pt_gp_preferred.attr,
 	&target_core_alua_tg_pt_gp_tg_pt_gp_id.attr,
 	&target_core_alua_tg_pt_gp_members.attr,
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 986afd2ee3f6..207b340498a3 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -313,14 +313,14 @@ int core_enable_device_list_for_node(
 	deve = nacl->device_list[mapped_lun];
 
 	/*
-	 * Check if the call is handling demo mode -> explict LUN ACL
+	 * Check if the call is handling demo mode -> explicit LUN ACL
 	 * transition.  This transition must be for the same struct se_lun
 	 * + mapped_lun that was setup in demo mode..
 	 */
 	if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) {
 		if (deve->se_lun_acl != NULL) {
 			pr_err("struct se_dev_entry->se_lun_acl"
-			       " already set for demo mode -> explict"
+			       " already set for demo mode -> explicit"
 			       " LUN ACL transition\n");
 			spin_unlock_irq(&nacl->device_list_lock);
 			return -EINVAL;
@@ -328,7 +328,7 @@ int core_enable_device_list_for_node(
 		if (deve->se_lun != lun) {
 			pr_err("struct se_dev_entry->se_lun does"
 			       " match passed struct se_lun for demo mode"
-			       " -> explict LUN ACL transition\n");
+			       " -> explicit LUN ACL transition\n");
 			spin_unlock_irq(&nacl->device_list_lock);
 			return -EINVAL;
 		}
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index b662f89dedac..0e34cda3271e 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -562,7 +562,7 @@ fd_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	} else {
 		ret = fd_do_rw(cmd, sgl, sgl_nents, 1);
 		/*
-		 * Perform implict vfs_fsync_range() for fd_do_writev() ops
+		 * Perform implicit vfs_fsync_range() for fd_do_writev() ops
 		 * for SCSI WRITEs with Forced Unit Access (FUA) set.
 		 * Allow this to happen independent of WCE=0 setting.
 		 */
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index d1ae4c5c3ffd..2f5d77932c80 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -474,7 +474,7 @@ static int core_scsi3_pr_seq_non_holder(
 	 * statement.
 	 */
 	if (!ret && !other_cdb) {
-		pr_debug("Allowing explict CDB: 0x%02x for %s"
+		pr_debug("Allowing explicit CDB: 0x%02x for %s"
 			" reservation holder\n", cdb[0],
 			core_scsi3_pr_dump_type(pr_reg_type));
 
@@ -507,7 +507,7 @@ static int core_scsi3_pr_seq_non_holder(
 			 */
 
 			if (!registered_nexus) {
-				pr_debug("Allowing implict CDB: 0x%02x"
+				pr_debug("Allowing implicit CDB: 0x%02x"
 					" for %s reservation on unregistered"
 					" nexus\n", cdb[0],
 					core_scsi3_pr_dump_type(pr_reg_type));
@@ -522,7 +522,7 @@ static int core_scsi3_pr_seq_non_holder(
 			 * allow commands from registered nexuses.
 			 */
 
-			pr_debug("Allowing implict CDB: 0x%02x for %s"
+			pr_debug("Allowing implicit CDB: 0x%02x for %s"
 				" reservation\n", cdb[0],
 				core_scsi3_pr_dump_type(pr_reg_type));
 
@@ -683,7 +683,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration(
 					alua_port_list) {
 			/*
 			 * This pointer will be NULL for demo mode MappedLUNs
-			 * that have not been make explict via a ConfigFS
+			 * that have not been make explicit via a ConfigFS
 			 * MappedLUN group for the SCSI Initiator Node ACL.
 			 */
 			if (!deve_tmp->se_lun_acl)
@@ -1158,7 +1158,7 @@ static void core_scsi3_put_pr_reg(struct t10_pr_registration *pr_reg)
 	smp_mb__after_atomic_dec();
 }
 
-static int core_scsi3_check_implict_release(
+static int core_scsi3_check_implicit_release(
 	struct se_device *dev,
 	struct t10_pr_registration *pr_reg)
 {
@@ -1174,7 +1174,7 @@ static int core_scsi3_check_implict_release(
 	}
 	if (pr_res_holder == pr_reg) {
 		/*
-		 * Perform an implict RELEASE if the registration that
+		 * Perform an implicit RELEASE if the registration that
 		 * is being released is holding the reservation.
 		 *
 		 * From spc4r17, section 5.7.11.1:
@@ -1192,7 +1192,7 @@ static int core_scsi3_check_implict_release(
 		 * For 'All Registrants' reservation types, all existing
 		 * registrations are still processed as reservation holders
 		 * in core_scsi3_pr_seq_non_holder() after the initial
-		 * reservation holder is implictly released here.
+		 * reservation holder is implicitly released here.
 		 */
 	} else if (pr_reg->pr_reg_all_tg_pt &&
 		  (!strcmp(pr_res_holder->pr_reg_nacl->initiatorname,
@@ -2125,7 +2125,7 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key,
 		/*
 		 * sa_res_key=0 Unregister Reservation Key for registered I_T Nexus.
 		 */
-		pr_holder = core_scsi3_check_implict_release(
+		pr_holder = core_scsi3_check_implicit_release(
 				cmd->se_dev, pr_reg);
 		if (pr_holder < 0) {
 			ret = TCM_RESERVATION_CONFLICT;
@@ -2402,7 +2402,7 @@ static void __core_scsi3_complete_pro_release(
 	struct se_device *dev,
 	struct se_node_acl *se_nacl,
 	struct t10_pr_registration *pr_reg,
-	int explict)
+	int explicit)
 {
 	struct target_core_fabric_ops *tfo = se_nacl->se_tpg->se_tpg_tfo;
 	char i_buf[PR_REG_ISID_ID_LEN];
@@ -2416,7 +2416,7 @@ static void __core_scsi3_complete_pro_release(
 
 	pr_debug("SPC-3 PR [%s] Service Action: %s RELEASE cleared"
 		" reservation holder TYPE: %s ALL_TG_PT: %d\n",
-		tfo->get_fabric_name(), (explict) ? "explict" : "implict",
+		tfo->get_fabric_name(), (explicit) ? "explicit" : "implicit",
 		core_scsi3_pr_dump_type(pr_reg->pr_res_type),
 		(pr_reg->pr_reg_all_tg_pt) ? 1 : 0);
 	pr_debug("SPC-3 PR [%s] RELEASE Node: %s%s\n",
@@ -2692,7 +2692,7 @@ static void __core_scsi3_complete_pro_preempt(
 	memset(i_buf, 0, PR_REG_ISID_ID_LEN);
 	core_pr_dump_initiator_port(pr_reg, i_buf, PR_REG_ISID_ID_LEN);
 	/*
-	 * Do an implict RELEASE of the existing reservation.
+	 * Do an implicit RELEASE of the existing reservation.
 	 */
 	if (dev->dev_pr_res_holder)
 		__core_scsi3_complete_pro_release(dev, nacl,
@@ -2845,7 +2845,7 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
 				 * 5.7.11.4 Preempting, Table 52 and Figure 7.
 				 *
 				 * For a ZERO SA Reservation key, release
-				 * all other registrations and do an implict
+				 * all other registrations and do an implicit
 				 * release of active persistent reservation.
 				 *
 				 * For a non-ZERO SA Reservation key, only
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index f89a86f29ee3..021c3f4a4f00 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -48,7 +48,7 @@ static void spc_fill_alua_data(struct se_port *port, unsigned char *buf)
 	buf[5]	= 0x80;
 
 	/*
-	 * Set TPGS field for explict and/or implict ALUA access type
+	 * Set TPGS field for explicit and/or implicit ALUA access type
 	 * and opteration.
 	 *
 	 * See spc4r17 section 6.4.2 Table 135
@@ -1257,7 +1257,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		*size = (cdb[3] << 8) + cdb[4];
 
 		/*
-		 * Do implict HEAD_OF_QUEUE processing for INQUIRY.
+		 * Do implicit HEAD_OF_QUEUE processing for INQUIRY.
 		 * See spc4r17 section 5.3
 		 */
 		cmd->sam_task_attr = MSG_HEAD_TAG;
@@ -1291,7 +1291,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size)
 		cmd->execute_cmd = spc_emulate_report_luns;
 		*size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9];
 		/*
-		 * Do implict HEAD_OF_QUEUE processing for REPORT_LUNS
+		 * Do implicit HEAD_OF_QUEUE processing for REPORT_LUNS
 		 * See spc4r17 section 5.3
 		 */
 		cmd->sam_task_attr = MSG_HEAD_TAG;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 46d82295fac9..269a7987dab9 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -462,7 +462,7 @@ void transport_deregister_session(struct se_session *se_sess)
 	pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
 		se_tpg->se_tpg_tfo->get_fabric_name());
 	/*
-	 * If last kref is dropping now for an explict NodeACL, awake sleeping
+	 * If last kref is dropping now for an explicit NodeACL, awake sleeping
 	 * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
 	 * removal context.
 	 */
@@ -636,7 +636,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 		cmd->transport_state |= CMD_T_FAILED;
 
 	/*
-	 * Check for case where an explict ABORT_TASK has been received
+	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
 	 */
 	if (cmd->transport_state & CMD_T_ABORTED &&
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index 0204952fe4d3..be912b36daae 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -19,7 +19,7 @@
 #define ASCQ_2AH_RESERVATIONS_RELEASED				0x04
 #define ASCQ_2AH_REGISTRATIONS_PREEMPTED			0x05
 #define ASCQ_2AH_ASYMMETRIC_ACCESS_STATE_CHANGED		0x06
-#define ASCQ_2AH_IMPLICT_ASYMMETRIC_ACCESS_STATE_TRANSITION_FAILED 0x07
+#define ASCQ_2AH_IMPLICIT_ASYMMETRIC_ACCESS_STATE_TRANSITION_FAILED 0x07
 #define ASCQ_2AH_PRIORITY_CHANGED				0x08
 
 #define ASCQ_2CH_PREVIOUS_RESERVATION_CONFLICT_STATUS		0x09
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index fab91baf8ef4..3b0b64aefc27 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -287,7 +287,7 @@ struct t10_alua_tg_pt_gp {
 	int	tg_pt_gp_alua_access_type;
 	int	tg_pt_gp_nonop_delay_msecs;
 	int	tg_pt_gp_trans_delay_msecs;
-	int	tg_pt_gp_implict_trans_secs;
+	int	tg_pt_gp_implicit_trans_secs;
 	int	tg_pt_gp_pref;
 	int	tg_pt_gp_write_metadata;
 	/* Used by struct t10_alua_tg_pt_gp->tg_pt_gp_md_buf_len */
-- 
cgit 


From c0dc941e2bdfad4deccf3ba2626f485b5a5f59a4 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Tue, 19 Nov 2013 09:07:49 +0100
Subject: target_core_alua: Store supported ALUA states

The supported ALUA states might be different for individual
devices, so store it in a separate field.

(nab: Remove unnecessary line continuation)

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
---
 drivers/target/target_core_alua.c | 14 ++++++++------
 drivers/target/target_core_alua.h | 11 +++++++++++
 include/target/target_core_base.h |  1 +
 3 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 08e41e33ab91..fdcee326bfbc 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -117,12 +117,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd)
 		/*
 		 * Set supported ASYMMETRIC ACCESS State bits
 		 */
-		buf[off] = 0x80; /* T_SUP */
-		buf[off] |= 0x40; /* O_SUP */
-		buf[off] |= 0x8; /* U_SUP */
-		buf[off] |= 0x4; /* S_SUP */
-		buf[off] |= 0x2; /* AN_SUP */
-		buf[off++] |= 0x1; /* AO_SUP */
+		buf[off++] |= tg_pt_gp->tg_pt_gp_alua_supported_states;
 		/*
 		 * TARGET PORT GROUP
 		 */
@@ -1367,6 +1362,13 @@ struct t10_alua_tg_pt_gp *core_alua_allocate_tg_pt_gp(struct se_device *dev,
 	tg_pt_gp->tg_pt_gp_trans_delay_msecs = ALUA_DEFAULT_TRANS_DELAY_MSECS;
 	tg_pt_gp->tg_pt_gp_implicit_trans_secs = ALUA_DEFAULT_IMPLICIT_TRANS_SECS;
 
+	/*
+	 * Enable all supported states
+	 */
+	tg_pt_gp->tg_pt_gp_alua_supported_states =
+	    ALUA_T_SUP | ALUA_O_SUP |
+	    ALUA_U_SUP | ALUA_S_SUP | ALUA_AN_SUP | ALUA_AO_SUP;
+
 	if (def_group) {
 		spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 		tg_pt_gp->tg_pt_gp_id =
diff --git a/drivers/target/target_core_alua.h b/drivers/target/target_core_alua.h
index d6db78b3e9e4..88e2e835f14a 100644
--- a/drivers/target/target_core_alua.h
+++ b/drivers/target/target_core_alua.h
@@ -22,6 +22,17 @@
 #define ALUA_ACCESS_STATE_OFFLINE		0xe
 #define ALUA_ACCESS_STATE_TRANSITION		0xf
 
+/*
+ * from spc4r36j section 6.37 Table 306
+ */
+#define ALUA_T_SUP		0x80
+#define ALUA_O_SUP		0x40
+#define ALUA_LBD_SUP		0x10
+#define ALUA_U_SUP		0x08
+#define ALUA_S_SUP		0x04
+#define ALUA_AN_SUP		0x02
+#define ALUA_AO_SUP		0x01
+
 /*
  * REPORT_TARGET_PORT_GROUP STATUS CODE
  *
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 3b0b64aefc27..45412a6afa69 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -283,6 +283,7 @@ struct t10_alua_lu_gp_member {
 struct t10_alua_tg_pt_gp {
 	u16	tg_pt_gp_id;
 	int	tg_pt_gp_valid_id;
+	int	tg_pt_gp_alua_supported_states;
 	int	tg_pt_gp_alua_access_status;
 	int	tg_pt_gp_alua_access_type;
 	int	tg_pt_gp_nonop_delay_msecs;
-- 
cgit 


From 8b2e9b712f6139df9c754af0d67fecc4bbc88545 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 20 Nov 2013 14:41:47 -0800
Subject: Revert "mm: create a separate slab for page->ptl allocation"

This reverts commit ea1e7ed33708c7a760419ff9ded0a6cb90586a50.

Al points out that while the commit *does* actually create a separate
slab for the page->ptl allocation, that slab is never actually used, and
the code continues to use kmalloc/kfree.

Damien Wyart points out that the original patch did have the conversion
to use kmem_cache_alloc/free, so it got lost somewhere on its way to me.

Revert the half-arsed attempt that didn't do anything.  If we really do
want the special slab (remember: this is all relevant just for debug
builds, so it's not necessarily all that critical) we might as well redo
the patch fully.

Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Kirill A Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 9 ---------
 init/main.c        | 2 +-
 mm/memory.c        | 7 -------
 3 files changed, 1 insertion(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0548eb201e05..1cedd000cf29 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1318,7 +1318,6 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 
 #if USE_SPLIT_PTE_PTLOCKS
 #if BLOATED_SPINLOCKS
-void __init ptlock_cache_init(void);
 extern bool ptlock_alloc(struct page *page);
 extern void ptlock_free(struct page *page);
 
@@ -1327,7 +1326,6 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
 	return page->ptl;
 }
 #else /* BLOATED_SPINLOCKS */
-static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_alloc(struct page *page)
 {
 	return true;
@@ -1380,17 +1378,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
-static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_init(struct page *page) { return true; }
 static inline void pte_lock_deinit(struct page *page) {}
 #endif /* USE_SPLIT_PTE_PTLOCKS */
 
-static inline void pgtable_init(void)
-{
-	ptlock_cache_init();
-	pgtable_cache_init();
-}
-
 static inline bool pgtable_page_ctor(struct page *page)
 {
 	inc_zone_page_state(page, NR_PAGETABLE);
diff --git a/init/main.c b/init/main.c
index 01573fdfa186..febc511e078a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -476,7 +476,7 @@ static void __init mm_init(void)
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
-	pgtable_init();
+	pgtable_cache_init();
 	vmalloc_init();
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 0409e8f43fa0..5d9025f3b3e1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4272,13 +4272,6 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
 #if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
-static struct kmem_cache *page_ptl_cachep;
-void __init ptlock_cache_init(void)
-{
-	page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0,
-			SLAB_PANIC, NULL);
-}
-
 bool ptlock_alloc(struct page *page)
 {
 	spinlock_t *ptl;
-- 
cgit 


From 4cd8587ce8fb79e49d1d6d1fc065f056188fb86a Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Nov 2013 22:57:29 -0500
Subject: btrfs: Use trace condition for get_extent tracepoint

Doing an if statement to test some condition to know if we should
trigger a tracepoint is pointless when tracing is disabled. This just
adds overhead and wastes a branch prediction. This is why the
TRACE_EVENT_CONDITION() was created. It places the check inside the jump
label so that the branch does not happen unless tracing is enabled.

That is, instead of doing:

	if (em)
		trace_btrfs_get_extent(root, em);

Which is basically this:

	if (em)
		if (static_key(trace_btrfs_get_extent)) {

Using a TRACE_EVENT_CONDITION() we can just do:

	trace_btrfs_get_extent(root, em);

And the condition trace event will do:

	if (static_key(trace_btrfs_get_extent)) {
		if (em) {
			...

The static key is a non conditional jump (or nop) that is faster than
having to check if em is NULL or not.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
---
 fs/btrfs/inode.c             | 3 +--
 include/trace/events/btrfs.h | 4 +++-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fd67b34e220d..f1a77449d032 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6187,8 +6187,7 @@ insert:
 	write_unlock(&em_tree->lock);
 out:
 
-	if (em)
-		trace_btrfs_get_extent(root, em);
+	trace_btrfs_get_extent(root, em);
 
 	if (path)
 		btrfs_free_path(path);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f18b3b76e01e..4832d75dcbae 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -162,12 +162,14 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 		{ EXTENT_FLAG_LOGGING,	 	"LOGGING" 	},	\
 		{ EXTENT_FLAG_FILLING,	 	"FILLING" 	})
 
-TRACE_EVENT(btrfs_get_extent,
+TRACE_EVENT_CONDITION(btrfs_get_extent,
 
 	TP_PROTO(struct btrfs_root *root, struct extent_map *map),
 
 	TP_ARGS(root, map),
 
+	TP_CONDITION(map),
+
 	TP_STRUCT__entry(
 		__field(	u64,  root_objectid	)
 		__field(	u64,  start		)
-- 
cgit 


From f3d3342602f8bcbf37d7c46641cb9bca7618eb1c Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 21 Nov 2013 03:14:22 +0100
Subject: net: rework recvmsg handler msg_name and msg_namelen logic

This patch now always passes msg->msg_namelen as 0. recvmsg handlers must
set msg_namelen to the proper size <= sizeof(struct sockaddr_storage)
to return msg_name to the user.

This prevents numerous uninitialized memory leaks we had in the
recvmsg handlers and makes it harder for new code to accidentally leak
uninitialized memory.

Optimize for the case recvfrom is called with NULL as address. We don't
need to copy the address at all, so set it to NULL before invoking the
recvmsg handler. We can do so, because all the recvmsg handlers must
cope with the case a plain read() is called on them. read() also sets
msg_name to NULL.

Also document these changes in include/linux/net.h as suggested by David
Miller.

Changes since RFC:

Set msg->msg_name = NULL if user specified a NULL in msg_name but had a
non-null msg_namelen in verify_iovec/verify_compat_iovec. This doesn't
affect sendto as it would bail out earlier while trying to copy-in the
address. It also more naturally reflects the logic by the callers of
verify_iovec.

With this change in place I could remove "
if (!uaddr || msg_sys->msg_namelen == 0)
	msg->msg_name = NULL
".

This change does not alter the user visible error logic as we ignore
msg_namelen as long as msg_name is NULL.

Also remove two unnecessary curly brackets in ___sys_recvmsg and change
comments to netdev style.

Cc: David Miller <davem@davemloft.net>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/algif_hash.c            |  2 --
 crypto/algif_skcipher.c        |  1 -
 drivers/isdn/mISDN/socket.c    | 13 ++++---------
 drivers/net/ppp/pppoe.c        |  2 --
 include/linux/net.h            |  8 ++++++++
 net/appletalk/ddp.c            | 16 +++++++---------
 net/atm/common.c               |  2 --
 net/ax25/af_ax25.c             |  4 ++--
 net/bluetooth/af_bluetooth.c   |  9 ++-------
 net/bluetooth/hci_sock.c       |  2 --
 net/bluetooth/rfcomm/sock.c    |  1 -
 net/bluetooth/sco.c            |  1 -
 net/caif/caif_socket.c         |  4 ----
 net/compat.c                   |  3 ++-
 net/core/iovec.c               |  3 ++-
 net/ipx/af_ipx.c               |  3 +--
 net/irda/af_irda.c             |  4 ----
 net/iucv/af_iucv.c             |  2 --
 net/key/af_key.c               |  1 -
 net/l2tp/l2tp_ppp.c            |  2 --
 net/llc/af_llc.c               |  2 --
 net/netlink/af_netlink.c       |  2 --
 net/netrom/af_netrom.c         |  3 +--
 net/nfc/llcp_sock.c            |  2 --
 net/nfc/rawsock.c              |  2 --
 net/packet/af_packet.c         | 32 +++++++++++++++-----------------
 net/rds/recv.c                 |  2 --
 net/rose/af_rose.c             |  8 +++++---
 net/rxrpc/ar-recvmsg.c         |  9 ++++++---
 net/socket.c                   | 19 +++++++++++--------
 net/tipc/socket.c              |  6 ------
 net/unix/af_unix.c             |  5 -----
 net/vmw_vsock/af_vsock.c       |  2 --
 net/vmw_vsock/vmci_transport.c |  2 --
 net/x25/af_x25.c               |  3 +--
 35 files changed, 67 insertions(+), 115 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 0262210cad38..ef5356cd280a 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -161,8 +161,6 @@ static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
 	else if (len < ds)
 		msg->msg_flags |= MSG_TRUNC;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	if (ctx->more) {
 		ctx->more = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a1c4f0a55583..6a6dfc062d2a 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -432,7 +432,6 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 	long copied = 0;
 
 	lock_sock(sk);
-	msg->msg_namelen = 0;
 	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index e47dcb9d1e91..5cefb479c707 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -117,7 +117,6 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sk_buff		*skb;
 	struct sock		*sk = sock->sk;
-	struct sockaddr_mISDN	*maddr;
 
 	int		copied, err;
 
@@ -135,9 +134,9 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return err;
 
-	if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) {
-		msg->msg_namelen = sizeof(struct sockaddr_mISDN);
-		maddr = (struct sockaddr_mISDN *)msg->msg_name;
+	if (msg->msg_name) {
+		struct sockaddr_mISDN *maddr = msg->msg_name;
+
 		maddr->family = AF_ISDN;
 		maddr->dev = _pms(sk)->dev->id;
 		if ((sk->sk_protocol == ISDN_P_LAPD_TE) ||
@@ -150,11 +149,7 @@ mISDN_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 			maddr->sapi = _pms(sk)->ch.addr & 0xFF;
 			maddr->tei =  (_pms(sk)->ch.addr >> 8) & 0xFF;
 		}
-	} else {
-		if (msg->msg_namelen)
-			printk(KERN_WARNING "%s: too small namelen %d\n",
-			       __func__, msg->msg_namelen);
-		msg->msg_namelen = 0;
+		msg->msg_namelen = sizeof(*maddr);
 	}
 
 	copied = skb->len + MISDN_HEADER_LEN;
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 5f66e30d9823..82ee6ed954cb 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -979,8 +979,6 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (error < 0)
 		goto end;
 
-	m->msg_namelen = 0;
-
 	if (skb) {
 		total_len = min_t(size_t, total_len, skb->len);
 		error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
diff --git a/include/linux/net.h b/include/linux/net.h
index b292a0435571..4bcee94cef93 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -164,6 +164,14 @@ struct proto_ops {
 #endif
 	int		(*sendmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len);
+	/* Notes for implementing recvmsg:
+	 * ===============================
+	 * msg->msg_namelen should get updated by the recvmsg handlers
+	 * iff msg_name != NULL. It is by default 0 to prevent
+	 * returning uninitialized memory to user space.  The recvfrom
+	 * handlers can assume that msg.msg_name is either NULL or has
+	 * a minimum size of sizeof(struct sockaddr_storage).
+	 */
 	int		(*recvmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len,
 				      int flags);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 7fee50d637f9..7d424ac6e760 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1735,7 +1735,6 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 			 size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
 	struct ddpehdr *ddp;
 	int copied = 0;
 	int offset = 0;
@@ -1764,14 +1763,13 @@ static int atalk_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	}
 	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
 
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
+	if (!err && msg->msg_name) {
+		struct sockaddr_at *sat = msg->msg_name;
+		sat->sat_family      = AF_APPLETALK;
+		sat->sat_port        = ddp->deh_sport;
+		sat->sat_addr.s_node = ddp->deh_snode;
+		sat->sat_addr.s_net  = ddp->deh_snet;
+		msg->msg_namelen     = sizeof(*sat);
 	}
 
 	skb_free_datagram(sk, skb);	/* Free the datagram. */
diff --git a/net/atm/common.c b/net/atm/common.c
index 737bef59ce89..7b491006eaf4 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	struct sk_buff *skb;
 	int copied, error = -EINVAL;
 
-	msg->msg_namelen = 0;
-
 	if (sock->state != SS_CONNECTED)
 		return -ENOTCONN;
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a00123ebb0ae..7bb1605bdfd9 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (msg->msg_namelen != 0) {
-		struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+	if (msg->msg_name) {
 		ax25_digi digi;
 		ax25_address src;
 		const unsigned char *mac = skb_mac_header(skb);
+		struct sockaddr_ax25 *sax = msg->msg_name;
 
 		memset(sax, 0, sizeof(struct full_sockaddr_ax25));
 		ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index f6a1671ea2ff..56ca494621c6 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -224,10 +224,9 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
-		if (sk->sk_shutdown & RCV_SHUTDOWN) {
-			msg->msg_namelen = 0;
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			return 0;
-		}
+
 		return err;
 	}
 
@@ -245,8 +244,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		if (bt_sk(sk)->skb_msg_name)
 			bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
 						&msg->msg_namelen);
-		else
-			msg->msg_namelen = 0;
 	}
 
 	skb_free_datagram(sk, skb);
@@ -295,8 +292,6 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	BT_DBG("sk %p size %zu", sk, size);
 
 	lock_sock(sk);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 71f0be173080..6a6c8bb4fd72 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -856,8 +856,6 @@ static int hci_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return err;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index c4d3d423f89b..c80766f892c3 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -615,7 +615,6 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
 		rfcomm_dlc_accept(d);
-		msg->msg_namelen = 0;
 		return 0;
 	}
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 12a0e51e21e1..24fa3964b3c8 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -711,7 +711,6 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	    test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
 		sco_conn_defer_accept(pi->conn->hcon, pi->setting);
 		sk->sk_state = BT_CONFIG;
-		msg->msg_namelen = 0;
 
 		release_sock(sk);
 		return 0;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 05a41c7ec304..d6be3edb7a43 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -286,8 +286,6 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (m->msg_flags&MSG_OOB)
 		goto read_error;
 
-	m->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
 	if (!skb)
 		goto read_error;
@@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	/*
 	 * Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
diff --git a/net/compat.c b/net/compat.c
index 89032580bd1d..618c6a8a911b 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -93,7 +93,8 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 			if (err < 0)
 				return err;
 		}
-		kern_msg->msg_name = kern_address;
+		if (kern_msg->msg_name)
+			kern_msg->msg_name = kern_address;
 	} else
 		kern_msg->msg_name = NULL;
 
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 4cdb7c48dad6..b61869429f4c 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		m->msg_name = address;
+		if (m->msg_name)
+			m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
 	}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 7a1e0fc1bd4d..e096025b477f 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1823,8 +1823,6 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (skb->tstamp.tv64)
 		sk->sk_stamp = skb->tstamp;
 
-	msg->msg_namelen = sizeof(*sipx);
-
 	if (sipx) {
 		sipx->sipx_family	= AF_IPX;
 		sipx->sipx_port		= ipx->ipx_source.sock;
@@ -1832,6 +1830,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sipx->sipx_network	= IPX_SKB_CB(skb)->ipx_source_net;
 		sipx->sipx_type 	= ipx->ipx_type;
 		sipx->sipx_zero		= 0;
+		msg->msg_namelen	= sizeof(*sipx);
 	}
 	rc = copied;
 
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0f676908d15b..de7db23049f1 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock,
 
 	IRDA_DEBUG(4, "%s()\n", __func__);
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)
@@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
 
-	msg->msg_namelen = 0;
-
 	do {
 		int chunk;
 		struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 168aff5e60de..c4b7218058b6 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int err = 0;
 	u32 offset;
 
-	msg->msg_namelen = 0;
-
 	if ((sk->sk_state == IUCV_DISCONN) &&
 	    skb_queue_empty(&iucv->backlog_skb_q) &&
 	    skb_queue_empty(&sk->sk_receive_queue) &&
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 911ef03bf8fb..545f047868ad 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3616,7 +3616,6 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
 		goto out;
 
-	msg->msg_namelen = 0;
 	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index ffda81ef1a70..be5fadf34739 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sk->sk_state & PPPOX_BOUND)
 		goto end;
 
-	msg->msg_namelen = 0;
-
 	err = 0;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 6cba486353e8..7b01b9f5846c 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -720,8 +720,6 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 	int target;	/* Read at least this many bytes */
 	long timeo;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	copied = -ENOTCONN;
 	if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f0176e1a5a81..bca50b95c182 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2335,8 +2335,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
-	msg->msg_namelen = 0;
-
 	copied = data_skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 698814bfa7ad..53c19a35fc6d 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sax->sax25_family = AF_NETROM;
 		skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
 			      AX25_ADDR_LEN);
+		msg->msg_namelen = sizeof(*sax);
 	}
 
-	msg->msg_namelen = sizeof(*sax);
-
 	skb_free_datagram(sk, skb);
 
 	release_sock(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index d308402b67d8..824c6056bf82 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -807,8 +807,6 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	pr_debug("%p %zu\n", sk, len);
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state == LLCP_CLOSED &&
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index cd958b381f96..66bcd2eb5773 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -244,8 +244,6 @@ static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (!skb)
 		return rc;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2e8286b47c28..61bd50adead1 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2660,7 +2660,6 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
-	struct sockaddr_ll *sll;
 	int vnet_hdr_len = 0;
 
 	err = -EINVAL;
@@ -2744,22 +2743,10 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 			goto out_free;
 	}
 
-	/*
-	 *	If the address length field is there to be filled in, we fill
-	 *	it in now.
-	 */
-
-	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	if (sock->type == SOCK_PACKET)
-		msg->msg_namelen = sizeof(struct sockaddr_pkt);
-	else
-		msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
-	/*
-	 *	You lose any data beyond the buffer you gave. If it worries a
-	 *	user program they can ask the device for its MTU anyway.
+	/* You lose any data beyond the buffer you gave. If it worries
+	 * a user program they can ask the device for its MTU
+	 * anyway.
 	 */
-
 	copied = skb->len;
 	if (copied > len) {
 		copied = len;
@@ -2772,9 +2759,20 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
+		/* If the address length field is there to be filled
+		 * in, we fill it in now.
+		 */
+		if (sock->type == SOCK_PACKET) {
+			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+		} else {
+			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+			msg->msg_namelen = sll->sll_halen +
+				offsetof(struct sockaddr_ll, sll_addr);
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
 		       msg->msg_namelen);
+	}
 
 	if (pkt_sk(sk)->auxdata) {
 		struct tpacket_auxdata aux;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9f0f17cf6bf9..de339b24ca14 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 
 	rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
 
-	msg->msg_namelen = 0;
-
 	if (msg_flags & MSG_OOB)
 		goto out;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index e98fcfbe6007..33af77246bfe 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
-	struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
 	size_t copied;
 	unsigned char *asmptr;
 	struct sk_buff *skb;
@@ -1252,8 +1251,11 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (srose != NULL) {
-		memset(srose, 0, msg->msg_namelen);
+	if (msg->msg_name) {
+		struct sockaddr_rose *srose;
+
+		memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+		srose = msg->msg_name;
 		srose->srose_family = AF_ROSE;
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4b48687c3890..898492a8d61b 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 		/* copy the peer address and timestamp */
 		if (!continue_call) {
-			if (msg->msg_name && msg->msg_namelen > 0)
+			if (msg->msg_name) {
+				size_t len =
+					sizeof(call->conn->trans->peer->srx);
 				memcpy(msg->msg_name,
-				       &call->conn->trans->peer->srx,
-				       sizeof(call->conn->trans->peer->srx));
+				       &call->conn->trans->peer->srx, len);
+				msg->msg_namelen = len;
+			}
 			sock_recv_ts_and_drops(msg, &rx->sk, skb);
 		}
 
diff --git a/net/socket.c b/net/socket.c
index c226aceee65b..fc285564e49e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1840,8 +1840,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 	msg.msg_iov = &iov;
 	iov.iov_len = size;
 	iov.iov_base = ubuf;
-	msg.msg_name = (struct sockaddr *)&address;
-	msg.msg_namelen = sizeof(address);
+	/* Save some cycles and don't copy the address if not needed */
+	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg.msg_namelen = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, size, flags);
@@ -2221,16 +2223,14 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 			goto out;
 	}
 
-	/*
-	 *      Save the user-mode address (verify_iovec will change the
-	 *      kernel msghdr to use the kernel address space)
+	/* Save the user-mode address (verify_iovec will change the
+	 * kernel msghdr to use the kernel address space)
 	 */
-
 	uaddr = (__force void __user *)msg_sys->msg_name;
 	uaddr_len = COMPAT_NAMELEN(msg);
-	if (MSG_CMSG_COMPAT & flags) {
+	if (MSG_CMSG_COMPAT & flags)
 		err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
-	} else
+	else
 		err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
 	if (err < 0)
 		goto out_freeiov;
@@ -2239,6 +2239,9 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
 
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg_sys->msg_namelen = 0;
+
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3906527259d1..3b61851bb927 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -980,9 +980,6 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 restart:
 
@@ -1091,9 +1088,6 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c1f403bed683..01625ccc3ae6 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1754,7 +1754,6 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	msg->msg_namelen = 0;
 	if (u->addr) {
 		msg->msg_namelen = u->addr->len;
 		memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1778,8 +1777,6 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	err = mutex_lock_interruptible(&u->readlock);
 	if (err) {
 		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
@@ -1924,8 +1921,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
 
-	msg->msg_namelen = 0;
-
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 545c08b8a1d4..5adfd94c5b85 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1662,8 +1662,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb,
 	vsk = vsock_sk(sk);
 	err = 0;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state != SS_CONNECTED) {
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 9d6986634e0b..687360da62d9 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb,
 	if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	/* Retrieve the head sk_buff from the socket's receive queue. */
 	err = 0;
 	skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 45a3ab5612c1..7622789d3750 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sx25) {
 		sx25->sx25_family = AF_X25;
 		sx25->sx25_addr   = x25->dest_addr;
+		msg->msg_namelen = sizeof(*sx25);
 	}
 
-	msg->msg_namelen = sizeof(struct sockaddr_x25);
-
 	x25_check_rbuf(sk);
 	rc = copied;
 out_free_dgram:
-- 
cgit 


From 3fb69bcadda6263b92dbf8dd74717cba27c77ed9 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@freescale.com>
Date: Wed, 20 Nov 2013 16:38:19 -0600
Subject: net/phy: Add the autocross feature for forced links on VSC82x4

Add auto-MDI/MDI-X capability for forced (autonegotiation disabled)
10/100 Mbps speeds on Vitesse VSC82x4 PHYs. Exported previously static
function genphy_setup_forced() required by the new config_aneg handler
in the Vitesse PHY module.

Signed-off-by: Madalin Bucur <madalin.bucur@freescale.com>
Signed-off-by: Shruti Kanetkar <Shruti@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c |  4 +--
 drivers/net/phy/vitesse.c    | 75 +++++++++++++++++++++++++++++++++++++++++---
 include/linux/phy.h          |  1 +
 3 files changed, 73 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 74630e94fa3b..d6447b3f7409 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -697,7 +697,7 @@ static int genphy_config_advert(struct phy_device *phydev)
  *   to the values in phydev. Assumes that the values are valid.
  *   Please see phy_sanitize_settings().
  */
-static int genphy_setup_forced(struct phy_device *phydev)
+int genphy_setup_forced(struct phy_device *phydev)
 {
 	int err;
 	int ctl = 0;
@@ -716,7 +716,7 @@ static int genphy_setup_forced(struct phy_device *phydev)
 
 	return err;
 }
-
+EXPORT_SYMBOL(genphy_setup_forced);
 
 /**
  * genphy_restart_aneg - Enable and Restart Autonegotiation
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 40406bc2f8af..508e4359338b 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -3,7 +3,7 @@
  *
  * Author: Kriston Carson
  *
- * Copyright (c) 2005, 2009 Freescale Semiconductor, Inc.
+ * Copyright (c) 2005, 2009, 2011 Freescale Semiconductor, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -18,6 +18,11 @@
 #include <linux/ethtool.h>
 #include <linux/phy.h>
 
+/* Vitesse Extended Page Magic Register(s) */
+#define MII_VSC82X4_EXT_PAGE_16E	0x10
+#define MII_VSC82X4_EXT_PAGE_17E	0x11
+#define MII_VSC82X4_EXT_PAGE_18E	0x12
+
 /* Vitesse Extended Control Register 1 */
 #define MII_VSC8244_EXT_CON1           0x17
 #define MII_VSC8244_EXTCON1_INIT       0x0000
@@ -54,6 +59,9 @@
 #define MII_VSC8221_AUXCONSTAT_INIT	0x0004 /* need to set this bit? */
 #define MII_VSC8221_AUXCONSTAT_RESERVED	0x0004
 
+/* Vitesse Extended Page Access Register */
+#define MII_VSC82X4_EXT_PAGE_ACCESS	0x1f
+
 #define PHY_ID_VSC8234			0x000fc620
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8574			0x000704a0
@@ -154,6 +162,63 @@ static int vsc8221_config_init(struct phy_device *phydev)
 	 */
 }
 
+/* vsc82x4_config_autocross_enable - Enable auto MDI/MDI-X for forced links
+ * @phydev: target phy_device struct
+ *
+ * Enable auto MDI/MDI-X when in 10/100 forced link speeds by writing
+ * special values in the VSC8234/VSC8244 extended reserved registers
+ */
+static int vsc82x4_config_autocross_enable(struct phy_device *phydev)
+{
+	int ret;
+
+	if (phydev->autoneg == AUTONEG_ENABLE || phydev->speed > SPEED_100)
+		return 0;
+
+	/* map extended registers set 0x10 - 0x1e */
+	ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x52b5);
+	if (ret >= 0)
+		ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_18E, 0x0012);
+	if (ret >= 0)
+		ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_17E, 0x2803);
+	if (ret >= 0)
+		ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_16E, 0x87fa);
+	/* map standard registers set 0x10 - 0x1e */
+	if (ret >= 0)
+		ret = phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x0000);
+	else
+		phy_write(phydev, MII_VSC82X4_EXT_PAGE_ACCESS, 0x0000);
+
+	return ret;
+}
+
+/* vsc82x4_config_aneg - restart auto-negotiation or write BMCR
+ * @phydev: target phy_device struct
+ *
+ * Description: If auto-negotiation is enabled, we configure the
+ *   advertising, and then restart auto-negotiation.  If it is not
+ *   enabled, then we write the BMCR and also start the auto
+ *   MDI/MDI-X feature
+ */
+static int vsc82x4_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Enable auto MDI/MDI-X when in 10/100 forced link speeds by
+	 * writing special values in the VSC8234 extended reserved registers
+	 */
+	if (phydev->autoneg != AUTONEG_ENABLE && phydev->speed <= SPEED_100) {
+		ret = genphy_setup_forced(phydev);
+
+		if (ret < 0) /* error */
+			return ret;
+
+		return vsc82x4_config_autocross_enable(phydev);
+	}
+
+	return genphy_config_aneg(phydev);
+}
+
 /* Vitesse 82xx */
 static struct phy_driver vsc82xx_driver[] = {
 {
@@ -163,7 +228,7 @@ static struct phy_driver vsc82xx_driver[] = {
 	.features       = PHY_GBIT_FEATURES,
 	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &genphy_config_aneg,
+	.config_aneg    = &vsc82x4_config_aneg,
 	.read_status    = &genphy_read_status,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
@@ -175,7 +240,7 @@ static struct phy_driver vsc82xx_driver[] = {
 	.features	= PHY_GBIT_FEATURES,
 	.flags		= PHY_HAS_INTERRUPT,
 	.config_init	= &vsc824x_config_init,
-	.config_aneg	= &genphy_config_aneg,
+	.config_aneg	= &vsc82x4_config_aneg,
 	.read_status	= &genphy_read_status,
 	.ack_interrupt	= &vsc824x_ack_interrupt,
 	.config_intr	= &vsc82xx_config_intr,
@@ -187,7 +252,7 @@ static struct phy_driver vsc82xx_driver[] = {
 	.features       = PHY_GBIT_FEATURES,
 	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &genphy_config_aneg,
+	.config_aneg    = &vsc82x4_config_aneg,
 	.read_status    = &genphy_read_status,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
@@ -199,7 +264,7 @@ static struct phy_driver vsc82xx_driver[] = {
 	.features       = PHY_GBIT_FEATURES,
 	.flags          = PHY_HAS_INTERRUPT,
 	.config_init    = &vsc824x_config_init,
-	.config_aneg    = &genphy_config_aneg,
+	.config_aneg    = &vsc82x4_config_aneg,
 	.read_status    = &genphy_read_status,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 64ab823f7b74..48a4dc3cb8cf 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -559,6 +559,7 @@ static inline int phy_read_status(struct phy_device *phydev) {
 	return phydev->drv->read_status(phydev);
 }
 
+int genphy_setup_forced(struct phy_device *phydev);
 int genphy_restart_aneg(struct phy_device *phydev);
 int genphy_config_aneg(struct phy_device *phydev);
 int genphy_update_link(struct phy_device *phydev);
-- 
cgit 


From 220815a9665f7deca98a09ecca655044f94cfa44 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 21 Nov 2013 18:17:04 +0100
Subject: genetlink: fix genlmsg_multicast() bug

Unfortunately, I introduced a tremendously stupid bug into
genlmsg_multicast() when doing all those multicast group
changes: it adjusts the group number, but then passes it
to genlmsg_multicast_netns() which does that again.

Somehow, my tests failed to catch this, so add a warning
into genlmsg_multicast_netns() and remove the offending
group ID adjustment.

Also add a warning to the similar code in other functions
so people who misuse them are more loudly warned.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 5 +----
 net/netlink/genetlink.c | 4 ++--
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index ace4abf118d7..771af09e90eb 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -265,7 +265,7 @@ static inline int genlmsg_multicast_netns(struct genl_family *family,
 					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
-	if (group >= family->n_mcgrps)
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return -EINVAL;
 	group = family->mcgrp_offset + group;
 	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
@@ -283,9 +283,6 @@ static inline int genlmsg_multicast(struct genl_family *family,
 				    struct sk_buff *skb, u32 portid,
 				    unsigned int group, gfp_t flags)
 {
-	if (group >= family->n_mcgrps)
-		return -EINVAL;
-	group = family->mcgrp_offset + group;
 	return genlmsg_multicast_netns(family, &init_net, skb,
 				       portid, group, flags);
 }
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 7dbc4f732c75..4518a57aa5fe 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1045,7 +1045,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
 int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
 			    u32 portid, unsigned int group, gfp_t flags)
 {
-	if (group >= family->n_mcgrps)
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return -EINVAL;
 	group = family->mcgrp_offset + group;
 	return genlmsg_mcast(skb, portid, group, flags);
@@ -1062,7 +1062,7 @@ void genl_notify(struct genl_family *family,
 	if (nlh)
 		report = nlmsg_report(nlh);
 
-	if (group >= family->n_mcgrps)
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
 		return;
 	group = family->mcgrp_offset + group;
 	nlmsg_notify(sk, skb, portid, group, report, flags);
-- 
cgit 


From 91398a0992c8aa18eb7749060b75761ece5ddc57 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 21 Nov 2013 18:20:28 +0100
Subject: genetlink: fix genl_set_err() group ID

Fix another really stupid bug - I introduced genl_set_err()
precisely to be able to adjust the group and reject invalid
ones, but then forgot to do so.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 771af09e90eb..1b177ed803b7 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -384,6 +384,9 @@ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags)
 static inline int genl_set_err(struct genl_family *family, struct net *net,
 			       u32 portid, u32 group, int code)
 {
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
 	return netlink_set_err(net->genl_sock, portid, group, code);
 }
 
-- 
cgit 


From 30b0a105d9f7141e4cbf72ae5511832457d89788 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 21 Nov 2013 14:31:58 -0800
Subject: mm: thp: give transparent hugepage code a separate copy_page

Right now, the migration code in migrate_page_copy() uses copy_huge_page()
for hugetlbfs and thp pages:

       if (PageHuge(page) || PageTransHuge(page))
                copy_huge_page(newpage, page);

So, yay for code reuse.  But:

  void copy_huge_page(struct page *dst, struct page *src)
  {
        struct hstate *h = page_hstate(src);

and a non-hugetlbfs page has no page_hstate().  This works 99% of the
time because page_hstate() determines the hstate from the page order
alone.  Since the page order of a THP page matches the default hugetlbfs
page order, it works.

But, if you change the default huge page size on the boot command-line
(say default_hugepagesz=1G), then we might not even *have* a 2MB hstate
so page_hstate() returns null and copy_huge_page() oopses pretty fast
since copy_huge_page() dereferences the hstate:

  void copy_huge_page(struct page *dst, struct page *src)
  {
        struct hstate *h = page_hstate(src);
        if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
  ...

Mel noticed that the migration code is really the only user of these
functions.  This moves all the copy code over to migrate.c and makes
copy_huge_page() work for THP by checking for it explicitly.

I believe the bug was introduced in commit b32967ff101a ("mm: numa: Add
THP migration for the NUMA working set scanning fault case")

[akpm@linux-foundation.org: fix coding-style and comment text, per Naoya Horiguchi]
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Tested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  4 ----
 mm/hugetlb.c            | 34 ----------------------------------
 mm/migrate.c            | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index acd2010328f3..85e0c58bdfdf 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -69,7 +69,6 @@ int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 bool is_hugepage_active(struct page *page);
-void copy_huge_page(struct page *dst, struct page *src);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
@@ -140,9 +139,6 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page)
 #define isolate_huge_page(p, l) false
 #define putback_active_hugepage(p)	do {} while (0)
 #define is_hugepage_active(x)	false
-static inline void copy_huge_page(struct page *dst, struct page *src)
-{
-}
 
 static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7d57af21f49e..2130365d387d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -476,40 +476,6 @@ static int vma_has_reserves(struct vm_area_struct *vma, long chg)
 	return 0;
 }
 
-static void copy_gigantic_page(struct page *dst, struct page *src)
-{
-	int i;
-	struct hstate *h = page_hstate(src);
-	struct page *dst_base = dst;
-	struct page *src_base = src;
-
-	for (i = 0; i < pages_per_huge_page(h); ) {
-		cond_resched();
-		copy_highpage(dst, src);
-
-		i++;
-		dst = mem_map_next(dst, dst_base, i);
-		src = mem_map_next(src, src_base, i);
-	}
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
-	int i;
-	struct hstate *h = page_hstate(src);
-
-	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
-		copy_gigantic_page(dst, src);
-		return;
-	}
-
-	might_sleep();
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		cond_resched();
-		copy_highpage(dst + i, src + i);
-	}
-}
-
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
 	int nid = page_to_nid(page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 316e720a2023..bb940045fe85 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -441,6 +441,54 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	return MIGRATEPAGE_SUCCESS;
 }
 
+/*
+ * Gigantic pages are so large that we do not guarantee that page++ pointer
+ * arithmetic will work across the entire page.  We need something more
+ * specialized.
+ */
+static void __copy_gigantic_page(struct page *dst, struct page *src,
+				int nr_pages)
+{
+	int i;
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+
+	for (i = 0; i < nr_pages; ) {
+		cond_resched();
+		copy_highpage(dst, src);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
+
+static void copy_huge_page(struct page *dst, struct page *src)
+{
+	int i;
+	int nr_pages;
+
+	if (PageHuge(src)) {
+		/* hugetlbfs page */
+		struct hstate *h = page_hstate(src);
+		nr_pages = pages_per_huge_page(h);
+
+		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
+			__copy_gigantic_page(dst, src, nr_pages);
+			return;
+		}
+	} else {
+		/* thp page */
+		BUG_ON(!PageTransHuge(src));
+		nr_pages = hpage_nr_pages(src);
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		cond_resched();
+		copy_highpage(dst + i, src + i);
+	}
+}
+
 /*
  * Copy the page to its new location
  */
-- 
cgit 


From 27c73ae759774e63313c1fbfeb17ba076cea64c5 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Thu, 21 Nov 2013 14:32:02 -0800
Subject: mm: hugetlbfs: fix hugetlbfs optimization

Commit 7cb2ef56e6a8 ("mm: fix aio performance regression for database
caused by THP") can cause dereference of a dangling pointer if
split_huge_page runs during PageHuge() if there are updates to the
tail_page->private field.

Also it is repeating compound_head twice for hugetlbfs and it is running
compound_head+compound_trans_head for THP when a single one is needed in
both cases.

The new code within the PageSlab() check doesn't need to verify that the
THP page size is never bigger than the smallest hugetlbfs page size, to
avoid memory corruption.

A longstanding theoretical race condition was found while fixing the
above (see the change right after the skip_unlock label, that is
relevant for the compound_lock path too).

By re-establishing the _mapcount tail refcounting for all compound
pages, this also fixes the below problem:

  echo 0 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages

  BUG: Bad page state in process bash  pfn:59a01
  page:ffffea000139b038 count:0 mapcount:10 mapping:          (null) index:0x0
  page flags: 0x1c00000000008000(tail)
  Modules linked in:
  CPU: 6 PID: 2018 Comm: bash Not tainted 3.12.0+ #25
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Call Trace:
    dump_stack+0x55/0x76
    bad_page+0xd5/0x130
    free_pages_prepare+0x213/0x280
    __free_pages+0x36/0x80
    update_and_free_page+0xc1/0xd0
    free_pool_huge_page+0xc2/0xe0
    set_max_huge_pages.part.58+0x14c/0x220
    nr_hugepages_store_common.isra.60+0xd0/0xf0
    nr_hugepages_store+0x13/0x20
    kobj_attr_store+0xf/0x20
    sysfs_write_file+0x189/0x1e0
    vfs_write+0xc5/0x1f0
    SyS_write+0x55/0xb0
    system_call_fastpath+0x16/0x1b

Signed-off-by: Khalid Aziz <khalid.aziz@oracle.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Tested-by: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Pravin Shelar <pshelar@nicira.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |   6 ++
 mm/hugetlb.c            |  17 ++++++
 mm/swap.c               | 143 ++++++++++++++++++++++++++++--------------------
 3 files changed, 106 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 85e0c58bdfdf..9649ff0c63f8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -31,6 +31,7 @@ struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
 int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page_head);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -103,6 +104,11 @@ static inline int PageHuge(struct page *page)
 	return 0;
 }
 
+static inline int PageHeadHuge(struct page *page_head)
+{
+	return 0;
+}
+
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2130365d387d..dee6cf4e6d34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -702,6 +702,23 @@ int PageHuge(struct page *page)
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageHead(page_head))
+		return 0;
+
+	dtor = get_compound_page_dtor(page_head);
+
+	return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
 pgoff_t __basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
diff --git a/mm/swap.c b/mm/swap.c
index 7a9f80d451f5..84b26aaabd03 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -82,19 +82,6 @@ static void __put_compound_page(struct page *page)
 
 static void put_compound_page(struct page *page)
 {
-	/*
-	 * hugetlbfs pages cannot be split from under us.  If this is a
-	 * hugetlbfs page, check refcount on head page and release the page if
-	 * the refcount becomes zero.
-	 */
-	if (PageHuge(page)) {
-		page = compound_head(page);
-		if (put_page_testzero(page))
-			__put_compound_page(page);
-
-		return;
-	}
-
 	if (unlikely(PageTail(page))) {
 		/* __split_huge_page_refcount can run under us */
 		struct page *page_head = compound_trans_head(page);
@@ -111,14 +98,31 @@ static void put_compound_page(struct page *page)
 			 * still hot on arches that do not support
 			 * this_cpu_cmpxchg_double().
 			 */
-			if (PageSlab(page_head)) {
-				if (PageTail(page)) {
+			if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+				if (likely(PageTail(page))) {
+					/*
+					 * __split_huge_page_refcount
+					 * cannot race here.
+					 */
+					VM_BUG_ON(!PageHead(page_head));
+					atomic_dec(&page->_mapcount);
 					if (put_page_testzero(page_head))
 						VM_BUG_ON(1);
-
-					atomic_dec(&page->_mapcount);
-					goto skip_lock_tail;
+					if (put_page_testzero(page_head))
+						__put_compound_page(page_head);
+					return;
 				} else
+					/*
+					 * __split_huge_page_refcount
+					 * run before us, "page" was a
+					 * THP tail. The split
+					 * page_head has been freed
+					 * and reallocated as slab or
+					 * hugetlbfs page of smaller
+					 * order (only possible if
+					 * reallocated as slab on
+					 * x86).
+					 */
 					goto skip_lock;
 			}
 			/*
@@ -132,8 +136,27 @@ static void put_compound_page(struct page *page)
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
 skip_lock:
-				if (put_page_testzero(page_head))
-					__put_single_page(page_head);
+				if (put_page_testzero(page_head)) {
+					/*
+					 * The head page may have been
+					 * freed and reallocated as a
+					 * compound page of smaller
+					 * order and then freed again.
+					 * All we know is that it
+					 * cannot have become: a THP
+					 * page, a compound page of
+					 * higher order, a tail page.
+					 * That is because we still
+					 * hold the refcount of the
+					 * split THP tail and
+					 * page_head was the THP head
+					 * before the split.
+					 */
+					if (PageHead(page_head))
+						__put_compound_page(page_head);
+					else
+						__put_single_page(page_head);
+				}
 out_put_single:
 				if (put_page_testzero(page))
 					__put_single_page(page);
@@ -155,7 +178,6 @@ out_put_single:
 			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
 
-skip_lock_tail:
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
@@ -198,51 +220,52 @@ bool __get_page_tail(struct page *page)
 	 * proper PT lock that already serializes against
 	 * split_huge_page().
 	 */
+	unsigned long flags;
 	bool got = false;
-	struct page *page_head;
-
-	/*
-	 * If this is a hugetlbfs page it cannot be split under us.  Simply
-	 * increment refcount for the head page.
-	 */
-	if (PageHuge(page)) {
-		page_head = compound_head(page);
-		atomic_inc(&page_head->_count);
-		got = true;
-	} else {
-		unsigned long flags;
+	struct page *page_head = compound_trans_head(page);
 
-		page_head = compound_trans_head(page);
-		if (likely(page != page_head &&
-					get_page_unless_zero(page_head))) {
-
-			/* Ref to put_compound_page() comment. */
-			if (PageSlab(page_head)) {
-				if (likely(PageTail(page))) {
-					__get_page_tail_foll(page, false);
-					return true;
-				} else {
-					put_page(page_head);
-					return false;
-				}
-			}
-
-			/*
-			 * page_head wasn't a dangling pointer but it
-			 * may not be a head page anymore by the time
-			 * we obtain the lock. That is ok as long as it
-			 * can't be freed from under us.
-			 */
-			flags = compound_lock_irqsave(page_head);
-			/* here __split_huge_page_refcount won't run anymore */
+	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+		/* Ref to put_compound_page() comment. */
+		if (PageSlab(page_head) || PageHeadHuge(page_head)) {
 			if (likely(PageTail(page))) {
+				/*
+				 * This is a hugetlbfs page or a slab
+				 * page. __split_huge_page_refcount
+				 * cannot race here.
+				 */
+				VM_BUG_ON(!PageHead(page_head));
 				__get_page_tail_foll(page, false);
-				got = true;
-			}
-			compound_unlock_irqrestore(page_head, flags);
-			if (unlikely(!got))
+				return true;
+			} else {
+				/*
+				 * __split_huge_page_refcount run
+				 * before us, "page" was a THP
+				 * tail. The split page_head has been
+				 * freed and reallocated as slab or
+				 * hugetlbfs page of smaller order
+				 * (only possible if reallocated as
+				 * slab on x86).
+				 */
 				put_page(page_head);
+				return false;
+			}
+		}
+
+		/*
+		 * page_head wasn't a dangling pointer but it
+		 * may not be a head page anymore by the time
+		 * we obtain the lock. That is ok as long as it
+		 * can't be freed from under us.
+		 */
+		flags = compound_lock_irqsave(page_head);
+		/* here __split_huge_page_refcount won't run anymore */
+		if (likely(PageTail(page))) {
+			__get_page_tail_foll(page, false);
+			got = true;
 		}
+		compound_unlock_irqrestore(page_head, flags);
+		if (unlikely(!got))
+			put_page(page_head);
 	}
 	return got;
 }
-- 
cgit 


From 7aa555bf26763b86332c7a3689701c999834b87a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 21 Nov 2013 14:32:11 -0800
Subject: mm: place page->pmd_huge_pte to right union

I don't know what went wrong, mis-merge or something, but ->pmd_huge_pte
placed in wrong union within struct page.

In original patch[1] it's placed to union with ->lru and ->slab, but in
commit e009bb30c8df ("mm: implement split page table lock for PMD
level") it's in union with ->index and ->freelist.

That union seems also unused for pages with table tables and safe to
re-use, but it's not what I've tested.

Let's move it to original place.  It fixes indentation at least.  :)

[1] https://lkml.org/lkml/2013/10/7/288

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 10f5a7272b80..011eb85d7b0f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -65,9 +65,6 @@ struct page {
 						 * this page is only used to
 						 * free other pages.
 						 */
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
-		pgtable_t pmd_huge_pte; /* protected by page->ptl */
-#endif
 		};
 
 		union {
@@ -135,6 +132,9 @@ struct page {
 
 		struct list_head list;	/* slobs list of pages */
 		struct slab *slab_page; /* slab fields */
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
+		pgtable_t pmd_huge_pte; /* protected by page->ptl */
+#endif
 	};
 
 	/* Remainder is not double word aligned */
-- 
cgit